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

Pull networking updates from David Miller:
 "Another merge window, another pull full of stuff:

   1) Support alternative names for network devices, from Jiri Pirko.

   2) Introduce per-netns netdev notifiers, also from Jiri Pirko.

   3) Support MSG_PEEK in vsock/virtio, from Matias Ezequiel Vara
      Larsen.

   4) Allow compiling out the TLS TOE code, from Jakub Kicinski.

   5) Add several new tracepoints to the kTLS code, also from Jakub.

   6) Support set channels ethtool callback in ena driver, from Sameeh
      Jubran.

   7) New SCTP events SCTP_ADDR_ADDED, SCTP_ADDR_REMOVED,
      SCTP_ADDR_MADE_PRIM, and SCTP_SEND_FAILED_EVENT. From Xin Long.

   8) Add XDP support to mvneta driver, from Lorenzo Bianconi.

   9) Lots of netfilter hw offload fixes, cleanups and enhancements,
      from Pablo Neira Ayuso.

  10) PTP support for aquantia chips, from Egor Pomozov.

  11) Add UDP segmentation offload support to igb, ixgbe, and i40e. From
      Josh Hunt.

  12) Add smart nagle to tipc, from Jon Maloy.

  13) Support L2 field rewrite by TC offloads in bnxt_en, from Venkat
      Duvvuru.

  14) Add a flow mask cache to OVS, from Tonghao Zhang.

  15) Add XDP support to ice driver, from Maciej Fijalkowski.

  16) Add AF_XDP support to ice driver, from Krzysztof Kazimierczak.

  17) Support UDP GSO offload in atlantic driver, from Igor Russkikh.

  18) Support it in stmmac driver too, from Jose Abreu.

  19) Support TIPC encryption and auth, from Tuong Lien.

  20) Introduce BPF trampolines, from Alexei Starovoitov.

  21) Make page_pool API more numa friendly, from Saeed Mahameed.

  22) Introduce route hints to ipv4 and ipv6, from Paolo Abeni.

  23) Add UDP segmentation offload to cxgb4, Rahul Lakkireddy"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1857 commits)
  libbpf: Fix usage of u32 in userspace code
  mm: Implement no-MMU variant of vmalloc_user_node_flags
  slip: Fix use-after-free Read in slip_open
  net: dsa: sja1105: fix sja1105_parse_rgmii_delays()
  macvlan: schedule bc_work even if error
  enetc: add support Credit Based Shaper(CBS) for hardware offload
  net: phy: add helpers phy_(un)lock_mdio_bus
  mdio_bus: don't use managed reset-controller
  ax88179_178a: add ethtool_op_get_ts_info()
  mlxsw: spectrum_router: Fix use of uninitialized adjacency index
  mlxsw: spectrum_router: After underlay moves, demote conflicting tunnels
  bpf: Simplify __bpf_arch_text_poke poke type handling
  bpf: Introduce BPF_TRACE_x helper for the tracing tests
  bpf: Add bpf_jit_blinding_enabled for !CONFIG_BPF_JIT
  bpf, testing: Add various tail call test cases
  bpf, x86: Emit patchable direct jump as tail call
  bpf: Constant map key tracking for prog array pokes
  bpf: Add poke dependency tracking for prog array maps
  bpf: Add initial poke descriptor table for jit images
  bpf: Move owner type, jited info into array auxiliary data
  ...

21 files changed, 2471 insertions, 912 deletions

diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore
index d9e9dec04605..35bf013e368c 100644
--- a/tools/lib/bpf/.gitignore
+++ b/tools/lib/bpf/.gitignore
@@ -3,3 +3,7 @@ libbpf.pc
 FEATURE-DUMP.libbpf
 test_libbpf
 libbpf.so.*
+TAGS
+tags
+cscope.*
+/bpf_helper_defs.h
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 56ce6292071b..99425d0be6ff 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -56,7 +56,7 @@ ifndef VERBOSE
 endif
 
 FEATURE_USER = .libbpf
-FEATURE_TESTS = libelf libelf-mmap bpf reallocarray cxx
+FEATURE_TESTS = libelf libelf-mmap bpf reallocarray
 FEATURE_DISPLAY = libelf bpf
 
 INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi
@@ -143,6 +143,8 @@ LIB_TARGET	:= $(addprefix $(OUTPUT),$(LIB_TARGET))
 LIB_FILE	:= $(addprefix $(OUTPUT),$(LIB_FILE))
 PC_FILE		:= $(addprefix $(OUTPUT),$(PC_FILE))
 
