selftests/bpf: Add BPF ringbuf selftests

Both singleton BPF ringbuf and BPF ringbuf with map-in-map use cases are tested.
Also reserve+submit/discards and output variants of API are validated.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20200529075424.3139988-4-andriin@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

tools/testing/selftests/bpf/prog_tests/ringbuf.c

@@ -0,0 +1,211 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+#include <test_progs.h>
+#include <sys/mman.h>
+#include <sys/epoll.h>
+#include <time.h>
+#include <sched.h>
+#include <signal.h>
+#include <pthread.h>
+#include <sys/sysinfo.h>
+#include <linux/perf_event.h>
+#include <linux/ring_buffer.h>
+#include "test_ringbuf.skel.h"
+
+#define EDONE 7777
+
+static int duration = 0;
+
+struct sample {
+	int pid;
+	int seq;
+	long value;
+	char comm[16];
+};
+
+static int sample_cnt;
+
+static int process_sample(void *ctx, void *data, size_t len)
+{
+	struct sample *s = data;
+
+	sample_cnt++;
+
+	switch (s->seq) {
+	case 0:
+		CHECK(s->value != 333, "sample1_value", "exp %ld, got %ld\n",
+		      333L, s->value);
+		return 0;
+	case 1:
+		CHECK(s->value != 777, "sample2_value", "exp %ld, got %ld\n",
+		      777L, s->value);
+		return -EDONE;
+	default:
+		/* we don't care about the rest */
+		return 0;
+	}
+}
+
+static struct test_ringbuf *skel;
+static struct ring_buffer *ringbuf;
+
+static void trigger_samples()
+{
+	skel->bss->dropped = 0;
+	skel->bss->total = 0;
+	skel->bss->discarded = 0;
+
+	/* trigger exactly two samples */
+	skel->bss->value = 333;
+	syscall(__NR_getpgid);
+	skel->bss->value = 777;
+	syscall(__NR_getpgid);
+}
+
+static void *poll_thread(void *input)
+{
+	long timeout = (long)input;
+
+	return (void *)(long)ring_buffer__poll(ringbuf, timeout);
+}
+
+void test_ringbuf(void)
+{
+	const size_t rec_sz = BPF_RINGBUF_HDR_SZ + sizeof(struct sample);
+	pthread_t thread;
+	long bg_ret = -1;
+	int err;
+
+	skel = test_ringbuf__open_and_load();
+	if (CHECK(!skel, "skel_open_load", "skeleton open&load failed\n"))
+		return;
+
+	/* only trigger BPF program for current process */
+	skel->bss->pid = getpid();
+
+	ringbuf = ring_buffer__new(bpf_map__fd(skel->maps.ringbuf),
+				   process_sample, NULL, NULL);
+	if (CHECK(!ringbuf, "ringbuf_create", "failed to create ringbuf\n"))
+		goto cleanup;
+
+	err = test_ringbuf__attach(skel);
+	if (CHECK(err, "skel_attach", "skeleton attachment failed: %d\n", err))
+		goto cleanup;
+
+	trigger_samples();
+
+	/* 2 submitted + 1 discarded records */
+	CHECK(skel->bss->avail_data != 3 * rec_sz,
+	      "err_avail_size", "exp %ld, got %ld\n",
+	      3L * rec_sz, skel->bss->avail_data);
+	CHECK(skel->bss->ring_size != 4096,
+	      "err_ring_size", "exp %ld, got %ld\n",
+	      4096L, skel->bss->ring_size);
+	CHECK(skel->bss->cons_pos != 0,
+	      "err_cons_pos", "exp %ld, got %ld\n",
+	      0L, skel->bss->cons_pos);
+	CHECK(skel->bss->prod_pos != 3 * rec_sz,
+	      "err_prod_pos", "exp %ld, got %ld\n",
+	      3L * rec_sz, skel->bss->prod_pos);
+
+	/* poll for samples */
+	err = ring_buffer__poll(ringbuf, -1);
+
+	/* -EDONE is used as an indicator that we are done */
+	if (CHECK(err != -EDONE, "err_done", "done err: %d\n", err))
