Merge branch 'bpf-ring-buffer'

Andrii Nakryiko says:

====================
Implement a new BPF ring buffer, as presented at BPF virtual conference ([0]).
It presents an alternative to perf buffer, following its semantics closely,
but allowing sharing same instance of ring buffer across multiple CPUs
efficiently.

Most patches have extensive commentary explaining various aspects, so I'll
keep cover letter short. Overall structure of the patch set:
- patch #1 adds BPF ring buffer implementation to kernel and necessary
  verifier support;
- patch #2 adds libbpf consumer implementation for BPF ringbuf;
- patch #3 adds selftest, both for single BPF ring buf use case, as well as
  using it with array/hash of maps;
- patch #4 adds extensive benchmarks and provide some analysis in commit
  message, it builds upon selftests/bpf's bench runner.
- patch #5 adds most of patch #1 commit message as a doc under
  Documentation/bpf/ringbuf.rst.

Litmus tests, validating consumer/producer protocols and memory orderings,
were moved out as discussed in [1] and are going to be posted against -rcu
tree and put under Documentation/litmus-tests/bpf-rb.

  [0] https://docs.google.com/presentation/d/18ITdg77Bj6YDOH2LghxrnFxiPWe0fAqcmJY95t_qr0w
  [1] https://lkml.org/lkml/2020/5/22/1011

v3->v4:
- fix ringbuf freeing (vunmap, __free_page); verified with a trivial loop
  creating and closing ringbuf map endlessly (Daniel);

v2->v3:
- dropped unnecessary smp_wmb() (Paul);
- verifier reference type enhancement patch was dropped (Alexei);
- better verifier message for various memory access checks (Alexei);
- clarified a bit roundup_len() bit shifting (Alexei);
- converted doc to .rst (Alexei);
- fixed warning on 32-bit arches regarding tautological ring area size check.

v1->v2:
- commit()/discard()/output() accept flags (NO_WAKEUP/FORCE_WAKEUP) (Stanislav);
- bpf_ringbuf_query() added, returning available data size, ringbuf size,
  consumer/producer positions, needed to implement smarter notification policy
  (Stanislav);
- added ringbuf UAPI constants to include/uapi/linux/bpf.h (Jonathan);
- fixed sample size check, added proper ringbuf size check (Jonathan, Alexei);
- wake_up_all() is done through irq_work (Alexei);
- consistent use of smp_load_acquire/smp_store_release, no
  READ_ONCE/WRITE_ONCE (Alexei);
- added Documentation/bpf/ringbuf.txt (Stanislav);
- updated litmus test with smp_load_acquire/smp_store_release changes;
- added ring_buffer__consume() API to libbpf for busy-polling;
- ring_buffer__poll() on success returns number of records consumed;
- fixed EPOLL notifications, don't assume available data, done similarly to
  perfbuf's implementation;
- both ringbuf and perfbuf now have --rb-sampled mode, instead of
  pb-raw/pb-custom mode, updated benchmark results;
- extended ringbuf selftests to validate epoll logic/manual notification
  logic, as well as bpf_ringbuf_query().
====================

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

24 files changed, 1640 insertions, 21 deletions

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 54b93f8b49b8..974ca6e948e3 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -147,6 +147,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_SK_STORAGE,
 	BPF_MAP_TYPE_DEVMAP_HASH,
 	BPF_MAP_TYPE_STRUCT_OPS,
+	BPF_MAP_TYPE_RINGBUF,
 };
 
