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

Daniel Borkmann says:

====================
pull-request: bpf-next 2019-11-20

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

We've added 81 non-merge commits during the last 17 day(s) which contain
a total of 120 files changed, 4958 insertions(+), 1081 deletions(-).

There are 3 trivial conflicts, resolve it by always taking the chunk from
196e8ca74886c433:

<<<<<<< HEAD
=======
void *bpf_map_area_mmapable_alloc(u64 size, int numa_node);
>>>>>>> 196e8ca74886c433dcfc64a809707074b936aaf5

<<<<<<< HEAD
void *bpf_map_area_alloc(u64 size, int numa_node)
=======
static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable)
>>>>>>> 196e8ca74886c433dcfc64a809707074b936aaf5

<<<<<<< HEAD
        if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
=======
        /* kmalloc()'ed memory can't be mmap()'ed */
        if (!mmapable && size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
>>>>>>> 196e8ca74886c433dcfc64a809707074b936aaf5

The main changes are:

1) Addition of BPF trampoline which works as a bridge between kernel functions,
   BPF programs and other BPF programs along with two new use cases: i) fentry/fexit
   BPF programs for tracing with practically zero overhead to call into BPF (as
   opposed to k[ret]probes) and ii) attachment of the former to networking related
   programs to see input/output of networking programs (covering xdpdump use case),
   from Alexei Starovoitov.

2) BPF array map mmap support and use in libbpf for global data maps; also a big
   batch of libbpf improvements, among others, support for reading bitfields in a
   relocatable manner (via libbpf's CO-RE helper API), from Andrii Nakryiko.

3) Extend s390x JIT with usage of relative long jumps and loads in order to lift
   the current 64/512k size limits on JITed BPF programs there, from Ilya Leoshkevich.

4) Add BPF audit support and emit messages upon successful prog load and unload in
   order to have a timeline of events, from Daniel Borkmann and Jiri Olsa.

5) Extension to libbpf and xdpsock sample programs to demo the shared umem mode
   (XDP_SHARED_UMEM) as well as RX-only and TX-only sockets, from Magnus Karlsson.

6) Several follow-up bug fixes for libbpf's auto-pinning code and a new API
   call named bpf_get_link_xdp_info() for retrieving the full set of prog
   IDs attached to XDP, from Toke Høiland-Jørgensen.

7) Add BTF support for array of int, array of struct and multidimensional arrays
   and enable it for skb->cb[] access in kfree_skb test, from Martin KaFai Lau.

8) Fix AF_XDP by using the correct number of channels from ethtool, from Luigi Rizzo.

9) Two fixes for BPF selftest to get rid of a hang in test_tc_tunnel and to avoid
   xdping to be run as standalone, from Jiri Benc.

10) Various BPF selftest fixes when run with latest LLVM trunk, from Yonghong Song.

11) Fix a memory leak in BPF fentry test run data, from Colin Ian King.

12) Various smaller misc cleanups and improvements mostly all over BPF selftests and
    samples, from Daniel T. Lee, Andre Guedes, Anders Roxell, Mao Wenan, Yue Haibing.
====================

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

14 files changed, 617 insertions, 181 deletions

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index ca0d635b1d5e..98596e15390f 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -189,7 +189,7 @@ static void *
 alloc_zero_tailing_info(const void *orecord, __u32 cnt,
 			__u32 actual_rec_size, __u32 expected_rec_size)
 {
-	__u64 info_len = actual_rec_size * cnt;
+	__u64 info_len = (__u64)actual_rec_size * cnt;
 	void *info, *nrecord;
 	int i;
 
@@ -228,10 +228,13 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = load_attr->prog_type;
 	attr.expected_attach_type = load_attr->expected_attach_type;
-	if (attr.prog_type == BPF_PROG_TYPE_TRACING)
+	if (attr.prog_type == BPF_PROG_TYPE_TRACING) {
 		attr.attach_btf_id = load_attr->attach_btf_id;
-	else
+		attr.attach_prog_fd = load_attr->attach_prog_fd;
+	} else {
 		attr.prog_ifindex = load_attr->prog_ifindex;
+		attr.kern_version = load_attr->kern_version;
+	}
 	attr.insn_cnt = (__u32)load_attr->insns_cnt;
 	attr.insns = ptr_to_u64(load_attr->insns);
 	attr.license = ptr_to_u64(load_attr->license);
@@ -245,7 +248,6 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 		attr.log_size = 0;
 	}
 
-	attr.kern_version = load_attr->kern_version;
 	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;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 1c53bc5b4b3c..3c791fa8e68e 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -77,7 +77,10 @@ struct bpf_load_program_attr {
 	const struct bpf_insn *insns;
 	size_t insns_cnt;
 	const char *license;
-	__u32 kern_version;
+	union {
+		__u32 kern_version;
+		__u32 attach_prog_fd;
+	};
 	union {
 		__u32 prog_ifindex;
 		__u32 attach_btf_id;
diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h
index a273df3784f4..7009dc90e012 100644
--- a/tools/lib/bpf/bpf_core_read.h
+++ b/tools/lib/bpf/bpf_core_read.h
@@ -12,9 +12,76 @@
  */
 enum bpf_field_info_kind {
 	BPF_FIELD_BYTE_OFFSET = 0,	/* field byte offset */
+	BPF_FIELD_BYTE_SIZE = 1,
 	BPF_FIELD_EXISTS = 2,		/* field existence in target kernel */
+	BPF_FIELD_SIGNED = 3,
+	BPF_FIELD_LSHIFT_U64 = 4,
+	BPF_FIELD_RSHIFT_U64 = 5,
 };
 
+#define __CORE_RELO(src, field, info)					      \
+	__builtin_preserve_field_info((src)->field, BPF_FIELD_##info)
+
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+#define __CORE_BITFIELD_PROBE_READ(dst, src, fld)			      \
+	bpf_probe_read((void *)dst,					      \
+		       __CORE_RELO(src, fld, BYTE_SIZE),		      \
+		       (const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET))
+#else
+/* semantics of LSHIFT_64 assumes loading values into low-ordered bytes, so
+ * for big-endian we need to adjust destination pointer accordingly, based on
+ * field byte size
+ */
+#define __CORE_BITFIELD_PROBE_READ(dst, src, fld)			      \
+	bpf_probe_read((void *)dst + (8 - __CORE_RELO(src, fld, BYTE_SIZE)),  \
+		       __CORE_RELO(src, fld, BYTE_SIZE),		      \
+		       (const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET))
+#endif
+
+/*
+ * Extract bitfield, identified by s->field, and return its value as u64.
+ * All this is done in relocatable manner, so bitfield changes such as
+ * signedness, bit size, offset changes, this will be handled automatically.
+ * This version of macro is using bpf_probe_read() to read underlying integer
+ * storage. Macro functions as an expression and its return type is
+ * bpf_probe_read()'s return value: 0, on success, <0 on error.
+ */
+#define BPF_CORE_READ_BITFIELD_PROBED(s, field) ({			      \
+	unsigned long long val = 0;					      \
+									      \
+	__CORE_BITFIELD_PROBE_READ(&val, s, field);			      \
+	val <<= __CORE_RELO(s, field, LSHIFT_U64);			      \
+	if (__CORE_RELO(s, field, SIGNED))				      \
+		val = ((long long)val) >> __CORE_RELO(s, field, RSHIFT_U64);  \
+	else								      \
+		val = val >> __CORE_RELO(s, field, RSHIFT_U64);		      \
+	val;								      \
+})
+
+/*
+ * Extract bitfield, identified by s->field, and return its value as u64.
+ * This version of macro is using direct memory reads and should be used from
+ * BPF program types that support such functionality (e.g., typed raw
+ * tracepoints).
+ */
+#define BPF_CORE_READ_BITFIELD(s, field) ({				      \
+	const void *p = (const void *)s + __CORE_RELO(s, field, BYTE_OFFSET); \
+	unsigned long long val;						      \
+									      \
+	switch (__CORE_RELO(s, field, BYTE_SIZE)) {			      \
+	case 1: val = *(const unsigned char *)p;			      \
+	case 2: val = *(const unsigned short *)p;			      \
+	case 4: val = *(const unsigned int *)p;				      \
+	case 8: val = *(const unsigned long long *)p;			      \
+	}								      \
+	val <<= __CORE_RELO(s, field, LSHIFT_U64);			      \
+	if (__CORE_RELO(s, field, SIGNED))				      \
+		val = ((long long)val) >> __CORE_RELO(s, field, RSHIFT_U64);  \
+	else								      \
+		val = val >> __CORE_RELO(s, field, RSHIFT_U64);		      \
+	val;								      \
+})
+
 /*
  * Convenience macro to check that field actually exists in target kernel's.
  * Returns:
@@ -25,6 +92,13 @@ enum bpf_field_info_kind {
 	__builtin_preserve_field_info(field, BPF_FIELD_EXISTS)
 
