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

Alexei Starovoitov says: ==================== pull-request: bpf-next 2021-12-30 The following pull-request contains BPF updates for your *net-next* tree. We've added 72 non-merge commits during the last 20 day(s) which contain a total of 223 files changed, 3510 insertions(+), 1591 deletions(-). The main changes are: 1) Automatic setrlimit in libbpf when bpf is memcg's in the kernel, from Andrii. 2) Beautify and de-verbose verifier logs, from Christy. 3) Composable verifier types, from Hao. 4) bpf_strncmp helper, from Hou. 5) bpf.h header dependency cleanup, from Jakub. 6) get_func_[arg|ret|arg_cnt] helpers, from Jiri. 7) Sleepable local storage, from KP. 8) Extend kfunc with PTR_TO_CTX, PTR_TO_MEM argument support, from Kumar. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2021-12-31 14:35:40 +00:00
parent ce2b6eb409 9e6b19a66d
commit e63a023489
221 changed files with 3501 additions and 1586 deletions
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -57,7 +57,7 @@ $(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_
 $(LIBBPF_BOOTSTRAP): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_BOOTSTRAP_OUTPUT)
 	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \
 		DESTDIR=$(LIBBPF_BOOTSTRAP_DESTDIR) prefix= \
-		ARCH= CC=$(HOSTCC) LD=$(HOSTLD) $@ install_headers
+		ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) $@ install_headers

 $(LIBBPF_BOOTSTRAP_INTERNAL_HDRS): $(LIBBPF_BOOTSTRAP_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_BOOTSTRAP_HDRS_DIR)
 	$(call QUIET_INSTALL, $@)
@@ -152,6 +152,9 @@ CFLAGS += -DHAVE_LIBBFD_SUPPORT
 SRCS += $(BFD_SRCS)
 endif

+HOST_CFLAGS = $(subst -I$(LIBBPF_INCLUDE),-I$(LIBBPF_BOOTSTRAP_INCLUDE),\
+		$(subst $(CLANG_CROSS_FLAGS),,$(CFLAGS)))
+
 BPFTOOL_BOOTSTRAP := $(BOOTSTRAP_OUTPUT)bpftool

 BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o xlated_dumper.o btf_dumper.o disasm.o)
@@ -202,7 +205,7 @@ endif
 CFLAGS += $(if $(BUILD_BPF_SKELS),,-DBPFTOOL_WITHOUT_SKELETONS)

 $(BOOTSTRAP_OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
-	$(QUIET_CC)$(HOSTCC) $(CFLAGS) -c -MMD $< -o $@
+	$(QUIET_CC)$(HOSTCC) $(HOST_CFLAGS) -c -MMD $< -o $@

 $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
 	$(QUIET_CC)$(CC) $(CFLAGS) -c -MMD $< -o $@
@@ -213,15 +216,13 @@ ifneq ($(feature-zlib), 1)
 endif

 $(BPFTOOL_BOOTSTRAP): $(BOOTSTRAP_OBJS) $(LIBBPF_BOOTSTRAP)
-	$(QUIET_LINK)$(HOSTCC) $(CFLAGS) $(LDFLAGS) $(BOOTSTRAP_OBJS) $(LIBS_BOOTSTRAP) -o $@
+	$(QUIET_LINK)$(HOSTCC) $(HOST_CFLAGS) $(LDFLAGS) $(BOOTSTRAP_OBJS) $(LIBS_BOOTSTRAP) -o $@

 $(OUTPUT)bpftool: $(OBJS) $(LIBBPF)
 	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(OBJS) $(LIBS) -o $@

 $(BOOTSTRAP_OUTPUT)%.o: %.c $(LIBBPF_BOOTSTRAP_INTERNAL_HDRS) | $(BOOTSTRAP_OUTPUT)
-	$(QUIET_CC)$(HOSTCC) \
-		$(subst -I$(LIBBPF_INCLUDE),-I$(LIBBPF_BOOTSTRAP_INCLUDE),$(CFLAGS)) \
-		-c -MMD $< -o $@
+	$(QUIET_CC)$(HOSTCC) $(HOST_CFLAGS) -c -MMD $< -o $@

 $(OUTPUT)%.o: %.c
 	$(QUIET_CC)$(CC) $(CFLAGS) -c -MMD $< -o $@
--- a/tools/bpf/bpftool/feature.c
+++ b/tools/bpf/bpftool/feature.c
@@ -642,12 +642,32 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type,
 		printf("\n");
 }

-static void
-probe_large_insn_limit(const char *define_prefix, __u32 ifindex)
+/*
+ * Probe for availability of kernel commit (5.3):
+ *
+ * c04c0d2b968a ("bpf: increase complexity limit and maximum program size")
+ */
+static void probe_large_insn_limit(const char *define_prefix, __u32 ifindex)
 {
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		.prog_ifindex = ifindex,
+	);
+	struct bpf_insn insns[BPF_MAXINSNS + 1];
 	bool res;
+	int i, fd;
+
+	for (i = 0; i < BPF_MAXINSNS; i++)
+		insns[i] = BPF_MOV64_IMM(BPF_REG_0, 1);
+	insns[BPF_MAXINSNS] = BPF_EXIT_INSN();
+
+	errno = 0;
+	fd = bpf_prog_load(BPF_PROG_TYPE_SCHED_CLS, NULL, "GPL",
+			   insns, ARRAY_SIZE(insns), &opts);
+	res = fd >= 0 || (errno != E2BIG && errno != EINVAL);
+
+	if (fd >= 0)
+		close(fd);

-	res = bpf_probe_large_insn_limit(ifindex);
 	print_bool_feature("have_large_insn_limit",
 			   "Large program size limit",
 			   "LARGE_INSN_LIMIT",
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -408,6 +408,8 @@ int main(int argc, char **argv)
 	bool version_requested = false;
 	int opt, ret;

+	setlinebuf(stdout);
+
 	last_do_help = do_help;
 	pretty_output = false;
 	json_output = false;
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -19,6 +19,7 @@ CC       = $(HOSTCC)
 LD       = $(HOSTLD)
 ARCH     = $(HOSTARCH)
 RM      ?= rm
+CROSS_COMPILE =

 OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/

--- a/tools/bpf/runqslower/Makefile
+++ b/tools/bpf/runqslower/Makefile
@@ -12,7 +12,7 @@ BPFOBJ := $(BPFOBJ_OUTPUT)libbpf.a
 BPF_DESTDIR := $(BPFOBJ_OUTPUT)
 BPF_INCLUDE := $(BPF_DESTDIR)/include
 INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../include/uapi)
-CFLAGS := -g -Wall
+CFLAGS := -g -Wall $(CLANG_CROSS_FLAGS)

 # Try to detect best kernel BTF source
 KERNEL_REL := $(shell uname -r)
@@ -88,4 +88,4 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(BPFOBJ_OU

 $(DEFAULT_BPFTOOL): $(BPFOBJ) | $(BPFTOOL_OUTPUT)
 	$(Q)$(MAKE) $(submake_extras) -C ../bpftool OUTPUT=$(BPFTOOL_OUTPUT)   \
-		    CC=$(HOSTCC) LD=$(HOSTLD)
+		    ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD)
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4983,6 +4983,41 @@ union bpf_attr {
 *	Return
 *		The number of loops performed, **-EINVAL** for invalid **flags**,
 *		**-E2BIG** if **nr_loops** exceeds the maximum number of loops.
+ *
+ * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2)
+ *	Description
+ *		Do strncmp() between **s1** and **s2**. **s1** doesn't need
+ *		to be null-terminated and **s1_sz** is the maximum storage
+ *		size of **s1**. **s2** must be a read-only string.
+ *	Return
+ *		An integer less than, equal to, or greater than zero
+ *		if the first **s1_sz** bytes of **s1** is found to be
+ *		less than, to match, or be greater than **s2**.
+ *
+ * long bpf_get_func_arg(void *ctx, u32 n, u64 *value)
+ *	Description
+ *		Get **n**-th argument (zero based) of the traced function (for tracing programs)
+ *		returned in **value**.
+ *
+ *	Return
+ *		0 on success.
+ *		**-EINVAL** if n >= arguments count of traced function.
+ *
+ * long bpf_get_func_ret(void *ctx, u64 *value)
+ *	Description
+ *		Get return value of the traced function (for tracing programs)
+ *		in **value**.
+ *
+ *	Return
+ *		0 on success.
+ *		**-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN.
+ *
+ * long bpf_get_func_arg_cnt(void *ctx)
+ *	Description
+ *		Get number of arguments of the traced function (for tracing programs).
+ *
+ *	Return
+ *		The number of arguments of the traced function.
 */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5167,6 +5202,10 @@ union bpf_attr {
 	FN(kallsyms_lookup_name),	\
 	FN(find_vma),			\
 	FN(loop),			\
+	FN(strncmp),			\
+	FN(get_func_arg),		\
+	FN(get_func_ret),		\
+	FN(get_func_arg_cnt),		\
 	/* */

 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -90,6 +90,7 @@ override CFLAGS += -Werror -Wall
 override CFLAGS += $(INCLUDES)
 override CFLAGS += -fvisibility=hidden
 override CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
+override CFLAGS += $(CLANG_CROSS_FLAGS)

 # flags specific for shared library
 SHLIB_FLAGS := -DSHARED -fPIC
@@ -162,7 +163,7 @@ $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h
 $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)

 $(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED) $(VERSION_SCRIPT)
-	$(QUIET_LINK)$(CC) $(LDFLAGS) \
+	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) \
 		--shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \
 		-Wl,--version-script=$(VERSION_SCRIPT) $< -lelf -lz -o $@
 	@ln -sf $(@F) $(OUTPUT)libbpf.so
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -28,7 +28,9 @@
 #include <asm/unistd.h>
 #include <errno.h>
 #include <linux/bpf.h>
+#include <linux/filter.h>
 #include <limits.h>
+#include <sys/resource.h>
 #include "bpf.h"
 #include "libbpf.h"
 #include "libbpf_internal.h"
@@ -94,6 +96,77 @@ static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int
 	return fd;
 }

+/* Probe whether kernel switched from memlock-based (RLIMIT_MEMLOCK) to
+ * memcg-based memory accounting for BPF maps and progs. This was done in [0].
+ * We use the support for bpf_ktime_get_coarse_ns() helper, which was added in
+ * the same 5.11 Linux release ([1]), to detect memcg-based accounting for BPF.
+ *
+ *   [0] https://lore.kernel.org/bpf/20201201215900.3569844-1-guro@fb.com/
+ *   [1] d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper")
+ */
+int probe_memcg_account(void)
+{
+	const size_t prog_load_attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd);
+	struct bpf_insn insns[] = {
+		BPF_EMIT_CALL(BPF_FUNC_ktime_get_coarse_ns),
+		BPF_EXIT_INSN(),
+	};
+	size_t insn_cnt = sizeof(insns) / sizeof(insns[0]);
+	union bpf_attr attr;
+	int prog_fd;
+
+	/* attempt loading freplace trying to use custom BTF */
+	memset(&attr, 0, prog_load_attr_sz);
+	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+	attr.insns = ptr_to_u64(insns);
+	attr.insn_cnt = insn_cnt;
+	attr.license = ptr_to_u64("GPL");
+
+	prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, prog_load_attr_sz);
+	if (prog_fd >= 0) {
+		close(prog_fd);
+		return 1;
+	}
+	return 0;
+}
+
+static bool memlock_bumped;
+static rlim_t memlock_rlim = RLIM_INFINITY;
+
+int libbpf_set_memlock_rlim(size_t memlock_bytes)
+{
+	if (memlock_bumped)
+		return libbpf_err(-EBUSY);
+
+	memlock_rlim = memlock_bytes;
+	return 0;
+}
+
+int bump_rlimit_memlock(void)
+{
+	struct rlimit rlim;
+
+	/* this the default in libbpf 1.0, but for now user has to opt-in explicitly */
+	if (!(libbpf_mode & LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK))
+		return 0;
+
+	/* if kernel supports memcg-based accounting, skip bumping RLIMIT_MEMLOCK */
+	if (memlock_bumped || kernel_supports(NULL, FEAT_MEMCG_ACCOUNT))
+		return 0;
+
+	memlock_bumped = true;
+
+	/* zero memlock_rlim_max disables auto-bumping RLIMIT_MEMLOCK */
+	if (memlock_rlim == 0)
+		return 0;
+
+	rlim.rlim_cur = rlim.rlim_max = memlock_rlim;
+	if (setrlimit(RLIMIT_MEMLOCK, &rlim))
+		return -errno;
+
+	return 0;
+}
+
 int bpf_map_create(enum bpf_map_type map_type,
 		   const char *map_name,
 		   __u32 key_size,
@@ -105,6 +178,8 @@ int bpf_map_create(enum bpf_map_type map_type,
 	union bpf_attr attr;
 	int fd;

+	bump_rlimit_memlock();
+
 	memset(&attr, 0, attr_sz);

 	if (!OPTS_VALID(opts, bpf_map_create_opts))
@@ -112,7 +187,7 @@ int bpf_map_create(enum bpf_map_type map_type,

 	attr.map_type = map_type;
 	if (map_name)
-		strncat(attr.map_name, map_name, sizeof(attr.map_name) - 1);
+		libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name));
 	attr.key_size = key_size;
 	attr.value_size = value_size;
 	attr.max_entries = max_entries;
@@ -251,6 +326,8 @@ int bpf_prog_load_v0_6_0(enum bpf_prog_type prog_type,
 	union bpf_attr attr;
 	char *log_buf;

+	bump_rlimit_memlock();
+
 	if (!OPTS_VALID(opts, bpf_prog_load_opts))
 		return libbpf_err(-EINVAL);

@@ -271,7 +348,7 @@ int bpf_prog_load_v0_6_0(enum bpf_prog_type prog_type,
 	attr.kern_version = OPTS_GET(opts, kern_version, 0);

 	if (prog_name)
-		strncat(attr.prog_name, prog_name, sizeof(attr.prog_name) - 1);
+		libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
 	attr.license = ptr_to_u64(license);

 	if (insn_cnt > UINT_MAX)
@@ -456,6 +533,8 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 	union bpf_attr attr;
 	int fd;

+	bump_rlimit_memlock();
+
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = type;
 	attr.insn_cnt = (__u32)insns_cnt;
@@ -1056,6 +1135,8 @@ int bpf_btf_load(const void *btf_data, size_t btf_size, const struct bpf_btf_loa
 	__u32 log_level;
 	int fd;

+	bump_rlimit_memlock();
+
 	memset(&attr, 0, attr_sz);

 	if (!OPTS_VALID(opts, bpf_btf_load_opts))
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -35,6 +35,8 @@
 extern "C" {
 #endif

+int libbpf_set_memlock_rlim(size_t memlock_bytes);
+
 struct bpf_map_create_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */

--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -66,277 +66,204 @@

 #if defined(__KERNEL__) || defined(__VMLINUX_H__)

-#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)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), di)
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), si)
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), dx)
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), cx)
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8)
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), sp)
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), bp)
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), ax)
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), ip)
+#define __PT_PARM1_REG di
+#define __PT_PARM2_REG si
+#define __PT_PARM3_REG dx
+#define __PT_PARM4_REG cx
+#define __PT_PARM5_REG r8
+#define __PT_RET_REG sp
+#define __PT_FP_REG bp
+#define __PT_RC_REG ax
+#define __PT_SP_REG sp
+#define __PT_IP_REG ip

 #else

 #ifdef __i386__
+
+#define __PT_PARM1_REG eax
+#define __PT_PARM2_REG edx
+#define __PT_PARM3_REG ecx
 /* 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)
+#define __PT_PARM4_REG __unsupported__
+#define __PT_PARM5_REG __unsupported__
+#define __PT_RET_REG esp
+#define __PT_FP_REG ebp
+#define __PT_RC_REG eax
+#define __PT_SP_REG esp
+#define __PT_IP_REG eip

-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), eax)
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), edx)
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), ecx)
-#define PT_REGS_PARM4_CORE(x) 0
-#define PT_REGS_PARM5_CORE(x) 0
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), esp)
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), ebp)
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), eax)
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), esp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), eip)
+#else /* __i386__ */

-#else
+#define __PT_PARM1_REG rdi
+#define __PT_PARM2_REG rsi
+#define __PT_PARM3_REG rdx
+#define __PT_PARM4_REG rcx
+#define __PT_PARM5_REG r8
+#define __PT_RET_REG rsp
+#define __PT_FP_REG rbp
+#define __PT_RC_REG rax
+#define __PT_SP_REG rsp
+#define __PT_IP_REG rip

-#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 /* __i386__ */

-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), rdi)
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), rsi)
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), rdx)
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), rcx)
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8)
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), rsp)
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), rbp)
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), rax)
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), rsp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), rip)
-
-#endif
-#endif
+#endif /* __KERNEL__ || __VMLINUX_H__ */

 #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 only with CONFIG_FRAME_POINTER */
-#define PT_REGS_FP(x) (((PT_REGS_S390 *)(x))->gprs[11])
-#define PT_REGS_RC(x) (((PT_REGS_S390 *)(x))->gprs[2])
-#define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15])
-#define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[3])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[4])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[5])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[6])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[14])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[11])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[15])
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), psw.addr)
+#define __PT_REGS_CAST(x) ((const user_pt_regs *)(x))
+#define __PT_PARM1_REG gprs[2]
+#define __PT_PARM2_REG gprs[3]
+#define __PT_PARM3_REG gprs[4]
+#define __PT_PARM4_REG gprs[5]
+#define __PT_PARM5_REG gprs[6]
+#define __PT_RET_REG grps[14]
+#define __PT_FP_REG gprs[11]	/* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG gprs[2]
+#define __PT_SP_REG gprs[15]
+#define __PT_IP_REG psw.addr

 #elif defined(bpf_target_arm)

-#define PT_REGS_PARM1(x) ((x)->uregs[0])
-#define PT_REGS_PARM2(x) ((x)->uregs[1])
-#define PT_REGS_PARM3(x) ((x)->uregs[2])
-#define PT_REGS_PARM4(x) ((x)->uregs[3])
-#define PT_REGS_PARM5(x) ((x)->uregs[4])
-#define PT_REGS_RET(x) ((x)->uregs[14])
-#define PT_REGS_FP(x) ((x)->uregs[11]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->uregs[0])
-#define PT_REGS_SP(x) ((x)->uregs[13])
-#define PT_REGS_IP(x) ((x)->uregs[12])
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), uregs[0])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), uregs[1])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), uregs[2])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), uregs[3])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), uregs[4])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), uregs[14])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), uregs[11])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), uregs[0])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), uregs[13])
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), uregs[12])
+#define __PT_PARM1_REG uregs[0]
+#define __PT_PARM2_REG uregs[1]
+#define __PT_PARM3_REG uregs[2]
+#define __PT_PARM4_REG uregs[3]
+#define __PT_PARM5_REG uregs[4]
+#define __PT_RET_REG uregs[14]
+#define __PT_FP_REG uregs[11]	/* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG uregs[0]
+#define __PT_SP_REG uregs[13]
+#define __PT_IP_REG uregs[12]

