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

Andrii Nakryiko says:

====================
bpf-next 2021-12-10 v2

We've added 115 non-merge commits during the last 26 day(s) which contain
a total of 182 files changed, 5747 insertions(+), 2564 deletions(-).

The main changes are:

1) Various samples fixes, from Alexander Lobakin.

2) BPF CO-RE support in kernel and light skeleton, from Alexei Starovoitov.

3) A batch of new unified APIs for libbpf, logging improvements, version
   querying, etc. Also a batch of old deprecations for old APIs and various
   bug fixes, in preparation for libbpf 1.0, from Andrii Nakryiko.

4) BPF documentation reorganization and improvements, from Christoph Hellwig
   and Dave Tucker.

5) Support for declarative initialization of BPF_MAP_TYPE_PROG_ARRAY in
   libbpf, from Hengqi Chen.

6) Verifier log fixes, from Hou Tao.

7) Runtime-bounded loops support with bpf_loop() helper, from Joanne Koong.

8) Extend branch record capturing to all platforms that support it,
   from Kajol Jain.

9) Light skeleton codegen improvements, from Kumar Kartikeya Dwivedi.

10) bpftool doc-generating script improvements, from Quentin Monnet.

11) Two libbpf v0.6 bug fixes, from Shuyi Cheng and Vincent Minet.

12) Deprecation warning fix for perf/bpf_counter, from Song Liu.

13) MAX_TAIL_CALL_CNT unification and MIPS build fix for libbpf,
    from Tiezhu Yang.

14) BTF_KING_TYPE_TAG follow-up fixes, from Yonghong Song.

15) Selftests fixes and improvements, from Ilya Leoshkevich, Jean-Philippe
    Brucker, Jiri Olsa, Maxim Mikityanskiy, Tirthendu Sarkar, Yucong Sun,
    and others.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (115 commits)
  libbpf: Add "bool skipped" to struct bpf_map
  libbpf: Fix typo in btf__dedup@LIBBPF_0.0.2 definition
  bpftool: Switch bpf_object__load_xattr() to bpf_object__load()
  selftests/bpf: Remove the only use of deprecated bpf_object__load_xattr()
  selftests/bpf: Add test for libbpf's custom log_buf behavior
  selftests/bpf: Replace all uses of bpf_load_btf() with bpf_btf_load()
  libbpf: Deprecate bpf_object__load_xattr()
  libbpf: Add per-program log buffer setter and getter
  libbpf: Preserve kernel error code and remove kprobe prog type guessing
  libbpf: Improve logging around BPF program loading
  libbpf: Allow passing user log setting through bpf_object_open_opts
  libbpf: Allow passing preallocated log_buf when loading BTF into kernel
  libbpf: Add OPTS-based bpf_btf_load() API
  libbpf: Fix bpf_prog_load() log_buf logic for log_level 0
  samples/bpf: Remove unneeded variable
  bpf: Remove redundant assignment to pointer t
  selftests/bpf: Fix a compilation warning
  perf/bpf_counter: Use bpf_map_create instead of bpf_create_map
  samples: bpf: Fix 'unknown warning group' build warning on Clang
  samples: bpf: Fix xdp_sample_user.o linking with Clang
  ...
====================

Link: https://lore.kernel.org/r/20211210234746.2100561-1-andrii@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

73 files changed, 2189 insertions, 517 deletions

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 5d42db2e129a..a795bca4c8ec 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -192,22 +192,26 @@ TEST_GEN_PROGS_EXTENDED += $(DEFAULT_BPFTOOL)
 
 $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(BPFOBJ)
 
-$(OUTPUT)/test_dev_cgroup: cgroup_helpers.c testing_helpers.o
-$(OUTPUT)/test_skb_cgroup_id_user: cgroup_helpers.c testing_helpers.o
-$(OUTPUT)/test_sock: cgroup_helpers.c testing_helpers.o
-$(OUTPUT)/test_sock_addr: cgroup_helpers.c testing_helpers.o
-$(OUTPUT)/test_sockmap: cgroup_helpers.c testing_helpers.o
-$(OUTPUT)/test_tcpnotify_user: cgroup_helpers.c trace_helpers.c testing_helpers.o
-$(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c testing_helpers.o
-$(OUTPUT)/test_cgroup_storage: cgroup_helpers.c testing_helpers.o
-$(OUTPUT)/test_sock_fields: cgroup_helpers.c testing_helpers.o
-$(OUTPUT)/test_sysctl: cgroup_helpers.c testing_helpers.o
-$(OUTPUT)/test_tag: testing_helpers.o
-$(OUTPUT)/test_lirc_mode2_user: testing_helpers.o
-$(OUTPUT)/xdping: testing_helpers.o
-$(OUTPUT)/flow_dissector_load: testing_helpers.o
-$(OUTPUT)/test_maps: testing_helpers.o
-$(OUTPUT)/test_verifier: testing_helpers.o
+CGROUP_HELPERS	:= $(OUTPUT)/cgroup_helpers.o
+TESTING_HELPERS	:= $(OUTPUT)/testing_helpers.o
+TRACE_HELPERS	:= $(OUTPUT)/trace_helpers.o
+
+$(OUTPUT)/test_dev_cgroup: $(CGROUP_HELPERS) $(TESTING_HELPERS)
+$(OUTPUT)/test_skb_cgroup_id_user: $(CGROUP_HELPERS) $(TESTING_HELPERS)
+$(OUTPUT)/test_sock: $(CGROUP_HELPERS) $(TESTING_HELPERS)
+$(OUTPUT)/test_sock_addr: $(CGROUP_HELPERS) $(TESTING_HELPERS)
+$(OUTPUT)/test_sockmap: $(CGROUP_HELPERS) $(TESTING_HELPERS)
+$(OUTPUT)/test_tcpnotify_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(TRACE_HELPERS)
+$(OUTPUT)/get_cgroup_id_user: $(CGROUP_HELPERS) $(TESTING_HELPERS)
+$(OUTPUT)/test_cgroup_storage: $(CGROUP_HELPERS) $(TESTING_HELPERS)
+$(OUTPUT)/test_sock_fields: $(CGROUP_HELPERS) $(TESTING_HELPERS)
+$(OUTPUT)/test_sysctl: $(CGROUP_HELPERS) $(TESTING_HELPERS)
+$(OUTPUT)/test_tag: $(TESTING_HELPERS)
+$(OUTPUT)/test_lirc_mode2_user: $(TESTING_HELPERS)
+$(OUTPUT)/xdping: $(TESTING_HELPERS)
+$(OUTPUT)/flow_dissector_load: $(TESTING_HELPERS)
+$(OUTPUT)/test_maps: $(TESTING_HELPERS)
+$(OUTPUT)/test_verifier: $(TESTING_HELPERS)
 
 BPFTOOL ?= $(DEFAULT_BPFTOOL)
 $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)    \
@@ -325,9 +329,10 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h		\
 		linked_vars.skel.h linked_maps.skel.h
 
 LSKELS := kfunc_call_test.c fentry_test.c fexit_test.c fexit_sleep.c \
-	test_ringbuf.c atomics.c trace_printk.c trace_vprintk.c
+	test_ringbuf.c atomics.c trace_printk.c trace_vprintk.c \
+	map_ptr_kern.c core_kern.c
 # Generate both light skeleton and libbpf skeleton for these
-LSKELS_EXTRA := test_ksyms_module.c test_ksyms_weak.c
+LSKELS_EXTRA := test_ksyms_module.c test_ksyms_weak.c kfunc_call_test_subprog.c
 SKEL_BLACKLIST += $$(LSKELS)
 
 test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o
@@ -531,14 +536,18 @@ $(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_bloom_filter_map.o: $(OUTPUT)/bloom_filter_bench.skel.h
+$(OUTPUT)/bench_bpf_loop.o: $(OUTPUT)/bpf_loop_bench.skel.h
 $(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ)
 $(OUTPUT)/bench: LDLIBS += -lm
-$(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \
+$(OUTPUT)/bench: $(OUTPUT)/bench.o \
+		 $(TESTING_HELPERS) \
+		 $(TRACE_HELPERS) \
 		 $(OUTPUT)/bench_count.o \
 		 $(OUTPUT)/bench_rename.o \
 		 $(OUTPUT)/bench_trigger.o \
 		 $(OUTPUT)/bench_ringbufs.o \
-		 $(OUTPUT)/bench_bloom_filter_map.o
+		 $(OUTPUT)/bench_bloom_filter_map.o \
+		 $(OUTPUT)/bench_bpf_loop.o
 	$(call msg,BINARY,,$@)
 	$(Q)$(CC) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@
 
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index cc4722f693e9..3d6082b97a56 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -134,6 +134,39 @@ void hits_drops_report_final(struct bench_res res[], int res_cnt)
 	       total_ops_mean, total_ops_stddev);
 }
 
+void ops_report_progress(int iter, struct bench_res *res, long delta_ns)
+{
+	double hits_per_sec, hits_per_prod;
+
+	hits_per_sec = res->hits / 1000000.0 / (delta_ns / 1000000000.0);
+	hits_per_prod = hits_per_sec / env.producer_cnt;
+
+	printf("Iter %3d (%7.3lfus): ", iter, (delta_ns - 1000000000) / 1000.0);
+
+	printf("hits %8.3lfM/s (%7.3lfM/prod)\n", hits_per_sec, hits_per_prod);
+}
+
+void ops_report_final(struct bench_res res[], int res_cnt)
+{
+	double hits_mean = 0.0, hits_stddev = 0.0;
+	int i;
+
+	for (i = 0; i < res_cnt; i++)
+		hits_mean += res[i].hits / 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);
+
+		hits_stddev = sqrt(hits_stddev);
+	}
+	printf("Summary: throughput %8.3lf \u00B1 %5.3lf M ops/s (%7.3lfM ops/prod), ",
+	       hits_mean, hits_stddev, hits_mean / env.producer_cnt);
+	printf("latency %8.3lf ns/op\n", 1000.0 / hits_mean * env.producer_cnt);
+}
+
 const char *argp_program_version = "benchmark";
 const char *argp_program_bug_address = "<bpf@vger.kernel.org>";
 const char argp_program_doc[] =
@@ -171,10 +204,12 @@ static const struct argp_option opts[] = {
 
 extern struct argp bench_ringbufs_argp;
 extern struct argp bench_bloom_map_argp;
+extern struct argp bench_bpf_loop_argp;
 
 static const struct argp_child bench_parsers[] = {
 	{ &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 },
 	{ &bench_bloom_map_argp, 0, "Bloom filter map benchmark", 0 },
+	{ &bench_bpf_loop_argp, 0, "bpf_loop helper benchmark", 0 },
 	{},
 };
 
@@ -359,6 +394,11 @@ extern const struct bench bench_trig_kprobe;
 extern const struct bench bench_trig_fentry;
 extern const struct bench bench_trig_fentry_sleep;
 extern const struct bench bench_trig_fmodret;
+extern const struct bench bench_trig_uprobe_base;
+extern const struct bench bench_trig_uprobe_with_nop;
+extern const struct bench bench_trig_uretprobe_with_nop;
+extern const struct bench bench_trig_uprobe_without_nop;
+extern const struct bench bench_trig_uretprobe_without_nop;
 extern const struct bench bench_rb_libbpf;
 extern const struct bench bench_rb_custom;
 extern const struct bench bench_pb_libbpf;
@@ -368,6 +408,7 @@ extern const struct bench bench_bloom_update;
 extern const struct bench bench_bloom_false_positive;
 extern const struct bench bench_hashmap_without_bloom;
 extern const struct bench bench_hashmap_with_bloom;
+extern const struct bench bench_bpf_loop;
 
 static const struct bench *benchs[] = {
 	&bench_count_global,
@@ -385,6 +426,11 @@ static const struct bench *benchs[] = {
 	&bench_trig_fentry,
 	&bench_trig_fentry_sleep,
 	&bench_trig_fmodret,
+	&bench_trig_uprobe_base,
+	&bench_trig_uprobe_with_nop,
+	&bench_trig_uretprobe_with_nop,
+	&bench_trig_uprobe_without_nop,
+	&bench_trig_uretprobe_without_nop,
 	&bench_rb_libbpf,
 	&bench_rb_custom,
 	&bench_pb_libbpf,
@@ -394,6 +440,7 @@ static const struct bench *benchs[] = {
 	&bench_bloom_false_positive,
 	&bench_hashmap_without_bloom,
 	&bench_hashmap_with_bloom,
+	&bench_bpf_loop,
 };
 
 static void setup_benchmark()
diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h
index 624c6b11501f..50785503756b 100644
--- a/tools/testing/selftests/bpf/bench.h
+++ b/tools/testing/selftests/bpf/bench.h
@@ -59,6 +59,8 @@ 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);
 void false_hits_report_progress(int iter, struct bench_res *res, long delta_ns);
 void false_hits_report_final(struct bench_res res[], int res_cnt);
+void ops_report_progress(int iter, struct bench_res *res, long delta_ns);
+void ops_report_final(struct bench_res res[], int res_cnt);
 
 static inline __u64 get_time_ns() {
 	struct timespec t;
diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c b/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c
new file mode 100644
index 000000000000..d0a6572bfab6
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <argp.h>
+#include "bench.h"
+#include "bpf_loop_bench.skel.h"
+
+/* BPF triggering benchmarks */
+static struct ctx {
+	struct bpf_loop_bench *skel;
+} ctx;
+
+static struct {
+	__u32 nr_loops;
+} args = {
+	.nr_loops = 10,
+};
+
+enum {
+	ARG_NR_LOOPS = 4000,
+};
+
+static const struct argp_option opts[] = {
+	{ "nr_loops", ARG_NR_LOOPS, "nr_loops", 0,
+		"Set number of loops for the bpf_loop helper"},
+	{},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+	switch (key) {
+	case ARG_NR_LOOPS:
+		args.nr_loops = strtol(arg, NULL, 10);
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+
+	return 0;
+}
+
+/* exported into benchmark runner */
+const struct argp bench_bpf_loop_argp = {
+	.options = opts,
+	.parser = parse_arg,
+};
+
+static void validate(void)
+{
+	if (env.consumer_cnt != 1) {
+		fprintf(stderr, "benchmark doesn't support multi-consumer!\n");
+		exit(1);
+	}
+}
+
+static void *producer(void *input)
+{
+	while (true)
+		/* trigger the bpf program */
+		syscall(__NR_getpgid);
+
+	return NULL;
+}
+
+static void *consumer(void *input)
+{
+	return NULL;
+}
+
+static void measure(struct bench_res *res)
+{
+	res->hits = atomic_swap(&ctx.skel->bss->hits, 0);
+}
+
+static void setup(void)
+{
+	struct bpf_link *link;
+
+	setup_libbpf();
+
+	ctx.skel = bpf_loop_bench__open_and_load();
+	if (!ctx.skel) {
+		fprintf(stderr, "failed to open skeleton\n");
+		exit(1);
+	}
+
+	link = bpf_program__attach(ctx.skel->progs.benchmark);
+	if (!link) {
+		fprintf(stderr, "failed to attach program!\n");
+		exit(1);
+	}
+
+	ctx.skel->bss->nr_loops = args.nr_loops;
+}
+
+const struct bench bench_bpf_loop = {
+	.name = "bpf-loop",
+	.validate = validate,
+	.setup = setup,
+	.producer_thread = producer,
+	.consumer_thread = consumer,
+	.measure = measure,
+	.report_progress = ops_report_progress,
+	.report_final = ops_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c
index f41a491a8cc0..049a5ad56f65 100644
--- a/tools/testing/selftests/bpf/benchs/bench_trigger.c
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2020 Facebook */
 #include "bench.h"
 #include "trigger_bench.skel.h"
+#include "trace_helpers.h"
 
 /* BPF triggering benchmarks */
 static struct trigger_ctx {
@@ -107,6 +108,101 @@ static void *trigger_consumer(void *input)
 	return NULL;
 }
 
+/* make sure call is not inlined and not avoided by compiler, so __weak and
+ * inline asm volatile in the body of the function
+ *
+ * There is a performance difference between uprobing at nop location vs other
+ * instructions. So use two different targets, one of which starts with nop
+ * and another doesn't.
+ *
+ * GCC doesn't generate stack setup preample for these functions due to them
+ * having no input arguments and doing nothing in the body.
+ */
+__weak void uprobe_target_with_nop(void)
+{
+	asm volatile ("nop");
+}
+
+__weak void uprobe_target_without_nop(void)
+{
+	asm volatile ("");
+}
+
+static void *uprobe_base_producer(void *input)
+{
+	while (true) {
+		uprobe_target_with_nop();
+		atomic_inc(&base_hits.value);
+	}
+	return NULL;
+}
+
+static void *uprobe_producer_with_nop(void *input)
+{
+	while (true)
+		uprobe_target_with_nop();
+	return NULL;
+}
+
+static void *uprobe_producer_without_nop(void *input)
+{
+	while (true)
+		uprobe_target_without_nop();
+	return NULL;
+}
+
+static void usetup(bool use_retprobe, bool use_nop)
+{
+	size_t uprobe_offset;
+	ssize_t base_addr;
+	struct bpf_link *link;
+
+	setup_libbpf();
+
+	ctx.skel = trigger_bench__open_and_load();
+	if (!ctx.skel) {
+		fprintf(stderr, "failed to open skeleton\n");
+		exit(1);
+	}
+
+	base_addr = get_base_addr();
+	if (use_nop)
+		uprobe_offset = get_uprobe_offset(&uprobe_target_with_nop, base_addr);
+	else
+		uprobe_offset = get_uprobe_offset(&uprobe_target_without_nop, base_addr);
+
+	link = bpf_program__attach_uprobe(ctx.skel->progs.bench_trigger_uprobe,
+					  use_retprobe,
+					  -1 /* all PIDs */,
+					  "/proc/self/exe",
+					  uprobe_offset);
+	if (!link) {
+		fprintf(stderr, "failed to attach uprobe!\n");
+		exit(1);
+	}
+	ctx.skel->links.bench_trigger_uprobe = link;
+}
+
+static void uprobe_setup_with_nop()
+{
+	usetup(false, true);
+}
+
+static void uretprobe_setup_with_nop()
+{
+	usetup(true, true);
+}
+
+static void uprobe_setup_without_nop()
+{
+	usetup(false, false);
+}
+
+static void uretprobe_setup_without_nop()
+{
+	usetup(true, false);
+}
+
 const struct bench bench_trig_base = {
 	.name = "trig-base",
 	.validate = trigger_validate,
@@ -182,3 +278,53 @@ const struct bench bench_trig_fmodret = {
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
 };
+
+const struct bench bench_trig_uprobe_base = {
+	.name = "trig-uprobe-base",
+	.setup = NULL, /* no uprobe/uretprobe is attached */
+	.producer_thread = uprobe_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_uprobe_with_nop = {
+	.name = "trig-uprobe-with-nop",
+	.setup = uprobe_setup_with_nop,
+	.producer_thread = uprobe_producer_with_nop,
+	.consumer_thread = trigger_consumer,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_uretprobe_with_nop = {
+	.name = "trig-uretprobe-with-nop",
+	.setup = uretprobe_setup_with_nop,
+	.producer_thread = uprobe_producer_with_nop,
+	.consumer_thread = trigger_consumer,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_uprobe_without_nop = {
+	.name = "trig-uprobe-without-nop",
+	.setup = uprobe_setup_without_nop,
+	.producer_thread = uprobe_producer_without_nop,
+	.consumer_thread = trigger_consumer,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_uretprobe_without_nop = {
+	.name = "trig-uretprobe-without-nop",
+	.setup = uretprobe_setup_without_nop,
+	.producer_thread = uprobe_producer_without_nop,
+	.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_bpf_loop.sh b/tools/testing/selftests/bpf/benchs/run_bench_bpf_loop.sh
new file mode 100755
index 000000000000..d4f5f73b356b
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_bpf_loop.sh
@@ -0,0 +1,15 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source ./benchs/run_common.sh
+
+set -eufo pipefail
+
+for t in 1 4 8 12 16; do
+for i in 10 100 500 1000 5000 10000 50000 100000 500000 1000000; do
+subtitle "nr_loops: $i, nr_threads: $t"
+	summarize_ops "bpf_loop: " \
+	    "$($RUN_BENCH -p $t --nr_loops $i bpf-loop)"
+	printf "\n"
+done
+done
diff --git a/tools/testing/selftests/bpf/benchs/run_common.sh b/tools/testing/selftests/bpf/benchs/run_common.sh
index 9a16be78b180..6c5e6023a69f 100644
--- a/tools/testing/selftests/bpf/benchs/run_common.sh
+++ b/tools/testing/selftests/bpf/benchs/run_common.sh
@@ -33,6 +33,14 @@ function percentage()
 	echo "$*" | sed -E "s/.*Percentage\s=\s+([0-9]+\.[0-9]+).*/\1/"
 }
 
+function ops()
+{
+	echo -n "throughput: "
+	echo -n "$*" | sed -E "s/.*throughput\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+\sM\sops\/s).*/\1/"
+	echo -n -e ", latency: "
+	echo "$*" | sed -E "s/.*latency\s+([0-9]+\.[0-9]+\sns\/op).*/\1/"
+}
+
 function total()
 {
 	echo "$*" | sed -E "s/.*total operations\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+M\/s).*/\1/"
@@ -52,6 +60,13 @@ function summarize_percentage()
 	printf "%-20s %s%%\n" "$bench" "$(percentage $summary)"
 }
 
+function summarize_ops()
+{
+	bench="$1"
+	summary=$(echo $2 | tail -n1)
+	printf "%-20s %s\n" "$bench" "$(ops $summary)"
+}
+
 function summarize_total()
 {
 	bench="$1"
diff --git a/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c
index f4d870da7684..78c76496b14a 100644
--- a/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c
+++ b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c
@@ -68,13 +68,6 @@ static void map_batch_verify(int *visited, __u32 max_entries, int *keys,
 
 static void __test_map_lookup_and_update_batch(bool is_pcpu)
 {
-	struct bpf_create_map_attr xattr = {
-		.name = "array_map",
-		.map_type = is_pcpu ? BPF_MAP_TYPE_PERCPU_ARRAY :
-				      BPF_MAP_TYPE_ARRAY,
-		.key_size = sizeof(int),
-		.value_size = sizeof(__s64),
-	};
 	int map_fd, *keys, *visited;
 	__u32 count, total, total_success;
 	const __u32 max_entries = 10;
@@ -86,10 +79,10 @@ static void __test_map_lookup_and_update_batch(bool is_pcpu)
 		.flags = 0,
 	);
 
