bpf: sync with latest bpf-next tree (#5)

sync with latest bpf-next tree.
the include/linux/filter.h is created as libbpf.c tries
to use various insn define macros.

Signed-off-by: Yonghong Song <yhs@fb.com>

include/linux/filter.h

@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+
+#ifndef __LINUX_FILTER_H
+#define __LINUX_FILTER_H
+
+#include <linux/bpf.h>
+
+#define BPF_MOV64_IMM(DST, IMM)					\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_MOV | BPF_K,		\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+#define BPF_EXIT_INSN()						\
+	((struct bpf_insn) {					\
+		.code  = BPF_JMP | BPF_EXIT,			\
+		.dst_reg = 0,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+#endif

include/uapi/linux/bpf.h

@@ -103,6 +103,7 @@ enum bpf_cmd {
 	BPF_BTF_LOAD,
 	BPF_BTF_GET_FD_BY_ID,
 	BPF_TASK_FD_QUERY,
+	BPF_MAP_LOOKUP_AND_DELETE_ELEM,
 };
 
 enum bpf_map_type {
@@ -128,6 +129,8 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_CGROUP_STORAGE,
 	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
 	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+	BPF_MAP_TYPE_QUEUE,
+	BPF_MAP_TYPE_STACK,
 };
 
 enum bpf_prog_type {
@@ -254,9 +257,6 @@ enum bpf_attach_type {
 /* Specify numa node during map creation */
 #define BPF_F_NUMA_NODE		(1U << 2)
 
-/* flags for BPF_PROG_QUERY */
-#define BPF_F_QUERY_EFFECTIVE	(1U << 0)
-
 #define BPF_OBJ_NAME_LEN 16U
 
 /* Flags for accessing BPF object */
@@ -266,6 +266,12 @@ enum bpf_attach_type {
 /* Flag for stack_map, store build_id+offset instead of pointer */
 #define BPF_F_STACK_BUILD_ID	(1U << 5)
 
+/* Zero-initialize hash function seed. This should only be used for testing. */
+#define BPF_F_ZERO_SEED		(1U << 6)
+
+/* flags for BPF_PROG_QUERY */
+#define BPF_F_QUERY_EFFECTIVE	(1U << 0)
+
 enum bpf_stack_build_id_status {
 	/* user space need an empty entry to identify end of a trace */
 	BPF_STACK_BUILD_ID_EMPTY = 0,
@@ -332,6 +338,10 @@ union bpf_attr {
 		 * (context accesses, allowed helpers, etc).
 		 */
 		__u32		expected_attach_type;
+		__u32		prog_btf_fd;	/* fd pointing to BTF type data */
+		__u32		func_info_rec_size;	/* userspace bpf_func_info size */
+		__aligned_u64	func_info;	/* func info */
+		__u32		func_info_cnt;	/* number of bpf_func_info records */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -462,6 +472,28 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
+ * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
+ * 	Description
+ * 		Push an element *value* in *map*. *flags* is one of:
+ *
+ * 		**BPF_EXIST**
+ * 		If the queue/stack is full, the oldest element is removed to
+ * 		make room for this.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_pop_elem(struct bpf_map *map, void *value)
+ * 	Description
+ * 		Pop an element from *map*.
+ * Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_peek_elem(struct bpf_map *map, void *value)
+ * 	Description
+ * 		Get an element from *map* without removing it.
+ * Return
+ * 		0 on success, or a negative error in case of failure.
+ *
  * int bpf_probe_read(void *dst, u32 size, const void *src)
  * 	Description
  * 		For tracing programs, safely attempt to read *size* bytes from
@@ -1433,7 +1465,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags)
+ * int bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags)
  * 	Description
  * 		Grow or shrink the room for data in the packet associated to
  * 		*skb* by *len_diff*, and according to the selected *mode*.
@@ -2176,6 +2208,8 @@ union bpf_attr {
  *		**CONFIG_NET** configuration option.
  *	Return
  *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *		For sockets with reuseport option, *struct bpf_sock*
+ *		return is from reuse->socks[] using hash of the packet.
  *
  * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
  *	Description
@@ -2208,6 +2242,8 @@ union bpf_attr {
  *		**CONFIG_NET** configuration option.
  *	Return
  *		Pointer to *struct bpf_sock*, or NULL in case of failure.
+ *		For sockets with reuseport option, *struct bpf_sock*
+ *		return is from reuse->socks[] using hash of the packet.
  *
  * int bpf_sk_release(struct bpf_sock *sk)
  *	Description
@@ -2215,6 +2251,23 @@ union bpf_attr {
  *		pointer that was returned from bpf_sk_lookup_xxx\ ().
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags)
+ *	Description
+ *		For socket policies, insert *len* bytes into msg at offset
+ *		*start*.
+ *
+ *		If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a
+ *		*msg* it may want to insert metadata or options into the msg.
+ *		This can later be read and used by any of the lower layer BPF
+ *		hooks.
+ *
+ *		This helper may fail if under memory pressure (a malloc
+ *		fails) in these cases BPF programs will get an appropriate
+ *		error and BPF programs will need to handle them.
+ *
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2303,7 +2356,11 @@ union bpf_attr {
 	FN(skb_ancestor_cgroup_id),	\
 	FN(sk_lookup_tcp),		\
 	FN(sk_lookup_udp),		\
-	FN(sk_release),
+	FN(sk_release),			\
+	FN(map_push_elem),		\
+	FN(map_pop_elem),		\
+	FN(map_peek_elem),		\
+	FN(msg_push_data),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2411,6 +2468,7 @@ struct __sk_buff {
 
 	__u32 data_meta;
 	struct bpf_flow_keys *flow_keys;
+	__u64 tstamp;
 };
 
 struct bpf_tunnel_key {
@@ -2585,6 +2643,10 @@ struct bpf_prog_info {
 	__u32 nr_jited_func_lens;
 	__aligned_u64 jited_ksyms;
 	__aligned_u64 jited_func_lens;
+	__u32 btf_id;
+	__u32 func_info_rec_size;
+	__aligned_u64 func_info;
+	__u32 func_info_cnt;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
@@ -2896,4 +2958,9 @@ struct bpf_flow_keys {
 	};
 };
 
+struct bpf_func_info {
+	__u32	insn_offset;
+	__u32	type_id;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */

include/uapi/linux/btf.h

@@ -40,7 +40,8 @@ struct btf_type {
 	/* "size" is used by INT, ENUM, STRUCT and UNION.
 	 * "size" tells the size of the type it is describing.
 	 *
-	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT.
+	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
+	 * FUNC and FUNC_PROTO.
 	 * "type" is a type_id referring to another type.
 	 */
 	union {
@@ -64,8 +65,10 @@ struct btf_type {
 #define BTF_KIND_VOLATILE	9	/* Volatile	*/
 #define BTF_KIND_CONST		10	/* Const	*/
 #define BTF_KIND_RESTRICT	11	/* Restrict	*/
-#define BTF_KIND_MAX		11
-#define NR_BTF_KINDS		12
+#define BTF_KIND_FUNC		12	/* Function	*/
+#define BTF_KIND_FUNC_PROTO	13	/* Function Proto	*/
+#define BTF_KIND_MAX		13
+#define NR_BTF_KINDS		14
 
 /* For some specific BTF_KIND, "struct btf_type" is immediately
  * followed by extra data.
@@ -110,4 +113,13 @@ struct btf_member {
 	__u32	offset;	/* offset in bits */
 };
 