 /* Note that tracing related programs such as
@@ -3157,6 +3158,59 @@ union bpf_attr {
  *		**bpf_sk_cgroup_id**\ ().
  *	Return
  *		The id is returned or 0 in case the id could not be retrieved.
+ *
+ * void *bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags)
+ * 	Description
+ * 		Copy *size* bytes from *data* into a ring buffer *ringbuf*.
+ * 		If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of
+ * 		new data availability is sent.
+ * 		IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of
+ * 		new data availability is sent unconditionally.
+ * 	Return
+ * 		0, on success;
+ * 		< 0, on error.
+ *
+ * void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags)
+ * 	Description
+ * 		Reserve *size* bytes of payload in a ring buffer *ringbuf*.
+ * 	Return
+ * 		Valid pointer with *size* bytes of memory available; NULL,
+ * 		otherwise.
+ *
+ * void bpf_ringbuf_submit(void *data, u64 flags)
+ * 	Description
+ * 		Submit reserved ring buffer sample, pointed to by *data*.
+ * 		If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of
+ * 		new data availability is sent.
+ * 		IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of
+ * 		new data availability is sent unconditionally.
+ * 	Return
+ * 		Nothing. Always succeeds.
+ *
+ * void bpf_ringbuf_discard(void *data, u64 flags)
+ * 	Description
+ * 		Discard reserved ring buffer sample, pointed to by *data*.
+ * 		If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of
+ * 		new data availability is sent.
+ * 		IF BPF_RB_FORCE_WAKEUP is specified in *flags*, notification of
+ * 		new data availability is sent unconditionally.
+ * 	Return
+ * 		Nothing. Always succeeds.
+ *
+ * u64 bpf_ringbuf_query(void *ringbuf, u64 flags)
+ *	Description
+ *		Query various characteristics of provided ring buffer. What
+ *		exactly is queries is determined by *flags*:
+ *		  - BPF_RB_AVAIL_DATA - amount of data not yet consumed;
+ *		  - BPF_RB_RING_SIZE - the size of ring buffer;
+ *		  - BPF_RB_CONS_POS - consumer position (can wrap around);
+ *		  - BPF_RB_PROD_POS - producer(s) position (can wrap around);
+ *		Data returned is just a momentary snapshots of actual values
+ *		and could be inaccurate, so this facility should be used to
+ *		power heuristics and for reporting, not to make 100% correct
+ *		calculation.
+ *	Return
+ *		Requested value, or 0, if flags are not recognized.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3288,7 +3342,12 @@ union bpf_attr {
 	FN(seq_printf),			\
 	FN(seq_write),			\
 	FN(sk_cgroup_id),		\
-	FN(sk_ancestor_cgroup_id),
+	FN(sk_ancestor_cgroup_id),	\
+	FN(ringbuf_output),		\
+	FN(ringbuf_reserve),		\
+	FN(ringbuf_submit),		\
+	FN(ringbuf_discard),		\
+	FN(ringbuf_query),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -3398,6 +3457,29 @@ enum {
 	BPF_F_GET_BRANCH_RECORDS_SIZE	= (1ULL << 0),
 };
 
+/* BPF_FUNC_bpf_ringbuf_commit, BPF_FUNC_bpf_ringbuf_discard, and
+ * BPF_FUNC_bpf_ringbuf_output flags.
+ */
+enum {
+	BPF_RB_NO_WAKEUP		= (1ULL << 0),
+	BPF_RB_FORCE_WAKEUP		= (1ULL << 1),
+};
+
+/* BPF_FUNC_bpf_ringbuf_query flags */
+enum {
+	BPF_RB_AVAIL_DATA = 0,
+	BPF_RB_RING_SIZE = 1,
+	BPF_RB_CONS_POS = 2,
+	BPF_RB_PROD_POS = 3,
+};
+
+/* BPF ring buffer constants */
+enum {
+	BPF_RINGBUF_BUSY_BIT		= (1U << 31),
+	BPF_RINGBUF_DISCARD_BIT		= (1U << 30),
+	BPF_RINGBUF_HDR_SZ		= 8,
+};
+
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
 	BPF_ADJ_ROOM_NET,
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index e3962cfbc9a6..190366d05588 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1,3 +1,3 @@
 libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \
 	    netlink.o bpf_prog_linfo.o libbpf_probes.o xsk.o hashmap.o \
-	    btf_dump.o
+	    btf_dump.o ringbuf.o
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 1e2e399a5f2c..8528a02d5af8 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -478,6 +478,27 @@ LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags);
 LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
 				     size_t info_size, __u32 flags);
 
