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

Pull networking updates from David Miller:

 1) Allow setting bluetooth L2CAP modes via socket option, from Luiz
    Augusto von Dentz.

 2) Add GSO partial support to igc, from Sasha Neftin.

 3) Several cleanups and improvements to r8169 from Heiner Kallweit.

 4) Add IF_OPER_TESTING link state and use it when ethtool triggers a
    device self-test. From Andrew Lunn.

 5) Start moving away from custom driver versions, use the globally
    defined kernel version instead, from Leon Romanovsky.

 6) Support GRO vis gro_cells in DSA layer, from Alexander Lobakin.

 7) Allow hard IRQ deferral during NAPI, from Eric Dumazet.

 8) Add sriov and vf support to hinic, from Luo bin.

 9) Support Media Redundancy Protocol (MRP) in the bridging code, from
    Horatiu Vultur.

10) Support netmap in the nft_nat code, from Pablo Neira Ayuso.

11) Allow UDPv6 encapsulation of ESP in the ipsec code, from Sabrina
    Dubroca. Also add ipv6 support for espintcp.

12) Lots of ReST conversions of the networking documentation, from Mauro
    Carvalho Chehab.

13) Support configuration of ethtool rxnfc flows in bcmgenet driver,
    from Doug Berger.

14) Allow to dump cgroup id and filter by it in inet_diag code, from
    Dmitry Yakunin.

15) Add infrastructure to export netlink attribute policies to
    userspace, from Johannes Berg.

16) Several optimizations to sch_fq scheduler, from Eric Dumazet.

17) Fallback to the default qdisc if qdisc init fails because otherwise
    a packet scheduler init failure will make a device inoperative. From
    Jesper Dangaard Brouer.

18) Several RISCV bpf jit optimizations, from Luke Nelson.

19) Correct the return type of the ->ndo_start_xmit() method in several
    drivers, it's netdev_tx_t but many drivers were using
    'int'. From Yunjian Wang.

20) Add an ethtool interface for PHY master/slave config, from Oleksij
    Rempel.

21) Add BPF iterators, from Yonghang Song.

22) Add cable test infrastructure, including ethool interfaces, from
    Andrew Lunn. Marvell PHY driver is the first to support this
    facility.

23) Remove zero-length arrays all over, from Gustavo A. R. Silva.

24) Calculate and maintain an explicit frame size in XDP, from Jesper
    Dangaard Brouer.

25) Add CAP_BPF, from Alexei Starovoitov.

26) Support terse dumps in the packet scheduler, from Vlad Buslov.

27) Support XDP_TX bulking in dpaa2 driver, from Ioana Ciornei.

28) Add devm_register_netdev(), from Bartosz Golaszewski.

29) Minimize qdisc resets, from Cong Wang.

30) Get rid of kernel_getsockopt and kernel_setsockopt in order to
    eliminate set_fs/get_fs calls. From Christoph Hellwig.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2517 commits)
  selftests: net: ip_defrag: ignore EPERM
  net_failover: fixed rollback in net_failover_open()
  Revert "tipc: Fix potential tipc_aead refcnt leak in tipc_crypto_rcv"
  Revert "tipc: Fix potential tipc_node refcnt leak in tipc_rcv"
  vmxnet3: allow rx flow hash ops only when rss is enabled
  hinic: add set_channels ethtool_ops support
  selftests/bpf: Add a default $(CXX) value
  tools/bpf: Don't use $(COMPILE.c)
  bpf, selftests: Use bpf_probe_read_kernel
  s390/bpf: Use bcr 0,%0 as tail call nop filler
  s390/bpf: Maintain 8-byte stack alignment
  selftests/bpf: Fix verifier test
  selftests/bpf: Fix sample_cnt shared between two threads
  bpf, selftests: Adapt cls_redirect to call csum_level helper
  bpf: Add csum_level helper for fixing up csum levels
  bpf: Fix up bpf_skb_adjust_room helper's skb csum setting
  sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf()
  crypto/chtls: IPv6 support for inline TLS
  Crypto/chcr: Fixes a coccinile check error
  Crypto/chcr: Fixes compilations warnings
  ...

115 files changed, 8472 insertions, 1386 deletions

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index c30079c86998..1bb204cee853 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -30,8 +30,6 @@ test_tcpnotify_user
 test_libbpf
 test_tcp_check_syncookie_user
 test_sysctl
-test_hashmap
-test_btf_dump
 test_current_pid_tgid_new_ns
 xdping
 test_cpp
@@ -39,4 +37,5 @@ test_cpp
 /no_alu32
 /bpf_gcc
 /tools
-
+/runqslower
+/bench
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 7729892e0b04..22aaec74ea0a 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -2,6 +2,8 @@
 include ../../../../scripts/Kbuild.include
 include ../../../scripts/Makefile.arch
 
+CXX ?= $(CROSS_COMPILE)g++
+
 CURDIR := $(abspath .)
 TOOLSDIR := $(abspath ../../..)
 LIBDIR := $(TOOLSDIR)/lib
@@ -20,9 +22,10 @@ CLANG		?= clang
 LLC		?= llc
 LLVM_OBJCOPY	?= llvm-objcopy
 BPF_GCC		?= $(shell command -v bpf-gcc;)
-CFLAGS += -g -rdynamic -Wall -O2 $(GENFLAGS) -I$(CURDIR)		\
-	  -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) -I$(TOOLSINCDIR)	\
-	  -I$(APIDIR)							\
+SAN_CFLAGS	?=
+CFLAGS += -g -rdynamic -Wall -O2 $(GENFLAGS) $(SAN_CFLAGS)		\
+	  -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR)		\
+	  -I$(TOOLSINCDIR) -I$(APIDIR)					\
 	  -Dbpf_prog_load=bpf_prog_test_load				\
 	  -Dbpf_load_program=bpf_test_load_program
 LDLIBS += -lcap -lelf -lz -lrt -lpthread
@@ -32,7 +35,7 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
 	test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
 	test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \
 	test_cgroup_storage \
-	test_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \
+	test_netcnt test_tcpnotify_user test_sock_fields test_sysctl \
 	test_progs-no_alu32 \
 	test_current_pid_tgid_new_ns
 
@@ -76,7 +79,7 @@ TEST_PROGS_EXTENDED := with_addr.sh \
 # Compile but not part of 'make run_tests'
 TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
 	flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
-	test_lirc_mode2_user xdping test_cpp runqslower
+	test_lirc_mode2_user xdping test_cpp runqslower bench
 
 TEST_CUSTOM_PROGS = urandom_read
 
@@ -141,7 +144,8 @@ VMLINUX_BTF := $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
 $(OUTPUT)/runqslower: $(BPFOBJ)
 	$(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower	\
 		    OUTPUT=$(SCRATCH_DIR)/ VMLINUX_BTF=$(VMLINUX_BTF)   \
-		    BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR)
+		    BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) &&	\
+		    cp $(SCRATCH_DIR)/runqslower $@
 
 $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(BPFOBJ)
 
@@ -241,7 +245,7 @@ define GCC_BPF_BUILD_RULE
 	$(BPF_GCC) $3 $4 -O2 -c $1 -o $2
 endef
 
-SKEL_BLACKLIST := btf__% test_pinning_invalid.c
+SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c
 
 # Set up extra TRUNNER_XXX "temporary" variables in the environment (relies on
 # $eval()) and pass control to DEFINE_TEST_RUNNER_RULES.
@@ -263,6 +267,7 @@ TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, $$(TRUNNER_BPF_SRCS)
 TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h,	\
 				 $$(filter-out $(SKEL_BLACKLIST),	\
 					       $$(TRUNNER_BPF_SRCS)))
+TEST_GEN_FILES += $$(TRUNNER_BPF_OBJS)
 
 # Evaluate rules now with extra TRUNNER_XXX variables above already defined
 $$(eval $$(call DEFINE_TEST_RUNNER_RULES,$1,$2))
@@ -323,7 +328,7 @@ $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o:			\
 		      $(TRUNNER_BPF_SKELS)				\
 		      $$(BPFOBJ) | $(TRUNNER_OUTPUT)
 	$$(call msg,TEST-OBJ,$(TRUNNER_BINARY),$$@)
-	cd $$(@D) && $$(CC) $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F)
+	cd $$(@D) && $$(CC) -I. $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F)
 
 $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
 		       %.c						\
@@ -352,6 +357,7 @@ endef
 TRUNNER_TESTS_DIR := prog_tests
 TRUNNER_BPF_PROGS_DIR := progs
 TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c	\
+			 network_helpers.c testing_helpers.c		\
 			 flow_dissector_load.h
 TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read				\
 		       $(wildcard progs/btf_dump_test_case_*.c)
@@ -403,6 +409,24 @@ $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
 	$(call msg,CXX,,$@)
 	$(CXX) $(CFLAGS) $^ $(LDLIBS) -o $@
 
+# Benchmark runner
+$(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h
+	$(call msg,CC,,$@)
+	$(CC) $(CFLAGS) -c $(filter %.c,$^) $(LDLIBS) -o $@
+$(OUTPUT)/bench_rename.o: $(OUTPUT)/test_overhead.skel.h
+$(OUTPUT)/bench_trigger.o: $(OUTPUT)/trigger_bench.skel.h
+$(OUTPUT)/bench_ringbufs.o: $(OUTPUT)/ringbuf_bench.skel.h \
+			    $(OUTPUT)/perfbuf_bench.skel.h
+$(OUTPUT)/bench.o: bench.h testing_helpers.h
+$(OUTPUT)/bench: LDLIBS += -lm
+$(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \
+		 $(OUTPUT)/bench_count.o \
+		 $(OUTPUT)/bench_rename.o \
+		 $(OUTPUT)/bench_trigger.o \
+		 $(OUTPUT)/bench_ringbufs.o
+	$(call msg,BINARY,,$@)
+	$(CC) $(LDFLAGS) -o $@ $(filter %.a %.o,$^) $(LDLIBS)
+
 EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR)			\
 	prog_tests/tests.h map_tests/tests.h verifier/tests.h		\
 	feature								\
diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
new file mode 100644
index 000000000000..e885d351595f
--- /dev/null
+++ b/tools/testing/selftests/bpf/README.rst
@@ -0,0 +1,45 @@
+==================
+BPF Selftest Notes
+==================
+General instructions on running selftests can be found in
+`Documentation/bpf/bpf_devel_QA.rst`_.
+
+Additional information about selftest failures are
+documented here.
+
+bpf_iter test failures with clang/llvm 10.0.0
+=============================================
+
+With clang/llvm 10.0.0, the following two bpf_iter tests failed:
+  * ``bpf_iter/ipv6_route``
+  * ``bpf_iter/netlink``
+
+The symptom for ``bpf_iter/ipv6_route`` looks like
+
+.. code-block:: c
+
+  2: (79) r8 = *(u64 *)(r1 +8)
+  ...
+  14: (bf) r2 = r8
+  15: (0f) r2 += r1
+  ; BPF_SEQ_PRINTF(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen);
+  16: (7b) *(u64 *)(r8 +64) = r2
+  only read is supported
+
+The symptom for ``bpf_iter/netlink`` looks like
+
+.. code-block:: c
+
+  ; struct netlink_sock *nlk = ctx->sk;
+  2: (79) r7 = *(u64 *)(r1 +8)
+  ...
+  15: (bf) r2 = r7
+  16: (0f) r2 += r1
+  ; BPF_SEQ_PRINTF(seq, "%pK %-3d ", s, s->sk_protocol);
+  17: (7b) *(u64 *)(r7 +0) = r2
+  only read is supported
+
+This is due to a llvm BPF backend bug. The fix 
+  https://reviews.llvm.org/D78466
+has been pushed to llvm 10.x release branch and will be
+available in 10.0.1. The fix is available in llvm 11.0.0 trunk.
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
new file mode 100644
index 000000000000..944ad4721c83
--- /dev/null
+++ b/tools/testing/selftests/bpf/bench.c
@@ -0,0 +1,465 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#define _GNU_SOURCE
+#include <argp.h>
+#include <linux/compiler.h>
+#include <sys/time.h>
+#include <sched.h>
+#include <fcntl.h>
+#include <pthread.h>
+#include <sys/sysinfo.h>
+#include <sys/resource.h>
+#include <signal.h>
+#include "bench.h"
+#include "testing_helpers.h"
+
+struct env env = {
+	.warmup_sec = 1,
+	.duration_sec = 5,
+	.affinity = false,
+	.consumer_cnt = 1,
+	.producer_cnt = 1,
+};
+
+static int libbpf_print_fn(enum libbpf_print_level level,
+		    const char *format, va_list args)
+{
+	if (level == LIBBPF_DEBUG && !env.verbose)
+		return 0;
+	return vfprintf(stderr, format, args);
+}
+
+static int bump_memlock_rlimit(void)
+{
+	struct rlimit rlim_new = {
+		.rlim_cur	= RLIM_INFINITY,
+		.rlim_max	= RLIM_INFINITY,
+	};
+
+	return setrlimit(RLIMIT_MEMLOCK, &rlim_new);
+}
+
+void setup_libbpf()
+{
+	int err;
+
+	libbpf_set_print(libbpf_print_fn);
+
+	err = bump_memlock_rlimit();
+	if (err)
+		fprintf(stderr, "failed to increase RLIMIT_MEMLOCK: %d", err);
+}
+
+void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns)
+{
+	double hits_per_sec, drops_per_sec;
+	double hits_per_prod;
+
+	hits_per_sec = res->hits / 1000000.0 / (delta_ns / 1000000000.0);
+	hits_per_prod = hits_per_sec / env.producer_cnt;
+	drops_per_sec = res->drops / 1000000.0 / (delta_ns / 1000000000.0);
+
+	printf("Iter %3d (%7.3lfus): ",
+	       iter, (delta_ns - 1000000000) / 1000.0);
+
+	printf("hits %8.3lfM/s (%7.3lfM/prod), drops %8.3lfM/s\n",
+	       hits_per_sec, hits_per_prod, drops_per_sec);
+}
+
+void hits_drops_report_final(struct bench_res res[], int res_cnt)
+{
+	int i;
+	double hits_mean = 0.0, drops_mean = 0.0;
+	double hits_stddev = 0.0, drops_stddev = 0.0;
+
+	for (i = 0; i < res_cnt; i++) {
+		hits_mean += res[i].hits / 1000000.0 / (0.0 + res_cnt);
+		drops_mean += res[i].drops / 1000000.0 / (0.0 + res_cnt);
+	}
+
+	if (res_cnt > 1)  {
+		for (i = 0; i < res_cnt; i++) {
+			hits_stddev += (hits_mean - res[i].hits / 1000000.0) *
+				       (hits_mean - res[i].hits / 1000000.0) /
+				       (res_cnt - 1.0);
+			drops_stddev += (drops_mean - res[i].drops / 1000000.0) *
+					(drops_mean - res[i].drops / 1000000.0) /
+					(res_cnt - 1.0);
+		}
+		hits_stddev = sqrt(hits_stddev);
+		drops_stddev = sqrt(drops_stddev);
+	}
+	printf("Summary: hits %8.3lf \u00B1 %5.3lfM/s (%7.3lfM/prod), ",
+	       hits_mean, hits_stddev, hits_mean / env.producer_cnt);
+	printf("drops %8.3lf \u00B1 %5.3lfM/s\n",
+	       drops_mean, drops_stddev);
+}
+
+const char *argp_program_version = "benchmark";
+const char *argp_program_bug_address = "<bpf@vger.kernel.org>";
+const char argp_program_doc[] =
+"benchmark    Generic benchmarking framework.\n"
+"\n"
+"This tool runs benchmarks.\n"
+"\n"
+"USAGE: benchmark <bench-name>\n"
+"\n"
+"EXAMPLES:\n"
+"    # run 'count-local' benchmark with 1 producer and 1 consumer\n"
+"    benchmark count-local\n"
+"    # run 'count-local' with 16 producer and 8 consumer thread, pinned to CPUs\n"
+"    benchmark -p16 -c8 -a count-local\n";
+
+enum {
+	ARG_PROD_AFFINITY_SET = 1000,
+	ARG_CONS_AFFINITY_SET = 1001,
+};
+
+static const struct argp_option opts[] = {
+	{ "list", 'l', NULL, 0, "List available benchmarks"},
+	{ "duration", 'd', "SEC", 0, "Duration of benchmark, seconds"},
+	{ "warmup", 'w', "SEC", 0, "Warm-up period, seconds"},
+	{ "producers", 'p', "NUM", 0, "Number of producer threads"},
+	{ "consumers", 'c', "NUM", 0, "Number of consumer threads"},
+	{ "verbose", 'v', NULL, 0, "Verbose debug output"},
+	{ "affinity", 'a', NULL, 0, "Set consumer/producer thread affinity"},
+	{ "prod-affinity", ARG_PROD_AFFINITY_SET, "CPUSET", 0,
+	  "Set of CPUs for producer threads; implies --affinity"},
+	{ "cons-affinity", ARG_CONS_AFFINITY_SET, "CPUSET", 0,
+	  "Set of CPUs for consumer threads; implies --affinity"},
+	{},
+};
+
+extern struct argp bench_ringbufs_argp;
+
+static const struct argp_child bench_parsers[] = {
+	{ &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 },
+	{},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+	static int pos_args;
+
+	switch (key) {
+	case 'v':
+		env.verbose = true;
+		break;
+	case 'l':
+		env.list = true;
+		break;
+	case 'd':
+		env.duration_sec = strtol(arg, NULL, 10);
+		if (env.duration_sec <= 0) {
+			fprintf(stderr, "Invalid duration: %s\n", arg);
+			argp_usage(state);
+		}
+		break;
+	case 'w':
+		env.warmup_sec = strtol(arg, NULL, 10);
+		if (env.warmup_sec <= 0) {
+			fprintf(stderr, "Invalid warm-up duration: %s\n", arg);
+			argp_usage(state);
+		}
+		break;
+	case 'p':
+		env.producer_cnt = strtol(arg, NULL, 10);
+		if (env.producer_cnt <= 0) {
+			fprintf(stderr, "Invalid producer count: %s\n", arg);
+			argp_usage(state);
+		}
+		break;
+	case 'c':
+		env.consumer_cnt = strtol(arg, NULL, 10);
+		if (env.consumer_cnt <= 0) {
+			fprintf(stderr, "Invalid consumer count: %s\n", arg);
+			argp_usage(state);
+		}
+		break;
+	case 'a':
+		env.affinity = true;
+		break;
+	case ARG_PROD_AFFINITY_SET:
+		env.affinity = true;
+		if (parse_num_list(arg, &env.prod_cpus.cpus,
+				   &env.prod_cpus.cpus_len)) {
+			fprintf(stderr, "Invalid format of CPU set for producers.");
+			argp_usage(state);
+		}
+		break;
+	case ARG_CONS_AFFINITY_SET:
+		env.affinity = true;
+		if (parse_num_list(arg, &env.cons_cpus.cpus,
+				   &env.cons_cpus.cpus_len)) {
+			fprintf(stderr, "Invalid format of CPU set for consumers.");
+			argp_usage(state);
+		}
+		break;
+	case ARGP_KEY_ARG:
+		if (pos_args++) {
+			fprintf(stderr,
+				"Unrecognized positional argument: %s\n", arg);
+			argp_usage(state);
+		}
+		env.bench_name = strdup(arg);
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+	return 0;
+}
+
+static void parse_cmdline_args(int argc, char **argv)
+{
+	static const struct argp argp = {
+		.options = opts,
+		.parser = parse_arg,
+		.doc = argp_program_doc,
+		.children = bench_parsers,
+	};
+	if (argp_parse(&argp, argc, argv, 0, NULL, NULL))
+		exit(1);
+	if (!env.list && !env.bench_name) {
+		argp_help(&argp, stderr, ARGP_HELP_DOC, "bench");
+		exit(1);
+	}
+}
+
+static void collect_measurements(long delta_ns);
+
+static __u64 last_time_ns;
+static void sigalarm_handler(int signo)
+{
+	long new_time_ns = get_time_ns();
+	long delta_ns = new_time_ns - last_time_ns;
+
+	collect_measurements(delta_ns);
+
+	last_time_ns = new_time_ns;
+}
+
+/* set up periodic 1-second timer */
+static void setup_timer()
+{
+	static struct sigaction sigalarm_action = {
+		.sa_handler = sigalarm_handler,
+	};
+	struct itimerval timer_settings = {};
+	int err;
+
+	last_time_ns = get_time_ns();
+	err = sigaction(SIGALRM, &sigalarm_action, NULL);
+	if (err < 0) {
+		fprintf(stderr, "failed to install SIGALRM handler: %d\n", -errno);
+		exit(1);
+	}
+	timer_settings.it_interval.tv_sec = 1;
+	timer_settings.it_value.tv_sec = 1;
+	err = setitimer(ITIMER_REAL, &timer_settings, NULL);
+	if (err < 0) {
+		fprintf(stderr, "failed to arm interval timer: %d\n", -errno);
+		exit(1);
+	}
+}
+
+static void set_thread_affinity(pthread_t thread, int cpu)
+{
+	cpu_set_t cpuset;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(cpu, &cpuset);
+	if (pthread_setaffinity_np(thread, sizeof(cpuset), &cpuset)) {
+		fprintf(stderr, "setting affinity to CPU #%d failed: %d\n",
+			cpu, errno);
+		exit(1);
+	}
+}
+
+static int next_cpu(struct cpu_set *cpu_set)
+{
+	if (cpu_set->cpus) {
+		int i;
+
+		/* find next available CPU */
+		for (i = cpu_set->next_cpu; i < cpu_set->cpus_len; i++) {
+			if (cpu_set->cpus[i]) {
+				cpu_set->next_cpu = i + 1;
+				return i;
+			}
+		}
+		fprintf(stderr, "Not enough CPUs specified, need CPU #%d or higher.\n", i);
+		exit(1);
+	}
+
+	return cpu_set->next_cpu++;
+}
+
+static struct bench_state {
+	int res_cnt;
+	struct bench_res *results;
+	pthread_t *consumers;
+	pthread_t *producers;
+} state;
+
+const struct bench *bench = NULL;
+
+extern const struct bench bench_count_global;
+extern const struct bench bench_count_local;
+extern const struct bench bench_rename_base;
+extern const struct bench bench_rename_kprobe;
+extern const struct bench bench_rename_kretprobe;
+extern const struct bench bench_rename_rawtp;
+extern const struct bench bench_rename_fentry;
+extern const struct bench bench_rename_fexit;
+extern const struct bench bench_rename_fmodret;
+extern const struct bench bench_trig_base;
+extern const struct bench bench_trig_tp;
+extern const struct bench bench_trig_rawtp;
+extern const struct bench bench_trig_kprobe;
+extern const struct bench bench_trig_fentry;
+extern const struct bench bench_trig_fmodret;
+extern const struct bench bench_rb_libbpf;
+extern const struct bench bench_rb_custom;
+extern const struct bench bench_pb_libbpf;
+extern const struct bench bench_pb_custom;
+
+static const struct bench *benchs[] = {
+	&bench_count_global,
+	&bench_count_local,
+	&bench_rename_base,
+	&bench_rename_kprobe,
+	&bench_rename_kretprobe,
+	&bench_rename_rawtp,
+	&bench_rename_fentry,
+	&bench_rename_fexit,
+	&bench_rename_fmodret,
+	&bench_trig_base,
+	&bench_trig_tp,
+	&bench_trig_rawtp,
+	&bench_trig_kprobe,
+	&bench_trig_fentry,
+	&bench_trig_fmodret,
+	&bench_rb_libbpf,
+	&bench_rb_custom,
+	&bench_pb_libbpf,
+	&bench_pb_custom,
+};
+
+static void setup_benchmark()
+{
+	int i, err;
+
+	if (!env.bench_name) {
+		fprintf(stderr, "benchmark name is not specified\n");
+		exit(1);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(benchs); i++) {
+		if (strcmp(benchs[i]->name, env.bench_name) == 0) {
+			bench = benchs[i];
+			break;
+		}
+	}
+	if (!bench) {
+		fprintf(stderr, "benchmark '%s' not found\n", env.bench_name);
+		exit(1);
+	}
+
+	printf("Setting up benchmark '%s'...\n", bench->name);
+
+	state.producers = calloc(env.producer_cnt, sizeof(*state.producers));
+	state.consumers = calloc(env.consumer_cnt, sizeof(*state.consumers));
+	state.results = calloc(env.duration_sec + env.warmup_sec + 2,
+			       sizeof(*state.results));
+	if (!state.producers || !state.consumers || !state.results)
+		exit(1);
+
+	if (bench->validate)
+		bench->validate();
+	if (bench->setup)
+		bench->setup();
+
+	for (i = 0; i < env.consumer_cnt; i++) {
+		err = pthread_create(&state.consumers[i], NULL,
+				     bench->consumer_thread, (void *)(long)i);
+		if (err) {
+			fprintf(stderr, "failed to create consumer thread #%d: %d\n",
+				i, -errno);
+			exit(1);
+		}
+		if (env.affinity)
+			set_thread_affinity(state.consumers[i],
+					    next_cpu(&env.cons_cpus));
+	}
+
+	/* unless explicit producer CPU list is specified, continue after
+	 * last consumer CPU
+	 */
+	if (!env.prod_cpus.cpus)
+		env.prod_cpus.next_cpu = env.cons_cpus.next_cpu;
+
+	for (i = 0; i < env.producer_cnt; i++) {
+		err = pthread_create(&state.producers[i], NULL,
+				     bench->producer_thread, (void *)(long)i);
+		if (err) {
+			fprintf(stderr, "failed to create producer thread #%d: %d\n",
+				i, -errno);
+			exit(1);
+		}
+		if (env.affinity)
+			set_thread_affinity(state.producers[i],
+					    next_cpu(&env.prod_cpus));
+	}
+
+	printf("Benchmark '%s' started.\n", bench->name);
+}
+
+static pthread_mutex_t bench_done_mtx = PTHREAD_MUTEX_INITIALIZER;
+static pthread_cond_t bench_done = PTHREAD_COND_INITIALIZER;
+
+static void collect_measurements(long delta_ns) {
+	int iter = state.res_cnt++;
+	struct bench_res *res = &state.results[iter];
+
+	bench->measure(res);
+
+	if (bench->report_progress)
+		bench->report_progress(iter, res, delta_ns);
+
+	if (iter == env.duration_sec + env.warmup_sec) {
+		pthread_mutex_lock(&bench_done_mtx);
+		pthread_cond_signal(&bench_done);
+		pthread_mutex_unlock(&bench_done_mtx);
+	}
+}
+
+int main(int argc, char **argv)
+{
+	parse_cmdline_args(argc, argv);
+
+	if (env.list) {
+		int i;
+
+		printf("Available benchmarks:\n");
+		for (i = 0; i < ARRAY_SIZE(benchs); i++) {
+			printf("- %s\n", benchs[i]->name);
+		}
+		return 0;
+	}
+
+	setup_benchmark();
+
+	setup_timer();
+
+	pthread_mutex_lock(&bench_done_mtx);
+	pthread_cond_wait(&bench_done, &bench_done_mtx);
+	pthread_mutex_unlock(&bench_done_mtx);
+
+	if (bench->report_final)
+		/* skip first sample */
+		bench->report_final(state.results + env.warmup_sec,
+				    state.res_cnt - env.warmup_sec);
+
+	return 0;
+}
+
diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h
new file mode 100644
index 000000000000..c1f48a473b02
--- /dev/null
+++ b/tools/testing/selftests/bpf/bench.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#pragma once
+#include <stdlib.h>
+#include <stdbool.h>
+#include <linux/err.h>
+#include <errno.h>
+#include <unistd.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <math.h>
+#include <time.h>
+#include <sys/syscall.h>
+
+struct cpu_set {
+	bool *cpus;
+	int cpus_len;
+	int next_cpu;
+};
+
+struct env {
+	char *bench_name;
+	int duration_sec;
+	int warmup_sec;
+	bool verbose;
+	bool list;
+	bool affinity;
+	int consumer_cnt;
+	int producer_cnt;
+	struct cpu_set prod_cpus;
+	struct cpu_set cons_cpus;
+};
+
+struct bench_res {
+	long hits;
+	long drops;
+};
+
+struct bench {
+	const char *name;
+	void (*validate)();
+	void (*setup)();
+	void *(*producer_thread)(void *ctx);
+	void *(*consumer_thread)(void *ctx);
+	void (*measure)(struct bench_res* res);
+	void (*report_progress)(int iter, struct bench_res* res, long delta_ns);
+	void (*report_final)(struct bench_res res[], int res_cnt);
+};
+
+struct counter {
+	long value;
+} __attribute__((aligned(128)));
+
+extern struct env env;
+extern const struct bench *bench;
+
+void setup_libbpf();
+void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns);
+void hits_drops_report_final(struct bench_res res[], int res_cnt);
+
+static inline __u64 get_time_ns() {
+	struct timespec t;
+
+	clock_gettime(CLOCK_MONOTONIC, &t);
+
+	return (u64)t.tv_sec * 1000000000 + t.tv_nsec;
+}
+
+static inline void atomic_inc(long *value)
+{
+	(void)__atomic_add_fetch(value, 1, __ATOMIC_RELAXED);
+}
+
+static inline void atomic_add(long *value, long n)
+{
+	(void)__atomic_add_fetch(value, n, __ATOMIC_RELAXED);
+}
+
+static inline long atomic_swap(long *value, long n)
+{
+	return __atomic_exchange_n(value, n, __ATOMIC_RELAXED);
+}
diff --git a/tools/testing/selftests/bpf/benchs/bench_count.c b/tools/testing/selftests/bpf/benchs/bench_count.c
new file mode 100644
index 000000000000..befba7a82643
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_count.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include "bench.h"
+
+/* COUNT-GLOBAL benchmark */
+
+static struct count_global_ctx {
+	struct counter hits;
+} count_global_ctx;
+
+static void *count_global_producer(void *input)
+{
+	struct count_global_ctx *ctx = &count_global_ctx;
+
+	while (true) {
+		atomic_inc(&ctx->hits.value);
+	}
+	return NULL;
+}
+
+static void *count_global_consumer(void *input)
+{
+	return NULL;
+}
+
+static void count_global_measure(struct bench_res *res)
+{
+	struct count_global_ctx *ctx = &count_global_ctx;
+
+	res->hits = atomic_swap(&ctx->hits.value, 0);
+}
+
+/* COUNT-local benchmark */
+
+static struct count_local_ctx {
+	struct counter *hits;
+} count_local_ctx;
+
+static void count_local_setup()
+{
+	struct count_local_ctx *ctx = &count_local_ctx;
+
+	ctx->hits = calloc(env.consumer_cnt, sizeof(*ctx->hits));
+	if (!ctx->hits)
+		exit(1);
+}
+
+static void *count_local_producer(void *input)
+{
+	struct count_local_ctx *ctx = &count_local_ctx;
+	int idx = (long)input;
+
+	while (true) {
+		atomic_inc(&ctx->hits[idx].value);
+	}
+	return NULL;
+}
+
+static void *count_local_consumer(void *input)
+{
+	return NULL;
+}
+
+static void count_local_measure(struct bench_res *res)
+{
+	struct count_local_ctx *ctx = &count_local_ctx;
+	int i;
+
+	for (i = 0; i < env.producer_cnt; i++) {
+		res->hits += atomic_swap(&ctx->hits[i].value, 0);
+	}
+}
+
+const struct bench bench_count_global = {
+	.name = "count-global",
+	.producer_thread = count_global_producer,
+	.consumer_thread = count_global_consumer,
+	.measure = count_global_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_count_local = {
+	.name = "count-local",
+	.setup = count_local_setup,
+	.producer_thread = count_local_producer,
+	.consumer_thread = count_local_consumer,
+	.measure = count_local_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/bench_rename.c b/tools/testing/selftests/bpf/benchs/bench_rename.c
new file mode 100644
index 000000000000..e74cff40f4fe
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_rename.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <fcntl.h>
+#include "bench.h"
+#include "test_overhead.skel.h"
+
+/* BPF triggering benchmarks */
+static struct ctx {
+	struct test_overhead *skel;
+	struct counter hits;
+	int fd;
+} ctx;
+
+static void validate()
+{
+	if (env.producer_cnt != 1) {
+		fprintf(stderr, "benchmark doesn't support multi-producer!\n");
+		exit(1);
+	}
+	if (env.consumer_cnt != 1) {
+		fprintf(stderr, "benchmark doesn't support multi-consumer!\n");
+		exit(1);
+	}
+}
+
+static void *producer(void *input)
+{
+	char buf[] = "test_overhead";
+	int err;
+
+	while (true) {
+		err = write(ctx.fd, buf, sizeof(buf));
+		if (err < 0) {
+			fprintf(stderr, "write failed\n");
+			exit(1);
+		}
+		atomic_inc(&ctx.hits.value);
+	}
+}
+
+static void measure(struct bench_res *res)
+{
+	res->hits = atomic_swap(&ctx.hits.value, 0);
+}
+
+static void setup_ctx()
+{
+	setup_libbpf();
+
+	ctx.skel = test_overhead__open_and_load();
+	if (!ctx.skel) {
+		fprintf(stderr, "failed to open skeleton\n");
+		exit(1);
+	}
+
+	ctx.fd = open("/proc/self/comm", O_WRONLY|O_TRUNC);
+	if (ctx.fd < 0) {
+		fprintf(stderr, "failed to open /proc/self/comm: %d\n", -errno);
+		exit(1);
+	}
+}
+
+static void attach_bpf(struct bpf_program *prog)
+{
+	struct bpf_link *link;
+
+	link = bpf_program__attach(prog);
+	if (IS_ERR(link)) {
+		fprintf(stderr, "failed to attach program!\n");
+		exit(1);
+	}
+}
+
+static void setup_base()
+{
+	setup_ctx();
+}
+
+static void setup_kprobe()
+{
+	setup_ctx();
+	attach_bpf(ctx.skel->progs.prog1);
+}
+
+static void setup_kretprobe()
+{
+	setup_ctx();
+	attach_bpf(ctx.skel->progs.prog2);
+}
+
+static void setup_rawtp()
+{
+	setup_ctx();
+	attach_bpf(ctx.skel->progs.prog3);
+}
+
+static void setup_fentry()
+{
+	setup_ctx();
+	attach_bpf(ctx.skel->progs.prog4);
+}
+
+static void setup_fexit()
+{
+	setup_ctx();
+	attach_bpf(ctx.skel->progs.prog5);
+}
+
+static void setup_fmodret()
+{
+	setup_ctx();
+	attach_bpf(ctx.skel->progs.prog6);
+}
+
+static void *consumer(void *input)
+{
+	return NULL;
+}
+
+const struct bench bench_rename_base = {
+	.name = "rename-base",
+	.validate = validate,
+	.setup = setup_base,
+	.producer_thread = producer,
+	.consumer_thread = consumer,
+	.measure = measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_rename_kprobe = {
+	.name = "rename-kprobe",
+	.validate = validate,
+	.setup = setup_kprobe,
+	.producer_thread = producer,
+	.consumer_thread = consumer,
+	.measure = measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_rename_kretprobe = {
+	.name = "rename-kretprobe",
+	.validate = validate,
+	.setup = setup_kretprobe,
+	.producer_thread = producer,
+	.consumer_thread = consumer,
+	.measure = measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_rename_rawtp = {
+	.name = "rename-rawtp",
+	.validate = validate,
+	.setup = setup_rawtp,
+	.producer_thread = producer,
+	.consumer_thread = consumer,
+	.measure = measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_rename_fentry = {
+	.name = "rename-fentry",
+	.validate = validate,
+	.setup = setup_fentry,
+	.producer_thread = producer,
+	.consumer_thread = consumer,
+	.measure = measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_rename_fexit = {
+	.name = "rename-fexit",
+	.validate = validate,
+	.setup = setup_fexit,
+	.producer_thread = producer,
+	.consumer_thread = consumer,
+	.measure = measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_rename_fmodret = {
+	.name = "rename-fmodret",
+	.validate = validate,
+	.setup = setup_fmodret,
+	.producer_thread = producer,
+	.consumer_thread = consumer,
+	.measure = measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
new file mode 100644
index 000000000000..da87c7f31891
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
@@ -0,0 +1,566 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <asm/barrier.h>
+#include <linux/perf_event.h>
+#include <linux/ring_buffer.h>
+#include <sys/epoll.h>
+#include <sys/mman.h>
+#include <argp.h>
+#include <stdlib.h>
+#include "bench.h"
+#include "ringbuf_bench.skel.h"
+#include "perfbuf_bench.skel.h"
+
+static struct {
+	bool back2back;
+	int batch_cnt;
+	bool sampled;
+	int sample_rate;
+	int ringbuf_sz; /* per-ringbuf, in bytes */
+	bool ringbuf_use_output; /* use slower output API */
+	int perfbuf_sz; /* per-CPU size, in pages */
+} args = {
+	.back2back = false,
+	.batch_cnt = 500,
+	.sampled = false,
+	.sample_rate = 500,
+	.ringbuf_sz = 512 * 1024,
+	.ringbuf_use_output = false,
+	.perfbuf_sz = 128,
+};
+
+enum {
+	ARG_RB_BACK2BACK = 2000,
+	ARG_RB_USE_OUTPUT = 2001,
+	ARG_RB_BATCH_CNT = 2002,
+	ARG_RB_SAMPLED = 2003,
+	ARG_RB_SAMPLE_RATE = 2004,
+};
+
+static const struct argp_option opts[] = {
+	{ "rb-b2b", ARG_RB_BACK2BACK, NULL, 0, "Back-to-back mode"},
+	{ "rb-use-output", ARG_RB_USE_OUTPUT, NULL, 0, "Use bpf_ringbuf_output() instead of bpf_ringbuf_reserve()"},
+	{ "rb-batch-cnt", ARG_RB_BATCH_CNT, "CNT", 0, "Set BPF-side record batch count"},
+	{ "rb-sampled", ARG_RB_SAMPLED, NULL, 0, "Notification sampling"},
+	{ "rb-sample-rate", ARG_RB_SAMPLE_RATE, "RATE", 0, "Notification sample rate"},
+	{},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+	switch (key) {
+	case ARG_RB_BACK2BACK:
+		args.back2back = true;
+		break;
+	case ARG_RB_USE_OUTPUT:
+		args.ringbuf_use_output = true;
+		break;
+	case ARG_RB_BATCH_CNT:
+		args.batch_cnt = strtol(arg, NULL, 10);
+		if (args.batch_cnt < 0) {
+			fprintf(stderr, "Invalid batch count.");
+			argp_usage(state);
+		}
+		break;
+	case ARG_RB_SAMPLED:
+		args.sampled = true;
+		break;
+	case ARG_RB_SAMPLE_RATE:
+		args.sample_rate = strtol(arg, NULL, 10);
+		if (args.sample_rate < 0) {
+			fprintf(stderr, "Invalid perfbuf sample rate.");
+			argp_usage(state);
+		}
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+	return 0;
+}
+
+/* exported into benchmark runner */
+const struct argp bench_ringbufs_argp = {
+	.options = opts,
+	.parser = parse_arg,
+};
+
+/* RINGBUF-LIBBPF benchmark */
+
+static struct counter buf_hits;
+
+static inline void bufs_trigger_batch()
+{
+	(void)syscall(__NR_getpgid);
+}
+
+static void bufs_validate()
+{
+	if (env.consumer_cnt != 1) {
+		fprintf(stderr, "rb-libbpf benchmark doesn't support multi-consumer!\n");
+		exit(1);
+	}
+
+	if (args.back2back && env.producer_cnt > 1) {
+		fprintf(stderr, "back-to-back mode makes sense only for single-producer case!\n");
+		exit(1);
+	}
+}
+
+static void *bufs_sample_producer(void *input)
+{
+	if (args.back2back) {
+		/* initial batch to get everything started */
+		bufs_trigger_batch();
+		return NULL;
+	}
+
+	while (true)
+		bufs_trigger_batch();
+	return NULL;
+}
+
+static struct ringbuf_libbpf_ctx {
+	struct ringbuf_bench *skel;
+	struct ring_buffer *ringbuf;
+} ringbuf_libbpf_ctx;
+
+static void ringbuf_libbpf_measure(struct bench_res *res)
+{
+	struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx;
+
+	res->hits = atomic_swap(&buf_hits.value, 0);
+	res->drops = atomic_swap(&ctx->skel->bss->dropped, 0);
+}
+
+static struct ringbuf_bench *ringbuf_setup_skeleton()
+{
+	struct ringbuf_bench *skel;
+
+	setup_libbpf();
+
+	skel = ringbuf_bench__open();
+	if (!skel) {
+		fprintf(stderr, "failed to open skeleton\n");
+		exit(1);
+	}
+
+	skel->rodata->batch_cnt = args.batch_cnt;
+	skel->rodata->use_output = args.ringbuf_use_output ? 1 : 0;
+
+	if (args.sampled)
+		/* record data + header take 16 bytes */
+		skel->rodata->wakeup_data_size = args.sample_rate * 16;
+
+	bpf_map__resize(skel->maps.ringbuf, args.ringbuf_sz);
+
+	if (ringbuf_bench__load(skel)) {
+		fprintf(stderr, "failed to load skeleton\n");
+		exit(1);
+	}
+
+	return skel;
+}
+
+static int buf_process_sample(void *ctx, void *data, size_t len)
+{
+	atomic_inc(&buf_hits.value);
+	return 0;
+}
+
+static void ringbuf_libbpf_setup()
+{
+	struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx;
+	struct bpf_link *link;
+
+	ctx->skel = ringbuf_setup_skeleton();
+	ctx->ringbuf = ring_buffer__new(bpf_map__fd(ctx->skel->maps.ringbuf),
+					buf_process_sample, NULL, NULL);
+	if (!ctx->ringbuf) {
+		fprintf(stderr, "failed to create ringbuf\n");
+		exit(1);
+	}
+
+	link = bpf_program__attach(ctx->skel->progs.bench_ringbuf);
+	if (IS_ERR(link)) {
+		fprintf(stderr, "failed to attach program!\n");
+		exit(1);
+	}
+}
+
+static void *ringbuf_libbpf_consumer(void *input)
+{
+	struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx;
+
+	while (ring_buffer__poll(ctx->ringbuf, -1) >= 0) {
+		if (args.back2back)
+			bufs_trigger_batch();
+	}
+	fprintf(stderr, "ringbuf polling failed!\n");
+	return NULL;
+}
+
+/* RINGBUF-CUSTOM benchmark */
+struct ringbuf_custom {
+	__u64 *consumer_pos;
+	__u64 *producer_pos;
+	__u64 mask;
+	void *data;
+	int map_fd;
+};
+
+static struct ringbuf_custom_ctx {
+	struct ringbuf_bench *skel;
+	struct ringbuf_custom ringbuf;
+	int epoll_fd;
+	struct epoll_event event;
+} ringbuf_custom_ctx;
+
+static void ringbuf_custom_measure(struct bench_res *res)
+{
+	struct ringbuf_custom_ctx *ctx = &ringbuf_custom_ctx;
+
+	res->hits = atomic_swap(&buf_hits.value, 0);
+	res->drops = atomic_swap(&ctx->skel->bss->dropped, 0);
+}
+
+static void ringbuf_custom_setup()
+{
+	struct ringbuf_custom_ctx *ctx = &ringbuf_custom_ctx;
+	const size_t page_size = getpagesize();
+	struct bpf_link *link;
+	struct ringbuf_custom *r;
+	void *tmp;
+	int err;
+
+	ctx->skel = ringbuf_setup_skeleton();
+
+	ctx->epoll_fd = epoll_create1(EPOLL_CLOEXEC);
+	if (ctx->epoll_fd < 0) {
+		fprintf(stderr, "failed to create epoll fd: %d\n", -errno);
+		exit(1);
+	}
+
+	r = &ctx->ringbuf;
+	r->map_fd = bpf_map__fd(ctx->skel->maps.ringbuf);
+	r->mask = args.ringbuf_sz - 1;
+
+	/* Map writable consumer page */
+	tmp = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED,
+		   r->map_fd, 0);
+	if (tmp == MAP_FAILED) {
+		fprintf(stderr, "failed to mmap consumer page: %d\n", -errno);
+		exit(1);
+	}
+	r->consumer_pos = tmp;
+
+	/* Map read-only producer page and data pages. */
+	tmp = mmap(NULL, page_size + 2 * args.ringbuf_sz, PROT_READ, MAP_SHARED,
+		   r->map_fd, page_size);
+	if (tmp == MAP_FAILED) {
+		fprintf(stderr, "failed to mmap data pages: %d\n", -errno);
+		exit(1);
+	}
+	r->producer_pos = tmp;
+	r->data = tmp + page_size;
+
+	ctx->event.events = EPOLLIN;
+	err = epoll_ctl(ctx->epoll_fd, EPOLL_CTL_ADD, r->map_fd, &ctx->event);
+	if (err < 0) {
+		fprintf(stderr, "failed to epoll add ringbuf: %d\n", -errno);
+		exit(1);
+	}
+
+	link = bpf_program__attach(ctx->skel->progs.bench_ringbuf);
+	if (IS_ERR(link)) {
+		fprintf(stderr, "failed to attach program\n");
+		exit(1);
+	}
+}
+
+#define RINGBUF_BUSY_BIT (1 << 31)
+#define RINGBUF_DISCARD_BIT (1 << 30)
+#define RINGBUF_META_LEN 8
+
+static inline int roundup_len(__u32 len)
+{
+	/* clear out top 2 bits */
+	len <<= 2;
+	len >>= 2;
+	/* add length prefix */
+	len += RINGBUF_META_LEN;
+	/* round up to 8 byte alignment */
+	return (len + 7) / 8 * 8;
+}
+
+static void ringbuf_custom_process_ring(struct ringbuf_custom *r)
+{
+	unsigned long cons_pos, prod_pos;
+	int *len_ptr, len;
+	bool got_new_data;
+
+	cons_pos = smp_load_acquire(r->consumer_pos);
+	while (true) {
+		got_new_data = false;
+		prod_pos = smp_load_acquire(r->producer_pos);
+		while (cons_pos < prod_pos) {
+			len_ptr = r->data + (cons_pos & r->mask);
+			len = smp_load_acquire(len_ptr);
+
+			/* sample not committed yet, bail out for now */
+			if (len & RINGBUF_BUSY_BIT)
+				return;
+
+			got_new_data = true;
+			cons_pos += roundup_len(len);
+
+			atomic_inc(&buf_hits.value);
+		}
+		if (got_new_data)
+			smp_store_release(r->consumer_pos, cons_pos);
+		else
+			break;
+	};
+}
+
+static void *ringbuf_custom_consumer(void *input)
+{
+	struct ringbuf_custom_ctx *ctx = &ringbuf_custom_ctx;
+	int cnt;
+
+	do {
+		if (args.back2back)
+			bufs_trigger_batch();
+		cnt = epoll_wait(ctx->epoll_fd, &ctx->event, 1, -1);
+		if (cnt > 0)
+			ringbuf_custom_process_ring(&ctx->ringbuf);
+	} while (cnt >= 0);
+	fprintf(stderr, "ringbuf polling failed!\n");
+	return 0;
+}
+
+/* PERFBUF-LIBBPF benchmark */
+static struct perfbuf_libbpf_ctx {
+	struct perfbuf_bench *skel;
+	struct perf_buffer *perfbuf;
+} perfbuf_libbpf_ctx;
+
+static void perfbuf_measure(struct bench_res *res)
+{
+	struct perfbuf_libbpf_ctx *ctx = &perfbuf_libbpf_ctx;
+
+	res->hits = atomic_swap(&buf_hits.value, 0);
+	res->drops = atomic_swap(&ctx->skel->bss->dropped, 0);
+}
+
+static struct perfbuf_bench *perfbuf_setup_skeleton()
+{
+	struct perfbuf_bench *skel;
+
+	setup_libbpf();
+
+	skel = perfbuf_bench__open();
+	if (!skel) {
+		fprintf(stderr, "failed to open skeleton\n");
+		exit(1);
+	}
+
+	skel->rodata->batch_cnt = args.batch_cnt;
+
+	if (perfbuf_bench__load(skel)) {
+		fprintf(stderr, "failed to load skeleton\n");
+		exit(1);
+	}
+
+	return skel;
+}
+
+static enum bpf_perf_event_ret
+perfbuf_process_sample_raw(void *input_ctx, int cpu,
+			   struct perf_event_header *e)
+{
+	switch (e->type) {
+	case PERF_RECORD_SAMPLE:
+		atomic_inc(&buf_hits.value);
+		break;
+	case PERF_RECORD_LOST:
+		break;
+	default:
+		return LIBBPF_PERF_EVENT_ERROR;
+	}
+	return LIBBPF_PERF_EVENT_CONT;
+}
+
+static void perfbuf_libbpf_setup()
+{
+	struct perfbuf_libbpf_ctx *ctx = &perfbuf_libbpf_ctx;
+	struct perf_event_attr attr;
+	struct perf_buffer_raw_opts pb_opts = {
+		.event_cb = perfbuf_process_sample_raw,
+		.ctx = (void *)(long)0,
+		.attr = &attr,
+	};
+	struct bpf_link *link;
+
+	ctx->skel = perfbuf_setup_skeleton();
+
+	memset(&attr, 0, sizeof(attr));
+	attr.config = PERF_COUNT_SW_BPF_OUTPUT,
+	attr.type = PERF_TYPE_SOFTWARE;
+	attr.sample_type = PERF_SAMPLE_RAW;
+	/* notify only every Nth sample */
+	if (args.sampled) {
+		attr.sample_period = args.sample_rate;
+		attr.wakeup_events = args.sample_rate;
+	} else {
+		attr.sample_period = 1;
+		attr.wakeup_events = 1;
+	}
+
+	if (args.sample_rate > args.batch_cnt) {
+		fprintf(stderr, "sample rate %d is too high for given batch count %d\n",
+			args.sample_rate, args.batch_cnt);
+		exit(1);
+	}
+
+	ctx->perfbuf = perf_buffer__new_raw(bpf_map__fd(ctx->skel->maps.perfbuf),
+					    args.perfbuf_sz, &pb_opts);
+	if (!ctx->perfbuf) {
+		fprintf(stderr, "failed to create perfbuf\n");
+		exit(1);
+	}
+
+	link = bpf_program__attach(ctx->skel->progs.bench_perfbuf);
+	if (IS_ERR(link)) {
+		fprintf(stderr, "failed to attach program\n");
+		exit(1);
+	}
+}
+
+static void *perfbuf_libbpf_consumer(void *input)
+{
+	struct perfbuf_libbpf_ctx *ctx = &perfbuf_libbpf_ctx;
+
+	while (perf_buffer__poll(ctx->perfbuf, -1) >= 0) {
+		if (args.back2back)
+			bufs_trigger_batch();
+	}
+	fprintf(stderr, "perfbuf polling failed!\n");
+	return NULL;
+}
+
+/* PERFBUF-CUSTOM benchmark */
+
+/* copies of internal libbpf definitions */
+struct perf_cpu_buf {
+	struct perf_buffer *pb;
+	void *base; /* mmap()'ed memory */
+	void *buf; /* for reconstructing segmented data */
+	size_t buf_size;
+	int fd;
+	int cpu;
+	int map_key;
+};
+
+struct perf_buffer {
+	perf_buffer_event_fn event_cb;
+	perf_buffer_sample_fn sample_cb;
+	perf_buffer_lost_fn lost_cb;
+	void *ctx; /* passed into callbacks */
+
+	size_t page_size;
+	size_t mmap_size;
+	struct perf_cpu_buf **cpu_bufs;
+	struct epoll_event *events;
+	int cpu_cnt; /* number of allocated CPU buffers */
+	int epoll_fd; /* perf event FD */
+	int map_fd; /* BPF_MAP_TYPE_PERF_EVENT_ARRAY BPF map FD */
+};
+
+static void *perfbuf_custom_consumer(void *input)
+{
+	struct perfbuf_libbpf_ctx *ctx = &perfbuf_libbpf_ctx;
+	struct perf_buffer *pb = ctx->perfbuf;
+	struct perf_cpu_buf *cpu_buf;
+	struct perf_event_mmap_page *header;
+	size_t mmap_mask = pb->mmap_size - 1;
+	struct perf_event_header *ehdr;
+	__u64 data_head, data_tail;
+	size_t ehdr_size;
+	void *base;
+	int i, cnt;
+
+	while (true) {
+		if (args.back2back)
+			bufs_trigger_batch();
+		cnt = epoll_wait(pb->epoll_fd, pb->events, pb->cpu_cnt, -1);
+		if (cnt <= 0) {
+			fprintf(stderr, "perf epoll failed: %d\n", -errno);
+			exit(1);
+		}
+
+		for (i = 0; i < cnt; ++i) {
+			cpu_buf = pb->events[i].data.ptr;
+			header = cpu_buf->base;
+			base = ((void *)header) + pb->page_size;
+
+			data_head = ring_buffer_read_head(header);
+			data_tail = header->data_tail;
+			while (data_head != data_tail) {
+				ehdr = base + (data_tail & mmap_mask);
+				ehdr_size = ehdr->size;
+
+				if (ehdr->type == PERF_RECORD_SAMPLE)
+					atomic_inc(&buf_hits.value);
+
+				data_tail += ehdr_size;
+			}
+			ring_buffer_write_tail(header, data_tail);
+		}
+	}
+	return NULL;
+}
+
+const struct bench bench_rb_libbpf = {
+	.name = "rb-libbpf",
+	.validate = bufs_validate,
+	.setup = ringbuf_libbpf_setup,
+	.producer_thread = bufs_sample_producer,
+	.consumer_thread = ringbuf_libbpf_consumer,
+	.measure = ringbuf_libbpf_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_rb_custom = {
+	.name = "rb-custom",
+	.validate = bufs_validate,
+	.setup = ringbuf_custom_setup,
+	.producer_thread = bufs_sample_producer,
+	.consumer_thread = ringbuf_custom_consumer,
+	.measure = ringbuf_custom_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_pb_libbpf = {
+	.name = "pb-libbpf",
+	.validate = bufs_validate,
+	.setup = perfbuf_libbpf_setup,
+	.producer_thread = bufs_sample_producer,
+	.consumer_thread = perfbuf_libbpf_consumer,
+	.measure = perfbuf_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_pb_custom = {
+	.name = "pb-custom",
+	.validate = bufs_validate,
+	.setup = perfbuf_libbpf_setup,
+	.producer_thread = bufs_sample_producer,
+	.consumer_thread = perfbuf_custom_consumer,
+	.measure = perfbuf_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c
new file mode 100644
index 000000000000..49c22832f216
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include "bench.h"
+#include "trigger_bench.skel.h"
+
+/* BPF triggering benchmarks */
+static struct trigger_ctx {
+	struct trigger_bench *skel;
+} ctx;
+
+static struct counter base_hits;
+
+static void trigger_validate()
+{
+	if (env.consumer_cnt != 1) {
+		fprintf(stderr, "benchmark doesn't support multi-consumer!\n");
+		exit(1);
+	}
+}
+
+static void *trigger_base_producer(void *input)
+{
+	while (true) {
+		(void)syscall(__NR_getpgid);
+		atomic_inc(&base_hits.value);
+	}
+	return NULL;
+}
+
+static void trigger_base_measure(struct bench_res *res)
+{
+	res->hits = atomic_swap(&base_hits.value, 0);
+}
+
+static void *trigger_producer(void *input)
+{
+	while (true)
+		(void)syscall(__NR_getpgid);
+	return NULL;
+}
+
+static void trigger_measure(struct bench_res *res)
+{
+	res->hits = atomic_swap(&ctx.skel->bss->hits, 0);
+}
+
+static void setup_ctx()
+{
+	setup_libbpf();
+
+	ctx.skel = trigger_bench__open_and_load();
+	if (!ctx.skel) {
+		fprintf(stderr, "failed to open skeleton\n");
+		exit(1);
+	}
+}
+
+static void attach_bpf(struct bpf_program *prog)
+{
+	struct bpf_link *link;
+
+	link = bpf_program__attach(prog);
+	if (IS_ERR(link)) {
+		fprintf(stderr, "failed to attach program!\n");
+		exit(1);
+	}
+}
+
+static void trigger_tp_setup()
+{
+	setup_ctx();
+	attach_bpf(ctx.skel->progs.bench_trigger_tp);
+}
+
+static void trigger_rawtp_setup()
+{
+	setup_ctx();
+	attach_bpf(ctx.skel->progs.bench_trigger_raw_tp);
+}
+
+static void trigger_kprobe_setup()
+{
+	setup_ctx();
+	attach_bpf(ctx.skel->progs.bench_trigger_kprobe);
+}
+
+static void trigger_fentry_setup()
+{
+	setup_ctx();
+	attach_bpf(ctx.skel->progs.bench_trigger_fentry);
+}
+
+static void trigger_fmodret_setup()
+{
+	setup_ctx();
+	attach_bpf(ctx.skel->progs.bench_trigger_fmodret);
+}
+
+static void *trigger_consumer(void *input)
+{
+	return NULL;
+}
+
+const struct bench bench_trig_base = {
+	.name = "trig-base",
+	.validate = trigger_validate,
+	.producer_thread = trigger_base_producer,
+	.consumer_thread = trigger_consumer,
+	.measure = trigger_base_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_tp = {
+	.name = "trig-tp",
+	.validate = trigger_validate,
+	.setup = trigger_tp_setup,
+	.producer_thread = trigger_producer,
+	.consumer_thread = trigger_consumer,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_rawtp = {
+	.name = "trig-rawtp",
+	.validate = trigger_validate,
+	.setup = trigger_rawtp_setup,
+	.producer_thread = trigger_producer,
+	.consumer_thread = trigger_consumer,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_kprobe = {
+	.name = "trig-kprobe",
+	.validate = trigger_validate,
+	.setup = trigger_kprobe_setup,
+	.producer_thread = trigger_producer,
+	.consumer_thread = trigger_consumer,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_fentry = {
+	.name = "trig-fentry",
+	.validate = trigger_validate,
+	.setup = trigger_fentry_setup,
+	.producer_thread = trigger_producer,
+	.consumer_thread = trigger_consumer,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_fmodret = {
+	.name = "trig-fmodret",
+	.validate = trigger_validate,
+	.setup = trigger_fmodret_setup,
+	.producer_thread = trigger_producer,
+	.consumer_thread = trigger_consumer,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_rename.sh b/tools/testing/selftests/bpf/benchs/run_bench_rename.sh
new file mode 100755
index 000000000000..16f774b1cdbe
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_rename.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+
+set -eufo pipefail
+
+for i in base kprobe kretprobe rawtp fentry fexit fmodret
+do
+	summary=$(sudo ./bench -w2 -d5 -a rename-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-)
+	printf "%-10s: %s\n" $i "$summary"
+done
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh
new file mode 100755
index 000000000000..af4aa04caba6
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh
@@ -0,0 +1,75 @@
+#!/bin/bash
+
+set -eufo pipefail
+
+RUN_BENCH="sudo ./bench -w3 -d10 -a"
+
+function hits()
+{
+	echo "$*" | sed -E "s/.*hits\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+M\/s).*/\1/"
+}
+
+function drops()
+{
+	echo "$*" | sed -E "s/.*drops\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+M\/s).*/\1/"
+}
+
+function header()
+{
+	local len=${#1}
+
+	printf "\n%s\n" "$1"
+	for i in $(seq 1 $len); do printf '='; done
+	printf '\n'
+}
+
+function summarize()
+{
+	bench="$1"
+	summary=$(echo $2 | tail -n1)
+	printf "%-20s %s (drops %s)\n" "$bench" "$(hits $summary)" "$(drops $summary)"
+}
+
+header "Single-producer, parallel producer"
+for b in rb-libbpf rb-custom pb-libbpf pb-custom; do
+	summarize $b "$($RUN_BENCH $b)"
+done
+
+header "Single-producer, parallel producer, sampled notification"
+for b in rb-libbpf rb-custom pb-libbpf pb-custom; do
+	summarize $b "$($RUN_BENCH --rb-sampled $b)"
+done
+
+header "Single-producer, back-to-back mode"
+for b in rb-libbpf rb-custom pb-libbpf pb-custom; do
+	summarize $b "$($RUN_BENCH --rb-b2b $b)"
+	summarize $b-sampled "$($RUN_BENCH --rb-sampled --rb-b2b $b)"
+done
+
+header "Ringbuf back-to-back, effect of sample rate"
+for b in 1 5 10 25 50 100 250 500 1000 2000 3000; do
+	summarize "rb-sampled-$b" "$($RUN_BENCH --rb-b2b --rb-batch-cnt $b --rb-sampled --rb-sample-rate $b rb-custom)"
+done
+header "Perfbuf back-to-back, effect of sample rate"
+for b in 1 5 10 25 50 100 250 500 1000 2000 3000; do
+	summarize "pb-sampled-$b" "$($RUN_BENCH --rb-b2b --rb-batch-cnt $b --rb-sampled --rb-sample-rate $b pb-custom)"
+done
+
+header "Ringbuf back-to-back, reserve+commit vs output"
+summarize "reserve" "$($RUN_BENCH --rb-b2b                 rb-custom)"
+summarize "output"  "$($RUN_BENCH --rb-b2b --rb-use-output rb-custom)"
+
+header "Ringbuf sampled, reserve+commit vs output"
+summarize "reserve-sampled" "$($RUN_BENCH --rb-sampled                 rb-custom)"
+summarize "output-sampled"  "$($RUN_BENCH --rb-sampled --rb-use-output rb-custom)"
+
+header "Single-producer, consumer/producer competing on the same CPU, low batch count"
+for b in rb-libbpf rb-custom pb-libbpf pb-custom; do
+	summarize $b "$($RUN_BENCH --rb-batch-cnt 1 --rb-sample-rate 1 --prod-affinity 0 --cons-affinity 0 $b)"
+done
+
+header "Ringbuf, multi-producer contention"
+for b in 1 2 3 4 8 12 16 20 24 28 32 36 40 44 48 52; do
+	summarize "rb-libbpf nr_prod $b" "$($RUN_BENCH -p$b --rb-batch-cnt 50 rb-libbpf)"
+done
+
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh b/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh
new file mode 100755
index 000000000000..78e83f243294
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+
+set -eufo pipefail
+
+for i in base tp rawtp kprobe fentry fmodret
+do
+	summary=$(sudo ./bench -w2 -d5 -a trig-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-)
+	printf "%-10s: %s\n" $i "$summary"
+done
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 60e3ae5d4e48..2118e23ac07a 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -25,6 +25,7 @@ CONFIG_XDP_SOCKETS=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_IPV6_TUNNEL=y
 CONFIG_IPV6_GRE=y
+CONFIG_IPV6_SEG6_BPF=y
 CONFIG_NET_FOU=m
 CONFIG_NET_FOU_IP_TUNNELS=y
 CONFIG_IPV6_FOU=m
@@ -37,3 +38,4 @@ CONFIG_IPV6_SIT=m
 CONFIG_BPF_JIT=y
 CONFIG_BPF_LSM=y
 CONFIG_SECURITY=y
+CONFIG_LIRC=y
diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
new file mode 100644
index 000000000000..e36dd1a1780d
--- /dev/null
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <errno.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <arpa/inet.h>
+
+#include <sys/epoll.h>
+
+#include <linux/err.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+
+#include "bpf_util.h"
+#include "network_helpers.h"
+
+#define clean_errno() (errno == 0 ? "None" : strerror(errno))
+#define log_err(MSG, ...) fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \
+	__FILE__, __LINE__, clean_errno(), ##__VA_ARGS__)
+
+struct ipv4_packet pkt_v4 = {
+	.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
+	.iph.ihl = 5,
+	.iph.protocol = IPPROTO_TCP,
+	.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+	.tcp.urg_ptr = 123,
+	.tcp.doff = 5,
+};
+
+struct ipv6_packet pkt_v6 = {
+	.eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
+	.iph.nexthdr = IPPROTO_TCP,
+	.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+	.tcp.urg_ptr = 123,
+	.tcp.doff = 5,
+};
+
+int start_server_with_port(int family, int type, __u16 port)
+{
+	struct sockaddr_storage addr = {};
+	socklen_t len;
+	int fd;
+
+	if (family == AF_INET) {
+		struct sockaddr_in *sin = (void *)&addr;
+
+		sin->sin_family = AF_INET;
+		sin->sin_port = htons(port);
+		len = sizeof(*sin);
+	} else {
+		struct sockaddr_in6 *sin6 = (void *)&addr;
+
+		sin6->sin6_family = AF_INET6;
+		sin6->sin6_port = htons(port);
+		len = sizeof(*sin6);
+	}
+
+	fd = socket(family, type | SOCK_NONBLOCK, 0);
+	if (fd < 0) {
+		log_err("Failed to create server socket");
+		return -1;
+	}
+
+	if (bind(fd, (const struct sockaddr *)&addr, len) < 0) {
+		log_err("Failed to bind socket");
+		close(fd);
+		return -1;
+	}
+
+	if (type == SOCK_STREAM) {
+		if (listen(fd, 1) < 0) {
+			log_err("Failed to listed on socket");
+			close(fd);
+			return -1;
+		}
+	}
+
+	return fd;
+}
+
+int start_server(int family, int type)
+{
+	return start_server_with_port(family, type, 0);
+}
+
+static const struct timeval timeo_sec = { .tv_sec = 3 };
+static const size_t timeo_optlen = sizeof(timeo_sec);
+
+int connect_to_fd(int family, int type, int server_fd)
+{
+	int fd, save_errno;
+
+	fd = socket(family, type, 0);
+	if (fd < 0) {
+		log_err("Failed to create client socket");
+		return -1;
+	}
+
+	if (connect_fd_to_fd(fd, server_fd) < 0 && errno != EINPROGRESS) {
+		save_errno = errno;
+		close(fd);
+		errno = save_errno;
+		return -1;
+	}
+
+	return fd;
+}
+
+int connect_fd_to_fd(int client_fd, int server_fd)
+{
+	struct sockaddr_storage addr;
+	socklen_t len = sizeof(addr);
+	int save_errno;
+
+	if (setsockopt(client_fd, SOL_SOCKET, SO_RCVTIMEO, &timeo_sec,
+		       timeo_optlen)) {
+		log_err("Failed to set SO_RCVTIMEO");
+		return -1;
+	}
+
+	if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) {
+		log_err("Failed to get server addr");
+		return -1;
+	}
+
+	if (connect(client_fd, (const struct sockaddr *)&addr, len) < 0) {
+		if (errno != EINPROGRESS) {
+			save_errno = errno;
+			log_err("Failed to connect to server");
+			errno = save_errno;
+		}
+		return -1;
+	}
+
+	return 0;
+}
+
+int connect_wait(int fd)
+{
+	struct epoll_event ev = {}, events[2];
+	int timeout_ms = 1000;
+	int efd, nfd;
+
+	efd = epoll_create1(EPOLL_CLOEXEC);
+	if (efd < 0) {
+		log_err("Failed to open epoll fd");
+		return -1;
+	}
+
+	ev.events = EPOLLRDHUP | EPOLLOUT;
+	ev.data.fd = fd;
+
+	if (epoll_ctl(efd, EPOLL_CTL_ADD, fd, &ev) < 0) {
+		log_err("Failed to register fd=%d on epoll fd=%d", fd, efd);
+		close(efd);
+		return -1;
+	}
+
+	nfd = epoll_wait(efd, events, ARRAY_SIZE(events), timeout_ms);
+	if (nfd < 0)
+		log_err("Failed to wait for I/O event on epoll fd=%d", efd);
+
+	close(efd);
+	return nfd;
+}
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
new file mode 100644
index 000000000000..6a8009605670
--- /dev/null
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NETWORK_HELPERS_H
+#define __NETWORK_HELPERS_H
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <linux/types.h>
+typedef __u16 __sum16;
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <netinet/tcp.h>
+#include <bpf/bpf_endian.h>
+
+#define MAGIC_VAL 0x1234
+#define NUM_ITER 100000
+#define VIP_NUM 5
+#define MAGIC_BYTES 123
+
+/* ipv4 test vector */
+struct ipv4_packet {
+	struct ethhdr eth;
+	struct iphdr iph;
+	struct tcphdr tcp;
+} __packed;
+extern struct ipv4_packet pkt_v4;
+
+/* ipv6 test vector */
+struct ipv6_packet {
+	struct ethhdr eth;
+	struct ipv6hdr iph;
+	struct tcphdr tcp;
+} __packed;
+extern struct ipv6_packet pkt_v6;
+
+int start_server(int family, int type);
+int start_server_with_port(int family, int type, __u16 port);
+int connect_to_fd(int family, int type, int server_fd);
+int connect_fd_to_fd(int client_fd, int server_fd);
+int connect_wait(int client_fd);
+
+#endif
diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/prog_tests/align.c
index 0262f7b374f9..c548aded6585 100644
--- a/tools/testing/selftests/bpf/test_align.c
+++ b/tools/testing/selftests/bpf/prog_tests/align.c
@@ -1,24 +1,5 @@
-#include <asm/types.h>
-#include <linux/types.h>
-#include <stdint.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <errno.h>
-#include <string.h>
-#include <stddef.h>
-#include <stdbool.h>
-
-#include <linux/unistd.h>
-#include <linux/filter.h>
-#include <linux/bpf_perf_event.h>
-#include <linux/bpf.h>
-
-#include <bpf/bpf.h>
-
-#include "../../../include/linux/filter.h"
-#include "bpf_rlimit.h"
-#include "bpf_util.h"
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
 