+		goto cleanup;
+
+	/* we expect extra polling to return nothing */
+	err = ring_buffer__poll(ringbuf, 0);
+	if (CHECK(err != 0, "extra_samples", "poll result: %d\n", err))
+		goto cleanup;
+
+	CHECK(skel->bss->dropped != 0, "err_dropped", "exp %ld, got %ld\n",
+	      0L, skel->bss->dropped);
+	CHECK(skel->bss->total != 2, "err_total", "exp %ld, got %ld\n",
+	      2L, skel->bss->total);
+	CHECK(skel->bss->discarded != 1, "err_discarded", "exp %ld, got %ld\n",
+	      1L, skel->bss->discarded);
+
+	/* now validate consumer position is updated and returned */
+	trigger_samples();
+	CHECK(skel->bss->cons_pos != 3 * rec_sz,
+	      "err_cons_pos", "exp %ld, got %ld\n",
+	      3L * rec_sz, skel->bss->cons_pos);
+	err = ring_buffer__poll(ringbuf, -1);
+	CHECK(err <= 0, "poll_err", "err %d\n", err);
+
+	/* start poll in background w/ long timeout */
+	err = pthread_create(&thread, NULL, poll_thread, (void *)(long)10000);
+	if (CHECK(err, "bg_poll", "pthread_create failed: %d\n", err))
+		goto cleanup;
+
+	/* turn off notifications now */
+	skel->bss->flags = BPF_RB_NO_WAKEUP;
+
+	/* give background thread a bit of a time */
+	usleep(50000);
+	trigger_samples();
+	/* sleeping arbitrarily is bad, but no better way to know that
+	 * epoll_wait() **DID NOT** unblock in background thread
+	 */
+	usleep(50000);
+	/* background poll should still be blocked */
+	err = pthread_tryjoin_np(thread, (void **)&bg_ret);
+	if (CHECK(err != EBUSY, "try_join", "err %d\n", err))
+		goto cleanup;
+
+	/* BPF side did everything right */
+	CHECK(skel->bss->dropped != 0, "err_dropped", "exp %ld, got %ld\n",
+	      0L, skel->bss->dropped);
+	CHECK(skel->bss->total != 2, "err_total", "exp %ld, got %ld\n",
+	      2L, skel->bss->total);
+	CHECK(skel->bss->discarded != 1, "err_discarded", "exp %ld, got %ld\n",
+	      1L, skel->bss->discarded);
+
+	/* clear flags to return to "adaptive" notification mode */
+	skel->bss->flags = 0;
+
+	/* produce new samples, no notification should be triggered, because
+	 * consumer is now behind
+	 */
+	trigger_samples();
+
+	/* background poll should still be blocked */
+	err = pthread_tryjoin_np(thread, (void **)&bg_ret);
+	if (CHECK(err != EBUSY, "try_join", "err %d\n", err))
+		goto cleanup;
+
+	/* now force notifications */
+	skel->bss->flags = BPF_RB_FORCE_WAKEUP;
+	sample_cnt = 0;
+	trigger_samples();
+
+	/* now we should get a pending notification */
+	usleep(50000);
+	err = pthread_tryjoin_np(thread, (void **)&bg_ret);
+	if (CHECK(err, "join_bg", "err %d\n", err))
+		goto cleanup;
+
+	if (CHECK(bg_ret != 1, "bg_ret", "epoll_wait result: %ld", bg_ret))
+		goto cleanup;
+
+	/* 3 rounds, 2 samples each */
+	CHECK(sample_cnt != 6, "wrong_sample_cnt",
+	      "expected to see %d samples, got %d\n", 6, sample_cnt);
+
+	/* BPF side did everything right */
+	CHECK(skel->bss->dropped != 0, "err_dropped", "exp %ld, got %ld\n",
+	      0L, skel->bss->dropped);
+	CHECK(skel->bss->total != 2, "err_total", "exp %ld, got %ld\n",
+	      2L, skel->bss->total);
+	CHECK(skel->bss->discarded != 1, "err_discarded", "exp %ld, got %ld\n",
+	      1L, skel->bss->discarded);
+
+	test_ringbuf__detach(skel);
+cleanup:
+	ring_buffer__free(ringbuf);
+	test_ringbuf__destroy(skel);
+}

tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c

@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <test_progs.h>
+#include <sys/epoll.h>
+#include "test_ringbuf_multi.skel.h"
+
+static int duration = 0;
+
+struct sample {
+	int pid;
+	int seq;
+	long value;
+	char comm[16];
+};
+
+static int process_sample(void *ctx, void *data, size_t len)
+{
+	int ring = (unsigned long)ctx;
+	struct sample *s = data;
+
+	switch (s->seq) {
+	case 0:
+		CHECK(ring != 1, "sample1_ring", "exp %d, got %d\n", 1, ring);
+		CHECK(s->value != 333, "sample1_value", "exp %ld, got %ld\n",
+		      333L, s->value);
+		break;
+	case 1:
+		CHECK(ring != 2, "sample2_ring", "exp %d, got %d\n", 2, ring);
+		CHECK(s->value != 777, "sample2_value", "exp %ld, got %ld\n",
+		      777L, s->value);
+		break;
+	default:
+		CHECK(true, "extra_sample", "unexpected sample seq %d, val %ld\n",
+		      s->seq, s->value);
+		return -1;
+	}
+
+	return 0;
+}
+
+void test_ringbuf_multi(void)
+{
+	struct test_ringbuf_multi *skel;
+	struct ring_buffer *ringbuf;
+	int err;
+
+	skel = test_ringbuf_multi__open_and_load();
+	if (CHECK(!skel, "skel_open_load", "skeleton open&load failed\n"))
+		return;
+
+	/* only trigger BPF program for current process */
+	skel->bss->pid = getpid();
+
+	ringbuf = ring_buffer__new(bpf_map__fd(skel->maps.ringbuf1),
+				   process_sample, (void *)(long)1, NULL);
+	if (CHECK(!ringbuf, "ringbuf_create", "failed to create ringbuf\n"))
+		goto cleanup;
+
+	err = ring_buffer__add(ringbuf, bpf_map__fd(skel->maps.ringbuf2),
+			      process_sample, (void *)(long)2);
+	if (CHECK(err, "ringbuf_add", "failed to add another ring\n"))
+		goto cleanup;
+
+	err = test_ringbuf_multi__attach(skel);
+	if (CHECK(err, "skel_attach", "skeleton attachment failed: %d\n", err))
+		goto cleanup;
+
+	/* trigger few samples, some will be skipped */
+	skel->bss->target_ring = 0;
+	skel->bss->value = 333;
+	syscall(__NR_getpgid);
+
+	/* skipped, no ringbuf in slot 1 */
+	skel->bss->target_ring = 1;
+	skel->bss->value = 555;
+	syscall(__NR_getpgid);
+
+	skel->bss->target_ring = 2;
+	skel->bss->value = 777;
+	syscall(__NR_getpgid);
+
+	/* poll for samples, should get 2 ringbufs back */
+	err = ring_buffer__poll(ringbuf, -1);
+	if (CHECK(err != 4, "poll_res", "expected 4 records, got %d\n", err))
+		goto cleanup;
+
+	/* expect extra polling to return nothing */
+	err = ring_buffer__poll(ringbuf, 0);
+	if (CHECK(err < 0, "extra_samples", "poll result: %d\n", err))
+		goto cleanup;
+
+	CHECK(skel->bss->dropped != 0, "err_dropped", "exp %ld, got %ld\n",
+	      0L, skel->bss->dropped);
+	CHECK(skel->bss->skipped != 1, "err_skipped", "exp %ld, got %ld\n",
+	      1L, skel->bss->skipped);
+	CHECK(skel->bss->total != 2, "err_total", "exp %ld, got %ld\n",
+	      2L, skel->bss->total);
+
+cleanup:
+	ring_buffer__free(ringbuf);
+	test_ringbuf_multi__destroy(skel);
+}

