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

Daniel Borkmann says:

====================
pull-request: bpf-next 2020-10-01

The following pull-request contains BPF updates for your *net-next* tree.

We've added 90 non-merge commits during the last 8 day(s) which contain
a total of 103 files changed, 7662 insertions(+), 1894 deletions(-).

Note that once bpf(/net) tree gets merged into net-next, there will be a small
merge conflict in tools/lib/bpf/btf.c between commit 1245008122d7 ("libbpf: Fix
native endian assumption when parsing BTF") from the bpf tree and the commit
3289959b97ca ("libbpf: Support BTF loading and raw data output in both endianness")
from the bpf-next tree. Correct resolution would be to stick with bpf-next, it
should look like:

  [...]
        /* check BTF magic */
        if (fread(&magic, 1, sizeof(magic), f) < sizeof(magic)) {
                err = -EIO;
                goto err_out;
        }
        if (magic != BTF_MAGIC && magic != bswap_16(BTF_MAGIC)) {
                /* definitely not a raw BTF */
                err = -EPROTO;
                goto err_out;
        }

        /* get file size */
  [...]

The main changes are:

1) Add bpf_snprintf_btf() and bpf_seq_printf_btf() helpers to support displaying
   BTF-based kernel data structures out of BPF programs, from Alan Maguire.

2) Speed up RCU tasks trace grace periods by a factor of 50 & fix a few race
   conditions exposed by it. It was discussed to take these via BPF and
   networking tree to get better testing exposure, from Paul E. McKenney.

3) Support multi-attach for freplace programs, needed for incremental attachment
   of multiple XDP progs using libxdp dispatcher model, from Toke Høiland-Jørgensen.

4) libbpf support for appending new BTF types at the end of BTF object, allowing
   intrusive changes of prog's BTF (useful for future linking), from Andrii Nakryiko.

5) Several BPF helper improvements e.g. avoid atomic op in cookie generator and add
   a redirect helper into neighboring subsys, from Daniel Borkmann.

6) Allow map updates on sockmaps from bpf_iter context in order to migrate sockmaps
   from one to another, from Lorenz Bauer.

7) Fix 32 bit to 64 bit assignment from latest alu32 bounds tracking which caused
   a verifier issue due to type downgrade to scalar, from John Fastabend.

8) Follow-up on tail-call support in BPF subprogs which optimizes x64 JIT prologue
   and epilogue sections, from Maciej Fijalkowski.

9) Add an option to perf RB map to improve sharing of event entries by avoiding remove-
   on-close behavior. Also, add BPF_PROG_TEST_RUN for raw_tracepoint, from Song Liu.

10) Fix a crash in AF_XDP's socket_release when memory allocation for UMEMs fails,
    from Magnus Karlsson.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

12 files changed, 1774 insertions, 183 deletions

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index f43249696d9f..5f9abed3e226 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -98,19 +98,18 @@ PC_FILE		= libbpf.pc
 ifdef EXTRA_CFLAGS
   CFLAGS := $(EXTRA_CFLAGS)
 else
-  CFLAGS := -g -Wall
+  CFLAGS := -g -O2
 endif
 
 # Append required CFLAGS
 override CFLAGS += $(EXTRA_WARNINGS) -Wno-switch-enum
 override CFLAGS += -Werror -Wall
-override CFLAGS += -fPIC
 override CFLAGS += $(INCLUDES)
 override CFLAGS += -fvisibility=hidden
 override CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
 
 # flags specific for shared library
-SHLIB_FLAGS := -DSHARED
+SHLIB_FLAGS := -DSHARED -fPIC
 
 ifeq ($(VERBOSE),1)
   Q =
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 2baa1308737c..d27e34133973 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -586,19 +586,31 @@ int bpf_link_create(int prog_fd, int target_fd,
 		    enum bpf_attach_type attach_type,
 		    const struct bpf_link_create_opts *opts)
 {
+	__u32 target_btf_id, iter_info_len;
 	union bpf_attr attr;
 
 	if (!OPTS_VALID(opts, bpf_link_create_opts))
 		return -EINVAL;
 
+	iter_info_len = OPTS_GET(opts, iter_info_len, 0);
+	target_btf_id = OPTS_GET(opts, target_btf_id, 0);
+
+	if (iter_info_len && target_btf_id)
+		return -EINVAL;
+
 	memset(&attr, 0, sizeof(attr));
 	attr.link_create.prog_fd = prog_fd;
 	attr.link_create.target_fd = target_fd;
 	attr.link_create.attach_type = attach_type;
 	attr.link_create.flags = OPTS_GET(opts, flags, 0);
-	attr.link_create.iter_info =
-		ptr_to_u64(OPTS_GET(opts, iter_info, (void *)0));
-	attr.link_create.iter_info_len = OPTS_GET(opts, iter_info_len, 0);
+
+	if (iter_info_len) {
+		attr.link_create.iter_info =
+			ptr_to_u64(OPTS_GET(opts, iter_info, (void *)0));
+		attr.link_create.iter_info_len = iter_info_len;
+	} else if (target_btf_id) {
+		attr.link_create.target_btf_id = target_btf_id;
+	}
 
 	return sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr));
 }
@@ -712,6 +724,37 @@ int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr)
 	return ret;
 }
 
+int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts)
+{
+	union bpf_attr attr;
+	int ret;
+
+	if (!OPTS_VALID(opts, bpf_test_run_opts))
+		return -EINVAL;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.test.prog_fd = prog_fd;
+	attr.test.cpu = OPTS_GET(opts, cpu, 0);
+	attr.test.flags = OPTS_GET(opts, flags, 0);
+	attr.test.repeat = OPTS_GET(opts, repeat, 0);
+	attr.test.duration = OPTS_GET(opts, duration, 0);
+	attr.test.ctx_size_in = OPTS_GET(opts, ctx_size_in, 0);
+	attr.test.ctx_size_out = OPTS_GET(opts, ctx_size_out, 0);
+	attr.test.data_size_in = OPTS_GET(opts, data_size_in, 0);
+	attr.test.data_size_out = OPTS_GET(opts, data_size_out, 0);
+	attr.test.ctx_in = ptr_to_u64(OPTS_GET(opts, ctx_in, NULL));
+	attr.test.ctx_out = ptr_to_u64(OPTS_GET(opts, ctx_out, NULL));
+	attr.test.data_in = ptr_to_u64(OPTS_GET(opts, data_in, NULL));
+	attr.test.data_out = ptr_to_u64(OPTS_GET(opts, data_out, NULL));
+
+	ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));
+	OPTS_SET(opts, data_size_out, attr.test.data_size_out);
+	OPTS_SET(opts, ctx_size_out, attr.test.ctx_size_out);
+	OPTS_SET(opts, duration, attr.test.duration);
+	OPTS_SET(opts, retval, attr.test.retval);
+	return ret;
+}
+
 static int bpf_obj_get_next_id(__u32 start_id, __u32 *next_id, int cmd)
 {
 	union bpf_attr attr;
@@ -815,7 +858,7 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd)
 	return sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
 }
 
-int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
+int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
 		 bool do_log)
 {
 	union bpf_attr attr = {};
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 8c1ac4b42f90..875dde20d56e 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -174,8 +174,9 @@ struct bpf_link_create_opts {
 	__u32 flags;
 	union bpf_iter_link_info *iter_info;
 	__u32 iter_info_len;
+	__u32 target_btf_id;
 };
-#define bpf_link_create_opts__last_field iter_info_len
+#define bpf_link_create_opts__last_field target_btf_id
 
 LIBBPF_API int bpf_link_create(int prog_fd, int target_fd,
 			       enum bpf_attach_type attach_type,
@@ -234,7 +235,7 @@ 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);
 LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd);
-LIBBPF_API int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf,
+LIBBPF_API int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf,
 			    __u32 log_buf_size, bool do_log);
 LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf,
 				 __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
@@ -251,6 +252,32 @@ struct bpf_prog_bind_opts {
 
 LIBBPF_API int bpf_prog_bind_map(int prog_fd, int map_fd,
 				 const struct bpf_prog_bind_opts *opts);
+
+struct bpf_test_run_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	const void *data_in; /* optional */
+	void *data_out;      /* optional */
+	__u32 data_size_in;
+	__u32 data_size_out; /* in: max length of data_out
+			      * out: length of data_out
+			      */
+	const void *ctx_in; /* optional */
+	void *ctx_out;      /* optional */
+	__u32 ctx_size_in;
+	__u32 ctx_size_out; /* in: max length of ctx_out
+			     * out: length of cxt_out
+			     */
+	__u32 retval;        /* out: return code of the BPF program */
+	int repeat;
+	__u32 duration;      /* out: average per repetition in ns */
+	__u32 flags;
+	__u32 cpu;
+};
+#define bpf_test_run_opts__last_field cpu
+
+LIBBPF_API int bpf_prog_test_run_opts(int prog_fd,
+				      struct bpf_test_run_opts *opts);
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index 1106777df00b..2bdb7d6dbad2 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -54,6 +54,52 @@
 #endif
 
 /*
+ * Helper macro to throw a compilation error if __bpf_unreachable() gets
+ * built into the resulting code. This works given BPF back end does not
+ * implement __builtin_trap(). This is useful to assert that certain paths
+ * of the program code are never used and hence eliminated by the compiler.
+ *
+ * For example, consider a switch statement that covers known cases used by
+ * the program. __bpf_unreachable() can then reside in the default case. If
+ * the program gets extended such that a case is not covered in the switch
+ * statement, then it will throw a build error due to the default case not
+ * being compiled out.
+ */
+#ifndef __bpf_unreachable
+# define __bpf_unreachable()	__builtin_trap()
+#endif
+
+/*
+ * Helper function to perform a tail call with a constant/immediate map slot.
+ */
+static __always_inline void
+bpf_tail_call_static(void *ctx, const void *map, const __u32 slot)
+{
+	if (!__builtin_constant_p(slot))
+		__bpf_unreachable();
+
+	/*
+	 * Provide a hard guarantee that LLVM won't optimize setting r2 (map
+	 * pointer) and r3 (constant map index) from _different paths_ ending
+	 * up at the _same_ call insn as otherwise we won't be able to use the
+	 * jmpq/nopl retpoline-free patching by the x86-64 JIT in the kernel
+	 * given they mismatch. See also d2e4c1e6c294 ("bpf: Constant map key
+	 * tracking for prog array pokes") for details on verifier tracking.
+	 *
+	 * Note on clobber list: we need to stay in-line with BPF calling
+	 * convention, so even if we don't end up using r0, r4, r5, we need
+	 * to mark them as clobber so that LLVM doesn't end up using them
+	 * before / after the call.
+	 */
+	asm volatile("r1 = %[ctx]\n\t"
+		     "r2 = %[map]\n\t"
+		     "r3 = %[slot]\n\t"
+		     "call 12"
+		     :: [ctx]"r"(ctx), [map]"r"(map), [slot]"i"(slot)
+		     : "r0", "r1", "r2", "r3", "r4", "r5");
+}
+
+/*
  * Helper structure used by eBPF C program
  * to describe BPF map attributes to libbpf loader
  */
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index a3d259e614b0..231b07203e3d 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 /* Copyright (c) 2018 Facebook */
 
