New added android kernel bpf helpers are not detected

I'm trying to patch an android kernel 4.9 to support probe_read_{user, kernel} and probe_read_{user, kernel} helpers. For the backporting I took example from another patch that adds bpf_probe_read_str helper. While I've patched the kernel to add the helpers and running bpftrace --info, the str helper shows up but the newly added ones don't. bpftrace output

System
  OS: Linux 4.9.337-g4fcceb75c5cd #1 SMP PREEMPT Sat May 18 17:26:12 EEST 2024
  Arch: aarch64

Build
  version: v0.19.1
  LLVM: 14.0.6
  unsafe probe: yes
  bfd: no
  libdw (DWARF support): no

libbpf: failed to find valid kernel BTF
Kernel helpers
  probe_read: yes
  probe_read_str: yes
  probe_read_user: no
  probe_read_user_str: no
  probe_read_kernel: no
  probe_read_kernel_str: no
  get_current_cgroup_id: no
  send_signal: no
  override_return: no
  get_boot_ns: no
  dpath: no
  skboutput: no
  get_tai_ns: no
  get_func_ip: no

Kernel features
  Instruction limit: -1
  Loop support: no
  btf: no
  module btf: no
  map batch: no
  uprobe refcount (depends on Build:bcc bpf_attach_uprobe refcount): no

Map types
  hash: yes
  percpu hash: yes
  array: yes
  percpu array: yes
  stack_trace: yes
  perf_event_array: yes
  ringbuf: no

Probe types
  kprobe: yes
  tracepoint: yes
  perf_event: yes
  kfunc: no
  kprobe_multi: no
  raw_tp_special: no
  iter: no

probe_read_{user, kernel} and probe_read_{user, kernel}

diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index cc5ba47062e8..48762ecbfd66 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -88,6 +88,7 @@ static inline unsigned long __copy_from_user_nocache(void *to,
  * happens, handle that and return -EFAULT.
  */
 extern long probe_kernel_read(void *dst, const void *src, size_t size);
+extern long probe_kernel_read_strict(void *dst, const void *src, size_t size);
 extern long __probe_kernel_read(void *dst, const void *src, size_t size);
 
 /*
@@ -126,6 +127,8 @@ extern long notrace probe_user_write(void __user *dst, const void *src, size_t s
 extern long notrace __probe_user_write(void __user *dst, const void *src, size_t size);
 
 extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
+long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr,
+		long count);
 extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr,
 				     long count);
 extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 67d7d771a944..d1036b0ba1fa 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -552,6 +552,11 @@ enum bpf_func_id {
 	 */
 	BPF_FUNC_get_socket_uid,
 
+	BPF_FUNC_probe_read_user,
+	BPF_FUNC_probe_read_kernel,
+	BPF_FUNC_probe_read_user_str,
+	BPF_FUNC_probe_read_kernel_str,
+
 	__BPF_FUNC_MAX_ID,
 };
 
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 83b20092b84c..e872ab1fb235 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -85,44 +85,6 @@ BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr)
 	return ret;
 }
 