 #define MAX_INSNS	512
 #define MAX_MATCHES	16
@@ -359,15 +340,15 @@ static struct bpf_align_test tests[] = {
 			 * is still (4n), fixed offset is not changed.
 			 * Also, we create a new reg->id.
 			 */
-			{29, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc))"},
+			{29, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (18)
 			 * which is 20.  Then the variable offset is (4n), so
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{33, "R4=pkt(id=4,off=22,r=22,umax_value=2040,var_off=(0x0; 0x7fc))"},
-			{33, "R5=pkt(id=4,off=18,r=22,umax_value=2040,var_off=(0x0; 0x7fc))"},
+			{33, "R4=pkt(id=4,off=22,r=22,umax_value=2040,var_off=(0x0; 0x7fc)"},
+			{33, "R5=pkt(id=4,off=18,r=22,umax_value=2040,var_off=(0x0; 0x7fc)"},
 		},
 	},
 	{
@@ -410,15 +391,15 @@ static struct bpf_align_test tests[] = {
 			/* Adding 14 makes R6 be (4n+2) */
 			{9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
 			/* Packet pointer has (4n+2) offset */
-			{11, "R5_w=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
-			{13, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
+			{11, "R5_w=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"},
+			{13, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (0)
 			 * which is 2.  Then the variable offset is (4n+2), so
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{15, "R5=pkt(id=1,off=0,r=4,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
+			{15, "R5=pkt(id=1,off=0,r=4,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"},
 			/* Newly read value in R6 was shifted left by 2, so has
 			 * known alignment of 4.
 			 */
@@ -426,15 +407,15 @@ static struct bpf_align_test tests[] = {
 			/* Added (4n) to packet pointer's (4n+2) var_off, giving
 			 * another (4n+2).
 			 */
-			{19, "R5_w=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"},
-			{21, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"},
+			{19, "R5_w=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"},
+			{21, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (0)
 			 * which is 2.  Then the variable offset is (4n+2), so
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{23, "R5=pkt(id=2,off=0,r=4,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"},
+			{23, "R5=pkt(id=2,off=0,r=4,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"},
 		},
 	},
 	{
@@ -469,16 +450,16 @@ static struct bpf_align_test tests[] = {
 		.matches = {
 			{4, "R5_w=pkt_end(id=0,off=0,imm=0)"},
 			/* (ptr - ptr) << 2 == unknown, (4n) */
-			{6, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc))"},
+			{6, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc)"},
 			/* (4n) + 14 == (4n+2).  We blow our bounds, because
 			 * the add could overflow.
 			 */
-			{7, "R5_w=inv(id=0,var_off=(0x2; 0xfffffffffffffffc))"},
+			{7, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"},
 			/* Checked s>=0 */
-			{9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
+			{9, "R5=inv(id=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"},
 			/* packet pointer + nonnegative (4n+2) */
-			{11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
-			{13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
+			{11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"},
+			{13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"},
 			/* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine.
 			 * We checked the bounds, but it might have been able
 			 * to overflow if the packet pointer started in the
@@ -486,7 +467,7 @@ static struct bpf_align_test tests[] = {
 			 * So we did not get a 'range' on R6, and the access
 			 * attempt will fail.
 			 */
-			{15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
+			{15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"},
 		}
 	},
 	{
@@ -528,7 +509,7 @@ static struct bpf_align_test tests[] = {
 			/* New unknown value in R7 is (4n) */
 			{11, "R7_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Subtracting it from R6 blows our unsigned bounds */
-			{12, "R6=inv(id=0,smin_value=-1006,smax_value=1034,var_off=(0x2; 0xfffffffffffffffc))"},
+			{12, "R6=inv(id=0,smin_value=-1006,smax_value=1034,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"},
 			/* Checked s>= 0 */
 			{14, "R6=inv(id=0,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"},
 			/* At the time the word size load is performed from R5,
@@ -537,7 +518,8 @@ static struct bpf_align_test tests[] = {
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{20, "R5=pkt(id=1,off=0,r=4,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"},
+			{20, "R5=pkt(id=1,off=0,r=4,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc)"},
+
 		},
 	},
 	{
@@ -579,18 +561,18 @@ static struct bpf_align_test tests[] = {
 			/* Adding 14 makes R6 be (4n+2) */
 			{11, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"},
 			/* Subtracting from packet pointer overflows ubounds */
-			{13, "R5_w=pkt(id=1,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c))"},
+			{13, "R5_w=pkt(id=1,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c)"},
 			/* New unknown value in R7 is (4n), >= 76 */
 			{15, "R7_w=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"},
 			/* Adding it to packet pointer gives nice bounds again */
-			{16, "R5_w=pkt(id=2,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"},
+			{16, "R5_w=pkt(id=2,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (0)
 			 * which is 2.  Then the variable offset is (4n+2), so
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{20, "R5=pkt(id=2,off=0,r=4,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"},
+			{20, "R5=pkt(id=2,off=0,r=4,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"},
 		},
 	},
 };
@@ -669,51 +651,16 @@ static int do_test_single(struct bpf_align_test *test)
 	return ret;
 }
 
-static int do_test(unsigned int from, unsigned int to)
+void test_align(void)
 {
-	int all_pass = 0;
-	int all_fail = 0;
 	unsigned int i;
 
-	for (i = from; i < to; i++) {
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		struct bpf_align_test *test = &tests[i];
-		int fail;
 
-		printf("Test %3d: %s ... ",
-		       i, test->descr);
-		fail = do_test_single(test);
-		if (fail) {
-			all_fail++;
-			printf("FAIL\n");
-		} else {
-			all_pass++;
-			printf("PASS\n");
-		}
-	}
-	printf("Results: %d pass %d fail\n",
-	       all_pass, all_fail);
-	return all_fail ? EXIT_FAILURE : EXIT_SUCCESS;
-}
+		if (!test__start_subtest(test->descr))
+			continue;
 
-int main(int argc, char **argv)
-{
-	unsigned int from = 0, to = ARRAY_SIZE(tests);
-
-	if (argc == 3) {
-		unsigned int l = atoi(argv[argc - 2]);
-		unsigned int u = atoi(argv[argc - 1]);
-
-		if (l < to && u < to) {
-			from = l;
-			to   = u + 1;
-		}
-	} else if (argc == 2) {
-		unsigned int t = atoi(argv[argc - 1]);
-
-		if (t < to) {
-			from = t;
-			to   = t + 1;
-		}
+		CHECK_FAIL(do_test_single(test));
 	}
-	return do_test(from, to);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
new file mode 100644
index 000000000000..87c29dde1cf9
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -0,0 +1,409 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+#include "bpf_iter_ipv6_route.skel.h"
+#include "bpf_iter_netlink.skel.h"
+#include "bpf_iter_bpf_map.skel.h"
+#include "bpf_iter_task.skel.h"
+#include "bpf_iter_task_file.skel.h"
+#include "bpf_iter_test_kern1.skel.h"
+#include "bpf_iter_test_kern2.skel.h"
+#include "bpf_iter_test_kern3.skel.h"
+#include "bpf_iter_test_kern4.skel.h"
+
+static int duration;
+
+static void test_btf_id_or_null(void)
+{
+	struct bpf_iter_test_kern3 *skel;
+
+	skel = bpf_iter_test_kern3__open_and_load();
+	if (CHECK(skel, "bpf_iter_test_kern3__open_and_load",
+		  "skeleton open_and_load unexpectedly succeeded\n")) {
+		bpf_iter_test_kern3__destroy(skel);
+		return;
+	}
+}
+
+static void do_dummy_read(struct bpf_program *prog)
+{
+	struct bpf_link *link;
+	char buf[16] = {};
+	int iter_fd, len;
+
+	link = bpf_program__attach_iter(prog, NULL);
+	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+		return;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+		goto free_link;
+
+	/* not check contents, but ensure read() ends without error */
+	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
+		;
+	CHECK(len < 0, "read", "read failed: %s\n", strerror(errno));
+
+	close(iter_fd);
+
+free_link:
+	bpf_link__destroy(link);
+}
+
+static void test_ipv6_route(void)
+{
+	struct bpf_iter_ipv6_route *skel;
+
+	skel = bpf_iter_ipv6_route__open_and_load();
+	if (CHECK(!skel, "bpf_iter_ipv6_route__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	do_dummy_read(skel->progs.dump_ipv6_route);
+
+	bpf_iter_ipv6_route__destroy(skel);
+}
+
+static void test_netlink(void)
+{
+	struct bpf_iter_netlink *skel;
+
+	skel = bpf_iter_netlink__open_and_load();
+	if (CHECK(!skel, "bpf_iter_netlink__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	do_dummy_read(skel->progs.dump_netlink);
+
+	bpf_iter_netlink__destroy(skel);
+}
+
+static void test_bpf_map(void)
+{
+	struct bpf_iter_bpf_map *skel;
+
+	skel = bpf_iter_bpf_map__open_and_load();
+	if (CHECK(!skel, "bpf_iter_bpf_map__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	do_dummy_read(skel->progs.dump_bpf_map);
+
+	bpf_iter_bpf_map__destroy(skel);
+}
+
+static void test_task(void)
+{
+	struct bpf_iter_task *skel;
+
+	skel = bpf_iter_task__open_and_load();
+	if (CHECK(!skel, "bpf_iter_task__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	do_dummy_read(skel->progs.dump_task);
+
+	bpf_iter_task__destroy(skel);
+}
+
+static void test_task_file(void)
+{
+	struct bpf_iter_task_file *skel;
+
+	skel = bpf_iter_task_file__open_and_load();
+	if (CHECK(!skel, "bpf_iter_task_file__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	do_dummy_read(skel->progs.dump_task_file);
+
+	bpf_iter_task_file__destroy(skel);
+}
+
+/* The expected string is less than 16 bytes */
+static int do_read_with_fd(int iter_fd, const char *expected,
+			   bool read_one_char)
+{
+	int err = -1, len, read_buf_len, start;
+	char buf[16] = {};
+
+	read_buf_len = read_one_char ? 1 : 16;
+	start = 0;
+	while ((len = read(iter_fd, buf + start, read_buf_len)) > 0) {
+		start += len;
+		if (CHECK(start >= 16, "read", "read len %d\n", len))
+			return -1;
+		read_buf_len = read_one_char ? 1 : 16 - start;
+	}
+	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+		return -1;
+
+	err = strcmp(buf, expected);
+	if (CHECK(err, "read", "incorrect read result: buf %s, expected %s\n",
+		  buf, expected))
+		return -1;
+
+	return 0;
+}
+
+static void test_anon_iter(bool read_one_char)
+{
+	struct bpf_iter_test_kern1 *skel;
+	struct bpf_link *link;
+	int iter_fd, err;
+
+	skel = bpf_iter_test_kern1__open_and_load();
+	if (CHECK(!skel, "bpf_iter_test_kern1__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	err = bpf_iter_test_kern1__attach(skel);
+	if (CHECK(err, "bpf_iter_test_kern1__attach",
+		  "skeleton attach failed\n")) {
+		goto out;
+	}
+
+	link = skel->links.dump_task;
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+		goto out;
+
+	do_read_with_fd(iter_fd, "abcd", read_one_char);
+	close(iter_fd);
+
+out:
+	bpf_iter_test_kern1__destroy(skel);
+}
+
+static int do_read(const char *path, const char *expected)
+{
+	int err, iter_fd;
+
+	iter_fd = open(path, O_RDONLY);
+	if (CHECK(iter_fd < 0, "open", "open %s failed: %s\n",
+		  path, strerror(errno)))
+		return -1;
+
+	err = do_read_with_fd(iter_fd, expected, false);
+	close(iter_fd);
+	return err;
+}
+
+static void test_file_iter(void)
+{
+	const char *path = "/sys/fs/bpf/bpf_iter_test1";
+	struct bpf_iter_test_kern1 *skel1;
+	struct bpf_iter_test_kern2 *skel2;
+	struct bpf_link *link;
+	int err;
+
+	skel1 = bpf_iter_test_kern1__open_and_load();
+	if (CHECK(!skel1, "bpf_iter_test_kern1__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	link = bpf_program__attach_iter(skel1->progs.dump_task, NULL);
+	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+		goto out;
+
+	/* unlink this path if it exists. */
+	unlink(path);
+
+	err = bpf_link__pin(link, path);
+	if (CHECK(err, "pin_iter", "pin_iter to %s failed: %d\n", path, err))
+		goto free_link;
+
+	err = do_read(path, "abcd");
+	if (err)
+		goto unlink_path;
+
+	/* file based iterator seems working fine. Let us a link update
+	 * of the underlying link and `cat` the iterator again, its content
+	 * should change.
+	 */
+	skel2 = bpf_iter_test_kern2__open_and_load();
+	if (CHECK(!skel2, "bpf_iter_test_kern2__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		goto unlink_path;
+
+	err = bpf_link__update_program(link, skel2->progs.dump_task);
+	if (CHECK(err, "update_prog", "update_prog failed\n"))
+		goto destroy_skel2;
+
+	do_read(path, "ABCD");
+
+destroy_skel2:
+	bpf_iter_test_kern2__destroy(skel2);
+unlink_path:
+	unlink(path);
+free_link:
+	bpf_link__destroy(link);
+out:
+	bpf_iter_test_kern1__destroy(skel1);
+}
+
+static void test_overflow(bool test_e2big_overflow, bool ret1)
+{
+	__u32 map_info_len, total_read_len, expected_read_len;
+	int err, iter_fd, map1_fd, map2_fd, len;
+	struct bpf_map_info map_info = {};
+	struct bpf_iter_test_kern4 *skel;
+	struct bpf_link *link;
+	__u32 page_size;
+	char *buf;
+
+	skel = bpf_iter_test_kern4__open();
+	if (CHECK(!skel, "bpf_iter_test_kern4__open",
+		  "skeleton open failed\n"))
+		return;
+
+	/* create two maps: bpf program will only do bpf_seq_write
+	 * for these two maps. The goal is one map output almost
+	 * fills seq_file buffer and then the other will trigger
+	 * overflow and needs restart.
+	 */
+	map1_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0);
+	if (CHECK(map1_fd < 0, "bpf_create_map",
+		  "map_creation failed: %s\n", strerror(errno)))
+		goto out;
+	map2_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0);
+	if (CHECK(map2_fd < 0, "bpf_create_map",
+		  "map_creation failed: %s\n", strerror(errno)))
+		goto free_map1;
+
+	/* bpf_seq_printf kernel buffer is one page, so one map
+	 * bpf_seq_write will mostly fill it, and the other map
+	 * will partially fill and then trigger overflow and need
+	 * bpf_seq_read restart.
+	 */
+	page_size = sysconf(_SC_PAGE_SIZE);
+
+	if (test_e2big_overflow) {
+		skel->rodata->print_len = (page_size + 8) / 8;
+		expected_read_len = 2 * (page_size + 8);
+	} else if (!ret1) {
+		skel->rodata->print_len = (page_size - 8) / 8;
+		expected_read_len = 2 * (page_size - 8);
+	} else {
+		skel->rodata->print_len = 1;
+		expected_read_len = 2 * 8;
+	}
+	skel->rodata->ret1 = ret1;
+
+	if (CHECK(bpf_iter_test_kern4__load(skel),
+		  "bpf_iter_test_kern4__load", "skeleton load failed\n"))
+		goto free_map2;
+
+	/* setup filtering map_id in bpf program */
+	map_info_len = sizeof(map_info);
+	err = bpf_obj_get_info_by_fd(map1_fd, &map_info, &map_info_len);
+	if (CHECK(err, "get_map_info", "get map info failed: %s\n",
+		  strerror(errno)))
+		goto free_map2;
+	skel->bss->map1_id = map_info.id;
+
+	err = bpf_obj_get_info_by_fd(map2_fd, &map_info, &map_info_len);
+	if (CHECK(err, "get_map_info", "get map info failed: %s\n",
+		  strerror(errno)))
+		goto free_map2;
+	skel->bss->map2_id = map_info.id;
+
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_map, NULL);
+	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+		goto free_map2;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+		goto free_link;
+
+	buf = malloc(expected_read_len);
+	if (!buf)
+		goto close_iter;
+
+	/* do read */
+	total_read_len = 0;
+	if (test_e2big_overflow) {
+		while ((len = read(iter_fd, buf, expected_read_len)) > 0)
+			total_read_len += len;
+
+		CHECK(len != -1 || errno != E2BIG, "read",
+		      "expected ret -1, errno E2BIG, but get ret %d, error %s\n",
+			  len, strerror(errno));
+		goto free_buf;
+	} else if (!ret1) {
+		while ((len = read(iter_fd, buf, expected_read_len)) > 0)
+			total_read_len += len;
+
+		if (CHECK(len < 0, "read", "read failed: %s\n",
+			  strerror(errno)))
+			goto free_buf;
+	} else {
+		do {
+			len = read(iter_fd, buf, expected_read_len);
+			if (len > 0)
+				total_read_len += len;
+		} while (len > 0 || len == -EAGAIN);
+
+		if (CHECK(len < 0, "read", "read failed: %s\n",
+			  strerror(errno)))
+			goto free_buf;
+	}
+
+	if (CHECK(total_read_len != expected_read_len, "read",
+		  "total len %u, expected len %u\n", total_read_len,
+		  expected_read_len))
+		goto free_buf;
+
+	if (CHECK(skel->bss->map1_accessed != 1, "map1_accessed",
+		  "expected 1 actual %d\n", skel->bss->map1_accessed))
+		goto free_buf;
+
+	if (CHECK(skel->bss->map2_accessed != 2, "map2_accessed",
+		  "expected 2 actual %d\n", skel->bss->map2_accessed))
+		goto free_buf;
+
+	CHECK(skel->bss->map2_seqnum1 != skel->bss->map2_seqnum2,
+	      "map2_seqnum", "two different seqnum %lld %lld\n",
+	      skel->bss->map2_seqnum1, skel->bss->map2_seqnum2);
+
+free_buf:
+	free(buf);
+close_iter:
+	close(iter_fd);
+free_link:
+	bpf_link__destroy(link);
+free_map2:
+	close(map2_fd);
+free_map1:
+	close(map1_fd);
+out:
+	bpf_iter_test_kern4__destroy(skel);
+}
+
+void test_bpf_iter(void)
+{
+	if (test__start_subtest("btf_id_or_null"))
+		test_btf_id_or_null();
+	if (test__start_subtest("ipv6_route"))
+		test_ipv6_route();
+	if (test__start_subtest("netlink"))
+		test_netlink();
+	if (test__start_subtest("bpf_map"))
+		test_bpf_map();
+	if (test__start_subtest("task"))
+		test_task();
+	if (test__start_subtest("task_file"))
+		test_task_file();
+	if (test__start_subtest("anon"))
+		test_anon_iter(false);
+	if (test__start_subtest("anon-read-one-char"))
+		test_anon_iter(true);
+	if (test__start_subtest("file"))
+		test_file_iter();
+	if (test__start_subtest("overflow"))
+		test_overflow(false, false);
+	if (test__start_subtest("overflow-e2big"))
+		test_overflow(true, false);
+	if (test__start_subtest("prog-ret-1"))
+		test_overflow(false, true);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
index f10029821e16..7afa4160416f 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
@@ -1,26 +1,30 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 
+#define nr_iters 2
+
 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];
+	struct bpf_object *objs[nr_iters] = {};
+	struct bpf_link *links[nr_iters] = {};
+	struct bpf_program *prog;
 	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];
+	struct bpf_link_info link_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];
+	char jited_insns[128], xlated_insns[128], zeros[128], tp_name[128];
 	__u32 i, next_id, info_len, nr_id_found, duration = 0;
 	struct timespec real_time_ts, boot_time_ts;
 	int err = 0;
@@ -36,14 +40,15 @@ void test_bpf_obj_id(void)
 	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;
+	err = bpf_link_get_fd_by_id(0);
+	CHECK(err >= 0 || errno != ENOENT,
+	      "get-fd-by-notexist-link-id", "err %d errno %d\n", err, errno);
 
 	/* 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,
+		err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT,
 				    &objs[i], &prog_fds[i]);
 		/* test_obj_id.o is a dumb prog. It should never fail
 		 * to load.
@@ -60,6 +65,17 @@ void test_bpf_obj_id(void)
 		if (CHECK_FAIL(err))
 			goto done;
 
+		prog = bpf_object__find_program_by_title(objs[i],
+							 "raw_tp/sys_enter");
+		if (CHECK_FAIL(!prog))
+			goto done;
+		links[i] = bpf_program__attach(prog);
+		err = libbpf_get_error(links[i]);
+		if (CHECK(err, "prog_attach", "prog #%d, err %d\n", i, err)) {
+			links[i] = NULL;
+			goto done;
+		}
+
 		/* Check getting map info */
 		info_len = sizeof(struct bpf_map_info) * 2;
 		bzero(&map_infos[i], info_len);
@@ -107,7 +123,7 @@ void test_bpf_obj_id(void)
 		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 ||
+			  prog_infos[i].type != BPF_PROG_TYPE_RAW_TRACEPOINT ||
 			  info_len != sizeof(struct bpf_prog_info) ||
 			  (env.jit_enabled && !prog_infos[i].jited_prog_len) ||
 			  (env.jit_enabled &&
@@ -120,7 +136,11 @@ void test_bpf_obj_id(void)
 			  *(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 %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),
@@ -135,6 +155,33 @@ void test_bpf_obj_id(void)
 			  *(int *)(long)prog_infos[i].map_ids, map_infos[i].id,
 			  prog_infos[i].name, expected_prog_name))
 			goto done;
+
+		/* Check getting link info */
+		info_len = sizeof(struct bpf_link_info) * 2;
+		bzero(&link_infos[i], info_len);
+		link_infos[i].raw_tracepoint.tp_name = (__u64)&tp_name;
+		link_infos[i].raw_tracepoint.tp_name_len = sizeof(tp_name);
+		err = bpf_obj_get_info_by_fd(bpf_link__fd(links[i]),
+					     &link_infos[i], &info_len);
+		if (CHECK(err ||
+			  link_infos[i].type != BPF_LINK_TYPE_RAW_TRACEPOINT ||
+			  link_infos[i].prog_id != prog_infos[i].id ||
+			  link_infos[i].raw_tracepoint.tp_name != (__u64)&tp_name ||
+			  strcmp((char *)link_infos[i].raw_tracepoint.tp_name,
+				 "sys_enter") ||
+			  info_len != sizeof(struct bpf_link_info),
+			  "get-link-info(fd)",
+			  "err %d errno %d info_len %u(%zu) type %d(%d) id %d "
+			  "prog_id %d (%d) tp_name %s(%s)\n",
+			  err, errno,
+			  info_len, sizeof(struct bpf_link_info),
+			  link_infos[i].type, BPF_LINK_TYPE_RAW_TRACEPOINT,
+			  link_infos[i].id,
+			  link_infos[i].prog_id, prog_infos[i].id,
+			  (char *)link_infos[i].raw_tracepoint.tp_name,
+			  "sys_enter"))
+			goto done;
+
 	}
 
 	/* Check bpf_prog_get_next_id() */
@@ -247,7 +294,52 @@ void test_bpf_obj_id(void)
 	      "nr_id_found %u(%u)\n",
 	      nr_id_found, nr_iters);
 