+#include <byteswap.h>
 #include <endian.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -27,17 +28,72 @@
 static struct btf_type btf_void;
 
 struct btf {
-	union {
-		struct btf_header *hdr;
-		void *data;
-	};
-	struct btf_type **types;
-	const char *strings;
-	void *nohdr_data;
+	/* raw BTF data in native endianness */
+	void *raw_data;
+	/* raw BTF data in non-native endianness */
+	void *raw_data_swapped;
+	__u32 raw_size;
+	/* whether target endianness differs from the native one */
+	bool swapped_endian;
+
+	/*
+	 * When BTF is loaded from an ELF or raw memory it is stored
+	 * in a contiguous memory block. The hdr, type_data, and, strs_data
+	 * point inside that memory region to their respective parts of BTF
+	 * representation:
+	 *
+	 * +--------------------------------+
+	 * |  Header  |  Types  |  Strings  |
+	 * +--------------------------------+
+	 * ^          ^         ^
+	 * |          |         |
+	 * hdr        |         |
+	 * types_data-+         |
+	 * strs_data------------+
+	 *
+	 * If BTF data is later modified, e.g., due to types added or
+	 * removed, BTF deduplication performed, etc, this contiguous
+	 * representation is broken up into three independently allocated
+	 * memory regions to be able to modify them independently.
+	 * raw_data is nulled out at that point, but can be later allocated
+	 * and cached again if user calls btf__get_raw_data(), at which point
+	 * raw_data will contain a contiguous copy of header, types, and
+	 * strings:
+	 *
+	 * +----------+  +---------+  +-----------+
+	 * |  Header  |  |  Types  |  |  Strings  |
+	 * +----------+  +---------+  +-----------+
+	 * ^             ^            ^
+	 * |             |            |
+	 * hdr           |            |
+	 * types_data----+            |
+	 * strs_data------------------+
+	 *
+	 *               +----------+---------+-----------+
+	 *               |  Header  |  Types  |  Strings  |
+	 * raw_data----->+----------+---------+-----------+
+	 */
+	struct btf_header *hdr;
+
+	void *types_data;
+	size_t types_data_cap; /* used size stored in hdr->type_len */
+
+	/* type ID to `struct btf_type *` lookup index */
+	__u32 *type_offs;
+	size_t type_offs_cap;
 	__u32 nr_types;
-	__u32 types_size;
-	__u32 data_size;
+
+	void *strs_data;
+	size_t strs_data_cap; /* used size stored in hdr->str_len */
+
+	/* lookup index for each unique string in strings section */
+	struct hashmap *strs_hash;
+	/* whether strings are already deduplicated */
+	bool strs_deduped;
+	/* BTF object FD, if loaded into kernel */
 	int fd;
+
+	/* Pointer size (in bytes) for a target architecture of this BTF */
 	int ptr_sz;
 };
 
@@ -46,60 +102,114 @@ 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)
+/* Ensure given dynamically allocated memory region pointed to by *data* with
+ * capacity of *cap_cnt* elements each taking *elem_sz* bytes has enough
+ * memory to accomodate *add_cnt* new elements, assuming *cur_cnt* elements
+ * are already used. At most *max_cnt* elements can be ever allocated.
+ * If necessary, memory is reallocated and all existing data is copied over,
+ * new pointer to the memory region is stored at *data, new memory region
+ * capacity (in number of elements) is stored in *cap.
+ * On success, memory pointer to the beginning of unused memory is returned.
+ * On error, NULL is returned.
+ */
+void *btf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz,
+		  size_t cur_cnt, size_t max_cnt, size_t add_cnt)
 {
-	if (btf->types_size - btf->nr_types < 2) {
-		struct btf_type **new_types;
-		__u32 expand_by, new_size;
+	size_t new_cnt;
+	void *new_data;
 
-		if (btf->types_size == BTF_MAX_NR_TYPES)
-			return -E2BIG;
+	if (cur_cnt + add_cnt <= *cap_cnt)
+		return *data + cur_cnt * elem_sz;
 
-		expand_by = max(btf->types_size >> 2, 16U);
-		new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by);
+	/* requested more than the set limit */
+	if (cur_cnt + add_cnt > max_cnt)
+		return NULL;
 
-		new_types = libbpf_reallocarray(btf->types, new_size, sizeof(*new_types));
-		if (!new_types)
-			return -ENOMEM;
+	new_cnt = *cap_cnt;
+	new_cnt += new_cnt / 4;		  /* expand by 25% */
+	if (new_cnt < 16)		  /* but at least 16 elements */
+		new_cnt = 16;
+	if (new_cnt > max_cnt)		  /* but not exceeding a set limit */
+		new_cnt = max_cnt;
+	if (new_cnt < cur_cnt + add_cnt)  /* also ensure we have enough memory */
+		new_cnt = cur_cnt + add_cnt;
+
+	new_data = libbpf_reallocarray(*data, new_cnt, elem_sz);
+	if (!new_data)
+		return NULL;
 
-		if (btf->nr_types == 0)
-			new_types[0] = &btf_void;
+	/* zero out newly allocated portion of memory */
+	memset(new_data + (*cap_cnt) * elem_sz, 0, (new_cnt - *cap_cnt) * elem_sz);
 
-		btf->types = new_types;
-		btf->types_size = new_size;
-	}
+	*data = new_data;
+	*cap_cnt = new_cnt;
+	return new_data + cur_cnt * elem_sz;
+}
+
+/* Ensure given dynamically allocated memory region has enough allocated space
+ * to accommodate *need_cnt* elements of size *elem_sz* bytes each
+ */
+int btf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_cnt)
+{
+	void *p;
+
+	if (need_cnt <= *cap_cnt)
+		return 0;
+
+	p = btf_add_mem(data, cap_cnt, elem_sz, *cap_cnt, SIZE_MAX, need_cnt - *cap_cnt);
+	if (!p)
+		return -ENOMEM;
+
+	return 0;
+}
 
-	btf->types[++(btf->nr_types)] = t;
+static int btf_add_type_idx_entry(struct btf *btf, __u32 type_off)
+{
+	__u32 *p;
 
+	p = btf_add_mem((void **)&btf->type_offs, &btf->type_offs_cap, sizeof(__u32),
+			btf->nr_types + 1, BTF_MAX_NR_TYPES, 1);
+	if (!p)
+		return -ENOMEM;
+
+	*p = type_off;
 	return 0;
 }
 
+static void btf_bswap_hdr(struct btf_header *h)
+{
+	h->magic = bswap_16(h->magic);
+	h->hdr_len = bswap_32(h->hdr_len);
+	h->type_off = bswap_32(h->type_off);
+	h->type_len = bswap_32(h->type_len);
+	h->str_off = bswap_32(h->str_off);
+	h->str_len = bswap_32(h->str_len);
+}
+
 static int btf_parse_hdr(struct btf *btf)
 {
-	const struct btf_header *hdr = btf->hdr;
+	struct btf_header *hdr = btf->hdr;
 	__u32 meta_left;
 
-	if (btf->data_size < sizeof(struct btf_header)) {
+	if (btf->raw_size < sizeof(struct btf_header)) {
 		pr_debug("BTF header not found\n");
 		return -EINVAL;
 	}
 
-	if (hdr->magic != BTF_MAGIC) {
+	if (hdr->magic == bswap_16(BTF_MAGIC)) {
+		btf->swapped_endian = true;
+		if (bswap_32(hdr->hdr_len) != sizeof(struct btf_header)) {
+			pr_warn("Can't load BTF with non-native endianness due to unsupported header length %u\n",
+				bswap_32(hdr->hdr_len));
+			return -ENOTSUP;
+		}
+		btf_bswap_hdr(hdr);
+	} else if (hdr->magic != BTF_MAGIC) {
 		pr_debug("Invalid BTF magic:%x\n", hdr->magic);
 		return -EINVAL;
 	}
 
-	if (hdr->version != BTF_VERSION) {
-		pr_debug("Unsupported BTF version:%u\n", hdr->version);
-		return -ENOTSUP;
-	}
-
-	if (hdr->flags) {
-		pr_debug("Unsupported BTF flags:%x\n", hdr->flags);
-		return -ENOTSUP;
-	}
-
-	meta_left = btf->data_size - sizeof(*hdr);
+	meta_left = btf->raw_size - sizeof(*hdr);
 	if (!meta_left) {
 		pr_debug("BTF has no data\n");
 		return -EINVAL;
@@ -125,15 +235,13 @@ static int btf_parse_hdr(struct btf *btf)
 		return -EINVAL;
 	}
 
-	btf->nohdr_data = btf->hdr + 1;
-
 	return 0;
 }
 
 static int btf_parse_str_sec(struct btf *btf)
 {
 	const struct btf_header *hdr = btf->hdr;
-	const char *start = btf->nohdr_data + hdr->str_off;
+	const char *start = btf->strs_data;
 	const char *end = start + btf->hdr->str_len;
 
 	if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_STR_OFFSET ||
@@ -142,14 +250,12 @@ static int btf_parse_str_sec(struct btf *btf)
 		return -EINVAL;
 	}
 
-	btf->strings = start;
-
 	return 0;
 }
 
-static int btf_type_size(struct btf_type *t)
+static int btf_type_size(const struct btf_type *t)
 {
-	int base_size = sizeof(struct btf_type);
+	const int base_size = sizeof(struct btf_type);
 	__u16 vlen = btf_vlen(t);
 
 	switch (btf_kind(t)) {
@@ -182,25 +288,120 @@ static int btf_type_size(struct btf_type *t)
 	}
 }
 
+static void btf_bswap_type_base(struct btf_type *t)
+{
+	t->name_off = bswap_32(t->name_off);
+	t->info = bswap_32(t->info);
+	t->type = bswap_32(t->type);
+}
+
+static int btf_bswap_type_rest(struct btf_type *t)
+{
+	struct btf_var_secinfo *v;
+	struct btf_member *m;
+	struct btf_array *a;
+	struct btf_param *p;
+	struct btf_enum *e;
+	__u16 vlen = btf_vlen(t);
+	int i;
+
+	switch (btf_kind(t)) {
+	case BTF_KIND_FWD:
+	case BTF_KIND_CONST:
+	case BTF_KIND_VOLATILE:
+	case BTF_KIND_RESTRICT:
+	case BTF_KIND_PTR:
+	case BTF_KIND_TYPEDEF:
+	case BTF_KIND_FUNC:
+		return 0;
+	case BTF_KIND_INT:
+		*(__u32 *)(t + 1) = bswap_32(*(__u32 *)(t + 1));
+		return 0;
+	case BTF_KIND_ENUM:
+		for (i = 0, e = btf_enum(t); i < vlen; i++, e++) {
+			e->name_off = bswap_32(e->name_off);
+			e->val = bswap_32(e->val);
+		}
+		return 0;
+	case BTF_KIND_ARRAY:
+		a = btf_array(t);
+		a->type = bswap_32(a->type);
+		a->index_type = bswap_32(a->index_type);
+		a->nelems = bswap_32(a->nelems);
+		return 0;
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION:
+		for (i = 0, m = btf_members(t); i < vlen; i++, m++) {
+			m->name_off = bswap_32(m->name_off);
+			m->type = bswap_32(m->type);
+			m->offset = bswap_32(m->offset);
+		}
+		return 0;
+	case BTF_KIND_FUNC_PROTO:
+		for (i = 0, p = btf_params(t); i < vlen; i++, p++) {
+			p->name_off = bswap_32(p->name_off);
+			p->type = bswap_32(p->type);
+		}
+		return 0;
+	case BTF_KIND_VAR:
+		btf_var(t)->linkage = bswap_32(btf_var(t)->linkage);
+		return 0;
+	case BTF_KIND_DATASEC:
+		for (i = 0, v = btf_var_secinfos(t); i < vlen; i++, v++) {
+			v->type = bswap_32(v->type);
+			v->offset = bswap_32(v->offset);
+			v->size = bswap_32(v->size);
+		}
+		return 0;
+	default:
+		pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t));
+		return -EINVAL;
+	}
+}
+
 static int btf_parse_type_sec(struct btf *btf)
 {
 	struct btf_header *hdr = btf->hdr;
-	void *nohdr_data = btf->nohdr_data;
-	void *next_type = nohdr_data + hdr->type_off;
-	void *end_type = nohdr_data + hdr->str_off;
+	void *next_type = btf->types_data;
+	void *end_type = next_type + hdr->type_len;
+	int err, i = 0, type_size;
 
