Merging upstream version 6.10.3.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

25 files changed, 559 insertions, 158 deletions

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 145b8bd1d5..2a4c71501a 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -766,6 +766,7 @@ int bpf_link_create(int prog_fd, int target_fd,
 			return libbpf_err(-EINVAL);
 		break;
 	case BPF_TRACE_KPROBE_MULTI:
+	case BPF_TRACE_KPROBE_SESSION:
 		attr.link_create.kprobe_multi.flags = OPTS_GET(opts, kprobe_multi.flags, 0);
 		attr.link_create.kprobe_multi.cnt = OPTS_GET(opts, kprobe_multi.cnt, 0);
 		attr.link_create.kprobe_multi.syms = ptr_to_u64(OPTS_GET(opts, kprobe_multi.syms, 0));
@@ -785,6 +786,7 @@ int bpf_link_create(int prog_fd, int target_fd,
 		if (!OPTS_ZEROED(opts, uprobe_multi))
 			return libbpf_err(-EINVAL);
 		break;
+	case BPF_TRACE_RAW_TP:
 	case BPF_TRACE_FENTRY:
 	case BPF_TRACE_FEXIT:
 	case BPF_MODIFY_RETURN:
@@ -1173,20 +1175,31 @@ int bpf_link_get_info_by_fd(int link_fd, struct bpf_link_info *info, __u32 *info
 	return bpf_obj_get_info_by_fd(link_fd, info, info_len);
 }
 
-int bpf_raw_tracepoint_open(const char *name, int prog_fd)
+int bpf_raw_tracepoint_open_opts(int prog_fd, struct bpf_raw_tp_opts *opts)
 {
 	const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint);
 	union bpf_attr attr;
 	int fd;
 
+	if (!OPTS_VALID(opts, bpf_raw_tp_opts))
+		return libbpf_err(-EINVAL);
+
 	memset(&attr, 0, attr_sz);
-	attr.raw_tracepoint.name = ptr_to_u64(name);
 	attr.raw_tracepoint.prog_fd = prog_fd;
+	attr.raw_tracepoint.name = ptr_to_u64(OPTS_GET(opts, tp_name, NULL));
+	attr.raw_tracepoint.cookie = OPTS_GET(opts, cookie, 0);
 
 	fd = sys_bpf_fd(BPF_RAW_TRACEPOINT_OPEN, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
+int bpf_raw_tracepoint_open(const char *name, int prog_fd)
+{
+	LIBBPF_OPTS(bpf_raw_tp_opts, opts, .tp_name = name);
+
+	return bpf_raw_tracepoint_open_opts(prog_fd, &opts);
+}
+
 int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts)
 {
 	const size_t attr_sz = offsetofend(union bpf_attr, btf_token_fd);
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index df0db2f0cd..972e17ec0c 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -617,6 +617,15 @@ LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type,
 			      __u32 query_flags, __u32 *attach_flags,
 			      __u32 *prog_ids, __u32 *prog_cnt);
 
+struct bpf_raw_tp_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	const char *tp_name;
+	__u64 cookie;
+	size_t :0;
+};
+#define bpf_raw_tp_opts__last_field cookie
+
+LIBBPF_API int bpf_raw_tracepoint_open_opts(int prog_fd, struct bpf_raw_tp_opts *opts);
 LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd);
 LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf,
 				 __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h
index 670726353a..c0e13cdf96 100644
--- a/tools/lib/bpf/bpf_core_read.h
+++ b/tools/lib/bpf/bpf_core_read.h
@@ -2,7 +2,7 @@
 #ifndef __BPF_CORE_READ_H__
 #define __BPF_CORE_READ_H__
 
-#include <bpf/bpf_helpers.h>
+#include "bpf_helpers.h"
 
 /*
  * enum bpf_field_info_kind is passed as a second argument into
diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index cd17f6d079..305c62817d 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -137,7 +137,8 @@
 /*
  * Helper function to perform a tail call with a constant/immediate map slot.
  */
-#if __clang_major__ >= 8 && defined(__bpf__)
+#if (defined(__clang__) && __clang_major__ >= 8) || (!defined(__clang__) && __GNUC__ > 12)
+#if defined(__bpf__)
 static __always_inline void
 bpf_tail_call_static(void *ctx, const void *map, const __u32 slot)
 {
@@ -165,6 +166,7 @@ bpf_tail_call_static(void *ctx, const void *map, const __u32 slot)
 		     : "r0", "r1", "r2", "r3", "r4", "r5");
 }
 #endif
+#endif
 
 enum libbpf_pin_type {
 	LIBBPF_PIN_NONE,
@@ -184,10 +186,21 @@ enum libbpf_tristate {
 #define __kptr __attribute__((btf_type_tag("kptr")))
 #define __percpu_kptr __attribute__((btf_type_tag("percpu_kptr")))
 
-#define bpf_ksym_exists(sym) ({									\
-	_Static_assert(!__builtin_constant_p(!!sym), #sym " should be marked as __weak");	\
-	!!sym;											\
+#if defined (__clang__)
+#define bpf_ksym_exists(sym) ({						\
+	_Static_assert(!__builtin_constant_p(!!sym),			\
+		       #sym " should be marked as __weak");		\
+	!!sym;								\
+})
+#elif __GNUC__ > 8
+#define bpf_ksym_exists(sym) ({						\
+	_Static_assert(__builtin_has_attribute (*sym, __weak__),	\
+		       #sym " should be marked as __weak");		\
+	!!sym;								\
 })
+#else
+#define bpf_ksym_exists(sym) !!sym
+#endif
 
 #define __arg_ctx __attribute__((btf_decl_tag("arg:ctx")))
 #define __arg_nonnull __attribute((btf_decl_tag("arg:nonnull")))
diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index 1c13f8e888..9314fa95f0 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -633,18 +633,18 @@ struct pt_regs;
 #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_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_cast1(x)           ___bpf_ctx_cast0(), ctx[0]
+#define ___bpf_ctx_cast2(x, args...)  ___bpf_ctx_cast1(args), ctx[1]
+#define ___bpf_ctx_cast3(x, args...)  ___bpf_ctx_cast2(args), ctx[2]
+#define ___bpf_ctx_cast4(x, args...)  ___bpf_ctx_cast3(args), ctx[3]
+#define ___bpf_ctx_cast5(x, args...)  ___bpf_ctx_cast4(args), ctx[4]
+#define ___bpf_ctx_cast6(x, args...)  ___bpf_ctx_cast5(args), ctx[5]
+#define ___bpf_ctx_cast7(x, args...)  ___bpf_ctx_cast6(args), ctx[6]
+#define ___bpf_ctx_cast8(x, args...)  ___bpf_ctx_cast7(args), ctx[7]
+#define ___bpf_ctx_cast9(x, args...)  ___bpf_ctx_cast8(args), ctx[8]
+#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), ctx[9]
+#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), ctx[10]
+#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), ctx[11]
 #define ___bpf_ctx_cast(args...)      ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args)
 
 /*
@@ -786,14 +786,14 @@ ____##name(unsigned long long *ctx ___bpf_ctx_decl(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_args6(x, args...) ___bpf_kprobe_args5(args), (void *)PT_REGS_PARM6(ctx)
-#define ___bpf_kprobe_args7(x, args...) ___bpf_kprobe_args6(args), (void *)PT_REGS_PARM7(ctx)
-#define ___bpf_kprobe_args8(x, args...) ___bpf_kprobe_args7(args), (void *)PT_REGS_PARM8(ctx)
+#define ___bpf_kprobe_args1(x)          ___bpf_kprobe_args0(), (unsigned long long)PT_REGS_PARM1(ctx)
+#define ___bpf_kprobe_args2(x, args...) ___bpf_kprobe_args1(args), (unsigned long long)PT_REGS_PARM2(ctx)
+#define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (unsigned long long)PT_REGS_PARM3(ctx)
+#define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (unsigned long long)PT_REGS_PARM4(ctx)
+#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (unsigned long long)PT_REGS_PARM5(ctx)
+#define ___bpf_kprobe_args6(x, args...) ___bpf_kprobe_args5(args), (unsigned long long)PT_REGS_PARM6(ctx)
+#define ___bpf_kprobe_args7(x, args...) ___bpf_kprobe_args6(args), (unsigned long long)PT_REGS_PARM7(ctx)
+#define ___bpf_kprobe_args8(x, args...) ___bpf_kprobe_args7(args), (unsigned long long)PT_REGS_PARM8(ctx)
 #define ___bpf_kprobe_args(args...)     ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
 