+/* BTF_KIND_FUNC_PROTO is followed by multiple "struct btf_param".
+ * The exact number of btf_param is stored in the vlen (of the
+ * info in "struct btf_type").
+ */
+struct btf_param {
+	__u32	name_off;
+	__u32	type;
+};
+
 #endif /* _UAPI__LINUX_BTF_H__ */

include/uapi/linux/if_link.h

@@ -287,6 +287,7 @@ enum {
 	IFLA_BR_MCAST_STATS_ENABLED,
 	IFLA_BR_MCAST_IGMP_VERSION,
 	IFLA_BR_MCAST_MLD_VERSION,
+	IFLA_BR_VLAN_STATS_PER_PORT,
 	__IFLA_BR_MAX,
 };
 

include/uapi/linux/netlink.h

@@ -155,6 +155,7 @@ enum nlmsgerr_attrs {
 #define NETLINK_LIST_MEMBERSHIPS	9
 #define NETLINK_CAP_ACK			10
 #define NETLINK_EXT_ACK			11
+#define NETLINK_DUMP_STRICT_CHK		12
 
 struct nl_pktinfo {
 	__u32	group;

src/bpf.c

@@ -177,6 +177,7 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 			   char *log_buf, size_t log_buf_sz)
 {
 	union bpf_attr attr;
+	void *finfo = NULL;
 	__u32 name_len;
 	int fd;
 
@@ -196,6 +197,10 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	attr.log_level = 0;
 	attr.kern_version = load_attr->kern_version;
 	attr.prog_ifindex = load_attr->prog_ifindex;
+	attr.prog_btf_fd = load_attr->prog_btf_fd;
+	attr.func_info_rec_size = load_attr->func_info_rec_size;
+	attr.func_info_cnt = load_attr->func_info_cnt;
+	attr.func_info = ptr_to_u64(load_attr->func_info);
 	memcpy(attr.prog_name, load_attr->name,
 	       min(name_len, BPF_OBJ_NAME_LEN - 1));
 
@@ -203,12 +208,55 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	if (fd >= 0 || !log_buf || !log_buf_sz)
 		return fd;
 
+	/* After bpf_prog_load, the kernel may modify certain attributes
+	 * to give user space a hint how to deal with loading failure.
+	 * Check to see whether we can make some changes and load again.
+	 */
+	if (errno == E2BIG && attr.func_info_cnt &&
+	    attr.func_info_rec_size < load_attr->func_info_rec_size) {
+		__u32 actual_rec_size = load_attr->func_info_rec_size;
+		__u32 expected_rec_size = attr.func_info_rec_size;
+		__u32 finfo_cnt = load_attr->func_info_cnt;
+		__u64 finfo_len = actual_rec_size * finfo_cnt;
+		const void *orecord;
+		void *nrecord;
+		int i;
+
+		finfo = malloc(finfo_len);
+		if (!finfo)
+			/* further try with log buffer won't help */
+			return fd;
+
+		/* zero out bytes kernel does not understand */
+		orecord = load_attr->func_info;
+		nrecord = finfo;
+		for (i = 0; i < load_attr->func_info_cnt; i++) {
+			memcpy(nrecord, orecord, expected_rec_size);
+			memset(nrecord + expected_rec_size, 0,
+			       actual_rec_size - expected_rec_size);
+			orecord += actual_rec_size;
+			nrecord += actual_rec_size;
+		}
+
+		/* try with corrected func info records */
+		attr.func_info = ptr_to_u64(finfo);
+		attr.func_info_rec_size = load_attr->func_info_rec_size;
+
+		fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+
+		if (fd >= 0 || !log_buf || !log_buf_sz)
+			goto done;
+	}
+
 	/* Try again with log */
 	attr.log_buf = ptr_to_u64(log_buf);
 	attr.log_size = log_buf_sz;
 	attr.log_level = 1;
 	log_buf[0] = 0;
-	return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+done:
+	free(finfo);
+	return fd;
 }
 
 int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
@@ -278,6 +326,18 @@ int bpf_map_lookup_elem(int fd, const void *key, void *value)
 	return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
 }
 
+int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.map_fd = fd;
+	attr.key = ptr_to_u64(key);
+	attr.value = ptr_to_u64(value);
+
+	return sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
+}
+
 int bpf_map_delete_elem(int fd, const void *key)
 {
 	union bpf_attr attr;

src/bpf.h

@@ -27,6 +27,10 @@
 #include <stdbool.h>
 #include <stddef.h>
 
+#ifdef __cplusplus
+extern "C" {
+#endif
+
 #ifndef LIBBPF_API
 #define LIBBPF_API __attribute__((visibility("default")))
 #endif
@@ -74,6 +78,10 @@ struct bpf_load_program_attr {
 	const char *license;
 	__u32 kern_version;
 	__u32 prog_ifindex;
+	__u32 prog_btf_fd;
+	__u32 func_info_rec_size;
+	const void *func_info;
+	__u32 func_info_cnt;
 };
 
 /* Flags to direct loading requirements */
@@ -99,6 +107,8 @@ LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value,
 				   __u64 flags);
 
 LIBBPF_API int bpf_map_lookup_elem(int fd, const void *key, void *value);
+LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key,
+					      void *value);
 LIBBPF_API int bpf_map_delete_elem(int fd, const void *key);
 LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
 LIBBPF_API int bpf_obj_pin(int fd, const char *pathname);
@@ -126,4 +136,9 @@ 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);
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
 #endif /* __LIBBPF_BPF_H */

src/btf.c

@@ -37,6 +37,23 @@ struct btf {
 	int fd;
 };
 