+/* Ring buffer APIs */
+struct ring_buffer;
+
+typedef int (*ring_buffer_sample_fn)(void *ctx, void *data, size_t size);
+
+struct ring_buffer_opts {
+	size_t sz; /* size of this struct, for forward/backward compatiblity */
+};
+
+#define ring_buffer_opts__last_field sz
+
+LIBBPF_API struct ring_buffer *
+ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx,
+		 const struct ring_buffer_opts *opts);
+LIBBPF_API void ring_buffer__free(struct ring_buffer *rb);
+LIBBPF_API int ring_buffer__add(struct ring_buffer *rb, int map_fd,
+				ring_buffer_sample_fn sample_cb, void *ctx);
+LIBBPF_API int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms);
+LIBBPF_API int ring_buffer__consume(struct ring_buffer *rb);
+
+/* Perf buffer APIs */
 struct perf_buffer;
 
 typedef void (*perf_buffer_sample_fn)(void *ctx, int cpu,
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 381a7342ecfc..c18860200abb 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -263,4 +263,9 @@ LIBBPF_0.0.9 {
 		bpf_link_get_next_id;
 		bpf_program__attach_iter;
 		perf_buffer__consume;
+		ring_buffer__add;
+		ring_buffer__consume;
+		ring_buffer__free;
+		ring_buffer__new;
+		ring_buffer__poll;
 } LIBBPF_0.0.8;
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index 2c92059c0c90..10cd8d1891f5 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -238,6 +238,11 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 		if (btf_fd < 0)
 			return false;
 		break;
+	case BPF_MAP_TYPE_RINGBUF:
+		key_size = 0;
+		value_size = 0;
+		max_entries = 4096;
+		break;
 	case BPF_MAP_TYPE_UNSPEC:
 	case BPF_MAP_TYPE_HASH:
 	case BPF_MAP_TYPE_ARRAY:
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
new file mode 100644
index 000000000000..bc10fa1d43c7
--- /dev/null
+++ b/tools/lib/bpf/ringbuf.c
@@ -0,0 +1,285 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/*
+ * Ring buffer operations.
+ *
+ * Copyright (C) 2020 Facebook, Inc.
+ */
+#include <stdlib.h>
+#include <stdio.h>
+#include <errno.h>
+#include <unistd.h>
+#include <linux/err.h>
+#include <linux/bpf.h>
+#include <asm/barrier.h>
+#include <sys/mman.h>
+#include <sys/epoll.h>
+#include <tools/libc_compat.h>
+
+#include "libbpf.h"
+#include "libbpf_internal.h"
+#include "bpf.h"
+
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
+struct ring {
+	ring_buffer_sample_fn sample_cb;
+	void *ctx;
+	void *data;
+	unsigned long *consumer_pos;
+	unsigned long *producer_pos;
+	unsigned long mask;
+	int map_fd;
+};
+
+struct ring_buffer {
+	struct epoll_event *events;
+	struct ring *rings;
+	size_t page_size;
+	int epoll_fd;
+	int ring_cnt;
+};
+
+static void ringbuf_unmap_ring(struct ring_buffer *rb, struct ring *r)
+{
+	if (r->consumer_pos) {
+		munmap(r->consumer_pos, rb->page_size);
+		r->consumer_pos = NULL;
+	}
+	if (r->producer_pos) {
+		munmap(r->producer_pos, rb->page_size + 2 * (r->mask + 1));
+		r->producer_pos = NULL;
+	}
+}
+
+/* Add extra RINGBUF maps to this ring buffer manager */
+int ring_buffer__add(struct ring_buffer *rb, int map_fd,
+		     ring_buffer_sample_fn sample_cb, void *ctx)
+{
+	struct bpf_map_info info;