-	xattr.max_entries = max_entries;
-	map_fd = bpf_create_map_xattr(&xattr);
+	map_fd = bpf_map_create(is_pcpu ? BPF_MAP_TYPE_PERCPU_ARRAY : BPF_MAP_TYPE_ARRAY,
+				"array_map", sizeof(int), sizeof(__s64), max_entries, NULL);
 	CHECK(map_fd == -1,
-	      "bpf_create_map_xattr()", "error:%s\n", strerror(errno));
+	      "bpf_map_create()", "error:%s\n", strerror(errno));
 
 	value_size = sizeof(__s64);
 	if (is_pcpu)
diff --git a/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c
index 976bf415fbdd..f807d53fd8dd 100644
--- a/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c
+++ b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c
@@ -83,22 +83,15 @@ void __test_map_lookup_and_delete_batch(bool is_pcpu)
 	int err, step, value_size;
 	bool nospace_err;
 	void *values;
-	struct bpf_create_map_attr xattr = {
-		.name = "hash_map",
-		.map_type = is_pcpu ? BPF_MAP_TYPE_PERCPU_HASH :
-			    BPF_MAP_TYPE_HASH,
-		.key_size = sizeof(int),
-		.value_size = sizeof(int),
-	};
 	DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
 		.elem_flags = 0,
 		.flags = 0,
 	);
 
-	xattr.max_entries = max_entries;
-	map_fd = bpf_create_map_xattr(&xattr);
+	map_fd = bpf_map_create(is_pcpu ? BPF_MAP_TYPE_PERCPU_HASH : BPF_MAP_TYPE_HASH,
+				"hash_map", sizeof(int), sizeof(int), max_entries, NULL);
 	CHECK(map_fd == -1,
-	      "bpf_create_map_xattr()", "error:%s\n", strerror(errno));
+	      "bpf_map_create()", "error:%s\n", strerror(errno));
 
 	value_size = is_pcpu ? sizeof(value) : sizeof(int);
 	keys = malloc(max_entries * sizeof(int));
diff --git a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c
index 2e986e5e4cac..87d07b596e17 100644
--- a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c
+++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c
@@ -64,13 +64,7 @@ static void map_batch_verify(int *visited, __u32 max_entries,
 
 void test_lpm_trie_map_batch_ops(void)
 {
-	struct bpf_create_map_attr xattr = {
-		.name = "lpm_trie_map",
-		.map_type = BPF_MAP_TYPE_LPM_TRIE,
-		.key_size = sizeof(struct test_lpm_key),
-		.value_size = sizeof(int),
-		.map_flags = BPF_F_NO_PREALLOC,
-	};
+	LIBBPF_OPTS(bpf_map_create_opts, create_opts, .map_flags = BPF_F_NO_PREALLOC);
 	struct test_lpm_key *keys, key;
 	int map_fd, *values, *visited;
 	__u32 step, count, total, total_success;
@@ -82,9 +76,10 @@ void test_lpm_trie_map_batch_ops(void)
 		.flags = 0,
 	);
 
-	xattr.max_entries = max_entries;
-	map_fd = bpf_create_map_xattr(&xattr);
-	CHECK(map_fd == -1, "bpf_create_map_xattr()", "error:%s\n",
+	map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, "lpm_trie_map",
+				sizeof(struct test_lpm_key), sizeof(int),
+				max_entries, &create_opts);
+	CHECK(map_fd == -1, "bpf_map_create()", "error:%s\n",
 	      strerror(errno));
 
 	keys = malloc(max_entries * sizeof(struct test_lpm_key));
diff --git a/tools/testing/selftests/bpf/map_tests/sk_storage_map.c b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c
index e569edc679d8..099eb4dfd4f7 100644
--- a/tools/testing/selftests/bpf/map_tests/sk_storage_map.c
+++ b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c
@@ -19,16 +19,12 @@
 #include <test_btf.h>
 #include <test_maps.h>
 
-static struct bpf_create_map_attr xattr = {
-	.name = "sk_storage_map",
-	.map_type = BPF_MAP_TYPE_SK_STORAGE,
-	.map_flags = BPF_F_NO_PREALLOC,
-	.max_entries = 0,
-	.key_size = 4,
-	.value_size = 8,
+static struct bpf_map_create_opts map_opts = {
+	.sz = sizeof(map_opts),
 	.btf_key_type_id = 1,
 	.btf_value_type_id = 3,
 	.btf_fd = -1,
+	.map_flags = BPF_F_NO_PREALLOC,
 };
 
 static unsigned int nr_sk_threads_done;
@@ -140,7 +136,7 @@ static int load_btf(void)
 	memcpy(raw_btf + sizeof(btf_hdr) + sizeof(btf_raw_types),
 	       btf_str_sec, sizeof(btf_str_sec));
 
-	return bpf_load_btf(raw_btf, sizeof(raw_btf), 0, 0, 0);
+	return bpf_btf_load(raw_btf, sizeof(raw_btf), NULL);
 }
 
 static int create_sk_storage_map(void)
@@ -150,13 +146,13 @@ static int create_sk_storage_map(void)
 	btf_fd = load_btf();
 	CHECK(btf_fd == -1, "bpf_load_btf", "btf_fd:%d errno:%d\n",
 	      btf_fd, errno);
-	xattr.btf_fd = btf_fd;
+	map_opts.btf_fd = btf_fd;
 
-	map_fd = bpf_create_map_xattr(&xattr);
-	xattr.btf_fd = -1;
+	map_fd = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "sk_storage_map", 4, 8, 0, &map_opts);
+	map_opts.btf_fd = -1;
 	close(btf_fd);
 	CHECK(map_fd == -1,
-	      "bpf_create_map_xattr()", "errno:%d\n", errno);
+	      "bpf_map_create()", "errno:%d\n", errno);
 
 	return map_fd;
 }
@@ -463,20 +459,20 @@ static void test_sk_storage_map_basic(void)
 		int cnt;
 		int lock;
 	} value = { .cnt = 0xeB9f, .lock = 0, }, lookup_value;
-	struct bpf_create_map_attr bad_xattr;
+	struct bpf_map_create_opts bad_xattr;
 	int btf_fd, map_fd, sk_fd, err;
 
 	btf_fd = load_btf();
 	CHECK(btf_fd == -1, "bpf_load_btf", "btf_fd:%d errno:%d\n",
 	      btf_fd, errno);
-	xattr.btf_fd = btf_fd;
+	map_opts.btf_fd = btf_fd;
 
 	sk_fd = socket(AF_INET6, SOCK_STREAM, 0);
 	CHECK(sk_fd == -1, "socket()", "sk_fd:%d errno:%d\n",
 	      sk_fd, errno);
 
-	map_fd = bpf_create_map_xattr(&xattr);
-	CHECK(map_fd == -1, "bpf_create_map_xattr(good_xattr)",
+	map_fd = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "sk_storage_map", 4, 8, 0, &map_opts);
+	CHECK(map_fd == -1, "bpf_map_create(good_xattr)",
 	      "map_fd:%d errno:%d\n", map_fd, errno);
 
 	/* Add new elem */
@@ -560,31 +556,29 @@ static void test_sk_storage_map_basic(void)
 	CHECK(!err || errno != ENOENT, "bpf_map_delete_elem()",
 	      "err:%d errno:%d\n", err, errno);
 
-	memcpy(&bad_xattr, &xattr, sizeof(xattr));
+	memcpy(&bad_xattr, &map_opts, sizeof(map_opts));
 	bad_xattr.btf_key_type_id = 0;
-	err = bpf_create_map_xattr(&bad_xattr);
-	CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)",
+	err = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "sk_storage_map", 4, 8, 0, &bad_xattr);
+	CHECK(!err || errno != EINVAL, "bpf_map_create(bad_xattr)",
 	      "err:%d errno:%d\n", err, errno);
 
-	memcpy(&bad_xattr, &xattr, sizeof(xattr));
+	memcpy(&bad_xattr, &map_opts, sizeof(map_opts));
 	bad_xattr.btf_key_type_id = 3;
-	err = bpf_create_map_xattr(&bad_xattr);
-	CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)",
+	err = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "sk_storage_map", 4, 8, 0, &bad_xattr);
+	CHECK(!err || errno != EINVAL, "bpf_map_create(bad_xattr)",
 	      "err:%d errno:%d\n", err, errno);
 
-	memcpy(&bad_xattr, &xattr, sizeof(xattr));
-	bad_xattr.max_entries = 1;
-	err = bpf_create_map_xattr(&bad_xattr);
-	CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)",
+	err = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "sk_storage_map", 4, 8, 1, &map_opts);
+	CHECK(!err || errno != EINVAL, "bpf_map_create(bad_xattr)",
 	      "err:%d errno:%d\n", err, errno);
 
-	memcpy(&bad_xattr, &xattr, sizeof(xattr));
+	memcpy(&bad_xattr, &map_opts, sizeof(map_opts));
 	bad_xattr.map_flags = 0;
-	err = bpf_create_map_xattr(&bad_xattr);
+	err = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "sk_storage_map", 4, 8, 0, &bad_xattr);
 	CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)",
 	      "err:%d errno:%d\n", err, errno);
 
-	xattr.btf_fd = -1;
+	map_opts.btf_fd = -1;
 	close(btf_fd);
 	close(map_fd);
 	close(sk_fd);
diff --git a/tools/testing/selftests/bpf/prog_tests/atomics.c b/tools/testing/selftests/bpf/prog_tests/atomics.c
index 0f9525293881..86b7d5d84eec 100644
--- a/tools/testing/selftests/bpf/prog_tests/atomics.c
+++ b/tools/testing/selftests/bpf/prog_tests/atomics.c
@@ -167,7 +167,7 @@ static void test_cmpxchg(struct atomics_lskel *skel)
 	prog_fd = skel->progs.cmpxchg.prog_fd;
 	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
 				NULL, NULL, &retval, &duration);
-	if (CHECK(err || retval, "test_run add",
+	if (CHECK(err || retval, "test_run cmpxchg",
 		  "err %d errno %d retval %d duration %d\n", err, errno, retval, duration))
 		goto cleanup;
 
@@ -196,7 +196,7 @@ static void test_xchg(struct atomics_lskel *skel)
 	prog_fd = skel->progs.xchg.prog_fd;
 	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
 				NULL, NULL, &retval, &duration);
-	if (CHECK(err || retval, "test_run add",
+	if (CHECK(err || retval, "test_run xchg",
 		  "err %d errno %d retval %d duration %d\n", err, errno, retval, duration))
 		goto cleanup;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
index be73e3de6668..d2d9e965eba5 100644
--- a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
@@ -7,32 +7,33 @@
 
 static void test_fail_cases(void)
 {
+	LIBBPF_OPTS(bpf_map_create_opts, opts);
 	__u32 value;
 	int fd, err;
 
 	/* Invalid key size */
-	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 4, sizeof(value), 100, 0);
-	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid key size"))
+	fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 4, sizeof(value), 100, NULL);
+	if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid key size"))
 		close(fd);
 
 	/* Invalid value size */
-	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, 0, 100, 0);
-	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid value size 0"))
+	fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, 0, 100, NULL);
+	if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid value size 0"))
 		close(fd);
 
 	/* Invalid max entries size */
-	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 0, 0);
-	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid max entries size"))
+	fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(value), 0, NULL);
+	if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid max entries size"))
 		close(fd);
 
 	/* Bloom filter maps do not support BPF_F_NO_PREALLOC */
-	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 100,
-			    BPF_F_NO_PREALLOC);
-	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid flags"))
+	opts.map_flags = BPF_F_NO_PREALLOC;
+	fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(value), 100, &opts);
+	if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid flags"))
 		close(fd);
 
-	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 100, 0);
-	if (!ASSERT_GE(fd, 0, "bpf_create_map bloom filter"))
+	fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(value), 100, NULL);
+	if (!ASSERT_GE(fd, 0, "bpf_map_create bloom filter"))
 		return;
 
 	/* Test invalid flags */
@@ -56,13 +57,14 @@ static void test_fail_cases(void)
 
 static void test_success_cases(void)
 {
+	LIBBPF_OPTS(bpf_map_create_opts, opts);
 	char value[11];
 	int fd, err;
 
 	/* Create a map */
-	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 100,
-			    BPF_F_ZERO_SEED | BPF_F_NUMA_NODE);
-	if (!ASSERT_GE(fd, 0, "bpf_create_map bloom filter success case"))
+	opts.map_flags = BPF_F_ZERO_SEED | BPF_F_NUMA_NODE;
+	fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(value), 100, &opts);
+	if (!ASSERT_GE(fd, 0, "bpf_map_create bloom filter success case"))
 		return;
 
 	/* Add a value to the bloom filter */
@@ -100,9 +102,9 @@ static void test_inner_map(struct bloom_filter_map *skel, const __u32 *rand_vals
 	struct bpf_link *link;
 
 	/* Create a bloom filter map that will be used as the inner map */
-	inner_map_fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(*rand_vals),
-				      nr_rand_vals, 0);
-	if (!ASSERT_GE(inner_map_fd, 0, "bpf_create_map bloom filter inner map"))
+	inner_map_fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(*rand_vals),
+				      nr_rand_vals, NULL);
+	if (!ASSERT_GE(inner_map_fd, 0, "bpf_map_create bloom filter inner map"))
 		return;
 
 	for (i = 0; i < nr_rand_vals; i++) {
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 3e10abce3e5a..b84f859b1267 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -469,12 +469,12 @@ static void test_overflow(bool test_e2big_overflow, bool ret1)
 	 * 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",
+	map1_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 8, 1, NULL);
+	if (CHECK(map1_fd < 0, "bpf_map_create",
 		  "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",
+	map2_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 8, 1, NULL);
+	if (CHECK(map2_fd < 0, "bpf_map_create",
 		  "map_creation failed: %s\n", strerror(errno)))
 		goto free_map1;
 
@@ -1206,13 +1206,14 @@ static void test_task_vma(void)
 		goto out;
 
 	/* Read CMP_BUFFER_SIZE (1kB) from bpf_iter. Read in small chunks
-	 * to trigger seq_file corner cases. The expected output is much
-	 * longer than 1kB, so the while loop will terminate.
+	 * to trigger seq_file corner cases.
 	 */
 	len = 0;
 	while (len < CMP_BUFFER_SIZE) {
 		err = read_fd_into_buffer(iter_fd, task_vma_output + len,
 					  min(read_size, CMP_BUFFER_SIZE - len));
+		if (!err)
+			break;
 		if (CHECK(err < 0, "read_iter_fd", "read_iter_fd failed\n"))
 			goto out;
 		len += err;
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_loop.c b/tools/testing/selftests/bpf/prog_tests/bpf_loop.c
new file mode 100644
index 000000000000..380d7a2072e3
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_loop.c
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "bpf_loop.skel.h"
+
+static void check_nr_loops(struct bpf_loop *skel)
+{
+	struct bpf_link *link;
+
+	link = bpf_program__attach(skel->progs.test_prog);
+	if (!ASSERT_OK_PTR(link, "link"))
+		return;
+
+	/* test 0 loops */
+	skel->bss->nr_loops = 0;
+
+	usleep(1);
+
+	ASSERT_EQ(skel->bss->nr_loops_returned, skel->bss->nr_loops,
+		  "0 loops");
+
+	/* test 500 loops */
+	skel->bss->nr_loops = 500;
+
+	usleep(1);
+
+	ASSERT_EQ(skel->bss->nr_loops_returned, skel->bss->nr_loops,
+		  "500 loops");
+	ASSERT_EQ(skel->bss->g_output, (500 * 499) / 2, "g_output");
+
+	/* test exceeding the max limit */
+	skel->bss->nr_loops = -1;
+
+	usleep(1);
+
+	ASSERT_EQ(skel->bss->err, -E2BIG, "over max limit");
+
+	bpf_link__destroy(link);
+}
+
+static void check_callback_fn_stop(struct bpf_loop *skel)
+{
+	struct bpf_link *link;
+
+	link = bpf_program__attach(skel->progs.test_prog);
+	if (!ASSERT_OK_PTR(link, "link"))
+		return;
+
+	/* testing that loop is stopped when callback_fn returns 1 */
+	skel->bss->nr_loops = 400;
+	skel->data->stop_index = 50;
+
+	usleep(1);
+
+	ASSERT_EQ(skel->bss->nr_loops_returned, skel->data->stop_index + 1,
+		  "nr_loops_returned");
+	ASSERT_EQ(skel->bss->g_output, (50 * 49) / 2,
+		  "g_output");
+
+	bpf_link__destroy(link);
+}
+
+static void check_null_callback_ctx(struct bpf_loop *skel)
+{
+	struct bpf_link *link;
+
+	/* check that user is able to pass in a null callback_ctx */
+	link = bpf_program__attach(skel->progs.prog_null_ctx);
+	if (!ASSERT_OK_PTR(link, "link"))
+		return;
+
+	skel->bss->nr_loops = 10;
+
+	usleep(1);
+
+	ASSERT_EQ(skel->bss->nr_loops_returned, skel->bss->nr_loops,
+		  "nr_loops_returned");
+
+	bpf_link__destroy(link);
+}
+
+static void check_invalid_flags(struct bpf_loop *skel)
+{
+	struct bpf_link *link;
+
+	/* check that passing in non-zero flags returns -EINVAL */
+	link = bpf_program__attach(skel->progs.prog_invalid_flags);
+	if (!ASSERT_OK_PTR(link, "link"))
+		return;
+
+	usleep(1);
+
+	ASSERT_EQ(skel->bss->err, -EINVAL, "err");
+
+	bpf_link__destroy(link);
+}
+
+static void check_nested_calls(struct bpf_loop *skel)
+{
+	__u32 nr_loops = 100, nested_callback_nr_loops = 4;
+	struct bpf_link *link;
+
+	/* check that nested calls are supported */
+	link = bpf_program__attach(skel->progs.prog_nested_calls);
+	if (!ASSERT_OK_PTR(link, "link"))
+		return;
+
+	skel->bss->nr_loops = nr_loops;
+	skel->bss->nested_callback_nr_loops = nested_callback_nr_loops;
+
+	usleep(1);
+
+	ASSERT_EQ(skel->bss->nr_loops_returned, nr_loops * nested_callback_nr_loops
+		  * nested_callback_nr_loops, "nr_loops_returned");
+	ASSERT_EQ(skel->bss->g_output, (4 * 3) / 2 * nested_callback_nr_loops
+		* nr_loops, "g_output");
+
+	bpf_link__destroy(link);
+}
+
+void test_bpf_loop(void)
+{
+	struct bpf_loop *skel;
+
+	skel = bpf_loop__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "bpf_loop__open_and_load"))
+		return;
+
+	skel->bss->pid = getpid();
+
+	if (test__start_subtest("check_nr_loops"))
+		check_nr_loops(skel);
+	if (test__start_subtest("check_callback_fn_stop"))
+		check_callback_fn_stop(skel);
+	if (test__start_subtest("check_null_callback_ctx"))
+		check_null_callback_ctx(skel);
+	if (test__start_subtest("check_invalid_flags"))
+		check_invalid_flags(skel);
+	if (test__start_subtest("check_nested_calls"))
+		check_nested_calls(skel);
+
+	bpf_loop__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index 94e03df69d71..8daca0ac909f 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -217,14 +217,16 @@ static bool found;
 static int libbpf_debug_print(enum libbpf_print_level level,
 			      const char *format, va_list args)
 {
-	char *log_buf;
+	const char *log_buf;
 
 	if (level != LIBBPF_WARN ||
-	    strcmp(format, "libbpf: \n%s\n")) {
+	    !strstr(format, "-- BEGIN PROG LOAD LOG --")) {
 		vprintf(format, args);
 		return 0;
 	}
 
+	/* skip prog_name */
+	va_arg(args, char *);
 	log_buf = va_arg(args, char *);
 	if (!log_buf)
 		goto out;
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
index 27f5d8ea7964..ff6cce9fef06 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
@@ -19,16 +19,28 @@ extern int extra_prog_load_log_flags;
 
 static int check_load(const char *file, enum bpf_prog_type type)
 {
-	struct bpf_prog_load_attr attr;
 	struct bpf_object *obj = NULL;
-	int err, prog_fd;
-
-	memset(&attr, 0, sizeof(struct bpf_prog_load_attr));
-	attr.file = file;
-	attr.prog_type = type;
-	attr.log_level = 4 | extra_prog_load_log_flags;
-	attr.prog_flags = BPF_F_TEST_RND_HI32;
-	err = bpf_prog_load_xattr(&attr, &obj, &prog_fd);
+	struct bpf_program *prog;
+	int err;
+
+	obj = bpf_object__open_file(file, NULL);
+	err = libbpf_get_error(obj);
+	if (err)
+		return err;
+
+	prog = bpf_object__next_program(obj, NULL);
+	if (!prog) {
+		err = -ENOENT;
+		goto err_out;
+	}
+
+	bpf_program__set_type(prog, type);
+	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32);
+	bpf_program__set_log_level(prog, 4 | extra_prog_load_log_flags);
+
+	err = bpf_object__load(obj);
+
+err_out:
 	bpf_object__close(obj);
 	return err;
 }
@@ -115,6 +127,12 @@ void test_verif_scale_pyperf600()
 	scale_test("pyperf600.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
 }
 
+void test_verif_scale_pyperf600_bpf_loop(void)
+{
+	/* use the bpf_loop helper*/
+	scale_test("pyperf600_bpf_loop.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
 void test_verif_scale_pyperf600_nounroll()
 {
 	/* no unroll at all.
@@ -165,6 +183,12 @@ void test_verif_scale_strobemeta()
 	scale_test("strobemeta.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
 }
 