+	/* Check bpf_link_get_next_id() */
+	nr_id_found = 0;
+	next_id = 0;
+	while (!bpf_link_get_next_id(next_id, &next_id)) {
+		struct bpf_link_info link_info;
+		int link_fd, cmp_res;
+
+		info_len = sizeof(link_info);
+		memset(&link_info, 0, info_len);
+
+		link_fd = bpf_link_get_fd_by_id(next_id);
+		if (link_fd < 0 && errno == ENOENT)
+			/* The bpf_link is in the dead row */
+			continue;
+		if (CHECK(link_fd < 0, "get-link-fd(next_id)",
+			  "link_fd %d next_id %u errno %d\n",
+			  link_fd, next_id, errno))
+			break;
+
+		for (i = 0; i < nr_iters; i++)
+			if (link_infos[i].id == next_id)
+				break;
+
+		if (i == nr_iters)
+			continue;
+
+		nr_id_found++;
+
+		err = bpf_obj_get_info_by_fd(link_fd, &link_info, &info_len);
+		cmp_res = memcmp(&link_info, &link_infos[i],
+				offsetof(struct bpf_link_info, raw_tracepoint));
+		CHECK(err || info_len != sizeof(link_info) || cmp_res,
+		      "check get-link-info(next_id->fd)",
+		      "err %d errno %d info_len %u(%zu) memcmp %d\n",
+		      err, errno, info_len, sizeof(struct bpf_link_info),
+		      cmp_res);
+
+		close(link_fd);
+	}
+	CHECK(nr_id_found != nr_iters,
+	      "check total link 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++)
+	for (i = 0; i < nr_iters; i++) {
+		bpf_link__destroy(links[i]);
 		bpf_object__close(objs[i]);
+	}
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
new file mode 100644
index 000000000000..f7ee8fa377ad
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <test_progs.h>
+
+#include "test_btf_map_in_map.skel.h"
+
+void test_btf_map_in_map(void)
+{
+	int duration = 0, err, key = 0, val;
+	struct test_btf_map_in_map* skel;
+
+	skel = test_btf_map_in_map__open_and_load();
+	if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n"))
+		return;
+
+	err = test_btf_map_in_map__attach(skel);
+	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+		goto cleanup;
+
+	/* inner1 = input, inner2 = input + 1 */
+	val = bpf_map__fd(skel->maps.inner_map1);
+	bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0);
+	val = bpf_map__fd(skel->maps.inner_map2);
+	bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0);
+	skel->bss->input = 1;
+	usleep(1);
+
+	bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val);
+	CHECK(val != 1, "inner1", "got %d != exp %d\n", val, 1);
+	bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val);
+	CHECK(val != 2, "inner2", "got %d != exp %d\n", val, 2);
+
+	/* inner1 = input + 1, inner2 = input */
+	val = bpf_map__fd(skel->maps.inner_map2);
+	bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0);
+	val = bpf_map__fd(skel->maps.inner_map1);
+	bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0);
+	skel->bss->input = 3;
+	usleep(1);
+
+	bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val);
+	CHECK(val != 4, "inner1", "got %d != exp %d\n", val, 4);
+	bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val);
+	CHECK(val != 3, "inner2", "got %d != exp %d\n", val, 3);
+
+cleanup:
+	test_btf_map_in_map__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c
new file mode 100644
index 000000000000..059047af7df3
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <test_progs.h>
+
+#include "network_helpers.h"
+#include "cgroup_skb_sk_lookup_kern.skel.h"
+
+static void run_lookup_test(__u16 *g_serv_port, int out_sk)
+{
+	int serv_sk = -1, in_sk = -1, serv_in_sk = -1, err;
+	struct sockaddr_in6 addr = {};
+	socklen_t addr_len = sizeof(addr);
+	__u32 duration = 0;
+
+	serv_sk = start_server(AF_INET6, SOCK_STREAM);
+	if (CHECK(serv_sk < 0, "start_server", "failed to start server\n"))
+		return;
+
+	err = getsockname(serv_sk, (struct sockaddr *)&addr, &addr_len);
+	if (CHECK(err, "getsockname", "errno %d\n", errno))
+		goto cleanup;
+
+	*g_serv_port = addr.sin6_port;
+
+	/* Client outside of test cgroup should fail to connect by timeout. */
+	err = connect_fd_to_fd(out_sk, serv_sk);
+	if (CHECK(!err || errno != EINPROGRESS, "connect_fd_to_fd",
+		  "unexpected result err %d errno %d\n", err, errno))
+		goto cleanup;
+
+	err = connect_wait(out_sk);
+	if (CHECK(err, "connect_wait", "unexpected result %d\n", err))
+		goto cleanup;
+
+	/* Client inside test cgroup should connect just fine. */
+	in_sk = connect_to_fd(AF_INET6, SOCK_STREAM, serv_sk);
+	if (CHECK(in_sk < 0, "connect_to_fd", "errno %d\n", errno))
+		goto cleanup;
+
+	serv_in_sk = accept(serv_sk, NULL, NULL);
+	if (CHECK(serv_in_sk < 0, "accept", "errno %d\n", errno))
+		goto cleanup;
+
+cleanup:
+	close(serv_in_sk);
+	close(in_sk);
+	close(serv_sk);
+}
+
+static void run_cgroup_bpf_test(const char *cg_path, int out_sk)
+{
+	struct cgroup_skb_sk_lookup_kern *skel;
+	struct bpf_link *link;
+	__u32 duration = 0;
+	int cgfd = -1;
+
+	skel = cgroup_skb_sk_lookup_kern__open_and_load();
+	if (CHECK(!skel, "skel_open_load", "open_load failed\n"))
+		return;
+
+	cgfd = test__join_cgroup(cg_path);
+	if (CHECK(cgfd < 0, "cgroup_join", "cgroup setup failed\n"))
+		goto cleanup;
+
+	link = bpf_program__attach_cgroup(skel->progs.ingress_lookup, cgfd);
+	if (CHECK(IS_ERR(link), "cgroup_attach", "err: %ld\n", PTR_ERR(link)))
+		goto cleanup;
+
+	run_lookup_test(&skel->bss->g_serv_port, out_sk);
+
+	bpf_link__destroy(link);
+
+cleanup:
+	close(cgfd);
+	cgroup_skb_sk_lookup_kern__destroy(skel);
+}
+
+void test_cgroup_skb_sk_lookup(void)
+{
+	const char *cg_path = "/foo";
+	int out_sk;
+
+	/* Create a socket before joining testing cgroup so that its cgroup id
+	 * differs from that of testing cgroup. Moving selftests process to
+	 * testing cgroup won't change cgroup id of an already created socket.
+	 */
+	out_sk = socket(AF_INET6, SOCK_STREAM | SOCK_NONBLOCK, 0);
+	if (CHECK_FAIL(out_sk < 0))
+		return;
+
+	run_cgroup_bpf_test(cg_path, out_sk);
+
+	close(out_sk);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c
new file mode 100644
index 000000000000..f259085cca6a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c
@@ -0,0 +1,456 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+// Copyright (c) 2020 Cloudflare
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <string.h>
+
+#include <linux/pkt_cls.h>
+
+#include <test_progs.h>
+
+#include "progs/test_cls_redirect.h"
+#include "test_cls_redirect.skel.h"
+
+#define ENCAP_IP INADDR_LOOPBACK
+#define ENCAP_PORT (1234)
+
+struct addr_port {
+	in_port_t port;
+	union {
+		struct in_addr in_addr;
+		struct in6_addr in6_addr;
+	};
+};
+
+struct tuple {
+	int family;
+	struct addr_port src;
+	struct addr_port dst;
+};
+
+static int start_server(const struct sockaddr *addr, socklen_t len, int type)
+{
+	int fd = socket(addr->sa_family, type, 0);
+	if (CHECK_FAIL(fd == -1))
+		return -1;
+	if (CHECK_FAIL(bind(fd, addr, len) == -1))
+		goto err;
+	if (type == SOCK_STREAM && CHECK_FAIL(listen(fd, 128) == -1))
+		goto err;
+
+	return fd;
+
+err:
+	close(fd);
+	return -1;
+}
+
+static int connect_to_server(const struct sockaddr *addr, socklen_t len,
+			     int type)
+{
+	int fd = socket(addr->sa_family, type, 0);
+	if (CHECK_FAIL(fd == -1))
+		return -1;
+	if (CHECK_FAIL(connect(fd, addr, len)))
+		goto err;
+
+	return fd;
+
+err:
+	close(fd);
+	return -1;
+}
+
+static bool fill_addr_port(const struct sockaddr *sa, struct addr_port *ap)
+{
+	const struct sockaddr_in6 *in6;
+	const struct sockaddr_in *in;
+
+	switch (sa->sa_family) {
+	case AF_INET:
+		in = (const struct sockaddr_in *)sa;
+		ap->in_addr = in->sin_addr;
+		ap->port = in->sin_port;
+		return true;
+
+	case AF_INET6:
+		in6 = (const struct sockaddr_in6 *)sa;
+		ap->in6_addr = in6->sin6_addr;
+		ap->port = in6->sin6_port;
+		return true;
+
+	default:
+		return false;
+	}
+}
+
+static bool set_up_conn(const struct sockaddr *addr, socklen_t len, int type,
+			int *server, int *conn, struct tuple *tuple)
+{
+	struct sockaddr_storage ss;
+	socklen_t slen = sizeof(ss);
+	struct sockaddr *sa = (struct sockaddr *)&ss;
+
+	*server = start_server(addr, len, type);
+	if (*server < 0)
+		return false;
+
+	if (CHECK_FAIL(getsockname(*server, sa, &slen)))
+		goto close_server;
+
+	*conn = connect_to_server(sa, slen, type);
+	if (*conn < 0)
+		goto close_server;
+
+	/* We want to simulate packets arriving at conn, so we have to
+	 * swap src and dst.
+	 */
+	slen = sizeof(ss);
+	if (CHECK_FAIL(getsockname(*conn, sa, &slen)))
+		goto close_conn;
+
+	if (CHECK_FAIL(!fill_addr_port(sa, &tuple->dst)))
+		goto close_conn;
+
+	slen = sizeof(ss);
+	if (CHECK_FAIL(getpeername(*conn, sa, &slen)))
+		goto close_conn;
+
+	if (CHECK_FAIL(!fill_addr_port(sa, &tuple->src)))
+		goto close_conn;
+
+	tuple->family = ss.ss_family;
+	return true;
+
+close_conn:
+	close(*conn);
+	*conn = -1;
+close_server:
+	close(*server);
+	*server = -1;
+	return false;
+}
+
+static socklen_t prepare_addr(struct sockaddr_storage *addr, int family)
+{
+	struct sockaddr_in *addr4;
+	struct sockaddr_in6 *addr6;
+
+	switch (family) {
+	case AF_INET:
+		addr4 = (struct sockaddr_in *)addr;
+		memset(addr4, 0, sizeof(*addr4));
+		addr4->sin_family = family;
+		addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+		return sizeof(*addr4);
+	case AF_INET6:
+		addr6 = (struct sockaddr_in6 *)addr;
+		memset(addr6, 0, sizeof(*addr6));
+		addr6->sin6_family = family;
+		addr6->sin6_addr = in6addr_loopback;
+		return sizeof(*addr6);
+	default:
+		fprintf(stderr, "Invalid family %d", family);
+		return 0;
+	}
+}
+
+static bool was_decapsulated(struct bpf_prog_test_run_attr *tattr)
+{
+	return tattr->data_size_out < tattr->data_size_in;
+}
+
+enum type {
+	UDP,
+	TCP,
+	__NR_KIND,
+};
+
+enum hops {
+	NO_HOPS,
+	ONE_HOP,
+};
+
+enum flags {
+	NONE,
+	SYN,
+	ACK,
+};
+
+enum conn {
+	KNOWN_CONN,
+	UNKNOWN_CONN,
+};
+
+enum result {
+	ACCEPT,
+	FORWARD,
+};
+
+struct test_cfg {
+	enum type type;
+	enum result result;
+	enum conn conn;
+	enum hops hops;
+	enum flags flags;
+};
+
+static int test_str(void *buf, size_t len, const struct test_cfg *test,
+		    int family)
+{
+	const char *family_str, *type, *conn, *hops, *result, *flags;
+
+	family_str = "IPv4";
+	if (family == AF_INET6)
+		family_str = "IPv6";
+
+	type = "TCP";
+	if (test->type == UDP)
+		type = "UDP";
+
+	conn = "known";
+	if (test->conn == UNKNOWN_CONN)
+		conn = "unknown";
+
+	hops = "no hops";
+	if (test->hops == ONE_HOP)
+		hops = "one hop";
+
+	result = "accept";
+	if (test->result == FORWARD)
+		result = "forward";
+
+	flags = "none";
+	if (test->flags == SYN)
+		flags = "SYN";
+	else if (test->flags == ACK)
+		flags = "ACK";
+
+	return snprintf(buf, len, "%s %s %s %s (%s, flags: %s)", family_str,
+			type, result, conn, hops, flags);
+}
+
+static struct test_cfg tests[] = {
+	{ TCP, ACCEPT, UNKNOWN_CONN, NO_HOPS, SYN },
+	{ TCP, ACCEPT, UNKNOWN_CONN, NO_HOPS, ACK },
+	{ TCP, FORWARD, UNKNOWN_CONN, ONE_HOP, ACK },
+	{ TCP, ACCEPT, KNOWN_CONN, ONE_HOP, ACK },
+	{ UDP, ACCEPT, UNKNOWN_CONN, NO_HOPS, NONE },
+	{ UDP, FORWARD, UNKNOWN_CONN, ONE_HOP, NONE },
+	{ UDP, ACCEPT, KNOWN_CONN, ONE_HOP, NONE },
+};
+
+static void encap_init(encap_headers_t *encap, uint8_t hop_count, uint8_t proto)
+{
+	const uint8_t hlen =
+		(sizeof(struct guehdr) / sizeof(uint32_t)) + hop_count;
+	*encap = (encap_headers_t){
+		.eth = { .h_proto = htons(ETH_P_IP) },
+		.ip = {
+			.ihl = 5,
+			.version = 4,
+			.ttl = IPDEFTTL,
+			.protocol = IPPROTO_UDP,
+			.daddr = htonl(ENCAP_IP)
+		},
+		.udp = {
+			.dest = htons(ENCAP_PORT),
+		},
+		.gue = {
+			.hlen = hlen,
+			.proto_ctype = proto
+		},
+		.unigue = {
+			.hop_count = hop_count
+		},
+	};
+}
+
+static size_t build_input(const struct test_cfg *test, void *const buf,
+			  const struct tuple *tuple)
+{
+	in_port_t sport = tuple->src.port;
+	encap_headers_t encap;
+	struct iphdr ip;
+	struct ipv6hdr ipv6;
+	struct tcphdr tcp;
+	struct udphdr udp;
+	struct in_addr next_hop;
+	uint8_t *p = buf;
+	int proto;
+
+	proto = IPPROTO_IPIP;
+	if (tuple->family == AF_INET6)
+		proto = IPPROTO_IPV6;
+
+	encap_init(&encap, test->hops == ONE_HOP ? 1 : 0, proto);
+	p = mempcpy(p, &encap, sizeof(encap));
+
+	if (test->hops == ONE_HOP) {
+		next_hop = (struct in_addr){ .s_addr = htonl(0x7f000002) };
+		p = mempcpy(p, &next_hop, sizeof(next_hop));
+	}
+
+	proto = IPPROTO_TCP;
+	if (test->type == UDP)
+		proto = IPPROTO_UDP;
+
+	switch (tuple->family) {
+	case AF_INET:
+		ip = (struct iphdr){
+			.ihl = 5,
+			.version = 4,
+			.ttl = IPDEFTTL,
+			.protocol = proto,
+			.saddr = tuple->src.in_addr.s_addr,
+			.daddr = tuple->dst.in_addr.s_addr,
+		};
+		p = mempcpy(p, &ip, sizeof(ip));
+		break;
+	case AF_INET6:
+		ipv6 = (struct ipv6hdr){
+			.version = 6,
+			.hop_limit = IPDEFTTL,
+			.nexthdr = proto,
+			.saddr = tuple->src.in6_addr,
+			.daddr = tuple->dst.in6_addr,
+		};
+		p = mempcpy(p, &ipv6, sizeof(ipv6));
+		break;
+	default:
+		return 0;
+	}
+
+	if (test->conn == UNKNOWN_CONN)
+		sport--;
+
+	switch (test->type) {
+	case TCP:
+		tcp = (struct tcphdr){
+			.source = sport,
+			.dest = tuple->dst.port,
+		};
+		if (test->flags == SYN)
+			tcp.syn = true;
+		if (test->flags == ACK)
+			tcp.ack = true;
+		p = mempcpy(p, &tcp, sizeof(tcp));
+		break;
+	case UDP:
+		udp = (struct udphdr){
+			.source = sport,
+			.dest = tuple->dst.port,
+		};
+		p = mempcpy(p, &udp, sizeof(udp));
+		break;
+	default:
+		return 0;
+	}
+
+	return (void *)p - buf;
+}
+
+static void close_fds(int *fds, int n)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		if (fds[i] > 0)
+			close(fds[i]);
+}
+
+void test_cls_redirect(void)
+{
+	struct test_cls_redirect *skel = NULL;
+	struct bpf_prog_test_run_attr tattr = {};
+	int families[] = { AF_INET, AF_INET6 };
+	struct sockaddr_storage ss;
+	struct sockaddr *addr;
+	socklen_t slen;
+	int i, j, err;
+
+	int servers[__NR_KIND][ARRAY_SIZE(families)] = {};
+	int conns[__NR_KIND][ARRAY_SIZE(families)] = {};
+	struct tuple tuples[__NR_KIND][ARRAY_SIZE(families)];
+
+	skel = test_cls_redirect__open();
+	if (CHECK_FAIL(!skel))
+		return;
+
+	skel->rodata->ENCAPSULATION_IP = htonl(ENCAP_IP);
+	skel->rodata->ENCAPSULATION_PORT = htons(ENCAP_PORT);
+
+	if (CHECK_FAIL(test_cls_redirect__load(skel)))
+		goto cleanup;
+
+	addr = (struct sockaddr *)&ss;
+	for (i = 0; i < ARRAY_SIZE(families); i++) {
+		slen = prepare_addr(&ss, families[i]);
+		if (CHECK_FAIL(!slen))
+			goto cleanup;
+
+		if (CHECK_FAIL(!set_up_conn(addr, slen, SOCK_DGRAM,
+					    &servers[UDP][i], &conns[UDP][i],
+					    &tuples[UDP][i])))
+			goto cleanup;
+
+		if (CHECK_FAIL(!set_up_conn(addr, slen, SOCK_STREAM,
+					    &servers[TCP][i], &conns[TCP][i],
+					    &tuples[TCP][i])))
+			goto cleanup;
+	}
+
+	tattr.prog_fd = bpf_program__fd(skel->progs.cls_redirect);
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		struct test_cfg *test = &tests[i];
+
+		for (j = 0; j < ARRAY_SIZE(families); j++) {
+			struct tuple *tuple = &tuples[test->type][j];
+			char input[256];
+			char tmp[256];
+
+			test_str(tmp, sizeof(tmp), test, tuple->family);
+			if (!test__start_subtest(tmp))
+				continue;
+
+			tattr.data_out = tmp;
+			tattr.data_size_out = sizeof(tmp);
+
+			tattr.data_in = input;
+			tattr.data_size_in = build_input(test, input, tuple);
+			if (CHECK_FAIL(!tattr.data_size_in))
+				continue;
+
+			err = bpf_prog_test_run_xattr(&tattr);
+			if (CHECK_FAIL(err))
+				continue;
+
+			if (tattr.retval != TC_ACT_REDIRECT) {
+				PRINT_FAIL("expected TC_ACT_REDIRECT, got %d\n",
+					   tattr.retval);
+				continue;
+			}
+
+			switch (test->result) {
+			case ACCEPT:
+				if (CHECK_FAIL(!was_decapsulated(&tattr)))
+					continue;
+				break;
+			case FORWARD:
+				if (CHECK_FAIL(was_decapsulated(&tattr)))
+					continue;
+				break;
+			default:
+				PRINT_FAIL("unknown result %d\n", test->result);
+				continue;
+			}
+		}
+	}
+
+cleanup:
+	test_cls_redirect__destroy(skel);
+	close_fds((int *)servers, sizeof(servers) / sizeof(servers[0][0]));
+	close_fds((int *)conns, sizeof(conns) / sizeof(conns[0][0]));
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c
new file mode 100644
index 000000000000..17bbf76812ca
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "network_helpers.h"
+
+static int verify_ports(int family, int fd,
+			__u16 expected_local, __u16 expected_peer)
+{
+	struct sockaddr_storage addr;
+	socklen_t len = sizeof(addr);
+	__u16 port;
+
+	if (getsockname(fd, (struct sockaddr *)&addr, &len)) {
+		log_err("Failed to get server addr");
+		return -1;
+	}
+
+	if (family == AF_INET)
+		port = ((struct sockaddr_in *)&addr)->sin_port;
+	else
+		port = ((struct sockaddr_in6 *)&addr)->sin6_port;
+
+	if (ntohs(port) != expected_local) {
+		log_err("Unexpected local port %d, expected %d", ntohs(port),
+			expected_local);
+		return -1;
+	}
+
+	if (getpeername(fd, (struct sockaddr *)&addr, &len)) {
+		log_err("Failed to get peer addr");
+		return -1;
+	}
+
+	if (family == AF_INET)
+		port = ((struct sockaddr_in *)&addr)->sin_port;
+	else
+		port = ((struct sockaddr_in6 *)&addr)->sin6_port;
+
+	if (ntohs(port) != expected_peer) {
+		log_err("Unexpected peer port %d, expected %d", ntohs(port),
+			expected_peer);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int run_test(int cgroup_fd, int server_fd, int family, int type)
+{
+	bool v4 = family == AF_INET;
+	__u16 expected_local_port = v4 ? 22222 : 22223;
+	__u16 expected_peer_port = 60000;
+	struct bpf_prog_load_attr attr = {
+		.file = v4 ? "./connect_force_port4.o" :
+			     "./connect_force_port6.o",
+	};
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	int xlate_fd, fd, err;
+	__u32 duration = 0;
+
+	err = bpf_prog_load_xattr(&attr, &obj, &xlate_fd);
+	if (err) {
+		log_err("Failed to load BPF object");
+		return -1;
+	}
+
+	prog = bpf_object__find_program_by_title(obj, v4 ?
+						 "cgroup/connect4" :
+						 "cgroup/connect6");
+	if (CHECK(!prog, "find_prog", "connect prog not found\n")) {
+		err = -EIO;
+		goto close_bpf_object;
+	}
+
+	err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, v4 ?
+			      BPF_CGROUP_INET4_CONNECT :
+			      BPF_CGROUP_INET6_CONNECT, 0);
+	if (err) {
+		log_err("Failed to attach BPF program");
+		goto close_bpf_object;
+	}
+
+	prog = bpf_object__find_program_by_title(obj, v4 ?
+						 "cgroup/getpeername4" :
+						 "cgroup/getpeername6");
+	if (CHECK(!prog, "find_prog", "getpeername prog not found\n")) {
+		err = -EIO;
+		goto close_bpf_object;
+	}
+
+	err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, v4 ?
+			      BPF_CGROUP_INET4_GETPEERNAME :
+			      BPF_CGROUP_INET6_GETPEERNAME, 0);
+	if (err) {
+		log_err("Failed to attach BPF program");
+		goto close_bpf_object;
+	}
+
+	prog = bpf_object__find_program_by_title(obj, v4 ?
+						 "cgroup/getsockname4" :
+						 "cgroup/getsockname6");
+	if (CHECK(!prog, "find_prog", "getsockname prog not found\n")) {
+		err = -EIO;
+		goto close_bpf_object;
+	}
+
+	err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, v4 ?
+			      BPF_CGROUP_INET4_GETSOCKNAME :
+			      BPF_CGROUP_INET6_GETSOCKNAME, 0);
+	if (err) {
+		log_err("Failed to attach BPF program");
+		goto close_bpf_object;
+	}
+
+	fd = connect_to_fd(family, type, server_fd);
+	if (fd < 0) {
+		err = -1;
+		goto close_bpf_object;
+	}
+
+	err = verify_ports(family, fd, expected_local_port,
+			   expected_peer_port);
+	close(fd);
+
+close_bpf_object:
+	bpf_object__close(obj);
+	return err;
+}
+
+void test_connect_force_port(void)
+{
+	int server_fd, cgroup_fd;
+
+	cgroup_fd = test__join_cgroup("/connect_force_port");
+	if (CHECK_FAIL(cgroup_fd < 0))
+		return;
+
+	server_fd = start_server_with_port(AF_INET, SOCK_STREAM, 60123);
+	if (CHECK_FAIL(server_fd < 0))
+		goto close_cgroup_fd;
+	CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET, SOCK_STREAM));
+	close(server_fd);
+
+	server_fd = start_server_with_port(AF_INET6, SOCK_STREAM, 60124);
+	if (CHECK_FAIL(server_fd < 0))
+		goto close_cgroup_fd;
+	CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET6, SOCK_STREAM));
+	close(server_fd);
+
+	server_fd = start_server_with_port(AF_INET, SOCK_DGRAM, 60123);
+	if (CHECK_FAIL(server_fd < 0))
+		goto close_cgroup_fd;
+	CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET, SOCK_DGRAM));
+	close(server_fd);
+
+	server_fd = start_server_with_port(AF_INET6, SOCK_DGRAM, 60124);
+	if (CHECK_FAIL(server_fd < 0))
+		goto close_cgroup_fd;
+	CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET6, SOCK_DGRAM));
+	close(server_fd);
+
+close_cgroup_fd:
+	close(cgroup_fd);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 31e177adbdf1..084ed26a7d78 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -392,7 +392,7 @@ static struct core_reloc_test_case test_cases[] = {
 		.input = STRUCT_TO_CHAR_PTR(core_reloc_existence___minimal) {
 			.a = 42,
 		},
-		.input_len = sizeof(struct core_reloc_existence),
+		.input_len = sizeof(struct core_reloc_existence___minimal),
 		.output = STRUCT_TO_CHAR_PTR(core_reloc_existence_output) {
 			.a_exists = 1,
 			.b_exists = 0,
diff --git a/tools/testing/selftests/bpf/prog_tests/enable_stats.c b/tools/testing/selftests/bpf/prog_tests/enable_stats.c
new file mode 100644
index 000000000000..2cb2085917e7
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/enable_stats.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "test_enable_stats.skel.h"
+
+void test_enable_stats(void)
+{
+	struct test_enable_stats *skel;
+	int stats_fd, err, prog_fd;
+	struct bpf_prog_info info;
+	__u32 info_len = sizeof(info);
+	int duration = 0;
+
+	skel = test_enable_stats__open_and_load();
+	if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n"))
+		return;
+
+	stats_fd = bpf_enable_stats(BPF_STATS_RUN_TIME);
+	if (CHECK(stats_fd < 0, "get_stats_fd", "failed %d\n", errno)) {
+		test_enable_stats__destroy(skel);
+		return;
+	}
+
+	err = test_enable_stats__attach(skel);
+	if (CHECK(err, "attach_raw_tp", "err %d\n", err))
+		goto cleanup;
+
+	test_enable_stats__detach(skel);
+
+	prog_fd = bpf_program__fd(skel->progs.test_enable_stats);
+	memset(&info, 0, info_len);
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	if (CHECK(err, "get_prog_info",
+		  "failed to get bpf_prog_info for fd %d\n", prog_fd))
+		goto cleanup;
+	if (CHECK(info.run_time_ns == 0, "check_stats_enabled",
+		  "failed to enable run_time_ns stats\n"))
+		goto cleanup;
+
+	CHECK(info.run_cnt != skel->bss->count, "check_run_cnt_valid",
+	      "invalid run_cnt stats\n");
+
+cleanup:
+	test_enable_stats__destroy(skel);
+	close(stats_fd);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index c2642517e1d8..a895bfed55db 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
 #include <test_progs.h>
+#include <network_helpers.h>
 
 static void test_fexit_bpf2bpf_common(const char *obj_file,
 				      const char *target_obj_file,
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index 92563898867c..ea14e3ece812 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -1,10 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <network_helpers.h>
 #include <error.h>
 #include <linux/if.h>
 #include <linux/if_tun.h>
 #include <sys/uio.h>
 
+#include "bpf_flow.skel.h"
+
 #ifndef IP_MF
 #define IP_MF 0x2000
 #endif
@@ -100,6 +103,7 @@ struct test {
 
 #define VLAN_HLEN	4
 
+static __u32 duration;
 struct test tests[] = {
 	{
 		.name = "ipv4",
@@ -443,17 +447,130 @@ static int ifup(const char *ifname)
 	return 0;
 }
 
+static int init_prog_array(struct bpf_object *obj, struct bpf_map *prog_array)
+{
+	int i, err, map_fd, prog_fd;
+	struct bpf_program *prog;
+	char prog_name[32];
+
+	map_fd = bpf_map__fd(prog_array);
+	if (map_fd < 0)
+		return -1;
+
+	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+		snprintf(prog_name, sizeof(prog_name), "flow_dissector/%i", i);
+
+		prog = bpf_object__find_program_by_title(obj, prog_name);
+		if (!prog)
+			return -1;
+
+		prog_fd = bpf_program__fd(prog);
+		if (prog_fd < 0)
+			return -1;
+
+		err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY);
+		if (err)
+			return -1;
+	}
+	return 0;
+}
+
+static void run_tests_skb_less(int tap_fd, struct bpf_map *keys)
+{
+	int i, err, keys_fd;
+
+	keys_fd = bpf_map__fd(keys);
+	if (CHECK(keys_fd < 0, "bpf_map__fd", "err %d\n", keys_fd))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		/* Keep in sync with 'flags' from eth_get_headlen. */
+		__u32 eth_get_headlen_flags =
+			BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG;
+		struct bpf_prog_test_run_attr tattr = {};
+		struct bpf_flow_keys flow_keys = {};
+		__u32 key = (__u32)(tests[i].keys.sport) << 16 |
+			    tests[i].keys.dport;
+
+		/* For skb-less case we can't pass input flags; run
+		 * only the tests that have a matching set of flags.
+		 */
+
+		if (tests[i].flags != eth_get_headlen_flags)
+			continue;
+
+		err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt));
+		CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno);
+
+		err = bpf_map_lookup_elem(keys_fd, &key, &flow_keys);
+		CHECK_ATTR(err, tests[i].name, "bpf_map_lookup_elem %d\n", err);
+
+		CHECK_ATTR(err, tests[i].name, "skb-less err %d\n", err);
+		CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys);
+
+		err = bpf_map_delete_elem(keys_fd, &key);
+		CHECK_ATTR(err, tests[i].name, "bpf_map_delete_elem %d\n", err);
+	}
+}
+
+static void test_skb_less_prog_attach(struct bpf_flow *skel, int tap_fd)
+{
+	int err, prog_fd;
+
+	prog_fd = bpf_program__fd(skel->progs._dissect);
+	if (CHECK(prog_fd < 0, "bpf_program__fd", "err %d\n", prog_fd))
+		return;
+
+	err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0);
+	if (CHECK(err, "bpf_prog_attach", "err %d errno %d\n", err, errno))
+		return;
+
+	run_tests_skb_less(tap_fd, skel->maps.last_dissection);
+
+	err = bpf_prog_detach(prog_fd, BPF_FLOW_DISSECTOR);
+	CHECK(err, "bpf_prog_detach", "err %d errno %d\n", err, errno);
+}
+
+static void test_skb_less_link_create(struct bpf_flow *skel, int tap_fd)
+{
+	struct bpf_link *link;
+	int err, net_fd;
+
+	net_fd = open("/proc/self/ns/net", O_RDONLY);
+	if (CHECK(net_fd < 0, "open(/proc/self/ns/net)", "err %d\n", errno))
+		return;
+
+	link = bpf_program__attach_netns(skel->progs._dissect, net_fd);
+	if (CHECK(IS_ERR(link), "attach_netns", "err %ld\n", PTR_ERR(link)))
+		goto out_close;
+
+	run_tests_skb_less(tap_fd, skel->maps.last_dissection);
+
+	err = bpf_link__destroy(link);
+	CHECK(err, "bpf_link__destroy", "err %d\n", err);
+out_close:
+	close(net_fd);
+}
+
 void test_flow_dissector(void)
 {
 	int i, err, prog_fd, keys_fd = -1, tap_fd;
-	struct bpf_object *obj;
-	__u32 duration = 0;
+	struct bpf_flow *skel;
 
-	err = bpf_flow_load(&obj, "./bpf_flow.o", "flow_dissector",
-			    "jmp_table", "last_dissection", &prog_fd, &keys_fd);
-	if (CHECK_FAIL(err))
+	skel = bpf_flow__open_and_load();
+	if (CHECK(!skel, "skel", "failed to open/load skeleton\n"))
 		return;
 
+	prog_fd = bpf_program__fd(skel->progs._dissect);
+	if (CHECK(prog_fd < 0, "bpf_program__fd", "err %d\n", prog_fd))
+		goto out_destroy_skel;
+	keys_fd = bpf_map__fd(skel->maps.last_dissection);
+	if (CHECK(keys_fd < 0, "bpf_map__fd", "err %d\n", keys_fd))
+		goto out_destroy_skel;
+	err = init_prog_array(skel->obj, skel->maps.jmp_table);
+	if (CHECK(err, "init_prog_array", "err %d\n", err))
+		goto out_destroy_skel;
+
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		struct bpf_flow_keys flow_keys;
 		struct bpf_prog_test_run_attr tattr = {
@@ -486,43 +603,17 @@ void test_flow_dissector(void)
 	 * via BPF map in this case.
 	 */
 
-	err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0);
-	CHECK(err, "bpf_prog_attach", "err %d errno %d\n", err, errno);
-
 	tap_fd = create_tap("tap0");
 	CHECK(tap_fd < 0, "create_tap", "tap_fd %d errno %d\n", tap_fd, errno);
 	err = ifup("tap0");
 	CHECK(err, "ifup", "err %d errno %d\n", err, errno);
 
-	for (i = 0; i < ARRAY_SIZE(tests); i++) {
-		/* Keep in sync with 'flags' from eth_get_headlen. */
-		__u32 eth_get_headlen_flags =
-			BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG;
-		struct bpf_prog_test_run_attr tattr = {};
-		struct bpf_flow_keys flow_keys = {};
-		__u32 key = (__u32)(tests[i].keys.sport) << 16 |
-			    tests[i].keys.dport;
-
-		/* For skb-less case we can't pass input flags; run
-		 * only the tests that have a matching set of flags.
-		 */
-
-		if (tests[i].flags != eth_get_headlen_flags)
-			continue;
-
-		err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt));
-		CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno);
-
-		err = bpf_map_lookup_elem(keys_fd, &key, &flow_keys);
-		CHECK_ATTR(err, tests[i].name, "bpf_map_lookup_elem %d\n", err);
-
-		CHECK_ATTR(err, tests[i].name, "skb-less err %d\n", err);
-		CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys);
-
-		err = bpf_map_delete_elem(keys_fd, &key);
-		CHECK_ATTR(err, tests[i].name, "bpf_map_delete_elem %d\n", err);
-	}
+	/* Test direct prog attachment */
+	test_skb_less_prog_attach(skel, tap_fd);
+	/* Test indirect prog attachment via link */
+	test_skb_less_link_create(skel, tap_fd);
 
-	bpf_prog_detach(prog_fd, BPF_FLOW_DISSECTOR);
-	bpf_object__close(obj);
+	close(tap_fd);
+out_destroy_skel:
+	bpf_flow__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c
index dc5ef155ec28..0e8a4d2f023d 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <network_helpers.h>
 
 void test_flow_dissector_load_bytes(void)
 {
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
index 1f51ba66b98b..15cb554a66d8 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
@@ -11,6 +11,7 @@
 #include <fcntl.h>
 #include <sched.h>
 #include <stdbool.h>
+#include <sys/stat.h>
 #include <unistd.h>
 
 #include <linux/bpf.h>
@@ -18,21 +19,30 @@
 
 #include "test_progs.h"
 
-static bool is_attached(int netns)
+static int init_net = -1;
+
+static __u32 query_attached_prog_id(int netns)
 {
-	__u32 cnt;
+	__u32 prog_ids[1] = {};
+	__u32 prog_cnt = ARRAY_SIZE(prog_ids);
 	int err;
 
-	err = bpf_prog_query(netns, BPF_FLOW_DISSECTOR, 0, NULL, NULL, &cnt);
+	err = bpf_prog_query(netns, BPF_FLOW_DISSECTOR, 0, NULL,
+			     prog_ids, &prog_cnt);
 	if (CHECK_FAIL(err)) {
 		perror("bpf_prog_query");
-		return true; /* fail-safe */
+		return 0;
 	}
 
-	return cnt > 0;
+	return prog_cnt == 1 ? prog_ids[0] : 0;
+}
+
+static bool prog_is_attached(int netns)
+{
+	return query_attached_prog_id(netns) > 0;
 }
 
-static int load_prog(void)
+static int load_prog(enum bpf_prog_type type)
 {
 	struct bpf_insn prog[] = {
 		BPF_MOV64_IMM(BPF_REG_0, BPF_OK),
@@ -40,61 +50,566 @@ static int load_prog(void)
 	};
 	int fd;
 
-	fd = bpf_load_program(BPF_PROG_TYPE_FLOW_DISSECTOR, prog,
-			      ARRAY_SIZE(prog), "GPL", 0, NULL, 0);
+	fd = bpf_load_program(type, prog, ARRAY_SIZE(prog), "GPL", 0, NULL, 0);
 	if (CHECK_FAIL(fd < 0))
 		perror("bpf_load_program");
 
 	return fd;
 }
 
-static void do_flow_dissector_reattach(void)
+static __u32 query_prog_id(int prog)
 {
-	int prog_fd[2] = { -1, -1 };
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
 	int err;
 
-	prog_fd[0] = load_prog();
-	if (prog_fd[0] < 0)
-		return;
+	err = bpf_obj_get_info_by_fd(prog, &info, &info_len);
+	if (CHECK_FAIL(err || info_len != sizeof(info))) {
+		perror("bpf_obj_get_info_by_fd");
+		return 0;
+	}
 
-	prog_fd[1] = load_prog();
-	if (prog_fd[1] < 0)
-		goto out_close;
+	return info.id;
+}
+
+static int unshare_net(int old_net)
+{
+	int err, new_net;
 
-	err = bpf_prog_attach(prog_fd[0], 0, BPF_FLOW_DISSECTOR, 0);
+	err = unshare(CLONE_NEWNET);
 	if (CHECK_FAIL(err)) {
-		perror("bpf_prog_attach-0");
-		goto out_close;
+		perror("unshare(CLONE_NEWNET)");
+		return -1;
+	}
+	new_net = open("/proc/self/ns/net", O_RDONLY);
+	if (CHECK_FAIL(new_net < 0)) {
+		perror("open(/proc/self/ns/net)");
+		setns(old_net, CLONE_NEWNET);
+		return -1;
 	}
+	return new_net;
+}
+
+static void test_prog_attach_prog_attach(int netns, int prog1, int prog2)
+{
+	int err;
+
+	err = bpf_prog_attach(prog1, 0, BPF_FLOW_DISSECTOR, 0);
+	if (CHECK_FAIL(err)) {
+		perror("bpf_prog_attach(prog1)");
+		return;
+	}
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
 
 	/* Expect success when attaching a different program */
-	err = bpf_prog_attach(prog_fd[1], 0, BPF_FLOW_DISSECTOR, 0);
+	err = bpf_prog_attach(prog2, 0, BPF_FLOW_DISSECTOR, 0);
 	if (CHECK_FAIL(err)) {
-		perror("bpf_prog_attach-1");
+		perror("bpf_prog_attach(prog2) #1");
 		goto out_detach;
 	}
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog2));
 
 	/* Expect failure when attaching the same program twice */
-	err = bpf_prog_attach(prog_fd[1], 0, BPF_FLOW_DISSECTOR, 0);
+	err = bpf_prog_attach(prog2, 0, BPF_FLOW_DISSECTOR, 0);
 	if (CHECK_FAIL(!err || errno != EINVAL))
-		perror("bpf_prog_attach-2");
+		perror("bpf_prog_attach(prog2) #2");
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog2));
 
 out_detach:
 	err = bpf_prog_detach(0, BPF_FLOW_DISSECTOR);
 	if (CHECK_FAIL(err))
 		perror("bpf_prog_detach");
+	CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_link_create_link_create(int netns, int prog1, int prog2)
+{
+	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts);
+	int link1, link2;
+
+	link1 = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &opts);
+	if (CHECK_FAIL(link < 0)) {
+		perror("bpf_link_create(prog1)");
+		return;
+	}
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	/* Expect failure creating link when another link exists */
+	errno = 0;
+	link2 = bpf_link_create(prog2, netns, BPF_FLOW_DISSECTOR, &opts);
+	if (CHECK_FAIL(link2 != -1 || errno != E2BIG))
+		perror("bpf_prog_attach(prog2) expected E2BIG");
+	if (link2 != -1)
+		close(link2);
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	close(link1);
+	CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_prog_attach_link_create(int netns, int prog1, int prog2)
+{
+	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts);
+	int err, link;
+
+	err = bpf_prog_attach(prog1, -1, BPF_FLOW_DISSECTOR, 0);
+	if (CHECK_FAIL(err)) {
+		perror("bpf_prog_attach(prog1)");
+		return;
+	}
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	/* Expect failure creating link when prog attached */
+	errno = 0;
+	link = bpf_link_create(prog2, netns, BPF_FLOW_DISSECTOR, &opts);
+	if (CHECK_FAIL(link != -1 || errno != EEXIST))
+		perror("bpf_link_create(prog2) expected EEXIST");
+	if (link != -1)
+		close(link);
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	err = bpf_prog_detach(-1, BPF_FLOW_DISSECTOR);
+	if (CHECK_FAIL(err))
+		perror("bpf_prog_detach");
+	CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_link_create_prog_attach(int netns, int prog1, int prog2)
+{
+	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts);
+	int err, link;
+
+	link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &opts);
+	if (CHECK_FAIL(link < 0)) {
+		perror("bpf_link_create(prog1)");
+		return;
+	}
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	/* Expect failure attaching prog when link exists */
+	errno = 0;
+	err = bpf_prog_attach(prog2, -1, BPF_FLOW_DISSECTOR, 0);
+	if (CHECK_FAIL(!err || errno != EEXIST))
+		perror("bpf_prog_attach(prog2) expected EEXIST");
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	close(link);
+	CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_link_create_prog_detach(int netns, int prog1, int prog2)
+{
+	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts);
+	int err, link;
+
+	link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &opts);
+	if (CHECK_FAIL(link < 0)) {
+		perror("bpf_link_create(prog1)");
+		return;
+	}
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	/* Expect failure detaching prog when link exists */
+	errno = 0;
+	err = bpf_prog_detach(-1, BPF_FLOW_DISSECTOR);
+	if (CHECK_FAIL(!err || errno != EINVAL))
+		perror("bpf_prog_detach expected EINVAL");
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	close(link);
+	CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_prog_attach_detach_query(int netns, int prog1, int prog2)
+{
+	int err;
+
+	err = bpf_prog_attach(prog1, 0, BPF_FLOW_DISSECTOR, 0);
+	if (CHECK_FAIL(err)) {
+		perror("bpf_prog_attach(prog1)");
+		return;
+	}
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	err = bpf_prog_detach(0, BPF_FLOW_DISSECTOR);
+	if (CHECK_FAIL(err)) {
+		perror("bpf_prog_detach");
+		return;
+	}
+
+	/* Expect no prog attached after successful detach */
+	CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_link_create_close_query(int netns, int prog1, int prog2)
+{
+	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts);
+	int link;
+
+	link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &opts);
+	if (CHECK_FAIL(link < 0)) {
+		perror("bpf_link_create(prog1)");
+		return;
+	}
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	close(link);
+	/* Expect no prog attached after closing last link FD */
+	CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_link_update_no_old_prog(int netns, int prog1, int prog2)
+{
+	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts);
+	DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts);
+	int err, link;
+
+	link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts);
+	if (CHECK_FAIL(link < 0)) {
+		perror("bpf_link_create(prog1)");
+		return;
+	}
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	/* Expect success replacing the prog when old prog not specified */
+	update_opts.flags = 0;
+	update_opts.old_prog_fd = 0;
+	err = bpf_link_update(link, prog2, &update_opts);
+	if (CHECK_FAIL(err))
+		perror("bpf_link_update");
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog2));
+
+	close(link);
+	CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_link_update_replace_old_prog(int netns, int prog1, int prog2)
+{
+	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts);
+	DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts);
+	int err, link;
 
+	link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts);
+	if (CHECK_FAIL(link < 0)) {
+		perror("bpf_link_create(prog1)");
+		return;
+	}
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	/* Expect success F_REPLACE and old prog specified to succeed */
+	update_opts.flags = BPF_F_REPLACE;
+	update_opts.old_prog_fd = prog1;
+	err = bpf_link_update(link, prog2, &update_opts);
+	if (CHECK_FAIL(err))
+		perror("bpf_link_update");
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog2));
+
+	close(link);
+	CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_link_update_invalid_opts(int netns, int prog1, int prog2)
+{
+	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts);
+	DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts);
+	int err, link;
+
+	link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts);
+	if (CHECK_FAIL(link < 0)) {
+		perror("bpf_link_create(prog1)");
+		return;
+	}
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	/* Expect update to fail w/ old prog FD but w/o F_REPLACE*/
+	errno = 0;
+	update_opts.flags = 0;
+	update_opts.old_prog_fd = prog1;
+	err = bpf_link_update(link, prog2, &update_opts);
+	if (CHECK_FAIL(!err || errno != EINVAL)) {
+		perror("bpf_link_update expected EINVAL");
+		goto out_close;
+	}
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	/* Expect update to fail on old prog FD mismatch */
+	errno = 0;
+	update_opts.flags = BPF_F_REPLACE;
+	update_opts.old_prog_fd = prog2;
+	err = bpf_link_update(link, prog2, &update_opts);
+	if (CHECK_FAIL(!err || errno != EPERM)) {
+		perror("bpf_link_update expected EPERM");
+		goto out_close;
+	}
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	/* Expect update to fail for invalid old prog FD */
+	errno = 0;
+	update_opts.flags = BPF_F_REPLACE;
+	update_opts.old_prog_fd = -1;
+	err = bpf_link_update(link, prog2, &update_opts);
+	if (CHECK_FAIL(!err || errno != EBADF)) {
+		perror("bpf_link_update expected EBADF");
+		goto out_close;
+	}
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	/* Expect update to fail with invalid flags */
+	errno = 0;
+	update_opts.flags = BPF_F_ALLOW_MULTI;
+	update_opts.old_prog_fd = 0;
+	err = bpf_link_update(link, prog2, &update_opts);
+	if (CHECK_FAIL(!err || errno != EINVAL))
+		perror("bpf_link_update expected EINVAL");
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+out_close:
+	close(link);
+	CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_link_update_invalid_prog(int netns, int prog1, int prog2)
+{
+	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts);
+	DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts);
+	int err, link, prog3;
+
+	link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts);
+	if (CHECK_FAIL(link < 0)) {
+		perror("bpf_link_create(prog1)");
+		return;
+	}
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	/* Expect failure when new prog FD is not valid */
+	errno = 0;
+	update_opts.flags = 0;
+	update_opts.old_prog_fd = 0;
+	err = bpf_link_update(link, -1, &update_opts);
+	if (CHECK_FAIL(!err || errno != EBADF)) {
+		perror("bpf_link_update expected EINVAL");
+		goto out_close_link;
+	}
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	prog3 = load_prog(BPF_PROG_TYPE_SOCKET_FILTER);
+	if (prog3 < 0)
+		goto out_close_link;
+
+	/* Expect failure when new prog FD type doesn't match */
+	errno = 0;
+	update_opts.flags = 0;
+	update_opts.old_prog_fd = 0;
+	err = bpf_link_update(link, prog3, &update_opts);
+	if (CHECK_FAIL(!err || errno != EINVAL))
+		perror("bpf_link_update expected EINVAL");
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	close(prog3);
+out_close_link:
+	close(link);
+	CHECK_FAIL(prog_is_attached(netns));
+}
+
+static void test_link_update_netns_gone(int netns, int prog1, int prog2)
+{
+	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts);
+	DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts);
+	int err, link, old_net;
+
+	old_net = netns;
+	netns = unshare_net(old_net);
+	if (netns < 0)
+		return;
+
+	link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts);
+	if (CHECK_FAIL(link < 0)) {
+		perror("bpf_link_create(prog1)");
+		return;
+	}
+	CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1));
+
+	close(netns);
+	err = setns(old_net, CLONE_NEWNET);
+	if (CHECK_FAIL(err)) {
+		perror("setns(CLONE_NEWNET)");
+		close(link);
+		return;
+	}
+
+	/* Expect failure when netns destroyed */
+	errno = 0;
+	update_opts.flags = 0;
+	update_opts.old_prog_fd = 0;
+	err = bpf_link_update(link, prog2, &update_opts);
+	if (CHECK_FAIL(!err || errno != ENOLINK))
+		perror("bpf_link_update");
+
+	close(link);
+}
+
+static void test_link_get_info(int netns, int prog1, int prog2)
+{
+	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, create_opts);
+	DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts);
+	struct bpf_link_info info = {};
+	struct stat netns_stat = {};
+	__u32 info_len, link_id;
+	int err, link, old_net;
+
+	old_net = netns;
+	netns = unshare_net(old_net);
+	if (netns < 0)
+		return;
+
+	err = fstat(netns, &netns_stat);
+	if (CHECK_FAIL(err)) {
+		perror("stat(netns)");
+		goto out_resetns;
+	}
+
+	link = bpf_link_create(prog1, netns, BPF_FLOW_DISSECTOR, &create_opts);
+	if (CHECK_FAIL(link < 0)) {
+		perror("bpf_link_create(prog1)");
+		goto out_resetns;
+	}
+
+	info_len = sizeof(info);
+	err = bpf_obj_get_info_by_fd(link, &info, &info_len);
+	if (CHECK_FAIL(err)) {
+		perror("bpf_obj_get_info");
+		goto out_unlink;
+	}
+	CHECK_FAIL(info_len != sizeof(info));
+
+	/* Expect link info to be sane and match prog and netns details */
+	CHECK_FAIL(info.type != BPF_LINK_TYPE_NETNS);
+	CHECK_FAIL(info.id == 0);
+	CHECK_FAIL(info.prog_id != query_prog_id(prog1));
+	CHECK_FAIL(info.netns.netns_ino != netns_stat.st_ino);
+	CHECK_FAIL(info.netns.attach_type != BPF_FLOW_DISSECTOR);
+
+	update_opts.flags = 0;
+	update_opts.old_prog_fd = 0;
+	err = bpf_link_update(link, prog2, &update_opts);
+	if (CHECK_FAIL(err)) {
+		perror("bpf_link_update(prog2)");
+		goto out_unlink;
+	}
+
+	link_id = info.id;
+	info_len = sizeof(info);
+	err = bpf_obj_get_info_by_fd(link, &info, &info_len);
+	if (CHECK_FAIL(err)) {
+		perror("bpf_obj_get_info");
+		goto out_unlink;
+	}
+	CHECK_FAIL(info_len != sizeof(info));
+
+	/* Expect no info change after update except in prog id */
+	CHECK_FAIL(info.type != BPF_LINK_TYPE_NETNS);
+	CHECK_FAIL(info.id != link_id);
+	CHECK_FAIL(info.prog_id != query_prog_id(prog2));
+	CHECK_FAIL(info.netns.netns_ino != netns_stat.st_ino);
+	CHECK_FAIL(info.netns.attach_type != BPF_FLOW_DISSECTOR);
+
+	/* Leave netns link is attached to and close last FD to it */
+	err = setns(old_net, CLONE_NEWNET);
+	if (CHECK_FAIL(err)) {
+		perror("setns(NEWNET)");
+		goto out_unlink;
+	}
+	close(netns);
+	old_net = -1;
+	netns = -1;
+
+	info_len = sizeof(info);
+	err = bpf_obj_get_info_by_fd(link, &info, &info_len);
+	if (CHECK_FAIL(err)) {
+		perror("bpf_obj_get_info");
+		goto out_unlink;
+	}
+	CHECK_FAIL(info_len != sizeof(info));
+
+	/* Expect netns_ino to change to 0 */
+	CHECK_FAIL(info.type != BPF_LINK_TYPE_NETNS);
+	CHECK_FAIL(info.id != link_id);
+	CHECK_FAIL(info.prog_id != query_prog_id(prog2));
+	CHECK_FAIL(info.netns.netns_ino != 0);
+	CHECK_FAIL(info.netns.attach_type != BPF_FLOW_DISSECTOR);
+
+out_unlink:
+	close(link);
+out_resetns:
+	if (old_net != -1)
+		setns(old_net, CLONE_NEWNET);
+	if (netns != -1)
+		close(netns);
+}
+
+static void run_tests(int netns)
+{
+	struct test {
+		const char *test_name;
+		void (*test_func)(int netns, int prog1, int prog2);
+	} tests[] = {
+		{ "prog attach, prog attach",
+		  test_prog_attach_prog_attach },
+		{ "link create, link create",
+		  test_link_create_link_create },
+		{ "prog attach, link create",
+		  test_prog_attach_link_create },
+		{ "link create, prog attach",
+		  test_link_create_prog_attach },
+		{ "link create, prog detach",
+		  test_link_create_prog_detach },
+		{ "prog attach, detach, query",
+		  test_prog_attach_detach_query },
+		{ "link create, close, query",
+		  test_link_create_close_query },
+		{ "link update no old prog",
+		  test_link_update_no_old_prog },
+		{ "link update with replace old prog",
+		  test_link_update_replace_old_prog },
+		{ "link update invalid opts",
+		  test_link_update_invalid_opts },
+		{ "link update invalid prog",
+		  test_link_update_invalid_prog },
+		{ "link update netns gone",
+		  test_link_update_netns_gone },
+		{ "link get info",
+		  test_link_get_info },
+	};
+	int i, progs[2] = { -1, -1 };
+	char test_name[80];
+
+	for (i = 0; i < ARRAY_SIZE(progs); i++) {
+		progs[i] = load_prog(BPF_PROG_TYPE_FLOW_DISSECTOR);
+		if (progs[i] < 0)
+			goto out_close;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		snprintf(test_name, sizeof(test_name),
+			 "flow dissector %s%s",
+			 tests[i].test_name,
+			 netns == init_net ? " (init_net)" : "");
+		if (test__start_subtest(test_name))
+			tests[i].test_func(netns, progs[0], progs[1]);
+	}
 out_close:
-	close(prog_fd[1]);
-	close(prog_fd[0]);
+	for (i = 0; i < ARRAY_SIZE(progs); i++) {
+		if (progs[i] != -1)
+			CHECK_FAIL(close(progs[i]));
+	}
 }
 
 void test_flow_dissector_reattach(void)
 {
-	int init_net, self_net, err;
+	int err, new_net, saved_net;
 