+struct btf_ext {
+	void *func_info;
+	__u32 func_info_rec_size;
+	__u32 func_info_len;
+};
+
+/* The minimum bpf_func_info checked by the loader */
+struct bpf_func_info_min {
+	__u32   insn_offset;
+	__u32   type_id;
+};
+
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+	return (__u64) (unsigned long) ptr;
+}
+
 static int btf_add_type(struct btf *btf, struct btf_type *t)
 {
 	if (btf->types_size - btf->nr_types < 2) {
@@ -165,6 +182,10 @@ static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log)
 		case BTF_KIND_ENUM:
 			next_type += vlen * sizeof(struct btf_enum);
 			break;
+		case BTF_KIND_FUNC_PROTO:
+			next_type += vlen * sizeof(struct btf_param);
+			break;
+		case BTF_KIND_FUNC:
 		case BTF_KIND_TYPEDEF:
 		case BTF_KIND_PTR:
 		case BTF_KIND_FWD:
@@ -393,3 +414,329 @@ const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
 	else
 		return NULL;
 }
+
+int btf_get_from_id(__u32 id, struct btf **btf)
+{
+	struct bpf_btf_info btf_info = { 0 };
+	__u32 len = sizeof(btf_info);
+	__u32 last_size;
+	int btf_fd;
+	void *ptr;
+	int err;
+
+	err = 0;
+	*btf = NULL;
+	btf_fd = bpf_btf_get_fd_by_id(id);
+	if (btf_fd < 0)
+		return 0;
+
+	/* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so
+	 * let's start with a sane default - 4KiB here - and resize it only if
+	 * bpf_obj_get_info_by_fd() needs a bigger buffer.
+	 */
+	btf_info.btf_size = 4096;
+	last_size = btf_info.btf_size;
+	ptr = malloc(last_size);
+	if (!ptr) {
+		err = -ENOMEM;
+		goto exit_free;
+	}
+
+	bzero(ptr, last_size);
+	btf_info.btf = ptr_to_u64(ptr);
+	err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
+
+	if (!err && btf_info.btf_size > last_size) {
+		void *temp_ptr;
+
+		last_size = btf_info.btf_size;
+		temp_ptr = realloc(ptr, last_size);
+		if (!temp_ptr) {
+			err = -ENOMEM;
+			goto exit_free;
+		}
+		ptr = temp_ptr;
+		bzero(ptr, last_size);
+		btf_info.btf = ptr_to_u64(ptr);
+		err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
+	}
+
+	if (err || btf_info.btf_size > last_size) {
+		err = errno;
+		goto exit_free;
+	}
+
+	*btf = btf__new((__u8 *)btf_info.btf, btf_info.btf_size, NULL);
+	if (IS_ERR(*btf)) {
+		err = PTR_ERR(*btf);
+		*btf = NULL;
+	}
+
+exit_free:
+	close(btf_fd);
+	free(ptr);
+
+	return err;
+}
+
+static int btf_ext_validate_func_info(const void *finfo, __u32 size,
+				      btf_print_fn_t err_log)
+{
+	int sec_hdrlen = sizeof(struct btf_sec_func_info);
+	__u32 size_left, num_records, record_size;
+	const struct btf_sec_func_info *sinfo;
+	__u64 total_record_size;
+
+	/* At least a func_info record size */
+	if (size < sizeof(__u32)) {
+		elog("BTF.ext func_info record size not found");
+		return -EINVAL;
+	}
+
+	/* The record size needs to meet below minimum standard */
+	record_size = *(__u32 *)finfo;
+	if (record_size < sizeof(struct bpf_func_info_min) ||
+	    record_size % sizeof(__u32)) {
+		elog("BTF.ext func_info invalid record size");
+		return -EINVAL;
+	}
+
+	sinfo = finfo + sizeof(__u32);
+	size_left = size - sizeof(__u32);
+
+	/* If no func_info records, return failure now so .BTF.ext
+	 * won't be used.
+	 */
+	if (!size_left) {
+		elog("BTF.ext no func info records");
+		return -EINVAL;
+	}
+
+	while (size_left) {
+		if (size_left < sec_hdrlen) {
+			elog("BTF.ext func_info header not found");
+			return -EINVAL;
+		}
+
+		num_records = sinfo->num_func_info;
+		if (num_records == 0) {
+			elog("incorrect BTF.ext num_func_info");
+			return -EINVAL;
+		}
+
+		total_record_size = sec_hdrlen +
+				    (__u64)num_records * record_size;
+		if (size_left < total_record_size) {
+			elog("incorrect BTF.ext num_func_info");
+			return -EINVAL;
+		}
+
+		size_left -= total_record_size;
+		sinfo = (void *)sinfo + total_record_size;
+	}
+
+	return 0;
+}
+
+static int btf_ext_parse_hdr(__u8 *data, __u32 data_size,
+			     btf_print_fn_t err_log)
+{
+	const struct btf_ext_header *hdr = (struct btf_ext_header *)data;
+	__u32 meta_left, last_func_info_pos;
+	void *finfo;
+
+	if (data_size < offsetof(struct btf_ext_header, func_info_off) ||
+	    data_size < hdr->hdr_len) {
+		elog("BTF.ext header not found");
+		return -EINVAL;
+	}
+
+	if (hdr->magic != BTF_MAGIC) {
+		elog("Invalid BTF.ext magic:%x\n", hdr->magic);
+		return -EINVAL;
+	}
+
+	if (hdr->version != BTF_VERSION) {
+		elog("Unsupported BTF.ext version:%u\n", hdr->version);
+		return -ENOTSUP;
+	}
+
+	if (hdr->flags) {
+		elog("Unsupported BTF.ext flags:%x\n", hdr->flags);
+		return -ENOTSUP;
+	}
+
+	meta_left = data_size - hdr->hdr_len;
+	if (!meta_left) {
+		elog("BTF.ext has no data\n");
+		return -EINVAL;
+	}
+
+	if (meta_left < hdr->func_info_off) {
+		elog("Invalid BTF.ext func_info section offset:%u\n",
+		     hdr->func_info_off);
+		return -EINVAL;
+	}
+
+	if (hdr->func_info_off & 0x03) {
+		elog("BTF.ext func_info section is not aligned to 4 bytes\n");
+		return -EINVAL;
+	}
+
+	last_func_info_pos = hdr->hdr_len + hdr->func_info_off +
+			     hdr->func_info_len;
+	if (last_func_info_pos > data_size) {
+		elog("Invalid BTF.ext func_info section size:%u\n",
+		     hdr->func_info_len);
+		return -EINVAL;
+	}
+
+	finfo = data + hdr->hdr_len + hdr->func_info_off;
+	return btf_ext_validate_func_info(finfo, hdr->func_info_len,
+					  err_log);
+}
+
+void btf_ext__free(struct btf_ext *btf_ext)
+{
+	if (!btf_ext)
+		return;
+
+	free(btf_ext->func_info);
+	free(btf_ext);
+}
+
+struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log)
+{
+	const struct btf_ext_header *hdr;
+	struct btf_ext *btf_ext;
+	void *org_fdata, *fdata;
+	__u32 hdrlen, size_u32;
+	int err;
+
+	err = btf_ext_parse_hdr(data, size, err_log);
+	if (err)
+		return ERR_PTR(err);
+
+	btf_ext = calloc(1, sizeof(struct btf_ext));
+	if (!btf_ext)
+		return ERR_PTR(-ENOMEM);
+
+	hdr = (const struct btf_ext_header *)data;
+	hdrlen = hdr->hdr_len;
+	size_u32 = sizeof(__u32);
+	fdata = malloc(hdr->func_info_len - size_u32);
+	if (!fdata) {
+		free(btf_ext);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/* remember record size and copy rest of func_info data */
+	org_fdata = data + hdrlen + hdr->func_info_off;
+	btf_ext->func_info_rec_size = *(__u32 *)org_fdata;
+	memcpy(fdata, org_fdata + size_u32, hdr->func_info_len - size_u32);
+	btf_ext->func_info = fdata;
+	btf_ext->func_info_len = hdr->func_info_len - size_u32;
+
+	return btf_ext;
+}
+
+int btf_ext__reloc_init(struct btf *btf, struct btf_ext *btf_ext,
+			const char *sec_name, void **func_info,
+			__u32 *func_info_rec_size, __u32 *func_info_len)
+{
+	__u32 sec_hdrlen = sizeof(struct btf_sec_func_info);
+	__u32 i, record_size, records_len;
+	struct btf_sec_func_info *sinfo;
+	const char *info_sec_name;
+	__s64 remain_len;
+	void *data;
+
+	record_size = btf_ext->func_info_rec_size;
+	sinfo = btf_ext->func_info;
+	remain_len = btf_ext->func_info_len;
+
+	while (remain_len > 0) {
+		records_len = sinfo->num_func_info * record_size;
+		info_sec_name = btf__name_by_offset(btf, sinfo->sec_name_off);
+		if (strcmp(info_sec_name, sec_name)) {
+			remain_len -= sec_hdrlen + records_len;
+			sinfo = (void *)sinfo + sec_hdrlen + records_len;
+			continue;
+		}
+
+		data = malloc(records_len);
+		if (!data)
+			return -ENOMEM;
+
+		memcpy(data, sinfo->data, records_len);
+
+		/* adjust the insn_offset, the data in .BTF.ext is
+		 * the actual byte offset, and the kernel expects
+		 * the offset in term of bpf_insn.
+		 *
+		 * adjust the insn offset only, the rest data will
+		 * be passed to kernel.
+		 */
+		for (i = 0; i < sinfo->num_func_info; i++) {
+			struct bpf_func_info_min *record;
+
+			record = data + i * record_size;
+			record->insn_offset /= sizeof(struct bpf_insn);
+		}
+
+		*func_info = data;
+		*func_info_len = records_len;
+		*func_info_rec_size = record_size;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+int btf_ext__reloc(struct btf *btf, struct btf_ext *btf_ext,
+		   const char *sec_name, __u32 insns_cnt,
+		   void **func_info, __u32 *func_info_len)
+{
+	__u32 sec_hdrlen = sizeof(struct btf_sec_func_info);
+	__u32 i, record_size, existing_flen, records_len;
+	struct btf_sec_func_info *sinfo;
+	const char *info_sec_name;
+	__u64 remain_len;
+	void *data;
+
+	record_size = btf_ext->func_info_rec_size;
+	sinfo = btf_ext->func_info;
+	remain_len = btf_ext->func_info_len;
+	while (remain_len > 0) {
+		records_len = sinfo->num_func_info * record_size;
+		info_sec_name = btf__name_by_offset(btf, sinfo->sec_name_off);
+		if (strcmp(info_sec_name, sec_name)) {
+			remain_len -= sec_hdrlen + records_len;
+			sinfo = (void *)sinfo + sec_hdrlen + records_len;
+			continue;
+		}
+
+		existing_flen = *func_info_len;
+		data = realloc(*func_info, existing_flen + records_len);
+		if (!data)
+			return -ENOMEM;
+
+		memcpy(data + existing_flen, sinfo->data, records_len);
+		/* adjust insn_offset only, the rest data will be passed
+		 * to the kernel.
+		 */
+		for (i = 0; i < sinfo->num_func_info; i++) {
+			struct bpf_func_info_min *record;
+
+			record = data + existing_flen + i * record_size;
+			record->insn_offset =
+				record->insn_offset / sizeof(struct bpf_insn) +
+				insns_cnt;
+		}
+		*func_info = data;
+		*func_info_len = existing_flen + records_len;
+		return 0;
+	}
+
+	return -EINVAL;
+}