 /*
@@ -821,7 +821,7 @@ static __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_args1(x)      ___bpf_kretprobe_args0(), (unsigned long long)PT_REGS_RC(ctx)
 #define ___bpf_kretprobe_args(args...) ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args)
 
 /*
@@ -845,24 +845,24 @@ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
 
 /* If kernel has CONFIG_ARCH_HAS_SYSCALL_WRAPPER, read pt_regs directly */
 #define ___bpf_syscall_args0()           ctx
-#define ___bpf_syscall_args1(x)          ___bpf_syscall_args0(), (void *)PT_REGS_PARM1_SYSCALL(regs)
-#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (void *)PT_REGS_PARM2_SYSCALL(regs)
-#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (void *)PT_REGS_PARM3_SYSCALL(regs)
-#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (void *)PT_REGS_PARM4_SYSCALL(regs)
-#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_SYSCALL(regs)
-#define ___bpf_syscall_args6(x, args...) ___bpf_syscall_args5(args), (void *)PT_REGS_PARM6_SYSCALL(regs)
-#define ___bpf_syscall_args7(x, args...) ___bpf_syscall_args6(args), (void *)PT_REGS_PARM7_SYSCALL(regs)
+#define ___bpf_syscall_args1(x)          ___bpf_syscall_args0(), (unsigned long long)PT_REGS_PARM1_SYSCALL(regs)
+#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (unsigned long long)PT_REGS_PARM2_SYSCALL(regs)
+#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (unsigned long long)PT_REGS_PARM3_SYSCALL(regs)
+#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (unsigned long long)PT_REGS_PARM4_SYSCALL(regs)
+#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (unsigned long long)PT_REGS_PARM5_SYSCALL(regs)
+#define ___bpf_syscall_args6(x, args...) ___bpf_syscall_args5(args), (unsigned long long)PT_REGS_PARM6_SYSCALL(regs)
+#define ___bpf_syscall_args7(x, args...) ___bpf_syscall_args6(args), (unsigned long long)PT_REGS_PARM7_SYSCALL(regs)
 #define ___bpf_syscall_args(args...)     ___bpf_apply(___bpf_syscall_args, ___bpf_narg(args))(args)
 
 /* If kernel doesn't have CONFIG_ARCH_HAS_SYSCALL_WRAPPER, we have to BPF_CORE_READ from pt_regs */
 #define ___bpf_syswrap_args0()           ctx
-#define ___bpf_syswrap_args1(x)          ___bpf_syswrap_args0(), (void *)PT_REGS_PARM1_CORE_SYSCALL(regs)
-#define ___bpf_syswrap_args2(x, args...) ___bpf_syswrap_args1(args), (void *)PT_REGS_PARM2_CORE_SYSCALL(regs)
-#define ___bpf_syswrap_args3(x, args...) ___bpf_syswrap_args2(args), (void *)PT_REGS_PARM3_CORE_SYSCALL(regs)
-#define ___bpf_syswrap_args4(x, args...) ___bpf_syswrap_args3(args), (void *)PT_REGS_PARM4_CORE_SYSCALL(regs)
-#define ___bpf_syswrap_args5(x, args...) ___bpf_syswrap_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs)
-#define ___bpf_syswrap_args6(x, args...) ___bpf_syswrap_args5(args), (void *)PT_REGS_PARM6_CORE_SYSCALL(regs)
-#define ___bpf_syswrap_args7(x, args...) ___bpf_syswrap_args6(args), (void *)PT_REGS_PARM7_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args1(x)          ___bpf_syswrap_args0(), (unsigned long long)PT_REGS_PARM1_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args2(x, args...) ___bpf_syswrap_args1(args), (unsigned long long)PT_REGS_PARM2_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args3(x, args...) ___bpf_syswrap_args2(args), (unsigned long long)PT_REGS_PARM3_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args4(x, args...) ___bpf_syswrap_args3(args), (unsigned long long)PT_REGS_PARM4_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args5(x, args...) ___bpf_syswrap_args4(args), (unsigned long long)PT_REGS_PARM5_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args6(x, args...) ___bpf_syswrap_args5(args), (unsigned long long)PT_REGS_PARM6_CORE_SYSCALL(regs)
+#define ___bpf_syswrap_args7(x, args...) ___bpf_syswrap_args6(args), (unsigned long long)PT_REGS_PARM7_CORE_SYSCALL(regs)
 #define ___bpf_syswrap_args(args...)     ___bpf_apply(___bpf_syswrap_args, ___bpf_narg(args))(args)
 
 /*
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 2d0840ef59..142060bbce 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -598,7 +598,7 @@ static int btf_sanity_check(const struct btf *btf)
 	__u32 i, n = btf__type_cnt(btf);
 	int err;
 
-	for (i = 1; i < n; i++) {
+	for (i = btf->start_id; i < n; i++) {
 		t = btf_type_by_id(btf, i);
 		err = btf_validate_type(btf, t, i);
 		if (err)
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 4d9f30bf7f..894860111d 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -1559,10 +1559,12 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 			 * Clang for BPF target generates func_proto with no
 			 * args as a func_proto with a single void arg (e.g.,
 			 * `int (*f)(void)` vs just `int (*f)()`). We are
-			 * going to pretend there are no args for such case.
+			 * going to emit valid empty args (void) syntax for
+			 * such case. Similarly and conveniently, valid
+			 * no args case can be special-cased here as well.
 			 */
-			if (vlen == 1 && p->type == 0) {
-				btf_dump_printf(d, ")");
+			if (vlen == 0 || (vlen == 1 && p->type == 0)) {
+				btf_dump_printf(d, "void)");
 				return;
 			}
 
@@ -1929,6 +1931,7 @@ static int btf_dump_int_data(struct btf_dump *d,
 			if (d->typed_dump->is_array_terminated)
 				break;
 			if (*(char *)data == '\0') {
+				btf_dump_type_values(d, "'\\0'");
 				d->typed_dump->is_array_terminated = true;
 				break;
 			}
@@ -2031,6 +2034,7 @@ static int btf_dump_array_data(struct btf_dump *d,
 	__u32 i, elem_type_id;
 	__s64 elem_size;
 	bool is_array_member;
+	bool is_array_terminated;
 
 	elem_type_id = array->type;
 	elem_type = skip_mods_and_typedefs(d->btf, elem_type_id, NULL);
@@ -2066,12 +2070,15 @@ static int btf_dump_array_data(struct btf_dump *d,
 	 */
 	is_array_member = d->typed_dump->is_array_member;
 	d->typed_dump->is_array_member = true;
+	is_array_terminated = d->typed_dump->is_array_terminated;
+	d->typed_dump->is_array_terminated = false;
 	for (i = 0; i < array->nelems; i++, data += elem_size) {
 		if (d->typed_dump->is_array_terminated)
 			break;
 		btf_dump_dump_type_data(d, NULL, elem_type, elem_type_id, data, 0, 0);
 	}
 	d->typed_dump->is_array_member = is_array_member;
+	d->typed_dump->is_array_terminated = is_array_terminated;
 	d->typed_dump->depth--;
 	btf_dump_data_pfx(d);
 	btf_dump_type_values(d, "]");
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index f515cf264a..5401f2df46 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -132,6 +132,7 @@ static const char * const attach_type_name[] = {
 	[BPF_TRACE_UPROBE_MULTI]	= "trace_uprobe_multi",
 	[BPF_NETKIT_PRIMARY]		= "netkit_primary",
 	[BPF_NETKIT_PEER]		= "netkit_peer",
+	[BPF_TRACE_KPROBE_SESSION]	= "trace_kprobe_session",
 };
 
 static const char * const link_type_name[] = {
@@ -149,6 +150,7 @@ static const char * const link_type_name[] = {
 	[BPF_LINK_TYPE_TCX]			= "tcx",
 	[BPF_LINK_TYPE_UPROBE_MULTI]		= "uprobe_multi",
 	[BPF_LINK_TYPE_NETKIT]			= "netkit",
+	[BPF_LINK_TYPE_SOCKMAP]			= "sockmap",
 };
 