+TAGS_PROG := $(if $(shell which etags 2>/dev/null),etags,ctags)
+
 GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \
 			   cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \
 			   awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}' | \
@@ -150,22 +152,14 @@ GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \
 VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \
 			      grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
 
-CMD_TARGETS = $(LIB_TARGET) $(PC_FILE)
-
-CXX_TEST_TARGET = $(OUTPUT)test_libbpf
-
-ifeq ($(feature-cxx), 1)
-	CMD_TARGETS += $(CXX_TEST_TARGET)
-endif
-
-TARGETS = $(CMD_TARGETS)
+CMD_TARGETS = $(LIB_TARGET) $(PC_FILE) $(OUTPUT)test_libbpf
 
 all: fixdep
 	$(Q)$(MAKE) all_cmd
 
 all_cmd: $(CMD_TARGETS) check
 
-$(BPF_IN_SHARED): force elfdep bpfdep
+$(BPF_IN_SHARED): force elfdep bpfdep bpf_helper_defs.h
 	@(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \
 	(diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true
@@ -183,22 +177,27 @@ $(BPF_IN_SHARED): force elfdep bpfdep
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true
 	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)"
 
-$(BPF_IN_STATIC): force elfdep bpfdep
+$(BPF_IN_STATIC): force elfdep bpfdep bpf_helper_defs.h
 	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR)
 
+bpf_helper_defs.h: $(srctree)/include/uapi/linux/bpf.h
+	$(Q)$(srctree)/scripts/bpf_helpers_doc.py --header 		\
+		--file $(srctree)/include/uapi/linux/bpf.h > bpf_helper_defs.h
+
 $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
 
 $(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED)
-	$(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \
-				    -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@
+	$(QUIET_LINK)$(CC) $(LDFLAGS) \
+		--shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \
+		-Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@
 	@ln -sf $(@F) $(OUTPUT)libbpf.so
 	@ln -sf $(@F) $(OUTPUT)libbpf.so.$(LIBBPF_MAJOR_VERSION)
 
 $(OUTPUT)libbpf.a: $(BPF_IN_STATIC)
 	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
 
-$(OUTPUT)test_libbpf: test_libbpf.cpp $(OUTPUT)libbpf.a
-	$(QUIET_LINK)$(CXX) $(INCLUDES) $^ -lelf -o $@
+$(OUTPUT)test_libbpf: test_libbpf.c $(OUTPUT)libbpf.a
+	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(INCLUDES) $^ -lelf -o $@
 
 $(OUTPUT)libbpf.pc:
 	$(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \
@@ -247,13 +246,18 @@ install_lib: all_cmd
 		$(call do_install_mkdir,$(libdir_SQ)); \
 		cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ)
 
-install_headers:
+install_headers: bpf_helper_defs.h
 	$(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); \
 		$(call do_install,libbpf_util.h,$(prefix)/include/bpf,644); \
-		$(call do_install,xsk.h,$(prefix)/include/bpf,644);
+		$(call do_install,xsk.h,$(prefix)/include/bpf,644); \
+		$(call do_install,bpf_helpers.h,$(prefix)/include/bpf,644); \
+		$(call do_install,bpf_helper_defs.h,$(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);
 
 install_pkgconfig: $(PC_FILE)
 	$(call QUIET_INSTALL, $(PC_FILE)) \
@@ -268,14 +272,15 @@ config-clean:
 	$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
 
 clean:
-	$(call QUIET_CLEAN, libbpf) $(RM) -rf $(TARGETS) $(CXX_TEST_TARGET) \
+	$(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \
 		*.o *~ *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) .*.d .*.cmd \
-		*.pc LIBBPF-CFLAGS $(SHARED_OBJDIR) $(STATIC_OBJDIR)
+		*.pc LIBBPF-CFLAGS bpf_helper_defs.h \
+		$(SHARED_OBJDIR) $(STATIC_OBJDIR)
 	$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
 
 
 
-PHONY += force elfdep bpfdep
+PHONY += force elfdep bpfdep cscope tags
 force:
 
 elfdep:
@@ -284,6 +289,17 @@ elfdep:
 bpfdep:
 	@if [ "$(feature-bpf)" != "1" ]; then echo "BPF API too old"; exit 1 ; fi
 
