15 files changed, 654 insertions, 5 deletions

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index a69e4b04ffeb..211b43afd0fb 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4957,6 +4957,30 @@ union bpf_attr {
  *		**-ENOENT** if *task->mm* is NULL, or no vma contains *addr*.
  *		**-EBUSY** if failed to try lock mmap_lock.
  *		**-EINVAL** for invalid **flags**.
+ *
+ * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags)
+ *	Description
+ *		For **nr_loops**, call **callback_fn** function
+ *		with **callback_ctx** as the context parameter.
+ *		The **callback_fn** should be a static function and
+ *		the **callback_ctx** should be a pointer to the stack.
+ *		The **flags** is used to control certain aspects of the helper.
+ *		Currently, the **flags** must be 0. Currently, nr_loops is
+ *		limited to 1 << 23 (~8 million) loops.
+ *
+ *		long (\*callback_fn)(u32 index, void \*ctx);
+ *
+ *		where **index** is the current index in the loop. The index
+ *		is zero-indexed.
+ *
+ *		If **callback_fn** returns 0, the helper will continue to the next
+ *		loop. If return value is 1, the helper will skip the rest of
+ *		the loops and return. Other return values are not used now,
+ *		and will be rejected by the verifier.
+ *
+ *	Return
+ *		The number of loops performed, **-EINVAL** for invalid **flags**,
+ *		**-E2BIG** if **nr_loops** exceeds the maximum number of loops.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5140,6 +5164,7 @@ union bpf_attr {
 	FN(skc_to_unix_sock),		\
 	FN(kallsyms_lookup_name),	\
 	FN(find_vma),			\
+	FN(loop),			\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 35684d61aaeb..a6c0e92c86a1 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -531,6 +531,7 @@ $(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 \
@@ -540,7 +541,8 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.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 c75e7ee28746..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 },
 	{},
 };
 
@@ -373,6 +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,
@@ -404,6 +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/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/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_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
index 27f5d8ea7964..1fb16f8dad56 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
@@ -115,6 +115,12 @@ 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 +171,12 @@ 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/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/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"