diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index 8376f22..379d03b 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -192,4 +192,122 @@ struct pt_regs;
 			  (void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
 #endif
 
+#define ___bpf_concat(a, b) a ## b
+#define ___bpf_apply(fn, n) ___bpf_concat(fn, n)
+#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N
+#define ___bpf_narg(...) \
+	___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+#define ___bpf_empty(...) \
+	___bpf_nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0)
+
+#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)
+
+/*
+ * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and
+ * similar kinds of BPF programs, that accept input arguments as a single
+ * pointer to untyped u64 array, where each u64 can actually be a typed
+ * pointer or integer of different size. Instead of requring user to write
+ * manual casts and work with array elements by index, BPF_PROG macro
+ * allows user to declare a list of named and typed input arguments in the
+ * same syntax as for normal C function. All the casting is hidden and
+ * performed transparently, while user code can just assume working with
+ * function arguments of specified type and name.
+ *
+ * Original raw context argument is preserved as well as 'ctx' argument.
+ * This is useful when using BPF helpers that expect original context
+ * as one of the parameters (e.g., for bpf_perf_event_output()).
+ */
+#define BPF_PROG(name, args...)						    \
+name(unsigned long long *ctx);						    \
+static __attribute__((always_inline)) typeof(name(0))			    \
+____##name(unsigned long long *ctx, ##args);				    \
+typeof(name(0)) name(unsigned long long *ctx)				    \
+{									    \
+	_Pragma("GCC diagnostic push")					    \
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
+	return ____##name(___bpf_ctx_cast(args));			    \
+	_Pragma("GCC diagnostic pop")					    \
+}									    \
+static __attribute__((always_inline)) typeof(name(0))			    \
+____##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)
+
+/*
+ * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for
+ * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific
+ * low-level way of getting kprobe input arguments from struct pt_regs, and
+ * provides a familiar typed and named function arguments syntax and
+ * semantics of accessing kprobe input paremeters.
+ *
+ * Original struct pt_regs* context is preserved as 'ctx' argument. This might
+ * be necessary when using BPF helpers like bpf_perf_event_output().
+ */
+#define BPF_KPROBE(name, args...)					    \
+name(struct pt_regs *ctx);						    \
+static __attribute__((always_inline)) typeof(name(0))			    \
+____##name(struct pt_regs *ctx, ##args);				    \
+typeof(name(0)) name(struct pt_regs *ctx)				    \
+{									    \
+	_Pragma("GCC diagnostic push")					    \
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
+	return ____##name(___bpf_kprobe_args(args));			    \
+	_Pragma("GCC diagnostic pop")					    \
+}									    \
+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_RET(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
+ * return value (in addition to `struct pt_regs *ctx`), but no input
+ * arguments, because they will be clobbered by the time probed function
+ * returns.
+ */
+#define BPF_KRETPROBE(name, args...)					    \
+name(struct pt_regs *ctx);						    \
+static __attribute__((always_inline)) typeof(name(0))			    \
+____##name(struct pt_regs *ctx, ##args);				    \
+typeof(name(0)) name(struct pt_regs *ctx)				    \
+{									    \
+	_Pragma("GCC diagnostic push")					    \
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
+	return ____##name(___bpf_kretprobe_args(args));			    \
+	_Pragma("GCC diagnostic pop")					    \
+}									    \
+static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
+
 #endif
diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index 8f21965..5bf2fe9 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -6,7 +6,7 @@
 #include <linux/types.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_core_read.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 #define BPF_STRUCT_OPS(name, args...) \
 SEC("struct_ops/"#name) \
diff --git a/tools/testing/selftests/bpf/bpf_trace_helpers.h b/tools/testing/selftests/bpf/bpf_trace_helpers.h
deleted file mode 100644
index 83b8e02..0000000
--- a/tools/testing/selftests/bpf/bpf_trace_helpers.h
+++ /dev/null
@@ -1,121 +0,0 @@
-/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
-#ifndef __BPF_TRACE_HELPERS_H
-#define __BPF_TRACE_HELPERS_H
-
-#include <bpf/bpf_helpers.h>
-
-#define ___bpf_concat(a, b) a ## b
-#define ___bpf_apply(fn, n) ___bpf_concat(fn, n)
-#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N
-#define ___bpf_narg(...) \
-	___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
-#define ___bpf_empty(...) \
-	___bpf_nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0)
-
-#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)
-
-/*
- * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and
- * similar kinds of BPF programs, that accept input arguments as a single
- * pointer to untyped u64 array, where each u64 can actually be a typed
- * pointer or integer of different size. Instead of requring user to write
- * manual casts and work with array elements by index, BPF_PROG macro
- * allows user to declare a list of named and typed input arguments in the
- * same syntax as for normal C function. All the casting is hidden and
- * performed transparently, while user code can just assume working with
- * function arguments of specified type and name.
- *
- * Original raw context argument is preserved as well as 'ctx' argument.
- * This is useful when using BPF helpers that expect original context
- * as one of the parameters (e.g., for bpf_perf_event_output()).
- */
-#define BPF_PROG(name, args...)						    \
-name(unsigned long long *ctx);						    \
-static __always_inline typeof(name(0))					    \
-____##name(unsigned long long *ctx, ##args);				    \
-typeof(name(0)) name(unsigned long long *ctx)				    \
-{									    \
-	_Pragma("GCC diagnostic push")					    \
-	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
-	return ____##name(___bpf_ctx_cast(args));			    \
-	_Pragma("GCC diagnostic pop")					    \
-}									    \
-static __always_inline typeof(name(0))					    \
-____##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)
-
-/*
- * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for
- * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific
- * low-level way of getting kprobe input arguments from struct pt_regs, and
- * provides a familiar typed and named function arguments syntax and
- * semantics of accessing kprobe input paremeters.
- *
- * Original struct pt_regs* context is preserved as 'ctx' argument. This might
- * be necessary when using BPF helpers like bpf_perf_event_output().
- */
-#define BPF_KPROBE(name, args...)					    \
-name(struct pt_regs *ctx);						    \
-static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args);\
-typeof(name(0)) name(struct pt_regs *ctx)				    \
-{									    \
-	_Pragma("GCC diagnostic push")					    \
-	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
-	return ____##name(___bpf_kprobe_args(args));			    \
-	_Pragma("GCC diagnostic pop")					    \
-}									    \
-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_RET(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
- * return value (in addition to `struct pt_regs *ctx`), but no input
- * arguments, because they will be clobbered by the time probed function
- * returns.
- */
-#define BPF_KRETPROBE(name, args...)					    \
-name(struct pt_regs *ctx);						    \
-static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args);\
-typeof(name(0)) name(struct pt_regs *ctx)				    \
-{									    \
-	_Pragma("GCC diagnostic push")					    \
-	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")		    \
-	return ____##name(___bpf_kretprobe_args(args));			    \
-	_Pragma("GCC diagnostic pop")					    \
-}									    \
-static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
-#endif
diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
index b631fb5..127ea76 100644
--- a/tools/testing/selftests/bpf/progs/bpf_dctcp.c
+++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
@@ -9,7 +9,7 @@
 #include <linux/bpf.h>
 #include <linux/types.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
 #include "bpf_tcp_helpers.h"
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/fentry_test.c b/tools/testing/selftests/bpf/progs/fentry_test.c
index 38d3a82..9365b68 100644
--- a/tools/testing/selftests/bpf/progs/fentry_test.c
+++ b/tools/testing/selftests/bpf/progs/fentry_test.c
@@ -2,7 +2,7 @@
 /* Copyright (c) 2019 Facebook */
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
index c329fcc..98e1efe 100644
--- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
@@ -5,7 +5,7 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 struct sk_buff {
 	unsigned int len;
diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c
index 92f3fa4..85c0b51 100644
--- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c
+++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c
@@ -2,7 +2,7 @@
 /* Copyright (c) 2019 Facebook */
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 struct sk_buff {
 	unsigned int len;
diff --git a/tools/testing/selftests/bpf/progs/fexit_test.c b/tools/testing/selftests/bpf/progs/fexit_test.c
index 348109b..bd1e17d 100644
--- a/tools/testing/selftests/bpf/progs/fexit_test.c
+++ b/tools/testing/selftests/bpf/progs/fexit_test.c
@@ -2,7 +2,7 @@
 /* Copyright (c) 2019 Facebook */
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c
index 8f48a90..a46a264 100644
--- a/tools/testing/selftests/bpf/progs/kfree_skb.c
+++ b/tools/testing/selftests/bpf/progs/kfree_skb.c
@@ -4,7 +4,7 @@
 #include <stdbool.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 struct {
diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe.c b/tools/testing/selftests/bpf/progs/test_attach_probe.c
index 38ed8c3..8056a4c 100644
--- a/tools/testing/selftests/bpf/progs/test_attach_probe.c
+++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c
@@ -4,7 +4,7 @@
 #include <linux/ptrace.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 int kprobe_res = 0;
 int kretprobe_res = 0;
diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c
index f43714c..56a50b2 100644
--- a/tools/testing/selftests/bpf/progs/test_overhead.c
+++ b/tools/testing/selftests/bpf/progs/test_overhead.c
@@ -6,7 +6,6 @@
 #include <linux/ptrace.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-#include "bpf_trace_helpers.h"
 