+cscope:
+	ls *.c *.h > cscope.files
+	cscope -b -q -I $(srctree)/include -f cscope.out
+
+tags:
+	rm -f TAGS tags
+	ls *.c *.h | xargs $(TAGS_PROG) -a
+
 # Declare the contents of the .PHONY variable as phony.  We keep that
 # information in a variable so we can use it in if_changed and friends.
 .PHONY: $(PHONY)
+
+# Delete partially updated (corrupted) files on error
+.DELETE_ON_ERROR:
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index cbb933532981..98596e15390f 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -189,7 +189,7 @@ static void *
 alloc_zero_tailing_info(const void *orecord, __u32 cnt,
 			__u32 actual_rec_size, __u32 expected_rec_size)
 {
-	__u64 info_len = actual_rec_size * cnt;
+	__u64 info_len = (__u64)actual_rec_size * cnt;
 	void *info, *nrecord;
 	int i;
 
@@ -228,6 +228,13 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = load_attr->prog_type;
 	attr.expected_attach_type = load_attr->expected_attach_type;
+	if (attr.prog_type == BPF_PROG_TYPE_TRACING) {
+		attr.attach_btf_id = load_attr->attach_btf_id;
+		attr.attach_prog_fd = load_attr->attach_prog_fd;
+	} else {
+		attr.prog_ifindex = load_attr->prog_ifindex;
+		attr.kern_version = load_attr->kern_version;
+	}
 	attr.insn_cnt = (__u32)load_attr->insns_cnt;
 	attr.insns = ptr_to_u64(load_attr->insns);
 	attr.license = ptr_to_u64(load_attr->license);
@@ -241,8 +248,6 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 		attr.log_size = 0;
 	}
 