src/btf.h

@@ -6,15 +6,60 @@
 
 #include <linux/types.h>
 
+#ifdef __cplusplus
+extern "C" {
+#endif
+
 #ifndef LIBBPF_API
 #define LIBBPF_API __attribute__((visibility("default")))
 #endif
 
 #define BTF_ELF_SEC ".BTF"
+#define BTF_EXT_ELF_SEC ".BTF.ext"
 
 struct btf;
+struct btf_ext;
 struct btf_type;
 
+/*
+ * The .BTF.ext ELF section layout defined as
+ *   struct btf_ext_header
+ *   func_info subsection
+ *
+ * The func_info subsection layout:
+ *   record size for struct bpf_func_info in the func_info subsection
+ *   struct btf_sec_func_info for section #1
+ *   a list of bpf_func_info records for section #1
+ *     where struct bpf_func_info mimics one in include/uapi/linux/bpf.h
+ *     but may not be identical
+ *   struct btf_sec_func_info for section #2
+ *   a list of bpf_func_info records for section #2
+ *   ......
+ *
+ * Note that the bpf_func_info record size in .BTF.ext may not
+ * be the same as the one defined in include/uapi/linux/bpf.h.
+ * The loader should ensure that record_size meets minimum
+ * requirement and pass the record as is to the kernel. The
+ * kernel will handle the func_info properly based on its contents.
+ */
+struct btf_ext_header {
+	__u16	magic;
+	__u8	version;
+	__u8	flags;
+	__u32	hdr_len;
+
+	/* All offsets are in bytes relative to the end of this header */
+	__u32	func_info_off;
+	__u32	func_info_len;
+};
+
+struct btf_sec_func_info {
+	__u32	sec_name_off;
+	__u32	num_func_info;
+	/* Followed by num_func_info number of bpf func_info records */
+	__u8	data[0];
+};
+
 typedef int (*btf_print_fn_t)(const char *, ...)
 	__attribute__((format(printf, 1, 2)));
 
@@ -28,5 +73,19 @@ LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__fd(const struct btf *btf);
 LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
+LIBBPF_API int btf_get_from_id(__u32 id, struct btf **btf);
+
+struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log);
+void btf_ext__free(struct btf_ext *btf_ext);
+int btf_ext__reloc_init(struct btf *btf, struct btf_ext *btf_ext,
+			const char *sec_name, void **func_info,
+			__u32 *func_info_rec_size, __u32 *func_info_len);
+int btf_ext__reloc(struct btf *btf, struct btf_ext *btf_ext,
+		   const char *sec_name, __u32 insns_cnt, void **func_info,
+		   __u32 *func_info_len);
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
 
 #endif /* __LIBBPF_BTF_H */

src/libbpf.c

@@ -24,9 +24,11 @@
 #include <linux/kernel.h>
 #include <linux/bpf.h>
 #include <linux/btf.h>
+#include <linux/filter.h>
 #include <linux/list.h>
 #include <linux/limits.h>
 #include <linux/perf_event.h>
+#include <linux/ring_buffer.h>
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <sys/vfs.h>
@@ -113,6 +115,11 @@ void libbpf_set_print(libbpf_print_fn_t warn,
 # define LIBBPF_ELF_C_READ_MMAP ELF_C_READ
 #endif
 
+struct bpf_capabilities {
+	/* v4.14: kernel support for program & map names. */
+	__u32 name:1;
+};
+
 /*
  * bpf_prog should be a better name but it has been used in
  * linux/filter.h.
@@ -123,6 +130,10 @@ struct bpf_program {
 	char *name;
 	int prog_ifindex;
 	char *section_name;
+	/* section_name with / replaced by _; makes recursive pinning
+	 * in bpf_object__pin_programs easier
+	 */
+	char *pin_name;
 	struct bpf_insn *insns;
 	size_t insns_cnt, main_prog_cnt;
 	enum bpf_prog_type type;
@@ -151,6 +162,12 @@ struct bpf_program {
 	bpf_program_clear_priv_t clear_priv;
 
 	enum bpf_attach_type expected_attach_type;
+	int btf_fd;
+	void *func_info;
+	__u32 func_info_rec_size;
+	__u32 func_info_len;
+
+	struct bpf_capabilities *caps;
 };
 
 struct bpf_map {
@@ -158,6 +175,7 @@ struct bpf_map {
 	char *name;
 	size_t offset;
 	int map_ifindex;
+	int inner_map_fd;
 	struct bpf_map_def def;
 	__u32 btf_key_type_id;
 	__u32 btf_value_type_id;
@@ -207,10 +225,13 @@ struct bpf_object {
 	struct list_head list;
 
 	struct btf *btf;
+	struct btf_ext *btf_ext;
 
 	void *priv;
 	bpf_object_clear_priv_t clear_priv;
 
+	struct bpf_capabilities caps;
+
 	char path[];
 };
 #define obj_elf_valid(o)	((o)->efile.elf)
@@ -236,6 +257,9 @@ void bpf_program__unload(struct bpf_program *prog)
 
 	prog->instances.nr = -1;
 	zfree(&prog->instances.fds);
+
+	zclose(prog->btf_fd);
+	zfree(&prog->func_info);
 }
 
 static void bpf_program__exit(struct bpf_program *prog)
@@ -252,6 +276,7 @@ static void bpf_program__exit(struct bpf_program *prog)
 	bpf_program__unload(prog);
 	zfree(&prog->name);
 	zfree(&prog->section_name);
+	zfree(&prog->pin_name);
 	zfree(&prog->insns);
 	zfree(&prog->reloc_desc);
 
@@ -260,6 +285,17 @@ static void bpf_program__exit(struct bpf_program *prog)
 	prog->idx = -1;
 }
 
+static char *__bpf_program__pin_name(struct bpf_program *prog)
+{
+	char *name, *p;
+
+	name = p = strdup(prog->section_name);
+	while ((p = strchr(p, '/')))
+		*p = '_';
+
+	return name;
+}
+
 static int
 bpf_program__init(void *data, size_t size, char *section_name, int idx,
 		  struct bpf_program *prog)
@@ -278,6 +314,13 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx,
 		goto errout;
 	}
 
+	prog->pin_name = __bpf_program__pin_name(prog);
+	if (!prog->pin_name) {
+		pr_warning("failed to alloc pin name for prog under section(%d) %s\n",
+			   idx, section_name);
+		goto errout;
+	}
+
 	prog->insns = malloc(size);
 	if (!prog->insns) {
 		pr_warning("failed to alloc insns for prog under section %s\n",
@@ -290,7 +333,8 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx,
 	prog->idx = idx;
 	prog->instances.fds = NULL;
 	prog->instances.nr = -1;
-	prog->type = BPF_PROG_TYPE_KPROBE;
+	prog->type = BPF_PROG_TYPE_UNSPEC;
+	prog->btf_fd = -1;
 
 	return 0;
 errout:
@@ -309,6 +353,7 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
 	if (err)
 		return err;
 