+	__u32 len = sizeof(info);
+	struct epoll_event *e;
+	struct ring *r;
+	void *tmp;
+	int err;
+
+	memset(&info, 0, sizeof(info));
+
+	err = bpf_obj_get_info_by_fd(map_fd, &info, &len);
+	if (err) {
+		err = -errno;
+		pr_warn("ringbuf: failed to get map info for fd=%d: %d\n",
+			map_fd, err);
+		return err;
+	}
+
+	if (info.type != BPF_MAP_TYPE_RINGBUF) {
+		pr_warn("ringbuf: map fd=%d is not BPF_MAP_TYPE_RINGBUF\n",
+			map_fd);
+		return -EINVAL;
+	}
+
+	tmp = reallocarray(rb->rings, rb->ring_cnt + 1, sizeof(*rb->rings));
+	if (!tmp)
+		return -ENOMEM;
+	rb->rings = tmp;
+
+	tmp = reallocarray(rb->events, rb->ring_cnt + 1, sizeof(*rb->events));
+	if (!tmp)
+		return -ENOMEM;
+	rb->events = tmp;
+
+	r = &rb->rings[rb->ring_cnt];
+	memset(r, 0, sizeof(*r));
+
+	r->map_fd = map_fd;
+	r->sample_cb = sample_cb;
+	r->ctx = ctx;
+	r->mask = info.max_entries - 1;
+
+	/* Map writable consumer page */
+	tmp = mmap(NULL, rb->page_size, PROT_READ | PROT_WRITE, MAP_SHARED,
+		   map_fd, 0);
+	if (tmp == MAP_FAILED) {
+		err = -errno;
+		pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %d\n",
+			map_fd, err);
+		return err;
+	}
+	r->consumer_pos = tmp;
+
+	/* Map read-only producer page and data pages. We map twice as big
+	 * data size to allow simple reading of samples that wrap around the
+	 * end of a ring buffer. See kernel implementation for details.
+	 * */
+	tmp = mmap(NULL, rb->page_size + 2 * info.max_entries, PROT_READ,
+		   MAP_SHARED, map_fd, rb->page_size);
+	if (tmp == MAP_FAILED) {
+		err = -errno;
+		ringbuf_unmap_ring(rb, r);
+		pr_warn("ringbuf: failed to mmap data pages for map fd=%d: %d\n",
+			map_fd, err);
+		return err;
+	}
+	r->producer_pos = tmp;
+	r->data = tmp + rb->page_size;
+
+	e = &rb->events[rb->ring_cnt];
+	memset(e, 0, sizeof(*e));
+
+	e->events = EPOLLIN;
+	e->data.fd = rb->ring_cnt;
+	if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, e) < 0) {
+		err = -errno;
+		ringbuf_unmap_ring(rb, r);
+		pr_warn("ringbuf: failed to epoll add map fd=%d: %d\n",
+			map_fd, err);
+		return err;
+	}
+
+	rb->ring_cnt++;
+	return 0;
+}
+
+void ring_buffer__free(struct ring_buffer *rb)
+{
+	int i;
+
+	if (!rb)
+		return;
+
+	for (i = 0; i < rb->ring_cnt; ++i)
+		ringbuf_unmap_ring(rb, &rb->rings[i]);
+	if (rb->epoll_fd >= 0)
+		close(rb->epoll_fd);
+
+	free(rb->events);
+	free(rb->rings);
+	free(rb);
+}
+
+struct ring_buffer *
+ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx,
+		 const struct ring_buffer_opts *opts)
+{
+	struct ring_buffer *rb;
+	int err;
+
+	if (!OPTS_VALID(opts, ring_buffer_opts))
+		return NULL;
+
+	rb = calloc(1, sizeof(*rb));
+	if (!rb)
+		return NULL;
+
+	rb->page_size = getpagesize();
+
+	rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC);
+	if (rb->epoll_fd < 0) {
+		err = -errno;
+		pr_warn("ringbuf: failed to create epoll instance: %d\n", err);
+		goto err_out;
+	}
+
+	err = ring_buffer__add(rb, map_fd, sample_cb, ctx);
+	if (err)
+		goto err_out;
+
+	return rb;
+
+err_out:
+	ring_buffer__free(rb);
+	return NULL;
+}
+
+static inline int roundup_len(__u32 len)
+{
+	/* clear out top 2 bits (discard and busy, if set) */