 #elif defined(bpf_target_arm64)

 /* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
-struct pt_regs;
-#define PT_REGS_ARM64 const volatile struct user_pt_regs
-#define PT_REGS_PARM1(x) (((PT_REGS_ARM64 *)(x))->regs[0])
-#define PT_REGS_PARM2(x) (((PT_REGS_ARM64 *)(x))->regs[1])
-#define PT_REGS_PARM3(x) (((PT_REGS_ARM64 *)(x))->regs[2])
-#define PT_REGS_PARM4(x) (((PT_REGS_ARM64 *)(x))->regs[3])
-#define PT_REGS_PARM5(x) (((PT_REGS_ARM64 *)(x))->regs[4])
-#define PT_REGS_RET(x) (((PT_REGS_ARM64 *)(x))->regs[30])
-/* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_FP(x) (((PT_REGS_ARM64 *)(x))->regs[29])
-#define PT_REGS_RC(x) (((PT_REGS_ARM64 *)(x))->regs[0])
-#define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp)
-#define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[1])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[2])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[3])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[4])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[30])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[29])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), sp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), pc)
+#define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x))
+#define __PT_PARM1_REG regs[0]
+#define __PT_PARM2_REG regs[1]
+#define __PT_PARM3_REG regs[2]
+#define __PT_PARM4_REG regs[3]
+#define __PT_PARM5_REG regs[4]
+#define __PT_RET_REG regs[30]
+#define __PT_FP_REG regs[29]	/* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG regs[0]
+#define __PT_SP_REG sp
+#define __PT_IP_REG pc

 #elif defined(bpf_target_mips)

-#define PT_REGS_PARM1(x) ((x)->regs[4])
-#define PT_REGS_PARM2(x) ((x)->regs[5])
-#define PT_REGS_PARM3(x) ((x)->regs[6])
-#define PT_REGS_PARM4(x) ((x)->regs[7])
-#define PT_REGS_PARM5(x) ((x)->regs[8])
-#define PT_REGS_RET(x) ((x)->regs[31])
-#define PT_REGS_FP(x) ((x)->regs[30]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->regs[2])
-#define PT_REGS_SP(x) ((x)->regs[29])
-#define PT_REGS_IP(x) ((x)->cp0_epc)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), regs[4])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), regs[5])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), regs[6])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), regs[7])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), regs[8])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), regs[31])
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), regs[30])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), regs[2])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), regs[29])
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), cp0_epc)
+#define __PT_PARM1_REG regs[4]
+#define __PT_PARM2_REG regs[5]
+#define __PT_PARM3_REG regs[6]
+#define __PT_PARM4_REG regs[7]
+#define __PT_PARM5_REG regs[8]
+#define __PT_RET_REG regs[31]
+#define __PT_FP_REG regs[30]	/* Works only with CONFIG_FRAME_POINTER */
+#define __PT_RC_REG regs[2]
+#define __PT_SP_REG regs[29]
+#define __PT_IP_REG cp0_epc

 #elif defined(bpf_target_powerpc)

-#define PT_REGS_PARM1(x) ((x)->gpr[3])
-#define PT_REGS_PARM2(x) ((x)->gpr[4])
-#define PT_REGS_PARM3(x) ((x)->gpr[5])
-#define PT_REGS_PARM4(x) ((x)->gpr[6])
-#define PT_REGS_PARM5(x) ((x)->gpr[7])
-#define PT_REGS_RC(x) ((x)->gpr[3])
-#define PT_REGS_SP(x) ((x)->sp)
-#define PT_REGS_IP(x) ((x)->nip)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), gpr[3])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), gpr[4])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), gpr[5])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), gpr[6])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), gpr[7])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), gpr[3])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), nip)
+#define __PT_PARM1_REG gpr[3]
+#define __PT_PARM2_REG gpr[4]
+#define __PT_PARM3_REG gpr[5]
+#define __PT_PARM4_REG gpr[6]
+#define __PT_PARM5_REG gpr[7]
+#define __PT_RET_REG regs[31]
+#define __PT_FP_REG __unsupported__
+#define __PT_RC_REG gpr[3]
+#define __PT_SP_REG sp
+#define __PT_IP_REG nip

 #elif defined(bpf_target_sparc)

-#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
-#define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1])
-#define PT_REGS_PARM3(x) ((x)->u_regs[UREG_I2])
-#define PT_REGS_PARM4(x) ((x)->u_regs[UREG_I3])
-#define PT_REGS_PARM5(x) ((x)->u_regs[UREG_I4])
-#define PT_REGS_RET(x) ((x)->u_regs[UREG_I7])
-#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
-#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0])
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I1])
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I2])
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I3])
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I4])
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I7])
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0])
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), u_regs[UREG_FP])
-
+#define __PT_PARM1_REG u_regs[UREG_I0]
+#define __PT_PARM2_REG u_regs[UREG_I1]
+#define __PT_PARM3_REG u_regs[UREG_I2]
+#define __PT_PARM4_REG u_regs[UREG_I3]
+#define __PT_PARM5_REG u_regs[UREG_I4]
+#define __PT_RET_REG u_regs[UREG_I7]
+#define __PT_FP_REG __unsupported__
+#define __PT_RC_REG u_regs[UREG_I0]
+#define __PT_SP_REG u_regs[UREG_FP]
 /* Should this also be a bpf_target check for the sparc case? */
 #if defined(__arch64__)
-#define PT_REGS_IP(x) ((x)->tpc)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), tpc)
+#define __PT_IP_REG tpc
 #else
-#define PT_REGS_IP(x) ((x)->pc)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), pc)
+#define __PT_IP_REG pc
 #endif

 #elif defined(bpf_target_riscv)

-struct pt_regs;
-#define PT_REGS_RV const volatile struct user_regs_struct
-#define PT_REGS_PARM1(x) (((PT_REGS_RV *)(x))->a0)
-#define PT_REGS_PARM2(x) (((PT_REGS_RV *)(x))->a1)
-#define PT_REGS_PARM3(x) (((PT_REGS_RV *)(x))->a2)
-#define PT_REGS_PARM4(x) (((PT_REGS_RV *)(x))->a3)
-#define PT_REGS_PARM5(x) (((PT_REGS_RV *)(x))->a4)
-#define PT_REGS_RET(x) (((PT_REGS_RV *)(x))->ra)
-#define PT_REGS_FP(x) (((PT_REGS_RV *)(x))->s5)
-#define PT_REGS_RC(x) (((PT_REGS_RV *)(x))->a5)
-#define PT_REGS_SP(x) (((PT_REGS_RV *)(x))->sp)
-#define PT_REGS_IP(x) (((PT_REGS_RV *)(x))->epc)
-
-#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a0)
-#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a1)
-#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a2)
-#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a3)
-#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a4)
-#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), ra)
-#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), fp)
-#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a5)
-#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), sp)
-#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), epc)
+#define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x))
+#define __PT_PARM1_REG a0
+#define __PT_PARM2_REG a1
+#define __PT_PARM3_REG a2
+#define __PT_PARM4_REG a3
+#define __PT_PARM5_REG a4
+#define __PT_RET_REG ra
+#define __PT_FP_REG fp
+#define __PT_RC_REG a5
+#define __PT_SP_REG sp
+#define __PT_IP_REG epc

 #endif

+#if defined(bpf_target_defined)
+
+struct pt_regs;
+
+/* allow some architecutres to override `struct pt_regs` */
+#ifndef __PT_REGS_CAST
+#define __PT_REGS_CAST(x) (x)
+#endif
+
+#define PT_REGS_PARM1(x) (__PT_REGS_CAST(x)->__PT_PARM1_REG)
+#define PT_REGS_PARM2(x) (__PT_REGS_CAST(x)->__PT_PARM2_REG)
+#define PT_REGS_PARM3(x) (__PT_REGS_CAST(x)->__PT_PARM3_REG)
+#define PT_REGS_PARM4(x) (__PT_REGS_CAST(x)->__PT_PARM4_REG)
+#define PT_REGS_PARM5(x) (__PT_REGS_CAST(x)->__PT_PARM5_REG)
+#define PT_REGS_RET(x) (__PT_REGS_CAST(x)->__PT_RET_REG)
+#define PT_REGS_FP(x) (__PT_REGS_CAST(x)->__PT_FP_REG)
+#define PT_REGS_RC(x) (__PT_REGS_CAST(x)->__PT_RC_REG)
+#define PT_REGS_SP(x) (__PT_REGS_CAST(x)->__PT_SP_REG)
+#define PT_REGS_IP(x) (__PT_REGS_CAST(x)->__PT_IP_REG)
+
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM1_REG)
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM2_REG)
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM3_REG)
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM4_REG)
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM5_REG)
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RET_REG)
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_FP_REG)
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RC_REG)
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_SP_REG)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_IP_REG)
+
 #if defined(bpf_target_powerpc)
+
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = (ctx)->link; })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
+
 #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
-#elif defined(bpf_target_defined)
+
+#else
+
 #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)				    \
-	({ bpf_probe_read_kernel(&(ip), sizeof(ip),			    \
-			  (void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
+	({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
+
 #endif

-#if !defined(bpf_target_defined)
+#else /* defined(bpf_target_defined) */

 #define PT_REGS_PARM1(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
 #define PT_REGS_PARM2(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; })
@@ -363,7 +290,7 @@ struct pt_regs;
 #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) */
+#endif /* defined(bpf_target_defined) */

 #ifndef ___bpf_concat
 #define ___bpf_concat(a, b) a ## b
@@ -375,25 +302,23 @@ struct pt_regs;
 #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_narg(...) ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
 #endif

-#define ___bpf_ctx_cast0() ctx
-#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0]
-#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1]
-#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2]
-#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3]
-#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4]
-#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5]
-#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6]
-#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7]
-#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8]
+#define ___bpf_ctx_cast0()            ctx
+#define ___bpf_ctx_cast1(x)           ___bpf_ctx_cast0(), (void *)ctx[0]
+#define ___bpf_ctx_cast2(x, args...)  ___bpf_ctx_cast1(args), (void *)ctx[1]
+#define ___bpf_ctx_cast3(x, args...)  ___bpf_ctx_cast2(args), (void *)ctx[2]
+#define ___bpf_ctx_cast4(x, args...)  ___bpf_ctx_cast3(args), (void *)ctx[3]
+#define ___bpf_ctx_cast5(x, args...)  ___bpf_ctx_cast4(args), (void *)ctx[4]
+#define ___bpf_ctx_cast6(x, args...)  ___bpf_ctx_cast5(args), (void *)ctx[5]
+#define ___bpf_ctx_cast7(x, args...)  ___bpf_ctx_cast6(args), (void *)ctx[6]
+#define ___bpf_ctx_cast8(x, args...)  ___bpf_ctx_cast7(args), (void *)ctx[7]
+#define ___bpf_ctx_cast9(x, args...)  ___bpf_ctx_cast8(args), (void *)ctx[8]
 #define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9]
 #define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10]
 #define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11]
-#define ___bpf_ctx_cast(args...) \
-	___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args)
+#define ___bpf_ctx_cast(args...)      ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args)

 /*
 * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and
@@ -426,19 +351,13 @@ ____##name(unsigned long long *ctx, ##args)

 struct pt_regs;

-#define ___bpf_kprobe_args0() ctx
-#define ___bpf_kprobe_args1(x) \
-	___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx)
-#define ___bpf_kprobe_args2(x, args...) \
-	___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx)
-#define ___bpf_kprobe_args3(x, args...) \
-	___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx)
-#define ___bpf_kprobe_args4(x, args...) \
-	___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx)
-#define ___bpf_kprobe_args5(x, args...) \
-	___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
-#define ___bpf_kprobe_args(args...) \
-	___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
+#define ___bpf_kprobe_args0()           ctx
+#define ___bpf_kprobe_args1(x)          ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx)
+#define ___bpf_kprobe_args2(x, args...) ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx)
+#define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx)
+#define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx)
+#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
+#define ___bpf_kprobe_args(args...)     ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)

 /*
 * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for
@@ -464,11 +383,9 @@ typeof(name(0)) name(struct pt_regs *ctx)				    \
 static __attribute__((always_inline)) typeof(name(0))			    \
 ____##name(struct pt_regs *ctx, ##args)

-#define ___bpf_kretprobe_args0() ctx
-#define ___bpf_kretprobe_args1(x) \
-	___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx)
-#define ___bpf_kretprobe_args(args...) \
-	___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args)
+#define ___bpf_kretprobe_args0()       ctx
+#define ___bpf_kretprobe_args1(x)      ___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx)
+#define ___bpf_kretprobe_args(args...) ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args)

 /*
 * BPF_KRETPROBE is similar to BPF_KPROBE, except, it only provides optional
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -313,12 +313,18 @@ LIBBPF_API struct btf_dump *btf_dump__new_deprecated(const struct btf *btf,
 *
 * The rest works just like in case of ___libbpf_override() usage with symbol
 * versioning.
+ *
+ * C++ compilers don't support __builtin_types_compatible_p(), so at least
+ * don't screw up compilation for them and let C++ users pick btf_dump__new
+ * vs btf_dump__new_deprecated explicitly.
 */
+#ifndef __cplusplus
 #define btf_dump__new(a1, a2, a3, a4) __builtin_choose_expr(				\
 	__builtin_types_compatible_p(typeof(a4), btf_dump_printf_fn_t) ||		\
 	__builtin_types_compatible_p(typeof(a4), void(void *, const char *, va_list)),	\
 	btf_dump__new_deprecated((void *)a1, (void *)a2, (void *)a3, (void *)a4),	\
 	btf_dump__new((void *)a1, (void *)a2, (void *)a3, (void *)a4))
+#endif

 LIBBPF_API void btf_dump__free(struct btf_dump *d);

--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -2321,8 +2321,8 @@ int btf_dump__dump_type_data(struct btf_dump *d, __u32 id,
 	if (!opts->indent_str)
 		d->typed_dump->indent_str[0] = '\t';
 	else
-		strncat(d->typed_dump->indent_str, opts->indent_str,
-			sizeof(d->typed_dump->indent_str) - 1);
+		libbpf_strlcpy(d->typed_dump->indent_str, opts->indent_str,
+			       sizeof(d->typed_dump->indent_str));

 	d->typed_dump->compact = OPTS_GET(opts, compact, false);
 	d->typed_dump->skip_names = OPTS_GET(opts, skip_names, false);
--- a/tools/lib/bpf/gen_loader.c
+++ b/tools/lib/bpf/gen_loader.c
@@ -371,8 +371,9 @@ int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps)
 {
 	int i;

-	if (nr_progs != gen->nr_progs || nr_maps != gen->nr_maps) {
-		pr_warn("progs/maps mismatch\n");
+	if (nr_progs < gen->nr_progs || nr_maps != gen->nr_maps) {
+		pr_warn("nr_progs %d/%d nr_maps %d/%d mismatch\n",
+			nr_progs, gen->nr_progs, nr_maps, gen->nr_maps);
 		gen->error = -EFAULT;
 		return gen->error;
 	}
@@ -462,8 +463,7 @@ void bpf_gen__map_create(struct bpf_gen *gen,
 	attr.map_flags = map_attr->map_flags;
 	attr.map_extra = map_attr->map_extra;
 	if (map_name)
-		memcpy(attr.map_name, map_name,
-		       min((unsigned)strlen(map_name), BPF_OBJ_NAME_LEN - 1));
+		libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name));
 	attr.numa_node = map_attr->numa_node;
 	attr.map_ifindex = map_attr->map_ifindex;
 	attr.max_entries = max_entries;
@@ -969,8 +969,7 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
 	core_relos = add_data(gen, gen->core_relos,
 			     attr.core_relo_cnt * attr.core_relo_rec_size);

-	memcpy(attr.prog_name, prog_name,
-	       min((unsigned)strlen(prog_name), BPF_OBJ_NAME_LEN - 1));
+	libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
 	prog_load_attr = add_data(gen, &attr, attr_size);

 	/* populate union bpf_attr with a pointer to license */
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -187,42 +187,6 @@ const char *libbpf_version_string(void)
 #undef __S
 }

-enum kern_feature_id {
-	/* v4.14: kernel support for program & map names. */
-	FEAT_PROG_NAME,
-	/* v5.2: kernel support for global data sections. */
-	FEAT_GLOBAL_DATA,
-	/* BTF support */
-	FEAT_BTF,
-	/* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */
-	FEAT_BTF_FUNC,
-	/* BTF_KIND_VAR and BTF_KIND_DATASEC support */
-	FEAT_BTF_DATASEC,
-	/* BTF_FUNC_GLOBAL is supported */
-	FEAT_BTF_GLOBAL_FUNC,
-	/* BPF_F_MMAPABLE is supported for arrays */
-	FEAT_ARRAY_MMAP,
-	/* kernel support for expected_attach_type in BPF_PROG_LOAD */
-	FEAT_EXP_ATTACH_TYPE,
-	/* bpf_probe_read_{kernel,user}[_str] helpers */
-	FEAT_PROBE_READ_KERN,
-	/* BPF_PROG_BIND_MAP is supported */
-	FEAT_PROG_BIND_MAP,
-	/* Kernel support for module BTFs */
-	FEAT_MODULE_BTF,
-	/* BTF_KIND_FLOAT support */
-	FEAT_BTF_FLOAT,
-	/* BPF perf link support */
-	FEAT_PERF_LINK,
-	/* BTF_KIND_DECL_TAG support */
-	FEAT_BTF_DECL_TAG,
-	/* BTF_KIND_TYPE_TAG support */
-	FEAT_BTF_TYPE_TAG,
-	__FEAT_CNT,
-};
-
-static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id);
-
 enum reloc_type {
 	RELO_LD64,
 	RELO_CALL,
@@ -831,11 +795,36 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
 	return 0;
 }

-static __u32 get_kernel_version(void)
+__u32 get_kernel_version(void)
 {
+	/* On Ubuntu LINUX_VERSION_CODE doesn't correspond to info.release,
+	 * but Ubuntu provides /proc/version_signature file, as described at
+	 * https://ubuntu.com/kernel, with an example contents below, which we
+	 * can use to get a proper LINUX_VERSION_CODE.
+	 *
+	 *   Ubuntu 5.4.0-12.15-generic 5.4.8
+	 *
+	 * In the above, 5.4.8 is what kernel is actually expecting, while
+	 * uname() call will return 5.4.0 in info.release.
+	 */
+	const char *ubuntu_kver_file = "/proc/version_signature";
 	__u32 major, minor, patch;
 	struct utsname info;