 /*
+ * Convenience macro to get byte size of a field. Works for integers,
+ * struct/unions, pointers, arrays, and enums.
+ */
+#define bpf_core_field_size(field)					    \
+	__builtin_preserve_field_info(field, BPF_FIELD_BYTE_SIZE)
+
+/*
  * bpf_core_read() abstracts away bpf_probe_read() call and captures offset
  * relocation for source address using __builtin_preserve_access_index()
  * built-in, provided by Clang.
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index 0c7d28292898..c63ab1add126 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -44,4 +44,17 @@ enum libbpf_pin_type {
 	LIBBPF_PIN_BY_NAME,
 };
 
+/* The following types should be used by BPF_PROG_TYPE_TRACING program to
+ * access kernel function arguments. BPF trampoline and raw tracepoints
+ * typecast arguments to 'unsigned long long'.
+ */
+typedef int __attribute__((aligned(8))) ks32;
+typedef char __attribute__((aligned(8))) ks8;
+typedef short __attribute__((aligned(8))) ks16;
+typedef long long __attribute__((aligned(8))) ks64;
+typedef unsigned int __attribute__((aligned(8))) ku32;
+typedef unsigned char __attribute__((aligned(8))) ku8;
+typedef unsigned short __attribute__((aligned(8))) ku16;
+typedef unsigned long long __attribute__((aligned(8))) ku64;
+
 #endif
diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c
index 8c67561c93b0..3ed1a27b5f7c 100644
--- a/tools/lib/bpf/bpf_prog_linfo.c
+++ b/tools/lib/bpf/bpf_prog_linfo.c
@@ -101,6 +101,7 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 {
 	struct bpf_prog_linfo *prog_linfo;
 	__u32 nr_linfo, nr_jited_func;
+	__u64 data_sz;
 
 	nr_linfo = info->nr_line_info;
 
@@ -122,11 +123,11 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 	/* Copy xlated line_info */
 	prog_linfo->nr_linfo = nr_linfo;
 	prog_linfo->rec_size = info->line_info_rec_size;
-	prog_linfo->raw_linfo = malloc(nr_linfo * prog_linfo->rec_size);
+	data_sz = (__u64)nr_linfo * prog_linfo->rec_size;
+	prog_linfo->raw_linfo = malloc(data_sz);
 	if (!prog_linfo->raw_linfo)
 		goto err_free;
-	memcpy(prog_linfo->raw_linfo, (void *)(long)info->line_info,
-	       nr_linfo * prog_linfo->rec_size);
+	memcpy(prog_linfo->raw_linfo, (void *)(long)info->line_info, data_sz);
 
 	nr_jited_func = info->nr_jited_ksyms;
 	if (!nr_jited_func ||
@@ -142,13 +143,12 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 	/* Copy jited_line_info */
 	prog_linfo->nr_jited_func = nr_jited_func;
 	prog_linfo->jited_rec_size = info->jited_line_info_rec_size;
-	prog_linfo->raw_jited_linfo = malloc(nr_linfo *
-					     prog_linfo->jited_rec_size);
+	data_sz = (__u64)nr_linfo * prog_linfo->jited_rec_size;
+	prog_linfo->raw_jited_linfo = malloc(data_sz);
 	if (!prog_linfo->raw_jited_linfo)
 		goto err_free;
 	memcpy(prog_linfo->raw_jited_linfo,
-	       (void *)(long)info->jited_line_info,
-	       nr_linfo * prog_linfo->jited_rec_size);
+	       (void *)(long)info->jited_line_info, data_sz);
 
 	/* Number of jited_line_info per jited func */
 	prog_linfo->nr_jited_linfo_per_func = malloc(nr_jited_func *
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index d72e9a79dce1..88efa2bb7137 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -269,10 +269,9 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 		t = btf__type_by_id(btf, type_id);
 	}
 
+done:
 	if (size < 0)
 		return -EINVAL;
-
-done:
 	if (nelems && size > UINT32_MAX / nelems)
 		return -E2BIG;
 
@@ -317,6 +316,28 @@ __s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 	return -ENOENT;
 }
 
+__s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
+			     __u32 kind)
+{
+	__u32 i;
+
+	if (kind == BTF_KIND_UNKN || !strcmp(type_name, "void"))
+		return 0;
+
+	for (i = 1; i <= btf->nr_types; i++) {
+		const struct btf_type *t = btf->types[i];
+		const char *name;
+
+		if (btf_kind(t) != kind)
+			continue;
+		name = btf__name_by_offset(btf, t->name_off);
+		if (name && !strcmp(type_name, name))
+			return i;
+	}
+
+	return -ENOENT;
+}
+
 void btf__free(struct btf *btf)
 {
 	if (!btf)
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index b18994116a44..d9ac73a02cde 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -72,6 +72,8 @@ LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf);
 LIBBPF_API int btf__load(struct btf *btf);
 LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
 				   const char *type_name);
+LIBBPF_API __s32 btf__find_by_name_kind(const struct btf *btf,
+					const char *type_name, __u32 kind);
 LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf);
 LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf,
 						  __u32 id);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 7aa2a2a22cef..a7d183f7ac72 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -142,6 +142,8 @@ struct bpf_capabilities {
 	__u32 btf_func:1;
 	/* BTF_KIND_VAR and BTF_KIND_DATASEC support */
 	__u32 btf_datasec:1;
+	/* BPF_F_MMAPABLE is supported for arrays */
+	__u32 array_mmap:1;
 };
 
 /*
@@ -189,6 +191,7 @@ struct bpf_program {
 
 	enum bpf_attach_type expected_attach_type;
 	__u32 attach_btf_id;
+	__u32 attach_prog_fd;
 	void *func_info;
 	__u32 func_info_rec_size;
 	__u32 func_info_cnt;
@@ -229,6 +232,7 @@ struct bpf_map {
 	enum libbpf_map_type libbpf_type;
 	char *pin_path;
 	bool pinned;
+	bool reused;
 };
 
 struct bpf_secdata {
@@ -855,8 +859,6 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 		pr_warn("failed to alloc map name\n");
 		return -ENOMEM;
 	}
-	pr_debug("map '%s' (global data): at sec_idx %d, offset %zu.\n",
-		 map_name, map->sec_idx, map->sec_offset);
 
 	def = &map->def;
 	def->type = BPF_MAP_TYPE_ARRAY;
@@ -864,6 +866,12 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 	def->value_size = data->d_size;
 	def->max_entries = 1;
 	def->map_flags = type == LIBBPF_MAP_RODATA ? BPF_F_RDONLY_PROG : 0;
+	if (obj->caps.array_mmap)
+		def->map_flags |= BPF_F_MMAPABLE;
+
+	pr_debug("map '%s' (global data): at sec_idx %d, offset %zu, flags %x.\n",
+		 map_name, map->sec_idx, map->sec_offset, def->map_flags);
+
 	if (data_buff) {
 		*data_buff = malloc(data->d_size);
 		if (!*data_buff) {
@@ -956,13 +964,13 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 	pr_debug("maps in %s: %d maps in %zd bytes\n",
 		 obj->path, nr_maps, data->d_size);
 
