Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - BPF:
      - add syscall program type and libbpf support for generating
        instructions and bindings for in-kernel BPF loaders (BPF loaders
        for BPF), this is a stepping stone for signed BPF programs
      - infrastructure to migrate TCP child sockets from one listener to
        another in the same reuseport group/map to improve flexibility
        of service hand-off/restart
      - add broadcast support to XDP redirect

   - allow bypass of the lockless qdisc to improving performance (for
     pktgen: +23% with one thread, +44% with 2 threads)

   - add a simpler version of "DO_ONCE()" which does not require jump
     labels, intended for slow-path usage

   - virtio/vsock: introduce SOCK_SEQPACKET support

   - add getsocketopt to retrieve netns cookie

   - ip: treat lowest address of a IPv4 subnet as ordinary unicast
     address allowing reclaiming of precious IPv4 addresses

   - ipv6: use prandom_u32() for ID generation

   - ip: add support for more flexible field selection for hashing
     across multi-path routes (w/ offload to mlxsw)

   - icmp: add support for extended RFC 8335 PROBE (ping)

   - seg6: add support for SRv6 End.DT46 behavior

   - mptcp:
      - DSS checksum support (RFC 8684) to detect middlebox meddling
      - support Connection-time 'C' flag
      - time stamping support

   - sctp: packetization Layer Path MTU Discovery (RFC 8899)

   - xfrm: speed up state addition with seq set

   - WiFi:
      - hidden AP discovery on 6 GHz and other HE 6 GHz improvements
      - aggregation handling improvements for some drivers
      - minstrel improvements for no-ack frames
      - deferred rate control for TXQs to improve reaction times
      - switch from round robin to virtual time-based airtime scheduler

   - add trace points:
      - tcp checksum errors
      - openvswitch - action execution, upcalls
      - socket errors via sk_error_report

  Device APIs:

   - devlink: add rate API for hierarchical control of max egress rate
     of virtual devices (VFs, SFs etc.)

   - don't require RCU read lock to be held around BPF hooks in NAPI
     context

   - page_pool: generic buffer recycling

  New hardware/drivers:

   - mobile:
      - iosm: PCIe Driver for Intel M.2 Modem
      - support for Qualcomm MSM8998 (ipa)

   - WiFi: Qualcomm QCN9074 and WCN6855 PCI devices

   - sparx5: Microchip SparX-5 family of Enterprise Ethernet switches

   - Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)

   - NXP SJA1110 Automotive Ethernet 10-port switch

   - Qualcomm QCA8327 switch support (qca8k)

   - Mikrotik 10/25G NIC (atl1c)

  Driver changes:

   - ACPI support for some MDIO, MAC and PHY devices from Marvell and
     NXP (our first foray into MAC/PHY description via ACPI)

   - HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx

   - Mellanox/Nvidia NIC (mlx5)
      - NIC VF offload of L2 bridging
      - support IRQ distribution to Sub-functions

   - Marvell (prestera):
      - add flower and match all
      - devlink trap
      - link aggregation

   - Netronome (nfp): connection tracking offload

   - Intel 1GE (igc): add AF_XDP support

   - Marvell DPU (octeontx2): ingress ratelimit offload

   - Google vNIC (gve): new ring/descriptor format support

   - Qualcomm mobile (rmnet & ipa): inline checksum offload support

   - MediaTek WiFi (mt76)
      - mt7915 MSI support
      - mt7915 Tx status reporting
      - mt7915 thermal sensors support
      - mt7921 decapsulation offload
      - mt7921 enable runtime pm and deep sleep

   - Realtek WiFi (rtw88)
      - beacon filter support
      - Tx antenna path diversity support
      - firmware crash information via devcoredump

   - Qualcomm WiFi (wcn36xx)
      - Wake-on-WLAN support with magic packets and GTK rekeying

   - Micrel PHY (ksz886x/ksz8081): add cable test support"

* tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits)
  tcp: change ICSK_CA_PRIV_SIZE definition
  tcp_yeah: check struct yeah size at compile time
  gve: DQO: Fix off by one in gve_rx_dqo()
  stmmac: intel: set PCI_D3hot in suspend
  stmmac: intel: Enable PHY WOL option in EHL
  net: stmmac: option to enable PHY WOL with PMT enabled
  net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del}
  net: use netdev_info in ndo_dflt_fdb_{add,del}
  ptp: Set lookup cookie when creating a PTP PPS source.
  net: sock: add trace for socket errors
  net: sock: introduce sk_error_report
  net: dsa: replay the local bridge FDB entries pointing to the bridge dev too
  net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev
  net: dsa: include fdb entries pointing to bridge in the host fdb list
  net: dsa: include bridge addresses which are local in the host fdb list
  net: dsa: sync static FDB entries on foreign interfaces to hardware
  net: dsa: install the host MDB and FDB entries in the master's RX filter
  net: dsa: reference count the FDB addresses at the cross-chip notifier level
  net: dsa: introduce a separate cross-chip notifier type for host FDBs
  net: dsa: reference count the MDB entries at the cross-chip notifier level
  ...

24 files changed, 2734 insertions, 907 deletions

diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index 9b057cc7650a..430f6874fa41 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1,3 +1,3 @@
 libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \
 	    netlink.o bpf_prog_linfo.o libbpf_probes.o xsk.o hashmap.o \
-	    btf_dump.o ringbuf.o strset.o linker.o
+	    btf_dump.o ringbuf.o strset.o linker.o gen_loader.o
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index e43e1896cb4b..ec14aa725bb0 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -223,18 +223,14 @@ install_lib: all_cmd
 		$(call do_install_mkdir,$(libdir_SQ)); \
 		cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ)
 
+INSTALL_HEADERS = bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h \
+		  bpf_helpers.h $(BPF_HELPER_DEFS) bpf_tracing.h	     \
+		  bpf_endian.h bpf_core_read.h skel_internal.h
+
 install_headers: $(BPF_HELPER_DEFS)
-	$(call QUIET_INSTALL, headers) \
-		$(call do_install,bpf.h,$(prefix)/include/bpf,644); \
-		$(call do_install,libbpf.h,$(prefix)/include/bpf,644); \
-		$(call do_install,btf.h,$(prefix)/include/bpf,644); \
-		$(call do_install,libbpf_common.h,$(prefix)/include/bpf,644); \
-		$(call do_install,xsk.h,$(prefix)/include/bpf,644); \
-		$(call do_install,bpf_helpers.h,$(prefix)/include/bpf,644); \
-		$(call do_install,$(BPF_HELPER_DEFS),$(prefix)/include/bpf,644); \
-		$(call do_install,bpf_tracing.h,$(prefix)/include/bpf,644); \
-		$(call do_install,bpf_endian.h,$(prefix)/include/bpf,644); \
-		$(call do_install,bpf_core_read.h,$(prefix)/include/bpf,644);
+	$(call QUIET_INSTALL, headers)					     \
+		$(foreach hdr,$(INSTALL_HEADERS),			     \
+			$(call do_install,$(hdr),$(prefix)/include/bpf,644);)
 
 install_pkgconfig: $(PC_FILE)
 	$(call QUIET_INSTALL, $(PC_FILE)) \
diff --git a/tools/lib/bpf/README.rst b/tools/lib/bpf/README.rst
deleted file mode 100644
index 8928f7787f2d..000000000000
--- a/tools/lib/bpf/README.rst
+++ /dev/null
@@ -1,168 +0,0 @@
-.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-
-libbpf API naming convention
-============================
-
-libbpf API provides access to a few logically separated groups of
-functions and types. Every group has its own naming convention
-described here. It's recommended to follow these conventions whenever a
-new function or type is added to keep libbpf API clean and consistent.
-
-All types and functions provided by libbpf API should have one of the
-following prefixes: ``bpf_``, ``btf_``, ``libbpf_``, ``xsk_``,
-``perf_buffer_``.
-
-System call wrappers
---------------------
-
-System call wrappers are simple wrappers for commands supported by
-sys_bpf system call. These wrappers should go to ``bpf.h`` header file
-and map one-on-one to corresponding commands.
-
-For example ``bpf_map_lookup_elem`` wraps ``BPF_MAP_LOOKUP_ELEM``
-command of sys_bpf, ``bpf_prog_attach`` wraps ``BPF_PROG_ATTACH``, etc.
-
-Objects
--------
-
-Another class of types and functions provided by libbpf API is "objects"
-and functions to work with them. Objects are high-level abstractions
-such as BPF program or BPF map. They're represented by corresponding
-structures such as ``struct bpf_object``, ``struct bpf_program``,
-``struct bpf_map``, etc.
-
-Structures are forward declared and access to their fields should be
-provided via corresponding getters and setters rather than directly.
-
-These objects are associated with corresponding parts of ELF object that
-contains compiled BPF programs.
-
-For example ``struct bpf_object`` represents ELF object itself created
-from an ELF file or from a buffer, ``struct bpf_program`` represents a
-program in ELF object and ``struct bpf_map`` is a map.
-
-Functions that work with an object have names built from object name,
-double underscore and part that describes function purpose.
-
-For example ``bpf_object__open`` consists of the name of corresponding
-object, ``bpf_object``, double underscore and ``open`` that defines the
-purpose of the function to open ELF file and create ``bpf_object`` from
-it.
-
-Another example: ``bpf_program__load`` is named for corresponding
-object, ``bpf_program``, that is separated from other part of the name
-by double underscore.
-
-All objects and corresponding functions other than BTF related should go
-to ``libbpf.h``. BTF types and functions should go to ``btf.h``.
-
-Auxiliary functions
--------------------
-
-Auxiliary functions and types that don't fit well in any of categories
-described above should have ``libbpf_`` prefix, e.g.
-``libbpf_get_error`` or ``libbpf_prog_type_by_name``.
-
-AF_XDP functions
--------------------
-
-AF_XDP functions should have an ``xsk_`` prefix, e.g.
-``xsk_umem__get_data`` or ``xsk_umem__create``. The interface consists
-of both low-level ring access functions and high-level configuration
-functions. These can be mixed and matched. Note that these functions
-are not reentrant for performance reasons.
-
-Please take a look at Documentation/networking/af_xdp.rst in the Linux
-kernel source tree on how to use XDP sockets and for some common
-mistakes in case you do not get any traffic up to user space.
-
-libbpf ABI
-==========
-
-libbpf can be both linked statically or used as DSO. To avoid possible
-conflicts with other libraries an application is linked with, all
-non-static libbpf symbols should have one of the prefixes mentioned in
-API documentation above. See API naming convention to choose the right
-name for a new symbol.
-
-Symbol visibility
------------------
-
-libbpf follow the model when all global symbols have visibility "hidden"
-by default and to make a symbol visible it has to be explicitly
-attributed with ``LIBBPF_API`` macro. For example:
-
-.. code-block:: c
-
-        LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id);
-
-This prevents from accidentally exporting a symbol, that is not supposed
-to be a part of ABI what, in turn, improves both libbpf developer- and
-user-experiences.
-
-ABI versionning
----------------
-
-To make future ABI extensions possible libbpf ABI is versioned.
-Versioning is implemented by ``libbpf.map`` version script that is
-passed to linker.
-
-Version name is ``LIBBPF_`` prefix + three-component numeric version,
-starting from ``0.0.1``.
-
-Every time ABI is being changed, e.g. because a new symbol is added or
-semantic of existing symbol is changed, ABI version should be bumped.
-This bump in ABI version is at most once per kernel development cycle.
-
-For example, if current state of ``libbpf.map`` is:
-
-.. code-block::
-        LIBBPF_0.0.1 {
-        	global:
-                        bpf_func_a;
-                        bpf_func_b;
-        	local:
-        		\*;
-        };
-
-, and a new symbol ``bpf_func_c`` is being introduced, then
-``libbpf.map`` should be changed like this:
-
-.. code-block::
-        LIBBPF_0.0.1 {
-        	global:
-                        bpf_func_a;
-                        bpf_func_b;
-        	local:
-        		\*;
-        };
-        LIBBPF_0.0.2 {
-                global:
-                        bpf_func_c;
-        } LIBBPF_0.0.1;
-
-, where new version ``LIBBPF_0.0.2`` depends on the previous
-``LIBBPF_0.0.1``.
-
-Format of version script and ways to handle ABI changes, including
-incompatible ones, described in details in [1].
-
-Stand-alone build
-=================
-
-Under https://github.com/libbpf/libbpf there is a (semi-)automated
-mirror of the mainline's version of libbpf for a stand-alone build.
-
-However, all changes to libbpf's code base must be upstreamed through
-the mainline kernel tree.
-
-License
-=======
-
-libbpf is dual-licensed under LGPL 2.1 and BSD 2-Clause.
-
-Links
-=====
-
-[1] https://www.akkadia.org/drepper/dsohowto.pdf
-    (Chapter 3. Maintaining APIs and ABIs).
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index bba48ff4c5c0..86dcac44f32f 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -80,6 +80,7 @@ static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size)
 int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, '\0', sizeof(attr));
 
@@ -102,7 +103,8 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
 	else
 		attr.inner_map_fd = create_attr->inner_map_fd;
 
-	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
@@ -160,6 +162,7 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
 			       __u32 map_flags, int node)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, '\0', sizeof(attr));
 
@@ -178,7 +181,8 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
 		attr.numa_node = node;
 	}
 
-	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name,
@@ -222,10 +226,10 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr)
 	int fd;
 
 	if (!load_attr->log_buf != !load_attr->log_buf_sz)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (load_attr->log_level > (4 | 2 | 1) || (load_attr->log_level && !load_attr->log_buf))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = load_attr->prog_type;
@@ -281,8 +285,10 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr)
 							load_attr->func_info_cnt,
 							load_attr->func_info_rec_size,
 							attr.func_info_rec_size);
-			if (!finfo)
+			if (!finfo) {
+				errno = E2BIG;
 				goto done;
+			}
 
 			attr.func_info = ptr_to_u64(finfo);
 			attr.func_info_rec_size = load_attr->func_info_rec_size;
@@ -293,8 +299,10 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr)
 							load_attr->line_info_cnt,
 							load_attr->line_info_rec_size,
 							attr.line_info_rec_size);
-			if (!linfo)
+			if (!linfo) {
+				errno = E2BIG;
 				goto done;
+			}
 
 			attr.line_info = ptr_to_u64(linfo);
 			attr.line_info_rec_size = load_attr->line_info_rec_size;
@@ -318,9 +326,10 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr)
 
 	fd = sys_bpf_prog_load(&attr, sizeof(attr));
 done:
+	/* free() doesn't affect errno, so we don't need to restore it */
 	free(finfo);
 	free(linfo);
-	return fd;
+	return libbpf_err_errno(fd);
 }
 
 int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
@@ -329,7 +338,7 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	struct bpf_prog_load_params p = {};
 
 	if (!load_attr || !log_buf != !log_buf_sz)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	p.prog_type = load_attr->prog_type;
 	p.expected_attach_type = load_attr->expected_attach_type;
@@ -391,6 +400,7 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 		       int log_level)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = type;
@@ -404,13 +414,15 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 	attr.kern_version = kern_version;
 	attr.prog_flags = prog_flags;
 
-	return sys_bpf_prog_load(&attr, sizeof(attr));
+	fd = sys_bpf_prog_load(&attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_map_update_elem(int fd, const void *key, const void *value,
 			__u64 flags)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
@@ -418,24 +430,28 @@ int bpf_map_update_elem(int fd, const void *key, const void *value,
 	attr.value = ptr_to_u64(value);
 	attr.flags = flags;
 
-	return sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_map_lookup_elem(int fd, const void *key, void *value)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
 
-	return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
@@ -443,17 +459,33 @@ int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags)
 	attr.value = ptr_to_u64(value);
 	attr.flags = flags;
 
-	return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value)
 {
 	union bpf_attr attr;
+	int ret;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.map_fd = fd;
+	attr.key = ptr_to_u64(key);
+	attr.value = ptr_to_u64(value);
+
+	ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
+}
+
+int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key, void *value, __u64 flags)
+{
+	union bpf_attr attr;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
+	attr.flags = flags;
 
 	return sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
 }
@@ -461,34 +493,40 @@ int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value)
 int bpf_map_delete_elem(int fd, const void *key)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 
-	return sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_map_get_next_key(int fd, const void *key, void *next_key)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.next_key = ptr_to_u64(next_key);
 
-	return sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_map_freeze(int fd)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 
-	return sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 static int bpf_map_batch_common(int cmd, int fd, void  *in_batch,
@@ -500,7 +538,7 @@ static int bpf_map_batch_common(int cmd, int fd, void  *in_batch,
 	int ret;
 
 	if (!OPTS_VALID(opts, bpf_map_batch_opts))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, sizeof(attr));
 	attr.batch.map_fd = fd;
@@ -515,7 +553,7 @@ static int bpf_map_batch_common(int cmd, int fd, void  *in_batch,
 	ret = sys_bpf(cmd, &attr, sizeof(attr));
 	*count = attr.batch.count;
 
-	return ret;
+	return libbpf_err_errno(ret);
 }
 
 int bpf_map_delete_batch(int fd, void *keys, __u32 *count,
@@ -552,22 +590,26 @@ int bpf_map_update_batch(int fd, void *keys, void *values, __u32 *count,
 int bpf_obj_pin(int fd, const char *pathname)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.pathname = ptr_to_u64((void *)pathname);
 	attr.bpf_fd = fd;
 
-	return sys_bpf(BPF_OBJ_PIN, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_OBJ_PIN, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_obj_get(const char *pathname)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.pathname = ptr_to_u64((void *)pathname);
 
-	return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
@@ -585,9 +627,10 @@ int bpf_prog_attach_xattr(int prog_fd, int target_fd,
 			  const struct bpf_prog_attach_opts *opts)
 {
 	union bpf_attr attr;
+	int ret;
 
 	if (!OPTS_VALID(opts, bpf_prog_attach_opts))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, sizeof(attr));
 	attr.target_fd	   = target_fd;
@@ -596,30 +639,35 @@ int bpf_prog_attach_xattr(int prog_fd, int target_fd,
 	attr.attach_flags  = OPTS_GET(opts, flags, 0);
 	attr.replace_bpf_fd = OPTS_GET(opts, replace_prog_fd, 0);
 
-	return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.target_fd	 = target_fd;
 	attr.attach_type = type;
 
-	return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.target_fd	 = target_fd;
 	attr.attach_bpf_fd = prog_fd;
 	attr.attach_type = type;
 
-	return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_link_create(int prog_fd, int target_fd,
@@ -628,15 +676,16 @@ int bpf_link_create(int prog_fd, int target_fd,
 {
 	__u32 target_btf_id, iter_info_len;
 	union bpf_attr attr;
+	int fd;
 
 	if (!OPTS_VALID(opts, bpf_link_create_opts))
-		return -EINVAL;
+		return libbpf_err(-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;
+		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, sizeof(attr));
 	attr.link_create.prog_fd = prog_fd;
@@ -652,26 +701,30 @@ int bpf_link_create(int prog_fd, int target_fd,
 		attr.link_create.target_btf_id = target_btf_id;
 	}
 
-	return sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_link_detach(int link_fd)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.link_detach.link_fd = link_fd;
 
-	return sys_bpf(BPF_LINK_DETACH, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_LINK_DETACH, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_link_update(int link_fd, int new_prog_fd,
 		    const struct bpf_link_update_opts *opts)
 {
 	union bpf_attr attr;
+	int ret;
 
 	if (!OPTS_VALID(opts, bpf_link_update_opts))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, sizeof(attr));
 	attr.link_update.link_fd = link_fd;
@@ -679,17 +732,20 @@ int bpf_link_update(int link_fd, int new_prog_fd,
 	attr.link_update.flags = OPTS_GET(opts, flags, 0);
 	attr.link_update.old_prog_fd = OPTS_GET(opts, old_prog_fd, 0);
 
-	return sys_bpf(BPF_LINK_UPDATE, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_LINK_UPDATE, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_iter_create(int link_fd)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.iter_create.link_fd = link_fd;
 
-	return sys_bpf(BPF_ITER_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_ITER_CREATE, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
@@ -706,10 +762,12 @@ int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
 	attr.query.prog_ids	= ptr_to_u64(prog_ids);
 
 	ret = sys_bpf(BPF_PROG_QUERY, &attr, sizeof(attr));
+
 	if (attach_flags)
 		*attach_flags = attr.query.attach_flags;
 	*prog_cnt = attr.query.prog_cnt;
-	return ret;
+
+	return libbpf_err_errno(ret);
 }
 
 int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
@@ -727,13 +785,15 @@ int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
 	attr.test.repeat = repeat;
 
 	ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));
+
 	if (size_out)
 		*size_out = attr.test.data_size_out;
 	if (retval)
 		*retval = attr.test.retval;
 	if (duration)
 		*duration = attr.test.duration;
-	return ret;
+
+	return libbpf_err_errno(ret);
 }
 
 int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr)
@@ -742,7 +802,7 @@ int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr)
 	int ret;
 
 	if (!test_attr->data_out && test_attr->data_size_out > 0)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, sizeof(attr));
 	attr.test.prog_fd = test_attr->prog_fd;
@@ -757,11 +817,13 @@ int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr)
 	attr.test.repeat = test_attr->repeat;
 
 	ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));
+
 	test_attr->data_size_out = attr.test.data_size_out;
 	test_attr->ctx_size_out = attr.test.ctx_size_out;
 	test_attr->retval = attr.test.retval;
 	test_attr->duration = attr.test.duration;
-	return ret;
+
+	return libbpf_err_errno(ret);
 }
 
 int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts)
@@ -770,7 +832,7 @@ int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts)
 	int ret;
 
 	if (!OPTS_VALID(opts, bpf_test_run_opts))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, sizeof(attr));
 	attr.test.prog_fd = prog_fd;
@@ -788,11 +850,13 @@ int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts)
 	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;
+
+	return libbpf_err_errno(ret);
 }
 
 static int bpf_obj_get_next_id(__u32 start_id, __u32 *next_id, int cmd)
@@ -807,7 +871,7 @@ static int bpf_obj_get_next_id(__u32 start_id, __u32 *next_id, int cmd)
 	if (!err)
 		*next_id = attr.next_id;
 
-	return err;
+	return libbpf_err_errno(err);
 }
 
 int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id)
@@ -833,41 +897,49 @@ int bpf_link_get_next_id(__u32 start_id, __u32 *next_id)
 int bpf_prog_get_fd_by_id(__u32 id)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_id = id;
 
-	return sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_map_get_fd_by_id(__u32 id)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.map_id = id;
 
-	return sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_btf_get_fd_by_id(__u32 id)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.btf_id = id;
 
-	return sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_link_get_fd_by_id(__u32 id)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.link_id = id;
 
-	return sys_bpf(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len)
@@ -881,21 +953,24 @@ int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len)
 	attr.info.info = ptr_to_u64(info);
 
 	err = sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, sizeof(attr));
+
 	if (!err)
 		*info_len = attr.info.info_len;
 
-	return err;
+	return libbpf_err_errno(err);
 }
 
 int bpf_raw_tracepoint_open(const char *name, int prog_fd)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.raw_tracepoint.name = ptr_to_u64(name);
 	attr.raw_tracepoint.prog_fd = prog_fd;
 
-	return sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
@@ -915,12 +990,13 @@ retry:
 	}
 
 	fd = sys_bpf(BPF_BTF_LOAD, &attr, sizeof(attr));
-	if (fd == -1 && !do_log && log_buf && log_buf_size) {
+
+	if (fd < 0 && !do_log && log_buf && log_buf_size) {
 		do_log = true;
 		goto retry;
 	}
 
-	return fd;
+	return libbpf_err_errno(fd);
 }
 
 int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len,
@@ -937,37 +1013,42 @@ int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len,
 	attr.task_fd_query.buf_len = *buf_len;
 
 	err = sys_bpf(BPF_TASK_FD_QUERY, &attr, sizeof(attr));
+
 	*buf_len = attr.task_fd_query.buf_len;
 	*prog_id = attr.task_fd_query.prog_id;
 	*fd_type = attr.task_fd_query.fd_type;
 	*probe_offset = attr.task_fd_query.probe_offset;
 	*probe_addr = attr.task_fd_query.probe_addr;
 
-	return err;
+	return libbpf_err_errno(err);
 }
 
 int bpf_enable_stats(enum bpf_stats_type type)
 {
 	union bpf_attr attr;
+	int fd;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.enable_stats.type = type;
 
-	return sys_bpf(BPF_ENABLE_STATS, &attr, sizeof(attr));
+	fd = sys_bpf(BPF_ENABLE_STATS, &attr, sizeof(attr));
+	return libbpf_err_errno(fd);
 }
 
 int bpf_prog_bind_map(int prog_fd, int map_fd,
 		      const struct bpf_prog_bind_opts *opts)
 {
 	union bpf_attr attr;
+	int ret;
 
 	if (!OPTS_VALID(opts, bpf_prog_bind_opts))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_bind_map.prog_fd = prog_fd;
 	attr.prog_bind_map.map_fd = map_fd;
 	attr.prog_bind_map.flags = OPTS_GET(opts, flags, 0);
 
-	return sys_bpf(BPF_PROG_BIND_MAP, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 875dde20d56e..4f758f8f50cd 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -124,6 +124,8 @@ LIBBPF_API int bpf_map_lookup_elem_flags(int fd, const void *key, void *value,
 					 __u64 flags);
 LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key,
 					      void *value);
+LIBBPF_API int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key,
+						    void *value, __u64 flags);
 LIBBPF_API int bpf_map_delete_elem(int fd, const void *key);
 LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
 LIBBPF_API int bpf_map_freeze(int fd);
diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h
new file mode 100644
index 000000000000..615400391e57
--- /dev/null
+++ b/tools/lib/bpf/bpf_gen_internal.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+/* Copyright (c) 2021 Facebook */
+#ifndef __BPF_GEN_INTERNAL_H
+#define __BPF_GEN_INTERNAL_H
+
+struct ksym_relo_desc {
+	const char *name;
+	int kind;
+	int insn_idx;
+};
+
+struct bpf_gen {
+	struct gen_loader_opts *opts;
+	void *data_start;
+	void *data_cur;
+	void *insn_start;
+	void *insn_cur;
+	ssize_t cleanup_label;
+	__u32 nr_progs;
+	__u32 nr_maps;
+	int log_level;
+	int error;
+	struct ksym_relo_desc *relos;
+	int relo_cnt;
+	char attach_target[128];
+	int attach_kind;
+};
+
+void bpf_gen__init(struct bpf_gen *gen, int log_level);
+int bpf_gen__finish(struct bpf_gen *gen);
+void bpf_gen__free(struct bpf_gen *gen);
+void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size);
+void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_attr *map_attr, int map_idx);
+struct bpf_prog_load_params;
+void bpf_gen__prog_load(struct bpf_gen *gen, struct bpf_prog_load_params *load_attr, int prog_idx);
+void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *value, __u32 value_size);
+void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx);
+void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *name, enum bpf_attach_type type);
+void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind, int insn_idx);
+
+#endif
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index 9720dc0b4605..b9987c3efa3c 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -158,4 +158,70 @@ enum libbpf_tristate {
 #define __kconfig __attribute__((section(".kconfig")))
 #define __ksym __attribute__((section(".ksyms")))
 
