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

Pull networking updates from David Miller:

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

21) Add BPF iterators, from Yonghang Song.

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

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

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

25) Add CAP_BPF, from Alexei Starovoitov.

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

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

28) Add devm_register_netdev(), from Bartosz Golaszewski.

29) Minimize qdisc resets, from Cong Wang.

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

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

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

tools/lib/bpf/Makefile

@@ -151,7 +151,7 @@ GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \
 			   sed 's/\[.*\]//' | \
 			   awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \
 			   sort -u | wc -l)
-VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \
+VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \
 			      grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
 
 CMD_TARGETS = $(LIB_TARGET) $(PC_FILE)
@@ -218,7 +218,7 @@ check_abi: $(OUTPUT)libbpf.so
 		    sed 's/\[.*\]//' |					 \
 		    awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'|  \
 		    sort -u > $(OUTPUT)libbpf_global_syms.tmp;		 \
-		readelf -s --wide $(OUTPUT)libbpf.so |			 \
+		readelf --dyn-syms --wide $(OUTPUT)libbpf.so |		 \
 		    grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 |		 \
 		    sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; 	 \
 		diff -u $(OUTPUT)libbpf_global_syms.tmp			 \
@@ -264,7 +264,7 @@ install_pkgconfig: $(PC_FILE)
 	$(call QUIET_INSTALL, $(PC_FILE)) \
 		$(call do_install,$(PC_FILE),$(libdir_SQ)/pkgconfig,644)
 
-install: install_lib install_pkgconfig
+install: install_lib install_pkgconfig install_headers
 
 ### Cleaning rules
 

tools/lib/bpf/bpf.c

@@ -619,6 +619,16 @@ int bpf_link_update(int link_fd, int new_prog_fd,
 	return sys_bpf(BPF_LINK_UPDATE, &attr, sizeof(attr));
 }
 
+int bpf_iter_create(int link_fd)
+{
+	union bpf_attr attr;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.iter_create.link_fd = link_fd;
+
+	return sys_bpf(BPF_ITER_CREATE, &attr, sizeof(attr));
+}
+
 int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
 		   __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt)
 {
@@ -721,6 +731,11 @@ int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id)
 	return bpf_obj_get_next_id(start_id, next_id, BPF_BTF_GET_NEXT_ID);
 }
 
+int bpf_link_get_next_id(__u32 start_id, __u32 *next_id)
+{
+	return bpf_obj_get_next_id(start_id, next_id, BPF_LINK_GET_NEXT_ID);
+}
+
 int bpf_prog_get_fd_by_id(__u32 id)
 {
 	union bpf_attr attr;
@@ -751,13 +766,23 @@ int bpf_btf_get_fd_by_id(__u32 id)
 	return sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr));
 }
 
-int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len)
+int bpf_link_get_fd_by_id(__u32 id)
+{
+	union bpf_attr attr;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.link_id = id;
+
+	return sys_bpf(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr));
+}
+
+int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len)
 {
 	union bpf_attr attr;
 	int err;
 
 	memset(&attr, 0, sizeof(attr));
-	attr.info.bpf_fd = prog_fd;
+	attr.info.bpf_fd = bpf_fd;
 	attr.info.info_len = *info_len;
 	attr.info.info = ptr_to_u64(info);
 
@@ -826,3 +851,13 @@ int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len,
 
 	return err;
 }
+
+int bpf_enable_stats(enum bpf_stats_type type)
+{
+	union bpf_attr attr;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.enable_stats.type = type;
+
+	return sys_bpf(BPF_ENABLE_STATS, &attr, sizeof(attr));
+}

tools/lib/bpf/bpf.h

@@ -187,6 +187,8 @@ struct bpf_link_update_opts {
 LIBBPF_API int bpf_link_update(int link_fd, int new_prog_fd,
 			       const struct bpf_link_update_opts *opts);
 
+LIBBPF_API int bpf_iter_create(int link_fd);
+
 struct bpf_prog_test_run_attr {
 	int prog_fd;
 	int repeat;
@@ -216,10 +218,12 @@ LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data,
 LIBBPF_API int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id);
 LIBBPF_API int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
 LIBBPF_API int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id);
+LIBBPF_API int bpf_link_get_next_id(__u32 start_id, __u32 *next_id);
 LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id);
 LIBBPF_API int bpf_map_get_fd_by_id(__u32 id);
 LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id);
-LIBBPF_API int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
+LIBBPF_API int bpf_link_get_fd_by_id(__u32 id);
+LIBBPF_API int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len);
 LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type,
 			      __u32 query_flags, __u32 *attach_flags,
 			      __u32 *prog_ids, __u32 *prog_cnt);
@@ -229,6 +233,7 @@ LIBBPF_API int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf,
 LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf,
 				 __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
 				 __u64 *probe_offset, __u64 *probe_addr);
+LIBBPF_API int bpf_enable_stats(enum bpf_stats_type type);
 
 #ifdef __cplusplus
 } /* extern "C" */

tools/lib/bpf/bpf_helpers.h

@@ -2,10 +2,17 @@
 #ifndef __BPF_HELPERS__
 #define __BPF_HELPERS__
 
+/*
+ * Note that bpf programs need to include either
+ * vmlinux.h (auto-generated from BTF) or linux/types.h
+ * in advance since bpf_helper_defs.h uses such types
+ * as __u64.
+ */
 #include "bpf_helper_defs.h"
 
 #define __uint(name, val) int (*name)[val]
 #define __type(name, val) typeof(val) *name
+#define __array(name, val) typeof(val) *name[]
 