-	map_def_sz = data->d_size / nr_maps;
-	if (!data->d_size || (data->d_size % nr_maps) != 0) {
+	if (!data->d_size || nr_maps == 0 || (data->d_size % nr_maps) != 0) {
 		pr_warn("unable to determine map definition size "
 			"section %s, %d maps in %zd bytes\n",
 			obj->path, nr_maps, data->d_size);
 		return -EINVAL;
 	}
+	map_def_sz = data->d_size / nr_maps;
 
 	/* Fill obj->maps using data in "maps" section.  */
 	for (i = 0; i < nr_syms; i++) {
@@ -1862,9 +1870,13 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
 				pr_warn("incorrect bpf_call opcode\n");
 				return -LIBBPF_ERRNO__RELOC;
 			}
+			if (sym.st_value % 8) {
+				pr_warn("bad call relo offset: %lu\n", sym.st_value);
+				return -LIBBPF_ERRNO__RELOC;
+			}
 			prog->reloc_desc[i].type = RELO_CALL;
 			prog->reloc_desc[i].insn_idx = insn_idx;
-			prog->reloc_desc[i].text_off = sym.st_value;
+			prog->reloc_desc[i].text_off = sym.st_value / 8;
 			obj->has_pseudo_calls = true;
 			continue;
 		}
@@ -1995,6 +2007,7 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 	map->def.map_flags = info.map_flags;
 	map->btf_key_type_id = info.btf_key_type_id;
 	map->btf_value_type_id = info.btf_value_type_id;
+	map->reused = true;
 
 	return 0;
 
@@ -2158,6 +2171,27 @@ static int bpf_object__probe_btf_datasec(struct bpf_object *obj)
 	return 0;
 }
 
+static int bpf_object__probe_array_mmap(struct bpf_object *obj)
+{
+	struct bpf_create_map_attr attr = {
+		.map_type = BPF_MAP_TYPE_ARRAY,
+		.map_flags = BPF_F_MMAPABLE,
+		.key_size = sizeof(int),
+		.value_size = sizeof(int),
+		.max_entries = 1,
+	};
+	int fd;
+
+	fd = bpf_create_map_xattr(&attr);
+	if (fd >= 0) {
+		obj->caps.array_mmap = 1;
+		close(fd);
+		return 1;
+	}
+
+	return 0;
+}
+
 static int
 bpf_object__probe_caps(struct bpf_object *obj)
 {
@@ -2166,6 +2200,7 @@ bpf_object__probe_caps(struct bpf_object *obj)
 		bpf_object__probe_global_data,
 		bpf_object__probe_btf_func,
 		bpf_object__probe_btf_datasec,
+		bpf_object__probe_array_mmap,
 	};
 	int i, ret;
 
@@ -2470,8 +2505,8 @@ struct bpf_core_spec {
 	int raw_spec[BPF_CORE_SPEC_MAX_LEN];
 	/* raw spec length */
 	int raw_len;
-	/* field byte offset represented by spec */
-	__u32 offset;
+	/* field bit offset represented by spec */
+	__u32 bit_offset;
 };
 
 static bool str_is_empty(const char *s)
@@ -2482,8 +2517,8 @@ static bool str_is_empty(const char *s)
 /*
  * Turn bpf_field_reloc into a low- and high-level spec representation,
  * validating correctness along the way, as well as calculating resulting
- * field offset (in bytes), specified by accessor string. Low-level spec
- * captures every single level of nestedness, including traversing anonymous
+ * field bit offset, specified by accessor string. Low-level spec captures
+ * every single level of nestedness, including traversing anonymous
  * struct/union members. High-level one only captures semantically meaningful
  * "turning points": named fields and array indicies.
  * E.g., for this case:
@@ -2555,7 +2590,7 @@ static int bpf_core_spec_parse(const struct btf *btf,
 	sz = btf__resolve_size(btf, id);
 	if (sz < 0)
 		return sz;
-	spec->offset = access_idx * sz;
+	spec->bit_offset = access_idx * sz * 8;
 
 	for (i = 1; i < spec->raw_len; i++) {
 		t = skip_mods_and_typedefs(btf, id, &id);
@@ -2566,17 +2601,13 @@ static int bpf_core_spec_parse(const struct btf *btf,
 
 		if (btf_is_composite(t)) {
 			const struct btf_member *m;
-			__u32 offset;
+			__u32 bit_offset;
 
 			if (access_idx >= btf_vlen(t))
 				return -EINVAL;
-			if (btf_member_bitfield_size(t, access_idx))
-				return -EINVAL;
 
-			offset = btf_member_bit_offset(t, access_idx);
-			if (offset % 8)
-				return -EINVAL;
-			spec->offset += offset / 8;
+			bit_offset = btf_member_bit_offset(t, access_idx);
+			spec->bit_offset += bit_offset;
 
 			m = btf_members(t) + access_idx;
 			if (m->name_off) {
@@ -2605,7 +2636,7 @@ static int bpf_core_spec_parse(const struct btf *btf,
 			sz = btf__resolve_size(btf, id);
 			if (sz < 0)
 				return sz;
-			spec->offset += access_idx * sz;
+			spec->bit_offset += access_idx * sz * 8;
 		} else {
 			pr_warn("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %d\n",
 				type_id, spec_str, i, id, btf_kind(t));
@@ -2706,12 +2737,14 @@ err_out:
 }
 
 /* Check two types for compatibility, skipping const/volatile/restrict and
- * typedefs, to ensure we are relocating offset to the compatible entities:
+ * typedefs, to ensure we are relocating compatible entities:
  *   - any two STRUCTs/UNIONs are compatible and can be mixed;
- *   - any two FWDs are compatible;
+ *   - any two FWDs are compatible, if their names match (modulo flavor suffix);
  *   - any two PTRs are always compatible;
+ *   - for ENUMs, names should be the same (ignoring flavor suffix) or at
+ *     least one of enums should be anonymous;
  *   - for ENUMs, check sizes, names are ignored;
- *   - for INT, size and bitness should match, signedness is ignored;
+ *   - for INT, size and signedness are ignored;
  *   - for ARRAY, dimensionality is ignored, element types are checked for
  *     compatibility recursively;
  *   - everything else shouldn't be ever a target of relocation.
@@ -2737,16 +2770,29 @@ recur:
 		return 0;
 
 	switch (btf_kind(local_type)) {
-	case BTF_KIND_FWD:
 	case BTF_KIND_PTR:
 		return 1;
-	case BTF_KIND_ENUM:
-		return local_type->size == targ_type->size;
+	case BTF_KIND_FWD:
+	case BTF_KIND_ENUM: {
+		const char *local_name, *targ_name;
+		size_t local_len, targ_len;
+
+		local_name = btf__name_by_offset(local_btf,
+						 local_type->name_off);
+		targ_name = btf__name_by_offset(targ_btf, targ_type->name_off);
+		local_len = bpf_core_essential_name_len(local_name);
+		targ_len = bpf_core_essential_name_len(targ_name);
+		/* one of them is anonymous or both w/ same flavor-less names */
+		return local_len == 0 || targ_len == 0 ||
+		       (local_len == targ_len &&
+			strncmp(local_name, targ_name, local_len) == 0);
+	}
 	case BTF_KIND_INT:
+		/* just reject deprecated bitfield-like integers; all other
+		 * integers are by default compatible between each other
+		 */
 		return btf_int_offset(local_type) == 0 &&
-		       btf_int_offset(targ_type) == 0 &&
-		       local_type->size == targ_type->size &&
-		       btf_int_bits(local_type) == btf_int_bits(targ_type);
+		       btf_int_offset(targ_type) == 0;
 	case BTF_KIND_ARRAY:
 		local_id = btf_array(local_type)->type;
 		targ_id = btf_array(targ_type)->type;
@@ -2762,7 +2808,7 @@ recur:
  * Given single high-level named field accessor in local type, find
  * corresponding high-level accessor for a target type. Along the way,
  * maintain low-level spec for target as well. Also keep updating target
- * offset.
+ * bit offset.
  *
  * Searching is performed through recursive exhaustive enumeration of all
  * fields of a struct/union. If there are any anonymous (embedded)
@@ -2801,21 +2847,16 @@ static int bpf_core_match_member(const struct btf *local_btf,
 	n = btf_vlen(targ_type);
 	m = btf_members(targ_type);
 	for (i = 0; i < n; i++, m++) {
-		__u32 offset;
+		__u32 bit_offset;
 