 static const char * const map_type_name[] = {
@@ -1126,17 +1128,46 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map)
 		const struct btf_type *mtype, *kern_mtype;
 		__u32 mtype_id, kern_mtype_id;
 		void *mdata, *kern_mdata;
+		struct bpf_program *prog;
 		__s64 msize, kern_msize;
 		__u32 moff, kern_moff;
 		__u32 kern_member_idx;
 		const char *mname;
 
 		mname = btf__name_by_offset(btf, member->name_off);
+		moff = member->offset / 8;
+		mdata = data + moff;
+		msize = btf__resolve_size(btf, member->type);
+		if (msize < 0) {
+			pr_warn("struct_ops init_kern %s: failed to resolve the size of member %s\n",
+				map->name, mname);
+			return msize;
+		}
+
 		kern_member = find_member_by_name(kern_btf, kern_type, mname);
 		if (!kern_member) {
-			pr_warn("struct_ops init_kern %s: Cannot find member %s in kernel BTF\n",
+			if (!libbpf_is_mem_zeroed(mdata, msize)) {
+				pr_warn("struct_ops init_kern %s: Cannot find member %s in kernel BTF\n",
+					map->name, mname);
+				return -ENOTSUP;
+			}
+
+			if (st_ops->progs[i]) {
+				/* If we had declaratively set struct_ops callback, we need to
+				 * force its autoload to false, because it doesn't have
+				 * a chance of succeeding from POV of the current struct_ops map.
+				 * If this program is still referenced somewhere else, though,
+				 * then bpf_object_adjust_struct_ops_autoload() will update its
+				 * autoload accordingly.
+				 */
+				st_ops->progs[i]->autoload = false;
+				st_ops->progs[i] = NULL;
+			}
+
+			/* Skip all-zero/NULL fields if they are not present in the kernel BTF */
+			pr_info("struct_ops %s: member %s not found in kernel, skipping it as it's set to zero\n",
 				map->name, mname);
-			return -ENOTSUP;
+			continue;
 		}
 
 		kern_member_idx = kern_member - btf_members(kern_type);
@@ -1147,10 +1178,7 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map)
 			return -ENOTSUP;
 		}
 
-		moff = member->offset / 8;
 		kern_moff = kern_member->offset / 8;
-
-		mdata = data + moff;
 		kern_mdata = kern_data + kern_moff;
 
 		mtype = skip_mods_and_typedefs(btf, member->type, &mtype_id);
@@ -1165,13 +1193,19 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map)
 		}
 
 		if (btf_is_ptr(mtype)) {
-			struct bpf_program *prog;
+			prog = *(void **)mdata;
+			/* just like for !kern_member case above, reset declaratively
+			 * set (at compile time) program's autload to false,
+			 * if user replaced it with another program or NULL
+			 */
+			if (st_ops->progs[i] && st_ops->progs[i] != prog)
+				st_ops->progs[i]->autoload = false;
 
 			/* Update the value from the shadow type */
-			prog = *(void **)mdata;
 			st_ops->progs[i] = prog;
 			if (!prog)
 				continue;
+
 			if (!is_valid_st_ops_program(obj, prog)) {
 				pr_warn("struct_ops init_kern %s: member %s is not a struct_ops program\n",
 					map->name, mname);
@@ -1230,9 +1264,8 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map)
 			continue;
 		}
 
-		msize = btf__resolve_size(btf, mtype_id);
 		kern_msize = btf__resolve_size(kern_btf, kern_mtype_id);
-		if (msize < 0 || kern_msize < 0 || msize != kern_msize) {
+		if (kern_msize < 0 || msize != kern_msize) {
 			pr_warn("struct_ops init_kern %s: Error in size of member %s: %zd != %zd(kernel)\n",
 				map->name, mname, (ssize_t)msize,
 				(ssize_t)kern_msize);
@@ -1956,6 +1989,20 @@ static struct extern_desc *find_extern_by_name(const struct bpf_object *obj,
 	return NULL;
 }
 
+static struct extern_desc *find_extern_by_name_with_len(const struct bpf_object *obj,
+							const void *name, int len)
+{
+	const char *ext_name;
+	int i;
+
+	for (i = 0; i < obj->nr_extern; i++) {
+		ext_name = obj->externs[i].name;
+		if (strlen(ext_name) == len && strncmp(ext_name, name, len) == 0)
+			return &obj->externs[i];
+	}
+	return NULL;
+}
+
 static int set_kcfg_value_tri(struct extern_desc *ext, void *ext_val,
 			      char value)
 {
@@ -7325,7 +7372,11 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog
 	__u32 log_level = prog->log_level;
 	int ret, err;
 
-	if (prog->type == BPF_PROG_TYPE_UNSPEC) {
+	/* Be more helpful by rejecting programs that can't be validated early
+	 * with more meaningful and actionable error message.
+	 */
+	switch (prog->type) {
+	case BPF_PROG_TYPE_UNSPEC:
 		/*
 		 * The program type must be set.  Most likely we couldn't find a proper
 		 * section definition at load time, and thus we didn't infer the type.
@@ -7333,6 +7384,15 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog
 		pr_warn("prog '%s': missing BPF prog type, check ELF section name '%s'\n",
 			prog->name, prog->sec_name);
 		return -EINVAL;
+	case BPF_PROG_TYPE_STRUCT_OPS:
+		if (prog->attach_btf_id == 0) {
+			pr_warn("prog '%s': SEC(\"struct_ops\") program isn't referenced anywhere, did you forget to use it?\n",
+				prog->name);
+			return -EINVAL;
+		}
+		break;
+	default:
+		break;
 	}
 
 	if (!insns || !insns_cnt)
@@ -7972,7 +8032,10 @@ static int bpf_object__sanitize_maps(struct bpf_object *obj)
 	return 0;
 }
 
-int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *ctx)
+typedef int (*kallsyms_cb_t)(unsigned long long sym_addr, char sym_type,
+			     const char *sym_name, void *ctx);
+
+static int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *ctx)
 {
 	char sym_type, sym_name[500];
 	unsigned long long sym_addr;
@@ -8012,8 +8075,13 @@ static int kallsyms_cb(unsigned long long sym_addr, char sym_type,
 	struct bpf_object *obj = ctx;
 	const struct btf_type *t;
 	struct extern_desc *ext;
+	char *res;
 
-	ext = find_extern_by_name(obj, sym_name);
+	res = strstr(sym_name, ".llvm.");
+	if (sym_type == 'd' && res)
+		ext = find_extern_by_name_with_len(obj, sym_name, res - sym_name);
+	else
+		ext = find_extern_by_name(obj, sym_name);
 	if (!ext || ext->type != EXT_KSYM)
 		return 0;
 
@@ -8562,6 +8630,11 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
 		return libbpf_err(-EINVAL);
 	}
 