-	attr.kern_version = load_attr->kern_version;
-	attr.prog_ifindex = load_attr->prog_ifindex;
 	attr.prog_btf_fd = load_attr->prog_btf_fd;
 	attr.func_info_rec_size = load_attr->func_info_rec_size;
 	attr.func_info_cnt = load_attr->func_info_cnt;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 0db01334740f..3c791fa8e68e 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -77,8 +77,14 @@ struct bpf_load_program_attr {
 	const struct bpf_insn *insns;
 	size_t insns_cnt;
 	const char *license;
-	__u32 kern_version;
-	__u32 prog_ifindex;
+	union {
+		__u32 kern_version;
+		__u32 attach_prog_fd;
+	};
+	union {
+		__u32 prog_ifindex;
+		__u32 attach_btf_id;
+	};
 	__u32 prog_btf_fd;
 	__u32 func_info_rec_size;
 	const void *func_info;
diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h
new file mode 100644
index 000000000000..7009dc90e012
--- /dev/null
+++ b/tools/lib/bpf/bpf_core_read.h
@@ -0,0 +1,263 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __BPF_CORE_READ_H__
+#define __BPF_CORE_READ_H__
+
+/*
+ * enum bpf_field_info_kind is passed as a second argument into
+ * __builtin_preserve_field_info() built-in to get a specific aspect of
+ * a field, captured as a first argument. __builtin_preserve_field_info(field,
+ * info_kind) returns __u32 integer and produces BTF field relocation, which
+ * is understood and processed by libbpf during BPF object loading. See
+ * selftests/bpf for examples.
+ */
+enum bpf_field_info_kind {
+	BPF_FIELD_BYTE_OFFSET = 0,	/* field byte offset */
+	BPF_FIELD_BYTE_SIZE = 1,
+	BPF_FIELD_EXISTS = 2,		/* field existence in target kernel */
+	BPF_FIELD_SIGNED = 3,
+	BPF_FIELD_LSHIFT_U64 = 4,
+	BPF_FIELD_RSHIFT_U64 = 5,
+};
+
+#define __CORE_RELO(src, field, info)					      \
+	__builtin_preserve_field_info((src)->field, BPF_FIELD_##info)
+
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+#define __CORE_BITFIELD_PROBE_READ(dst, src, fld)			      \
+	bpf_probe_read((void *)dst,					      \
+		       __CORE_RELO(src, fld, BYTE_SIZE),		      \
+		       (const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET))
+#else
+/* semantics of LSHIFT_64 assumes loading values into low-ordered bytes, so
+ * for big-endian we need to adjust destination pointer accordingly, based on
+ * field byte size
+ */
+#define __CORE_BITFIELD_PROBE_READ(dst, src, fld)			      \
+	bpf_probe_read((void *)dst + (8 - __CORE_RELO(src, fld, BYTE_SIZE)),  \
+		       __CORE_RELO(src, fld, BYTE_SIZE),		      \
+		       (const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET))
+#endif
+
+/*
+ * Extract bitfield, identified by s->field, and return its value as u64.
+ * All this is done in relocatable manner, so bitfield changes such as
+ * signedness, bit size, offset changes, this will be handled automatically.
+ * This version of macro is using bpf_probe_read() to read underlying integer
+ * storage. Macro functions as an expression and its return type is
+ * bpf_probe_read()'s return value: 0, on success, <0 on error.
+ */
+#define BPF_CORE_READ_BITFIELD_PROBED(s, field) ({			      \
+	unsigned long long val = 0;					      \
+									      \
+	__CORE_BITFIELD_PROBE_READ(&val, s, field);			      \
+	val <<= __CORE_RELO(s, field, LSHIFT_U64);			      \
+	if (__CORE_RELO(s, field, SIGNED))				      \
+		val = ((long long)val) >> __CORE_RELO(s, field, RSHIFT_U64);  \
+	else								      \
+		val = val >> __CORE_RELO(s, field, RSHIFT_U64);		      \
+	val;								      \
+})
+
+/*
+ * Extract bitfield, identified by s->field, and return its value as u64.
+ * This version of macro is using direct memory reads and should be used from
+ * BPF program types that support such functionality (e.g., typed raw
+ * tracepoints).
+ */
+#define BPF_CORE_READ_BITFIELD(s, field) ({				      \
+	const void *p = (const void *)s + __CORE_RELO(s, field, BYTE_OFFSET); \
+	unsigned long long val;						      \
+									      \
+	switch (__CORE_RELO(s, field, BYTE_SIZE)) {			      \
+	case 1: val = *(const unsigned char *)p;			      \
+	case 2: val = *(const unsigned short *)p;			      \
+	case 4: val = *(const unsigned int *)p;				      \
+	case 8: val = *(const unsigned long long *)p;			      \
+	}								      \
+	val <<= __CORE_RELO(s, field, LSHIFT_U64);			      \
+	if (__CORE_RELO(s, field, SIGNED))				      \
+		val = ((long long)val) >> __CORE_RELO(s, field, RSHIFT_U64);  \
+	else								      \
+		val = val >> __CORE_RELO(s, field, RSHIFT_U64);		      \
+	val;								      \
+})
+
+/*
+ * Convenience macro to check that field actually exists in target kernel's.
+ * Returns:
+ *    1, if matching field is present in target kernel;
+ *    0, if no matching field found.
+ */
+#define bpf_core_field_exists(field)					    \
+	__builtin_preserve_field_info(field, BPF_FIELD_EXISTS)
+
+/*
+ * Convenience macro to get byte size of a field. Works for integers,
+ * struct/unions, pointers, arrays, and enums.
+ */
+#define bpf_core_field_size(field)					    \
+	__builtin_preserve_field_info(field, BPF_FIELD_BYTE_SIZE)
+
+/*
+ * bpf_core_read() abstracts away bpf_probe_read() call and captures offset
+ * relocation for source address using __builtin_preserve_access_index()
+ * built-in, provided by Clang.
+ *
+ * __builtin_preserve_access_index() takes as an argument an expression of
+ * taking an address of a field within struct/union. It makes compiler emit
+ * a relocation, which records BTF type ID describing root struct/union and an
+ * accessor string which describes exact embedded field that was used to take
+ * an address. See detailed description of this relocation format and