-		/* bitfield relocations not supported */
-		if (btf_member_bitfield_size(targ_type, i))
-			continue;
-		offset = btf_member_bit_offset(targ_type, i);
-		if (offset % 8)
-			continue;
+		bit_offset = btf_member_bit_offset(targ_type, i);
 
 		/* too deep struct/union/array nesting */
 		if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN)
 			return -E2BIG;
 
 		/* speculate this member will be the good one */
-		spec->offset += offset / 8;
+		spec->bit_offset += bit_offset;
 		spec->raw_spec[spec->raw_len++] = i;
 
 		targ_name = btf__name_by_offset(targ_btf, m->name_off);
@@ -2844,7 +2885,7 @@ static int bpf_core_match_member(const struct btf *local_btf,
 			return found;
 		}
 		/* member turned out not to be what we looked for */
-		spec->offset -= offset / 8;
+		spec->bit_offset -= bit_offset;
 		spec->raw_len--;
 	}
 
@@ -2853,7 +2894,7 @@ static int bpf_core_match_member(const struct btf *local_btf,
 
 /*
  * Try to match local spec to a target type and, if successful, produce full
- * target spec (high-level, low-level + offset).
+ * target spec (high-level, low-level + bit offset).
  */
 static int bpf_core_spec_match(struct bpf_core_spec *local_spec,
 			       const struct btf *targ_btf, __u32 targ_id,
@@ -2916,13 +2957,120 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec,
 			sz = btf__resolve_size(targ_btf, targ_id);
 			if (sz < 0)
 				return sz;
-			targ_spec->offset += local_acc->idx * sz;
+			targ_spec->bit_offset += local_acc->idx * sz * 8;
 		}
 	}
 
 	return 1;
 }
 
+static int bpf_core_calc_field_relo(const struct bpf_program *prog,
+				    const struct bpf_field_reloc *relo,
+				    const struct bpf_core_spec *spec,
+				    __u32 *val, bool *validate)
+{
+	const struct bpf_core_accessor *acc = &spec->spec[spec->len - 1];
+	const struct btf_type *t = btf__type_by_id(spec->btf, acc->type_id);
+	__u32 byte_off, byte_sz, bit_off, bit_sz;
+	const struct btf_member *m;
+	const struct btf_type *mt;
+	bool bitfield;
+	__s64 sz;
+
+	/* a[n] accessor needs special handling */
+	if (!acc->name) {
+		if (relo->kind == BPF_FIELD_BYTE_OFFSET) {
+			*val = spec->bit_offset / 8;
+		} else if (relo->kind == BPF_FIELD_BYTE_SIZE) {
+			sz = btf__resolve_size(spec->btf, acc->type_id);
+			if (sz < 0)
+				return -EINVAL;
+			*val = sz;
+		} else {
+			pr_warn("prog '%s': relo %d at insn #%d can't be applied to array access\n",
+				bpf_program__title(prog, false),
+				relo->kind, relo->insn_off / 8);
+			return -EINVAL;
+		}
+		if (validate)
+			*validate = true;
+		return 0;
+	}
+
+	m = btf_members(t) + acc->idx;
+	mt = skip_mods_and_typedefs(spec->btf, m->type, NULL);
+	bit_off = spec->bit_offset;
+	bit_sz = btf_member_bitfield_size(t, acc->idx);
+
+	bitfield = bit_sz > 0;
+	if (bitfield) {
+		byte_sz = mt->size;
+		byte_off = bit_off / 8 / byte_sz * byte_sz;
+		/* figure out smallest int size necessary for bitfield load */
+		while (bit_off + bit_sz - byte_off * 8 > byte_sz * 8) {
+			if (byte_sz >= 8) {
+				/* bitfield can't be read with 64-bit read */
+				pr_warn("prog '%s': relo %d at insn #%d can't be satisfied for bitfield\n",
+					bpf_program__title(prog, false),
+					relo->kind, relo->insn_off / 8);
+				return -E2BIG;
+			}
+			byte_sz *= 2;
+			byte_off = bit_off / 8 / byte_sz * byte_sz;
+		}
+	} else {
+		sz = btf__resolve_size(spec->btf, m->type);
+		if (sz < 0)
+			return -EINVAL;
+		byte_sz = sz;
+		byte_off = spec->bit_offset / 8;
+		bit_sz = byte_sz * 8;
+	}
+
+	/* for bitfields, all the relocatable aspects are ambiguous and we
+	 * might disagree with compiler, so turn off validation of expected
+	 * value, except for signedness
+	 */
+	if (validate)
+		*validate = !bitfield;
+
+	switch (relo->kind) {
+	case BPF_FIELD_BYTE_OFFSET:
+		*val = byte_off;
+		break;
+	case BPF_FIELD_BYTE_SIZE:
+		*val = byte_sz;
+		break;
+	case BPF_FIELD_SIGNED:
+		/* enums will be assumed unsigned */
+		*val = btf_is_enum(mt) ||
+		       (btf_int_encoding(mt) & BTF_INT_SIGNED);
+		if (validate)
+			*validate = true; /* signedness is never ambiguous */
+		break;
+	case BPF_FIELD_LSHIFT_U64:
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+		*val = 64 - (bit_off + bit_sz - byte_off  * 8);
+#else
+		*val = (8 - byte_sz) * 8 + (bit_off - byte_off * 8);
+#endif
+		break;
+	case BPF_FIELD_RSHIFT_U64:
+		*val = 64 - bit_sz;
+		if (validate)
+			*validate = true; /* right shift is never ambiguous */
+		break;
+	case BPF_FIELD_EXISTS:
+	default:
+		pr_warn("prog '%s': unknown relo %d at insn #%d\n",
+			bpf_program__title(prog, false),
+			relo->kind, relo->insn_off / 8);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /*
  * Patch relocatable BPF instruction.
  *
@@ -2942,36 +3090,31 @@ static int bpf_core_reloc_insn(struct bpf_program *prog,
 			       const struct bpf_core_spec *local_spec,
 			       const struct bpf_core_spec *targ_spec)
 {
+	bool failed = false, validate = true;
 	__u32 orig_val, new_val;
 	struct bpf_insn *insn;
-	int insn_idx;
+	int insn_idx, err;
 	__u8 class;
 
 	if (relo->insn_off % sizeof(struct bpf_insn))
 		return -EINVAL;
 	insn_idx = relo->insn_off / sizeof(struct bpf_insn);
 