+#ifndef ___bpf_concat
+#define ___bpf_concat(a, b) a ## b
+#endif
+#ifndef ___bpf_apply
+#define ___bpf_apply(fn, n) ___bpf_concat(fn, n)
+#endif
+#ifndef ___bpf_nth
+#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N
+#endif
+#ifndef ___bpf_narg
+#define ___bpf_narg(...) \
+	___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+#endif
+
+#define ___bpf_fill0(arr, p, x) do {} while (0)
+#define ___bpf_fill1(arr, p, x) arr[p] = x
+#define ___bpf_fill2(arr, p, x, args...) arr[p] = x; ___bpf_fill1(arr, p + 1, args)
+#define ___bpf_fill3(arr, p, x, args...) arr[p] = x; ___bpf_fill2(arr, p + 1, args)
+#define ___bpf_fill4(arr, p, x, args...) arr[p] = x; ___bpf_fill3(arr, p + 1, args)
+#define ___bpf_fill5(arr, p, x, args...) arr[p] = x; ___bpf_fill4(arr, p + 1, args)
+#define ___bpf_fill6(arr, p, x, args...) arr[p] = x; ___bpf_fill5(arr, p + 1, args)
+#define ___bpf_fill7(arr, p, x, args...) arr[p] = x; ___bpf_fill6(arr, p + 1, args)
+#define ___bpf_fill8(arr, p, x, args...) arr[p] = x; ___bpf_fill7(arr, p + 1, args)
+#define ___bpf_fill9(arr, p, x, args...) arr[p] = x; ___bpf_fill8(arr, p + 1, args)
+#define ___bpf_fill10(arr, p, x, args...) arr[p] = x; ___bpf_fill9(arr, p + 1, args)
+#define ___bpf_fill11(arr, p, x, args...) arr[p] = x; ___bpf_fill10(arr, p + 1, args)
+#define ___bpf_fill12(arr, p, x, args...) arr[p] = x; ___bpf_fill11(arr, p + 1, args)
+#define ___bpf_fill(arr, args...) \
+	___bpf_apply(___bpf_fill, ___bpf_narg(args))(arr, 0, args)
+
+/*
+ * BPF_SEQ_PRINTF to wrap bpf_seq_printf to-be-printed values
+ * in a structure.
+ */
+#define BPF_SEQ_PRINTF(seq, fmt, args...)			\
+({								\
+	static const char ___fmt[] = fmt;			\
+	unsigned long long ___param[___bpf_narg(args)];		\
+								\
+	_Pragma("GCC diagnostic push")				\
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	\
+	___bpf_fill(___param, args);				\
+	_Pragma("GCC diagnostic pop")				\
+								\
+	bpf_seq_printf(seq, ___fmt, sizeof(___fmt),		\
+		       ___param, sizeof(___param));		\
+})
+
+/*
+ * BPF_SNPRINTF wraps the bpf_snprintf helper with variadic arguments instead of
+ * an array of u64.
+ */
+#define BPF_SNPRINTF(out, out_size, fmt, args...)		\
+({								\
+	static const char ___fmt[] = fmt;			\
+	unsigned long long ___param[___bpf_narg(args)];		\
+								\
+	_Pragma("GCC diagnostic push")				\
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	\
+	___bpf_fill(___param, args);				\
+	_Pragma("GCC diagnostic pop")				\
+								\
+	bpf_snprintf(out, out_size, ___fmt,			\
+		     ___param, sizeof(___param));		\
+})
+
 #endif
diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c
index 3ed1a27b5f7c..5c503096ef43 100644
--- a/tools/lib/bpf/bpf_prog_linfo.c
+++ b/tools/lib/bpf/bpf_prog_linfo.c
@@ -106,7 +106,7 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 	nr_linfo = info->nr_line_info;
 
 	if (!nr_linfo)
-		return NULL;
+		return errno = EINVAL, NULL;
 
 	/*
 	 * The min size that bpf_prog_linfo has to access for
@@ -114,11 +114,11 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 	 */
 	if (info->line_info_rec_size <
 	    offsetof(struct bpf_line_info, file_name_off))
-		return NULL;
+		return errno = EINVAL, NULL;
 
 	prog_linfo = calloc(1, sizeof(*prog_linfo));
 	if (!prog_linfo)
-		return NULL;
+		return errno = ENOMEM, NULL;
 
 	/* Copy xlated line_info */
 	prog_linfo->nr_linfo = nr_linfo;
@@ -174,7 +174,7 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 
 err_free:
 	bpf_prog_linfo__free(prog_linfo);
-	return NULL;
+	return errno = EINVAL, NULL;
 }
 
 const struct bpf_line_info *
@@ -186,11 +186,11 @@ bpf_prog_linfo__lfind_addr_func(const struct bpf_prog_linfo *prog_linfo,
 	const __u64 *jited_linfo;
 
 	if (func_idx >= prog_linfo->nr_jited_func)
-		return NULL;
+		return errno = ENOENT, NULL;
 
 	nr_linfo = prog_linfo->nr_jited_linfo_per_func[func_idx];
 	if (nr_skip >= nr_linfo)
-		return NULL;
+		return errno = ENOENT, NULL;
 
 	start = prog_linfo->jited_linfo_func_idx[func_idx] + nr_skip;
 	jited_rec_size = prog_linfo->jited_rec_size;
@@ -198,7 +198,7 @@ bpf_prog_linfo__lfind_addr_func(const struct bpf_prog_linfo *prog_linfo,
 		(start * jited_rec_size);
 	jited_linfo = raw_jited_linfo;
 	if (addr < *jited_linfo)
-		return NULL;
+		return errno = ENOENT, NULL;
 
 	nr_linfo -= nr_skip;
 	rec_size = prog_linfo->rec_size;
@@ -225,13 +225,13 @@ bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo,
 
 	nr_linfo = prog_linfo->nr_linfo;
 	if (nr_skip >= nr_linfo)
-		return NULL;
+		return errno = ENOENT, NULL;
 
 	rec_size = prog_linfo->rec_size;
 	raw_linfo = prog_linfo->raw_linfo + (nr_skip * rec_size);
 	linfo = raw_linfo;
 	if (insn_off < linfo->insn_off)
-		return NULL;
+		return errno = ENOENT, NULL;
 
 	nr_linfo -= nr_skip;
 	for (i = 0; i < nr_linfo; i++) {
diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index 8c954ebc0c7c..d6bfbe009296 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -25,26 +25,35 @@
 	#define bpf_target_sparc
 	#define bpf_target_defined
 #else
-	#undef bpf_target_defined
-#endif
 
 /* Fall back to what the compiler says */
-#ifndef bpf_target_defined
 #if defined(__x86_64__)
 	#define bpf_target_x86
+	#define bpf_target_defined
 #elif defined(__s390__)
 	#define bpf_target_s390
+	#define bpf_target_defined
 #elif defined(__arm__)
 	#define bpf_target_arm
+	#define bpf_target_defined
 #elif defined(__aarch64__)
 	#define bpf_target_arm64
+	#define bpf_target_defined
 #elif defined(__mips__)
 	#define bpf_target_mips
+	#define bpf_target_defined
 #elif defined(__powerpc__)
 	#define bpf_target_powerpc
+	#define bpf_target_defined
 #elif defined(__sparc__)
 	#define bpf_target_sparc
+	#define bpf_target_defined
+#endif /* no compiler target */
+
 #endif
+
+#ifndef __BPF_TARGET_MISSING
+#define __BPF_TARGET_MISSING "GCC error \"Must specify a BPF target arch via __TARGET_ARCH_xxx\""
 #endif
 
 #if defined(bpf_target_x86)
@@ -287,7 +296,7 @@ struct pt_regs;
 #elif defined(bpf_target_sparc)
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = PT_REGS_RET(ctx); })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
-#else
+#elif defined(bpf_target_defined)
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)					    \
 	({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); })
 #define BPF_KRETPROBE_READ_RET_IP(ip, ctx)				    \
@@ -295,13 +304,48 @@ struct pt_regs;
 			  (void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
 #endif
 
+#if !defined(bpf_target_defined)
+
+#define PT_REGS_PARM1(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM2(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM3(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM4(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM5(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_RET(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_FP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_RC(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_SP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_IP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+
+#define PT_REGS_PARM1_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM2_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM3_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM4_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_PARM5_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_RET_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_FP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_RC_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_SP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define PT_REGS_IP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+
+#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+#define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
+
+#endif /* !defined(bpf_target_defined) */
+
+#ifndef ___bpf_concat
 #define ___bpf_concat(a, b) a ## b
+#endif
+#ifndef ___bpf_apply
 #define ___bpf_apply(fn, n) ___bpf_concat(fn, n)
+#endif
+#ifndef ___bpf_nth
 #define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N
+#endif
+#ifndef ___bpf_narg
 #define ___bpf_narg(...) \
 	___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
-#define ___bpf_empty(...) \
-	___bpf_nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0)
+#endif
 
 #define ___bpf_ctx_cast0() ctx
 #define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0]
@@ -413,56 +457,4 @@ typeof(name(0)) name(struct pt_regs *ctx)				    \
 }									    \
 static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
 
-#define ___bpf_fill0(arr, p, x) do {} while (0)
-#define ___bpf_fill1(arr, p, x) arr[p] = x
-#define ___bpf_fill2(arr, p, x, args...) arr[p] = x; ___bpf_fill1(arr, p + 1, args)
-#define ___bpf_fill3(arr, p, x, args...) arr[p] = x; ___bpf_fill2(arr, p + 1, args)
-#define ___bpf_fill4(arr, p, x, args...) arr[p] = x; ___bpf_fill3(arr, p + 1, args)
-#define ___bpf_fill5(arr, p, x, args...) arr[p] = x; ___bpf_fill4(arr, p + 1, args)
-#define ___bpf_fill6(arr, p, x, args...) arr[p] = x; ___bpf_fill5(arr, p + 1, args)
-#define ___bpf_fill7(arr, p, x, args...) arr[p] = x; ___bpf_fill6(arr, p + 1, args)
-#define ___bpf_fill8(arr, p, x, args...) arr[p] = x; ___bpf_fill7(arr, p + 1, args)
-#define ___bpf_fill9(arr, p, x, args...) arr[p] = x; ___bpf_fill8(arr, p + 1, args)
-#define ___bpf_fill10(arr, p, x, args...) arr[p] = x; ___bpf_fill9(arr, p + 1, args)
-#define ___bpf_fill11(arr, p, x, args...) arr[p] = x; ___bpf_fill10(arr, p + 1, args)
-#define ___bpf_fill12(arr, p, x, args...) arr[p] = x; ___bpf_fill11(arr, p + 1, args)
-#define ___bpf_fill(arr, args...) \
-	___bpf_apply(___bpf_fill, ___bpf_narg(args))(arr, 0, args)
-
-/*
- * BPF_SEQ_PRINTF to wrap bpf_seq_printf to-be-printed values
- * in a structure.
- */
-#define BPF_SEQ_PRINTF(seq, fmt, args...)			\
-({								\
-	static const char ___fmt[] = fmt;			\
-	unsigned long long ___param[___bpf_narg(args)];		\
-								\
-	_Pragma("GCC diagnostic push")				\
-	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	\
-	___bpf_fill(___param, args);				\
-	_Pragma("GCC diagnostic pop")				\
-								\
-	bpf_seq_printf(seq, ___fmt, sizeof(___fmt),		\
-		       ___param, sizeof(___param));		\
-})
-
-/*
- * BPF_SNPRINTF wraps the bpf_snprintf helper with variadic arguments instead of
- * an array of u64.
- */
-#define BPF_SNPRINTF(out, out_size, fmt, args...)		\
-({								\
-	static const char ___fmt[] = fmt;			\
-	unsigned long long ___param[___bpf_narg(args)];		\
-								\
-	_Pragma("GCC diagnostic push")				\
-	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	\
-	___bpf_fill(___param, args);				\
-	_Pragma("GCC diagnostic pop")				\
-								\
-	bpf_snprintf(out, out_size, ___fmt,			\
-		     ___param, sizeof(___param));		\
-})
-
 #endif
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index d57e13a13798..b46760b93bb4 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -443,7 +443,7 @@ struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id)
 const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id)
 {
 	if (type_id >= btf->start_id + btf->nr_types)
-		return NULL;
+		return errno = EINVAL, NULL;
 	return btf_type_by_id((struct btf *)btf, type_id);
 }
 
@@ -510,7 +510,7 @@ size_t btf__pointer_size(const struct btf *btf)
 int btf__set_pointer_size(struct btf *btf, size_t ptr_sz)
 {
 	if (ptr_sz != 4 && ptr_sz != 8)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	btf->ptr_sz = ptr_sz;
 	return 0;
 }
@@ -537,7 +537,7 @@ enum btf_endianness btf__endianness(const struct btf *btf)
 int btf__set_endianness(struct btf *btf, enum btf_endianness endian)
 {
 	if (endian != BTF_LITTLE_ENDIAN && endian != BTF_BIG_ENDIAN)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	btf->swapped_endian = is_host_big_endian() != (endian == BTF_BIG_ENDIAN);
 	if (!btf->swapped_endian) {
@@ -568,8 +568,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 	int i;
 
 	t = btf__type_by_id(btf, type_id);
-	for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t);
-	     i++) {
+	for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t); i++) {
 		switch (btf_kind(t)) {
 		case BTF_KIND_INT:
 		case BTF_KIND_STRUCT:
@@ -592,12 +591,12 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 		case BTF_KIND_ARRAY:
 			array = btf_array(t);
 			if (nelems && array->nelems > UINT32_MAX / nelems)
-				return -E2BIG;
+				return libbpf_err(-E2BIG);
 			nelems *= array->nelems;
 			type_id = array->type;
 			break;
 		default:
-			return -EINVAL;
+			return libbpf_err(-EINVAL);
 		}
 
 		t = btf__type_by_id(btf, type_id);
@@ -605,9 +604,9 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 
 done:
 	if (size < 0)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	if (nelems && size > UINT32_MAX / nelems)
-		return -E2BIG;
+		return libbpf_err(-E2BIG);
 
 	return nelems * size;
 }
@@ -640,7 +639,7 @@ int btf__align_of(const struct btf *btf, __u32 id)
 		for (i = 0; i < vlen; i++, m++) {
 			align = btf__align_of(btf, m->type);
 			if (align <= 0)
-				return align;
+				return libbpf_err(align);
 			max_align = max(max_align, align);
 		}
 
@@ -648,7 +647,7 @@ int btf__align_of(const struct btf *btf, __u32 id)
 	}
 	default:
 		pr_warn("unsupported BTF_KIND:%u\n", btf_kind(t));
-		return 0;
+		return errno = EINVAL, 0;
 	}
 }
 
@@ -667,7 +666,7 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id)
 	}
 
 	if (depth == MAX_RESOLVE_DEPTH || btf_type_is_void_or_null(t))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	return type_id;
 }
@@ -687,7 +686,7 @@ __s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 			return i;
 	}
 
-	return -ENOENT;
+	return libbpf_err(-ENOENT);
 }
 
 __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
@@ -709,7 +708,7 @@ __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
 			return i;
 	}
 
-	return -ENOENT;
+	return libbpf_err(-ENOENT);
 }
 
 static bool btf_is_modifiable(const struct btf *btf)
@@ -785,12 +784,12 @@ static struct btf *btf_new_empty(struct btf *base_btf)
 
 struct btf *btf__new_empty(void)
 {
-	return btf_new_empty(NULL);
+	return libbpf_ptr(btf_new_empty(NULL));
 }
 
 struct btf *btf__new_empty_split(struct btf *base_btf)
 {
-	return btf_new_empty(base_btf);
+	return libbpf_ptr(btf_new_empty(base_btf));
 }
 
 static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf)
@@ -846,7 +845,7 @@ done:
 
 struct btf *btf__new(const void *data, __u32 size)
 {
-	return btf_new(data, size, NULL);
+	return libbpf_ptr(btf_new(data, size, NULL));
 }
 
 static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
@@ -937,7 +936,8 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
 		goto done;
 	}
 	btf = btf_new(btf_data->d_buf, btf_data->d_size, base_btf);
-	if (IS_ERR(btf))
+	err = libbpf_get_error(btf);
+	if (err)
 		goto done;
 
 	switch (gelf_getclass(elf)) {
@@ -953,9 +953,9 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
 	}
 
 	if (btf_ext && btf_ext_data) {
-		*btf_ext = btf_ext__new(btf_ext_data->d_buf,
-					btf_ext_data->d_size);
-		if (IS_ERR(*btf_ext))
+		*btf_ext = btf_ext__new(btf_ext_data->d_buf, btf_ext_data->d_size);
+		err = libbpf_get_error(*btf_ext);
+		if (err)
 			goto done;
 	} else if (btf_ext) {
 		*btf_ext = NULL;
@@ -965,30 +965,24 @@ done:
 		elf_end(elf);
 	close(fd);
 
-	if (err)
-		return ERR_PTR(err);
-	/*
-	 * btf is always parsed before btf_ext, so no need to clean up
-	 * btf_ext, if btf loading failed
-	 */
-	if (IS_ERR(btf))
+	if (!err)
 		return btf;
-	if (btf_ext && IS_ERR(*btf_ext)) {
-		btf__free(btf);
-		err = PTR_ERR(*btf_ext);
-		return ERR_PTR(err);
-	}
-	return btf;
+
+	if (btf_ext)
+		btf_ext__free(*btf_ext);
+	btf__free(btf);
+
+	return ERR_PTR(err);
 }
 
 struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext)
 {
-	return btf_parse_elf(path, NULL, btf_ext);
+	return libbpf_ptr(btf_parse_elf(path, NULL, btf_ext));
 }
 
 struct btf *btf__parse_elf_split(const char *path, struct btf *base_btf)
 {
-	return btf_parse_elf(path, base_btf, NULL);
+	return libbpf_ptr(btf_parse_elf(path, base_btf, NULL));
 }
 
 static struct btf *btf_parse_raw(const char *path, struct btf *base_btf)
@@ -1056,36 +1050,39 @@ err_out:
 
 struct btf *btf__parse_raw(const char *path)
 {
-	return btf_parse_raw(path, NULL);
+	return libbpf_ptr(btf_parse_raw(path, NULL));
 }
 
 struct btf *btf__parse_raw_split(const char *path, struct btf *base_btf)
 {
-	return btf_parse_raw(path, base_btf);
+	return libbpf_ptr(btf_parse_raw(path, base_btf));
 }
 
 static struct btf *btf_parse(const char *path, struct btf *base_btf, struct btf_ext **btf_ext)
 {
 	struct btf *btf;
+	int err;
 
 	if (btf_ext)
 		*btf_ext = NULL;
 
 	btf = btf_parse_raw(path, base_btf);
-	if (!IS_ERR(btf) || PTR_ERR(btf) != -EPROTO)
+	err = libbpf_get_error(btf);
+	if (!err)
 		return btf;
-
+	if (err != -EPROTO)
+		return ERR_PTR(err);
 	return btf_parse_elf(path, base_btf, btf_ext);
 }
 
 struct btf *btf__parse(const char *path, struct btf_ext **btf_ext)
 {
-	return btf_parse(path, NULL, btf_ext);
+	return libbpf_ptr(btf_parse(path, NULL, btf_ext));
 }
 
 struct btf *btf__parse_split(const char *path, struct btf *base_btf)
 {
-	return btf_parse(path, base_btf, NULL);
+	return libbpf_ptr(btf_parse(path, base_btf, NULL));
 }
 
 static int compare_vsi_off(const void *_a, const void *_b)
@@ -1178,7 +1175,7 @@ int btf__finalize_data(struct bpf_object *obj, struct btf *btf)
 		}
 	}
 
-	return err;
+	return libbpf_err(err);
 }
 
 static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian);
@@ -1191,13 +1188,13 @@ int btf__load(struct btf *btf)
 	int err = 0;
 
 	if (btf->fd >= 0)
-		return -EEXIST;
+		return libbpf_err(-EEXIST);
 
 retry_load:
 	if (log_buf_size) {
 		log_buf = malloc(log_buf_size);
 		if (!log_buf)
-			return -ENOMEM;
+			return libbpf_err(-ENOMEM);
 
 		*log_buf = 0;
 	}
@@ -1229,7 +1226,7 @@ retry_load:
 
 done:
 	free(log_buf);
-	return err;
+	return libbpf_err(err);
 }
 
 int btf__fd(const struct btf *btf)
@@ -1305,7 +1302,7 @@ const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size)
 
 	data = btf_get_raw_data(btf, &data_sz, btf->swapped_endian);
 	if (!data)
-		return NULL;
+		return errno = -ENOMEM, NULL;
 
 	btf->raw_size = data_sz;
 	if (btf->swapped_endian)
@@ -1323,7 +1320,7 @@ const char *btf__str_by_offset(const struct btf *btf, __u32 offset)
 	else if (offset - btf->start_str_off < btf->hdr->str_len)
 		return btf_strs_data(btf) + (offset - btf->start_str_off);
 	else
-		return NULL;
+		return errno = EINVAL, NULL;
 }
 
 const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
@@ -1388,17 +1385,20 @@ exit_free:
 int btf__get_from_id(__u32 id, struct btf **btf)
 {
 	struct btf *res;
-	int btf_fd;
+	int err, btf_fd;
 
 	*btf = NULL;
 	btf_fd = bpf_btf_get_fd_by_id(id);
 	if (btf_fd < 0)
-		return -errno;
+		return libbpf_err(-errno);
 
 	res = btf_get_from_fd(btf_fd, NULL);
+	err = libbpf_get_error(res);
+
 	close(btf_fd);
-	if (IS_ERR(res))
-		return PTR_ERR(res);
+
+	if (err)
+		return libbpf_err(err);
 
 	*btf = res;
 	return 0;
@@ -1415,31 +1415,30 @@ int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
 	__s64 key_size, value_size;
 	__s32 container_id;
 
-	if (snprintf(container_name, max_name, "____btf_map_%s", map_name) ==
-	    max_name) {
+	if (snprintf(container_name, max_name, "____btf_map_%s", map_name) == max_name) {
 		pr_warn("map:%s length of '____btf_map_%s' is too long\n",
 			map_name, map_name);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	container_id = btf__find_by_name(btf, container_name);
 	if (container_id < 0) {
 		pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n",
 			 map_name, container_name);
-		return container_id;
+		return libbpf_err(container_id);
 	}
 
 	container_type = btf__type_by_id(btf, container_id);
 	if (!container_type) {
 		pr_warn("map:%s cannot find BTF type for container_id:%u\n",
 			map_name, container_id);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (!btf_is_struct(container_type) || btf_vlen(container_type) < 2) {
 		pr_warn("map:%s container_name:%s is an invalid container struct\n",
 			map_name, container_name);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	key = btf_members(container_type);
@@ -1448,25 +1447,25 @@ int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
 	key_size = btf__resolve_size(btf, key->type);
 	if (key_size < 0) {
 		pr_warn("map:%s invalid BTF key_type_size\n", map_name);
-		return key_size;
+		return libbpf_err(key_size);
 	}
 
 	if (expected_key_size != key_size) {
 		pr_warn("map:%s btf_key_type_size:%u != map_def_key_size:%u\n",
 			map_name, (__u32)key_size, expected_key_size);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	value_size = btf__resolve_size(btf, value->type);
 	if (value_size < 0) {
 		pr_warn("map:%s invalid BTF value_type_size\n", map_name);
-		return value_size;
+		return libbpf_err(value_size);
 	}
 
 	if (expected_value_size != value_size) {
 		pr_warn("map:%s btf_value_type_size:%u != map_def_value_size:%u\n",
 			map_name, (__u32)value_size, expected_value_size);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	*key_type_id = key->type;
@@ -1563,11 +1562,11 @@ int btf__find_str(struct btf *btf, const char *s)
 
 	/* BTF needs to be in a modifiable state to build string lookup index */
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	off = strset__find_str(btf->strs_set, s);
 	if (off < 0)
-		return off;
+		return libbpf_err(off);
 
 	return btf->start_str_off + off;
 }
@@ -1588,11 +1587,11 @@ int btf__add_str(struct btf *btf, const char *s)
 	}
 
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	off = strset__add_str(btf->strs_set, s);
 	if (off < 0)
-		return off;
+		return libbpf_err(off);
 
 	btf->hdr->str_len = strset__data_size(btf->strs_set);
 
@@ -1616,7 +1615,7 @@ static int btf_commit_type(struct btf *btf, int data_sz)
 
 	err = btf_add_type_idx_entry(btf, btf->hdr->type_len);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	btf->hdr->type_len += data_sz;
 	btf->hdr->str_off += data_sz;
@@ -1653,21 +1652,21 @@ int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_t
 
 	sz = btf_type_size(src_type);
 	if (sz < 0)
-		return sz;
+		return libbpf_err(sz);
 
 	/* deconstruct BTF, if necessary, and invalidate raw_data */
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	memcpy(t, src_type, sz);
 
 	err = btf_type_visit_str_offs(t, btf_rewrite_str, &p);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	return btf_commit_type(btf, sz);
 }
@@ -1688,21 +1687,21 @@ int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding
 
 	/* non-empty name */
 	if (!name || !name[0])
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	/* byte_sz must be power of 2 */
 	if (!byte_sz || (byte_sz & (byte_sz - 1)) || byte_sz > 16)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	if (encoding & ~(BTF_INT_SIGNED | BTF_INT_CHAR | BTF_INT_BOOL))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	/* deconstruct BTF, if necessary, and invalidate raw_data */
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_type) + sizeof(int);
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-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
@@ -1736,20 +1735,20 @@ int btf__add_float(struct btf *btf, const char *name, size_t byte_sz)
 
 	/* non-empty name */
 	if (!name || !name[0])
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	/* byte_sz must be one of the explicitly allowed values */
 	if (byte_sz != 2 && byte_sz != 4 && byte_sz != 8 && byte_sz != 12 &&
 	    byte_sz != 16)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_type);
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	name_off = btf__add_str(btf, name);
 	if (name_off < 0)
@@ -1780,15 +1779,15 @@ static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref
 	int sz, name_off = 0;
 
 	if (validate_type_id(ref_type_id))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_type);
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	if (name && name[0]) {
 		name_off = btf__add_str(btf, name);
@@ -1831,15 +1830,15 @@ int btf__add_array(struct btf *btf, int index_type_id, int elem_type_id, __u32 n
 	int sz;
 
 	if (validate_type_id(index_type_id) || validate_type_id(elem_type_id))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_type) + sizeof(struct btf_array);
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	t->name_off = 0;
 	t->info = btf_type_info(BTF_KIND_ARRAY, 0, 0);
@@ -1860,12 +1859,12 @@ static int btf_add_composite(struct btf *btf, int kind, const char *name, __u32
 	int sz, name_off = 0;
 
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_type);
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	if (name && name[0]) {
 		name_off = btf__add_str(btf, name);
@@ -1943,30 +1942,30 @@ int btf__add_field(struct btf *btf, const char *name, int type_id,
 
 	/* last type should be union/struct */
 	if (btf->nr_types == 0)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	t = btf_last_type(btf);
 	if (!btf_is_composite(t))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (validate_type_id(type_id))
-		return -EINVAL;
+		return libbpf_err(-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;
+		return libbpf_err(-EINVAL);
 
 	/* only offset 0 is allowed for unions */
 	if (btf_is_union(t) && bit_offset)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	/* decompose and invalidate raw data */
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_member);
 	m = btf_add_type_mem(btf, sz);
 	if (!m)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	if (name && name[0]) {
 		name_off = btf__add_str(btf, name);
@@ -2008,15 +2007,15 @@ int btf__add_enum(struct btf *btf, const char *name, __u32 byte_sz)
 
 	/* byte_sz must be power of 2 */
 	if (!byte_sz || (byte_sz & (byte_sz - 1)) || byte_sz > 8)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_type);
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	if (name && name[0]) {
 		name_off = btf__add_str(btf, name);
@@ -2048,25 +2047,25 @@ int btf__add_enum_value(struct btf *btf, const char *name, __s64 value)
 
 	/* last type should be BTF_KIND_ENUM */
 	if (btf->nr_types == 0)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	t = btf_last_type(btf);
 	if (!btf_is_enum(t))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	/* non-empty name */
 	if (!name || !name[0])
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	if (value < INT_MIN || value > UINT_MAX)
-		return -E2BIG;
+		return libbpf_err(-E2BIG);
 
 	/* decompose and invalidate raw data */
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_enum);
 	v = btf_add_type_mem(btf, sz);
 	if (!v)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	name_off = btf__add_str(btf, name);
 	if (name_off < 0)
@@ -2096,7 +2095,7 @@ int btf__add_enum_value(struct btf *btf, const char *name, __s64 value)
 int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind)
 {
 	if (!name || !name[0])
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	switch (fwd_kind) {
 	case BTF_FWD_STRUCT:
@@ -2117,7 +2116,7 @@ int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind)
 		 */
 		return btf__add_enum(btf, name, sizeof(int));
 	default:
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 }
 
@@ -2132,7 +2131,7 @@ int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind)
 int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id)
 {
 	if (!name || !name[0])
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	return btf_add_ref_kind(btf, BTF_KIND_TYPEDEF, name, ref_type_id);
 }
@@ -2187,10 +2186,10 @@ int btf__add_func(struct btf *btf, const char *name,
 	int id;
 
 	if (!name || !name[0])
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	if (linkage != BTF_FUNC_STATIC && linkage != BTF_FUNC_GLOBAL &&
 	    linkage != BTF_FUNC_EXTERN)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	id = btf_add_ref_kind(btf, BTF_KIND_FUNC, name, proto_type_id);
 	if (id > 0) {
@@ -2198,7 +2197,7 @@ int btf__add_func(struct btf *btf, const char *name,
 
 		t->info = btf_type_info(BTF_KIND_FUNC, linkage, 0);
 	}
-	return id;
+	return libbpf_err(id);
 }
 
 /*
@@ -2219,15 +2218,15 @@ int btf__add_func_proto(struct btf *btf, int ret_type_id)
 	int sz;
 
 	if (validate_type_id(ret_type_id))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_type);
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	/* start out with vlen=0; this will be adjusted when adding enum
 	 * values, if necessary
@@ -2254,23 +2253,23 @@ int btf__add_func_param(struct btf *btf, const char *name, int type_id)
 	int sz, name_off = 0;
 
 	if (validate_type_id(type_id))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	/* last type should be BTF_KIND_FUNC_PROTO */
 	if (btf->nr_types == 0)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	t = btf_last_type(btf);
 	if (!btf_is_func_proto(t))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	/* decompose and invalidate raw data */
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_param);
 	p = btf_add_type_mem(btf, sz);
 	if (!p)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	if (name && name[0]) {
 		name_off = btf__add_str(btf, name);
@@ -2308,21 +2307,21 @@ int btf__add_var(struct btf *btf, const char *name, int linkage, int type_id)
 