-	self_net = open("/proc/self/ns/net", O_RDONLY);
-	if (CHECK_FAIL(self_net < 0)) {
+	saved_net = open("/proc/self/ns/net", O_RDONLY);
+	if (CHECK_FAIL(saved_net < 0)) {
 		perror("open(/proc/self/ns/net");
 		return;
 	}
@@ -111,30 +626,29 @@ void test_flow_dissector_reattach(void)
 		goto out_close;
 	}
 
-	if (is_attached(init_net)) {
+	if (prog_is_attached(init_net)) {
 		test__skip();
 		printf("Can't test with flow dissector attached to init_net\n");
 		goto out_setns;
 	}
 
 	/* First run tests in root network namespace */
-	do_flow_dissector_reattach();
+	run_tests(init_net);
 
 	/* Then repeat tests in a non-root namespace */
-	err = unshare(CLONE_NEWNET);
-	if (CHECK_FAIL(err)) {
-		perror("unshare(CLONE_NEWNET)");
+	new_net = unshare_net(init_net);
+	if (new_net < 0)
 		goto out_setns;
-	}
-	do_flow_dissector_reattach();
+	run_tests(new_net);
+	close(new_net);
 
 out_setns:
 	/* Move back to netns we started in. */
-	err = setns(self_net, CLONE_NEWNET);
+	err = setns(saved_net, CLONE_NEWNET);
 	if (CHECK_FAIL(err))
 		perror("setns(/proc/self/ns/net)");
 
 out_close:
 	close(init_net);
-	close(self_net);
+	close(saved_net);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/global_data.c b/tools/testing/selftests/bpf/prog_tests/global_data.c
index c680926fce73..e3cb62b0a110 100644
--- a/tools/testing/selftests/bpf/prog_tests/global_data.c
+++ b/tools/testing/selftests/bpf/prog_tests/global_data.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <network_helpers.h>
 
 static void test_global_data_number(struct bpf_object *obj, __u32 duration)
 {
diff --git a/tools/testing/selftests/bpf/test_hashmap.c b/tools/testing/selftests/bpf/prog_tests/hashmap.c
index c490e012c23f..428d488830c6 100644
--- a/tools/testing/selftests/bpf/test_hashmap.c
+++ b/tools/testing/selftests/bpf/prog_tests/hashmap.c
@@ -5,26 +5,17 @@
  *
  * Copyright (c) 2019 Facebook
  */
-#include <stdio.h>
-#include <errno.h>
-#include <linux/err.h>
+#include "test_progs.h"
 #include "bpf/hashmap.h"
 
-#define CHECK(condition, format...) ({					\
-	int __ret = !!(condition);					\
-	if (__ret) {							\
-		fprintf(stderr, "%s:%d:FAIL ", __func__, __LINE__);	\
-		fprintf(stderr, format);				\
-	}								\
-	__ret;								\
-})
+static int duration = 0;
 
-size_t hash_fn(const void *k, void *ctx)
+static size_t hash_fn(const void *k, void *ctx)
 {
 	return (long)k;
 }
 
-bool equal_fn(const void *a, const void *b, void *ctx)
+static bool equal_fn(const void *a, const void *b, void *ctx)
 {
 	return (long)a == (long)b;
 }
@@ -49,53 +40,55 @@ static inline size_t exp_cap(size_t sz)
 
 #define ELEM_CNT 62
 
-int test_hashmap_generic(void)
+static void test_hashmap_generic(void)
 {
 	struct hashmap_entry *entry, *tmp;
 	int err, bkt, found_cnt, i;
 	long long found_msk;
 	struct hashmap *map;
 
-	fprintf(stderr, "%s: ", __func__);
-
 	map = hashmap__new(hash_fn, equal_fn, NULL);
-	if (CHECK(IS_ERR(map), "failed to create map: %ld\n", PTR_ERR(map)))
-		return 1;
+	if (CHECK(IS_ERR(map), "hashmap__new",
+		  "failed to create map: %ld\n", PTR_ERR(map)))
+		return;
 
 	for (i = 0; i < ELEM_CNT; i++) {
 		const void *oldk, *k = (const void *)(long)i;
 		void *oldv, *v = (void *)(long)(1024 + i);
 
 		err = hashmap__update(map, k, v, &oldk, &oldv);
-		if (CHECK(err != -ENOENT, "unexpected result: %d\n", err))
-			return 1;
+		if (CHECK(err != -ENOENT, "hashmap__update",
+			  "unexpected result: %d\n", err))
+			goto cleanup;
 
 		if (i % 2) {
 			err = hashmap__add(map, k, v);
 		} else {
 			err = hashmap__set(map, k, v, &oldk, &oldv);
-			if (CHECK(oldk != NULL || oldv != NULL,
+			if (CHECK(oldk != NULL || oldv != NULL, "check_kv",
 				  "unexpected k/v: %p=%p\n", oldk, oldv))
-				return 1;
+				goto cleanup;
 		}
 
-		if (CHECK(err, "failed to add k/v %ld = %ld: %d\n",
+		if (CHECK(err, "elem_add", "failed to add k/v %ld = %ld: %d\n",
 			       (long)k, (long)v, err))
-			return 1;
+			goto cleanup;
 
-		if (CHECK(!hashmap__find(map, k, &oldv),
+		if (CHECK(!hashmap__find(map, k, &oldv), "elem_find",
 			  "failed to find key %ld\n", (long)k))
-			return 1;
-		if (CHECK(oldv != v, "found value is wrong: %ld\n", (long)oldv))
-			return 1;
+			goto cleanup;
+		if (CHECK(oldv != v, "elem_val",
+			  "found value is wrong: %ld\n", (long)oldv))
+			goto cleanup;
 	}
 
-	if (CHECK(hashmap__size(map) != ELEM_CNT,
+	if (CHECK(hashmap__size(map) != ELEM_CNT, "hashmap__size",
 		  "invalid map size: %zu\n", hashmap__size(map)))
-		return 1;
+		goto cleanup;
 	if (CHECK(hashmap__capacity(map) != exp_cap(hashmap__size(map)),
+		  "hashmap_cap",
 		  "unexpected map capacity: %zu\n", hashmap__capacity(map)))
-		return 1;
+		goto cleanup;
 
 	found_msk = 0;
 	hashmap__for_each_entry(map, entry, bkt) {
@@ -103,42 +96,47 @@ int test_hashmap_generic(void)
 		long v = (long)entry->value;
 
 		found_msk |= 1ULL << k;
-		if (CHECK(v - k != 1024, "invalid k/v pair: %ld = %ld\n", k, v))
-			return 1;
+		if (CHECK(v - k != 1024, "check_kv",
+			  "invalid k/v pair: %ld = %ld\n", k, v))
+			goto cleanup;
 	}
-	if (CHECK(found_msk != (1ULL << ELEM_CNT) - 1,
+	if (CHECK(found_msk != (1ULL << ELEM_CNT) - 1, "elem_cnt",
 		  "not all keys iterated: %llx\n", found_msk))
-		return 1;
+		goto cleanup;
 
 	for (i = 0; i < ELEM_CNT; i++) {
 		const void *oldk, *k = (const void *)(long)i;
 		void *oldv, *v = (void *)(long)(256 + i);
 
 		err = hashmap__add(map, k, v);
-		if (CHECK(err != -EEXIST, "unexpected add result: %d\n", err))
-			return 1;
+		if (CHECK(err != -EEXIST, "hashmap__add",
+			  "unexpected add result: %d\n", err))
+			goto cleanup;
 
 		if (i % 2)
 			err = hashmap__update(map, k, v, &oldk, &oldv);
 		else
 			err = hashmap__set(map, k, v, &oldk, &oldv);
 
-		if (CHECK(err, "failed to update k/v %ld = %ld: %d\n",
-			       (long)k, (long)v, err))
-			return 1;
-		if (CHECK(!hashmap__find(map, k, &oldv),
+		if (CHECK(err, "elem_upd",
+			  "failed to update k/v %ld = %ld: %d\n",
+			  (long)k, (long)v, err))
+			goto cleanup;
+		if (CHECK(!hashmap__find(map, k, &oldv), "elem_find",
 			  "failed to find key %ld\n", (long)k))
-			return 1;
-		if (CHECK(oldv != v, "found value is wrong: %ld\n", (long)oldv))
-			return 1;
+			goto cleanup;
+		if (CHECK(oldv != v, "elem_val",
+			  "found value is wrong: %ld\n", (long)oldv))
+			goto cleanup;
 	}
 
-	if (CHECK(hashmap__size(map) != ELEM_CNT,
+	if (CHECK(hashmap__size(map) != ELEM_CNT, "hashmap__size",
 		  "invalid updated map size: %zu\n", hashmap__size(map)))
-		return 1;
+		goto cleanup;
 	if (CHECK(hashmap__capacity(map) != exp_cap(hashmap__size(map)),
+		  "hashmap__capacity",
 		  "unexpected map capacity: %zu\n", hashmap__capacity(map)))
-		return 1;
+		goto cleanup;
 
 	found_msk = 0;
 	hashmap__for_each_entry_safe(map, entry, tmp, bkt) {
@@ -146,20 +144,21 @@ int test_hashmap_generic(void)
 		long v = (long)entry->value;
 
 		found_msk |= 1ULL << k;
-		if (CHECK(v - k != 256,
+		if (CHECK(v - k != 256, "elem_check",
 			  "invalid updated k/v pair: %ld = %ld\n", k, v))
-			return 1;
+			goto cleanup;
 	}
-	if (CHECK(found_msk != (1ULL << ELEM_CNT) - 1,
+	if (CHECK(found_msk != (1ULL << ELEM_CNT) - 1, "elem_cnt",
 		  "not all keys iterated after update: %llx\n", found_msk))
-		return 1;
+		goto cleanup;
 
 	found_cnt = 0;
 	hashmap__for_each_key_entry(map, entry, (void *)0) {
 		found_cnt++;
 	}
-	if (CHECK(!found_cnt, "didn't find any entries for key 0\n"))
-		return 1;
+	if (CHECK(!found_cnt, "found_cnt",
+		  "didn't find any entries for key 0\n"))
+		goto cleanup;
 
 	found_msk = 0;
 	found_cnt = 0;
@@ -173,30 +172,31 @@ int test_hashmap_generic(void)
 		found_cnt++;
 		found_msk |= 1ULL << (long)k;
 
-		if (CHECK(!hashmap__delete(map, k, &oldk, &oldv),
+		if (CHECK(!hashmap__delete(map, k, &oldk, &oldv), "elem_del",
 			  "failed to delete k/v %ld = %ld\n",
 			  (long)k, (long)v))
-			return 1;
-		if (CHECK(oldk != k || oldv != v,
+			goto cleanup;
+		if (CHECK(oldk != k || oldv != v, "check_old",
 			  "invalid deleted k/v: expected %ld = %ld, got %ld = %ld\n",
 			  (long)k, (long)v, (long)oldk, (long)oldv))
-			return 1;
-		if (CHECK(hashmap__delete(map, k, &oldk, &oldv),
+			goto cleanup;
+		if (CHECK(hashmap__delete(map, k, &oldk, &oldv), "elem_del",
 			  "unexpectedly deleted k/v %ld = %ld\n",
 			  (long)oldk, (long)oldv))
-			return 1;
+			goto cleanup;
 	}
 
-	if (CHECK(!found_cnt || !found_msk,
+	if (CHECK(!found_cnt || !found_msk, "found_entries",
 		  "didn't delete any key entries\n"))
-		return 1;
-	if (CHECK(hashmap__size(map) != ELEM_CNT - found_cnt,
+		goto cleanup;
+	if (CHECK(hashmap__size(map) != ELEM_CNT - found_cnt, "elem_cnt",
 		  "invalid updated map size (already deleted: %d): %zu\n",
 		  found_cnt, hashmap__size(map)))
-		return 1;
+		goto cleanup;
 	if (CHECK(hashmap__capacity(map) != exp_cap(hashmap__size(map)),
+		  "hashmap__capacity",
 		  "unexpected map capacity: %zu\n", hashmap__capacity(map)))
-		return 1;
+		goto cleanup;
 
 	hashmap__for_each_entry_safe(map, entry, tmp, bkt) {
 		const void *oldk, *k;
@@ -208,53 +208,56 @@ int test_hashmap_generic(void)
 		found_cnt++;
 		found_msk |= 1ULL << (long)k;
 
-		if (CHECK(!hashmap__delete(map, k, &oldk, &oldv),
+		if (CHECK(!hashmap__delete(map, k, &oldk, &oldv), "elem_del",
 			  "failed to delete k/v %ld = %ld\n",
 			  (long)k, (long)v))
-			return 1;
-		if (CHECK(oldk != k || oldv != v,
+			goto cleanup;
+		if (CHECK(oldk != k || oldv != v, "elem_check",
 			  "invalid old k/v: expect %ld = %ld, got %ld = %ld\n",
 			  (long)k, (long)v, (long)oldk, (long)oldv))
-			return 1;
-		if (CHECK(hashmap__delete(map, k, &oldk, &oldv),
+			goto cleanup;
+		if (CHECK(hashmap__delete(map, k, &oldk, &oldv), "elem_del",
 			  "unexpectedly deleted k/v %ld = %ld\n",
 			  (long)k, (long)v))
-			return 1;
+			goto cleanup;
 	}
 
 	if (CHECK(found_cnt != ELEM_CNT || found_msk != (1ULL << ELEM_CNT) - 1,
+		  "found_cnt",
 		  "not all keys were deleted: found_cnt:%d, found_msk:%llx\n",
 		  found_cnt, found_msk))
-		return 1;
-	if (CHECK(hashmap__size(map) != 0,
+		goto cleanup;
+	if (CHECK(hashmap__size(map) != 0, "hashmap__size",
 		  "invalid updated map size (already deleted: %d): %zu\n",
 		  found_cnt, hashmap__size(map)))
-		return 1;
+		goto cleanup;
 
 	found_cnt = 0;
 	hashmap__for_each_entry(map, entry, bkt) {
-		CHECK(false, "unexpected map entries left: %ld = %ld\n",
-			     (long)entry->key, (long)entry->value);
-		return 1;
+		CHECK(false, "elem_exists",
+		      "unexpected map entries left: %ld = %ld\n",
+		      (long)entry->key, (long)entry->value);
+		goto cleanup;
 	}
 
-	hashmap__free(map);
+	hashmap__clear(map);
 	hashmap__for_each_entry(map, entry, bkt) {
-		CHECK(false, "unexpected map entries left: %ld = %ld\n",
-			     (long)entry->key, (long)entry->value);
-		return 1;
+		CHECK(false, "elem_exists",
+		      "unexpected map entries left: %ld = %ld\n",
+		      (long)entry->key, (long)entry->value);
+		goto cleanup;
 	}
 
-	fprintf(stderr, "OK\n");
-	return 0;
+cleanup:
+	hashmap__free(map);
 }
 
-size_t collision_hash_fn(const void *k, void *ctx)
+static size_t collision_hash_fn(const void *k, void *ctx)
 {
 	return 0;
 }
 
-int test_hashmap_multimap(void)
+static void test_hashmap_multimap(void)
 {
 	void *k1 = (void *)0, *k2 = (void *)1;
 	struct hashmap_entry *entry;
@@ -262,121 +265,116 @@ int test_hashmap_multimap(void)
 	long found_msk;
 	int err, bkt;
 
-	fprintf(stderr, "%s: ", __func__);
-
 	/* force collisions */
 	map = hashmap__new(collision_hash_fn, equal_fn, NULL);
-	if (CHECK(IS_ERR(map), "failed to create map: %ld\n", PTR_ERR(map)))
-		return 1;
-
+	if (CHECK(IS_ERR(map), "hashmap__new",
+		  "failed to create map: %ld\n", PTR_ERR(map)))
+		return;
 
 	/* set up multimap:
 	 * [0] -> 1, 2, 4;
 	 * [1] -> 8, 16, 32;
 	 */
 	err = hashmap__append(map, k1, (void *)1);
-	if (CHECK(err, "failed to add k/v: %d\n", err))
-		return 1;
+	if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err))
+		goto cleanup;
 	err = hashmap__append(map, k1, (void *)2);
-	if (CHECK(err, "failed to add k/v: %d\n", err))
-		return 1;
+	if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err))
+		goto cleanup;
 	err = hashmap__append(map, k1, (void *)4);
-	if (CHECK(err, "failed to add k/v: %d\n", err))
-		return 1;
+	if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err))
+		goto cleanup;
 
 	err = hashmap__append(map, k2, (void *)8);
-	if (CHECK(err, "failed to add k/v: %d\n", err))
-		return 1;
+	if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err))
+		goto cleanup;
 	err = hashmap__append(map, k2, (void *)16);
-	if (CHECK(err, "failed to add k/v: %d\n", err))
-		return 1;
+	if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err))
+		goto cleanup;
 	err = hashmap__append(map, k2, (void *)32);
-	if (CHECK(err, "failed to add k/v: %d\n", err))
-		return 1;
+	if (CHECK(err, "elem_add", "failed to add k/v: %d\n", err))
+		goto cleanup;
 
-	if (CHECK(hashmap__size(map) != 6,
+	if (CHECK(hashmap__size(map) != 6, "hashmap_size",
 		  "invalid map size: %zu\n", hashmap__size(map)))
-		return 1;
+		goto cleanup;
 
 	/* verify global iteration still works and sees all values */
 	found_msk = 0;
 	hashmap__for_each_entry(map, entry, bkt) {
 		found_msk |= (long)entry->value;
 	}
-	if (CHECK(found_msk != (1 << 6) - 1,
+	if (CHECK(found_msk != (1 << 6) - 1, "found_msk",
 		  "not all keys iterated: %lx\n", found_msk))
-		return 1;
+		goto cleanup;
 
 	/* iterate values for key 1 */
 	found_msk = 0;
 	hashmap__for_each_key_entry(map, entry, k1) {
 		found_msk |= (long)entry->value;
 	}
-	if (CHECK(found_msk != (1 | 2 | 4),
+	if (CHECK(found_msk != (1 | 2 | 4), "found_msk",
 		  "invalid k1 values: %lx\n", found_msk))
-		return 1;
+		goto cleanup;
 
 	/* iterate values for key 2 */
 	found_msk = 0;
 	hashmap__for_each_key_entry(map, entry, k2) {
 		found_msk |= (long)entry->value;
 	}
-	if (CHECK(found_msk != (8 | 16 | 32),
+	if (CHECK(found_msk != (8 | 16 | 32), "found_msk",
 		  "invalid k2 values: %lx\n", found_msk))
-		return 1;
+		goto cleanup;
 
-	fprintf(stderr, "OK\n");
-	return 0;
+cleanup:
+	hashmap__free(map);
 }
 
-int test_hashmap_empty()
+static void test_hashmap_empty()
 {
 	struct hashmap_entry *entry;
 	int bkt;
 	struct hashmap *map;
 	void *k = (void *)0;
 
-	fprintf(stderr, "%s: ", __func__);
-
 	/* force collisions */
 	map = hashmap__new(hash_fn, equal_fn, NULL);
-	if (CHECK(IS_ERR(map), "failed to create map: %ld\n", PTR_ERR(map)))
-		return 1;
+	if (CHECK(IS_ERR(map), "hashmap__new",
+		  "failed to create map: %ld\n", PTR_ERR(map)))
+		goto cleanup;
 
-	if (CHECK(hashmap__size(map) != 0,
+	if (CHECK(hashmap__size(map) != 0, "hashmap__size",
 		  "invalid map size: %zu\n", hashmap__size(map)))
-		return 1;
-	if (CHECK(hashmap__capacity(map) != 0,
+		goto cleanup;
+	if (CHECK(hashmap__capacity(map) != 0, "hashmap__capacity",
 		  "invalid map capacity: %zu\n", hashmap__capacity(map)))
-		return 1;
-	if (CHECK(hashmap__find(map, k, NULL), "unexpected find\n"))
-		return 1;
-	if (CHECK(hashmap__delete(map, k, NULL, NULL), "unexpected delete\n"))
-		return 1;
+		goto cleanup;
+	if (CHECK(hashmap__find(map, k, NULL), "elem_find",
+		  "unexpected find\n"))
+		goto cleanup;
+	if (CHECK(hashmap__delete(map, k, NULL, NULL), "elem_del",
+		  "unexpected delete\n"))
+		goto cleanup;
 
 	hashmap__for_each_entry(map, entry, bkt) {
-		CHECK(false, "unexpected iterated entry\n");
-		return 1;
+		CHECK(false, "elem_found", "unexpected iterated entry\n");
+		goto cleanup;
 	}
 	hashmap__for_each_key_entry(map, entry, k) {
-		CHECK(false, "unexpected key entry\n");
-		return 1;
+		CHECK(false, "key_found", "unexpected key entry\n");
+		goto cleanup;
 	}
 
-	fprintf(stderr, "OK\n");
-	return 0;
+cleanup:
+	hashmap__free(map);
 }
 
-int main(int argc, char **argv)
+void test_hashmap()
 {
-	bool failed = false;
-
-	if (test_hashmap_generic())
-		failed = true;
-	if (test_hashmap_multimap())
-		failed = true;
-	if (test_hashmap_empty())
-		failed = true;
-
-	return failed;
+	if (test__start_subtest("generic"))
+		test_hashmap_generic();
+	if (test__start_subtest("multimap"))
+		test_hashmap_multimap();
+	if (test__start_subtest("empty"))
+		test_hashmap_empty();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
index 7507c8f689bc..42c3a3103c26 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <network_helpers.h>
 
 struct meta {
 	int ifindex;
diff --git a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c
index eaf64595be88..c2d373e294bb 100644
--- a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c
+++ b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <network_helpers.h>
 
 static void test_l4lb(const char *file)
 {
diff --git a/tools/testing/selftests/bpf/prog_tests/map_lock.c b/tools/testing/selftests/bpf/prog_tests/map_lock.c
index 8f91f1881d11..ce17b1ed8709 100644
--- a/tools/testing/selftests/bpf/prog_tests/map_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/map_lock.c
@@ -1,5 +1,19 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <network_helpers.h>
+
+static void *spin_lock_thread(void *arg)
+{
+	__u32 duration, retval;
+	int err, prog_fd = *(u32 *) arg;
+
+	err = bpf_prog_test_run(prog_fd, 10000, &pkt_v4, sizeof(pkt_v4),
+				NULL, NULL, &retval, &duration);
+	CHECK(err || retval, "",
+	      "err %d errno %d retval %d duration %d\n",
+	      err, errno, retval, duration);
+	pthread_exit(arg);
+}
 
 static void *parallel_map_access(void *arg)
 {
diff --git a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
index 542240e16564..e74dc501b27f 100644
--- a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
+++ b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
@@ -80,9 +80,6 @@ void test_ns_current_pid_tgid(void)
 		  "User pid/tgid %llu BPF pid/tgid %llu\n", id, bss.pid_tgid))
 		goto cleanup;
 cleanup:
-	if (!link) {
-		bpf_link__destroy(link);
-		link = NULL;
-	}
+	bpf_link__destroy(link);
 	bpf_object__close(obj);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
index 1450ea2dd4cc..a122ce3b360e 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
@@ -6,6 +6,11 @@
 #include <test_progs.h>
 #include "bpf/libbpf_internal.h"
 
+/* AddressSanitizer sometimes crashes due to data dereference below, due to
+ * this being mmap()'ed memory. Disable instrumentation with
+ * no_sanitize_address attribute
+ */
+__attribute__((no_sanitize_address))
 static void on_sample(void *ctx, int cpu, void *data, __u32 size)
 {
 	int cpu_data = *(int *)data, duration = 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/pkt_access.c b/tools/testing/selftests/bpf/prog_tests/pkt_access.c
index a2537dfa899c..44b514fabccd 100644
--- a/tools/testing/selftests/bpf/prog_tests/pkt_access.c
+++ b/tools/testing/selftests/bpf/prog_tests/pkt_access.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <network_helpers.h>
 
 void test_pkt_access(void)
 {
diff --git a/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c b/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c
index 5f7aea605019..939015cd6dba 100644
--- a/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c
+++ b/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <network_helpers.h>
 
 void test_pkt_md_access(void)
 {
diff --git a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c
index 5dd89b941f53..dde2b7ae7bc9 100644
--- a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c
+++ b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <network_helpers.h>
 
 void test_prog_run_xattr(void)
 {
diff --git a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
index faccc66f4e39..f47e7b1cb32c 100644
--- a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <network_helpers.h>
 
 enum {
 	QUEUE,
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
new file mode 100644
index 000000000000..2bba908dfa63
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -0,0 +1,211 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+#include <test_progs.h>
+#include <sys/mman.h>
+#include <sys/epoll.h>
+#include <time.h>
+#include <sched.h>
+#include <signal.h>
+#include <pthread.h>
+#include <sys/sysinfo.h>
+#include <linux/perf_event.h>
+#include <linux/ring_buffer.h>
+#include "test_ringbuf.skel.h"
+
+#define EDONE 7777
+
+static int duration = 0;
+
+struct sample {
+	int pid;
+	int seq;
+	long value;
+	char comm[16];
+};
+
+static volatile int sample_cnt;
+
+static int process_sample(void *ctx, void *data, size_t len)
+{
+	struct sample *s = data;
+
+	sample_cnt++;
+
+	switch (s->seq) {
+	case 0:
+		CHECK(s->value != 333, "sample1_value", "exp %ld, got %ld\n",
+		      333L, s->value);
+		return 0;
+	case 1:
+		CHECK(s->value != 777, "sample2_value", "exp %ld, got %ld\n",
+		      777L, s->value);
+		return -EDONE;
+	default:
+		/* we don't care about the rest */
+		return 0;
+	}
+}
+
+static struct test_ringbuf *skel;
+static struct ring_buffer *ringbuf;
+
+static void trigger_samples()
+{
+	skel->bss->dropped = 0;
+	skel->bss->total = 0;
+	skel->bss->discarded = 0;
+
+	/* trigger exactly two samples */
+	skel->bss->value = 333;
+	syscall(__NR_getpgid);
+	skel->bss->value = 777;
+	syscall(__NR_getpgid);
+}
+
+static void *poll_thread(void *input)
+{
+	long timeout = (long)input;
+
+	return (void *)(long)ring_buffer__poll(ringbuf, timeout);
+}
+
+void test_ringbuf(void)
+{
+	const size_t rec_sz = BPF_RINGBUF_HDR_SZ + sizeof(struct sample);
+	pthread_t thread;
+	long bg_ret = -1;
+	int err;
+
+	skel = test_ringbuf__open_and_load();
+	if (CHECK(!skel, "skel_open_load", "skeleton open&load failed\n"))
+		return;
+
+	/* only trigger BPF program for current process */
+	skel->bss->pid = getpid();
+
+	ringbuf = ring_buffer__new(bpf_map__fd(skel->maps.ringbuf),
+				   process_sample, NULL, NULL);
+	if (CHECK(!ringbuf, "ringbuf_create", "failed to create ringbuf\n"))
+		goto cleanup;
+
+	err = test_ringbuf__attach(skel);
+	if (CHECK(err, "skel_attach", "skeleton attachment failed: %d\n", err))
+		goto cleanup;
+
+	trigger_samples();
+
+	/* 2 submitted + 1 discarded records */
+	CHECK(skel->bss->avail_data != 3 * rec_sz,
+	      "err_avail_size", "exp %ld, got %ld\n",
+	      3L * rec_sz, skel->bss->avail_data);
+	CHECK(skel->bss->ring_size != 4096,
+	      "err_ring_size", "exp %ld, got %ld\n",
+	      4096L, skel->bss->ring_size);
+	CHECK(skel->bss->cons_pos != 0,
+	      "err_cons_pos", "exp %ld, got %ld\n",
+	      0L, skel->bss->cons_pos);
+	CHECK(skel->bss->prod_pos != 3 * rec_sz,
+	      "err_prod_pos", "exp %ld, got %ld\n",
+	      3L * rec_sz, skel->bss->prod_pos);
+
+	/* poll for samples */
+	err = ring_buffer__poll(ringbuf, -1);
+
+	/* -EDONE is used as an indicator that we are done */
+	if (CHECK(err != -EDONE, "err_done", "done err: %d\n", err))
+		goto cleanup;
+
+	/* we expect extra polling to return nothing */
+	err = ring_buffer__poll(ringbuf, 0);
+	if (CHECK(err != 0, "extra_samples", "poll result: %d\n", err))
+		goto cleanup;
+
+	CHECK(skel->bss->dropped != 0, "err_dropped", "exp %ld, got %ld\n",
+	      0L, skel->bss->dropped);
+	CHECK(skel->bss->total != 2, "err_total", "exp %ld, got %ld\n",
+	      2L, skel->bss->total);
+	CHECK(skel->bss->discarded != 1, "err_discarded", "exp %ld, got %ld\n",
+	      1L, skel->bss->discarded);
+
+	/* now validate consumer position is updated and returned */
+	trigger_samples();
+	CHECK(skel->bss->cons_pos != 3 * rec_sz,
+	      "err_cons_pos", "exp %ld, got %ld\n",
+	      3L * rec_sz, skel->bss->cons_pos);
+	err = ring_buffer__poll(ringbuf, -1);
+	CHECK(err <= 0, "poll_err", "err %d\n", err);
+
+	/* start poll in background w/ long timeout */
+	err = pthread_create(&thread, NULL, poll_thread, (void *)(long)10000);
+	if (CHECK(err, "bg_poll", "pthread_create failed: %d\n", err))
+		goto cleanup;
+
+	/* turn off notifications now */
+	skel->bss->flags = BPF_RB_NO_WAKEUP;
+
+	/* give background thread a bit of a time */
+	usleep(50000);
+	trigger_samples();
+	/* sleeping arbitrarily is bad, but no better way to know that
+	 * epoll_wait() **DID NOT** unblock in background thread
+	 */
+	usleep(50000);
+	/* background poll should still be blocked */
+	err = pthread_tryjoin_np(thread, (void **)&bg_ret);
+	if (CHECK(err != EBUSY, "try_join", "err %d\n", err))
+		goto cleanup;
+
+	/* BPF side did everything right */
+	CHECK(skel->bss->dropped != 0, "err_dropped", "exp %ld, got %ld\n",
+	      0L, skel->bss->dropped);
+	CHECK(skel->bss->total != 2, "err_total", "exp %ld, got %ld\n",
+	      2L, skel->bss->total);
+	CHECK(skel->bss->discarded != 1, "err_discarded", "exp %ld, got %ld\n",
+	      1L, skel->bss->discarded);
+
+	/* clear flags to return to "adaptive" notification mode */
+	skel->bss->flags = 0;
+
+	/* produce new samples, no notification should be triggered, because
+	 * consumer is now behind
+	 */
+	trigger_samples();
+
+	/* background poll should still be blocked */
+	err = pthread_tryjoin_np(thread, (void **)&bg_ret);
+	if (CHECK(err != EBUSY, "try_join", "err %d\n", err))
+		goto cleanup;
+
+	/* now force notifications */
+	skel->bss->flags = BPF_RB_FORCE_WAKEUP;
+	sample_cnt = 0;
+	trigger_samples();
+
+	/* now we should get a pending notification */
+	usleep(50000);
+	err = pthread_tryjoin_np(thread, (void **)&bg_ret);
+	if (CHECK(err, "join_bg", "err %d\n", err))
+		goto cleanup;
+
+	if (CHECK(bg_ret != 1, "bg_ret", "epoll_wait result: %ld", bg_ret))
+		goto cleanup;
+
+	/* 3 rounds, 2 samples each */
+	CHECK(sample_cnt != 6, "wrong_sample_cnt",
+	      "expected to see %d samples, got %d\n", 6, sample_cnt);
+
+	/* BPF side did everything right */
+	CHECK(skel->bss->dropped != 0, "err_dropped", "exp %ld, got %ld\n",
+	      0L, skel->bss->dropped);
+	CHECK(skel->bss->total != 2, "err_total", "exp %ld, got %ld\n",
+	      2L, skel->bss->total);
+	CHECK(skel->bss->discarded != 1, "err_discarded", "exp %ld, got %ld\n",
+	      1L, skel->bss->discarded);
+
+	test_ringbuf__detach(skel);
+cleanup:
+	ring_buffer__free(ringbuf);
+	test_ringbuf__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
new file mode 100644
index 000000000000..78e450609803
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <test_progs.h>
+#include <sys/epoll.h>
+#include "test_ringbuf_multi.skel.h"
+
+static int duration = 0;
+
+struct sample {
+	int pid;
+	int seq;
+	long value;
+	char comm[16];
+};
+
+static int process_sample(void *ctx, void *data, size_t len)
+{
+	int ring = (unsigned long)ctx;
+	struct sample *s = data;
+
+	switch (s->seq) {
+	case 0:
+		CHECK(ring != 1, "sample1_ring", "exp %d, got %d\n", 1, ring);
+		CHECK(s->value != 333, "sample1_value", "exp %ld, got %ld\n",
+		      333L, s->value);
+		break;
+	case 1:
+		CHECK(ring != 2, "sample2_ring", "exp %d, got %d\n", 2, ring);
+		CHECK(s->value != 777, "sample2_value", "exp %ld, got %ld\n",
+		      777L, s->value);
+		break;
+	default:
+		CHECK(true, "extra_sample", "unexpected sample seq %d, val %ld\n",
+		      s->seq, s->value);
+		return -1;
+	}
+
+	return 0;
+}
+
+void test_ringbuf_multi(void)
+{
+	struct test_ringbuf_multi *skel;
+	struct ring_buffer *ringbuf;
+	int err;
+
+	skel = test_ringbuf_multi__open_and_load();
+	if (CHECK(!skel, "skel_open_load", "skeleton open&load failed\n"))
+		return;
+
+	/* only trigger BPF program for current process */
+	skel->bss->pid = getpid();
+
+	ringbuf = ring_buffer__new(bpf_map__fd(skel->maps.ringbuf1),
+				   process_sample, (void *)(long)1, NULL);
+	if (CHECK(!ringbuf, "ringbuf_create", "failed to create ringbuf\n"))
+		goto cleanup;
+
+	err = ring_buffer__add(ringbuf, bpf_map__fd(skel->maps.ringbuf2),
+			      process_sample, (void *)(long)2);
+	if (CHECK(err, "ringbuf_add", "failed to add another ring\n"))
+		goto cleanup;
+
+	err = test_ringbuf_multi__attach(skel);
+	if (CHECK(err, "skel_attach", "skeleton attachment failed: %d\n", err))
+		goto cleanup;
+
+	/* trigger few samples, some will be skipped */
+	skel->bss->target_ring = 0;
+	skel->bss->value = 333;
+	syscall(__NR_getpgid);
+
+	/* skipped, no ringbuf in slot 1 */
+	skel->bss->target_ring = 1;
+	skel->bss->value = 555;
+	syscall(__NR_getpgid);
+
+	skel->bss->target_ring = 2;
+	skel->bss->value = 777;
+	syscall(__NR_getpgid);
+
+	/* poll for samples, should get 2 ringbufs back */
+	err = ring_buffer__poll(ringbuf, -1);
+	if (CHECK(err != 4, "poll_res", "expected 4 records, got %d\n", err))
+		goto cleanup;
+
+	/* expect extra polling to return nothing */
+	err = ring_buffer__poll(ringbuf, 0);
+	if (CHECK(err < 0, "extra_samples", "poll result: %d\n", err))
+		goto cleanup;
+
+	CHECK(skel->bss->dropped != 0, "err_dropped", "exp %ld, got %ld\n",
+	      0L, skel->bss->dropped);
+	CHECK(skel->bss->skipped != 1, "err_skipped", "exp %ld, got %ld\n",
+	      1L, skel->bss->skipped);
+	CHECK(skel->bss->total != 2, "err_total", "exp %ld, got %ld\n",
+	      2L, skel->bss->total);
+
+cleanup:
+	ring_buffer__free(ringbuf);
+	test_ringbuf_multi__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/signal_pending.c b/tools/testing/selftests/bpf/prog_tests/signal_pending.c
index 996e808f43a2..dfcbddcbe4d3 100644
--- a/tools/testing/selftests/bpf/prog_tests/signal_pending.c
+++ b/tools/testing/selftests/bpf/prog_tests/signal_pending.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <network_helpers.h>
 
 static void sigalrm_handler(int s) {}
 static struct sigaction sigalrm_action = {
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_assign.c b/tools/testing/selftests/bpf/prog_tests/sk_assign.c
index d572e1a2c297..47fa04adc147 100644
--- a/tools/testing/selftests/bpf/prog_tests/sk_assign.c
+++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c
@@ -20,6 +20,7 @@
 #define CONNECT_PORT 4321
 #define TEST_DADDR (0xC0A80203)
 #define NS_SELF "/proc/self/ns/net"
+#define SERVER_MAP_PATH "/sys/fs/bpf/tc/globals/server_map"
 
 static const struct timeval timeo_sec = { .tv_sec = 3 };
 static const size_t timeo_optlen = sizeof(timeo_sec);
@@ -265,6 +266,7 @@ void test_sk_assign(void)
 		TEST("ipv6 udp addr redir", AF_INET6, SOCK_DGRAM, true),
 	};
 	int server = -1;
+	int server_map;
 	int self_net;
 
 	self_net = open(NS_SELF, O_RDONLY);
@@ -278,9 +280,17 @@ void test_sk_assign(void)
 		goto cleanup;
 	}
 
+	server_map = bpf_obj_get(SERVER_MAP_PATH);
+	if (CHECK_FAIL(server_map < 0)) {
+		perror("Unable to open " SERVER_MAP_PATH);
+		goto cleanup;
+	}
+
 	for (int i = 0; i < ARRAY_SIZE(tests) && !READ_ONCE(stop); i++) {
 		struct test_sk_cfg *test = &tests[i];
 		const struct sockaddr *addr;
+		const int zero = 0;
+		int err;
 
 		if (!test__start_subtest(test->name))
 			continue;
@@ -288,7 +298,13 @@ void test_sk_assign(void)
 		addr = (const struct sockaddr *)test->addr;
 		server = start_server(addr, test->len, test->type);
 		if (server == -1)
-			goto cleanup;
+			goto close;
+
+		err = bpf_map_update_elem(server_map, &zero, &server, BPF_ANY);
+		if (CHECK_FAIL(err)) {
+			perror("Unable to update server_map");
+			goto close;
+		}
 
 		/* connect to unbound ports */
 		prepare_addr(test->addr, test->family, CONNECT_PORT,
@@ -302,7 +318,10 @@ void test_sk_assign(void)
 
 close:
 	close(server);
+	close(server_map);
 cleanup:
+	if (CHECK_FAIL(unlink(SERVER_MAP_PATH)))
+		perror("Unable to unlink " SERVER_MAP_PATH);
 	if (CHECK_FAIL(setns(self_net, CLONE_NEWNET)))
 		perror("Failed to setns("NS_SELF")");
 	close(self_net);
diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
index 4538bd08203f..7021b92af313 100644
--- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
+++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <network_helpers.h>
 
 void test_skb_ctx(void)
 {
diff --git a/tools/testing/selftests/bpf/prog_tests/skb_helpers.c b/tools/testing/selftests/bpf/prog_tests/skb_helpers.c
new file mode 100644
index 000000000000..f302ad84a298
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/skb_helpers.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <network_helpers.h>
+
+void test_skb_helpers(void)
+{
+	struct __sk_buff skb = {
+		.wire_len = 100,
+		.gso_segs = 8,
+		.gso_size = 10,
+	};
+	struct bpf_prog_test_run_attr tattr = {
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.ctx_in = &skb,
+		.ctx_size_in = sizeof(skb),
+		.ctx_out = &skb,
+		.ctx_size_out = sizeof(skb),
+	};
+	struct bpf_object *obj;
+	int err;
+
+	err = bpf_prog_load("./test_skb_helpers.o", BPF_PROG_TYPE_SCHED_CLS, &obj,
+			    &tattr.prog_fd);
+	if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno))
+		return;
+	err = bpf_prog_test_run_xattr(&tattr);
+	CHECK_ATTR(err, "len", "err %d errno %d\n", err, errno);
+	bpf_object__close(obj);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index aa43e0bd210c..96e7b7f84c65 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -1,7 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2020 Cloudflare
+#include <error.h>
 
 #include "test_progs.h"
+#include "test_skmsg_load_helpers.skel.h"
 
 #define TCP_REPAIR		19	/* TCP sock is under repair right now */
 
@@ -70,10 +72,43 @@ out:
 	close(s);
 }
 
+static void test_skmsg_helpers(enum bpf_map_type map_type)
+{
+	struct test_skmsg_load_helpers *skel;
+	int err, map, verdict;
+
+	skel = test_skmsg_load_helpers__open_and_load();
+	if (CHECK_FAIL(!skel)) {
+		perror("test_skmsg_load_helpers__open_and_load");
+		return;
+	}
+
+	verdict = bpf_program__fd(skel->progs.prog_msg_verdict);
+	map = bpf_map__fd(skel->maps.sock_map);
+
+	err = bpf_prog_attach(verdict, map, BPF_SK_MSG_VERDICT, 0);
+	if (CHECK_FAIL(err)) {
+		perror("bpf_prog_attach");
+		goto out;
+	}
+
+	err = bpf_prog_detach2(verdict, map, BPF_SK_MSG_VERDICT);
+	if (CHECK_FAIL(err)) {
+		perror("bpf_prog_detach2");
+		goto out;
+	}
+out:
+	test_skmsg_load_helpers__destroy(skel);
+}
+
 void test_sockmap_basic(void)
 {
 	if (test__start_subtest("sockmap create_update_free"))
 		test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKMAP);
 	if (test__start_subtest("sockhash create_update_free"))
 		test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKHASH);
+	if (test__start_subtest("sockmap sk_msg load helpers"))
+		test_skmsg_helpers(BPF_MAP_TYPE_SOCKMAP);
+	if (test__start_subtest("sockhash sk_msg load helpers"))
+		test_skmsg_helpers(BPF_MAP_TYPE_SOCKHASH);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/spinlock.c b/tools/testing/selftests/bpf/prog_tests/spinlock.c
index 1ae00cd3174e..7577a77a4c4c 100644
--- a/tools/testing/selftests/bpf/prog_tests/spinlock.c
+++ b/tools/testing/selftests/bpf/prog_tests/spinlock.c
@@ -1,5 +1,19 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <network_helpers.h>
+
+static void *spin_lock_thread(void *arg)
+{
+	__u32 duration, retval;
+	int err, prog_fd = *(u32 *) arg;
+
+	err = bpf_prog_test_run(prog_fd, 10000, &pkt_v4, sizeof(pkt_v4),
+				NULL, NULL, &retval, &duration);
+	CHECK(err || retval, "",
+	      "err %d errno %d retval %d duration %d\n",
+	      err, errno, retval, duration);
+	pthread_exit(arg);
+}
 
 void test_spinlock(void)
 {
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
index e56b52ab41da..9013a0c01eed 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 #include "cgroup_helpers.h"
+#include "network_helpers.h"
 
 struct tcp_rtt_storage {
 	__u32 invoked;
@@ -87,34 +88,6 @@ static int verify_sk(int map_fd, int client_fd, const char *msg, __u32 invoked,
 	return err;
 }
 
-static int connect_to_server(int server_fd)
-{
-	struct sockaddr_storage addr;
-	socklen_t len = sizeof(addr);
-	int fd;
-
-	fd = socket(AF_INET, SOCK_STREAM, 0);
-	if (fd < 0) {
-		log_err("Failed to create client socket");
-		return -1;
-	}
-
-	if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) {
-		log_err("Failed to get server addr");
-		goto out;
-	}
-
-	if (connect(fd, (const struct sockaddr *)&addr, len) < 0) {
-		log_err("Fail to connect to server");
-		goto out;
-	}
-
-	return fd;
-
-out:
-	close(fd);
-	return -1;
-}
 
 static int run_test(int cgroup_fd, int server_fd)
 {
@@ -145,7 +118,7 @@ static int run_test(int cgroup_fd, int server_fd)
 		goto close_bpf_object;
 	}
 
-	client_fd = connect_to_server(server_fd);
+	client_fd = connect_to_fd(AF_INET, SOCK_STREAM, server_fd);
 	if (client_fd < 0) {
 		err = -1;
 		goto close_bpf_object;
@@ -180,103 +153,22 @@ close_bpf_object:
 	return err;
 }
 
-static int start_server(void)
-{
-	struct sockaddr_in addr = {
-		.sin_family = AF_INET,
-		.sin_addr.s_addr = htonl(INADDR_LOOPBACK),
-	};
-	int fd;
-
-	fd = socket(AF_INET, SOCK_STREAM | SOCK_NONBLOCK, 0);
-	if (fd < 0) {
-		log_err("Failed to create server socket");
-		return -1;
-	}
-
-	if (bind(fd, (const struct sockaddr *)&addr, sizeof(addr)) < 0) {
-		log_err("Failed to bind socket");
-		close(fd);
-		return -1;
-	}
-
-	return fd;
-}
-
-static pthread_mutex_t server_started_mtx = PTHREAD_MUTEX_INITIALIZER;
-static pthread_cond_t server_started = PTHREAD_COND_INITIALIZER;
-static volatile bool server_done = false;
-
-static void *server_thread(void *arg)
-{
-	struct sockaddr_storage addr;
-	socklen_t len = sizeof(addr);
-	int fd = *(int *)arg;
-	int client_fd;
-	int err;
-
-	err = listen(fd, 1);
-
-	pthread_mutex_lock(&server_started_mtx);
-	pthread_cond_signal(&server_started);
-	pthread_mutex_unlock(&server_started_mtx);
-
-	if (CHECK_FAIL(err < 0)) {
-		perror("Failed to listed on socket");
-		return ERR_PTR(err);
-	}
-
-	while (true) {
-		client_fd = accept(fd, (struct sockaddr *)&addr, &len);
-		if (client_fd == -1 && errno == EAGAIN) {
-			usleep(50);
-			continue;
-		}
-		break;
-	}
-	if (CHECK_FAIL(client_fd < 0)) {
-		perror("Failed to accept client");
-		return ERR_PTR(err);
-	}
-
-	while (!server_done)
-		usleep(50);
-
-	close(client_fd);
-
-	return NULL;
-}
-
 void test_tcp_rtt(void)
 {
 	int server_fd, cgroup_fd;
-	pthread_t tid;
-	void *server_res;
 
 	cgroup_fd = test__join_cgroup("/tcp_rtt");
 	if (CHECK_FAIL(cgroup_fd < 0))
 		return;
 
-	server_fd = start_server();
+	server_fd = start_server(AF_INET, SOCK_STREAM);
 	if (CHECK_FAIL(server_fd < 0))
 		goto close_cgroup_fd;
 
-	if (CHECK_FAIL(pthread_create(&tid, NULL, server_thread,
-				      (void *)&server_fd)))
-		goto close_server_fd;
-
-	pthread_mutex_lock(&server_started_mtx);
-	pthread_cond_wait(&server_started, &server_started_mtx);
-	pthread_mutex_unlock(&server_started_mtx);
-
 	CHECK_FAIL(run_test(cgroup_fd, server_fd));
 
-	server_done = true;
-	CHECK_FAIL(pthread_join(tid, &server_res));
-	CHECK_FAIL(IS_ERR(server_res));
-
-close_server_fd:
 	close(server_fd);
+
 close_cgroup_fd:
 	close(cgroup_fd);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/test_overhead.c b/tools/testing/selftests/bpf/prog_tests/test_overhead.c
index 465b371a561d..2702df2b2343 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_overhead.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_overhead.c
@@ -61,9 +61,10 @@ void test_test_overhead(void)
 	const char *raw_tp_name = "raw_tp/task_rename";
 	const char *fentry_name = "fentry/__set_task_comm";
 	const char *fexit_name = "fexit/__set_task_comm";
+	const char *fmodret_name = "fmod_ret/__set_task_comm";
 	const char *kprobe_func = "__set_task_comm";
 	struct bpf_program *kprobe_prog, *kretprobe_prog, *raw_tp_prog;
-	struct bpf_program *fentry_prog, *fexit_prog;
+	struct bpf_program *fentry_prog, *fexit_prog, *fmodret_prog;
 	struct bpf_object *obj;
 	struct bpf_link *link;
 	int err, duration = 0;
@@ -96,6 +97,10 @@ void test_test_overhead(void)
 	if (CHECK(!fexit_prog, "find_probe",
 		  "prog '%s' not found\n", fexit_name))
 		goto cleanup;
+	fmodret_prog = bpf_object__find_program_by_title(obj, fmodret_name);
+	if (CHECK(!fmodret_prog, "find_probe",
+		  "prog '%s' not found\n", fmodret_name))
+		goto cleanup;
 
 	err = bpf_object__load(obj);
 	if (CHECK(err, "obj_load", "err %d\n", err))
@@ -142,6 +147,13 @@ void test_test_overhead(void)
 		goto cleanup;
 	test_run("fexit");
 	bpf_link__destroy(link);
+
+	/* attach fmod_ret */
+	link = bpf_program__attach_trace(fmodret_prog);
+	if (CHECK(IS_ERR(link), "attach fmod_ret", "err %ld\n", PTR_ERR(link)))
+		goto cleanup;
+	test_run("fmod_ret");
+	bpf_link__destroy(link);
 cleanup:
 	prctl(PR_SET_NAME, comm, 0L, 0L, 0L);
 	bpf_object__close(obj);
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp.c b/tools/testing/selftests/bpf/prog_tests/xdp.c
index dcb5ecac778e..48921ff74850 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <network_helpers.h>
 
 void test_xdp(void)
 {
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
index 3744196d7cba..d5c98f2cb12f 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
@@ -1,13 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <network_helpers.h>
 