+	len <<= 2;
+	len >>= 2;
+	/* add length prefix */
+	len += BPF_RINGBUF_HDR_SZ;
+	/* round up to 8 byte alignment */
+	return (len + 7) / 8 * 8;
+}
+
+static int ringbuf_process_ring(struct ring* r)
+{
+	int *len_ptr, len, err, cnt = 0;
+	unsigned long cons_pos, prod_pos;
+	bool got_new_data;
+	void *sample;
+
+	cons_pos = smp_load_acquire(r->consumer_pos);
+	do {
+		got_new_data = false;
+		prod_pos = smp_load_acquire(r->producer_pos);
+		while (cons_pos < prod_pos) {
+			len_ptr = r->data + (cons_pos & r->mask);
+			len = smp_load_acquire(len_ptr);
+
+			/* sample not committed yet, bail out for now */
+			if (len & BPF_RINGBUF_BUSY_BIT)
+				goto done;
+
+			got_new_data = true;
+			cons_pos += roundup_len(len);
+
+			if ((len & BPF_RINGBUF_DISCARD_BIT) == 0) {
+				sample = (void *)len_ptr + BPF_RINGBUF_HDR_SZ;
+				err = r->sample_cb(r->ctx, sample, len);
+				if (err) {
+					/* update consumer pos and bail out */
+					smp_store_release(r->consumer_pos,
+							  cons_pos);
+					return err;
+				}
+				cnt++;
+			}
+
+			smp_store_release(r->consumer_pos, cons_pos);
+		}
+	} while (got_new_data);
+done:
+	return cnt;
+}
+
+/* Consume available ring buffer(s) data without event polling.
+ * Returns number of records consumed across all registered ring buffers, or
+ * negative number if any of the callbacks return error.
+ */
+int ring_buffer__consume(struct ring_buffer *rb)
+{
+	int i, err, res = 0;
+
+	for (i = 0; i < rb->ring_cnt; i++) {
+		struct ring *ring = &rb->rings[i];
+
+		err = ringbuf_process_ring(ring);
+		if (err < 0)
+			return err;
+		res += err;
+	}
+	return res;
+}
+
+/* Poll for available data and consume records, if any are available.
+ * Returns number of records consumed, or negative number, if any of the
+ * registered callbacks returned error.
+ */
+int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms)
+{
+	int i, cnt, err, res = 0;
+
+	cnt = epoll_wait(rb->epoll_fd, rb->events, rb->ring_cnt, timeout_ms);
+	for (i = 0; i < cnt; i++) {
+		__u32 ring_id = rb->events[i].data.fd;
+		struct ring *ring = &rb->rings[ring_id];
+
+		err = ringbuf_process_ring(ring);
+		if (err < 0)
+			return err;
+		res += cnt;
+	}
+	return cnt < 0 ? -errno : res;
+}
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index e716e931d0c9..3ce548eff8a8 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -413,12 +413,15 @@ $(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h
 	$(CC) $(CFLAGS) -c $(filter %.c,$^) $(LDLIBS) -o $@
 $(OUTPUT)/bench_rename.o: $(OUTPUT)/test_overhead.skel.h
 $(OUTPUT)/bench_trigger.o: $(OUTPUT)/trigger_bench.skel.h
+$(OUTPUT)/bench_ringbufs.o: $(OUTPUT)/ringbuf_bench.skel.h \
+			    $(OUTPUT)/perfbuf_bench.skel.h
 $(OUTPUT)/bench.o: bench.h testing_helpers.h
 $(OUTPUT)/bench: LDLIBS += -lm
 $(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \
 		 $(OUTPUT)/bench_count.o \
 		 $(OUTPUT)/bench_rename.o \
-		 $(OUTPUT)/bench_trigger.o
+		 $(OUTPUT)/bench_trigger.o \
+		 $(OUTPUT)/bench_ringbufs.o
 	$(call msg,BINARY,,$@)
 	$(CC) $(LDFLAGS) -o $@ $(filter %.a %.o,$^) $(LDLIBS)
 