 	/* non-empty name */
 	if (!name || !name[0])
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	if (linkage != BTF_VAR_STATIC && linkage != BTF_VAR_GLOBAL_ALLOCATED &&
 	    linkage != BTF_VAR_GLOBAL_EXTERN)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	if (validate_type_id(type_id))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	/* deconstruct BTF, if necessary, and invalidate raw_data */
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_type) + sizeof(struct btf_var);
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	name_off = btf__add_str(btf, name);
 	if (name_off < 0)
@@ -2357,15 +2356,15 @@ int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz)
 
 	/* non-empty name */
 	if (!name || !name[0])
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_type);
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	name_off = btf__add_str(btf, name);
 	if (name_off < 0)
@@ -2397,22 +2396,22 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __
 
 	/* last type should be BTF_KIND_DATASEC */
 	if (btf->nr_types == 0)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	t = btf_last_type(btf);
 	if (!btf_is_datasec(t))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (validate_type_id(var_type_id))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	/* decompose and invalidate raw data */
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	sz = sizeof(struct btf_var_secinfo);
 	v = btf_add_type_mem(btf, sz);
 	if (!v)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	v->type = var_type_id;
 	v->offset = offset;
@@ -2614,11 +2613,11 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size)
 
 	err = btf_ext_parse_hdr(data, size);
 	if (err)
-		return ERR_PTR(err);
+		return libbpf_err_ptr(err);
 
 	btf_ext = calloc(1, sizeof(struct btf_ext));
 	if (!btf_ext)
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 
 	btf_ext->data_size = size;
 	btf_ext->data = malloc(size);
@@ -2628,9 +2627,11 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size)
 	}
 	memcpy(btf_ext->data, data, size);
 
-	if (btf_ext->hdr->hdr_len <
-	    offsetofend(struct btf_ext_header, line_info_len))
+	if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, line_info_len)) {
+		err = -EINVAL;
 		goto done;
+	}
+
 	err = btf_ext_setup_func_info(btf_ext);
 	if (err)
 		goto done;
@@ -2639,8 +2640,11 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size)
 	if (err)
 		goto done;
 
-	if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len))
+	if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) {
+		err = -EINVAL;
 		goto done;
+	}
+
 	err = btf_ext_setup_core_relos(btf_ext);
 	if (err)
 		goto done;
@@ -2648,7 +2652,7 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size)
 done:
 	if (err) {
 		btf_ext__free(btf_ext);
-		return ERR_PTR(err);
+		return libbpf_err_ptr(err);
 	}
 
 	return btf_ext;
@@ -2687,7 +2691,7 @@ static int btf_ext_reloc_info(const struct btf *btf,
 		existing_len = (*cnt) * record_size;
 		data = realloc(*info, existing_len + records_len);
 		if (!data)
-			return -ENOMEM;
+			return libbpf_err(-ENOMEM);
 
 		memcpy(data + existing_len, sinfo->data, records_len);
 		/* adjust insn_off only, the rest data will be passed
@@ -2697,15 +2701,14 @@ static int btf_ext_reloc_info(const struct btf *btf,
 			__u32 *insn_off;
 
 			insn_off = data + existing_len + (i * record_size);
-			*insn_off = *insn_off / sizeof(struct bpf_insn) +
-				insns_cnt;
+			*insn_off = *insn_off / sizeof(struct bpf_insn) + insns_cnt;
 		}
 		*info = data;
 		*cnt += sinfo->num_info;
 		return 0;
 	}
 
-	return -ENOENT;
+	return libbpf_err(-ENOENT);
 }
 
 int btf_ext__reloc_func_info(const struct btf *btf,
@@ -2894,11 +2897,11 @@ int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
 
 	if (IS_ERR(d)) {
 		pr_debug("btf_dedup_new failed: %ld", PTR_ERR(d));
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (btf_ensure_modifiable(btf))
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	err = btf_dedup_prep(d);
 	if (err) {
@@ -2938,7 +2941,7 @@ int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
 
 done:
 	btf_dedup_free(d);
-	return err;
+	return libbpf_err(err);
 }
 
 #define BTF_UNPROCESSED_ID ((__u32)-1)
@@ -4411,7 +4414,7 @@ struct btf *libbpf_find_kernel_btf(void)
 	char path[PATH_MAX + 1];
 	struct utsname buf;
 	struct btf *btf;
-	int i;
+	int i, err;
 
 	uname(&buf);
 
@@ -4425,17 +4428,16 @@ struct btf *libbpf_find_kernel_btf(void)
 			btf = btf__parse_raw(path);
 		else
 			btf = btf__parse_elf(path, NULL);
-
-		pr_debug("loading kernel BTF '%s': %ld\n",
-			 path, IS_ERR(btf) ? PTR_ERR(btf) : 0);
-		if (IS_ERR(btf))
+		err = libbpf_get_error(btf);
+		pr_debug("loading kernel BTF '%s': %d\n", path, err);
+		if (err)
 			continue;
 
 		return btf;
 	}
 
 	pr_warn("failed to find valid kernel BTF\n");
-	return ERR_PTR(-ESRCH);
+	return libbpf_err_ptr(-ESRCH);
 }
 
 int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ctx)
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 5e2809d685bf..5dc6b5172bb3 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -128,7 +128,7 @@ struct btf_dump *btf_dump__new(const struct btf *btf,
 
 	d = calloc(1, sizeof(struct btf_dump));
 	if (!d)
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 
 	d->btf = btf;
 	d->btf_ext = btf_ext;
@@ -156,7 +156,7 @@ struct btf_dump *btf_dump__new(const struct btf *btf,
 	return d;
 err:
 	btf_dump__free(d);
-	return ERR_PTR(err);
+	return libbpf_err_ptr(err);
 }
 
 static int btf_dump_resize(struct btf_dump *d)
@@ -236,16 +236,16 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id)
 	int err, i;
 
 	if (id > btf__get_nr_types(d->btf))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	err = btf_dump_resize(d);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	d->emit_queue_cnt = 0;
 	err = btf_dump_order_type(d, id, false);
 	if (err < 0)
-		return err;
+		return libbpf_err(err);
 
 	for (i = 0; i < d->emit_queue_cnt; i++)
 		btf_dump_emit_type(d, d->emit_queue[i], 0 /*top-level*/);
@@ -1075,11 +1075,11 @@ int btf_dump__emit_type_decl(struct btf_dump *d, __u32 id,
 	int lvl, err;
 
 	if (!OPTS_VALID(opts, btf_dump_emit_type_decl_opts))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	err = btf_dump_resize(d);
 	if (err)
-		return -EINVAL;
+		return libbpf_err(err);
 
 	fname = OPTS_GET(opts, field_name, "");
 	lvl = OPTS_GET(opts, indent_level, 0);
diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
new file mode 100644
index 000000000000..8df718a6b142
--- /dev/null
+++ b/tools/lib/bpf/gen_loader.c
@@ -0,0 +1,729 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/* Copyright (c) 2021 Facebook */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <linux/filter.h>
+#include "btf.h"
+#include "bpf.h"
+#include "libbpf.h"
+#include "libbpf_internal.h"
+#include "hashmap.h"
+#include "bpf_gen_internal.h"
+#include "skel_internal.h"
+
+#define MAX_USED_MAPS 64
+#define MAX_USED_PROGS 32
+
+/* The following structure describes the stack layout of the loader program.
+ * In addition R6 contains the pointer to context.
+ * R7 contains the result of the last sys_bpf command (typically error or FD).
+ * R9 contains the result of the last sys_close command.
+ *
+ * Naming convention:
+ * ctx - bpf program context
+ * stack - bpf program stack
+ * blob - bpf_attr-s, strings, insns, map data.
+ *        All the bytes that loader prog will use for read/write.
+ */
+struct loader_stack {
+	__u32 btf_fd;
+	__u32 map_fd[MAX_USED_MAPS];
+	__u32 prog_fd[MAX_USED_PROGS];
+	__u32 inner_map_fd;
+};
+
+#define stack_off(field) \
+	(__s16)(-sizeof(struct loader_stack) + offsetof(struct loader_stack, field))
+
+#define attr_field(attr, field) (attr + offsetof(union bpf_attr, field))
+
+static int realloc_insn_buf(struct bpf_gen *gen, __u32 size)
+{
+	size_t off = gen->insn_cur - gen->insn_start;
+	void *insn_start;
+
+	if (gen->error)
+		return gen->error;
+	if (size > INT32_MAX || off + size > INT32_MAX) {
+		gen->error = -ERANGE;
+		return -ERANGE;
+	}
+	insn_start = realloc(gen->insn_start, off + size);
+	if (!insn_start) {
+		gen->error = -ENOMEM;
+		free(gen->insn_start);
+		gen->insn_start = NULL;
+		return -ENOMEM;
+	}
+	gen->insn_start = insn_start;
+	gen->insn_cur = insn_start + off;
+	return 0;
+}
+
+static int realloc_data_buf(struct bpf_gen *gen, __u32 size)
+{
+	size_t off = gen->data_cur - gen->data_start;
+	void *data_start;
+
+	if (gen->error)
+		return gen->error;
+	if (size > INT32_MAX || off + size > INT32_MAX) {
+		gen->error = -ERANGE;
+		return -ERANGE;
+	}
+	data_start = realloc(gen->data_start, off + size);
+	if (!data_start) {
+		gen->error = -ENOMEM;
+		free(gen->data_start);
+		gen->data_start = NULL;
+		return -ENOMEM;
+	}
+	gen->data_start = data_start;
+	gen->data_cur = data_start + off;
+	return 0;
+}
+
+static void emit(struct bpf_gen *gen, struct bpf_insn insn)
+{
+	if (realloc_insn_buf(gen, sizeof(insn)))
+		return;
+	memcpy(gen->insn_cur, &insn, sizeof(insn));
+	gen->insn_cur += sizeof(insn);
+}
+
+static void emit2(struct bpf_gen *gen, struct bpf_insn insn1, struct bpf_insn insn2)
+{
+	emit(gen, insn1);
+	emit(gen, insn2);
+}
+
+void bpf_gen__init(struct bpf_gen *gen, int log_level)
+{
+	size_t stack_sz = sizeof(struct loader_stack);
+	int i;
+
+	gen->log_level = log_level;
+	/* save ctx pointer into R6 */
+	emit(gen, BPF_MOV64_REG(BPF_REG_6, BPF_REG_1));
+
+	/* bzero stack */
+	emit(gen, BPF_MOV64_REG(BPF_REG_1, BPF_REG_10));
+	emit(gen, BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -stack_sz));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_2, stack_sz));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel));
+
+	/* jump over cleanup code */
+	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0,
+			      /* size of cleanup code below */
+			      (stack_sz / 4) * 3 + 2));
+
+	/* remember the label where all error branches will jump to */
+	gen->cleanup_label = gen->insn_cur - gen->insn_start;
+	/* emit cleanup code: close all temp FDs */
+	for (i = 0; i < stack_sz; i += 4) {
+		emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, -stack_sz + i));
+		emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0, 1));
+		emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close));
+	}
+	/* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */
+	emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
+	emit(gen, BPF_EXIT_INSN());
+}
+
+static int add_data(struct bpf_gen *gen, const void *data, __u32 size)
+{
+	void *prev;
+
+	if (realloc_data_buf(gen, size))
+		return 0;
+	prev = gen->data_cur;
+	memcpy(gen->data_cur, data, size);
+	gen->data_cur += size;
+	return prev - gen->data_start;
+}
+
+static int insn_bytes_to_bpf_size(__u32 sz)
+{
+	switch (sz) {
+	case 8: return BPF_DW;
+	case 4: return BPF_W;
+	case 2: return BPF_H;
+	case 1: return BPF_B;
+	default: return -1;
+	}
+}
+
+/* *(u64 *)(blob + off) = (u64)(void *)(blob + data) */
+static void emit_rel_store(struct bpf_gen *gen, int off, int data)
+{
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, data));
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, off));
+	emit(gen, BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0));
+}
+
+/* *(u64 *)(blob + off) = (u64)(void *)(%sp + stack_off) */
+static void emit_rel_store_sp(struct bpf_gen *gen, int off, int stack_off)
+{
+	emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_10));
+	emit(gen, BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, stack_off));
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, off));
+	emit(gen, BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0));
+}
+
+static void move_ctx2blob(struct bpf_gen *gen, int off, int size, int ctx_off,
+				   bool check_non_zero)
+{
+	emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_6, ctx_off));
+	if (check_non_zero)
+		/* If value in ctx is zero don't update the blob.
+		 * For example: when ctx->map.max_entries == 0, keep default max_entries from bpf.c
+		 */
+		emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3));
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, off));
+	emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_1, BPF_REG_0, 0));
+}
+
+static void move_stack2blob(struct bpf_gen *gen, int off, int size, int stack_off)
+{
+	emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_10, stack_off));
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, off));
+	emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_1, BPF_REG_0, 0));
+}
+
+static void move_stack2ctx(struct bpf_gen *gen, int ctx_off, int size, int stack_off)
+{
+	emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_10, stack_off));
+	emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_6, BPF_REG_0, ctx_off));
+}
+
+static void emit_sys_bpf(struct bpf_gen *gen, int cmd, int attr, int attr_size)
+{
+	emit(gen, BPF_MOV64_IMM(BPF_REG_1, cmd));
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_2, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, attr));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_3, attr_size));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_bpf));
+	/* remember the result in R7 */
+	emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0));
+}
+
+static bool is_simm16(__s64 value)
+{
+	return value == (__s64)(__s16)value;
+}
+
+static void emit_check_err(struct bpf_gen *gen)
+{
+	__s64 off = -(gen->insn_cur - gen->insn_start - gen->cleanup_label) / 8 - 1;
+
+	/* R7 contains result of last sys_bpf command.
+	 * if (R7 < 0) goto cleanup;
+	 */
+	if (is_simm16(off)) {
+		emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, off));
+	} else {
+		gen->error = -ERANGE;
+		emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, -1));
+	}
+}
+
+/* reg1 and reg2 should not be R1 - R5. They can be R0, R6 - R10 */
+static void emit_debug(struct bpf_gen *gen, int reg1, int reg2,
+		       const char *fmt, va_list args)
+{
+	char buf[1024];
+	int addr, len, ret;
+
+	if (!gen->log_level)
+		return;
+	ret = vsnprintf(buf, sizeof(buf), fmt, args);
+	if (ret < 1024 - 7 && reg1 >= 0 && reg2 < 0)
+		/* The special case to accommodate common debug_ret():
+		 * to avoid specifying BPF_REG_7 and adding " r=%%d" to
+		 * prints explicitly.
+		 */
+		strcat(buf, " r=%d");
+	len = strlen(buf) + 1;
+	addr = add_data(gen, buf, len);
+
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, addr));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_2, len));
+	if (reg1 >= 0)
+		emit(gen, BPF_MOV64_REG(BPF_REG_3, reg1));
+	if (reg2 >= 0)
+		emit(gen, BPF_MOV64_REG(BPF_REG_4, reg2));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_trace_printk));
+}
+
+static void debug_regs(struct bpf_gen *gen, int reg1, int reg2, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	emit_debug(gen, reg1, reg2, fmt, args);
+	va_end(args);
+}
+
+static void debug_ret(struct bpf_gen *gen, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	emit_debug(gen, BPF_REG_7, -1, fmt, args);
+	va_end(args);
+}
+
+static void __emit_sys_close(struct bpf_gen *gen)
+{
+	emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0,
+			      /* 2 is the number of the following insns
+			       * * 6 is additional insns in debug_regs
+			       */
+			      2 + (gen->log_level ? 6 : 0)));
+	emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_1));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close));
+	debug_regs(gen, BPF_REG_9, BPF_REG_0, "close(%%d) = %%d");
+}
+
+static void emit_sys_close_stack(struct bpf_gen *gen, int stack_off)
+{
+	emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, stack_off));
+	__emit_sys_close(gen);
+}
+
+static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off)
+{
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, blob_off));
+	emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0));
+	__emit_sys_close(gen);
+}
+
+int bpf_gen__finish(struct bpf_gen *gen)
+{
+	int i;
+
+	emit_sys_close_stack(gen, stack_off(btf_fd));
+	for (i = 0; i < gen->nr_progs; i++)
+		move_stack2ctx(gen,
+			       sizeof(struct bpf_loader_ctx) +
+			       sizeof(struct bpf_map_desc) * gen->nr_maps +
+			       sizeof(struct bpf_prog_desc) * i +
+			       offsetof(struct bpf_prog_desc, prog_fd), 4,
+			       stack_off(prog_fd[i]));
+	for (i = 0; i < gen->nr_maps; i++)
+		move_stack2ctx(gen,
+			       sizeof(struct bpf_loader_ctx) +
+			       sizeof(struct bpf_map_desc) * i +
+			       offsetof(struct bpf_map_desc, map_fd), 4,
+			       stack_off(map_fd[i]));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_0, 0));
+	emit(gen, BPF_EXIT_INSN());
+	pr_debug("gen: finish %d\n", gen->error);
+	if (!gen->error) {
+		struct gen_loader_opts *opts = gen->opts;
+
+		opts->insns = gen->insn_start;
+		opts->insns_sz = gen->insn_cur - gen->insn_start;
+		opts->data = gen->data_start;
+		opts->data_sz = gen->data_cur - gen->data_start;
+	}
+	return gen->error;
+}
+
+void bpf_gen__free(struct bpf_gen *gen)
+{
+	if (!gen)
+		return;
+	free(gen->data_start);
+	free(gen->insn_start);
+	free(gen);
+}
+
+void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data,
+		       __u32 btf_raw_size)
+{
+	int attr_size = offsetofend(union bpf_attr, btf_log_level);
+	int btf_data, btf_load_attr;
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_size);
+	pr_debug("gen: load_btf: size %d\n", btf_raw_size);
+	btf_data = add_data(gen, btf_raw_data, btf_raw_size);
+
+	attr.btf_size = btf_raw_size;
+	btf_load_attr = add_data(gen, &attr, attr_size);
+
+	/* populate union bpf_attr with user provided log details */
+	move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_level), 4,
+		      offsetof(struct bpf_loader_ctx, log_level), false);
+	move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_size), 4,
+		      offsetof(struct bpf_loader_ctx, log_size), false);
+	move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_buf), 8,
+		      offsetof(struct bpf_loader_ctx, log_buf), false);
+	/* populate union bpf_attr with a pointer to the BTF data */
+	emit_rel_store(gen, attr_field(btf_load_attr, btf), btf_data);
+	/* emit BTF_LOAD command */
+	emit_sys_bpf(gen, BPF_BTF_LOAD, btf_load_attr, attr_size);
+	debug_ret(gen, "btf_load size %d", btf_raw_size);
+	emit_check_err(gen);
+	/* remember btf_fd in the stack, if successful */
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, stack_off(btf_fd)));
+}
+
+void bpf_gen__map_create(struct bpf_gen *gen,
+			 struct bpf_create_map_attr *map_attr, int map_idx)
+{
+	int attr_size = offsetofend(union bpf_attr, btf_vmlinux_value_type_id);
+	bool close_inner_map_fd = false;
+	int map_create_attr;
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_size);
+	attr.map_type = map_attr->map_type;
+	attr.key_size = map_attr->key_size;
+	attr.value_size = map_attr->value_size;
+	attr.map_flags = map_attr->map_flags;
+	memcpy(attr.map_name, map_attr->name,
+	       min((unsigned)strlen(map_attr->name), BPF_OBJ_NAME_LEN - 1));
+	attr.numa_node = map_attr->numa_node;
+	attr.map_ifindex = map_attr->map_ifindex;
+	attr.max_entries = map_attr->max_entries;
+	switch (attr.map_type) {
+	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
+	case BPF_MAP_TYPE_CGROUP_ARRAY:
+	case BPF_MAP_TYPE_STACK_TRACE:
+	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
+	case BPF_MAP_TYPE_HASH_OF_MAPS:
+	case BPF_MAP_TYPE_DEVMAP:
+	case BPF_MAP_TYPE_DEVMAP_HASH:
+	case BPF_MAP_TYPE_CPUMAP:
+	case BPF_MAP_TYPE_XSKMAP:
+	case BPF_MAP_TYPE_SOCKMAP:
+	case BPF_MAP_TYPE_SOCKHASH:
+	case BPF_MAP_TYPE_QUEUE:
+	case BPF_MAP_TYPE_STACK:
+	case BPF_MAP_TYPE_RINGBUF:
+		break;
+	default:
+		attr.btf_key_type_id = map_attr->btf_key_type_id;
+		attr.btf_value_type_id = map_attr->btf_value_type_id;
+	}
+
+	pr_debug("gen: map_create: %s idx %d type %d value_type_id %d\n",
+		 attr.map_name, map_idx, map_attr->map_type, attr.btf_value_type_id);
+
+	map_create_attr = add_data(gen, &attr, attr_size);
+	if (attr.btf_value_type_id)
+		/* populate union bpf_attr with btf_fd saved in the stack earlier */
+		move_stack2blob(gen, attr_field(map_create_attr, btf_fd), 4,
+				stack_off(btf_fd));
+	switch (attr.map_type) {
+	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
+	case BPF_MAP_TYPE_HASH_OF_MAPS:
+		move_stack2blob(gen, attr_field(map_create_attr, inner_map_fd), 4,
+				stack_off(inner_map_fd));
+		close_inner_map_fd = true;
+		break;
+	default:
+		break;
+	}
+	/* conditionally update max_entries */
+	if (map_idx >= 0)
+		move_ctx2blob(gen, attr_field(map_create_attr, max_entries), 4,
+			      sizeof(struct bpf_loader_ctx) +
+			      sizeof(struct bpf_map_desc) * map_idx +
+			      offsetof(struct bpf_map_desc, max_entries),
+			      true /* check that max_entries != 0 */);
+	/* emit MAP_CREATE command */
+	emit_sys_bpf(gen, BPF_MAP_CREATE, map_create_attr, attr_size);
+	debug_ret(gen, "map_create %s idx %d type %d value_size %d value_btf_id %d",
+		  attr.map_name, map_idx, map_attr->map_type, attr.value_size,
+		  attr.btf_value_type_id);
+	emit_check_err(gen);
+	/* remember map_fd in the stack, if successful */
+	if (map_idx < 0) {
+		/* This bpf_gen__map_create() function is called with map_idx >= 0
+		 * for all maps that libbpf loading logic tracks.
+		 * It's called with -1 to create an inner map.
+		 */
+		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7,
+				      stack_off(inner_map_fd)));
+	} else if (map_idx != gen->nr_maps) {
+		gen->error = -EDOM; /* internal bug */
+		return;
+	} else {
+		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7,
+				      stack_off(map_fd[map_idx])));
+		gen->nr_maps++;
+	}
+	if (close_inner_map_fd)
+		emit_sys_close_stack(gen, stack_off(inner_map_fd));
+}
+
+void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *attach_name,
+				   enum bpf_attach_type type)
+{
+	const char *prefix;
+	int kind, ret;
+
+	btf_get_kernel_prefix_kind(type, &prefix, &kind);
+	gen->attach_kind = kind;
+	ret = snprintf(gen->attach_target, sizeof(gen->attach_target), "%s%s",
+		       prefix, attach_name);
+	if (ret == sizeof(gen->attach_target))
+		gen->error = -ENOSPC;
+}
+
+static void emit_find_attach_target(struct bpf_gen *gen)
+{
+	int name, len = strlen(gen->attach_target) + 1;
+
+	pr_debug("gen: find_attach_tgt %s %d\n", gen->attach_target, gen->attach_kind);
+	name = add_data(gen, gen->attach_target, len);
+
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, name));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_2, len));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_3, gen->attach_kind));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_4, 0));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_btf_find_by_name_kind));
+	emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0));
+	debug_ret(gen, "find_by_name_kind(%s,%d)",
+		  gen->attach_target, gen->attach_kind);
+	emit_check_err(gen);
+	/* if successful, btf_id is in lower 32-bit of R7 and
+	 * btf_obj_fd is in upper 32-bit
+	 */
+}
+
+void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind,
+			    int insn_idx)
+{
+	struct ksym_relo_desc *relo;
+
+	relo = libbpf_reallocarray(gen->relos, gen->relo_cnt + 1, sizeof(*relo));
+	if (!relo) {
+		gen->error = -ENOMEM;
+		return;
+	}
+	gen->relos = relo;
+	relo += gen->relo_cnt;
+	relo->name = name;
+	relo->kind = kind;
+	relo->insn_idx = insn_idx;
+	gen->relo_cnt++;
+}
+
+static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insns)
+{
+	int name, insn, len = strlen(relo->name) + 1;
+
+	pr_debug("gen: emit_relo: %s at %d\n", relo->name, relo->insn_idx);
+	name = add_data(gen, relo->name, len);
+
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, name));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_2, len));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_3, relo->kind));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_4, 0));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_btf_find_by_name_kind));
+	emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0));
+	debug_ret(gen, "find_by_name_kind(%s,%d)", relo->name, relo->kind);
+	emit_check_err(gen);
+	/* store btf_id into insn[insn_idx].imm */
+	insn = insns + sizeof(struct bpf_insn) * relo->insn_idx +
+		offsetof(struct bpf_insn, imm);
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, insn));
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, 0));
+	if (relo->kind == BTF_KIND_VAR) {
+		/* store btf_obj_fd into insn[insn_idx + 1].imm */
+		emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32));
+		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7,
+				      sizeof(struct bpf_insn)));
+	}
+}
+
+static void emit_relos(struct bpf_gen *gen, int insns)
+{
+	int i;
+
+	for (i = 0; i < gen->relo_cnt; i++)
+		emit_relo(gen, gen->relos + i, insns);
+}
+
+static void cleanup_relos(struct bpf_gen *gen, int insns)
+{
+	int i, insn;
+
+	for (i = 0; i < gen->relo_cnt; i++) {
+		if (gen->relos[i].kind != BTF_KIND_VAR)
+			continue;
+		/* close fd recorded in insn[insn_idx + 1].imm */
+		insn = insns +
+			sizeof(struct bpf_insn) * (gen->relos[i].insn_idx + 1) +
+			offsetof(struct bpf_insn, imm);
+		emit_sys_close_blob(gen, insn);
+	}
+	if (gen->relo_cnt) {
+		free(gen->relos);
+		gen->relo_cnt = 0;
+		gen->relos = NULL;
+	}
+}
+
+void bpf_gen__prog_load(struct bpf_gen *gen,
+			struct bpf_prog_load_params *load_attr, int prog_idx)
+{
+	int attr_size = offsetofend(union bpf_attr, fd_array);
+	int prog_load_attr, license, insns, func_info, line_info;
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_size);
+	pr_debug("gen: prog_load: type %d insns_cnt %zd\n",
+		 load_attr->prog_type, load_attr->insn_cnt);
+	/* add license string to blob of bytes */
+	license = add_data(gen, load_attr->license, strlen(load_attr->license) + 1);
+	/* add insns to blob of bytes */
+	insns = add_data(gen, load_attr->insns,
+			 load_attr->insn_cnt * sizeof(struct bpf_insn));
+
+	attr.prog_type = load_attr->prog_type;
+	attr.expected_attach_type = load_attr->expected_attach_type;
+	attr.attach_btf_id = load_attr->attach_btf_id;
+	attr.prog_ifindex = load_attr->prog_ifindex;
+	attr.kern_version = 0;
+	attr.insn_cnt = (__u32)load_attr->insn_cnt;
+	attr.prog_flags = load_attr->prog_flags;
+
+	attr.func_info_rec_size = load_attr->func_info_rec_size;
+	attr.func_info_cnt = load_attr->func_info_cnt;
+	func_info = add_data(gen, load_attr->func_info,
+			     attr.func_info_cnt * attr.func_info_rec_size);
+
+	attr.line_info_rec_size = load_attr->line_info_rec_size;
+	attr.line_info_cnt = load_attr->line_info_cnt;
+	line_info = add_data(gen, load_attr->line_info,
+			     attr.line_info_cnt * attr.line_info_rec_size);
+
+	memcpy(attr.prog_name, load_attr->name,
+	       min((unsigned)strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1));
+	prog_load_attr = add_data(gen, &attr, attr_size);
+
+	/* populate union bpf_attr with a pointer to license */
+	emit_rel_store(gen, attr_field(prog_load_attr, license), license);
+
+	/* populate union bpf_attr with a pointer to instructions */
+	emit_rel_store(gen, attr_field(prog_load_attr, insns), insns);
+
+	/* populate union bpf_attr with a pointer to func_info */
+	emit_rel_store(gen, attr_field(prog_load_attr, func_info), func_info);
+
+	/* populate union bpf_attr with a pointer to line_info */
+	emit_rel_store(gen, attr_field(prog_load_attr, line_info), line_info);
+
+	/* populate union bpf_attr fd_array with a pointer to stack where map_fds are saved */
+	emit_rel_store_sp(gen, attr_field(prog_load_attr, fd_array),
+			  stack_off(map_fd[0]));
+
+	/* populate union bpf_attr with user provided log details */
+	move_ctx2blob(gen, attr_field(prog_load_attr, log_level), 4,
+		      offsetof(struct bpf_loader_ctx, log_level), false);
+	move_ctx2blob(gen, attr_field(prog_load_attr, log_size), 4,
+		      offsetof(struct bpf_loader_ctx, log_size), false);
+	move_ctx2blob(gen, attr_field(prog_load_attr, log_buf), 8,
+		      offsetof(struct bpf_loader_ctx, log_buf), false);
+	/* populate union bpf_attr with btf_fd saved in the stack earlier */
+	move_stack2blob(gen, attr_field(prog_load_attr, prog_btf_fd), 4,
+			stack_off(btf_fd));
+	if (gen->attach_kind) {
+		emit_find_attach_target(gen);
+		/* populate union bpf_attr with btf_id and btf_obj_fd found by helper */
+		emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE,
+						 0, 0, 0, prog_load_attr));
+		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7,
+				      offsetof(union bpf_attr, attach_btf_id)));
+		emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32));
+		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7,
+				      offsetof(union bpf_attr, attach_btf_obj_fd)));
+	}
+	emit_relos(gen, insns);
+	/* emit PROG_LOAD command */
+	emit_sys_bpf(gen, BPF_PROG_LOAD, prog_load_attr, attr_size);
+	debug_ret(gen, "prog_load %s insn_cnt %d", attr.prog_name, attr.insn_cnt);
+	/* successful or not, close btf module FDs used in extern ksyms and attach_btf_obj_fd */
+	cleanup_relos(gen, insns);
+	if (gen->attach_kind)
+		emit_sys_close_blob(gen,
+				    attr_field(prog_load_attr, attach_btf_obj_fd));
+	emit_check_err(gen);
+	/* remember prog_fd in the stack, if successful */
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7,
+			      stack_off(prog_fd[gen->nr_progs])));
+	gen->nr_progs++;
+}
+
+void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue,
+			      __u32 value_size)
+{
+	int attr_size = offsetofend(union bpf_attr, flags);
+	int map_update_attr, value, key;
+	union bpf_attr attr;
+	int zero = 0;
+
+	memset(&attr, 0, attr_size);
+	pr_debug("gen: map_update_elem: idx %d\n", map_idx);
+
+	value = add_data(gen, pvalue, value_size);
+	key = add_data(gen, &zero, sizeof(zero));
+
+	/* if (map_desc[map_idx].initial_value)
+	 *    copy_from_user(value, initial_value, value_size);
+	 */
+	emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_6,
+			      sizeof(struct bpf_loader_ctx) +
+			      sizeof(struct bpf_map_desc) * map_idx +
+			      offsetof(struct bpf_map_desc, initial_value)));
+	emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 4));
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, value));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_2, value_size));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_copy_from_user));
+
+	map_update_attr = add_data(gen, &attr, attr_size);
+	move_stack2blob(gen, attr_field(map_update_attr, map_fd), 4,
+			stack_off(map_fd[map_idx]));
+	emit_rel_store(gen, attr_field(map_update_attr, key), key);
+	emit_rel_store(gen, attr_field(map_update_attr, value), value);
+	/* emit MAP_UPDATE_ELEM command */
+	emit_sys_bpf(gen, BPF_MAP_UPDATE_ELEM, map_update_attr, attr_size);
+	debug_ret(gen, "update_elem idx %d value_size %d", map_idx, value_size);
+	emit_check_err(gen);
+}
+
+void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx)
+{
+	int attr_size = offsetofend(union bpf_attr, map_fd);
+	int map_freeze_attr;
+	union bpf_attr attr;
+
+	memset(&attr, 0, attr_size);
+	pr_debug("gen: map_freeze: idx %d\n", map_idx);
+	map_freeze_attr = add_data(gen, &attr, attr_size);
+	move_stack2blob(gen, attr_field(map_freeze_attr, map_fd), 4,
+			stack_off(map_fd[map_idx]));
+	/* emit MAP_FREEZE command */
+	emit_sys_bpf(gen, BPF_MAP_FREEZE, map_freeze_attr, attr_size);
+	debug_ret(gen, "map_freeze");
+	emit_check_err(gen);
+}
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index c41d9b2b59ac..1e04ce724240 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -54,6 +54,7 @@
 #include "str_error.h"
 #include "libbpf_internal.h"
 #include "hashmap.h"
+#include "bpf_gen_internal.h"
 