-void test_xdp_adjust_tail(void)
+void test_xdp_adjust_tail_shrink(void)
 {
-	const char *file = "./test_adjust_tail.o";
+	const char *file = "./test_xdp_adjust_tail_shrink.o";
+	__u32 duration, retval, size, expect_sz;
 	struct bpf_object *obj;
-	char buf[128];
-	__u32 duration, retval, size;
 	int err, prog_fd;
+	char buf[128];
 
 	err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
 	if (CHECK_FAIL(err))
@@ -20,10 +21,121 @@ void test_xdp_adjust_tail(void)
 	      "ipv4", "err %d errno %d retval %d size %d\n",
 	      err, errno, retval, size);
 
+	expect_sz = sizeof(pkt_v6) - 20;  /* Test shrink with 20 bytes */
 	err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6),
 				buf, &size, &retval, &duration);
-	CHECK(err || retval != XDP_TX || size != 54,
-	      "ipv6", "err %d errno %d retval %d size %d\n",
+	CHECK(err || retval != XDP_TX || size != expect_sz,
+	      "ipv6", "err %d errno %d retval %d size %d expect-size %d\n",
+	      err, errno, retval, size, expect_sz);
+	bpf_object__close(obj);
+}
+
+void test_xdp_adjust_tail_grow(void)
+{
+	const char *file = "./test_xdp_adjust_tail_grow.o";
+	struct bpf_object *obj;
+	char buf[4096]; /* avoid segfault: large buf to hold grow results */
+	__u32 duration, retval, size, expect_sz;
+	int err, prog_fd;
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
+	if (CHECK_FAIL(err))
+		return;
+
+	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				buf, &size, &retval, &duration);
+	CHECK(err || retval != XDP_DROP,
+	      "ipv4", "err %d errno %d retval %d size %d\n",
 	      err, errno, retval, size);
+
+	expect_sz = sizeof(pkt_v6) + 40; /* Test grow with 40 bytes */
+	err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6) /* 74 */,
+				buf, &size, &retval, &duration);
+	CHECK(err || retval != XDP_TX || size != expect_sz,
+	      "ipv6", "err %d errno %d retval %d size %d expect-size %d\n",
+	      err, errno, retval, size, expect_sz);
+
+	bpf_object__close(obj);
+}
+
+void test_xdp_adjust_tail_grow2(void)
+{
+	const char *file = "./test_xdp_adjust_tail_grow.o";
+	char buf[4096]; /* avoid segfault: large buf to hold grow results */
+	int tailroom = 320; /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info))*/;
+	struct bpf_object *obj;
+	int err, cnt, i;
+	int max_grow;
+
+	struct bpf_prog_test_run_attr tattr = {
+		.repeat		= 1,
+		.data_in	= &buf,
+		.data_out	= &buf,
+		.data_size_in	= 0, /* Per test */
+		.data_size_out	= 0, /* Per test */
+	};
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &tattr.prog_fd);
+	if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno))
+		return;
+
+	/* Test case-64 */
+	memset(buf, 1, sizeof(buf));
+	tattr.data_size_in  =  64; /* Determine test case via pkt size */
+	tattr.data_size_out = 128; /* Limit copy_size */
+	/* Kernel side alloc packet memory area that is zero init */
+	err = bpf_prog_test_run_xattr(&tattr);
+
+	CHECK_ATTR(errno != ENOSPC /* Due limit copy_size in bpf_test_finish */
+		   || tattr.retval != XDP_TX
+		   || tattr.data_size_out != 192, /* Expected grow size */
+		   "case-64",
+		   "err %d errno %d retval %d size %d\n",
+		   err, errno, tattr.retval, tattr.data_size_out);
+
+	/* Extra checks for data contents */
+	CHECK_ATTR(tattr.data_size_out != 192
+		   || buf[0]   != 1 ||  buf[63]  != 1  /*  0-63  memset to 1 */
+		   || buf[64]  != 0 ||  buf[127] != 0  /* 64-127 memset to 0 */
+		   || buf[128] != 1 ||  buf[191] != 1, /*128-191 memset to 1 */
+		   "case-64-data",
+		   "err %d errno %d retval %d size %d\n",
+		   err, errno, tattr.retval, tattr.data_size_out);
+
+	/* Test case-128 */
+	memset(buf, 2, sizeof(buf));
+	tattr.data_size_in  = 128; /* Determine test case via pkt size */
+	tattr.data_size_out = sizeof(buf);   /* Copy everything */
+	err = bpf_prog_test_run_xattr(&tattr);
+
+	max_grow = 4096 - XDP_PACKET_HEADROOM -	tailroom; /* 3520 */
+	CHECK_ATTR(err
+		   || tattr.retval != XDP_TX
+		   || tattr.data_size_out != max_grow,/* Expect max grow size */
+		   "case-128",
+		   "err %d errno %d retval %d size %d expect-size %d\n",
+		   err, errno, tattr.retval, tattr.data_size_out, max_grow);
+
+	/* Extra checks for data content: Count grow size, will contain zeros */
+	for (i = 0, cnt = 0; i < sizeof(buf); i++) {
+		if (buf[i] == 0)
+			cnt++;
+	}
+	CHECK_ATTR((cnt != (max_grow - tattr.data_size_in)) /* Grow increase */
+		   || tattr.data_size_out != max_grow, /* Total grow size */
+		   "case-128-data",
+		   "err %d errno %d retval %d size %d grow-size %d\n",
+		   err, errno, tattr.retval, tattr.data_size_out, cnt);
+
 	bpf_object__close(obj);
 }
+
+void test_xdp_adjust_tail(void)
+{
+	if (test__start_subtest("xdp_adjust_tail_shrink"))
+		test_xdp_adjust_tail_shrink();
+	if (test__start_subtest("xdp_adjust_tail_grow"))
+		test_xdp_adjust_tail_grow();
+	if (test__start_subtest("xdp_adjust_tail_grow2"))
+		test_xdp_adjust_tail_grow2();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
index a0f688c37023..2c6c570b21f8 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <network_helpers.h>
 #include <net/if.h>
 #include "test_xdp.skel.h"
 #include "test_xdp_bpf2bpf.skel.h"
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
new file mode 100644
index 000000000000..d19dbd668f6a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <uapi/linux/bpf.h>
+#include <linux/if_link.h>
+#include <test_progs.h>
+
+#include "test_xdp_devmap_helpers.skel.h"
+#include "test_xdp_with_devmap_helpers.skel.h"
+
+#define IFINDEX_LO 1
+
+struct bpf_devmap_val {
+	u32 ifindex;   /* device index */
+	union {
+		int fd;  /* prog fd on map write */
+		u32 id;  /* prog id on map read */
+	} bpf_prog;
+};
+
+void test_xdp_with_devmap_helpers(void)
+{
+	struct test_xdp_with_devmap_helpers *skel;
+	struct bpf_prog_info info = {};
+	struct bpf_devmap_val val = {
+		.ifindex = IFINDEX_LO,
+	};
+	__u32 len = sizeof(info);
+	__u32 duration = 0, idx = 0;
+	int err, dm_fd, map_fd;
+
+
+	skel = test_xdp_with_devmap_helpers__open_and_load();
+	if (CHECK_FAIL(!skel)) {
+		perror("test_xdp_with_devmap_helpers__open_and_load");
+		return;
+	}
+
+	/* can not attach program with DEVMAPs that allow programs
+	 * as xdp generic
+	 */
+	dm_fd = bpf_program__fd(skel->progs.xdp_redir_prog);
+	err = bpf_set_link_xdp_fd(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE);
+	CHECK(err == 0, "Generic attach of program with 8-byte devmap",
+	      "should have failed\n");
+
+	dm_fd = bpf_program__fd(skel->progs.xdp_dummy_dm);
+	map_fd = bpf_map__fd(skel->maps.dm_ports);
+	err = bpf_obj_get_info_by_fd(dm_fd, &info, &len);
+	if (CHECK_FAIL(err))
+		goto out_close;
+
+	val.bpf_prog.fd = dm_fd;
+	err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+	CHECK(err, "Add program to devmap entry",
+	      "err %d errno %d\n", err, errno);
+
+	err = bpf_map_lookup_elem(map_fd, &idx, &val);
+	CHECK(err, "Read devmap entry", "err %d errno %d\n", err, errno);
+	CHECK(info.id != val.bpf_prog.id, "Expected program id in devmap entry",
+	      "expected %u read %u\n", info.id, val.bpf_prog.id);
+
+	/* can not attach BPF_XDP_DEVMAP program to a device */
+	err = bpf_set_link_xdp_fd(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE);
+	CHECK(err == 0, "Attach of BPF_XDP_DEVMAP program",
+	      "should have failed\n");
+
+	val.ifindex = 1;
+	val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_prog);
+	err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+	CHECK(err == 0, "Add non-BPF_XDP_DEVMAP program to devmap entry",
+	      "should have failed\n");
+
+out_close:
+	test_xdp_with_devmap_helpers__destroy(skel);
+}
+
+void test_neg_xdp_devmap_helpers(void)
+{
+	struct test_xdp_devmap_helpers *skel;
+	__u32 duration = 0;
+
+	skel = test_xdp_devmap_helpers__open_and_load();
+	if (CHECK(skel,
+		  "Load of XDP program accessing egress ifindex without attach type",
+		  "should have failed\n")) {
+		test_xdp_devmap_helpers__destroy(skel);
+	}
+}
+
+
+void test_xdp_devmap_attach(void)
+{
+	if (test__start_subtest("DEVMAP with programs in entries"))
+		test_xdp_with_devmap_helpers();
+
+	if (test__start_subtest("Verifier check of DEVMAP programs"))
+		test_neg_xdp_devmap_helpers();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c
index c9404e6b226e..f284f72158ef 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <network_helpers.h>
 
 void test_xdp_noinline(void)
 {
diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c
index 9941f0ba471e..de6de9221518 100644
--- a/tools/testing/selftests/bpf/progs/bpf_flow.c
+++ b/tools/testing/selftests/bpf/progs/bpf_flow.c
@@ -20,20 +20,20 @@
 #include <bpf/bpf_endian.h>
 
 int _version SEC("version") = 1;
-#define PROG(F) SEC(#F) int bpf_func_##F
+#define PROG(F) PROG_(F, _##F)
+#define PROG_(NUM, NAME) SEC("flow_dissector/"#NUM) int bpf_func##NAME
 
 /* These are the identifiers of the BPF programs that will be used in tail
  * calls. Name is limited to 16 characters, with the terminating character and
  * bpf_func_ above, we have only 6 to work with, anything after will be cropped.
  */
-enum {
-	IP,
-	IPV6,
-	IPV6OP,	/* Destination/Hop-by-Hop Options IPv6 Extension header */
-	IPV6FR,	/* Fragmentation IPv6 Extension Header */
-	MPLS,
-	VLAN,
-};
+#define IP		0
+#define IPV6		1
+#define IPV6OP		2 /* Destination/Hop-by-Hop Options IPv6 Ext. Header */
+#define IPV6FR		3 /* Fragmentation IPv6 Extension Header */
+#define MPLS		4
+#define VLAN		5
+#define MAX_PROG	6
 
 #define IP_MF		0x2000
 #define IP_OFFSET	0x1FFF
@@ -59,7 +59,7 @@ struct frag_hdr {
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
-	__uint(max_entries, 8);
+	__uint(max_entries, MAX_PROG);
 	__uint(key_size, sizeof(__u32));
 	__uint(value_size, sizeof(__u32));
 } jmp_table SEC(".maps");
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
new file mode 100644
index 000000000000..b57bd6fef208
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+/* "undefine" structs in vmlinux.h, because we "override" them below */
+#define bpf_iter_meta bpf_iter_meta___not_used
+#define bpf_iter__bpf_map bpf_iter__bpf_map___not_used
+#include "vmlinux.h"
+#undef bpf_iter_meta
+#undef bpf_iter__bpf_map
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct bpf_iter_meta {
+	struct seq_file *seq;
+	__u64 session_id;
+	__u64 seq_num;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__bpf_map {
+	struct bpf_iter_meta *meta;
+	struct bpf_map *map;
+} __attribute__((preserve_access_index));
+
+SEC("iter/bpf_map")
+int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	__u64 seq_num = ctx->meta->seq_num;
+	struct bpf_map *map = ctx->map;
+
+	if (map == (void *)0) {
+		BPF_SEQ_PRINTF(seq, "      %%%%%% END %%%%%%\n");
+		return 0;
+	}
+
+	if (seq_num == 0)
+		BPF_SEQ_PRINTF(seq, "      id   refcnt  usercnt  locked_vm\n");
+
+	BPF_SEQ_PRINTF(seq, "%8u %8ld %8ld %10lu\n", map->id, map->refcnt.counter,
+		       map->usercnt.counter,
+		       map->memory.user->locked_vm.counter);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c
new file mode 100644
index 000000000000..c8e9ca74c87b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+/* "undefine" structs in vmlinux.h, because we "override" them below */
+#define bpf_iter_meta bpf_iter_meta___not_used
+#define bpf_iter__ipv6_route bpf_iter__ipv6_route___not_used
+#include "vmlinux.h"
+#undef bpf_iter_meta
+#undef bpf_iter__ipv6_route
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+struct bpf_iter_meta {
+	struct seq_file *seq;
+	__u64 session_id;
+	__u64 seq_num;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__ipv6_route {
+	struct bpf_iter_meta *meta;
+	struct fib6_info *rt;
+} __attribute__((preserve_access_index));
+
+char _license[] SEC("license") = "GPL";
+
+extern bool CONFIG_IPV6_SUBTREES __kconfig __weak;
+
+#define RTF_GATEWAY		0x0002
+#define IFNAMSIZ		16
+#define fib_nh_gw_family	nh_common.nhc_gw_family
+#define fib_nh_gw6		nh_common.nhc_gw.ipv6
+#define fib_nh_dev		nh_common.nhc_dev
+
+SEC("iter/ipv6_route")
+int dump_ipv6_route(struct bpf_iter__ipv6_route *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct fib6_info *rt = ctx->rt;
+	const struct net_device *dev;
+	struct fib6_nh *fib6_nh;
+	unsigned int flags;
+	struct nexthop *nh;
+
+	if (rt == (void *)0)
+		return 0;
+
+	fib6_nh = &rt->fib6_nh[0];
+	flags = rt->fib6_flags;
+
+	/* FIXME: nexthop_is_multipath is not handled here. */
+	nh = rt->nh;
+	if (rt->nh)
+		fib6_nh = &nh->nh_info->fib6_nh;
+
+	BPF_SEQ_PRINTF(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen);
+
+	if (CONFIG_IPV6_SUBTREES)
+		BPF_SEQ_PRINTF(seq, "%pi6 %02x ", &rt->fib6_src.addr,
+			       rt->fib6_src.plen);
+	else
+		BPF_SEQ_PRINTF(seq, "00000000000000000000000000000000 00 ");
+
+	if (fib6_nh->fib_nh_gw_family) {
+		flags |= RTF_GATEWAY;
+		BPF_SEQ_PRINTF(seq, "%pi6 ", &fib6_nh->fib_nh_gw6);
+	} else {
+		BPF_SEQ_PRINTF(seq, "00000000000000000000000000000000 ");
+	}
+
+	dev = fib6_nh->fib_nh_dev;
+	if (dev)
+		BPF_SEQ_PRINTF(seq, "%08x %08x %08x %08x %8s\n", rt->fib6_metric,
+			       rt->fib6_ref.refs.counter, 0, flags, dev->name);
+	else
+		BPF_SEQ_PRINTF(seq, "%08x %08x %08x %08x\n", rt->fib6_metric,
+			       rt->fib6_ref.refs.counter, 0, flags);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c
new file mode 100644
index 000000000000..e7b8753eac0b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+/* "undefine" structs in vmlinux.h, because we "override" them below */
+#define bpf_iter_meta bpf_iter_meta___not_used
+#define bpf_iter__netlink bpf_iter__netlink___not_used
+#include "vmlinux.h"
+#undef bpf_iter_meta
+#undef bpf_iter__netlink
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+#define sk_rmem_alloc	sk_backlog.rmem_alloc
+#define sk_refcnt	__sk_common.skc_refcnt
+
+struct bpf_iter_meta {
+	struct seq_file *seq;
+	__u64 session_id;
+	__u64 seq_num;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__netlink {
+	struct bpf_iter_meta *meta;
+	struct netlink_sock *sk;
+} __attribute__((preserve_access_index));
+
+static inline struct inode *SOCK_INODE(struct socket *socket)
+{
+	return &container_of(socket, struct socket_alloc, socket)->vfs_inode;
+}
+
+SEC("iter/netlink")
+int dump_netlink(struct bpf_iter__netlink *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct netlink_sock *nlk = ctx->sk;
+	unsigned long group, ino;
+	struct inode *inode;
+	struct socket *sk;
+	struct sock *s;
+
+	if (nlk == (void *)0)
+		return 0;
+
+	if (ctx->meta->seq_num == 0)
+		BPF_SEQ_PRINTF(seq, "sk               Eth Pid        Groups   "
+				    "Rmem     Wmem     Dump  Locks    Drops    "
+				    "Inode\n");
+
+	s = &nlk->sk;
+	BPF_SEQ_PRINTF(seq, "%pK %-3d ", s, s->sk_protocol);
+
+	if (!nlk->groups)  {
+		group = 0;
+	} else {
+		/* FIXME: temporary use bpf_probe_read here, needs
+		 * verifier support to do direct access.
+		 */
+		bpf_probe_read(&group, sizeof(group), &nlk->groups[0]);
+	}
+	BPF_SEQ_PRINTF(seq, "%-10u %08x %-8d %-8d %-5d %-8d ",
+		       nlk->portid, (u32)group,
+		       s->sk_rmem_alloc.counter,
+		       s->sk_wmem_alloc.refs.counter - 1,
+		       nlk->cb_running, s->sk_refcnt.refs.counter);
+
+	sk = s->sk_socket;
+	if (!sk) {
+		ino = 0;
+	} else {
+		/* FIXME: container_of inside SOCK_INODE has a forced
+		 * type conversion, and direct access cannot be used
+		 * with current verifier.
+		 */
+		inode = SOCK_INODE(sk);
+		bpf_probe_read(&ino, sizeof(ino), &inode->i_ino);
+	}
+	BPF_SEQ_PRINTF(seq, "%-8u %-8lu\n", s->sk_drops.counter, ino);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_task.c
new file mode 100644
index 000000000000..ee754021f98e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+/* "undefine" structs in vmlinux.h, because we "override" them below */
+#define bpf_iter_meta bpf_iter_meta___not_used
+#define bpf_iter__task bpf_iter__task___not_used
+#include "vmlinux.h"
+#undef bpf_iter_meta
+#undef bpf_iter__task
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct bpf_iter_meta {
+	struct seq_file *seq;
+	__u64 session_id;
+	__u64 seq_num;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__task {
+	struct bpf_iter_meta *meta;
+	struct task_struct *task;
+} __attribute__((preserve_access_index));
+
+SEC("iter/task")
+int dump_task(struct bpf_iter__task *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct task_struct *task = ctx->task;
+
+	if (task == (void *)0) {
+		BPF_SEQ_PRINTF(seq, "    === END ===\n");
+		return 0;
+	}
+
+	if (ctx->meta->seq_num == 0)
+		BPF_SEQ_PRINTF(seq, "    tgid      gid\n");
+
+	BPF_SEQ_PRINTF(seq, "%8d %8d\n", task->tgid, task->pid);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c
new file mode 100644
index 000000000000..0f0ec3db20ba
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+/* "undefine" structs in vmlinux.h, because we "override" them below */
+#define bpf_iter_meta bpf_iter_meta___not_used
+#define bpf_iter__task_file bpf_iter__task_file___not_used
+#include "vmlinux.h"
+#undef bpf_iter_meta
+#undef bpf_iter__task_file
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct bpf_iter_meta {
+	struct seq_file *seq;
+	__u64 session_id;
+	__u64 seq_num;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__task_file {
+	struct bpf_iter_meta *meta;
+	struct task_struct *task;
+	__u32 fd;
+	struct file *file;
+} __attribute__((preserve_access_index));
+
+SEC("iter/task_file")
+int dump_task_file(struct bpf_iter__task_file *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct task_struct *task = ctx->task;
+	__u32 fd = ctx->fd;
+	struct file *file = ctx->file;
+
+	if (task == (void *)0 || file == (void *)0)
+		return 0;
+
+	if (ctx->meta->seq_num == 0)
+		BPF_SEQ_PRINTF(seq, "    tgid      gid       fd      file\n");
+
+	BPF_SEQ_PRINTF(seq, "%8d %8d %8d %lx\n", task->tgid, task->pid, fd,
+		       (long)file->f_op);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern1.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern1.c
new file mode 100644
index 000000000000..c71a7c283108
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern1.c
@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#define START_CHAR 'a'
+#include "bpf_iter_test_kern_common.h"
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern2.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern2.c
new file mode 100644
index 000000000000..8bdc8dc07444
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern2.c
@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#define START_CHAR 'A'
+#include "bpf_iter_test_kern_common.h"
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c
new file mode 100644
index 000000000000..13c2c90c835f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#define bpf_iter_meta bpf_iter_meta___not_used
+#define bpf_iter__task bpf_iter__task___not_used
+#include "vmlinux.h"
+#undef bpf_iter_meta
+#undef bpf_iter__task
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct bpf_iter_meta {
+	struct seq_file *seq;
+	__u64 session_id;
+	__u64 seq_num;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__task {
+	struct bpf_iter_meta *meta;
+	struct task_struct *task;
+} __attribute__((preserve_access_index));
+
+SEC("iter/task")
+int dump_task(struct bpf_iter__task *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct task_struct *task = ctx->task;
+	int tgid;
+
+	tgid = task->tgid;
+	bpf_seq_write(seq, &tgid, sizeof(tgid));
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
new file mode 100644
index 000000000000..0aa71b333cf3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#define bpf_iter_meta bpf_iter_meta___not_used
+#define bpf_iter__bpf_map bpf_iter__bpf_map___not_used
+#include "vmlinux.h"
+#undef bpf_iter_meta
+#undef bpf_iter__bpf_map
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct bpf_iter_meta {
+	struct seq_file *seq;
+	__u64 session_id;
+	__u64 seq_num;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__bpf_map {
+	struct bpf_iter_meta *meta;
+	struct bpf_map *map;
+} __attribute__((preserve_access_index));
+
+__u32 map1_id = 0, map2_id = 0;
+__u32 map1_accessed = 0, map2_accessed = 0;
+__u64 map1_seqnum = 0, map2_seqnum1 = 0, map2_seqnum2 = 0;
+
+static volatile const __u32 print_len;
+static volatile const __u32 ret1;
+
+SEC("iter/bpf_map")
+int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct bpf_map *map = ctx->map;
+	__u64 seq_num;
+	int i, ret = 0;
+
+	if (map == (void *)0)
+		return 0;
+
+	/* only dump map1_id and map2_id */
+	if (map->id != map1_id && map->id != map2_id)
+		return 0;
+
+	seq_num = ctx->meta->seq_num;
+	if (map->id == map1_id) {
+		map1_seqnum = seq_num;
+		map1_accessed++;
+	}
+
+	if (map->id == map2_id) {
+		if (map2_accessed == 0) {
+			map2_seqnum1 = seq_num;
+			if (ret1)
+				ret = 1;
+		} else {
+			map2_seqnum2 = seq_num;
+		}
+		map2_accessed++;
+	}
+
+	/* fill seq_file buffer */
+	for (i = 0; i < print_len; i++)
+		bpf_seq_write(seq, &seq_num, sizeof(seq_num));
+
+	return ret;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h
new file mode 100644
index 000000000000..dee1339e6905
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2020 Facebook */
+/* "undefine" structs in vmlinux.h, because we "override" them below */
+#define bpf_iter_meta bpf_iter_meta___not_used
+#define bpf_iter__task bpf_iter__task___not_used
+#include "vmlinux.h"
+#undef bpf_iter_meta
+#undef bpf_iter__task
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+int count = 0;
+
+struct bpf_iter_meta {
+	struct seq_file *seq;
+	__u64 session_id;
+	__u64 seq_num;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__task {
+	struct bpf_iter_meta *meta;
+	struct task_struct *task;
+} __attribute__((preserve_access_index));
+
+SEC("iter/task")
+int dump_task(struct bpf_iter__task *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	char c;
+
+	if (count < 4) {
+		c = START_CHAR + count;
+		bpf_seq_write(seq, &c, sizeof(c));
+		count++;
+	}
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c
new file mode 100644
index 000000000000..3f757e30d7a0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/bpf.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+
+#include <sys/types.h>
+#include <sys/socket.h>
+
+int _version SEC("version") = 1;
+char _license[] SEC("license") = "GPL";
+
+__u16 g_serv_port = 0;
+
+static inline void set_ip(__u32 *dst, const struct in6_addr *src)
+{
+	dst[0] = src->in6_u.u6_addr32[0];
+	dst[1] = src->in6_u.u6_addr32[1];
+	dst[2] = src->in6_u.u6_addr32[2];
+	dst[3] = src->in6_u.u6_addr32[3];
+}
+
+static inline void set_tuple(struct bpf_sock_tuple *tuple,
+			     const struct ipv6hdr *ip6h,
+			     const struct tcphdr *tcph)
+{
+	set_ip(tuple->ipv6.saddr, &ip6h->daddr);
+	set_ip(tuple->ipv6.daddr, &ip6h->saddr);
+	tuple->ipv6.sport = tcph->dest;
+	tuple->ipv6.dport = tcph->source;
+}
+
+static inline int is_allowed_peer_cg(struct __sk_buff *skb,
+				     const struct ipv6hdr *ip6h,
+				     const struct tcphdr *tcph)
+{
+	__u64 cgid, acgid, peer_cgid, peer_acgid;
+	struct bpf_sock_tuple tuple;
+	size_t tuple_len = sizeof(tuple.ipv6);
+	struct bpf_sock *peer_sk;
+
+	set_tuple(&tuple, ip6h, tcph);
+
+	peer_sk = bpf_sk_lookup_tcp(skb, &tuple, tuple_len,
+				    BPF_F_CURRENT_NETNS, 0);
+	if (!peer_sk)
+		return 0;
+
+	cgid = bpf_skb_cgroup_id(skb);
+	peer_cgid = bpf_sk_cgroup_id(peer_sk);
+
+	acgid = bpf_skb_ancestor_cgroup_id(skb, 2);
+	peer_acgid = bpf_sk_ancestor_cgroup_id(peer_sk, 2);
+
+	bpf_sk_release(peer_sk);
+
+	return cgid && cgid == peer_cgid && acgid && acgid == peer_acgid;
+}
+
+SEC("cgroup_skb/ingress")
+int ingress_lookup(struct __sk_buff *skb)
+{
+	__u32 serv_port_key = 0;
+	struct ipv6hdr ip6h;
+	struct tcphdr tcph;
+
+	if (skb->protocol != bpf_htons(ETH_P_IPV6))
+		return 1;
+
+	/* For SYN packets coming to listening socket skb->remote_port will be
+	 * zero, so IPv6/TCP headers are loaded to identify remote peer
+	 * instead.
+	 */
+	if (bpf_skb_load_bytes(skb, 0, &ip6h, sizeof(ip6h)))
+		return 1;
+
+	if (ip6h.nexthdr != IPPROTO_TCP)
+		return 1;
+
+	if (bpf_skb_load_bytes(skb, sizeof(ip6h), &tcph, sizeof(tcph)))
+		return 1;
+
+	if (!g_serv_port)
+		return 0;
+
+	if (tcph.dest != g_serv_port)
+		return 1;
+
+	return is_allowed_peer_cg(skb, &ip6h, &tcph);
+}
diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c
index ad3c498a8150..1ab2c5eba86c 100644
--- a/tools/testing/selftests/bpf/progs/connect4_prog.c
+++ b/tools/testing/selftests/bpf/progs/connect4_prog.c
@@ -8,6 +8,9 @@
 #include <linux/in.h>
 #include <linux/in6.h>
 #include <sys/socket.h>
+#include <netinet/tcp.h>
+#include <linux/if.h>
+#include <errno.h>
 
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
@@ -16,6 +19,14 @@
 #define DST_REWRITE_IP4		0x7f000001U
 #define DST_REWRITE_PORT4	4444
 
+#ifndef TCP_CA_NAME_MAX
+#define TCP_CA_NAME_MAX 16
+#endif
+
+#ifndef IFNAMSIZ
+#define IFNAMSIZ 16
+#endif
+
 int _version SEC("version") = 1;
 
 __attribute__ ((noinline))
@@ -33,6 +44,66 @@ int do_bind(struct bpf_sock_addr *ctx)
 	return 1;
 }
 
+static __inline int verify_cc(struct bpf_sock_addr *ctx,
+			      char expected[TCP_CA_NAME_MAX])
+{
+	char buf[TCP_CA_NAME_MAX];
+	int i;
+
+	if (bpf_getsockopt(ctx, SOL_TCP, TCP_CONGESTION, &buf, sizeof(buf)))
+		return 1;
+
+	for (i = 0; i < TCP_CA_NAME_MAX; i++) {
+		if (buf[i] != expected[i])
+			return 1;
+		if (buf[i] == 0)
+			break;
+	}
+
+	return 0;
+}
+
+static __inline int set_cc(struct bpf_sock_addr *ctx)
+{
+	char reno[TCP_CA_NAME_MAX] = "reno";
+	char cubic[TCP_CA_NAME_MAX] = "cubic";
+
+	if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &reno, sizeof(reno)))
+		return 1;
+	if (verify_cc(ctx, reno))
+		return 1;
+
+	if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &cubic, sizeof(cubic)))
+		return 1;
+	if (verify_cc(ctx, cubic))
+		return 1;
+
+	return 0;
+}
+
+static __inline int bind_to_device(struct bpf_sock_addr *ctx)
+{
+	char veth1[IFNAMSIZ] = "test_sock_addr1";
+	char veth2[IFNAMSIZ] = "test_sock_addr2";
+	char missing[IFNAMSIZ] = "nonexistent_dev";
+	char del_bind[IFNAMSIZ] = "";
+
+	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+				&veth1, sizeof(veth1)))
+		return 1;
+	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+				&veth2, sizeof(veth2)))
+		return 1;
+	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+				&missing, sizeof(missing)) != -ENODEV)
+		return 1;
+	if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+				&del_bind, sizeof(del_bind)))
+		return 1;
+
+	return 0;
+}
+
 SEC("cgroup/connect4")
 int connect_v4_prog(struct bpf_sock_addr *ctx)
 {
@@ -46,6 +117,10 @@ int connect_v4_prog(struct bpf_sock_addr *ctx)
 	tuple.ipv4.daddr = bpf_htonl(DST_REWRITE_IP4);
 	tuple.ipv4.dport = bpf_htons(DST_REWRITE_PORT4);
 
+	/* Bind to device and unbind it. */
+	if (bind_to_device(ctx))
+		return 0;
+
 	if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
 		return 0;
 	else if (ctx->type == SOCK_STREAM)
@@ -66,6 +141,10 @@ int connect_v4_prog(struct bpf_sock_addr *ctx)
 
 	bpf_sk_release(sk);
 
+	/* Rewrite congestion control. */
+	if (ctx->type == SOCK_STREAM && set_cc(ctx))
+		return 0;
+
 	/* Rewrite destination. */
 	ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4);
 	ctx->user_port = bpf_htons(DST_REWRITE_PORT4);
diff --git a/tools/testing/selftests/bpf/progs/connect_force_port4.c b/tools/testing/selftests/bpf/progs/connect_force_port4.c
new file mode 100644
index 000000000000..7396308677a3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/connect_force_port4.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include <stdbool.h>
+
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <sys/socket.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+char _license[] SEC("license") = "GPL";
+int _version SEC("version") = 1;
+
+struct svc_addr {
+	__be32 addr;
+	__be16 port;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct svc_addr);
+} service_mapping SEC(".maps");
+
+SEC("cgroup/connect4")
+int connect4(struct bpf_sock_addr *ctx)
+{
+	struct sockaddr_in sa = {};
+	struct svc_addr *orig;
+
+	/* Force local address to 127.0.0.1:22222. */
+	sa.sin_family = AF_INET;
+	sa.sin_port = bpf_htons(22222);
+	sa.sin_addr.s_addr = bpf_htonl(0x7f000001);
+
+	if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
+		return 0;
+
+	/* Rewire service 1.2.3.4:60000 to backend 127.0.0.1:60123. */
+	if (ctx->user_port == bpf_htons(60000)) {
+		orig = bpf_sk_storage_get(&service_mapping, ctx->sk, 0,
+					  BPF_SK_STORAGE_GET_F_CREATE);
+		if (!orig)
+			return 0;
+
+		orig->addr = ctx->user_ip4;
+		orig->port = ctx->user_port;
+
+		ctx->user_ip4 = bpf_htonl(0x7f000001);
+		ctx->user_port = bpf_htons(60123);
+	}
+	return 1;
+}
+
+SEC("cgroup/getsockname4")
+int getsockname4(struct bpf_sock_addr *ctx)
+{
+	/* Expose local server as 1.2.3.4:60000 to client. */
+	if (ctx->user_port == bpf_htons(60123)) {
+		ctx->user_ip4 = bpf_htonl(0x01020304);
+		ctx->user_port = bpf_htons(60000);
+	}
+	return 1;
+}
+
+SEC("cgroup/getpeername4")
+int getpeername4(struct bpf_sock_addr *ctx)
+{
+	struct svc_addr *orig;
+
+	/* Expose service 1.2.3.4:60000 as peer instead of backend. */
+	if (ctx->user_port == bpf_htons(60123)) {
+		orig = bpf_sk_storage_get(&service_mapping, ctx->sk, 0, 0);
+		if (orig) {
+			ctx->user_ip4 = orig->addr;
+			ctx->user_port = orig->port;
+		}
+	}
+	return 1;
+}
diff --git a/tools/testing/selftests/bpf/progs/connect_force_port6.c b/tools/testing/selftests/bpf/progs/connect_force_port6.c
new file mode 100644
index 000000000000..c1a2b555e9ad
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/connect_force_port6.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <sys/socket.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+char _license[] SEC("license") = "GPL";
+int _version SEC("version") = 1;
+
+struct svc_addr {
+	__be32 addr[4];
+	__be16 port;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct svc_addr);
+} service_mapping SEC(".maps");
+
+SEC("cgroup/connect6")
+int connect6(struct bpf_sock_addr *ctx)
+{
+	struct sockaddr_in6 sa = {};
+	struct svc_addr *orig;
+
+	/* Force local address to [::1]:22223. */
+	sa.sin6_family = AF_INET6;
+	sa.sin6_port = bpf_htons(22223);
+	sa.sin6_addr.s6_addr32[3] = bpf_htonl(1);
+
+	if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
+		return 0;
+
+	/* Rewire service [fc00::1]:60000 to backend [::1]:60124. */
+	if (ctx->user_port == bpf_htons(60000)) {
+		orig = bpf_sk_storage_get(&service_mapping, ctx->sk, 0,
+					  BPF_SK_STORAGE_GET_F_CREATE);
+		if (!orig)
+			return 0;
+
+		orig->addr[0] = ctx->user_ip6[0];
+		orig->addr[1] = ctx->user_ip6[1];
+		orig->addr[2] = ctx->user_ip6[2];
+		orig->addr[3] = ctx->user_ip6[3];
+		orig->port = ctx->user_port;
+
+		ctx->user_ip6[0] = 0;
+		ctx->user_ip6[1] = 0;
+		ctx->user_ip6[2] = 0;
+		ctx->user_ip6[3] = bpf_htonl(1);
+		ctx->user_port = bpf_htons(60124);
+	}
+	return 1;
+}
+
+SEC("cgroup/getsockname6")
+int getsockname6(struct bpf_sock_addr *ctx)
+{
+	/* Expose local server as [fc00::1]:60000 to client. */
+	if (ctx->user_port == bpf_htons(60124)) {
+		ctx->user_ip6[0] = bpf_htonl(0xfc000000);
+		ctx->user_ip6[1] = 0;
+		ctx->user_ip6[2] = 0;
+		ctx->user_ip6[3] = bpf_htonl(1);
+		ctx->user_port = bpf_htons(60000);
+	}
+	return 1;
+}
+
+SEC("cgroup/getpeername6")
+int getpeername6(struct bpf_sock_addr *ctx)
+{
+	struct svc_addr *orig;
+
+	/* Expose service [fc00::1]:60000 as peer instead of backend. */
+	if (ctx->user_port == bpf_htons(60124)) {
+		orig = bpf_sk_storage_get(&service_mapping, ctx->sk, 0, 0);
+		if (orig) {
+			ctx->user_ip6[0] = orig->addr[0];
+			ctx->user_ip6[1] = orig->addr[1];
+			ctx->user_ip6[2] = orig->addr[2];
+			ctx->user_ip6[3] = orig->addr[3];
+			ctx->user_port = orig->port;
+		}
+	}
+	return 1;
+}
diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h
index 6d598cfbdb3e..34d84717c946 100644
--- a/tools/testing/selftests/bpf/progs/core_reloc_types.h
+++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h
@@ -379,7 +379,7 @@ struct core_reloc_arrays___equiv_zero_sz_arr {
 	struct core_reloc_arrays_substruct c[3];
 	struct core_reloc_arrays_substruct d[1][2];
 	/* equivalent to flexible array */
-	struct core_reloc_arrays_substruct f[0][2];
+	struct core_reloc_arrays_substruct f[][2];
 };
 