+ * semantics in comments to struct bpf_field_reloc in libbpf_internal.h.
+ *
+ * This relocation allows libbpf to adjust BPF instruction to use correct
+ * actual field offset, based on target kernel BTF type that matches original
+ * (local) BTF, used to record relocation.
+ */
+#define bpf_core_read(dst, sz, src)					    \
+	bpf_probe_read(dst, sz,						    \
+		       (const void *)__builtin_preserve_access_index(src))
+
+/*
+ * bpf_core_read_str() is a thin wrapper around bpf_probe_read_str()
+ * additionally emitting BPF CO-RE field relocation for specified source
+ * argument.
+ */
+#define bpf_core_read_str(dst, sz, src)					    \
+	bpf_probe_read_str(dst, sz,					    \
+			   (const void *)__builtin_preserve_access_index(src))
+
+#define ___concat(a, b) a ## b
+#define ___apply(fn, n) ___concat(fn, n)
+#define ___nth(_1, _2, _3, _4, _5, _6, _7, _8, _9, _10, __11, N, ...) N
+
+/*
+ * return number of provided arguments; used for switch-based variadic macro
+ * definitions (see ___last, ___arrow, etc below)
+ */
+#define ___narg(...) ___nth(_, ##__VA_ARGS__, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+/*
+ * return 0 if no arguments are passed, N - otherwise; used for
+ * recursively-defined macros to specify termination (0) case, and generic
+ * (N) case (e.g., ___read_ptrs, ___core_read)
+ */
+#define ___empty(...) ___nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0)
+
+#define ___last1(x) x
+#define ___last2(a, x) x
+#define ___last3(a, b, x) x
+#define ___last4(a, b, c, x) x
+#define ___last5(a, b, c, d, x) x
+#define ___last6(a, b, c, d, e, x) x
+#define ___last7(a, b, c, d, e, f, x) x
+#define ___last8(a, b, c, d, e, f, g, x) x
+#define ___last9(a, b, c, d, e, f, g, h, x) x
+#define ___last10(a, b, c, d, e, f, g, h, i, x) x
+#define ___last(...) ___apply(___last, ___narg(__VA_ARGS__))(__VA_ARGS__)
+
+#define ___nolast2(a, _) a
+#define ___nolast3(a, b, _) a, b
+#define ___nolast4(a, b, c, _) a, b, c
+#define ___nolast5(a, b, c, d, _) a, b, c, d
+#define ___nolast6(a, b, c, d, e, _) a, b, c, d, e
+#define ___nolast7(a, b, c, d, e, f, _) a, b, c, d, e, f
+#define ___nolast8(a, b, c, d, e, f, g, _) a, b, c, d, e, f, g
+#define ___nolast9(a, b, c, d, e, f, g, h, _) a, b, c, d, e, f, g, h
+#define ___nolast10(a, b, c, d, e, f, g, h, i, _) a, b, c, d, e, f, g, h, i
+#define ___nolast(...) ___apply(___nolast, ___narg(__VA_ARGS__))(__VA_ARGS__)
+
+#define ___arrow1(a) a
+#define ___arrow2(a, b) a->b
+#define ___arrow3(a, b, c) a->b->c
+#define ___arrow4(a, b, c, d) a->b->c->d
+#define ___arrow5(a, b, c, d, e) a->b->c->d->e
+#define ___arrow6(a, b, c, d, e, f) a->b->c->d->e->f
+#define ___arrow7(a, b, c, d, e, f, g) a->b->c->d->e->f->g
+#define ___arrow8(a, b, c, d, e, f, g, h) a->b->c->d->e->f->g->h
+#define ___arrow9(a, b, c, d, e, f, g, h, i) a->b->c->d->e->f->g->h->i
+#define ___arrow10(a, b, c, d, e, f, g, h, i, j) a->b->c->d->e->f->g->h->i->j
+#define ___arrow(...) ___apply(___arrow, ___narg(__VA_ARGS__))(__VA_ARGS__)
+
+#define ___type(...) typeof(___arrow(__VA_ARGS__))
+
+#define ___read(read_fn, dst, src_type, src, accessor)			    \
+	read_fn((void *)(dst), sizeof(*(dst)), &((src_type)(src))->accessor)
+
+/* "recursively" read a sequence of inner pointers using local __t var */
+#define ___rd_first(src, a) ___read(bpf_core_read, &__t, ___type(src), src, a);
+#define ___rd_last(...)							    \
+	___read(bpf_core_read, &__t,					    \
+		___type(___nolast(__VA_ARGS__)), __t, ___last(__VA_ARGS__));
+#define ___rd_p1(...) const void *__t; ___rd_first(__VA_ARGS__)
+#define ___rd_p2(...) ___rd_p1(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
+#define ___rd_p3(...) ___rd_p2(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
+#define ___rd_p4(...) ___rd_p3(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
+#define ___rd_p5(...) ___rd_p4(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
+#define ___rd_p6(...) ___rd_p5(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
+#define ___rd_p7(...) ___rd_p6(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
+#define ___rd_p8(...) ___rd_p7(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
+#define ___rd_p9(...) ___rd_p8(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__)
+#define ___read_ptrs(src, ...)						    \
+	___apply(___rd_p, ___narg(__VA_ARGS__))(src, __VA_ARGS__)
+
+#define ___core_read0(fn, dst, src, a)					    \
+	___read(fn, dst, ___type(src), src, a);
+#define ___core_readN(fn, dst, src, ...)				    \
+	___read_ptrs(src, ___nolast(__VA_ARGS__))			    \
+	___read(fn, dst, ___type(src, ___nolast(__VA_ARGS__)), __t,	    \
+		___last(__VA_ARGS__));
+#define ___core_read(fn, dst, src, a, ...)				    \
+	___apply(___core_read, ___empty(__VA_ARGS__))(fn, dst,		    \
+						      src, a, ##__VA_ARGS__)
+
+/*
+ * BPF_CORE_READ_INTO() is a more performance-conscious variant of
+ * BPF_CORE_READ(), in which final field is read into user-provided storage.
+ * See BPF_CORE_READ() below for more details on general usage.
+ */
+#define BPF_CORE_READ_INTO(dst, src, a, ...)				    \
+	({								    \
+		___core_read(bpf_core_read, dst, src, a, ##__VA_ARGS__)	    \
+	})
+
+/*
+ * BPF_CORE_READ_STR_INTO() does same "pointer chasing" as
+ * BPF_CORE_READ() for intermediate pointers, but then executes (and returns
+ * corresponding error code) bpf_core_read_str() for final string read.
+ */
+#define BPF_CORE_READ_STR_INTO(dst, src, a, ...)			    \
+	({								    \
+		___core_read(bpf_core_read_str, dst, src, a, ##__VA_ARGS__) \
+	})
+
+/*
+ * BPF_CORE_READ() is used to simplify BPF CO-RE relocatable read, especially