-	while (next_type < end_type) {
-		struct btf_type *t = next_type;
-		int type_size;
-		int err;
+	/* VOID (type_id == 0) is specially handled by btf__get_type_by_id(),
+	 * so ensure we can never properly use its offset from index by
+	 * setting it to a large value
+	 */
+	err = btf_add_type_idx_entry(btf, UINT_MAX);
+	if (err)
+		return err;
+
+	while (next_type + sizeof(struct btf_type) <= end_type) {
+		i++;
+
+		if (btf->swapped_endian)
+			btf_bswap_type_base(next_type);
 
-		type_size = btf_type_size(t);
+		type_size = btf_type_size(next_type);
 		if (type_size < 0)
 			return type_size;
-		next_type += type_size;
-		err = btf_add_type(btf, t);
+		if (next_type + type_size > end_type) {
+			pr_warn("BTF type [%d] is malformed\n", i);
+			return -EINVAL;
+		}
+
+		if (btf->swapped_endian && btf_bswap_type_rest(next_type))
+			return -EINVAL;
+
+		err = btf_add_type_idx_entry(btf, next_type - btf->types_data);
 		if (err)
 			return err;
+
+		next_type += type_size;
+		btf->nr_types++;
+	}
+
+	if (next_type != end_type) {
+		pr_warn("BTF types data is malformed\n");
+		return -EINVAL;
 	}
 
 	return 0;
@@ -211,12 +412,20 @@ __u32 btf__get_nr_types(const struct btf *btf)
 	return btf->nr_types;
 }
 
+/* internal helper returning non-const pointer to a type */
+static struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id)
+{
+	if (type_id == 0)
+		return &btf_void;
+
+	return btf->types_data + btf->type_offs[type_id];
+}
+
 const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id)
 {
 	if (type_id > btf->nr_types)
 		return NULL;
-
-	return btf->types[type_id];
+	return btf_type_by_id((struct btf *)btf, type_id);
 }
 
 static int determine_ptr_size(const struct btf *btf)
@@ -283,6 +492,38 @@ int btf__set_pointer_size(struct btf *btf, size_t ptr_sz)
 	return 0;
 }
 
+static bool is_host_big_endian(void)
+{
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+	return false;
+#elif __BYTE_ORDER == __BIG_ENDIAN
+	return true;
+#else
+# error "Unrecognized __BYTE_ORDER__"
+#endif
+}
+
+enum btf_endianness btf__endianness(const struct btf *btf)
+{
+	if (is_host_big_endian())
+		return btf->swapped_endian ? BTF_LITTLE_ENDIAN : BTF_BIG_ENDIAN;
+	else
+		return btf->swapped_endian ? BTF_BIG_ENDIAN : BTF_LITTLE_ENDIAN;
+}
+
+int btf__set_endianness(struct btf *btf, enum btf_endianness endian)
+{
+	if (endian != BTF_LITTLE_ENDIAN && endian != BTF_BIG_ENDIAN)
+		return -EINVAL;
+
+	btf->swapped_endian = is_host_big_endian() != (endian == BTF_BIG_ENDIAN);
+	if (!btf->swapped_endian) {
+		free(btf->raw_data_swapped);
+		btf->raw_data_swapped = NULL;
+	}
+	return 0;
+}
+
 static bool btf_type_is_void(const struct btf_type *t)
 {
 	return t == &btf_void || btf_is_fwd(t);
@@ -414,7 +655,7 @@ __s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 		return 0;
 
 	for (i = 1; i <= btf->nr_types; i++) {
-		const struct btf_type *t = btf->types[i];
+		const struct btf_type *t = btf__type_by_id(btf, i);
 		const char *name = btf__name_by_offset(btf, t->name_off);
 
 		if (name && !strcmp(type_name, name))
@@ -433,7 +674,7 @@ __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
 		return 0;
 
 	for (i = 1; i <= btf->nr_types; i++) {
-		const struct btf_type *t = btf->types[i];
+		const struct btf_type *t = btf__type_by_id(btf, i);
 		const char *name;
 
 		if (btf_kind(t) != kind)
@@ -446,6 +687,11 @@ __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
 	return -ENOENT;
 }
 
+static bool btf_is_modifiable(const struct btf *btf)
+{
+	return (void *)btf->hdr != btf->raw_data;
+}
+
 void btf__free(struct btf *btf)
 {
 	if (IS_ERR_OR_NULL(btf))
@@ -454,11 +700,55 @@ void btf__free(struct btf *btf)
 	if (btf->fd >= 0)
 		close(btf->fd);
 
-	free(btf->data);
-	free(btf->types);
+	if (btf_is_modifiable(btf)) {
+		/* if BTF was modified after loading, it will have a split
+		 * in-memory representation for header, types, and strings
+		 * sections, so we need to free all of them individually. It
+		 * might still have a cached contiguous raw data present,
+		 * which will be unconditionally freed below.
+		 */
+		free(btf->hdr);
+		free(btf->types_data);
+		free(btf->strs_data);
+	}
+	free(btf->raw_data);
+	free(btf->raw_data_swapped);
+	free(btf->type_offs);
 	free(btf);
 }
 
+struct btf *btf__new_empty(void)
+{
+	struct btf *btf;
+
+	btf = calloc(1, sizeof(*btf));
+	if (!btf)
+		return ERR_PTR(-ENOMEM);
+
+	btf->fd = -1;
+	btf->ptr_sz = sizeof(void *);
+	btf->swapped_endian = false;
+
+	/* +1 for empty string at offset 0 */
+	btf->raw_size = sizeof(struct btf_header) + 1;
+	btf->raw_data = calloc(1, btf->raw_size);
+	if (!btf->raw_data) {
+		free(btf);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	btf->hdr = btf->raw_data;
+	btf->hdr->hdr_len = sizeof(struct btf_header);
+	btf->hdr->magic = BTF_MAGIC;
+	btf->hdr->version = BTF_VERSION;
+
+	btf->types_data = btf->raw_data + btf->hdr->hdr_len;
+	btf->strs_data = btf->raw_data + btf->hdr->hdr_len;
+	btf->hdr->str_len = 1; /* empty string at offset 0 */
+
+	return btf;
+}
+
 struct btf *btf__new(const void *data, __u32 size)
 {
 	struct btf *btf;
@@ -468,26 +758,28 @@ struct btf *btf__new(const void *data, __u32 size)
 	if (!btf)
 		return ERR_PTR(-ENOMEM);
 
-	btf->fd = -1;
-
-	btf->data = malloc(size);
-	if (!btf->data) {
+	btf->raw_data = malloc(size);
+	if (!btf->raw_data) {
 		err = -ENOMEM;
 		goto done;
 	}
+	memcpy(btf->raw_data, data, size);
+	btf->raw_size = size;
 
-	memcpy(btf->data, data, size);
-	btf->data_size = size;
-
+	btf->hdr = btf->raw_data;
 	err = btf_parse_hdr(btf);
 	if (err)
 		goto done;
 
+	btf->strs_data = btf->raw_data + btf->hdr->hdr_len + btf->hdr->str_off;
+	btf->types_data = btf->raw_data + btf->hdr->hdr_len + btf->hdr->type_off;
+
 	err = btf_parse_str_sec(btf);
+	err = err ?: btf_parse_type_sec(btf);
 	if (err)
 		goto done;
 
-	err = btf_parse_type_sec(btf);
+	btf->fd = -1;
 
 done:
 	if (err) {
@@ -498,17 +790,6 @@ done:
 	return btf;
 }
 
-static bool btf_check_endianness(const GElf_Ehdr *ehdr)
-{
-#if __BYTE_ORDER == __LITTLE_ENDIAN
-	return ehdr->e_ident[EI_DATA] == ELFDATA2LSB;
-#elif __BYTE_ORDER == __BIG_ENDIAN
-	return ehdr->e_ident[EI_DATA] == ELFDATA2MSB;
-#else
-# error "Unrecognized __BYTE_ORDER__"
-#endif
-}
-
 struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext)
 {
 	Elf_Data *btf_data = NULL, *btf_ext_data = NULL;
@@ -541,10 +822,6 @@ struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext)
 		pr_warn("failed to get EHDR from %s\n", path);
 		goto done;
 	}
-	if (!btf_check_endianness(&ehdr)) {
-		pr_warn("non-native ELF endianness is not supported\n");
-		goto done;
-	}
 	if (!elf_rawdata(elf_getscn(elf, ehdr.e_shstrndx), NULL)) {
 		pr_warn("failed to get e_shstrndx from %s\n", path);
 		goto done;
@@ -656,7 +933,7 @@ struct btf *btf__parse_raw(const char *path)
 		err = -EIO;
 		goto err_out;
 	}
-	if (magic != BTF_MAGIC) {
+	if (magic != BTF_MAGIC && magic != bswap_16(BTF_MAGIC)) {
 		/* definitely not a raw BTF */
 		err = -EPROTO;
 		goto err_out;
@@ -789,7 +1066,7 @@ int btf__finalize_data(struct bpf_object *obj, struct btf *btf)
 	__u32 i;
 
 	for (i = 1; i <= btf->nr_types; i++) {
-		struct btf_type *t = btf->types[i];
+		struct btf_type *t = btf_type_by_id(btf, i);
 
 		/* Loader needs to fix up some of the things compiler
 		 * couldn't get its hands on while emitting BTF. This
@@ -806,10 +1083,13 @@ int btf__finalize_data(struct bpf_object *obj, struct btf *btf)
 	return err;
 }
 
+static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian);
+
 int btf__load(struct btf *btf)
 {
-	__u32 log_buf_size = 0;
+	__u32 log_buf_size = 0, raw_size;
 	char *log_buf = NULL;
+	void *raw_data;
 	int err = 0;
 
 	if (btf->fd >= 0)
@@ -824,8 +1104,16 @@ retry_load:
 		*log_buf = 0;
 	}
 
-	btf->fd = bpf_load_btf(btf->data, btf->data_size,
-			       log_buf, log_buf_size, false);
+	raw_data = btf_get_raw_data(btf, &raw_size, false);
+	if (!raw_data) {
+		err = -ENOMEM;
+		goto done;
+	}
+	/* cache native raw data representation */
+	btf->raw_size = raw_size;
+	btf->raw_data = raw_data;
+
+	btf->fd = bpf_load_btf(raw_data, raw_size, log_buf, log_buf_size, false);
 	if (btf->fd < 0) {
 		if (!log_buf || errno == ENOSPC) {
 			log_buf_size = max((__u32)BPF_LOG_BUF_SIZE,
@@ -856,20 +1144,88 @@ void btf__set_fd(struct btf *btf, int fd)
 	btf->fd = fd;
 }
 