+void test_verif_scale_strobemeta_bpf_loop(void)
+{
+	/* use the bpf_loop helper*/
+	scale_test("strobemeta_bpf_loop.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
 void test_verif_scale_strobemeta_nounroll1()
 {
 	/* no unroll, tiny loops */
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 4aa6343dc4c8..01b776a7beeb 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -4071,10 +4071,32 @@ done:
 	return raw_btf;
 }
 
+static int load_raw_btf(const void *raw_data, size_t raw_size)
+{
+	LIBBPF_OPTS(bpf_btf_load_opts, opts);
+	int btf_fd;
+
+	if (always_log) {
+		opts.log_buf = btf_log_buf,
+		opts.log_size = BTF_LOG_BUF_SIZE,
+		opts.log_level = 1;
+	}
+
+	btf_fd = bpf_btf_load(raw_data, raw_size, &opts);
+	if (btf_fd < 0 && !always_log) {
+		opts.log_buf = btf_log_buf,
+		opts.log_size = BTF_LOG_BUF_SIZE,
+		opts.log_level = 1;
+		btf_fd = bpf_btf_load(raw_data, raw_size, &opts);
+	}
+
+	return btf_fd;
+}
+
 static void do_test_raw(unsigned int test_num)
 {
 	struct btf_raw_test *test = &raw_tests[test_num - 1];
-	struct bpf_create_map_attr create_attr = {};
+	LIBBPF_OPTS(bpf_map_create_opts, opts);
 	int map_fd = -1, btf_fd = -1;
 	unsigned int raw_btf_size;
 	struct btf_header *hdr;
@@ -4100,16 +4122,14 @@ static void do_test_raw(unsigned int test_num)
 	hdr->str_len = (int)hdr->str_len + test->str_len_delta;
 
 	*btf_log_buf = '\0';
-	btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
-			      btf_log_buf, BTF_LOG_BUF_SIZE,
-			      always_log);
+	btf_fd = load_raw_btf(raw_btf, raw_btf_size);
 	free(raw_btf);
 
 	err = ((btf_fd < 0) != test->btf_load_err);
 	if (CHECK(err, "btf_fd:%d test->btf_load_err:%u",
 		  btf_fd, test->btf_load_err) ||
 	    CHECK(test->err_str && !strstr(btf_log_buf, test->err_str),
-		  "expected err_str:%s", test->err_str)) {
+		  "expected err_str:%s\n", test->err_str)) {
 		err = -1;
 		goto done;
 	}
@@ -4117,16 +4137,11 @@ static void do_test_raw(unsigned int test_num)
 	if (err || btf_fd < 0)
 		goto done;
 
-	create_attr.name = test->map_name;
-	create_attr.map_type = test->map_type;
-	create_attr.key_size = test->key_size;
-	create_attr.value_size = test->value_size;
-	create_attr.max_entries = test->max_entries;
-	create_attr.btf_fd = btf_fd;
-	create_attr.btf_key_type_id = test->key_type_id;
-	create_attr.btf_value_type_id = test->value_type_id;
-
-	map_fd = bpf_create_map_xattr(&create_attr);
+	opts.btf_fd = btf_fd;
+	opts.btf_key_type_id = test->key_type_id;
+	opts.btf_value_type_id = test->value_type_id;
+	map_fd = bpf_map_create(test->map_type, test->map_name,
+				test->key_size, test->value_size, test->max_entries, &opts);
 
 	err = ((map_fd < 0) != test->map_create_err);
 	CHECK(err, "map_fd:%d test->map_create_err:%u",
@@ -4232,9 +4247,7 @@ static int test_big_btf_info(unsigned int test_num)
 		goto done;
 	}
 
-	btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
-			      btf_log_buf, BTF_LOG_BUF_SIZE,
-			      always_log);
+	btf_fd = load_raw_btf(raw_btf, raw_btf_size);
 	if (CHECK(btf_fd < 0, "errno:%d", errno)) {
 		err = -1;
 		goto done;
@@ -4290,7 +4303,7 @@ done:
 static int test_btf_id(unsigned int test_num)
 {
 	const struct btf_get_info_test *test = &get_info_tests[test_num - 1];
-	struct bpf_create_map_attr create_attr = {};
+	LIBBPF_OPTS(bpf_map_create_opts, opts);
 	uint8_t *raw_btf = NULL, *user_btf[2] = {};
 	int btf_fd[2] = {-1, -1}, map_fd = -1;
 	struct bpf_map_info map_info = {};
@@ -4320,9 +4333,7 @@ static int test_btf_id(unsigned int test_num)
 		info[i].btf_size = raw_btf_size;
 	}
 
-	btf_fd[0] = bpf_load_btf(raw_btf, raw_btf_size,
-				 btf_log_buf, BTF_LOG_BUF_SIZE,
-				 always_log);
+	btf_fd[0] = load_raw_btf(raw_btf, raw_btf_size);
 	if (CHECK(btf_fd[0] < 0, "errno:%d", errno)) {
 		err = -1;
 		goto done;
@@ -4355,16 +4366,11 @@ static int test_btf_id(unsigned int test_num)
 	}
 
 	/* Test btf members in struct bpf_map_info */
-	create_attr.name = "test_btf_id";
-	create_attr.map_type = BPF_MAP_TYPE_ARRAY;
-	create_attr.key_size = sizeof(int);
-	create_attr.value_size = sizeof(unsigned int);
-	create_attr.max_entries = 4;
-	create_attr.btf_fd = btf_fd[0];
-	create_attr.btf_key_type_id = 1;
-	create_attr.btf_value_type_id = 2;
-
-	map_fd = bpf_create_map_xattr(&create_attr);
+	opts.btf_fd = btf_fd[0];
+	opts.btf_key_type_id = 1;
+	opts.btf_value_type_id = 2;
+	map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "test_btf_id",
+				sizeof(int), sizeof(int), 4, &opts);
 	if (CHECK(map_fd < 0, "errno:%d", errno)) {
 		err = -1;
 		goto done;
@@ -4457,9 +4463,7 @@ static void do_test_get_info(unsigned int test_num)
 		goto done;
 	}
 
-	btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
-			      btf_log_buf, BTF_LOG_BUF_SIZE,
-			      always_log);
+	btf_fd = load_raw_btf(raw_btf, raw_btf_size);
 	if (CHECK(btf_fd <= 0, "errno:%d", errno)) {
 		err = -1;
 		goto done;
@@ -5153,7 +5157,7 @@ static void do_test_pprint(int test_num)
 {
 	const struct btf_raw_test *test = &pprint_test_template[test_num];
 	enum pprint_mapv_kind_t mapv_kind = test->mapv_kind;
-	struct bpf_create_map_attr create_attr = {};
+	LIBBPF_OPTS(bpf_map_create_opts, opts);
 	bool ordered_map, lossless_map, percpu_map;
 	int err, ret, num_cpus, rounded_value_size;
 	unsigned int key, nr_read_elems;
@@ -5179,26 +5183,19 @@ static void do_test_pprint(int test_num)
 		return;
 
 	*btf_log_buf = '\0';
-	btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
-			      btf_log_buf, BTF_LOG_BUF_SIZE,
-			      always_log);
+	btf_fd = load_raw_btf(raw_btf, raw_btf_size);
 	free(raw_btf);
 
-	if (CHECK(btf_fd < 0, "errno:%d", errno)) {
+	if (CHECK(btf_fd < 0, "errno:%d\n", errno)) {
 		err = -1;
 		goto done;
 	}
 
-	create_attr.name = test->map_name;
-	create_attr.map_type = test->map_type;
-	create_attr.key_size = test->key_size;
-	create_attr.value_size = test->value_size;
-	create_attr.max_entries = test->max_entries;
-	create_attr.btf_fd = btf_fd;
-	create_attr.btf_key_type_id = test->key_type_id;
-	create_attr.btf_value_type_id = test->value_type_id;
-
-	map_fd = bpf_create_map_xattr(&create_attr);
+	opts.btf_fd = btf_fd;
+	opts.btf_key_type_id = test->key_type_id;
+	opts.btf_value_type_id = test->value_type_id;
+	map_fd = bpf_map_create(test->map_type, test->map_name,
+				test->key_size, test->value_size, test->max_entries, &opts);
 	if (CHECK(map_fd < 0, "errno:%d", errno)) {
 		err = -1;
 		goto done;
@@ -6553,9 +6550,7 @@ static void do_test_info_raw(unsigned int test_num)
 		return;
 
 	*btf_log_buf = '\0';
-	btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
-			      btf_log_buf, BTF_LOG_BUF_SIZE,
-			      always_log);
+	btf_fd = load_raw_btf(raw_btf, raw_btf_size);
 	free(raw_btf);
 
 	if (CHECK(btf_fd < 0, "invalid btf_fd errno:%d", errno)) {
@@ -7352,6 +7347,32 @@ static struct btf_dedup_test dedup_tests[] = {
 		BTF_STR_SEC("\0tag1"),
 	},
 },
+{
+	.descr = "dedup: btf_type_tag #5, struct",
+	.input = {
+		.raw_types = {
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),				/* [1] */
+			BTF_TYPE_TAG_ENC(NAME_NTH(1), 1),					/* [2] */
+			BTF_TYPE_ENC(NAME_NTH(2), BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 1), 4),	/* [3] */
+			BTF_MEMBER_ENC(NAME_NTH(3), 2, BTF_MEMBER_OFFSET(0, 0)),
+			BTF_TYPE_TAG_ENC(NAME_NTH(1), 1),					/* [4] */
+			BTF_TYPE_ENC(NAME_NTH(2), BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 1), 4),	/* [5] */
+			BTF_MEMBER_ENC(NAME_NTH(3), 4, BTF_MEMBER_OFFSET(0, 0)),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0tag1\0t\0m"),
+	},
+	.expect = {
+		.raw_types = {
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),				/* [1] */
+			BTF_TYPE_TAG_ENC(NAME_NTH(1), 1),					/* [2] */
+			BTF_TYPE_ENC(NAME_NTH(2), BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 1), 4),	/* [3] */
+			BTF_MEMBER_ENC(NAME_NTH(3), 2, BTF_MEMBER_OFFSET(0, 0)),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0tag1\0t\0m"),
+	},
+},
 
 };
 
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c b/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c
index 9d3b8d7a1537..90aac437576d 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c
@@ -314,6 +314,117 @@ cleanup:
 	btf__free(btf1);
 }
 
+static void btf_add_dup_struct_in_cu(struct btf *btf, int start_id)
+{
+#define ID(n) (start_id + n)
+	btf__set_pointer_size(btf, 8); /* enforce 64-bit arch */
+
+	btf__add_int(btf, "int", 4, BTF_INT_SIGNED);    /* [1] int */
+
+	btf__add_struct(btf, "s", 8);                   /* [2] struct s { */
+	btf__add_field(btf, "a", ID(3), 0, 0);          /*      struct anon a; */
+	btf__add_field(btf, "b", ID(4), 0, 0);          /*      struct anon b; */
+							/* } */
+
+	btf__add_struct(btf, "(anon)", 8);              /* [3] struct anon { */
+	btf__add_field(btf, "f1", ID(1), 0, 0);         /*      int f1; */
+	btf__add_field(btf, "f2", ID(1), 32, 0);        /*      int f2; */
+							/* } */
+
+	btf__add_struct(btf, "(anon)", 8);              /* [4] struct anon { */
+	btf__add_field(btf, "f1", ID(1), 0, 0);         /*      int f1; */
+	btf__add_field(btf, "f2", ID(1), 32, 0);        /*      int f2; */
+							/* } */
+#undef ID
+}
+
+static void test_split_dup_struct_in_cu()
+{
+	struct btf *btf1, *btf2 = NULL;
+	int err;
+
+	/* generate the base data.. */
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+
+	btf_add_dup_struct_in_cu(btf1, 0);
+
+	VALIDATE_RAW_BTF(
+			btf1,
+			"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+			"[2] STRUCT 's' size=8 vlen=2\n"
+			"\t'a' type_id=3 bits_offset=0\n"
+			"\t'b' type_id=4 bits_offset=0",
+			"[3] STRUCT '(anon)' size=8 vlen=2\n"
+			"\t'f1' type_id=1 bits_offset=0\n"
+			"\t'f2' type_id=1 bits_offset=32",
+			"[4] STRUCT '(anon)' size=8 vlen=2\n"
+			"\t'f1' type_id=1 bits_offset=0\n"
+			"\t'f2' type_id=1 bits_offset=32");
+
+	/* ..dedup them... */
+	err = btf__dedup(btf1, NULL);
+	if (!ASSERT_OK(err, "btf_dedup"))
+		goto cleanup;
+
+	VALIDATE_RAW_BTF(
+			btf1,
+			"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+			"[2] STRUCT 's' size=8 vlen=2\n"
+			"\t'a' type_id=3 bits_offset=0\n"
+			"\t'b' type_id=3 bits_offset=0",
+			"[3] STRUCT '(anon)' size=8 vlen=2\n"
+			"\t'f1' type_id=1 bits_offset=0\n"
+			"\t'f2' type_id=1 bits_offset=32");
+
+	/* and add the same data on top of it */
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+
+	btf_add_dup_struct_in_cu(btf2, 3);
+
+	VALIDATE_RAW_BTF(
+			btf2,
+			"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+			"[2] STRUCT 's' size=8 vlen=2\n"
+			"\t'a' type_id=3 bits_offset=0\n"
+			"\t'b' type_id=3 bits_offset=0",
+			"[3] STRUCT '(anon)' size=8 vlen=2\n"
+			"\t'f1' type_id=1 bits_offset=0\n"
+			"\t'f2' type_id=1 bits_offset=32",
+			"[4] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+			"[5] STRUCT 's' size=8 vlen=2\n"
+			"\t'a' type_id=6 bits_offset=0\n"
+			"\t'b' type_id=7 bits_offset=0",
+			"[6] STRUCT '(anon)' size=8 vlen=2\n"
+			"\t'f1' type_id=4 bits_offset=0\n"
+			"\t'f2' type_id=4 bits_offset=32",
+			"[7] STRUCT '(anon)' size=8 vlen=2\n"
+			"\t'f1' type_id=4 bits_offset=0\n"
+			"\t'f2' type_id=4 bits_offset=32");
+
+	err = btf__dedup(btf2, NULL);
+	if (!ASSERT_OK(err, "btf_dedup"))
+		goto cleanup;
+
+	/* after dedup it should match the original data */
+	VALIDATE_RAW_BTF(
+			btf2,
+			"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+			"[2] STRUCT 's' size=8 vlen=2\n"
+			"\t'a' type_id=3 bits_offset=0\n"
+			"\t'b' type_id=3 bits_offset=0",
+			"[3] STRUCT '(anon)' size=8 vlen=2\n"
+			"\t'f1' type_id=1 bits_offset=0\n"
+			"\t'f2' type_id=1 bits_offset=32");
+
+cleanup:
+	btf__free(btf2);
+	btf__free(btf1);
+}
+
 void test_btf_dedup_split()
 {
 	if (test__start_subtest("split_simple"))
@@ -322,4 +433,6 @@ void test_btf_dedup_split()
 		test_split_struct_duped();
 	if (test__start_subtest("split_fwd_resolve"))
 		test_split_fwd_resolve();
+	if (test__start_subtest("split_dup_struct_in_cu"))
+		test_split_dup_struct_in_cu();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index d6272013a5a3..9e26903f9170 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -323,7 +323,7 @@ static void test_btf_dump_int_data(struct btf *btf, struct btf_dump *d,
 				   char *str)
 {
 #ifdef __SIZEOF_INT128__
-	__int128 i = 0xffffffffffffffff;
+	unsigned __int128 i = 0xffffffffffffffff;
 
 	/* this dance is required because we cannot directly initialize
 	 * a 128-bit value to anything larger than a 64-bit value.
@@ -756,7 +756,7 @@ static void test_btf_dump_struct_data(struct btf *btf, struct btf_dump *d,
 	/* overflow bpf_sock_ops struct with final element nonzero/zero.
 	 * Regardless of the value of the final field, we don't have all the
 	 * data we need to display it, so we should trigger an overflow.
-	 * In other words oveflow checking should trump "is field zero?"
+	 * In other words overflow checking should trump "is field zero?"
 	 * checks because if we've overflowed, it shouldn't matter what the
 	 * field is - we can't trust its value so shouldn't display it.
 	 */
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
index de9c3e12b0ea..d3e8f729c623 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
@@ -15,22 +15,22 @@ static int prog_load_cnt(int verdict, int val)
 	int cgroup_storage_fd, percpu_cgroup_storage_fd;
 
 	if (map_fd < 0)
-		map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0);
+		map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 8, 1, NULL);
 	if (map_fd < 0) {
 		printf("failed to create map '%s'\n", strerror(errno));
 		return -1;
 	}
 
-	cgroup_storage_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE,
-				sizeof(struct bpf_cgroup_storage_key), 8, 0, 0);
+	cgroup_storage_fd = bpf_map_create(BPF_MAP_TYPE_CGROUP_STORAGE, NULL,
+				sizeof(struct bpf_cgroup_storage_key), 8, 0, NULL);
 	if (cgroup_storage_fd < 0) {
 		printf("failed to create map '%s'\n", strerror(errno));
 		return -1;
 	}
 
-	percpu_cgroup_storage_fd = bpf_create_map(
-		BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
-		sizeof(struct bpf_cgroup_storage_key), 8, 0, 0);
+	percpu_cgroup_storage_fd = bpf_map_create(
+		BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, NULL,
+		sizeof(struct bpf_cgroup_storage_key), 8, 0, NULL);
 	if (percpu_cgroup_storage_fd < 0) {
 		printf("failed to create map '%s'\n", strerror(errno));
 		return -1;
diff --git a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c
index 9229db2f5ca5..ca574e1e30e6 100644
--- a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c
+++ b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c
@@ -51,19 +51,20 @@ 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;
+	const char *obj_file = v4 ? "connect_force_port4.o" : "connect_force_port6.o";
+	int fd, err;
 	__u32 duration = 0;
 
-	err = bpf_prog_load_xattr(&attr, &obj, &xlate_fd);
-	if (err) {
-		log_err("Failed to load BPF object");
+	obj = bpf_object__open_file(obj_file, NULL);
+	if (!ASSERT_OK_PTR(obj, "bpf_obj_open"))
 		return -1;
+
+	err = bpf_object__load(obj);
+	if (!ASSERT_OK(err, "bpf_obj_load")) {
+		err = -EIO;
+		goto close_bpf_object;
 	}
 
 	prog = bpf_object__find_program_by_title(obj, v4 ?
diff --git a/tools/testing/selftests/bpf/prog_tests/core_kern.c b/tools/testing/selftests/bpf/prog_tests/core_kern.c
new file mode 100644
index 000000000000..561c5185d886
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/core_kern.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "test_progs.h"
+#include "core_kern.lskel.h"
+
+void test_core_kern_lskel(void)
+{
+	struct core_kern_lskel *skel;
+
+	skel = core_kern_lskel__open_and_load();
+	ASSERT_OK_PTR(skel, "open_and_load");
+	core_kern_lskel__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 1041d0c593f6..44a9868c70ea 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -881,7 +881,8 @@ void test_core_reloc(void)
 		data = mmap_data;
 
 		memset(mmap_data, 0, sizeof(*data));
-		memcpy(data->in, test_case->input, test_case->input_len);
+		if (test_case->input_len)
+			memcpy(data->in, test_case->input, test_case->input_len);
 		data->my_pid_tgid = my_pid_tgid;
 
 		link = bpf_program__attach_raw_tracepoint(prog, tp_name);
diff --git a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
index 4184c399d4c6..977ab433a946 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
@@ -24,13 +24,19 @@ static void get_stack_print_output(void *ctx, int cpu, void *data, __u32 size)
 {
 	bool good_kern_stack = false, good_user_stack = false;
 	const char *nonjit_func = "___bpf_prog_run";
-	struct get_stack_trace_t *e = data;
+	/* perfbuf-submitted data is 4-byte aligned, but we need 8-byte
+	 * alignment, so copy data into a local variable, for simplicity
+	 */
+	struct get_stack_trace_t e;
 	int i, num_stack;
 	static __u64 cnt;
 	struct ksym *ks;
 
 	cnt++;
 
+	memset(&e, 0, sizeof(e));
+	memcpy(&e, data, size <= sizeof(e) ? size : sizeof(e));
+
 	if (size < sizeof(struct get_stack_trace_t)) {
 		__u64 *raw_data = data;
 		bool found = false;
@@ -57,19 +63,19 @@ static void get_stack_print_output(void *ctx, int cpu, void *data, __u32 size)
 			good_user_stack = true;
 		}
 	} else {
-		num_stack = e->kern_stack_size / sizeof(__u64);
+		num_stack = e.kern_stack_size / sizeof(__u64);
 		if (env.jit_enabled) {
 			good_kern_stack = num_stack > 0;
 		} else {
 			for (i = 0; i < num_stack; i++) {
-				ks = ksym_search(e->kern_stack[i]);
+				ks = ksym_search(e.kern_stack[i]);
 				if (ks && (strcmp(ks->name, nonjit_func) == 0)) {
 					good_kern_stack = true;
 					break;
 				}
 			}
 		}
-		if (e->user_stack_size > 0 && e->user_stack_buildid_size > 0)
+		if (e.user_stack_size > 0 && e.user_stack_buildid_size > 0)
 			good_user_stack = true;
 	}
 
diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
index 2a49f8fcde06..ce10d2fc3a6c 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 #include <network_helpers.h>
+#include "kfree_skb.skel.h"
 
 struct meta {
 	int ifindex;
@@ -58,16 +59,11 @@ void serial_test_kfree_skb(void)
 		.ctx_in = &skb,
 		.ctx_size_in = sizeof(skb),
 	};
-	struct bpf_prog_load_attr attr = {
-		.file = "./kfree_skb.o",
-	};
-
-	struct bpf_link *link = NULL, *link_fentry = NULL, *link_fexit = NULL;
-	struct bpf_map *perf_buf_map, *global_data;
-	struct bpf_program *prog, *fentry, *fexit;
-	struct bpf_object *obj, *obj2 = NULL;
+	struct kfree_skb *skel = NULL;
+	struct bpf_link *link;
+	struct bpf_object *obj;
 	struct perf_buffer *pb = NULL;
-	int err, kfree_skb_fd;
+	int err;
 	bool passed = false;
 	__u32 duration = 0;
 	const int zero = 0;
@@ -78,40 +74,27 @@ void serial_test_kfree_skb(void)
 	if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno))
 		return;
 