+ * when there are few pointer chasing steps.
+ * E.g., what in non-BPF world (or in BPF w/ BCC) would be something like:
+ *	int x = s->a.b.c->d.e->f->g;
+ * can be succinctly achieved using BPF_CORE_READ as:
+ *	int x = BPF_CORE_READ(s, a.b.c, d.e, f, g);
+ *
+ * BPF_CORE_READ will decompose above statement into 4 bpf_core_read (BPF
+ * CO-RE relocatable bpf_probe_read() wrapper) calls, logically equivalent to:
+ * 1. const void *__t = s->a.b.c;
+ * 2. __t = __t->d.e;
+ * 3. __t = __t->f;
+ * 4. return __t->g;
+ *
+ * Equivalence is logical, because there is a heavy type casting/preservation
+ * involved, as well as all the reads are happening through bpf_probe_read()
+ * calls using __builtin_preserve_access_index() to emit CO-RE relocations.
+ *
+ * N.B. Only up to 9 "field accessors" are supported, which should be more
+ * than enough for any practical purpose.
+ */
+#define BPF_CORE_READ(src, a, ...)					    \
+	({								    \
+		___type(src, a, ##__VA_ARGS__) __r;			    \
+		BPF_CORE_READ_INTO(&__r, src, a, ##__VA_ARGS__);	    \
+		__r;							    \
+	})
+
+#endif
+
diff --git a/tools/lib/bpf/bpf_endian.h b/tools/lib/bpf/bpf_endian.h
new file mode 100644
index 000000000000..fbe28008450f
--- /dev/null
+++ b/tools/lib/bpf/bpf_endian.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __BPF_ENDIAN__
+#define __BPF_ENDIAN__
+
+#include <linux/stddef.h>
+#include <linux/swab.h>
+
+/* LLVM's BPF target selects the endianness of the CPU
+ * it compiles on, or the user specifies (bpfel/bpfeb),
+ * respectively. The used __BYTE_ORDER__ is defined by
+ * the compiler, we cannot rely on __BYTE_ORDER from
+ * libc headers, since it doesn't reflect the actual
+ * requested byte order.
+ *
+ * Note, LLVM's BPF target has different __builtin_bswapX()
+ * semantics. It does map to BPF_ALU | BPF_END | BPF_TO_BE
+ * in bpfel and bpfeb case, which means below, that we map
+ * to cpu_to_be16(). We could use it unconditionally in BPF
+ * case, but better not rely on it, so that this header here
+ * can be used from application and BPF program side, which
+ * use different targets.
+ */
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+# define __bpf_ntohs(x)			__builtin_bswap16(x)
+# define __bpf_htons(x)			__builtin_bswap16(x)
+# define __bpf_constant_ntohs(x)	___constant_swab16(x)
+# define __bpf_constant_htons(x)	___constant_swab16(x)
+# define __bpf_ntohl(x)			__builtin_bswap32(x)
+# define __bpf_htonl(x)			__builtin_bswap32(x)
+# define __bpf_constant_ntohl(x)	___constant_swab32(x)
+# define __bpf_constant_htonl(x)	___constant_swab32(x)
+# define __bpf_be64_to_cpu(x)		__builtin_bswap64(x)
+# define __bpf_cpu_to_be64(x)		__builtin_bswap64(x)
+# define __bpf_constant_be64_to_cpu(x)	___constant_swab64(x)
+# define __bpf_constant_cpu_to_be64(x)	___constant_swab64(x)
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+# define __bpf_ntohs(x)			(x)
+# define __bpf_htons(x)			(x)
+# define __bpf_constant_ntohs(x)	(x)
+# define __bpf_constant_htons(x)	(x)
+# define __bpf_ntohl(x)			(x)
+# define __bpf_htonl(x)			(x)
+# define __bpf_constant_ntohl(x)	(x)
+# define __bpf_constant_htonl(x)	(x)
+# define __bpf_be64_to_cpu(x)		(x)
+# define __bpf_cpu_to_be64(x)		(x)
+# define __bpf_constant_be64_to_cpu(x)  (x)
+# define __bpf_constant_cpu_to_be64(x)  (x)
+#else
+# error "Fix your compiler's __BYTE_ORDER__?!"
+#endif
+
+#define bpf_htons(x)				\
+	(__builtin_constant_p(x) ?		\
+	 __bpf_constant_htons(x) : __bpf_htons(x))
+#define bpf_ntohs(x)				\
+	(__builtin_constant_p(x) ?		\
+	 __bpf_constant_ntohs(x) : __bpf_ntohs(x))
+#define bpf_htonl(x)				\
+	(__builtin_constant_p(x) ?		\
+	 __bpf_constant_htonl(x) : __bpf_htonl(x))
+#define bpf_ntohl(x)				\
+	(__builtin_constant_p(x) ?		\
+	 __bpf_constant_ntohl(x) : __bpf_ntohl(x))
+#define bpf_cpu_to_be64(x)			\
+	(__builtin_constant_p(x) ?		\
+	 __bpf_constant_cpu_to_be64(x) : __bpf_cpu_to_be64(x))
+#define bpf_be64_to_cpu(x)			\
+	(__builtin_constant_p(x) ?		\
+	 __bpf_constant_be64_to_cpu(x) : __bpf_be64_to_cpu(x))
+
+#endif /* __BPF_ENDIAN__ */
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
new file mode 100644
index 000000000000..0c7d28292898
--- /dev/null
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __BPF_HELPERS__
+#define __BPF_HELPERS__
+
+#include "bpf_helper_defs.h"
+
+#define __uint(name, val) int (*name)[val]
+#define __type(name, val) typeof(val) *name
+
+/* Helper macro to print out debug messages */
+#define bpf_printk(fmt, ...)				\
+({							\
+	char ____fmt[] = fmt;				\
+	bpf_trace_printk(____fmt, sizeof(____fmt),	\
+			 ##__VA_ARGS__);		\
+})
+
+/*
+ * Helper macro to place programs, maps, license in
+ * different sections in elf_bpf file. Section names
+ * are interpreted by elf_bpf loader
+ */
+#define SEC(NAME) __attribute__((section(NAME), used))
+
+#ifndef __always_inline
+#define __always_inline __attribute__((always_inline))
+#endif
+
+/*
+ * Helper structure used by eBPF C program
+ * to describe BPF map attributes to libbpf loader
+ */
+struct bpf_map_def {
+	unsigned int type;
+	unsigned int key_size;
+	unsigned int value_size;
+	unsigned int max_entries;
+	unsigned int map_flags;
+};
+
+enum libbpf_pin_type {
+	LIBBPF_PIN_NONE,
+	/* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */
+	LIBBPF_PIN_BY_NAME,
+};
+
+#endif
diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c
index 8c67561c93b0..3ed1a27b5f7c 100644
--- a/tools/lib/bpf/bpf_prog_linfo.c
+++ b/tools/lib/bpf/bpf_prog_linfo.c
@@ -101,6 +101,7 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 {
 	struct bpf_prog_linfo *prog_linfo;
 	__u32 nr_linfo, nr_jited_func;
+	__u64 data_sz;
 