-	switch (relo->kind) {
-	case BPF_FIELD_BYTE_OFFSET:
-		orig_val = local_spec->offset;
-		if (targ_spec) {
-			new_val = targ_spec->offset;
-		} else {
-			pr_warn("prog '%s': patching insn #%d w/ failed reloc, imm %d -> %d\n",
-				bpf_program__title(prog, false), insn_idx,
-				orig_val, -1);
-			new_val = (__u32)-1;
-		}
-		break;
-	case BPF_FIELD_EXISTS:
+	if (relo->kind == BPF_FIELD_EXISTS) {
 		orig_val = 1; /* can't generate EXISTS relo w/o local field */
 		new_val = targ_spec ? 1 : 0;
-		break;
-	default:
-		pr_warn("prog '%s': unknown relo %d at insn #%d'\n",
-			bpf_program__title(prog, false),
-			relo->kind, insn_idx);
-		return -EINVAL;
+	} else if (!targ_spec) {
+		failed = true;
+		new_val = (__u32)-1;
+	} else {
+		err = bpf_core_calc_field_relo(prog, relo, local_spec,
+					       &orig_val, &validate);
+		if (err)
+			return err;
+		err = bpf_core_calc_field_relo(prog, relo, targ_spec,
+					       &new_val, NULL);
+		if (err)
+			return err;
 	}
 
 	insn = &prog->insns[insn_idx];
@@ -2980,12 +3123,17 @@ static int bpf_core_reloc_insn(struct bpf_program *prog,
 	if (class == BPF_ALU || class == BPF_ALU64) {
 		if (BPF_SRC(insn->code) != BPF_K)
 			return -EINVAL;
-		if (insn->imm != orig_val)
+		if (!failed && validate && insn->imm != orig_val) {
+			pr_warn("prog '%s': unexpected insn #%d value: got %u, exp %u -> %u\n",
+				bpf_program__title(prog, false), insn_idx,
+				insn->imm, orig_val, new_val);
 			return -EINVAL;
+		}
+		orig_val = insn->imm;
 		insn->imm = new_val;
-		pr_debug("prog '%s': patched insn #%d (ALU/ALU64) imm %d -> %d\n",
-			 bpf_program__title(prog, false),
-			 insn_idx, orig_val, new_val);
+		pr_debug("prog '%s': patched insn #%d (ALU/ALU64)%s imm %u -> %u\n",
+			 bpf_program__title(prog, false), insn_idx,
+			 failed ? " w/ failed reloc" : "", orig_val, new_val);
 	} else {
 		pr_warn("prog '%s': trying to relocate unrecognized insn #%d, code:%x, src:%x, dst:%x, off:%x, imm:%x\n",
 			bpf_program__title(prog, false),
@@ -3103,7 +3251,8 @@ static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec)
 		libbpf_print(level, "%d%s", spec->raw_spec[i],
 			     i == spec->raw_len - 1 ? " => " : ":");
 
-	libbpf_print(level, "%u @ &x", spec->offset);
+	libbpf_print(level, "%u.%u @ &x",
+		     spec->bit_offset / 8, spec->bit_offset % 8);
 
 	for (i = 0; i < spec->len; i++) {
 		if (spec->spec[i].name)
@@ -3217,7 +3366,8 @@ static int bpf_core_reloc_field(struct bpf_program *prog,
 		return -EINVAL;
 	}
 
-	pr_debug("prog '%s': relo #%d: spec is ", prog_name, relo_idx);
+	pr_debug("prog '%s': relo #%d: kind %d, spec is ", prog_name, relo_idx,
+		 relo->kind);
 	bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec);
 	libbpf_print(LIBBPF_DEBUG, "\n");
 
@@ -3257,13 +3407,13 @@ static int bpf_core_reloc_field(struct bpf_program *prog,
 
 		if (j == 0) {
 			targ_spec = cand_spec;
-		} else if (cand_spec.offset != targ_spec.offset) {
+		} else if (cand_spec.bit_offset != targ_spec.bit_offset) {
 			/* if there are many candidates, they should all
-			 * resolve to the same offset
+			 * resolve to the same bit offset
 			 */
 			pr_warn("prog '%s': relo #%d: offset ambiguity: %u != %u\n",
-				prog_name, relo_idx, cand_spec.offset,
-				targ_spec.offset);
+				prog_name, relo_idx, cand_spec.bit_offset,
+				targ_spec.bit_offset);
 			return -EINVAL;
 		}
 
@@ -3408,6 +3558,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 			pr_warn("oom in prog realloc\n");
 			return -ENOMEM;
 		}
+		prog->insns = new_insn;
 
 		if (obj->btf_ext) {
 			err = bpf_program_reloc_btf_ext(prog, obj,
@@ -3419,7 +3570,6 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 
 		memcpy(new_insn + prog->insns_cnt, text->insns,
 		       text->insns_cnt * sizeof(*insn));
-		prog->insns = new_insn;
 		prog->main_prog_cnt = prog->insns_cnt;
 		prog->insns_cnt = new_cnt;
 		pr_debug("added %zd insn from %s to prog %s\n",
@@ -3427,7 +3577,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 			 prog->section_name);
 	}
 	insn = &prog->insns[relo->insn_idx];
-	insn->imm += prog->main_prog_cnt - relo->insn_idx;
+	insn->imm += relo->text_off + prog->main_prog_cnt - relo->insn_idx;
 	return 0;
 }
 
@@ -3566,8 +3716,13 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	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->prog_ifindex;
+	if (prog->type == BPF_PROG_TYPE_TRACING) {
+		load_attr.attach_prog_fd = prog->attach_prog_fd;
+		load_attr.attach_btf_id = prog->attach_btf_id;
+	} else {
+		load_attr.kern_version = kern_version;
+		load_attr.prog_ifindex = prog->prog_ifindex;
+	}
 	/* if .BTF.ext was loaded, kernel supports associated BTF for prog */
 	if (prog->obj->btf_ext)
 		btf_fd = bpf_object__btf_fd(prog->obj);
@@ -3582,7 +3737,6 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	load_attr.line_info_cnt = prog->line_info_cnt;
 	load_attr.log_level = prog->log_level;
 	load_attr.prog_flags = prog->prog_flags;
-	load_attr.attach_btf_id = prog->attach_btf_id;
 
 retry_load:
 	log_buf = malloc(log_buf_size);
@@ -3604,7 +3758,7 @@ retry_load:
 		free(log_buf);
 		goto retry_load;
 	}
-	ret = -LIBBPF_ERRNO__LOAD;
+	ret = -errno;
 	cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 	pr_warn("load bpf program failed: %s\n", cp);
 
@@ -3617,23 +3771,18 @@ retry_load:
 		pr_warn("Program too large (%zu insns), at most %d insns\n",
 			load_attr.insns_cnt, BPF_MAXINSNS);
 		ret = -LIBBPF_ERRNO__PROG2BIG;
-	} else {
+	} else if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) {
 		/* Wrong program type? */
-		if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) {
-			int fd;
-
-			load_attr.prog_type = BPF_PROG_TYPE_KPROBE;
-			load_attr.expected_attach_type = 0;
-			fd = bpf_load_program_xattr(&load_attr, NULL, 0);
-			if (fd >= 0) {
-				close(fd);
-				ret = -LIBBPF_ERRNO__PROGTYPE;
-				goto out;
-			}
-		}
+		int fd;
 
-		if (log_buf)
-			ret = -LIBBPF_ERRNO__KVER;
+		load_attr.prog_type = BPF_PROG_TYPE_KPROBE;
+		load_attr.expected_attach_type = 0;
+		fd = bpf_load_program_xattr(&load_attr, NULL, 0);
+		if (fd >= 0) {
+			close(fd);
+			ret = -LIBBPF_ERRNO__PROGTYPE;
+			goto out;
+		}
 	}
 
 out:
@@ -3744,8 +3893,9 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level)
 	return 0;
 }
 