+	if (access(ubuntu_kver_file, R_OK) == 0) {
+		FILE *f;
+
+		f = fopen(ubuntu_kver_file, "r");
+		if (f) {
+			if (fscanf(f, "%*s %*s %d.%d.%d\n", &major, &minor, &patch) == 3) {
+				fclose(f);
+				return KERNEL_VERSION(major, minor, patch);
+			}
+			fclose(f);
+		}
+		/* something went wrong, fall back to uname() approach */
+	}
+
 	uname(&info);
 	if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3)
 		return 0;
@@ -1201,12 +1190,10 @@ static struct bpf_object *bpf_object__new(const char *path,

 	strcpy(obj->path, path);
 	if (obj_name) {
-		strncpy(obj->name, obj_name, sizeof(obj->name) - 1);
-		obj->name[sizeof(obj->name) - 1] = 0;
+		libbpf_strlcpy(obj->name, obj_name, sizeof(obj->name));
 	} else {
 		/* Using basename() GNU version which doesn't modify arg. */
-		strncpy(obj->name, basename((void *)path),
-			sizeof(obj->name) - 1);
+		libbpf_strlcpy(obj->name, basename((void *)path), sizeof(obj->name));
 		end = strchr(obj->name, '.');
 		if (end)
 			*end = 0;
@@ -1358,7 +1345,10 @@ static int bpf_object__check_endianness(struct bpf_object *obj)
 static int
 bpf_object__init_license(struct bpf_object *obj, void *data, size_t size)
 {
-	memcpy(obj->license, data, min(size, sizeof(obj->license) - 1));
+	/* libbpf_strlcpy() only copies first N - 1 bytes, so size + 1 won't
+	 * go over allowed ELF data section buffer
+	 */
+	libbpf_strlcpy(obj->license, data, min(size + 1, sizeof(obj->license)));
 	pr_debug("license of %s is %s\n", obj->path, obj->license);
 	return 0;
 }
@@ -4354,6 +4344,10 @@ bpf_object__probe_loading(struct bpf_object *obj)
 	if (obj->gen_loader)
 		return 0;

+	ret = bump_rlimit_memlock();
+	if (ret)
+		pr_warn("Failed to bump RLIMIT_MEMLOCK (err = %d), you might need to do it explicitly!\n", ret);
+
 	/* make sure basic loading works */
 	ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL);
 	if (ret < 0)
@@ -4720,14 +4714,17 @@ static struct kern_feature_desc {
 	[FEAT_BTF_TYPE_TAG] = {
 		"BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag,
 	},
+	[FEAT_MEMCG_ACCOUNT] = {
+		"memcg-based memory accounting", probe_memcg_account,
+	},
 };

-static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id)
+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)
+	if (obj && obj->gen_loader)
 		/* To generate loader program assume the latest kernel
 		 * to avoid doing extra prog_load, map_create syscalls.
 		 */
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -227,6 +227,7 @@ struct btf;
 LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj);
 LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj);

+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__find_program_by_name() instead")
 LIBBPF_API struct bpf_program *
 bpf_object__find_program_by_title(const struct bpf_object *obj,
 				  const char *title);
@@ -339,7 +340,31 @@ LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated"
 LIBBPF_API int bpf_program__unpin_instance(struct bpf_program *prog,
 					   const char *path,
 					   int instance);
+
+/**
+ * @brief **bpf_program__pin()** pins the BPF program to a file
+ * in the BPF FS specified by a path. This increments the programs
+ * reference count, allowing it to stay loaded after the process
+ * which loaded it has exited.
+ *
+ * @param prog BPF program to pin, must already be loaded
+ * @param path file path in a BPF file system
+ * @return 0, on success; negative error code, otherwise
+ */
 LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path);
+
+/**
+ * @brief **bpf_program__unpin()** unpins the BPF program from a file
+ * in the BPFFS specified by a path. This decrements the programs
+ * reference count.
+ *
+ * The file pinning the BPF program can also be unlinked by a different
+ * process in which case this function will return an error.
+ *
+ * @param prog BPF program to unpin
+ * @param path file path to the pin in a BPF file system
+ * @return 0, on success; negative error code, otherwise
+ */
 LIBBPF_API int bpf_program__unpin(struct bpf_program *prog, const char *path);
 LIBBPF_API void bpf_program__unload(struct bpf_program *prog);

@@ -1027,13 +1052,57 @@ bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo,
 * user, causing subsequent probes to fail. In this case, the caller may want
 * to adjust that limit with setrlimit().
 */
-LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type,
-				    __u32 ifindex);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_prog_type() instead")
+LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_map_type() instead")
 LIBBPF_API bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex);
-LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id,
-				 enum bpf_prog_type prog_type, __u32 ifindex);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_helper() instead")
+LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type, __u32 ifindex);
+LIBBPF_DEPRECATED_SINCE(0, 8, "implement your own or use bpftool for feature detection")
 LIBBPF_API bool bpf_probe_large_insn_limit(__u32 ifindex);

+/**
+ * @brief **libbpf_probe_bpf_prog_type()** detects if host kernel supports
+ * BPF programs of a given type.
+ * @param prog_type BPF program type to detect kernel support for
+ * @param opts reserved for future extensibility, should be NULL
+ * @return 1, if given program type is supported; 0, if given program type is
+ * not supported; negative error code if feature detection failed or can't be
+ * performed
+ *
+ * Make sure the process has required set of CAP_* permissions (or runs as
+ * root) when performing feature checking.
+ */
+LIBBPF_API int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts);
+/**
+ * @brief **libbpf_probe_bpf_map_type()** detects if host kernel supports
+ * BPF maps of a given type.
+ * @param map_type BPF map type to detect kernel support for
+ * @param opts reserved for future extensibility, should be NULL
+ * @return 1, if given map type is supported; 0, if given map type is
+ * not supported; negative error code if feature detection failed or can't be
+ * performed
+ *
+ * Make sure the process has required set of CAP_* permissions (or runs as
+ * root) when performing feature checking.
+ */
+LIBBPF_API int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts);
+/**
+ * @brief **libbpf_probe_bpf_helper()** detects if host kernel supports the
+ * use of a given BPF helper from specified BPF program type.
+ * @param prog_type BPF program type used to check the support of BPF helper
+ * @param helper_id BPF helper ID (enum bpf_func_id) to check support for
+ * @param opts reserved for future extensibility, should be NULL
+ * @return 1, if given combination of program type and helper is supported; 0,
+ * if the combination is not supported; negative error code if feature
+ * detection for provided input arguments failed or can't be performed
+ *
+ * Make sure the process has required set of CAP_* permissions (or runs as
+ * root) when performing feature checking.
+ */
+LIBBPF_API int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type,
+				       enum bpf_func_id helper_id, const void *opts);
+
 /*
 * Get bpf_prog_info in continuous memory
 *
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -427,4 +427,8 @@ LIBBPF_0.7.0 {
 		bpf_program__log_level;
 		bpf_program__set_log_buf;
 		bpf_program__set_log_level;
+		libbpf_probe_bpf_helper;
+		libbpf_probe_bpf_map_type;
+		libbpf_probe_bpf_prog_type;
+		libbpf_set_memlock_rlim_max;
 };
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -169,6 +169,27 @@ static inline void *libbpf_reallocarray(void *ptr, size_t nmemb, size_t size)
 	return realloc(ptr, total);
 }

+/* Copy up to sz - 1 bytes from zero-terminated src string and ensure that dst
+ * is zero-terminated string no matter what (unless sz == 0, in which case
+ * it's a no-op). It's conceptually close to FreeBSD's strlcpy(), but differs
+ * in what is returned. Given this is internal helper, it's trivial to extend
+ * this, when necessary. Use this instead of strncpy inside libbpf source code.
+ */
+static inline void libbpf_strlcpy(char *dst, const char *src, size_t sz)
+{
+	size_t i;
+
+	if (sz == 0)
+		return;
+
+	sz--;
+	for (i = 0; i < sz && src[i]; i++)
+		dst[i] = src[i];
+	dst[i] = '\0';
+}
+
+__u32 get_kernel_version(void);
+
 struct btf;
 struct btf_type;

@@ -272,6 +293,45 @@ static inline bool libbpf_validate_opts(const char *opts,
 					(opts)->sz - __off);		      \
 })

+enum kern_feature_id {
+	/* v4.14: kernel support for program & map names. */
+	FEAT_PROG_NAME,
+	/* v5.2: kernel support for global data sections. */
+	FEAT_GLOBAL_DATA,
+	/* BTF support */
+	FEAT_BTF,
+	/* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */
+	FEAT_BTF_FUNC,
+	/* BTF_KIND_VAR and BTF_KIND_DATASEC support */
+	FEAT_BTF_DATASEC,
+	/* BTF_FUNC_GLOBAL is supported */
+	FEAT_BTF_GLOBAL_FUNC,
+	/* BPF_F_MMAPABLE is supported for arrays */
+	FEAT_ARRAY_MMAP,
+	/* kernel support for expected_attach_type in BPF_PROG_LOAD */
+	FEAT_EXP_ATTACH_TYPE,
+	/* bpf_probe_read_{kernel,user}[_str] helpers */
+	FEAT_PROBE_READ_KERN,
+	/* BPF_PROG_BIND_MAP is supported */
+	FEAT_PROG_BIND_MAP,
+	/* Kernel support for module BTFs */
+	FEAT_MODULE_BTF,
+	/* BTF_KIND_FLOAT support */
+	FEAT_BTF_FLOAT,
+	/* BPF perf link support */
+	FEAT_PERF_LINK,
+	/* BTF_KIND_DECL_TAG support */
+	FEAT_BTF_DECL_TAG,
+	/* BTF_KIND_TYPE_TAG support */
+	FEAT_BTF_TYPE_TAG,
+	/* memcg-based accounting for BPF maps and progs */
+	FEAT_MEMCG_ACCOUNT,
+	__FEAT_CNT,
+};
+
+int probe_memcg_account(void);
+bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id);
+int bump_rlimit_memlock(void);

 int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz);
 int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz);
--- a/tools/lib/bpf/libbpf_legacy.h
+++ b/tools/lib/bpf/libbpf_legacy.h
@@ -45,7 +45,6 @@ enum libbpf_strict_mode {
 	 * (positive) error code.
 	 */
 	LIBBPF_STRICT_DIRECT_ERRS = 0x02,
-
 	/*
 	 * Enforce strict BPF program section (SEC()) names.
 	 * E.g., while prefiously SEC("xdp_whatever") or SEC("perf_event_blah") were
@@ -63,6 +62,17 @@ enum libbpf_strict_mode {
 	 * Clients can maintain it on their own if it is valuable for them.
 	 */
 	LIBBPF_STRICT_NO_OBJECT_LIST = 0x08,
+	/*
+	 * Automatically bump RLIMIT_MEMLOCK using setrlimit() before the
+	 * first BPF program or map creation operation. This is done only if
+	 * kernel is too old to support memcg-based memory accounting for BPF
+	 * subsystem. By default, RLIMIT_MEMLOCK limit is set to RLIM_INFINITY,
+	 * but it can be overriden with libbpf_set_memlock_rlim_max() API.
+	 * Note that libbpf_set_memlock_rlim_max() needs to be called before
+	 * the very first bpf_prog_load(), bpf_map_create() or bpf_object__load()
+	 * operation.
+	 */
+	LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK = 0x10,

 	__LIBBPF_STRICT_LAST,
 };
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -48,28 +48,20 @@ static int get_vendor_id(int ifindex)
 	return strtol(buf, NULL, 0);
 }

-static int get_kernel_version(void)
+static int probe_prog_load(enum bpf_prog_type prog_type,
+			   const struct bpf_insn *insns, size_t insns_cnt,
+			   char *log_buf, size_t log_buf_sz,
+			   __u32 ifindex)
 {
-	int version, subversion, patchlevel;
-	struct utsname utsn;
-
-	/* Return 0 on failure, and attempt to probe with empty kversion */
-	if (uname(&utsn))
-		return 0;
-
-	if (sscanf(utsn.release, "%d.%d.%d",
-		   &version, &subversion, &patchlevel) != 3)
-		return 0;
-
-	return (version << 16) + (subversion << 8) + patchlevel;
-}
-
-static void
-probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
-	   size_t insns_cnt, char *buf, size_t buf_len, __u32 ifindex)
-{
-	LIBBPF_OPTS(bpf_prog_load_opts, opts);
-	int fd;
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		.log_buf = log_buf,
+		.log_size = log_buf_sz,
+		.log_level = log_buf ? 1 : 0,
+		.prog_ifindex = ifindex,
+	);
+	int fd, err, exp_err = 0;
+	const char *exp_msg = NULL;
+	char buf[4096];

 	switch (prog_type) {
 	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
@@ -84,6 +76,38 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
 	case BPF_PROG_TYPE_KPROBE:
 		opts.kern_version = get_kernel_version();
 		break;
+	case BPF_PROG_TYPE_LIRC_MODE2:
+		opts.expected_attach_type = BPF_LIRC_MODE2;
+		break;
+	case BPF_PROG_TYPE_TRACING:
+	case BPF_PROG_TYPE_LSM:
+		opts.log_buf = buf;
+		opts.log_size = sizeof(buf);
+		opts.log_level = 1;
+		if (prog_type == BPF_PROG_TYPE_TRACING)
+			opts.expected_attach_type = BPF_TRACE_FENTRY;
+		else
+			opts.expected_attach_type = BPF_MODIFY_RETURN;
+		opts.attach_btf_id = 1;
+
+		exp_err = -EINVAL;
+		exp_msg = "attach_btf_id 1 is not a function";
+		break;
+	case BPF_PROG_TYPE_EXT:
+		opts.log_buf = buf;
+		opts.log_size = sizeof(buf);
+		opts.log_level = 1;
+		opts.attach_btf_id = 1;
+
+		exp_err = -EINVAL;
+		exp_msg = "Cannot replace kernel functions";
+		break;
+	case BPF_PROG_TYPE_SYSCALL:
+		opts.prog_flags = BPF_F_SLEEPABLE;
+		break;
+	case BPF_PROG_TYPE_STRUCT_OPS:
+		exp_err = -524; /* -ENOTSUPP */
+		break;
 	case BPF_PROG_TYPE_UNSPEC:
 	case BPF_PROG_TYPE_SOCKET_FILTER:
 	case BPF_PROG_TYPE_SCHED_CLS:
@@ -103,25 +127,42 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
 	case BPF_PROG_TYPE_RAW_TRACEPOINT:
 	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
 	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
-	case BPF_PROG_TYPE_LIRC_MODE2:
 	case BPF_PROG_TYPE_SK_REUSEPORT:
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
-	case BPF_PROG_TYPE_TRACING:
-	case BPF_PROG_TYPE_STRUCT_OPS:
-	case BPF_PROG_TYPE_EXT:
-	case BPF_PROG_TYPE_LSM:
-	default:
 		break;
+	default:
+		return -EOPNOTSUPP;
 	}

-	opts.prog_ifindex = ifindex;
-	opts.log_buf = buf;
-	opts.log_size = buf_len;
-
-	fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, NULL);
+	fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, &opts);
+	err = -errno;
 	if (fd >= 0)
 		close(fd);
+	if (exp_err) {
+		if (fd >= 0 || err != exp_err)
+			return 0;
+		if (exp_msg && !strstr(buf, exp_msg))
+			return 0;
+		return 1;
+	}
+	return fd >= 0 ? 1 : 0;
+}
+
+int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts)
+{
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN()
+	};
+	const size_t insn_cnt = ARRAY_SIZE(insns);
+	int ret;
+
+	if (opts)
+		return libbpf_err(-EINVAL);
+
+	ret = probe_prog_load(prog_type, insns, insn_cnt, NULL, 0, 0);
+	return libbpf_err(ret);
 }

 bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex)
@@ -131,12 +172,16 @@ bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex)
 		BPF_EXIT_INSN()
 	};

+	/* prefer libbpf_probe_bpf_prog_type() unless offload is requested */
+	if (ifindex == 0)
+		return libbpf_probe_bpf_prog_type(prog_type, NULL) == 1;
+
 	if (ifindex && prog_type == BPF_PROG_TYPE_SCHED_CLS)
 		/* nfp returns -EINVAL on exit(0) with TC offload */
 		insns[0].imm = 2;

 	errno = 0;
-	probe_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex);
+	probe_prog_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex);

 	return errno != EINVAL && errno != EOPNOTSUPP;
 }
@@ -197,16 +242,18 @@ static int load_local_storage_btf(void)
 				     strs, sizeof(strs));
 }

-bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
+static int probe_map_create(enum bpf_map_type map_type, __u32 ifindex)
 {
-	int key_size, value_size, max_entries, map_flags;
+	LIBBPF_OPTS(bpf_map_create_opts, opts);
+	int key_size, value_size, max_entries;
 	__u32 btf_key_type_id = 0, btf_value_type_id = 0;
-	int fd = -1, btf_fd = -1, fd_inner;
+	int fd = -1, btf_fd = -1, fd_inner = -1, exp_err = 0, err;
+
+	opts.map_ifindex = ifindex;

 	key_size	= sizeof(__u32);
 	value_size	= sizeof(__u32);
 	max_entries	= 1;
-	map_flags	= 0;

 	switch (map_type) {
 	case BPF_MAP_TYPE_STACK_TRACE:
@@ -215,7 +262,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 	case BPF_MAP_TYPE_LPM_TRIE:
 		key_size	= sizeof(__u64);
 		value_size	= sizeof(__u64);
-		map_flags	= BPF_F_NO_PREALLOC;
+		opts.map_flags	= BPF_F_NO_PREALLOC;
 		break;
 	case BPF_MAP_TYPE_CGROUP_STORAGE:
 	case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE:
@@ -234,17 +281,25 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 		btf_value_type_id = 3;
 		value_size = 8;
 		max_entries = 0;
-		map_flags = BPF_F_NO_PREALLOC;
+		opts.map_flags = BPF_F_NO_PREALLOC;
 		btf_fd = load_local_storage_btf();
 		if (btf_fd < 0)
-			return false;
+			return btf_fd;
 		break;
 	case BPF_MAP_TYPE_RINGBUF:
 		key_size = 0;
 		value_size = 0;
 		max_entries = 4096;
 		break;
-	case BPF_MAP_TYPE_UNSPEC:
+	case BPF_MAP_TYPE_STRUCT_OPS:
+		/* we'll get -ENOTSUPP for invalid BTF type ID for struct_ops */
+		opts.btf_vmlinux_value_type_id = 1;
+		exp_err = -524; /* -ENOTSUPP */
+		break;
+	case BPF_MAP_TYPE_BLOOM_FILTER:
+		key_size = 0;
+		max_entries = 1;
+		break;
 	case BPF_MAP_TYPE_HASH:
 	case BPF_MAP_TYPE_ARRAY:
 	case BPF_MAP_TYPE_PROG_ARRAY:
@@ -263,49 +318,114 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 	case BPF_MAP_TYPE_XSKMAP:
 	case BPF_MAP_TYPE_SOCKHASH:
 	case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
-	case BPF_MAP_TYPE_STRUCT_OPS:
-	default:
 		break;
+	case BPF_MAP_TYPE_UNSPEC:
+	default:
+		return -EOPNOTSUPP;
 	}

 	if (map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
 	    map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
-		LIBBPF_OPTS(bpf_map_create_opts, opts);
-
 		/* TODO: probe for device, once libbpf has a function to create
 		 * map-in-map for offload
 		 */
 		if (ifindex)
-			return false;
+			goto cleanup;

 		fd_inner = bpf_map_create(BPF_MAP_TYPE_HASH, NULL,
 					  sizeof(__u32), sizeof(__u32), 1, NULL);
 		if (fd_inner < 0)
-			return false;
+			goto cleanup;

 		opts.inner_map_fd = fd_inner;
-		fd = bpf_map_create(map_type, NULL, sizeof(__u32), sizeof(__u32), 1, &opts);
-		close(fd_inner);
-	} else {
-		LIBBPF_OPTS(bpf_map_create_opts, opts);
-
-		/* Note: No other restriction on map type probes for offload */
-		opts.map_flags = map_flags;
-		opts.map_ifindex = ifindex;
-		if (btf_fd >= 0) {
-			opts.btf_fd = btf_fd;
-			opts.btf_key_type_id = btf_key_type_id;
-			opts.btf_value_type_id = btf_value_type_id;
-		}
-
-		fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, &opts);
 	}
+
+	if (btf_fd >= 0) {
+		opts.btf_fd = btf_fd;
+		opts.btf_key_type_id = btf_key_type_id;
+		opts.btf_value_type_id = btf_value_type_id;
+	}
+
+	fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, &opts);
+	err = -errno;
+
+cleanup:
 	if (fd >= 0)
 		close(fd);
+	if (fd_inner >= 0)
+		close(fd_inner);
 	if (btf_fd >= 0)
 		close(btf_fd);