 	nr_linfo = info->nr_line_info;
 
@@ -122,11 +123,11 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 	/* Copy xlated line_info */
 	prog_linfo->nr_linfo = nr_linfo;
 	prog_linfo->rec_size = info->line_info_rec_size;
-	prog_linfo->raw_linfo = malloc(nr_linfo * prog_linfo->rec_size);
+	data_sz = (__u64)nr_linfo * prog_linfo->rec_size;
+	prog_linfo->raw_linfo = malloc(data_sz);
 	if (!prog_linfo->raw_linfo)
 		goto err_free;
-	memcpy(prog_linfo->raw_linfo, (void *)(long)info->line_info,
-	       nr_linfo * prog_linfo->rec_size);
+	memcpy(prog_linfo->raw_linfo, (void *)(long)info->line_info, data_sz);
 
 	nr_jited_func = info->nr_jited_ksyms;
 	if (!nr_jited_func ||
@@ -142,13 +143,12 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 	/* Copy jited_line_info */
 	prog_linfo->nr_jited_func = nr_jited_func;
 	prog_linfo->jited_rec_size = info->jited_line_info_rec_size;
-	prog_linfo->raw_jited_linfo = malloc(nr_linfo *
-					     prog_linfo->jited_rec_size);
+	data_sz = (__u64)nr_linfo * prog_linfo->jited_rec_size;
+	prog_linfo->raw_jited_linfo = malloc(data_sz);
 	if (!prog_linfo->raw_jited_linfo)
 		goto err_free;
 	memcpy(prog_linfo->raw_jited_linfo,
-	       (void *)(long)info->jited_line_info,
-	       nr_linfo * prog_linfo->jited_rec_size);
+	       (void *)(long)info->jited_line_info, data_sz);
 