 #ifndef BPF_FS_MAGIC
 #define BPF_FS_MAGIC		0xcafe4a11
@@ -150,6 +151,23 @@ static inline __u64 ptr_to_u64(const void *ptr)
 	return (__u64) (unsigned long) ptr;
 }
 
+/* this goes away in libbpf 1.0 */
+enum libbpf_strict_mode libbpf_mode = LIBBPF_STRICT_NONE;
+
+int libbpf_set_strict_mode(enum libbpf_strict_mode mode)
+{
+	/* __LIBBPF_STRICT_LAST is the last power-of-2 value used + 1, so to
+	 * get all possible values we compensate last +1, and then (2*x - 1)
+	 * to get the bit mask
+	 */
+	if (mode != LIBBPF_STRICT_ALL
+	    && (mode & ~((__LIBBPF_STRICT_LAST - 1) * 2 - 1)))
+		return errno = EINVAL, -EINVAL;
+
+	libbpf_mode = mode;
+	return 0;
+}
+
 enum kern_feature_id {
 	/* v4.14: kernel support for program & map names. */
 	FEAT_PROG_NAME,
@@ -178,7 +196,7 @@ enum kern_feature_id {
 	__FEAT_CNT,
 };
 
-static bool kernel_supports(enum kern_feature_id feat_id);
+static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id);
 
 enum reloc_type {
 	RELO_LD64,
@@ -432,6 +450,8 @@ struct bpf_object {
 	bool loaded;
 	bool has_subcalls;
 
+	struct bpf_gen *gen_loader;
+
 	/*
 	 * Information when doing elf related work. Only valid if fd
 	 * is valid.
@@ -677,6 +697,11 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
+		if (sec_idx != obj->efile.text_shndx && GELF_ST_BIND(sym.st_info) == STB_LOCAL) {
+			pr_warn("sec '%s': program '%s' is static and not supported\n", sec_name, name);
+			return -ENOTSUP;
+		}
+
 		pr_debug("sec '%s': found program '%s' at insn offset %zu (%zu bytes), code size %zu insns (%zu bytes)\n",
 			 sec_name, name, sec_off / BPF_INSN_SZ, sec_off, prog_sz / BPF_INSN_SZ, prog_sz);
 
@@ -700,13 +725,14 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
 		if (err)
 			return err;
 
-		/* if function is a global/weak symbol, but has hidden
-		 * visibility (STV_HIDDEN), mark its BTF FUNC as static to
-		 * enable more permissive BPF verification mode with more
-		 * outside context available to BPF verifier
+		/* if function is a global/weak symbol, but has restricted
+		 * (STV_HIDDEN or STV_INTERNAL) visibility, mark its BTF FUNC
+		 * as static to enable more permissive BPF verification mode
+		 * with more outside context available to BPF verifier
 		 */
 		if (GELF_ST_BIND(sym.st_info) != STB_LOCAL
-		    && GELF_ST_VISIBILITY(sym.st_other) == STV_HIDDEN)
+		    && (GELF_ST_VISIBILITY(sym.st_other) == STV_HIDDEN
+			|| GELF_ST_VISIBILITY(sym.st_other) == STV_INTERNAL))
 			prog->mark_btf_static = true;
 
 		nr_progs++;
@@ -1794,7 +1820,6 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 	if (!symbols)
 		return -EINVAL;
 
-
 	scn = elf_sec_by_idx(obj, obj->efile.maps_shndx);
 	data = elf_sec_data(obj, scn);
 	if (!scn || !data) {
@@ -1854,6 +1879,12 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
+		if (GELF_ST_TYPE(sym.st_info) == STT_SECTION
+		    || GELF_ST_BIND(sym.st_info) == STB_LOCAL) {
+			pr_warn("map '%s' (legacy): static maps are not supported\n", map_name);
+			return -ENOTSUP;
+		}
+
 		map->libbpf_type = LIBBPF_MAP_UNSPEC;
 		map->sec_idx = sym.st_shndx;
 		map->sec_offset = sym.st_value;
@@ -2261,6 +2292,16 @@ static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def
 		pr_debug("map '%s': found inner map definition.\n", map->name);
 }
 
+static const char *btf_var_linkage_str(__u32 linkage)
+{
+	switch (linkage) {
+	case BTF_VAR_STATIC: return "static";
+	case BTF_VAR_GLOBAL_ALLOCATED: return "global";
+	case BTF_VAR_GLOBAL_EXTERN: return "extern";
+	default: return "unknown";
+	}
+}
+
 static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 					 const struct btf_type *sec,
 					 int var_idx, int sec_idx,
@@ -2293,10 +2334,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 			map_name, btf_kind_str(var));
 		return -EINVAL;
 	}
-	if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED &&
-	    var_extra->linkage != BTF_VAR_STATIC) {
-		pr_warn("map '%s': unsupported var linkage %u.\n",
-			map_name, var_extra->linkage);
+	if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED) {
+		pr_warn("map '%s': unsupported map linkage %s.\n",
+			map_name, btf_var_linkage_str(var_extra->linkage));
 		return -EOPNOTSUPP;
 	}
 
@@ -2425,10 +2465,8 @@ static int bpf_object__init_maps(struct bpf_object *obj,
 	err = err ?: bpf_object__init_global_data_maps(obj);
 	err = err ?: bpf_object__init_kconfig_map(obj);
 	err = err ?: bpf_object__init_struct_ops_maps(obj);
-	if (err)
-		return err;
 
-	return 0;
+	return err;
 }
 
 static bool section_have_execinstr(struct bpf_object *obj, int idx)
@@ -2443,20 +2481,20 @@ static bool section_have_execinstr(struct bpf_object *obj, int idx)
 
 static bool btf_needs_sanitization(struct bpf_object *obj)
 {
-	bool has_func_global = kernel_supports(FEAT_BTF_GLOBAL_FUNC);
-	bool has_datasec = kernel_supports(FEAT_BTF_DATASEC);
-	bool has_float = kernel_supports(FEAT_BTF_FLOAT);
-	bool has_func = kernel_supports(FEAT_BTF_FUNC);
+	bool has_func_global = kernel_supports(obj, FEAT_BTF_GLOBAL_FUNC);
+	bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC);
+	bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT);
+	bool has_func = kernel_supports(obj, FEAT_BTF_FUNC);
 
 	return !has_func || !has_datasec || !has_func_global || !has_float;
 }
 
 static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf)
 {
-	bool has_func_global = kernel_supports(FEAT_BTF_GLOBAL_FUNC);
-	bool has_datasec = kernel_supports(FEAT_BTF_DATASEC);
-	bool has_float = kernel_supports(FEAT_BTF_FLOAT);
-	bool has_func = kernel_supports(FEAT_BTF_FUNC);
+	bool has_func_global = kernel_supports(obj, FEAT_BTF_GLOBAL_FUNC);
+	bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC);
+	bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT);
+	bool has_func = kernel_supports(obj, FEAT_BTF_FUNC);
 	struct btf_type *t;
 	int i, j, vlen;
 
@@ -2539,16 +2577,14 @@ static int bpf_object__init_btf(struct bpf_object *obj,
 
 	if (btf_data) {
 		obj->btf = btf__new(btf_data->d_buf, btf_data->d_size);
-		if (IS_ERR(obj->btf)) {
-			err = PTR_ERR(obj->btf);
+		err = libbpf_get_error(obj->btf);
+		if (err) {
 			obj->btf = NULL;
-			pr_warn("Error loading ELF section %s: %d.\n",
-				BTF_ELF_SEC, err);
+			pr_warn("Error loading ELF section %s: %d.\n", BTF_ELF_SEC, err);
 			goto out;
 		}
 		/* enforce 8-byte pointers for BPF-targeted BTFs */
 		btf__set_pointer_size(obj->btf, 8);
-		err = 0;
 	}
 	if (btf_ext_data) {
 		if (!obj->btf) {
@@ -2556,11 +2592,11 @@ static int bpf_object__init_btf(struct bpf_object *obj,
 				 BTF_EXT_ELF_SEC, BTF_ELF_SEC);
 			goto out;
 		}
-		obj->btf_ext = btf_ext__new(btf_ext_data->d_buf,
-					    btf_ext_data->d_size);
-		if (IS_ERR(obj->btf_ext)) {
-			pr_warn("Error loading ELF section %s: %ld. Ignored and continue.\n",
-				BTF_EXT_ELF_SEC, PTR_ERR(obj->btf_ext));
+		obj->btf_ext = btf_ext__new(btf_ext_data->d_buf, btf_ext_data->d_size);
+		err = libbpf_get_error(obj->btf_ext);
+		if (err) {
+			pr_warn("Error loading ELF section %s: %d. Ignored and continue.\n",
+				BTF_EXT_ELF_SEC, err);
 			obj->btf_ext = NULL;
 			goto out;
 		}
@@ -2637,15 +2673,15 @@ static int bpf_object__load_vmlinux_btf(struct bpf_object *obj, bool force)
 	int err;
 
 	/* btf_vmlinux could be loaded earlier */
-	if (obj->btf_vmlinux)
+	if (obj->btf_vmlinux || obj->gen_loader)
 		return 0;
 
 	if (!force && !obj_needs_vmlinux_btf(obj))
 		return 0;
 
 	obj->btf_vmlinux = libbpf_find_kernel_btf();
-	if (IS_ERR(obj->btf_vmlinux)) {
-		err = PTR_ERR(obj->btf_vmlinux);
+	err = libbpf_get_error(obj->btf_vmlinux);
+	if (err) {
 		pr_warn("Error loading vmlinux BTF: %d\n", err);
 		obj->btf_vmlinux = NULL;
 		return err;
@@ -2662,7 +2698,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 	if (!obj->btf)
 		return 0;
 
-	if (!kernel_supports(FEAT_BTF)) {
+	if (!kernel_supports(obj, FEAT_BTF)) {
 		if (kernel_needs_btf(obj)) {
 			err = -EOPNOTSUPP;
 			goto report;
@@ -2711,15 +2747,29 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 		/* clone BTF to sanitize a copy and leave the original intact */
 		raw_data = btf__get_raw_data(obj->btf, &sz);
 		kern_btf = btf__new(raw_data, sz);
-		if (IS_ERR(kern_btf))
-			return PTR_ERR(kern_btf);
+		err = libbpf_get_error(kern_btf);
+		if (err)
+			return err;
 
 		/* enforce 8-byte pointers for BPF-targeted BTFs */
 		btf__set_pointer_size(obj->btf, 8);
 		bpf_object__sanitize_btf(obj, kern_btf);
 	}
 
-	err = btf__load(kern_btf);
+	if (obj->gen_loader) {
+		__u32 raw_size = 0;
+		const void *raw_data = btf__get_raw_data(kern_btf, &raw_size);
+
+		if (!raw_data)
+			return -ENOMEM;
+		bpf_gen__load_btf(obj->gen_loader, raw_data, raw_size);
+		/* Pretend to have valid FD to pass various fd >= 0 checks.
+		 * This fd == 0 will not be used with any syscall and will be reset to -1 eventually.
+		 */
+		btf__set_fd(kern_btf, 0);
+	} else {
+		err = btf__load(kern_btf);
+	}
 	if (sanitize) {
 		if (!err) {
 			/* move fd to libbpf's BTF */
@@ -3473,7 +3523,7 @@ bpf_object__find_program_by_title(const struct bpf_object *obj,
 		if (pos->sec_name && !strcmp(pos->sec_name, title))
 			return pos;
 	}
-	return NULL;
+	return errno = ENOENT, NULL;
 }
 
 static bool prog_is_subprog(const struct bpf_object *obj,
@@ -3506,7 +3556,7 @@ bpf_object__find_program_by_name(const struct bpf_object *obj,
 		if (!strcmp(prog->name, name))
 			return prog;
 	}
-	return NULL;
+	return errno = ENOENT, NULL;
 }
 
 static bool bpf_object__shndx_is_data(const struct bpf_object *obj,
@@ -3853,11 +3903,11 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 
 	err = bpf_obj_get_info_by_fd(fd, &info, &len);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	new_name = strdup(info.name);
 	if (!new_name)
-		return -errno;
+		return libbpf_err(-errno);
 
 	new_fd = open("/", O_RDONLY | O_CLOEXEC);
 	if (new_fd < 0) {
@@ -3895,7 +3945,7 @@ err_close_new_fd:
 	close(new_fd);
 err_free_new_name:
 	free(new_name);
-	return err;
+	return libbpf_err(err);
 }
 
 __u32 bpf_map__max_entries(const struct bpf_map *map)
@@ -3906,7 +3956,7 @@ __u32 bpf_map__max_entries(const struct bpf_map *map)
 struct bpf_map *bpf_map__inner_map(struct bpf_map *map)
 {
 	if (!bpf_map_type__is_map_in_map(map->def.type))
-		return NULL;
+		return errno = EINVAL, NULL;
 
 	return map->inner_map;
 }
@@ -3914,7 +3964,7 @@ struct bpf_map *bpf_map__inner_map(struct bpf_map *map)
 int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries)
 {
 	if (map->fd >= 0)
-		return -EBUSY;
+		return libbpf_err(-EBUSY);
 	map->def.max_entries = max_entries;
 	return 0;
 }
@@ -3922,7 +3972,7 @@ int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries)
 int bpf_map__resize(struct bpf_map *map, __u32 max_entries)
 {
 	if (!map || !max_entries)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	return bpf_map__set_max_entries(map, max_entries);
 }
@@ -3938,6 +3988,9 @@ bpf_object__probe_loading(struct bpf_object *obj)
 	};
 	int ret;
 
+	if (obj->gen_loader)
+		return 0;
+
 	/* make sure basic loading works */
 
 	memset(&attr, 0, sizeof(attr));
@@ -3948,6 +4001,10 @@ bpf_object__probe_loading(struct bpf_object *obj)
 
 	ret = bpf_load_program_xattr(&attr, NULL, 0);
 	if (ret < 0) {
+		attr.prog_type = BPF_PROG_TYPE_TRACEPOINT;
+		ret = bpf_load_program_xattr(&attr, NULL, 0);
+	}
+	if (ret < 0) {
 		ret = errno;
 		cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
 		pr_warn("Error in %s():%s(%d). Couldn't load trivial BPF "
@@ -4293,11 +4350,17 @@ static struct kern_feature_desc {
 	},
 };
 
-static bool kernel_supports(enum kern_feature_id feat_id)
+static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id)
 {
 	struct kern_feature_desc *feat = &feature_probes[feat_id];
 	int ret;
 
+	if (obj->gen_loader)
+		/* To generate loader program assume the latest kernel
+		 * to avoid doing extra prog_load, map_create syscalls.
+		 */
+		return true;
+
 	if (READ_ONCE(feat->res) == FEAT_UNKNOWN) {
 		ret = feat->probe();
 		if (ret > 0) {
@@ -4380,6 +4443,13 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
 	char *cp, errmsg[STRERR_BUFSIZE];
 	int err, zero = 0;
 
+	if (obj->gen_loader) {
+		bpf_gen__map_update_elem(obj->gen_loader, map - obj->maps,
+					 map->mmaped, map->def.value_size);
+		if (map_type == LIBBPF_MAP_RODATA || map_type == LIBBPF_MAP_KCONFIG)
+			bpf_gen__map_freeze(obj->gen_loader, map - obj->maps);
+		return 0;
+	}
 	err = bpf_map_update_elem(map->fd, &zero, map->mmaped, 0);
 	if (err) {
 		err = -errno;
@@ -4405,14 +4475,14 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
 
 static void bpf_map__destroy(struct bpf_map *map);
 
-static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map)
+static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, bool is_inner)
 {
 	struct bpf_create_map_attr create_attr;
 	struct bpf_map_def *def = &map->def;
 
 	memset(&create_attr, 0, sizeof(create_attr));
 
-	if (kernel_supports(FEAT_PROG_NAME))
+	if (kernel_supports(obj, FEAT_PROG_NAME))
 		create_attr.name = map->name;
 	create_attr.map_ifindex = map->map_ifindex;
 	create_attr.map_type = def->type;
@@ -4453,7 +4523,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map)
 		if (map->inner_map) {
 			int err;
 
-			err = bpf_object__create_map(obj, map->inner_map);
+			err = bpf_object__create_map(obj, map->inner_map, true);
 			if (err) {
 				pr_warn("map '%s': failed to create inner map: %d\n",
 					map->name, err);
@@ -4465,7 +4535,15 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map)
 			create_attr.inner_map_fd = map->inner_map_fd;
 	}
 
-	map->fd = bpf_create_map_xattr(&create_attr);
+	if (obj->gen_loader) {
+		bpf_gen__map_create(obj->gen_loader, &create_attr, is_inner ? -1 : map - obj->maps);
+		/* Pretend to have valid FD to pass various fd >= 0 checks.
+		 * This fd == 0 will not be used with any syscall and will be reset to -1 eventually.
+		 */
+		map->fd = 0;
+	} else {
+		map->fd = bpf_create_map_xattr(&create_attr);
+	}
 	if (map->fd < 0 && (create_attr.btf_key_type_id ||
 			    create_attr.btf_value_type_id)) {
 		char *cp, errmsg[STRERR_BUFSIZE];
@@ -4486,6 +4564,8 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map)
 		return -errno;
 
 	if (bpf_map_type__is_map_in_map(def->type) && map->inner_map) {
+		if (obj->gen_loader)
+			map->inner_map->fd = -1;
 		bpf_map__destroy(map->inner_map);
 		zfree(&map->inner_map);
 	}
@@ -4493,11 +4573,11 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map)
 	return 0;
 }
 
-static int init_map_slots(struct bpf_map *map)
+static int init_map_slots(struct bpf_object *obj, struct bpf_map *map)
 {
 	const struct bpf_map *targ_map;
 	unsigned int i;
-	int fd, err;
+	int fd, err = 0;
 
 	for (i = 0; i < map->init_slots_sz; i++) {
 		if (!map->init_slots[i])
@@ -4505,7 +4585,13 @@ static int init_map_slots(struct bpf_map *map)
 
 		targ_map = map->init_slots[i];
 		fd = bpf_map__fd(targ_map);
-		err = bpf_map_update_elem(map->fd, &i, &fd, 0);
+		if (obj->gen_loader) {
+			pr_warn("// TODO map_update_elem: idx %td key %d value==map_idx %td\n",
+				map - obj->maps, i, targ_map - obj->maps);
+			return -ENOTSUP;
+		} else {
+			err = bpf_map_update_elem(map->fd, &i, &fd, 0);
+		}
 		if (err) {
 			err = -errno;
 			pr_warn("map '%s': failed to initialize slot [%d] to map '%s' fd=%d: %d\n",
@@ -4547,7 +4633,7 @@ bpf_object__create_maps(struct bpf_object *obj)
 			pr_debug("map '%s': skipping creation (preset fd=%d)\n",
 				 map->name, map->fd);
 		} else {
-			err = bpf_object__create_map(obj, map);
+			err = bpf_object__create_map(obj, map, false);
 			if (err)
 				goto err_out;
 
@@ -4563,7 +4649,7 @@ bpf_object__create_maps(struct bpf_object *obj)
 			}
 
 			if (map->init_slots_sz) {
-				err = init_map_slots(map);
+				err = init_map_slots(obj, map);
 				if (err < 0) {
 					zclose(map->fd);
 					goto err_out;
@@ -4973,11 +5059,14 @@ static int load_module_btfs(struct bpf_object *obj)
 	if (obj->btf_modules_loaded)
 		return 0;
 
+	if (obj->gen_loader)
+		return 0;
+
 	/* don't do this again, even if we find no module BTFs */
 	obj->btf_modules_loaded = true;
 
 	/* kernel too old to support module BTFs */
-	if (!kernel_supports(FEAT_MODULE_BTF))
+	if (!kernel_supports(obj, FEAT_MODULE_BTF))
 		return 0;
 
 	while (true) {
@@ -5018,10 +5107,10 @@ static int load_module_btfs(struct bpf_object *obj)
 		}
 
 		btf = btf_get_from_fd(fd, obj->btf_vmlinux);
-		if (IS_ERR(btf)) {
-			pr_warn("failed to load module [%s]'s BTF object #%d: %ld\n",
-				name, id, PTR_ERR(btf));
-			err = PTR_ERR(btf);
+		err = libbpf_get_error(btf);
+		if (err) {
+			pr_warn("failed to load module [%s]'s BTF object #%d: %d\n",
+				name, id, err);
 			goto err_out;
 		}
 
@@ -6120,6 +6209,12 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 	if (str_is_empty(spec_str))
 		return -EINVAL;
 
+	if (prog->obj->gen_loader) {
+		pr_warn("// TODO core_relo: prog %td insn[%d] %s %s kind %d\n",
+			prog - prog->obj->programs, relo->insn_off / 8,
+			local_name, spec_str, relo->kind);
+		return -ENOTSUP;
+	}
 	err = bpf_core_parse_spec(local_btf, local_id, spec_str, relo->kind, &local_spec);
 	if (err) {
 		pr_warn("prog '%s': relo #%d: parsing [%d] %s %s + %s failed: %d\n",
@@ -6275,8 +6370,8 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path)
 
 	if (targ_btf_path) {
 		obj->btf_vmlinux_override = btf__parse(targ_btf_path, NULL);
-		if (IS_ERR_OR_NULL(obj->btf_vmlinux_override)) {
-			err = PTR_ERR(obj->btf_vmlinux_override);
+		err = libbpf_get_error(obj->btf_vmlinux_override);
+		if (err) {
 			pr_warn("failed to parse target BTF: %d\n", err);
 			return err;
 		}
@@ -6371,19 +6466,34 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
 
 		switch (relo->type) {
 		case RELO_LD64:
-			insn[0].src_reg = BPF_PSEUDO_MAP_FD;
-			insn[0].imm = obj->maps[relo->map_idx].fd;
+			if (obj->gen_loader) {
+				insn[0].src_reg = BPF_PSEUDO_MAP_IDX;
+				insn[0].imm = relo->map_idx;
+			} else {
+				insn[0].src_reg = BPF_PSEUDO_MAP_FD;
+				insn[0].imm = obj->maps[relo->map_idx].fd;
+			}
 			break;
 		case RELO_DATA:
-			insn[0].src_reg = BPF_PSEUDO_MAP_VALUE;
 			insn[1].imm = insn[0].imm + relo->sym_off;
-			insn[0].imm = obj->maps[relo->map_idx].fd;
+			if (obj->gen_loader) {
+				insn[0].src_reg = BPF_PSEUDO_MAP_IDX_VALUE;
+				insn[0].imm = relo->map_idx;
+			} else {
+				insn[0].src_reg = BPF_PSEUDO_MAP_VALUE;
+				insn[0].imm = obj->maps[relo->map_idx].fd;
+			}
 			break;
 		case RELO_EXTERN_VAR:
 			ext = &obj->externs[relo->sym_off];
 			if (ext->type == EXT_KCFG) {
-				insn[0].src_reg = BPF_PSEUDO_MAP_VALUE;
-				insn[0].imm = obj->maps[obj->kconfig_map_idx].fd;
+				if (obj->gen_loader) {
+					insn[0].src_reg = BPF_PSEUDO_MAP_IDX_VALUE;
+					insn[0].imm = obj->kconfig_map_idx;
+				} else {
+					insn[0].src_reg = BPF_PSEUDO_MAP_VALUE;
+					insn[0].imm = obj->maps[obj->kconfig_map_idx].fd;
+				}
 				insn[1].imm = ext->kcfg.data_off;
 			} else /* EXT_KSYM */ {
 				if (ext->ksym.type_id) { /* typed ksyms */
@@ -6402,11 +6512,15 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
 			insn[0].imm = ext->ksym.kernel_btf_id;
 			break;
 		case RELO_SUBPROG_ADDR:
-			insn[0].src_reg = BPF_PSEUDO_FUNC;
-			/* will be handled as a follow up pass */
+			if (insn[0].src_reg != BPF_PSEUDO_FUNC) {
+				pr_warn("prog '%s': relo #%d: bad insn\n",
+					prog->name, i);
+				return -EINVAL;
+			}
+			/* handled already */
 			break;
 		case RELO_CALL:
-			/* will be handled as a follow up pass */
+			/* handled already */
 			break;
 		default:
 			pr_warn("prog '%s': relo #%d: bad relo type %d\n",
@@ -6497,7 +6611,7 @@ reloc_prog_func_and_line_info(const struct bpf_object *obj,
 	/* no .BTF.ext relocation if .BTF.ext is missing or kernel doesn't
 	 * supprot func/line info
 	 */
-	if (!obj->btf_ext || !kernel_supports(FEAT_BTF_FUNC))
+	if (!obj->btf_ext || !kernel_supports(obj, FEAT_BTF_FUNC))
 		return 0;
 