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index 14390689ef90..944ad4721c83 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -130,6 +130,13 @@ static const struct argp_option opts[] = {
 	{},
 };
 
+extern struct argp bench_ringbufs_argp;
+
+static const struct argp_child bench_parsers[] = {
+	{ &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 },
+	{},
+};
+
 static error_t parse_arg(int key, char *arg, struct argp_state *state)
 {
 	static int pos_args;
@@ -208,6 +215,7 @@ static void parse_cmdline_args(int argc, char **argv)
 		.options = opts,
 		.parser = parse_arg,
 		.doc = argp_program_doc,
+		.children = bench_parsers,
 	};
 	if (argp_parse(&argp, argc, argv, 0, NULL, NULL))
 		exit(1);
@@ -310,6 +318,10 @@ extern const struct bench bench_trig_rawtp;
 extern const struct bench bench_trig_kprobe;
 extern const struct bench bench_trig_fentry;
 extern const struct bench bench_trig_fmodret;
+extern const struct bench bench_rb_libbpf;
+extern const struct bench bench_rb_custom;
+extern const struct bench bench_pb_libbpf;
+extern const struct bench bench_pb_custom;
 
 static const struct bench *benchs[] = {
 	&bench_count_global,
@@ -327,6 +339,10 @@ static const struct bench *benchs[] = {
 	&bench_trig_kprobe,
 	&bench_trig_fentry,
 	&bench_trig_fmodret,
+	&bench_rb_libbpf,
+	&bench_rb_custom,
+	&bench_pb_libbpf,
+	&bench_pb_custom,
 };
 