+	if (map->fd < 0) {
+		pr_warn("map '%s': can't pin BPF map without FD (was it created?)\n", map->name);
+		return libbpf_err(-EINVAL);
+	}
+
 	if (map->pin_path) {
 		if (path && strcmp(path, map->pin_path)) {
 			pr_warn("map '%s' already has pin path '%s' different from '%s'\n",
@@ -9230,6 +9303,7 @@ static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_lin
 static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link);
 static int attach_trace(const struct bpf_program *prog, long cookie, struct bpf_link **link);
 static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link);
+static int attach_kprobe_session(const struct bpf_program *prog, long cookie, struct bpf_link **link);
 static int attach_uprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link);
 static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_link **link);
 static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_link **link);
@@ -9246,6 +9320,7 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("uretprobe.s+",		KPROBE, 0, SEC_SLEEPABLE, attach_uprobe),
 	SEC_DEF("kprobe.multi+",	KPROBE,	BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi),
 	SEC_DEF("kretprobe.multi+",	KPROBE,	BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi),
+	SEC_DEF("kprobe.session+",	KPROBE,	BPF_TRACE_KPROBE_SESSION, SEC_NONE, attach_kprobe_session),
 	SEC_DEF("uprobe.multi+",	KPROBE,	BPF_TRACE_UPROBE_MULTI, SEC_NONE, attach_uprobe_multi),
 	SEC_DEF("uretprobe.multi+",	KPROBE,	BPF_TRACE_UPROBE_MULTI, SEC_NONE, attach_uprobe_multi),
 	SEC_DEF("uprobe.multi.s+",	KPROBE,	BPF_TRACE_UPROBE_MULTI, SEC_SLEEPABLE, attach_uprobe_multi),
@@ -9297,6 +9372,7 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("sockops",		SOCK_OPS, BPF_CGROUP_SOCK_OPS, SEC_ATTACHABLE_OPT),
 	SEC_DEF("sk_skb/stream_parser",	SK_SKB, BPF_SK_SKB_STREAM_PARSER, SEC_ATTACHABLE_OPT),
 	SEC_DEF("sk_skb/stream_verdict",SK_SKB, BPF_SK_SKB_STREAM_VERDICT, SEC_ATTACHABLE_OPT),
+	SEC_DEF("sk_skb/verdict",	SK_SKB, BPF_SK_SKB_VERDICT, SEC_ATTACHABLE_OPT),
 	SEC_DEF("sk_skb",		SK_SKB, 0, SEC_NONE),
 	SEC_DEF("sk_msg",		SK_MSG, BPF_SK_MSG_VERDICT, SEC_ATTACHABLE_OPT),
 	SEC_DEF("lirc_mode2",		LIRC_MODE2, BPF_LIRC_MODE2, SEC_ATTACHABLE_OPT),
@@ -9815,16 +9891,28 @@ static int find_kernel_btf_id(struct bpf_object *obj, const char *attach_name,
 			      enum bpf_attach_type attach_type,
 			      int *btf_obj_fd, int *btf_type_id)
 {
-	int ret, i;
+	int ret, i, mod_len;
+	const char *fn_name, *mod_name = NULL;
 
-	ret = find_attach_btf_id(obj->btf_vmlinux, attach_name, attach_type);
-	if (ret > 0) {
-		*btf_obj_fd = 0; /* vmlinux BTF */
-		*btf_type_id = ret;
-		return 0;
+	fn_name = strchr(attach_name, ':');
+	if (fn_name) {
+		mod_name = attach_name;
+		mod_len = fn_name - mod_name;
+		fn_name++;
+	}
+
+	if (!mod_name || strncmp(mod_name, "vmlinux", mod_len) == 0) {
+		ret = find_attach_btf_id(obj->btf_vmlinux,
+					 mod_name ? fn_name : attach_name,
+					 attach_type);
+		if (ret > 0) {
+			*btf_obj_fd = 0; /* vmlinux BTF */
+			*btf_type_id = ret;
+			return 0;
+		}
+		if (ret != -ENOENT)
+			return ret;
 	}
-	if (ret != -ENOENT)
-		return ret;
 
 	ret = load_module_btfs(obj);
 	if (ret)
@@ -9833,7 +9921,12 @@ static int find_kernel_btf_id(struct bpf_object *obj, const char *attach_name,
 	for (i = 0; i < obj->btf_module_cnt; i++) {
 		const struct module_btf *mod = &obj->btf_modules[i];
 
-		ret = find_attach_btf_id(mod->btf, attach_name, attach_type);
+		if (mod_name && strncmp(mod->name, mod_name, mod_len) != 0)
+			continue;
+
+		ret = find_attach_btf_id(mod->btf,
+					 mod_name ? fn_name : attach_name,
+					 attach_type);
 		if (ret > 0) {
 			*btf_obj_fd = mod->fd;
 			*btf_type_id = ret;
@@ -10306,6 +10399,11 @@ static int validate_map_op(const struct bpf_map *map, size_t key_sz,
 		return -EINVAL;
 	}
 
+	if (map->fd < 0) {
+		pr_warn("map '%s': can't use BPF map without FD (was it created?)\n", map->name);
+		return -EINVAL;
+	}
+
 	if (!check_value_sz)
 		return 0;
 
@@ -10418,8 +10516,15 @@ long libbpf_get_error(const void *ptr)
 int bpf_link__update_program(struct bpf_link *link, struct bpf_program *prog)
 {
 	int ret;
+	int prog_fd = bpf_program__fd(prog);
+
+	if (prog_fd < 0) {
+		pr_warn("prog '%s': can't use BPF program without FD (was it loaded?)\n",
+			prog->name);
+		return libbpf_err(-EINVAL);
+	}
 
-	ret = bpf_link_update(bpf_link__fd(link), bpf_program__fd(prog), NULL);
+	ret = bpf_link_update(bpf_link__fd(link), prog_fd, NULL);
 	return libbpf_err_errno(ret);
 }
 
@@ -10613,7 +10718,7 @@ struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *p
 	}
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
-		pr_warn("prog '%s': can't attach BPF program w/o FD (did you load it?)\n",
+		pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n",
 			prog->name);
 		return libbpf_err_ptr(-EINVAL);
 	}
@@ -11325,18 +11430,26 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 	struct kprobe_multi_resolve res = {
 		.pattern = pattern,
 	};
+	enum bpf_attach_type attach_type;
 	struct bpf_link *link = NULL;
 	char errmsg[STRERR_BUFSIZE];
 	const unsigned long *addrs;
 	int err, link_fd, prog_fd;
+	bool retprobe, session;
 	const __u64 *cookies;
 	const char **syms;
-	bool retprobe;
 	size_t cnt;
 
 	if (!OPTS_VALID(opts, bpf_kprobe_multi_opts))
 		return libbpf_err_ptr(-EINVAL);
 
+	prog_fd = bpf_program__fd(prog);
+	if (prog_fd < 0) {
+		pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n",
+			prog->name);
+		return libbpf_err_ptr(-EINVAL);
+	}
+
 	syms    = OPTS_GET(opts, syms, false);
 	addrs   = OPTS_GET(opts, addrs, false);
 	cnt     = OPTS_GET(opts, cnt, false);
@@ -11363,6 +11476,12 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 	}
 
 	retprobe = OPTS_GET(opts, retprobe, false);
+	session  = OPTS_GET(opts, session, false);
+
+	if (retprobe && session)
+		return libbpf_err_ptr(-EINVAL);
+
+	attach_type = session ? BPF_TRACE_KPROBE_SESSION : BPF_TRACE_KPROBE_MULTI;
 
 	lopts.kprobe_multi.syms = syms;
 	lopts.kprobe_multi.addrs = addrs;
@@ -11377,8 +11496,7 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 	}
 	link->detach = &bpf_link__detach_fd;
 
-	prog_fd = bpf_program__fd(prog);
-	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, &lopts);
+	link_fd = bpf_link_create(prog_fd, 0, attach_type, &lopts);
 	if (link_fd < 0) {
 		err = -errno;
 		pr_warn("prog '%s': failed to attach: %s\n",
@@ -11484,6 +11602,32 @@ static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, stru
 	return libbpf_get_error(*link);
 }
 
+static int attach_kprobe_session(const struct bpf_program *prog, long cookie,
+				 struct bpf_link **link)
+{
+	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts, .session = true);
+	const char *spec;
+	char *pattern;
+	int n;
+
+	*link = NULL;
+
+	/* no auto-attach for SEC("kprobe.session") */
+	if (strcmp(prog->sec_name, "kprobe.session") == 0)
+		return 0;
+
+	spec = prog->sec_name + sizeof("kprobe.session/") - 1;
+	n = sscanf(spec, "%m[a-zA-Z0-9_.*?]", &pattern);
+	if (n < 1) {
+		pr_warn("kprobe session pattern is invalid: %s\n", spec);
+		return -EINVAL;
+	}
+
+	*link = bpf_program__attach_kprobe_multi_opts(prog, pattern, &opts);
+	free(pattern);
+	return *link ? 0 : -errno;
+}
+
 static int attach_uprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link)
 {
 	char *probe_type = NULL, *binary_path = NULL, *func_name = NULL;
@@ -11760,6 +11904,13 @@ bpf_program__attach_uprobe_multi(const struct bpf_program *prog,
 	if (!OPTS_VALID(opts, bpf_uprobe_multi_opts))
 		return libbpf_err_ptr(-EINVAL);
 