 	/* only attempt func info relocation if main program's func_info
@@ -6575,6 +6689,30 @@ static struct reloc_desc *find_prog_insn_relo(const struct bpf_program *prog, si
 		       sizeof(*prog->reloc_desc), cmp_relo_by_insn_idx);
 }
 
+static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_program *subprog)
+{
+	int new_cnt = main_prog->nr_reloc + subprog->nr_reloc;
+	struct reloc_desc *relos;
+	int i;
+
+	if (main_prog == subprog)
+		return 0;
+	relos = libbpf_reallocarray(main_prog->reloc_desc, new_cnt, sizeof(*relos));
+	if (!relos)
+		return -ENOMEM;
+	memcpy(relos + main_prog->nr_reloc, subprog->reloc_desc,
+	       sizeof(*relos) * subprog->nr_reloc);
+
+	for (i = main_prog->nr_reloc; i < new_cnt; i++)
+		relos[i].insn_idx += subprog->sub_insn_off;
+	/* After insn_idx adjustment the 'relos' array is still sorted
+	 * by insn_idx and doesn't break bsearch.
+	 */
+	main_prog->reloc_desc = relos;
+	main_prog->nr_reloc = new_cnt;
+	return 0;
+}
+
 static int
 bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
 		       struct bpf_program *prog)
@@ -6595,6 +6733,11 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
 			continue;
 
 		relo = find_prog_insn_relo(prog, insn_idx);
+		if (relo && relo->type == RELO_EXTERN_FUNC)
+			/* kfunc relocations will be handled later
+			 * in bpf_object__relocate_data()
+			 */
+			continue;
 		if (relo && relo->type != RELO_CALL && relo->type != RELO_SUBPROG_ADDR) {
 			pr_warn("prog '%s': unexpected relo for insn #%zu, type %d\n",
 				prog->name, insn_idx, relo->type);
@@ -6669,6 +6812,10 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
 			pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n",
 				 main_prog->name, subprog->insns_cnt, subprog->name);
 
+			/* The subprog insns are now appended. Append its relos too. */
+			err = append_subprog_relos(main_prog, subprog);
+			if (err)
+				return err;
 			err = bpf_object__reloc_code(obj, main_prog, subprog);
 			if (err)
 				return err;
@@ -6798,11 +6945,25 @@ bpf_object__relocate_calls(struct bpf_object *obj, struct bpf_program *prog)
 	return 0;
 }
 
+static void
+bpf_object__free_relocs(struct bpf_object *obj)
+{
+	struct bpf_program *prog;
+	int i;
+
+	/* free up relocation descriptors */
+	for (i = 0; i < obj->nr_programs; i++) {
+		prog = &obj->programs[i];
+		zfree(&prog->reloc_desc);
+		prog->nr_reloc = 0;
+	}
+}
+
 static int
 bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 {
 	struct bpf_program *prog;
-	size_t i;
+	size_t i, j;
 	int err;
 
 	if (obj->btf_ext) {
@@ -6813,23 +6974,32 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 			return err;
 		}
 	}
-	/* relocate data references first for all programs and sub-programs,
-	 * as they don't change relative to code locations, so subsequent
-	 * subprogram processing won't need to re-calculate any of them
+
+	/* Before relocating calls pre-process relocations and mark
+	 * few ld_imm64 instructions that points to subprogs.
+	 * Otherwise bpf_object__reloc_code() later would have to consider
+	 * all ld_imm64 insns as relocation candidates. That would
+	 * reduce relocation speed, since amount of find_prog_insn_relo()
+	 * would increase and most of them will fail to find a relo.
 	 */
 	for (i = 0; i < obj->nr_programs; i++) {
 		prog = &obj->programs[i];
-		err = bpf_object__relocate_data(obj, prog);
-		if (err) {
-			pr_warn("prog '%s': failed to relocate data references: %d\n",
-				prog->name, err);
-			return err;
+		for (j = 0; j < prog->nr_reloc; j++) {
+			struct reloc_desc *relo = &prog->reloc_desc[j];
+			struct bpf_insn *insn = &prog->insns[relo->insn_idx];
+
+			/* mark the insn, so it's recognized by insn_is_pseudo_func() */
+			if (relo->type == RELO_SUBPROG_ADDR)
+				insn[0].src_reg = BPF_PSEUDO_FUNC;
 		}
 	}
-	/* now relocate subprogram calls and append used subprograms to main
+
+	/* relocate subprogram calls and append used subprograms to main
 	 * programs; each copy of subprogram code needs to be relocated
 	 * differently for each main program, because its code location might
-	 * have changed
+	 * have changed.
+	 * Append subprog relos to main programs to allow data relos to be
+	 * processed after text is completely relocated.
 	 */
 	for (i = 0; i < obj->nr_programs; i++) {
 		prog = &obj->programs[i];
@@ -6846,12 +7016,20 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 			return err;
 		}
 	}
-	/* free up relocation descriptors */
+	/* Process data relos for main programs */
 	for (i = 0; i < obj->nr_programs; i++) {
 		prog = &obj->programs[i];
-		zfree(&prog->reloc_desc);
-		prog->nr_reloc = 0;
+		if (prog_is_subprog(obj, prog))
+			continue;
+		err = bpf_object__relocate_data(obj, prog);
+		if (err) {
+			pr_warn("prog '%s': failed to relocate data references: %d\n",
+				prog->name, err);
+			return err;
+		}
 	}
+	if (!obj->gen_loader)
+		bpf_object__free_relocs(obj);
 	return 0;
 }
 
@@ -7040,6 +7218,9 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program
 	enum bpf_func_id func_id;
 	int i;
 
+	if (obj->gen_loader)
+		return 0;
+
 	for (i = 0; i < prog->insns_cnt; i++, insn++) {
 		if (!insn_is_helper_call(insn, &func_id))
 			continue;
@@ -7051,12 +7232,12 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program
 		switch (func_id) {
 		case BPF_FUNC_probe_read_kernel:
 		case BPF_FUNC_probe_read_user:
-			if (!kernel_supports(FEAT_PROBE_READ_KERN))
+			if (!kernel_supports(obj, FEAT_PROBE_READ_KERN))
 				insn->imm = BPF_FUNC_probe_read;
 			break;
 		case BPF_FUNC_probe_read_kernel_str:
 		case BPF_FUNC_probe_read_user_str:
-			if (!kernel_supports(FEAT_PROBE_READ_KERN))
+			if (!kernel_supports(obj, FEAT_PROBE_READ_KERN))
 				insn->imm = BPF_FUNC_probe_read_str;
 			break;
 		default:
@@ -7091,12 +7272,12 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 
 	load_attr.prog_type = prog->type;
 	/* old kernels might not support specifying expected_attach_type */
-	if (!kernel_supports(FEAT_EXP_ATTACH_TYPE) && prog->sec_def &&
+	if (!kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE) && prog->sec_def &&
 	    prog->sec_def->is_exp_attach_type_optional)
 		load_attr.expected_attach_type = 0;
 	else
 		load_attr.expected_attach_type = prog->expected_attach_type;
-	if (kernel_supports(FEAT_PROG_NAME))
+	if (kernel_supports(prog->obj, FEAT_PROG_NAME))
 		load_attr.name = prog->name;
 	load_attr.insns = insns;
 	load_attr.insn_cnt = insns_cnt;
@@ -7112,7 +7293,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 
 	/* specify func_info/line_info only if kernel supports them */
 	btf_fd = bpf_object__btf_fd(prog->obj);
-	if (btf_fd >= 0 && kernel_supports(FEAT_BTF_FUNC)) {
+	if (btf_fd >= 0 && kernel_supports(prog->obj, FEAT_BTF_FUNC)) {
 		load_attr.prog_btf_fd = btf_fd;
 		load_attr.func_info = prog->func_info;
 		load_attr.func_info_rec_size = prog->func_info_rec_size;
@@ -7124,6 +7305,12 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	load_attr.log_level = prog->log_level;
 	load_attr.prog_flags = prog->prog_flags;
 
+	if (prog->obj->gen_loader) {
+		bpf_gen__prog_load(prog->obj->gen_loader, &load_attr,
+				   prog - prog->obj->programs);
+		*pfd = -1;
+		return 0;
+	}
 retry_load:
 	if (log_buf_size) {
 		log_buf = malloc(log_buf_size);
@@ -7142,7 +7329,7 @@ retry_load:
 			pr_debug("verifier log:\n%s", log_buf);
 
 		if (prog->obj->rodata_map_idx >= 0 &&
-		    kernel_supports(FEAT_PROG_BIND_MAP)) {
+		    kernel_supports(prog->obj, FEAT_PROG_BIND_MAP)) {
 			struct bpf_map *rodata_map =
 				&prog->obj->maps[prog->obj->rodata_map_idx];
 
@@ -7201,6 +7388,38 @@ out:
 	return ret;
 }
 
+static int bpf_program__record_externs(struct bpf_program *prog)
+{
+	struct bpf_object *obj = prog->obj;
+	int i;
+
+	for (i = 0; i < prog->nr_reloc; i++) {
+		struct reloc_desc *relo = &prog->reloc_desc[i];
+		struct extern_desc *ext = &obj->externs[relo->sym_off];
+
+		switch (relo->type) {
+		case RELO_EXTERN_VAR:
+			if (ext->type != EXT_KSYM)
+				continue;
+			if (!ext->ksym.type_id) {
+				pr_warn("typeless ksym %s is not supported yet\n",
+					ext->name);
+				return -ENOTSUP;
+			}
+			bpf_gen__record_extern(obj->gen_loader, ext->name, BTF_KIND_VAR,
+					       relo->insn_idx);
+			break;
+		case RELO_EXTERN_FUNC:
+			bpf_gen__record_extern(obj->gen_loader, ext->name, BTF_KIND_FUNC,
+					       relo->insn_idx);
+			break;
+		default:
+			continue;
+		}
+	}
+	return 0;
+}
+
 static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id);
 
 int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
@@ -7209,7 +7428,7 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 
 	if (prog->obj->loaded) {
 		pr_warn("prog '%s': can't load after object was loaded\n", prog->name);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if ((prog->type == BPF_PROG_TYPE_TRACING ||
@@ -7219,7 +7438,7 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 
 		err = libbpf_find_attach_btf_id(prog, &btf_obj_fd, &btf_type_id);
 		if (err)
-			return err;
+			return libbpf_err(err);
 
 		prog->attach_btf_obj_fd = btf_obj_fd;
 		prog->attach_btf_id = btf_type_id;
@@ -7229,13 +7448,13 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 		if (prog->preprocessor) {
 			pr_warn("Internal error: can't load program '%s'\n",
 				prog->name);
-			return -LIBBPF_ERRNO__INTERNAL;
+			return libbpf_err(-LIBBPF_ERRNO__INTERNAL);
 		}
 
 		prog->instances.fds = malloc(sizeof(int));
 		if (!prog->instances.fds) {
 			pr_warn("Not enough memory for BPF fds\n");
-			return -ENOMEM;
+			return libbpf_err(-ENOMEM);
 		}
 		prog->instances.nr = 1;
 		prog->instances.fds[0] = -1;
@@ -7246,6 +7465,8 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 			pr_warn("prog '%s': inconsistent nr(%d) != 1\n",
 				prog->name, prog->instances.nr);
 		}
+		if (prog->obj->gen_loader)
+			bpf_program__record_externs(prog);
 		err = load_program(prog, prog->insns, prog->insns_cnt,
 				   license, kern_ver, &fd);
 		if (!err)
@@ -7292,7 +7513,7 @@ out:
 		pr_warn("failed to load program '%s'\n", prog->name);
 	zfree(&prog->insns);
 	prog->insns_cnt = 0;
-	return err;
+	return libbpf_err(err);
 }
 
 static int
@@ -7322,6 +7543,8 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level)
 		if (err)
 			return err;
 	}
+	if (obj->gen_loader)
+		bpf_object__free_relocs(obj);
 	return 0;
 }
 
@@ -7423,7 +7646,7 @@ __bpf_object__open_xattr(struct bpf_object_open_attr *attr, int flags)
 
 struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr)
 {
-	return __bpf_object__open_xattr(attr, 0);
+	return libbpf_ptr(__bpf_object__open_xattr(attr, 0));
 }
 
 struct bpf_object *bpf_object__open(const char *path)
@@ -7433,18 +7656,18 @@ struct bpf_object *bpf_object__open(const char *path)
 		.prog_type	= BPF_PROG_TYPE_UNSPEC,
 	};
 
-	return bpf_object__open_xattr(&attr);
+	return libbpf_ptr(__bpf_object__open_xattr(&attr, 0));
 }
 
 struct bpf_object *
 bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts)
 {
 	if (!path)
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 
 	pr_debug("loading %s\n", path);
 
-	return __bpf_object__open(path, NULL, 0, opts);
+	return libbpf_ptr(__bpf_object__open(path, NULL, 0, opts));
 }
 
 struct bpf_object *
@@ -7452,9 +7675,9 @@ bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz,
 		     const struct bpf_object_open_opts *opts)
 {
 	if (!obj_buf || obj_buf_sz == 0)
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 
-	return __bpf_object__open(NULL, obj_buf, obj_buf_sz, opts);
+	return libbpf_ptr(__bpf_object__open(NULL, obj_buf, obj_buf_sz, opts));
 }
 
 struct bpf_object *
@@ -7469,9 +7692,9 @@ bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz,
 
 	/* returning NULL is wrong, but backwards-compatible */
 	if (!obj_buf || obj_buf_sz == 0)
-		return NULL;
+		return errno = EINVAL, NULL;
 
-	return bpf_object__open_mem(obj_buf, obj_buf_sz, &opts);
+	return libbpf_ptr(__bpf_object__open(NULL, obj_buf, obj_buf_sz, &opts));
 }
 
 int bpf_object__unload(struct bpf_object *obj)
@@ -7479,7 +7702,7 @@ int bpf_object__unload(struct bpf_object *obj)
 	size_t i;
 
 	if (!obj)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	for (i = 0; i < obj->nr_maps; i++) {
 		zclose(obj->maps[i].fd);
@@ -7500,11 +7723,11 @@ static int bpf_object__sanitize_maps(struct bpf_object *obj)
 	bpf_object__for_each_map(m, obj) {
 		if (!bpf_map__is_internal(m))
 			continue;
-		if (!kernel_supports(FEAT_GLOBAL_DATA)) {
+		if (!kernel_supports(obj, FEAT_GLOBAL_DATA)) {
 			pr_warn("kernel doesn't support global data\n");
 			return -ENOTSUP;
 		}
-		if (!kernel_supports(FEAT_ARRAY_MMAP))
+		if (!kernel_supports(obj, FEAT_ARRAY_MMAP))
 			m->def.map_flags ^= BPF_F_MMAPABLE;
 	}
 
@@ -7702,6 +7925,12 @@ static int bpf_object__resolve_ksyms_btf_id(struct bpf_object *obj)
 		if (ext->type != EXT_KSYM || !ext->ksym.type_id)
 			continue;
 
+		if (obj->gen_loader) {
+			ext->is_set = true;
+			ext->ksym.kernel_btf_obj_fd = 0;
+			ext->ksym.kernel_btf_id = 0;
+			continue;
+		}
 		t = btf__type_by_id(obj->btf, ext->btf_id);
 		if (btf_is_var(t))
 			err = bpf_object__resolve_ksym_var_btf_id(obj, ext);
@@ -7806,16 +8035,19 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 	int err, i;
 
 	if (!attr)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	obj = attr->obj;
 	if (!obj)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (obj->loaded) {
 		pr_warn("object '%s': load can't be attempted twice\n", obj->name);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
+	if (obj->gen_loader)
+		bpf_gen__init(obj->gen_loader, attr->log_level);
+
 	err = bpf_object__probe_loading(obj);
 	err = err ? : bpf_object__load_vmlinux_btf(obj, false);
 	err = err ? : bpf_object__resolve_externs(obj, obj->kconfig);
@@ -7826,6 +8058,15 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 	err = err ? : bpf_object__relocate(obj, attr->target_btf_path);
 	err = err ? : bpf_object__load_progs(obj, attr->log_level);
 
+	if (obj->gen_loader) {
+		/* reset FDs */
+		btf__set_fd(obj->btf, -1);
+		for (i = 0; i < obj->nr_maps; i++)
+			obj->maps[i].fd = -1;
+		if (!err)
+			err = bpf_gen__finish(obj->gen_loader);
+	}
+
 	/* clean up module BTFs */
 	for (i = 0; i < obj->btf_module_cnt; i++) {
 		close(obj->btf_modules[i].fd);
@@ -7852,7 +8093,7 @@ out:
 
 	bpf_object__unload(obj);
 	pr_warn("failed to load object '%s'\n", obj->path);
-	return err;
+	return libbpf_err(err);
 }
 
 int bpf_object__load(struct bpf_object *obj)
@@ -7924,28 +8165,28 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
 
 	err = make_parent_dir(path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	err = check_path(path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	if (prog == NULL) {
 		pr_warn("invalid program pointer\n");
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (instance < 0 || instance >= prog->instances.nr) {
 		pr_warn("invalid prog instance %d of prog %s (max %d)\n",
 			instance, prog->name, prog->instances.nr);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (bpf_obj_pin(prog->instances.fds[instance], path)) {
 		err = -errno;
 		cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
 		pr_warn("failed to pin program: %s\n", cp);
-		return err;
+		return libbpf_err(err);
 	}
 	pr_debug("pinned program '%s'\n", path);
 
@@ -7959,22 +8200,23 @@ int bpf_program__unpin_instance(struct bpf_program *prog, const char *path,
 
 	err = check_path(path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	if (prog == NULL) {
 		pr_warn("invalid program pointer\n");
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (instance < 0 || instance >= prog->instances.nr) {
 		pr_warn("invalid prog instance %d of prog %s (max %d)\n",
 			instance, prog->name, prog->instances.nr);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	err = unlink(path);
 	if (err != 0)
-		return -errno;
+		return libbpf_err(-errno);
+
 	pr_debug("unpinned program '%s'\n", path);
 
 	return 0;
@@ -7986,20 +8228,20 @@ int bpf_program__pin(struct bpf_program *prog, const char *path)
 
 	err = make_parent_dir(path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	err = check_path(path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	if (prog == NULL) {
 		pr_warn("invalid program pointer\n");
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (prog->instances.nr <= 0) {
 		pr_warn("no instances of prog %s to pin\n", prog->name);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (prog->instances.nr == 1) {
@@ -8043,7 +8285,7 @@ err_unpin:
 
 	rmdir(path);
 
-	return err;
+	return libbpf_err(err);
 }
 
 int bpf_program__unpin(struct bpf_program *prog, const char *path)
@@ -8052,16 +8294,16 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path)
 
 	err = check_path(path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	if (prog == NULL) {
 		pr_warn("invalid program pointer\n");
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (prog->instances.nr <= 0) {
 		pr_warn("no instances of prog %s to pin\n", prog->name);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (prog->instances.nr == 1) {
@@ -8075,9 +8317,9 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path)
 
 		len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
 		if (len < 0)
-			return -EINVAL;
+			return libbpf_err(-EINVAL);
 		else if (len >= PATH_MAX)
-			return -ENAMETOOLONG;
+			return libbpf_err(-ENAMETOOLONG);
 
 		err = bpf_program__unpin_instance(prog, buf, i);
 		if (err)
@@ -8086,7 +8328,7 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path)
 
 	err = rmdir(path);
 	if (err)
-		return -errno;
+		return libbpf_err(-errno);
 
 	return 0;
 }
@@ -8098,14 +8340,14 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
 
 	if (map == NULL) {
 		pr_warn("invalid map pointer\n");
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (map->pin_path) {
 		if (path && strcmp(path, map->pin_path)) {
 			pr_warn("map '%s' already has pin path '%s' different from '%s'\n",
 				bpf_map__name(map), map->pin_path, path);
-			return -EINVAL;
+			return libbpf_err(-EINVAL);
 		} else if (map->pinned) {
 			pr_debug("map '%s' already pinned at '%s'; not re-pinning\n",
 				 bpf_map__name(map), map->pin_path);
@@ -8115,10 +8357,10 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
 		if (!path) {
 			pr_warn("missing a path to pin map '%s' at\n",
 				bpf_map__name(map));
-			return -EINVAL;
+			return libbpf_err(-EINVAL);
 		} else if (map->pinned) {
 			pr_warn("map '%s' already pinned\n", bpf_map__name(map));
-			return -EEXIST;
+			return libbpf_err(-EEXIST);
 		}
 
 		map->pin_path = strdup(path);
@@ -8130,11 +8372,11 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
 
 	err = make_parent_dir(map->pin_path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	err = check_path(map->pin_path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	if (bpf_obj_pin(map->fd, map->pin_path)) {
 		err = -errno;
@@ -8149,7 +8391,7 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
 out_err:
 	cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg));
 	pr_warn("failed to pin map: %s\n", cp);
-	return err;
+	return libbpf_err(err);
 }
 
 int bpf_map__unpin(struct bpf_map *map, const char *path)
@@ -8158,29 +8400,29 @@ int bpf_map__unpin(struct bpf_map *map, const char *path)
 
 	if (map == NULL) {
 		pr_warn("invalid map pointer\n");
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	if (map->pin_path) {
 		if (path && strcmp(path, map->pin_path)) {
 			pr_warn("map '%s' already has pin path '%s' different from '%s'\n",
 				bpf_map__name(map), map->pin_path, path);
-			return -EINVAL;
+			return libbpf_err(-EINVAL);
 		}
 		path = map->pin_path;
 	} else if (!path) {
 		pr_warn("no path to unpin map '%s' from\n",
 			bpf_map__name(map));
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	err = check_path(path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	err = unlink(path);
 	if (err != 0)
-		return -errno;
+		return libbpf_err(-errno);
 
 	map->pinned = false;
 	pr_debug("unpinned map '%s' from '%s'\n", bpf_map__name(map), path);
@@ -8195,7 +8437,7 @@ int bpf_map__set_pin_path(struct bpf_map *map, const char *path)
 	if (path) {
 		new = strdup(path);
 		if (!new)
-			return -errno;
+			return libbpf_err(-errno);
 	}
 
 	free(map->pin_path);
@@ -8229,11 +8471,11 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path)
 	int err;
 
 	if (!obj)
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 
 	if (!obj->loaded) {
 		pr_warn("object not yet loaded; load it first\n");
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 	}
 
 	bpf_object__for_each_map(map, obj) {
@@ -8273,7 +8515,7 @@ err_unpin_maps:
 		bpf_map__unpin(map, NULL);
 	}
 
-	return err;
+	return libbpf_err(err);
 }
 
 int bpf_object__unpin_maps(struct bpf_object *obj, const char *path)
@@ -8282,7 +8524,7 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path)
 	int err;
 
 	if (!obj)
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 
 	bpf_object__for_each_map(map, obj) {
 		char *pin_path = NULL;
@@ -8294,9 +8536,9 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path)
 			len = snprintf(buf, PATH_MAX, "%s/%s", path,
 				       bpf_map__name(map));
 			if (len < 0)
-				return -EINVAL;
+				return libbpf_err(-EINVAL);
 			else if (len >= PATH_MAX)
-				return -ENAMETOOLONG;
+				return libbpf_err(-ENAMETOOLONG);
 			sanitize_pin_path(buf);
 			pin_path = buf;
 		} else if (!map->pin_path) {
@@ -8305,7 +8547,7 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path)
 
 		err = bpf_map__unpin(map, pin_path);
 		if (err)
-			return err;
+			return libbpf_err(err);
 	}
 
 	return 0;
@@ -8317,11 +8559,11 @@ int bpf_object__pin_programs(struct bpf_object *obj, const char *path)
 	int err;
 
 	if (!obj)
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 
 	if (!obj->loaded) {
 		pr_warn("object not yet loaded; load it first\n");
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 	}
 
 	bpf_object__for_each_program(prog, obj) {
@@ -8360,7 +8602,7 @@ err_unpin_programs:
 		bpf_program__unpin(prog, buf);
 	}
 
-	return err;
+	return libbpf_err(err);
 }
 
 int bpf_object__unpin_programs(struct bpf_object *obj, const char *path)
@@ -8369,7 +8611,7 @@ int bpf_object__unpin_programs(struct bpf_object *obj, const char *path)
 	int err;
 
 	if (!obj)
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 
 	bpf_object__for_each_program(prog, obj) {
 		char buf[PATH_MAX];
@@ -8378,13 +8620,13 @@ int bpf_object__unpin_programs(struct bpf_object *obj, const char *path)
 		len = snprintf(buf, PATH_MAX, "%s/%s", path,
 			       prog->pin_name);
 		if (len < 0)
-			return -EINVAL;
+			return libbpf_err(-EINVAL);
 		else if (len >= PATH_MAX)
-			return -ENAMETOOLONG;
+			return libbpf_err(-ENAMETOOLONG);
 
 		err = bpf_program__unpin(prog, buf);
 		if (err)
-			return err;
+			return libbpf_err(err);
 	}
 
 	return 0;
@@ -8396,12 +8638,12 @@ int bpf_object__pin(struct bpf_object *obj, const char *path)
 
 	err = bpf_object__pin_maps(obj, path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	err = bpf_object__pin_programs(obj, path);
 	if (err) {
 		bpf_object__unpin_maps(obj, path);
-		return err;
+		return libbpf_err(err);
 	}
 
 	return 0;
@@ -8451,6 +8693,7 @@ void bpf_object__close(struct bpf_object *obj)
 	if (obj->clear_priv)
 		obj->clear_priv(obj, obj->priv);
 
+	bpf_gen__free(obj->gen_loader);
 	bpf_object__elf_finish(obj);
 	bpf_object__unload(obj);
 	btf__free(obj->btf);
@@ -8497,7 +8740,7 @@ bpf_object__next(struct bpf_object *prev)
 
 const char *bpf_object__name(const struct bpf_object *obj)
 {
-	return obj ? obj->name : ERR_PTR(-EINVAL);
+	return obj ? obj->name : libbpf_err_ptr(-EINVAL);
 }
 
 unsigned int bpf_object__kversion(const struct bpf_object *obj)
@@ -8518,7 +8761,7 @@ int bpf_object__btf_fd(const struct bpf_object *obj)
 int bpf_object__set_kversion(struct bpf_object *obj, __u32 kern_version)
 {
 	if (obj->loaded)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	obj->kern_version = kern_version;
 
@@ -8538,7 +8781,23 @@ int bpf_object__set_priv(struct bpf_object *obj, void *priv,
 
 void *bpf_object__priv(const struct bpf_object *obj)
 {
-	return obj ? obj->priv : ERR_PTR(-EINVAL);
+	return obj ? obj->priv : libbpf_err_ptr(-EINVAL);
+}
+
+int bpf_object__gen_loader(struct bpf_object *obj, struct gen_loader_opts *opts)
+{
+	struct bpf_gen *gen;
+
+	if (!opts)
+		return -EFAULT;
+	if (!OPTS_VALID(opts, gen_loader_opts))
+		return -EINVAL;
+	gen = calloc(sizeof(*gen), 1);
+	if (!gen)
+		return -ENOMEM;
+	gen->opts = opts;
+	obj->gen_loader = gen;
+	return 0;
 }
 
 static struct bpf_program *
@@ -8558,7 +8817,7 @@ __bpf_program__iter(const struct bpf_program *p, const struct bpf_object *obj,
 
 	if (p->obj != obj) {
 		pr_warn("error: program handler doesn't match object\n");
-		return NULL;
+		return errno = EINVAL, NULL;
 	}
 
 	idx = (p - obj->programs) + (forward ? 1 : -1);
@@ -8604,7 +8863,7 @@ int bpf_program__set_priv(struct bpf_program *prog, void *priv,
 
 void *bpf_program__priv(const struct bpf_program *prog)
 {
-	return prog ? prog->priv : ERR_PTR(-EINVAL);
+	return prog ? prog->priv : libbpf_err_ptr(-EINVAL);
 }
 
 void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex)
@@ -8631,7 +8890,7 @@ const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy)
 		title = strdup(title);
 		if (!title) {
 			pr_warn("failed to strdup program title\n");
-			return ERR_PTR(-ENOMEM);
+			return libbpf_err_ptr(-ENOMEM);
 		}
 	}
 
@@ -8646,7 +8905,7 @@ bool bpf_program__autoload(const struct bpf_program *prog)
 int bpf_program__set_autoload(struct bpf_program *prog, bool autoload)
 {
 	if (prog->obj->loaded)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	prog->load = autoload;
 	return 0;
@@ -8668,17 +8927,17 @@ int bpf_program__set_prep(struct bpf_program *prog, int nr_instances,
 	int *instances_fds;
 
 	if (nr_instances <= 0 || !prep)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (prog->instances.nr > 0 || prog->instances.fds) {
 		pr_warn("Can't set pre-processor after loading\n");
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	instances_fds = malloc(sizeof(int) * nr_instances);
 	if (!instances_fds) {
 		pr_warn("alloc memory failed for fds\n");
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 	}
 