 static void setup_benchmark()
diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
new file mode 100644
index 000000000000..da87c7f31891
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
@@ -0,0 +1,566 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <asm/barrier.h>
+#include <linux/perf_event.h>
+#include <linux/ring_buffer.h>
+#include <sys/epoll.h>
+#include <sys/mman.h>
+#include <argp.h>
+#include <stdlib.h>
+#include "bench.h"
+#include "ringbuf_bench.skel.h"
+#include "perfbuf_bench.skel.h"
+
+static struct {
+	bool back2back;
+	int batch_cnt;
+	bool sampled;
+	int sample_rate;
+	int ringbuf_sz; /* per-ringbuf, in bytes */
+	bool ringbuf_use_output; /* use slower output API */
+	int perfbuf_sz; /* per-CPU size, in pages */
+} args = {
+	.back2back = false,
+	.batch_cnt = 500,
+	.sampled = false,
+	.sample_rate = 500,
+	.ringbuf_sz = 512 * 1024,
+	.ringbuf_use_output = false,
+	.perfbuf_sz = 128,
+};
+
+enum {
+	ARG_RB_BACK2BACK = 2000,
+	ARG_RB_USE_OUTPUT = 2001,
+	ARG_RB_BATCH_CNT = 2002,
+	ARG_RB_SAMPLED = 2003,
+	ARG_RB_SAMPLE_RATE = 2004,
+};
+
+static const struct argp_option opts[] = {
+	{ "rb-b2b", ARG_RB_BACK2BACK, NULL, 0, "Back-to-back mode"},
+	{ "rb-use-output", ARG_RB_USE_OUTPUT, NULL, 0, "Use bpf_ringbuf_output() instead of bpf_ringbuf_reserve()"},
+	{ "rb-batch-cnt", ARG_RB_BATCH_CNT, "CNT", 0, "Set BPF-side record batch count"},
+	{ "rb-sampled", ARG_RB_SAMPLED, NULL, 0, "Notification sampling"},
+	{ "rb-sample-rate", ARG_RB_SAMPLE_RATE, "RATE", 0, "Notification sample rate"},
+	{},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+	switch (key) {
+	case ARG_RB_BACK2BACK:
+		args.back2back = true;
+		break;
+	case ARG_RB_USE_OUTPUT:
+		args.ringbuf_use_output = true;
+		break;
+	case ARG_RB_BATCH_CNT:
+		args.batch_cnt = strtol(arg, NULL, 10);
+		if (args.batch_cnt < 0) {
+			fprintf(stderr, "Invalid batch count.");
+			argp_usage(state);
+		}
+		break;
+	case ARG_RB_SAMPLED:
+		args.sampled = true;
+		break;
+	case ARG_RB_SAMPLE_RATE:
+		args.sample_rate = strtol(arg, NULL, 10);
+		if (args.sample_rate < 0) {
+			fprintf(stderr, "Invalid perfbuf sample rate.");
+			argp_usage(state);
+		}
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+	return 0;
+}
+
+/* exported into benchmark runner */
+const struct argp bench_ringbufs_argp = {
+	.options = opts,
+	.parser = parse_arg,
+};
+
+/* RINGBUF-LIBBPF benchmark */
+
+static struct counter buf_hits;
+
+static inline void bufs_trigger_batch()
+{
+	(void)syscall(__NR_getpgid);
+}
+
+static void bufs_validate()
+{
+	if (env.consumer_cnt != 1) {
+		fprintf(stderr, "rb-libbpf benchmark doesn't support multi-consumer!\n");
+		exit(1);
+	}
+
+	if (args.back2back && env.producer_cnt > 1) {
+		fprintf(stderr, "back-to-back mode makes sense only for single-producer case!\n");
+		exit(1);
+	}
+}
+
+static void *bufs_sample_producer(void *input)
+{
+	if (args.back2back) {
+		/* initial batch to get everything started */
+		bufs_trigger_batch();
+		return NULL;
+	}
+
+	while (true)
+		bufs_trigger_batch();
+	return NULL;
+}
+
+static struct ringbuf_libbpf_ctx {
+	struct ringbuf_bench *skel;
+	struct ring_buffer *ringbuf;
+} ringbuf_libbpf_ctx;
+
+static void ringbuf_libbpf_measure(struct bench_res *res)
+{
+	struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx;
+
+	res->hits = atomic_swap(&buf_hits.value, 0);
+	res->drops = atomic_swap(&ctx->skel->bss->dropped, 0);
+}
+
+static struct ringbuf_bench *ringbuf_setup_skeleton()
+{
+	struct ringbuf_bench *skel;
+
+	setup_libbpf();
+
+	skel = ringbuf_bench__open();
+	if (!skel) {
+		fprintf(stderr, "failed to open skeleton\n");
+		exit(1);
+	}
+