-static const struct bpf_func_proto bpf_probe_read_proto = {
-	.func		= bpf_probe_read,
-	.gpl_only	= true,
-	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_RAW_STACK,
-	.arg2_type	= ARG_CONST_STACK_SIZE,
-	.arg3_type	= ARG_ANYTHING,
-};
-
-BPF_CALL_3(bpf_probe_read_str, void *, dst, u32, size, const void *, unsafe_ptr)
-{
-	int ret;
-
-	/*
-	 * The strncpy_from_unsafe() call will likely not fill the entire
-	 * buffer, but that's okay in this circumstance as we're probing
-	 * arbitrary memory anyway similar to bpf_probe_read() and might
-	 * as well probe the stack. Thus, memory is explicitly cleared
-	 * only in error case, so that improper users ignoring return
-	 * code altogether don't copy garbage; otherwise length of string
-	 * is returned that can be used for bpf_perf_event_output() et al.
-	 */
-	ret = strncpy_from_unsafe(dst, unsafe_ptr, size);
-	if (unlikely(ret < 0))
-		memset(dst, 0, size);
-
-	return ret;
-}
-
-static const struct bpf_func_proto bpf_probe_read_str_proto = {
-	.func           = bpf_probe_read_str,
-	.gpl_only       = true,
-	.ret_type       = RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_RAW_STACK,
-	.arg2_type	= ARG_CONST_STACK_SIZE,
-	.arg3_type	= ARG_ANYTHING,
-};
-
 BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
 	   u32, size)
 {
@@ -465,6 +427,139 @@ static const struct bpf_func_proto bpf_current_task_under_cgroup_proto = {
 	.arg2_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_3(bpf_probe_read_user, void *, dst, u32, size,
+	   const void __user *, unsafe_ptr)
+{
+	int ret = probe_user_read(dst, unsafe_ptr, size);
+
+	if (unlikely(ret < 0))
+		memset(dst, 0, size);
+
+	return ret;
+}
+
+static const struct bpf_func_proto bpf_probe_read_user_proto = {
+	.func		    = bpf_probe_read_user,
+	.gpl_only	  = true,
+	.ret_type	  = RET_INTEGER,
+	.arg1_type  = ARG_PTR_TO_RAW_STACK,
+	.arg2_type	= ARG_CONST_STACK_SIZE,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_3(bpf_probe_read_user_str, void *, dst, u32, size,
+	   const void __user *, unsafe_ptr)
+{
+	int ret = strncpy_from_unsafe_user(dst, unsafe_ptr, size);
+
+	if (unlikely(ret < 0))
+		memset(dst, 0, size);
+
+	return ret;
+}
+
+static const struct bpf_func_proto bpf_probe_read_user_str_proto = {
+	.func		= bpf_probe_read_user_str,
+	.gpl_only   = true,
+	.ret_type   = RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_RAW_STACK,
+	.arg2_type	= ARG_CONST_STACK_SIZE,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+static __always_inline int
+bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr,
+			     const bool compat)
+{
+	int ret;
+	ret = compat ? probe_kernel_read(dst, unsafe_ptr, size) :
+	      probe_kernel_read_strict(dst, unsafe_ptr, size);
+	if (unlikely(ret < 0))
+		memset(dst, 0, size);
+	return ret;
+}
+
+BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size,
+	   const void *, unsafe_ptr)
+{
+	return bpf_probe_read_kernel_common(dst, size, unsafe_ptr, false);
+}
+
+static const struct bpf_func_proto bpf_probe_read_kernel_proto = {
+	.func		= bpf_probe_read_kernel,
+	.gpl_only   = true,
+	.ret_type   = RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_RAW_STACK,
+	.arg2_type	= ARG_CONST_STACK_SIZE,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_3(bpf_probe_read_compat, void *, dst, u32, size,
+	   const void *, unsafe_ptr)
+{
+	return bpf_probe_read_kernel_common(dst, size, unsafe_ptr, true);
+}
+
+static const struct bpf_func_proto bpf_probe_read_compat_proto = {
+	.func		= bpf_probe_read_compat,
+	.gpl_only   = true,
+	.ret_type   = RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_RAW_STACK,
+	.arg2_type	= ARG_CONST_STACK_SIZE,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+static __always_inline int
+bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr,
+				 const bool compat)
+{
+	int ret;
+	/*
+	 * The strncpy_from_unsafe_*() call will likely not fill the entire
+	 * buffer, but that's okay in this circumstance as we're probing
+	 * arbitrary memory anyway similar to bpf_probe_read_*() and might
+	 * as well probe the stack. Thus, memory is explicitly cleared
+	 * only in error case, so that improper users ignoring return
+	 * code altogether don't copy garbage; otherwise length of string
+	 * is returned that can be used for bpf_perf_event_output() et al.
+	 */
+	ret = compat ? strncpy_from_unsafe(dst, unsafe_ptr, size) :
+	      strncpy_from_unsafe_strict(dst, unsafe_ptr, size);
+	if (unlikely(ret < 0))
+		memset(dst, 0, size);
+	return ret;
+}
+
+BPF_CALL_3(bpf_probe_read_kernel_str, void *, dst, u32, size,
+	   const void *, unsafe_ptr)
+{
+	return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr, false);
+}
+
+static const struct bpf_func_proto bpf_probe_read_kernel_str_proto = {
+	.func		= bpf_probe_read_kernel_str,
+	.gpl_only   = true,
+	.ret_type   = RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_RAW_STACK,
+	.arg2_type	= ARG_CONST_STACK_SIZE,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_3(bpf_probe_read_compat_str, void *, dst, u32, size,
+	   const void *, unsafe_ptr)
+{
+	return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr, true);
+}
+
+static const struct bpf_func_proto bpf_probe_read_compat_str_proto = {
+	.func		= bpf_probe_read_compat_str,
+	.gpl_only   = true,
+	.ret_type   = RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_RAW_STACK,
+	.arg2_type	= ARG_CONST_STACK_SIZE,
+	.arg3_type	= ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
@@ -474,10 +569,8 @@ static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
 		return &bpf_map_update_elem_proto;
 	case BPF_FUNC_map_delete_elem:
 		return &bpf_map_delete_elem_proto;
-	case BPF_FUNC_probe_read:
-		return &bpf_probe_read_proto;
 	case BPF_FUNC_probe_read_str:
-		return &bpf_probe_read_str_proto;
+		return &bpf_probe_read_compat_str_proto;
 	case BPF_FUNC_ktime_get_ns:
 		return &bpf_ktime_get_ns_proto;
 	case BPF_FUNC_tail_call:
@@ -504,6 +597,17 @@ static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
 		return &bpf_current_task_under_cgroup_proto;
 	case BPF_FUNC_get_prandom_u32:
 		return &bpf_get_prandom_u32_proto;
+	case BPF_FUNC_probe_read_user:
+		return &bpf_probe_read_user_proto;
+	case BPF_FUNC_probe_read_kernel:
+		return &bpf_probe_read_kernel_proto;
+	case BPF_FUNC_probe_read:
+		return &bpf_probe_read_compat_proto;
+	case BPF_FUNC_probe_read_user_str:
+		return &bpf_probe_read_user_str_proto;
+	case BPF_FUNC_probe_read_kernel_str:
+		return &bpf_probe_read_kernel_str_proto;
+
 	default:
 		return NULL;
 	}
diff --git a/mm/maccess.c b/mm/maccess.c
index 03ea550f5a74..583935a288ad 100644
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -47,6 +47,9 @@ probe_write_common(void __user *dst, const void *src, size_t size)
 long __weak probe_kernel_read(void *dst, const void *src, size_t size)
     __attribute__((alias("__probe_kernel_read")));
 