 struct core_reloc_arrays___fixed_arr {
diff --git a/tools/testing/selftests/bpf/progs/perfbuf_bench.c b/tools/testing/selftests/bpf/progs/perfbuf_bench.c
new file mode 100644
index 000000000000..e5ab4836a641
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/perfbuf_bench.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/bpf.h>
+#include <stdint.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(value_size, sizeof(int));
+	__uint(key_size, sizeof(int));
+} perfbuf SEC(".maps");
+
+const volatile int batch_cnt = 0;
+
+long sample_val = 42;
+long dropped __attribute__((aligned(128))) = 0;
+
+SEC("fentry/__x64_sys_getpgid")
+int bench_perfbuf(void *ctx)
+{
+	__u64 *sample;
+	int i;
+
+	for (i = 0; i < batch_cnt; i++) {
+		if (bpf_perf_event_output(ctx, &perfbuf, BPF_F_CURRENT_CPU,
+					  &sample_val, sizeof(sample_val)))
+			__sync_add_and_fetch(&dropped, 1);
+	}
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/ringbuf_bench.c b/tools/testing/selftests/bpf/progs/ringbuf_bench.c
new file mode 100644
index 000000000000..123607d314d6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/ringbuf_bench.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/bpf.h>
+#include <stdint.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_RINGBUF);
+} ringbuf SEC(".maps");
+
+const volatile int batch_cnt = 0;
+const volatile long use_output = 0;
+
+long sample_val = 42;
+long dropped __attribute__((aligned(128))) = 0;
+
+const volatile long wakeup_data_size = 0;
+
+static __always_inline long get_flags()
+{
+	long sz;
+
+	if (!wakeup_data_size)
+		return 0;
+
+	sz = bpf_ringbuf_query(&ringbuf, BPF_RB_AVAIL_DATA);
+	return sz >= wakeup_data_size ? BPF_RB_FORCE_WAKEUP : BPF_RB_NO_WAKEUP;
+}
+
+SEC("fentry/__x64_sys_getpgid")
+int bench_ringbuf(void *ctx)
+{
+	long *sample, flags;
+	int i;
+
+	if (!use_output) {
+		for (i = 0; i < batch_cnt; i++) {
+			sample = bpf_ringbuf_reserve(&ringbuf,
+					             sizeof(sample_val), 0);
+			if (!sample) {
+				__sync_add_and_fetch(&dropped, 1);
+			} else {
+				*sample = sample_val;
+				flags = get_flags();
+				bpf_ringbuf_submit(sample, flags);
+			}
+		}
+	} else {
+		for (i = 0; i < batch_cnt; i++) {
+			flags = get_flags();
+			if (bpf_ringbuf_output(&ringbuf, &sample_val,
+					       sizeof(sample_val), flags))
+				__sync_add_and_fetch(&dropped, 1);
+		}
+	}
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c
new file mode 100644
index 000000000000..e5093796be97
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2020 Facebook */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct inner_map {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} inner_map1 SEC(".maps"),
+  inner_map2 SEC(".maps");
+
+struct outer_arr {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__uint(max_entries, 3);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+	/* it's possible to use anonymous struct as inner map definition here */
+	__array(values, struct {
+		__uint(type, BPF_MAP_TYPE_ARRAY);
+		/* changing max_entries to 2 will fail during load
+		 * due to incompatibility with inner_map definition */
+		__uint(max_entries, 1);
+		__type(key, int);
+		__type(value, int);
+	});
+} outer_arr SEC(".maps") = {
+	/* (void *) cast is necessary because we didn't use `struct inner_map`
+	 * in __inner(values, ...)
+	 * Actually, a conscious effort is required to screw up initialization
+	 * of inner map slots, which is a great thing!
+	 */
+	.values = { (void *)&inner_map1, 0, (void *)&inner_map2 },
+};
+
+struct outer_hash {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__uint(max_entries, 5);
+	__uint(key_size, sizeof(int));
+	/* Here everything works flawlessly due to reuse of struct inner_map
+	 * and compiler will complain at the attempt to use non-inner_map
+	 * references below. This is great experience.
+	 */
+	__array(values, struct inner_map);
+} outer_hash SEC(".maps") = {
+	.values = {
+		[0] = &inner_map2,
+		[4] = &inner_map1,
+	},
+};
+
+int input = 0;
+
+SEC("raw_tp/sys_enter")
+int handle__sys_enter(void *ctx)
+{
+	struct inner_map *inner_map;
+	int key = 0, val;
+
+	inner_map = bpf_map_lookup_elem(&outer_arr, &key);
+	if (!inner_map)
+		return 1;
+	val = input;
+	bpf_map_update_elem(inner_map, &key, &val, 0);
+
+	inner_map = bpf_map_lookup_elem(&outer_hash, &key);
+	if (!inner_map)
+		return 1;
+	val = input + 1;
+	bpf_map_update_elem(inner_map, &key, &val, 0);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c
new file mode 100644
index 000000000000..f0b72e86bee5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c
@@ -0,0 +1,1061 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+// Copyright (c) 2019, 2020 Cloudflare
+
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+#include <string.h>
+
+#include <linux/bpf.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/pkt_cls.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#include "test_cls_redirect.h"
+
+#define offsetofend(TYPE, MEMBER) \
+	(offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER)))
+
+#define IP_OFFSET_MASK (0x1FFF)
+#define IP_MF (0x2000)
+
+char _license[] SEC("license") = "Dual BSD/GPL";
+
+/**
+ * Destination port and IP used for UDP encapsulation.
+ */
+static volatile const __be16 ENCAPSULATION_PORT;
+static volatile const __be32 ENCAPSULATION_IP;
+
+typedef struct {
+	uint64_t processed_packets_total;
+	uint64_t l3_protocol_packets_total_ipv4;
+	uint64_t l3_protocol_packets_total_ipv6;
+	uint64_t l4_protocol_packets_total_tcp;
+	uint64_t l4_protocol_packets_total_udp;
+	uint64_t accepted_packets_total_syn;
+	uint64_t accepted_packets_total_syn_cookies;
+	uint64_t accepted_packets_total_last_hop;
+	uint64_t accepted_packets_total_icmp_echo_request;
+	uint64_t accepted_packets_total_established;
+	uint64_t forwarded_packets_total_gue;
+	uint64_t forwarded_packets_total_gre;
+
+	uint64_t errors_total_unknown_l3_proto;
+	uint64_t errors_total_unknown_l4_proto;
+	uint64_t errors_total_malformed_ip;
+	uint64_t errors_total_fragmented_ip;
+	uint64_t errors_total_malformed_icmp;
+	uint64_t errors_total_unwanted_icmp;
+	uint64_t errors_total_malformed_icmp_pkt_too_big;
+	uint64_t errors_total_malformed_tcp;
+	uint64_t errors_total_malformed_udp;
+	uint64_t errors_total_icmp_echo_replies;
+	uint64_t errors_total_malformed_encapsulation;
+	uint64_t errors_total_encap_adjust_failed;
+	uint64_t errors_total_encap_buffer_too_small;
+	uint64_t errors_total_redirect_loop;
+} metrics_t;
+
+typedef enum {
+	INVALID = 0,
+	UNKNOWN,
+	ECHO_REQUEST,
+	SYN,
+	SYN_COOKIE,
+	ESTABLISHED,
+} verdict_t;
+
+typedef struct {
+	uint16_t src, dst;
+} flow_ports_t;
+
+_Static_assert(
+	sizeof(flow_ports_t) !=
+		offsetofend(struct bpf_sock_tuple, ipv4.dport) -
+			offsetof(struct bpf_sock_tuple, ipv4.sport) - 1,
+	"flow_ports_t must match sport and dport in struct bpf_sock_tuple");
+_Static_assert(
+	sizeof(flow_ports_t) !=
+		offsetofend(struct bpf_sock_tuple, ipv6.dport) -
+			offsetof(struct bpf_sock_tuple, ipv6.sport) - 1,
+	"flow_ports_t must match sport and dport in struct bpf_sock_tuple");
+
+typedef int ret_t;
+
+/* This is a bit of a hack. We need a return value which allows us to
+ * indicate that the regular flow of the program should continue,
+ * while allowing functions to use XDP_PASS and XDP_DROP, etc.
+ */
+static const ret_t CONTINUE_PROCESSING = -1;
+
+/* Convenience macro to call functions which return ret_t.
+ */
+#define MAYBE_RETURN(x)                           \
+	do {                                      \
+		ret_t __ret = x;                  \
+		if (__ret != CONTINUE_PROCESSING) \
+			return __ret;             \
+	} while (0)
+
+/* Linux packet pointers are either aligned to NET_IP_ALIGN (aka 2 bytes),
+ * or not aligned if the arch supports efficient unaligned access.
+ *
+ * Since the verifier ensures that eBPF packet accesses follow these rules,
+ * we can tell LLVM to emit code as if we always had a larger alignment.
+ * It will yell at us if we end up on a platform where this is not valid.
+ */
+typedef uint8_t *net_ptr __attribute__((align_value(8)));
+
+typedef struct buf {
+	struct __sk_buff *skb;
+	net_ptr head;
+	/* NB: tail musn't have alignment other than 1, otherwise
+	* LLVM will go and eliminate code, e.g. when checking packet lengths.
+	*/
+	uint8_t *const tail;
+} buf_t;
+
+static size_t buf_off(const buf_t *buf)
+{
+	/* Clang seems to optimize constructs like
+	 *    a - b + c
+	 * if c is known:
+	 *    r? = c
+	 *    r? -= b
+	 *    r? += a
+	 *
+	 * This is a problem if a and b are packet pointers,
+	 * since the verifier allows subtracting two pointers to
+	 * get a scalar, but not a scalar and a pointer.
+	 *
+	 * Use inline asm to break this optimization.
+	 */
+	size_t off = (size_t)buf->head;
+	asm("%0 -= %1" : "+r"(off) : "r"(buf->skb->data));
+	return off;
+}
+
+static bool buf_copy(buf_t *buf, void *dst, size_t len)
+{
+	if (bpf_skb_load_bytes(buf->skb, buf_off(buf), dst, len)) {
+		return false;
+	}
+
+	buf->head += len;
+	return true;
+}
+
+static bool buf_skip(buf_t *buf, const size_t len)
+{
+	/* Check whether off + len is valid in the non-linear part. */
+	if (buf_off(buf) + len > buf->skb->len) {
+		return false;
+	}
+
+	buf->head += len;
+	return true;
+}
+
+/* Returns a pointer to the start of buf, or NULL if len is
+ * larger than the remaining data. Consumes len bytes on a successful
+ * call.
+ *
+ * If scratch is not NULL, the function will attempt to load non-linear
+ * data via bpf_skb_load_bytes. On success, scratch is returned.
+ */
+static void *buf_assign(buf_t *buf, const size_t len, void *scratch)
+{
+	if (buf->head + len > buf->tail) {
+		if (scratch == NULL) {
+			return NULL;
+		}
+
+		return buf_copy(buf, scratch, len) ? scratch : NULL;
+	}
+
+	void *ptr = buf->head;
+	buf->head += len;
+	return ptr;
+}
+
+static bool pkt_skip_ipv4_options(buf_t *buf, const struct iphdr *ipv4)
+{
+	if (ipv4->ihl <= 5) {
+		return true;
+	}
+
+	return buf_skip(buf, (ipv4->ihl - 5) * 4);
+}
+
+static bool ipv4_is_fragment(const struct iphdr *ip)
+{
+	uint16_t frag_off = ip->frag_off & bpf_htons(IP_OFFSET_MASK);
+	return (ip->frag_off & bpf_htons(IP_MF)) != 0 || frag_off > 0;
+}
+
+static struct iphdr *pkt_parse_ipv4(buf_t *pkt, struct iphdr *scratch)
+{
+	struct iphdr *ipv4 = buf_assign(pkt, sizeof(*ipv4), scratch);
+	if (ipv4 == NULL) {
+		return NULL;
+	}
+
+	if (ipv4->ihl < 5) {
+		return NULL;
+	}
+
+	if (!pkt_skip_ipv4_options(pkt, ipv4)) {
+		return NULL;
+	}
+
+	return ipv4;
+}
+
+/* Parse the L4 ports from a packet, assuming a layout like TCP or UDP. */
+static bool pkt_parse_icmp_l4_ports(buf_t *pkt, flow_ports_t *ports)
+{
+	if (!buf_copy(pkt, ports, sizeof(*ports))) {
+		return false;
+	}
+
+	/* Ports in the L4 headers are reversed, since we are parsing an ICMP
+	 * payload which is going towards the eyeball.
+	 */
+	uint16_t dst = ports->src;
+	ports->src = ports->dst;
+	ports->dst = dst;
+	return true;
+}
+
+static uint16_t pkt_checksum_fold(uint32_t csum)
+{
+	/* The highest reasonable value for an IPv4 header
+	 * checksum requires two folds, so we just do that always.
+	 */
+	csum = (csum & 0xffff) + (csum >> 16);
+	csum = (csum & 0xffff) + (csum >> 16);
+	return (uint16_t)~csum;
+}
+
+static void pkt_ipv4_checksum(struct iphdr *iph)
+{
+	iph->check = 0;
+
+	/* An IP header without options is 20 bytes. Two of those
+	 * are the checksum, which we always set to zero. Hence,
+	 * the maximum accumulated value is 18 / 2 * 0xffff = 0x8fff7,
+	 * which fits in 32 bit.
+	 */
+	_Static_assert(sizeof(struct iphdr) == 20, "iphdr must be 20 bytes");
+	uint32_t acc = 0;
+	uint16_t *ipw = (uint16_t *)iph;
+
+#pragma clang loop unroll(full)
+	for (size_t i = 0; i < sizeof(struct iphdr) / 2; i++) {
+		acc += ipw[i];
+	}
+
+	iph->check = pkt_checksum_fold(acc);
+}
+
+static bool pkt_skip_ipv6_extension_headers(buf_t *pkt,
+					    const struct ipv6hdr *ipv6,
+					    uint8_t *upper_proto,
+					    bool *is_fragment)
+{
+	/* We understand five extension headers.
+	 * https://tools.ietf.org/html/rfc8200#section-4.1 states that all
+	 * headers should occur once, except Destination Options, which may
+	 * occur twice. Hence we give up after 6 headers.
+	 */
+	struct {
+		uint8_t next;
+		uint8_t len;
+	} exthdr = {
+		.next = ipv6->nexthdr,
+	};
+	*is_fragment = false;
+
+#pragma clang loop unroll(full)
+	for (int i = 0; i < 6; i++) {
+		switch (exthdr.next) {
+		case IPPROTO_FRAGMENT:
+			*is_fragment = true;
+			/* NB: We don't check that hdrlen == 0 as per spec. */
+			/* fallthrough; */
+
+		case IPPROTO_HOPOPTS:
+		case IPPROTO_ROUTING:
+		case IPPROTO_DSTOPTS:
+		case IPPROTO_MH:
+			if (!buf_copy(pkt, &exthdr, sizeof(exthdr))) {
+				return false;
+			}
+
+			/* hdrlen is in 8-octet units, and excludes the first 8 octets. */
+			if (!buf_skip(pkt,
+				      (exthdr.len + 1) * 8 - sizeof(exthdr))) {
+				return false;
+			}
+
+			/* Decode next header */
+			break;
+
+		default:
+			/* The next header is not one of the known extension
+			 * headers, treat it as the upper layer header.
+			 *
+			 * This handles IPPROTO_NONE.
+			 *
+			 * Encapsulating Security Payload (50) and Authentication
+			 * Header (51) also end up here (and will trigger an
+			 * unknown proto error later). They have a custom header
+			 * format and seem too esoteric to care about.
+			 */
+			*upper_proto = exthdr.next;
+			return true;
+		}
+	}
+
+	/* We never found an upper layer header. */
+	return false;
+}
+
+/* This function has to be inlined, because the verifier otherwise rejects it
+ * due to returning a pointer to the stack. This is technically correct, since
+ * scratch is allocated on the stack. However, this usage should be safe since
+ * it's the callers stack after all.
+ */
+static inline __attribute__((__always_inline__)) struct ipv6hdr *
+pkt_parse_ipv6(buf_t *pkt, struct ipv6hdr *scratch, uint8_t *proto,
+	       bool *is_fragment)
+{
+	struct ipv6hdr *ipv6 = buf_assign(pkt, sizeof(*ipv6), scratch);
+	if (ipv6 == NULL) {
+		return NULL;
+	}
+
+	if (!pkt_skip_ipv6_extension_headers(pkt, ipv6, proto, is_fragment)) {
+		return NULL;
+	}
+
+	return ipv6;
+}
+
+/* Global metrics, per CPU
+ */
+struct bpf_map_def metrics_map SEC("maps") = {
+	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
+	.key_size = sizeof(unsigned int),
+	.value_size = sizeof(metrics_t),
+	.max_entries = 1,
+};
+
+static metrics_t *get_global_metrics(void)
+{
+	uint64_t key = 0;
+	return bpf_map_lookup_elem(&metrics_map, &key);
+}
+
+static ret_t accept_locally(struct __sk_buff *skb, encap_headers_t *encap)
+{
+	const int payload_off =
+		sizeof(*encap) +
+		sizeof(struct in_addr) * encap->unigue.hop_count;
+	int32_t encap_overhead = payload_off - sizeof(struct ethhdr);
+
+	// Changing the ethertype if the encapsulated packet is ipv6
+	if (encap->gue.proto_ctype == IPPROTO_IPV6) {
+		encap->eth.h_proto = bpf_htons(ETH_P_IPV6);
+	}
+
+	if (bpf_skb_adjust_room(skb, -encap_overhead, BPF_ADJ_ROOM_MAC,
+				BPF_F_ADJ_ROOM_FIXED_GSO |
+				BPF_F_ADJ_ROOM_NO_CSUM_RESET) ||
+	    bpf_csum_level(skb, BPF_CSUM_LEVEL_DEC))
+		return TC_ACT_SHOT;
+
+	return bpf_redirect(skb->ifindex, BPF_F_INGRESS);
+}
+
+static ret_t forward_with_gre(struct __sk_buff *skb, encap_headers_t *encap,
+			      struct in_addr *next_hop, metrics_t *metrics)
+{
+	metrics->forwarded_packets_total_gre++;
+
+	const int payload_off =
+		sizeof(*encap) +
+		sizeof(struct in_addr) * encap->unigue.hop_count;
+	int32_t encap_overhead =
+		payload_off - sizeof(struct ethhdr) - sizeof(struct iphdr);
+	int32_t delta = sizeof(struct gre_base_hdr) - encap_overhead;
+	uint16_t proto = ETH_P_IP;
+
+	/* Loop protection: the inner packet's TTL is decremented as a safeguard
+	 * against any forwarding loop. As the only interesting field is the TTL
+	 * hop limit for IPv6, it is easier to use bpf_skb_load_bytes/bpf_skb_store_bytes
+	 * as they handle the split packets if needed (no need for the data to be
+	 * in the linear section).
+	 */
+	if (encap->gue.proto_ctype == IPPROTO_IPV6) {
+		proto = ETH_P_IPV6;
+		uint8_t ttl;
+		int rc;
+
+		rc = bpf_skb_load_bytes(
+			skb, payload_off + offsetof(struct ipv6hdr, hop_limit),
+			&ttl, 1);
+		if (rc != 0) {
+			metrics->errors_total_malformed_encapsulation++;
+			return TC_ACT_SHOT;
+		}
+
+		if (ttl == 0) {
+			metrics->errors_total_redirect_loop++;
+			return TC_ACT_SHOT;
+		}
+
+		ttl--;
+		rc = bpf_skb_store_bytes(
+			skb, payload_off + offsetof(struct ipv6hdr, hop_limit),
+			&ttl, 1, 0);
+		if (rc != 0) {
+			metrics->errors_total_malformed_encapsulation++;
+			return TC_ACT_SHOT;
+		}
+	} else {
+		uint8_t ttl;
+		int rc;
+
+		rc = bpf_skb_load_bytes(
+			skb, payload_off + offsetof(struct iphdr, ttl), &ttl,
+			1);
+		if (rc != 0) {
+			metrics->errors_total_malformed_encapsulation++;
+			return TC_ACT_SHOT;
+		}
+
+		if (ttl == 0) {
+			metrics->errors_total_redirect_loop++;
+			return TC_ACT_SHOT;
+		}
+
+		/* IPv4 also has a checksum to patch. While the TTL is only one byte,
+		 * this function only works for 2 and 4 bytes arguments (the result is
+		 * the same).
+		 */
+		rc = bpf_l3_csum_replace(
+			skb, payload_off + offsetof(struct iphdr, check), ttl,
+			ttl - 1, 2);
+		if (rc != 0) {
+			metrics->errors_total_malformed_encapsulation++;
+			return TC_ACT_SHOT;
+		}
+
+		ttl--;
+		rc = bpf_skb_store_bytes(
+			skb, payload_off + offsetof(struct iphdr, ttl), &ttl, 1,
+			0);
+		if (rc != 0) {
+			metrics->errors_total_malformed_encapsulation++;
+			return TC_ACT_SHOT;
+		}
+	}
+
+	if (bpf_skb_adjust_room(skb, delta, BPF_ADJ_ROOM_NET,
+				BPF_F_ADJ_ROOM_FIXED_GSO |
+				BPF_F_ADJ_ROOM_NO_CSUM_RESET) ||
+	    bpf_csum_level(skb, BPF_CSUM_LEVEL_INC)) {
+		metrics->errors_total_encap_adjust_failed++;
+		return TC_ACT_SHOT;
+	}
+
+	if (bpf_skb_pull_data(skb, sizeof(encap_gre_t))) {
+		metrics->errors_total_encap_buffer_too_small++;
+		return TC_ACT_SHOT;
+	}
+
+	buf_t pkt = {
+		.skb = skb,
+		.head = (uint8_t *)(long)skb->data,
+		.tail = (uint8_t *)(long)skb->data_end,
+	};
+
+	encap_gre_t *encap_gre = buf_assign(&pkt, sizeof(encap_gre_t), NULL);
+	if (encap_gre == NULL) {
+		metrics->errors_total_encap_buffer_too_small++;
+		return TC_ACT_SHOT;
+	}
+
+	encap_gre->ip.protocol = IPPROTO_GRE;
+	encap_gre->ip.daddr = next_hop->s_addr;
+	encap_gre->ip.saddr = ENCAPSULATION_IP;
+	encap_gre->ip.tot_len =
+		bpf_htons(bpf_ntohs(encap_gre->ip.tot_len) + delta);
+	encap_gre->gre.flags = 0;
+	encap_gre->gre.protocol = bpf_htons(proto);
+	pkt_ipv4_checksum((void *)&encap_gre->ip);
+
+	return bpf_redirect(skb->ifindex, 0);
+}
+
+static ret_t forward_to_next_hop(struct __sk_buff *skb, encap_headers_t *encap,
+				 struct in_addr *next_hop, metrics_t *metrics)
+{
+	/* swap L2 addresses */
+	/* This assumes that packets are received from a router.
+	 * So just swapping the MAC addresses here will make the packet go back to
+	 * the router, which will send it to the appropriate machine.
+	 */
+	unsigned char temp[ETH_ALEN];
+	memcpy(temp, encap->eth.h_dest, sizeof(temp));
+	memcpy(encap->eth.h_dest, encap->eth.h_source,
+	       sizeof(encap->eth.h_dest));
+	memcpy(encap->eth.h_source, temp, sizeof(encap->eth.h_source));
+
+	if (encap->unigue.next_hop == encap->unigue.hop_count - 1 &&
+	    encap->unigue.last_hop_gre) {
+		return forward_with_gre(skb, encap, next_hop, metrics);
+	}
+
+	metrics->forwarded_packets_total_gue++;
+	uint32_t old_saddr = encap->ip.saddr;
+	encap->ip.saddr = encap->ip.daddr;
+	encap->ip.daddr = next_hop->s_addr;
+	if (encap->unigue.next_hop < encap->unigue.hop_count) {
+		encap->unigue.next_hop++;
+	}
+
+	/* Remove ip->saddr, add next_hop->s_addr */
+	const uint64_t off = offsetof(typeof(*encap), ip.check);
+	int ret = bpf_l3_csum_replace(skb, off, old_saddr, next_hop->s_addr, 4);
+	if (ret < 0) {
+		return TC_ACT_SHOT;
+	}
+
+	return bpf_redirect(skb->ifindex, 0);
+}
+
+static ret_t skip_next_hops(buf_t *pkt, int n)
+{
+	switch (n) {
+	case 1:
+		if (!buf_skip(pkt, sizeof(struct in_addr)))
+			return TC_ACT_SHOT;
+	case 0:
+		return CONTINUE_PROCESSING;
+
+	default:
+		return TC_ACT_SHOT;
+	}
+}
+
+/* Get the next hop from the GLB header.
+ *
+ * Sets next_hop->s_addr to 0 if there are no more hops left.
+ * pkt is positioned just after the variable length GLB header
+ * iff the call is successful.
+ */
+static ret_t get_next_hop(buf_t *pkt, encap_headers_t *encap,
+			  struct in_addr *next_hop)
+{
+	if (encap->unigue.next_hop > encap->unigue.hop_count) {
+		return TC_ACT_SHOT;
+	}
+
+	/* Skip "used" next hops. */
+	MAYBE_RETURN(skip_next_hops(pkt, encap->unigue.next_hop));
+
+	if (encap->unigue.next_hop == encap->unigue.hop_count) {
+		/* No more next hops, we are at the end of the GLB header. */
+		next_hop->s_addr = 0;
+		return CONTINUE_PROCESSING;
+	}
+
+	if (!buf_copy(pkt, next_hop, sizeof(*next_hop))) {
+		return TC_ACT_SHOT;
+	}
+
+	/* Skip the remainig next hops (may be zero). */
+	return skip_next_hops(pkt, encap->unigue.hop_count -
+					   encap->unigue.next_hop - 1);
+}
+
+/* Fill a bpf_sock_tuple to be used with the socket lookup functions.
+ * This is a kludge that let's us work around verifier limitations:
+ *
+ *    fill_tuple(&t, foo, sizeof(struct iphdr), 123, 321)
+ *
+ * clang will substitue a costant for sizeof, which allows the verifier
+ * to track it's value. Based on this, it can figure out the constant
+ * return value, and calling code works while still being "generic" to
+ * IPv4 and IPv6.
+ */
+static uint64_t fill_tuple(struct bpf_sock_tuple *tuple, void *iph,
+			   uint64_t iphlen, uint16_t sport, uint16_t dport)
+{
+	switch (iphlen) {
+	case sizeof(struct iphdr): {
+		struct iphdr *ipv4 = (struct iphdr *)iph;
+		tuple->ipv4.daddr = ipv4->daddr;
+		tuple->ipv4.saddr = ipv4->saddr;
+		tuple->ipv4.sport = sport;
+		tuple->ipv4.dport = dport;
+		return sizeof(tuple->ipv4);
+	}
+
+	case sizeof(struct ipv6hdr): {
+		struct ipv6hdr *ipv6 = (struct ipv6hdr *)iph;
+		memcpy(&tuple->ipv6.daddr, &ipv6->daddr,
+		       sizeof(tuple->ipv6.daddr));
+		memcpy(&tuple->ipv6.saddr, &ipv6->saddr,
+		       sizeof(tuple->ipv6.saddr));
+		tuple->ipv6.sport = sport;
+		tuple->ipv6.dport = dport;
+		return sizeof(tuple->ipv6);
+	}
+
+	default:
+		return 0;
+	}
+}
+
+static verdict_t classify_tcp(struct __sk_buff *skb,
+			      struct bpf_sock_tuple *tuple, uint64_t tuplen,
+			      void *iph, struct tcphdr *tcp)
+{
+	struct bpf_sock *sk =
+		bpf_skc_lookup_tcp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0);
+	if (sk == NULL) {
+		return UNKNOWN;
+	}
+
+	if (sk->state != BPF_TCP_LISTEN) {
+		bpf_sk_release(sk);
+		return ESTABLISHED;
+	}
+
+	if (iph != NULL && tcp != NULL) {
+		/* Kludge: we've run out of arguments, but need the length of the ip header. */
+		uint64_t iphlen = sizeof(struct iphdr);
+		if (tuplen == sizeof(tuple->ipv6)) {
+			iphlen = sizeof(struct ipv6hdr);
+		}
+
+		if (bpf_tcp_check_syncookie(sk, iph, iphlen, tcp,
+					    sizeof(*tcp)) == 0) {
+			bpf_sk_release(sk);
+			return SYN_COOKIE;
+		}
+	}
+
+	bpf_sk_release(sk);
+	return UNKNOWN;
+}
+
+static verdict_t classify_udp(struct __sk_buff *skb,
+			      struct bpf_sock_tuple *tuple, uint64_t tuplen)
+{
+	struct bpf_sock *sk =
+		bpf_sk_lookup_udp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0);
+	if (sk == NULL) {
+		return UNKNOWN;
+	}
+
+	if (sk->state == BPF_TCP_ESTABLISHED) {
+		bpf_sk_release(sk);
+		return ESTABLISHED;
+	}
+
+	bpf_sk_release(sk);
+	return UNKNOWN;
+}
+
+static verdict_t classify_icmp(struct __sk_buff *skb, uint8_t proto,
+			       struct bpf_sock_tuple *tuple, uint64_t tuplen,
+			       metrics_t *metrics)
+{
+	switch (proto) {
+	case IPPROTO_TCP:
+		return classify_tcp(skb, tuple, tuplen, NULL, NULL);
+
+	case IPPROTO_UDP:
+		return classify_udp(skb, tuple, tuplen);
+
+	default:
+		metrics->errors_total_malformed_icmp++;
+		return INVALID;
+	}
+}
+
+static verdict_t process_icmpv4(buf_t *pkt, metrics_t *metrics)
+{
+	struct icmphdr icmp;
+	if (!buf_copy(pkt, &icmp, sizeof(icmp))) {
+		metrics->errors_total_malformed_icmp++;
+		return INVALID;
+	}
+
+	/* We should never receive encapsulated echo replies. */
+	if (icmp.type == ICMP_ECHOREPLY) {
+		metrics->errors_total_icmp_echo_replies++;
+		return INVALID;
+	}
+
+	if (icmp.type == ICMP_ECHO) {
+		return ECHO_REQUEST;
+	}
+
+	if (icmp.type != ICMP_DEST_UNREACH || icmp.code != ICMP_FRAG_NEEDED) {
+		metrics->errors_total_unwanted_icmp++;
+		return INVALID;
+	}
+
+	struct iphdr _ip4;
+	const struct iphdr *ipv4 = pkt_parse_ipv4(pkt, &_ip4);
+	if (ipv4 == NULL) {
+		metrics->errors_total_malformed_icmp_pkt_too_big++;
+		return INVALID;
+	}
+
+	/* The source address in the outer IP header is from the entity that
+	 * originated the ICMP message. Use the original IP header to restore
+	 * the correct flow tuple.
+	 */
+	struct bpf_sock_tuple tuple;
+	tuple.ipv4.saddr = ipv4->daddr;
+	tuple.ipv4.daddr = ipv4->saddr;
+
+	if (!pkt_parse_icmp_l4_ports(pkt, (flow_ports_t *)&tuple.ipv4.sport)) {
+		metrics->errors_total_malformed_icmp_pkt_too_big++;
+		return INVALID;
+	}
+
+	return classify_icmp(pkt->skb, ipv4->protocol, &tuple,
+			     sizeof(tuple.ipv4), metrics);
+}
+
+static verdict_t process_icmpv6(buf_t *pkt, metrics_t *metrics)
+{
+	struct icmp6hdr icmp6;
+	if (!buf_copy(pkt, &icmp6, sizeof(icmp6))) {
+		metrics->errors_total_malformed_icmp++;
+		return INVALID;
+	}
+
+	/* We should never receive encapsulated echo replies. */
+	if (icmp6.icmp6_type == ICMPV6_ECHO_REPLY) {
+		metrics->errors_total_icmp_echo_replies++;
+		return INVALID;
+	}
+
+	if (icmp6.icmp6_type == ICMPV6_ECHO_REQUEST) {
+		return ECHO_REQUEST;
+	}
+
+	if (icmp6.icmp6_type != ICMPV6_PKT_TOOBIG) {
+		metrics->errors_total_unwanted_icmp++;
+		return INVALID;
+	}
+
+	bool is_fragment;
+	uint8_t l4_proto;
+	struct ipv6hdr _ipv6;
+	const struct ipv6hdr *ipv6 =
+		pkt_parse_ipv6(pkt, &_ipv6, &l4_proto, &is_fragment);
+	if (ipv6 == NULL) {
+		metrics->errors_total_malformed_icmp_pkt_too_big++;
+		return INVALID;
+	}
+
+	if (is_fragment) {
+		metrics->errors_total_fragmented_ip++;
+		return INVALID;
+	}
+
+	/* Swap source and dest addresses. */
+	struct bpf_sock_tuple tuple;
+	memcpy(&tuple.ipv6.saddr, &ipv6->daddr, sizeof(tuple.ipv6.saddr));
+	memcpy(&tuple.ipv6.daddr, &ipv6->saddr, sizeof(tuple.ipv6.daddr));
+
+	if (!pkt_parse_icmp_l4_ports(pkt, (flow_ports_t *)&tuple.ipv6.sport)) {
+		metrics->errors_total_malformed_icmp_pkt_too_big++;
+		return INVALID;
+	}
+
+	return classify_icmp(pkt->skb, l4_proto, &tuple, sizeof(tuple.ipv6),
+			     metrics);
+}
+
+static verdict_t process_tcp(buf_t *pkt, void *iph, uint64_t iphlen,
+			     metrics_t *metrics)
+{
+	metrics->l4_protocol_packets_total_tcp++;
+
+	struct tcphdr _tcp;
+	struct tcphdr *tcp = buf_assign(pkt, sizeof(_tcp), &_tcp);
+	if (tcp == NULL) {
+		metrics->errors_total_malformed_tcp++;
+		return INVALID;
+	}
+
+	if (tcp->syn) {
+		return SYN;
+	}
+
+	struct bpf_sock_tuple tuple;
+	uint64_t tuplen =
+		fill_tuple(&tuple, iph, iphlen, tcp->source, tcp->dest);
+	return classify_tcp(pkt->skb, &tuple, tuplen, iph, tcp);
+}
+
+static verdict_t process_udp(buf_t *pkt, void *iph, uint64_t iphlen,
+			     metrics_t *metrics)
+{
+	metrics->l4_protocol_packets_total_udp++;
+
+	struct udphdr _udp;
+	struct udphdr *udph = buf_assign(pkt, sizeof(_udp), &_udp);
+	if (udph == NULL) {
+		metrics->errors_total_malformed_udp++;
+		return INVALID;
+	}
+
+	struct bpf_sock_tuple tuple;
+	uint64_t tuplen =
+		fill_tuple(&tuple, iph, iphlen, udph->source, udph->dest);
+	return classify_udp(pkt->skb, &tuple, tuplen);
+}
+
+static verdict_t process_ipv4(buf_t *pkt, metrics_t *metrics)
+{
+	metrics->l3_protocol_packets_total_ipv4++;
+
+	struct iphdr _ip4;
+	struct iphdr *ipv4 = pkt_parse_ipv4(pkt, &_ip4);
+	if (ipv4 == NULL) {
+		metrics->errors_total_malformed_ip++;
+		return INVALID;
+	}
+
+	if (ipv4->version != 4) {
+		metrics->errors_total_malformed_ip++;
+		return INVALID;
+	}
+
+	if (ipv4_is_fragment(ipv4)) {
+		metrics->errors_total_fragmented_ip++;
+		return INVALID;
+	}
+
+	switch (ipv4->protocol) {
+	case IPPROTO_ICMP:
+		return process_icmpv4(pkt, metrics);
+
+	case IPPROTO_TCP:
+		return process_tcp(pkt, ipv4, sizeof(*ipv4), metrics);
+
+	case IPPROTO_UDP:
+		return process_udp(pkt, ipv4, sizeof(*ipv4), metrics);
+
+	default:
+		metrics->errors_total_unknown_l4_proto++;
+		return INVALID;
+	}
+}
+
+static verdict_t process_ipv6(buf_t *pkt, metrics_t *metrics)
+{
+	metrics->l3_protocol_packets_total_ipv6++;
+
+	uint8_t l4_proto;
+	bool is_fragment;
+	struct ipv6hdr _ipv6;
+	struct ipv6hdr *ipv6 =
+		pkt_parse_ipv6(pkt, &_ipv6, &l4_proto, &is_fragment);
+	if (ipv6 == NULL) {
+		metrics->errors_total_malformed_ip++;
+		return INVALID;
+	}
+
+	if (ipv6->version != 6) {
+		metrics->errors_total_malformed_ip++;
+		return INVALID;
+	}
+
+	if (is_fragment) {
+		metrics->errors_total_fragmented_ip++;
+		return INVALID;
+	}
+
+	switch (l4_proto) {
+	case IPPROTO_ICMPV6:
+		return process_icmpv6(pkt, metrics);
+
+	case IPPROTO_TCP:
+		return process_tcp(pkt, ipv6, sizeof(*ipv6), metrics);
+
+	case IPPROTO_UDP:
+		return process_udp(pkt, ipv6, sizeof(*ipv6), metrics);
+
+	default:
+		metrics->errors_total_unknown_l4_proto++;
+		return INVALID;
+	}
+}
+
+SEC("classifier/cls_redirect")
+int cls_redirect(struct __sk_buff *skb)
+{
+	metrics_t *metrics = get_global_metrics();
+	if (metrics == NULL) {
+		return TC_ACT_SHOT;
+	}
+
+	metrics->processed_packets_total++;
+
+	/* Pass bogus packets as long as we're not sure they're
+	 * destined for us.
+	 */
+	if (skb->protocol != bpf_htons(ETH_P_IP)) {
+		return TC_ACT_OK;
+	}
+
+	encap_headers_t *encap;
+
+	/* Make sure that all encapsulation headers are available in
+	 * the linear portion of the skb. This makes it easy to manipulate them.
+	 */
+	if (bpf_skb_pull_data(skb, sizeof(*encap))) {
+		return TC_ACT_OK;
+	}
+
+	buf_t pkt = {
+		.skb = skb,
+		.head = (uint8_t *)(long)skb->data,
+		.tail = (uint8_t *)(long)skb->data_end,
+	};
+
+	encap = buf_assign(&pkt, sizeof(*encap), NULL);
+	if (encap == NULL) {
+		return TC_ACT_OK;
+	}
+
+	if (encap->ip.ihl != 5) {
+		/* We never have any options. */
+		return TC_ACT_OK;
+	}
+
+	if (encap->ip.daddr != ENCAPSULATION_IP ||
+	    encap->ip.protocol != IPPROTO_UDP) {
+		return TC_ACT_OK;
+	}
+
+	/* TODO Check UDP length? */
+	if (encap->udp.dest != ENCAPSULATION_PORT) {
+		return TC_ACT_OK;
+	}
+
+	/* We now know that the packet is destined to us, we can
+	 * drop bogus ones.
+	 */
+	if (ipv4_is_fragment((void *)&encap->ip)) {
+		metrics->errors_total_fragmented_ip++;
+		return TC_ACT_SHOT;
+	}
+
+	if (encap->gue.variant != 0) {
+		metrics->errors_total_malformed_encapsulation++;
+		return TC_ACT_SHOT;
+	}
+
+	if (encap->gue.control != 0) {
+		metrics->errors_total_malformed_encapsulation++;
+		return TC_ACT_SHOT;
+	}
+
+	if (encap->gue.flags != 0) {
+		metrics->errors_total_malformed_encapsulation++;
+		return TC_ACT_SHOT;
+	}
+
+	if (encap->gue.hlen !=
+	    sizeof(encap->unigue) / 4 + encap->unigue.hop_count) {
+		metrics->errors_total_malformed_encapsulation++;
+		return TC_ACT_SHOT;
+	}
+
+	if (encap->unigue.version != 0) {
+		metrics->errors_total_malformed_encapsulation++;
+		return TC_ACT_SHOT;
+	}
+
+	if (encap->unigue.reserved != 0) {
+		return TC_ACT_SHOT;
+	}
+
+	struct in_addr next_hop;
+	MAYBE_RETURN(get_next_hop(&pkt, encap, &next_hop));
+
+	if (next_hop.s_addr == 0) {
+		metrics->accepted_packets_total_last_hop++;
+		return accept_locally(skb, encap);
+	}
+
+	verdict_t verdict;
+	switch (encap->gue.proto_ctype) {
+	case IPPROTO_IPIP:
+		verdict = process_ipv4(&pkt, metrics);
+		break;
+
+	case IPPROTO_IPV6:
+		verdict = process_ipv6(&pkt, metrics);
+		break;
+
+	default:
+		metrics->errors_total_unknown_l3_proto++;
+		return TC_ACT_SHOT;
+	}
+
+	switch (verdict) {
+	case INVALID:
+		/* metrics have already been bumped */
+		return TC_ACT_SHOT;
+
+	case UNKNOWN:
+		return forward_to_next_hop(skb, encap, &next_hop, metrics);
+
+	case ECHO_REQUEST:
+		metrics->accepted_packets_total_icmp_echo_request++;
+		break;
+
+	case SYN:
+		if (encap->unigue.forward_syn) {
+			return forward_to_next_hop(skb, encap, &next_hop,
+						   metrics);
+		}
+
+		metrics->accepted_packets_total_syn++;
+		break;
+
+	case SYN_COOKIE:
+		metrics->accepted_packets_total_syn_cookies++;
+		break;
+
+	case ESTABLISHED:
+		metrics->accepted_packets_total_established++;
+		break;
+	}
+
+	return accept_locally(skb, encap);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.h b/tools/testing/selftests/bpf/progs/test_cls_redirect.h
new file mode 100644
index 000000000000..76eab0aacba0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/* Copyright 2019, 2020 Cloudflare */
+
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+#include <string.h>
+
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/udp.h>
+
+struct gre_base_hdr {
+	uint16_t flags;
+	uint16_t protocol;
+} __attribute__((packed));
+
+struct guehdr {
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	uint8_t hlen : 5, control : 1, variant : 2;
+#else
+	uint8_t variant : 2, control : 1, hlen : 5;
+#endif
+	uint8_t proto_ctype;
+	uint16_t flags;
+};
+
+struct unigue {
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	uint8_t _r : 2, last_hop_gre : 1, forward_syn : 1, version : 4;
+#else
+	uint8_t version : 4, forward_syn : 1, last_hop_gre : 1, _r : 2;
+#endif
+	uint8_t reserved;
+	uint8_t next_hop;
+	uint8_t hop_count;
+	// Next hops go here
+} __attribute__((packed));
+
+typedef struct {
+	struct ethhdr eth;
+	struct iphdr ip;
+	struct gre_base_hdr gre;
+} __attribute__((packed)) encap_gre_t;
+
+typedef struct {
+	struct ethhdr eth;
+	struct iphdr ip;
+	struct udphdr udp;
+	struct guehdr gue;
+	struct unigue unigue;
+} __attribute__((packed)) encap_headers_t;
diff --git a/tools/testing/selftests/bpf/progs/test_enable_stats.c b/tools/testing/selftests/bpf/progs/test_enable_stats.c
new file mode 100644
index 000000000000..01a002ade529
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_enable_stats.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/bpf.h>
+#include <stdint.h>
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u64 count = 0;
+
+SEC("raw_tracepoint/sys_enter")
+int test_enable_stats(void *ctx)
+{
+	count += 1;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_obj_id.c b/tools/testing/selftests/bpf/progs/test_obj_id.c
index 98b9de2fafd0..ded71b3ff6b4 100644
--- a/tools/testing/selftests/bpf/progs/test_obj_id.c
+++ b/tools/testing/selftests/bpf/progs/test_obj_id.c
@@ -3,16 +3,8 @@
  */
 #include <stddef.h>
 #include <linux/bpf.h>
-#include <linux/pkt_cls.h>
 #include <bpf/bpf_helpers.h>
 
-/* It is a dumb bpf program such that it must have no
- * issue to be loaded since testing the verifier is
- * not the focus here.
- */
-
-int _version SEC("version") = 1;
-
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
 	__uint(max_entries, 1);
@@ -20,13 +12,13 @@ struct {
 	__type(value, __u64);
 } test_map_id SEC(".maps");
 
-SEC("test_obj_id_dummy")
-int test_obj_id(struct __sk_buff *skb)
+SEC("raw_tp/sys_enter")
+int test_obj_id(void *ctx)
 {
 	__u32 key = 0;
 	__u64 *value;
 
 	value = bpf_map_lookup_elem(&test_map_id, &key);
 
-	return TC_ACT_OK;
+	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c
index abb7344b531f..42403d088abc 100644
--- a/tools/testing/selftests/bpf/progs/test_overhead.c
+++ b/tools/testing/selftests/bpf/progs/test_overhead.c
@@ -39,4 +39,10 @@ int BPF_PROG(prog5, struct task_struct *tsk, const char *buf, bool exec)
 	return 0;
 }
 
+SEC("fmod_ret/__set_task_comm")
+int BPF_PROG(prog6, struct task_struct *tsk, const char *buf, bool exec)
+{
+	return !tsk;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf.c b/tools/testing/selftests/bpf/progs/test_ringbuf.c
new file mode 100644
index 000000000000..8ba9959b036b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ringbuf.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct sample {
+	int pid;
+	int seq;
+	long value;
+	char comm[16];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_RINGBUF);
+	__uint(max_entries, 1 << 12);
+} ringbuf SEC(".maps");
+
+/* inputs */
+int pid = 0;
+long value = 0;
+long flags = 0;
+
+/* outputs */
+long total = 0;
+long discarded = 0;
+long dropped = 0;
+
+long avail_data = 0;
+long ring_size = 0;
+long cons_pos = 0;
+long prod_pos = 0;
+
+/* inner state */
+long seq = 0;
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int test_ringbuf(void *ctx)
+{
+	int cur_pid = bpf_get_current_pid_tgid() >> 32;
+	struct sample *sample;
+	int zero = 0;
+
+	if (cur_pid != pid)
+		return 0;
+
+	sample = bpf_ringbuf_reserve(&ringbuf, sizeof(*sample), 0);
+	if (!sample) {
+		__sync_fetch_and_add(&dropped, 1);
+		return 1;
+	}
+
+	sample->pid = pid;
+	bpf_get_current_comm(sample->comm, sizeof(sample->comm));
+	sample->value = value;
+
+	sample->seq = seq++;
+	__sync_fetch_and_add(&total, 1);
+
+	if (sample->seq & 1) {
+		/* copy from reserved sample to a new one... */
+		bpf_ringbuf_output(&ringbuf, sample, sizeof(*sample), flags);
+		/* ...and then discard reserved sample */
+		bpf_ringbuf_discard(sample, flags);
+		__sync_fetch_and_add(&discarded, 1);
+	} else {
+		bpf_ringbuf_submit(sample, flags);
+	}
+
+	avail_data = bpf_ringbuf_query(&ringbuf, BPF_RB_AVAIL_DATA);
+	ring_size = bpf_ringbuf_query(&ringbuf, BPF_RB_RING_SIZE);
+	cons_pos = bpf_ringbuf_query(&ringbuf, BPF_RB_CONS_POS);
+	prod_pos = bpf_ringbuf_query(&ringbuf, BPF_RB_PROD_POS);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c b/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c
new file mode 100644
index 000000000000..edf3b6953533
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct sample {
+	int pid;
+	int seq;
+	long value;
+	char comm[16];
+};
+
+struct ringbuf_map {
+	__uint(type, BPF_MAP_TYPE_RINGBUF);
+	__uint(max_entries, 1 << 12);
+} ringbuf1 SEC(".maps"),
+  ringbuf2 SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__uint(max_entries, 4);
+	__type(key, int);
+	__array(values, struct ringbuf_map);
+} ringbuf_arr SEC(".maps") = {
+	.values = {
+		[0] = &ringbuf1,
+		[2] = &ringbuf2,
+	},
+};
+
+/* inputs */
+int pid = 0;
+int target_ring = 0;
+long value = 0;
+
+/* outputs */
+long total = 0;
+long dropped = 0;
+long skipped = 0;
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int test_ringbuf(void *ctx)
+{
+	int cur_pid = bpf_get_current_pid_tgid() >> 32;
+	struct sample *sample;
+	void *rb;
+	int zero = 0;
+
+	if (cur_pid != pid)
+		return 0;
+
+	rb = bpf_map_lookup_elem(&ringbuf_arr, &target_ring);
+	if (!rb) {
+		skipped += 1;
+		return 1;
+	}
+
+	sample = bpf_ringbuf_reserve(rb, sizeof(*sample), 0);
+	if (!sample) {
+		dropped += 1;
+		return 1;
+	}
+
+	sample->pid = pid;
+	bpf_get_current_comm(sample->comm, sizeof(sample->comm));
+	sample->value = value;
+
+	sample->seq = total;
+	total += 1;
+
+	bpf_ringbuf_submit(sample, 0);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign.c b/tools/testing/selftests/bpf/progs/test_sk_assign.c
index 8f530843b4da..1ecd987005d2 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_assign.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_assign.c
@@ -16,6 +16,26 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
+/* Pin map under /sys/fs/bpf/tc/globals/<map name> */
+#define PIN_GLOBAL_NS 2
+
+/* Must match struct bpf_elf_map layout from iproute2 */
+struct {
+	__u32 type;
+	__u32 size_key;
+	__u32 size_value;
+	__u32 max_elem;
+	__u32 flags;
+	__u32 id;
+	__u32 pinning;
+} server_map SEC("maps") = {
+	.type = BPF_MAP_TYPE_SOCKMAP,
+	.size_key = sizeof(int),
+	.size_value  = sizeof(__u64),
+	.max_elem = 1,
+	.pinning = PIN_GLOBAL_NS,
+};
+
 int _version SEC("version") = 1;
 char _license[] SEC("license") = "GPL";
 
@@ -72,7 +92,9 @@ handle_udp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4)
 {
 	struct bpf_sock_tuple ln = {0};
 	struct bpf_sock *sk;
+	const int zero = 0;
 	size_t tuple_len;
+	__be16 dport;
 	int ret;
 
 	tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6);
@@ -83,32 +105,11 @@ handle_udp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4)
 	if (sk)
 		goto assign;
 
-	if (ipv4) {
-		if (tuple->ipv4.dport != bpf_htons(4321))
-			return TC_ACT_OK;
-
-		ln.ipv4.daddr = bpf_htonl(0x7f000001);
-		ln.ipv4.dport = bpf_htons(1234);
-
-		sk = bpf_sk_lookup_udp(skb, &ln, sizeof(ln.ipv4),
-					BPF_F_CURRENT_NETNS, 0);
-	} else {
-		if (tuple->ipv6.dport != bpf_htons(4321))
-			return TC_ACT_OK;
-
-		/* Upper parts of daddr are already zero. */
-		ln.ipv6.daddr[3] = bpf_htonl(0x1);
-		ln.ipv6.dport = bpf_htons(1234);
-
-		sk = bpf_sk_lookup_udp(skb, &ln, sizeof(ln.ipv6),
-					BPF_F_CURRENT_NETNS, 0);
-	}
+	dport = ipv4 ? tuple->ipv4.dport : tuple->ipv6.dport;
+	if (dport != bpf_htons(4321))
+		return TC_ACT_OK;
 
-	/* workaround: We can't do a single socket lookup here, because then
-	 * the compiler will likely spill tuple_len to the stack. This makes it
-	 * lose all bounds information in the verifier, which then rejects the
-	 * call as unsafe.
-	 */
+	sk = bpf_map_lookup_elem(&server_map, &zero);
 	if (!sk)
 		return TC_ACT_SHOT;
 
@@ -123,7 +124,9 @@ handle_tcp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4)
 {
 	struct bpf_sock_tuple ln = {0};
 	struct bpf_sock *sk;
+	const int zero = 0;
 	size_t tuple_len;
+	__be16 dport;
 	int ret;
 
 	tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6);
@@ -137,32 +140,11 @@ handle_tcp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4)
 		bpf_sk_release(sk);
 	}
 
-	if (ipv4) {
-		if (tuple->ipv4.dport != bpf_htons(4321))
-			return TC_ACT_OK;
+	dport = ipv4 ? tuple->ipv4.dport : tuple->ipv6.dport;
+	if (dport != bpf_htons(4321))
+		return TC_ACT_OK;
 
-		ln.ipv4.daddr = bpf_htonl(0x7f000001);
-		ln.ipv4.dport = bpf_htons(1234);
-
-		sk = bpf_skc_lookup_tcp(skb, &ln, sizeof(ln.ipv4),
-					BPF_F_CURRENT_NETNS, 0);
-	} else {
-		if (tuple->ipv6.dport != bpf_htons(4321))
-			return TC_ACT_OK;
-
-		/* Upper parts of daddr are already zero. */
-		ln.ipv6.daddr[3] = bpf_htonl(0x1);
-		ln.ipv6.dport = bpf_htons(1234);
-
-		sk = bpf_skc_lookup_tcp(skb, &ln, sizeof(ln.ipv6),
-					BPF_F_CURRENT_NETNS, 0);
-	}
-
-	/* workaround: We can't do a single socket lookup here, because then
-	 * the compiler will likely spill tuple_len to the stack. This makes it
-	 * lose all bounds information in the verifier, which then rejects the
-	 * call as unsafe.
-	 */
+	sk = bpf_map_lookup_elem(&server_map, &zero);
 	if (!sk)
 		return TC_ACT_SHOT;
 
diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
index d2b38fa6a5b0..e83d0b48d80c 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
@@ -73,6 +73,7 @@ int bpf_sk_lookup_test0(struct __sk_buff *skb)
 
 	tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6);
 	sk = bpf_sk_lookup_tcp(skb, tuple, tuple_len, BPF_F_CURRENT_NETNS, 0);
+	bpf_printk("sk=%d\n", sk ? 1 : 0);
 	if (sk)
 		bpf_sk_release(sk);
 	return sk ? TC_ACT_OK : TC_ACT_UNSPEC;
diff --git a/tools/testing/selftests/bpf/progs/test_skb_helpers.c b/tools/testing/selftests/bpf/progs/test_skb_helpers.c
new file mode 100644
index 000000000000..bb3fbf1a29e3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_skb_helpers.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define TEST_COMM_LEN 16
+
+struct {
+	__uint(type, BPF_MAP_TYPE_CGROUP_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, u32);
+	__type(value, u32);
+} cgroup_map SEC(".maps");
+
+char _license[] SEC("license") = "GPL";
+
+SEC("classifier/test_skb_helpers")
+int test_skb_helpers(struct __sk_buff *skb)
+{
+	struct task_struct *task;
+	char comm[TEST_COMM_LEN];
+	__u32 tpid;
+
+	task = (struct task_struct *)bpf_get_current_task();
+	bpf_probe_read_kernel(&tpid , sizeof(tpid), &task->tgid);
+	bpf_probe_read_kernel_str(&comm, sizeof(comm), &task->comm);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_skmsg_load_helpers.c b/tools/testing/selftests/bpf/progs/test_skmsg_load_helpers.c
new file mode 100644
index 000000000000..45e8fc75a739
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_skmsg_load_helpers.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Isovalent, Inc.
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 2);
+	__type(key, __u32);
+	__type(value, __u64);
+} sock_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKHASH);
+	__uint(max_entries, 2);
+	__type(key, __u32);
+	__type(value, __u64);
+} sock_hash SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, __u32);
+	__type(value, __u64);
+} socket_storage SEC(".maps");
+
+SEC("sk_msg")
+int prog_msg_verdict(struct sk_msg_md *msg)
+{
+	struct task_struct *task = (struct task_struct *)bpf_get_current_task();
+	int verdict = SK_PASS;
+	__u32 pid, tpid;
+	__u64 *sk_stg;
+
+	pid = bpf_get_current_pid_tgid() >> 32;
+	sk_stg = bpf_sk_storage_get(&socket_storage, msg->sk, 0, BPF_SK_STORAGE_GET_F_CREATE);
+	if (!sk_stg)
+		return SK_DROP;
+	*sk_stg = pid;
+	bpf_probe_read_kernel(&tpid , sizeof(tpid), &task->tgid);
+	if (pid != tpid)
+		verdict = SK_DROP;
+	bpf_sk_storage_delete(&socket_storage, (void *)msg->sk);
+	return verdict;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
index 9b4d3a68a91a..057036ca1111 100644
--- a/tools/testing/selftests/bpf/test_sockmap_kern.h
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
@@ -79,11 +79,18 @@ struct {
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__uint(max_entries, 1);
+	__uint(max_entries, 2);
 	__type(key, int);
 	__type(value, int);
 } sock_skb_opts SEC(".maps");
 
+struct {
+	__uint(type, TEST_MAP_TYPE);
+	__uint(max_entries, 20);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+} tls_sock_map SEC(".maps");
+
 SEC("sk_skb1")
 int bpf_prog1(struct __sk_buff *skb)
 {
@@ -110,8 +117,6 @@ int bpf_prog2(struct __sk_buff *skb)
 		flags = *f;
 	}
 
-	bpf_printk("sk_skb2: redirect(%iB) flags=%i\n",
-		   len, flags);
 #ifdef SOCKMAP
 	return bpf_sk_redirect_map(skb, &sock_map, ret, flags);
 #else
@@ -120,6 +125,43 @@ int bpf_prog2(struct __sk_buff *skb)
 
 }
 
+SEC("sk_skb3")
+int bpf_prog3(struct __sk_buff *skb)
+{
+	const int one = 1;
+	int err, *f, ret = SK_PASS;
+	void *data_end;
+	char *c;
+
+	err = bpf_skb_pull_data(skb, 19);
+	if (err)
+		goto tls_out;
+
+	c = (char *)(long)skb->data;
+	data_end = (void *)(long)skb->data_end;
+
+	if (c + 18 < data_end)
+		memcpy(&c[13], "PASS", 4);
+	f = bpf_map_lookup_elem(&sock_skb_opts, &one);
+	if (f && *f) {
+		__u64 flags = 0;
+
+		ret = 0;
+		flags = *f;
+#ifdef SOCKMAP
+		return bpf_sk_redirect_map(skb, &tls_sock_map, ret, flags);
+#else
+		return bpf_sk_redirect_hash(skb, &tls_sock_map, &ret, flags);
+#endif
+	}
+
+	f = bpf_map_lookup_elem(&sock_skb_opts, &one);
+	if (f && *f)
+		ret = SK_DROP;
+tls_out:
+	return ret;
+}
+
 SEC("sockops")
 int bpf_sockmap(struct bpf_sock_ops *skops)
 {
@@ -143,8 +185,6 @@ int bpf_sockmap(struct bpf_sock_ops *skops)
 			err = bpf_sock_hash_update(skops, &sock_map, &ret,
 						   BPF_NOEXIST);
 #endif
-			bpf_printk("passive(%i -> %i) map ctx update err: %d\n",
-				   lport, bpf_ntohl(rport), err);
 		}
 		break;
 	case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
@@ -160,8 +200,6 @@ int bpf_sockmap(struct bpf_sock_ops *skops)
 			err = bpf_sock_hash_update(skops, &sock_map, &ret,
 						   BPF_NOEXIST);
 #endif
-			bpf_printk("active(%i -> %i) map ctx update err: %d\n",
-				   lport, bpf_ntohl(rport), err);
 		}
 		break;
 	default:
@@ -199,72 +237,6 @@ int bpf_prog4(struct sk_msg_md *msg)
 }
 