-	err = bpf_prog_load_xattr(&attr, &obj2, &kfree_skb_fd);
-	if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno))
-		goto close_prog;
-
-	prog = bpf_object__find_program_by_title(obj2, "tp_btf/kfree_skb");
-	if (CHECK(!prog, "find_prog", "prog kfree_skb not found\n"))
-		goto close_prog;
-	fentry = bpf_object__find_program_by_title(obj2, "fentry/eth_type_trans");
-	if (CHECK(!fentry, "find_prog", "prog eth_type_trans not found\n"))
-		goto close_prog;
-	fexit = bpf_object__find_program_by_title(obj2, "fexit/eth_type_trans");
-	if (CHECK(!fexit, "find_prog", "prog eth_type_trans not found\n"))
-		goto close_prog;
-
-	global_data = bpf_object__find_map_by_name(obj2, ".bss");
-	if (CHECK(!global_data, "find global data", "not found\n"))
+	skel = kfree_skb__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "kfree_skb_skel"))
 		goto close_prog;
 
-	link = bpf_program__attach_raw_tracepoint(prog, NULL);
+	link = bpf_program__attach_raw_tracepoint(skel->progs.trace_kfree_skb, NULL);
 	if (!ASSERT_OK_PTR(link, "attach_raw_tp"))
 		goto close_prog;
-	link_fentry = bpf_program__attach_trace(fentry);
-	if (!ASSERT_OK_PTR(link_fentry, "attach fentry"))
-		goto close_prog;
-	link_fexit = bpf_program__attach_trace(fexit);
-	if (!ASSERT_OK_PTR(link_fexit, "attach fexit"))
+	skel->links.trace_kfree_skb = link;
+
+	link = bpf_program__attach_trace(skel->progs.fentry_eth_type_trans);
+	if (!ASSERT_OK_PTR(link, "attach fentry"))
 		goto close_prog;
+	skel->links.fentry_eth_type_trans = link;
 
-	perf_buf_map = bpf_object__find_map_by_name(obj2, "perf_buf_map");
-	if (CHECK(!perf_buf_map, "find_perf_buf_map", "not found\n"))
+	link = bpf_program__attach_trace(skel->progs.fexit_eth_type_trans);
+	if (!ASSERT_OK_PTR(link, "attach fexit"))
 		goto close_prog;
+	skel->links.fexit_eth_type_trans = link;
 
 	/* set up perf buffer */
-	pb = perf_buffer__new(bpf_map__fd(perf_buf_map), 1,
+	pb = perf_buffer__new(bpf_map__fd(skel->maps.perf_buf_map), 1,
 			      on_sample, NULL, &passed, NULL);
 	if (!ASSERT_OK_PTR(pb, "perf_buf__new"))
 		goto close_prog;
@@ -133,7 +116,7 @@ void serial_test_kfree_skb(void)
 	 */
 	ASSERT_TRUE(passed, "passed");
 
-	err = bpf_map_lookup_elem(bpf_map__fd(global_data), &zero, test_ok);
+	err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.bss), &zero, test_ok);
 	if (CHECK(err, "get_result",
 		  "failed to get output data: %d\n", err))
 		goto close_prog;
@@ -141,9 +124,6 @@ void serial_test_kfree_skb(void)
 	CHECK_FAIL(!test_ok[0] || !test_ok[1]);
 close_prog:
 	perf_buffer__free(pb);
-	bpf_link__destroy(link);
-	bpf_link__destroy(link_fentry);
-	bpf_link__destroy(link_fexit);
 	bpf_object__close(obj);
-	bpf_object__close(obj2);
+	kfree_skb__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
index 5c9c0176991b..7d7445ccc141 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
@@ -4,6 +4,7 @@
 #include <network_helpers.h>
 #include "kfunc_call_test.lskel.h"
 #include "kfunc_call_test_subprog.skel.h"
+#include "kfunc_call_test_subprog.lskel.h"
 
 static void test_main(void)
 {
@@ -49,6 +50,26 @@ static void test_subprog(void)
 	kfunc_call_test_subprog__destroy(skel);
 }
 
+static void test_subprog_lskel(void)
+{
+	struct kfunc_call_test_subprog_lskel *skel;
+	int prog_fd, retval, err;
+
+	skel = kfunc_call_test_subprog_lskel__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel"))
+		return;
+
+	prog_fd = skel->progs.kfunc_call_test1.prog_fd;
+	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				NULL, NULL, (__u32 *)&retval, NULL);
+	ASSERT_OK(err, "bpf_prog_test_run(test1)");
+	ASSERT_EQ(retval, 10, "test1-retval");
+	ASSERT_NEQ(skel->data->active_res, -1, "active_res");
+	ASSERT_EQ(skel->data->sk_state_res, BPF_TCP_CLOSE, "sk_state_res");
+
+	kfunc_call_test_subprog_lskel__destroy(skel);
+}
+
 void test_kfunc_call(void)
 {
 	if (test__start_subtest("main"))
@@ -56,4 +77,7 @@ void test_kfunc_call(void)
 
 	if (test__start_subtest("subprog"))
 		test_subprog();
+
+	if (test__start_subtest("subprog_lskel"))
+		test_subprog_lskel();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/legacy_printk.c b/tools/testing/selftests/bpf/prog_tests/legacy_printk.c
new file mode 100644
index 000000000000..ec6e45f2a644
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/legacy_printk.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <test_progs.h>
+#include "test_legacy_printk.skel.h"
+
+static int execute_one_variant(bool legacy)
+{
+	struct test_legacy_printk *skel;
+	int err, zero = 0, my_pid = getpid(), res, map_fd;
+
+	skel = test_legacy_printk__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return -errno;
+
+	bpf_program__set_autoload(skel->progs.handle_legacy, legacy);
+	bpf_program__set_autoload(skel->progs.handle_modern, !legacy);
+
+	err = test_legacy_printk__load(skel);
+	/* no ASSERT_OK, we expect one of two variants can fail here */
+	if (err)
+		goto err_out;
+
+	if (legacy) {
+		map_fd = bpf_map__fd(skel->maps.my_pid_map);
+		err = bpf_map_update_elem(map_fd, &zero, &my_pid, BPF_ANY);
+		if (!ASSERT_OK(err, "my_pid_map_update"))
+			goto err_out;
+		err = bpf_map_lookup_elem(map_fd, &zero, &res);
+	} else {
+		skel->bss->my_pid_var = my_pid;
+	}
+
+	err = test_legacy_printk__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto err_out;
+
+	usleep(1); /* trigger */
+
+	if (legacy) {
+		map_fd = bpf_map__fd(skel->maps.res_map);
+		err = bpf_map_lookup_elem(map_fd, &zero, &res);
+		if (!ASSERT_OK(err, "res_map_lookup"))
+			goto err_out;
+	} else {
+		res = skel->bss->res_var;
+	}
+
+	if (!ASSERT_GT(res, 0, "res")) {
+		err = -EINVAL;
+		goto err_out;
+	}
+
+err_out:
+	test_legacy_printk__destroy(skel);
+	return err;
+}
+
+void test_legacy_printk(void)
+{
+	/* legacy variant should work everywhere */
+	ASSERT_OK(execute_one_variant(true /* legacy */), "legacy_case");
+
+	/* execute modern variant, can fail the load on old kernels */
+	execute_one_variant(false);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/log_buf.c b/tools/testing/selftests/bpf/prog_tests/log_buf.c
new file mode 100644
index 000000000000..e469b023962b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/log_buf.c
@@ -0,0 +1,276 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <test_progs.h>
+#include <bpf/btf.h>
+
+#include "test_log_buf.skel.h"
+
+static size_t libbpf_log_pos;
+static char libbpf_log_buf[1024 * 1024];
+static bool libbpf_log_error;
+
+static int libbpf_print_cb(enum libbpf_print_level level, const char *fmt, va_list args)
+{
+	int emitted_cnt;
+	size_t left_cnt;
+
+	left_cnt = sizeof(libbpf_log_buf) - libbpf_log_pos;
+	emitted_cnt = vsnprintf(libbpf_log_buf + libbpf_log_pos, left_cnt, fmt, args);
+
+	if (emitted_cnt < 0 || emitted_cnt + 1 > left_cnt) {
+		libbpf_log_error = true;
+		return 0;
+	}
+
+	libbpf_log_pos += emitted_cnt;
+	return 0;
+}
+
+static void obj_load_log_buf(void)
+{
+	libbpf_print_fn_t old_print_cb = libbpf_set_print(libbpf_print_cb);
+	LIBBPF_OPTS(bpf_object_open_opts, opts);
+	const size_t log_buf_sz = 1024 * 1024;
+	struct test_log_buf* skel;
+	char *obj_log_buf, *good_log_buf, *bad_log_buf;
+	int err;
+
+	obj_log_buf = malloc(3 * log_buf_sz);
+	if (!ASSERT_OK_PTR(obj_log_buf, "obj_log_buf"))
+		return;
+
+	good_log_buf = obj_log_buf + log_buf_sz;
+	bad_log_buf = obj_log_buf + 2 * log_buf_sz;
+	obj_log_buf[0] = good_log_buf[0] = bad_log_buf[0] = '\0';
+
+	opts.kernel_log_buf = obj_log_buf;
+	opts.kernel_log_size = log_buf_sz;
+	opts.kernel_log_level = 4; /* for BTF this will turn into 1 */
+
+	/* In the first round every prog has its own log_buf, so libbpf logs
+	 * don't have program failure logs
+	 */
+	skel = test_log_buf__open_opts(&opts);
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	/* set very verbose level for good_prog so we always get detailed logs */
+	bpf_program__set_log_buf(skel->progs.good_prog, good_log_buf, log_buf_sz);
+	bpf_program__set_log_level(skel->progs.good_prog, 2);
+
+	bpf_program__set_log_buf(skel->progs.bad_prog, bad_log_buf, log_buf_sz);
+	/* log_level 0 with custom log_buf means that verbose logs are not
+	 * requested if program load is successful, but libbpf should retry
+	 * with log_level 1 on error and put program's verbose load log into
+	 * custom log_buf
+	 */
+	bpf_program__set_log_level(skel->progs.bad_prog, 0);
+
+	err = test_log_buf__load(skel);
+	if (!ASSERT_ERR(err, "unexpected_load_success"))
+		goto cleanup;
+
+	ASSERT_FALSE(libbpf_log_error, "libbpf_log_error");
+
+	/* there should be no prog loading log because we specified per-prog log buf */
+	ASSERT_NULL(strstr(libbpf_log_buf, "-- BEGIN PROG LOAD LOG --"), "unexp_libbpf_log");
+	ASSERT_OK_PTR(strstr(libbpf_log_buf, "prog 'bad_prog': BPF program load failed"),
+		      "libbpf_log_not_empty");
+	ASSERT_OK_PTR(strstr(obj_log_buf, "DATASEC license"), "obj_log_not_empty");
+	ASSERT_OK_PTR(strstr(good_log_buf, "0: R1=ctx(id=0,off=0,imm=0) R10=fp0"),
+		      "good_log_verbose");
+	ASSERT_OK_PTR(strstr(bad_log_buf, "invalid access to map value, value_size=16 off=16000 size=4"),
+		      "bad_log_not_empty");
+
+	if (env.verbosity > VERBOSE_NONE) {
+		printf("LIBBPF LOG:   \n=================\n%s=================\n", libbpf_log_buf);
+		printf("OBJ LOG:      \n=================\n%s=================\n", obj_log_buf);
+		printf("GOOD_PROG LOG:\n=================\n%s=================\n", good_log_buf);
+		printf("BAD_PROG  LOG:\n=================\n%s=================\n", bad_log_buf);
+	}
+
+	/* reset everything */
+	test_log_buf__destroy(skel);
+	obj_log_buf[0] = good_log_buf[0] = bad_log_buf[0] = '\0';
+	libbpf_log_buf[0] = '\0';
+	libbpf_log_pos = 0;
+	libbpf_log_error = false;
+
+	/* In the second round we let bad_prog's failure be logged through print callback */
+	opts.kernel_log_buf = NULL; /* let everything through into print callback */
+	opts.kernel_log_size = 0;
+	opts.kernel_log_level = 1;
+
+	skel = test_log_buf__open_opts(&opts);
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	/* set normal verbose level for good_prog to check log_level is taken into account */
+	bpf_program__set_log_buf(skel->progs.good_prog, good_log_buf, log_buf_sz);
+	bpf_program__set_log_level(skel->progs.good_prog, 1);
+
+	err = test_log_buf__load(skel);
+	if (!ASSERT_ERR(err, "unexpected_load_success"))
+		goto cleanup;
+
+	ASSERT_FALSE(libbpf_log_error, "libbpf_log_error");
+
+	/* this time prog loading error should be logged through print callback */
+	ASSERT_OK_PTR(strstr(libbpf_log_buf, "libbpf: prog 'bad_prog': -- BEGIN PROG LOAD LOG --"),
+		      "libbpf_log_correct");
+	ASSERT_STREQ(obj_log_buf, "", "obj_log__empty");
+	ASSERT_STREQ(good_log_buf, "processed 4 insns (limit 1000000) max_states_per_insn 0 total_states 0 peak_states 0 mark_read 0\n",
+		     "good_log_ok");
+	ASSERT_STREQ(bad_log_buf, "", "bad_log_empty");
+
+	if (env.verbosity > VERBOSE_NONE) {
+		printf("LIBBPF LOG:   \n=================\n%s=================\n", libbpf_log_buf);
+		printf("OBJ LOG:      \n=================\n%s=================\n", obj_log_buf);
+		printf("GOOD_PROG LOG:\n=================\n%s=================\n", good_log_buf);
+		printf("BAD_PROG  LOG:\n=================\n%s=================\n", bad_log_buf);
+	}
+
+cleanup:
+	free(obj_log_buf);
+	test_log_buf__destroy(skel);
+	libbpf_set_print(old_print_cb);
+}
+
+static void bpf_prog_load_log_buf(void)
+{
+	const struct bpf_insn good_prog_insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	const size_t good_prog_insn_cnt = sizeof(good_prog_insns) / sizeof(struct bpf_insn);
+	const struct bpf_insn bad_prog_insns[] = {
+		BPF_EXIT_INSN(),
+	};
+	size_t bad_prog_insn_cnt = sizeof(bad_prog_insns) / sizeof(struct bpf_insn);
+	LIBBPF_OPTS(bpf_prog_load_opts, opts);
+	const size_t log_buf_sz = 1024 * 1024;
+	char *log_buf;
+	int fd = -1;
+
+	log_buf = malloc(log_buf_sz);
+	if (!ASSERT_OK_PTR(log_buf, "log_buf_alloc"))
+		return;
+	opts.log_buf = log_buf;
+	opts.log_size = log_buf_sz;
+
+	/* with log_level == 0 log_buf shoud stay empty for good prog */
+	log_buf[0] = '\0';
+	opts.log_level = 0;
+	fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "good_prog", "GPL",
+			   good_prog_insns, good_prog_insn_cnt, &opts);
+	ASSERT_STREQ(log_buf, "", "good_log_0");
+	ASSERT_GE(fd, 0, "good_fd1");
+	if (fd >= 0)
+		close(fd);
+	fd = -1;
+
+	/* log_level == 2 should always fill log_buf, even for good prog */
+	log_buf[0] = '\0';
+	opts.log_level = 2;
+	fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "good_prog", "GPL",
+			   good_prog_insns, good_prog_insn_cnt, &opts);
+	ASSERT_OK_PTR(strstr(log_buf, "0: R1=ctx(id=0,off=0,imm=0) R10=fp0"), "good_log_2");
+	ASSERT_GE(fd, 0, "good_fd2");
+	if (fd >= 0)
+		close(fd);
+	fd = -1;
+
+	/* log_level == 0 should fill log_buf for bad prog */
+	log_buf[0] = '\0';
+	opts.log_level = 0;
+	fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "bad_prog", "GPL",
+			   bad_prog_insns, bad_prog_insn_cnt, &opts);
+	ASSERT_OK_PTR(strstr(log_buf, "R0 !read_ok"), "bad_log_0");
+	ASSERT_LT(fd, 0, "bad_fd");
+	if (fd >= 0)
+		close(fd);
+	fd = -1;
+
+	free(log_buf);
+}
+
+static void bpf_btf_load_log_buf(void)
+{
+	LIBBPF_OPTS(bpf_btf_load_opts, opts);
+	const size_t log_buf_sz = 1024 * 1024;
+	const void *raw_btf_data;
+	__u32 raw_btf_size;
+	struct btf *btf;
+	char *log_buf;
+	int fd = -1;
+
+	btf = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf, "empty_btf"))
+		return;
+
+	ASSERT_GT(btf__add_int(btf, "int", 4, 0), 0, "int_type");
+
+	raw_btf_data = btf__raw_data(btf, &raw_btf_size);
+	if (!ASSERT_OK_PTR(raw_btf_data, "raw_btf_data_good"))
+		goto cleanup;
+
+	log_buf = malloc(log_buf_sz);
+	if (!ASSERT_OK_PTR(log_buf, "log_buf_alloc"))
+		goto cleanup;
+	opts.log_buf = log_buf;
+	opts.log_size = log_buf_sz;
+
+	/* with log_level == 0 log_buf shoud stay empty for good BTF */
+	log_buf[0] = '\0';
+	opts.log_level = 0;
+	fd = bpf_btf_load(raw_btf_data, raw_btf_size, &opts);
+	ASSERT_STREQ(log_buf, "", "good_log_0");
+	ASSERT_GE(fd, 0, "good_fd1");
+	if (fd >= 0)
+		close(fd);
+	fd = -1;
+
+	/* log_level == 2 should always fill log_buf, even for good BTF */
+	log_buf[0] = '\0';
+	opts.log_level = 2;
+	fd = bpf_btf_load(raw_btf_data, raw_btf_size, &opts);
+	printf("LOG_BUF: %s\n", log_buf);
+	ASSERT_OK_PTR(strstr(log_buf, "magic: 0xeb9f"), "good_log_2");
+	ASSERT_GE(fd, 0, "good_fd2");
+	if (fd >= 0)
+		close(fd);
+	fd = -1;
+
+	/* make BTF bad, add pointer pointing to non-existing type */
+	ASSERT_GT(btf__add_ptr(btf, 100), 0, "bad_ptr_type");
+
+	raw_btf_data = btf__raw_data(btf, &raw_btf_size);
+	if (!ASSERT_OK_PTR(raw_btf_data, "raw_btf_data_bad"))
+		goto cleanup;
+
+	/* log_level == 0 should fill log_buf for bad BTF */
+	log_buf[0] = '\0';
+	opts.log_level = 0;
+	fd = bpf_btf_load(raw_btf_data, raw_btf_size, &opts);
+	printf("LOG_BUF: %s\n", log_buf);
+	ASSERT_OK_PTR(strstr(log_buf, "[2] PTR (anon) type_id=100 Invalid type_id"), "bad_log_0");
+	ASSERT_LT(fd, 0, "bad_fd");
+	if (fd >= 0)
+		close(fd);
+	fd = -1;
+
+cleanup:
+	free(log_buf);
+	btf__free(btf);
+}
+
+void test_log_buf(void)
+{
+	if (test__start_subtest("obj_load_log_buf"))
+		obj_load_log_buf();
+	if (test__start_subtest("bpf_prog_load_log_buf"))
+		bpf_prog_load_log_buf();
+	if (test__start_subtest("bpf_btf_load_log_buf"))
+		bpf_btf_load_log_buf();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/map_ptr.c b/tools/testing/selftests/bpf/prog_tests/map_ptr.c
index 4972f92205c7..273725504f11 100644
--- a/tools/testing/selftests/bpf/prog_tests/map_ptr.c
+++ b/tools/testing/selftests/bpf/prog_tests/map_ptr.c
@@ -4,31 +4,29 @@
 #include <test_progs.h>
 #include <network_helpers.h>
 
-#include "map_ptr_kern.skel.h"
+#include "map_ptr_kern.lskel.h"
 
 void test_map_ptr(void)
 {
-	struct map_ptr_kern *skel;
+	struct map_ptr_kern_lskel *skel;
 	__u32 duration = 0, retval;
 	char buf[128];
 	int err;
 	int page_size = getpagesize();
 
-	skel = map_ptr_kern__open();
+	skel = map_ptr_kern_lskel__open();
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
 		return;
 
-	err = bpf_map__set_max_entries(skel->maps.m_ringbuf, page_size);
-	if (!ASSERT_OK(err, "bpf_map__set_max_entries"))
-		goto cleanup;
+	skel->maps.m_ringbuf.max_entries = page_size;
 
-	err = map_ptr_kern__load(skel);
+	err = map_ptr_kern_lskel__load(skel);
 	if (!ASSERT_OK(err, "skel_load"))
 		goto cleanup;
 
 	skel->bss->page_size = page_size;
 
-	err = bpf_prog_test_run(bpf_program__fd(skel->progs.cg_skb), 1, &pkt_v4,
+	err = bpf_prog_test_run(skel->progs.cg_skb.prog_fd, 1, &pkt_v4,
 				sizeof(pkt_v4), buf, NULL, &retval, NULL);
 
 	if (CHECK(err, "test_run", "err=%d errno=%d\n", err, errno))
@@ -39,5 +37,5 @@ void test_map_ptr(void)
 		goto cleanup;
 
 cleanup:
-	map_ptr_kern__destroy(skel);
+	map_ptr_kern_lskel__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/pinning.c b/tools/testing/selftests/bpf/prog_tests/pinning.c
index d4b953ae3407..31c09ba577eb 100644
--- a/tools/testing/selftests/bpf/prog_tests/pinning.c
+++ b/tools/testing/selftests/bpf/prog_tests/pinning.c
@@ -241,8 +241,8 @@ void test_pinning(void)
 		goto out;
 	}
 