+	prog.caps = &obj->caps;
 	progs = obj->programs;
 	nr_progs = obj->nr_programs;
 
@@ -561,6 +606,14 @@ static int compare_bpf_map(const void *_a, const void *_b)
 	return a->offset - b->offset;
 }
 
+static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
+{
+	if (type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
+	    type == BPF_MAP_TYPE_HASH_OF_MAPS)
+		return true;
+	return false;
+}
+
 static int
 bpf_object__init_maps(struct bpf_object *obj, int flags)
 {
@@ -624,13 +677,15 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
 	}
 	obj->nr_maps = nr_maps;
 
-	/*
-	 * fill all fd with -1 so won't close incorrect
-	 * fd (fd=0 is stdin) when failure (zclose won't close
-	 * negative fd)).
-	 */
-	for (i = 0; i < nr_maps; i++)
+	for (i = 0; i < nr_maps; i++) {
+		/*
+		 * fill all fd with -1 so won't close incorrect
+		 * fd (fd=0 is stdin) when failure (zclose won't close
+		 * negative fd)).
+		 */
 		obj->maps[i].fd = -1;
+		obj->maps[i].inner_map_fd = -1;
+	}
 
 	/*
 	 * Fill obj->maps using data in "maps" section.
@@ -783,6 +838,15 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
 					   BTF_ELF_SEC, PTR_ERR(obj->btf));
 				obj->btf = NULL;
 			}
+		} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
+			obj->btf_ext = btf_ext__new(data->d_buf, data->d_size,
+						    __pr_debug);
+			if (IS_ERR(obj->btf_ext)) {
+				pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
+					   BTF_EXT_ELF_SEC,
+					   PTR_ERR(obj->btf_ext));
+				obj->btf_ext = NULL;
+			}
 		} else if (sh.sh_type == SHT_SYMTAB) {
 			if (obj->efile.symbols) {
 				pr_warning("bpf: multiple SYMTAB in %s\n",
@@ -1093,6 +1157,52 @@ err_free_new_name:
 	return -errno;
 }
 
+static int
+bpf_object__probe_name(struct bpf_object *obj)
+{
+	struct bpf_load_program_attr attr;
+	char *cp, errmsg[STRERR_BUFSIZE];
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int ret;
+
+	/* make sure basic loading works */
+
+	memset(&attr, 0, sizeof(attr));
+	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+	attr.insns = insns;
+	attr.insns_cnt = ARRAY_SIZE(insns);
+	attr.license = "GPL";
+
+	ret = bpf_load_program_xattr(&attr, NULL, 0);
+	if (ret < 0) {
+		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+		pr_warning("Error in %s():%s(%d). Couldn't load basic 'r0 = 0' BPF program.\n",
+			   __func__, cp, errno);
+		return -errno;
+	}
+	close(ret);
+
+	/* now try the same program, but with the name */
+
+	attr.name = "test";
+	ret = bpf_load_program_xattr(&attr, NULL, 0);
+	if (ret >= 0) {
+		obj->caps.name = 1;
+		close(ret);
+	}
+
+	return 0;
+}
+
+static int
+bpf_object__probe_caps(struct bpf_object *obj)
+{
+	return bpf_object__probe_name(obj);
+}
+
 static int
 bpf_object__create_maps(struct bpf_object *obj)
 {
@@ -1112,7 +1222,8 @@ bpf_object__create_maps(struct bpf_object *obj)
 			continue;
 		}
 
-		create_attr.name = map->name;
+		if (obj->caps.name)
+			create_attr.name = map->name;
 		create_attr.map_ifindex = map->map_ifindex;
 		create_attr.map_type = def->type;
 		create_attr.map_flags = def->map_flags;
@@ -1122,6 +1233,9 @@ bpf_object__create_maps(struct bpf_object *obj)
 		create_attr.btf_fd = 0;
 		create_attr.btf_key_type_id = 0;
 		create_attr.btf_value_type_id = 0;
+		if (bpf_map_type__is_map_in_map(def->type) &&
+		    map->inner_map_fd >= 0)
+			create_attr.inner_map_fd = map->inner_map_fd;
 
 		if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) {
 			create_attr.btf_fd = btf__fd(obj->btf);
@@ -1166,6 +1280,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 	struct bpf_insn *insn, *new_insn;
 	struct bpf_program *text;
 	size_t new_cnt;
+	int err;
 
 	if (relo->type != RELO_CALL)
 		return -LIBBPF_ERRNO__RELOC;
@@ -1188,6 +1303,20 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 			pr_warning("oom in prog realloc\n");
 			return -ENOMEM;
 		}
+
+		if (obj->btf && obj->btf_ext) {
+			err = btf_ext__reloc(obj->btf, obj->btf_ext,
+					     text->section_name,
+					     prog->insns_cnt,
+					     &prog->func_info,
+					     &prog->func_info_len);
+			if (err) {
+				pr_warning("error in btf_ext__reloc for sec %s\n",
+					   text->section_name);
+				return err;
+			}
+		}
+
 		memcpy(new_insn + prog->insns_cnt, text->insns,
 		       text->insns_cnt * sizeof(*insn));
 		prog->insns = new_insn;
@@ -1207,7 +1336,24 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
 {
 	int i, err;
 
-	if (!prog || !prog->reloc_desc)
+	if (!prog)
+		return 0;
+
+	if (obj->btf && obj->btf_ext) {
+		err = btf_ext__reloc_init(obj->btf, obj->btf_ext,
+					  prog->section_name,
+					  &prog->func_info,
+					  &prog->func_info_rec_size,
+					  &prog->func_info_len);
+		if (err) {
+			pr_warning("err in btf_ext__reloc_init for sec %s\n",
+				   prog->section_name);
+			return err;
+		}
+		prog->btf_fd = btf__fd(obj->btf);
+	}
+
+	if (!prog->reloc_desc)
 		return 0;
 
 	for (i = 0; i < prog->nr_reloc; i++) {
@@ -1295,9 +1441,9 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 }
 
 static int
-load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
-	     const char *name, struct bpf_insn *insns, int insns_cnt,
-	     char *license, __u32 kern_version, int *pfd, int prog_ifindex)
+load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
+	     char *license, __u32 kern_version, int *pfd,
+	     __u32 func_info_cnt)
 {
 	struct bpf_load_program_attr load_attr;
 	char *cp, errmsg[STRERR_BUFSIZE];
@@ -1305,14 +1451,19 @@ load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
 	int ret;
 
 	memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
-	load_attr.prog_type = type;
-	load_attr.expected_attach_type = expected_attach_type;
-	load_attr.name = name;
+	load_attr.prog_type = prog->type;
+	load_attr.expected_attach_type = prog->expected_attach_type;
+	if (prog->caps->name)
+		load_attr.name = prog->name;
 	load_attr.insns = insns;
 	load_attr.insns_cnt = insns_cnt;
 	load_attr.license = license;
 	load_attr.kern_version = kern_version;
-	load_attr.prog_ifindex = prog_ifindex;
+	load_attr.prog_ifindex = prog->prog_ifindex;
+	load_attr.prog_btf_fd = prog->btf_fd >= 0 ? prog->btf_fd : 0;
+	load_attr.func_info = prog->func_info;
+	load_attr.func_info_rec_size = prog->func_info_rec_size;
+	load_attr.func_info_cnt = func_info_cnt;
 
 	if (!load_attr.insns || !load_attr.insns_cnt)
 		return -EINVAL;
@@ -1370,8 +1521,14 @@ int
 bpf_program__load(struct bpf_program *prog,
 		  char *license, __u32 kern_version)
 {
+	__u32 func_info_cnt;
 	int err = 0, fd, i;
 