 	/* fill all fd with -1 */
@@ -8695,19 +8954,19 @@ int bpf_program__nth_fd(const struct bpf_program *prog, int n)
 	int fd;
 
 	if (!prog)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (n >= prog->instances.nr || n < 0) {
 		pr_warn("Can't get the %dth fd from program %s: only %d instances\n",
 			n, prog->name, prog->instances.nr);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	fd = prog->instances.fds[n];
 	if (fd < 0) {
 		pr_warn("%dth instance of program '%s' is invalid\n",
 			n, prog->name);
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 	}
 
 	return fd;
@@ -8733,7 +8992,7 @@ static bool bpf_program__is_type(const struct bpf_program *prog,
 int bpf_program__set_##NAME(struct bpf_program *prog)		\
 {								\
 	if (!prog)						\
-		return -EINVAL;					\
+		return libbpf_err(-EINVAL);			\
 	bpf_program__set_type(prog, TYPE);			\
 	return 0;						\
 }								\
@@ -8823,7 +9082,10 @@ static struct bpf_link *attach_iter(const struct bpf_sec_def *sec,
 
 static const struct bpf_sec_def section_defs[] = {
 	BPF_PROG_SEC("socket",			BPF_PROG_TYPE_SOCKET_FILTER),
-	BPF_PROG_SEC("sk_reuseport",		BPF_PROG_TYPE_SK_REUSEPORT),
+	BPF_EAPROG_SEC("sk_reuseport/migrate",	BPF_PROG_TYPE_SK_REUSEPORT,
+						BPF_SK_REUSEPORT_SELECT_OR_MIGRATE),
+	BPF_EAPROG_SEC("sk_reuseport",		BPF_PROG_TYPE_SK_REUSEPORT,
+						BPF_SK_REUSEPORT_SELECT),
 	SEC_DEF("kprobe/", KPROBE,
 		.attach_fn = attach_kprobe),
 	BPF_PROG_SEC("uprobe/",			BPF_PROG_TYPE_KPROBE),
@@ -8887,6 +9149,8 @@ static const struct bpf_sec_def section_defs[] = {
 		.expected_attach_type = BPF_TRACE_ITER,
 		.is_attach_btf = true,
 		.attach_fn = attach_iter),
+	SEC_DEF("syscall", SYSCALL,
+		.is_sleepable = true),
 	BPF_EAPROG_SEC("xdp_devmap/",		BPF_PROG_TYPE_XDP,
 						BPF_XDP_DEVMAP),
 	BPF_EAPROG_SEC("xdp_cpumap/",		BPF_PROG_TYPE_XDP,
@@ -9018,7 +9282,7 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
 	char *type_names;
 
 	if (!name)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	sec_def = find_sec_def(name);
 	if (sec_def) {
@@ -9034,7 +9298,7 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
 		free(type_names);
 	}
 
-	return -ESRCH;
+	return libbpf_err(-ESRCH);
 }
 
 static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj,
@@ -9176,6 +9440,28 @@ invalid_prog:
 #define BTF_ITER_PREFIX "bpf_iter_"
 #define BTF_MAX_NAME_SIZE 128
 
+void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type,
+				const char **prefix, int *kind)
+{
+	switch (attach_type) {
+	case BPF_TRACE_RAW_TP:
+		*prefix = BTF_TRACE_PREFIX;
+		*kind = BTF_KIND_TYPEDEF;
+		break;
+	case BPF_LSM_MAC:
+		*prefix = BTF_LSM_PREFIX;
+		*kind = BTF_KIND_FUNC;
+		break;
+	case BPF_TRACE_ITER:
+		*prefix = BTF_ITER_PREFIX;
+		*kind = BTF_KIND_FUNC;
+		break;
+	default:
+		*prefix = "";
+		*kind = BTF_KIND_FUNC;
+	}
+}
+
 static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix,
 				   const char *name, __u32 kind)
 {
@@ -9196,21 +9482,11 @@ static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix,
 static inline int find_attach_btf_id(struct btf *btf, const char *name,
 				     enum bpf_attach_type attach_type)
 {
-	int err;
+	const char *prefix;
+	int kind;
 
-	if (attach_type == BPF_TRACE_RAW_TP)
-		err = find_btf_by_prefix_kind(btf, BTF_TRACE_PREFIX, name,
-					      BTF_KIND_TYPEDEF);
-	else if (attach_type == BPF_LSM_MAC)
-		err = find_btf_by_prefix_kind(btf, BTF_LSM_PREFIX, name,
-					      BTF_KIND_FUNC);
-	else if (attach_type == BPF_TRACE_ITER)
-		err = find_btf_by_prefix_kind(btf, BTF_ITER_PREFIX, name,
-					      BTF_KIND_FUNC);
-	else
-		err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC);
-
-	return err;
+	btf_get_kernel_prefix_kind(attach_type, &prefix, &kind);
+	return find_btf_by_prefix_kind(btf, prefix, name, kind);
 }
 
 int libbpf_find_vmlinux_btf_id(const char *name,
@@ -9220,9 +9496,10 @@ int libbpf_find_vmlinux_btf_id(const char *name,
 	int err;
 
 	btf = libbpf_find_kernel_btf();
-	if (IS_ERR(btf)) {
+	err = libbpf_get_error(btf);
+	if (err) {
 		pr_warn("vmlinux BTF is not found\n");
-		return -EINVAL;
+		return libbpf_err(err);
 	}
 
 	err = find_attach_btf_id(btf, name, attach_type);
@@ -9230,7 +9507,7 @@ int libbpf_find_vmlinux_btf_id(const char *name,
 		pr_warn("%s is not found in vmlinux BTF\n", name);
 
 	btf__free(btf);
-	return err;
+	return libbpf_err(err);
 }
 
 static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
@@ -9241,10 +9518,11 @@ static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
 	int err = -EINVAL;
 
 	info_linear = bpf_program__get_prog_info_linear(attach_prog_fd, 0);
-	if (IS_ERR_OR_NULL(info_linear)) {
+	err = libbpf_get_error(info_linear);
+	if (err) {
 		pr_warn("failed get_prog_info_linear for FD %d\n",
 			attach_prog_fd);
-		return -EINVAL;
+		return err;
 	}
 	info = &info_linear->info;
 	if (!info->btf_id) {
@@ -9309,7 +9587,7 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd,
 	__u32 attach_prog_fd = prog->attach_prog_fd;
 	const char *name = prog->sec_name, *attach_name;
 	const struct bpf_sec_def *sec = NULL;
-	int i, err;
+	int i, err = 0;
 
 	if (!name)
 		return -EINVAL;
@@ -9344,7 +9622,13 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd,
 	}
 
 	/* kernel/module BTF ID */
-	err = find_kernel_btf_id(prog->obj, attach_name, attach_type, btf_obj_fd, btf_type_id);
+	if (prog->obj->gen_loader) {
+		bpf_gen__record_attach_target(prog->obj->gen_loader, attach_name, attach_type);
+		*btf_obj_fd = 0;
+		*btf_type_id = 1;
+	} else {
+		err = find_kernel_btf_id(prog->obj, attach_name, attach_type, btf_obj_fd, btf_type_id);
+	}
 	if (err) {
 		pr_warn("failed to find kernel BTF type ID of '%s': %d\n", attach_name, err);
 		return err;
@@ -9359,13 +9643,13 @@ int libbpf_attach_type_by_name(const char *name,
 	int i;
 
 	if (!name)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	for (i = 0; i < ARRAY_SIZE(section_defs); i++) {
 		if (strncmp(name, section_defs[i].sec, section_defs[i].len))
 			continue;
 		if (!section_defs[i].is_attachable)
-			return -EINVAL;
+			return libbpf_err(-EINVAL);
 		*attach_type = section_defs[i].expected_attach_type;
 		return 0;
 	}
@@ -9376,17 +9660,17 @@ int libbpf_attach_type_by_name(const char *name,
 		free(type_names);
 	}
 
-	return -EINVAL;
+	return libbpf_err(-EINVAL);
 }
 
 int bpf_map__fd(const struct bpf_map *map)
 {
-	return map ? map->fd : -EINVAL;
+	return map ? map->fd : libbpf_err(-EINVAL);
 }
 
 const struct bpf_map_def *bpf_map__def(const struct bpf_map *map)
 {
-	return map ? &map->def : ERR_PTR(-EINVAL);
+	return map ? &map->def : libbpf_err_ptr(-EINVAL);
 }
 
 const char *bpf_map__name(const struct bpf_map *map)
@@ -9402,7 +9686,7 @@ enum bpf_map_type bpf_map__type(const struct bpf_map *map)
 int bpf_map__set_type(struct bpf_map *map, enum bpf_map_type type)
 {
 	if (map->fd >= 0)
-		return -EBUSY;
+		return libbpf_err(-EBUSY);
 	map->def.type = type;
 	return 0;
 }
@@ -9415,7 +9699,7 @@ __u32 bpf_map__map_flags(const struct bpf_map *map)
 int bpf_map__set_map_flags(struct bpf_map *map, __u32 flags)
 {
 	if (map->fd >= 0)
-		return -EBUSY;
+		return libbpf_err(-EBUSY);
 	map->def.map_flags = flags;
 	return 0;
 }
@@ -9428,7 +9712,7 @@ __u32 bpf_map__numa_node(const struct bpf_map *map)
 int bpf_map__set_numa_node(struct bpf_map *map, __u32 numa_node)
 {
 	if (map->fd >= 0)
-		return -EBUSY;
+		return libbpf_err(-EBUSY);
 	map->numa_node = numa_node;
 	return 0;
 }
@@ -9441,7 +9725,7 @@ __u32 bpf_map__key_size(const struct bpf_map *map)
 int bpf_map__set_key_size(struct bpf_map *map, __u32 size)
 {
 	if (map->fd >= 0)
-		return -EBUSY;
+		return libbpf_err(-EBUSY);
 	map->def.key_size = size;
 	return 0;
 }
@@ -9454,7 +9738,7 @@ __u32 bpf_map__value_size(const struct bpf_map *map)
 int bpf_map__set_value_size(struct bpf_map *map, __u32 size)
 {
 	if (map->fd >= 0)
-		return -EBUSY;
+		return libbpf_err(-EBUSY);
 	map->def.value_size = size;
 	return 0;
 }
@@ -9473,7 +9757,7 @@ int bpf_map__set_priv(struct bpf_map *map, void *priv,
 		     bpf_map_clear_priv_t clear_priv)
 {
 	if (!map)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (map->priv) {
 		if (map->clear_priv)
@@ -9487,7 +9771,7 @@ int bpf_map__set_priv(struct bpf_map *map, void *priv,
 
 void *bpf_map__priv(const struct bpf_map *map)
 {
-	return map ? map->priv : ERR_PTR(-EINVAL);
+	return map ? map->priv : libbpf_err_ptr(-EINVAL);
 }
 
 int bpf_map__set_initial_value(struct bpf_map *map,
@@ -9495,12 +9779,20 @@ int bpf_map__set_initial_value(struct bpf_map *map,
 {
 	if (!map->mmaped || map->libbpf_type == LIBBPF_MAP_KCONFIG ||
 	    size != map->def.value_size || map->fd >= 0)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	memcpy(map->mmaped, data, size);
 	return 0;
 }
 
+const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize)
+{
+	if (!map->mmaped)
+		return NULL;
+	*psize = map->def.value_size;
+	return map->mmaped;
+}
+
 bool bpf_map__is_offload_neutral(const struct bpf_map *map)
 {
 	return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
@@ -9519,7 +9811,7 @@ __u32 bpf_map__ifindex(const struct bpf_map *map)
 int bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
 {
 	if (map->fd >= 0)
-		return -EBUSY;
+		return libbpf_err(-EBUSY);
 	map->map_ifindex = ifindex;
 	return 0;
 }
@@ -9528,11 +9820,11 @@ int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd)
 {
 	if (!bpf_map_type__is_map_in_map(map->def.type)) {
 		pr_warn("error: unsupported map type\n");
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 	if (map->inner_map_fd != -1) {
 		pr_warn("error: inner_map_fd already specified\n");
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 	zfree(&map->inner_map);
 	map->inner_map_fd = fd;
@@ -9546,7 +9838,7 @@ __bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i)
 	struct bpf_map *s, *e;
 
 	if (!obj || !obj->maps)
-		return NULL;
+		return errno = EINVAL, NULL;
 
 	s = obj->maps;
 	e = obj->maps + obj->nr_maps;
@@ -9554,7 +9846,7 @@ __bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i)
 	if ((m < s) || (m >= e)) {
 		pr_warn("error in %s: map handler doesn't belong to object\n",
 			 __func__);
-		return NULL;
+		return errno = EINVAL, NULL;
 	}
 
 	idx = (m - obj->maps) + i;
@@ -9593,7 +9885,7 @@ bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name)
 		if (pos->name && !strcmp(pos->name, name))
 			return pos;
 	}
-	return NULL;
+	return errno = ENOENT, NULL;
 }
 
 int
@@ -9605,12 +9897,23 @@ bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name)
 struct bpf_map *
 bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset)
 {
-	return ERR_PTR(-ENOTSUP);
+	return libbpf_err_ptr(-ENOTSUP);
 }
 
 long libbpf_get_error(const void *ptr)
 {
-	return PTR_ERR_OR_ZERO(ptr);
+	if (!IS_ERR_OR_NULL(ptr))
+		return 0;
+
+	if (IS_ERR(ptr))
+		errno = -PTR_ERR(ptr);
+
+	/* If ptr == NULL, then errno should be already set by the failing
+	 * API, because libbpf never returns NULL on success and it now always
+	 * sets errno on error. So no extra errno handling for ptr == NULL
+	 * case.
+	 */
+	return -errno;
 }
 
 int bpf_prog_load(const char *file, enum bpf_prog_type type,
@@ -9636,16 +9939,17 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 	int err;
 
 	if (!attr)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	if (!attr->file)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	open_attr.file = attr->file;
 	open_attr.prog_type = attr->prog_type;
 
 	obj = bpf_object__open_xattr(&open_attr);
-	if (IS_ERR_OR_NULL(obj))
-		return -ENOENT;
+	err = libbpf_get_error(obj);
+	if (err)
+		return libbpf_err(-ENOENT);
 
 	bpf_object__for_each_program(prog, obj) {
 		enum bpf_attach_type attach_type = attr->expected_attach_type;
@@ -9665,7 +9969,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 			 * didn't provide a fallback type, too bad...
 			 */
 			bpf_object__close(obj);
-			return -EINVAL;
+			return libbpf_err(-EINVAL);
 		}
 
 		prog->prog_ifindex = attr->ifindex;
@@ -9683,13 +9987,13 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 	if (!first_prog) {
 		pr_warn("object file doesn't contain bpf program\n");
 		bpf_object__close(obj);
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 	}
 
 	err = bpf_object__load(obj);
 	if (err) {
 		bpf_object__close(obj);
-		return err;
+		return libbpf_err(err);
 	}
 
 	*pobj = obj;
@@ -9708,7 +10012,10 @@ struct bpf_link {
 /* Replace link's underlying BPF program with the new one */
 int bpf_link__update_program(struct bpf_link *link, struct bpf_program *prog)
 {
-	return bpf_link_update(bpf_link__fd(link), bpf_program__fd(prog), NULL);
+	int ret;
+	
+	ret = bpf_link_update(bpf_link__fd(link), bpf_program__fd(prog), NULL);
+	return libbpf_err_errno(ret);
 }
 
 /* Release "ownership" of underlying BPF resource (typically, BPF program
@@ -9741,7 +10048,7 @@ int bpf_link__destroy(struct bpf_link *link)
 		free(link->pin_path);
 	free(link);
 
-	return err;
+	return libbpf_err(err);
 }
 
 int bpf_link__fd(const struct bpf_link *link)
@@ -9756,7 +10063,7 @@ const char *bpf_link__pin_path(const struct bpf_link *link)
 
 static int bpf_link__detach_fd(struct bpf_link *link)
 {
-	return close(link->fd);
+	return libbpf_err_errno(close(link->fd));
 }
 
 struct bpf_link *bpf_link__open(const char *path)
@@ -9768,13 +10075,13 @@ struct bpf_link *bpf_link__open(const char *path)
 	if (fd < 0) {
 		fd = -errno;
 		pr_warn("failed to open link at %s: %d\n", path, fd);
-		return ERR_PTR(fd);
+		return libbpf_err_ptr(fd);
 	}
 
 	link = calloc(1, sizeof(*link));
 	if (!link) {
 		close(fd);
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 	}
 	link->detach = &bpf_link__detach_fd;
 	link->fd = fd;
@@ -9782,7 +10089,7 @@ struct bpf_link *bpf_link__open(const char *path)
 	link->pin_path = strdup(path);
 	if (!link->pin_path) {
 		bpf_link__destroy(link);
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 	}
 
 	return link;
@@ -9798,22 +10105,22 @@ int bpf_link__pin(struct bpf_link *link, const char *path)
 	int err;
 
 	if (link->pin_path)
-		return -EBUSY;
+		return libbpf_err(-EBUSY);
 	err = make_parent_dir(path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 	err = check_path(path);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	link->pin_path = strdup(path);
 	if (!link->pin_path)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 
 	if (bpf_obj_pin(link->fd, link->pin_path)) {
 		err = -errno;
 		zfree(&link->pin_path);
-		return err;
+		return libbpf_err(err);
 	}
 
 	pr_debug("link fd=%d: pinned at %s\n", link->fd, link->pin_path);
@@ -9825,11 +10132,11 @@ int bpf_link__unpin(struct bpf_link *link)
 	int err;
 
 	if (!link->pin_path)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	err = unlink(link->pin_path);
 	if (err != 0)
-		return -errno;
+		return libbpf_err_errno(err);
 
 	pr_debug("link fd=%d: unpinned from %s\n", link->fd, link->pin_path);
 	zfree(&link->pin_path);
@@ -9845,11 +10152,10 @@ static int bpf_link__detach_perf_event(struct bpf_link *link)
 		err = -errno;
 
 	close(link->fd);
-	return err;
+	return libbpf_err(err);
 }
 
-struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
-						int pfd)
+struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, int pfd)
 {
 	char errmsg[STRERR_BUFSIZE];
 	struct bpf_link *link;
@@ -9858,18 +10164,18 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
 	if (pfd < 0) {
 		pr_warn("prog '%s': invalid perf event FD %d\n",
 			prog->name, pfd);
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 	}
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
 		pr_warn("prog '%s': can't attach BPF program w/o FD (did you load it?)\n",
 			prog->name);
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 	}
 
 	link = calloc(1, sizeof(*link));
 	if (!link)
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 	link->detach = &bpf_link__detach_perf_event;
 	link->fd = pfd;
 
@@ -9881,14 +10187,14 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog,
 		if (err == -EPROTO)
 			pr_warn("prog '%s': try add PERF_SAMPLE_CALLCHAIN to or remove exclude_callchain_[kernel|user] from pfd %d\n",
 				prog->name, pfd);
-		return ERR_PTR(err);
+		return libbpf_err_ptr(err);
 	}
 	if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
 		err = -errno;
 		free(link);
 		pr_warn("prog '%s': failed to enable pfd %d: %s\n",
 			prog->name, pfd, libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
-		return ERR_PTR(err);
+		return libbpf_err_ptr(err);
 	}
 	return link;
 }
@@ -10012,16 +10318,16 @@ struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
 		pr_warn("prog '%s': failed to create %s '%s' perf event: %s\n",
 			prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
 			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
-		return ERR_PTR(pfd);
+		return libbpf_err_ptr(pfd);
 	}
 	link = bpf_program__attach_perf_event(prog, pfd);
-	if (IS_ERR(link)) {
+	err = libbpf_get_error(link);
+	if (err) {
 		close(pfd);
-		err = PTR_ERR(link);
 		pr_warn("prog '%s': failed to attach to %s '%s': %s\n",
 			prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
 			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
-		return link;
+		return libbpf_err_ptr(err);
 	}
 	return link;
 }
@@ -10054,17 +10360,17 @@ struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
 			prog->name, retprobe ? "uretprobe" : "uprobe",
 			binary_path, func_offset,
 			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
-		return ERR_PTR(pfd);
+		return libbpf_err_ptr(pfd);
 	}
 	link = bpf_program__attach_perf_event(prog, pfd);
-	if (IS_ERR(link)) {
+	err = libbpf_get_error(link);
+	if (err) {
 		close(pfd);
-		err = PTR_ERR(link);
 		pr_warn("prog '%s': failed to attach to %s '%s:0x%zx': %s\n",
 			prog->name, retprobe ? "uretprobe" : "uprobe",
 			binary_path, func_offset,
 			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
-		return link;
+		return libbpf_err_ptr(err);
 	}
 	return link;
 }
@@ -10132,16 +10438,16 @@ struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog,
 		pr_warn("prog '%s': failed to create tracepoint '%s/%s' perf event: %s\n",
 			prog->name, tp_category, tp_name,
 			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
-		return ERR_PTR(pfd);
+		return libbpf_err_ptr(pfd);
 	}
 	link = bpf_program__attach_perf_event(prog, pfd);
-	if (IS_ERR(link)) {
+	err = libbpf_get_error(link);
+	if (err) {
 		close(pfd);
-		err = PTR_ERR(link);
 		pr_warn("prog '%s': failed to attach to tracepoint '%s/%s': %s\n",
 			prog->name, tp_category, tp_name,
 			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
-		return link;
+		return libbpf_err_ptr(err);
 	}
 	return link;
 }
@@ -10154,20 +10460,19 @@ static struct bpf_link *attach_tp(const struct bpf_sec_def *sec,
 
 	sec_name = strdup(prog->sec_name);
 	if (!sec_name)
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 
 	/* extract "tp/<category>/<name>" */
 	tp_cat = sec_name + sec->len;
 	tp_name = strchr(tp_cat, '/');
 	if (!tp_name) {
-		link = ERR_PTR(-EINVAL);
-		goto out;
+		free(sec_name);
+		return libbpf_err_ptr(-EINVAL);
 	}
 	*tp_name = '\0';
 	tp_name++;
 
 	link = bpf_program__attach_tracepoint(prog, tp_cat, tp_name);
-out:
 	free(sec_name);
 	return link;
 }
@@ -10182,12 +10487,12 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
 		pr_warn("prog '%s': can't attach before loaded\n", prog->name);
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 	}
 
 	link = calloc(1, sizeof(*link));
 	if (!link)
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 	link->detach = &bpf_link__detach_fd;
 
 	pfd = bpf_raw_tracepoint_open(tp_name, prog_fd);
@@ -10196,7 +10501,7 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 		free(link);
 		pr_warn("prog '%s': failed to attach to raw tracepoint '%s': %s\n",
 			prog->name, tp_name, libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
-		return ERR_PTR(pfd);
+		return libbpf_err_ptr(pfd);
 	}
 	link->fd = pfd;
 	return link;
@@ -10220,12 +10525,12 @@ static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog)
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
 		pr_warn("prog '%s': can't attach before loaded\n", prog->name);
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 	}
 
 	link = calloc(1, sizeof(*link));
 	if (!link)
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 	link->detach = &bpf_link__detach_fd;
 
 	pfd = bpf_raw_tracepoint_open(NULL, prog_fd);
@@ -10234,7 +10539,7 @@ static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog)
 		free(link);
 		pr_warn("prog '%s': failed to attach: %s\n",
 			prog->name, libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
-		return ERR_PTR(pfd);
+		return libbpf_err_ptr(pfd);
 	}
 	link->fd = pfd;
 	return (struct bpf_link *)link;
@@ -10262,12 +10567,6 @@ static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec,
 	return bpf_program__attach_lsm(prog);
 }
 
-static struct bpf_link *attach_iter(const struct bpf_sec_def *sec,
-				    struct bpf_program *prog)
-{
-	return bpf_program__attach_iter(prog, NULL);
-}
-
 static struct bpf_link *
 bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id,
 		       const char *target_name)
@@ -10282,12 +10581,12 @@ bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id,
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
 		pr_warn("prog '%s': can't attach before loaded\n", prog->name);
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 	}
 
 	link = calloc(1, sizeof(*link));
 	if (!link)
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 	link->detach = &bpf_link__detach_fd;
 
 	attach_type = bpf_program__get_expected_attach_type(prog);
@@ -10298,7 +10597,7 @@ bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id,
 		pr_warn("prog '%s': failed to attach to %s: %s\n",
 			prog->name, target_name,
 			libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg)));
-		return ERR_PTR(link_fd);
+		return libbpf_err_ptr(link_fd);
 	}
 	link->fd = link_fd;
 	return link;
@@ -10331,19 +10630,19 @@ struct bpf_link *bpf_program__attach_freplace(struct bpf_program *prog,
 	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);
+		return libbpf_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);
+		return libbpf_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 libbpf_err_ptr(btf_id);
 
 		return bpf_program__attach_fd(prog, target_fd, btf_id, "freplace");
 	} else {
@@ -10365,7 +10664,7 @@ bpf_program__attach_iter(struct bpf_program *prog,
 	__u32 target_fd = 0;
 
 	if (!OPTS_VALID(opts, bpf_iter_attach_opts))
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 
 	link_create_opts.iter_info = OPTS_GET(opts, link_info, (void *)0);
 	link_create_opts.iter_info_len = OPTS_GET(opts, link_info_len, 0);
@@ -10373,12 +10672,12 @@ bpf_program__attach_iter(struct bpf_program *prog,
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
 		pr_warn("prog '%s': can't attach before loaded\n", prog->name);
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 	}
 
 	link = calloc(1, sizeof(*link));
 	if (!link)
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 	link->detach = &bpf_link__detach_fd;
 
 	link_fd = bpf_link_create(prog_fd, target_fd, BPF_TRACE_ITER,
@@ -10388,19 +10687,25 @@ bpf_program__attach_iter(struct bpf_program *prog,
 		free(link);
 		pr_warn("prog '%s': failed to attach to iterator: %s\n",
 			prog->name, libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg)));
-		return ERR_PTR(link_fd);
+		return libbpf_err_ptr(link_fd);
 	}
 	link->fd = link_fd;
 	return link;
 }
 
+static struct bpf_link *attach_iter(const struct bpf_sec_def *sec,
+				    struct bpf_program *prog)
+{
+	return bpf_program__attach_iter(prog, NULL);
+}
+
 struct bpf_link *bpf_program__attach(struct bpf_program *prog)
 {
 	const struct bpf_sec_def *sec_def;
 
 	sec_def = find_sec_def(prog->sec_name);
 	if (!sec_def || !sec_def->attach_fn)
-		return ERR_PTR(-ESRCH);
+		return libbpf_err_ptr(-ESRCH);
 
 	return sec_def->attach_fn(sec_def, prog);
 }
@@ -10423,11 +10728,11 @@ struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map)
 	int err;
 
 	if (!bpf_map__is_struct_ops(map) || map->fd == -1)
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 
 	link = calloc(1, sizeof(*link));
 	if (!link)
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 
 	st_ops = map->st_ops;
 	for (i = 0; i < btf_vlen(st_ops->type); i++) {
@@ -10447,7 +10752,7 @@ struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map)
 	if (err) {
 		err = -errno;
 		free(link);
-		return ERR_PTR(err);
+		return libbpf_err_ptr(err);
 	}
 
 	link->detach = bpf_link__detach_struct_ops;
@@ -10501,7 +10806,7 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
 	}
 
 	ring_buffer_write_tail(header, data_tail);
-	return ret;
+	return libbpf_err(ret);
 }
 
 struct perf_buffer;
@@ -10654,7 +10959,7 @@ struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt,
 	p.lost_cb = opts ? opts->lost_cb : NULL;
 	p.ctx = opts ? opts->ctx : NULL;
 
-	return __perf_buffer__new(map_fd, page_cnt, &p);
+	return libbpf_ptr(__perf_buffer__new(map_fd, page_cnt, &p));
 }
 
 struct perf_buffer *
@@ -10670,7 +10975,7 @@ perf_buffer__new_raw(int map_fd, size_t page_cnt,
 	p.cpus = opts->cpus;
 	p.map_keys = opts->map_keys;
 
-	return __perf_buffer__new(map_fd, page_cnt, &p);
+	return libbpf_ptr(__perf_buffer__new(map_fd, page_cnt, &p));
 }
 
 static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt,
@@ -10891,16 +11196,19 @@ int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms)
 	int i, cnt, err;
 
 	cnt = epoll_wait(pb->epoll_fd, pb->events, pb->cpu_cnt, timeout_ms);
+	if (cnt < 0)
+		return libbpf_err_errno(cnt);
+
 	for (i = 0; i < cnt; i++) {
 		struct perf_cpu_buf *cpu_buf = pb->events[i].data.ptr;
 
 		err = perf_buffer__process_records(pb, cpu_buf);
 		if (err) {
 			pr_warn("error while processing records: %d\n", err);
-			return err;
+			return libbpf_err(err);
 		}
 	}
-	return cnt < 0 ? -errno : cnt;
+	return cnt;
 }
 