+	prog_fd = bpf_program__fd(prog);
+	if (prog_fd < 0) {
+		pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n",
+			prog->name);
+		return libbpf_err_ptr(-EINVAL);
+	}
+
 	syms = OPTS_GET(opts, syms, NULL);
 	offsets = OPTS_GET(opts, offsets, NULL);
 	ref_ctr_offsets = OPTS_GET(opts, ref_ctr_offsets, NULL);
@@ -11835,7 +11986,6 @@ bpf_program__attach_uprobe_multi(const struct bpf_program *prog,
 	}
 	link->detach = &bpf_link__detach_fd;
 
-	prog_fd = bpf_program__fd(prog);
 	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &lopts);
 	if (link_fd < 0) {
 		err = -errno;
@@ -12079,7 +12229,7 @@ struct bpf_link *bpf_program__attach_usdt(const struct bpf_program *prog,
 		return libbpf_err_ptr(-EINVAL);
 
 	if (bpf_program__fd(prog) < 0) {
-		pr_warn("prog '%s': can't attach BPF program w/o FD (did you load it?)\n",
+		pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n",
 			prog->name);
 		return libbpf_err_ptr(-EINVAL);
 	}
@@ -12270,13 +12420,19 @@ static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_lin
 	return libbpf_get_error(*link);
 }
 
-struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *prog,
-						    const char *tp_name)
+struct bpf_link *
+bpf_program__attach_raw_tracepoint_opts(const struct bpf_program *prog,
+					const char *tp_name,
+					struct bpf_raw_tracepoint_opts *opts)
 {
+	LIBBPF_OPTS(bpf_raw_tp_opts, raw_opts);
 	char errmsg[STRERR_BUFSIZE];
 	struct bpf_link *link;
 	int prog_fd, pfd;
 
+	if (!OPTS_VALID(opts, bpf_raw_tracepoint_opts))
+		return libbpf_err_ptr(-EINVAL);
+
 	prog_fd = bpf_program__fd(prog);
 	if (prog_fd < 0) {
 		pr_warn("prog '%s': can't attach before loaded\n", prog->name);
@@ -12288,7 +12444,9 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *pr
 		return libbpf_err_ptr(-ENOMEM);
 	link->detach = &bpf_link__detach_fd;
 
-	pfd = bpf_raw_tracepoint_open(tp_name, prog_fd);
+	raw_opts.tp_name = tp_name;
+	raw_opts.cookie = OPTS_GET(opts, cookie, 0);
+	pfd = bpf_raw_tracepoint_open_opts(prog_fd, &raw_opts);
 	if (pfd < 0) {
 		pfd = -errno;
 		free(link);
@@ -12300,6 +12458,12 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *pr
 	return link;
 }
 
+struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *prog,
+						    const char *tp_name)
+{
+	return bpf_program__attach_raw_tracepoint_opts(prog, tp_name, NULL);
+}
+
 static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link)
 {
 	static const char *const prefixes[] = {
@@ -12453,6 +12617,12 @@ bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd)
 	return bpf_program_attach_fd(prog, netns_fd, "netns", NULL);
 }
 
+struct bpf_link *
+bpf_program__attach_sockmap(const struct bpf_program *prog, int map_fd)
+{
+	return bpf_program_attach_fd(prog, map_fd, "sockmap", NULL);
+}
+
 struct bpf_link *bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex)
 {
 	/* target_fd/target_ifindex use the same field in LINK_CREATE */
@@ -12661,6 +12831,12 @@ struct bpf_link *bpf_program__attach(const struct bpf_program *prog)
 	if (!prog->sec_def || !prog->sec_def->prog_attach_fn)
 		return libbpf_err_ptr(-EOPNOTSUPP);
 
+	if (bpf_program__fd(prog) < 0) {
+		pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n",
+			prog->name);
+		return libbpf_err_ptr(-EINVAL);
+	}
+
 	err = prog->sec_def->prog_attach_fn(prog, prog->sec_def->cookie, &link);
 	if (err)
 		return libbpf_err_ptr(err);
@@ -12701,8 +12877,13 @@ struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map)
 	__u32 zero = 0;
 	int err, fd;
 
-	if (!bpf_map__is_struct_ops(map) || map->fd == -1)
+	if (!bpf_map__is_struct_ops(map))
+		return libbpf_err_ptr(-EINVAL);
+
+	if (map->fd < 0) {
+		pr_warn("map '%s': can't attach BPF map without FD (was it created?)\n", map->name);
 		return libbpf_err_ptr(-EINVAL);
+	}
 
 	link = calloc(1, sizeof(*link));
 	if (!link)
@@ -12750,9 +12931,14 @@ int bpf_link__update_map(struct bpf_link *link, const struct bpf_map *map)
 	__u32 zero = 0;
 	int err;
 
-	if (!bpf_map__is_struct_ops(map) || !map_is_created(map))
+	if (!bpf_map__is_struct_ops(map))
 		return -EINVAL;
 
+	if (map->fd < 0) {
+		pr_warn("map '%s': can't use BPF map without FD (was it created?)\n", map->name);
+		return -EINVAL;
+	}
+
 	st_ops_link = container_of(link, struct bpf_link_struct_ops, link);
 	/* Ensure the type of a link is correct */
 	if (st_ops_link->map_fd < 0)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 7b510761f5..c3f77d9260 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -539,10 +539,12 @@ struct bpf_kprobe_multi_opts {
 	size_t cnt;
 	/* create return kprobes */
 	bool retprobe;
+	/* create session kprobes */
+	bool session;
 	size_t :0;
 };
 
-#define bpf_kprobe_multi_opts__last_field retprobe
+#define bpf_kprobe_multi_opts__last_field session
 
 LIBBPF_API struct bpf_link *
 bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
@@ -760,9 +762,20 @@ bpf_program__attach_tracepoint_opts(const struct bpf_program *prog,
 				    const char *tp_name,
 				    const struct bpf_tracepoint_opts *opts);
 
+struct bpf_raw_tracepoint_opts {
+	size_t sz; /* size of this struct for forward/backward compatibility */
+	__u64 cookie;
+	size_t :0;
+};
+#define bpf_raw_tracepoint_opts__last_field cookie
+
 LIBBPF_API struct bpf_link *
 bpf_program__attach_raw_tracepoint(const struct bpf_program *prog,
 				   const char *tp_name);
+LIBBPF_API struct bpf_link *
+bpf_program__attach_raw_tracepoint_opts(const struct bpf_program *prog,
+					const char *tp_name,
+					struct bpf_raw_tracepoint_opts *opts);
 
 struct bpf_trace_opts {
 	/* size of this struct, for forward/backward compatibility */
@@ -784,6 +797,8 @@ bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd);
 LIBBPF_API struct bpf_link *
 bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd);
 LIBBPF_API struct bpf_link *
+bpf_program__attach_sockmap(const struct bpf_program *prog, int map_fd);
+LIBBPF_API struct bpf_link *
 bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex);
 LIBBPF_API struct bpf_link *
 bpf_program__attach_freplace(const struct bpf_program *prog,
@@ -1282,6 +1297,7 @@ LIBBPF_API int ring_buffer__add(struct ring_buffer *rb, int map_fd,
 				ring_buffer_sample_fn sample_cb, void *ctx);
 LIBBPF_API int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms);
 LIBBPF_API int ring_buffer__consume(struct ring_buffer *rb);
+LIBBPF_API int ring_buffer__consume_n(struct ring_buffer *rb, size_t n);
 LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb);
 
 /**
@@ -1356,6 +1372,17 @@ LIBBPF_API int ring__map_fd(const struct ring *r);
  */
 LIBBPF_API int ring__consume(struct ring *r);
 
+/**
+ * @brief **ring__consume_n()** consumes up to a requested amount of items from
+ * a ringbuffer without event polling.
+ *
+ * @param r A ringbuffer object.
+ * @param n Maximum amount of items to consume.
+ * @return The number of items consumed, or a negative number if any of the
+ * callbacks return an error.
+ */
+LIBBPF_API int ring__consume_n(struct ring *r, size_t n);
+
 struct user_ring_buffer_opts {
 	size_t sz; /* size of this struct, for forward/backward compatibility */
 };
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 86804fd90d..c1ce8aa352 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -410,7 +410,16 @@ LIBBPF_1.3.0 {
 