+	if (prog->func_info_len == 0)
+		func_info_cnt = 0;
+	else
+		func_info_cnt = prog->func_info_len / prog->func_info_rec_size;
+
 	if (prog->instances.nr < 0 || !prog->instances.fds) {
 		if (prog->preprocessor) {
 			pr_warning("Internal error: can't load program '%s'\n",
@@ -1393,10 +1550,9 @@ bpf_program__load(struct bpf_program *prog,
 			pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n",
 				   prog->section_name, prog->instances.nr);
 		}
-		err = load_program(prog->type, prog->expected_attach_type,
-				   prog->name, prog->insns, prog->insns_cnt,
+		err = load_program(prog, prog->insns, prog->insns_cnt,
 				   license, kern_version, &fd,
-				   prog->prog_ifindex);
+				   func_info_cnt);
 		if (!err)
 			prog->instances.fds[0] = fd;
 		goto out;
@@ -1424,11 +1580,10 @@ bpf_program__load(struct bpf_program *prog,
 			continue;
 		}
 
-		err = load_program(prog->type, prog->expected_attach_type,
-				   prog->name, result.new_insn_ptr,
+		err = load_program(prog, result.new_insn_ptr,
 				   result.new_insn_cnt,
 				   license, kern_version, &fd,
-				   prog->prog_ifindex);
+				   func_info_cnt);
 
 		if (err) {
 			pr_warning("Loading the %dth instance of program '%s' failed\n",
@@ -1494,12 +1649,12 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
 	case BPF_PROG_TYPE_LIRC_MODE2:
 	case BPF_PROG_TYPE_SK_REUSEPORT:
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
-		return false;
 	case BPF_PROG_TYPE_UNSPEC:
-	case BPF_PROG_TYPE_KPROBE:
 	case BPF_PROG_TYPE_TRACEPOINT:
-	case BPF_PROG_TYPE_PERF_EVENT:
 	case BPF_PROG_TYPE_RAW_TRACEPOINT:
+	case BPF_PROG_TYPE_PERF_EVENT:
+		return false;
+	case BPF_PROG_TYPE_KPROBE:
 	default:
 		return true;
 	}
@@ -1626,6 +1781,7 @@ int bpf_object__load(struct bpf_object *obj)
 
 	obj->loaded = true;
 
+	CHECK_ERR(bpf_object__probe_caps(obj), err, out);
 	CHECK_ERR(bpf_object__create_maps(obj), err, out);
 	CHECK_ERR(bpf_object__relocate(obj), err, out);
 	CHECK_ERR(bpf_object__load_progs(obj), err, out);
@@ -1698,6 +1854,34 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
 	return 0;
 }
 
+int bpf_program__unpin_instance(struct bpf_program *prog, const char *path,
+				int instance)
+{
+	int err;
+
+	err = check_path(path);
+	if (err)
+		return err;
+
+	if (prog == NULL) {
+		pr_warning("invalid program pointer\n");
+		return -EINVAL;
+	}
+
+	if (instance < 0 || instance >= prog->instances.nr) {
+		pr_warning("invalid prog instance %d of prog %s (max %d)\n",
+			   instance, prog->section_name, prog->instances.nr);
+		return -EINVAL;
+	}
+
+	err = unlink(path);
+	if (err != 0)
+		return -errno;
+	pr_debug("unpinned program '%s'\n", path);
+
+	return 0;
+}
+
 static int make_dir(const char *path)
 {
 	char *cp, errmsg[STRERR_BUFSIZE];
@@ -1732,10 +1916,78 @@ int bpf_program__pin(struct bpf_program *prog, const char *path)
 		return -EINVAL;
 	}
 
+	if (prog->instances.nr == 1) {
+		/* don't create subdirs when pinning single instance */
+		return bpf_program__pin_instance(prog, path, 0);
+	}
+
 	err = make_dir(path);
 	if (err)
 		return err;
 
+	for (i = 0; i < prog->instances.nr; i++) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
+		if (len < 0) {
+			err = -EINVAL;
+			goto err_unpin;
+		} else if (len >= PATH_MAX) {
+			err = -ENAMETOOLONG;
+			goto err_unpin;
+		}
+
+		err = bpf_program__pin_instance(prog, buf, i);
+		if (err)
+			goto err_unpin;
+	}
+
+	return 0;
+
+err_unpin:
+	for (i = i - 1; i >= 0; i--) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
+		if (len < 0)
+			continue;
+		else if (len >= PATH_MAX)
+			continue;
+
+		bpf_program__unpin_instance(prog, buf, i);
+	}
+
+	rmdir(path);
+
+	return err;
+}
+
+int bpf_program__unpin(struct bpf_program *prog, const char *path)
+{
+	int i, err;
+
+	err = check_path(path);
+	if (err)
+		return err;
+
+	if (prog == NULL) {
+		pr_warning("invalid program pointer\n");
+		return -EINVAL;
+	}
+
+	if (prog->instances.nr <= 0) {
+		pr_warning("no instances of prog %s to pin\n",
+			   prog->section_name);
+		return -EINVAL;
+	}
+
+	if (prog->instances.nr == 1) {
+		/* don't create subdirs when pinning single instance */
+		return bpf_program__unpin_instance(prog, path, 0);
+	}
+
 	for (i = 0; i < prog->instances.nr; i++) {
 		char buf[PATH_MAX];
 		int len;
@@ -1746,11 +1998,15 @@ int bpf_program__pin(struct bpf_program *prog, const char *path)
 		else if (len >= PATH_MAX)
 			return -ENAMETOOLONG;
 
-		err = bpf_program__pin_instance(prog, buf, i);
+		err = bpf_program__unpin_instance(prog, buf, i);
 		if (err)
 			return err;
 	}
 
+	err = rmdir(path);
+	if (err)
+		return -errno;
+
 	return 0;
 }
 
@@ -1775,12 +2031,33 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
 	}
 
 	pr_debug("pinned map '%s'\n", path);
+
 	return 0;
 }
 
-int bpf_object__pin(struct bpf_object *obj, const char *path)
+int bpf_map__unpin(struct bpf_map *map, const char *path)
+{
+	int err;
+
+	err = check_path(path);
+	if (err)
+		return err;
+
+	if (map == NULL) {
+		pr_warning("invalid map pointer\n");
+		return -EINVAL;
+	}
+
+	err = unlink(path);
+	if (err != 0)
+		return -errno;
+	pr_debug("unpinned map '%s'\n", path);
+
+	return 0;
+}
+
+int bpf_object__pin_maps(struct bpf_object *obj, const char *path)
 {
-	struct bpf_program *prog;
 	struct bpf_map *map;
 	int err;
 
@@ -1796,6 +2073,53 @@ int bpf_object__pin(struct bpf_object *obj, const char *path)
 	if (err)
 		return err;
 
+	bpf_map__for_each(map, obj) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%s", path,
+			       bpf_map__name(map));
+		if (len < 0) {
+			err = -EINVAL;
+			goto err_unpin_maps;
+		} else if (len >= PATH_MAX) {
+			err = -ENAMETOOLONG;
+			goto err_unpin_maps;
+		}
+
+		err = bpf_map__pin(map, buf);
+		if (err)
+			goto err_unpin_maps;
+	}
+
+	return 0;
+
+err_unpin_maps:
+	while ((map = bpf_map__prev(map, obj))) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%s", path,
+			       bpf_map__name(map));
+		if (len < 0)
+			continue;
+		else if (len >= PATH_MAX)
+			continue;
+
+		bpf_map__unpin(map, buf);
+	}
+
+	return err;
+}
+
+int bpf_object__unpin_maps(struct bpf_object *obj, const char *path)
+{
+	struct bpf_map *map;
+	int err;
+
+	if (!obj)
+		return -ENOENT;
+
 	bpf_map__for_each(map, obj) {
 		char buf[PATH_MAX];
 		int len;
@@ -1807,23 +2131,90 @@ int bpf_object__pin(struct bpf_object *obj, const char *path)
 		else if (len >= PATH_MAX)
 			return -ENAMETOOLONG;
 