 /* Return number of PERF_EVENT_ARRAY map slots set up by this perf_buffer
@@ -10921,11 +11229,11 @@ int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_idx)
 	struct perf_cpu_buf *cpu_buf;
 
 	if (buf_idx >= pb->cpu_cnt)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	cpu_buf = pb->cpu_bufs[buf_idx];
 	if (!cpu_buf)
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 
 	return cpu_buf->fd;
 }
@@ -10943,11 +11251,11 @@ int perf_buffer__consume_buffer(struct perf_buffer *pb, size_t buf_idx)
 	struct perf_cpu_buf *cpu_buf;
 
 	if (buf_idx >= pb->cpu_cnt)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	cpu_buf = pb->cpu_bufs[buf_idx];
 	if (!cpu_buf)
-		return -ENOENT;
+		return libbpf_err(-ENOENT);
 
 	return perf_buffer__process_records(pb, cpu_buf);
 }
@@ -10965,7 +11273,7 @@ int perf_buffer__consume(struct perf_buffer *pb)
 		err = perf_buffer__process_records(pb, cpu_buf);
 		if (err) {
 			pr_warn("perf_buffer: failed to process records in buffer #%d: %d\n", i, err);
-			return err;
+			return libbpf_err(err);
 		}
 	}
 	return 0;
@@ -11077,13 +11385,13 @@ bpf_program__get_prog_info_linear(int fd, __u64 arrays)
 	void *ptr;
 
 	if (arrays >> BPF_PROG_INFO_LAST_ARRAY)
-		return ERR_PTR(-EINVAL);
+		return libbpf_err_ptr(-EINVAL);
 
 	/* step 1: get array dimensions */
 	err = bpf_obj_get_info_by_fd(fd, &info, &info_len);
 	if (err) {
 		pr_debug("can't get prog info: %s", strerror(errno));
-		return ERR_PTR(-EFAULT);
+		return libbpf_err_ptr(-EFAULT);
 	}
 
 	/* step 2: calculate total size of all arrays */
@@ -11115,7 +11423,7 @@ bpf_program__get_prog_info_linear(int fd, __u64 arrays)
 	data_len = roundup(data_len, sizeof(__u64));
 	info_linear = malloc(sizeof(struct bpf_prog_info_linear) + data_len);
 	if (!info_linear)
-		return ERR_PTR(-ENOMEM);
+		return libbpf_err_ptr(-ENOMEM);
 
 	/* step 4: fill data to info_linear->info */
 	info_linear->arrays = arrays;
@@ -11147,7 +11455,7 @@ bpf_program__get_prog_info_linear(int fd, __u64 arrays)
 	if (err) {
 		pr_debug("can't get prog info: %s", strerror(errno));
 		free(info_linear);
-		return ERR_PTR(-EFAULT);
+		return libbpf_err_ptr(-EFAULT);
 	}
 
 	/* step 6: verify the data */
@@ -11226,26 +11534,26 @@ int bpf_program__set_attach_target(struct bpf_program *prog,
 	int btf_obj_fd = 0, btf_id = 0, err;
 
 	if (!prog || attach_prog_fd < 0 || !attach_func_name)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (prog->obj->loaded)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (attach_prog_fd) {
 		btf_id = libbpf_find_prog_btf_id(attach_func_name,
 						 attach_prog_fd);
 		if (btf_id < 0)
-			return btf_id;
+			return libbpf_err(btf_id);
 	} else {
 		/* load btf_vmlinux, if not yet */
 		err = bpf_object__load_vmlinux_btf(prog->obj, true);
 		if (err)
-			return err;
+			return libbpf_err(err);
 		err = find_kernel_btf_id(prog->obj, attach_func_name,
 					 prog->expected_attach_type,
 					 &btf_obj_fd, &btf_id);
 		if (err)
-			return err;
+			return libbpf_err(err);
 	}
 
 	prog->attach_btf_id = btf_id;
@@ -11344,7 +11652,7 @@ int libbpf_num_possible_cpus(void)
 
 	err = parse_cpu_mask_file(fcpu, &mask, &n);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	tmp_cpus = 0;
 	for (i = 0; i < n; i++) {
@@ -11364,7 +11672,7 @@ int bpf_object__open_skeleton(struct bpf_object_skeleton *s,
 		.object_name = s->name,
 	);
 	struct bpf_object *obj;
-	int i;
+	int i, err;
 
 	/* Attempt to preserve opts->object_name, unless overriden by user
 	 * explicitly. Overwriting object name for skeletons is discouraged,
@@ -11379,10 +11687,11 @@ int bpf_object__open_skeleton(struct bpf_object_skeleton *s,
 	}
 
 	obj = bpf_object__open_mem(s->data, s->data_sz, &skel_opts);
-	if (IS_ERR(obj)) {
-		pr_warn("failed to initialize skeleton BPF object '%s': %ld\n",
-			s->name, PTR_ERR(obj));
-		return PTR_ERR(obj);
+	err = libbpf_get_error(obj);
+	if (err) {
+		pr_warn("failed to initialize skeleton BPF object '%s': %d\n",
+			s->name, err);
+		return libbpf_err(err);
 	}
 
 	*s->obj = obj;
@@ -11395,7 +11704,7 @@ int bpf_object__open_skeleton(struct bpf_object_skeleton *s,
 		*map = bpf_object__find_map_by_name(obj, name);
 		if (!*map) {
 			pr_warn("failed to find skeleton map '%s'\n", name);
-			return -ESRCH;
+			return libbpf_err(-ESRCH);
 		}
 
 		/* externs shouldn't be pre-setup from user code */
@@ -11410,7 +11719,7 @@ int bpf_object__open_skeleton(struct bpf_object_skeleton *s,
 		*prog = bpf_object__find_program_by_name(obj, name);
 		if (!*prog) {
 			pr_warn("failed to find skeleton program '%s'\n", name);
-			return -ESRCH;
+			return libbpf_err(-ESRCH);
 		}
 	}
 
@@ -11424,7 +11733,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s)
 	err = bpf_object__load(*s->obj);
 	if (err) {
 		pr_warn("failed to load BPF skeleton '%s': %d\n", s->name, err);
-		return err;
+		return libbpf_err(err);
 	}
 
 	for (i = 0; i < s->map_cnt; i++) {
@@ -11463,7 +11772,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s)
 			*mmaped = NULL;
 			pr_warn("failed to re-mmap() map '%s': %d\n",
 				 bpf_map__name(map), err);
-			return err;
+			return libbpf_err(err);
 		}
 	}
 
@@ -11472,7 +11781,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s)
 
 int bpf_object__attach_skeleton(struct bpf_object_skeleton *s)
 {
-	int i;
+	int i, err;
 
 	for (i = 0; i < s->prog_cnt; i++) {
 		struct bpf_program *prog = *s->progs[i].prog;
@@ -11487,10 +11796,11 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s)
 			continue;
 
 		*link = sec_def->attach_fn(sec_def, prog);
-		if (IS_ERR(*link)) {
-			pr_warn("failed to auto-attach program '%s': %ld\n",
-				bpf_program__name(prog), PTR_ERR(*link));
-			return PTR_ERR(*link);
+		err = libbpf_get_error(*link);
+		if (err) {
+			pr_warn("failed to auto-attach program '%s': %d\n",
+				bpf_program__name(prog), err);
+			return libbpf_err(err);
 		}
 	}
 
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index bec4e6a6e31d..6e61342ba56c 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -18,6 +18,7 @@
 #include <linux/bpf.h>
 
 #include "libbpf_common.h"
+#include "libbpf_legacy.h"
 
 #ifdef __cplusplus
 extern "C" {
@@ -471,6 +472,7 @@ LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv,
 LIBBPF_API void *bpf_map__priv(const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map,
 					  const void *data, size_t size);
+LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize);
 LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map);
 LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path);
@@ -498,6 +500,7 @@ 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);
 
+/* XDP related API */
 struct xdp_link_info {
 	__u32 prog_id;
 	__u32 drv_prog_id;
@@ -520,6 +523,49 @@ 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);
 
+/* TC related API */
+enum bpf_tc_attach_point {
+	BPF_TC_INGRESS = 1 << 0,
+	BPF_TC_EGRESS  = 1 << 1,
+	BPF_TC_CUSTOM  = 1 << 2,
+};
+
+#define BPF_TC_PARENT(a, b) 	\
+	((((a) << 16) & 0xFFFF0000U) | ((b) & 0x0000FFFFU))
+
+enum bpf_tc_flags {
+	BPF_TC_F_REPLACE = 1 << 0,
+};
+
+struct bpf_tc_hook {
+	size_t sz;
+	int ifindex;
+	enum bpf_tc_attach_point attach_point;
+	__u32 parent;
+	size_t :0;
+};
+#define bpf_tc_hook__last_field parent
+
+struct bpf_tc_opts {
+	size_t sz;
+	int prog_fd;
+	__u32 flags;
+	__u32 prog_id;
+	__u32 handle;
+	__u32 priority;
+	size_t :0;
+};
+#define bpf_tc_opts__last_field priority
+
+LIBBPF_API int bpf_tc_hook_create(struct bpf_tc_hook *hook);
+LIBBPF_API int bpf_tc_hook_destroy(struct bpf_tc_hook *hook);
+LIBBPF_API int bpf_tc_attach(const struct bpf_tc_hook *hook,
+			     struct bpf_tc_opts *opts);
+LIBBPF_API int bpf_tc_detach(const struct bpf_tc_hook *hook,
+			     const struct bpf_tc_opts *opts);
+LIBBPF_API int bpf_tc_query(const struct bpf_tc_hook *hook,
+			    struct bpf_tc_opts *opts);
+
 /* Ring buffer APIs */
 struct ring_buffer;
 
@@ -756,6 +802,18 @@ LIBBPF_API int bpf_object__attach_skeleton(struct bpf_object_skeleton *s);
 LIBBPF_API void bpf_object__detach_skeleton(struct bpf_object_skeleton *s);
 LIBBPF_API void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s);
 
+struct gen_loader_opts {
+	size_t sz; /* size of this struct, for forward/backward compatiblity */
+	const char *data;
+	const char *insns;
+	__u32 data_sz;
+	__u32 insns_sz;
+};
+
+#define gen_loader_opts__last_field insns_sz
+LIBBPF_API int bpf_object__gen_loader(struct bpf_object *obj,
+				      struct gen_loader_opts *opts);
+
 enum libbpf_tristate {
 	TRI_NO = 0,
 	TRI_YES = 1,
@@ -768,10 +826,18 @@ struct bpf_linker_opts {
 };
 #define bpf_linker_opts__last_field sz
 
+struct bpf_linker_file_opts {
+	/* size of this struct, for forward/backward compatiblity */
+	size_t sz;
+};
+#define bpf_linker_file_opts__last_field sz
+
 struct bpf_linker;
 
 LIBBPF_API struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts *opts);
-LIBBPF_API int bpf_linker__add_file(struct bpf_linker *linker, const char *filename);
+LIBBPF_API int bpf_linker__add_file(struct bpf_linker *linker,
+				    const char *filename,
+				    const struct bpf_linker_file_opts *opts);
 LIBBPF_API int bpf_linker__finalize(struct bpf_linker *linker);
 LIBBPF_API void bpf_linker__free(struct bpf_linker *linker);
 
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index b9b29baf1df8..944c99d1ded3 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -361,4 +361,17 @@ LIBBPF_0.4.0 {
 		bpf_linker__new;
 		bpf_map__inner_map;
 		bpf_object__set_kversion;
+		bpf_tc_attach;
+		bpf_tc_detach;
+		bpf_tc_hook_create;
+		bpf_tc_hook_destroy;
+		bpf_tc_query;
 } LIBBPF_0.3.0;
+
+LIBBPF_0.5.0 {
+	global:
+		bpf_map__initial_value;
+		bpf_map_lookup_and_delete_elem_flags;
+		bpf_object__gen_loader;
+		libbpf_set_strict_mode;
+} LIBBPF_0.4.0;
diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c
index 0afb51f7a919..96f67a772a1b 100644
--- a/tools/lib/bpf/libbpf_errno.c
+++ b/tools/lib/bpf/libbpf_errno.c
@@ -12,6 +12,7 @@
 #include <string.h>
 
 #include "libbpf.h"
+#include "libbpf_internal.h"
 
 /* make sure libbpf doesn't use kernel-only integer typedefs */
 #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
@@ -39,7 +40,7 @@ static const char *libbpf_strerror_table[NR_ERRNO] = {
 int libbpf_strerror(int err, char *buf, size_t size)
 {
 	if (!buf || !size)
-		return -1;
+		return libbpf_err(-EINVAL);
 
 	err = err > 0 ? err : -err;
 
@@ -48,7 +49,7 @@ int libbpf_strerror(int err, char *buf, size_t size)
 
 		ret = strerror_r(err, buf, size);
 		buf[size - 1] = '\0';
-		return ret;
+		return libbpf_err_errno(ret);
 	}
 
 	if (err < __LIBBPF_ERRNO__END) {
@@ -62,5 +63,5 @@ int libbpf_strerror(int err, char *buf, size_t size)
 
 	snprintf(buf, size, "Unknown libbpf error %d", err);
 	buf[size - 1] = '\0';
-	return -1;
+	return libbpf_err(-ENOENT);
 }
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index acbcf6c7bdf8..016ca7cb4f8a 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -11,6 +11,9 @@
 
 #include <stdlib.h>
 #include <limits.h>
+#include <errno.h>
+#include <linux/err.h>
+#include "libbpf_legacy.h"
 
 /* make sure libbpf doesn't use kernel-only integer typedefs */
 #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
@@ -28,6 +31,12 @@
 #ifndef R_BPF_64_64
 #define R_BPF_64_64 1
 #endif
+#ifndef R_BPF_64_ABS64
+#define R_BPF_64_ABS64 2
+#endif
+#ifndef R_BPF_64_ABS32
+#define R_BPF_64_ABS32 3
+#endif
 #ifndef R_BPF_64_32
 #define R_BPF_64_32 10
 #endif
@@ -263,6 +272,8 @@ int bpf_object__section_size(const struct bpf_object *obj, const char *name,
 int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
 				__u32 *off);
 struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf);
+void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type,
+				const char **prefix, int *kind);
 
 struct btf_ext_info {
 	/*
@@ -433,4 +444,54 @@ int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ct
 int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx);
 int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void *ctx);
 
+extern enum libbpf_strict_mode libbpf_mode;
+
+/* handle direct returned errors */
+static inline int libbpf_err(int ret)
+{
+	if (ret < 0)
+		errno = -ret;
+	return ret;
+}
+
+/* handle errno-based (e.g., syscall or libc) errors according to libbpf's
+ * strict mode settings
+ */
+static inline int libbpf_err_errno(int ret)
+{
+	if (libbpf_mode & LIBBPF_STRICT_DIRECT_ERRS)
+		/* errno is already assumed to be set on error */
+		return ret < 0 ? -errno : ret;
+
+	/* legacy: on error return -1 directly and don't touch errno */
+	return ret;
+}
+
+/* handle error for pointer-returning APIs, err is assumed to be < 0 always */
+static inline void *libbpf_err_ptr(int err)
+{
+	/* set errno on error, this doesn't break anything */
+	errno = -err;
+
+	if (libbpf_mode & LIBBPF_STRICT_CLEAN_PTRS)
+		return NULL;
+
+	/* legacy: encode err as ptr */
+	return ERR_PTR(err);
+}
+
+/* handle pointer-returning APIs' error handling */
+static inline void *libbpf_ptr(void *ret)
+{
+	/* set errno on error, this doesn't break anything */
+	if (IS_ERR(ret))
+		errno = -PTR_ERR(ret);
+
+	if (libbpf_mode & LIBBPF_STRICT_CLEAN_PTRS)
+		return IS_ERR(ret) ? NULL : ret;
+
+	/* legacy: pass-through original pointer */
+	return ret;
+}
+
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */
diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h
new file mode 100644
index 000000000000..df0d03dcffab
--- /dev/null
+++ b/tools/lib/bpf/libbpf_legacy.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+
+/*
+ * Libbpf legacy APIs (either discouraged or deprecated, as mentioned in [0])
+ *
+ *   [0] https://docs.google.com/document/d/1UyjTZuPFWiPFyKk1tV5an11_iaRuec6U-ZESZ54nNTY
+ *
+ * Copyright (C) 2021 Facebook
+ */
+#ifndef __LIBBPF_LEGACY_BPF_H
+#define __LIBBPF_LEGACY_BPF_H
+
+#include <linux/bpf.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+#include "libbpf_common.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+enum libbpf_strict_mode {
+	/* Turn on all supported strict features of libbpf to simulate libbpf
+	 * v1.0 behavior.
+	 * This will be the default behavior in libbpf v1.0.
+	 */
+	LIBBPF_STRICT_ALL = 0xffffffff,
+
+	/*
+	 * Disable any libbpf 1.0 behaviors. This is the default before libbpf
+	 * v1.0. It won't be supported anymore in v1.0, please update your
+	 * code so that it handles LIBBPF_STRICT_ALL mode before libbpf v1.0.
+	 */
+	LIBBPF_STRICT_NONE = 0x00,
+	/*
+	 * Return NULL pointers on error, not ERR_PTR(err).
+	 * Additionally, libbpf also always sets errno to corresponding Exx
+	 * (positive) error code.
+	 */
+	LIBBPF_STRICT_CLEAN_PTRS = 0x01,
+	/*
+	 * Return actual error codes from low-level APIs directly, not just -1.
+	 * Additionally, libbpf also always sets errno to corresponding Exx
+	 * (positive) error code.
+	 */
+	LIBBPF_STRICT_DIRECT_ERRS = 0x02,
+
+	__LIBBPF_STRICT_LAST,
+};
+
+LIBBPF_API int libbpf_set_strict_mode(enum libbpf_strict_mode mode);
+
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
+#endif /* __LIBBPF_LEGACY_BPF_H */
diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
index 9de084b1c699..10911a8cad0f 100644
--- a/tools/lib/bpf/linker.c
+++ b/tools/lib/bpf/linker.c
@@ -158,7 +158,9 @@ struct bpf_linker {
 
 static int init_output_elf(struct bpf_linker *linker, const char *file);
 
-static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, struct src_obj *obj);
+static int linker_load_obj_file(struct bpf_linker *linker, const char *filename,
+				const struct bpf_linker_file_opts *opts,
+				struct src_obj *obj);
 static int linker_sanity_check_elf(struct src_obj *obj);
 static int linker_sanity_check_elf_symtab(struct src_obj *obj, struct src_sec *sec);
 static int linker_sanity_check_elf_relos(struct src_obj *obj, struct src_sec *sec);
@@ -218,16 +220,16 @@ struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts
 	int err;
 
 	if (!OPTS_VALID(opts, bpf_linker_opts))
-		return NULL;
+		return errno = EINVAL, NULL;
 
 	if (elf_version(EV_CURRENT) == EV_NONE) {
 		pr_warn_elf("libelf initialization failed");
-		return NULL;
+		return errno = EINVAL, NULL;
 	}
 
 	linker = calloc(1, sizeof(*linker));
 	if (!linker)
-		return NULL;
+		return errno = ENOMEM, NULL;
 
 	linker->fd = -1;
 
@@ -239,7 +241,7 @@ struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts
 
 err_out:
 	bpf_linker__free(linker);
-	return NULL;
+	return errno = -err, NULL;
 }
 
 static struct dst_sec *add_dst_sec(struct bpf_linker *linker, const char *sec_name)
@@ -435,15 +437,19 @@ static int init_output_elf(struct bpf_linker *linker, const char *file)
 	return 0;
 }
 
-int bpf_linker__add_file(struct bpf_linker *linker, const char *filename)
+int bpf_linker__add_file(struct bpf_linker *linker, const char *filename,
+			 const struct bpf_linker_file_opts *opts)
 {
 	struct src_obj obj = {};
 	int err = 0;
 
+	if (!OPTS_VALID(opts, bpf_linker_file_opts))
+		return libbpf_err(-EINVAL);
+
 	if (!linker->elf)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
-	err = err ?: linker_load_obj_file(linker, filename, &obj);
+	err = err ?: linker_load_obj_file(linker, filename, opts, &obj);
 	err = err ?: linker_append_sec_data(linker, &obj);
 	err = err ?: linker_append_elf_syms(linker, &obj);
 	err = err ?: linker_append_elf_relos(linker, &obj);
@@ -461,7 +467,7 @@ int bpf_linker__add_file(struct bpf_linker *linker, const char *filename)
 	if (obj.fd >= 0)
 		close(obj.fd);
 
-	return err;
+	return libbpf_err(err);
 }
 
 static bool is_dwarf_sec_name(const char *name)
@@ -529,7 +535,9 @@ static struct src_sec *add_src_sec(struct src_obj *obj, const char *sec_name)
 	return sec;
 }
 
-static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, struct src_obj *obj)
+static int linker_load_obj_file(struct bpf_linker *linker, const char *filename,
+				const struct bpf_linker_file_opts *opts,
+				struct src_obj *obj)
 {
 #if __BYTE_ORDER == __LITTLE_ENDIAN
 	const int host_endianness = ELFDATA2LSB;
@@ -884,7 +892,8 @@ static int linker_sanity_check_elf_relos(struct src_obj *obj, struct src_sec *se
 		size_t sym_idx = ELF64_R_SYM(relo->r_info);
 		size_t sym_type = ELF64_R_TYPE(relo->r_info);
 
-		if (sym_type != R_BPF_64_64 && sym_type != R_BPF_64_32) {
+		if (sym_type != R_BPF_64_64 && sym_type != R_BPF_64_32 &&
+		    sym_type != R_BPF_64_ABS64 && sym_type != R_BPF_64_ABS32) {
 			pr_warn("ELF relo #%d in section #%zu has unexpected type %zu in %s\n",
 				i, sec->sec_idx, sym_type, obj->filename);
 			return -EINVAL;
@@ -1780,7 +1789,7 @@ static void sym_update_visibility(Elf64_Sym *sym, int sym_vis)
 	/* libelf doesn't provide setters for ST_VISIBILITY,
 	 * but it is stored in the lower 2 bits of st_other
 	 */
-	sym->st_other &= 0x03;
+	sym->st_other &= ~0x03;
 	sym->st_other |= sym_vis;
 }
 
@@ -2539,11 +2548,11 @@ int bpf_linker__finalize(struct bpf_linker *linker)
 	int err, i;
 
 	if (!linker->elf)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	err = finalize_btf(linker);
 	if (err)
-		return err;
+		return libbpf_err(err);
 
 	/* Finalize strings */
 	strs_sz = strset__data_size(linker->strtab_strs);
@@ -2575,14 +2584,14 @@ int bpf_linker__finalize(struct bpf_linker *linker)
 	if (elf_update(linker->elf, ELF_C_NULL) < 0) {
 		err = -errno;
 		pr_warn_elf("failed to finalize ELF layout");
-		return err;
+		return libbpf_err(err);
 	}
 
 	/* Write out final ELF contents */
 	if (elf_update(linker->elf, ELF_C_WRITE) < 0) {
 		err = -errno;
 		pr_warn_elf("failed to write ELF contents");
-		return err;
+		return libbpf_err(err);
 	}
 
 	elf_end(linker->elf);
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index d2cb28e9ef52..39f25e09b51e 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -4,7 +4,10 @@
 #include <stdlib.h>
 #include <memory.h>
 #include <unistd.h>
+#include <arpa/inet.h>
 #include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/pkt_cls.h>
 #include <linux/rtnetlink.h>
 #include <sys/socket.h>
 #include <errno.h>
@@ -73,9 +76,20 @@ cleanup:
 	return ret;
 }
 
-static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
-			    __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn,
-			    void *cookie)
+static void libbpf_netlink_close(int sock)
+{
+	close(sock);
+}
+
+enum {
+	NL_CONT,
+	NL_NEXT,
+	NL_DONE,
+};
+
+static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq,
+			       __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn,
+			       void *cookie)
 {
 	bool multipart = true;
 	struct nlmsgerr *err;
@@ -84,6 +98,7 @@ static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
 	int len, ret;
 
 	while (multipart) {
+start:
 		multipart = false;
 		len = recv(sock, buf, sizeof(buf), 0);
 		if (len < 0) {
@@ -121,8 +136,16 @@ static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
 			}
 			if (_fn) {
 				ret = _fn(nh, fn, cookie);
-				if (ret)
+				switch (ret) {
+				case NL_CONT:
+					break;
+				case NL_NEXT:
+					goto start;
+				case NL_DONE:
+					return 0;
+				default:
 					return ret;
+				}
 			}
 		}
 	}
@@ -131,95 +154,92 @@ done:
 	return ret;
 }
 
-static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd,
-					 __u32 flags)
+static int libbpf_netlink_send_recv(struct libbpf_nla_req *req,
+				    __dump_nlmsg_t parse_msg,
+				    libbpf_dump_nlmsg_t parse_attr,
+				    void *cookie)
 {
-	int sock, seq = 0, ret;
-	struct nlattr *nla, *nla_xdp;
-	struct {
-		struct nlmsghdr  nh;
-		struct ifinfomsg ifinfo;
-		char             attrbuf[64];
-	} req;
 	__u32 nl_pid = 0;
+	int sock, ret;
 
 	sock = libbpf_netlink_open(&nl_pid);
 	if (sock < 0)
 		return sock;
 
+	req->nh.nlmsg_pid = 0;
+	req->nh.nlmsg_seq = time(NULL);
+
+	if (send(sock, req, req->nh.nlmsg_len, 0) < 0) {
+		ret = -errno;
+		goto out;
+	}
+
+	ret = libbpf_netlink_recv(sock, nl_pid, req->nh.nlmsg_seq,
+				  parse_msg, parse_attr, cookie);
+out:
+	libbpf_netlink_close(sock);
+	return ret;
+}
+
+static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd,
+					 __u32 flags)
+{
+	struct nlattr *nla;
+	int ret;
+	struct libbpf_nla_req req;
+
 	memset(&req, 0, sizeof(req));
-	req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
-	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
-	req.nh.nlmsg_type = RTM_SETLINK;
-	req.nh.nlmsg_pid = 0;
-	req.nh.nlmsg_seq = ++seq;
+	req.nh.nlmsg_len      = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+	req.nh.nlmsg_flags    = NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_type     = RTM_SETLINK;
 	req.ifinfo.ifi_family = AF_UNSPEC;
-	req.ifinfo.ifi_index = ifindex;
-
-	/* started nested attribute for XDP */
-	nla = (struct nlattr *)(((char *)&req)
-				+ NLMSG_ALIGN(req.nh.nlmsg_len));
-	nla->nla_type = NLA_F_NESTED | IFLA_XDP;
-	nla->nla_len = NLA_HDRLEN;
-
-	/* add XDP fd */
-	nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
-	nla_xdp->nla_type = IFLA_XDP_FD;
-	nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
-	memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
-	nla->nla_len += nla_xdp->nla_len;
-
-	/* if user passed in any flags, add those too */
+	req.ifinfo.ifi_index  = ifindex;
+
+	nla = nlattr_begin_nested(&req, IFLA_XDP);
+	if (!nla)
+		return -EMSGSIZE;
+	ret = nlattr_add(&req, IFLA_XDP_FD, &fd, sizeof(fd));
+	if (ret < 0)
+		return ret;
 	if (flags) {
-		nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
-		nla_xdp->nla_type = IFLA_XDP_FLAGS;
-		nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
-		memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
-		nla->nla_len += nla_xdp->nla_len;
+		ret = nlattr_add(&req, IFLA_XDP_FLAGS, &flags, sizeof(flags));
+		if (ret < 0)
+			return ret;
 	}
-
 	if (flags & XDP_FLAGS_REPLACE) {
-		nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
-		nla_xdp->nla_type = IFLA_XDP_EXPECTED_FD;
-		nla_xdp->nla_len = NLA_HDRLEN + sizeof(old_fd);
-		memcpy((char *)nla_xdp + NLA_HDRLEN, &old_fd, sizeof(old_fd));
-		nla->nla_len += nla_xdp->nla_len;
+		ret = nlattr_add(&req, IFLA_XDP_EXPECTED_FD, &old_fd,
+				 sizeof(old_fd));
+		if (ret < 0)
+			return ret;
 	}
+	nlattr_end_nested(&req, nla);
 