-	return fd >= 0;
+	if (exp_err)
+		return fd < 0 && err == exp_err ? 1 : 0;
+	else
+		return fd >= 0 ? 1 : 0;
+}
+
+int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts)
+{
+	int ret;
+
+	if (opts)
+		return libbpf_err(-EINVAL);
+
+	ret = probe_map_create(map_type, 0);
+	return libbpf_err(ret);
+}
+
+bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
+{
+	return probe_map_create(map_type, ifindex) == 1;
+}
+
+int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, enum bpf_func_id helper_id,
+			    const void *opts)
+{
+	struct bpf_insn insns[] = {
+		BPF_EMIT_CALL((__u32)helper_id),
+		BPF_EXIT_INSN(),
+	};
+	const size_t insn_cnt = ARRAY_SIZE(insns);
+	char buf[4096];
+	int ret;
+
+	if (opts)
+		return libbpf_err(-EINVAL);
+
+	/* we can't successfully load all prog types to check for BPF helper
+	 * support, so bail out with -EOPNOTSUPP error
+	 */
+	switch (prog_type) {
+	case BPF_PROG_TYPE_TRACING:
+	case BPF_PROG_TYPE_EXT:
+	case BPF_PROG_TYPE_LSM:
+	case BPF_PROG_TYPE_STRUCT_OPS:
+		return -EOPNOTSUPP;
+	default:
+		break;
+	}
+
+	buf[0] = '\0';
+	ret = probe_prog_load(prog_type, insns, insn_cnt, buf, sizeof(buf), 0);
+	if (ret < 0)
+		return libbpf_err(ret);
+
+	/* If BPF verifier doesn't recognize BPF helper ID (enum bpf_func_id)
+	 * at all, it will emit something like "invalid func unknown#181".
+	 * If BPF verifier recognizes BPF helper but it's not supported for
+	 * given BPF program type, it will emit "unknown func bpf_sys_bpf#166".
+	 * In both cases, provided combination of BPF program type and BPF
+	 * helper is not supported by the kernel.
+	 * In all other cases, probe_prog_load() above will either succeed (e.g.,
+	 * because BPF helper happens to accept no input arguments or it
+	 * accepts one input argument and initial PTR_TO_CTX is fine for
+	 * that), or we'll get some more specific BPF verifier error about
+	 * some unsatisfied conditions.
+	 */
+	if (ret == 0 && (strstr(buf, "invalid func ") || strstr(buf, "unknown func ")))
+		return 0;
+	return 1; /* assume supported */
 }

 bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type,
@@ -318,8 +438,7 @@ bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type,
 	char buf[4096] = {};
 	bool res;

-	probe_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf),
-		   ifindex);
+	probe_prog_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf), ifindex);
 	res = !grep(buf, "invalid func ") && !grep(buf, "unknown func ");

 	if (ifindex) {
@@ -351,8 +470,8 @@ bool bpf_probe_large_insn_limit(__u32 ifindex)
 	insns[BPF_MAXINSNS] = BPF_EXIT_INSN();

 	errno = 0;
-	probe_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0,
-		   ifindex);
+	probe_prog_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0,
+			ifindex);

 	return errno != E2BIG && errno != EINVAL;
 }
--- a/tools/lib/bpf/relo_core.c
+++ b/tools/lib/bpf/relo_core.c
@@ -709,10 +709,14 @@ static int bpf_core_calc_field_relo(const char *prog_name,

 static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo,
 				   const struct bpf_core_spec *spec,
-				   __u32 *val)
+				   __u32 *val, bool *validate)
 {
 	__s64 sz;

+	/* by default, always check expected value in bpf_insn */
+	if (validate)
+		*validate = true;
+
 	/* type-based relos return zero when target type is not found */
 	if (!spec) {
 		*val = 0;
@@ -722,6 +726,11 @@ static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo,
 	switch (relo->kind) {
 	case BPF_CORE_TYPE_ID_TARGET:
 		*val = spec->root_type_id;
+		/* type ID, embedded in bpf_insn, might change during linking,
+		 * so enforcing it is pointless
+		 */
+		if (validate)
+			*validate = false;
 		break;
 	case BPF_CORE_TYPE_EXISTS:
 		*val = 1;
@@ -861,8 +870,8 @@ static int bpf_core_calc_relo(const char *prog_name,
 			res->fail_memsz_adjust = true;
 		}
 	} else if (core_relo_is_type_based(relo->kind)) {
-		err = bpf_core_calc_type_relo(relo, local_spec, &res->orig_val);
-		err = err ?: bpf_core_calc_type_relo(relo, targ_spec, &res->new_val);
+		err = bpf_core_calc_type_relo(relo, local_spec, &res->orig_val, &res->validate);
+		err = err ?: bpf_core_calc_type_relo(relo, targ_spec, &res->new_val, NULL);
 	} else if (core_relo_is_enumval_based(relo->kind)) {
 		err = bpf_core_calc_enumval_relo(relo, local_spec, &res->orig_val);
 		err = err ?: bpf_core_calc_enumval_relo(relo, targ_spec, &res->new_val);
@@ -1213,7 +1222,9 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,

 	/* TYPE_ID_LOCAL relo is special and doesn't need candidate search */
 	if (relo->kind == BPF_CORE_TYPE_ID_LOCAL) {
-		targ_res.validate = true;
+		/* bpf_insn's imm value could get out of sync during linking */
+		memset(&targ_res, 0, sizeof(targ_res));
+		targ_res.validate = false;
 		targ_res.poison = false;
 		targ_res.orig_val = local_spec->root_type_id;
 		targ_res.new_val = local_spec->root_type_id;
@@ -1227,7 +1238,6 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn,
 		return -EOPNOTSUPP;
 	}

-
 	for (i = 0, j = 0; i < cands->len; i++) {
 		err = bpf_core_spec_match(local_spec, cands->cands[i].btf,
 					  cands->cands[i].id, cand_spec);
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -548,8 +548,7 @@ static int xsk_get_max_queues(struct xsk_socket *xsk)
 		return -errno;

 	ifr.ifr_data = (void *)&channels;
-	memcpy(ifr.ifr_name, ctx->ifname, IFNAMSIZ - 1);
-	ifr.ifr_name[IFNAMSIZ - 1] = '\0';
+	libbpf_strlcpy(ifr.ifr_name, ctx->ifname, IFNAMSIZ);
 	err = ioctl(fd, SIOCETHTOOL, &ifr);
 	if (err && errno != EOPNOTSUPP) {
 		ret = -errno;
@@ -768,8 +767,7 @@ static int xsk_create_xsk_struct(int ifindex, struct xsk_socket *xsk)
 	}

 	ctx->ifindex = ifindex;
-	memcpy(ctx->ifname, ifname, IFNAMSIZ -1);
-	ctx->ifname[IFNAMSIZ - 1] = 0;
+	libbpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ);

 	xsk->ctx = ctx;
 	xsk->ctx->has_bpf_link = xsk_probe_bpf_link();
@@ -951,8 +949,7 @@ static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk,
 	ctx->refcount = 1;
 	ctx->umem = umem;
 	ctx->queue_id = queue_id;
-	memcpy(ctx->ifname, ifname, IFNAMSIZ - 1);
-	ctx->ifname[IFNAMSIZ - 1] = '\0';
+	libbpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ);

 	ctx->fill = fill;
 	ctx->comp = comp;
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -3257,10 +3257,21 @@ static void trace__set_bpf_map_syscalls(struct trace *trace)

 static struct bpf_program *trace__find_bpf_program_by_title(struct trace *trace, const char *name)
 {
+	struct bpf_program *pos, *prog = NULL;
+	const char *sec_name;
+
 	if (trace->bpf_obj == NULL)
 		return NULL;

-	return bpf_object__find_program_by_title(trace->bpf_obj, name);
+	bpf_object__for_each_program(pos, trace->bpf_obj) {
+		sec_name = bpf_program__section_name(pos);
+		if (sec_name && !strcmp(sec_name, name)) {
+			prog = pos;
+			break;
+		}
+	}
+
+	return prog;
 }

 static struct bpf_program *trace__find_syscall_bpf_prog(struct trace *trace, struct syscall *sc,
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -87,7 +87,18 @@ LLVM_STRIP	?= llvm-strip

 ifeq ($(CC_NO_CLANG), 1)
 EXTRA_WARNINGS += -Wstrict-aliasing=3
-endif
+
+else ifneq ($(CROSS_COMPILE),)
+CLANG_CROSS_FLAGS := --target=$(notdir $(CROSS_COMPILE:%-=%))
+GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)gcc))
+ifneq ($(GCC_TOOLCHAIN_DIR),)
+CLANG_CROSS_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE))
+CLANG_CROSS_FLAGS += --sysroot=$(shell $(CROSS_COMPILE)gcc -print-sysroot)
+CLANG_CROSS_FLAGS += --gcc-toolchain=$(realpath $(GCC_TOOLCHAIN_DIR)/..)
+endif # GCC_TOOLCHAIN_DIR
+CFLAGS += $(CLANG_CROSS_FLAGS)
+AFLAGS += $(CLANG_CROSS_FLAGS)
+endif # CROSS_COMPILE

 # Hack to avoid type-punned warnings on old systems such as RHEL5:
 # We should be changing CFLAGS and checking gcc version, but this
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -170,7 +170,7 @@ $(OUTPUT)/%:%.c

 $(OUTPUT)/urandom_read: urandom_read.c
 	$(call msg,BINARY,,$@)
-	$(Q)$(CC) $(LDFLAGS) $< $(LDLIBS) -Wl,--build-id=sha1 -o $@
+	$(Q)$(CC) $(CFLAGS) $(LDFLAGS) $< $(LDLIBS) -Wl,--build-id=sha1 -o $@

 $(OUTPUT)/bpf_testmod.ko: $(VMLINUX_BTF) $(wildcard bpf_testmod/Makefile bpf_testmod/*.[ch])
 	$(call msg,MOD,,$@)
@@ -217,7 +217,7 @@ BPFTOOL ?= $(DEFAULT_BPFTOOL)
 $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)    \
 		    $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool
 	$(Q)$(MAKE) $(submake_extras)  -C $(BPFTOOLDIR)			       \
-		    CC=$(HOSTCC) LD=$(HOSTLD)				       \
+		    ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) 	       \
 		    EXTRA_CFLAGS='-g -O0'				       \
 		    OUTPUT=$(HOST_BUILD_DIR)/bpftool/			       \
 		    LIBBPF_OUTPUT=$(HOST_BUILD_DIR)/libbpf/		       \
@@ -248,7 +248,7 @@ $(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \
 		$(APIDIR)/linux/bpf.h					       \
 		| $(HOST_BUILD_DIR)/libbpf
 	$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR)                             \
-		    EXTRA_CFLAGS='-g -O0'				       \
+		    EXTRA_CFLAGS='-g -O0' ARCH= CROSS_COMPILE=		       \
 		    OUTPUT=$(HOST_BUILD_DIR)/libbpf/ CC=$(HOSTCC) LD=$(HOSTLD) \
 		    DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers
 endif
@@ -537,6 +537,7 @@ $(OUTPUT)/bench_ringbufs.o: $(OUTPUT)/ringbuf_bench.skel.h \
 			    $(OUTPUT)/perfbuf_bench.skel.h
 $(OUTPUT)/bench_bloom_filter_map.o: $(OUTPUT)/bloom_filter_bench.skel.h
 $(OUTPUT)/bench_bpf_loop.o: $(OUTPUT)/bpf_loop_bench.skel.h
+$(OUTPUT)/bench_strncmp.o: $(OUTPUT)/strncmp_bench.skel.h
 $(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ)
 $(OUTPUT)/bench: LDLIBS += -lm
 $(OUTPUT)/bench: $(OUTPUT)/bench.o \
@@ -547,9 +548,10 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \
 		 $(OUTPUT)/bench_trigger.o \
 		 $(OUTPUT)/bench_ringbufs.o \
 		 $(OUTPUT)/bench_bloom_filter_map.o \
-		 $(OUTPUT)/bench_bpf_loop.o
+		 $(OUTPUT)/bench_bpf_loop.o \
+		 $(OUTPUT)/bench_strncmp.o
 	$(call msg,BINARY,,$@)
-	$(Q)$(CC) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@
+	$(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@

 EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR)	\
 	prog_tests/tests.h map_tests/tests.h verifier/tests.h		\
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -29,26 +29,10 @@ static int libbpf_print_fn(enum libbpf_print_level level,
 	return vfprintf(stderr, format, args);
 }

-static int bump_memlock_rlimit(void)
+void setup_libbpf(void)
 {
-	struct rlimit rlim_new = {
-		.rlim_cur	= RLIM_INFINITY,
-		.rlim_max	= RLIM_INFINITY,
-	};
-
-	return setrlimit(RLIMIT_MEMLOCK, &rlim_new);
-}
-
-void setup_libbpf()
-{
-	int err;
-
 	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
 	libbpf_set_print(libbpf_print_fn);
-
-	err = bump_memlock_rlimit();
-	if (err)
-		fprintf(stderr, "failed to increase RLIMIT_MEMLOCK: %d", err);
 }

 void false_hits_report_progress(int iter, struct bench_res *res, long delta_ns)
@@ -205,11 +189,13 @@ static const struct argp_option opts[] = {
 extern struct argp bench_ringbufs_argp;
 extern struct argp bench_bloom_map_argp;
 extern struct argp bench_bpf_loop_argp;
+extern struct argp bench_strncmp_argp;

 static const struct argp_child bench_parsers[] = {
 	{ &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 },
 	{ &bench_bloom_map_argp, 0, "Bloom filter map benchmark", 0 },
 	{ &bench_bpf_loop_argp, 0, "bpf_loop helper benchmark", 0 },
+	{ &bench_strncmp_argp, 0, "bpf_strncmp helper benchmark", 0 },
 	{},
 };

@@ -409,6 +395,8 @@ extern const struct bench bench_bloom_false_positive;
 extern const struct bench bench_hashmap_without_bloom;
 extern const struct bench bench_hashmap_with_bloom;
 extern const struct bench bench_bpf_loop;
+extern const struct bench bench_strncmp_no_helper;
+extern const struct bench bench_strncmp_helper;

 static const struct bench *benchs[] = {
 	&bench_count_global,
@@ -441,6 +429,8 @@ static const struct bench *benchs[] = {
 	&bench_hashmap_without_bloom,
 	&bench_hashmap_with_bloom,
 	&bench_bpf_loop,
+	&bench_strncmp_no_helper,
+	&bench_strncmp_helper,
 };

 static void setup_benchmark()
--- a/tools/testing/selftests/bpf/bench.h
+++ b/tools/testing/selftests/bpf/bench.h
@@ -38,8 +38,8 @@ struct bench_res {

 struct bench {
 	const char *name;
-	void (*validate)();
-	void (*setup)();
+	void (*validate)(void);
+	void (*setup)(void);
 	void *(*producer_thread)(void *ctx);
 	void *(*consumer_thread)(void *ctx);
 	void (*measure)(struct bench_res* res);
@@ -54,7 +54,7 @@ struct counter {
 extern struct env env;
 extern const struct bench *bench;

-void setup_libbpf();
+void setup_libbpf(void);
 void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns);
 void hits_drops_report_final(struct bench_res res[], int res_cnt);
 void false_hits_report_progress(int iter, struct bench_res *res, long delta_ns);
@@ -62,7 +62,8 @@ void false_hits_report_final(struct bench_res res[], int res_cnt);
 void ops_report_progress(int iter, struct bench_res *res, long delta_ns);
 void ops_report_final(struct bench_res res[], int res_cnt);

-static inline __u64 get_time_ns() {
+static inline __u64 get_time_ns(void)
+{
 	struct timespec t;

 	clock_gettime(CLOCK_MONOTONIC, &t);
--- a/tools/testing/selftests/bpf/benchs/bench_count.c
+++ b/tools/testing/selftests/bpf/benchs/bench_count.c
@@ -36,7 +36,7 @@ static struct count_local_ctx {
 	struct counter *hits;
 } count_local_ctx;

-static void count_local_setup()
+static void count_local_setup(void)
 {
 	struct count_local_ctx *ctx = &count_local_ctx;

--- a/tools/testing/selftests/bpf/benchs/bench_rename.c
+++ b/tools/testing/selftests/bpf/benchs/bench_rename.c
@@ -11,7 +11,7 @@ static struct ctx {
 	int fd;
 } ctx;

-static void validate()
+static void validate(void)
 {
 	if (env.producer_cnt != 1) {
 		fprintf(stderr, "benchmark doesn't support multi-producer!\n");
@@ -43,7 +43,7 @@ static void measure(struct bench_res *res)
 	res->hits = atomic_swap(&ctx.hits.value, 0);
 }

-static void setup_ctx()
+static void setup_ctx(void)
 {
 	setup_libbpf();

@@ -71,36 +71,36 @@ static void attach_bpf(struct bpf_program *prog)
 	}
 }

-static void setup_base()
+static void setup_base(void)
 {
 	setup_ctx();
 }

-static void setup_kprobe()
+static void setup_kprobe(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.prog1);
 }

-static void setup_kretprobe()
+static void setup_kretprobe(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.prog2);
 }

-static void setup_rawtp()
+static void setup_rawtp(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.prog3);
 }

-static void setup_fentry()
+static void setup_fentry(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.prog4);
 }

-static void setup_fexit()
+static void setup_fexit(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.prog5);
--- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
+++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
@@ -88,12 +88,12 @@ const struct argp bench_ringbufs_argp = {

 static struct counter buf_hits;