-		err = bpf_map__pin(map, buf);
+		err = bpf_map__unpin(map, buf);
 		if (err)
 			return err;
 	}
 
+	return 0;
+}
+
+int bpf_object__pin_programs(struct bpf_object *obj, const char *path)
+{
+	struct bpf_program *prog;
+	int err;
+
+	if (!obj)
+		return -ENOENT;
+
+	if (!obj->loaded) {
+		pr_warning("object not yet loaded; load it first\n");
+		return -ENOENT;
+	}
+
+	err = make_dir(path);
+	if (err)
+		return err;
+
 	bpf_object__for_each_program(prog, obj) {
 		char buf[PATH_MAX];
 		int len;
 
 		len = snprintf(buf, PATH_MAX, "%s/%s", path,
-			       prog->section_name);
+			       prog->pin_name);
+		if (len < 0) {
+			err = -EINVAL;
+			goto err_unpin_programs;
+		} else if (len >= PATH_MAX) {
+			err = -ENAMETOOLONG;
+			goto err_unpin_programs;
+		}
+
+		err = bpf_program__pin(prog, buf);
+		if (err)
+			goto err_unpin_programs;
+	}
+
+	return 0;
+
+err_unpin_programs:
+	while ((prog = bpf_program__prev(prog, obj))) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%s", path,
+			       prog->pin_name);
+		if (len < 0)
+			continue;
+		else if (len >= PATH_MAX)
+			continue;
+
+		bpf_program__unpin(prog, buf);
+	}
+
+	return err;
+}
+
+int bpf_object__unpin_programs(struct bpf_object *obj, const char *path)
+{
+	struct bpf_program *prog;
+	int err;
+
+	if (!obj)
+		return -ENOENT;
+
+	bpf_object__for_each_program(prog, obj) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%s", path,
+			       prog->pin_name);
 		if (len < 0)
 			return -EINVAL;
 		else if (len >= PATH_MAX)
 			return -ENAMETOOLONG;
 
-		err = bpf_program__pin(prog, buf);
+		err = bpf_program__unpin(prog, buf);
 		if (err)
 			return err;
 	}
@@ -1831,6 +2222,23 @@ int bpf_object__pin(struct bpf_object *obj, const char *path)
 	return 0;
 }
 
+int bpf_object__pin(struct bpf_object *obj, const char *path)
+{
+	int err;
+
+	err = bpf_object__pin_maps(obj, path);
+	if (err)
+		return err;
+
+	err = bpf_object__pin_programs(obj, path);
+	if (err) {
+		bpf_object__unpin_maps(obj, path);
+		return err;
+	}
+
+	return 0;
+}
+
 void bpf_object__close(struct bpf_object *obj)
 {
 	size_t i;
@@ -1844,6 +2252,7 @@ void bpf_object__close(struct bpf_object *obj)
 	bpf_object__elf_finish(obj);
 	bpf_object__unload(obj);
 	btf__free(obj->btf);
+	btf_ext__free(obj->btf_ext);
 
 	for (i = 0; i < obj->nr_maps; i++) {
 		zfree(&obj->maps[i].name);
@@ -1917,23 +2326,26 @@ void *bpf_object__priv(struct bpf_object *obj)
 }
 
 static struct bpf_program *
-__bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
+__bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward)
 {
-	size_t idx;
+	size_t nr_programs = obj->nr_programs;
+	ssize_t idx;
 
-	if (!obj->programs)
+	if (!nr_programs)
 		return NULL;
-	/* First handler */
-	if (prev == NULL)
-		return &obj->programs[0];
 
-	if (prev->obj != obj) {
+	if (!p)
+		/* Iter from the beginning */
+		return forward ? &obj->programs[0] :
+			&obj->programs[nr_programs - 1];
+
+	if (p->obj != obj) {
 		pr_warning("error: program handler doesn't match object\n");
 		return NULL;
 	}
 
-	idx = (prev - obj->programs) + 1;
-	if (idx >= obj->nr_programs)
+	idx = (p - obj->programs) + (forward ? 1 : -1);
+	if (idx >= obj->nr_programs || idx < 0)
 		return NULL;
 	return &obj->programs[idx];
 }
@@ -1944,7 +2356,19 @@ bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
 	struct bpf_program *prog = prev;
 
 	do {
-		prog = __bpf_program__next(prog, obj);
+		prog = __bpf_program__iter(prog, obj, true);
+	} while (prog && bpf_program__is_function_storage(prog, obj));
+
+	return prog;
+}
+
+struct bpf_program *
+bpf_program__prev(struct bpf_program *next, struct bpf_object *obj)
+{
+	struct bpf_program *prog = next;
+
+	do {
+		prog = __bpf_program__iter(prog, obj, false);
 	} while (prog && bpf_program__is_function_storage(prog, obj));
 
 	return prog;
@@ -2083,19 +2507,19 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog,
 	prog->expected_attach_type = type;
 }
 
-#define BPF_PROG_SEC_IMPL(string, ptype, eatype, atype) \
-	{ string, sizeof(string) - 1, ptype, eatype, atype }
+#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, atype) \
+	{ string, sizeof(string) - 1, ptype, eatype, is_attachable, atype }
 
 /* Programs that can NOT be attached. */
-#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, -EINVAL)
+#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0)
 
 /* Programs that can be attached. */
 #define BPF_APROG_SEC(string, ptype, atype) \
-	BPF_PROG_SEC_IMPL(string, ptype, 0, atype)
+	BPF_PROG_SEC_IMPL(string, ptype, 0, 1, atype)
 
 /* Programs that must specify expected attach type at load time. */
 #define BPF_EAPROG_SEC(string, ptype, eatype) \
-	BPF_PROG_SEC_IMPL(string, ptype, eatype, eatype)
+	BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, eatype)
 
 /* Programs that can be attached but attach type can't be identified by section
  * name. Kept for backward compatibility.
@@ -2107,6 +2531,7 @@ static const struct {
 	size_t len;
 	enum bpf_prog_type prog_type;
 	enum bpf_attach_type expected_attach_type;
+	int is_attachable;
 	enum bpf_attach_type attach_type;
 } section_names[] = {
 	BPF_PROG_SEC("socket",			BPF_PROG_TYPE_SOCKET_FILTER),
@@ -2197,7 +2622,7 @@ int libbpf_attach_type_by_name(const char *name,
 	for (i = 0; i < ARRAY_SIZE(section_names); i++) {
 		if (strncmp(name, section_names[i].sec, section_names[i].len))
 			continue;
-		if (section_names[i].attach_type == -EINVAL)
+		if (!section_names[i].is_attachable)
 			return -EINVAL;
 		*attach_type = section_names[i].attach_type;
 		return 0;
@@ -2270,10 +2695,24 @@ void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
 	map->map_ifindex = ifindex;
 }
 
-struct bpf_map *
-bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
+int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd)
 {
-	size_t idx;
+	if (!bpf_map_type__is_map_in_map(map->def.type)) {
+		pr_warning("error: unsupported map type\n");
+		return -EINVAL;
+	}
+	if (map->inner_map_fd != -1) {
+		pr_warning("error: inner_map_fd already specified\n");
+		return -EINVAL;
+	}
+	map->inner_map_fd = fd;
+	return 0;
+}
+
+static struct bpf_map *
+__bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i)
+{
+	ssize_t idx;
 	struct bpf_map *s, *e;
 
 	if (!obj || !obj->maps)
@@ -2282,21 +2721,39 @@ bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
 	s = obj->maps;
 	e = obj->maps + obj->nr_maps;
 
-	if (prev == NULL)
-		return s;
-
-	if ((prev < s) || (prev >= e)) {
+	if ((m < s) || (m >= e)) {
 		pr_warning("error in %s: map handler doesn't belong to object\n",
 			   __func__);
 		return NULL;
 	}
 