-	req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
-
-	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
-		ret = -errno;
-		goto cleanup;
-	}
-	ret = bpf_netlink_recv(sock, nl_pid, seq, NULL, NULL, NULL);
-
-cleanup:
-	close(sock);
-	return ret;
+	return libbpf_netlink_send_recv(&req, NULL, NULL, NULL);
 }
 
 int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags,
 			     const struct bpf_xdp_set_link_opts *opts)
 {
-	int old_fd = -1;
+	int old_fd = -1, ret;
 
 	if (!OPTS_VALID(opts, bpf_xdp_set_link_opts))
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	if (OPTS_HAS(opts, old_fd)) {
 		old_fd = OPTS_GET(opts, old_fd, -1);
 		flags |= XDP_FLAGS_REPLACE;
 	}
 
-	return __bpf_set_link_xdp_fd_replace(ifindex, fd,
-					     old_fd,
-					     flags);
+	ret = __bpf_set_link_xdp_fd_replace(ifindex, fd, old_fd, flags);
+	return libbpf_err(ret);
 }
 
 int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 {
-	return __bpf_set_link_xdp_fd_replace(ifindex, fd, 0, flags);
+	int ret;
+
+	ret = __bpf_set_link_xdp_fd_replace(ifindex, fd, 0, flags);
+	return libbpf_err(ret);
 }
 
 static int __dump_link_nlmsg(struct nlmsghdr *nlh,
@@ -231,6 +251,7 @@ static int __dump_link_nlmsg(struct nlmsghdr *nlh,
 
 	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi));
 	attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi)));
+
 	if (libbpf_nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
@@ -282,34 +303,33 @@ static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb)
 	return 0;
 }
 
-static int libbpf_nl_get_link(int sock, unsigned int nl_pid,
-			      libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie);
-
 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 = 0;
 	__u32 mask;
+	int ret;
+	struct libbpf_nla_req req = {
+		.nh.nlmsg_len      = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
+		.nh.nlmsg_type     = RTM_GETLINK,
+		.nh.nlmsg_flags    = NLM_F_DUMP | NLM_F_REQUEST,
+		.ifinfo.ifi_family = AF_PACKET,
+	};
 
 	if (flags & ~XDP_FLAGS_MASK || !info_size)
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 
 	/* Check whether the single {HW,DRV,SKB} mode is set */
 	flags &= (XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE);
 	mask = flags - 1;
 	if (flags && flags & mask)
-		return -EINVAL;
-
-	sock = libbpf_netlink_open(&nl_pid);
-	if (sock < 0)
-		return sock;
+		return libbpf_err(-EINVAL);
 
 	xdp_id.ifindex = ifindex;
 	xdp_id.flags = flags;
 
-	ret = libbpf_nl_get_link(sock, nl_pid, get_xdp_info, &xdp_id);
+	ret = libbpf_netlink_send_recv(&req, __dump_link_nlmsg,
+				       get_xdp_info, &xdp_id);
 	if (!ret) {
 		size_t sz = min(info_size, sizeof(xdp_id.info));
 
@@ -317,8 +337,7 @@ int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
 		memset((void *) info + sz, 0, info_size - sz);
 	}
 
-	close(sock);
-	return ret;
+	return libbpf_err(ret);
 }
 
 static __u32 get_xdp_id(struct xdp_link_info *info, __u32 flags)
@@ -346,27 +365,394 @@ int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags)
 	if (!ret)
 		*prog_id = get_xdp_id(&info, flags);
 
-	return ret;
+	return libbpf_err(ret);
 }
 
-int libbpf_nl_get_link(int sock, unsigned int nl_pid,
-		       libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie)
+typedef int (*qdisc_config_t)(struct libbpf_nla_req *req);
+
+static int clsact_config(struct libbpf_nla_req *req)
 {
-	struct {
-		struct nlmsghdr nlh;
-		struct ifinfomsg ifm;
-	} req = {
-		.nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
-		.nlh.nlmsg_type = RTM_GETLINK,
-		.nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
-		.ifm.ifi_family = AF_PACKET,
-	};
-	int seq = time(NULL);
+	req->tc.tcm_parent = TC_H_CLSACT;
+	req->tc.tcm_handle = TC_H_MAKE(TC_H_CLSACT, 0);
+
+	return nlattr_add(req, TCA_KIND, "clsact", sizeof("clsact"));
+}
+
+static int attach_point_to_config(struct bpf_tc_hook *hook,
+				  qdisc_config_t *config)
+{
+	switch (OPTS_GET(hook, attach_point, 0)) {
+	case BPF_TC_INGRESS:
+	case BPF_TC_EGRESS:
+	case BPF_TC_INGRESS | BPF_TC_EGRESS:
+		if (OPTS_GET(hook, parent, 0))
+			return -EINVAL;
+		*config = &clsact_config;
+		return 0;
+	case BPF_TC_CUSTOM:
+		return -EOPNOTSUPP;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int tc_get_tcm_parent(enum bpf_tc_attach_point attach_point,
+			     __u32 *parent)
+{
+	switch (attach_point) {
+	case BPF_TC_INGRESS:
+	case BPF_TC_EGRESS:
+		if (*parent)
+			return -EINVAL;
+		*parent = TC_H_MAKE(TC_H_CLSACT,
+				    attach_point == BPF_TC_INGRESS ?
+				    TC_H_MIN_INGRESS : TC_H_MIN_EGRESS);
+		break;
+	case BPF_TC_CUSTOM:
+		if (!*parent)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int tc_qdisc_modify(struct bpf_tc_hook *hook, int cmd, int flags)
+{
+	qdisc_config_t config;
+	int ret;
+	struct libbpf_nla_req req;
+
+	ret = attach_point_to_config(hook, &config);
+	if (ret < 0)
+		return ret;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len   = NLMSG_LENGTH(sizeof(struct tcmsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | flags;
+	req.nh.nlmsg_type  = cmd;
+	req.tc.tcm_family  = AF_UNSPEC;
+	req.tc.tcm_ifindex = OPTS_GET(hook, ifindex, 0);
+
+	ret = config(&req);
+	if (ret < 0)
+		return ret;
+
+	return libbpf_netlink_send_recv(&req, NULL, NULL, NULL);
+}
+
+static int tc_qdisc_create_excl(struct bpf_tc_hook *hook)
+{
+	return tc_qdisc_modify(hook, RTM_NEWQDISC, NLM_F_CREATE | NLM_F_EXCL);
+}
+
+static int tc_qdisc_delete(struct bpf_tc_hook *hook)
+{
+	return tc_qdisc_modify(hook, RTM_DELQDISC, 0);
+}
+
+int bpf_tc_hook_create(struct bpf_tc_hook *hook)
+{
+	int ret;
+
+	if (!hook || !OPTS_VALID(hook, bpf_tc_hook) ||
+	    OPTS_GET(hook, ifindex, 0) <= 0)
+		return libbpf_err(-EINVAL);
+
+	ret = tc_qdisc_create_excl(hook);
+	return libbpf_err(ret);
+}
+
+static int __bpf_tc_detach(const struct bpf_tc_hook *hook,
+			   const struct bpf_tc_opts *opts,
+			   const bool flush);
+
+int bpf_tc_hook_destroy(struct bpf_tc_hook *hook)
+{
+	if (!hook || !OPTS_VALID(hook, bpf_tc_hook) ||
+	    OPTS_GET(hook, ifindex, 0) <= 0)
+		return libbpf_err(-EINVAL);
+
+	switch (OPTS_GET(hook, attach_point, 0)) {
+	case BPF_TC_INGRESS:
+	case BPF_TC_EGRESS:
+		return libbpf_err(__bpf_tc_detach(hook, NULL, true));
+	case BPF_TC_INGRESS | BPF_TC_EGRESS:
+		return libbpf_err(tc_qdisc_delete(hook));
+	case BPF_TC_CUSTOM:
+		return libbpf_err(-EOPNOTSUPP);
+	default:
+		return libbpf_err(-EINVAL);
+	}
+}
+
+struct bpf_cb_ctx {
+	struct bpf_tc_opts *opts;
+	bool processed;
+};
+
+static int __get_tc_info(void *cookie, struct tcmsg *tc, struct nlattr **tb,
+			 bool unicast)
+{
+	struct nlattr *tbb[TCA_BPF_MAX + 1];
+	struct bpf_cb_ctx *info = cookie;
+
+	if (!info || !info->opts)
+		return -EINVAL;
+	if (unicast && info->processed)
+		return -EINVAL;
+	if (!tb[TCA_OPTIONS])
+		return NL_CONT;
+
+	libbpf_nla_parse_nested(tbb, TCA_BPF_MAX, tb[TCA_OPTIONS], NULL);
+	if (!tbb[TCA_BPF_ID])
+		return -EINVAL;
+
+	OPTS_SET(info->opts, prog_id, libbpf_nla_getattr_u32(tbb[TCA_BPF_ID]));
+	OPTS_SET(info->opts, handle, tc->tcm_handle);
+	OPTS_SET(info->opts, priority, TC_H_MAJ(tc->tcm_info) >> 16);
+
+	info->processed = true;
+	return unicast ? NL_NEXT : NL_DONE;
+}
+
+static int get_tc_info(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn,
+		       void *cookie)
+{
+	struct tcmsg *tc = NLMSG_DATA(nh);
+	struct nlattr *tb[TCA_MAX + 1];
+
+	libbpf_nla_parse(tb, TCA_MAX,
+			 (struct nlattr *)((void *)tc + NLMSG_ALIGN(sizeof(*tc))),
+			 NLMSG_PAYLOAD(nh, sizeof(*tc)), NULL);
+	if (!tb[TCA_KIND])
+		return NL_CONT;
+	return __get_tc_info(cookie, tc, tb, nh->nlmsg_flags & NLM_F_ECHO);
+}
+
+static int tc_add_fd_and_name(struct libbpf_nla_req *req, int fd)
+{
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
+	char name[256];
+	int len, ret;
+
+	ret = bpf_obj_get_info_by_fd(fd, &info, &info_len);
+	if (ret < 0)
+		return ret;
 
-	req.nlh.nlmsg_seq = seq;
-	if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
+	ret = nlattr_add(req, TCA_BPF_FD, &fd, sizeof(fd));
+	if (ret < 0)
+		return ret;
+	len = snprintf(name, sizeof(name), "%s:[%u]", info.name, info.id);
+	if (len < 0)
 		return -errno;
+	if (len >= sizeof(name))
+		return -ENAMETOOLONG;
+	return nlattr_add(req, TCA_BPF_NAME, name, len + 1);
+}
+
+int bpf_tc_attach(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts)
+{
+	__u32 protocol, bpf_flags, handle, priority, parent, prog_id, flags;
+	int ret, ifindex, attach_point, prog_fd;
+	struct bpf_cb_ctx info = {};
+	struct libbpf_nla_req req;
+	struct nlattr *nla;
+
+	if (!hook || !opts ||
+	    !OPTS_VALID(hook, bpf_tc_hook) ||
+	    !OPTS_VALID(opts, bpf_tc_opts))
+		return libbpf_err(-EINVAL);
+
+	ifindex      = OPTS_GET(hook, ifindex, 0);
+	parent       = OPTS_GET(hook, parent, 0);
+	attach_point = OPTS_GET(hook, attach_point, 0);
+
+	handle       = OPTS_GET(opts, handle, 0);
+	priority     = OPTS_GET(opts, priority, 0);
+	prog_fd      = OPTS_GET(opts, prog_fd, 0);
+	prog_id      = OPTS_GET(opts, prog_id, 0);
+	flags        = OPTS_GET(opts, flags, 0);
+
+	if (ifindex <= 0 || !prog_fd || prog_id)
+		return libbpf_err(-EINVAL);
+	if (priority > UINT16_MAX)
+		return libbpf_err(-EINVAL);
+	if (flags & ~BPF_TC_F_REPLACE)
+		return libbpf_err(-EINVAL);
+
+	flags = (flags & BPF_TC_F_REPLACE) ? NLM_F_REPLACE : NLM_F_EXCL;
+	protocol = ETH_P_ALL;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len   = NLMSG_LENGTH(sizeof(struct tcmsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_CREATE |
+			     NLM_F_ECHO | flags;
+	req.nh.nlmsg_type  = RTM_NEWTFILTER;
+	req.tc.tcm_family  = AF_UNSPEC;
+	req.tc.tcm_ifindex = ifindex;
+	req.tc.tcm_handle  = handle;
+	req.tc.tcm_info    = TC_H_MAKE(priority << 16, htons(protocol));
+
+	ret = tc_get_tcm_parent(attach_point, &parent);
+	if (ret < 0)
+		return libbpf_err(ret);
+	req.tc.tcm_parent = parent;
+
+	ret = nlattr_add(&req, TCA_KIND, "bpf", sizeof("bpf"));
+	if (ret < 0)
+		return libbpf_err(ret);
+	nla = nlattr_begin_nested(&req, TCA_OPTIONS);
+	if (!nla)
+		return libbpf_err(-EMSGSIZE);
+	ret = tc_add_fd_and_name(&req, prog_fd);
+	if (ret < 0)
+		return libbpf_err(ret);
+	bpf_flags = TCA_BPF_FLAG_ACT_DIRECT;
+	ret = nlattr_add(&req, TCA_BPF_FLAGS, &bpf_flags, sizeof(bpf_flags));
+	if (ret < 0)
+		return libbpf_err(ret);
+	nlattr_end_nested(&req, nla);
+
+	info.opts = opts;
+
+	ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info);
+	if (ret < 0)
+		return libbpf_err(ret);
+	if (!info.processed)
+		return libbpf_err(-ENOENT);
+	return ret;
+}
+
+static int __bpf_tc_detach(const struct bpf_tc_hook *hook,
+			   const struct bpf_tc_opts *opts,
+			   const bool flush)
+{
+	__u32 protocol = 0, handle, priority, parent, prog_id, flags;
+	int ret, ifindex, attach_point, prog_fd;
+	struct libbpf_nla_req req;
+
+	if (!hook ||
+	    !OPTS_VALID(hook, bpf_tc_hook) ||
+	    !OPTS_VALID(opts, bpf_tc_opts))
+		return -EINVAL;
+
+	ifindex      = OPTS_GET(hook, ifindex, 0);
+	parent       = OPTS_GET(hook, parent, 0);
+	attach_point = OPTS_GET(hook, attach_point, 0);
+
+	handle       = OPTS_GET(opts, handle, 0);
+	priority     = OPTS_GET(opts, priority, 0);
+	prog_fd      = OPTS_GET(opts, prog_fd, 0);
+	prog_id      = OPTS_GET(opts, prog_id, 0);
+	flags        = OPTS_GET(opts, flags, 0);
+
+	if (ifindex <= 0 || flags || prog_fd || prog_id)
+		return -EINVAL;
+	if (priority > UINT16_MAX)
+		return -EINVAL;
+	if (!flush) {
+		if (!handle || !priority)
+			return -EINVAL;
+		protocol = ETH_P_ALL;
+	} else {
+		if (handle || priority)
+			return -EINVAL;
+	}
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len   = NLMSG_LENGTH(sizeof(struct tcmsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_type  = RTM_DELTFILTER;
+	req.tc.tcm_family  = AF_UNSPEC;
+	req.tc.tcm_ifindex = ifindex;
+	if (!flush) {
+		req.tc.tcm_handle = handle;
+		req.tc.tcm_info   = TC_H_MAKE(priority << 16, htons(protocol));
+	}
+
+	ret = tc_get_tcm_parent(attach_point, &parent);
+	if (ret < 0)
+		return ret;
+	req.tc.tcm_parent = parent;
 
-	return bpf_netlink_recv(sock, nl_pid, seq, __dump_link_nlmsg,
-				dump_link_nlmsg, cookie);
+	if (!flush) {
+		ret = nlattr_add(&req, TCA_KIND, "bpf", sizeof("bpf"));
+		if (ret < 0)
+			return ret;
+	}
+
+	return libbpf_netlink_send_recv(&req, NULL, NULL, NULL);
+}
+
+int bpf_tc_detach(const struct bpf_tc_hook *hook,
+		  const struct bpf_tc_opts *opts)
+{
+	int ret;
+
+	if (!opts)
+		return libbpf_err(-EINVAL);
+
+	ret = __bpf_tc_detach(hook, opts, false);
+	return libbpf_err(ret);
+}
+
+int bpf_tc_query(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts)
+{
+	__u32 protocol, handle, priority, parent, prog_id, flags;
+	int ret, ifindex, attach_point, prog_fd;
+	struct bpf_cb_ctx info = {};
+	struct libbpf_nla_req req;
+
+	if (!hook || !opts ||
+	    !OPTS_VALID(hook, bpf_tc_hook) ||
+	    !OPTS_VALID(opts, bpf_tc_opts))
+		return libbpf_err(-EINVAL);
+
+	ifindex      = OPTS_GET(hook, ifindex, 0);
+	parent       = OPTS_GET(hook, parent, 0);
+	attach_point = OPTS_GET(hook, attach_point, 0);
+
+	handle       = OPTS_GET(opts, handle, 0);
+	priority     = OPTS_GET(opts, priority, 0);
+	prog_fd      = OPTS_GET(opts, prog_fd, 0);
+	prog_id      = OPTS_GET(opts, prog_id, 0);
+	flags        = OPTS_GET(opts, flags, 0);
+
+	if (ifindex <= 0 || flags || prog_fd || prog_id ||
+	    !handle || !priority)
+		return libbpf_err(-EINVAL);
+	if (priority > UINT16_MAX)
+		return libbpf_err(-EINVAL);
+
+	protocol = ETH_P_ALL;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len   = NLMSG_LENGTH(sizeof(struct tcmsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST;
+	req.nh.nlmsg_type  = RTM_GETTFILTER;
+	req.tc.tcm_family  = AF_UNSPEC;
+	req.tc.tcm_ifindex = ifindex;
+	req.tc.tcm_handle  = handle;
+	req.tc.tcm_info    = TC_H_MAKE(priority << 16, htons(protocol));
+
+	ret = tc_get_tcm_parent(attach_point, &parent);
+	if (ret < 0)
+		return libbpf_err(ret);
+	req.tc.tcm_parent = parent;
+
+	ret = nlattr_add(&req, TCA_KIND, "bpf", sizeof("bpf"));
+	if (ret < 0)
+		return libbpf_err(ret);
+
+	info.opts = opts;
+
+	ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info);
+	if (ret < 0)
+		return libbpf_err(ret);
+	if (!info.processed)
+		return libbpf_err(-ENOENT);
+	return ret;
 }
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
index b607fa9852b1..f57e77a6e40f 100644
--- a/tools/lib/bpf/nlattr.c
+++ b/tools/lib/bpf/nlattr.c
@@ -27,7 +27,7 @@ static struct nlattr *nla_next(const struct nlattr *nla, int *remaining)
 	int totlen = NLA_ALIGN(nla->nla_len);
 
 	*remaining -= totlen;
-	return (struct nlattr *) ((char *) nla + totlen);
+	return (struct nlattr *)((void *)nla + totlen);
 }
 
 static int nla_ok(const struct nlattr *nla, int remaining)
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
index 6cc3ac91690f..4d15ae2ff812 100644
--- a/tools/lib/bpf/nlattr.h
+++ b/tools/lib/bpf/nlattr.h
@@ -10,7 +10,11 @@
 #define __LIBBPF_NLATTR_H
 
 #include <stdint.h>
+#include <string.h>
+#include <errno.h>
 #include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+
 /* avoid multiple definition of netlink features */
 #define __LINUX_NETLINK_H
 
@@ -49,6 +53,15 @@ struct libbpf_nla_policy {
 	uint16_t	maxlen;
 };
 
+struct libbpf_nla_req {
+	struct nlmsghdr nh;
+	union {
+		struct ifinfomsg ifinfo;
+		struct tcmsg tc;
+	};
+	char buf[128];
+};
+
 /**
  * @ingroup attr
  * Iterate over a stream of attributes
@@ -68,7 +81,7 @@ struct libbpf_nla_policy {
  */
 static inline void *libbpf_nla_data(const struct nlattr *nla)
 {
-	return (char *) nla + NLA_HDRLEN;
+	return (void *)nla + NLA_HDRLEN;
 }
 
 static inline uint8_t libbpf_nla_getattr_u8(const struct nlattr *nla)
@@ -103,4 +116,49 @@ int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype,
 
 int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh);
 
+static inline struct nlattr *nla_data(struct nlattr *nla)
+{
+	return (struct nlattr *)((void *)nla + NLA_HDRLEN);
+}
+
+static inline struct nlattr *req_tail(struct libbpf_nla_req *req)
+{
+	return (struct nlattr *)((void *)req + NLMSG_ALIGN(req->nh.nlmsg_len));
+}
+
+static inline int nlattr_add(struct libbpf_nla_req *req, int type,
+			     const void *data, int len)
+{
+	struct nlattr *nla;
+
+	if (NLMSG_ALIGN(req->nh.nlmsg_len) + NLA_ALIGN(NLA_HDRLEN + len) > sizeof(*req))
+		return -EMSGSIZE;
+	if (!!data != !!len)
+		return -EINVAL;
+
+	nla = req_tail(req);
+	nla->nla_type = type;
+	nla->nla_len = NLA_HDRLEN + len;
+	if (data)
+		memcpy(nla_data(nla), data, len);
+	req->nh.nlmsg_len = NLMSG_ALIGN(req->nh.nlmsg_len) + NLA_ALIGN(nla->nla_len);
+	return 0;
+}
+
+static inline struct nlattr *nlattr_begin_nested(struct libbpf_nla_req *req, int type)
+{
+	struct nlattr *tail;
+
+	tail = req_tail(req);
+	if (nlattr_add(req, type | NLA_F_NESTED, NULL, 0))
+		return NULL;
+	return tail;
+}
+
+static inline void nlattr_end_nested(struct libbpf_nla_req *req,
+				     struct nlattr *tail)
+{
+	tail->nla_len = (void *)req_tail(req) - (void *)tail;
+}
+
 #endif /* __LIBBPF_NLATTR_H */
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index 1d80ad4e0de8..8bc117bcc7bc 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -69,23 +69,23 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 		err = -errno;
 		pr_warn("ringbuf: failed to get map info for fd=%d: %d\n",
 			map_fd, err);
-		return err;
+		return libbpf_err(err);
 	}
 
 	if (info.type != BPF_MAP_TYPE_RINGBUF) {
 		pr_warn("ringbuf: map fd=%d is not BPF_MAP_TYPE_RINGBUF\n",
 			map_fd);
-		return -EINVAL;
+		return libbpf_err(-EINVAL);
 	}
 
 	tmp = libbpf_reallocarray(rb->rings, rb->ring_cnt + 1, sizeof(*rb->rings));
 	if (!tmp)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 	rb->rings = tmp;
 
 	tmp = libbpf_reallocarray(rb->events, rb->ring_cnt + 1, sizeof(*rb->events));
 	if (!tmp)
-		return -ENOMEM;
+		return libbpf_err(-ENOMEM);
 	rb->events = tmp;
 
 	r = &rb->rings[rb->ring_cnt];
@@ -103,7 +103,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 		err = -errno;
 		pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %d\n",
 			map_fd, err);
-		return err;
+		return libbpf_err(err);
 	}
 	r->consumer_pos = tmp;
 
@@ -118,7 +118,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 		ringbuf_unmap_ring(rb, r);
 		pr_warn("ringbuf: failed to mmap data pages for map fd=%d: %d\n",
 			map_fd, err);
-		return err;
+		return libbpf_err(err);
 	}
 	r->producer_pos = tmp;
 	r->data = tmp + rb->page_size;
@@ -133,7 +133,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 		ringbuf_unmap_ring(rb, r);
 		pr_warn("ringbuf: failed to epoll add map fd=%d: %d\n",
 			map_fd, err);
-		return err;
+		return libbpf_err(err);
 	}
 
 	rb->ring_cnt++;
@@ -165,11 +165,11 @@ ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx,
 	int err;
 
 	if (!OPTS_VALID(opts, ring_buffer_opts))
-		return NULL;
+		return errno = EINVAL, NULL;
 
 	rb = calloc(1, sizeof(*rb));
 	if (!rb)
-		return NULL;
+		return errno = ENOMEM, NULL;
 
 	rb->page_size = getpagesize();
 
@@ -188,7 +188,7 @@ ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx,
 
 err_out:
 	ring_buffer__free(rb);
-	return NULL;
+	return errno = -err, NULL;
 }
 
 static inline int roundup_len(__u32 len)
@@ -260,7 +260,7 @@ int ring_buffer__consume(struct ring_buffer *rb)
 
 		err = ringbuf_process_ring(ring);
 		if (err < 0)
-			return err;
+			return libbpf_err(err);
 		res += err;
 	}
 	if (res > INT_MAX)
@@ -279,7 +279,7 @@ int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms)
 
 	cnt = epoll_wait(rb->epoll_fd, rb->events, rb->ring_cnt, timeout_ms);
 	if (cnt < 0)
-		return -errno;
+		return libbpf_err(-errno);
 
 	for (i = 0; i < cnt; i++) {
 		__u32 ring_id = rb->events[i].data.fd;
@@ -287,7 +287,7 @@ int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms)
 
 		err = ringbuf_process_ring(ring);
 		if (err < 0)
-			return err;
+			return libbpf_err(err);
 		res += err;
 	}
 	if (res > INT_MAX)
diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h
new file mode 100644
index 000000000000..b22b50c1b173
--- /dev/null
+++ b/tools/lib/bpf/skel_internal.h
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+/* Copyright (c) 2021 Facebook */
+#ifndef __SKEL_INTERNAL_H
+#define __SKEL_INTERNAL_H
+
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/mman.h>
+
+/* This file is a base header for auto-generated *.lskel.h files.
+ * Its contents will change and may become part of auto-generation in the future.
+ *
+ * The layout of bpf_[map|prog]_desc and bpf_loader_ctx is feature dependent
+ * and will change from one version of libbpf to another and features
+ * requested during loader program generation.
+ */
+struct bpf_map_desc {
+	union {
+		/* input for the loader prog */
+		struct {
+			__aligned_u64 initial_value;
+			__u32 max_entries;
+		};
+		/* output of the loader prog */
+		struct {
+			int map_fd;
+		};
+	};
+};
+struct bpf_prog_desc {
+	int prog_fd;
+};
+
+struct bpf_loader_ctx {
+	size_t sz;
+	__u32 log_level;
+	__u32 log_size;
+	__u64 log_buf;
+};
+
+struct bpf_load_and_run_opts {
+	struct bpf_loader_ctx *ctx;
+	const void *data;
+	const void *insns;
+	__u32 data_sz;
+	__u32 insns_sz;
+	const char *errstr;
+};
+
+static inline int skel_sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
+			  unsigned int size)
+{
+	return syscall(__NR_bpf, cmd, attr, size);
+}
+
+static inline int skel_closenz(int fd)
+{
+	if (fd > 0)
+		return close(fd);
+	return -EINVAL;
+}
+
+static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
+{
+	int map_fd = -1, prog_fd = -1, key = 0, err;
+	union bpf_attr attr;
+
+	map_fd = bpf_create_map_name(BPF_MAP_TYPE_ARRAY, "__loader.map", 4,
+				     opts->data_sz, 1, 0);
+	if (map_fd < 0) {
+		opts->errstr = "failed to create loader map";
+		err = -errno;
+		goto out;
+	}
+
+	err = bpf_map_update_elem(map_fd, &key, opts->data, 0);
+	if (err < 0) {
+		opts->errstr = "failed to update loader map";
+		err = -errno;
+		goto out;
+	}
+
+	memset(&attr, 0, sizeof(attr));
+	attr.prog_type = BPF_PROG_TYPE_SYSCALL;
+	attr.insns = (long) opts->insns;
+	attr.insn_cnt = opts->insns_sz / sizeof(struct bpf_insn);
+	attr.license = (long) "Dual BSD/GPL";
+	memcpy(attr.prog_name, "__loader.prog", sizeof("__loader.prog"));
+	attr.fd_array = (long) &map_fd;
+	attr.log_level = opts->ctx->log_level;
+	attr.log_size = opts->ctx->log_size;
+	attr.log_buf = opts->ctx->log_buf;
+	attr.prog_flags = BPF_F_SLEEPABLE;
+	prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+	if (prog_fd < 0) {
+		opts->errstr = "failed to load loader prog";
+		err = -errno;
+		goto out;
+	}
+
+	memset(&attr, 0, sizeof(attr));
+	attr.test.prog_fd = prog_fd;
+	attr.test.ctx_in = (long) opts->ctx;
+	attr.test.ctx_size_in = opts->ctx->sz;
+	err = skel_sys_bpf(BPF_PROG_RUN, &attr, sizeof(attr));
+	if (err < 0 || (int)attr.test.retval < 0) {
+		opts->errstr = "failed to execute loader prog";
+		if (err < 0)
+			err = -errno;
+		else
+			err = (int)attr.test.retval;
+		goto out;
+	}
+	err = 0;
+out:
+	if (map_fd >= 0)
+		close(map_fd);
+	if (prog_fd >= 0)
+		close(prog_fd);
+	return err;
+}
+
+#endif