-static inline void bufs_trigger_batch()
+static inline void bufs_trigger_batch(void)
 {
 	(void)syscall(__NR_getpgid);
 }

-static void bufs_validate()
+static void bufs_validate(void)
 {
 	if (env.consumer_cnt != 1) {
 		fprintf(stderr, "rb-libbpf benchmark doesn't support multi-consumer!\n");
@@ -132,7 +132,7 @@ static void ringbuf_libbpf_measure(struct bench_res *res)
 	res->drops = atomic_swap(&ctx->skel->bss->dropped, 0);
 }

-static struct ringbuf_bench *ringbuf_setup_skeleton()
+static struct ringbuf_bench *ringbuf_setup_skeleton(void)
 {
 	struct ringbuf_bench *skel;

@@ -167,7 +167,7 @@ static int buf_process_sample(void *ctx, void *data, size_t len)
 	return 0;
 }

-static void ringbuf_libbpf_setup()
+static void ringbuf_libbpf_setup(void)
 {
 	struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx;
 	struct bpf_link *link;
@@ -223,7 +223,7 @@ static void ringbuf_custom_measure(struct bench_res *res)
 	res->drops = atomic_swap(&ctx->skel->bss->dropped, 0);
 }

-static void ringbuf_custom_setup()
+static void ringbuf_custom_setup(void)
 {
 	struct ringbuf_custom_ctx *ctx = &ringbuf_custom_ctx;
 	const size_t page_size = getpagesize();
@@ -352,7 +352,7 @@ static void perfbuf_measure(struct bench_res *res)
 	res->drops = atomic_swap(&ctx->skel->bss->dropped, 0);
 }

-static struct perfbuf_bench *perfbuf_setup_skeleton()
+static struct perfbuf_bench *perfbuf_setup_skeleton(void)
 {
 	struct perfbuf_bench *skel;

@@ -390,7 +390,7 @@ perfbuf_process_sample_raw(void *input_ctx, int cpu,
 	return LIBBPF_PERF_EVENT_CONT;
 }

-static void perfbuf_libbpf_setup()
+static void perfbuf_libbpf_setup(void)
 {
 	struct perfbuf_libbpf_ctx *ctx = &perfbuf_libbpf_ctx;
 	struct perf_event_attr attr;
--- a/tools/testing/selftests/bpf/benchs/bench_strncmp.c
+++ b/tools/testing/selftests/bpf/benchs/bench_strncmp.c
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021. Huawei Technologies Co., Ltd */
+#include <argp.h>
+#include "bench.h"
+#include "strncmp_bench.skel.h"
+
+static struct strncmp_ctx {
+	struct strncmp_bench *skel;
+} ctx;
+
+static struct strncmp_args {
+	u32 cmp_str_len;
+} args = {
+	.cmp_str_len = 32,
+};
+
+enum {
+	ARG_CMP_STR_LEN = 5000,
+};
+
+static const struct argp_option opts[] = {
+	{ "cmp-str-len", ARG_CMP_STR_LEN, "CMP_STR_LEN", 0,
+	  "Set the length of compared string" },
+	{},
+};
+
+static error_t strncmp_parse_arg(int key, char *arg, struct argp_state *state)
+{
+	switch (key) {
+	case ARG_CMP_STR_LEN:
+		args.cmp_str_len = strtoul(arg, NULL, 10);
+		if (!args.cmp_str_len ||
+		    args.cmp_str_len >= sizeof(ctx.skel->bss->str)) {
+			fprintf(stderr, "Invalid cmp str len (limit %zu)\n",
+				sizeof(ctx.skel->bss->str));
+			argp_usage(state);
+		}
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+
+	return 0;
+}
+
+const struct argp bench_strncmp_argp = {
+	.options = opts,
+	.parser = strncmp_parse_arg,
+};
+
+static void strncmp_validate(void)
+{
+	if (env.consumer_cnt != 1) {
+		fprintf(stderr, "strncmp benchmark doesn't support multi-consumer!\n");
+		exit(1);
+	}
+}
+
+static void strncmp_setup(void)
+{
+	int err;
+	char *target;
+	size_t i, sz;
+
+	sz = sizeof(ctx.skel->rodata->target);
+	if (!sz || sz < sizeof(ctx.skel->bss->str)) {
+		fprintf(stderr, "invalid string size (target %zu, src %zu)\n",
+			sz, sizeof(ctx.skel->bss->str));
+		exit(1);
+	}
+
+	setup_libbpf();
+
+	ctx.skel = strncmp_bench__open();
+	if (!ctx.skel) {
+		fprintf(stderr, "failed to open skeleton\n");
+		exit(1);
+	}
+
+	srandom(time(NULL));
+	target = ctx.skel->rodata->target;
+	for (i = 0; i < sz - 1; i++)
+		target[i] = '1' + random() % 9;
+	target[sz - 1] = '\0';
+
+	ctx.skel->rodata->cmp_str_len = args.cmp_str_len;
+
+	memcpy(ctx.skel->bss->str, target, args.cmp_str_len);
+	ctx.skel->bss->str[args.cmp_str_len] = '\0';
+	/* Make bss->str < rodata->target */
+	ctx.skel->bss->str[args.cmp_str_len - 1] -= 1;
+
+	err = strncmp_bench__load(ctx.skel);
+	if (err) {
+		fprintf(stderr, "failed to load skeleton\n");
+		strncmp_bench__destroy(ctx.skel);
+		exit(1);
+	}
+}
+
+static void strncmp_attach_prog(struct bpf_program *prog)
+{
+	struct bpf_link *link;
+
+	link = bpf_program__attach(prog);
+	if (!link) {
+		fprintf(stderr, "failed to attach program!\n");
+		exit(1);
+	}
+}
+
+static void strncmp_no_helper_setup(void)
+{
+	strncmp_setup();
+	strncmp_attach_prog(ctx.skel->progs.strncmp_no_helper);
+}
+
+static void strncmp_helper_setup(void)
+{
+	strncmp_setup();
+	strncmp_attach_prog(ctx.skel->progs.strncmp_helper);
+}
+
+static void *strncmp_producer(void *ctx)
+{
+	while (true)
+		(void)syscall(__NR_getpgid);
+	return NULL;
+}
+
+static void *strncmp_consumer(void *ctx)
+{
+	return NULL;
+}
+
+static void strncmp_measure(struct bench_res *res)
+{
+	res->hits = atomic_swap(&ctx.skel->bss->hits, 0);
+}
+
+const struct bench bench_strncmp_no_helper = {
+	.name = "strncmp-no-helper",
+	.validate = strncmp_validate,
+	.setup = strncmp_no_helper_setup,
+	.producer_thread = strncmp_producer,
+	.consumer_thread = strncmp_consumer,
+	.measure = strncmp_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_strncmp_helper = {
+	.name = "strncmp-helper",
+	.validate = strncmp_validate,
+	.setup = strncmp_helper_setup,
+	.producer_thread = strncmp_producer,
+	.consumer_thread = strncmp_consumer,
+	.measure = strncmp_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
--- a/tools/testing/selftests/bpf/benchs/bench_trigger.c
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -11,7 +11,7 @@ static struct trigger_ctx {

 static struct counter base_hits;

-static void trigger_validate()
+static void trigger_validate(void)
 {
 	if (env.consumer_cnt != 1) {
 		fprintf(stderr, "benchmark doesn't support multi-consumer!\n");
@@ -45,7 +45,7 @@ static void trigger_measure(struct bench_res *res)
 	res->hits = atomic_swap(&ctx.skel->bss->hits, 0);
 }

-static void setup_ctx()
+static void setup_ctx(void)
 {
 	setup_libbpf();

@@ -67,37 +67,37 @@ static void attach_bpf(struct bpf_program *prog)
 	}
 }

-static void trigger_tp_setup()
+static void trigger_tp_setup(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.bench_trigger_tp);
 }

-static void trigger_rawtp_setup()
+static void trigger_rawtp_setup(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.bench_trigger_raw_tp);
 }

-static void trigger_kprobe_setup()
+static void trigger_kprobe_setup(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.bench_trigger_kprobe);
 }

-static void trigger_fentry_setup()
+static void trigger_fentry_setup(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.bench_trigger_fentry);
 }

-static void trigger_fentry_sleep_setup()
+static void trigger_fentry_sleep_setup(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.bench_trigger_fentry_sleep);
 }

-static void trigger_fmodret_setup()
+static void trigger_fmodret_setup(void)
 {
 	setup_ctx();
 	attach_bpf(ctx.skel->progs.bench_trigger_fmodret);
@@ -183,22 +183,22 @@ static void usetup(bool use_retprobe, bool use_nop)
 	ctx.skel->links.bench_trigger_uprobe = link;
 }

-static void uprobe_setup_with_nop()
+static void uprobe_setup_with_nop(void)
 {
 	usetup(false, true);
 }

-static void uretprobe_setup_with_nop()
+static void uretprobe_setup_with_nop(void)
 {
 	usetup(true, true);
 }

-static void uprobe_setup_without_nop()
+static void uprobe_setup_without_nop(void)
 {
 	usetup(false, false);
 }

-static void uretprobe_setup_without_nop()
+static void uretprobe_setup_without_nop(void)
 {
 	usetup(true, false);
 }
--- a/tools/testing/selftests/bpf/benchs/run_bench_strncmp.sh
+++ b/tools/testing/selftests/bpf/benchs/run_bench_strncmp.sh
@@ -0,0 +1,12 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source ./benchs/run_common.sh
+
+set -eufo pipefail
+
+for s in 1 8 64 512 2048 4095; do
+	for b in no-helper helper; do
+		summarize ${b}-${s} "$($RUN_BENCH --cmp-str-len=$s strncmp-${b})"
+	done
+done
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -38,7 +38,9 @@ CONFIG_IPV6_SIT=m
 CONFIG_BPF_JIT=y
 CONFIG_BPF_LSM=y
 CONFIG_SECURITY=y
+CONFIG_RC_CORE=y
 CONFIG_LIRC=y
+CONFIG_BPF_LIRC_MODE2=y
 CONFIG_IMA=y
 CONFIG_SECURITYFS=y
 CONFIG_IMA_WRITE_POLICY=y
--- a/tools/testing/selftests/bpf/prog_tests/align.c
+++ b/tools/testing/selftests/bpf/prog_tests/align.c
@@ -39,13 +39,13 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{1, "R1=ctx(id=0,off=0,imm=0)"},
-			{1, "R10=fp0"},
-			{1, "R3_w=inv2"},
-			{2, "R3_w=inv4"},
-			{3, "R3_w=inv8"},
-			{4, "R3_w=inv16"},
-			{5, "R3_w=inv32"},
+			{0, "R1=ctx(id=0,off=0,imm=0)"},
+			{0, "R10=fp0"},
+			{0, "R3_w=inv2"},
+			{1, "R3_w=inv4"},
+			{2, "R3_w=inv8"},
+			{3, "R3_w=inv16"},
+			{4, "R3_w=inv32"},
 		},
 	},
 	{
@@ -67,19 +67,19 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{1, "R1=ctx(id=0,off=0,imm=0)"},
-			{1, "R10=fp0"},
-			{1, "R3_w=inv1"},
-			{2, "R3_w=inv2"},
-			{3, "R3_w=inv4"},
-			{4, "R3_w=inv8"},
-			{5, "R3_w=inv16"},
-			{6, "R3_w=inv1"},
-			{7, "R4_w=inv32"},
-			{8, "R4_w=inv16"},
-			{9, "R4_w=inv8"},
-			{10, "R4_w=inv4"},
-			{11, "R4_w=inv2"},
+			{0, "R1=ctx(id=0,off=0,imm=0)"},
+			{0, "R10=fp0"},
+			{0, "R3_w=inv1"},
+			{1, "R3_w=inv2"},
+			{2, "R3_w=inv4"},
+			{3, "R3_w=inv8"},
+			{4, "R3_w=inv16"},
+			{5, "R3_w=inv1"},
+			{6, "R4_w=inv32"},
+			{7, "R4_w=inv16"},
+			{8, "R4_w=inv8"},
+			{9, "R4_w=inv4"},
+			{10, "R4_w=inv2"},
 		},
 	},
 	{
@@ -96,14 +96,14 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{1, "R1=ctx(id=0,off=0,imm=0)"},
-			{1, "R10=fp0"},
-			{1, "R3_w=inv4"},
-			{2, "R3_w=inv8"},
-			{3, "R3_w=inv10"},
-			{4, "R4_w=inv8"},
-			{5, "R4_w=inv12"},
-			{6, "R4_w=inv14"},
+			{0, "R1=ctx(id=0,off=0,imm=0)"},
+			{0, "R10=fp0"},
+			{0, "R3_w=inv4"},
+			{1, "R3_w=inv8"},
+			{2, "R3_w=inv10"},
+			{3, "R4_w=inv8"},
+			{4, "R4_w=inv12"},
+			{5, "R4_w=inv14"},
 		},
 	},
 	{
@@ -118,12 +118,12 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{1, "R1=ctx(id=0,off=0,imm=0)"},
-			{1, "R10=fp0"},
+			{0, "R1=ctx(id=0,off=0,imm=0)"},
+			{0, "R10=fp0"},
+			{0, "R3_w=inv7"},
 			{1, "R3_w=inv7"},
-			{2, "R3_w=inv7"},
-			{3, "R3_w=inv14"},
-			{4, "R3_w=inv56"},
+			{2, "R3_w=inv14"},
+			{3, "R3_w=inv56"},
 		},
 	},

@@ -161,19 +161,19 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{7, "R0_w=pkt(id=0,off=8,r=8,imm=0)"},
-			{7, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
-			{8, "R3_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
-			{9, "R3_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
-			{10, "R3_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
-			{11, "R3_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
-			{18, "R3=pkt_end(id=0,off=0,imm=0)"},
-			{18, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
-			{19, "R4_w=inv(id=0,umax_value=8160,var_off=(0x0; 0x1fe0))"},
-			{20, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
-			{21, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
-			{22, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
-			{23, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
+			{6, "R0_w=pkt(id=0,off=8,r=8,imm=0)"},
+			{6, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+			{7, "R3_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
+			{8, "R3_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{9, "R3_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
+			{10, "R3_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
+			{12, "R3_w=pkt_end(id=0,off=0,imm=0)"},
+			{17, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+			{18, "R4_w=inv(id=0,umax_value=8160,var_off=(0x0; 0x1fe0))"},
+			{19, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
+			{20, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
+			{21, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{22, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
 		},
 	},
 	{
@@ -194,16 +194,16 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{7, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
-			{8, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
-			{9, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
-			{10, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
-			{11, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
-			{12, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
-			{13, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
-			{14, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
-			{15, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
-			{16, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
+			{6, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+			{7, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
+			{8, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+			{9, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
+			{10, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
+			{11, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
+			{12, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{13, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
+			{14, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
+			{15, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
 		},
 	},
 	{
@@ -234,14 +234,14 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{4, "R5_w=pkt(id=0,off=0,r=0,imm=0)"},
-			{5, "R5_w=pkt(id=0,off=14,r=0,imm=0)"},
-			{6, "R4_w=pkt(id=0,off=14,r=0,imm=0)"},
-			{10, "R2=pkt(id=0,off=0,r=18,imm=0)"},
+			{2, "R5_w=pkt(id=0,off=0,r=0,imm=0)"},
+			{4, "R5_w=pkt(id=0,off=14,r=0,imm=0)"},
+			{5, "R4_w=pkt(id=0,off=14,r=0,imm=0)"},
+			{9, "R2=pkt(id=0,off=0,r=18,imm=0)"},
 			{10, "R5=pkt(id=0,off=14,r=18,imm=0)"},
 			{10, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+			{13, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"},
 			{14, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"},
-			{15, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"},
 		},
 	},
 	{
@@ -296,8 +296,8 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{8, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
-			{8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
+			{7, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Offset is added to packet pointer R5, resulting in
 			 * known fixed offset, and variable offset from R6.
 			 */
@@ -313,11 +313,11 @@ static struct bpf_align_test tests[] = {
 			/* Variable offset is added to R5 packet pointer,
 			 * resulting in auxiliary alignment of 4.
 			 */
-			{18, "R5_w=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{17, "R5_w=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Constant offset is added to R5, resulting in
 			 * reg->off of 14.
 			 */
-			{19, "R5_w=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{18, "R5_w=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off
 			 * (14) which is 16.  Then the variable offset is 4-byte
@@ -329,18 +329,18 @@ static struct bpf_align_test tests[] = {
 			/* Constant offset is added to R5 packet pointer,
 			 * resulting in reg->off value of 14.
 			 */
-			{26, "R5_w=pkt(id=0,off=14,r=8"},
+			{25, "R5_w=pkt(id=0,off=14,r=8"},
 			/* Variable offset is added to R5, resulting in a
 			 * variable offset of (4n).
 			 */
-			{27, "R5_w=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{26, "R5_w=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Constant is added to R5 again, setting reg->off to 18. */
-			{28, "R5_w=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{27, "R5_w=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* And once more we add a variable; resulting var_off
 			 * is still (4n), fixed offset is not changed.
 			 * Also, we create a new reg->id.
 			 */
-			{29, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc)"},
+			{28, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (18)
 			 * which is 20.  Then the variable offset is (4n), so
@@ -386,13 +386,13 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{8, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
-			{8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
+			{7, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Adding 14 makes R6 be (4n+2) */
-			{9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
+			{8, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
 			/* Packet pointer has (4n+2) offset */
 			{11, "R5_w=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"},
-			{13, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"},
+			{12, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (0)
 			 * which is 2.  Then the variable offset is (4n+2), so
@@ -403,12 +403,12 @@ static struct bpf_align_test tests[] = {
 			/* Newly read value in R6 was shifted left by 2, so has
 			 * known alignment of 4.
 			 */
-			{18, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{17, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Added (4n) to packet pointer's (4n+2) var_off, giving
 			 * another (4n+2).
 			 */
 			{19, "R5_w=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"},
-			{21, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"},
+			{20, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (0)
 			 * which is 2.  Then the variable offset is (4n+2), so
@@ -448,18 +448,18 @@ static struct bpf_align_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = REJECT,
 		.matches = {
-			{4, "R5_w=pkt_end(id=0,off=0,imm=0)"},
+			{3, "R5_w=pkt_end(id=0,off=0,imm=0)"},
 			/* (ptr - ptr) << 2 == unknown, (4n) */
-			{6, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc)"},
+			{5, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc)"},
 			/* (4n) + 14 == (4n+2).  We blow our bounds, because
 			 * the add could overflow.
 			 */
-			{7, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"},
+			{6, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"},
 			/* Checked s>=0 */
 			{9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
 			/* packet pointer + nonnegative (4n+2) */
 			{11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
-			{13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
+			{12, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
 			/* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine.
 			 * We checked the bounds, but it might have been able
 			 * to overflow if the packet pointer started in the
@@ -502,14 +502,14 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{7, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
-			{9, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
+			{8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Adding 14 makes R6 be (4n+2) */
-			{10, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
+			{9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
 			/* New unknown value in R7 is (4n) */
-			{11, "R7_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
+			{10, "R7_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
 			/* Subtracting it from R6 blows our unsigned bounds */
-			{12, "R6=inv(id=0,smin_value=-1006,smax_value=1034,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"},
+			{11, "R6=inv(id=0,smin_value=-1006,smax_value=1034,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"},
 			/* Checked s>= 0 */
 			{14, "R6=inv(id=0,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"},
 			/* At the time the word size load is performed from R5,
@@ -556,14 +556,14 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{7, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
-			{10, "R6_w=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"},
+			{6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"},
+			{9, "R6_w=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"},
 			/* Adding 14 makes R6 be (4n+2) */
-			{11, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"},
+			{10, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"},
 			/* Subtracting from packet pointer overflows ubounds */
 			{13, "R5_w=pkt(id=2,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c)"},
 			/* New unknown value in R7 is (4n), >= 76 */
-			{15, "R7_w=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"},
+			{14, "R7_w=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"},
 			/* Adding it to packet pointer gives nice bounds again */
 			{16, "R5_w=pkt(id=3,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"},
 			/* At the time the word size load is performed from R5,
@@ -625,12 +625,15 @@ static int do_test_single(struct bpf_align_test *test)
 		line_ptr = strtok(bpf_vlog_copy, "\n");
 		for (i = 0; i < MAX_MATCHES; i++) {
 			struct bpf_reg_match m = test->matches[i];
+			int tmp;

 			if (!m.match)
 				break;
 			while (line_ptr) {
 				cur_line = -1;
 				sscanf(line_ptr, "%u: ", &cur_line);
+				if (cur_line == -1)
+					sscanf(line_ptr, "from %u to %u: ", &tmp, &cur_line);
 				if (cur_line == m.line)
 					break;
 				line_ptr = strtok(NULL, "\n");
@@ -642,7 +645,19 @@ static int do_test_single(struct bpf_align_test *test)
 				printf("%s", bpf_vlog);
 				break;
 			}
+			/* Check the next line as well in case the previous line
+			 * did not have a corresponding bpf insn. Example:
+			 * func#0 @0
+			 * 0: R1=ctx(id=0,off=0,imm=0) R10=fp0
+			 * 0: (b7) r3 = 2                 ; R3_w=inv2
+			 */
 			if (!strstr(line_ptr, m.match)) {
+				cur_line = -1;
+				line_ptr = strtok(NULL, "\n");
+				sscanf(line_ptr, "%u: ", &cur_line);
+			}
+			if (cur_line != m.line || !line_ptr ||
+			    !strstr(line_ptr, m.match)) {
 				printf("Failed to find match %u: %s\n",
 				       m.line, m.match);
 				ret = 1;
--- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
@@ -65,8 +65,8 @@ void serial_test_bpf_obj_id(void)
 		if (CHECK_FAIL(err))
 			goto done;