-const void *btf__get_raw_data(const struct btf *btf, __u32 *size)
+static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian)
+{
+	struct btf_header *hdr = btf->hdr;
+	struct btf_type *t;
+	void *data, *p;
+	__u32 data_sz;
+	int i;
+
+	data = swap_endian ? btf->raw_data_swapped : btf->raw_data;
+	if (data) {
+		*size = btf->raw_size;
+		return data;
+	}
+
+	data_sz = hdr->hdr_len + hdr->type_len + hdr->str_len;
+	data = calloc(1, data_sz);
+	if (!data)
+		return NULL;
+	p = data;
+
+	memcpy(p, hdr, hdr->hdr_len);
+	if (swap_endian)
+		btf_bswap_hdr(p);
+	p += hdr->hdr_len;
+
+	memcpy(p, btf->types_data, hdr->type_len);
+	if (swap_endian) {
+		for (i = 1; i <= btf->nr_types; i++) {
+			t = p  + btf->type_offs[i];
+			/* btf_bswap_type_rest() relies on native t->info, so
+			 * we swap base type info after we swapped all the
+			 * additional information
+			 */
+			if (btf_bswap_type_rest(t))
+				goto err_out;
+			btf_bswap_type_base(t);
+		}
+	}
+	p += hdr->type_len;
+
+	memcpy(p, btf->strs_data, hdr->str_len);
+	p += hdr->str_len;
+
+	*size = data_sz;
+	return data;
+err_out:
+	free(data);
+	return NULL;
+}
+
+const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size)
 {
-	*size = btf->data_size;
-	return btf->data;
+	struct btf *btf = (struct btf *)btf_ro;
+	__u32 data_sz;
+	void *data;
+
+	data = btf_get_raw_data(btf, &data_sz, btf->swapped_endian);
+	if (!data)
+		return NULL;
+
+	btf->raw_size = data_sz;
+	if (btf->swapped_endian)
+		btf->raw_data_swapped = data;
+	else
+		btf->raw_data = data;
+	*size = data_sz;
+	return data;
 }
 
-const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
+const char *btf__str_by_offset(const struct btf *btf, __u32 offset)
 {
 	if (offset < btf->hdr->str_len)
-		return &btf->strings[offset];
+		return btf->strs_data + offset;
 	else
 		return NULL;
 }
 
+const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
+{
+	return btf__str_by_offset(btf, offset);
+}
+
 int btf__get_from_id(__u32 id, struct btf **btf)
 {
 	struct bpf_btf_info btf_info = { 0 };
@@ -1005,6 +1361,970 @@ int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
 	return 0;
 }
 