-	map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(__u32),
-				sizeof(__u64), 1, 0);
+	map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(__u32),
+				sizeof(__u64), 1, NULL);
 	if (CHECK(map_fd < 0, "create pinmap manually", "fd %d\n", map_fd))
 		goto out;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/prog_array_init.c b/tools/testing/selftests/bpf/prog_tests/prog_array_init.c
new file mode 100644
index 000000000000..fc4657619739
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/prog_array_init.c
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2021 Hengqi Chen */
+
+#include <test_progs.h>
+#include "test_prog_array_init.skel.h"
+
+void test_prog_array_init(void)
+{
+	struct test_prog_array_init *skel;
+	int err;
+
+	skel = test_prog_array_init__open();
+	if (!ASSERT_OK_PTR(skel, "could not open BPF object"))
+		return;
+
+	skel->rodata->my_pid = getpid();
+
+	err = test_prog_array_init__load(skel);
+	if (!ASSERT_OK(err, "could not load BPF object"))
+		goto cleanup;
+
+	skel->links.entry = bpf_program__attach_raw_tracepoint(skel->progs.entry, "sys_enter");
+	if (!ASSERT_OK_PTR(skel->links.entry, "could not attach BPF program"))
+		goto cleanup;
+
+	usleep(1);
+
+	ASSERT_EQ(skel->bss->value, 42, "unexpected value");
+
+cleanup:
+	test_prog_array_init__destroy(skel);
+}
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 8ccba3ab70ee..b9822f914eeb 100644
--- a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
@@ -14,7 +14,7 @@ static void test_queue_stack_map_by_type(int type)
 	int i, err, prog_fd, map_in_fd, map_out_fd;
 	char file[32], buf[128];
 	struct bpf_object *obj;
-	struct iphdr *iph = (void *)buf + sizeof(struct ethhdr);
+	struct iphdr iph;
 
 	/* Fill test values to be used */
 	for (i = 0; i < MAP_SIZE; i++)
@@ -60,15 +60,17 @@ static void test_queue_stack_map_by_type(int type)
 
 		err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
 					buf, &size, &retval, &duration);
-		if (err || retval || size != sizeof(pkt_v4) ||
-		    iph->daddr != val)
+		if (err || retval || size != sizeof(pkt_v4))
+			break;
+		memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph));
+		if (iph.daddr != val)
 			break;
 	}
 
-	CHECK(err || retval || size != sizeof(pkt_v4) || iph->daddr != val,
+	CHECK(err || retval || size != sizeof(pkt_v4) || iph.daddr != val,
 	      "bpf_map_pop_elem",
 	      "err %d errno %d retval %d size %d iph->daddr %u\n",
-	      err, errno, retval, size, iph->daddr);
+	      err, errno, retval, size, iph.daddr);
 
 	/* Queue is empty, program should return TC_ACT_SHOT */
 	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
index 167cd8a2edfd..e945195b24c9 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
@@ -62,8 +62,8 @@ void test_ringbuf_multi(void)
 	if (CHECK(err != 0, "bpf_map__set_max_entries", "bpf_map__set_max_entries failed\n"))
 		goto cleanup;
 
-	proto_fd = bpf_create_map(BPF_MAP_TYPE_RINGBUF, 0, 0, page_size, 0);
-	if (CHECK(proto_fd < 0, "bpf_create_map", "bpf_create_map failed\n"))
+	proto_fd = bpf_map_create(BPF_MAP_TYPE_RINGBUF, NULL, 0, 0, page_size, NULL);
+	if (CHECK(proto_fd < 0, "bpf_map_create", "bpf_map_create failed\n"))
 		goto cleanup;
 
 	err = bpf_map__set_inner_map_fd(skel->maps.ringbuf_hash, proto_fd);
diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
index 3cfc910ab3c1..980ac0f2c0bb 100644
--- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
+++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
@@ -66,29 +66,20 @@ static union sa46 {
 
 static int create_maps(enum bpf_map_type inner_type)
 {
-	struct bpf_create_map_attr attr = {};
+	LIBBPF_OPTS(bpf_map_create_opts, opts);
 
 	inner_map_type = inner_type;
 
 	/* Creating reuseport_array */
-	attr.name = "reuseport_array";
-	attr.map_type = inner_type;
-	attr.key_size = sizeof(__u32);
-	attr.value_size = sizeof(__u32);
-	attr.max_entries = REUSEPORT_ARRAY_SIZE;
-
-	reuseport_array = bpf_create_map_xattr(&attr);
+	reuseport_array = bpf_map_create(inner_type, "reuseport_array",
+					 sizeof(__u32), sizeof(__u32), REUSEPORT_ARRAY_SIZE, NULL);
 	RET_ERR(reuseport_array < 0, "creating reuseport_array",
 		"reuseport_array:%d errno:%d\n", reuseport_array, errno);
 
 	/* Creating outer_map */
-	attr.name = "outer_map";
-	attr.map_type = BPF_MAP_TYPE_ARRAY_OF_MAPS;
-	attr.key_size = sizeof(__u32);
-	attr.value_size = sizeof(__u32);
-	attr.max_entries = 1;
-	attr.inner_map_fd = reuseport_array;
-	outer_map = bpf_create_map_xattr(&attr);
+	opts.inner_map_fd = reuseport_array;
+	outer_map = bpf_map_create(BPF_MAP_TYPE_ARRAY_OF_MAPS, "outer_map",
+				   sizeof(__u32), sizeof(__u32), 1, &opts);
 	RET_ERR(outer_map < 0, "creating outer_map",
 		"outer_map:%d errno:%d\n", outer_map, errno);
 
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 1352ec104149..85db0f4cdd95 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -91,9 +91,9 @@ static void test_sockmap_create_update_free(enum bpf_map_type map_type)
 	if (CHECK_FAIL(s < 0))
 		return;
 
-	map = bpf_create_map(map_type, sizeof(int), sizeof(int), 1, 0);
+	map = bpf_map_create(map_type, NULL, sizeof(int), sizeof(int), 1, NULL);
 	if (CHECK_FAIL(map < 0)) {
-		perror("bpf_create_map");
+		perror("bpf_cmap_create");
 		goto out;
 	}
 
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
index 7a0d64fdc192..af293ea1542c 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
@@ -97,7 +97,7 @@ static void run_tests(int family, enum bpf_map_type map_type)
 	char test_name[MAX_TEST_NAME];
 	int map;
 
-	map = bpf_create_map(map_type, sizeof(int), sizeof(int), 1, 0);
+	map = bpf_map_create(map_type, NULL, sizeof(int), sizeof(int), 1, NULL);
 	if (CHECK_FAIL(map < 0)) {
 		perror("bpf_map_create");
 		return;
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index 2a9cb951bfd6..7e21bfab6358 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -502,8 +502,8 @@ static void test_lookup_32_bit_value(int family, int sotype, int mapfd)
 	if (s < 0)
 		return;
 
-	mapfd = bpf_create_map(BPF_MAP_TYPE_SOCKMAP, sizeof(key),
-			       sizeof(value32), 1, 0);
+	mapfd = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(key),
+			       sizeof(value32), 1, NULL);
 	if (mapfd < 0) {
 		FAIL_ERRNO("map_create");
 		goto close;
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
index 86f97681ad89..6a953f4adfdc 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
@@ -167,20 +167,20 @@ static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title)
 
 static void run_test(int cgroup_fd)
 {
-	struct bpf_prog_load_attr attr = {
-		.file = "./sockopt_inherit.o",
-	};
 	int server_fd = -1, client_fd;
 	struct bpf_object *obj;
 	void *server_err;
 	pthread_t tid;
-	int ignored;
 	int err;
 
-	err = bpf_prog_load_xattr(&attr, &obj, &ignored);
-	if (CHECK_FAIL(err))
+	obj = bpf_object__open_file("sockopt_inherit.o", NULL);
+	if (!ASSERT_OK_PTR(obj, "obj_open"))
 		return;
 
+	err = bpf_object__load(obj);
+	if (!ASSERT_OK(err, "obj_load"))
+		goto close_bpf_object;
+
 	err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt");
 	if (CHECK_FAIL(err))
 		goto close_bpf_object;
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c
index bc34f7773444..abce12ddcc37 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c
@@ -297,14 +297,10 @@ detach:
 
 void test_sockopt_multi(void)
 {
-	struct bpf_prog_load_attr attr = {
-		.file = "./sockopt_multi.o",
-	};
 	int cg_parent = -1, cg_child = -1;
 	struct bpf_object *obj = NULL;
 	int sock_fd = -1;
 	int err = -1;
-	int ignored;
 
 	cg_parent = test__join_cgroup("/parent");
 	if (CHECK_FAIL(cg_parent < 0))
@@ -314,8 +310,12 @@ void test_sockopt_multi(void)
 	if (CHECK_FAIL(cg_child < 0))
 		goto out;
 
-	err = bpf_prog_load_xattr(&attr, &obj, &ignored);
-	if (CHECK_FAIL(err))
+	obj = bpf_object__open_file("sockopt_multi.o", NULL);
+	if (!ASSERT_OK_PTR(obj, "obj_load"))
+		goto out;
+
+	err = bpf_object__load(obj);
+	if (!ASSERT_OK(err, "obj_load"))
 		goto out;
 
 	sock_fd = socket(AF_INET, SOCK_STREAM, 0);
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
index 265b4fe33ec3..96ff2c20af81 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
@@ -2,6 +2,7 @@
 #include <test_progs.h>
 #include "cgroup_helpers.h"
 #include "network_helpers.h"
+#include "tcp_rtt.skel.h"
 
 struct tcp_rtt_storage {
 	__u32 invoked;
@@ -91,26 +92,18 @@ static int verify_sk(int map_fd, int client_fd, const char *msg, __u32 invoked,
 
 static int run_test(int cgroup_fd, int server_fd)
 {
-	struct bpf_prog_load_attr attr = {
-		.prog_type = BPF_PROG_TYPE_SOCK_OPS,
-		.file = "./tcp_rtt.o",
-		.expected_attach_type = BPF_CGROUP_SOCK_OPS,
-	};
-	struct bpf_object *obj;
-	struct bpf_map *map;
+	struct tcp_rtt *skel;
 	int client_fd;
 	int prog_fd;
 	int map_fd;
 	int err;
 
-	err = bpf_prog_load_xattr(&attr, &obj, &prog_fd);
-	if (err) {
-		log_err("Failed to load BPF object");
+	skel = tcp_rtt__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_load"))
 		return -1;
-	}
 
-	map = bpf_object__next_map(obj, NULL);
-	map_fd = bpf_map__fd(map);
+	map_fd = bpf_map__fd(skel->maps.socket_storage_map);
+	prog_fd = bpf_program__fd(skel->progs._sockops);
 
 	err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_SOCK_OPS, 0);
 	if (err) {
@@ -149,7 +142,7 @@ close_client_fd:
 	close(client_fd);
 
 close_bpf_object:
-	bpf_object__close(obj);
+	tcp_rtt__destroy(skel);
 	return err;
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpffs.c b/tools/testing/selftests/bpf/prog_tests/test_bpffs.c
index d29ebfeef9c5..214d9f4a94a5 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_bpffs.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_bpffs.c
@@ -19,11 +19,13 @@ static int read_iter(char *file)
 	fd = open(file, 0);
 	if (fd < 0)
 		return -1;
-	while ((len = read(fd, buf, sizeof(buf))) > 0)
+	while ((len = read(fd, buf, sizeof(buf))) > 0) {
+		buf[sizeof(buf) - 1] = '\0';
 		if (strstr(buf, "iter")) {
 			close(fd);
 			return 0;
 		}
+	}
 	close(fd);
 	return -1;
 }
@@ -80,7 +82,7 @@ static int fn(void)
 	if (!ASSERT_OK(err, "creating " TDIR "/fs1/b"))
 		goto out;
 
-	map = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 4, 1, 0);
+	map = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 4, 1, NULL);
 	if (!ASSERT_GT(map, 0, "create_map(ARRAY)"))
 		goto out;
 	err = bpf_obj_pin(map, TDIR "/fs1/c");
diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
index 7e13129f593a..509e21d5cb9d 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
@@ -30,17 +30,29 @@ extern int extra_prog_load_log_flags;
 
 static int check_load(const char *file)
 {
-	struct bpf_prog_load_attr attr;
 	struct bpf_object *obj = NULL;
-	int err, prog_fd;
+	struct bpf_program *prog;
+	int err;
 
-	memset(&attr, 0, sizeof(struct bpf_prog_load_attr));
-	attr.file = file;
-	attr.prog_type = BPF_PROG_TYPE_UNSPEC;
-	attr.log_level = extra_prog_load_log_flags;
-	attr.prog_flags = BPF_F_TEST_RND_HI32;
 	found = false;
-	err = bpf_prog_load_xattr(&attr, &obj, &prog_fd);
+
+	obj = bpf_object__open_file(file, NULL);
+	err = libbpf_get_error(obj);
+	if (err)
+		return err;
+
+	prog = bpf_object__next_program(obj, NULL);
+	if (!prog) {
+		err = -ENOENT;
+		goto err_out;
+	}
+
+	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32);
+	bpf_program__set_log_level(prog, extra_prog_load_log_flags);
+
+	err = bpf_object__load(obj);
+
+err_out:
 	bpf_object__close(obj);
 	return err;
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp.c b/tools/testing/selftests/bpf/prog_tests/xdp.c
index 7a7ef9d4e151..ac65456b7ab8 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp.c
@@ -11,8 +11,8 @@ void test_xdp(void)
 	const char *file = "./test_xdp.o";
 	struct bpf_object *obj;
 	char buf[128];
-	struct ipv6hdr *iph6 = (void *)buf + sizeof(struct ethhdr);
-	struct iphdr *iph = (void *)buf + sizeof(struct ethhdr);
+	struct ipv6hdr iph6;
+	struct iphdr iph;
 	__u32 duration, retval, size;
 	int err, prog_fd, map_fd;
 
@@ -28,16 +28,17 @@ void test_xdp(void)
 
 	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
 				buf, &size, &retval, &duration);
-
+	memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph));
 	CHECK(err || retval != XDP_TX || size != 74 ||
-	      iph->protocol != IPPROTO_IPIP, "ipv4",
+	      iph.protocol != IPPROTO_IPIP, "ipv4",
 	      "err %d errno %d retval %d size %d\n",
 	      err, errno, retval, size);
 
 	err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6),
 				buf, &size, &retval, &duration);
+	memcpy(&iph6, buf + sizeof(struct ethhdr), sizeof(iph6));
 	CHECK(err || retval != XDP_TX || size != 114 ||
-	      iph6->nexthdr != IPPROTO_IPV6, "ipv6",
+	      iph6.nexthdr != IPPROTO_IPV6, "ipv6",
 	      "err %d errno %d retval %d size %d\n",
 	      err, errno, retval, size);
 out:
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
index faa22b84f2ee..5e3a26b15ec6 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
@@ -218,9 +218,9 @@ static int send_udp_packets(int vary_dst_ip)
 		.h_dest = BOND2_MAC,
 		.h_proto = htons(ETH_P_IP),
 	};
-	uint8_t buf[128] = {};
-	struct iphdr *iph = (struct iphdr *)(buf + sizeof(eh));
-	struct udphdr *uh = (struct udphdr *)(buf + sizeof(eh) + sizeof(*iph));
+	struct iphdr iph = {};
+	struct udphdr uh = {};
+	uint8_t buf[128];
 	int i, s = -1;
 	int ifindex;
 
@@ -232,17 +232,16 @@ static int send_udp_packets(int vary_dst_ip)
 	if (!ASSERT_GT(ifindex, 0, "get bond1 ifindex"))
 		goto err;
 
-	memcpy(buf, &eh, sizeof(eh));
-	iph->ihl = 5;
-	iph->version = 4;
-	iph->tos = 16;
-	iph->id = 1;
-	iph->ttl = 64;
-	iph->protocol = IPPROTO_UDP;
-	iph->saddr = 1;
-	iph->daddr = 2;
-	iph->tot_len = htons(sizeof(buf) - ETH_HLEN);
-	iph->check = 0;
+	iph.ihl = 5;
+	iph.version = 4;
+	iph.tos = 16;
+	iph.id = 1;
+	iph.ttl = 64;
+	iph.protocol = IPPROTO_UDP;
+	iph.saddr = 1;
+	iph.daddr = 2;
+	iph.tot_len = htons(sizeof(buf) - ETH_HLEN);
+	iph.check = 0;
 
 	for (i = 1; i <= NPACKETS; i++) {
 		int n;
@@ -253,10 +252,15 @@ static int send_udp_packets(int vary_dst_ip)
 		};
 
 		/* vary the UDP destination port for even distribution with roundrobin/xor modes */
-		uh->dest++;
+		uh.dest++;
 
 		if (vary_dst_ip)
-			iph->daddr++;
+			iph.daddr++;
+
+		/* construct a packet */
+		memcpy(buf, &eh, sizeof(eh));
+		memcpy(buf + sizeof(eh), &iph, sizeof(iph));
+		memcpy(buf + sizeof(eh) + sizeof(iph), &uh, sizeof(uh));
 
 		n = sendto(s, buf, sizeof(buf), 0, (struct sockaddr *)&saddr_ll, sizeof(saddr_ll));
 		if (!ASSERT_EQ(n, sizeof(buf), "sendto"))
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
index f99386d1dc4c..c98a897ad692 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
@@ -42,7 +42,7 @@ void test_xdp_bpf2bpf(void)
 	char buf[128];
 	int err, pkt_fd, map_fd;
 	bool passed = false;
-	struct iphdr *iph = (void *)buf + sizeof(struct ethhdr);
+	struct iphdr iph;
 	struct iptnl_info value4 = {.family = AF_INET};
 	struct test_xdp *pkt_skel = NULL;
 	struct test_xdp_bpf2bpf *ftrace_skel = NULL;
@@ -93,9 +93,9 @@ void test_xdp_bpf2bpf(void)
 	/* Run test program */
 	err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4),
 				buf, &size, &retval, &duration);
-
+	memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph));
 	if (CHECK(err || retval != XDP_TX || size != 74 ||
-		  iph->protocol != IPPROTO_IPIP, "ipv4",
+		  iph.protocol != IPPROTO_IPIP, "ipv4",
 		  "err %d errno %d retval %d size %d\n",
 		  err, errno, retval, size))
 		goto out;
diff --git a/tools/testing/selftests/bpf/progs/bpf_loop.c b/tools/testing/selftests/bpf/progs/bpf_loop.c
new file mode 100644
index 000000000000..12349e4601e8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_loop.c
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct callback_ctx {
+	int output;
+};
+
+/* These should be set by the user program */
+u32 nested_callback_nr_loops;
+u32 stop_index = -1;
+u32 nr_loops;
+int pid;
+
+/* Making these global variables so that the userspace program
+ * can verify the output through the skeleton
+ */
+int nr_loops_returned;
+int g_output;
+int err;
+
+static int callback(__u32 index, void *data)
+{
+	struct callback_ctx *ctx = data;
+
+	if (index >= stop_index)
+		return 1;
+
+	ctx->output += index;
+
+	return 0;
+}
+
+static int empty_callback(__u32 index, void *data)
+{
+	return 0;
+}
+
+static int nested_callback2(__u32 index, void *data)
+{
+	nr_loops_returned += bpf_loop(nested_callback_nr_loops, callback, data, 0);
+
+	return 0;
+}
+
+static int nested_callback1(__u32 index, void *data)
+{
+	bpf_loop(nested_callback_nr_loops, nested_callback2, data, 0);
+	return 0;
+}
+
+SEC("fentry/__x64_sys_nanosleep")
+int test_prog(void *ctx)
+{
+	struct callback_ctx data = {};
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	nr_loops_returned = bpf_loop(nr_loops, callback, &data, 0);
+
+	if (nr_loops_returned < 0)
+		err = nr_loops_returned;
+	else
+		g_output = data.output;
+
+	return 0;
+}
+
+SEC("fentry/__x64_sys_nanosleep")
+int prog_null_ctx(void *ctx)
+{
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	nr_loops_returned = bpf_loop(nr_loops, empty_callback, NULL, 0);
+
+	return 0;
+}
+
+SEC("fentry/__x64_sys_nanosleep")
+int prog_invalid_flags(void *ctx)
+{
+	struct callback_ctx data = {};
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	err = bpf_loop(nr_loops, callback, &data, 1);
+
+	return 0;
+}
+
+SEC("fentry/__x64_sys_nanosleep")
+int prog_nested_calls(void *ctx)
+{
+	struct callback_ctx data = {};
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	nr_loops_returned = 0;
+	bpf_loop(nr_loops, nested_callback1, &data, 0);
+
+	g_output = data.output;
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c
new file mode 100644
index 000000000000..9dafdc244462
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+u32 nr_loops;
+long hits;
+
+static int empty_callback(__u32 index, void *data)
+{
+	return 0;
+}
+
+SEC("fentry/__x64_sys_getpgid")
+int benchmark(void *ctx)
+{
+	for (int i = 0; i < 1000; i++) {
+		bpf_loop(nr_loops, empty_callback, NULL, 0);
+
+		__sync_add_and_fetch(&hits, nr_loops);
+	}
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/core_kern.c b/tools/testing/selftests/bpf/progs/core_kern.c
new file mode 100644
index 000000000000..13499cc15c7d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/core_kern.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include "vmlinux.h"
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+#define ATTR __always_inline
+#include "test_jhash.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, u32);
+	__uint(max_entries, 256);
+} array1 SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, u32);
+	__uint(max_entries, 256);
+} array2 SEC(".maps");
+
+static __noinline int randmap(int v, const struct net_device *dev)
+{
+	struct bpf_map *map = (struct bpf_map *)&array1;
+	int key = bpf_get_prandom_u32() & 0xff;
+	int *val;
+
+	if (bpf_get_prandom_u32() & 1)
+		map = (struct bpf_map *)&array2;
+
+	val = bpf_map_lookup_elem(map, &key);
+	if (val)
+		*val = bpf_get_prandom_u32() + v + dev->mtu;
+
+	return 0;
+}
+
+SEC("tp_btf/xdp_devmap_xmit")
+int BPF_PROG(tp_xdp_devmap_xmit_multi, const struct net_device
+	     *from_dev, const struct net_device *to_dev, int sent, int drops,
+	     int err)
+{
+	return randmap(from_dev->ifindex, from_dev);
+}
+
+SEC("fentry/eth_type_trans")
+int BPF_PROG(fentry_eth_type_trans, struct sk_buff *skb,
+	     struct net_device *dev, unsigned short protocol)
+{
+	return randmap(dev->ifindex + skb->len, dev);
+}
+
+SEC("fexit/eth_type_trans")
+int BPF_PROG(fexit_eth_type_trans, struct sk_buff *skb,
+	     struct net_device *dev, unsigned short protocol)
+{
+	return randmap(dev->ifindex + skb->len, dev);
+}
+
+volatile const int never;
+
+struct __sk_bUfF /* it will not exist in vmlinux */ {
+	int len;
+} __attribute__((preserve_access_index));
+
+struct bpf_testmod_test_read_ctx /* it exists in bpf_testmod */ {
+	size_t len;
+} __attribute__((preserve_access_index));
+
+SEC("tc")
+int balancer_ingress(struct __sk_buff *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	void *ptr;
+	int ret = 0, nh_off, i = 0;
+
+	nh_off = 14;
+
+	/* pragma unroll doesn't work on large loops */
+#define C do { \
+	ptr = data + i; \
+	if (ptr + nh_off > data_end) \
+		break; \
+	ctx->tc_index = jhash(ptr, nh_off, ctx->cb[0] + i++); \
+	if (never) { \
+		/* below is a dead code with unresolvable CO-RE relo */ \
+		i += ((struct __sk_bUfF *)ctx)->len; \
+		/* this CO-RE relo may or may not resolve
+		 * depending on whether bpf_testmod is loaded.
+		 */ \
+		i += ((struct bpf_testmod_test_read_ctx *)ctx)->len; \
+	} \
+	} while (0);
+#define C30 C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;
+	C30;C30;C30; /* 90 calls */
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
index b1b711d9b214..b64df94ec476 100644
--- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c
+++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
@@ -334,9 +334,11 @@ static inline int check_lpm_trie(void)
 	return 1;
 }
 