 LIBBPF_1.4.0 {
 	global:
+		bpf_program__attach_raw_tracepoint_opts;
+		bpf_raw_tracepoint_open_opts;
 		bpf_token_create;
 		btf__new_split;
 		btf_ext__raw_data;
 } LIBBPF_1.3.0;
+
+LIBBPF_1.5.0 {
+	global:
+		bpf_program__attach_sockmap;
+		ring__consume_n;
+		ring_buffer__consume_n;
+} LIBBPF_1.4.0;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 864b361774..7e7e686008 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -518,11 +518,6 @@ int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void
 __s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name,
 				 __u32 kind);
 
-typedef int (*kallsyms_cb_t)(unsigned long long sym_addr, char sym_type,
-			     const char *sym_name, void *ctx);
-
-int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *arg);
-
 /* handle direct returned errors */
 static inline int libbpf_err(int ret)
 {
@@ -602,13 +597,9 @@ static inline int ensure_good_fd(int fd)
 	return fd;
 }
 
-static inline int sys_dup2(int oldfd, int newfd)
+static inline int sys_dup3(int oldfd, int newfd, int flags)
 {
-#ifdef __NR_dup2
-	return syscall(__NR_dup2, oldfd, newfd);
-#else
-	return syscall(__NR_dup3, oldfd, newfd, 0);
-#endif
+	return syscall(__NR_dup3, oldfd, newfd, flags);
 }
 
 /* Point *fixed_fd* to the same file that *tmp_fd* points to.
@@ -619,7 +610,7 @@ static inline int reuse_fd(int fixed_fd, int tmp_fd)
 {
 	int err;
 
-	err = sys_dup2(tmp_fd, fixed_fd);
+	err = sys_dup3(tmp_fd, fixed_fd, O_CLOEXEC);
 	err = err < 0 ? -errno : 0;
 	close(tmp_fd); /* clean up temporary FD */
 	return err;
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index 3021881224..9dfbe7750f 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -448,7 +448,8 @@ int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, enum bpf_func_id helpe
 	/* 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".
+	 * given BPF program type, it will emit "unknown func bpf_sys_bpf#166"
+	 * or "program of this type cannot use helper 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.,
@@ -457,7 +458,8 @@ int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, enum bpf_func_id helpe
 	 * 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 ")))
+	if (ret == 0 && (strstr(buf, "invalid func ") || strstr(buf, "unknown func ") ||
+			 strstr(buf, "program of this type cannot use helper ")))
 		return 0;
 	return 1; /* assume supported */
 }
diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h
index e783a47da8..d6e5eff967 100644
--- a/tools/lib/bpf/libbpf_version.h
+++ b/tools/lib/bpf/libbpf_version.h
@@ -4,6 +4,6 @@
 #define __LIBBPF_VERSION_H
 
 #define LIBBPF_MAJOR_VERSION 1
-#define LIBBPF_MINOR_VERSION 4
+#define LIBBPF_MINOR_VERSION 5
 
 #endif /* __LIBBPF_VERSION_H */
diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
index 0d4be82955..5a583053e3 100644
--- a/tools/lib/bpf/linker.c
+++ b/tools/lib/bpf/linker.c
@@ -2213,10 +2213,17 @@ static int linker_fixup_btf(struct src_obj *obj)
 		vi = btf_var_secinfos(t);
 		for (j = 0, m = btf_vlen(t); j < m; j++, vi++) {
 			const struct btf_type *vt = btf__type_by_id(obj->btf, vi->type);
-			const char *var_name = btf__str_by_offset(obj->btf, vt->name_off);
-			int var_linkage = btf_var(vt)->linkage;
+			const char *var_name;
+			int var_linkage;
 			Elf64_Sym *sym;
 
+			/* could be a variable or function */
+			if (!btf_is_var(vt))
+				continue;
+
+			var_name = btf__str_by_offset(obj->btf, vt->name_off);
+			var_linkage = btf_var(vt)->linkage;
+
 			/* no need to patch up static or extern vars */
 			if (var_linkage != BTF_VAR_GLOBAL_ALLOCATED)
 				continue;
diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
index aacb64278a..bfd8dac4c0 100644
--- a/tools/lib/bpf/ringbuf.c
+++ b/tools/lib/bpf/ringbuf.c
@@ -231,7 +231,7 @@ static inline int roundup_len(__u32 len)
 	return (len + 7) / 8 * 8;
 }
 
-static int64_t ringbuf_process_ring(struct ring *r)
+static int64_t ringbuf_process_ring(struct ring *r, size_t n)
 {
 	int *len_ptr, len, err;
 	/* 64-bit to avoid overflow in case of extreme application behavior */
@@ -268,12 +268,42 @@ static int64_t ringbuf_process_ring(struct ring *r)
 			}
 
 			smp_store_release(r->consumer_pos, cons_pos);
+
+			if (cnt >= n)
+				goto done;
 		}
 	} while (got_new_data);
 done:
 	return cnt;
 }
 
+/* Consume available ring buffer(s) data without event polling, up to n
+ * records.
+ *
+ * Returns number of records consumed across all registered ring buffers (or
+ * n, whichever is less), or negative number if any of the callbacks return
+ * error.
+ */
+int ring_buffer__consume_n(struct ring_buffer *rb, size_t n)
+{
+	int64_t err, res = 0;
+	int i;
+
+	for (i = 0; i < rb->ring_cnt; i++) {
+		struct ring *ring = rb->rings[i];
+
+		err = ringbuf_process_ring(ring, n);
+		if (err < 0)
+			return libbpf_err(err);
+		res += err;
+		n -= err;
+
+		if (n == 0)
+			break;
+	}
+	return res > INT_MAX ? INT_MAX : res;
+}
+
 /* Consume available ring buffer(s) data without event polling.
  * Returns number of records consumed across all registered ring buffers (or
  * INT_MAX, whichever is less), or negative number if any of the callbacks
@@ -287,13 +317,15 @@ int ring_buffer__consume(struct ring_buffer *rb)
 	for (i = 0; i < rb->ring_cnt; i++) {
 		struct ring *ring = rb->rings[i];
 
-		err = ringbuf_process_ring(ring);
+		err = ringbuf_process_ring(ring, INT_MAX);
 		if (err < 0)
 			return libbpf_err(err);
 		res += err;
+		if (res > INT_MAX) {
+			res = INT_MAX;
+			break;
+		}
 	}
-	if (res > INT_MAX)
-		return INT_MAX;
 	return res;
 }
 
@@ -314,13 +346,13 @@ int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms)
 		__u32 ring_id = rb->events[i].data.fd;
 		struct ring *ring = rb->rings[ring_id];
 
-		err = ringbuf_process_ring(ring);
+		err = ringbuf_process_ring(ring, INT_MAX);
 		if (err < 0)
 			return libbpf_err(err);
 		res += err;
 	}
 	if (res > INT_MAX)
-		return INT_MAX;
+		res = INT_MAX;
 	return res;
 }
 
@@ -371,17 +403,22 @@ int ring__map_fd(const struct ring *r)
 	return r->map_fd;
 }
 
-int ring__consume(struct ring *r)
+int ring__consume_n(struct ring *r, size_t n)
 {
 	int64_t res;
 
-	res = ringbuf_process_ring(r);
+	res = ringbuf_process_ring(r, n);
 	if (res < 0)
 		return libbpf_err(res);
 
 	return res > INT_MAX ? INT_MAX : res;
 }
 
+int ring__consume(struct ring *r)
+{
+	return ring__consume_n(r, INT_MAX);
+}
+
 static void user_ringbuf_unmap_ring(struct user_ring_buffer *rb)
 {
 	if (rb->consumer_pos) {
diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c
index 146da01979..5e6a1e27dd 100644
--- a/tools/lib/bpf/str_error.c
+++ b/tools/lib/bpf/str_error.c
@@ -2,6 +2,7 @@
 #undef _GNU_SOURCE
 #include <string.h>
 #include <stdio.h>
+#include <errno.h>
 #include "str_error.h"
 