 SEC("sk_msg2")
-int bpf_prog5(struct sk_msg_md *msg)
-{
-	int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
-	int *start, *end, *start_push, *end_push, *start_pop, *pop;
-	int *bytes, len1, len2 = 0, len3, len4;
-	int err1 = -1, err2 = -1;
-
-	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
-	if (bytes)
-		err1 = bpf_msg_apply_bytes(msg, *bytes);
-	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
-	if (bytes)
-		err2 = bpf_msg_cork_bytes(msg, *bytes);
-	len1 = (__u64)msg->data_end - (__u64)msg->data;
-	start = bpf_map_lookup_elem(&sock_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_bytes, &one);
-	if (start && end) {
-		int err;
-
-		bpf_printk("sk_msg2: pull(%i:%i)\n",
-			   start ? *start : 0, end ? *end : 0);
-		err = bpf_msg_pull_data(msg, *start, *end, 0);
-		if (err)
-			bpf_printk("sk_msg2: pull_data err %i\n",
-				   err);
-		len2 = (__u64)msg->data_end - (__u64)msg->data;
-		bpf_printk("sk_msg2: length update %i->%i\n",
-			   len1, len2);
-	}
-
-	start_push = bpf_map_lookup_elem(&sock_bytes, &two);
-	end_push = bpf_map_lookup_elem(&sock_bytes, &three);
-	if (start_push && end_push) {
-		int err;
-
-		bpf_printk("sk_msg2: push(%i:%i)\n",
-			   start_push ? *start_push : 0,
-			   end_push ? *end_push : 0);
-		err = bpf_msg_push_data(msg, *start_push, *end_push, 0);
-		if (err)
-			bpf_printk("sk_msg2: push_data err %i\n", err);
-		len3 = (__u64)msg->data_end - (__u64)msg->data;
-		bpf_printk("sk_msg2: length push_update %i->%i\n",
-			   len2 ? len2 : len1, len3);
-	}
-	start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
-	pop = bpf_map_lookup_elem(&sock_bytes, &five);
-	if (start_pop && pop) {
-		int err;
-
-		bpf_printk("sk_msg2: pop(%i@%i)\n",
-			   start_pop, pop);
-		err = bpf_msg_pop_data(msg, *start_pop, *pop, 0);
-		if (err)
-			bpf_printk("sk_msg2: pop_data err %i\n", err);
-		len4 = (__u64)msg->data_end - (__u64)msg->data;
-		bpf_printk("sk_msg2: length pop_data %i->%i\n",
-			   len1 ? len1 : 0,  len4);
-	}
-
-	bpf_printk("sk_msg2: data length %i err1 %i err2 %i\n",
-		   len1, err1, err2);
-	return SK_PASS;
-}
-
-SEC("sk_msg3")
 int bpf_prog6(struct sk_msg_md *msg)
 {
 	int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, key = 0;
@@ -305,86 +277,7 @@ int bpf_prog6(struct sk_msg_md *msg)
 #endif
 }
 
-SEC("sk_msg4")
-int bpf_prog7(struct sk_msg_md *msg)
-{
-	int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop, *f;
-	int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
-	int len1, len2 = 0, len3, len4;
-	int err1 = 0, err2 = 0, key = 0;
-	__u64 flags = 0;
-
-		int err;
-	bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
-	if (bytes)
-		err1 = bpf_msg_apply_bytes(msg, *bytes);
-	bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
-	if (bytes)
-		err2 = bpf_msg_cork_bytes(msg, *bytes);
-	len1 = (__u64)msg->data_end - (__u64)msg->data;
-
-	start = bpf_map_lookup_elem(&sock_bytes, &zero);
-	end = bpf_map_lookup_elem(&sock_bytes, &one);
-	if (start && end) {
-		bpf_printk("sk_msg2: pull(%i:%i)\n",
-			   start ? *start : 0, end ? *end : 0);
-		err = bpf_msg_pull_data(msg, *start, *end, 0);
-		if (err)
-			bpf_printk("sk_msg2: pull_data err %i\n",
-				   err);
-		len2 = (__u64)msg->data_end - (__u64)msg->data;
-		bpf_printk("sk_msg2: length update %i->%i\n",
-			   len1, len2);
-	}
-
-	start_push = bpf_map_lookup_elem(&sock_bytes, &two);
-	end_push = bpf_map_lookup_elem(&sock_bytes, &three);
-	if (start_push && end_push) {
-		bpf_printk("sk_msg4: push(%i:%i)\n",
-			   start_push ? *start_push : 0,
-			   end_push ? *end_push : 0);
-		err = bpf_msg_push_data(msg, *start_push, *end_push, 0);
-		if (err)
-			bpf_printk("sk_msg4: push_data err %i\n",
-				   err);
-		len3 = (__u64)msg->data_end - (__u64)msg->data;
-		bpf_printk("sk_msg4: length push_update %i->%i\n",
-			   len2 ? len2 : len1, len3);
-	}
-
-	start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
-	pop = bpf_map_lookup_elem(&sock_bytes, &five);
-	if (start_pop && pop) {
-		int err;
-
-		bpf_printk("sk_msg4: pop(%i@%i)\n",
-			   start_pop, pop);
-		err = bpf_msg_pop_data(msg, *start_pop, *pop, 0);
-		if (err)
-			bpf_printk("sk_msg4: pop_data err %i\n", err);
-		len4 = (__u64)msg->data_end - (__u64)msg->data;
-		bpf_printk("sk_msg4: length pop_data %i->%i\n",
-			   len1 ? len1 : 0,  len4);
-	}
-
-
-	f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
-	if (f && *f) {
-		key = 2;
-		flags = *f;
-	}
-	bpf_printk("sk_msg3: redirect(%iB) flags=%i err=%i\n",
-		   len1, flags, err1 ? err1 : err2);
-#ifdef SOCKMAP
-	err = bpf_msg_redirect_map(msg, &sock_map_redir, key, flags);
-#else
-	err = bpf_msg_redirect_hash(msg, &sock_map_redir, &key, flags);
-#endif
-	bpf_printk("sk_msg3: err %i\n", err);
-	return err;
-}
-
-SEC("sk_msg5")
+SEC("sk_msg3")
 int bpf_prog8(struct sk_msg_md *msg)
 {
 	void *data_end = (void *)(long) msg->data_end;
@@ -401,7 +294,7 @@ int bpf_prog8(struct sk_msg_md *msg)
 	}
 	return SK_PASS;
 }
-SEC("sk_msg6")
+SEC("sk_msg4")
 int bpf_prog9(struct sk_msg_md *msg)
 {
 	void *data_end = (void *)(long) msg->data_end;
@@ -419,7 +312,7 @@ int bpf_prog9(struct sk_msg_md *msg)
 	return SK_PASS;
 }
 
-SEC("sk_msg7")
+SEC("sk_msg5")
 int bpf_prog10(struct sk_msg_md *msg)
 {
 	int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop;
@@ -443,7 +336,6 @@ int bpf_prog10(struct sk_msg_md *msg)
 	pop = bpf_map_lookup_elem(&sock_bytes, &five);
 	if (start_pop && pop)
 		bpf_msg_pop_data(msg, *start_pop, *pop, 0);
-	bpf_printk("return sk drop\n");
 	return SK_DROP;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
index 2d0b0b82a78a..50525235380e 100644
--- a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
+++ b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
@@ -45,7 +45,7 @@ int sysctl_tcp_mem(struct bpf_sysctl *ctx)
 	unsigned long tcp_mem[3] = {0, 0, 0};
 	char value[MAX_VALUE_STR_LEN];
 	unsigned char i, off = 0;
-	int ret;
+	volatile int ret;
 
 	if (ctx->write)
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c
new file mode 100644
index 000000000000..3d66599eee2e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("xdp_adjust_tail_grow")
+int _xdp_adjust_tail_grow(struct xdp_md *xdp)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	unsigned int data_len;
+	int offset = 0;
+
+	/* Data length determine test case */
+	data_len = data_end - data;
+
+	if (data_len == 54) { /* sizeof(pkt_v4) */
+		offset = 4096; /* test too large offset */
+	} else if (data_len == 74) { /* sizeof(pkt_v6) */
+		offset = 40;
+	} else if (data_len == 64) {
+		offset = 128;
+	} else if (data_len == 128) {
+		offset = 4096 - 256 - 320 - data_len; /* Max tail grow 3520 */
+	} else {
+		return XDP_ABORTED; /* No matching test */
+	}
+
+	if (bpf_xdp_adjust_tail(xdp, offset))
+		return XDP_DROP;
+	return XDP_TX;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_adjust_tail.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c
index b7fc85769bdc..22065a9cfb25 100644
--- a/tools/testing/selftests/bpf/progs/test_adjust_tail.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Copyright (c) 2018 Facebook
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Facebook
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -11,15 +11,15 @@
 
 int _version SEC("version") = 1;
 
-SEC("xdp_adjust_tail")
-int _xdp_adjust_tail(struct xdp_md *xdp)
+SEC("xdp_adjust_tail_shrink")
+int _xdp_adjust_tail_shrink(struct xdp_md *xdp)
 {
 	void *data_end = (void *)(long)xdp->data_end;
 	void *data = (void *)(long)xdp->data;
 	int offset = 0;
 
-	if (data_end - data == 54)
-		offset = 256;
+	if (data_end - data == 54) /* sizeof(pkt_v4) */
+		offset = 256; /* shrink too much */
 	else
 		offset = 20;
 	if (bpf_xdp_adjust_tail(xdp, 0 - offset))
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c
new file mode 100644
index 000000000000..e5c0f131c8a7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+/* fails to load without expected_attach_type = BPF_XDP_DEVMAP
+ * because of access to egress_ifindex
+ */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+SEC("xdp_dm_log")
+int xdpdm_devlog(struct xdp_md *ctx)
+{
+	char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n";
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	unsigned int len = data_end - data;
+
+	bpf_trace_printk(fmt, sizeof(fmt),
+			 ctx->ingress_ifindex, ctx->egress_ifindex, len);
+
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c
new file mode 100644
index 000000000000..deef0e050863
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_devmap_val));
+	__uint(max_entries, 4);
+} dm_ports SEC(".maps");
+
+SEC("xdp_redir")
+int xdp_redir_prog(struct xdp_md *ctx)
+{
+	return bpf_redirect_map(&dm_ports, 1, 0);
+}
+
+/* invalid program on DEVMAP entry;
+ * SEC name means expected attach type not set
+ */
+SEC("xdp_dummy")
+int xdp_dummy_prog(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
+/* valid program on DEVMAP entry via SEC name;
+ * has access to egress and ingress ifindex
+ */
+SEC("xdp_devmap")
+int xdp_dummy_dm(struct xdp_md *ctx)
+{
+	char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n";
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	unsigned int len = data_end - data;
+
+	bpf_trace_printk(fmt, sizeof(fmt),
+			 ctx->ingress_ifindex, ctx->egress_ifindex, len);
+
+	return XDP_PASS;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c
new file mode 100644
index 000000000000..8b36b6640e7e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/trigger_bench.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/bpf.h>
+#include <asm/unistd.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+long hits = 0;
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int bench_trigger_tp(void *ctx)
+{
+	__sync_add_and_fetch(&hits, 1);
+	return 0;
+}
+
+SEC("raw_tp/sys_enter")
+int BPF_PROG(bench_trigger_raw_tp, struct pt_regs *regs, long id)
+{
+	if (id == __NR_getpgid)
+		__sync_add_and_fetch(&hits, 1);
+	return 0;
+}
+
+SEC("kprobe/__x64_sys_getpgid")
+int bench_trigger_kprobe(void *ctx)
+{
+	__sync_add_and_fetch(&hits, 1);
+	return 0;
+}
+
+SEC("fentry/__x64_sys_getpgid")
+int bench_trigger_fentry(void *ctx)
+{
+	__sync_add_and_fetch(&hits, 1);
+	return 0;
+}
+
+SEC("fmod_ret/__x64_sys_getpgid")
+int bench_trigger_fmodret(void *ctx)
+{
+	__sync_add_and_fetch(&hits, 1);
+	return -22;
+}
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index c6766b2cff85..6a12a0e01e07 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -1394,23 +1394,25 @@ static void test_map_rdonly(void)
 
 	key = 1;
 	value = 1234;
-	/* Insert key=1 element. */
+	/* Try to insert key=1 element. */
 	assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == -1 &&
 	       errno == EPERM);
 
-	/* Check that key=2 is not found. */
+	/* Check that key=1 is not found. */
 	assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT);
 	assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == ENOENT);
+
+	close(fd);
 }
 
-static void test_map_wronly(void)
+static void test_map_wronly_hash(void)
 {
 	int fd, key = 0, value = 0;
 
 	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
 			    MAP_SIZE, map_flags | BPF_F_WRONLY);
 	if (fd < 0) {
-		printf("Failed to create map for read only test '%s'!\n",
+		printf("Failed to create map for write only test '%s'!\n",
 		       strerror(errno));
 		exit(1);
 	}
@@ -1420,9 +1422,49 @@ static void test_map_wronly(void)
 	/* Insert key=1 element. */
 	assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0);
 
-	/* Check that key=2 is not found. */
+	/* Check that reading elements and keys from the map is not allowed. */
 	assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == EPERM);
 	assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == EPERM);
+
+	close(fd);
+}
+
+static void test_map_wronly_stack_or_queue(enum bpf_map_type map_type)
+{
+	int fd, value = 0;
+
+	assert(map_type == BPF_MAP_TYPE_QUEUE ||
+	       map_type == BPF_MAP_TYPE_STACK);
+	fd = bpf_create_map(map_type, 0, sizeof(value), MAP_SIZE,
+			    map_flags | BPF_F_WRONLY);
+	/* Stack/Queue maps do not support BPF_F_NO_PREALLOC */
+	if (map_flags & BPF_F_NO_PREALLOC) {
+		assert(fd < 0 && errno == EINVAL);
+		return;
+	}
+	if (fd < 0) {
+		printf("Failed to create map '%s'!\n", strerror(errno));
+		exit(1);
+	}
+
+	value = 1234;
+	assert(bpf_map_update_elem(fd, NULL, &value, BPF_ANY) == 0);
+
+	/* Peek element should fail */
+	assert(bpf_map_lookup_elem(fd, NULL, &value) == -1 && errno == EPERM);
+
+	/* Pop element should fail */
+	assert(bpf_map_lookup_and_delete_elem(fd, NULL, &value) == -1 &&
+	       errno == EPERM);
+
+	close(fd);
+}
+
+static void test_map_wronly(void)
+{
+	test_map_wronly_hash();
+	test_map_wronly_stack_or_queue(BPF_MAP_TYPE_STACK);
+	test_map_wronly_stack_or_queue(BPF_MAP_TYPE_QUEUE);
 }
 
 static void prepare_reuseport_grp(int type, int map_fd, size_t map_elem_size,
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index b521e0a512b6..54fa5fa688ce 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -222,23 +222,6 @@ int test__join_cgroup(const char *path)
 	return fd;
 }
 
-struct ipv4_packet pkt_v4 = {
-	.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
-	.iph.ihl = 5,
-	.iph.protocol = IPPROTO_TCP,
-	.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
-	.tcp.urg_ptr = 123,
-	.tcp.doff = 5,
-};
-
-struct ipv6_packet pkt_v6 = {
-	.eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
-	.iph.nexthdr = IPPROTO_TCP,
-	.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
-	.tcp.urg_ptr = 123,
-	.tcp.doff = 5,
-};
-
 int bpf_find_map(const char *test, struct bpf_object *obj, const char *name)
 {
 	struct bpf_map *map;
@@ -351,25 +334,13 @@ int extract_build_id(char *build_id, size_t size)
 		len = size;
 	memcpy(build_id, line, len);
 	build_id[len] = '\0';
+	free(line);
 	return 0;
 err:
 	fclose(fp);
 	return -1;
 }
 
-void *spin_lock_thread(void *arg)
-{
-	__u32 duration, retval;
-	int err, prog_fd = *(u32 *) arg;
-
-	err = bpf_prog_test_run(prog_fd, 10000, &pkt_v4, sizeof(pkt_v4),
-				NULL, NULL, &retval, &duration);
-	CHECK(err || retval, "",
-	      "err %d errno %d retval %d duration %d\n",
-	      err, errno, retval, duration);
-	pthread_exit(arg);
-}
-
 /* extern declarations for test funcs */
 #define DEFINE_TEST(name) extern void test_##name(void);
 #include <prog_tests/tests.h>
@@ -420,6 +391,18 @@ static int libbpf_print_fn(enum libbpf_print_level level,
 	return 0;
 }
 
+static void free_str_set(const struct str_set *set)
+{
+	int i;
+
+	if (!set)
+		return;
+
+	for (i = 0; i < set->cnt; i++)
+		free((void *)set->strs[i]);
+	free(set->strs);
+}
+
 static int parse_str_list(const char *s, struct str_set *set)
 {
 	char *input, *state = NULL, *next, **tmp, **strs = NULL;
@@ -455,67 +438,6 @@ err:
 	return -ENOMEM;
 }
 
-int parse_num_list(const char *s, struct test_selector *sel)
-{
-	int i, set_len = 0, new_len, num, start = 0, end = -1;
-	bool *set = NULL, *tmp, parsing_end = false;
-	char *next;
-
-	while (s[0]) {
-		errno = 0;
-		num = strtol(s, &next, 10);
-		if (errno)
-			return -errno;
-
-		if (parsing_end)
-			end = num;
-		else
-			start = num;
-
-		if (!parsing_end && *next == '-') {
-			s = next + 1;
-			parsing_end = true;
-			continue;
-		} else if (*next == ',') {
-			parsing_end = false;
-			s = next + 1;
-			end = num;
-		} else if (*next == '\0') {
-			parsing_end = false;
-			s = next;
-			end = num;
-		} else {
-			return -EINVAL;
-		}
-
-		if (start > end)
-			return -EINVAL;
-
-		if (end + 1 > set_len) {
-			new_len = end + 1;
-			tmp = realloc(set, new_len);
-			if (!tmp) {
-				free(set);
-				return -ENOMEM;
-			}
-			for (i = set_len; i < start; i++)
-				tmp[i] = false;
-			set = tmp;
-			set_len = new_len;
-		}
-		for (i = start; i <= end; i++)
-			set[i] = true;
-	}
-
-	if (!set)
-		return -EINVAL;
-
-	sel->num_set = set;
-	sel->num_set_len = set_len;
-
-	return 0;
-}
-
 extern int extra_prog_load_log_flags;
 
 static error_t parse_arg(int key, char *arg, struct argp_state *state)
@@ -529,13 +451,15 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 		if (subtest_str) {
 			*subtest_str = '\0';
 			if (parse_num_list(subtest_str + 1,
-					   &env->subtest_selector)) {
+					   &env->subtest_selector.num_set,
+					   &env->subtest_selector.num_set_len)) {
 				fprintf(stderr,
 					"Failed to parse subtest numbers.\n");
 				return -EINVAL;
 			}
 		}
-		if (parse_num_list(arg, &env->test_selector)) {
+		if (parse_num_list(arg, &env->test_selector.num_set,
+				   &env->test_selector.num_set_len)) {
 			fprintf(stderr, "Failed to parse test numbers.\n");
 			return -EINVAL;
 		}
@@ -756,11 +680,11 @@ int main(int argc, char **argv)
 	fprintf(stdout, "Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n",
 		env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt);
 
-	free(env.test_selector.blacklist.strs);
-	free(env.test_selector.whitelist.strs);
+	free_str_set(&env.test_selector.blacklist);
+	free_str_set(&env.test_selector.whitelist);
 	free(env.test_selector.num_set);
-	free(env.subtest_selector.blacklist.strs);
-	free(env.subtest_selector.whitelist.strs);
+	free_str_set(&env.subtest_selector.blacklist);
+	free_str_set(&env.subtest_selector.whitelist);
 	free(env.subtest_selector.num_set);
 
 	return env.fail_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index f4aff6b8284b..f4503c926aca 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -37,6 +37,7 @@ typedef __u16 __sum16;
 #include "bpf_util.h"
 #include <bpf/bpf_endian.h>
 #include "trace_helpers.h"
+#include "testing_helpers.h"
 #include "flow_dissector_load.h"
 
 enum verbosity {
@@ -87,23 +88,12 @@ extern void test__skip(void);
 extern void test__fail(void);
 extern int test__join_cgroup(const char *path);
 
-#define MAGIC_BYTES 123
-
-/* ipv4 test vector */
-struct ipv4_packet {
-	struct ethhdr eth;
-	struct iphdr iph;
-	struct tcphdr tcp;
-} __packed;
-extern struct ipv4_packet pkt_v4;
-
-/* ipv6 test vector */
-struct ipv6_packet {
-	struct ethhdr eth;
-	struct ipv6hdr iph;
-	struct tcphdr tcp;
-} __packed;
-extern struct ipv6_packet pkt_v6;
+#define PRINT_FAIL(format...)                                                  \
+	({                                                                     \
+		test__fail();                                                  \
+		fprintf(stdout, "%s:FAIL:%d ", __func__, __LINE__);            \
+		fprintf(stdout, ##format);                                     \
+	})
 
 #define _CHECK(condition, tag, duration, format...) ({			\
 	int __ret = !!(condition);					\
@@ -136,10 +126,6 @@ extern struct ipv6_packet pkt_v6;
 #define CHECK_ATTR(condition, tag, format...) \
 	_CHECK(condition, tag, tattr.duration, format)
 
-#define MAGIC_VAL 0x1234
-#define NUM_ITER 100000
-#define VIP_NUM 5
-
 static inline __u64 ptr_to_u64(const void *ptr)
 {
 	return (__u64) (unsigned long) ptr;
@@ -149,7 +135,6 @@ int bpf_find_map(const char *test, struct bpf_object *obj, const char *name);
 int compare_map_keys(int map1_fd, int map2_fd);
 int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len);
 int extract_build_id(char *build_id, size_t size);
-void *spin_lock_thread(void *arg);
 
 #ifdef __x86_64__
 #define SYS_NANOSLEEP_KPROBE_NAME "__x64_sys_nanosleep"
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index 61fd95b89af8..0358814c67dc 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -677,7 +677,7 @@ static int bind4_prog_load(const struct sock_addr_test *test)
 		uint8_t u4_addr8[4];
 		uint16_t u4_addr16[2];
 		uint32_t u4_addr32;
-	} ip4;
+	} ip4, port;
 	struct sockaddr_in addr4_rw;
 
 	if (inet_pton(AF_INET, SERV4_IP, (void *)&ip4) != 1) {
@@ -685,6 +685,8 @@ static int bind4_prog_load(const struct sock_addr_test *test)
 		return -1;
 	}
 
+	port.u4_addr32 = htons(SERV4_PORT);
+
 	if (mk_sockaddr(AF_INET, SERV4_REWRITE_IP, SERV4_REWRITE_PORT,
 			(struct sockaddr *)&addr4_rw, sizeof(addr4_rw)) == -1)
 		return -1;
@@ -696,49 +698,65 @@ static int bind4_prog_load(const struct sock_addr_test *test)
 		/* if (sk.family == AF_INET && */
 		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
 			    offsetof(struct bpf_sock_addr, family)),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 24),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 32),
 
 		/*     (sk.type == SOCK_DGRAM || sk.type == SOCK_STREAM) && */
 		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
 			    offsetof(struct bpf_sock_addr, type)),
 		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_DGRAM, 1),
 		BPF_JMP_A(1),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_STREAM, 20),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_STREAM, 28),
 
 		/*     1st_byte_of_user_ip4 == expected && */
 		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
 			    offsetof(struct bpf_sock_addr, user_ip4)),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[0], 18),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[0], 26),
 
 		/*     2nd_byte_of_user_ip4 == expected && */
 		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
 			    offsetof(struct bpf_sock_addr, user_ip4) + 1),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[1], 16),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[1], 24),
 
 		/*     3rd_byte_of_user_ip4 == expected && */
 		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
 			    offsetof(struct bpf_sock_addr, user_ip4) + 2),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[2], 14),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[2], 22),
 
 		/*     4th_byte_of_user_ip4 == expected && */
 		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
 			    offsetof(struct bpf_sock_addr, user_ip4) + 3),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[3], 12),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[3], 20),
 
 		/*     1st_half_of_user_ip4 == expected && */
 		BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
 			    offsetof(struct bpf_sock_addr, user_ip4)),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[0], 10),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[0], 18),
 
 		/*     2nd_half_of_user_ip4 == expected && */
 		BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
 			    offsetof(struct bpf_sock_addr, user_ip4) + 2),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[1], 8),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[1], 16),
 
-		/*     whole_user_ip4 == expected) { */
+		/*     whole_user_ip4 == expected && */
 		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
 			    offsetof(struct bpf_sock_addr, user_ip4)),
 		BPF_LD_IMM64(BPF_REG_8, ip4.u4_addr32), /* See [2]. */
+		BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_8, 12),
+
+		/*     1st_byte_of_user_port == expected && */
+		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
+			    offsetof(struct bpf_sock_addr, user_port)),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, port.u4_addr8[0], 10),
+
+		/*     1st_half_of_user_port == expected && */
+		BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
+			    offsetof(struct bpf_sock_addr, user_port)),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, port.u4_addr16[0], 8),
+
+		/*     user_port == expected) { */
+		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
+			    offsetof(struct bpf_sock_addr, user_port)),
+		BPF_LD_IMM64(BPF_REG_8, port.u4_addr32), /* See [2]. */
 		BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_8, 4),
 
 		/*      user_ip4 = addr4_rw.sin_addr */
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 779e11da979c..37695fc8096a 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -54,7 +54,7 @@ static void running_handler(int a);
 #define S1_PORT 10000
 #define S2_PORT 10001
 
-#define BPF_SOCKMAP_FILENAME "test_sockmap_kern.o"
+#define BPF_SOCKMAP_FILENAME  "test_sockmap_kern.o"
 #define BPF_SOCKHASH_FILENAME "test_sockhash_kern.o"
 #define CG_PATH "/sockmap"
 
@@ -63,14 +63,12 @@ int s1, s2, c1, c2, p1, p2;
 int test_cnt;
 int passed;
 int failed;
-int map_fd[8];
-struct bpf_map *maps[8];
+int map_fd[9];
+struct bpf_map *maps[9];
 int prog_fd[11];
 
 int txmsg_pass;
-int txmsg_noisy;
 int txmsg_redir;
-int txmsg_redir_noisy;
 int txmsg_drop;
 int txmsg_apply;
 int txmsg_cork;
@@ -81,7 +79,10 @@ int txmsg_end_push;
 int txmsg_start_pop;
 int txmsg_pop;
 int txmsg_ingress;
-int txmsg_skb;
+int txmsg_redir_skb;
+int txmsg_ktls_skb;
+int txmsg_ktls_skb_drop;
+int txmsg_ktls_skb_redir;
 int ktls;
 int peek_flag;
 
@@ -89,15 +90,13 @@ static const struct option long_options[] = {
 	{"help",	no_argument,		NULL, 'h' },
 	{"cgroup",	required_argument,	NULL, 'c' },
 	{"rate",	required_argument,	NULL, 'r' },
-	{"verbose",	no_argument,		NULL, 'v' },
+	{"verbose",	optional_argument,	NULL, 'v' },
 	{"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'},
@@ -108,12 +107,108 @@ static const struct option long_options[] = {
 	{"txmsg_start_pop",  required_argument,	NULL, 'w'},
 	{"txmsg_pop",	     required_argument,	NULL, 'x'},
 	{"txmsg_ingress", no_argument,		&txmsg_ingress, 1 },
-	{"txmsg_skb", no_argument,		&txmsg_skb, 1 },
+	{"txmsg_redir_skb", no_argument,	&txmsg_redir_skb, 1 },
 	{"ktls", no_argument,			&ktls, 1 },
 	{"peek", no_argument,			&peek_flag, 1 },
+	{"whitelist", required_argument,	NULL, 'n' },
+	{"blacklist", required_argument,	NULL, 'b' },
 	{0, 0, NULL, 0 }
 };
 
+struct test_env {
+	const char *type;
+	const char *subtest;
+	const char *prepend;
+
+	int test_num;
+	int subtest_num;
+
+	int succ_cnt;
+	int fail_cnt;
+	int fail_last;
+};
+
+struct test_env env;
+
+struct sockmap_options {
+	int verbose;
+	bool base;
+	bool sendpage;
+	bool data_test;
+	bool drop_expected;
+	int iov_count;
+	int iov_length;
+	int rate;
+	char *map;
+	char *whitelist;
+	char *blacklist;
+	char *prepend;
+};
+
+struct _test {
+	char *title;
+	void (*tester)(int cg_fd, struct sockmap_options *opt);
+};
+
+static void test_start(void)
+{
+	env.subtest_num++;
+}
+
+static void test_fail(void)
+{
+	env.fail_cnt++;
+}
+
+static void test_pass(void)
+{
+	env.succ_cnt++;
+}
+
+static void test_reset(void)
+{
+	txmsg_start = txmsg_end = 0;
+	txmsg_start_pop = txmsg_pop = 0;
+	txmsg_start_push = txmsg_end_push = 0;
+	txmsg_pass = txmsg_drop = txmsg_redir = 0;
+	txmsg_apply = txmsg_cork = 0;
+	txmsg_ingress = txmsg_redir_skb = 0;
+	txmsg_ktls_skb = txmsg_ktls_skb_drop = txmsg_ktls_skb_redir = 0;
+}
+
+static int test_start_subtest(const struct _test *t, struct sockmap_options *o)
+{
+	env.type = o->map;
+	env.subtest = t->title;
+	env.prepend = o->prepend;
+	env.test_num++;
+	env.subtest_num = 0;
+	env.fail_last = env.fail_cnt;
+	test_reset();
+	return 0;
+}
+
+static void test_end_subtest(void)
+{
+	int error = env.fail_cnt - env.fail_last;
+	int type = strcmp(env.type, BPF_SOCKMAP_FILENAME);
+
+	if (!error)
+		test_pass();
+
+	fprintf(stdout, "#%2d/%2d %8s:%s:%s:%s\n",
+		env.test_num, env.subtest_num,
+		!type ? "sockmap" : "sockhash",
+		env.prepend ? : "",
+		env.subtest, error ? "FAIL" : "OK");
+}
+
+static void test_print_results(void)
+{
+	fprintf(stdout, "Pass: %d Fail: %d\n",
+		env.succ_cnt, env.fail_cnt);
+}
+
 static void usage(char *argv[])
 {
 	int i;
@@ -296,7 +391,7 @@ static int sockmap_init_sockets(int verbose)
 		return errno;
 	}
 
-	if (verbose) {
+	if (verbose > 1) {
 		printf("connected sockets: c1 <-> p1, c2 <-> p2\n");
 		printf("cgroups binding: c1(%i) <-> s1(%i) - - - c2(%i) <-> s2(%i)\n",
 			c1, s1, c2, s2);
@@ -311,17 +406,6 @@ struct msg_stats {
 	struct timespec end;
 };
 
-struct sockmap_options {
-	int verbose;
-	bool base;
-	bool sendpage;
-	bool data_test;
-	bool drop_expected;
-	int iov_count;
-	int iov_length;
-	int rate;
-};
-
 static int msg_loop_sendpage(int fd, int iov_length, int cnt,
 			     struct msg_stats *s,
 			     struct sockmap_options *opt)
@@ -345,14 +429,18 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt,
 
 	clock_gettime(CLOCK_MONOTONIC, &s->start);
 	for (i = 0; i < cnt; i++) {
-		int sent = sendfile(fd, fp, NULL, iov_length);
+		int sent;
+
+		errno = 0;
+		sent = sendfile(fd, fp, NULL, iov_length);
 
 		if (!drop && sent < 0) {
-			perror("send loop error");
+			perror("sendpage loop error");
 			fclose(file);
 			return sent;
 		} else if (drop && sent >= 0) {
-			printf("sendpage loop error expected: %i\n", sent);
+			printf("sendpage loop error expected: %i errno %i\n",
+			       sent, errno);
 			fclose(file);
 			return -EIO;
 		}
@@ -418,14 +506,41 @@ unwind_iov:
 
 static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz)
 {
-	int i, j, bytes_cnt = 0;
+	int i, j = 0, 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++) {
+		/* Special case test for skb ingress + ktls */
+		if (i == 0 && txmsg_ktls_skb) {
+			if (msg->msg_iov[i].iov_len < 4)
+				return -EIO;
+			if (txmsg_ktls_skb_redir) {
+				if (memcmp(&d[13], "PASS", 4) != 0) {
+					fprintf(stderr,
+						"detected redirect ktls_skb data error with skb ingress update @iov[%i]:%i \"%02x %02x %02x %02x\" != \"PASS\"\n", i, 0, d[13], d[14], d[15], d[16]);
+					return -EIO;
+				}
+				d[13] = 0;
+				d[14] = 1;
+				d[15] = 2;
+				d[16] = 3;
+				j = 13;
+			} else if (txmsg_ktls_skb) {
+				if (memcmp(d, "PASS", 4) != 0) {
+					fprintf(stderr,
+						"detected ktls_skb data error with skb ingress update @iov[%i]:%i \"%02x %02x %02x %02x\" != \"PASS\"\n", i, 0, d[0], d[1], d[2], d[3]);
+					return -EIO;
+				}
+				d[0] = 0;
+				d[1] = 1;
+				d[2] = 2;
+				d[3] = 3;
+			}
+		}
+
+		for (; 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",
@@ -464,13 +579,18 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 	if (tx) {
 		clock_gettime(CLOCK_MONOTONIC, &s->start);
 		for (i = 0; i < cnt; i++) {
-			int sent = sendmsg(fd, &msg, flags);
+			int sent;
+
+			errno = 0;
+			sent = sendmsg(fd, &msg, flags);
 
 			if (!drop && sent < 0) {
-				perror("send loop error");
+				perror("sendmsg loop error");
 				goto out_errno;
 			} else if (drop && sent >= 0) {
-				printf("send loop error expected: %i\n", sent);
+				fprintf(stderr,
+					"sendmsg loop error expected: %i errno %i\n",
+					sent, errno);
 				errno = -EIO;
 				goto out_errno;
 			}
@@ -497,9 +617,10 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		 * paths.
 		 */
 		total_bytes = (float)iov_count * (float)iov_length * (float)cnt;
-		txmsg_pop_total = txmsg_pop;
 		if (txmsg_apply)
-			txmsg_pop_total *= (total_bytes / txmsg_apply);
+			txmsg_pop_total = txmsg_pop * (total_bytes / txmsg_apply);
+		else
+			txmsg_pop_total = txmsg_pop * cnt;
 		total_bytes -= txmsg_pop_total;
 		err = clock_gettime(CLOCK_MONOTONIC, &s->start);
 		if (err < 0)
@@ -633,14 +754,18 @@ static int sendmsg_test(struct sockmap_options *opt)
 
 	rxpid = fork();
 	if (rxpid == 0) {
-		if (opt->drop_expected)
-			exit(0);
+		iov_buf -= (txmsg_pop - txmsg_start_pop + 1);
+		if (opt->drop_expected || txmsg_ktls_skb_drop)
+			_exit(0);
+
+		if (!iov_buf) /* zero bytes sent case */
+			_exit(0);
 
 		if (opt->sendpage)
 			iov_count = 1;
 		err = msg_loop(rx_fd, iov_count, iov_buf,
 			       cnt, &s, false, opt);
-		if (opt->verbose)
+		if (opt->verbose > 1)
 			fprintf(stderr,
 				"msg_loop_rx: iov_count %i iov_buf %i cnt %i err %i\n",
 				iov_count, iov_buf, cnt, err);
@@ -648,7 +773,7 @@ static int sendmsg_test(struct sockmap_options *opt)
 			sent_Bps = sentBps(s);
 			recvd_Bps = recvdBps(s);
 		}
-		if (opt->verbose)
+		if (opt->verbose > 1)
 			fprintf(stdout,
 				"rx_sendmsg: TX: %zuB %fB/s %fGB/s RX: %zuB %fB/s %fGB/s %s\n",
 				s.bytes_sent, sent_Bps, sent_Bps/giga,
@@ -678,7 +803,7 @@ static int sendmsg_test(struct sockmap_options *opt)
 			sent_Bps = sentBps(s);
 			recvd_Bps = recvdBps(s);
 		}
-		if (opt->verbose)
+		if (opt->verbose > 1)
 			fprintf(stdout,
 				"tx_sendmsg: TX: %zuB %fB/s %f GB/s RX: %zuB %fB/s %fGB/s\n",
 				s.bytes_sent, sent_Bps, sent_Bps/giga,
@@ -694,14 +819,14 @@ static int sendmsg_test(struct sockmap_options *opt)
 	if (WIFEXITED(rx_status)) {
 		err = WEXITSTATUS(rx_status);
 		if (err) {
-			fprintf(stderr, "rx thread exited with err %d. ", err);
+			fprintf(stderr, "rx thread exited with err %d.\n", err);
 			goto out;
 		}
 	}
 	if (WIFEXITED(tx_status)) {
 		err = WEXITSTATUS(tx_status);
 		if (err)
-			fprintf(stderr, "tx thread exited with err %d. ", err);
+			fprintf(stderr, "tx thread exited with err %d.\n", err);
 	}
 out:
 	return err;
@@ -783,6 +908,7 @@ static int forever_ping_pong(int rate, struct sockmap_options *opt)
 }
 
 enum {
+	SELFTESTS,
 	PING_PONG,
 	SENDMSG,
 	BASE,
@@ -816,8 +942,28 @@ static int run_options(struct sockmap_options *options, int cg_fd,  int test)
 		return err;
 	}
 
+	/* Attach programs to TLS sockmap */
+	if (txmsg_ktls_skb) {
+		err = bpf_prog_attach(prog_fd[0], map_fd[8],
+					BPF_SK_SKB_STREAM_PARSER, 0);
+		if (err) {
+			fprintf(stderr,
+				"ERROR: bpf_prog_attach (TLS sockmap %i->%i): %d (%s)\n",
+				prog_fd[0], map_fd[8], err, strerror(errno));
+			return err;
+		}
+
+		err = bpf_prog_attach(prog_fd[2], map_fd[8],
+				      BPF_SK_SKB_STREAM_VERDICT, 0);
+		if (err) {
+			fprintf(stderr, "ERROR: bpf_prog_attach (TLS sockmap): %d (%s)\n",
+				err, strerror(errno));
+			return err;
+		}
+	}
+
 	/* Attach to cgroups */
-	err = bpf_prog_attach(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS, 0);
+	err = bpf_prog_attach(prog_fd[3], cg_fd, BPF_CGROUP_SOCK_OPS, 0);
 	if (err) {
 		fprintf(stderr, "ERROR: bpf_prog_attach (groups): %d (%s)\n",
 			err, strerror(errno));
@@ -833,19 +979,14 @@ run:
 
 	/* 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];
+		tx_prog_fd = prog_fd[6];
 	else if (txmsg_cork)
+		tx_prog_fd = prog_fd[7];
+	else if (txmsg_drop)
 		tx_prog_fd = prog_fd[8];
 	else
 		tx_prog_fd = 0;
@@ -870,7 +1011,7 @@ run:
 			goto out;
 		}
 
-		if (txmsg_redir || txmsg_redir_noisy)
+		if (txmsg_redir)
 			redir_fd = c2;
 		else
 			redir_fd = c1;
@@ -1018,7 +1159,35 @@ run:
 			}
 		}
 
-		if (txmsg_skb) {
+		if (txmsg_ktls_skb) {
+			int ingress = BPF_F_INGRESS;
+
+			i = 0;
+			err = bpf_map_update_elem(map_fd[8], &i, &p2, BPF_ANY);
+			if (err) {
+				fprintf(stderr,
+					"ERROR: bpf_map_update_elem (c1 sockmap): %d (%s)\n",
+					err, strerror(errno));
+			}
+
+			if (txmsg_ktls_skb_redir) {
+				i = 1;
+				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));
+				}
+			}
+
+			if (txmsg_ktls_skb_drop) {
+				i = 1;
+				err = bpf_map_update_elem(map_fd[7], &i, &i, BPF_ANY);
+			}
+		}
+
+		if (txmsg_redir_skb) {
 			int skb_fd = (test == SENDMSG || test == SENDPAGE) ?
 					p2 : p1;
 			int ingress = BPF_F_INGRESS;
@@ -1033,8 +1202,7 @@ run:
 			}
 
 			i = 3;
-			err = bpf_map_update_elem(map_fd[0],
-						  &i, &skb_fd, BPF_ANY);
+			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",
@@ -1068,9 +1236,12 @@ run:
 		fprintf(stderr, "unknown test\n");
 out:
 	/* Detatch and zero all the maps */
-	bpf_prog_detach2(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS);
+	bpf_prog_detach2(prog_fd[3], cg_fd, BPF_CGROUP_SOCK_OPS);
 	bpf_prog_detach2(prog_fd[0], map_fd[0], BPF_SK_SKB_STREAM_PARSER);
 	bpf_prog_detach2(prog_fd[1], map_fd[0], BPF_SK_SKB_STREAM_VERDICT);
+	bpf_prog_detach2(prog_fd[0], map_fd[8], BPF_SK_SKB_STREAM_PARSER);
+	bpf_prog_detach2(prog_fd[2], map_fd[8], BPF_SK_SKB_STREAM_VERDICT);
+
 	if (tx_prog_fd >= 0)
 		bpf_prog_detach2(tx_prog_fd, map_fd[1], BPF_SK_MSG_VERDICT);
 
@@ -1112,12 +1283,8 @@ static void test_options(char *options)
 
 	if (txmsg_pass)
 		strncat(options, "pass,", OPTSTRING);
-	if (txmsg_noisy)
-		strncat(options, "pass_noisy,", OPTSTRING);
 	if (txmsg_redir)
 		strncat(options, "redir,", OPTSTRING);
-	if (txmsg_redir_noisy)
-		strncat(options, "redir_noisy,", OPTSTRING);
 	if (txmsg_drop)
 		strncat(options, "drop,", OPTSTRING);
 	if (txmsg_apply) {
@@ -1143,8 +1310,10 @@ static void test_options(char *options)
 	}
 	if (txmsg_ingress)
 		strncat(options, "ingress,", OPTSTRING);
-	if (txmsg_skb)
-		strncat(options, "skb,", OPTSTRING);
+	if (txmsg_redir_skb)
+		strncat(options, "redir_skb,", OPTSTRING);
+	if (txmsg_ktls_skb)
+		strncat(options, "ktls_skb,", OPTSTRING);
 	if (ktls)
 		strncat(options, "ktls,", OPTSTRING);
 	if (peek_flag)
@@ -1168,416 +1337,317 @@ static int __test_exec(int cgrp, int test, struct sockmap_options *opt)
 
 	test_options(options);
 
-	fprintf(stdout,
-		"[TEST %i]: (%i, %i, %i, %s, %s): ",
-		test_cnt, opt->rate, opt->iov_count, opt->iov_length,
-		test_to_str(test), options);
-	fflush(stdout);
+	if (opt->verbose) {
+		fprintf(stdout,
+			" [TEST %i]: (%i, %i, %i, %s, %s): ",
+			test_cnt, opt->rate, opt->iov_count, opt->iov_length,
+			test_to_str(test), options);
+		fflush(stdout);
+	}
 	err = run_options(opt, cgrp, test);
-	fprintf(stdout, "%s\n", !err ? "PASS" : "FAILED");
+	if (opt->verbose)
+		fprintf(stdout, " %s\n", !err ? "PASS" : "FAILED");
 	test_cnt++;
 	!err ? passed++ : failed++;
 	free(options);
 	return err;
 }
 
-static int test_exec(int cgrp, struct sockmap_options *opt)
-{
-	int err = __test_exec(cgrp, SENDMSG, opt);
-
-	if (err)
-		goto out;
-
-	err = __test_exec(cgrp, SENDPAGE, opt);
-out:
-	return err;
-}
-
-static int test_loop(int cgrp)
-{
-	struct sockmap_options opt;
-
-	int err, i, l, r;
-
-	opt.verbose = 0;
-	opt.base = false;
-	opt.sendpage = false;
-	opt.data_test = false;
-	opt.drop_expected = false;
-	opt.iov_count = 0;
-	opt.iov_length = 0;
-	opt.rate = 0;
-
-	r = 1;
-	for (i = 1; i < 100; i += 33) {
-		for (l = 1; l < 100; l += 33) {
-			opt.rate = r;
-			opt.iov_count = i;
-			opt.iov_length = l;
-			err = test_exec(cgrp, &opt);
-			if (err)
-				goto out;
-		}
-	}
-	sched_yield();
-out:
-	return err;
-}
-
-static int test_txmsg(int cgrp)
+static void test_exec(int cgrp, struct sockmap_options *opt)
 {
+	int type = strcmp(opt->map, BPF_SOCKMAP_FILENAME);
 	int err;
 
-	txmsg_pass = txmsg_noisy = txmsg_redir_noisy = txmsg_drop = 0;
-	txmsg_apply = txmsg_cork = 0;
-	txmsg_ingress = txmsg_skb = 0;
-
-	txmsg_pass = 1;
-	err = test_loop(cgrp);
-	txmsg_pass = 0;
-	if (err)
-		goto out;
-
-	txmsg_redir = 1;
-	err = test_loop(cgrp);
-	txmsg_redir = 0;
-	if (err)
-		goto out;
-
-	txmsg_drop = 1;
-	err = test_loop(cgrp);
-	txmsg_drop = 0;
-	if (err)
-		goto out;
-
-	txmsg_redir = 1;
-	txmsg_ingress = 1;
-	err = test_loop(cgrp);
-	txmsg_redir = 0;
-	txmsg_ingress = 0;
-	if (err)
-		goto out;
-out:
-	txmsg_pass = 0;
-	txmsg_redir = 0;
-	txmsg_drop = 0;
-	return err;
+	if (type == 0) {
+		test_start();
+		err = __test_exec(cgrp, SENDMSG, opt);
+		if (err)
+			test_fail();
+	} else {
+		test_start();
+		err = __test_exec(cgrp, SENDPAGE, opt);
+		if (err)
+			test_fail();
+	}
 }
 
-static int test_send(struct sockmap_options *opt, int cgrp)
+static void test_send_one(struct sockmap_options *opt, int cgrp)
 {
-	int err;
-
 	opt->iov_length = 1;
 	opt->iov_count = 1;
 	opt->rate = 1;
-	err = test_exec(cgrp, opt);
-	if (err)
-		goto out;
+	test_exec(cgrp, opt);
 
 	opt->iov_length = 1;
 	opt->iov_count = 1024;
 	opt->rate = 1;
-	err = test_exec(cgrp, opt);
-	if (err)
-		goto out;
+	test_exec(cgrp, opt);
 
 	opt->iov_length = 1024;
 	opt->iov_count = 1;
 	opt->rate = 1;
-	err = test_exec(cgrp, opt);
-	if (err)
-		goto out;
+	test_exec(cgrp, opt);
 
-	opt->iov_length = 1;
+}
+
+static void test_send_many(struct sockmap_options *opt, int cgrp)
+{
+	opt->iov_length = 3;
 	opt->iov_count = 1;
 	opt->rate = 512;
-	err = test_exec(cgrp, opt);
-	if (err)
-		goto out;
-
-	opt->iov_length = 256;
-	opt->iov_count = 1024;
-	opt->rate = 2;
-	err = test_exec(cgrp, opt);
-	if (err)
-		goto out;
+	test_exec(cgrp, opt);
 
 	opt->rate = 100;
 	opt->iov_count = 1;
 	opt->iov_length = 5;
-	err = test_exec(cgrp, opt);
-	if (err)
-		goto out;
-out:
-	sched_yield();
-	return err;
+	test_exec(cgrp, opt);
 }
 
-static int test_mixed(int cgrp)
+static void test_send_large(struct sockmap_options *opt, int cgrp)
 {
-	struct sockmap_options opt = {0};
-	int err;
+	opt->iov_length = 256;
+	opt->iov_count = 1024;
+	opt->rate = 2;
+	test_exec(cgrp, opt);
+}
 
-	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;
-	txmsg_start_pop = txmsg_pop = 0;
+static void test_send(struct sockmap_options *opt, int cgrp)
+{
+	test_send_one(opt, cgrp);
+	test_send_many(opt, cgrp);
+	test_send_large(opt, cgrp);
+	sched_yield();
+}
 
+static void test_txmsg_pass(int cgrp, struct sockmap_options *opt)
+{
 	/* Test small and large iov_count values with pass/redir/apply/cork */
 	txmsg_pass = 1;
-	txmsg_redir = 0;
-	txmsg_apply = 1;
-	txmsg_cork = 0;
-	err = test_send(&opt, cgrp);
-	if (err)
-		goto out;
+	test_send(opt, cgrp);
+}
 
-	txmsg_pass = 1;
-	txmsg_redir = 0;
-	txmsg_apply = 0;
-	txmsg_cork = 1;
-	err = test_send(&opt, cgrp);
-	if (err)
-		goto out;
+static void test_txmsg_redir(int cgrp, struct sockmap_options *opt)
+{
+	txmsg_redir = 1;
+	test_send(opt, cgrp);
+}
 
-	txmsg_pass = 1;
-	txmsg_redir = 0;
-	txmsg_apply = 1;
-	txmsg_cork = 1;
-	err = test_send(&opt, cgrp);
-	if (err)
-		goto out;
+static void test_txmsg_drop(int cgrp, struct sockmap_options *opt)
+{
+	txmsg_drop = 1;
+	test_send(opt, cgrp);
+}
 
-	txmsg_pass = 1;
-	txmsg_redir = 0;
-	txmsg_apply = 1024;
-	txmsg_cork = 0;
-	err = test_send(&opt, cgrp);
-	if (err)
-		goto out;
+static void test_txmsg_ingress_redir(int cgrp, struct sockmap_options *opt)
+{
+	txmsg_pass = txmsg_drop = 0;
+	txmsg_ingress = txmsg_redir = 1;
+	test_send(opt, cgrp);
+}
 
-	txmsg_pass = 1;
-	txmsg_redir = 0;
-	txmsg_apply = 0;
-	txmsg_cork = 1024;
-	err = test_send(&opt, cgrp);
-	if (err)
-		goto out;
+static void test_txmsg_skb(int cgrp, struct sockmap_options *opt)
+{
+	bool data = opt->data_test;
+	int k = ktls;
 