+#define INNER_MAX_ENTRIES 1234
+
 struct inner_map {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__uint(max_entries, 1);
+	__uint(max_entries, INNER_MAX_ENTRIES);
 	__type(key, __u32);
 	__type(value, __u32);
 } inner_map SEC(".maps");
@@ -348,7 +350,7 @@ struct {
 	__type(value, __u32);
 	__array(values, struct {
 		__uint(type, BPF_MAP_TYPE_ARRAY);
-		__uint(max_entries, 1);
+		__uint(max_entries, INNER_MAX_ENTRIES);
 		__type(key, __u32);
 		__type(value, __u32);
 	});
@@ -360,8 +362,13 @@ static inline int check_array_of_maps(void)
 {
 	struct bpf_array *array_of_maps = (struct bpf_array *)&m_array_of_maps;
 	struct bpf_map *map = (struct bpf_map *)&m_array_of_maps;
+	struct bpf_array *inner_map;
+	int key = 0;
 
 	VERIFY(check_default(&array_of_maps->map, map));
+	inner_map = bpf_map_lookup_elem(array_of_maps, &key);
+	VERIFY(inner_map != 0);
+	VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES);
 
 	return 1;
 }
@@ -382,8 +389,13 @@ static inline int check_hash_of_maps(void)
 {
 	struct bpf_htab *hash_of_maps = (struct bpf_htab *)&m_hash_of_maps;
 	struct bpf_map *map = (struct bpf_map *)&m_hash_of_maps;
+	struct bpf_htab *inner_map;
+	int key = 2;
 
 	VERIFY(check_default(&hash_of_maps->map, map));
+	inner_map = bpf_map_lookup_elem(hash_of_maps, &key);
+	VERIFY(inner_map != 0);
+	VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES);
 
 	return 1;
 }
diff --git a/tools/testing/selftests/bpf/progs/pyperf.h b/tools/testing/selftests/bpf/progs/pyperf.h
index 2fb7adafb6b6..1ed28882daf3 100644
--- a/tools/testing/selftests/bpf/progs/pyperf.h
+++ b/tools/testing/selftests/bpf/progs/pyperf.h
@@ -159,6 +159,59 @@ struct {
 	__uint(value_size, sizeof(long long) * 127);
 } stackmap SEC(".maps");
 
+#ifdef USE_BPF_LOOP
+struct process_frame_ctx {
+	int cur_cpu;
+	int32_t *symbol_counter;
+	void *frame_ptr;
+	FrameData *frame;
+	PidData *pidData;
+	Symbol *sym;
+	Event *event;
+	bool done;
+};
+
+#define barrier_var(var) asm volatile("" : "=r"(var) : "0"(var))
+
+static int process_frame_callback(__u32 i, struct process_frame_ctx *ctx)
+{
+	int zero = 0;
+	void *frame_ptr = ctx->frame_ptr;
+	PidData *pidData = ctx->pidData;
+	FrameData *frame = ctx->frame;
+	int32_t *symbol_counter = ctx->symbol_counter;
+	int cur_cpu = ctx->cur_cpu;
+	Event *event = ctx->event;
+	Symbol *sym = ctx->sym;
+
+	if (frame_ptr && get_frame_data(frame_ptr, pidData, frame, sym)) {
+		int32_t new_symbol_id = *symbol_counter * 64 + cur_cpu;
+		int32_t *symbol_id = bpf_map_lookup_elem(&symbolmap, sym);
+
+		if (!symbol_id) {
+			bpf_map_update_elem(&symbolmap, sym, &zero, 0);
+			symbol_id = bpf_map_lookup_elem(&symbolmap, sym);
+			if (!symbol_id) {
+				ctx->done = true;
+				return 1;
+			}
+		}
+		if (*symbol_id == new_symbol_id)
+			(*symbol_counter)++;
+
+		barrier_var(i);
+		if (i >= STACK_MAX_LEN)
+			return 1;
+
+		event->stack[i] = *symbol_id;
+
+		event->stack_len = i + 1;
+		frame_ptr = frame->f_back;
+	}
+	return 0;
+}
+#endif /* USE_BPF_LOOP */
+
 #ifdef GLOBAL_FUNC
 __noinline
 #elif defined(SUBPROGS)
@@ -228,11 +281,26 @@ int __on_event(struct bpf_raw_tracepoint_args *ctx)
 		int32_t* symbol_counter = bpf_map_lookup_elem(&symbolmap, &sym);
 		if (symbol_counter == NULL)
 			return 0;
+#ifdef USE_BPF_LOOP
+	struct process_frame_ctx ctx = {
+		.cur_cpu = cur_cpu,
+		.symbol_counter = symbol_counter,
+		.frame_ptr = frame_ptr,
+		.frame = &frame,
+		.pidData = pidData,
+		.sym = &sym,
+		.event = event,
+	};
+
+	bpf_loop(STACK_MAX_LEN, process_frame_callback, &ctx, 0);
+	if (ctx.done)
+		return 0;
+#else
 #ifdef NO_UNROLL
 #pragma clang loop unroll(disable)
 #else
 #pragma clang loop unroll(full)
-#endif
+#endif /* NO_UNROLL */
 		/* Unwind python stack */
 		for (int i = 0; i < STACK_MAX_LEN; ++i) {
 			if (frame_ptr && get_frame_data(frame_ptr, pidData, &frame, &sym)) {
@@ -251,6 +319,7 @@ int __on_event(struct bpf_raw_tracepoint_args *ctx)
 				frame_ptr = frame.f_back;
 			}
 		}
+#endif /* USE_BPF_LOOP */
 		event->stack_complete = frame_ptr == NULL;
 	} else {
 		event->stack_complete = 1;
diff --git a/tools/testing/selftests/bpf/progs/pyperf600_bpf_loop.c b/tools/testing/selftests/bpf/progs/pyperf600_bpf_loop.c
new file mode 100644
index 000000000000..5c2059dc01af
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/pyperf600_bpf_loop.c
@@ -0,0 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#define STACK_MAX_LEN 600
+#define USE_BPF_LOOP
+#include "pyperf.h"
diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h
index 60c93aee2f4a..753718595c26 100644
--- a/tools/testing/selftests/bpf/progs/strobemeta.h
+++ b/tools/testing/selftests/bpf/progs/strobemeta.h
@@ -445,6 +445,48 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
 	return payload;
 }
 
+#ifdef USE_BPF_LOOP
+enum read_type {
+	READ_INT_VAR,
+	READ_MAP_VAR,
+	READ_STR_VAR,
+};
+
+struct read_var_ctx {
+	struct strobemeta_payload *data;
+	void *tls_base;
+	struct strobemeta_cfg *cfg;
+	void *payload;
+	/* value gets mutated */
+	struct strobe_value_generic *value;
+	enum read_type type;
+};
+
+static int read_var_callback(__u32 index, struct read_var_ctx *ctx)
+{
+	switch (ctx->type) {
+	case READ_INT_VAR:
+		if (index >= STROBE_MAX_INTS)
+			return 1;
+		read_int_var(ctx->cfg, index, ctx->tls_base, ctx->value, ctx->data);
+		break;
+	case READ_MAP_VAR:
+		if (index >= STROBE_MAX_MAPS)
+			return 1;
+		ctx->payload = read_map_var(ctx->cfg, index, ctx->tls_base,
+					    ctx->value, ctx->data, ctx->payload);
+		break;
+	case READ_STR_VAR:
+		if (index >= STROBE_MAX_STRS)
+			return 1;
+		ctx->payload += read_str_var(ctx->cfg, index, ctx->tls_base,
+					     ctx->value, ctx->data, ctx->payload);
+		break;
+	}
+	return 0;
+}
+#endif /* USE_BPF_LOOP */
+
 /*
  * read_strobe_meta returns NULL, if no metadata was read; otherwise returns
  * pointer to *right after* payload ends
@@ -475,11 +517,36 @@ static void *read_strobe_meta(struct task_struct *task,
 	 */
 	tls_base = (void *)task;
 
+#ifdef USE_BPF_LOOP
+	struct read_var_ctx ctx = {
+		.cfg = cfg,
+		.tls_base = tls_base,
+		.value = &value,
+		.data = data,
+		.payload = payload,
+	};
+	int err;
+
+	ctx.type = READ_INT_VAR;
+	err = bpf_loop(STROBE_MAX_INTS, read_var_callback, &ctx, 0);
+	if (err != STROBE_MAX_INTS)
+		return NULL;
+
+	ctx.type = READ_STR_VAR;
+	err = bpf_loop(STROBE_MAX_STRS, read_var_callback, &ctx, 0);
+	if (err != STROBE_MAX_STRS)
+		return NULL;
+
+	ctx.type = READ_MAP_VAR;
+	err = bpf_loop(STROBE_MAX_MAPS, read_var_callback, &ctx, 0);
+	if (err != STROBE_MAX_MAPS)
+		return NULL;
+#else
 #ifdef NO_UNROLL
 #pragma clang loop unroll(disable)
 #else
 #pragma unroll
-#endif
+#endif /* NO_UNROLL */
 	for (int i = 0; i < STROBE_MAX_INTS; ++i) {
 		read_int_var(cfg, i, tls_base, &value, data);
 	}
@@ -487,7 +554,7 @@ static void *read_strobe_meta(struct task_struct *task,
 #pragma clang loop unroll(disable)
 #else
 #pragma unroll
-#endif
+#endif /* NO_UNROLL */
 	for (int i = 0; i < STROBE_MAX_STRS; ++i) {
 		payload += read_str_var(cfg, i, tls_base, &value, data, payload);
 	}
@@ -495,10 +562,12 @@ static void *read_strobe_meta(struct task_struct *task,
 #pragma clang loop unroll(disable)
 #else
 #pragma unroll
-#endif
+#endif /* NO_UNROLL */
 	for (int i = 0; i < STROBE_MAX_MAPS; ++i) {
 		payload = read_map_var(cfg, i, tls_base, &value, data, payload);
 	}
+#endif /* USE_BPF_LOOP */
+
 	/*
 	 * return pointer right after end of payload, so it's possible to
 	 * calculate exact amount of useful data that needs to be sent
diff --git a/tools/testing/selftests/bpf/progs/strobemeta_bpf_loop.c b/tools/testing/selftests/bpf/progs/strobemeta_bpf_loop.c
new file mode 100644
index 000000000000..d18b992f0165
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/strobemeta_bpf_loop.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/* Copyright (c) 2021 Facebook */
+
+#define STROBE_MAX_INTS 2
+#define STROBE_MAX_STRS 25
+#define STROBE_MAX_MAPS 100
+#define STROBE_MAX_MAP_ENTRIES 20
+#define USE_BPF_LOOP
+#include "strobemeta.h"
diff --git a/tools/testing/selftests/bpf/progs/test_ksyms_weak.c b/tools/testing/selftests/bpf/progs/test_ksyms_weak.c
index 8eadbd4caf7a..5f8379aadb29 100644
--- a/tools/testing/selftests/bpf/progs/test_ksyms_weak.c
+++ b/tools/testing/selftests/bpf/progs/test_ksyms_weak.c
@@ -38,7 +38,7 @@ int pass_handler(const void *ctx)
 	/* tests existing symbols. */
 	rq = (struct rq *)bpf_per_cpu_ptr(&runqueues, 0);
 	if (rq)
-		out__existing_typed = 0;
+		out__existing_typed = rq->cpu;
 	out__existing_typeless = (__u64)&bpf_prog_active;
 
 	/* tests non-existent symbols. */
diff --git a/tools/testing/selftests/bpf/progs/test_legacy_printk.c b/tools/testing/selftests/bpf/progs/test_legacy_printk.c
new file mode 100644
index 000000000000..64c2d9ced529
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_legacy_printk.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <linux/bpf.h>
+#define BPF_NO_GLOBAL_DATA
+#include <bpf/bpf_helpers.h>
+
+char LICENSE[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 1);
+} my_pid_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 1);
+} res_map SEC(".maps");
+
+volatile int my_pid_var = 0;
+volatile int res_var = 0;
+
+SEC("tp/raw_syscalls/sys_enter")
+int handle_legacy(void *ctx)
+{
+	int zero = 0, *my_pid, cur_pid, *my_res;
+
+	my_pid = bpf_map_lookup_elem(&my_pid_map, &zero);
+	if (!my_pid)
+		return 1;
+
+	cur_pid = bpf_get_current_pid_tgid() >> 32;
+	if (cur_pid != *my_pid)
+		return 1;
+
+	my_res = bpf_map_lookup_elem(&res_map, &zero);
+	if (!my_res)
+		return 1;
+
+	if (*my_res == 0)
+		/* use bpf_printk() in combination with BPF_NO_GLOBAL_DATA to
+		 * force .rodata.str1.1 section that previously caused
+		 * problems on old kernels due to libbpf always tried to
+		 * create a global data map for it
+		 */
+		bpf_printk("Legacy-case bpf_printk test, pid %d\n", cur_pid);
+	*my_res = 1;
+
+	return *my_res;
+}
+
+SEC("tp/raw_syscalls/sys_enter")
+int handle_modern(void *ctx)
+{
+	int zero = 0, cur_pid;
+
+	cur_pid = bpf_get_current_pid_tgid() >> 32;
+	if (cur_pid != my_pid_var)
+		return 1;
+
+	if (res_var == 0)
+		/* we need bpf_printk() to validate libbpf logic around unused
+		 * global maps and legacy kernels; see comment in handle_legacy()
+		 */
+		bpf_printk("Modern-case bpf_printk test, pid %d\n", cur_pid);
+	res_var = 1;
+
+	return res_var;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_log_buf.c b/tools/testing/selftests/bpf/progs/test_log_buf.c
new file mode 100644
index 000000000000..199f459bd5ae
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_log_buf.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+int a[4];
+const volatile int off = 4000;
+
+SEC("raw_tp/sys_enter")
+int good_prog(const void *ctx)
+{
+	a[0] = (int)(long)ctx;
+	return a[1];
+}
+
+SEC("raw_tp/sys_enter")
+int bad_prog(const void *ctx)
+{
+	/* out of bounds access */
+	return a[off];
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_prog_array_init.c b/tools/testing/selftests/bpf/progs/test_prog_array_init.c
new file mode 100644
index 000000000000..2cd138356126
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_prog_array_init.c
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2021 Hengqi Chen */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+const volatile pid_t my_pid = 0;
+int value = 0;
+
+SEC("raw_tp/sys_enter")
+int tailcall_1(void *ctx)
+{
+	value = 42;
+	return 0;
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 2);
+	__uint(key_size, sizeof(__u32));
+	__array(values, int (void *));
+} prog_array_init SEC(".maps") = {
+	.values = {
+		[1] = (void *)&tailcall_1,
+	},
+};
+
+SEC("raw_tp/sys_enter")
+int entry(void *ctx)
+{
+	pid_t pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid != my_pid)
+		return 0;
+
+	bpf_tail_call(ctx, &prog_array_init, 1);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale2.c b/tools/testing/selftests/bpf/progs/test_verif_scale2.c
index f024154c7be7..f90ffcafd1e8 100644
--- a/tools/testing/selftests/bpf/progs/test_verif_scale2.c
+++ b/tools/testing/selftests/bpf/progs/test_verif_scale2.c
@@ -1,11 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2019 Facebook
-#include <linux/bpf.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #define ATTR __always_inline
 #include "test_jhash.h"
 
-SEC("scale90_inline")
+SEC("tc")
 int balancer_ingress(struct __sk_buff *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c
index 9a4d09590b3d..2098f3f27f18 100644
--- a/tools/testing/selftests/bpf/progs/trigger_bench.c
+++ b/tools/testing/selftests/bpf/progs/trigger_bench.c
@@ -52,3 +52,10 @@ int bench_trigger_fmodret(void *ctx)
 	__sync_add_and_fetch(&hits, 1);
 	return -22;
 }
+
+SEC("uprobe/self/uprobe_target")
+int bench_trigger_uprobe(void *ctx)
+{
+	__sync_add_and_fetch(&hits, 1);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_bpftool_synctypes.py b/tools/testing/selftests/bpf/test_bpftool_synctypes.py
index be54b7335a76..6bf21e47882a 100755
--- a/tools/testing/selftests/bpf/test_bpftool_synctypes.py
+++ b/tools/testing/selftests/bpf/test_bpftool_synctypes.py
@@ -9,7 +9,15 @@ import os, sys
 
 LINUX_ROOT = os.path.abspath(os.path.join(__file__,
     os.pardir, os.pardir, os.pardir, os.pardir, os.pardir))
-BPFTOOL_DIR = os.path.join(LINUX_ROOT, 'tools/bpf/bpftool')
+BPFTOOL_DIR = os.getenv('BPFTOOL_DIR',
+    os.path.join(LINUX_ROOT, 'tools/bpf/bpftool'))
+BPFTOOL_BASHCOMP_DIR = os.getenv('BPFTOOL_BASHCOMP_DIR',
+    os.path.join(BPFTOOL_DIR, 'bash-completion'))
+BPFTOOL_DOC_DIR = os.getenv('BPFTOOL_DOC_DIR',
+    os.path.join(BPFTOOL_DIR, 'Documentation'))
+INCLUDE_DIR = os.getenv('INCLUDE_DIR',
+    os.path.join(LINUX_ROOT, 'tools/include'))
+
 retval = 0
 
 class BlockParser(object):
@@ -242,12 +250,6 @@ class FileExtractor(object):
         end_marker = re.compile('}\\\\n')
         return self.__get_description_list(start_marker, pattern, end_marker)
 
-    def default_options(self):
-        """
-        Return the default options contained in HELP_SPEC_OPTIONS
-        """
-        return { '-j', '--json', '-p', '--pretty', '-d', '--debug' }
-
     def get_bashcomp_list(self, block_name):
         """
         Search for and parse a list of type names from a variable in bash
@@ -274,7 +276,56 @@ class SourceFileExtractor(FileExtractor):
     defined in children classes.
     """
     def get_options(self):
-        return self.default_options().union(self.get_help_list_macro('HELP_SPEC_OPTIONS'))
+        return self.get_help_list_macro('HELP_SPEC_OPTIONS')
+
+class MainHeaderFileExtractor(SourceFileExtractor):
+    """
+    An extractor for bpftool's main.h
+    """
+    filename = os.path.join(BPFTOOL_DIR, 'main.h')
+
+    def get_common_options(self):
+        """
+        Parse the list of common options in main.h (options that apply to all
+        commands), which looks to the lists of options in other source files
+        but has different start and end markers:
+
+            "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-d|--debug} | {-l|--legacy}"
+
+        Return a set containing all options, such as:
+
+            {'-p', '-d', '--legacy', '--pretty', '--debug', '--json', '-l', '-j'}
+        """
+        start_marker = re.compile(f'"OPTIONS :=')
+        pattern = re.compile('([\w-]+) ?(?:\||}[ }\]"])')
+        end_marker = re.compile('#define')
+
+        parser = InlineListParser(self.reader)
+        parser.search_block(start_marker)
+        return parser.parse(pattern, end_marker)
+
+class ManSubstitutionsExtractor(SourceFileExtractor):
+    """
+    An extractor for substitutions.rst
+    """
+    filename = os.path.join(BPFTOOL_DOC_DIR, 'substitutions.rst')
+
+    def get_common_options(self):
+        """
+        Parse the list of common options in substitutions.rst (options that
+        apply to all commands).
+
+        Return a set containing all options, such as:
+
+            {'-p', '-d', '--legacy', '--pretty', '--debug', '--json', '-l', '-j'}
+        """
+        start_marker = re.compile('\|COMMON_OPTIONS\| replace:: {')
+        pattern = re.compile('\*\*([\w/-]+)\*\*')
+        end_marker = re.compile('}$')
+
+        parser = InlineListParser(self.reader)
+        parser.search_block(start_marker)
+        return parser.parse(pattern, end_marker)
 
 class ProgFileExtractor(SourceFileExtractor):
     """
@@ -350,7 +401,7 @@ class BpfHeaderExtractor(FileExtractor):
     """
     An extractor for the UAPI BPF header.
     """
-    filename = os.path.join(LINUX_ROOT, 'tools/include/uapi/linux/bpf.h')
+    filename = os.path.join(INCLUDE_DIR, 'uapi/linux/bpf.h')
 
     def get_prog_types(self):
         return self.get_enum('bpf_prog_type')
@@ -374,7 +425,7 @@ class ManProgExtractor(ManPageExtractor):
     """
     An extractor for bpftool-prog.rst.
     """
-    filename = os.path.join(BPFTOOL_DIR, 'Documentation/bpftool-prog.rst')
+    filename = os.path.join(BPFTOOL_DOC_DIR, 'bpftool-prog.rst')
 
     def get_attach_types(self):
         return self.get_rst_list('ATTACH_TYPE')
@@ -383,7 +434,7 @@ class ManMapExtractor(ManPageExtractor):
     """
     An extractor for bpftool-map.rst.
     """
-    filename = os.path.join(BPFTOOL_DIR, 'Documentation/bpftool-map.rst')
+    filename = os.path.join(BPFTOOL_DOC_DIR, 'bpftool-map.rst')
 
     def get_map_types(self):
         return self.get_rst_list('TYPE')
@@ -392,7 +443,7 @@ class ManCgroupExtractor(ManPageExtractor):
     """
     An extractor for bpftool-cgroup.rst.
     """
-    filename = os.path.join(BPFTOOL_DIR, 'Documentation/bpftool-cgroup.rst')
+    filename = os.path.join(BPFTOOL_DOC_DIR, 'bpftool-cgroup.rst')
 
     def get_attach_types(self):
         return self.get_rst_list('ATTACH_TYPE')
@@ -411,7 +462,7 @@ class BashcompExtractor(FileExtractor):
     """
     An extractor for bpftool's bash completion file.
     """
-    filename = os.path.join(BPFTOOL_DIR, 'bash-completion/bpftool')
+    filename = os.path.join(BPFTOOL_BASHCOMP_DIR, 'bpftool')
 
     def get_prog_attach_types(self):
         return self.get_bashcomp_list('BPFTOOL_PROG_ATTACH_TYPES')
@@ -562,7 +613,7 @@ def main():
         help_cmd_options = source_info.get_options()
         source_info.close()
 