-		prog = bpf_object__find_program_by_title(objs[i],
-							 "raw_tp/sys_enter");
+		prog = bpf_object__find_program_by_name(objs[i],
+							"test_obj_id");
 		if (CHECK_FAIL(!prog))
 			goto done;
 		links[i] = bpf_program__attach(prog);
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -217,7 +217,7 @@ static bool found;
 static int libbpf_debug_print(enum libbpf_print_level level,
 			      const char *format, va_list args)
 {
-	const char *log_buf;
+	const char *prog_name, *log_buf;

 	if (level != LIBBPF_WARN ||
 	    !strstr(format, "-- BEGIN PROG LOAD LOG --")) {
@@ -225,15 +225,14 @@ static int libbpf_debug_print(enum libbpf_print_level level,
 		return 0;
 	}

-	/* skip prog_name */
-	va_arg(args, char *);
+	prog_name = va_arg(args, char *);
 	log_buf = va_arg(args, char *);
 	if (!log_buf)
 		goto out;
 	if (err_str && strstr(log_buf, err_str) != NULL)
 		found = true;
 out:
-	printf(format, log_buf);
+	printf(format, prog_name, log_buf);
 	return 0;
 }

--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -22,7 +22,6 @@
 #include <bpf/libbpf.h>
 #include <bpf/btf.h>

-#include "bpf_rlimit.h"
 #include "bpf_util.h"
 #include "../test_btf.h"
 #include "test_progs.h"
--- a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c
+++ b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c
@@ -67,9 +67,9 @@ static int run_test(int cgroup_fd, int server_fd, int family, int type)
 		goto close_bpf_object;
 	}

-	prog = bpf_object__find_program_by_title(obj, v4 ?
-						 "cgroup/connect4" :
-						 "cgroup/connect6");
+	prog = bpf_object__find_program_by_name(obj, v4 ?
+						"connect4" :
+						"connect6");
 	if (CHECK(!prog, "find_prog", "connect prog not found\n")) {
 		err = -EIO;
 		goto close_bpf_object;
@@ -83,9 +83,9 @@ static int run_test(int cgroup_fd, int server_fd, int family, int type)
 		goto close_bpf_object;
 	}

-	prog = bpf_object__find_program_by_title(obj, v4 ?
-						 "cgroup/getpeername4" :
-						 "cgroup/getpeername6");
+	prog = bpf_object__find_program_by_name(obj, v4 ?
+						"getpeername4" :
+						"getpeername6");
 	if (CHECK(!prog, "find_prog", "getpeername prog not found\n")) {
 		err = -EIO;
 		goto close_bpf_object;
@@ -99,9 +99,9 @@ static int run_test(int cgroup_fd, int server_fd, int family, int type)
 		goto close_bpf_object;
 	}

-	prog = bpf_object__find_program_by_title(obj, v4 ?
-						 "cgroup/getsockname4" :
-						 "cgroup/getsockname6");
+	prog = bpf_object__find_program_by_name(obj, v4 ?
+						"getsockname4" :
+						"getsockname6");
 	if (CHECK(!prog, "find_prog", "getsockname prog not found\n")) {
 		err = -EIO;
 		goto close_bpf_object;
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -10,7 +10,7 @@ static int duration = 0;

 #define STRUCT_TO_CHAR_PTR(struct_name) (const char *)&(struct struct_name)

-#define MODULES_CASE(name, sec_name, tp_name) {				\
+#define MODULES_CASE(name, pg_name, tp_name) {				\
 	.case_name = name,						\
 	.bpf_obj_file = "test_core_reloc_module.o",			\
 	.btf_src_file = NULL, /* find in kernel module BTFs */		\
@@ -28,7 +28,7 @@ static int duration = 0;
 		.comm_len = sizeof("test_progs"),			\
 	},								\
 	.output_len = sizeof(struct core_reloc_module_output),		\
-	.prog_sec_name = sec_name,					\
+	.prog_name = pg_name,						\
 	.raw_tp_name = tp_name,						\
 	.trigger = __trigger_module_test_read,				\
 	.needs_testmod = true,						\
@@ -43,7 +43,9 @@ static int duration = 0;
 #define FLAVORS_CASE_COMMON(name)					\
 	.case_name = #name,						\
 	.bpf_obj_file = "test_core_reloc_flavors.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o"			\
+	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.raw_tp_name = "sys_enter",					\
+	.prog_name = "test_core_flavors"				\

 #define FLAVORS_CASE(name) {						\
 	FLAVORS_CASE_COMMON(name),					\
@@ -66,7 +68,9 @@ static int duration = 0;
 #define NESTING_CASE_COMMON(name)					\
 	.case_name = #name,						\
 	.bpf_obj_file = "test_core_reloc_nesting.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o"
+	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.raw_tp_name = "sys_enter",					\
+	.prog_name = "test_core_nesting"				\

 #define NESTING_CASE(name) {						\
 	NESTING_CASE_COMMON(name),					\
@@ -91,7 +95,9 @@ static int duration = 0;
 #define ARRAYS_CASE_COMMON(name)					\
 	.case_name = #name,						\
 	.bpf_obj_file = "test_core_reloc_arrays.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o"
+	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.raw_tp_name = "sys_enter",					\
+	.prog_name = "test_core_arrays"					\

 #define ARRAYS_CASE(name) {						\
 	ARRAYS_CASE_COMMON(name),					\
@@ -123,7 +129,9 @@ static int duration = 0;
 #define PRIMITIVES_CASE_COMMON(name)					\
 	.case_name = #name,						\
 	.bpf_obj_file = "test_core_reloc_primitives.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o"
+	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.raw_tp_name = "sys_enter",					\
+	.prog_name = "test_core_primitives"				\

 #define PRIMITIVES_CASE(name) {						\
 	PRIMITIVES_CASE_COMMON(name),					\
@@ -158,6 +166,8 @@ static int duration = 0;
 		.e = 5, .f = 6, .g = 7, .h = 8,				\
 	},								\
 	.output_len = sizeof(struct core_reloc_mods_output),		\
+	.raw_tp_name = "sys_enter",					\
+	.prog_name = "test_core_mods",					\
 }

 #define PTR_AS_ARR_CASE(name) {						\
@@ -174,6 +184,8 @@ static int duration = 0;
 		.a = 3,							\
 	},								\
 	.output_len = sizeof(struct core_reloc_ptr_as_arr),		\
+	.raw_tp_name = "sys_enter",					\
+	.prog_name = "test_core_ptr_as_arr",				\
 }

 #define INTS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) {	\
@@ -190,7 +202,9 @@ static int duration = 0;
 #define INTS_CASE_COMMON(name)						\
 	.case_name = #name,						\
 	.bpf_obj_file = "test_core_reloc_ints.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o"
+	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.raw_tp_name = "sys_enter",					\
+	.prog_name = "test_core_ints"

 #define INTS_CASE(name) {						\
 	INTS_CASE_COMMON(name),						\
@@ -208,7 +222,9 @@ static int duration = 0;
 #define FIELD_EXISTS_CASE_COMMON(name)					\
 	.case_name = #name,						\
 	.bpf_obj_file = "test_core_reloc_existence.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o"			\
+	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.raw_tp_name = "sys_enter",					\
+	.prog_name = "test_core_existence"

 #define BITFIELDS_CASE_COMMON(objfile, test_name_prefix,  name)		\
 	.case_name = test_name_prefix#name,				\
@@ -223,6 +239,8 @@ static int duration = 0;
 	.output = STRUCT_TO_CHAR_PTR(core_reloc_bitfields_output)	\
 		__VA_ARGS__,						\
 	.output_len = sizeof(struct core_reloc_bitfields_output),	\
+	.raw_tp_name = "sys_enter",					\
+	.prog_name = "test_core_bitfields",				\
 }, {									\
 	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_direct.o",	\
 			      "direct:", name),				\
@@ -231,7 +249,7 @@ static int duration = 0;
 	.output = STRUCT_TO_CHAR_PTR(core_reloc_bitfields_output)	\
 		__VA_ARGS__,						\
 	.output_len = sizeof(struct core_reloc_bitfields_output),	\
-	.prog_sec_name = "tp_btf/sys_enter",				\
+	.prog_name = "test_core_bitfields_direct",			\
 }


@@ -239,17 +257,21 @@ static int duration = 0;
 	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_probed.o",	\
 			      "probed:", name),				\
 	.fails = true,							\
+	.raw_tp_name = "sys_enter",					\
+	.prog_name = "test_core_bitfields",				\
 }, {									\
 	BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_direct.o",	\
 			      "direct:", name),				\
-	.prog_sec_name = "tp_btf/sys_enter",				\
 	.fails = true,							\
+	.prog_name = "test_core_bitfields_direct",			\
 }

 #define SIZE_CASE_COMMON(name)						\
 	.case_name = #name,						\
 	.bpf_obj_file = "test_core_reloc_size.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o"
+	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.raw_tp_name = "sys_enter",					\
+	.prog_name = "test_core_size"

 #define SIZE_OUTPUT_DATA(type)						\
 	STRUCT_TO_CHAR_PTR(core_reloc_size_output) {			\
@@ -277,8 +299,10 @@ static int duration = 0;

 #define TYPE_BASED_CASE_COMMON(name)					\
 	.case_name = #name,						\
-	.bpf_obj_file = "test_core_reloc_type_based.o",		\
-	.btf_src_file = "btf__core_reloc_" #name ".o"			\
+	.bpf_obj_file = "test_core_reloc_type_based.o",			\
+	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.raw_tp_name = "sys_enter",					\
+	.prog_name = "test_core_type_based"

 #define TYPE_BASED_CASE(name, ...) {					\
 	TYPE_BASED_CASE_COMMON(name),					\
@@ -295,7 +319,9 @@ static int duration = 0;
 #define TYPE_ID_CASE_COMMON(name)					\
 	.case_name = #name,						\
 	.bpf_obj_file = "test_core_reloc_type_id.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o"			\
+	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.raw_tp_name = "sys_enter",					\
+	.prog_name = "test_core_type_id"

 #define TYPE_ID_CASE(name, setup_fn) {					\
 	TYPE_ID_CASE_COMMON(name),					\
@@ -312,7 +338,9 @@ static int duration = 0;
 #define ENUMVAL_CASE_COMMON(name)					\
 	.case_name = #name,						\
 	.bpf_obj_file = "test_core_reloc_enumval.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o"			\
+	.btf_src_file = "btf__core_reloc_" #name ".o",			\
+	.raw_tp_name = "sys_enter",					\
+	.prog_name = "test_core_enumval"

 #define ENUMVAL_CASE(name, ...) {					\
 	ENUMVAL_CASE_COMMON(name),					\
@@ -342,7 +370,7 @@ struct core_reloc_test_case {
 	bool fails;
 	bool needs_testmod;
 	bool relaxed_core_relocs;
-	const char *prog_sec_name;
+	const char *prog_name;
 	const char *raw_tp_name;
 	setup_test_fn setup;
 	trigger_test_fn trigger;
@@ -497,11 +525,13 @@ static struct core_reloc_test_case test_cases[] = {
 			.comm_len = sizeof("test_progs"),
 		},
 		.output_len = sizeof(struct core_reloc_kernel_output),
+		.raw_tp_name = "sys_enter",
+		.prog_name = "test_core_kernel",
 	},

 	/* validate we can find kernel module BTF types for relocs/attach */
-	MODULES_CASE("module_probed", "raw_tp/bpf_testmod_test_read", "bpf_testmod_test_read"),
-	MODULES_CASE("module_direct", "tp_btf/bpf_testmod_test_read", NULL),
+	MODULES_CASE("module_probed", "test_core_module_probed", "bpf_testmod_test_read"),
+	MODULES_CASE("module_direct", "test_core_module_direct", NULL),

 	/* validate BPF program can use multiple flavors to match against
 	 * single target BTF type
@@ -580,6 +610,8 @@ static struct core_reloc_test_case test_cases[] = {
 			.c = 0, /* BUG in clang, should be 3 */
 		},
 		.output_len = sizeof(struct core_reloc_misc_output),
+		.raw_tp_name = "sys_enter",
+		.prog_name = "test_core_misc",
 	},

 	/* validate field existence checks */
@@ -848,14 +880,9 @@ void test_core_reloc(void)
 		if (!ASSERT_OK_PTR(obj, "obj_open"))
 			goto cleanup;

-		probe_name = "raw_tracepoint/sys_enter";
-		tp_name = "sys_enter";
-		if (test_case->prog_sec_name) {
-			probe_name = test_case->prog_sec_name;
-			tp_name = test_case->raw_tp_name; /* NULL for tp_btf */
-		}
-
-		prog = bpf_object__find_program_by_title(obj, probe_name);
+		probe_name = test_case->prog_name;
+		tp_name = test_case->raw_tp_name; /* NULL for tp_btf */
+		prog = bpf_object__find_program_by_name(obj, probe_name);
 		if (CHECK(!prog, "find_probe",
 			  "prog '%s' not found\n", probe_name))
 			goto cleanup;
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -101,6 +101,8 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,

 	for (i = 0; i < prog_cnt; i++) {
 		struct bpf_link_info link_info;
+		struct bpf_program *pos;
+		const char *pos_sec_name;
 		char *tgt_name;
 		__s32 btf_id;

@@ -109,7 +111,14 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 			goto close_prog;
 		btf_id = btf__find_by_name_kind(btf, tgt_name + 1, BTF_KIND_FUNC);

-		prog[i] = bpf_object__find_program_by_title(obj, prog_name[i]);
+		prog[i] = NULL;
+		bpf_object__for_each_program(pos, obj) {
+			pos_sec_name = bpf_program__section_name(pos);
+			if (pos_sec_name && !strcmp(pos_sec_name, prog_name[i])) {
+				prog[i] = pos;
+				break;
+			}
+		}
 		if (!ASSERT_OK_PTR(prog[i], prog_name[i]))
 			goto close_prog;

@@ -211,8 +220,8 @@ static void test_func_replace_verify(void)

 static int test_second_attach(struct bpf_object *obj)
 {
-	const char *prog_name = "freplace/get_constant";
-	const char *tgt_name = prog_name + 9; /* cut off freplace/ */
+	const char *prog_name = "security_new_get_constant";
+	const char *tgt_name = "get_constant";
 	const char *tgt_obj_file = "./test_pkt_access.o";
 	struct bpf_program *prog = NULL;
 	struct bpf_object *tgt_obj;
@@ -220,7 +229,7 @@ static int test_second_attach(struct bpf_object *obj)
 	struct bpf_link *link;
 	int err = 0, tgt_fd;

-	prog = bpf_object__find_program_by_title(obj, prog_name);
+	prog = bpf_object__find_program_by_name(obj, prog_name);
 	if (CHECK(!prog, "find_prog", "prog %s not found\n", prog_name))
 		return -ENOENT;

--- a/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "get_func_args_test.skel.h"
+
+void test_get_func_args_test(void)
+{
+	struct get_func_args_test *skel = NULL;
+	__u32 duration = 0, retval;
+	int err, prog_fd;
+
+	skel = get_func_args_test__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "get_func_args_test__open_and_load"))
+		return;
+
+	err = get_func_args_test__attach(skel);
+	if (!ASSERT_OK(err, "get_func_args_test__attach"))
+		goto cleanup;
+
+	/* This runs bpf_fentry_test* functions and triggers
+	 * fentry/fexit programs.
+	 */
+	prog_fd = bpf_program__fd(skel->progs.test1);
+	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
+				NULL, NULL, &retval, &duration);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(retval, 0, "test_run");
+
+	/* This runs bpf_modify_return_test function and triggers
+	 * fmod_ret_test and fexit_test programs.
+	 */
+	prog_fd = bpf_program__fd(skel->progs.fmod_ret_test);
+	err = bpf_prog_test_run(prog_fd, 1, NULL, 0,
+				NULL, NULL, &retval, &duration);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(retval, 1234, "test_run");
+
+	ASSERT_EQ(skel->bss->test1_result, 1, "test1_result");
+	ASSERT_EQ(skel->bss->test2_result, 1, "test2_result");
+	ASSERT_EQ(skel->bss->test3_result, 1, "test3_result");
+	ASSERT_EQ(skel->bss->test4_result, 1, "test4_result");
+
+cleanup:
+	get_func_args_test__destroy(skel);
+}
--- a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
@@ -89,7 +89,7 @@ void test_get_stack_raw_tp(void)
 {
 	const char *file = "./test_get_stack_rawtp.o";
 	const char *file_err = "./test_get_stack_rawtp_err.o";
-	const char *prog_name = "raw_tracepoint/sys_enter";
+	const char *prog_name = "bpf_prog1";
 	int i, err, prog_fd, exp_cnt = MAX_CNT_RAWTP;
 	struct perf_buffer *pb = NULL;
 	struct bpf_link *link = NULL;
@@ -107,7 +107,7 @@ void test_get_stack_raw_tp(void)
 	if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno))
 		return;