 /* Helper macro to print out debug messages */
 #define bpf_printk(fmt, ...)				\
@@ -29,6 +36,20 @@
 #define __weak __attribute__((weak))
 #endif
 
+/*
+ * Helper macro to manipulate data structures
+ */
+#ifndef offsetof
+#define offsetof(TYPE, MEMBER)  ((size_t)&((TYPE *)0)->MEMBER)
+#endif
+#ifndef container_of
+#define container_of(ptr, type, member)				\
+	({							\
+		void *__mptr = (void *)(ptr);			\
+		((type *)(__mptr - offsetof(type, member)));	\
+	})
+#endif
+
 /*
  * Helper structure used by eBPF C program
  * to describe BPF map attributes to libbpf loader

tools/lib/bpf/bpf_tracing.h

@@ -413,4 +413,20 @@ typeof(name(0)) name(struct pt_regs *ctx)				    \
 }									    \
 static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
 
+/*
+ * BPF_SEQ_PRINTF to wrap bpf_seq_printf to-be-printed values
+ * in a structure.
+ */
+#define BPF_SEQ_PRINTF(seq, fmt, args...)				    \
+	({								    \
+		_Pragma("GCC diagnostic push")				    \
+		_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	    \
+		static const char ___fmt[] = fmt;			    \
+		unsigned long long ___param[] = { args };		    \
+		_Pragma("GCC diagnostic pop")				    \
+		int ___ret = bpf_seq_printf(seq, ___fmt, sizeof(___fmt),    \
+					    ___param, sizeof(___param));    \
+		___ret;							    \
+	})
+
 #endif

tools/lib/bpf/btf_dump.c

@@ -658,7 +658,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
 			if (!btf_dump_is_blacklisted(d, id)) {
 				btf_dump_emit_typedef_def(d, id, t, 0);
 				btf_dump_printf(d, ";\n\n");
-			};
+			}
 			tstate->fwd_emitted = 1;
 			break;
 		default:

tools/lib/bpf/hashmap.c

@@ -59,7 +59,14 @@ struct hashmap *hashmap__new(hashmap_hash_fn hash_fn,
 
 void hashmap__clear(struct hashmap *map)
 {
+	struct hashmap_entry *cur, *tmp;
+	size_t bkt;
+
+	hashmap__for_each_entry_safe(map, cur, tmp, bkt) {
+		free(cur);
+	}
 	free(map->buckets);
+	map->buckets = NULL;
 	map->cap = map->cap_bits = map->sz = 0;
 }
 
@@ -93,8 +100,7 @@ static int hashmap_grow(struct hashmap *map)
 	struct hashmap_entry **new_buckets;
 	struct hashmap_entry *cur, *tmp;
 	size_t new_cap_bits, new_cap;
-	size_t h;
-	int bkt;
+	size_t h, bkt;
 
 	new_cap_bits = map->cap_bits + 1;
 	if (new_cap_bits < HASHMAP_MIN_CAP_BITS)

tools/lib/bpf/hashmap.h

@@ -15,7 +15,6 @@
 #else
 #include <bits/reg.h>
 #endif
-#include "libbpf_internal.h"
 
 static inline size_t hash_bits(size_t h, int bits)
 {

tools/lib/bpf/libbpf.h

@@ -253,11 +253,22 @@ LIBBPF_API struct bpf_link *
 bpf_program__attach_lsm(struct bpf_program *prog);
 LIBBPF_API struct bpf_link *
 bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_netns(struct bpf_program *prog, int netns_fd);
 
 struct bpf_map;
 
 LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map);
 
+struct bpf_iter_attach_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+};
+#define bpf_iter_attach_opts__last_field sz
+
+LIBBPF_API struct bpf_link *
+bpf_program__attach_iter(struct bpf_program *prog,
+			 const struct bpf_iter_attach_opts *opts);
+
 struct bpf_insn;
 
 /*
@@ -469,6 +480,27 @@ 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,
@@ -524,6 +556,7 @@ perf_buffer__new_raw(int map_fd, size_t page_cnt,
 
 LIBBPF_API void perf_buffer__free(struct perf_buffer *pb);
 LIBBPF_API int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms);
+LIBBPF_API int perf_buffer__consume(struct perf_buffer *pb);
 
 typedef enum bpf_perf_event_ret
 	(*bpf_perf_event_print_t)(struct perf_event_header *hdr,

tools/lib/bpf/libbpf.map

@@ -254,3 +254,19 @@ LIBBPF_0.0.8 {
 		bpf_program__set_lsm;
 		bpf_set_link_xdp_fd_opts;
 } LIBBPF_0.0.7;
+
+LIBBPF_0.0.9 {
+	global:
+		bpf_enable_stats;
+		bpf_iter_create;
+		bpf_link_get_fd_by_id;
+		bpf_link_get_next_id;
+		bpf_program__attach_iter;
+		bpf_program__attach_netns;
+		perf_buffer__consume;
+		ring_buffer__add;
+		ring_buffer__consume;
+		ring_buffer__free;
+		ring_buffer__new;
+		ring_buffer__poll;
+} LIBBPF_0.0.8;

tools/lib/bpf/libbpf_internal.h

@@ -153,7 +153,7 @@ struct btf_ext_info_sec {
 	__u32	sec_name_off;
 	__u32	num_info;
 	/* Followed by num_info * record_size number of bytes */
-	__u8	data[0];
+	__u8	data[];
 };
 
 /* The minimum bpf_func_info checked by the loader */

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:

tools/lib/bpf/ringbuf.c

@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/*
+ * Ring buffer operations.
+ *
+ * Copyright (C) 2020 Facebook, Inc.
+ */
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
+#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;
+}