-static int libbpf_attach_btf_id_by_name(const char *name, __u32 *btf_id);
-
+static int libbpf_find_attach_btf_id(const char *name,
+				     enum bpf_attach_type attach_type,
+				     __u32 attach_prog_fd);
 static struct bpf_object *
 __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 		   struct bpf_object_open_opts *opts)
@@ -3756,6 +3906,7 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 	const char *obj_name;
 	char tmp_name[64];
 	bool relaxed_maps;
+	__u32 attach_prog_fd;
 	int err;
 
 	if (elf_version(EV_CURRENT) == EV_NONE) {
@@ -3786,6 +3937,7 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 	obj->relaxed_core_relocs = OPTS_GET(opts, relaxed_core_relocs, false);
 	relaxed_maps = OPTS_GET(opts, relaxed_maps, false);
 	pin_root_path = OPTS_GET(opts, pin_root_path, NULL);
+	attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0);
 
 	CHECK_ERR(bpf_object__elf_init(obj), err, out);
 	CHECK_ERR(bpf_object__check_endianness(obj), err, out);
@@ -3798,7 +3950,6 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 	bpf_object__for_each_program(prog, obj) {
 		enum bpf_prog_type prog_type;
 		enum bpf_attach_type attach_type;
-		__u32 btf_id;
 
 		err = libbpf_prog_type_by_name(prog->section_name, &prog_type,
 					       &attach_type);
@@ -3811,10 +3962,13 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 		bpf_program__set_type(prog, prog_type);
 		bpf_program__set_expected_attach_type(prog, attach_type);
 		if (prog_type == BPF_PROG_TYPE_TRACING) {
-			err = libbpf_attach_btf_id_by_name(prog->section_name, &btf_id);
-			if (err)
+			err = libbpf_find_attach_btf_id(prog->section_name,
+							attach_type,
+							attach_prog_fd);
+			if (err <= 0)
 				goto out;
-			prog->attach_btf_id = btf_id;
+			prog->attach_btf_id = err;
+			prog->attach_prog_fd = attach_prog_fd;
 		}
 	}
 
@@ -3911,7 +4065,7 @@ int bpf_object__unload(struct bpf_object *obj)
 int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 {
 	struct bpf_object *obj;
-	int err;
+	int err, i;
 
 	if (!attr)
 		return -EINVAL;
@@ -3932,6 +4086,11 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 
 	return 0;
 out:
+	/* unpin any maps that were auto-pinned during load */
+	for (i = 0; i < obj->nr_maps; i++)
+		if (obj->maps[i].pinned && !obj->maps[i].reused)
+			bpf_map__unpin(&obj->maps[i], NULL);
+
 	bpf_object__unload(obj);
 	pr_warn("failed to load object '%s'\n", obj->path);
 	return err;
@@ -4665,6 +4824,11 @@ int bpf_program__fd(const struct bpf_program *prog)
 	return bpf_program__nth_fd(prog, 0);
 }
 
+size_t bpf_program__size(const struct bpf_program *prog)
+{
+	return prog->insns_cnt * sizeof(struct bpf_insn);
+}
+
 int bpf_program__set_prep(struct bpf_program *prog, int nr_instances,
 			  bpf_program_prep_t prep)
 {
@@ -4813,6 +4977,10 @@ static const struct {
 	BPF_PROG_SEC("raw_tp/",			BPF_PROG_TYPE_RAW_TRACEPOINT),
 	BPF_PROG_BTF("tp_btf/",			BPF_PROG_TYPE_TRACING,
 						BPF_TRACE_RAW_TP),
+	BPF_PROG_BTF("fentry/",			BPF_PROG_TYPE_TRACING,
+						BPF_TRACE_FENTRY),
+	BPF_PROG_BTF("fexit/",			BPF_PROG_TYPE_TRACING,
+						BPF_TRACE_FEXIT),
 	BPF_PROG_SEC("xdp",			BPF_PROG_TYPE_XDP),
 	BPF_PROG_SEC("perf_event",		BPF_PROG_TYPE_PERF_EVENT),
 	BPF_PROG_SEC("lwt_in",			BPF_PROG_TYPE_LWT_IN),
@@ -4930,43 +5098,94 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
 }
 
 #define BTF_PREFIX "btf_trace_"
-static int libbpf_attach_btf_id_by_name(const char *name, __u32 *btf_id)
+int libbpf_find_vmlinux_btf_id(const char *name,
+			       enum bpf_attach_type attach_type)
 {
 	struct btf *btf = bpf_core_find_kernel_btf();
-	char raw_tp_btf_name[128] = BTF_PREFIX;
-	char *dst = raw_tp_btf_name + sizeof(BTF_PREFIX) - 1;
-	int ret, i, err = -EINVAL;
+	char raw_tp_btf[128] = BTF_PREFIX;
+	char *dst = raw_tp_btf + sizeof(BTF_PREFIX) - 1;
+	const char *btf_name;
+	int err = -EINVAL;
+	u32 kind;
 
 	if (IS_ERR(btf)) {
 		pr_warn("vmlinux BTF is not found\n");
 		return -EINVAL;
 	}
 
-	if (!name)
+	if (attach_type == BPF_TRACE_RAW_TP) {
+		/* prepend "btf_trace_" prefix per kernel convention */
+		strncat(dst, name, sizeof(raw_tp_btf) - sizeof(BTF_PREFIX));
+		btf_name = raw_tp_btf;
+		kind = BTF_KIND_TYPEDEF;
+	} else {
+		btf_name = name;
+		kind = BTF_KIND_FUNC;
+	}
+	err = btf__find_by_name_kind(btf, btf_name, kind);
+	btf__free(btf);
+	return err;
+}
+
+static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
+{
+	struct bpf_prog_info_linear *info_linear;
+	struct bpf_prog_info *info;
+	struct btf *btf = NULL;
+	int err = -EINVAL;
+
+	info_linear = bpf_program__get_prog_info_linear(attach_prog_fd, 0);
+	if (IS_ERR_OR_NULL(info_linear)) {
+		pr_warn("failed get_prog_info_linear for FD %d\n",
+			attach_prog_fd);
+		return -EINVAL;
+	}
+	info = &info_linear->info;
+	if (!info->btf_id) {
+		pr_warn("The target program doesn't have BTF\n");
 		goto out;
+	}
+	if (btf__get_from_id(info->btf_id, &btf)) {
+		pr_warn("Failed to get BTF of the program\n");
+		goto out;
+	}
+	err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC);
+	btf__free(btf);
+	if (err <= 0) {
+		pr_warn("%s is not found in prog's BTF\n", name);
+		goto out;
+	}
+out:
+	free(info_linear);
+	return err;
+}
+
+static int libbpf_find_attach_btf_id(const char *name,
+				     enum bpf_attach_type attach_type,
+				     __u32 attach_prog_fd)
+{
+	int i, err;
+
+	if (!name)
+		return -EINVAL;
 
 	for (i = 0; i < ARRAY_SIZE(section_names); i++) {
 		if (!section_names[i].is_attach_btf)
 			continue;
 		if (strncmp(name, section_names[i].sec, section_names[i].len))
 			continue;
-		/* prepend "btf_trace_" prefix per kernel convention */
-		strncat(dst, name + section_names[i].len,
-			sizeof(raw_tp_btf_name) - sizeof(BTF_PREFIX));
-		ret = btf__find_by_name(btf, raw_tp_btf_name);
-		if (ret <= 0) {
-			pr_warn("%s is not found in vmlinux BTF\n", dst);
-			goto out;
-		}
-		*btf_id = ret;
-		err = 0;
-		goto out;
+		if (attach_prog_fd)
+			err = libbpf_find_prog_btf_id(name + section_names[i].len,
+						      attach_prog_fd);
+		else
+			err = libbpf_find_vmlinux_btf_id(name + section_names[i].len,
+							 attach_type);
+		if (err <= 0)
+			pr_warn("%s is not found in vmlinux BTF\n", name);
+		return err;
 	}
 	pr_warn("failed to identify btf_id based on ELF section name '%s'\n", name);
-	err = -ESRCH;
-out:
-	btf__free(btf);
-	return err;
+	return -ESRCH;
 }
 
 int libbpf_attach_type_by_name(const char *name,
@@ -5594,6 +5813,37 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 	return (struct bpf_link *)link;
 }
 
+struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog)
+{
+	char errmsg[STRERR_BUFSIZE];
+	struct bpf_link_fd *link;
+	int prog_fd, pfd;
+
+	prog_fd = bpf_program__fd(prog);
+	if (prog_fd < 0) {
+		pr_warn("program '%s': can't attach before loaded\n",
+			bpf_program__title(prog, false));
+		return ERR_PTR(-EINVAL);
+	}
+
+	link = malloc(sizeof(*link));
+	if (!link)
+		return ERR_PTR(-ENOMEM);
+	link->link.destroy = &bpf_link__destroy_fd;
+
+	pfd = bpf_raw_tracepoint_open(NULL, prog_fd);
+	if (pfd < 0) {
+		pfd = -errno;
+		free(link);
+		pr_warn("program '%s': failed to attach to trace: %s\n",
+			bpf_program__title(prog, false),
+			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
+		return ERR_PTR(pfd);
+	}
+	link->fd = pfd;
+	return (struct bpf_link *)link;
+}
+
 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,
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 6ddc0419337b..0dbf4bfba0c4 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -108,8 +108,9 @@ struct bpf_object_open_opts {
 	 * auto-pinned to that path on load; defaults to "/sys/fs/bpf".
 	 */
 	const char *pin_root_path;
+	__u32 attach_prog_fd;
 };
-#define bpf_object_open_opts__last_field pin_root_path
+#define bpf_object_open_opts__last_field attach_prog_fd
 
 LIBBPF_API struct bpf_object *bpf_object__open(const char *path);
 LIBBPF_API struct bpf_object *
@@ -188,6 +189,8 @@ libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
 			 enum bpf_attach_type *expected_attach_type);
 LIBBPF_API int libbpf_attach_type_by_name(const char *name,
 					  enum bpf_attach_type *attach_type);
+LIBBPF_API int libbpf_find_vmlinux_btf_id(const char *name,
+					  enum bpf_attach_type attach_type);
 
 /* Accessors of bpf_program */
 struct bpf_program;
@@ -214,6 +217,9 @@ LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog,
 LIBBPF_API const char *bpf_program__title(const struct bpf_program *prog,
 					  bool needs_copy);
 
+/* returns program size in bytes */
+LIBBPF_API size_t bpf_program__size(const struct bpf_program *prog);
+
 LIBBPF_API int bpf_program__load(struct bpf_program *prog, char *license,
 				 __u32 kern_version);
 LIBBPF_API int bpf_program__fd(const struct bpf_program *prog);
@@ -248,6 +254,8 @@ LIBBPF_API struct bpf_link *
 bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 				   const char *tp_name);
 
+LIBBPF_API struct bpf_link *
+bpf_program__attach_trace(struct bpf_program *prog);
 struct bpf_insn;
 
 /*
@@ -427,8 +435,18 @@ LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type,
 			     struct bpf_object **pobj, int *prog_fd);
 
+struct xdp_link_info {
+	__u32 prog_id;
+	__u32 drv_prog_id;
+	__u32 hw_prog_id;
+	__u32 skb_prog_id;
+	__u8 attach_mode;
+};
+
 LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
 LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags);
+LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
+				     size_t info_size, __u32 flags);
 
 struct perf_buffer;
 
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 86173cbb159d..8ddc2c40e482 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -193,13 +193,18 @@ LIBBPF_0.0.5 {
 
 LIBBPF_0.0.6 {
 	global:
+		bpf_get_link_xdp_info;
 		bpf_map__get_pin_path;
 		bpf_map__is_pinned;
 		bpf_map__set_pin_path;
 		bpf_object__open_file;
 		bpf_object__open_mem;
+		bpf_program__attach_trace;
 		bpf_program__get_expected_attach_type;
 		bpf_program__get_type;
 		bpf_program__is_tracing;
 		bpf_program__set_tracing;
+		bpf_program__size;
+		btf__find_by_name_kind;
+		libbpf_find_vmlinux_btf_id;
 } LIBBPF_0.0.5;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index bd6f48ea407b..97ac17a64a58 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -158,7 +158,11 @@ struct bpf_line_info_min {
  */
 enum bpf_field_info_kind {
 	BPF_FIELD_BYTE_OFFSET = 0,	/* field byte offset */
+	BPF_FIELD_BYTE_SIZE = 1,
 	BPF_FIELD_EXISTS = 2,		/* field existence in target kernel */
+	BPF_FIELD_SIGNED = 3,
+	BPF_FIELD_LSHIFT_U64 = 4,
+	BPF_FIELD_RSHIFT_U64 = 5,
 };
 
 /* The minimum bpf_field_reloc checked by the loader
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index ce3ec81b71c0..5065c1aa1061 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -12,6 +12,7 @@
 
 #include "bpf.h"
 #include "libbpf.h"
+#include "libbpf_internal.h"
 #include "nlattr.h"
 
 #ifndef SOL_NETLINK
@@ -24,7 +25,7 @@ typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, libbpf_dump_nlmsg_t,
 struct xdp_id_md {
 	int ifindex;
 	__u32 flags;
-	__u32 id;
+	struct xdp_link_info info;
 };
 
 int libbpf_netlink_open(__u32 *nl_pid)
@@ -43,7 +44,7 @@ int libbpf_netlink_open(__u32 *nl_pid)
 
 	if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
 		       &one, sizeof(one)) < 0) {
-		fprintf(stderr, "Netlink error reporting not supported\n");
+		pr_warn("Netlink error reporting not supported\n");
 	}
 
 	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
@@ -202,26 +203,11 @@ static int __dump_link_nlmsg(struct nlmsghdr *nlh,
 	return dump_link_nlmsg(cookie, ifi, tb);
 }
 
-static unsigned char get_xdp_id_attr(unsigned char mode, __u32 flags)
-{
-	if (mode != XDP_ATTACHED_MULTI)
-		return IFLA_XDP_PROG_ID;
-	if (flags & XDP_FLAGS_DRV_MODE)
-		return IFLA_XDP_DRV_PROG_ID;
-	if (flags & XDP_FLAGS_HW_MODE)
-		return IFLA_XDP_HW_PROG_ID;
-	if (flags & XDP_FLAGS_SKB_MODE)
-		return IFLA_XDP_SKB_PROG_ID;
-
-	return IFLA_XDP_UNSPEC;
-}
-
-static int get_xdp_id(void *cookie, void *msg, struct nlattr **tb)
+static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb)
 {
 	struct nlattr *xdp_tb[IFLA_XDP_MAX + 1];
 	struct xdp_id_md *xdp_id = cookie;
 	struct ifinfomsg *ifinfo = msg;
-	unsigned char mode, xdp_attr;
 	int ret;
 
 	if (xdp_id->ifindex && xdp_id->ifindex != ifinfo->ifi_index)
@@ -237,27 +223,40 @@ static int get_xdp_id(void *cookie, void *msg, struct nlattr **tb)
 	if (!xdp_tb[IFLA_XDP_ATTACHED])
 		return 0;
 
-	mode = libbpf_nla_getattr_u8(xdp_tb[IFLA_XDP_ATTACHED]);
-	if (mode == XDP_ATTACHED_NONE)
-		return 0;
+	xdp_id->info.attach_mode = libbpf_nla_getattr_u8(
+		xdp_tb[IFLA_XDP_ATTACHED]);
 
-	xdp_attr = get_xdp_id_attr(mode, xdp_id->flags);
-	if (!xdp_attr || !xdp_tb[xdp_attr])
+	if (xdp_id->info.attach_mode == XDP_ATTACHED_NONE)
 		return 0;
 