-        man_cmd_info = ManGenericExtractor(os.path.join('Documentation', 'bpftool-' + cmd + '.rst'))
+        man_cmd_info = ManGenericExtractor(os.path.join(BPFTOOL_DOC_DIR, 'bpftool-' + cmd + '.rst'))
         man_cmd_options = man_cmd_info.get_options()
         man_cmd_info.close()
 
@@ -573,13 +624,26 @@ def main():
     help_main_options = source_main_info.get_options()
     source_main_info.close()
 
-    man_main_info = ManGenericExtractor(os.path.join('Documentation', 'bpftool.rst'))
+    man_main_info = ManGenericExtractor(os.path.join(BPFTOOL_DOC_DIR, 'bpftool.rst'))
     man_main_options = man_main_info.get_options()
     man_main_info.close()
 
     verify(help_main_options, man_main_options,
             f'Comparing {source_main_info.filename} (do_help() OPTIONS) and {man_main_info.filename} (OPTIONS):')
 
+    # Compare common options (options that apply to all commands)
+
+    main_hdr_info = MainHeaderFileExtractor()
+    source_common_options = main_hdr_info.get_common_options()
+    main_hdr_info.close()
+
+    man_substitutions = ManSubstitutionsExtractor()
+    man_common_options = man_substitutions.get_common_options()
+    man_substitutions.close()
+
+    verify(source_common_options, man_common_options,
+            f'Comparing common options from {main_hdr_info.filename} (HELP_SPEC_OPTIONS) and {man_substitutions.filename}:')
+
     sys.exit(retval)
 
 if __name__ == "__main__":
diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c
index a63787e7bb1a..5b8314cd77fd 100644
--- a/tools/testing/selftests/bpf/test_cgroup_storage.c
+++ b/tools/testing/selftests/bpf/test_cgroup_storage.c
@@ -51,15 +51,15 @@ int main(int argc, char **argv)
 		goto err;
 	}
 
-	map_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE, sizeof(key),
-				sizeof(value), 0, 0);
+	map_fd = bpf_map_create(BPF_MAP_TYPE_CGROUP_STORAGE, NULL, sizeof(key),
+				sizeof(value), 0, NULL);
 	if (map_fd < 0) {
 		printf("Failed to create map: %s\n", strerror(errno));
 		goto out;
 	}
 
-	percpu_map_fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
-				       sizeof(key), sizeof(value), 0, 0);
+	percpu_map_fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, NULL,
+				       sizeof(key), sizeof(value), 0, NULL);
 	if (percpu_map_fd < 0) {
 		printf("Failed to create map: %s\n", strerror(errno));
 		goto out;
diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c
index 006be3963977..baa3e3ecae82 100644
--- a/tools/testing/selftests/bpf/test_lpm_map.c
+++ b/tools/testing/selftests/bpf/test_lpm_map.c
@@ -208,6 +208,7 @@ static void test_lpm_order(void)
 
 static void test_lpm_map(int keysize)
 {
+	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC);
 	size_t i, j, n_matches, n_matches_after_delete, n_nodes, n_lookups;
 	struct tlpm_node *t, *list = NULL;
 	struct bpf_lpm_trie_key *key;
@@ -233,11 +234,11 @@ static void test_lpm_map(int keysize)
 	key = alloca(sizeof(*key) + keysize);
 	memset(key, 0, sizeof(*key) + keysize);
 
-	map = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE,
+	map = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL,
 			     sizeof(*key) + keysize,
 			     keysize + 1,
 			     4096,
-			     BPF_F_NO_PREALLOC);
+			     &opts);
 	assert(map >= 0);
 
 	for (i = 0; i < n_nodes; ++i) {
@@ -329,6 +330,7 @@ static void test_lpm_map(int keysize)
 
 static void test_lpm_ipaddr(void)
 {
+	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC);
 	struct bpf_lpm_trie_key *key_ipv4;
 	struct bpf_lpm_trie_key *key_ipv6;
 	size_t key_size_ipv4;
@@ -342,14 +344,14 @@ static void test_lpm_ipaddr(void)
 	key_ipv4 = alloca(key_size_ipv4);
 	key_ipv6 = alloca(key_size_ipv6);
 
-	map_fd_ipv4 = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE,
+	map_fd_ipv4 = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL,
 				     key_size_ipv4, sizeof(value),
-				     100, BPF_F_NO_PREALLOC);
+				     100, &opts);
 	assert(map_fd_ipv4 >= 0);
 
-	map_fd_ipv6 = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE,
+	map_fd_ipv6 = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL,
 				     key_size_ipv6, sizeof(value),
-				     100, BPF_F_NO_PREALLOC);
+				     100, &opts);
 	assert(map_fd_ipv6 >= 0);
 
 	/* Fill data some IPv4 and IPv6 address ranges */
@@ -423,6 +425,7 @@ static void test_lpm_ipaddr(void)
 
 static void test_lpm_delete(void)
 {
+	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC);
 	struct bpf_lpm_trie_key *key;
 	size_t key_size;
 	int map_fd;
@@ -431,9 +434,9 @@ static void test_lpm_delete(void)
 	key_size = sizeof(*key) + sizeof(__u32);
 	key = alloca(key_size);
 
-	map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE,
+	map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL,
 				key_size, sizeof(value),
-				100, BPF_F_NO_PREALLOC);
+				100, &opts);
 	assert(map_fd >= 0);
 
 	/* Add nodes:
@@ -535,6 +538,7 @@ static void test_lpm_delete(void)
 
 static void test_lpm_get_next_key(void)
 {
+	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC);
 	struct bpf_lpm_trie_key *key_p, *next_key_p;
 	size_t key_size;
 	__u32 value = 0;
@@ -544,8 +548,7 @@ static void test_lpm_get_next_key(void)
 	key_p = alloca(key_size);
 	next_key_p = alloca(key_size);
 
-	map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, key_size, sizeof(value),
-				100, BPF_F_NO_PREALLOC);
+	map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, key_size, sizeof(value), 100, &opts);
 	assert(map_fd >= 0);
 
 	/* empty tree. get_next_key should return ENOENT */
@@ -753,6 +756,7 @@ static void setup_lpm_mt_test_info(struct lpm_mt_test_info *info, int map_fd)
 
 static void test_lpm_multi_thread(void)
 {
+	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC);
 	struct lpm_mt_test_info info[4];
 	size_t key_size, value_size;
 	pthread_t thread_id[4];
@@ -762,8 +766,7 @@ static void test_lpm_multi_thread(void)
 	/* create a trie */
 	value_size = sizeof(__u32);
 	key_size = sizeof(struct bpf_lpm_trie_key) + value_size;
-	map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, key_size, value_size,
-				100, BPF_F_NO_PREALLOC);
+	map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, key_size, value_size, 100, &opts);
 
 	/* create 4 threads to test update, delete, lookup and get_next_key */
 	setup_lpm_mt_test_info(&info[0], map_fd);
diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c
index 7f3d1d8460b4..b9f1bbbc8aba 100644
--- a/tools/testing/selftests/bpf/test_lru_map.c
+++ b/tools/testing/selftests/bpf/test_lru_map.c
@@ -28,13 +28,14 @@ static int nr_cpus;
 
 static int create_map(int map_type, int map_flags, unsigned int size)
 {
+	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = map_flags);
 	int map_fd;
 
-	map_fd = bpf_create_map(map_type, sizeof(unsigned long long),
-				sizeof(unsigned long long), size, map_flags);
+	map_fd = bpf_map_create(map_type, NULL,  sizeof(unsigned long long),
+				sizeof(unsigned long long), size, &opts);
 
 	if (map_fd == -1)
-		perror("bpf_create_map");
+		perror("bpf_map_create");
 
 	return map_fd;
 }
@@ -42,7 +43,6 @@ static int create_map(int map_type, int map_flags, unsigned int size)
 static int bpf_map_lookup_elem_with_ref_bit(int fd, unsigned long long key,
 					    void *value)
 {
-	struct bpf_create_map_attr map;
 	struct bpf_insn insns[] = {
 		BPF_LD_MAP_VALUE(BPF_REG_9, 0, 0),
 		BPF_LD_MAP_FD(BPF_REG_1, fd),
@@ -63,13 +63,7 @@ static int bpf_map_lookup_elem_with_ref_bit(int fd, unsigned long long key,
 	int mfd, pfd, ret, zero = 0;
 	__u32 retval = 0;
 
-	memset(&map, 0, sizeof(map));
-	map.map_type = BPF_MAP_TYPE_ARRAY;
-	map.key_size = sizeof(int);
-	map.value_size = sizeof(unsigned long long);
-	map.max_entries = 1;
-
-	mfd = bpf_create_map_xattr(&map);
+	mfd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), sizeof(__u64), 1, NULL);
 	if (mfd < 0)
 		return -1;
 
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 8b31bc1a801d..f4cd658bbe00 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -33,15 +33,14 @@
 
 static int skips;
 
-static int map_flags;
+static struct bpf_map_create_opts map_opts = { .sz = sizeof(map_opts) };
 
 static void test_hashmap(unsigned int task, void *data)
 {
 	long long key, next_key, first_key, value;
 	int fd;
 
-	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
-			    2, map_flags);
+	fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(key), sizeof(value), 2, &map_opts);
 	if (fd < 0) {
 		printf("Failed to create hashmap '%s'!\n", strerror(errno));
 		exit(1);
@@ -138,8 +137,7 @@ static void test_hashmap_sizes(unsigned int task, void *data)
 
 	for (i = 1; i <= 512; i <<= 1)
 		for (j = 1; j <= 1 << 18; j <<= 1) {
-			fd = bpf_create_map(BPF_MAP_TYPE_HASH, i, j,
-					    2, map_flags);
+			fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, i, j, 2, &map_opts);
 			if (fd < 0) {
 				if (errno == ENOMEM)
 					return;
@@ -160,8 +158,8 @@ static void test_hashmap_percpu(unsigned int task, void *data)
 	int expected_key_mask = 0;
 	int fd, i;
 
-	fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_HASH, sizeof(key),
-			    sizeof(bpf_percpu(value, 0)), 2, map_flags);
+	fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_HASH, NULL, sizeof(key),
+			    sizeof(bpf_percpu(value, 0)), 2, &map_opts);
 	if (fd < 0) {
 		printf("Failed to create hashmap '%s'!\n", strerror(errno));
 		exit(1);
@@ -272,11 +270,11 @@ static int helper_fill_hashmap(int max_entries)
 	int i, fd, ret;
 	long long key, value;
 
-	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
-			    max_entries, map_flags);
+	fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(key), sizeof(value),
+			    max_entries, &map_opts);
 	CHECK(fd < 0,
 	      "failed to create hashmap",
-	      "err: %s, flags: 0x%x\n", strerror(errno), map_flags);
+	      "err: %s, flags: 0x%x\n", strerror(errno), map_opts.map_flags);
 
 	for (i = 0; i < max_entries; i++) {
 		key = i; value = key;
@@ -332,8 +330,8 @@ static void test_hashmap_zero_seed(void)
 	int i, first, second, old_flags;
 	long long key, next_first, next_second;
 
-	old_flags = map_flags;
-	map_flags |= BPF_F_ZERO_SEED;
+	old_flags = map_opts.map_flags;
+	map_opts.map_flags |= BPF_F_ZERO_SEED;
 
 	first = helper_fill_hashmap(3);
 	second = helper_fill_hashmap(3);
@@ -355,7 +353,7 @@ static void test_hashmap_zero_seed(void)
 		key = next_first;
 	}
 
-	map_flags = old_flags;
+	map_opts.map_flags = old_flags;
 	close(first);
 	close(second);
 }
@@ -365,8 +363,7 @@ static void test_arraymap(unsigned int task, void *data)
 	int key, next_key, fd;
 	long long value;
 
-	fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value),
-			    2, 0);
+	fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(key), sizeof(value), 2, NULL);
 	if (fd < 0) {
 		printf("Failed to create arraymap '%s'!\n", strerror(errno));
 		exit(1);
@@ -421,8 +418,8 @@ static void test_arraymap_percpu(unsigned int task, void *data)
 	BPF_DECLARE_PERCPU(long, values);
 	int key, next_key, fd, i;
 
-	fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key),
-			    sizeof(bpf_percpu(values, 0)), 2, 0);
+	fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, NULL, sizeof(key),
+			    sizeof(bpf_percpu(values, 0)), 2, NULL);
 	if (fd < 0) {
 		printf("Failed to create arraymap '%s'!\n", strerror(errno));
 		exit(1);
@@ -484,8 +481,8 @@ static void test_arraymap_percpu_many_keys(void)
 	unsigned int nr_keys = 2000;
 	int key, fd, i;
 
-	fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key),
-			    sizeof(bpf_percpu(values, 0)), nr_keys, 0);
+	fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, NULL, sizeof(key),
+			    sizeof(bpf_percpu(values, 0)), nr_keys, NULL);
 	if (fd < 0) {
 		printf("Failed to create per-cpu arraymap '%s'!\n",
 		       strerror(errno));
@@ -516,8 +513,7 @@ static void test_devmap(unsigned int task, void *data)
 	int fd;
 	__u32 key, value;
 
-	fd = bpf_create_map(BPF_MAP_TYPE_DEVMAP, sizeof(key), sizeof(value),
-			    2, 0);
+	fd = bpf_map_create(BPF_MAP_TYPE_DEVMAP, NULL, sizeof(key), sizeof(value), 2, NULL);
 	if (fd < 0) {
 		printf("Failed to create devmap '%s'!\n", strerror(errno));
 		exit(1);
@@ -531,8 +527,7 @@ static void test_devmap_hash(unsigned int task, void *data)
 	int fd;
 	__u32 key, value;
 
-	fd = bpf_create_map(BPF_MAP_TYPE_DEVMAP_HASH, sizeof(key), sizeof(value),
-			    2, 0);
+	fd = bpf_map_create(BPF_MAP_TYPE_DEVMAP_HASH, NULL, sizeof(key), sizeof(value), 2, NULL);
 	if (fd < 0) {
 		printf("Failed to create devmap_hash '%s'!\n", strerror(errno));
 		exit(1);
@@ -552,14 +547,12 @@ static void test_queuemap(unsigned int task, void *data)
 		vals[i] = rand();
 
 	/* Invalid key size */
-	fd = bpf_create_map(BPF_MAP_TYPE_QUEUE, 4, sizeof(val), MAP_SIZE,
-			    map_flags);
+	fd = bpf_map_create(BPF_MAP_TYPE_QUEUE, NULL, 4, sizeof(val), MAP_SIZE, &map_opts);
 	assert(fd < 0 && errno == EINVAL);
 
-	fd = bpf_create_map(BPF_MAP_TYPE_QUEUE, 0, sizeof(val), MAP_SIZE,
-			    map_flags);
+	fd = bpf_map_create(BPF_MAP_TYPE_QUEUE, NULL, 0, sizeof(val), MAP_SIZE, &map_opts);
 	/* Queue map does not support BPF_F_NO_PREALLOC */
-	if (map_flags & BPF_F_NO_PREALLOC) {
+	if (map_opts.map_flags & BPF_F_NO_PREALLOC) {
 		assert(fd < 0 && errno == EINVAL);
 		return;
 	}
@@ -610,14 +603,12 @@ static void test_stackmap(unsigned int task, void *data)
 		vals[i] = rand();
 
 	/* Invalid key size */
-	fd = bpf_create_map(BPF_MAP_TYPE_STACK, 4, sizeof(val), MAP_SIZE,
-			    map_flags);
+	fd = bpf_map_create(BPF_MAP_TYPE_STACK, NULL, 4, sizeof(val), MAP_SIZE, &map_opts);
 	assert(fd < 0 && errno == EINVAL);
 
-	fd = bpf_create_map(BPF_MAP_TYPE_STACK, 0, sizeof(val), MAP_SIZE,
-			    map_flags);
+	fd = bpf_map_create(BPF_MAP_TYPE_STACK, NULL, 0, sizeof(val), MAP_SIZE, &map_opts);
 	/* Stack map does not support BPF_F_NO_PREALLOC */
-	if (map_flags & BPF_F_NO_PREALLOC) {
+	if (map_opts.map_flags & BPF_F_NO_PREALLOC) {
 		assert(fd < 0 && errno == EINVAL);
 		return;
 	}
@@ -744,9 +735,9 @@ static void test_sockmap(unsigned int tasks, void *data)
 	}
 
 	/* Test sockmap with connected sockets */
-	fd = bpf_create_map(BPF_MAP_TYPE_SOCKMAP,
+	fd = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL,
 			    sizeof(key), sizeof(value),
-			    6, 0);
+			    6, NULL);
 	if (fd < 0) {
 		if (!bpf_probe_map_type(BPF_MAP_TYPE_SOCKMAP, 0)) {
 			printf("%s SKIP (unsupported map type BPF_MAP_TYPE_SOCKMAP)\n",
@@ -1168,8 +1159,7 @@ static void test_map_in_map(void)
 
 	obj = bpf_object__open(MAPINMAP_PROG);
 
-	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(int), sizeof(int),
-			    2, 0);
+	fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(int), sizeof(int), 2, NULL);
 	if (fd < 0) {
 		printf("Failed to create hashmap '%s'!\n", strerror(errno));
 		exit(1);
@@ -1315,8 +1305,8 @@ static void test_map_large(void)
 	} key;
 	int fd, i, value;
 
-	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
-			    MAP_SIZE, map_flags);
+	fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(key), sizeof(value),
+			    MAP_SIZE, &map_opts);
 	if (fd < 0) {
 		printf("Failed to create large map '%s'!\n", strerror(errno));
 		exit(1);
@@ -1469,8 +1459,8 @@ static void test_map_parallel(void)
 	int i, fd, key = 0, value = 0;
 	int data[2];
 
-	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
-			    MAP_SIZE, map_flags);
+	fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(key), sizeof(value),
+			    MAP_SIZE, &map_opts);
 	if (fd < 0) {
 		printf("Failed to create map for parallel test '%s'!\n",
 		       strerror(errno));
@@ -1518,9 +1508,13 @@ static void test_map_parallel(void)
 static void test_map_rdonly(void)
 {
 	int fd, key = 0, value = 0;
+	__u32 old_flags;
 
-	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
-			    MAP_SIZE, map_flags | BPF_F_RDONLY);
+	old_flags = map_opts.map_flags;
+	map_opts.map_flags |= BPF_F_RDONLY;
+	fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(key), sizeof(value),
+			    MAP_SIZE, &map_opts);
+	map_opts.map_flags = old_flags;
 	if (fd < 0) {
 		printf("Failed to create map for read only test '%s'!\n",
 		       strerror(errno));
@@ -1543,9 +1537,13 @@ static void test_map_rdonly(void)
 static void test_map_wronly_hash(void)
 {
 	int fd, key = 0, value = 0;
+	__u32 old_flags;
 
-	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
-			    MAP_SIZE, map_flags | BPF_F_WRONLY);
+	old_flags = map_opts.map_flags;
+	map_opts.map_flags |= BPF_F_WRONLY;
+	fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(key), sizeof(value),
+			    MAP_SIZE, &map_opts);
+	map_opts.map_flags = old_flags;
 	if (fd < 0) {
 		printf("Failed to create map for write only test '%s'!\n",
 		       strerror(errno));
@@ -1567,13 +1565,17 @@ static void test_map_wronly_hash(void)
 static void test_map_wronly_stack_or_queue(enum bpf_map_type map_type)
 {
 	int fd, value = 0;
+	__u32 old_flags;
+
 
 	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);
+	old_flags = map_opts.map_flags;
+	map_opts.map_flags |= BPF_F_WRONLY;
+	fd = bpf_map_create(map_type, NULL, 0, sizeof(value), MAP_SIZE, &map_opts);
+	map_opts.map_flags = old_flags;
 	/* Stack/Queue maps do not support BPF_F_NO_PREALLOC */
-	if (map_flags & BPF_F_NO_PREALLOC) {
+	if (map_opts.map_flags & BPF_F_NO_PREALLOC) {
 		assert(fd < 0 && errno == EINVAL);
 		return;
 	}
@@ -1700,8 +1702,8 @@ static void test_reuseport_array(void)
 	__u32 fds_idx = 0;
 	int fd;
 