 /* make sure libbpf doesn't use kernel-only integer typedefs */
@@ -15,7 +16,18 @@
 char *libbpf_strerror_r(int err, char *dst, int len)
 {
 	int ret = strerror_r(err < 0 ? -err : err, dst, len);
-	if (ret)
-		snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret);
+	/* on glibc <2.13, ret == -1 and errno is set, if strerror_r() can't
+	 * handle the error, on glibc >=2.13 *positive* (errno-like) error
+	 * code is returned directly
+	 */
+	if (ret == -1)
+		ret = errno;
+	if (ret) {
+		if (ret == EINVAL)
+			/* strerror_r() doesn't recognize this specific error */
+			snprintf(dst, len, "unknown error (%d)", err < 0 ? err : -err);
+		else
+			snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret);
+	}
 	return dst;
 }
diff --git a/tools/lib/bpf/usdt.bpf.h b/tools/lib/bpf/usdt.bpf.h
index f6763300b2..76359bcdc9 100644
--- a/tools/lib/bpf/usdt.bpf.h
+++ b/tools/lib/bpf/usdt.bpf.h
@@ -214,18 +214,18 @@ long bpf_usdt_cookie(struct pt_regs *ctx)
 
 /* we rely on ___bpf_apply() and ___bpf_narg() macros already defined in bpf_tracing.h */
 #define ___bpf_usdt_args0() ctx
-#define ___bpf_usdt_args1(x) ___bpf_usdt_args0(), ({ long _x; bpf_usdt_arg(ctx, 0, &_x); (void *)_x; })
-#define ___bpf_usdt_args2(x, args...) ___bpf_usdt_args1(args), ({ long _x; bpf_usdt_arg(ctx, 1, &_x); (void *)_x; })
-#define ___bpf_usdt_args3(x, args...) ___bpf_usdt_args2(args), ({ long _x; bpf_usdt_arg(ctx, 2, &_x); (void *)_x; })
-#define ___bpf_usdt_args4(x, args...) ___bpf_usdt_args3(args), ({ long _x; bpf_usdt_arg(ctx, 3, &_x); (void *)_x; })
-#define ___bpf_usdt_args5(x, args...) ___bpf_usdt_args4(args), ({ long _x; bpf_usdt_arg(ctx, 4, &_x); (void *)_x; })
-#define ___bpf_usdt_args6(x, args...) ___bpf_usdt_args5(args), ({ long _x; bpf_usdt_arg(ctx, 5, &_x); (void *)_x; })
-#define ___bpf_usdt_args7(x, args...) ___bpf_usdt_args6(args), ({ long _x; bpf_usdt_arg(ctx, 6, &_x); (void *)_x; })
-#define ___bpf_usdt_args8(x, args...) ___bpf_usdt_args7(args), ({ long _x; bpf_usdt_arg(ctx, 7, &_x); (void *)_x; })
-#define ___bpf_usdt_args9(x, args...) ___bpf_usdt_args8(args), ({ long _x; bpf_usdt_arg(ctx, 8, &_x); (void *)_x; })
-#define ___bpf_usdt_args10(x, args...) ___bpf_usdt_args9(args), ({ long _x; bpf_usdt_arg(ctx, 9, &_x); (void *)_x; })
-#define ___bpf_usdt_args11(x, args...) ___bpf_usdt_args10(args), ({ long _x; bpf_usdt_arg(ctx, 10, &_x); (void *)_x; })
-#define ___bpf_usdt_args12(x, args...) ___bpf_usdt_args11(args), ({ long _x; bpf_usdt_arg(ctx, 11, &_x); (void *)_x; })
+#define ___bpf_usdt_args1(x) ___bpf_usdt_args0(), ({ long _x; bpf_usdt_arg(ctx, 0, &_x); _x; })
+#define ___bpf_usdt_args2(x, args...) ___bpf_usdt_args1(args), ({ long _x; bpf_usdt_arg(ctx, 1, &_x); _x; })
+#define ___bpf_usdt_args3(x, args...) ___bpf_usdt_args2(args), ({ long _x; bpf_usdt_arg(ctx, 2, &_x); _x; })
+#define ___bpf_usdt_args4(x, args...) ___bpf_usdt_args3(args), ({ long _x; bpf_usdt_arg(ctx, 3, &_x); _x; })
+#define ___bpf_usdt_args5(x, args...) ___bpf_usdt_args4(args), ({ long _x; bpf_usdt_arg(ctx, 4, &_x); _x; })
+#define ___bpf_usdt_args6(x, args...) ___bpf_usdt_args5(args), ({ long _x; bpf_usdt_arg(ctx, 5, &_x); _x; })
+#define ___bpf_usdt_args7(x, args...) ___bpf_usdt_args6(args), ({ long _x; bpf_usdt_arg(ctx, 6, &_x); _x; })
+#define ___bpf_usdt_args8(x, args...) ___bpf_usdt_args7(args), ({ long _x; bpf_usdt_arg(ctx, 7, &_x); _x; })
+#define ___bpf_usdt_args9(x, args...) ___bpf_usdt_args8(args), ({ long _x; bpf_usdt_arg(ctx, 8, &_x); _x; })
+#define ___bpf_usdt_args10(x, args...) ___bpf_usdt_args9(args), ({ long _x; bpf_usdt_arg(ctx, 9, &_x); _x; })
+#define ___bpf_usdt_args11(x, args...) ___bpf_usdt_args10(args), ({ long _x; bpf_usdt_arg(ctx, 10, &_x); _x; })
+#define ___bpf_usdt_args12(x, args...) ___bpf_usdt_args11(args), ({ long _x; bpf_usdt_arg(ctx, 11, &_x); _x; })
 #define ___bpf_usdt_args(args...) ___bpf_apply(___bpf_usdt_args, ___bpf_narg(args))(args)
 
 /*
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index 4adcd7920d..cae799ad44 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -18,9 +18,13 @@ void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus)
 
 struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus)
 {
-	RC_STRUCT(perf_cpu_map) *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus);
+	RC_STRUCT(perf_cpu_map) *cpus;
 	struct perf_cpu_map *result;
 
+	if (nr_cpus == 0)
+		return NULL;
+
+	cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus);
 	if (ADD_RC_CHK(result, cpus)) {
 		cpus->nr = nr_cpus;
 		refcount_set(&cpus->refcnt, 1);
@@ -316,6 +320,19 @@ bool perf_cpu_map__has_any_cpu_or_is_empty(const struct perf_cpu_map *map)
 	return map ? __perf_cpu_map__cpu(map, 0).cpu == -1 : true;
 }
 
+bool perf_cpu_map__is_any_cpu_or_is_empty(const struct perf_cpu_map *map)
+{
+	if (!map)
+		return true;
+
+	return __perf_cpu_map__nr(map) == 1 && __perf_cpu_map__cpu(map, 0).cpu == -1;
+}
+
+bool perf_cpu_map__is_empty(const struct perf_cpu_map *map)
+{
+	return map == NULL;
+}
+
 int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
 {
 	int low, high;
@@ -372,6 +389,20 @@ bool perf_cpu_map__has_any_cpu(const struct perf_cpu_map *map)
 	return map && __perf_cpu_map__cpu(map, 0).cpu == -1;
 }
 