-	xdp_id->id = libbpf_nla_getattr_u32(xdp_tb[xdp_attr]);
+	if (xdp_tb[IFLA_XDP_PROG_ID])
+		xdp_id->info.prog_id = libbpf_nla_getattr_u32(
+			xdp_tb[IFLA_XDP_PROG_ID]);
+
+	if (xdp_tb[IFLA_XDP_SKB_PROG_ID])
+		xdp_id->info.skb_prog_id = libbpf_nla_getattr_u32(
+			xdp_tb[IFLA_XDP_SKB_PROG_ID]);
+
+	if (xdp_tb[IFLA_XDP_DRV_PROG_ID])
+		xdp_id->info.drv_prog_id = libbpf_nla_getattr_u32(
+			xdp_tb[IFLA_XDP_DRV_PROG_ID]);
+
+	if (xdp_tb[IFLA_XDP_HW_PROG_ID])
+		xdp_id->info.hw_prog_id = libbpf_nla_getattr_u32(
+			xdp_tb[IFLA_XDP_HW_PROG_ID]);
 
 	return 0;
 }
 
-int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags)
+int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
+			  size_t info_size, __u32 flags)
 {
 	struct xdp_id_md xdp_id = {};
 	int sock, ret;
 	__u32 nl_pid;
 	__u32 mask;
 
-	if (flags & ~XDP_FLAGS_MASK)
+	if (flags & ~XDP_FLAGS_MASK || !info_size)
 		return -EINVAL;
 
 	/* Check whether the single {HW,DRV,SKB} mode is set */
@@ -273,14 +272,44 @@ int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags)
 	xdp_id.ifindex = ifindex;
 	xdp_id.flags = flags;
 
-	ret = libbpf_nl_get_link(sock, nl_pid, get_xdp_id, &xdp_id);
-	if (!ret)
-		*prog_id = xdp_id.id;
+	ret = libbpf_nl_get_link(sock, nl_pid, get_xdp_info, &xdp_id);
+	if (!ret) {
+		size_t sz = min(info_size, sizeof(xdp_id.info));
+
+		memcpy(info, &xdp_id.info, sz);
+		memset((void *) info + sz, 0, info_size - sz);
+	}
 
 	close(sock);
 	return ret;
 }
 
+static __u32 get_xdp_id(struct xdp_link_info *info, __u32 flags)
+{
+	if (info->attach_mode != XDP_ATTACHED_MULTI)
+		return info->prog_id;
+	if (flags & XDP_FLAGS_DRV_MODE)
+		return info->drv_prog_id;
+	if (flags & XDP_FLAGS_HW_MODE)
+		return info->hw_prog_id;
+	if (flags & XDP_FLAGS_SKB_MODE)
+		return info->skb_prog_id;
+
+	return 0;
+}
+
+int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags)
+{
+	struct xdp_link_info info;
+	int ret;
+
+	ret = bpf_get_link_xdp_info(ifindex, &info, sizeof(info), flags);
+	if (!ret)
+		*prog_id = get_xdp_id(&info, flags);
+
+	return ret;
+}
+
 int libbpf_nl_get_link(int sock, unsigned int nl_pid,
 		       libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie)
 {
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
index 1e69c0c8d413..8db44bbfc66d 100644
--- a/tools/lib/bpf/nlattr.c
+++ b/tools/lib/bpf/nlattr.c
@@ -8,6 +8,7 @@
 
 #include <errno.h>
 #include "nlattr.h"
+#include "libbpf_internal.h"
 #include <linux/rtnetlink.h>
 #include <string.h>
 #include <stdio.h>
@@ -121,8 +122,8 @@ int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head,
 		}
 
 		if (tb[type])
-			fprintf(stderr, "Attribute of type %#x found multiple times in message, "
-				  "previous attribute is being ignored.\n", type);
+			pr_warn("Attribute of type %#x found multiple times in message, "
+				"previous attribute is being ignored.\n", type);
 
 		tb[type] = nla;
 	}
@@ -181,15 +182,14 @@ int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh)
 
 	if (libbpf_nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen,
 			     extack_policy) != 0) {
-		fprintf(stderr,
-			"Failed to parse extended error attributes\n");
+		pr_warn("Failed to parse extended error attributes\n");
 		return 0;
 	}
 
 	if (tb[NLMSGERR_ATTR_MSG])
 		errmsg = (char *) libbpf_nla_data(tb[NLMSGERR_ATTR_MSG]);
 
-	fprintf(stderr, "Kernel error message: %s\n", errmsg);
+	pr_warn("Kernel error message: %s\n", errmsg);
 
 	return 0;
 }
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 74d84f36a5b2..8e0ffa800a71 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -431,13 +431,18 @@ static int xsk_get_max_queues(struct xsk_socket *xsk)
 		goto out;
 	}
 
-	if (err || channels.max_combined == 0)
+	if (err) {
 		/* If the device says it has no channels, then all traffic
 		 * is sent to a single stream, so max queues = 1.
 		 */
 		ret = 1;
-	else
-		ret = channels.max_combined;
+	} else {
+		/* Take the max of rx, tx, combined. Drivers return
+		 * the number of channels in different ways.
+		 */
+		ret = max(channels.max_rx, channels.max_tx);
+		ret = max(ret, (int)channels.max_combined);
+	}
 
 out:
 	close(fd);
@@ -553,6 +558,8 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
 		}
 	} else {
 		xsk->prog_fd = bpf_prog_get_fd_by_id(prog_id);
+		if (xsk->prog_fd < 0)
+			return -errno;
 		err = xsk_lookup_bpf_maps(xsk);
 		if (err) {
 			close(xsk->prog_fd);
@@ -560,7 +567,8 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk)
 		}
 	}
 
-	err = xsk_set_bpf_maps(xsk);
+	if (xsk->rx)
+		err = xsk_set_bpf_maps(xsk);
 	if (err) {
 		xsk_delete_bpf_maps(xsk);
 		close(xsk->prog_fd);
@@ -581,18 +589,24 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	struct xsk_socket *xsk;
 	int err;
 
-	if (!umem || !xsk_ptr || !rx || !tx)
+	if (!umem || !xsk_ptr || !(rx || tx))
 		return -EFAULT;
 
-	if (umem->refcount) {
-		pr_warn("Error: shared umems not supported by libbpf.\n");
-		return -EBUSY;
-	}
-
 	xsk = calloc(1, sizeof(*xsk));
 	if (!xsk)
 		return -ENOMEM;
 
+	err = xsk_set_xdp_socket_config(&xsk->config, usr_config);
+	if (err)
+		goto out_xsk_alloc;
+
+	if (umem->refcount &&
+	    !(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) {
+		pr_warn("Error: shared umems not supported by libbpf supplied XDP program.\n");
+		err = -EBUSY;
+		goto out_xsk_alloc;
+	}
+
 	if (umem->refcount++ > 0) {
 		xsk->fd = socket(AF_XDP, SOCK_RAW, 0);
 		if (xsk->fd < 0) {
@@ -614,10 +628,6 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	memcpy(xsk->ifname, ifname, IFNAMSIZ - 1);
 	xsk->ifname[IFNAMSIZ - 1] = '\0';
 
-	err = xsk_set_xdp_socket_config(&xsk->config, usr_config);
-	if (err)
-		goto out_socket;
-
 	if (rx) {
 		err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING,
 				 &xsk->config.rx_size,
@@ -685,7 +695,12 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	sxdp.sxdp_family = PF_XDP;
 	sxdp.sxdp_ifindex = xsk->ifindex;
 	sxdp.sxdp_queue_id = xsk->queue_id;
-	sxdp.sxdp_flags = xsk->config.bind_flags;
+	if (umem->refcount > 1) {
+		sxdp.sxdp_flags = XDP_SHARED_UMEM;
+		sxdp.sxdp_shared_umem_fd = umem->fd;
+	} else {
+		sxdp.sxdp_flags = xsk->config.bind_flags;
+	}
 
 	err = bind(xsk->fd, (struct sockaddr *)&sxdp, sizeof(sxdp));
 	if (err) {