-	prog = bpf_object__find_program_by_title(obj, prog_name);
+	prog = bpf_object__find_program_by_name(obj, prog_name);
 	if (CHECK(!prog, "find_probe", "prog '%s' not found\n", prog_name))
 		goto close_prog;

--- a/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
@@ -8,6 +8,7 @@
 #include "test_ksyms_btf_null_check.skel.h"
 #include "test_ksyms_weak.skel.h"
 #include "test_ksyms_weak.lskel.h"
+#include "test_ksyms_btf_write_check.skel.h"

 static int duration;

@@ -137,6 +138,16 @@ cleanup:
 	test_ksyms_weak_lskel__destroy(skel);
 }

+static void test_write_check(void)
+{
+	struct test_ksyms_btf_write_check *skel;
+
+	skel = test_ksyms_btf_write_check__open_and_load();
+	ASSERT_ERR_PTR(skel, "unexpected load of a prog writing to ksym memory\n");
+
+	test_ksyms_btf_write_check__destroy(skel);
+}
+
 void test_ksyms_btf(void)
 {
 	int percpu_datasec;
@@ -167,4 +178,7 @@ void test_ksyms_btf(void)

 	if (test__start_subtest("weak_ksyms_lskel"))
 		test_weak_syms_lskel();
+
+	if (test__start_subtest("write_check"))
+		test_write_check();
 }
--- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
+++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2021 Facebook */
+
+#include <test_progs.h>
+#include <bpf/btf.h>
+
+void test_libbpf_probe_prog_types(void)
+{
+	struct btf *btf;
+	const struct btf_type *t;
+	const struct btf_enum *e;
+	int i, n, id;
+
+	btf = btf__parse("/sys/kernel/btf/vmlinux", NULL);
+	if (!ASSERT_OK_PTR(btf, "btf_parse"))
+		return;
+
+	/* find enum bpf_prog_type and enumerate each value */
+	id = btf__find_by_name_kind(btf, "bpf_prog_type", BTF_KIND_ENUM);
+	if (!ASSERT_GT(id, 0, "bpf_prog_type_id"))
+		goto cleanup;
+	t = btf__type_by_id(btf, id);
+	if (!ASSERT_OK_PTR(t, "bpf_prog_type_enum"))
+		goto cleanup;
+
+	for (e = btf_enum(t), i = 0, n = btf_vlen(t); i < n; e++, i++) {
+		const char *prog_type_name = btf__str_by_offset(btf, e->name_off);
+		enum bpf_prog_type prog_type = (enum bpf_prog_type)e->val;
+		int res;
+
+		if (prog_type == BPF_PROG_TYPE_UNSPEC)
+			continue;
+
+		if (!test__start_subtest(prog_type_name))
+			continue;
+
+		res = libbpf_probe_bpf_prog_type(prog_type, NULL);
+		ASSERT_EQ(res, 1, prog_type_name);
+	}
+
+cleanup:
+	btf__free(btf);
+}
+
+void test_libbpf_probe_map_types(void)
+{
+	struct btf *btf;
+	const struct btf_type *t;
+	const struct btf_enum *e;
+	int i, n, id;
+
+	btf = btf__parse("/sys/kernel/btf/vmlinux", NULL);
+	if (!ASSERT_OK_PTR(btf, "btf_parse"))
+		return;
+
+	/* find enum bpf_map_type and enumerate each value */
+	id = btf__find_by_name_kind(btf, "bpf_map_type", BTF_KIND_ENUM);
+	if (!ASSERT_GT(id, 0, "bpf_map_type_id"))
+		goto cleanup;
+	t = btf__type_by_id(btf, id);
+	if (!ASSERT_OK_PTR(t, "bpf_map_type_enum"))
+		goto cleanup;
+
+	for (e = btf_enum(t), i = 0, n = btf_vlen(t); i < n; e++, i++) {
+		const char *map_type_name = btf__str_by_offset(btf, e->name_off);
+		enum bpf_map_type map_type = (enum bpf_map_type)e->val;
+		int res;
+
+		if (map_type == BPF_MAP_TYPE_UNSPEC)
+			continue;
+
+		if (!test__start_subtest(map_type_name))
+			continue;
+
+		res = libbpf_probe_bpf_map_type(map_type, NULL);
+		ASSERT_EQ(res, 1, map_type_name);
+	}
+
+cleanup:
+	btf__free(btf);
+}
+
+void test_libbpf_probe_helpers(void)
+{
+#define CASE(prog, helper, supp) {			\
+	.prog_type_name = "BPF_PROG_TYPE_" # prog,	\
+	.helper_name = "bpf_" # helper,			\
+	.prog_type = BPF_PROG_TYPE_ ## prog,		\
+	.helper_id = BPF_FUNC_ ## helper,		\
+	.supported = supp,				\
+}
+	const struct case_def {
+		const char *prog_type_name;
+		const char *helper_name;
+		enum bpf_prog_type prog_type;
+		enum bpf_func_id helper_id;
+		bool supported;
+	} cases[] = {
+		CASE(KPROBE, unspec, false),
+		CASE(KPROBE, map_lookup_elem, true),
+		CASE(KPROBE, loop, true),
+
+		CASE(KPROBE, ktime_get_coarse_ns, false),
+		CASE(SOCKET_FILTER, ktime_get_coarse_ns, true),
+
+		CASE(KPROBE, sys_bpf, false),
+		CASE(SYSCALL, sys_bpf, true),
+	};
+	size_t case_cnt = ARRAY_SIZE(cases), i;
+	char buf[128];
+
+	for (i = 0; i < case_cnt; i++) {
+		const struct case_def *d = &cases[i];
+		int res;
+
+		snprintf(buf, sizeof(buf), "%s+%s", d->prog_type_name, d->helper_name);
+
+		if (!test__start_subtest(buf))
+			continue;
+
+		res = libbpf_probe_bpf_helper(d->prog_type, d->helper_id, NULL);
+		ASSERT_EQ(res, d->supported, buf);
+	}
+}
--- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
+++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
@@ -18,7 +18,6 @@
 #include <netinet/in.h>
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
-#include "bpf_rlimit.h"
 #include "bpf_util.h"

 #include "test_progs.h"
--- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
+++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
@@ -30,7 +30,6 @@
 #include <bpf/bpf.h>

 #include "test_progs.h"
-#include "bpf_rlimit.h"
 #include "bpf_util.h"
 #include "cgroup_helpers.h"
 #include "network_helpers.h"
--- a/tools/testing/selftests/bpf/prog_tests/sock_fields.c
+++ b/tools/testing/selftests/bpf/prog_tests/sock_fields.c
@@ -15,7 +15,6 @@
 #include "network_helpers.h"
 #include "cgroup_helpers.h"
 #include "test_progs.h"
-#include "bpf_rlimit.h"
 #include "test_sock_fields.skel.h"

 enum bpf_linum_array_idx {
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
@@ -136,7 +136,8 @@ static int start_server(void)
 	return fd;
 }

-static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title)
+static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title,
+		       const char *prog_name)
 {
 	enum bpf_attach_type attach_type;
 	enum bpf_prog_type prog_type;
@@ -145,20 +146,20 @@ static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title)

 	err = libbpf_prog_type_by_name(title, &prog_type, &attach_type);
 	if (err) {
-		log_err("Failed to deduct types for %s BPF program", title);
+		log_err("Failed to deduct types for %s BPF program", prog_name);
 		return -1;
 	}

-	prog = bpf_object__find_program_by_title(obj, title);
+	prog = bpf_object__find_program_by_name(obj, prog_name);
 	if (!prog) {
-		log_err("Failed to find %s BPF program", title);
+		log_err("Failed to find %s BPF program", prog_name);
 		return -1;
 	}

 	err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd,
 			      attach_type, 0);
 	if (err) {
-		log_err("Failed to attach %s BPF program", title);
+		log_err("Failed to attach %s BPF program", prog_name);
 		return -1;
 	}

@@ -181,11 +182,11 @@ static void run_test(int cgroup_fd)
 	if (!ASSERT_OK(err, "obj_load"))
 		goto close_bpf_object;

-	err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt");
+	err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt", "_getsockopt");
 	if (CHECK_FAIL(err))
 		goto close_bpf_object;

-	err = prog_attach(obj, cgroup_fd, "cgroup/setsockopt");
+	err = prog_attach(obj, cgroup_fd, "cgroup/setsockopt", "_setsockopt");
 	if (CHECK_FAIL(err))
 		goto close_bpf_object;

--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
@@ -4,7 +4,7 @@
 void test_stacktrace_map(void)
 {
 	int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
-	const char *prog_name = "tracepoint/sched/sched_switch";
+	const char *prog_name = "oncpu";
 	int err, prog_fd, stack_trace_len;
 	const char *file = "./test_stacktrace_map.o";
 	__u32 key, val, duration = 0;
@@ -16,7 +16,7 @@ void test_stacktrace_map(void)
 	if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
 		return;

-	prog = bpf_object__find_program_by_title(obj, prog_name);
+	prog = bpf_object__find_program_by_name(obj, prog_name);
 	if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name))
 		goto close_prog;

--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
@@ -3,7 +3,7 @@

 void test_stacktrace_map_raw_tp(void)
 {
-	const char *prog_name = "tracepoint/sched/sched_switch";
+	const char *prog_name = "oncpu";
 	int control_map_fd, stackid_hmap_fd, stackmap_fd;
 	const char *file = "./test_stacktrace_map.o";
 	__u32 key, val, duration = 0;
@@ -16,7 +16,7 @@ void test_stacktrace_map_raw_tp(void)
 	if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno))
 		return;

-	prog = bpf_object__find_program_by_title(obj, prog_name);
+	prog = bpf_object__find_program_by_name(obj, prog_name);
 	if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name))
 		goto close_prog;

--- a/tools/testing/selftests/bpf/prog_tests/test_local_storage.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_local_storage.c
@@ -28,10 +28,6 @@ static unsigned int duration;
 struct storage {
 	void *inode;
 	unsigned int value;
-	/* Lock ensures that spin locked versions of local stoage operations
-	 * also work, most operations in this tests are still single threaded
-	 */
-	struct bpf_spin_lock lock;
 };

 /* Fork and exec the provided rm binary and return the exit code of the
@@ -66,27 +62,24 @@ static int run_self_unlink(int *monitored_pid, const char *rm_path)

 static bool check_syscall_operations(int map_fd, int obj_fd)
 {
-	struct storage val = { .value = TEST_STORAGE_VALUE, .lock = { 0 } },
-		       lookup_val = { .value = 0, .lock = { 0 } };
+	struct storage val = { .value = TEST_STORAGE_VALUE },
+		       lookup_val = { .value = 0 };
 	int err;

 	/* Looking up an existing element should fail initially */
-	err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val,
-					BPF_F_LOCK);
+	err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val, 0);
 	if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem",
 		  "err:%d errno:%d\n", err, errno))
 		return false;

 	/* Create a new element */
-	err = bpf_map_update_elem(map_fd, &obj_fd, &val,
-				  BPF_NOEXIST | BPF_F_LOCK);
+	err = bpf_map_update_elem(map_fd, &obj_fd, &val, BPF_NOEXIST);
 	if (CHECK(err < 0, "bpf_map_update_elem", "err:%d errno:%d\n", err,
 		  errno))
 		return false;

 	/* Lookup the newly created element */
-	err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val,
-					BPF_F_LOCK);
+	err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val, 0);
 	if (CHECK(err < 0, "bpf_map_lookup_elem", "err:%d errno:%d", err,
 		  errno))
 		return false;
@@ -102,8 +95,7 @@ static bool check_syscall_operations(int map_fd, int obj_fd)
 		return false;

 	/* The lookup should fail, now that the element has been deleted */
-	err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val,
-					BPF_F_LOCK);
+	err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val, 0);
 	if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem",
 		  "err:%d errno:%d\n", err, errno))
 		return false;
--- a/tools/testing/selftests/bpf/prog_tests/test_overhead.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_overhead.c
@@ -56,11 +56,11 @@ static void setaffinity(void)

 void test_test_overhead(void)
 {
-	const char *kprobe_name = "kprobe/__set_task_comm";
-	const char *kretprobe_name = "kretprobe/__set_task_comm";
-	const char *raw_tp_name = "raw_tp/task_rename";
-	const char *fentry_name = "fentry/__set_task_comm";
-	const char *fexit_name = "fexit/__set_task_comm";
+	const char *kprobe_name = "prog1";
+	const char *kretprobe_name = "prog2";
+	const char *raw_tp_name = "prog3";
+	const char *fentry_name = "prog4";
+	const char *fexit_name = "prog5";
 	const char *kprobe_func = "__set_task_comm";
 	struct bpf_program *kprobe_prog, *kretprobe_prog, *raw_tp_prog;
 	struct bpf_program *fentry_prog, *fexit_prog;
@@ -76,23 +76,23 @@ void test_test_overhead(void)
 	if (!ASSERT_OK_PTR(obj, "obj_open_file"))
 		return;

-	kprobe_prog = bpf_object__find_program_by_title(obj, kprobe_name);
+	kprobe_prog = bpf_object__find_program_by_name(obj, kprobe_name);
 	if (CHECK(!kprobe_prog, "find_probe",
 		  "prog '%s' not found\n", kprobe_name))
 		goto cleanup;
-	kretprobe_prog = bpf_object__find_program_by_title(obj, kretprobe_name);
+	kretprobe_prog = bpf_object__find_program_by_name(obj, kretprobe_name);
 	if (CHECK(!kretprobe_prog, "find_probe",
 		  "prog '%s' not found\n", kretprobe_name))
 		goto cleanup;
-	raw_tp_prog = bpf_object__find_program_by_title(obj, raw_tp_name);
+	raw_tp_prog = bpf_object__find_program_by_name(obj, raw_tp_name);
 	if (CHECK(!raw_tp_prog, "find_probe",
 		  "prog '%s' not found\n", raw_tp_name))
 		goto cleanup;
-	fentry_prog = bpf_object__find_program_by_title(obj, fentry_name);
+	fentry_prog = bpf_object__find_program_by_name(obj, fentry_name);
 	if (CHECK(!fentry_prog, "find_probe",
 		  "prog '%s' not found\n", fentry_name))
 		goto cleanup;
-	fexit_prog = bpf_object__find_program_by_title(obj, fexit_name);
+	fexit_prog = bpf_object__find_program_by_name(obj, fexit_name);
 	if (CHECK(!fexit_prog, "find_probe",
 		  "prog '%s' not found\n", fexit_name))
 		goto cleanup;
--- a/tools/testing/selftests/bpf/prog_tests/test_strncmp.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_strncmp.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021. Huawei Technologies Co., Ltd */
+#include <test_progs.h>
+#include "strncmp_test.skel.h"
+
+static int trigger_strncmp(const struct strncmp_test *skel)
+{
+	int cmp;
+
+	usleep(1);
+
+	cmp = skel->bss->cmp_ret;
+	if (cmp > 0)
+		return 1;
+	if (cmp < 0)
+		return -1;
+	return 0;
+}
+
+/*
+ * Compare str and target after making str[i] != target[i].
+ * When exp is -1, make str[i] < target[i] and delta = -1.
+ */
+static void strncmp_full_str_cmp(struct strncmp_test *skel, const char *name,
+				 int exp)
+{
+	size_t nr = sizeof(skel->bss->str);
+	char *str = skel->bss->str;
+	int delta = exp;
+	int got;
+	size_t i;
+
+	memcpy(str, skel->rodata->target, nr);
+	for (i = 0; i < nr - 1; i++) {
+		str[i] += delta;
+
+		got = trigger_strncmp(skel);
+		ASSERT_EQ(got, exp, name);
+
+		str[i] -= delta;
+	}
+}
+
+static void test_strncmp_ret(void)
+{
+	struct strncmp_test *skel;
+	struct bpf_program *prog;
+	int err, got;
+
+	skel = strncmp_test__open();
+	if (!ASSERT_OK_PTR(skel, "strncmp_test open"))
+		return;
+
+	bpf_object__for_each_program(prog, skel->obj)
+		bpf_program__set_autoload(prog, false);
+
+	bpf_program__set_autoload(skel->progs.do_strncmp, true);
+
+	err = strncmp_test__load(skel);
+	if (!ASSERT_EQ(err, 0, "strncmp_test load"))
+		goto out;
+
+	err = strncmp_test__attach(skel);
+	if (!ASSERT_EQ(err, 0, "strncmp_test attach"))
+		goto out;
+
+	skel->bss->target_pid = getpid();
+
+	/* Empty str */
+	skel->bss->str[0] = '\0';
+	got = trigger_strncmp(skel);
+	ASSERT_EQ(got, -1, "strncmp: empty str");
+
+	/* Same string */
+	memcpy(skel->bss->str, skel->rodata->target, sizeof(skel->bss->str));
+	got = trigger_strncmp(skel);
+	ASSERT_EQ(got, 0, "strncmp: same str");
+
+	/* Not-null-termainted string  */
+	memcpy(skel->bss->str, skel->rodata->target, sizeof(skel->bss->str));
+	skel->bss->str[sizeof(skel->bss->str) - 1] = 'A';
+	got = trigger_strncmp(skel);
+	ASSERT_EQ(got, 1, "strncmp: not-null-term str");
+
+	strncmp_full_str_cmp(skel, "strncmp: less than", -1);
+	strncmp_full_str_cmp(skel, "strncmp: greater than", 1);
+out:
+	strncmp_test__destroy(skel);
+}
+
+static void test_strncmp_bad_not_const_str_size(void)
+{
+	struct strncmp_test *skel;
+	struct bpf_program *prog;
+	int err;
+
+	skel = strncmp_test__open();
+	if (!ASSERT_OK_PTR(skel, "strncmp_test open"))
+		return;
+
+	bpf_object__for_each_program(prog, skel->obj)
+		bpf_program__set_autoload(prog, false);
+
+	bpf_program__set_autoload(skel->progs.strncmp_bad_not_const_str_size,
+				  true);
+
+	err = strncmp_test__load(skel);
+	ASSERT_ERR(err, "strncmp_test load bad_not_const_str_size");
+
+	strncmp_test__destroy(skel);
+}
+
+static void test_strncmp_bad_writable_target(void)
+{
+	struct strncmp_test *skel;
+	struct bpf_program *prog;
+	int err;
+
+	skel = strncmp_test__open();
+	if (!ASSERT_OK_PTR(skel, "strncmp_test open"))
+		return;
+
+	bpf_object__for_each_program(prog, skel->obj)
+		bpf_program__set_autoload(prog, false);
+
+	bpf_program__set_autoload(skel->progs.strncmp_bad_writable_target,
+				  true);
+
+	err = strncmp_test__load(skel);
+	ASSERT_ERR(err, "strncmp_test load bad_writable_target");
+
+	strncmp_test__destroy(skel);
+}
+
+static void test_strncmp_bad_not_null_term_target(void)
+{
+	struct strncmp_test *skel;
+	struct bpf_program *prog;
+	int err;
+
+	skel = strncmp_test__open();
+	if (!ASSERT_OK_PTR(skel, "strncmp_test open"))
+		return;
+
+	bpf_object__for_each_program(prog, skel->obj)
+		bpf_program__set_autoload(prog, false);
+
+	bpf_program__set_autoload(skel->progs.strncmp_bad_not_null_term_target,
+				  true);
+
+	err = strncmp_test__load(skel);
+	ASSERT_ERR(err, "strncmp_test load bad_not_null_term_target");
+
+	strncmp_test__destroy(skel);
+}
+
+void test_test_strncmp(void)
+{
+	if (test__start_subtest("strncmp_ret"))
+		test_strncmp_ret();
+	if (test__start_subtest("strncmp_bad_not_const_str_size"))
+		test_strncmp_bad_not_const_str_size();
+	if (test__start_subtest("strncmp_bad_writable_target"))
+		test_strncmp_bad_writable_target();
+	if (test__start_subtest("strncmp_bad_not_null_term_target"))
+		test_strncmp_bad_not_null_term_target();
+}
--- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
+++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
@@ -35,7 +35,7 @@ static struct bpf_link *load(struct bpf_object *obj, const char *name)
 	struct bpf_program *prog;
 	int duration = 0;