+long __weak probe_kernel_read_strict(void *dst, const void *src, size_t size)
+    __attribute__((alias("__probe_kernel_read")));
+
 long __probe_kernel_read(void *dst, const void *src, size_t size)
 {
 	long ret;
@@ -157,6 +160,10 @@ EXPORT_SYMBOL_GPL(probe_user_write);
  * If @count is smaller than the length of the string, copies @count-1 bytes,
  * sets the last byte of @dst buffer to NUL and returns @count.
  */
+long __weak strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr,
+				       long count)
+    __attribute__((alias("strncpy_from_unsafe")));
+
 long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)
 {
 	mm_segment_t old_fs = get_fs();
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index a339bea1f4c8..e6caf916d217 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -516,6 +516,11 @@ enum bpf_func_id {
 	 */
 	BPF_FUNC_get_socket_uid,
 
+	BPF_FUNC_probe_read_user,
+	BPF_FUNC_probe_read_kernel,
+	BPF_FUNC_probe_read_user_str,
+	BPF_FUNC_probe_read_kernel_str,
+
 	__BPF_FUNC_MAX_ID,
 };

bpf: add bpf_probe_read_str helper

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 83b20092b84c..59182e6d6f51 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -465,6 +465,36 @@ static const struct bpf_func_proto bpf_current_task_under_cgroup_proto = {
 	.arg2_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_3(bpf_probe_read_str, void *, dst, u32, size,
+	   const void *, unsafe_ptr)
+{
+	int ret;
+
+	/*
+	 * The strncpy_from_unsafe() call will likely not fill the entire
+	 * buffer, but that's okay in this circumstance as we're probing
+	 * arbitrary memory anyway similar to bpf_probe_read() and might
+	 * as well probe the stack. Thus, memory is explicitly cleared
+	 * only in error case, so that improper users ignoring return
+	 * code altogether don't copy garbage; otherwise length of string
+	 * is returned that can be used for bpf_perf_event_output() et al.
+	 */
+	ret = strncpy_from_unsafe(dst, unsafe_ptr, size);
+	if (unlikely(ret < 0))
+		memset(dst, 0, size);
+
+	return ret;
+}
+
+static const struct bpf_func_proto bpf_probe_read_str_proto = {
+	.func		= bpf_probe_read_str,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_RAW_STACK,
+	.arg2_type	= ARG_CONST_STACK_SIZE,
+	.arg3_type	= ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
@@ -504,6 +534,8 @@ static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
 		return &bpf_current_task_under_cgroup_proto;
 	case BPF_FUNC_get_prandom_u32:
 		return &bpf_get_prandom_u32_proto;
+	case BPF_FUNC_probe_read_str:
+		return &bpf_probe_read_str_proto;
 	default:
 		return NULL;
 	}