-	idx = (prev - obj->maps) + 1;
-	if (idx >= obj->nr_maps)
+	idx = (m - obj->maps) + i;
+	if (idx >= obj->nr_maps || idx < 0)
 		return NULL;
 	return &obj->maps[idx];
 }
 
+struct bpf_map *
+bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
+{
+	if (prev == NULL)
+		return obj->maps;
+
+	return __bpf_map__iter(prev, obj, 1);
+}
+
+struct bpf_map *
+bpf_map__prev(struct bpf_map *next, struct bpf_object *obj)
+{
+	if (next == NULL) {
+		if (!obj->nr_maps)
+			return NULL;
+		return obj->maps + obj->nr_maps - 1;
+	}
+
+	return __bpf_map__iter(next, obj, -1);
+}
+
 struct bpf_map *
 bpf_object__find_map_by_name(struct bpf_object *obj, const char *name)
 {
@@ -2414,61 +2871,49 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 }
 
 enum bpf_perf_event_ret
-bpf_perf_event_read_simple(void *mem, unsigned long size,
-			   unsigned long page_size, void **buf, size_t *buf_len,
-			   bpf_perf_event_print_t fn, void *priv)
+bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
+			   void **copy_mem, size_t *copy_size,
+			   bpf_perf_event_print_t fn, void *private_data)
 {
-	volatile struct perf_event_mmap_page *header = mem;
+	struct perf_event_mmap_page *header = mmap_mem;
+	__u64 data_head = ring_buffer_read_head(header);
 	__u64 data_tail = header->data_tail;
-	__u64 data_head = header->data_head;
-	int ret = LIBBPF_PERF_EVENT_ERROR;
-	void *base, *begin, *end;
+	void *base = ((__u8 *)header) + page_size;
+	int ret = LIBBPF_PERF_EVENT_CONT;
+	struct perf_event_header *ehdr;
+	size_t ehdr_size;
 
-	asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */
-	if (data_head == data_tail)
-		return LIBBPF_PERF_EVENT_CONT;
+	while (data_head != data_tail) {
+		ehdr = base + (data_tail & (mmap_size - 1));
+		ehdr_size = ehdr->size;
 
-	base = ((char *)header) + page_size;
+		if (((void *)ehdr) + ehdr_size > base + mmap_size) {
+			void *copy_start = ehdr;
+			size_t len_first = base + mmap_size - copy_start;
+			size_t len_secnd = ehdr_size - len_first;
 
-	begin = base + data_tail % size;
-	end = base + data_head % size;
-
-	while (begin != end) {
-		struct perf_event_header *ehdr;
-
-		ehdr = begin;
-		if (begin + ehdr->size > base + size) {
-			long len = base + size - begin;
-
-			if (*buf_len < ehdr->size) {
-				free(*buf);
-				*buf = malloc(ehdr->size);
-				if (!*buf) {
+			if (*copy_size < ehdr_size) {
+				free(*copy_mem);
+				*copy_mem = malloc(ehdr_size);
+				if (!*copy_mem) {
+					*copy_size = 0;
 					ret = LIBBPF_PERF_EVENT_ERROR;
 					break;
 				}
-				*buf_len = ehdr->size;
+				*copy_size = ehdr_size;
 			}
 
-			memcpy(*buf, begin, len);
-			memcpy(*buf + len, base, ehdr->size - len);
-			ehdr = (void *)*buf;
-			begin = base + ehdr->size - len;
-		} else if (begin + ehdr->size == base + size) {
-			begin = base;
-		} else {
-			begin += ehdr->size;
+			memcpy(*copy_mem, copy_start, len_first);
+			memcpy(*copy_mem + len_first, base, len_secnd);
+			ehdr = *copy_mem;
 		}
 
-		ret = fn(ehdr, priv);
+		ret = fn(ehdr, private_data);
+		data_tail += ehdr_size;
 		if (ret != LIBBPF_PERF_EVENT_CONT)
 			break;
-
-		data_tail += ehdr->size;
 	}
 
-	__sync_synchronize(); /* smp_mb() */
-	header->data_tail = data_tail;
-
+	ring_buffer_write_tail(header, data_tail);
 	return ret;
 }

src/libbpf.h

@@ -16,6 +16,10 @@
 #include <sys/types.h>  // for size_t
 #include <linux/bpf.h>
 
+#ifdef __cplusplus
+extern "C" {
+#endif
+
 #ifndef LIBBPF_API
 #define LIBBPF_API __attribute__((visibility("default")))
 #endif
@@ -71,6 +75,13 @@ struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
 LIBBPF_API struct bpf_object *bpf_object__open_buffer(void *obj_buf,
 						      size_t obj_buf_sz,
 						      const char *name);
+LIBBPF_API int bpf_object__pin_maps(struct bpf_object *obj, const char *path);
+LIBBPF_API int bpf_object__unpin_maps(struct bpf_object *obj,
+				      const char *path);
+LIBBPF_API int bpf_object__pin_programs(struct bpf_object *obj,
+					const char *path);
+LIBBPF_API int bpf_object__unpin_programs(struct bpf_object *obj,
+					  const char *path);
 LIBBPF_API int bpf_object__pin(struct bpf_object *object, const char *path);
 LIBBPF_API void bpf_object__close(struct bpf_object *object);
 
@@ -112,6 +123,9 @@ LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog,
 	     (pos) != NULL;				\
 	     (pos) = bpf_program__next((pos), (obj)))
 
+LIBBPF_API struct bpf_program *bpf_program__prev(struct bpf_program *prog,
+						 struct bpf_object *obj);
+
 typedef void (*bpf_program_clear_priv_t)(struct bpf_program *,
 					 void *);
 
@@ -131,7 +145,11 @@ LIBBPF_API int bpf_program__fd(struct bpf_program *prog);
 LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog,
 					 const char *path,
 					 int instance);
+LIBBPF_API int bpf_program__unpin_instance(struct bpf_program *prog,
+					   const char *path,
+					   int instance);
 LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path);
+LIBBPF_API int bpf_program__unpin(struct bpf_program *prog, const char *path);
 LIBBPF_API void bpf_program__unload(struct bpf_program *prog);
 
 struct bpf_insn;
@@ -260,6 +278,9 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
 	     (pos) != NULL;				\
 	     (pos) = bpf_map__next((pos), (obj)))
 
+LIBBPF_API struct bpf_map *
+bpf_map__prev(struct bpf_map *map, struct bpf_object *obj);
+
 LIBBPF_API int bpf_map__fd(struct bpf_map *map);
 LIBBPF_API const struct bpf_map_def *bpf_map__def(struct bpf_map *map);
 LIBBPF_API const char *bpf_map__name(struct bpf_map *map);
@@ -274,6 +295,9 @@ LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd);
 LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map);
 LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
 LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path);
+LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path);
+
+LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd);
 
 LIBBPF_API long libbpf_get_error(const void *ptr);
 
@@ -297,13 +321,14 @@ enum bpf_perf_event_ret {
 	LIBBPF_PERF_EVENT_CONT	= -2,
 };
 
-typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(void *event,
-							  void *priv);
-LIBBPF_API int bpf_perf_event_read_simple(void *mem, unsigned long size,
-					  unsigned long page_size,
-					  void **buf, size_t *buf_len,
-					  bpf_perf_event_print_t fn,
-					  void *priv);
+struct perf_event_header;
+typedef enum bpf_perf_event_ret
+	(*bpf_perf_event_print_t)(struct perf_event_header *hdr,
+				  void *private_data);
+LIBBPF_API enum bpf_perf_event_ret
+bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
+			   void **copy_mem, size_t *copy_size,
+			   bpf_perf_event_print_t fn, void *private_data);
 
 struct nlattr;
 typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);
@@ -316,4 +341,9 @@ int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
 			libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie);
 int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
 			 libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie);
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
 #endif /* __LIBBPF_LIBBPF_H */