-	txmsg_pass = 1;
-	txmsg_redir = 0;
-	txmsg_apply = 1024;
-	txmsg_cork = 1024;
-	err = test_send(&opt, cgrp);
-	if (err)
-		goto out;
+	opt->data_test = true;
+	ktls = 1;
 
+	txmsg_pass = txmsg_drop = 0;
+	txmsg_ingress = txmsg_redir = 0;
+	txmsg_ktls_skb = 1;
 	txmsg_pass = 1;
-	txmsg_redir = 0;
-	txmsg_cork = 4096;
-	txmsg_apply = 4096;
-	err = test_send(&opt, cgrp);
-	if (err)
-		goto out;
 
-	txmsg_pass = 0;
-	txmsg_redir = 1;
-	txmsg_apply = 1;
-	txmsg_cork = 0;
-	err = test_send(&opt, cgrp);
-	if (err)
-		goto out;
+	/* Using data verification so ensure iov layout is
+	 * expected from test receiver side. e.g. has enough
+	 * bytes to write test code.
+	 */
+	opt->iov_length = 100;
+	opt->iov_count = 1;
+	opt->rate = 1;
+	test_exec(cgrp, opt);
 
-	txmsg_pass = 0;
-	txmsg_redir = 1;
-	txmsg_apply = 0;
-	txmsg_cork = 1;
-	err = test_send(&opt, cgrp);
-	if (err)
-		goto out;
+	txmsg_ktls_skb_drop = 1;
+	test_exec(cgrp, opt);
 
-	txmsg_pass = 0;
-	txmsg_redir = 1;
-	txmsg_apply = 1024;
-	txmsg_cork = 0;
-	err = test_send(&opt, cgrp);
-	if (err)
-		goto out;
+	txmsg_ktls_skb_drop = 0;
+	txmsg_ktls_skb_redir = 1;
+	test_exec(cgrp, opt);
 
-	txmsg_pass = 0;
-	txmsg_redir = 1;
-	txmsg_apply = 0;
-	txmsg_cork = 1024;
-	err = test_send(&opt, cgrp);
-	if (err)
-		goto out;
+	opt->data_test = data;
+	ktls = k;
+}
+
+
+/* Test cork with hung data. This tests poor usage patterns where
+ * cork can leave data on the ring if user program is buggy and
+ * doesn't flush them somehow. They do take some time however
+ * because they wait for a timeout. Test pass, redir and cork with
+ * apply logic. Use cork size of 4097 with send_large to avoid
+ * aligning cork size with send size.
+ */
+static void test_txmsg_cork_hangs(int cgrp, struct sockmap_options *opt)
+{
+	txmsg_pass = 1;
+	txmsg_redir = 0;
+	txmsg_cork = 4097;
+	txmsg_apply = 4097;
+	test_send_large(opt, cgrp);
 
 	txmsg_pass = 0;
 	txmsg_redir = 1;
-	txmsg_apply = 1024;
-	txmsg_cork = 1024;
-	err = test_send(&opt, cgrp);
-	if (err)
-		goto out;
+	txmsg_apply = 0;
+	txmsg_cork = 4097;
+	test_send_large(opt, cgrp);
 
 	txmsg_pass = 0;
 	txmsg_redir = 1;
-	txmsg_cork = 4096;
-	txmsg_apply = 4096;
-	err = test_send(&opt, cgrp);
-	if (err)
-		goto out;
-out:
-	return err;
+	txmsg_apply = 4097;
+	txmsg_cork = 4097;
+	test_send_large(opt, cgrp);
 }
 
-static int test_start_end(int cgrp)
+static void test_txmsg_pull(int cgrp, struct sockmap_options *opt)
 {
-	struct sockmap_options opt = {0};
-	int err, i;
+	/* Test basic start/end */
+	txmsg_start = 1;
+	txmsg_end = 2;
+	test_send(opt, cgrp);
+
+	/* Test >4k pull */
+	txmsg_start = 4096;
+	txmsg_end = 9182;
+	test_send_large(opt, cgrp);
 
-	/* Test basic start/end with lots of iov_count and iov_lengths */
+	/* Test pull + redirect */
+	txmsg_redir = 0;
 	txmsg_start = 1;
 	txmsg_end = 2;
-	txmsg_start_push = 1;
-	txmsg_end_push = 2;
-	txmsg_start_pop = 1;
-	txmsg_pop = 1;
-	err = test_txmsg(cgrp);
-	if (err)
-		goto out;
+	test_send(opt, cgrp);
 
-	/* Cut a byte of pushed data but leave reamining in place */
+	/* Test pull + cork */
+	txmsg_redir = 0;
+	txmsg_cork = 512;
 	txmsg_start = 1;
 	txmsg_end = 2;
-	txmsg_start_push = 1;
-	txmsg_end_push = 3;
+	test_send_many(opt, cgrp);
+
+	/* Test pull + cork + redirect */
+	txmsg_redir = 1;
+	txmsg_cork = 512;
+	txmsg_start = 1;
+	txmsg_end = 2;
+	test_send_many(opt, cgrp);
+}
+
+static void test_txmsg_pop(int cgrp, struct sockmap_options *opt)
+{
+	/* Test basic pop */
 	txmsg_start_pop = 1;
-	txmsg_pop = 1;
-	err = test_txmsg(cgrp);
-	if (err)
-		goto out;
+	txmsg_pop = 2;
+	test_send_many(opt, cgrp);
 
-	/* Test start/end with cork */
-	opt.rate = 16;
-	opt.iov_count = 1;
-	opt.iov_length = 100;
-	txmsg_cork = 1600;
-
-	txmsg_start_pop = 0;
-	txmsg_pop = 0;
-
-	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;
-	}
+	/* Test pop with >4k */
+	txmsg_start_pop = 4096;
+	txmsg_pop = 4096;
+	test_send_large(opt, cgrp);
 
-	/* Test pop data in middle of cork */
-	for (i = 99; i <= 1600; i += 500) {
-		txmsg_start_pop = 10;
-		txmsg_pop = i;
-		err = test_exec(cgrp, &opt);
-		if (err)
-			goto out;
-	}
-	txmsg_start_pop = 0;
-	txmsg_pop = 0;
-
-	/* Test start/end with cork but pull data in middle */
-	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;
-	}
+	/* Test pop + redirect */
+	txmsg_redir = 1;
+	txmsg_start_pop = 1;
+	txmsg_pop = 2;
+	test_send_many(opt, 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;
+	/* Test pop + cork */
+	txmsg_redir = 0;
+	txmsg_cork = 512;
+	txmsg_start_pop = 1;
+	txmsg_pop = 2;
+	test_send_many(opt, cgrp);
 
-	/* Test pop with cork pulling last sg entry */
-	txmsg_start_pop = 1500;
-	txmsg_pop = 1600;
-	err = test_exec(cgrp, &opt);
-	if (err)
-		goto out;
-	txmsg_start_pop = 0;
-	txmsg_pop = 0;
-
-	/* 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;
+	/* Test pop + redirect + cork */
+	txmsg_redir = 1;
+	txmsg_cork = 4;
+	txmsg_start_pop = 1;
+	txmsg_pop = 2;
+	test_send_many(opt, cgrp);
+}
 
-	/* Test pop of single byte in last page */
-	txmsg_start_pop = 1111;
-	txmsg_pop = 1112;
-	err = test_exec(cgrp, &opt);
-	if (err)
-		goto out;
+static void test_txmsg_push(int cgrp, struct sockmap_options *opt)
+{
+	/* Test basic push */
+	txmsg_start_push = 1;
+	txmsg_end_push = 1;
+	test_send(opt, 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;
+	/* Test push 4kB >4k */
+	txmsg_start_push = 4096;
+	txmsg_end_push = 4096;
+	test_send_large(opt, 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;
+	/* Test push + redirect */
+	txmsg_redir = 1;
+	txmsg_start_push = 1;
+	txmsg_end_push = 2;
+	test_send_many(opt, 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);
-	if (err)
-		goto out;
+	/* Test push + cork */
+	txmsg_redir = 0;
+	txmsg_cork = 512;
+	txmsg_start_push = 1;
+	txmsg_end_push = 2;
+	test_send_many(opt, cgrp);
+}
 
-	/* Test pop with start > data */
-	txmsg_start_pop = 1601;
-	txmsg_pop = 1;
-	err = test_exec(cgrp, &opt);
-	if (err)
-		goto out;
+static void test_txmsg_push_pop(int cgrp, struct sockmap_options *opt)
+{
+	txmsg_start_push = 1;
+	txmsg_end_push = 10;
+	txmsg_start_pop = 5;
+	txmsg_pop = 4;
+	test_send_large(opt, cgrp);
+}
 
-	/* Test pop with pop range > data */
-	txmsg_start_pop = 1599;
-	txmsg_pop = 10;
-	err = test_exec(cgrp, &opt);
-out:
-	txmsg_start = 0;
-	txmsg_end = 0;
-	sched_yield();
-	return err;
+static void test_txmsg_apply(int cgrp, struct sockmap_options *opt)
+{
+	txmsg_pass = 1;
+	txmsg_redir = 0;
+	txmsg_apply = 1;
+	txmsg_cork = 0;
+	test_send_one(opt, cgrp);
+
+	txmsg_pass = 0;
+	txmsg_redir = 1;
+	txmsg_apply = 1;
+	txmsg_cork = 0;
+	test_send_one(opt, cgrp);
+
+	txmsg_pass = 1;
+	txmsg_redir = 0;
+	txmsg_apply = 1024;
+	txmsg_cork = 0;
+	test_send_large(opt, cgrp);
+
+	txmsg_pass = 0;
+	txmsg_redir = 1;
+	txmsg_apply = 1024;
+	txmsg_cork = 0;
+	test_send_large(opt, cgrp);
+}
+
+static void test_txmsg_cork(int cgrp, struct sockmap_options *opt)
+{
+	txmsg_pass = 1;
+	txmsg_redir = 0;
+	txmsg_apply = 0;
+	txmsg_cork = 1;
+	test_send(opt, cgrp);
+
+	txmsg_pass = 1;
+	txmsg_redir = 0;
+	txmsg_apply = 1;
+	txmsg_cork = 1;
+	test_send(opt, cgrp);
 }
 
 char *map_names[] = {
@@ -1589,11 +1659,13 @@ char *map_names[] = {
 	"sock_bytes",
 	"sock_redir_flags",
 	"sock_skb_opts",
+	"tls_sock_map",
 };
 
 int prog_attach_type[] = {
 	BPF_SK_SKB_STREAM_PARSER,
 	BPF_SK_SKB_STREAM_VERDICT,
+	BPF_SK_SKB_STREAM_VERDICT,
 	BPF_CGROUP_SOCK_OPS,
 	BPF_SK_MSG_VERDICT,
 	BPF_SK_MSG_VERDICT,
@@ -1607,6 +1679,7 @@ int prog_attach_type[] = {
 int prog_type[] = {
 	BPF_PROG_TYPE_SK_SKB,
 	BPF_PROG_TYPE_SK_SKB,
+	BPF_PROG_TYPE_SK_SKB,
 	BPF_PROG_TYPE_SOCK_OPS,
 	BPF_PROG_TYPE_SK_MSG,
 	BPF_PROG_TYPE_SK_MSG,
@@ -1662,73 +1735,117 @@ static int populate_progs(char *bpf_file)
 	return 0;
 }
 
-static int __test_suite(int cg_fd, char *bpf_file)
+struct _test test[] = {
+	{"txmsg test passthrough", test_txmsg_pass},
+	{"txmsg test redirect", test_txmsg_redir},
+	{"txmsg test drop", test_txmsg_drop},
+	{"txmsg test ingress redirect", test_txmsg_ingress_redir},
+	{"txmsg test skb", test_txmsg_skb},
+	{"txmsg test apply", test_txmsg_apply},
+	{"txmsg test cork", test_txmsg_cork},
+	{"txmsg test hanging corks", test_txmsg_cork_hangs},
+	{"txmsg test push_data", test_txmsg_push},
+	{"txmsg test pull-data", test_txmsg_pull},
+	{"txmsg test pop-data", test_txmsg_pop},
+	{"txmsg test push/pop data", test_txmsg_push_pop},
+};
+
+static int check_whitelist(struct _test *t, struct sockmap_options *opt)
 {
-	int err, cleanup = cg_fd;
+	char *entry, *ptr;
+
+	if (!opt->whitelist)
+		return 0;
+	ptr = strdup(opt->whitelist);
+	if (!ptr)
+		return -ENOMEM;
+	entry = strtok(ptr, ",");
+	while (entry) {
+		if ((opt->prepend && strstr(opt->prepend, entry) != 0) ||
+		    strstr(opt->map, entry) != 0 ||
+		    strstr(t->title, entry) != 0)
+			return 0;
+		entry = strtok(NULL, ",");
+	}
+	return -EINVAL;
+}
 
-	err = populate_progs(bpf_file);
+static int check_blacklist(struct _test *t, struct sockmap_options *opt)
+{
+	char *entry, *ptr;
+
+	if (!opt->blacklist)
+		return -EINVAL;
+	ptr = strdup(opt->blacklist);
+	if (!ptr)
+		return -ENOMEM;
+	entry = strtok(ptr, ",");
+	while (entry) {
+		if ((opt->prepend && strstr(opt->prepend, entry) != 0) ||
+		    strstr(opt->map, entry) != 0 ||
+		    strstr(t->title, entry) != 0)
+			return 0;
+		entry = strtok(NULL, ",");
+	}
+	return -EINVAL;
+}
+
+static int __test_selftests(int cg_fd, struct sockmap_options *opt)
+{
+	int i, err;
+
+	err = populate_progs(opt->map);
 	if (err < 0) {
 		fprintf(stderr, "ERROR: (%i) load bpf failed\n", err);
 		return err;
 	}
 
-	if (cg_fd < 0) {
-		if (setup_cgroup_environment()) {
-			fprintf(stderr, "ERROR: cgroup env failed\n");
-			return -EINVAL;
-		}
+	/* Tests basic commands and APIs */
+	for (i = 0; i < sizeof(test)/sizeof(struct _test); i++) {
+		struct _test t = test[i];
 
-		cg_fd = create_and_get_cgroup(CG_PATH);
-		if (cg_fd < 0) {
-			fprintf(stderr,
-				"ERROR: (%i) open cg path failed: %s\n",
-				cg_fd, optarg);
-			return cg_fd;
-		}
+		if (check_whitelist(&t, opt) != 0)
+			continue;
+		if (check_blacklist(&t, opt) == 0)
+			continue;
 
-		if (join_cgroup(CG_PATH)) {
-			fprintf(stderr, "ERROR: failed to join cgroup\n");
-			return -EINVAL;
-		}
+		test_start_subtest(&t, opt);
+		t.tester(cg_fd, opt);
+		test_end_subtest();
 	}
 
-	/* Tests basic commands and APIs with range of iov values */
-	txmsg_start = txmsg_end = txmsg_start_push = txmsg_end_push = 0;
-	err = test_txmsg(cg_fd);
-	if (err)
-		goto out;
+	return err;
+}
 
-	/* Tests interesting combinations of APIs used together */
-	err = test_mixed(cg_fd);
-	if (err)
-		goto out;
+static void test_selftests_sockmap(int cg_fd, struct sockmap_options *opt)
+{
+	opt->map = BPF_SOCKMAP_FILENAME;
+	__test_selftests(cg_fd, opt);
+}
 
-	/* Tests pull_data API using start/end API */
-	err = test_start_end(cg_fd);
-	if (err)
-		goto out;
+static void test_selftests_sockhash(int cg_fd, struct sockmap_options *opt)
+{
+	opt->map = BPF_SOCKHASH_FILENAME;
+	__test_selftests(cg_fd, opt);
+}
 
-out:
-	printf("Summary: %i PASSED %i FAILED\n", passed, failed);
-	if (cleanup < 0) {
-		cleanup_cgroup_environment();
-		close(cg_fd);
-	}
-	return err;
+static void test_selftests_ktls(int cg_fd, struct sockmap_options *opt)
+{
+	opt->map = BPF_SOCKHASH_FILENAME;
+	opt->prepend = "ktls";
+	ktls = 1;
+	__test_selftests(cg_fd, opt);
+	ktls = 0;
 }
 
-static int test_suite(int cg_fd)
+static int test_selftest(int cg_fd, struct sockmap_options *opt)
 {
-	int err;
 
-	err = __test_suite(cg_fd, BPF_SOCKMAP_FILENAME);
-	if (err)
-		goto out;
-	err = __test_suite(cg_fd, BPF_SOCKHASH_FILENAME);
-out:
-	if (cg_fd > -1)
-		close(cg_fd);
-	return err;
+	test_selftests_sockmap(cg_fd, opt);
+	test_selftests_sockhash(cg_fd, opt);
+	test_selftests_ktls(cg_fd, opt);
+	test_print_results();
+	return 0;
 }
 
 int main(int argc, char **argv)
@@ -1737,12 +1854,10 @@ int main(int argc, char **argv)
 	struct sockmap_options options = {0};
 	int opt, longindex, err, cg_fd = 0;
 	char *bpf_file = BPF_SOCKMAP_FILENAME;
-	int test = PING_PONG;
-
-	if (argc < 2)
-		return test_suite(-1);
+	int test = SELFTESTS;
+	bool cg_created = 0;
 
-	while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:p:q:",
+	while ((opt = getopt_long(argc, argv, ":dhv:c:r:i:l:t:p:q:n:b:",
 				  long_options, &longindex)) != -1) {
 		switch (opt) {
 		case 's':
@@ -1783,6 +1898,8 @@ int main(int argc, char **argv)
 			break;
 		case 'v':
 			options.verbose = 1;
+			if (optarg)
+				options.verbose = atoi(optarg);
 			break;
 		case 'i':
 			iov_count = atoi(optarg);
@@ -1809,6 +1926,15 @@ int main(int argc, char **argv)
 				return -1;
 			}
 			break;
+		case 'n':
+			options.whitelist = strdup(optarg);
+			if (!options.whitelist)
+				return -ENOMEM;
+			break;
+		case 'b':
+			options.blacklist = strdup(optarg);
+			if (!options.blacklist)
+				return -ENOMEM;
 		case 0:
 			break;
 		case 'h':
@@ -1818,13 +1944,30 @@ int main(int argc, char **argv)
 		}
 	}
 
-	if (argc <= 3 && cg_fd)
-		return test_suite(cg_fd);
-
 	if (!cg_fd) {
-		fprintf(stderr, "%s requires cgroup option: --cgroup <path>\n",
-			argv[0]);
-		return -1;
+		if (setup_cgroup_environment()) {
+			fprintf(stderr, "ERROR: cgroup env failed\n");
+			return -EINVAL;
+		}
+
+		cg_fd = create_and_get_cgroup(CG_PATH);
+		if (cg_fd < 0) {
+			fprintf(stderr,
+				"ERROR: (%i) open cg path failed: %s\n",
+				cg_fd, strerror(errno));
+			return cg_fd;
+		}
+
+		if (join_cgroup(CG_PATH)) {
+			fprintf(stderr, "ERROR: failed to join cgroup\n");
+			return -EINVAL;
+		}
+		cg_created = 1;
+	}
+
+	if (test == SELFTESTS) {
+		err = test_selftest(cg_fd, &options);
+		goto out;
 	}
 
 	err = populate_progs(bpf_file);
@@ -1843,6 +1986,13 @@ int main(int argc, char **argv)
 	options.rate = rate;
 
 	err = run_options(&options, cg_fd, test);
+out:
+	if (options.whitelist)
+		free(options.whitelist);
+	if (options.blacklist)
+		free(options.blacklist);
+	if (cg_created)
+		cleanup_cgroup_environment();
 	close(cg_fd);
 	return err;
 }
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 87eaa49609a0..78a6bae56ea6 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -50,7 +50,7 @@
 #define MAX_INSNS	BPF_MAXINSNS
 #define MAX_TEST_INSNS	1000000
 #define MAX_FIXUPS	8
-#define MAX_NR_MAPS	19
+#define MAX_NR_MAPS	20
 #define MAX_TEST_RUNS	8
 #define POINTER_VALUE	0xcafe4all
 #define TEST_DATA_LEN	64
@@ -86,6 +86,7 @@ struct bpf_test {
 	int fixup_map_array_small[MAX_FIXUPS];
 	int fixup_sk_storage_map[MAX_FIXUPS];
 	int fixup_map_event_output[MAX_FIXUPS];
+	int fixup_map_reuseport_array[MAX_FIXUPS];
 	const char *errstr;
 	const char *errstr_unpriv;
 	uint32_t insn_processed;
@@ -637,6 +638,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 	int *fixup_map_array_small = test->fixup_map_array_small;
 	int *fixup_sk_storage_map = test->fixup_sk_storage_map;
 	int *fixup_map_event_output = test->fixup_map_event_output;
+	int *fixup_map_reuseport_array = test->fixup_map_reuseport_array;
 
 	if (test->fill_helper) {
 		test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn));
@@ -806,12 +808,28 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 			fixup_map_event_output++;
 		} while (*fixup_map_event_output);
 	}
+	if (*fixup_map_reuseport_array) {
+		map_fds[19] = __create_map(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
+					   sizeof(u32), sizeof(u64), 1, 0);
+		do {
+			prog[*fixup_map_reuseport_array].imm = map_fds[19];
+			fixup_map_reuseport_array++;
+		} while (*fixup_map_reuseport_array);
+	}
 }
 
+struct libcap {
+	struct __user_cap_header_struct hdr;
+	struct __user_cap_data_struct data[2];
+};
+
 static int set_admin(bool admin)
 {
 	cap_t caps;
-	const cap_value_t cap_val = CAP_SYS_ADMIN;
+	/* need CAP_BPF, CAP_NET_ADMIN, CAP_PERFMON to load progs */
+	const cap_value_t cap_net_admin = CAP_NET_ADMIN;
+	const cap_value_t cap_sys_admin = CAP_SYS_ADMIN;
+	struct libcap *cap;
 	int ret = -1;
 
 	caps = cap_get_proc();
@@ -819,11 +837,26 @@ static int set_admin(bool admin)
 		perror("cap_get_proc");
 		return -1;
 	}
-	if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_val,
+	cap = (struct libcap *)caps;
+	if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_sys_admin, CAP_CLEAR)) {
+		perror("cap_set_flag clear admin");
+		goto out;
+	}
+	if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_net_admin,
 				admin ? CAP_SET : CAP_CLEAR)) {
-		perror("cap_set_flag");
+		perror("cap_set_flag set_or_clear net");
 		goto out;
 	}
+	/* libcap is likely old and simply ignores CAP_BPF and CAP_PERFMON,
+	 * so update effective bits manually
+	 */
+	if (admin) {
+		cap->data[1].effective |= 1 << (38 /* CAP_PERFMON */ - 32);
+		cap->data[1].effective |= 1 << (39 /* CAP_BPF */ - 32);
+	} else {
+		cap->data[1].effective &= ~(1 << (38 - 32));
+		cap->data[1].effective &= ~(1 << (39 - 32));
+	}
 	if (cap_set_proc(caps)) {
 		perror("cap_set_proc");
 		goto out;
@@ -943,7 +976,12 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	attr.insns = prog;
 	attr.insns_cnt = prog_len;
 	attr.license = "GPL";
-	attr.log_level = verbose || expected_ret == VERBOSE_ACCEPT ? 1 : 4;
+	if (verbose)
+		attr.log_level = 1;
+	else if (expected_ret == VERBOSE_ACCEPT)
+		attr.log_level = 2;
+	else
+		attr.log_level = 4;
 	attr.prog_flags = pflags;
 
 	fd_prog = bpf_load_program_xattr(&attr, bpf_vlog, sizeof(bpf_vlog));
@@ -1052,9 +1090,11 @@ fail_log:
 
 static bool is_admin(void)
 {
+	cap_flag_value_t net_priv = CAP_CLEAR;
+	bool perfmon_priv = false;
+	bool bpf_priv = false;
+	struct libcap *cap;
 	cap_t caps;
-	cap_flag_value_t sysadmin = CAP_CLEAR;
-	const cap_value_t cap_val = CAP_SYS_ADMIN;
 
 #ifdef CAP_IS_SUPPORTED
 	if (!CAP_IS_SUPPORTED(CAP_SETFCAP)) {
@@ -1067,11 +1107,14 @@ static bool is_admin(void)
 		perror("cap_get_proc");
 		return false;
 	}
-	if (cap_get_flag(caps, cap_val, CAP_EFFECTIVE, &sysadmin))
-		perror("cap_get_flag");
+	cap = (struct libcap *)caps;
+	bpf_priv = cap->data[1].effective & (1 << (39/* CAP_BPF */ - 32));
+	perfmon_priv = cap->data[1].effective & (1 << (38/* CAP_PERFMON */ - 32));
+	if (cap_get_flag(caps, CAP_NET_ADMIN, CAP_EFFECTIVE, &net_priv))
+		perror("cap_get_flag NET");
 	if (cap_free(caps))
 		perror("cap_free");
-	return (sysadmin == CAP_SET);
+	return bpf_priv && perfmon_priv && net_priv == CAP_SET;
 }
 
 static void get_unpriv_disabled()
diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c
new file mode 100644
index 000000000000..0af6337a8962
--- /dev/null
+++ b/tools/testing/selftests/bpf/testing_helpers.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/* Copyright (C) 2020 Facebook, Inc. */
+#include <stdlib.h>
+#include <errno.h>
+#include "testing_helpers.h"
+
+int parse_num_list(const char *s, bool **num_set, int *num_set_len)
+{
+	int i, set_len = 0, new_len, num, start = 0, end = -1;
+	bool *set = NULL, *tmp, parsing_end = false;
+	char *next;
+
+	while (s[0]) {
+		errno = 0;
+		num = strtol(s, &next, 10);
+		if (errno)
+			return -errno;
+
+		if (parsing_end)
+			end = num;
+		else
+			start = num;
+
+		if (!parsing_end && *next == '-') {
+			s = next + 1;
+			parsing_end = true;
+			continue;
+		} else if (*next == ',') {
+			parsing_end = false;
+			s = next + 1;
+			end = num;
+		} else if (*next == '\0') {
+			parsing_end = false;
+			s = next;
+			end = num;
+		} else {
+			return -EINVAL;
+		}
+
+		if (start > end)
+			return -EINVAL;
+
+		if (end + 1 > set_len) {
+			new_len = end + 1;
+			tmp = realloc(set, new_len);
+			if (!tmp) {
+				free(set);
+				return -ENOMEM;
+			}
+			for (i = set_len; i < start; i++)
+				tmp[i] = false;
+			set = tmp;
+			set_len = new_len;
+		}
+		for (i = start; i <= end; i++)
+			set[i] = true;
+	}
+
+	if (!set)
+		return -EINVAL;
+
+	*num_set = set;
+	*num_set_len = set_len;
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h
new file mode 100644
index 000000000000..923b51762759
--- /dev/null
+++ b/tools/testing/selftests/bpf/testing_helpers.h
@@ -0,0 +1,5 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+/* Copyright (C) 2020 Facebook, Inc. */
+#include <stdbool.h>
+
+int parse_num_list(const char *s, bool **set, int *set_len);
diff --git a/tools/testing/selftests/bpf/verifier/and.c b/tools/testing/selftests/bpf/verifier/and.c
index e0fad1548737..d781bc86e100 100644
--- a/tools/testing/selftests/bpf/verifier/and.c
+++ b/tools/testing/selftests/bpf/verifier/and.c
@@ -15,7 +15,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
-	.errstr = "R0 max value is outside of the array range",
+	.errstr = "R0 max value is outside of the allowed memory range",
 	.result = REJECT,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
@@ -44,7 +44,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
-	.errstr = "R0 max value is outside of the array range",
+	.errstr = "R0 max value is outside of the allowed memory range",
 	.result = REJECT,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
diff --git a/tools/testing/selftests/bpf/verifier/array_access.c b/tools/testing/selftests/bpf/verifier/array_access.c
index f3c33e128709..1c4b1939f5a8 100644
--- a/tools/testing/selftests/bpf/verifier/array_access.c
+++ b/tools/testing/selftests/bpf/verifier/array_access.c
@@ -117,7 +117,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
-	.errstr = "R0 min value is outside of the array range",
+	.errstr = "R0 min value is outside of the allowed memory range",
 	.result = REJECT,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
@@ -137,7 +137,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
-	.errstr = "R0 unbounded memory access, make sure to bounds check any array access into a map",
+	.errstr = "R0 unbounded memory access, make sure to bounds check any such access",
 	.result = REJECT,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c
index 58f4aa593b1b..4d6645f2874c 100644
--- a/tools/testing/selftests/bpf/verifier/bounds.c
+++ b/tools/testing/selftests/bpf/verifier/bounds.c
@@ -20,7 +20,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_8b = { 3 },
-	.errstr = "R0 max value is outside of the array range",
+	.errstr = "R0 max value is outside of the allowed memory range",
 	.result = REJECT,
 },
 {
@@ -146,7 +146,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_8b = { 3 },
-	.errstr = "R0 min value is outside of the array range",
+	.errstr = "R0 min value is outside of the allowed memory range",
 	.result = REJECT
 },
 {
@@ -354,7 +354,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_8b = { 3 },
-	.errstr = "R0 max value is outside of the array range",
+	.errstr = "R0 max value is outside of the allowed memory range",
 	.result = REJECT
 },
 {
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index 2d752c4f8d9d..94258c6b5235 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -19,7 +19,7 @@
 	BPF_MOV64_IMM(BPF_REG_0, 2),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+	.errstr_unpriv = "function calls to other bpf functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 1,
@@ -105,7 +105,7 @@
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.fixup_map_hash_8b = { 16 },
 	.result = REJECT,
-	.errstr = "R0 min value is outside of the array range",
+	.errstr = "R0 min value is outside of the allowed memory range",
 },
 {
 	"calls: overlapping caller/callee",
@@ -315,7 +315,7 @@
 	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "allowed for root only",
+	.errstr_unpriv = "allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = POINTER_VALUE,
@@ -346,7 +346,7 @@
 	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "allowed for root only",
+	.errstr_unpriv = "allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = TEST_DATA_LEN + TEST_DATA_LEN - ETH_HLEN - ETH_HLEN,
@@ -397,7 +397,7 @@
 	BPF_MOV64_IMM(BPF_REG_0, 1),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+	.errstr_unpriv = "function calls to other bpf functions are allowed for",
 	.fixup_map_hash_48b = { 3 },
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
@@ -1064,7 +1064,7 @@
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "allowed for root only",
+	.errstr_unpriv = "allowed for",
 	.result_unpriv = REJECT,
 	.errstr = "R0 !read_ok",
 	.result = REJECT,
@@ -1977,7 +1977,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-	.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+	.errstr_unpriv = "function calls to other bpf functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
@@ -2003,7 +2003,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-	.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+	.errstr_unpriv = "function calls to other bpf functions are allowed for",
 	.errstr = "!read_ok",
 	.result = REJECT,
 },
@@ -2028,7 +2028,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-	.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+	.errstr_unpriv = "function calls to other bpf functions are allowed for",
 	.errstr = "!read_ok",
 	.result = REJECT,
 },
diff --git a/tools/testing/selftests/bpf/verifier/const_or.c b/tools/testing/selftests/bpf/verifier/const_or.c
index 84446dfc7c1d..6c214c58e8d4 100644
--- a/tools/testing/selftests/bpf/verifier/const_or.c
+++ b/tools/testing/selftests/bpf/verifier/const_or.c
@@ -6,7 +6,7 @@
 	BPF_MOV64_IMM(BPF_REG_2, 34),
 	BPF_ALU64_IMM(BPF_OR, BPF_REG_2, 13),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.result = ACCEPT,
@@ -20,7 +20,7 @@
 	BPF_MOV64_IMM(BPF_REG_2, 34),
 	BPF_ALU64_IMM(BPF_OR, BPF_REG_2, 24),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.errstr = "invalid stack type R1 off=-48 access_size=58",
@@ -36,7 +36,7 @@
 	BPF_MOV64_IMM(BPF_REG_4, 13),
 	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_4),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.result = ACCEPT,
@@ -51,7 +51,7 @@
 	BPF_MOV64_IMM(BPF_REG_4, 24),
 	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_4),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.errstr = "invalid stack type R1 off=-48 access_size=58",
diff --git a/tools/testing/selftests/bpf/verifier/dead_code.c b/tools/testing/selftests/bpf/verifier/dead_code.c
index 50a8a63be4ac..5cf361d8eb1c 100644
--- a/tools/testing/selftests/bpf/verifier/dead_code.c
+++ b/tools/testing/selftests/bpf/verifier/dead_code.c
@@ -85,7 +85,7 @@
 	BPF_MOV64_IMM(BPF_REG_0, 12),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+	.errstr_unpriv = "function calls to other bpf functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 7,
@@ -103,7 +103,7 @@
 	BPF_MOV64_IMM(BPF_REG_0, 12),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+	.errstr_unpriv = "function calls to other bpf functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 7,
@@ -121,7 +121,7 @@
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -5),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+	.errstr_unpriv = "function calls to other bpf functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 7,
@@ -137,7 +137,7 @@
 	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+	.errstr_unpriv = "function calls to other bpf functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
@@ -152,7 +152,7 @@
 	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+	.errstr_unpriv = "function calls to other bpf functions are allowed for",
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
diff --git a/tools/testing/selftests/bpf/verifier/direct_value_access.c b/tools/testing/selftests/bpf/verifier/direct_value_access.c
index b9fb28e8e224..988f46a1a4c7 100644
--- a/tools/testing/selftests/bpf/verifier/direct_value_access.c
+++ b/tools/testing/selftests/bpf/verifier/direct_value_access.c
@@ -68,7 +68,7 @@
 	},
 	.fixup_map_array_48b = { 1 },
 	.result = REJECT,
-	.errstr = "R1 min value is outside of the array range",
+	.errstr = "R1 min value is outside of the allowed memory range",
 },
 {
 	"direct map access, write test 7",
@@ -220,7 +220,7 @@
 	},
 	.fixup_map_array_small = { 1 },
 	.result = REJECT,
-	.errstr = "R1 min value is outside of the array range",
+	.errstr = "R1 min value is outside of the allowed memory range",
 },
 {
 	"direct map access, write test 19",
diff --git a/tools/testing/selftests/bpf/verifier/event_output.c b/tools/testing/selftests/bpf/verifier/event_output.c
index 130553e19eca..99f8f582c02b 100644
--- a/tools/testing/selftests/bpf/verifier/event_output.c
+++ b/tools/testing/selftests/bpf/verifier/event_output.c
@@ -92,3 +92,27 @@
 	.result = ACCEPT,
 	.retval = 1,
 },
+{
+	"perfevent for cgroup dev",
+	.insns =  { __PERF_EVENT_INSNS__ },
+	.prog_type = BPF_PROG_TYPE_CGROUP_DEVICE,
+	.fixup_map_event_output = { 4 },
+	.result = ACCEPT,
+	.retval = 1,
+},
+{
+	"perfevent for cgroup sysctl",
+	.insns =  { __PERF_EVENT_INSNS__ },
+	.prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL,
+	.fixup_map_event_output = { 4 },
+	.result = ACCEPT,
+	.retval = 1,
+},
+{
+	"perfevent for cgroup sockopt",
+	.insns =  { __PERF_EVENT_INSNS__ },
+	.prog_type = BPF_PROG_TYPE_CGROUP_SOCKOPT,
+	.fixup_map_event_output = { 4 },
+	.result = ACCEPT,
+	.retval = 1,
+},
diff --git a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c b/tools/testing/selftests/bpf/verifier/helper_access_var_len.c
index 67ab12410050..87c4e7900083 100644
--- a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c
+++ b/tools/testing/selftests/bpf/verifier/helper_access_var_len.c
@@ -19,7 +19,7 @@
 	BPF_MOV64_IMM(BPF_REG_4, 0),
 	BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -36,7 +36,7 @@
 	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
 	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.errstr = "invalid indirect read from stack off -64+0 size 64",
@@ -55,7 +55,7 @@
 	BPF_MOV64_IMM(BPF_REG_4, 0),
 	BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -84,7 +84,7 @@
 	BPF_MOV64_IMM(BPF_REG_4, 0),
 	BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -112,7 +112,7 @@
 	BPF_MOV64_IMM(BPF_REG_4, 0),
 	BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -132,7 +132,7 @@
 	BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 3),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -152,7 +152,7 @@
 	BPF_MOV64_IMM(BPF_REG_4, 0),
 	BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -171,7 +171,7 @@
 	BPF_MOV64_IMM(BPF_REG_4, 0),
 	BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -190,7 +190,7 @@
 	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
 	BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 64, 3),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -208,7 +208,7 @@
 	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
 	BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, 64, 3),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -233,7 +233,7 @@
 	BPF_MOV64_IMM(BPF_REG_4, 0),
 	BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -259,7 +259,7 @@
 	BPF_MOV64_IMM(BPF_REG_4, 0),
 	BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -286,7 +286,7 @@
 	BPF_MOV64_IMM(BPF_REG_4, 0),
 	BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -313,12 +313,12 @@
 	BPF_MOV64_IMM(BPF_REG_4, 0),
 	BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 4 },
-	.errstr = "R1 min value is outside of the array range",
+	.errstr = "R1 min value is outside of the allowed memory range",
 	.result = REJECT,
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 },
@@ -468,7 +468,7 @@
 	BPF_MOV64_IMM(BPF_REG_1, 0),
 	BPF_MOV64_IMM(BPF_REG_2, 0),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.errstr = "R1 type=inv expected=fp",
@@ -481,7 +481,7 @@
 	BPF_MOV64_IMM(BPF_REG_1, 0),
 	BPF_MOV64_IMM(BPF_REG_2, 1),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.errstr = "R1 type=inv expected=fp",
@@ -495,7 +495,7 @@
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
 	BPF_MOV64_IMM(BPF_REG_2, 0),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.result = ACCEPT,
@@ -513,7 +513,7 @@
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 	BPF_MOV64_IMM(BPF_REG_2, 0),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_8b = { 3 },
@@ -534,7 +534,7 @@
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_8b = { 3 },
@@ -554,7 +554,7 @@
 	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
 	BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 2),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_8b = { 3 },
@@ -580,7 +580,7 @@
 	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 63),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
 	BPF_EXIT_INSN(),
 	},
@@ -607,7 +607,7 @@
 	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 32),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 32),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
 	BPF_EXIT_INSN(),
 	},
diff --git a/tools/testing/selftests/bpf/verifier/helper_value_access.c b/tools/testing/selftests/bpf/verifier/helper_value_access.c
index 7572e403ddb9..1c7882ddfa63 100644
--- a/tools/testing/selftests/bpf/verifier/helper_value_access.c
+++ b/tools/testing/selftests/bpf/verifier/helper_value_access.c
@@ -10,7 +10,7 @@
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 	BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
@@ -29,7 +29,7 @@
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 	BPF_MOV64_IMM(BPF_REG_2, 8),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
@@ -67,7 +67,7 @@
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 	BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val) + 8),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
@@ -87,7 +87,7 @@
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 	BPF_MOV64_IMM(BPF_REG_2, -8),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
@@ -109,7 +109,7 @@
 	BPF_MOV64_IMM(BPF_REG_2,
 		      sizeof(struct test_val) -	offsetof(struct test_val, foo)),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
@@ -129,7 +129,7 @@
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, offsetof(struct test_val, foo)),
 	BPF_MOV64_IMM(BPF_REG_2, 8),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
@@ -170,7 +170,7 @@
 	BPF_MOV64_IMM(BPF_REG_2,
 		      sizeof(struct test_val) - offsetof(struct test_val, foo) + 8),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
@@ -191,7 +191,7 @@
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, offsetof(struct test_val, foo)),
 	BPF_MOV64_IMM(BPF_REG_2, -8),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
@@ -212,7 +212,7 @@
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, offsetof(struct test_val, foo)),
 	BPF_MOV64_IMM(BPF_REG_2, -1),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
@@ -235,7 +235,7 @@
 	BPF_MOV64_IMM(BPF_REG_2,
 		      sizeof(struct test_val) - offsetof(struct test_val, foo)),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
@@ -256,7 +256,7 @@
 	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
 	BPF_MOV64_IMM(BPF_REG_2, 8),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
@@ -280,7 +280,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
-	.errstr = "R1 min value is outside of the array range",
+	.errstr = "R1 min value is outside of the allowed memory range",
 	.result = REJECT,
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 },
@@ -300,7 +300,7 @@
 		      sizeof(struct test_val) -
 		      offsetof(struct test_val, foo) + 8),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
@@ -322,7 +322,7 @@
 	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
 	BPF_MOV64_IMM(BPF_REG_2, -8),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
@@ -344,7 +344,7 @@
 	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
 	BPF_MOV64_IMM(BPF_REG_2, -1),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
@@ -368,7 +368,7 @@
 	BPF_MOV64_IMM(BPF_REG_2,
 		      sizeof(struct test_val) - offsetof(struct test_val, foo)),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
@@ -390,7 +390,7 @@
 	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
 	BPF_MOV64_IMM(BPF_REG_2, 8),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
@@ -415,7 +415,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
-	.errstr = "R1 min value is outside of the array range",
+	.errstr = "R1 min value is outside of the allowed memory range",
 	.result = REJECT,
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 },
@@ -433,7 +433,7 @@
 	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
 	BPF_MOV64_IMM(BPF_REG_2, 1),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
@@ -458,7 +458,7 @@
 		      sizeof(struct test_val) -
 		      offsetof(struct test_val, foo) + 1),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_48b = { 3 },
@@ -926,7 +926,7 @@
 	},
 	.fixup_map_hash_16b = { 3, 10 },
 	.result = REJECT,
-	.errstr = "R2 unbounded memory access, make sure to bounds check any array access into a map",
+	.errstr = "R2 unbounded memory access, make sure to bounds check any such access",
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 },
 {
diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c
index 02151f8c940f..6dc8003ffc70 100644
--- a/tools/testing/selftests/bpf/verifier/precise.c
+++ b/tools/testing/selftests/bpf/verifier/precise.c
@@ -31,14 +31,14 @@
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_FP),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	.fixup_map_array_48b = { 1 },
 	.result = VERBOSE_ACCEPT,
 	.errstr =
-	"26: (85) call bpf_probe_read#4\
+	"26: (85) call bpf_probe_read_kernel#113\
 	last_idx 26 first_idx 20\
 	regs=4 stack=0 before 25\
 	regs=4 stack=0 before 24\
@@ -91,7 +91,7 @@
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_FP),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
 	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read),
+	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
@@ -99,7 +99,7 @@
 	.result = VERBOSE_ACCEPT,
 	.flags = BPF_F_TEST_STATE_FREQ,
 	.errstr =
-	"26: (85) call bpf_probe_read#4\
+	"26: (85) call bpf_probe_read_kernel#113\
 	last_idx 26 first_idx 22\
 	regs=4 stack=0 before 25\
 	regs=4 stack=0 before 24\
diff --git a/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c b/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c
index da7a4b37cb98..fc4e301260f6 100644
--- a/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c
+++ b/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c
@@ -1,34 +1,4 @@
 {
-	"prevent map lookup in sockmap",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_sockmap = { 3 },
-	.result = REJECT,
-	.errstr = "cannot pass map_type 15 into func bpf_map_lookup_elem",
-	.prog_type = BPF_PROG_TYPE_SOCK_OPS,
-},
-{
-	"prevent map lookup in sockhash",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_sockhash = { 3 },
-	.result = REJECT,
-	.errstr = "cannot pass map_type 18 into func bpf_map_lookup_elem",
-	.prog_type = BPF_PROG_TYPE_SOCK_OPS,
-},
-{
 	"prevent map lookup in stack trace",
 	.insns = {
 	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c
index 604b46151736..056e0273bf12 100644
--- a/tools/testing/selftests/bpf/verifier/ref_tracking.c
+++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c
@@ -821,3 +821,36 @@
 	.result = REJECT,
 	.errstr = "invalid mem access",
 },
+{
+	"reference tracking: branch tracking valid pointer null comparison",
+	.insns = {
+	BPF_SK_LOOKUP(sk_lookup_tcp),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_MOV64_IMM(BPF_REG_3, 1),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 0, 1),
+	BPF_MOV64_IMM(BPF_REG_3, 0),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 2),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = ACCEPT,
+},
+{
+	"reference tracking: branch tracking valid pointer value comparison",
+	.insns = {
+	BPF_SK_LOOKUP(sk_lookup_tcp),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_MOV64_IMM(BPF_REG_3, 1),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 4),
+	BPF_MOV64_IMM(BPF_REG_3, 0),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 1234, 2),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.errstr = "Unreleased reference",
+	.result = REJECT,
+},
diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c
index 9ed192e14f5f..b1aac2641498 100644
--- a/tools/testing/selftests/bpf/verifier/sock.c
+++ b/tools/testing/selftests/bpf/verifier/sock.c
@@ -222,7 +222,7 @@
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetofend(struct bpf_sock, state)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetofend(struct bpf_sock, rx_queue_mapping)),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -516,3 +516,118 @@
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.result = ACCEPT,
 },
+{
+	"bpf_map_lookup_elem(sockmap, &key)",
+	.insns = {
+	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_sockmap = { 3 },
+	.prog_type = BPF_PROG_TYPE_SK_SKB,
+	.result = REJECT,
+	.errstr = "Unreleased reference id=2 alloc_insn=5",
+},
+{
+	"bpf_map_lookup_elem(sockhash, &key)",
+	.insns = {
+	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_sockhash = { 3 },
+	.prog_type = BPF_PROG_TYPE_SK_SKB,
+	.result = REJECT,
+	.errstr = "Unreleased reference id=2 alloc_insn=5",
+},
+{
+	"bpf_map_lookup_elem(sockmap, &key); sk->type [fullsock field]; bpf_sk_release(sk)",
+	.insns = {
+	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, type)),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_sockmap = { 3 },
+	.prog_type = BPF_PROG_TYPE_SK_SKB,
+	.result = ACCEPT,
+},
+{
+	"bpf_map_lookup_elem(sockhash, &key); sk->type [fullsock field]; bpf_sk_release(sk)",
+	.insns = {
+	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, type)),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_sockhash = { 3 },
+	.prog_type = BPF_PROG_TYPE_SK_SKB,
+	.result = ACCEPT,
+},
+{
+	"bpf_sk_select_reuseport(ctx, reuseport_array, &key, flags)",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_4, 0),
+	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+	BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -4),
+	BPF_LD_MAP_FD(BPF_REG_2, 0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_select_reuseport),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_reuseport_array = { 4 },
+	.prog_type = BPF_PROG_TYPE_SK_REUSEPORT,
+	.result = ACCEPT,
+},
+{
+	"bpf_sk_select_reuseport(ctx, sockmap, &key, flags)",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_4, 0),
+	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+	BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -4),
+	BPF_LD_MAP_FD(BPF_REG_2, 0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_select_reuseport),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_sockmap = { 4 },
+	.prog_type = BPF_PROG_TYPE_SK_REUSEPORT,
+	.result = ACCEPT,
+},
+{
+	"bpf_sk_select_reuseport(ctx, sockhash, &key, flags)",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_4, 0),
+	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+	BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -4),
+	BPF_LD_MAP_FD(BPF_REG_2, 0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_select_reuseport),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_sockmap = { 4 },
+	.prog_type = BPF_PROG_TYPE_SK_REUSEPORT,
+	.result = ACCEPT,
+},
diff --git a/tools/testing/selftests/bpf/verifier/value_or_null.c b/tools/testing/selftests/bpf/verifier/value_or_null.c
index 860d4a71cd83..3ecb70a3d939 100644
--- a/tools/testing/selftests/bpf/verifier/value_or_null.c
+++ b/tools/testing/selftests/bpf/verifier/value_or_null.c
@@ -150,3 +150,22 @@
 	.result_unpriv = REJECT,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
+{
+	"map lookup and null branch prediction",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_1, 10),
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 2),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 0, 1),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_10, 10),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_8b = { 4 },
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = ACCEPT,
+},
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index a53d99cebd9f..97ee658e1242 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -50,7 +50,7 @@
 	.fixup_map_array_48b = { 8 },
 	.result = ACCEPT,
 	.result_unpriv = REJECT,
-	.errstr_unpriv = "R0 min value is outside of the array range",
+	.errstr_unpriv = "R0 min value is outside of the allowed memory range",
 	.retval = 1,
 },
 {
@@ -325,7 +325,7 @@
 	},
 	.fixup_map_array_48b = { 3 },
 	.result = REJECT,
-	.errstr = "R0 min value is outside of the array range",
+	.errstr = "R0 min value is outside of the allowed memory range",
 	.result_unpriv = REJECT,
 	.errstr_unpriv = "R0 pointer arithmetic of map value goes out of range",
 },
@@ -601,7 +601,7 @@
 	},
 	.fixup_map_array_48b = { 3 },
 	.result = REJECT,
-	.errstr = "R1 max value is outside of the array range",
+	.errstr = "R1 max value is outside of the allowed memory range",
 	.errstr_unpriv = "R1 pointer arithmetic of map value goes out of range",
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
@@ -726,7 +726,7 @@
 	},
 	.fixup_map_array_48b = { 3 },
 	.result = REJECT,
-	.errstr = "R0 min value is outside of the array range",
+	.errstr = "R0 min value is outside of the allowed memory range",
 },
 {
 	"map access: value_ptr -= known scalar, 2",