+static size_t strs_hash_fn(const void *key, void *ctx)
+{
+	struct btf *btf = ctx;
+	const char *str = btf->strs_data + (long)key;
+
+	return str_hash(str);
+}
+
+static bool strs_hash_equal_fn(const void *key1, const void *key2, void *ctx)
+{
+	struct btf *btf = ctx;
+	const char *str1 = btf->strs_data + (long)key1;
+	const char *str2 = btf->strs_data + (long)key2;
+
+	return strcmp(str1, str2) == 0;
+}
+
+static void btf_invalidate_raw_data(struct btf *btf)
+{
+	if (btf->raw_data) {
+		free(btf->raw_data);
+		btf->raw_data = NULL;
+	}
+	if (btf->raw_data_swapped) {
+		free(btf->raw_data_swapped);
+		btf->raw_data_swapped = NULL;
+	}
+}
+
+/* Ensure BTF is ready to be modified (by splitting into a three memory
+ * regions for header, types, and strings). Also invalidate cached
+ * raw_data, if any.
+ */
+static int btf_ensure_modifiable(struct btf *btf)
+{
+	void *hdr, *types, *strs, *strs_end, *s;
+	struct hashmap *hash = NULL;
+	long off;
+	int err;
+
+	if (btf_is_modifiable(btf)) {
+		/* any BTF modification invalidates raw_data */
+		btf_invalidate_raw_data(btf);
+		return 0;
+	}
+
+	/* split raw data into three memory regions */
+	hdr = malloc(btf->hdr->hdr_len);
+	types = malloc(btf->hdr->type_len);
+	strs = malloc(btf->hdr->str_len);
+	if (!hdr || !types || !strs)
+		goto err_out;
+
+	memcpy(hdr, btf->hdr, btf->hdr->hdr_len);
+	memcpy(types, btf->types_data, btf->hdr->type_len);
+	memcpy(strs, btf->strs_data, btf->hdr->str_len);
+
+	/* build lookup index for all strings */
+	hash = hashmap__new(strs_hash_fn, strs_hash_equal_fn, btf);
+	if (IS_ERR(hash)) {
+		err = PTR_ERR(hash);
+		hash = NULL;
+		goto err_out;
+	}
+
+	strs_end = strs + btf->hdr->str_len;
+	for (off = 0, s = strs; s < strs_end; off += strlen(s) + 1, s = strs + off) {
+		/* hashmap__add() returns EEXIST if string with the same
+		 * content already is in the hash map
+		 */
+		err = hashmap__add(hash, (void *)off, (void *)off);
+		if (err == -EEXIST)
+			continue; /* duplicate */
+		if (err)
+			goto err_out;
+	}
+
+	/* only when everything was successful, update internal state */
+	btf->hdr = hdr;
+	btf->types_data = types;
+	btf->types_data_cap = btf->hdr->type_len;
+	btf->strs_data = strs;
+	btf->strs_data_cap = btf->hdr->str_len;
+	btf->strs_hash = hash;
+	/* if BTF was created from scratch, all strings are guaranteed to be
+	 * unique and deduplicated
+	 */
+	btf->strs_deduped = btf->hdr->str_len <= 1;
+
+	/* invalidate raw_data representation */
+	btf_invalidate_raw_data(btf);
+
+	return 0;
+
+err_out:
+	hashmap__free(hash);
+	free(hdr);
+	free(types);
+	free(strs);
+	return -ENOMEM;
+}
+
+static void *btf_add_str_mem(struct btf *btf, size_t add_sz)
+{
+	return btf_add_mem(&btf->strs_data, &btf->strs_data_cap, 1,
+			   btf->hdr->str_len, BTF_MAX_STR_OFFSET, add_sz);
+}
+
+/* Find an offset in BTF string section that corresponds to a given string *s*.
+ * Returns:
+ *   - >0 offset into string section, if string is found;
+ *   - -ENOENT, if string is not in the string section;
+ *   - <0, on any other error.
+ */
+int btf__find_str(struct btf *btf, const char *s)
+{
+	long old_off, new_off, len;
+	void *p;
+
+	/* BTF needs to be in a modifiable state to build string lookup index */
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	/* see btf__add_str() for why we do this */
+	len = strlen(s) + 1;
+	p = btf_add_str_mem(btf, len);
+	if (!p)
+		return -ENOMEM;
+
+	new_off = btf->hdr->str_len;
+	memcpy(p, s, len);
+
+	if (hashmap__find(btf->strs_hash, (void *)new_off, (void **)&old_off))
+		return old_off;
+
+	return -ENOENT;
+}
+
+/* Add a string s to the BTF string section.
+ * Returns:
+ *   - > 0 offset into string section, on success;
+ *   - < 0, on error.
+ */
+int btf__add_str(struct btf *btf, const char *s)
+{
+	long old_off, new_off, len;
+	void *p;
+	int err;
+
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	/* Hashmap keys are always offsets within btf->strs_data, so to even
+	 * look up some string from the "outside", we need to first append it
+	 * at the end, so that it can be addressed with an offset. Luckily,
+	 * until btf->hdr->str_len is incremented, that string is just a piece
+	 * of garbage for the rest of BTF code, so no harm, no foul. On the
+	 * other hand, if the string is unique, it's already appended and
+	 * ready to be used, only a simple btf->hdr->str_len increment away.
+	 */
+	len = strlen(s) + 1;
+	p = btf_add_str_mem(btf, len);
+	if (!p)
+		return -ENOMEM;
+
+	new_off = btf->hdr->str_len;
+	memcpy(p, s, len);
+
+	/* Now attempt to add the string, but only if the string with the same
+	 * contents doesn't exist already (HASHMAP_ADD strategy). If such
+	 * string exists, we'll get its offset in old_off (that's old_key).
+	 */
+	err = hashmap__insert(btf->strs_hash, (void *)new_off, (void *)new_off,
+			      HASHMAP_ADD, (const void **)&old_off, NULL);
+	if (err == -EEXIST)
+		return old_off; /* duplicated string, return existing offset */
+	if (err)
+		return err;
+
+	btf->hdr->str_len += len; /* new unique string, adjust data length */
+	return new_off;
+}
+
+static void *btf_add_type_mem(struct btf *btf, size_t add_sz)
+{
+	return btf_add_mem(&btf->types_data, &btf->types_data_cap, 1,
+			   btf->hdr->type_len, UINT_MAX, add_sz);
+}
+
+static __u32 btf_type_info(int kind, int vlen, int kflag)
+{
+	return (kflag << 31) | (kind << 24) | vlen;
+}
+
+static void btf_type_inc_vlen(struct btf_type *t)
+{
+	t->info = btf_type_info(btf_kind(t), btf_vlen(t) + 1, btf_kflag(t));
+}
+
+/*
+ * Append new BTF_KIND_INT type with:
+ *   - *name* - non-empty, non-NULL type name;
+ *   - *sz* - power-of-2 (1, 2, 4, ..) size of the type, in bytes;
+ *   - encoding is a combination of BTF_INT_SIGNED, BTF_INT_CHAR, BTF_INT_BOOL.
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding)
+{
+	struct btf_type *t;
+	int sz, err, name_off;
+
+	/* non-empty name */
+	if (!name || !name[0])
+		return -EINVAL;
+	/* byte_sz must be power of 2 */
+	if (!byte_sz || (byte_sz & (byte_sz - 1)) || byte_sz > 16)
+		return -EINVAL;
+	if (encoding & ~(BTF_INT_SIGNED | BTF_INT_CHAR | BTF_INT_BOOL))
+		return -EINVAL;
+
+	/* deconstruct BTF, if necessary, and invalidate raw_data */
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_type) + sizeof(int);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return -ENOMEM;
+
+	/* if something goes wrong later, we might end up with an extra string,
+	 * but that shouldn't be a problem, because BTF can't be constructed
+	 * completely anyway and will most probably be just discarded
+	 */
+	name_off = btf__add_str(btf, name);
+	if (name_off < 0)
+		return name_off;
+
+	t->name_off = name_off;
+	t->info = btf_type_info(BTF_KIND_INT, 0, 0);
+	t->size = byte_sz;
+	/* set INT info, we don't allow setting legacy bit offset/size */
+	*(__u32 *)(t + 1) = (encoding << 24) | (byte_sz * 8);
+
+	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
+	if (err)
+		return err;
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	btf->nr_types++;
+	return btf->nr_types;
+}
+
+/* it's completely legal to append BTF types with type IDs pointing forward to
+ * types that haven't been appended yet, so we only make sure that id looks
+ * sane, we can't guarantee that ID will always be valid
+ */
+static int validate_type_id(int id)
+{
+	if (id < 0 || id > BTF_MAX_NR_TYPES)
+		return -EINVAL;
+	return 0;
+}
+
+/* generic append function for PTR, TYPEDEF, CONST/VOLATILE/RESTRICT */
+static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref_type_id)
+{
+	struct btf_type *t;
+	int sz, name_off = 0, err;
+
+	if (validate_type_id(ref_type_id))
+		return -EINVAL;
+
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_type);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return -ENOMEM;
+
+	if (name && name[0]) {
+		name_off = btf__add_str(btf, name);
+		if (name_off < 0)
+			return name_off;
+	}
+
+	t->name_off = name_off;
+	t->info = btf_type_info(kind, 0, 0);
+	t->type = ref_type_id;
+
+	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
+	if (err)
+		return err;
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	btf->nr_types++;
+	return btf->nr_types;
+}
+
+/*
+ * Append new BTF_KIND_PTR type with:
+ *   - *ref_type_id* - referenced type ID, it might not exist yet;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_ptr(struct btf *btf, int ref_type_id)
+{
+	return btf_add_ref_kind(btf, BTF_KIND_PTR, NULL, ref_type_id);
+}
+
+/*
+ * Append new BTF_KIND_ARRAY type with:
+ *   - *index_type_id* - type ID of the type describing array index;
+ *   - *elem_type_id* - type ID of the type describing array element;
+ *   - *nr_elems* - the size of the array;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_array(struct btf *btf, int index_type_id, int elem_type_id, __u32 nr_elems)
+{
+	struct btf_type *t;
+	struct btf_array *a;
+	int sz, err;
+
+	if (validate_type_id(index_type_id) || validate_type_id(elem_type_id))
+		return -EINVAL;
+
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_type) + sizeof(struct btf_array);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return -ENOMEM;
+
+	t->name_off = 0;
+	t->info = btf_type_info(BTF_KIND_ARRAY, 0, 0);
+	t->size = 0;
+
+	a = btf_array(t);
+	a->type = elem_type_id;
+	a->index_type = index_type_id;
+	a->nelems = nr_elems;
+
+	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
+	if (err)
+		return err;
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	btf->nr_types++;
+	return btf->nr_types;
+}
+
+/* generic STRUCT/UNION append function */
+static int btf_add_composite(struct btf *btf, int kind, const char *name, __u32 bytes_sz)
+{
+	struct btf_type *t;
+	int sz, err, name_off = 0;
+
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_type);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return -ENOMEM;
+
+	if (name && name[0]) {
+		name_off = btf__add_str(btf, name);
+		if (name_off < 0)
+			return name_off;
+	}
+
+	/* start out with vlen=0 and no kflag; this will be adjusted when
+	 * adding each member
+	 */
+	t->name_off = name_off;
+	t->info = btf_type_info(kind, 0, 0);
+	t->size = bytes_sz;
+
+	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
+	if (err)
+		return err;
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	btf->nr_types++;
+	return btf->nr_types;
+}
+
+/*
+ * Append new BTF_KIND_STRUCT type with:
+ *   - *name* - name of the struct, can be NULL or empty for anonymous structs;
+ *   - *byte_sz* - size of the struct, in bytes;
+ *
+ * Struct initially has no fields in it. Fields can be added by
+ * btf__add_field() right after btf__add_struct() succeeds. 
+ *
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_struct(struct btf *btf, const char *name, __u32 byte_sz)
+{
+	return btf_add_composite(btf, BTF_KIND_STRUCT, name, byte_sz);
+}
+
+/*
+ * Append new BTF_KIND_UNION type with:
+ *   - *name* - name of the union, can be NULL or empty for anonymous union;
+ *   - *byte_sz* - size of the union, in bytes;
+ *
+ * Union initially has no fields in it. Fields can be added by
+ * btf__add_field() right after btf__add_union() succeeds. All fields
+ * should have *bit_offset* of 0.
+ *
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_union(struct btf *btf, const char *name, __u32 byte_sz)
+{
+	return btf_add_composite(btf, BTF_KIND_UNION, name, byte_sz);
+}
+
+/*
+ * Append new field for the current STRUCT/UNION type with:
+ *   - *name* - name of the field, can be NULL or empty for anonymous field;
+ *   - *type_id* - type ID for the type describing field type;
+ *   - *bit_offset* - bit offset of the start of the field within struct/union;
+ *   - *bit_size* - bit size of a bitfield, 0 for non-bitfield fields;
+ * Returns:
+ *   -  0, on success;
+ *   - <0, on error.
+ */
+int btf__add_field(struct btf *btf, const char *name, int type_id,
+		   __u32 bit_offset, __u32 bit_size)
+{
+	struct btf_type *t;
+	struct btf_member *m;
+	bool is_bitfield;
+	int sz, name_off = 0;
+
+	/* last type should be union/struct */
+	if (btf->nr_types == 0)
+		return -EINVAL;
+	t = btf_type_by_id(btf, btf->nr_types);
+	if (!btf_is_composite(t))
+		return -EINVAL;
+
+	if (validate_type_id(type_id))
+		return -EINVAL;
+	/* best-effort bit field offset/size enforcement */
+	is_bitfield = bit_size || (bit_offset % 8 != 0);
+	if (is_bitfield && (bit_size == 0 || bit_size > 255 || bit_offset > 0xffffff))
+		return -EINVAL;
+
+	/* only offset 0 is allowed for unions */
+	if (btf_is_union(t) && bit_offset)
+		return -EINVAL;
+
+	/* decompose and invalidate raw data */
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_member);
+	m = btf_add_type_mem(btf, sz);
+	if (!m)
+		return -ENOMEM;
+
+	if (name && name[0]) {
+		name_off = btf__add_str(btf, name);
+		if (name_off < 0)
+			return name_off;
+	}
+
+	m->name_off = name_off;
+	m->type = type_id;
+	m->offset = bit_offset | (bit_size << 24);
+
+	/* btf_add_type_mem can invalidate t pointer */
+	t = btf_type_by_id(btf, btf->nr_types);
+	/* update parent type's vlen and kflag */
+	t->info = btf_type_info(btf_kind(t), btf_vlen(t) + 1, is_bitfield || btf_kflag(t));
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	return 0;
+}
+
+/*
+ * Append new BTF_KIND_ENUM type with:
+ *   - *name* - name of the enum, can be NULL or empty for anonymous enums;
+ *   - *byte_sz* - size of the enum, in bytes.
+ *
+ * Enum initially has no enum values in it (and corresponds to enum forward
+ * declaration). Enumerator values can be added by btf__add_enum_value()
+ * immediately after btf__add_enum() succeeds.
+ *
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_enum(struct btf *btf, const char *name, __u32 byte_sz)
+{
+	struct btf_type *t;
+	int sz, err, name_off = 0;
+
+	/* byte_sz must be power of 2 */
+	if (!byte_sz || (byte_sz & (byte_sz - 1)) || byte_sz > 8)
+		return -EINVAL;
+
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_type);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return -ENOMEM;
+
+	if (name && name[0]) {
+		name_off = btf__add_str(btf, name);
+		if (name_off < 0)
+			return name_off;
+	}
+
+	/* start out with vlen=0; it will be adjusted when adding enum values */
+	t->name_off = name_off;
+	t->info = btf_type_info(BTF_KIND_ENUM, 0, 0);
+	t->size = byte_sz;
+
+	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
+	if (err)
+		return err;
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	btf->nr_types++;
+	return btf->nr_types;
+}
+
+/*
+ * Append new enum value for the current ENUM type with:
+ *   - *name* - name of the enumerator value, can't be NULL or empty;
+ *   - *value* - integer value corresponding to enum value *name*;
+ * Returns:
+ *   -  0, on success;
+ *   - <0, on error.
+ */
+int btf__add_enum_value(struct btf *btf, const char *name, __s64 value)
+{
+	struct btf_type *t;
+	struct btf_enum *v;
+	int sz, name_off;
+
+	/* last type should be BTF_KIND_ENUM */
+	if (btf->nr_types == 0)
+		return -EINVAL;
+	t = btf_type_by_id(btf, btf->nr_types);
+	if (!btf_is_enum(t))
+		return -EINVAL;
+
+	/* non-empty name */
+	if (!name || !name[0])
+		return -EINVAL;
+	if (value < INT_MIN || value > UINT_MAX)
+		return -E2BIG;
+
+	/* decompose and invalidate raw data */
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_enum);
+	v = btf_add_type_mem(btf, sz);
+	if (!v)
+		return -ENOMEM;
+
+	name_off = btf__add_str(btf, name);
+	if (name_off < 0)
+		return name_off;
+
+	v->name_off = name_off;
+	v->val = value;
+
+	/* update parent type's vlen */
+	t = btf_type_by_id(btf, btf->nr_types);
+	btf_type_inc_vlen(t);
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	return 0;
+}
+
+/*
+ * Append new BTF_KIND_FWD type with:
+ *   - *name*, non-empty/non-NULL name;
+ *   - *fwd_kind*, kind of forward declaration, one of BTF_FWD_STRUCT,
+ *     BTF_FWD_UNION, or BTF_FWD_ENUM;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind)
+{
+	if (!name || !name[0])
+		return -EINVAL;
+
+	switch (fwd_kind) {
+	case BTF_FWD_STRUCT:
+	case BTF_FWD_UNION: {
+		struct btf_type *t;
+		int id;
+
+		id = btf_add_ref_kind(btf, BTF_KIND_FWD, name, 0);
+		if (id <= 0)
+			return id;
+		t = btf_type_by_id(btf, id);
+		t->info = btf_type_info(BTF_KIND_FWD, 0, fwd_kind == BTF_FWD_UNION);
+		return id;
+	}
+	case BTF_FWD_ENUM:
+		/* enum forward in BTF currently is just an enum with no enum
+		 * values; we also assume a standard 4-byte size for it
+		 */
+		return btf__add_enum(btf, name, sizeof(int));
+	default:
+		return -EINVAL;
+	}
+}
+
+/*
+ * Append new BTF_KING_TYPEDEF type with:
+ *   - *name*, non-empty/non-NULL name;
+ *   - *ref_type_id* - referenced type ID, it might not exist yet;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id)
+{
+	if (!name || !name[0])
+		return -EINVAL;
+
+	return btf_add_ref_kind(btf, BTF_KIND_TYPEDEF, name, ref_type_id);
+}
+
+/*
+ * Append new BTF_KIND_VOLATILE type with:
+ *   - *ref_type_id* - referenced type ID, it might not exist yet;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_volatile(struct btf *btf, int ref_type_id)
+{
+	return btf_add_ref_kind(btf, BTF_KIND_VOLATILE, NULL, ref_type_id);
+}
+
+/*
+ * Append new BTF_KIND_CONST type with:
+ *   - *ref_type_id* - referenced type ID, it might not exist yet;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_const(struct btf *btf, int ref_type_id)
+{
+	return btf_add_ref_kind(btf, BTF_KIND_CONST, NULL, ref_type_id);
+}
+
+/*
+ * Append new BTF_KIND_RESTRICT type with:
+ *   - *ref_type_id* - referenced type ID, it might not exist yet;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_restrict(struct btf *btf, int ref_type_id)
+{
+	return btf_add_ref_kind(btf, BTF_KIND_RESTRICT, NULL, ref_type_id);
+}
+
+/*
+ * Append new BTF_KIND_FUNC type with:
+ *   - *name*, non-empty/non-NULL name;
+ *   - *proto_type_id* - FUNC_PROTO's type ID, it might not exist yet;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_func(struct btf *btf, const char *name,
+		  enum btf_func_linkage linkage, int proto_type_id)
+{
+	int id;
+
+	if (!name || !name[0])
+		return -EINVAL;
+	if (linkage != BTF_FUNC_STATIC && linkage != BTF_FUNC_GLOBAL &&
+	    linkage != BTF_FUNC_EXTERN)
+		return -EINVAL;
+
+	id = btf_add_ref_kind(btf, BTF_KIND_FUNC, name, proto_type_id);
+	if (id > 0) {
+		struct btf_type *t = btf_type_by_id(btf, id);
+
+		t->info = btf_type_info(BTF_KIND_FUNC, linkage, 0);
+	}
+	return id;
+}
+
+/*
+ * Append new BTF_KIND_FUNC_PROTO with:
+ *   - *ret_type_id* - type ID for return result of a function.
+ *
+ * Function prototype initially has no arguments, but they can be added by
+ * btf__add_func_param() one by one, immediately after
+ * btf__add_func_proto() succeeded.
+ *
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_func_proto(struct btf *btf, int ret_type_id)
+{
+	struct btf_type *t;
+	int sz, err;
+
+	if (validate_type_id(ret_type_id))
+		return -EINVAL;
+
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_type);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return -ENOMEM;
+
+	/* start out with vlen=0; this will be adjusted when adding enum
+	 * values, if necessary
+	 */
+	t->name_off = 0;
+	t->info = btf_type_info(BTF_KIND_FUNC_PROTO, 0, 0);
+	t->type = ret_type_id;
+
+	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
+	if (err)
+		return err;
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	btf->nr_types++;
+	return btf->nr_types;
+}
+
+/*
+ * Append new function parameter for current FUNC_PROTO type with:
+ *   - *name* - parameter name, can be NULL or empty;
+ *   - *type_id* - type ID describing the type of the parameter.
+ * Returns:
+ *   -  0, on success;
+ *   - <0, on error.
+ */
+int btf__add_func_param(struct btf *btf, const char *name, int type_id)
+{
+	struct btf_type *t;
+	struct btf_param *p;
+	int sz, name_off = 0;
+
+	if (validate_type_id(type_id))
+		return -EINVAL;
+
+	/* last type should be BTF_KIND_FUNC_PROTO */
+	if (btf->nr_types == 0)
+		return -EINVAL;
+	t = btf_type_by_id(btf, btf->nr_types);
+	if (!btf_is_func_proto(t))
+		return -EINVAL;
+
+	/* decompose and invalidate raw data */
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_param);
+	p = btf_add_type_mem(btf, sz);
+	if (!p)
+		return -ENOMEM;
+
+	if (name && name[0]) {
+		name_off = btf__add_str(btf, name);
+		if (name_off < 0)
+			return name_off;
+	}
+
+	p->name_off = name_off;
+	p->type = type_id;
+
+	/* update parent type's vlen */
+	t = btf_type_by_id(btf, btf->nr_types);
+	btf_type_inc_vlen(t);
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	return 0;
+}
+
+/*
+ * Append new BTF_KIND_VAR type with:
+ *   - *name* - non-empty/non-NULL name;
+ *   - *linkage* - variable linkage, one of BTF_VAR_STATIC,
+ *     BTF_VAR_GLOBAL_ALLOCATED, or BTF_VAR_GLOBAL_EXTERN;
+ *   - *type_id* - type ID of the type describing the type of the variable.
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_var(struct btf *btf, const char *name, int linkage, int type_id)
+{
+	struct btf_type *t;
+	struct btf_var *v;
+	int sz, err, name_off;
+
+	/* non-empty name */
+	if (!name || !name[0])
+		return -EINVAL;
+	if (linkage != BTF_VAR_STATIC && linkage != BTF_VAR_GLOBAL_ALLOCATED &&
+	    linkage != BTF_VAR_GLOBAL_EXTERN)
+		return -EINVAL;
+	if (validate_type_id(type_id))
+		return -EINVAL;
+
+	/* deconstruct BTF, if necessary, and invalidate raw_data */
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_type) + sizeof(struct btf_var);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return -ENOMEM;
+
+	name_off = btf__add_str(btf, name);
+	if (name_off < 0)
+		return name_off;
+
+	t->name_off = name_off;
+	t->info = btf_type_info(BTF_KIND_VAR, 0, 0);
+	t->type = type_id;
+
+	v = btf_var(t);
+	v->linkage = linkage;
+
+	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
+	if (err)
+		return err;
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	btf->nr_types++;
+	return btf->nr_types;
+}
+
+/*
+ * Append new BTF_KIND_DATASEC type with:
+ *   - *name* - non-empty/non-NULL name;
+ *   - *byte_sz* - data section size, in bytes.
+ *
+ * Data section is initially empty. Variables info can be added with
+ * btf__add_datasec_var_info() calls, after btf__add_datasec() succeeds.
+ *
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz)
+{
+	struct btf_type *t;
+	int sz, err, name_off;
+
+	/* non-empty name */
+	if (!name || !name[0])
+		return -EINVAL;
+
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_type);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return -ENOMEM;
+
+	name_off = btf__add_str(btf, name);
+	if (name_off < 0)
+		return name_off;
+
+	/* start with vlen=0, which will be update as var_secinfos are added */
+	t->name_off = name_off;
+	t->info = btf_type_info(BTF_KIND_DATASEC, 0, 0);
+	t->size = byte_sz;
+
+	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
+	if (err)
+		return err;
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	btf->nr_types++;
+	return btf->nr_types;
+}
+
+/*
+ * Append new data section variable information entry for current DATASEC type:
+ *   - *var_type_id* - type ID, describing type of the variable;
+ *   - *offset* - variable offset within data section, in bytes;
+ *   - *byte_sz* - variable size, in bytes.
+ *
+ * Returns:
+ *   -  0, on success;
+ *   - <0, on error.
+ */
+int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __u32 byte_sz)
+{
+	struct btf_type *t;
+	struct btf_var_secinfo *v;
+	int sz;
+
+	/* last type should be BTF_KIND_DATASEC */
+	if (btf->nr_types == 0)
+		return -EINVAL;
+	t = btf_type_by_id(btf, btf->nr_types);
+	if (!btf_is_datasec(t))
+		return -EINVAL;
+
+	if (validate_type_id(var_type_id))
+		return -EINVAL;
+
+	/* decompose and invalidate raw data */
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
+	sz = sizeof(struct btf_var_secinfo);
+	v = btf_add_type_mem(btf, sz);
+	if (!v)
+		return -ENOMEM;
+
+	v->type = var_type_id;
+	v->offset = offset;
+	v->size = byte_sz;
+
+	/* update parent type's vlen */
+	t = btf_type_by_id(btf, btf->nr_types);
+	btf_type_inc_vlen(t);
+
+	btf->hdr->type_len += sz;
+	btf->hdr->str_off += sz;
+	return 0;
+}
+
 struct btf_ext_sec_setup_param {
 	__u32 off;
 	__u32 len;
@@ -1151,7 +2471,10 @@ static int btf_ext_parse_hdr(__u8 *data, __u32 data_size)
 		return -EINVAL;
 	}
 