+	skel->rodata->batch_cnt = args.batch_cnt;
+	skel->rodata->use_output = args.ringbuf_use_output ? 1 : 0;
+
+	if (args.sampled)
+		/* record data + header take 16 bytes */
+		skel->rodata->wakeup_data_size = args.sample_rate * 16;
+
+	bpf_map__resize(skel->maps.ringbuf, args.ringbuf_sz);
+
+	if (ringbuf_bench__load(skel)) {
+		fprintf(stderr, "failed to load skeleton\n");
+		exit(1);
+	}
+
+	return skel;
+}
+
+static int buf_process_sample(void *ctx, void *data, size_t len)
+{
+	atomic_inc(&buf_hits.value);
+	return 0;
+}
+
+static void ringbuf_libbpf_setup()
+{
+	struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx;
+	struct bpf_link *link;
+
+	ctx->skel = ringbuf_setup_skeleton();
+	ctx->ringbuf = ring_buffer__new(bpf_map__fd(ctx->skel->maps.ringbuf),
+					buf_process_sample, NULL, NULL);
+	if (!ctx->ringbuf) {
+		fprintf(stderr, "failed to create ringbuf\n");
+		exit(1);
+	}
+
+	link = bpf_program__attach(ctx->skel->progs.bench_ringbuf);
+	if (IS_ERR(link)) {
+		fprintf(stderr, "failed to attach program!\n");
+		exit(1);
+	}
+}
+
+static void *ringbuf_libbpf_consumer(void *input)
+{
+	struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx;
+
+	while (ring_buffer__poll(ctx->ringbuf, -1) >= 0) {
+		if (args.back2back)
+			bufs_trigger_batch();
+	}
+	fprintf(stderr, "ringbuf polling failed!\n");
+	return NULL;
+}
+
+/* RINGBUF-CUSTOM benchmark */
+struct ringbuf_custom {
+	__u64 *consumer_pos;
+	__u64 *producer_pos;
+	__u64 mask;
+	void *data;
+	int map_fd;
+};
+
+static struct ringbuf_custom_ctx {
+	struct ringbuf_bench *skel;
+	struct ringbuf_custom ringbuf;
+	int epoll_fd;
+	struct epoll_event event;
+} ringbuf_custom_ctx;
+
+static void ringbuf_custom_measure(struct bench_res *res)
+{
+	struct ringbuf_custom_ctx *ctx = &ringbuf_custom_ctx;
+
+	res->hits = atomic_swap(&buf_hits.value, 0);
+	res->drops = atomic_swap(&ctx->skel->bss->dropped, 0);
+}
+
+static void ringbuf_custom_setup()
+{
+	struct ringbuf_custom_ctx *ctx = &ringbuf_custom_ctx;
+	const size_t page_size = getpagesize();
+	struct bpf_link *link;
+	struct ringbuf_custom *r;
+	void *tmp;
+	int err;
+
+	ctx->skel = ringbuf_setup_skeleton();
+
+	ctx->epoll_fd = epoll_create1(EPOLL_CLOEXEC);
+	if (ctx->epoll_fd < 0) {
+		fprintf(stderr, "failed to create epoll fd: %d\n", -errno);
+		exit(1);
+	}
+
+	r = &ctx->ringbuf;
+	r->map_fd = bpf_map__fd(ctx->skel->maps.ringbuf);
+	r->mask = args.ringbuf_sz - 1;
+
+	/* Map writable consumer page */
+	tmp = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED,
+		   r->map_fd, 0);
+	if (tmp == MAP_FAILED) {
+		fprintf(stderr, "failed to mmap consumer page: %d\n", -errno);
+		exit(1);
+	}
+	r->consumer_pos = tmp;
+
+	/* Map read-only producer page and data pages. */
+	tmp = mmap(NULL, page_size + 2 * args.ringbuf_sz, PROT_READ, MAP_SHARED,
+		   r->map_fd, page_size);
+	if (tmp == MAP_FAILED) {
+		fprintf(stderr, "failed to mmap data pages: %d\n", -errno);
+		exit(1);
+	}
+	r->producer_pos = tmp;
+	r->data = tmp + page_size;
+
+	ctx->event.events = EPOLLIN;
+	err = epoll_ctl(ctx->epoll_fd, EPOLL_CTL_ADD, r->map_fd, &ctx->event);
+	if (err < 0) {
+		fprintf(stderr, "failed to epoll add ringbuf: %d\n", -errno);
+		exit(1);
+	}
+
+	link = bpf_program__attach(ctx->skel->progs.bench_ringbuf);
+	if (IS_ERR(link)) {
+		fprintf(stderr, "failed to attach program\n");
+		exit(1);
+	}
+}
+
+#define RINGBUF_BUSY_BIT (1 << 31)
+#define RINGBUF_DISCARD_BIT (1 << 30)
+#define RINGBUF_META_LEN 8
+
+static inline int roundup_len(__u32 len)
+{
+	/* clear out top 2 bits */
+	len <<= 2;
+	len >>= 2;
+	/* add length prefix */
+	len += RINGBUF_META_LEN;
+	/* round up to 8 byte alignment */
+	return (len + 7) / 8 * 8;