+struct perf_cpu perf_cpu_map__min(const struct perf_cpu_map *map)
+{
+	struct perf_cpu cpu, result = {
+		.cpu = -1
+	};
+	int idx;
+
+	perf_cpu_map__for_each_cpu_skip_any(cpu, idx, map) {
+		result = cpu;
+		break;
+	}
+	return result;
+}
+
 struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map)
 {
 	struct perf_cpu result = {
diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index 228c6c629b..90457d17fb 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -61,6 +61,22 @@ LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
  * perf_cpu_map__has_any_cpu_or_is_empty - is map either empty or has the "any CPU"/dummy value.
  */
 LIBPERF_API bool perf_cpu_map__has_any_cpu_or_is_empty(const struct perf_cpu_map *map);
+/**
+ * perf_cpu_map__is_any_cpu_or_is_empty - is map either empty or the "any CPU"/dummy value.
+ */
+LIBPERF_API bool perf_cpu_map__is_any_cpu_or_is_empty(const struct perf_cpu_map *map);
+/**
+ * perf_cpu_map__is_empty - does the map contain no values and it doesn't
+ *                          contain the special "any CPU"/dummy value.
+ */
+LIBPERF_API bool perf_cpu_map__is_empty(const struct perf_cpu_map *map);
+/**
+ * perf_cpu_map__min - the minimum CPU value or -1 if empty or just the "any CPU"/dummy value.
+ */
+LIBPERF_API struct perf_cpu perf_cpu_map__min(const struct perf_cpu_map *map);
+/**
+ * perf_cpu_map__max - the maximum CPU value or -1 if empty or just the "any CPU"/dummy value.
+ */
 LIBPERF_API struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map);
 LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu);
 LIBPERF_API bool perf_cpu_map__equal(const struct perf_cpu_map *lhs,
diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map
index 10b3f37226..2aa79b6960 100644
--- a/tools/lib/perf/libperf.map
+++ b/tools/lib/perf/libperf.map
@@ -10,6 +10,10 @@ LIBPERF_0.0.1 {
 		perf_cpu_map__nr;
 		perf_cpu_map__cpu;
 		perf_cpu_map__has_any_cpu_or_is_empty;
+		perf_cpu_map__is_any_cpu_or_is_empty;
+		perf_cpu_map__is_empty;
+		perf_cpu_map__has_any_cpu;
+		perf_cpu_map__min;
 		perf_cpu_map__max;
 		perf_cpu_map__has;
 		perf_thread_map__new_array;
diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c
index 0c903c2372..c1a51d925e 100644
--- a/tools/lib/perf/mmap.c
+++ b/tools/lib/perf/mmap.c
@@ -279,7 +279,7 @@ union perf_event *perf_mmap__read_event(struct perf_mmap *map)
 	if (!refcount_read(&map->refcnt))
 		return NULL;
 
-	/* non-overwirte doesn't pause the ringbuffer */
+	/* non-overwrite doesn't pause the ringbuffer */
 	if (!map->overwrite)
 		map->end = perf_mmap__read_head(map);
 
diff --git a/tools/lib/rbtree.c b/tools/lib/rbtree.c
index 727396de6b..9e7307186b 100644
--- a/tools/lib/rbtree.c
+++ b/tools/lib/rbtree.c
@@ -58,7 +58,7 @@
 
 static inline void rb_set_black(struct rb_node *rb)
 {
-	rb->__rb_parent_color |= RB_BLACK;
+	rb->__rb_parent_color += RB_BLACK;
 }
 
 static inline struct rb_node *rb_red_parent(struct rb_node *red)
diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c
index d943d78b78..4b60ec03b0 100644
--- a/tools/lib/subcmd/parse-options.c
+++ b/tools/lib/subcmd/parse-options.c
@@ -808,18 +808,30 @@ static int option__cmp(const void *va, const void *vb)
 
 static struct option *options__order(const struct option *opts)
 {
-	int nr_opts = 0, nr_group = 0, len;
-	const struct option *o = opts;
-	struct option *opt, *ordered, *group;
-
-	for (o = opts; o->type != OPTION_END; o++)
-		++nr_opts;
-
-	len = sizeof(*o) * (nr_opts + 1);
-	ordered = malloc(len);
-	if (!ordered)
-		goto out;
-	memcpy(ordered, opts, len);
+	int nr_opts = 0, nr_group = 0, nr_parent = 0, len;
+	const struct option *o, *p = opts;
+	struct option *opt, *ordered = NULL, *group;
+
+	/* flatten the options that have parents */
+	for (p = opts; p != NULL; p = o->parent) {
+		for (o = p; o->type != OPTION_END; o++)
+			++nr_opts;
+
+		/*
+		 * the length is given by the number of options plus a null
+		 * terminator for the last loop iteration.
+		 */
+		len = sizeof(*o) * (nr_opts + !o->parent);
+		group = realloc(ordered, len);
+		if (!group)
+			goto out;
+		ordered = group;
+		memcpy(&ordered[nr_parent], p, sizeof(*o) * (nr_opts - nr_parent));
+
+		nr_parent = nr_opts;
+	}
+	/* copy the last OPTION_END */
+	memcpy(&ordered[nr_opts], o, sizeof(*o));
 
 	/* sort each option group individually */
 	for (opt = group = ordered; opt->type != OPTION_END; opt++) {
diff --git a/tools/lib/subcmd/run-command.c b/tools/lib/subcmd/run-command.c
index d435eb4235..4e3a557a2f 100644
--- a/tools/lib/subcmd/run-command.c
+++ b/tools/lib/subcmd/run-command.c
@@ -165,43 +165,65 @@ int start_command(struct child_process *cmd)
 	return 0;
 }
 
-static int wait_or_whine(pid_t pid)
+static int wait_or_whine(struct child_process *cmd, bool block)
 {
-	char sbuf[STRERR_BUFSIZE];
+	bool finished = cmd->finished;
+	int result = cmd->finish_result;
 
-	for (;;) {
+	while (!finished) {
 		int status, code;
-		pid_t waiting = waitpid(pid, &status, 0);
+		pid_t waiting = waitpid(cmd->pid, &status, block ? 0 : WNOHANG);
+
+		if (!block && waiting == 0)
+			break;
+
+		if (waiting < 0 && errno == EINTR)
+			continue;
 
+		finished = true;
 		if (waiting < 0) {
-			if (errno == EINTR)
-				continue;
+			char sbuf[STRERR_BUFSIZE];
+
 			fprintf(stderr, " Error: waitpid failed (%s)",
 				str_error_r(errno, sbuf, sizeof(sbuf)));
-			return -ERR_RUN_COMMAND_WAITPID;
-		}
-		if (waiting != pid)
-			return -ERR_RUN_COMMAND_WAITPID_WRONG_PID;
-		if (WIFSIGNALED(status))
-			return -ERR_RUN_COMMAND_WAITPID_SIGNAL;
-
-		if (!WIFEXITED(status))
-			return -ERR_RUN_COMMAND_WAITPID_NOEXIT;
-		code = WEXITSTATUS(status);
-		switch (code) {
-		case 127:
-			return -ERR_RUN_COMMAND_EXEC;
-		case 0:
-			return 0;
-		default:
-			return -code;
+			result = -ERR_RUN_COMMAND_WAITPID;
+		} else if (waiting != cmd->pid) {
+			result = -ERR_RUN_COMMAND_WAITPID_WRONG_PID;
+		} else if (WIFSIGNALED(status)) {
+			result = -ERR_RUN_COMMAND_WAITPID_SIGNAL;
+		} else if (!WIFEXITED(status)) {
+			result = -ERR_RUN_COMMAND_WAITPID_NOEXIT;
+		} else {
+			code = WEXITSTATUS(status);
+			switch (code) {
+			case 127:
+				result = -ERR_RUN_COMMAND_EXEC;
+				break;
+			case 0:
+				result = 0;
+				break;
+			default:
+				result = -code;
+				break;
+			}
 		}
 	}
+	if (finished) {
+		cmd->finished = 1;
+		cmd->finish_result = result;
+	}
+	return result;
+}
+
+int check_if_command_finished(struct child_process *cmd)
+{
+	wait_or_whine(cmd, /*block=*/false);
+	return cmd->finished;
 }
 
 int finish_command(struct child_process *cmd)
 {
-	return wait_or_whine(cmd->pid);
+	return wait_or_whine(cmd, /*block=*/true);
 }
 
 int run_command(struct child_process *cmd)
diff --git a/tools/lib/subcmd/run-command.h b/tools/lib/subcmd/run-command.h
index d794138a79..b2d39de6e6 100644
--- a/tools/lib/subcmd/run-command.h
+++ b/tools/lib/subcmd/run-command.h
@@ -41,17 +41,20 @@ struct child_process {
 	int err;
 	const char *dir;
 	const char *const *env;
+	int finish_result;
 	unsigned no_stdin:1;
 	unsigned no_stdout:1;
 	unsigned no_stderr:1;
 	unsigned exec_cmd:1; /* if this is to be external sub-command */
 	unsigned stdout_to_stderr:1;
+	unsigned finished:1;
 	void (*preexec_cb)(void);
 	 /* If set, call function in child rather than doing an exec. */
 	int (*no_exec_cmd)(struct child_process *process);
 };
 
 int start_command(struct child_process *);
+int check_if_command_finished(struct child_process *);
 int finish_command(struct child_process *);
 int run_command(struct child_process *);