-	if (hdr->magic != BTF_MAGIC) {
+	if (hdr->magic == bswap_16(BTF_MAGIC)) {
+		pr_warn("BTF.ext in non-native endianness is not supported\n");
+		return -ENOTSUP;
+	} else if (hdr->magic != BTF_MAGIC) {
 		pr_debug("Invalid BTF.ext magic:%x\n", hdr->magic);
 		return -EINVAL;
 	}
@@ -1471,6 +2794,9 @@ int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
 		return -EINVAL;
 	}
 
+	if (btf_ensure_modifiable(btf))
+		return -ENOMEM;
+
 	err = btf_dedup_strings(d);
 	if (err < 0) {
 		pr_debug("btf_dedup_strings failed:%d\n", err);
@@ -1655,7 +2981,7 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
 	/* special BTF "void" type is made canonical immediately */
 	d->map[0] = 0;
 	for (i = 1; i <= btf->nr_types; i++) {
-		struct btf_type *t = d->btf->types[i];
+		struct btf_type *t = btf_type_by_id(d->btf, i);
 
 		/* VAR and DATASEC are never deduped and are self-canonical */
 		if (btf_is_var(t) || btf_is_datasec(t))
@@ -1694,7 +3020,7 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx)
 	struct btf_type *t;
 
 	for (i = 1; i <= d->btf->nr_types; i++) {
-		t = d->btf->types[i];
+		t = btf_type_by_id(d->btf, i);
 		r = fn(&t->name_off, ctx);
 		if (r)
 			return r;
@@ -1848,8 +3174,7 @@ static int btf_str_remap_offset(__u32 *str_off_ptr, void *ctx)
  */
 static int btf_dedup_strings(struct btf_dedup *d)
 {
-	const struct btf_header *hdr = d->btf->hdr;
-	char *start = (char *)d->btf->nohdr_data + hdr->str_off;
+	char *start = d->btf->strs_data;
 	char *end = start + d->btf->hdr->str_len;
 	char *p = start, *tmp_strs = NULL;
 	struct btf_str_ptrs strs = {
@@ -1861,6 +3186,9 @@ static int btf_dedup_strings(struct btf_dedup *d)
 	int i, j, err = 0, grp_idx;
 	bool grp_used;
 
+	if (d->btf->strs_deduped)
+		return 0;
+
 	/* build index of all strings */
 	while (p < end) {
 		if (strs.cnt + 1 > strs.cap) {
@@ -1953,6 +3281,7 @@ static int btf_dedup_strings(struct btf_dedup *d)
 		goto done;
 
 	d->btf->hdr->str_len = end - start;
+	d->btf->strs_deduped = true;
 
 done:
 	free(tmp_strs);
@@ -2229,7 +3558,7 @@ static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2)
  */
 static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 {
-	struct btf_type *t = d->btf->types[type_id];
+	struct btf_type *t = btf_type_by_id(d->btf, type_id);
 	struct hashmap_entry *hash_entry;
 	struct btf_type *cand;
 	/* if we don't find equivalent type, then we are canonical */
@@ -2256,7 +3585,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 		h = btf_hash_int(t);
 		for_each_dedup_cand(d, hash_entry, h) {
 			cand_id = (__u32)(long)hash_entry->value;
-			cand = d->btf->types[cand_id];
+			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_int(t, cand)) {
 				new_id = cand_id;
 				break;
@@ -2268,7 +3597,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 		h = btf_hash_enum(t);
 		for_each_dedup_cand(d, hash_entry, h) {
 			cand_id = (__u32)(long)hash_entry->value;
-			cand = d->btf->types[cand_id];
+			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_enum(t, cand)) {
 				new_id = cand_id;
 				break;
@@ -2291,7 +3620,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 		h = btf_hash_common(t);
 		for_each_dedup_cand(d, hash_entry, h) {
 			cand_id = (__u32)(long)hash_entry->value;
-			cand = d->btf->types[cand_id];
+			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_common(t, cand)) {
 				new_id = cand_id;
 				break;
@@ -2350,13 +3679,13 @@ static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id)
 {
 	__u32 orig_type_id = type_id;
 