tools/testing/selftests/bpf/progs/test_ringbuf.c

@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct sample {
+	int pid;
+	int seq;
+	long value;
+	char comm[16];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_RINGBUF);
+	__uint(max_entries, 1 << 12);
+} ringbuf SEC(".maps");
+
+/* inputs */
+int pid = 0;
+long value = 0;
+long flags = 0;
+
+/* outputs */
+long total = 0;
+long discarded = 0;
+long dropped = 0;
+
+long avail_data = 0;
+long ring_size = 0;
+long cons_pos = 0;
+long prod_pos = 0;
+
+/* inner state */
+long seq = 0;
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int test_ringbuf(void *ctx)
+{
+	int cur_pid = bpf_get_current_pid_tgid() >> 32;
+	struct sample *sample;
+	int zero = 0;
+
+	if (cur_pid != pid)
+		return 0;
+
+	sample = bpf_ringbuf_reserve(&ringbuf, sizeof(*sample), 0);
+	if (!sample) {
+		__sync_fetch_and_add(&dropped, 1);
+		return 1;
+	}
+
+	sample->pid = pid;
+	bpf_get_current_comm(sample->comm, sizeof(sample->comm));
+	sample->value = value;
+
+	sample->seq = seq++;
+	__sync_fetch_and_add(&total, 1);
+
+	if (sample->seq & 1) {
+		/* copy from reserved sample to a new one... */
+		bpf_ringbuf_output(&ringbuf, sample, sizeof(*sample), flags);
+		/* ...and then discard reserved sample */
+		bpf_ringbuf_discard(sample, flags);
+		__sync_fetch_and_add(&discarded, 1);
+	} else {
+		bpf_ringbuf_submit(sample, flags);
+	}
+
+	avail_data = bpf_ringbuf_query(&ringbuf, BPF_RB_AVAIL_DATA);
+	ring_size = bpf_ringbuf_query(&ringbuf, BPF_RB_RING_SIZE);
+	cons_pos = bpf_ringbuf_query(&ringbuf, BPF_RB_CONS_POS);
+	prod_pos = bpf_ringbuf_query(&ringbuf, BPF_RB_PROD_POS);
+
+	return 0;
+}

tools/testing/selftests/bpf/progs/test_ringbuf_multi.c

@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct sample {
+	int pid;
+	int seq;
+	long value;
+	char comm[16];
+};
+
+struct ringbuf_map {
+	__uint(type, BPF_MAP_TYPE_RINGBUF);
+	__uint(max_entries, 1 << 12);
+} ringbuf1 SEC(".maps"),
+  ringbuf2 SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__uint(max_entries, 4);
+	__type(key, int);
+	__array(values, struct ringbuf_map);
+} ringbuf_arr SEC(".maps") = {
+	.values = {
+		[0] = &ringbuf1,
+		[2] = &ringbuf2,
+	},
+};
+
+/* inputs */
+int pid = 0;
+int target_ring = 0;
+long value = 0;
+
+/* outputs */
+long total = 0;
+long dropped = 0;
+long skipped = 0;
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int test_ringbuf(void *ctx)
+{
+	int cur_pid = bpf_get_current_pid_tgid() >> 32;
+	struct sample *sample;
+	void *rb;
+	int zero = 0;
+
+	if (cur_pid != pid)
+		return 0;
+
+	rb = bpf_map_lookup_elem(&ringbuf_arr, &target_ring);
+	if (!rb) {
+		skipped += 1;
+		return 1;
+	}
+
+	sample = bpf_ringbuf_reserve(rb, sizeof(*sample), 0);
+	if (!sample) {
+		dropped += 1;
+		return 1;
+	}
+
+	sample->pid = pid;
+	bpf_get_current_comm(sample->comm, sizeof(sample->comm));
+	sample->value = value;
+
+	sample->seq = total;
+	total += 1;
+
+	bpf_ringbuf_submit(sample, 0);
+
+	return 0;
+}