-	prog = bpf_object__find_program_by_title(obj, name);
+	prog = bpf_object__find_program_by_name(obj, name);
 	if (CHECK(!prog, "find_probe", "prog '%s' not found\n", name))
 		return ERR_PTR(-EINVAL);
 	return bpf_program__attach_trace(prog);
@@ -44,8 +44,8 @@ static struct bpf_link *load(struct bpf_object *obj, const char *name)
 /* TODO: use different target function to run in concurrent mode */
 void serial_test_trampoline_count(void)
 {
-	const char *fentry_name = "fentry/__set_task_comm";
-	const char *fexit_name = "fexit/__set_task_comm";
+	const char *fentry_name = "prog1";
+	const char *fexit_name = "prog2";
 	const char *object = "test_trampoline_count.o";
 	struct inst inst[MAX_TRAMP_PROGS] = {};
 	int err, i = 0, duration = 0;
--- a/tools/testing/selftests/bpf/progs/get_func_args_test.c
+++ b/tools/testing/selftests/bpf/progs/get_func_args_test.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <errno.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u64 test1_result = 0;
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(test1)
+{
+	__u64 cnt = bpf_get_func_arg_cnt(ctx);
+	__u64 a = 0, z = 0, ret = 0;
+	__s64 err;
+
+	test1_result = cnt == 1;
+
+	/* valid arguments */
+	err = bpf_get_func_arg(ctx, 0, &a);
+
+	/* We need to cast access to traced function argument values with
+	 * proper type cast, because trampoline uses type specific instruction
+	 * to save it, like for 'int a' with 32-bit mov like:
+	 *
+	 *   mov %edi,-0x8(%rbp)
+	 *
+	 * so the upper 4 bytes are not zeroed.
+	 */
+	test1_result &= err == 0 && ((int) a == 1);
+
+	/* not valid argument */
+	err = bpf_get_func_arg(ctx, 1, &z);
+	test1_result &= err == -EINVAL;
+
+	/* return value fails in fentry */
+	err = bpf_get_func_ret(ctx, &ret);
+	test1_result &= err == -EOPNOTSUPP;
+	return 0;
+}
+
+__u64 test2_result = 0;
+SEC("fexit/bpf_fentry_test2")
+int BPF_PROG(test2)
+{
+	__u64 cnt = bpf_get_func_arg_cnt(ctx);
+	__u64 a = 0, b = 0, z = 0, ret = 0;
+	__s64 err;
+
+	test2_result = cnt == 2;
+
+	/* valid arguments */
+	err = bpf_get_func_arg(ctx, 0, &a);
+	test2_result &= err == 0 && (int) a == 2;
+
+	err = bpf_get_func_arg(ctx, 1, &b);
+	test2_result &= err == 0 && b == 3;
+
+	/* not valid argument */
+	err = bpf_get_func_arg(ctx, 2, &z);
+	test2_result &= err == -EINVAL;
+
+	/* return value */
+	err = bpf_get_func_ret(ctx, &ret);
+	test2_result &= err == 0 && ret == 5;
+	return 0;
+}
+
+__u64 test3_result = 0;
+SEC("fmod_ret/bpf_modify_return_test")
+int BPF_PROG(fmod_ret_test, int _a, int *_b, int _ret)
+{
+	__u64 cnt = bpf_get_func_arg_cnt(ctx);
+	__u64 a = 0, b = 0, z = 0, ret = 0;
+	__s64 err;
+
+	test3_result = cnt == 2;
+
+	/* valid arguments */
+	err = bpf_get_func_arg(ctx, 0, &a);
+	test3_result &= err == 0 && ((int) a == 1);
+
+	err = bpf_get_func_arg(ctx, 1, &b);
+	test3_result &= err == 0 && ((int *) b == _b);
+
+	/* not valid argument */
+	err = bpf_get_func_arg(ctx, 2, &z);
+	test3_result &= err == -EINVAL;
+
+	/* return value */
+	err = bpf_get_func_ret(ctx, &ret);
+	test3_result &= err == 0 && ret == 0;
+
+	/* change return value, it's checked in fexit_test program */
+	return 1234;
+}
+
+__u64 test4_result = 0;
+SEC("fexit/bpf_modify_return_test")
+int BPF_PROG(fexit_test, int _a, int *_b, int _ret)
+{
+	__u64 cnt = bpf_get_func_arg_cnt(ctx);
+	__u64 a = 0, b = 0, z = 0, ret = 0;
+	__s64 err;
+
+	test4_result = cnt == 2;
+
+	/* valid arguments */
+	err = bpf_get_func_arg(ctx, 0, &a);
+	test4_result &= err == 0 && ((int) a == 1);
+
+	err = bpf_get_func_arg(ctx, 1, &b);
+	test4_result &= err == 0 && ((int *) b == _b);
+
+	/* not valid argument */
+	err = bpf_get_func_arg(ctx, 2, &z);
+	test4_result &= err == -EINVAL;
+
+	/* return value */
+	err = bpf_get_func_ret(ctx, &ret);
+	test4_result &= err == 0 && ret == 1234;
+	return 0;
+}
--- a/tools/testing/selftests/bpf/progs/local_storage.c
+++ b/tools/testing/selftests/bpf/progs/local_storage.c
@@ -20,7 +20,6 @@ int sk_storage_result = -1;
 struct local_storage {
 	struct inode *exec_inode;
 	__u32 value;
-	struct bpf_spin_lock lock;
 };

 struct {
@@ -58,9 +57,7 @@ int BPF_PROG(unlink_hook, struct inode *dir, struct dentry *victim)
 				       bpf_get_current_task_btf(), 0, 0);
 	if (storage) {
 		/* Don't let an executable delete itself */
-		bpf_spin_lock(&storage->lock);
 		is_self_unlink = storage->exec_inode == victim->d_inode;
-		bpf_spin_unlock(&storage->lock);
 		if (is_self_unlink)
 			return -EPERM;
 	}
@@ -68,7 +65,7 @@ int BPF_PROG(unlink_hook, struct inode *dir, struct dentry *victim)
 	return 0;
 }

-SEC("lsm/inode_rename")
+SEC("lsm.s/inode_rename")
 int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry,
 	     struct inode *new_dir, struct dentry *new_dentry,
 	     unsigned int flags)
@@ -89,10 +86,8 @@ int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry,
 	if (!storage)
 		return 0;

-	bpf_spin_lock(&storage->lock);
 	if (storage->value != DUMMY_STORAGE_VALUE)
 		inode_storage_result = -1;
-	bpf_spin_unlock(&storage->lock);

 	err = bpf_inode_storage_delete(&inode_storage_map, old_dentry->d_inode);
 	if (!err)
@@ -101,7 +96,7 @@ int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry,
 	return 0;
 }

-SEC("lsm/socket_bind")
+SEC("lsm.s/socket_bind")
 int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address,
 	     int addrlen)
 {
@@ -117,10 +112,8 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address,
 	if (!storage)
 		return 0;

-	bpf_spin_lock(&storage->lock);
 	if (storage->value != DUMMY_STORAGE_VALUE)
 		sk_storage_result = -1;
-	bpf_spin_unlock(&storage->lock);

 	err = bpf_sk_storage_delete(&sk_storage_map, sock->sk);
 	if (!err)
@@ -129,7 +122,7 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address,
 	return 0;
 }

-SEC("lsm/socket_post_create")
+SEC("lsm.s/socket_post_create")
 int BPF_PROG(socket_post_create, struct socket *sock, int family, int type,
 	     int protocol, int kern)
 {
@@ -144,9 +137,7 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, int type,
 	if (!storage)
 		return 0;

-	bpf_spin_lock(&storage->lock);
 	storage->value = DUMMY_STORAGE_VALUE;
-	bpf_spin_unlock(&storage->lock);

 	return 0;
 }
@@ -154,7 +145,7 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, int type,
 /* This uses the local storage to remember the inode of the binary that a
 * process was originally executing.
 */
-SEC("lsm/bprm_committed_creds")
+SEC("lsm.s/bprm_committed_creds")
 void BPF_PROG(exec, struct linux_binprm *bprm)
 {
 	__u32 pid = bpf_get_current_pid_tgid() >> 32;
@@ -166,18 +157,13 @@ void BPF_PROG(exec, struct linux_binprm *bprm)
 	storage = bpf_task_storage_get(&task_storage_map,
 				       bpf_get_current_task_btf(), 0,
 				       BPF_LOCAL_STORAGE_GET_F_CREATE);
-	if (storage) {
-		bpf_spin_lock(&storage->lock);
+	if (storage)
 		storage->exec_inode = bprm->file->f_inode;
-		bpf_spin_unlock(&storage->lock);
-	}

 	storage = bpf_inode_storage_get(&inode_storage_map, bprm->file->f_inode,
 					0, BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!storage)
 		return;

-	bpf_spin_lock(&storage->lock);
 	storage->value = DUMMY_STORAGE_VALUE;
-	bpf_spin_unlock(&storage->lock);
 }
--- a/tools/testing/selftests/bpf/progs/strncmp_bench.c
+++ b/tools/testing/selftests/bpf/progs/strncmp_bench.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021. Huawei Technologies Co., Ltd */
+#include <linux/types.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#define STRNCMP_STR_SZ 4096
+
+/* Will be updated by benchmark before program loading */
+const volatile unsigned int cmp_str_len = 1;
+const char target[STRNCMP_STR_SZ];
+
+long hits = 0;
+char str[STRNCMP_STR_SZ];
+
+char _license[] SEC("license") = "GPL";
+
+static __always_inline int local_strncmp(const char *s1, unsigned int sz,
+					 const char *s2)
+{
+	int ret = 0;
+	unsigned int i;
+
+	for (i = 0; i < sz; i++) {
+		/* E.g. 0xff > 0x31 */
+		ret = (unsigned char)s1[i] - (unsigned char)s2[i];
+		if (ret || !s1[i])
+			break;
+	}
+
+	return ret;
+}
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int strncmp_no_helper(void *ctx)
+{
+	if (local_strncmp(str, cmp_str_len + 1, target) < 0)
+		__sync_add_and_fetch(&hits, 1);
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int strncmp_helper(void *ctx)
+{
+	if (bpf_strncmp(str, cmp_str_len + 1, target) < 0)
+		__sync_add_and_fetch(&hits, 1);
+	return 0;
+}
+
--- a/tools/testing/selftests/bpf/progs/strncmp_test.c
+++ b/tools/testing/selftests/bpf/progs/strncmp_test.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021. Huawei Technologies Co., Ltd */
+#include <stdbool.h>
+#include <linux/types.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#define STRNCMP_STR_SZ 8
+
+const char target[STRNCMP_STR_SZ] = "EEEEEEE";
+char str[STRNCMP_STR_SZ];
+int cmp_ret = 0;
+int target_pid = 0;
+
+const char no_str_target[STRNCMP_STR_SZ] = "12345678";
+char writable_target[STRNCMP_STR_SZ];
+unsigned int no_const_str_size = STRNCMP_STR_SZ;
+
+char _license[] SEC("license") = "GPL";
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int do_strncmp(void *ctx)
+{
+	if ((bpf_get_current_pid_tgid() >> 32) != target_pid)
+		return 0;
+
+	cmp_ret = bpf_strncmp(str, STRNCMP_STR_SZ, target);
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int strncmp_bad_not_const_str_size(void *ctx)
+{
+	/* The value of string size is not const, so will fail */
+	cmp_ret = bpf_strncmp(str, no_const_str_size, target);
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int strncmp_bad_writable_target(void *ctx)
+{
+	/* Compared target is not read-only, so will fail */
+	cmp_ret = bpf_strncmp(str, STRNCMP_STR_SZ, writable_target);
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int strncmp_bad_not_null_term_target(void *ctx)
+{
+	/* Compared target is not null-terminated, so will fail */
+	cmp_ret = bpf_strncmp(str, STRNCMP_STR_SZ, no_str_target);
+	return 0;
+}
--- a/tools/testing/selftests/bpf/progs/test_ksyms_btf_write_check.c
+++ b/tools/testing/selftests/bpf/progs/test_ksyms_btf_write_check.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Google */
+
+#include "vmlinux.h"
+
+#include <bpf/bpf_helpers.h>
+
+extern const int bpf_prog_active __ksym; /* int type global var. */
+
+SEC("raw_tp/sys_enter")
+int handler(const void *ctx)
+{
+	int *active;
+	__u32 cpu;
+
+	cpu = bpf_get_smp_processor_id();
+	active = (int *)bpf_per_cpu_ptr(&bpf_prog_active, cpu);
+	if (active) {
+		/* Kernel memory obtained from bpf_{per,this}_cpu_ptr
+		 * is read-only, should _not_ pass verification.
+		 */
+		/* WRITE_ONCE */
+		*(volatile int *)active = -1;
+	}
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
--- a/tools/testing/selftests/bpf/test_cpp.cpp
+++ b/tools/testing/selftests/bpf/test_cpp.cpp
@@ -7,9 +7,15 @@

 /* do nothing, just make sure we can link successfully */

+static void dump_printf(void *ctx, const char *fmt, va_list args)
+{
+}
+
 int main(int argc, char *argv[])
 {
+	struct btf_dump_opts opts = { };
 	struct test_core_extern *skel;
+	struct btf *btf;

 	/* libbpf.h */
 	libbpf_set_print(NULL);
@@ -18,7 +24,8 @@ int main(int argc, char *argv[])
 	bpf_prog_get_fd_by_id(0);

 	/* btf.h */
-	btf__new(NULL, 0);
+	btf = btf__new(NULL, 0);
+	btf_dump__new(btf, dump_printf, nullptr, &opts);

 	/* BPF skeleton */
 	skel = test_core_extern__open_and_load();
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -23,7 +23,6 @@
 #include <bpf/libbpf.h>

 #include "bpf_util.h"
-#include "bpf_rlimit.h"
 #include "test_maps.h"
 #include "testing_helpers.h"

--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -4,7 +4,6 @@
 #define _GNU_SOURCE
 #include "test_progs.h"
 #include "cgroup_helpers.h"
-#include "bpf_rlimit.h"
 #include <argp.h>
 #include <pthread.h>
 #include <sched.h>
@@ -1342,7 +1341,6 @@ int main(int argc, char **argv)

 	/* Use libbpf 1.0 API mode */
 	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
-
 	libbpf_set_print(libbpf_print_fn);

 	srand(time(NULL));
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -41,7 +41,6 @@
 #  define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS 1
 # endif
 #endif
-#include "bpf_rlimit.h"
 #include "bpf_rand.h"
 #include "bpf_util.h"
 #include "test_btf.h"
@@ -701,22 +700,18 @@ static int create_sk_storage_map(void)

 static int create_map_timer(void)
 {
-	struct bpf_create_map_attr attr = {
-		.name = "test_map",
-		.map_type = BPF_MAP_TYPE_ARRAY,
-		.key_size = 4,
-		.value_size = 16,
-		.max_entries = 1,
+	LIBBPF_OPTS(bpf_map_create_opts, opts,
 		.btf_key_type_id = 1,
 		.btf_value_type_id = 5,
-	};
+	);
 	int fd, btf_fd;

 	btf_fd = load_btf();
 	if (btf_fd < 0)
 		return -1;
-	attr.btf_fd = btf_fd;
-	fd = bpf_create_map_xattr(&attr);
+
+	opts.btf_fd = btf_fd;
+	fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "test_map", 4, 16, 1, &opts);
 	if (fd < 0)
 		printf("Failed to create map with timer\n");
 	return fd;
@@ -1399,6 +1394,9 @@ int main(int argc, char **argv)
 		return EXIT_FAILURE;
 	}

+	/* Use libbpf 1.0 API mode */
+	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+
 	bpf_semi_rand_init();
 	return do_test(unpriv, from, to);
 }
--- a/tools/testing/selftests/bpf/verifier/btf_ctx_access.c
+++ b/tools/testing/selftests/bpf/verifier/btf_ctx_access.c
@@ -0,0 +1,12 @@
+{
+	"btf_ctx_access accept",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 8),	/* load 2nd argument value (int pointer) */
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_TRACING,
+	.expected_attach_type = BPF_TRACE_FENTRY,
+	.kfunc = "bpf_modify_return_test",
+},
--- a/tools/testing/selftests/bpf/vmtest.sh
+++ b/tools/testing/selftests/bpf/vmtest.sh
@@ -32,7 +32,7 @@ ROOTFS_IMAGE="root.img"
 OUTPUT_DIR="$HOME/.bpf_selftests"
 KCONFIG_URL="https://raw.githubusercontent.com/libbpf/libbpf/master/travis-ci/vmtest/configs/config-latest.${ARCH}"
 KCONFIG_API_URL="https://api.github.com/repos/libbpf/libbpf/contents/travis-ci/vmtest/configs/config-latest.${ARCH}"
-INDEX_URL="https://raw.githubusercontent.com/libbpf/libbpf/master/travis-ci/vmtest/configs/INDEX"
+INDEX_URL="https://raw.githubusercontent.com/libbpf/ci/master/INDEX"
 NUM_COMPILE_JOBS="$(nproc)"
 LOG_FILE_BASE="$(date +"bpf_selftests.%Y-%m-%d_%H-%M-%S")"
 LOG_FILE="${LOG_FILE_BASE}.log"