-	map_fd = bpf_create_map(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
-				sizeof(__u32), sizeof(__u64), array_size, 0);
+	map_fd = bpf_map_create(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, NULL,
+				sizeof(__u32), sizeof(__u64), array_size, NULL);
 	CHECK(map_fd < 0, "reuseport array create",
 	      "map_fd:%d, errno:%d\n", map_fd, errno);
 
@@ -1837,8 +1839,8 @@ static void test_reuseport_array(void)
 	close(map_fd);
 
 	/* Test 32 bit fd */
-	map_fd = bpf_create_map(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
-				sizeof(__u32), sizeof(__u32), array_size, 0);
+	map_fd = bpf_map_create(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, NULL,
+				sizeof(__u32), sizeof(__u32), array_size, NULL);
 	CHECK(map_fd < 0, "reuseport array create",
 	      "map_fd:%d, errno:%d\n", map_fd, errno);
 	prepare_reuseport_grp(SOCK_STREAM, map_fd, sizeof(__u32), &fd64,
@@ -1896,10 +1898,10 @@ int main(void)
 
 	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
 
-	map_flags = 0;
+	map_opts.map_flags = 0;
 	run_all_tests();
 
-	map_flags = BPF_F_NO_PREALLOC;
+	map_opts.map_flags = BPF_F_NO_PREALLOC;
 	run_all_tests();
 
 #define DEFINE_TEST(name) test_##name();
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index c65986bd9d07..296928948bb9 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -473,11 +473,11 @@ static struct prog_test_def prog_test_defs[] = {
 #include <prog_tests/tests.h>
 #undef DEFINE_TEST
 };
-const int prog_test_cnt = ARRAY_SIZE(prog_test_defs);
+static const int prog_test_cnt = ARRAY_SIZE(prog_test_defs);
 
 const char *argp_program_version = "test_progs 0.1";
 const char *argp_program_bug_address = "<bpf@vger.kernel.org>";
-const char argp_program_doc[] = "BPF selftests test runner";
+static const char argp_program_doc[] = "BPF selftests test runner";
 
 enum ARG_KEYS {
 	ARG_TEST_NUM = 'n',
@@ -939,7 +939,7 @@ static void *dispatch_thread(void *ctx)
 {
 	struct dispatch_data *data = ctx;
 	int sock_fd;
-	FILE *log_fd = NULL;
+	FILE *log_fp = NULL;
 
 	sock_fd = data->sock_fd;
 
@@ -1002,8 +1002,8 @@ static void *dispatch_thread(void *ctx)
 
 			/* collect all logs */
 			if (msg_test_done.test_done.have_log) {
-				log_fd = open_memstream(&result->log_buf, &result->log_cnt);
-				if (!log_fd)
+				log_fp = open_memstream(&result->log_buf, &result->log_cnt);
+				if (!log_fp)
 					goto error;
 
 				while (true) {
@@ -1014,12 +1014,12 @@ static void *dispatch_thread(void *ctx)
 					if (msg_log.type != MSG_TEST_LOG)
 						goto error;
 
-					fprintf(log_fd, "%s", msg_log.test_log.log_buf);
+					fprintf(log_fp, "%s", msg_log.test_log.log_buf);
 					if (msg_log.test_log.is_last)
 						break;
 				}
-				fclose(log_fd);
-				log_fd = NULL;
+				fclose(log_fp);
+				log_fp = NULL;
 			}
 			/* output log */
 			{
@@ -1045,8 +1045,8 @@ error:
 	if (env.debug)
 		fprintf(stderr, "[%d]: Protocol/IO error: %s.\n", data->worker_id, strerror(errno));
 
-	if (log_fd)
-		fclose(log_fd);
+	if (log_fp)
+		fclose(log_fp);
 done:
 	{
 		struct msg msg_exit;
@@ -1198,11 +1198,11 @@ static int server_main(void)
 		env.sub_succ_cnt += result->sub_succ_cnt;
 	}
 
+	print_all_error_logs();
+
 	fprintf(stdout, "Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n",
 		env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt);
 
-	print_all_error_logs();
-
 	/* reap all workers */
 	for (i = 0; i < env.workers; i++) {
 		int wstatus, pid;
@@ -1484,11 +1484,11 @@ int main(int argc, char **argv)
 	if (env.list_test_names)
 		goto out;
 
+	print_all_error_logs();
+
 	fprintf(stdout, "Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n",
 		env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt);
 
-	print_all_error_logs();
-
 	close(env.saved_netns_fd);
 out:
 	if (!env.list_test_names && env.has_testmod)
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index 05c9e4944c01..f0c8d05ba6d1 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -663,23 +663,36 @@ static int load_insns(const struct sock_addr_test *test,
 
 static int load_path(const struct sock_addr_test *test, const char *path)
 {
-	struct bpf_prog_load_attr attr;
 	struct bpf_object *obj;
-	int prog_fd;
+	struct bpf_program *prog;
+	int err;
 
-	memset(&attr, 0, sizeof(struct bpf_prog_load_attr));
-	attr.file = path;
-	attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
-	attr.expected_attach_type = test->expected_attach_type;
-	attr.prog_flags = BPF_F_TEST_RND_HI32;
+	obj = bpf_object__open_file(path, NULL);
+	err = libbpf_get_error(obj);
+	if (err) {
+		log_err(">>> Opening BPF object (%s) error.\n", path);
+		return -1;
+	}
+
+	prog = bpf_object__next_program(obj, NULL);
+	if (!prog)
+		goto err_out;
 
-	if (bpf_prog_load_xattr(&attr, &obj, &prog_fd)) {
+	bpf_program__set_type(prog, BPF_PROG_TYPE_CGROUP_SOCK_ADDR);
+	bpf_program__set_expected_attach_type(prog, test->expected_attach_type);
+	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32);
+
+	err = bpf_object__load(obj);
+	if (err) {
 		if (test->expected_result != LOAD_REJECT)
 			log_err(">>> Loading program (%s) error.\n", path);
-		return -1;
+		goto err_out;
 	}
 
-	return prog_fd;
+	return bpf_program__fd(prog);
+err_out:
+	bpf_object__close(obj);
+	return -1;
 }
 
 static int bind4_prog_load(const struct sock_addr_test *test)
diff --git a/tools/testing/selftests/bpf/test_tag.c b/tools/testing/selftests/bpf/test_tag.c
index 5c7bea525626..0851c42ee31c 100644
--- a/tools/testing/selftests/bpf/test_tag.c
+++ b/tools/testing/selftests/bpf/test_tag.c
@@ -185,11 +185,12 @@ static void do_test(uint32_t *tests, int start_insns, int fd_map,
 
 int main(void)
 {
+	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC);
 	uint32_t tests = 0;
 	int i, fd_map;
 
-	fd_map = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(int),
-				sizeof(int), 1, BPF_F_NO_PREALLOC);
+	fd_map = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(int),
+				sizeof(int), 1, &opts);
 	assert(fd_map > 0);
 
 	for (i = 0; i < 5; i++) {
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 9fbef396a716..16ce2ad097f4 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -462,11 +462,11 @@ static int __create_map(uint32_t type, uint32_t size_key,
 			uint32_t size_value, uint32_t max_elem,
 			uint32_t extra_flags)
 {
+	LIBBPF_OPTS(bpf_map_create_opts, opts);
 	int fd;
 
-	fd = bpf_create_map(type, size_key, size_value, max_elem,
-			    (type == BPF_MAP_TYPE_HASH ?
-			     BPF_F_NO_PREALLOC : 0) | extra_flags);
+	opts.map_flags = (type == BPF_MAP_TYPE_HASH ? BPF_F_NO_PREALLOC : 0) | extra_flags;
+	fd = bpf_map_create(type, NULL, size_key, size_value, max_elem, &opts);
 	if (fd < 0) {
 		if (skip_unsupported_map(type))
 			return -1;
@@ -522,8 +522,8 @@ static int create_prog_array(enum bpf_prog_type prog_type, uint32_t max_elem,
 {
 	int mfd, p1fd, p2fd, p3fd;
 
-	mfd = bpf_create_map(BPF_MAP_TYPE_PROG_ARRAY, sizeof(int),
-			     sizeof(int), max_elem, 0);
+	mfd = bpf_map_create(BPF_MAP_TYPE_PROG_ARRAY, NULL, sizeof(int),
+			     sizeof(int), max_elem, NULL);
 	if (mfd < 0) {
 		if (skip_unsupported_map(BPF_MAP_TYPE_PROG_ARRAY))
 			return -1;
@@ -553,10 +553,11 @@ err:
 
 static int create_map_in_map(void)
 {
+	LIBBPF_OPTS(bpf_map_create_opts, opts);
 	int inner_map_fd, outer_map_fd;
 
-	inner_map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(int),
-				      sizeof(int), 1, 0);
+	inner_map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int),
+				      sizeof(int), 1, NULL);
 	if (inner_map_fd < 0) {
 		if (skip_unsupported_map(BPF_MAP_TYPE_ARRAY))
 			return -1;
@@ -564,8 +565,9 @@ static int create_map_in_map(void)
 		return inner_map_fd;
 	}
 
-	outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL,
-					     sizeof(int), inner_map_fd, 1, 0);
+	opts.inner_map_fd = inner_map_fd;
+	outer_map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL,
+				      sizeof(int), sizeof(int), 1, &opts);
 	if (outer_map_fd < 0) {
 		if (skip_unsupported_map(BPF_MAP_TYPE_ARRAY_OF_MAPS))
 			return -1;
@@ -584,8 +586,8 @@ static int create_cgroup_storage(bool percpu)
 		BPF_MAP_TYPE_CGROUP_STORAGE;
 	int fd;
 
-	fd = bpf_create_map(type, sizeof(struct bpf_cgroup_storage_key),
-			    TEST_DATA_LEN, 0, 0);
+	fd = bpf_map_create(type, NULL, sizeof(struct bpf_cgroup_storage_key),
+			    TEST_DATA_LEN, 0, NULL);
 	if (fd < 0) {
 		if (skip_unsupported_map(type))
 			return -1;
@@ -652,7 +654,7 @@ static int load_btf(void)
 	memcpy(ptr, btf_str_sec, hdr.str_len);
 	ptr += hdr.str_len;
 
-	btf_fd = bpf_load_btf(raw_btf, ptr - raw_btf, 0, 0, 0);
+	btf_fd = bpf_btf_load(raw_btf, ptr - raw_btf, NULL);
 	free(raw_btf);
 	if (btf_fd < 0)
 		return -1;
@@ -661,22 +663,17 @@ static int load_btf(void)
 
 static int create_map_spin_lock(void)
 {
-	struct bpf_create_map_attr attr = {
-		.name = "test_map",
-		.map_type = BPF_MAP_TYPE_ARRAY,
-		.key_size = 4,
-		.value_size = 8,
-		.max_entries = 1,
+	LIBBPF_OPTS(bpf_map_create_opts, opts,
 		.btf_key_type_id = 1,
 		.btf_value_type_id = 3,
-	};
+	);
 	int fd, btf_fd;
 
 	btf_fd = load_btf();
 	if (btf_fd < 0)
 		return -1;
-	attr.btf_fd = btf_fd;
-	fd = bpf_create_map_xattr(&attr);
+	opts.btf_fd = btf_fd;
+	fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "test_map", 4, 8, 1, &opts);
 	if (fd < 0)
 		printf("Failed to create map with spin_lock\n");
 	return fd;
@@ -684,24 +681,19 @@ static int create_map_spin_lock(void)
 
 static int create_sk_storage_map(void)
 {
-	struct bpf_create_map_attr attr = {
-		.name = "test_map",
-		.map_type = BPF_MAP_TYPE_SK_STORAGE,
-		.key_size = 4,
-		.value_size = 8,
-		.max_entries = 0,
+	LIBBPF_OPTS(bpf_map_create_opts, opts,
 		.map_flags = BPF_F_NO_PREALLOC,
 		.btf_key_type_id = 1,
 		.btf_value_type_id = 3,
-	};
+	);
 	int fd, btf_fd;
 
 	btf_fd = load_btf();
 	if (btf_fd < 0)
 		return -1;
-	attr.btf_fd = btf_fd;
-	fd = bpf_create_map_xattr(&attr);
-	close(attr.btf_fd);
+	opts.btf_fd = btf_fd;
+	fd = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "test_map", 4, 8, 0, &opts);
+	close(opts.btf_fd);
 	if (fd < 0)
 		printf("Failed to create sk_storage_map\n");
 	return fd;
diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c
index 52c2f24e0898..795b6798ccee 100644
--- a/tools/testing/selftests/bpf/testing_helpers.c
+++ b/tools/testing/selftests/bpf/testing_helpers.c
@@ -88,12 +88,15 @@ int extra_prog_load_log_flags = 0;
 int bpf_prog_test_load(const char *file, enum bpf_prog_type type,
 		       struct bpf_object **pobj, int *prog_fd)
 {
-	struct bpf_object_load_attr attr = {};
+	LIBBPF_OPTS(bpf_object_open_opts, opts,
+		.kernel_log_level = extra_prog_load_log_flags,
+	);
 	struct bpf_object *obj;
 	struct bpf_program *prog;
+	__u32 flags;
 	int err;
 
-	obj = bpf_object__open(file);
+	obj = bpf_object__open_file(file, &opts);
 	if (!obj)
 		return -errno;
 
@@ -106,11 +109,10 @@ int bpf_prog_test_load(const char *file, enum bpf_prog_type type,
 	if (type != BPF_PROG_TYPE_UNSPEC)
 		bpf_program__set_type(prog, type);
 
-	bpf_program__set_extra_flags(prog, BPF_F_TEST_RND_HI32);
+	flags = bpf_program__flags(prog) | BPF_F_TEST_RND_HI32;
+	bpf_program__set_flags(prog, flags);
 
-	attr.obj = obj;
-	attr.log_level = extra_prog_load_log_flags;
-	err = bpf_object__load_xattr(&attr);
+	err = bpf_object__load(obj);
 	if (err)
 		goto err_out;
 
diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh
index 027198768fad..5e43c79ddc6e 100755
--- a/tools/testing/selftests/bpf/vmtest.sh
+++ b/tools/testing/selftests/bpf/vmtest.sh
@@ -4,17 +4,34 @@
 set -u
 set -e
 
-# This script currently only works for x86_64, as
-# it is based on the VM image used by the BPF CI which is
-# x86_64.
-QEMU_BINARY="${QEMU_BINARY:="qemu-system-x86_64"}"
-X86_BZIMAGE="arch/x86/boot/bzImage"
+# This script currently only works for x86_64 and s390x, as
+# it is based on the VM image used by the BPF CI, which is
+# available only for these architectures.
+ARCH="$(uname -m)"
+case "${ARCH}" in
+s390x)
+	QEMU_BINARY=qemu-system-s390x
+	QEMU_CONSOLE="ttyS1"
+	QEMU_FLAGS=(-smp 2)
+	BZIMAGE="arch/s390/boot/compressed/vmlinux"
+	;;
+x86_64)
+	QEMU_BINARY=qemu-system-x86_64
+	QEMU_CONSOLE="ttyS0,115200"
+	QEMU_FLAGS=(-cpu host -smp 8)
+	BZIMAGE="arch/x86/boot/bzImage"
+	;;
+*)
+	echo "Unsupported architecture"
+	exit 1
+	;;
+esac
 DEFAULT_COMMAND="./test_progs"
 MOUNT_DIR="mnt"
 ROOTFS_IMAGE="root.img"
 OUTPUT_DIR="$HOME/.bpf_selftests"
-KCONFIG_URL="https://raw.githubusercontent.com/libbpf/libbpf/master/travis-ci/vmtest/configs/latest.config"
-KCONFIG_API_URL="https://api.github.com/repos/libbpf/libbpf/contents/travis-ci/vmtest/configs/latest.config"
+KCONFIG_URL="https://raw.githubusercontent.com/libbpf/libbpf/master/travis-ci/vmtest/configs/config-latest.${ARCH}"
+KCONFIG_API_URL="https://api.github.com/repos/libbpf/libbpf/contents/travis-ci/vmtest/configs/config-latest.${ARCH}"
 INDEX_URL="https://raw.githubusercontent.com/libbpf/libbpf/master/travis-ci/vmtest/configs/INDEX"
 NUM_COMPILE_JOBS="$(nproc)"
 LOG_FILE_BASE="$(date +"bpf_selftests.%Y-%m-%d_%H-%M-%S")"
@@ -85,7 +102,7 @@ newest_rootfs_version()
 {
 	{
 	for file in "${!URLS[@]}"; do
-		if [[ $file =~ ^libbpf-vmtest-rootfs-(.*)\.tar\.zst$ ]]; then
+		if [[ $file =~ ^"${ARCH}"/libbpf-vmtest-rootfs-(.*)\.tar\.zst$ ]]; then
 			echo "${BASH_REMATCH[1]}"
 		fi
 	done
@@ -102,7 +119,7 @@ download_rootfs()
 		exit 1
 	fi
 
-	download "libbpf-vmtest-rootfs-$rootfsversion.tar.zst" |
+	download "${ARCH}/libbpf-vmtest-rootfs-$rootfsversion.tar.zst" |
 		zstd -d | sudo tar -C "$dir" -x
 }
 
@@ -224,13 +241,12 @@ EOF
 		-nodefaults \
 		-display none \
 		-serial mon:stdio \
-		-cpu host \
+		"${qemu_flags[@]}" \
 		-enable-kvm \
-		-smp 8 \
 		-m 4G \
 		-drive file="${rootfs_img}",format=raw,index=1,media=disk,if=virtio,cache=none \
 		-kernel "${kernel_bzimage}" \
-		-append "root=/dev/vda rw console=ttyS0,115200"
+		-append "root=/dev/vda rw console=${QEMU_CONSOLE}"
 }
 
 copy_logs()
@@ -282,7 +298,7 @@ main()
 	local kernel_checkout=$(realpath "${script_dir}"/../../../../)
 	# By default the script searches for the kernel in the checkout directory but
 	# it also obeys environment variables O= and KBUILD_OUTPUT=
-	local kernel_bzimage="${kernel_checkout}/${X86_BZIMAGE}"
+	local kernel_bzimage="${kernel_checkout}/${BZIMAGE}"
 	local command="${DEFAULT_COMMAND}"
 	local update_image="no"
 	local exit_command="poweroff -f"
@@ -337,13 +353,13 @@ main()
 		if is_rel_path "${O}"; then
 			O="$(realpath "${PWD}/${O}")"
 		fi
-		kernel_bzimage="${O}/${X86_BZIMAGE}"
+		kernel_bzimage="${O}/${BZIMAGE}"
 		make_command="${make_command} O=${O}"
 	elif [[ "${KBUILD_OUTPUT:=""}" != "" ]]; then
 		if is_rel_path "${KBUILD_OUTPUT}"; then
 			KBUILD_OUTPUT="$(realpath "${PWD}/${KBUILD_OUTPUT}")"
 		fi
-		kernel_bzimage="${KBUILD_OUTPUT}/${X86_BZIMAGE}"
+		kernel_bzimage="${KBUILD_OUTPUT}/${BZIMAGE}"
 		make_command="${make_command} KBUILD_OUTPUT=${KBUILD_OUTPUT}"
 	fi
 
diff --git a/tools/testing/selftests/bpf/xdp_redirect_multi.c b/tools/testing/selftests/bpf/xdp_redirect_multi.c
index f5ffba341c17..51c8224b4ccc 100644
--- a/tools/testing/selftests/bpf/xdp_redirect_multi.c
+++ b/tools/testing/selftests/bpf/xdp_redirect_multi.c
@@ -85,10 +85,7 @@ int main(int argc, char **argv)
 {
 	int prog_fd, group_all, mac_map;
 	struct bpf_program *ingress_prog, *egress_prog;
-	struct bpf_prog_load_attr prog_load_attr = {
-		.prog_type = BPF_PROG_TYPE_UNSPEC,
-	};
-	int i, ret, opt, egress_prog_fd = 0;
+	int i, err, ret, opt, egress_prog_fd = 0;
 	struct bpf_devmap_val devmap_val;
 	bool attach_egress_prog = false;
 	unsigned char mac_addr[6];
@@ -147,10 +144,14 @@ int main(int argc, char **argv)
 	printf("\n");
 
 	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
-	prog_load_attr.file = filename;
-
-	if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
+	obj = bpf_object__open_file(filename, NULL);
+	err = libbpf_get_error(obj);
+	if (err)
+		goto err_out;
+	err = bpf_object__load(obj);
+	if (err)
 		goto err_out;
+	prog_fd = bpf_program__fd(bpf_object__next_program(obj, NULL));
 
 	if (attach_egress_prog)
 		group_all = bpf_object__find_map_fd_by_name(obj, "map_egress");
diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index fe7f423b8c3f..0a5d23da486d 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -100,6 +100,12 @@
 #include "xdpxceiver.h"
 #include "../kselftest.h"
 
+/* AF_XDP APIs were moved into libxdp and marked as deprecated in libbpf.
+ * Until xdpxceiver is either moved or re-writed into libxdp, suppress
+ * deprecation warnings in this file
+ */
+#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
+
 static const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62";
 static const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61";
 static const char *IP1 = "192.168.100.162";
@@ -1217,7 +1223,7 @@ static bool hugepages_present(struct ifobject *ifobject)
 	void *bufs;
 
 	bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE,
-		    MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE | MAP_HUGETLB, -1, 0);
+		    MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0);
 	if (bufs == MAP_FAILED)
 		return false;
 
@@ -1364,6 +1370,10 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 		testapp_invalid_desc(test);
 		break;
 	case TEST_TYPE_UNALIGNED_INV_DESC:
+		if (!hugepages_present(test->ifobj_tx)) {
+			ksft_test_result_skip("No 2M huge pages present.\n");
+			return;
+		}
 		test_spec_set_name(test, "UNALIGNED_INV_DESC");
 		test->ifobj_tx->umem->unaligned_mode = true;
 		test->ifobj_rx->umem->unaligned_mode = true;