 	/* Number of jited_line_info per jited func */
 	prog_linfo->nr_jited_linfo_per_func = malloc(nr_jited_func *
diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
new file mode 100644
index 000000000000..b0dafe8b4ebc
--- /dev/null
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -0,0 +1,195 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __BPF_TRACING_H__
+#define __BPF_TRACING_H__
+
+/* Scan the ARCH passed in from ARCH env variable (see Makefile) */
+#if defined(__TARGET_ARCH_x86)
+	#define bpf_target_x86
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_s390)
+	#define bpf_target_s390
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_arm)
+	#define bpf_target_arm
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_arm64)
+	#define bpf_target_arm64
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_mips)
+	#define bpf_target_mips
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_powerpc)
+	#define bpf_target_powerpc
+	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_sparc)
+	#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
+#elif defined(__s390__)
+	#define bpf_target_s390
+#elif defined(__arm__)
+	#define bpf_target_arm
+#elif defined(__aarch64__)
+	#define bpf_target_arm64
+#elif defined(__mips__)
+	#define bpf_target_mips
+#elif defined(__powerpc__)
+	#define bpf_target_powerpc
+#elif defined(__sparc__)
+	#define bpf_target_sparc
+#endif
+#endif
+
+#if defined(bpf_target_x86)
+
+#ifdef __KERNEL__
+#define PT_REGS_PARM1(x) ((x)->di)
+#define PT_REGS_PARM2(x) ((x)->si)
+#define PT_REGS_PARM3(x) ((x)->dx)
+#define PT_REGS_PARM4(x) ((x)->cx)
+#define PT_REGS_PARM5(x) ((x)->r8)
+#define PT_REGS_RET(x) ((x)->sp)
+#define PT_REGS_FP(x) ((x)->bp)
+#define PT_REGS_RC(x) ((x)->ax)
+#define PT_REGS_SP(x) ((x)->sp)
+#define PT_REGS_IP(x) ((x)->ip)
+#else
+#ifdef __i386__
+/* i386 kernel is built with -mregparm=3 */
+#define PT_REGS_PARM1(x) ((x)->eax)
+#define PT_REGS_PARM2(x) ((x)->edx)
+#define PT_REGS_PARM3(x) ((x)->ecx)
+#define PT_REGS_PARM4(x) 0
+#define PT_REGS_PARM5(x) 0
+#define PT_REGS_RET(x) ((x)->esp)
+#define PT_REGS_FP(x) ((x)->ebp)
+#define PT_REGS_RC(x) ((x)->eax)
+#define PT_REGS_SP(x) ((x)->esp)
+#define PT_REGS_IP(x) ((x)->eip)
+#else
+#define PT_REGS_PARM1(x) ((x)->rdi)
+#define PT_REGS_PARM2(x) ((x)->rsi)
+#define PT_REGS_PARM3(x) ((x)->rdx)
+#define PT_REGS_PARM4(x) ((x)->rcx)
+#define PT_REGS_PARM5(x) ((x)->r8)
+#define PT_REGS_RET(x) ((x)->rsp)
+#define PT_REGS_FP(x) ((x)->rbp)
+#define PT_REGS_RC(x) ((x)->rax)
+#define PT_REGS_SP(x) ((x)->rsp)
+#define PT_REGS_IP(x) ((x)->rip)
+#endif
+#endif
+
+#elif defined(bpf_target_s390)
+
+/* s390 provides user_pt_regs instead of struct pt_regs to userspace */
+struct pt_regs;
+#define PT_REGS_S390 const volatile user_pt_regs
+#define PT_REGS_PARM1(x) (((PT_REGS_S390 *)(x))->gprs[2])
+#define PT_REGS_PARM2(x) (((PT_REGS_S390 *)(x))->gprs[3])
+#define PT_REGS_PARM3(x) (((PT_REGS_S390 *)(x))->gprs[4])
+#define PT_REGS_PARM4(x) (((PT_REGS_S390 *)(x))->gprs[5])
+#define PT_REGS_PARM5(x) (((PT_REGS_S390 *)(x))->gprs[6])
+#define PT_REGS_RET(x) (((PT_REGS_S390 *)(x))->gprs[14])
+/* Works