-	if (!btf_is_fwd(d->btf->types[type_id]))
+	if (!btf_is_fwd(btf__type_by_id(d->btf, type_id)))
 		return type_id;
 
 	while (is_type_mapped(d, type_id) && d->map[type_id] != type_id)
 		type_id = d->map[type_id];
 
-	if (!btf_is_fwd(d->btf->types[type_id]))
+	if (!btf_is_fwd(btf__type_by_id(d->btf, type_id)))
 		return type_id;
 
 	return orig_type_id;
@@ -2484,8 +3813,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 	if (btf_dedup_hypot_map_add(d, canon_id, cand_id))
 		return -ENOMEM;
 
-	cand_type = d->btf->types[cand_id];
-	canon_type = d->btf->types[canon_id];
+	cand_type = btf_type_by_id(d->btf, cand_id);
+	canon_type = btf_type_by_id(d->btf, canon_id);
 	cand_kind = btf_kind(cand_type);
 	canon_kind = btf_kind(canon_type);
 
@@ -2636,8 +3965,8 @@ static void btf_dedup_merge_hypot_map(struct btf_dedup *d)
 		targ_type_id = d->hypot_map[cand_type_id];
 		t_id = resolve_type_id(d, targ_type_id);
 		c_id = resolve_type_id(d, cand_type_id);
-		t_kind = btf_kind(d->btf->types[t_id]);
-		c_kind = btf_kind(d->btf->types[c_id]);
+		t_kind = btf_kind(btf__type_by_id(d->btf, t_id));
+		c_kind = btf_kind(btf__type_by_id(d->btf, c_id));
 		/*
 		 * Resolve FWD into STRUCT/UNION.
 		 * It's ok to resolve FWD into STRUCT/UNION that's not yet
@@ -2705,7 +4034,7 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
 	if (d->map[type_id] <= BTF_MAX_NR_TYPES)
 		return 0;
 
-	t = d->btf->types[type_id];
+	t = btf_type_by_id(d->btf, type_id);
 	kind = btf_kind(t);
 
 	if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION)
@@ -2726,7 +4055,7 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id)
 		 * creating a loop (FWD -> STRUCT and STRUCT -> FWD), because
 		 * FWD and compatible STRUCT/UNION are considered equivalent.
 		 */
-		cand_type = d->btf->types[cand_id];
+		cand_type = btf_type_by_id(d->btf, cand_id);
 		if (!btf_shallow_equal_struct(t, cand_type))
 			continue;
 
@@ -2798,7 +4127,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 	if (d->map[type_id] <= BTF_MAX_NR_TYPES)
 		return resolve_type_id(d, type_id);
 
-	t = d->btf->types[type_id];
+	t = btf_type_by_id(d->btf, type_id);
 	d->map[type_id] = BTF_IN_PROGRESS_ID;
 
 	switch (btf_kind(t)) {
@@ -2816,7 +4145,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 		h = btf_hash_common(t);
 		for_each_dedup_cand(d, hash_entry, h) {
 			cand_id = (__u32)(long)hash_entry->value;
-			cand = d->btf->types[cand_id];
+			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_common(t, cand)) {
 				new_id = cand_id;
 				break;
@@ -2840,7 +4169,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 		h = btf_hash_array(t);
 		for_each_dedup_cand(d, hash_entry, h) {
 			cand_id = (__u32)(long)hash_entry->value;
-			cand = d->btf->types[cand_id];
+			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_array(t, cand)) {
 				new_id = cand_id;
 				break;
@@ -2872,7 +4201,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 		h = btf_hash_fnproto(t);
 		for_each_dedup_cand(d, hash_entry, h) {
 			cand_id = (__u32)(long)hash_entry->value;
-			cand = d->btf->types[cand_id];
+			cand = btf_type_by_id(d->btf, cand_id);
 			if (btf_equal_fnproto(t, cand)) {
 				new_id = cand_id;
 				break;
@@ -2920,9 +4249,9 @@ static int btf_dedup_ref_types(struct btf_dedup *d)
  */
 static int btf_dedup_compact_types(struct btf_dedup *d)
 {
-	struct btf_type **new_types;
+	__u32 *new_offs;
 	__u32 next_type_id = 1;
-	char *types_start, *p;
+	void *p;
 	int i, len;
 
 	/* we are going to reuse hypot_map to store compaction remapping */
@@ -2930,41 +4259,34 @@ static int btf_dedup_compact_types(struct btf_dedup *d)
 	for (i = 1; i <= d->btf->nr_types; i++)
 		d->hypot_map[i] = BTF_UNPROCESSED_ID;
 
-	types_start = d->btf->nohdr_data + d->btf->hdr->type_off;
-	p = types_start;
+	p = d->btf->types_data;
 
 	for (i = 1; i <= d->btf->nr_types; i++) {
 		if (d->map[i] != i)
 			continue;
 
-		len = btf_type_size(d->btf->types[i]);
+		len = btf_type_size(btf__type_by_id(d->btf, i));
 		if (len < 0)
 			return len;
 
-		memmove(p, d->btf->types[i], len);
+		memmove(p, btf__type_by_id(d->btf, i), len);
 		d->hypot_map[i] = next_type_id;
-		d->btf->types[next_type_id] = (struct btf_type *)p;
+		d->btf->type_offs[next_type_id] = p - d->btf->types_data;
 		p += len;
 		next_type_id++;
 	}
 
 	/* shrink struct btf's internal types index and update btf_header */
 	d->btf->nr_types = next_type_id - 1;
-	d->btf->types_size = d->btf->nr_types;
-	d->btf->hdr->type_len = p - types_start;
-	new_types = libbpf_reallocarray(d->btf->types, (1 + d->btf->nr_types),
-					sizeof(struct btf_type *));
-	if (!new_types)
+	d->btf->type_offs_cap = d->btf->nr_types + 1;
+	d->btf->hdr->type_len = p - d->btf->types_data;
+	new_offs = libbpf_reallocarray(d->btf->type_offs, d->btf->type_offs_cap,
+				       sizeof(*new_offs));
+	if (!new_offs)
 		return -ENOMEM;
-	d->btf->types = new_types;
-
-	/* make sure string section follows type information without gaps */
-	d->btf->hdr->str_off = p - (char *)d->btf->nohdr_data;
-	memmove(p, d->btf->strings, d->btf->hdr->str_len);
-	d->btf->strings = p;
-	p += d->btf->hdr->str_len;
-
-	d->btf->data_size = p - (char *)d->btf->data;
+	d->btf->type_offs = new_offs;
+	d->btf->hdr->str_off = d->btf->hdr->type_len;
+	d->btf->raw_size = d->btf->hdr->hdr_len + d->btf->hdr->type_len + d->btf->hdr->str_len;
 	return 0;
 }
 
@@ -2997,7 +4319,7 @@ static int btf_dedup_remap_type_id(struct btf_dedup *d, __u32 type_id)
  */
 static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id)
 {
-	struct btf_type *t = d->btf->types[type_id];
+	struct btf_type *t = btf_type_by_id(d->btf, type_id);
 	int i, r;
 
 	switch (btf_kind(t)) {
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 2a55320d87d0..57247240a20a 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -5,6 +5,7 @@
 #define __LIBBPF_BTF_H
 
 #include <stdarg.h>
+#include <stdbool.h>
 #include <linux/btf.h>
 #include <linux/types.h>
 
@@ -24,8 +25,14 @@ struct btf_type;
 
 struct bpf_object;
 
+enum btf_endianness {
+	BTF_LITTLE_ENDIAN = 0,
+	BTF_BIG_ENDIAN = 1,
+};
+
 LIBBPF_API void btf__free(struct btf *btf);
 LIBBPF_API struct btf *btf__new(const void *data, __u32 size);
+LIBBPF_API struct btf *btf__new_empty(void);
 LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext);
 LIBBPF_API struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext);
 LIBBPF_API struct btf *btf__parse_raw(const char *path);
@@ -40,6 +47,8 @@ LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf,
 						  __u32 id);
 LIBBPF_API size_t btf__pointer_size(const struct btf *btf);
 LIBBPF_API int btf__set_pointer_size(struct btf *btf, size_t ptr_sz);
+LIBBPF_API enum btf_endianness btf__endianness(const struct btf *btf);
+LIBBPF_API int btf__set_endianness(struct btf *btf, enum btf_endianness endian);
 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__align_of(const struct btf *btf, __u32 id);
@@ -47,6 +56,7 @@ LIBBPF_API int btf__fd(const struct btf *btf);
 LIBBPF_API void btf__set_fd(struct btf *btf, int fd);
 LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size);
 LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
+LIBBPF_API const char *btf__str_by_offset(const struct btf *btf, __u32 offset);
 LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf);
 LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
 				    __u32 expected_key_size,
@@ -72,6 +82,47 @@ LIBBPF_API __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext);
 
 LIBBPF_API struct btf *libbpf_find_kernel_btf(void);
 
+LIBBPF_API int btf__find_str(struct btf *btf, const char *s);
+LIBBPF_API int btf__add_str(struct btf *btf, const char *s);
+
+LIBBPF_API int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding);
+LIBBPF_API int btf__add_ptr(struct btf *btf, int ref_type_id);
+LIBBPF_API int btf__add_array(struct btf *btf,
+			      int index_type_id, int elem_type_id, __u32 nr_elems);
+/* struct/union construction APIs */
+LIBBPF_API int btf__add_struct(struct btf *btf, const char *name, __u32 sz);
+LIBBPF_API int btf__add_union(struct btf *btf, const char *name, __u32 sz);
+LIBBPF_API int btf__add_field(struct btf *btf, const char *name, int field_type_id,
+			      __u32 bit_offset, __u32 bit_size);
+
+/* enum construction APIs */
+LIBBPF_API int btf__add_enum(struct btf *btf, const char *name, __u32 bytes_sz);
+LIBBPF_API int btf__add_enum_value(struct btf *btf, const char *name, __s64 value);
+
+enum btf_fwd_kind {
+	BTF_FWD_STRUCT = 0,
+	BTF_FWD_UNION = 1,
+	BTF_FWD_ENUM = 2,
+};
+
+LIBBPF_API int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind);
+LIBBPF_API int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id);
+LIBBPF_API int btf__add_volatile(struct btf *btf, int ref_type_id);
+LIBBPF_API int btf__add_const(struct btf *btf, int ref_type_id);
+LIBBPF_API int btf__add_restrict(struct btf *btf, int ref_type_id);
+
+/* func and func_proto construction APIs */
+LIBBPF_API int btf__add_func(struct btf *btf, const char *name,
+			     enum btf_func_linkage linkage, int proto_type_id);
+LIBBPF_API int btf__add_func_proto(struct btf *btf, int ret_type_id);
+LIBBPF_API int btf__add_func_param(struct btf *btf, const char *name, int type_id);
+
+/* var & datasec construction APIs */
+LIBBPF_API int btf__add_var(struct btf *btf, const char *name, int linkage, int type_id);
+LIBBPF_API int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz);
+LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id,
+					 __u32 offset, __u32 byte_sz);
+
 struct btf_dedup_opts {
 	unsigned int dedup_table_size;
 	bool dont_resolve_fwds;
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 6c079b3c8679..2f9d685bd522 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -60,11 +60,14 @@ struct btf_dump {
 	struct btf_dump_opts opts;
 	int ptr_sz;
 	bool strip_mods;
+	int last_id;
 