 struct task_struct;
 
diff --git a/tools/testing/selftests/bpf/progs/test_perf_branches.c b/tools/testing/selftests/bpf/progs/test_perf_branches.c
index 0f7e27d..a1ccc83 100644
--- a/tools/testing/selftests/bpf/progs/test_perf_branches.c
+++ b/tools/testing/selftests/bpf/progs/test_perf_branches.c
@@ -5,7 +5,7 @@
 #include <linux/ptrace.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 int valid = 0;
 int required_size_out = 0;
diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
index ebfcc9f..ad59c4c9 100644
--- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c
+++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
@@ -4,7 +4,7 @@
 #include <linux/ptrace.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
diff --git a/tools/testing/selftests/bpf/progs/test_probe_user.c b/tools/testing/selftests/bpf/progs/test_probe_user.c
index d556b15..89b3532 100644
--- a/tools/testing/selftests/bpf/progs/test_probe_user.c
+++ b/tools/testing/selftests/bpf/progs/test_probe_user.c
@@ -7,7 +7,6 @@
 
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-#include "bpf_trace_helpers.h"
 
 static struct sockaddr_in old;
 
diff --git a/tools/testing/selftests/bpf/progs/test_trampoline_count.c b/tools/testing/selftests/bpf/progs/test_trampoline_count.c
index e51e6e3..f030e46 100644
--- a/tools/testing/selftests/bpf/progs/test_trampoline_count.c
+++ b/tools/testing/selftests/bpf/progs/test_trampoline_count.c
@@ -2,7 +2,8 @@
 #include <stdbool.h>
 #include <stddef.h>
 #include <linux/bpf.h>
-#include "bpf_trace_helpers.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 
 struct task_struct;
 
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c
index b840fc9..42dd2fe 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/bpf.h>
+#include <bpf/bpf_tracing.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_trace_helpers.h"
 
 struct net_device {
 	/* Structure does not need to contain all entries,