 	/* per-type auxiliary state */
 	struct btf_dump_type_aux_state *type_states;
+	size_t type_states_cap;
 	/* per-type optional cached unique name, must be freed, if present */
 	const char **cached_names;
+	size_t cached_names_cap;
 
 	/* topo-sorted list of dependent type definitions */
 	__u32 *emit_queue;
@@ -90,14 +93,7 @@ struct btf_dump {
 
 static size_t str_hash_fn(const void *key, void *ctx)
 {
-	const char *s = key;
-	size_t h = 0;
-
-	while (*s) {
-		h = h * 31 + *s;
-		s++;
-	}
-	return h;
+	return str_hash(key);
 }
 
 static bool str_equal_fn(const void *a, const void *b, void *ctx)
@@ -120,6 +116,7 @@ static void btf_dump_printf(const struct btf_dump *d, const char *fmt, ...)
 }
 
 static int btf_dump_mark_referenced(struct btf_dump *d);
+static int btf_dump_resize(struct btf_dump *d);
 
 struct btf_dump *btf_dump__new(const struct btf *btf,
 			       const struct btf_ext *btf_ext,
@@ -151,25 +148,8 @@ struct btf_dump *btf_dump__new(const struct btf *btf,
 		d->ident_names = NULL;
 		goto err;
 	}
-	d->type_states = calloc(1 + btf__get_nr_types(d->btf),
-				sizeof(d->type_states[0]));
-	if (!d->type_states) {
-		err = -ENOMEM;
-		goto err;
-	}
-	d->cached_names = calloc(1 + btf__get_nr_types(d->btf),
-				 sizeof(d->cached_names[0]));
-	if (!d->cached_names) {
-		err = -ENOMEM;
-		goto err;
-	}
 
-	/* VOID is special */
-	d->type_states[0].order_state = ORDERED;
-	d->type_states[0].emit_state = EMITTED;
-
-	/* eagerly determine referenced types for anon enums */
-	err = btf_dump_mark_referenced(d);
+	err = btf_dump_resize(d);
 	if (err)
 		goto err;
 
@@ -179,9 +159,38 @@ err:
 	return ERR_PTR(err);
 }
 
+static int btf_dump_resize(struct btf_dump *d)
+{
+	int err, last_id = btf__get_nr_types(d->btf);
+
+	if (last_id <= d->last_id)
+		return 0;
+
+	if (btf_ensure_mem((void **)&d->type_states, &d->type_states_cap,
+			   sizeof(*d->type_states), last_id + 1))
+		return -ENOMEM;
+	if (btf_ensure_mem((void **)&d->cached_names, &d->cached_names_cap,
+			   sizeof(*d->cached_names), last_id + 1))
+		return -ENOMEM;
+
+	if (d->last_id == 0) {
+		/* VOID is special */
+		d->type_states[0].order_state = ORDERED;
+		d->type_states[0].emit_state = EMITTED;
+	}
+
+	/* eagerly determine referenced types for anon enums */
+	err = btf_dump_mark_referenced(d);
+	if (err)
+		return err;
+
+	d->last_id = last_id;
+	return 0;
+}
+
 void btf_dump__free(struct btf_dump *d)
 {
-	int i, cnt;
+	int i;
 
 	if (IS_ERR_OR_NULL(d))
 		return;
@@ -189,7 +198,7 @@ void btf_dump__free(struct btf_dump *d)
 	free(d->type_states);
 	if (d->cached_names) {
 		/* any set cached name is owned by us and should be freed */
-		for (i = 0, cnt = btf__get_nr_types(d->btf); i <= cnt; i++) {
+		for (i = 0; i <= d->last_id; i++) {
 			if (d->cached_names[i])
 				free((void *)d->cached_names[i]);
 		}
@@ -229,6 +238,10 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id)
 	if (id > btf__get_nr_types(d->btf))
 		return -EINVAL;
 
+	err = btf_dump_resize(d);
+	if (err)
+		return err;
+
 	d->emit_queue_cnt = 0;
 	err = btf_dump_order_type(d, id, false);
 	if (err < 0)
@@ -258,7 +271,7 @@ static int btf_dump_mark_referenced(struct btf_dump *d)
 	const struct btf_type *t;
 	__u16 vlen;
 
-	for (i = 1; i <= n; i++) {
+	for (i = d->last_id + 1; i <= n; i++) {
 		t = btf__type_by_id(d->btf, i);
 		vlen = btf_vlen(t);
 
@@ -313,6 +326,7 @@ static int btf_dump_mark_referenced(struct btf_dump *d)
 	}
 	return 0;
 }
+
 static int btf_dump_add_emit_queue_id(struct btf_dump *d, __u32 id)
 {
 	__u32 *new_queue;
@@ -1056,11 +1070,15 @@ int btf_dump__emit_type_decl(struct btf_dump *d, __u32 id,
 			     const struct btf_dump_emit_type_decl_opts *opts)
 {
 	const char *fname;
-	int lvl;
+	int lvl, err;
 
 	if (!OPTS_VALID(opts, btf_dump_emit_type_decl_opts))
 		return -EINVAL;
 
+	err = btf_dump_resize(d);
+	if (err)
+		return -EINVAL;
+
 	fname = OPTS_GET(opts, field_name, "");
 	lvl = OPTS_GET(opts, indent_level, 0);
 	d->strip_mods = OPTS_GET(opts, strip_mods, false);
diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h
index e0af36b0e5d8..d9b385fe808c 100644
--- a/tools/lib/bpf/hashmap.h
+++ b/tools/lib/bpf/hashmap.h
@@ -25,6 +25,18 @@ static inline size_t hash_bits(size_t h, int bits)
 #endif
 }
 
+/* generic C-string hashing function */
+static inline size_t str_hash(const char *s)
+{
+	size_t h = 0;
+
+	while (*s) {
+		h = h * 31 + *s;
+		s++;
+	}
+	return h;
+}
+
 typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx);
 typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx);
 
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 32dc444224d8..a4f55f8a460d 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -9390,9 +9390,11 @@ static struct bpf_link *attach_iter(const struct bpf_sec_def *sec,
 }
 
 static struct bpf_link *
-bpf_program__attach_fd(struct bpf_program *prog, int target_fd,
+bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id,
 		       const char *target_name)
 {
+	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts,
+			    .target_btf_id = btf_id);
 	enum bpf_attach_type attach_type;
 	char errmsg[STRERR_BUFSIZE];
 	struct bpf_link *link;
@@ -9410,7 +9412,7 @@ bpf_program__attach_fd(struct bpf_program *prog, int target_fd,
 	link->detach = &bpf_link__detach_fd;
 
 	attach_type = bpf_program__get_expected_attach_type(prog);
-	link_fd = bpf_link_create(prog_fd, target_fd, attach_type, NULL);
+	link_fd = bpf_link_create(prog_fd, target_fd, attach_type, &opts);
 	if (link_fd < 0) {
 		link_fd = -errno;
 		free(link);
@@ -9426,19 +9428,51 @@ bpf_program__attach_fd(struct bpf_program *prog, int target_fd,
 struct bpf_link *
 bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd)
 {
-	return bpf_program__attach_fd(prog, cgroup_fd, "cgroup");
+	return bpf_program__attach_fd(prog, cgroup_fd, 0, "cgroup");
 }
 
 struct bpf_link *
 bpf_program__attach_netns(struct bpf_program *prog, int netns_fd)
 {
-	return bpf_program__attach_fd(prog, netns_fd, "netns");
+	return bpf_program__attach_fd(prog, netns_fd, 0, "netns");
 }
 
 struct bpf_link *bpf_program__attach_xdp(struct bpf_program *prog, int ifindex)
 {
 	/* target_fd/target_ifindex use the same field in LINK_CREATE */
-	return bpf_program__attach_fd(prog, ifindex, "xdp");
+	return bpf_program__attach_fd(prog, ifindex, 0, "xdp");
+}
+
+struct bpf_link *bpf_program__attach_freplace(struct bpf_program *prog,
+					      int target_fd,
+					      const char *attach_func_name)
+{
+	int btf_id;
+
+	if (!!target_fd != !!attach_func_name) {
+		pr_warn("prog '%s': supply none or both of target_fd and attach_func_name\n",
+			prog->name);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (prog->type != BPF_PROG_TYPE_EXT) {
+		pr_warn("prog '%s': only BPF_PROG_TYPE_EXT can attach as freplace",
+			prog->name);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (target_fd) {
+		btf_id = libbpf_find_prog_btf_id(attach_func_name, target_fd);
+		if (btf_id < 0)
+			return ERR_PTR(btf_id);
+
+		return bpf_program__attach_fd(prog, target_fd, btf_id, "freplace");
+	} else {
+		/* no target, so use raw_tracepoint_open for compatibility
+		 * with old kernels
+		 */
+		return bpf_program__attach_trace(prog);
+	}
 }
 
 struct bpf_link *
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index a750f67a23f6..6909ee81113a 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -261,6 +261,9 @@ LIBBPF_API struct bpf_link *
 bpf_program__attach_netns(struct bpf_program *prog, int netns_fd);
 LIBBPF_API struct bpf_link *
 bpf_program__attach_xdp(struct bpf_program *prog, int ifindex);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_freplace(struct bpf_program *prog,
+			     int target_fd, const char *attach_func_name);
 
 struct bpf_map;
 
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 5f054dadf082..4ebfadf45b47 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -303,7 +303,34 @@ LIBBPF_0.1.0 {
 LIBBPF_0.2.0 {
 	global:
 		bpf_prog_bind_map;
+		bpf_prog_test_run_opts;
+		bpf_program__attach_freplace;
 		bpf_program__section_name;
+		btf__add_array;
+		btf__add_const;
+		btf__add_enum;
+		btf__add_enum_value;
+		btf__add_datasec;
+		btf__add_datasec_var_info;
+		btf__add_field;
+		btf__add_func;
+		btf__add_func_param;
+		btf__add_func_proto;
+		btf__add_fwd;
+		btf__add_int;
+		btf__add_ptr;
+		btf__add_restrict;
+		btf__add_str;
+		btf__add_struct;
+		btf__add_typedef;
+		btf__add_union;
+		btf__add_var;
+		btf__add_volatile;
+		btf__endianness;
+		btf__find_str;
+		btf__new_empty;
+		btf__set_endianness;
+		btf__str_by_offset;
 		perf_buffer__buffer_cnt;
 		perf_buffer__buffer_fd;
 		perf_buffer__epoll_fd;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 4d1c366fca2c..d99bc847bf84 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -105,6 +105,10 @@ static inline void *libbpf_reallocarray(void *ptr, size_t nmemb, size_t size)
 	return realloc(ptr, total);
 }
 
+void *btf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz,
+		  size_t cur_cnt, size_t max_cnt, size_t add_cnt);
+int btf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_cnt);
+
 static inline bool libbpf_validate_opts(const char *opts,
 					size_t opts_sz, size_t user_sz,
 					const char *type_name)
@@ -136,6 +140,11 @@ static inline bool libbpf_validate_opts(const char *opts,
 	((opts) && opts->sz >= offsetofend(typeof(*(opts)), field))
 #define OPTS_GET(opts, field, fallback_value) \
 	(OPTS_HAS(opts, field) ? (opts)->field : fallback_value)
+#define OPTS_SET(opts, field, value)		\
+	do {					\
+		if (OPTS_HAS(opts, field))	\
+			(opts)->field = value;	\
+	} while (0)
 
 int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz);
 int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz);