Merge tag 'nolibc.2022.05.20a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu

Pull nolibc library updates from Paul McKenney:
 "This adds a number of library functions and splits this library into
  multiple files"

* tag 'nolibc.2022.05.20a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (61 commits)
  tools/nolibc/string: Implement `strdup()` and `strndup()`
  tools/nolibc/string: Implement `strnlen()`
  tools/nolibc/stdlib: Implement `malloc()`, `calloc()`, `realloc()` and `free()`
  tools/nolibc/types: Implement `offsetof()` and `container_of()` macro
  tools/nolibc/sys: Implement `mmap()` and `munmap()`
  tools/nolibc: i386: Implement syscall with 6 arguments
  tools/nolibc: Remove .global _start from the entry point code
  tools/nolibc: Replace `asm` with `__asm__`
  tools/nolibc: x86-64: Update System V ABI document link
  tools/nolibc/stdlib: only reference the external environ when inlined
  tools/nolibc/string: do not use __builtin_strlen() at -O0
  tools/nolibc: add the nolibc subdir to the common Makefile
  tools/nolibc: add a makefile to install headers
  tools/nolibc/types: add poll() and waitpid() flag definitions
  tools/nolibc/sys: add syscall definition for getppid()
  tools/nolibc/string: add strcmp() and strncmp()
  tools/nolibc/stdio: add support for '%p' to vfprintf()
  tools/nolibc/stdlib: add a simple getenv() implementation
  tools/nolibc/stdio: make printf(%s) accept NULL
  tools/nolibc/stdlib: implement abort()
  ...

21 files changed, 4114 insertions, 2505 deletions

diff --git a/tools/Makefile b/tools/Makefile
index db2f7b8ebed5..724134f0e56c 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -24,6 +24,7 @@ help:
 	@echo '  intel-speed-select     - Intel Speed Select tool'
 	@echo '  kvm_stat               - top-like utility for displaying kvm statistics'
 	@echo '  leds                   - LEDs  tools'
+	@echo '  nolibc                 - nolibc headers testing and installation'
 	@echo '  objtool                - an ELF object analysis tool'
 	@echo '  pci                    - PCI tools'
 	@echo '  perf                   - Linux performance measurement and analysis tool'
@@ -74,6 +75,9 @@ bpf/%: FORCE
 libapi: FORCE
 	$(call descend,lib/api)
 
+nolibc_%: FORCE
+	$(call descend,include/nolibc,$(patsubst nolibc_%,%,$@))
+
 # The perf build does not follow the descend function setup,
 # invoking it via it's own make rule.
 PERF_O   = $(if $(O),$(O)/tools/perf,)
diff --git a/tools/include/nolibc/Makefile b/tools/include/nolibc/Makefile
new file mode 100644
index 000000000000..7a16d917c185
--- /dev/null
+++ b/tools/include/nolibc/Makefile
@@ -0,0 +1,42 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for nolibc installation and tests
+include ../../scripts/Makefile.include
+
+# we're in ".../tools/include/nolibc"
+ifeq ($(srctree),)
+srctree := $(patsubst %/tools/include/,%,$(dir $(CURDIR)))
+endif
+
+nolibc_arch := $(patsubst arm64,aarch64,$(ARCH))
+arch_file := arch-$(nolibc_arch).h
+all_files := ctype.h errno.h nolibc.h signal.h std.h stdio.h stdlib.h string.h \
+             sys.h time.h types.h unistd.h
+
+# install all headers needed to support a bare-metal compiler
+all:
+
+# Note: when ARCH is "x86" we concatenate both x86_64 and i386
+headers:
+	$(Q)mkdir -p $(OUTPUT)sysroot
+	$(Q)mkdir -p $(OUTPUT)sysroot/include
+	$(Q)cp $(all_files) $(OUTPUT)sysroot/include/
+	$(Q)if [ "$(ARCH)" = "x86" ]; then      \
+		sed -e                          \
+		  's,^#ifndef _NOLIBC_ARCH_X86_64_H,#if !defined(_NOLIBC_ARCH_X86_64_H) \&\& defined(__x86_64__),' \
+		  arch-x86_64.h;                \
+		sed -e                          \
+		  's,^#ifndef _NOLIBC_ARCH_I386_H,#if !defined(_NOLIBC_ARCH_I386_H) \&\& !defined(__x86_64__),' \
+		  arch-i386.h;                  \
+	elif [ -e "$(arch_file)" ]; then        \
+		cat $(arch_file);               \
+	else                                    \
+		echo "Fatal: architecture $(ARCH) not yet supported by nolibc." >&2; \
+		exit 1;                         \
+	fi > $(OUTPUT)sysroot/include/arch.h
+
+headers_standalone: headers
+	$(Q)$(MAKE) -C $(srctree) headers
+	$(Q)$(MAKE) -C $(srctree) headers_install INSTALL_HDR_PATH=$(OUTPUT)/sysroot
+
+clean:
+	$(call QUIET_CLEAN, nolibc) rm -rf "$(OUTPUT)sysroot"
diff --git a/tools/include/nolibc/arch-aarch64.h b/tools/include/nolibc/arch-aarch64.h
new file mode 100644
index 000000000000..f68baf8f395f
--- /dev/null
+++ b/tools/include/nolibc/arch-aarch64.h
@@ -0,0 +1,199 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * AARCH64 specific definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ARCH_AARCH64_H
+#define _NOLIBC_ARCH_AARCH64_H
+
+/* O_* macros for fcntl/open are architecture-specific */
+#define O_RDONLY            0
+#define O_WRONLY            1
+#define O_RDWR              2
+#define O_CREAT          0x40
+#define O_EXCL           0x80
+#define O_NOCTTY        0x100
+#define O_TRUNC         0x200
+#define O_APPEND        0x400
+#define O_NONBLOCK      0x800
+#define O_DIRECTORY    0x4000
+
+/* The struct returned by the newfstatat() syscall. Differs slightly from the
+ * x86_64's stat one by field ordering, so be careful.
+ */
+struct sys_stat_struct {
+	unsigned long   st_dev;
+	unsigned long   st_ino;
+	unsigned int    st_mode;
+	unsigned int    st_nlink;
+	unsigned int    st_uid;
+	unsigned int    st_gid;
+
+	unsigned long   st_rdev;
+	unsigned long   __pad1;
+	long            st_size;
+	int             st_blksize;
+	int             __pad2;
+
+	long            st_blocks;
+	long            st_atime;
+	unsigned long   st_atime_nsec;
+	long            st_mtime;
+
+	unsigned long   st_mtime_nsec;
+	long            st_ctime;
+	unsigned long   st_ctime_nsec;
+	unsigned int    __unused[2];
+};
+
+/* Syscalls for AARCH64 :
+ *   - registers are 64-bit
+ *   - stack is 16-byte aligned
+ *   - syscall number is passed in x8
+ *   - arguments are in x0, x1, x2, x3, x4, x5
+ *   - the system call is performed by calling svc 0
+ *   - syscall return comes in x0.
+ *   - the arguments are cast to long and assigned into the target registers
+ *     which are then simply passed as registers to the asm code, so that we
+ *     don't have to experience issues with register constraints.
+ *
+ * On aarch64, select() is not implemented so we have to use pselect6().
+ */
+#define __ARCH_WANT_SYS_PSELECT6
+
+#define my_syscall0(num)                                                      \
+({                                                                            \
+	register long _num  __asm__ ("x8") = (num);                           \
+	register long _arg1 __asm__ ("x0");                                   \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"svc #0\n"                                                    \
+		: "=r"(_arg1)                                                 \
+		: "r"(_num)                                                   \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+#define my_syscall1(num, arg1)                                                \
+({                                                                            \
+	register long _num  __asm__ ("x8") = (num);                           \
+	register long _arg1 __asm__ ("x0") = (long)(arg1);                    \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"svc #0\n"                                                    \
+		: "=r"(_arg1)                                                 \
+		: "r"(_arg1),                                                 \
+		  "r"(_num)                                                   \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+#define my_syscall2(num, arg1, arg2)                                          \
+({                                                                            \
+	register long _num  __asm__ ("x8") = (num);                           \
+	register long _arg1 __asm__ ("x0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("x1") = (long)(arg2);                    \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"svc #0\n"                                                    \
+		: "=r"(_arg1)                                                 \
+		: "r"(_arg1), "r"(_arg2),                                     \
+		  "r"(_num)                                                   \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3)                                    \
+({                                                                            \
+	register long _num  __asm__ ("x8") = (num);                           \
+	register long _arg1 __asm__ ("x0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("x1") = (long)(arg2);                    \
+	register long _arg3 __asm__ ("x2") = (long)(arg3);                    \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"svc #0\n"                                                    \
+		: "=r"(_arg1)                                                 \
+		: "r"(_arg1), "r"(_arg2), "r"(_arg3),                         \
+		  "r"(_num)                                                   \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4)                              \
+({                                                                            \
+	register long _num  __asm__ ("x8") = (num);                           \
+	register long _arg1 __asm__ ("x0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("x1") = (long)(arg2);                    \
+	register long _arg3 __asm__ ("x2") = (long)(arg3);                    \
+	register long _arg4 __asm__ ("x3") = (long)(arg4);                    \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"svc #0\n"                                                    \
+		: "=r"(_arg1)                                                 \
+		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4),             \
+		  "r"(_num)                                                   \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5)                        \
+({                                                                            \
+	register long _num  __asm__ ("x8") = (num);                           \
+	register long _arg1 __asm__ ("x0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("x1") = (long)(arg2);                    \
+	register long _arg3 __asm__ ("x2") = (long)(arg3);                    \
+	register long _arg4 __asm__ ("x3") = (long)(arg4);                    \
+	register long _arg5 __asm__ ("x4") = (long)(arg5);                    \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"svc #0\n"                                                    \
+		: "=r" (_arg1)                                                \
+		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+		  "r"(_num)                                                   \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6)                  \
+({                                                                            \
+	register long _num  __asm__ ("x8") = (num);                           \
+	register long _arg1 __asm__ ("x0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("x1") = (long)(arg2);                    \
+	register long _arg3 __asm__ ("x2") = (long)(arg3);                    \
+	register long _arg4 __asm__ ("x3") = (long)(arg4);                    \
+	register long _arg5 __asm__ ("x4") = (long)(arg5);                    \
+	register long _arg6 __asm__ ("x5") = (long)(arg6);                    \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"svc #0\n"                                                    \
+		: "=r" (_arg1)                                                \
+		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+		  "r"(_arg6), "r"(_num)                                       \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+/* startup code */
+__asm__ (".section .text\n"
+    ".weak _start\n"
+    "_start:\n"
+    "ldr x0, [sp]\n"              // argc (x0) was in the stack
+    "add x1, sp, 8\n"             // argv (x1) = sp
+    "lsl x2, x0, 3\n"             // envp (x2) = 8*argc ...
+    "add x2, x2, 8\n"             //           + 8 (skip null)
+    "add x2, x2, x1\n"            //           + argv
+    "and sp, x1, -16\n"           // sp must be 16-byte aligned in the callee
+    "bl main\n"                   // main() returns the status code, we'll exit with it.
+    "mov x8, 93\n"                // NR_exit == 93
+    "svc #0\n"
+    "");
+
+#endif // _NOLIBC_ARCH_AARCH64_H
diff --git a/tools/include/nolibc/arch-arm.h b/tools/include/nolibc/arch-arm.h
new file mode 100644
index 000000000000..f31be8e967d6
--- /dev/null
+++ b/tools/include/nolibc/arch-arm.h
@@ -0,0 +1,204 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * ARM specific definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ARCH_ARM_H
+#define _NOLIBC_ARCH_ARM_H
+
+/* O_* macros for fcntl/open are architecture-specific */
+#define O_RDONLY            0
+#define O_WRONLY            1
+#define O_RDWR              2
+#define O_CREAT          0x40
+#define O_EXCL           0x80
+#define O_NOCTTY        0x100
+#define O_TRUNC         0x200
+#define O_APPEND        0x400
+#define O_NONBLOCK      0x800
+#define O_DIRECTORY    0x4000
+
+/* The struct returned by the stat() syscall, 32-bit only, the syscall returns
+ * exactly 56 bytes (stops before the unused array). In big endian, the format
+ * differs as devices are returned as short only.
+ */
+struct sys_stat_struct {
+#if defined(__ARMEB__)
+	unsigned short st_dev;
+	unsigned short __pad1;
+#else
+	unsigned long  st_dev;
+#endif
+	unsigned long  st_ino;
+	unsigned short st_mode;
+	unsigned short st_nlink;
+	unsigned short st_uid;
+	unsigned short st_gid;
+
+#if defined(__ARMEB__)
+	unsigned short st_rdev;
+	unsigned short __pad2;
+#else
+	unsigned long  st_rdev;
+#endif
+	unsigned long  st_size;
+	unsigned long  st_blksize;
+	unsigned long  st_blocks;
+
+	unsigned long  st_atime;
+	unsigned long  st_atime_nsec;
+	unsigned long  st_mtime;
+	unsigned long  st_mtime_nsec;
+
+	unsigned long  st_ctime;
+	unsigned long  st_ctime_nsec;
+	unsigned long  __unused[2];
+};
+
+/* Syscalls for ARM in ARM or Thumb modes :
+ *   - registers are 32-bit
+ *   - stack is 8-byte aligned
+ *     ( http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.faqs/ka4127.html)
+ *   - syscall number is passed in r7
+ *   - arguments are in r0, r1, r2, r3, r4, r5
+ *   - the system call is performed by calling svc #0
+ *   - syscall return comes in r0.
+ *   - only lr is clobbered.
+ *   - the arguments are cast to long and assigned into the target registers
+ *     which are then simply passed as registers to the asm code, so that we
+ *     don't have to experience issues with register constraints.
+ *   - the syscall number is always specified last in order to allow to force
+ *     some registers before (gcc refuses a %-register at the last position).
+ *
+ * Also, ARM supports the old_select syscall if newselect is not available
+ */
+#define __ARCH_WANT_SYS_OLD_SELECT
+
+#define my_syscall0(num)                                                      \
+({                                                                            \
+	register long _num __asm__ ("r7") = (num);                            \
+	register long _arg1 __asm__ ("r0");                                   \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"svc #0\n"                                                    \
+		: "=r"(_arg1)                                                 \
+		: "r"(_num)                                                   \
+		: "memory", "cc", "lr"                                        \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+#define my_syscall1(num, arg1)                                                \
+({                                                                            \
+	register long _num __asm__ ("r7") = (num);                            \
+	register long _arg1 __asm__ ("r0") = (long)(arg1);                    \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"svc #0\n"                                                    \
+		: "=r"(_arg1)                                                 \
+		: "r"(_arg1),                                                 \
+		  "r"(_num)                                                   \
+		: "memory", "cc", "lr"                                        \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+#define my_syscall2(num, arg1, arg2)                                          \
+({                                                                            \
+	register long _num __asm__ ("r7") = (num);                            \
+	register long _arg1 __asm__ ("r0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("r1") = (long)(arg2);                    \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"svc #0\n"                                                    \
+		: "=r"(_arg1)                                                 \
+		: "r"(_arg1), "r"(_arg2),                                     \
+		  "r"(_num)                                                   \
+		: "memory", "cc", "lr"                                        \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3)                                    \
+({                                                                            \
+	register long _num __asm__ ("r7") = (num);                            \
+	register long _arg1 __asm__ ("r0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("r1") = (long)(arg2);                    \
+	register long _arg3 __asm__ ("r2") = (long)(arg3);                    \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"svc #0\n"                                                    \
+		: "=r"(_arg1)                                                 \
+		: "r"(_arg1), "r"(_arg2), "r"(_arg3),                         \
+		  "r"(_num)                                                   \
+		: "memory", "cc", "lr"                                        \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4)                              \
+({                                                                            \
+	register long _num __asm__ ("r7") = (num);                            \
+	register long _arg1 __asm__ ("r0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("r1") = (long)(arg2);                    \
+	register long _arg3 __asm__ ("r2") = (long)(arg3);                    \
+	register long _arg4 __asm__ ("r3") = (long)(arg4);                    \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"svc #0\n"                                                    \
+		: "=r"(_arg1)                                                 \
+		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4),             \
+		  "r"(_num)                                                   \
+		: "memory", "cc", "lr"                                        \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5)                        \
+({                                                                            \
+	register long _num __asm__ ("r7") = (num);                            \
+	register long _arg1 __asm__ ("r0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("r1") = (long)(arg2);                    \
+	register long _arg3 __asm__ ("r2") = (long)(arg3);                    \
+	register long _arg4 __asm__ ("r3") = (long)(arg4);                    \
+	register long _arg5 __asm__ ("r4") = (long)(arg5);                    \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"svc #0\n"                                                    \
+		: "=r" (_arg1)                                                \
+		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+		  "r"(_num)                                                   \
+		: "memory", "cc", "lr"                                        \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+/* startup code */
+__asm__ (".section .text\n"
+    ".weak _start\n"
+    "_start:\n"
+#if defined(__THUMBEB__) || defined(__THUMBEL__)
+    /* We enter here in 32-bit mode but if some previous functions were in
+     * 16-bit mode, the assembler cannot know, so we need to tell it we're in
+     * 32-bit now, then switch to 16-bit (is there a better way to do it than
+     * adding 1 by hand ?) and tell the asm we're now in 16-bit mode so that
+     * it generates correct instructions. Note that we do not support thumb1.
+     */
+    ".code 32\n"
+    "add     r0, pc, #1\n"
+    "bx      r0\n"
+    ".code 16\n"
+#endif
+    "pop {%r0}\n"                 // argc was in the stack
+    "mov %r1, %sp\n"              // argv = sp
+    "add %r2, %r1, %r0, lsl #2\n" // envp = argv + 4*argc ...
+    "add %r2, %r2, $4\n"          //        ... + 4
+    "and %r3, %r1, $-8\n"         // AAPCS : sp must be 8-byte aligned in the
+    "mov %sp, %r3\n"              //         callee, an bl doesn't push (lr=pc)
+    "bl main\n"                   // main() returns the status code, we'll exit with it.
+    "movs r7, $1\n"               // NR_exit == 1
+    "svc $0x00\n"
+    "");
+
+#endif // _NOLIBC_ARCH_ARM_H
diff --git a/tools/include/nolibc/arch-i386.h b/tools/include/nolibc/arch-i386.h
new file mode 100644
index 000000000000..d7e7212346e2
--- /dev/null
+++ b/tools/include/nolibc/arch-i386.h
@@ -0,0 +1,219 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * i386 specific definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ARCH_I386_H
+#define _NOLIBC_ARCH_I386_H
+
+/* O_* macros for fcntl/open are architecture-specific */
+#define O_RDONLY            0
+#define O_WRONLY            1
+#define O_RDWR              2
+#define O_CREAT          0x40
+#define O_EXCL           0x80
+#define O_NOCTTY        0x100
+#define O_TRUNC         0x200
+#define O_APPEND        0x400
+#define O_NONBLOCK      0x800
+#define O_DIRECTORY   0x10000
+
+/* The struct returned by the stat() syscall, 32-bit only, the syscall returns
+ * exactly 56 bytes (stops before the unused array).
+ */
+struct sys_stat_struct {
+	unsigned long  st_dev;
+	unsigned long  st_ino;
+	unsigned short st_mode;
+	unsigned short st_nlink;
+	unsigned short st_uid;
+	unsigned short st_gid;
+
+	unsigned long  st_rdev;
+	unsigned long  st_size;
+	unsigned long  st_blksize;
+	unsigned long  st_blocks;
+
+	unsigned long  st_atime;
+	unsigned long  st_atime_nsec;
+	unsigned long  st_mtime;
+	unsigned long  st_mtime_nsec;
+
+	unsigned long  st_ctime;
+	unsigned long  st_ctime_nsec;
+	unsigned long  __unused[2];
+};
+
+/* Syscalls for i386 :
+ *   - mostly similar to x86_64
+ *   - registers are 32-bit
+ *   - syscall number is passed in eax
+ *   - arguments are in ebx, ecx, edx, esi, edi, ebp respectively
+ *   - all registers are preserved (except eax of course)
+ *   - the system call is performed by calling int $0x80
+ *   - syscall return comes in eax
+ *   - the arguments are cast to long and assigned into the target registers
+ *     which are then simply passed as registers to the asm code, so that we
+ *     don't have to experience issues with register constraints.
+ *   - the syscall number is always specified last in order to allow to force
+ *     some registers before (gcc refuses a %-register at the last position).
+ *
+ * Also, i386 supports the old_select syscall if newselect is not available
+ */
+#define __ARCH_WANT_SYS_OLD_SELECT
+
+#define my_syscall0(num)                                                      \
+({                                                                            \
+	long _ret;                                                            \
+	register long _num __asm__ ("eax") = (num);                           \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"int $0x80\n"                                                 \
+		: "=a" (_ret)                                                 \
+		: "0"(_num)                                                   \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_ret;                                                                 \
+})
+
+#define my_syscall1(num, arg1)                                                \
+({                                                                            \
+	long _ret;                                                            \
+	register long _num __asm__ ("eax") = (num);                           \
+	register long _arg1 __asm__ ("ebx") = (long)(arg1);                   \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"int $0x80\n"                                                 \
+		: "=a" (_ret)                                                 \
+		: "r"(_arg1),                                                 \
+		  "0"(_num)                                                   \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_ret;                                                                 \
+})
+
+#define my_syscall2(num, arg1, arg2)                                          \
+({                                                                            \
+	long _ret;                                                            \
+	register long _num __asm__ ("eax") = (num);                           \
+	register long _arg1 __asm__ ("ebx") = (long)(arg1);                   \
+	register long _arg2 __asm__ ("ecx") = (long)(arg2);                   \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"int $0x80\n"                                                 \
+		: "=a" (_ret)                                                 \
+		: "r"(_arg1), "r"(_arg2),                                     \
+		  "0"(_num)                                                   \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_ret;                                                                 \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3)                                    \
+({                                                                            \
+	long _ret;                                                            \
+	register long _num __asm__ ("eax") = (num);                           \
+	register long _arg1 __asm__ ("ebx") = (long)(arg1);                   \
+	register long _arg2 __asm__ ("ecx") = (long)(arg2);                   \
+	register long _arg3 __asm__ ("edx") = (long)(arg3);                   \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"int $0x80\n"                                                 \
+		: "=a" (_ret)                                                 \
+		: "r"(_arg1), "r"(_arg2), "r"(_arg3),                         \
+		  "0"(_num)                                                   \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_ret;                                                                 \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4)                              \
+({                                                                            \
+	long _ret;                                                            \
+	register long _num __asm__ ("eax") = (num);                           \
+	register long _arg1 __asm__ ("ebx") = (long)(arg1);                   \
+	register long _arg2 __asm__ ("ecx") = (long)(arg2);                   \
+	register long _arg3 __asm__ ("edx") = (long)(arg3);                   \
+	register long _arg4 __asm__ ("esi") = (long)(arg4);                   \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"int $0x80\n"                                                 \
+		: "=a" (_ret)                                                 \
+		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4),             \
+		  "0"(_num)                                                   \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_ret;                                                                 \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5)                        \
+({                                                                            \
+	long _ret;                                                            \
+	register long _num __asm__ ("eax") = (num);                           \
+	register long _arg1 __asm__ ("ebx") = (long)(arg1);                   \
+	register long _arg2 __asm__ ("ecx") = (long)(arg2);                   \
+	register long _arg3 __asm__ ("edx") = (long)(arg3);                   \
+	register long _arg4 __asm__ ("esi") = (long)(arg4);                   \
+	register long _arg5 __asm__ ("edi") = (long)(arg5);                   \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"int $0x80\n"                                                 \
+		: "=a" (_ret)                                                 \
+		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+		  "0"(_num)                                                   \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_ret;                                                                 \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6)	\
+({								\
+	long _eax  = (long)(num);				\
+	long _arg6 = (long)(arg6); /* Always in memory */	\
+	__asm__ volatile (					\
+		"pushl	%[_arg6]\n\t"				\
+		"pushl	%%ebp\n\t"				\
+		"movl	4(%%esp),%%ebp\n\t"			\
+		"int	$0x80\n\t"				\
+		"popl	%%ebp\n\t"				\
+		"addl	$4,%%esp\n\t"				\
+		: "+a"(_eax)		/* %eax */		\
+		: "b"(arg1),		/* %ebx */		\
+		  "c"(arg2),		/* %ecx */		\
+		  "d"(arg3),		/* %edx */		\
+		  "S"(arg4),		/* %esi */		\
+		  "D"(arg5),		/* %edi */		\
+		  [_arg6]"m"(_arg6)	/* memory */		\
+		: "memory", "cc"				\
+	);							\
+	_eax;							\
+})
+
+/* startup code */
+/*
+ * i386 System V ABI mandates:
+ * 1) last pushed argument must be 16-byte aligned.
+ * 2) The deepest stack frame should be set to zero
+ *
+ */
+__asm__ (".section .text\n"
+    ".weak _start\n"
+    "_start:\n"
+    "pop %eax\n"                // argc   (first arg, %eax)
+    "mov %esp, %ebx\n"          // argv[] (second arg, %ebx)
+    "lea 4(%ebx,%eax,4),%ecx\n" // then a NULL then envp (third arg, %ecx)
+    "xor %ebp, %ebp\n"          // zero the stack frame
+    "and $-16, %esp\n"          // x86 ABI : esp must be 16-byte aligned before
+    "sub $4, %esp\n"            // the call instruction (args are aligned)
+    "push %ecx\n"               // push all registers on the stack so that we
+    "push %ebx\n"               // support both regparm and plain stack modes
+    "push %eax\n"
+    "call main\n"               // main() returns the status code in %eax
+    "mov %eax, %ebx\n"          // retrieve exit code (32-bit int)
+    "movl $1, %eax\n"           // NR_exit == 1
+    "int $0x80\n"               // exit now
+    "hlt\n"                     // ensure it does not
+    "");
+
+#endif // _NOLIBC_ARCH_I386_H
diff --git a/tools/include/nolibc/arch-mips.h b/tools/include/nolibc/arch-mips.h
new file mode 100644
index 000000000000..5fc5b8029bff
--- /dev/null
+++ b/tools/include/nolibc/arch-mips.h
@@ -0,0 +1,215 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * MIPS specific definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ARCH_MIPS_H
+#define _NOLIBC_ARCH_MIPS_H
+
+/* O_* macros for fcntl/open are architecture-specific */
+#define O_RDONLY            0
+#define O_WRONLY            1
+#define O_RDWR              2
+#define O_APPEND       0x0008
+#define O_NONBLOCK     0x0080
+#define O_CREAT        0x0100
+#define O_TRUNC        0x0200
+#define O_EXCL         0x0400
+#define O_NOCTTY       0x0800
+#define O_DIRECTORY   0x10000
+
+/* The struct returned by the stat() syscall. 88 bytes are returned by the
+ * syscall.
+ */
+struct sys_stat_struct {
+	unsigned int  st_dev;
+	long          st_pad1[3];
+	unsigned long st_ino;
+	unsigned int  st_mode;
+	unsigned int  st_nlink;
+	unsigned int  st_uid;
+	unsigned int  st_gid;
+	unsigned int  st_rdev;
+	long          st_pad2[2];
+	long          st_size;
+	long          st_pad3;
+
+	long          st_atime;
+	long          st_atime_nsec;
+	long          st_mtime;
+	long          st_mtime_nsec;
+
+	long          st_ctime;
+	long          st_ctime_nsec;
+	long          st_blksize;
+	long          st_blocks;
+	long          st_pad4[14];
+};
+
+/* Syscalls for MIPS ABI O32 :
+ *   - WARNING! there's always a delayed slot!
+ *   - WARNING again, the syntax is different, registers take a '$' and numbers
+ *     do not.
+ *   - registers are 32-bit
+ *   - stack is 8-byte aligned
+ *   - syscall number is passed in v0 (starts at 0xfa0).
+ *   - arguments are in a0, a1, a2, a3, then the stack. The caller needs to
+ *     leave some room in the stack for the callee to save a0..a3 if needed.
+ *   - Many registers are clobbered, in fact only a0..a2 and s0..s8 are
+ *     preserved. See: https://www.linux-mips.org/wiki/Syscall as well as
+ *     scall32-o32.S in the kernel sources.
+ *   - the system call is performed by calling "syscall"
+ *   - syscall return comes in v0, and register a3 needs to be checked to know
+ *     if an error occurred, in which case errno is in v0.
+ *   - the arguments are cast to long and assigned into the target registers
+ *     which are then simply passed as registers to the asm code, so that we
+ *     don't have to experience issues with register constraints.
+ */
+
+#define my_syscall0(num)                                                      \
+({                                                                            \
+	register long _num __asm__ ("v0") = (num);                            \
+	register long _arg4 __asm__ ("a3");                                   \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"addiu $sp, $sp, -32\n"                                       \
+		"syscall\n"                                                   \
+		"addiu $sp, $sp, 32\n"                                        \
+		: "=r"(_num), "=r"(_arg4)                                     \
+		: "r"(_num)                                                   \
+		: "memory", "cc", "at", "v1", "hi", "lo",                     \
+	          "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"  \
+	);                                                                    \
+	_arg4 ? -_num : _num;                                                 \
+})
+
+#define my_syscall1(num, arg1)                                                \
+({                                                                            \
+	register long _num __asm__ ("v0") = (num);                            \
+	register long _arg1 __asm__ ("a0") = (long)(arg1);                    \
+	register long _arg4 __asm__ ("a3");                                   \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"addiu $sp, $sp, -32\n"                                       \
+		"syscall\n"                                                   \
+		"addiu $sp, $sp, 32\n"                                        \
+		: "=r"(_num), "=r"(_arg4)                                     \
+		: "0"(_num),                                                  \
+		  "r"(_arg1)                                                  \
+		: "memory", "cc", "at", "v1", "hi", "lo",                     \
+	          "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"  \
+	);                                                                    \
+	_arg4 ? -_num : _num;                                                 \
+})
+
+#define my_syscall2(num, arg1, arg2)                                          \
+({                                                                            \
+	register long _num __asm__ ("v0") = (num);                            \
+	register long _arg1 __asm__ ("a0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("a1") = (long)(arg2);                    \
+	register long _arg4 __asm__ ("a3");                                   \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"addiu $sp, $sp, -32\n"                                       \
+		"syscall\n"                                                   \
+		"addiu $sp, $sp, 32\n"                                        \
+		: "=r"(_num), "=r"(_arg4)                                     \
+		: "0"(_num),                                                  \
+		  "r"(_arg1), "r"(_arg2)                                      \
+		: "memory", "cc", "at", "v1", "hi", "lo",                     \
+	          "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"  \
+	);                                                                    \
+	_arg4 ? -_num : _num;                                                 \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3)                                    \
+({                                                                            \
+	register long _num __asm__ ("v0")  = (num);                           \
+	register long _arg1 __asm__ ("a0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("a1") = (long)(arg2);                    \
+	register long _arg3 __asm__ ("a2") = (long)(arg3);                    \
+	register long _arg4 __asm__ ("a3");                                   \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"addiu $sp, $sp, -32\n"                                       \
+		"syscall\n"                                                   \
+		"addiu $sp, $sp, 32\n"                                        \
+		: "=r"(_num), "=r"(_arg4)                                     \
+		: "0"(_num),                                                  \
+		  "r"(_arg1), "r"(_arg2), "r"(_arg3)                          \
+		: "memory", "cc", "at", "v1", "hi", "lo",                     \
+	          "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"  \
+	);                                                                    \
+	_arg4 ? -_num : _num;                                                 \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4)                              \
+({                                                                            \
+	register long _num __asm__ ("v0") = (num);                            \
+	register long _arg1 __asm__ ("a0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("a1") = (long)(arg2);                    \
+	register long _arg3 __asm__ ("a2") = (long)(arg3);                    \
+	register long _arg4 __asm__ ("a3") = (long)(arg4);                    \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"addiu $sp, $sp, -32\n"                                       \
+		"syscall\n"                                                   \
+		"addiu $sp, $sp, 32\n"                                        \
+		: "=r" (_num), "=r"(_arg4)                                    \
+		: "0"(_num),                                                  \
+		  "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4)              \
+		: "memory", "cc", "at", "v1", "hi", "lo",                     \
+	          "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"  \
+	);                                                                    \
+	_arg4 ? -_num : _num;                                                 \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5)                        \
+({                                                                            \
+	register long _num __asm__ ("v0") = (num);                            \
+	register long _arg1 __asm__ ("a0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("a1") = (long)(arg2);                    \
+	register long _arg3 __asm__ ("a2") = (long)(arg3);                    \
+	register long _arg4 __asm__ ("a3") = (long)(arg4);                    \
+	register long _arg5 = (long)(arg5);                                   \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"addiu $sp, $sp, -32\n"                                       \
+		"sw %7, 16($sp)\n"                                            \
+		"syscall\n  "                                                 \
+		"addiu $sp, $sp, 32\n"                                        \
+		: "=r" (_num), "=r"(_arg4)                                    \
+		: "0"(_num),                                                  \
+		  "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5)  \
+		: "memory", "cc", "at", "v1", "hi", "lo",                     \
+	          "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"  \
+	);                                                                    \
+	_arg4 ? -_num : _num;                                                 \
+})
+
+/* startup code, note that it's called __start on MIPS */
+__asm__ (".section .text\n"
+    ".weak __start\n"
+    ".set nomips16\n"
+    ".set    noreorder\n"
+    ".option pic0\n"
+    ".ent __start\n"
+    "__start:\n"
+    "lw $a0,($sp)\n"              // argc was in the stack
+    "addiu  $a1, $sp, 4\n"        // argv = sp + 4
+    "sll $a2, $a0, 2\n"           // a2 = argc * 4
+    "add   $a2, $a2, $a1\n"       // envp = argv + 4*argc ...
+    "addiu $a2, $a2, 4\n"         //        ... + 4
+    "li $t0, -8\n"
+    "and $sp, $sp, $t0\n"         // sp must be 8-byte aligned
+    "addiu $sp,$sp,-16\n"         // the callee expects to save a0..a3 there!
+    "jal main\n"                  // main() returns the status code, we'll exit with it.
+    "nop\n"                       // delayed slot
+    "move $a0, $v0\n"             // retrieve 32-bit exit code from v0
+    "li $v0, 4001\n"              // NR_exit == 4001
+    "syscall\n"
+    ".end __start\n"
+    "");
+
+#endif // _NOLIBC_ARCH_MIPS_H
diff --git a/tools/include/nolibc/arch-riscv.h b/tools/include/nolibc/arch-riscv.h
new file mode 100644
index 000000000000..95e2b7924925
--- /dev/null
+++ b/tools/include/nolibc/arch-riscv.h
@@ -0,0 +1,204 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * RISCV (32 and 64) specific definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ARCH_RISCV_H
+#define _NOLIBC_ARCH_RISCV_H
+
+/* O_* macros for fcntl/open are architecture-specific */
+#define O_RDONLY            0
+#define O_WRONLY            1
+#define O_RDWR              2
+#define O_CREAT         0x100
+#define O_EXCL          0x200
+#define O_NOCTTY        0x400
+#define O_TRUNC        0x1000
+#define O_APPEND       0x2000
+#define O_NONBLOCK     0x4000
+#define O_DIRECTORY  0x200000
+
+struct sys_stat_struct {
+	unsigned long	st_dev;		/* Device.  */
+	unsigned long	st_ino;		/* File serial number.  */
+	unsigned int	st_mode;	/* File mode.  */
+	unsigned int	st_nlink;	/* Link count.  */
+	unsigned int	st_uid;		/* User ID of the file's owner.  */
+	unsigned int	st_gid;		/* Group ID of the file's group. */
+	unsigned long	st_rdev;	/* Device number, if device.  */
+	unsigned long	__pad1;
+	long		st_size;	/* Size of file, in bytes.  */
+	int		st_blksize;	/* Optimal block size for I/O.  */
+	int		__pad2;
+	long		st_blocks;	/* Number 512-byte blocks allocated. */
+	long		st_atime;	/* Time of last access.  */
+	unsigned long	st_atime_nsec;
+	long		st_mtime;	/* Time of last modification.  */
+	unsigned long	st_mtime_nsec;
+	long		st_ctime;	/* Time of last status change.  */
+	unsigned long	st_ctime_nsec;
+	unsigned int	__unused4;
+	unsigned int	__unused5;
+};
+
+#if   __riscv_xlen == 64
+#define PTRLOG "3"
+#define SZREG  "8"
+#elif __riscv_xlen == 32
+#define PTRLOG "2"
+#define SZREG  "4"
+#endif
+
+/* Syscalls for RISCV :
+ *   - stack is 16-byte aligned
+ *   - syscall number is passed in a7
+ *   - arguments are in a0, a1, a2, a3, a4, a5
+ *   - the system call is performed by calling ecall
+ *   - syscall return comes in a0
+ *   - the arguments are cast to long and assigned into the target
+ *     registers which are then simply passed as registers to the asm code,
+ *     so that we don't have to experience issues with register constraints.
+ *
+ * On riscv, select() is not implemented so we have to use pselect6().
+ */
+#define __ARCH_WANT_SYS_PSELECT6
+
+#define my_syscall0(num)                                                      \
+({                                                                            \
+	register long _num  __asm__ ("a7") = (num);                           \
+	register long _arg1 __asm__ ("a0");                                   \
+									      \
+	__asm__  volatile (                                                   \
+		"ecall\n\t"                                                   \
+		: "=r"(_arg1)                                                 \
+		: "r"(_num)                                                   \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+#define my_syscall1(num, arg1)                                                \
+({                                                                            \
+	register long _num  __asm__ ("a7") = (num);                           \
+	register long _arg1 __asm__ ("a0") = (long)(arg1);		      \
+									      \
+	__asm__  volatile (                                                   \
+		"ecall\n"                                                     \
+		: "+r"(_arg1)                                                 \
+		: "r"(_num)                                                   \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+#define my_syscall2(num, arg1, arg2)                                          \
+({                                                                            \
+	register long _num  __asm__ ("a7") = (num);                           \
+	register long _arg1 __asm__ ("a0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("a1") = (long)(arg2);                    \
+									      \
+	__asm__  volatile (                                                   \
+		"ecall\n"                                                     \
+		: "+r"(_arg1)                                                 \
+		: "r"(_arg2),                                                 \
+		  "r"(_num)                                                   \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3)                                    \
+({                                                                            \
+	register long _num  __asm__ ("a7") = (num);                           \
+	register long _arg1 __asm__ ("a0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("a1") = (long)(arg2);                    \
+	register long _arg3 __asm__ ("a2") = (long)(arg3);                    \
+									      \
+	__asm__  volatile (                                                   \
+		"ecall\n\t"                                                   \
+		: "+r"(_arg1)                                                 \
+		: "r"(_arg2), "r"(_arg3),                                     \
+		  "r"(_num)                                                   \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4)                              \
+({                                                                            \
+	register long _num  __asm__ ("a7") = (num);                           \
+	register long _arg1 __asm__ ("a0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("a1") = (long)(arg2);                    \
+	register long _arg3 __asm__ ("a2") = (long)(arg3);                    \
+	register long _arg4 __asm__ ("a3") = (long)(arg4);                    \
+									      \
+	__asm__  volatile (                                                   \
+		"ecall\n"                                                     \
+		: "+r"(_arg1)                                                 \
+		: "r"(_arg2), "r"(_arg3), "r"(_arg4),                         \
+		  "r"(_num)                                                   \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5)                        \
+({                                                                            \
+	register long _num  __asm__ ("a7") = (num);                           \
+	register long _arg1 __asm__ ("a0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("a1") = (long)(arg2);                    \
+	register long _arg3 __asm__ ("a2") = (long)(arg3);                    \
+	register long _arg4 __asm__ ("a3") = (long)(arg4);                    \
+	register long _arg5 __asm__ ("a4") = (long)(arg5);                    \
+									      \
+	__asm__  volatile (                                                   \
+		"ecall\n"                                                     \
+		: "+r"(_arg1)                                                 \
+		: "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5),             \
+		  "r"(_num)                                                   \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6)                  \
+({                                                                            \
+	register long _num  __asm__ ("a7") = (num);                           \
+	register long _arg1 __asm__ ("a0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("a1") = (long)(arg2);                    \
+	register long _arg3 __asm__ ("a2") = (long)(arg3);                    \
+	register long _arg4 __asm__ ("a3") = (long)(arg4);                    \
+	register long _arg5 __asm__ ("a4") = (long)(arg5);                    \
+	register long _arg6 __asm__ ("a5") = (long)(arg6);                    \
+									      \
+	__asm__  volatile (                                                   \
+		"ecall\n"                                                     \
+		: "+r"(_arg1)                                                 \
+		: "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), "r"(_arg6), \
+		  "r"(_num)                                                   \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+/* startup code */
+__asm__ (".section .text\n"
+    ".weak _start\n"
+    "_start:\n"
+    ".option push\n"
+    ".option norelax\n"
+    "lla   gp, __global_pointer$\n"
+    ".option pop\n"
+    "ld    a0, 0(sp)\n"          // argc (a0) was in the stack
+    "add   a1, sp, "SZREG"\n"    // argv (a1) = sp
+    "slli  a2, a0, "PTRLOG"\n"   // envp (a2) = SZREG*argc ...
+    "add   a2, a2, "SZREG"\n"    //             + SZREG (skip null)
+    "add   a2,a2,a1\n"           //             + argv
+    "andi  sp,a1,-16\n"          // sp must be 16-byte aligned
+    "call  main\n"               // main() returns the status code, we'll exit with it.
+    "li a7, 93\n"                // NR_exit == 93
+    "ecall\n"
+    "");
+
+#endif // _NOLIBC_ARCH_RISCV_H
diff --git a/tools/include/nolibc/arch-x86_64.h b/tools/include/nolibc/arch-x86_64.h
new file mode 100644
index 000000000000..0e1e9eb8545d
--- /dev/null
+++ b/tools/include/nolibc/arch-x86_64.h
@@ -0,0 +1,215 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * x86_64 specific definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ARCH_X86_64_H
+#define _NOLIBC_ARCH_X86_64_H
+
+/* O_* macros for fcntl/open are architecture-specific */
+#define O_RDONLY            0
+#define O_WRONLY            1
+#define O_RDWR              2
+#define O_CREAT          0x40
+#define O_EXCL           0x80
+#define O_NOCTTY        0x100
+#define O_TRUNC         0x200
+#define O_APPEND        0x400
+#define O_NONBLOCK      0x800
+#define O_DIRECTORY   0x10000
+
+/* The struct returned by the stat() syscall, equivalent to stat64(). The
+ * syscall returns 116 bytes and stops in the middle of __unused.
+ */
+struct sys_stat_struct {
+	unsigned long st_dev;
+	unsigned long st_ino;
+	unsigned long st_nlink;
+	unsigned int  st_mode;
+	unsigned int  st_uid;
+
+	unsigned int  st_gid;
+	unsigned int  __pad0;
+	unsigned long st_rdev;
+	long          st_size;
+	long          st_blksize;
+
+	long          st_blocks;
+	unsigned long st_atime;
+	unsigned long st_atime_nsec;
+	unsigned long st_mtime;
+
+	unsigned long st_mtime_nsec;
+	unsigned long st_ctime;
+	unsigned long st_ctime_nsec;
+	long          __unused[3];
+};
+
+/* Syscalls for x86_64 :
+ *   - registers are 64-bit
+ *   - syscall number is passed in rax
+ *   - arguments are in rdi, rsi, rdx, r10, r8, r9 respectively
+ *   - the system call is performed by calling the syscall instruction
+ *   - syscall return comes in rax
+ *   - rcx and r11 are clobbered, others are preserved.
+ *   - the arguments are cast to long and assigned into the target registers
+ *     which are then simply passed as registers to the asm code, so that we
+ *     don't have to experience issues with register constraints.
+ *   - the syscall number is always specified last in order to allow to force
+ *     some registers before (gcc refuses a %-register at the last position).
+ *   - see also x86-64 ABI section A.2 AMD64 Linux Kernel Conventions, A.2.1
+ *     Calling Conventions.
+ *
+ * Link x86-64 ABI: https://gitlab.com/x86-psABIs/x86-64-ABI/-/wikis/home
+ *
+ */
+
+#define my_syscall0(num)                                                      \
+({                                                                            \
+	long _ret;                                                            \
+	register long _num  __asm__ ("rax") = (num);                          \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"syscall\n"                                                   \
+		: "=a"(_ret)                                                  \
+		: "0"(_num)                                                   \
+		: "rcx", "r11", "memory", "cc"                                \
+	);                                                                    \
+	_ret;                                                                 \
+})
+
+#define my_syscall1(num, arg1)                                                \
+({                                                                            \
+	long _ret;                                                            \
+	register long _num  __asm__ ("rax") = (num);                          \
+	register long _arg1 __asm__ ("rdi") = (long)(arg1);                   \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"syscall\n"                                                   \
+		: "=a"(_ret)                                                  \
+		: "r"(_arg1),                                                 \
+		  "0"(_num)                                                   \
+		: "rcx", "r11", "memory", "cc"                                \
+	);                                                                    \
+	_ret;                                                                 \
+})
+
+#define my_syscall2(num, arg1, arg2)                                          \
+({                                                                            \
+	long _ret;                                                            \
+	register long _num  __asm__ ("rax") = (num);                          \
+	register long _arg1 __asm__ ("rdi") = (long)(arg1);                   \
+	register long _arg2 __asm__ ("rsi") = (long)(arg2);                   \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"syscall\n"                                                   \
+		: "=a"(_ret)                                                  \
+		: "r"(_arg1), "r"(_arg2),                                     \
+		  "0"(_num)                                                   \
+		: "rcx", "r11", "memory", "cc"                                \
+	);                                                                    \
+	_ret;                                                                 \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3)                                    \
+({                                                                            \
+	long _ret;                                                            \
+	register long _num  __asm__ ("rax") = (num);                          \
+	register long _arg1 __asm__ ("rdi") = (long)(arg1);                   \
+	register long _arg2 __asm__ ("rsi") = (long)(arg2);                   \
+	register long _arg3 __asm__ ("rdx") = (long)(arg3);                   \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"syscall\n"                                                   \
+		: "=a"(_ret)                                                  \
+		: "r"(_arg1), "r"(_arg2), "r"(_arg3),                         \
+		  "0"(_num)                                                   \
+		: "rcx", "r11", "memory", "cc"                                \
+	);                                                                    \
+	_ret;                                                                 \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4)                              \
+({                                                                            \
+	long _ret;                                                            \
+	register long _num  __asm__ ("rax") = (num);                          \
+	register long _arg1 __asm__ ("rdi") = (long)(arg1);                   \
+	register long _arg2 __asm__ ("rsi") = (long)(arg2);                   \
+	register long _arg3 __asm__ ("rdx") = (long)(arg3);                   \
+	register long _arg4 __asm__ ("r10") = (long)(arg4);                   \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"syscall\n"                                                   \
+		: "=a"(_ret)                                                  \
+		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4),             \
+		  "0"(_num)                                                   \
+		: "rcx", "r11", "memory", "cc"                                \
+	);                                                                    \
+	_ret;                                                                 \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5)                        \
+({                                                                            \
+	long _ret;                                                            \
+	register long _num  __asm__ ("rax") = (num);                          \
+	register long _arg1 __asm__ ("rdi") = (long)(arg1);                   \
+	register long _arg2 __asm__ ("rsi") = (long)(arg2);                   \
+	register long _arg3 __asm__ ("rdx") = (long)(arg3);                   \
+	register long _arg4 __asm__ ("r10") = (long)(arg4);                   \
+	register long _arg5 __asm__ ("r8")  = (long)(arg5);                   \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"syscall\n"                                                   \
+		: "=a"(_ret)                                                  \
+		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+		  "0"(_num)                                                   \
+		: "rcx", "r11", "memory", "cc"                                \
+	);                                                                    \
+	_ret;                                                                 \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6)                  \
+({                                                                            \
+	long _ret;                                                            \
+	register long _num  __asm__ ("rax") = (num);                          \
+	register long _arg1 __asm__ ("rdi") = (long)(arg1);                   \
+	register long _arg2 __asm__ ("rsi") = (long)(arg2);                   \
+	register long _arg3 __asm__ ("rdx") = (long)(arg3);                   \
+	register long _arg4 __asm__ ("r10") = (long)(arg4);                   \
+	register long _arg5 __asm__ ("r8")  = (long)(arg5);                   \
+	register long _arg6 __asm__ ("r9")  = (long)(arg6);                   \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"syscall\n"                                                   \
+		: "=a"(_ret)                                                  \
+		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+		  "r"(_arg6), "0"(_num)                                       \
+		: "rcx", "r11", "memory", "cc"                                \
+	);                                                                    \
+	_ret;                                                                 \
+})
+
+/* startup code */
+/*
+ * x86-64 System V ABI mandates:
+ * 1) %rsp must be 16-byte aligned right before the function call.
+ * 2) The deepest stack frame should be zero (the %rbp).
+ *
+ */
+__asm__ (".section .text\n"
+    ".weak _start\n"
+    "_start:\n"
+    "pop %rdi\n"                // argc   (first arg, %rdi)
+    "mov %rsp, %rsi\n"          // argv[] (second arg, %rsi)
+    "lea 8(%rsi,%rdi,8),%rdx\n" // then a NULL then envp (third arg, %rdx)
+    "xor %ebp, %ebp\n"          // zero the stack frame
+    "and $-16, %rsp\n"          // x86 ABI : esp must be 16-byte aligned before call
+    "call main\n"               // main() returns the status code, we'll exit with it.
+    "mov %eax, %edi\n"          // retrieve exit code (32 bit)
+    "mov $60, %eax\n"           // NR_exit == 60
+    "syscall\n"                 // really exit
+    "hlt\n"                     // ensure it does not return
+    "");
+
+#endif // _NOLIBC_ARCH_X86_64_H
diff --git a/tools/include/nolibc/arch.h b/tools/include/nolibc/arch.h
new file mode 100644
index 000000000000..4c6992321b0d
--- /dev/null
+++ b/tools/include/nolibc/arch.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+/* Below comes the architecture-specific code. For each architecture, we have
+ * the syscall declarations and the _start code definition. This is the only
+ * global part. On all architectures the kernel puts everything in the stack
+ * before jumping to _start just above us, without any return address (_start
+ * is not a function but an entry pint). So at the stack pointer we find argc.
+ * Then argv[] begins, and ends at the first NULL. Then we have envp which
+ * starts and ends with a NULL as well. So envp=argv+argc+1.
+ */
+
+#ifndef _NOLIBC_ARCH_H
+#define _NOLIBC_ARCH_H
+
+#if defined(__x86_64__)
+#include "arch-x86_64.h"
+#elif defined(__i386__) || defined(__i486__) || defined(__i586__) || defined(__i686__)
+#include "arch-i386.h"
+#elif defined(__ARM_EABI__)
+#include "arch-arm.h"
+#elif defined(__aarch64__)
+#include "arch-aarch64.h"
+#elif defined(__mips__) && defined(_ABIO32)
+#include "arch-mips.h"
+#elif defined(__riscv)
+#include "arch-riscv.h"
+#endif
+
+#endif /* _NOLIBC_ARCH_H */
diff --git a/tools/include/nolibc/ctype.h b/tools/include/nolibc/ctype.h
new file mode 100644
index 000000000000..e3000b2992d7
--- /dev/null
+++ b/tools/include/nolibc/ctype.h
@@ -0,0 +1,99 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * ctype function definitions for NOLIBC
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_CTYPE_H
+#define _NOLIBC_CTYPE_H
+
+#include "std.h"
+
+/*
+ * As much as possible, please keep functions alphabetically sorted.
+ */
+
+static __attribute__((unused))
+int isascii(int c)
+{
+	/* 0x00..0x7f */
+	return (unsigned int)c <= 0x7f;
+}
+
+static __attribute__((unused))
+int isblank(int c)
+{
+	return c == '\t' || c == ' ';
+}
+
+static __attribute__((unused))
+int iscntrl(int c)
+{
+	/* 0x00..0x1f, 0x7f */
+	return (unsigned int)c < 0x20 || c == 0x7f;
+}
+
+static __attribute__((unused))
+int isdigit(int c)
+{
+	return (unsigned int)(c - '0') < 10;
+}
+
+static __attribute__((unused))
+int isgraph(int c)
+{
+	/* 0x21..0x7e */
+	return (unsigned int)(c - 0x21) < 0x5e;
+}
+
+static __attribute__((unused))
+int islower(int c)
+{
+	return (unsigned int)(c - 'a') < 26;
+}
+
+static __attribute__((unused))
+int isprint(int c)
+{
+	/* 0x20..0x7e */
+	return (unsigned int)(c - 0x20) < 0x5f;
+}
+
+static __attribute__((unused))
+int isspace(int c)
+{
+	/* \t is 0x9, \n is 0xA, \v is 0xB, \f is 0xC, \r is 0xD */
+	return ((unsigned int)c == ' ') || (unsigned int)(c - 0x09) < 5;
+}
+
+static __attribute__((unused))
+int isupper(int c)
+{
+	return (unsigned int)(c - 'A') < 26;
+}
+
+static __attribute__((unused))
+int isxdigit(int c)
+{
+	return isdigit(c) || (unsigned int)(c - 'A') < 6 || (unsigned int)(c - 'a') < 6;
+}
+
+static __attribute__((unused))
+int isalpha(int c)
+{
+	return islower(c) || isupper(c);
+}
+
+static __attribute__((unused))
+int isalnum(int c)
+{
+	return isalpha(c) || isdigit(c);
+}
+
+static __attribute__((unused))
+int ispunct(int c)
+{
+	return isgraph(c) && !isalnum(c);
+}
+
+#endif /* _NOLIBC_CTYPE_H */
diff --git a/tools/include/nolibc/errno.h b/tools/include/nolibc/errno.h
new file mode 100644
index 000000000000..06893d6dfb7a
--- /dev/null
+++ b/tools/include/nolibc/errno.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Minimal errno definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ERRNO_H
+#define _NOLIBC_ERRNO_H
+
+#include <asm/errno.h>
+
+/* this way it will be removed if unused */
+static int errno;
+
+#ifndef NOLIBC_IGNORE_ERRNO
+#define SET_ERRNO(v) do { errno = (v); } while (0)
+#else
+#define SET_ERRNO(v) do { } while (0)
+#endif
+
+
+/* errno codes all ensure that they will not conflict with a valid pointer
+ * because they all correspond to the highest addressable memory page.
+ */
+#define MAX_ERRNO 4095
+
+#endif /* _NOLIBC_ERRNO_H */
diff --git a/tools/include/nolibc/nolibc.h b/tools/include/nolibc/nolibc.h
index c1c285fe494a..b2bc48d3cfe4 100644
--- a/tools/include/nolibc/nolibc.h
+++ b/tools/include/nolibc/nolibc.h
@@ -57,22 +57,32 @@
  * having to specify anything.
  *
  * Finally some very common libc-level functions are provided. It is the case
- * for a few functions usually found in string.h, ctype.h, or stdlib.h. Nothing
- * is currently provided regarding stdio emulation.
+ * for a few functions usually found in string.h, ctype.h, or stdlib.h.
  *
- * The macro NOLIBC is always defined, so that it is possible for a program to
- * check this macro to know if it is being built against and decide to disable
- * some features or simply not to include some standard libc files.
- *
- * Ideally this file should be split in multiple files for easier long term
- * maintenance, but provided as a single file as it is now, it's quite
- * convenient to use. Maybe some variations involving a set of includes at the
- * top could work.
+ * The nolibc.h file is only a convenient entry point which includes all other
+ * files. It also defines the NOLIBC macro, so that it is possible for a
+ * program to check this macro to know if it is being built against and decide
+ * to disable some features or simply not to include some standard libc files.
  *
  * A simple static executable may be built this way :
  *      $ gcc -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
  *            -static -include nolibc.h -o hello hello.c -lgcc
  *
+ * Simple programs meant to be reasonably portable to various libc and using
+ * only a few common includes, may also be built by simply making the include
+ * path point to the nolibc directory:
+ *      $ gcc -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
+ *            -I../nolibc -o hello hello.c -lgcc
+ *
+ * The available standard (but limited) include files are:
+ *   ctype.h, errno.h, signal.h, stdio.h, stdlib.h, string.h, time.h
+ *
+ * In addition, the following ones are expected to be provided by the compiler:
+ *   float.h, stdarg.h, stddef.h
+ *
+ * The following ones which are part to the C standard are not provided:
+ *   assert.h, locale.h, math.h, setjmp.h, limits.h
+ *
  * A very useful calling convention table may be found here :
  *      http://man7.org/linux/man-pages/man2/syscall.2.html
  *
@@ -80,2502 +90,22 @@
  *      https://w3challs.com/syscalls/
  *
  */
+#ifndef _NOLIBC_H
+#define _NOLIBC_H
 
-#include <asm/unistd.h>
-#include <asm/ioctls.h>
-#include <asm/errno.h>
-#include <linux/fs.h>
-#include <linux/loop.h>
-#include <linux/time.h>
+#include "std.h"
+#include "arch.h"
+#include "types.h"
+#include "sys.h"
+#include "ctype.h"
+#include "signal.h"
+#include "stdio.h"
+#include "stdlib.h"
+#include "string.h"
+#include "time.h"
+#include "unistd.h"
 
+/* Used by programs to avoid std includes */
 #define NOLIBC
 
-/* this way it will be removed if unused */
-static int errno;
-
-#ifndef NOLIBC_IGNORE_ERRNO
-#define SET_ERRNO(v) do { errno = (v); } while (0)
-#else
-#define SET_ERRNO(v) do { } while (0)
-#endif
-
-/* errno codes all ensure that they will not conflict with a valid pointer
- * because they all correspond to the highest addressable memory page.
- */
-#define MAX_ERRNO 4095
-
-/* Declare a few quite common macros and types that usually are in stdlib.h,
- * stdint.h, ctype.h, unistd.h and a few other common locations.
- */
-
-#define NULL ((void *)0)
-
-/* stdint types */
-typedef unsigned char       uint8_t;
-typedef   signed char        int8_t;
-typedef unsigned short     uint16_t;
-typedef   signed short      int16_t;
-typedef unsigned int       uint32_t;
-typedef   signed int        int32_t;
-typedef unsigned long long uint64_t;
-typedef   signed long long  int64_t;
-typedef unsigned long        size_t;
-typedef   signed long       ssize_t;
-typedef unsigned long     uintptr_t;
-typedef   signed long      intptr_t;
-typedef   signed long     ptrdiff_t;
-
-/* for stat() */
-typedef unsigned int          dev_t;
-typedef unsigned long         ino_t;
-typedef unsigned int         mode_t;
-typedef   signed int          pid_t;
-typedef unsigned int          uid_t;
-typedef unsigned int          gid_t;
-typedef unsigned long       nlink_t;
-typedef   signed long         off_t;
-typedef   signed long     blksize_t;
-typedef   signed long      blkcnt_t;
-typedef   signed long        time_t;
-
-/* for poll() */
-struct pollfd {
-	int fd;
-	short int events;
-	short int revents;
-};
-
-/* for getdents64() */
-struct linux_dirent64 {
-	uint64_t       d_ino;
-	int64_t        d_off;
-	unsigned short d_reclen;
-	unsigned char  d_type;
-	char           d_name[];
-};
-
-/* commonly an fd_set represents 256 FDs */
-#define FD_SETSIZE 256
-typedef struct { uint32_t fd32[FD_SETSIZE/32]; } fd_set;
-
-/* needed by wait4() */
-struct rusage {
-	struct timeval ru_utime;
-	struct timeval ru_stime;
-	long   ru_maxrss;
-	long   ru_ixrss;
-	long   ru_idrss;
-	long   ru_isrss;
-	long   ru_minflt;
-	long   ru_majflt;
-	long   ru_nswap;
-	long   ru_inblock;
-	long   ru_oublock;
-	long   ru_msgsnd;
-	long   ru_msgrcv;
-	long   ru_nsignals;
-	long   ru_nvcsw;
-	long   ru_nivcsw;
-};
-
-/* stat flags (WARNING, octal here) */
-#define S_IFDIR       0040000
-#define S_IFCHR       0020000
-#define S_IFBLK       0060000
-#define S_IFREG       0100000
-#define S_IFIFO       0010000
-#define S_IFLNK       0120000
-#define S_IFSOCK      0140000
-#define S_IFMT        0170000
-
-#define S_ISDIR(mode)  (((mode) & S_IFDIR) == S_IFDIR)
-#define S_ISCHR(mode)  (((mode) & S_IFCHR) == S_IFCHR)
-#define S_ISBLK(mode)  (((mode) & S_IFBLK) == S_IFBLK)
-#define S_ISREG(mode)  (((mode) & S_IFREG) == S_IFREG)
-#define S_ISFIFO(mode) (((mode) & S_IFIFO) == S_IFIFO)
-#define S_ISLNK(mode)  (((mode) & S_IFLNK) == S_IFLNK)
-#define S_ISSOCK(mode) (((mode) & S_IFSOCK) == S_IFSOCK)
-
-#define DT_UNKNOWN 0
-#define DT_FIFO    1
-#define DT_CHR     2
-#define DT_DIR     4
-#define DT_BLK     6
-#define DT_REG     8
-#define DT_LNK    10
-#define DT_SOCK   12
-
-/* all the *at functions */
-#ifndef AT_FDCWD
-#define AT_FDCWD             -100
-#endif
-
-/* lseek */
-#define SEEK_SET        0
-#define SEEK_CUR        1
-#define SEEK_END        2
-
-/* reboot */
-#define LINUX_REBOOT_MAGIC1         0xfee1dead
-#define LINUX_REBOOT_MAGIC2         0x28121969
-#define LINUX_REBOOT_CMD_HALT       0xcdef0123
-#define LINUX_REBOOT_CMD_POWER_OFF  0x4321fedc
-#define LINUX_REBOOT_CMD_RESTART    0x01234567
-#define LINUX_REBOOT_CMD_SW_SUSPEND 0xd000fce2
-
-
-/* The format of the struct as returned by the libc to the application, which
- * significantly differs from the format returned by the stat() syscall flavours.
- */
-struct stat {
-	dev_t     st_dev;     /* ID of device containing file */
-	ino_t     st_ino;     /* inode number */
-	mode_t    st_mode;    /* protection */
-	nlink_t   st_nlink;   /* number of hard links */
-	uid_t     st_uid;     /* user ID of owner */
-	gid_t     st_gid;     /* group ID of owner */
-	dev_t     st_rdev;    /* device ID (if special file) */
-	off_t     st_size;    /* total size, in bytes */
-	blksize_t st_blksize; /* blocksize for file system I/O */
-	blkcnt_t  st_blocks;  /* number of 512B blocks allocated */
-	time_t    st_atime;   /* time of last access */
-	time_t    st_mtime;   /* time of last modification */
-	time_t    st_ctime;   /* time of last status change */
-};
-
-#define WEXITSTATUS(status)   (((status) & 0xff00) >> 8)
-#define WIFEXITED(status)     (((status) & 0x7f) == 0)
-
-/* for SIGCHLD */
-#include <asm/signal.h>
-
-/* Below comes the architecture-specific code. For each architecture, we have
- * the syscall declarations and the _start code definition. This is the only
- * global part. On all architectures the kernel puts everything in the stack
- * before jumping to _start just above us, without any return address (_start
- * is not a function but an entry pint). So at the stack pointer we find argc.
- * Then argv[] begins, and ends at the first NULL. Then we have envp which
- * starts and ends with a NULL as well. So envp=argv+argc+1.
- */
-
-#if defined(__x86_64__)
-/* Syscalls for x86_64 :
- *   - registers are 64-bit
- *   - syscall number is passed in rax
- *   - arguments are in rdi, rsi, rdx, r10, r8, r9 respectively
- *   - the system call is performed by calling the syscall instruction
- *   - syscall return comes in rax
- *   - rcx and r11 are clobbered, others are preserved.
- *   - the arguments are cast to long and assigned into the target registers
- *     which are then simply passed as registers to the asm code, so that we
- *     don't have to experience issues with register constraints.
- *   - the syscall number is always specified last in order to allow to force
- *     some registers before (gcc refuses a %-register at the last position).
- *   - see also x86-64 ABI section A.2 AMD64 Linux Kernel Conventions, A.2.1
- *     Calling Conventions.
- *
- * Link x86-64 ABI: https://gitlab.com/x86-psABIs/x86-64-ABI/-/wikis/x86-64-psABI
- *
- */
-
-#define my_syscall0(num)                                                      \
-({                                                                            \
-	long _ret;                                                            \
-	register long _num  asm("rax") = (num);                               \
-									      \
-	asm volatile (                                                        \
-		"syscall\n"                                                   \
-		: "=a"(_ret)                                                  \
-		: "0"(_num)                                                   \
-		: "rcx", "r11", "memory", "cc"                                \
-	);                                                                    \
-	_ret;                                                                 \
-})
-
-#define my_syscall1(num, arg1)                                                \
-({                                                                            \
-	long _ret;                                                            \
-	register long _num  asm("rax") = (num);                               \
-	register long _arg1 asm("rdi") = (long)(arg1);                        \
-									      \
-	asm volatile (                                                        \
-		"syscall\n"                                                   \
-		: "=a"(_ret)                                                  \
-		: "r"(_arg1),                                                 \
-		  "0"(_num)                                                   \
-		: "rcx", "r11", "memory", "cc"                                \
-	);                                                                    \
-	_ret;                                                                 \
-})
-
-#define my_syscall2(num, arg1, arg2)                                          \
-({                                                                            \
-	long _ret;                                                            \
-	register long _num  asm("rax") = (num);                               \
-	register long _arg1 asm("rdi") = (long)(arg1);                        \
-	register long _arg2 asm("rsi") = (long)(arg2);                        \
-									      \
-	asm volatile (                                                        \
-		"syscall\n"                                                   \
-		: "=a"(_ret)                                                  \
-		: "r"(_arg1), "r"(_arg2),                                     \
-		  "0"(_num)                                                   \
-		: "rcx", "r11", "memory", "cc"                                \
-	);                                                                    \
-	_ret;                                                                 \
-})
-
-#define my_syscall3(num, arg1, arg2, arg3)                                    \
-({                                                                            \
-	long _ret;                                                            \
-	register long _num  asm("rax") = (num);                               \
-	register long _arg1 asm("rdi") = (long)(arg1);                        \
-	register long _arg2 asm("rsi") = (long)(arg2);                        \
-	register long _arg3 asm("rdx") = (long)(arg3);                        \
-									      \
-	asm volatile (                                                        \
-		"syscall\n"                                                   \
-		: "=a"(_ret)                                                  \
-		: "r"(_arg1), "r"(_arg2), "r"(_arg3),                         \
-		  "0"(_num)                                                   \
-		: "rcx", "r11", "memory", "cc"                                \
-	);                                                                    \
-	_ret;                                                                 \
-})
-
-#define my_syscall4(num, arg1, arg2, arg3, arg4)                              \
-({                                                                            \
-	long _ret;                                                            \
-	register long _num  asm("rax") = (num);                               \
-	register long _arg1 asm("rdi") = (long)(arg1);                        \
-	register long _arg2 asm("rsi") = (long)(arg2);                        \
-	register long _arg3 asm("rdx") = (long)(arg3);                        \
-	register long _arg4 asm("r10") = (long)(arg4);                        \
-									      \
-	asm volatile (                                                        \
-		"syscall\n"                                                   \
-		: "=a"(_ret)                                                  \
-		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4),             \
-		  "0"(_num)                                                   \
-		: "rcx", "r11", "memory", "cc"                                \
-	);                                                                    \
-	_ret;                                                                 \
-})
-
-#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5)                        \
-({                                                                            \
-	long _ret;                                                            \
-	register long _num  asm("rax") = (num);                               \
-	register long _arg1 asm("rdi") = (long)(arg1);                        \
-	register long _arg2 asm("rsi") = (long)(arg2);                        \
-	register long _arg3 asm("rdx") = (long)(arg3);                        \
-	register long _arg4 asm("r10") = (long)(arg4);                        \
-	register long _arg5 asm("r8")  = (long)(arg5);                        \
-									      \
-	asm volatile (                                                        \
-		"syscall\n"                                                   \
-		: "=a"(_ret)                                                  \
-		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
-		  "0"(_num)                                                   \
-		: "rcx", "r11", "memory", "cc"                                \
-	);                                                                    \
-	_ret;                                                                 \
-})
-
-#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6)                  \
-({                                                                            \
-	long _ret;                                                            \
-	register long _num  asm("rax") = (num);                               \
-	register long _arg1 asm("rdi") = (long)(arg1);                        \
-	register long _arg2 asm("rsi") = (long)(arg2);                        \
-	register long _arg3 asm("rdx") = (long)(arg3);                        \
-	register long _arg4 asm("r10") = (long)(arg4);                        \
-	register long _arg5 asm("r8")  = (long)(arg5);                        \
-	register long _arg6 asm("r9")  = (long)(arg6);                        \
-									      \
-	asm volatile (                                                        \
-		"syscall\n"                                                   \
-		: "=a"(_ret)                                                  \
-		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
-		  "r"(_arg6), "0"(_num)                                       \
-		: "rcx", "r11", "memory", "cc"                                \
-	);                                                                    \
-	_ret;                                                                 \
-})
-
-/* startup code */
-/*
- * x86-64 System V ABI mandates:
- * 1) %rsp must be 16-byte aligned right before the function call.
- * 2) The deepest stack frame should be zero (the %rbp).
- *
- */
-asm(".section .text\n"
-    ".global _start\n"
-    "_start:\n"
-    "pop %rdi\n"                // argc   (first arg, %rdi)
-    "mov %rsp, %rsi\n"          // argv[] (second arg, %rsi)
-    "lea 8(%rsi,%rdi,8),%rdx\n" // then a NULL then envp (third arg, %rdx)
-    "xor %ebp, %ebp\n"          // zero the stack frame
-    "and $-16, %rsp\n"          // x86 ABI : esp must be 16-byte aligned before call
-    "call main\n"               // main() returns the status code, we'll exit with it.
-    "mov %eax, %edi\n"          // retrieve exit code (32 bit)
-    "mov $60, %eax\n"           // NR_exit == 60
-    "syscall\n"                 // really exit
-    "hlt\n"                     // ensure it does not return
-    "");
-
-/* fcntl / open */
-#define O_RDONLY            0
-#define O_WRONLY            1
-#define O_RDWR              2
-#define O_CREAT          0x40
-#define O_EXCL           0x80
-#define O_NOCTTY        0x100
-#define O_TRUNC         0x200
-#define O_APPEND        0x400
-#define O_NONBLOCK      0x800
-#define O_DIRECTORY   0x10000
-
-/* The struct returned by the stat() syscall, equivalent to stat64(). The
- * syscall returns 116 bytes and stops in the middle of __unused.
- */
-struct sys_stat_struct {
-	unsigned long st_dev;
-	unsigned long st_ino;
-	unsigned long st_nlink;
-	unsigned int  st_mode;
-	unsigned int  st_uid;
-
-	unsigned int  st_gid;
-	unsigned int  __pad0;
-	unsigned long st_rdev;
-	long          st_size;
-	long          st_blksize;
-
-	long          st_blocks;
-	unsigned long st_atime;
-	unsigned long st_atime_nsec;
-	unsigned long st_mtime;
-
-	unsigned long st_mtime_nsec;
-	unsigned long st_ctime;
-	unsigned long st_ctime_nsec;
-	long          __unused[3];
-};
-
-#elif defined(__i386__) || defined(__i486__) || defined(__i586__) || defined(__i686__)
-/* Syscalls for i386 :
- *   - mostly similar to x86_64
- *   - registers are 32-bit
- *   - syscall number is passed in eax
- *   - arguments are in ebx, ecx, edx, esi, edi, ebp respectively
- *   - all registers are preserved (except eax of course)
- *   - the system call is performed by calling int $0x80
- *   - syscall return comes in eax
- *   - the arguments are cast to long and assigned into the target registers
- *     which are then simply passed as registers to the asm code, so that we
- *     don't have to experience issues with register constraints.
- *   - the syscall number is always specified last in order to allow to force
- *     some registers before (gcc refuses a %-register at the last position).
- *
- * Also, i386 supports the old_select syscall if newselect is not available
- */
-#define __ARCH_WANT_SYS_OLD_SELECT
-
-#define my_syscall0(num)                                                      \
-({                                                                            \
-	long _ret;                                                            \
-	register long _num asm("eax") = (num);                                \
-									      \
-	asm volatile (                                                        \
-		"int $0x80\n"                                                 \
-		: "=a" (_ret)                                                 \
-		: "0"(_num)                                                   \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_ret;                                                                 \
-})
-
-#define my_syscall1(num, arg1)                                                \
-({                                                                            \
-	long _ret;                                                            \
-	register long _num asm("eax") = (num);                                \
-	register long _arg1 asm("ebx") = (long)(arg1);                        \
-									      \
-	asm volatile (                                                        \
-		"int $0x80\n"                                                 \
-		: "=a" (_ret)                                                 \
-		: "r"(_arg1),                                                 \
-		  "0"(_num)                                                   \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_ret;                                                                 \
-})
-
-#define my_syscall2(num, arg1, arg2)                                          \
-({                                                                            \
-	long _ret;                                                            \
-	register long _num asm("eax") = (num);                                \
-	register long _arg1 asm("ebx") = (long)(arg1);                        \
-	register long _arg2 asm("ecx") = (long)(arg2);                        \
-									      \
-	asm volatile (                                                        \
-		"int $0x80\n"                                                 \
-		: "=a" (_ret)                                                 \
-		: "r"(_arg1), "r"(_arg2),                                     \
-		  "0"(_num)                                                   \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_ret;                                                                 \
-})
-
-#define my_syscall3(num, arg1, arg2, arg3)                                    \
-({                                                                            \
-	long _ret;                                                            \
-	register long _num asm("eax") = (num);                                \
-	register long _arg1 asm("ebx") = (long)(arg1);                        \
-	register long _arg2 asm("ecx") = (long)(arg2);                        \
-	register long _arg3 asm("edx") = (long)(arg3);                        \
-									      \
-	asm volatile (                                                        \
-		"int $0x80\n"                                                 \
-		: "=a" (_ret)                                                 \
-		: "r"(_arg1), "r"(_arg2), "r"(_arg3),                         \
-		  "0"(_num)                                                   \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_ret;                                                                 \
-})
-
-#define my_syscall4(num, arg1, arg2, arg3, arg4)                              \
-({                                                                            \
-	long _ret;                                                            \
-	register long _num asm("eax") = (num);                                \
-	register long _arg1 asm("ebx") = (long)(arg1);                        \
-	register long _arg2 asm("ecx") = (long)(arg2);                        \
-	register long _arg3 asm("edx") = (long)(arg3);                        \
-	register long _arg4 asm("esi") = (long)(arg4);                        \
-									      \
-	asm volatile (                                                        \
-		"int $0x80\n"                                                 \
-		: "=a" (_ret)                                                 \
-		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4),             \
-		  "0"(_num)                                                   \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_ret;                                                                 \
-})
-
-#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5)                        \
-({                                                                            \
-	long _ret;                                                            \
-	register long _num asm("eax") = (num);                                \
-	register long _arg1 asm("ebx") = (long)(arg1);                        \
-	register long _arg2 asm("ecx") = (long)(arg2);                        \
-	register long _arg3 asm("edx") = (long)(arg3);                        \
-	register long _arg4 asm("esi") = (long)(arg4);                        \
-	register long _arg5 asm("edi") = (long)(arg5);                        \
-									      \
-	asm volatile (                                                        \
-		"int $0x80\n"                                                 \
-		: "=a" (_ret)                                                 \
-		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
-		  "0"(_num)                                                   \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_ret;                                                                 \
-})
-
-/* startup code */
-/*
- * i386 System V ABI mandates:
- * 1) last pushed argument must be 16-byte aligned.
- * 2) The deepest stack frame should be set to zero
- *
- */
-asm(".section .text\n"
-    ".global _start\n"
-    "_start:\n"
-    "pop %eax\n"                // argc   (first arg, %eax)
-    "mov %esp, %ebx\n"          // argv[] (second arg, %ebx)
-    "lea 4(%ebx,%eax,4),%ecx\n" // then a NULL then envp (third arg, %ecx)
-    "xor %ebp, %ebp\n"          // zero the stack frame
-    "and $-16, %esp\n"          // x86 ABI : esp must be 16-byte aligned before
-    "sub $4, %esp\n"            // the call instruction (args are aligned)
-    "push %ecx\n"               // push all registers on the stack so that we
-    "push %ebx\n"               // support both regparm and plain stack modes
-    "push %eax\n"
-    "call main\n"               // main() returns the status code in %eax
-    "mov %eax, %ebx\n"          // retrieve exit code (32-bit int)
-    "movl $1, %eax\n"           // NR_exit == 1
-    "int $0x80\n"               // exit now
-    "hlt\n"                     // ensure it does not
-    "");
-
-/* fcntl / open */
-#define O_RDONLY            0
-#define O_WRONLY            1
-#define O_RDWR              2
-#define O_CREAT          0x40
-#define O_EXCL           0x80
-#define O_NOCTTY        0x100
-#define O_TRUNC         0x200
-#define O_APPEND        0x400
-#define O_NONBLOCK      0x800
-#define O_DIRECTORY   0x10000
-
-/* The struct returned by the stat() syscall, 32-bit only, the syscall returns
- * exactly 56 bytes (stops before the unused array).
- */
-struct sys_stat_struct {
-	unsigned long  st_dev;
-	unsigned long  st_ino;
-	unsigned short st_mode;
-	unsigned short st_nlink;
-	unsigned short st_uid;
-	unsigned short st_gid;
-
-	unsigned long  st_rdev;
-	unsigned long  st_size;
-	unsigned long  st_blksize;
-	unsigned long  st_blocks;
-
-	unsigned long  st_atime;
-	unsigned long  st_atime_nsec;
-	unsigned long  st_mtime;
-	unsigned long  st_mtime_nsec;
-
-	unsigned long  st_ctime;
-	unsigned long  st_ctime_nsec;
-	unsigned long  __unused[2];
-};
-
-#elif defined(__ARM_EABI__)
-/* Syscalls for ARM in ARM or Thumb modes :
- *   - registers are 32-bit
- *   - stack is 8-byte aligned
- *     ( http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.faqs/ka4127.html)
- *   - syscall number is passed in r7
- *   - arguments are in r0, r1, r2, r3, r4, r5
- *   - the system call is performed by calling svc #0
- *   - syscall return comes in r0.
- *   - only lr is clobbered.
- *   - the arguments are cast to long and assigned into the target registers
- *     which are then simply passed as registers to the asm code, so that we
- *     don't have to experience issues with register constraints.
- *   - the syscall number is always specified last in order to allow to force
- *     some registers before (gcc refuses a %-register at the last position).
- *
- * Also, ARM supports the old_select syscall if newselect is not available
- */
-#define __ARCH_WANT_SYS_OLD_SELECT
-
-#define my_syscall0(num)                                                      \
-({                                                                            \
-	register long _num asm("r7") = (num);                                 \
-	register long _arg1 asm("r0");                                        \
-									      \
-	asm volatile (                                                        \
-		"svc #0\n"                                                    \
-		: "=r"(_arg1)                                                 \
-		: "r"(_num)                                                   \
-		: "memory", "cc", "lr"                                        \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-#define my_syscall1(num, arg1)                                                \
-({                                                                            \
-	register long _num asm("r7") = (num);                                 \
-	register long _arg1 asm("r0") = (long)(arg1);                         \
-									      \
-	asm volatile (                                                        \
-		"svc #0\n"                                                    \
-		: "=r"(_arg1)                                                 \
-		: "r"(_arg1),                                                 \
-		  "r"(_num)                                                   \
-		: "memory", "cc", "lr"                                        \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-#define my_syscall2(num, arg1, arg2)                                          \
-({                                                                            \
-	register long _num asm("r7") = (num);                                 \
-	register long _arg1 asm("r0") = (long)(arg1);                         \
-	register long _arg2 asm("r1") = (long)(arg2);                         \
-									      \
-	asm volatile (                                                        \
-		"svc #0\n"                                                    \
-		: "=r"(_arg1)                                                 \
-		: "r"(_arg1), "r"(_arg2),                                     \
-		  "r"(_num)                                                   \
-		: "memory", "cc", "lr"                                        \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-#define my_syscall3(num, arg1, arg2, arg3)                                    \
-({                                                                            \
-	register long _num asm("r7") = (num);                                 \
-	register long _arg1 asm("r0") = (long)(arg1);                         \
-	register long _arg2 asm("r1") = (long)(arg2);                         \
-	register long _arg3 asm("r2") = (long)(arg3);                         \
-									      \
-	asm volatile (                                                        \
-		"svc #0\n"                                                    \
-		: "=r"(_arg1)                                                 \
-		: "r"(_arg1), "r"(_arg2), "r"(_arg3),                         \
-		  "r"(_num)                                                   \
-		: "memory", "cc", "lr"                                        \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-#define my_syscall4(num, arg1, arg2, arg3, arg4)                              \
-({                                                                            \
-	register long _num asm("r7") = (num);                                 \
-	register long _arg1 asm("r0") = (long)(arg1);                         \
-	register long _arg2 asm("r1") = (long)(arg2);                         \
-	register long _arg3 asm("r2") = (long)(arg3);                         \
-	register long _arg4 asm("r3") = (long)(arg4);                         \
-									      \
-	asm volatile (                                                        \
-		"svc #0\n"                                                    \
-		: "=r"(_arg1)                                                 \
-		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4),             \
-		  "r"(_num)                                                   \
-		: "memory", "cc", "lr"                                        \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5)                        \
-({                                                                            \
-	register long _num asm("r7") = (num);                                 \
-	register long _arg1 asm("r0") = (long)(arg1);                         \
-	register long _arg2 asm("r1") = (long)(arg2);                         \
-	register long _arg3 asm("r2") = (long)(arg3);                         \
-	register long _arg4 asm("r3") = (long)(arg4);                         \
-	register long _arg5 asm("r4") = (long)(arg5);                         \
-									      \
-	asm volatile (                                                        \
-		"svc #0\n"                                                    \
-		: "=r" (_arg1)                                                \
-		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
-		  "r"(_num)                                                   \
-		: "memory", "cc", "lr"                                        \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-/* startup code */
-asm(".section .text\n"
-    ".global _start\n"
-    "_start:\n"
-#if defined(__THUMBEB__) || defined(__THUMBEL__)
-    /* We enter here in 32-bit mode but if some previous functions were in
-     * 16-bit mode, the assembler cannot know, so we need to tell it we're in
-     * 32-bit now, then switch to 16-bit (is there a better way to do it than
-     * adding 1 by hand ?) and tell the asm we're now in 16-bit mode so that
-     * it generates correct instructions. Note that we do not support thumb1.
-     */
-    ".code 32\n"
-    "add     r0, pc, #1\n"
-    "bx      r0\n"
-    ".code 16\n"
-#endif
-    "pop {%r0}\n"                 // argc was in the stack
-    "mov %r1, %sp\n"              // argv = sp
-    "add %r2, %r1, %r0, lsl #2\n" // envp = argv + 4*argc ...
-    "add %r2, %r2, $4\n"          //        ... + 4
-    "and %r3, %r1, $-8\n"         // AAPCS : sp must be 8-byte aligned in the
-    "mov %sp, %r3\n"              //         callee, an bl doesn't push (lr=pc)
-    "bl main\n"                   // main() returns the status code, we'll exit with it.
-    "movs r7, $1\n"               // NR_exit == 1
-    "svc $0x00\n"
-    "");
-
-/* fcntl / open */
-#define O_RDONLY            0
-#define O_WRONLY            1
-#define O_RDWR              2
-#define O_CREAT          0x40
-#define O_EXCL           0x80
-#define O_NOCTTY        0x100
-#define O_TRUNC         0x200
-#define O_APPEND        0x400
-#define O_NONBLOCK      0x800
-#define O_DIRECTORY    0x4000
-
-/* The struct returned by the stat() syscall, 32-bit only, the syscall returns
- * exactly 56 bytes (stops before the unused array). In big endian, the format
- * differs as devices are returned as short only.
- */
-struct sys_stat_struct {
-#if defined(__ARMEB__)
-	unsigned short st_dev;
-	unsigned short __pad1;
-#else
-	unsigned long  st_dev;
-#endif
-	unsigned long  st_ino;
-	unsigned short st_mode;
-	unsigned short st_nlink;
-	unsigned short st_uid;
-	unsigned short st_gid;
-#if defined(__ARMEB__)
-	unsigned short st_rdev;
-	unsigned short __pad2;
-#else
-	unsigned long  st_rdev;
-#endif
-	unsigned long  st_size;
-	unsigned long  st_blksize;
-	unsigned long  st_blocks;
-	unsigned long  st_atime;
-	unsigned long  st_atime_nsec;
-	unsigned long  st_mtime;
-	unsigned long  st_mtime_nsec;
-	unsigned long  st_ctime;
-	unsigned long  st_ctime_nsec;
-	unsigned long  __unused[2];
-};
-
-#elif defined(__aarch64__)
-/* Syscalls for AARCH64 :
- *   - registers are 64-bit
- *   - stack is 16-byte aligned
- *   - syscall number is passed in x8
- *   - arguments are in x0, x1, x2, x3, x4, x5
- *   - the system call is performed by calling svc 0
- *   - syscall return comes in x0.
- *   - the arguments are cast to long and assigned into the target registers
- *     which are then simply passed as registers to the asm code, so that we
- *     don't have to experience issues with register constraints.
- *
- * On aarch64, select() is not implemented so we have to use pselect6().
- */
-#define __ARCH_WANT_SYS_PSELECT6
-
-#define my_syscall0(num)                                                      \
-({                                                                            \
-	register long _num  asm("x8") = (num);                                \
-	register long _arg1 asm("x0");                                        \
-									      \
-	asm volatile (                                                        \
-		"svc #0\n"                                                    \
-		: "=r"(_arg1)                                                 \
-		: "r"(_num)                                                   \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-#define my_syscall1(num, arg1)                                                \
-({                                                                            \
-	register long _num  asm("x8") = (num);                                \
-	register long _arg1 asm("x0") = (long)(arg1);                         \
-									      \
-	asm volatile (                                                        \
-		"svc #0\n"                                                    \
-		: "=r"(_arg1)                                                 \
-		: "r"(_arg1),                                                 \
-		  "r"(_num)                                                   \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-#define my_syscall2(num, arg1, arg2)                                          \
-({                                                                            \
-	register long _num  asm("x8") = (num);                                \
-	register long _arg1 asm("x0") = (long)(arg1);                         \
-	register long _arg2 asm("x1") = (long)(arg2);                         \
-									      \
-	asm volatile (                                                        \
-		"svc #0\n"                                                    \
-		: "=r"(_arg1)                                                 \
-		: "r"(_arg1), "r"(_arg2),                                     \
-		  "r"(_num)                                                   \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-#define my_syscall3(num, arg1, arg2, arg3)                                    \
-({                                                                            \
-	register long _num  asm("x8") = (num);                                \
-	register long _arg1 asm("x0") = (long)(arg1);                         \
-	register long _arg2 asm("x1") = (long)(arg2);                         \
-	register long _arg3 asm("x2") = (long)(arg3);                         \
-									      \
-	asm volatile (                                                        \
-		"svc #0\n"                                                    \
-		: "=r"(_arg1)                                                 \
-		: "r"(_arg1), "r"(_arg2), "r"(_arg3),                         \
-		  "r"(_num)                                                   \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-#define my_syscall4(num, arg1, arg2, arg3, arg4)                              \
-({                                                                            \
-	register long _num  asm("x8") = (num);                                \
-	register long _arg1 asm("x0") = (long)(arg1);                         \
-	register long _arg2 asm("x1") = (long)(arg2);                         \
-	register long _arg3 asm("x2") = (long)(arg3);                         \
-	register long _arg4 asm("x3") = (long)(arg4);                         \
-									      \
-	asm volatile (                                                        \
-		"svc #0\n"                                                    \
-		: "=r"(_arg1)                                                 \
-		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4),             \
-		  "r"(_num)                                                   \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5)                        \
-({                                                                            \
-	register long _num  asm("x8") = (num);                                \
-	register long _arg1 asm("x0") = (long)(arg1);                         \
-	register long _arg2 asm("x1") = (long)(arg2);                         \
-	register long _arg3 asm("x2") = (long)(arg3);                         \
-	register long _arg4 asm("x3") = (long)(arg4);                         \
-	register long _arg5 asm("x4") = (long)(arg5);                         \
-									      \
-	asm volatile (                                                        \
-		"svc #0\n"                                                    \
-		: "=r" (_arg1)                                                \
-		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
-		  "r"(_num)                                                   \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6)                  \
-({                                                                            \
-	register long _num  asm("x8") = (num);                                \
-	register long _arg1 asm("x0") = (long)(arg1);                         \
-	register long _arg2 asm("x1") = (long)(arg2);                         \
-	register long _arg3 asm("x2") = (long)(arg3);                         \
-	register long _arg4 asm("x3") = (long)(arg4);                         \
-	register long _arg5 asm("x4") = (long)(arg5);                         \
-	register long _arg6 asm("x5") = (long)(arg6);                         \
-									      \
-	asm volatile (                                                        \
-		"svc #0\n"                                                    \
-		: "=r" (_arg1)                                                \
-		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
-		  "r"(_arg6), "r"(_num)                                       \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-/* startup code */
-asm(".section .text\n"
-    ".global _start\n"
-    "_start:\n"
-    "ldr x0, [sp]\n"              // argc (x0) was in the stack
-    "add x1, sp, 8\n"             // argv (x1) = sp
-    "lsl x2, x0, 3\n"             // envp (x2) = 8*argc ...
-    "add x2, x2, 8\n"             //           + 8 (skip null)
-    "add x2, x2, x1\n"            //           + argv
-    "and sp, x1, -16\n"           // sp must be 16-byte aligned in the callee
-    "bl main\n"                   // main() returns the status code, we'll exit with it.
-    "mov x8, 93\n"                // NR_exit == 93
-    "svc #0\n"
-    "");
-
-/* fcntl / open */
-#define O_RDONLY            0
-#define O_WRONLY            1
-#define O_RDWR              2
-#define O_CREAT          0x40
-#define O_EXCL           0x80
-#define O_NOCTTY        0x100
-#define O_TRUNC         0x200
-#define O_APPEND        0x400
-#define O_NONBLOCK      0x800
-#define O_DIRECTORY    0x4000
-
-/* The struct returned by the newfstatat() syscall. Differs slightly from the
- * x86_64's stat one by field ordering, so be careful.
- */
-struct sys_stat_struct {
-	unsigned long   st_dev;
-	unsigned long   st_ino;
-	unsigned int    st_mode;
-	unsigned int    st_nlink;
-	unsigned int    st_uid;
-	unsigned int    st_gid;
-
-	unsigned long   st_rdev;
-	unsigned long   __pad1;
-	long            st_size;
-	int             st_blksize;
-	int             __pad2;
-
-	long            st_blocks;
-	long            st_atime;
-	unsigned long   st_atime_nsec;
-	long            st_mtime;
-
-	unsigned long   st_mtime_nsec;
-	long            st_ctime;
-	unsigned long   st_ctime_nsec;
-	unsigned int    __unused[2];
-};
-
-#elif defined(__mips__) && defined(_ABIO32)
-/* Syscalls for MIPS ABI O32 :
- *   - WARNING! there's always a delayed slot!
- *   - WARNING again, the syntax is different, registers take a '$' and numbers
- *     do not.
- *   - registers are 32-bit
- *   - stack is 8-byte aligned
- *   - syscall number is passed in v0 (starts at 0xfa0).
- *   - arguments are in a0, a1, a2, a3, then the stack. The caller needs to
- *     leave some room in the stack for the callee to save a0..a3 if needed.
- *   - Many registers are clobbered, in fact only a0..a2 and s0..s8 are
- *     preserved. See: https://www.linux-mips.org/wiki/Syscall as well as
- *     scall32-o32.S in the kernel sources.
- *   - the system call is performed by calling "syscall"
- *   - syscall return comes in v0, and register a3 needs to be checked to know
- *     if an error occurred, in which case errno is in v0.
- *   - the arguments are cast to long and assigned into the target registers
- *     which are then simply passed as registers to the asm code, so that we
- *     don't have to experience issues with register constraints.
- */
-
-#define my_syscall0(num)                                                      \
-({                                                                            \
-	register long _num asm("v0") = (num);                                 \
-	register long _arg4 asm("a3");                                        \
-									      \
-	asm volatile (                                                        \
-		"addiu $sp, $sp, -32\n"                                       \
-		"syscall\n"                                                   \
-		"addiu $sp, $sp, 32\n"                                        \
-		: "=r"(_num), "=r"(_arg4)                                     \
-		: "r"(_num)                                                   \
-		: "memory", "cc", "at", "v1", "hi", "lo",                     \
-		  "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"  \
-	);                                                                    \
-	_arg4 ? -_num : _num;                                                 \
-})
-
-#define my_syscall1(num, arg1)                                                \
-({                                                                            \
-	register long _num asm("v0") = (num);                                 \
-	register long _arg1 asm("a0") = (long)(arg1);                         \
-	register long _arg4 asm("a3");                                        \
-									      \
-	asm volatile (                                                        \
-		"addiu $sp, $sp, -32\n"                                       \
-		"syscall\n"                                                   \
-		"addiu $sp, $sp, 32\n"                                        \
-		: "=r"(_num), "=r"(_arg4)                                     \
-		: "0"(_num),                                                  \
-		  "r"(_arg1)                                                  \
-		: "memory", "cc", "at", "v1", "hi", "lo",                     \
-		  "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"  \
-	);                                                                    \
-	_arg4 ? -_num : _num;                                                 \
-})
-
-#define my_syscall2(num, arg1, arg2)                                          \
-({                                                                            \
-	register long _num asm("v0") = (num);                                 \
-	register long _arg1 asm("a0") = (long)(arg1);                         \
-	register long _arg2 asm("a1") = (long)(arg2);                         \
-	register long _arg4 asm("a3");                                        \
-									      \
-	asm volatile (                                                        \
-		"addiu $sp, $sp, -32\n"                                       \
-		"syscall\n"                                                   \
-		"addiu $sp, $sp, 32\n"                                        \
-		: "=r"(_num), "=r"(_arg4)                                     \
-		: "0"(_num),                                                  \
-		  "r"(_arg1), "r"(_arg2)                                      \
-		: "memory", "cc", "at", "v1", "hi", "lo",                     \
-		  "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"  \
-	);                                                                    \
-	_arg4 ? -_num : _num;                                                 \
-})
-
-#define my_syscall3(num, arg1, arg2, arg3)                                    \
-({                                                                            \
-	register long _num asm("v0")  = (num);                                \
-	register long _arg1 asm("a0") = (long)(arg1);                         \
-	register long _arg2 asm("a1") = (long)(arg2);                         \
-	register long _arg3 asm("a2") = (long)(arg3);                         \
-	register long _arg4 asm("a3");                                        \
-									      \
-	asm volatile (                                                        \
-		"addiu $sp, $sp, -32\n"                                       \
-		"syscall\n"                                                   \
-		"addiu $sp, $sp, 32\n"                                        \
-		: "=r"(_num), "=r"(_arg4)                                     \
-		: "0"(_num),                                                  \
-		  "r"(_arg1), "r"(_arg2), "r"(_arg3)                          \
-		: "memory", "cc", "at", "v1", "hi", "lo",                     \
-		  "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"  \
-	);                                                                    \
-	_arg4 ? -_num : _num;                                                 \
-})
-
-#define my_syscall4(num, arg1, arg2, arg3, arg4)                              \
-({                                                                            \
-	register long _num asm("v0") = (num);                                 \
-	register long _arg1 asm("a0") = (long)(arg1);                         \
-	register long _arg2 asm("a1") = (long)(arg2);                         \
-	register long _arg3 asm("a2") = (long)(arg3);                         \
-	register long _arg4 asm("a3") = (long)(arg4);                         \
-									      \
-	asm volatile (                                                        \
-		"addiu $sp, $sp, -32\n"                                       \
-		"syscall\n"                                                   \
-		"addiu $sp, $sp, 32\n"                                        \
-		: "=r" (_num), "=r"(_arg4)                                    \
-		: "0"(_num),                                                  \
-		  "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4)              \
-		: "memory", "cc", "at", "v1", "hi", "lo",                     \
-		  "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"  \
-	);                                                                    \
-	_arg4 ? -_num : _num;                                                 \
-})
-
-#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5)                        \
-({                                                                            \
-	register long _num asm("v0") = (num);                                 \
-	register long _arg1 asm("a0") = (long)(arg1);                         \
-	register long _arg2 asm("a1") = (long)(arg2);                         \
-	register long _arg3 asm("a2") = (long)(arg3);                         \
-	register long _arg4 asm("a3") = (long)(arg4);                         \
-	register long _arg5 = (long)(arg5);				      \
-									      \
-	asm volatile (                                                        \
-		"addiu $sp, $sp, -32\n"                                       \
-		"sw %7, 16($sp)\n"                                            \
-		"syscall\n  "                                                 \
-		"addiu $sp, $sp, 32\n"                                        \
-		: "=r" (_num), "=r"(_arg4)                                    \
-		: "0"(_num),                                                  \
-		  "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5)  \
-		: "memory", "cc", "at", "v1", "hi", "lo",                     \
-		  "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"  \
-	);                                                                    \
-	_arg4 ? -_num : _num;                                                 \
-})
-
-/* startup code, note that it's called __start on MIPS */
-asm(".section .text\n"
-    ".set nomips16\n"
-    ".global __start\n"
-    ".set    noreorder\n"
-    ".option pic0\n"
-    ".ent __start\n"
-    "__start:\n"
-    "lw $a0,($sp)\n"              // argc was in the stack
-    "addiu  $a1, $sp, 4\n"        // argv = sp + 4
-    "sll $a2, $a0, 2\n"           // a2 = argc * 4
-    "add   $a2, $a2, $a1\n"       // envp = argv + 4*argc ...
-    "addiu $a2, $a2, 4\n"         //        ... + 4
-    "li $t0, -8\n"
-    "and $sp, $sp, $t0\n"         // sp must be 8-byte aligned
-    "addiu $sp,$sp,-16\n"         // the callee expects to save a0..a3 there!
-    "jal main\n"                  // main() returns the status code, we'll exit with it.
-    "nop\n"                       // delayed slot
-    "move $a0, $v0\n"             // retrieve 32-bit exit code from v0
-    "li $v0, 4001\n"              // NR_exit == 4001
-    "syscall\n"
-    ".end __start\n"
-    "");
-
-/* fcntl / open */
-#define O_RDONLY            0
-#define O_WRONLY            1
-#define O_RDWR              2
-#define O_APPEND       0x0008
-#define O_NONBLOCK     0x0080
-#define O_CREAT        0x0100
-#define O_TRUNC        0x0200
-#define O_EXCL         0x0400
-#define O_NOCTTY       0x0800
-#define O_DIRECTORY   0x10000
-
-/* The struct returned by the stat() syscall. 88 bytes are returned by the
- * syscall.
- */
-struct sys_stat_struct {
-	unsigned int  st_dev;
-	long          st_pad1[3];
-	unsigned long st_ino;
-	unsigned int  st_mode;
-	unsigned int  st_nlink;
-	unsigned int  st_uid;
-	unsigned int  st_gid;
-	unsigned int  st_rdev;
-	long          st_pad2[2];
-	long          st_size;
-	long          st_pad3;
-	long          st_atime;
-	long          st_atime_nsec;
-	long          st_mtime;
-	long          st_mtime_nsec;
-	long          st_ctime;
-	long          st_ctime_nsec;
-	long          st_blksize;
-	long          st_blocks;
-	long          st_pad4[14];
-};
-
-#elif defined(__riscv)
-
-#if   __riscv_xlen == 64
-#define PTRLOG "3"
-#define SZREG  "8"
-#elif __riscv_xlen == 32
-#define PTRLOG "2"
-#define SZREG  "4"
-#endif
-
-/* Syscalls for RISCV :
- *   - stack is 16-byte aligned
- *   - syscall number is passed in a7
- *   - arguments are in a0, a1, a2, a3, a4, a5
- *   - the system call is performed by calling ecall
- *   - syscall return comes in a0
- *   - the arguments are cast to long and assigned into the target
- *     registers which are then simply passed as registers to the asm code,
- *     so that we don't have to experience issues with register constraints.
- */
-
-#define my_syscall0(num)                                                      \
-({                                                                            \
-	register long _num  asm("a7") = (num);                                \
-	register long _arg1 asm("a0");                                        \
-									      \
-	asm volatile (                                                        \
-		"ecall\n\t"                                                   \
-		: "=r"(_arg1)                                                 \
-		: "r"(_num)                                                   \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-#define my_syscall1(num, arg1)                                                \
-({                                                                            \
-	register long _num  asm("a7") = (num);                                \
-	register long _arg1 asm("a0") = (long)(arg1);		              \
-									      \
-	asm volatile (                                                        \
-		"ecall\n"                                                     \
-		: "+r"(_arg1)                                                 \
-		: "r"(_num)                                                   \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-#define my_syscall2(num, arg1, arg2)                                          \
-({                                                                            \
-	register long _num  asm("a7") = (num);                                \
-	register long _arg1 asm("a0") = (long)(arg1);                         \
-	register long _arg2 asm("a1") = (long)(arg2);                         \
-									      \
-	asm volatile (                                                        \
-		"ecall\n"                                                     \
-		: "+r"(_arg1)                                                 \
-		: "r"(_arg2),                                                 \
-		  "r"(_num)                                                   \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-#define my_syscall3(num, arg1, arg2, arg3)                                    \
-({                                                                            \
-	register long _num  asm("a7") = (num);                                \
-	register long _arg1 asm("a0") = (long)(arg1);                         \
-	register long _arg2 asm("a1") = (long)(arg2);                         \
-	register long _arg3 asm("a2") = (long)(arg3);                         \
-									      \
-	asm volatile (                                                        \
-		"ecall\n\t"                                                   \
-		: "+r"(_arg1)                                                 \
-		: "r"(_arg2), "r"(_arg3),                                     \
-		  "r"(_num)                                                   \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-#define my_syscall4(num, arg1, arg2, arg3, arg4)                              \
-({                                                                            \
-	register long _num  asm("a7") = (num);                                \
-	register long _arg1 asm("a0") = (long)(arg1);                         \
-	register long _arg2 asm("a1") = (long)(arg2);                         \
-	register long _arg3 asm("a2") = (long)(arg3);                         \
-	register long _arg4 asm("a3") = (long)(arg4);                         \
-									      \
-	asm volatile (                                                        \
-		"ecall\n"                                                     \
-		: "+r"(_arg1)                                                 \
-		: "r"(_arg2), "r"(_arg3), "r"(_arg4),                         \
-		  "r"(_num)                                                   \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5)                        \
-({                                                                            \
-	register long _num  asm("a7") = (num);                                \
-	register long _arg1 asm("a0") = (long)(arg1);                         \
-	register long _arg2 asm("a1") = (long)(arg2);                         \
-	register long _arg3 asm("a2") = (long)(arg3);                         \
-	register long _arg4 asm("a3") = (long)(arg4);                         \
-	register long _arg5 asm("a4") = (long)(arg5);                         \
-									      \
-	asm volatile (                                                        \
-		"ecall\n"                                                     \
-		: "+r"(_arg1)                                                 \
-		: "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5),             \
-		  "r"(_num)                                                   \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6)                  \
-({                                                                            \
-	register long _num  asm("a7") = (num);                                \
-	register long _arg1 asm("a0") = (long)(arg1);                         \
-	register long _arg2 asm("a1") = (long)(arg2);                         \
-	register long _arg3 asm("a2") = (long)(arg3);                         \
-	register long _arg4 asm("a3") = (long)(arg4);                         \
-	register long _arg5 asm("a4") = (long)(arg5);                         \
-	register long _arg6 asm("a5") = (long)(arg6);                         \
-									      \
-	asm volatile (                                                        \
-		"ecall\n"                                                     \
-		: "+r"(_arg1)                                                 \
-		: "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), "r"(_arg6), \
-		  "r"(_num)                                                   \
-		: "memory", "cc"                                              \
-	);                                                                    \
-	_arg1;                                                                \
-})
-
-/* startup code */
-asm(".section .text\n"
-    ".global _start\n"
-    "_start:\n"
-    ".option push\n"
-    ".option norelax\n"
-    "lla   gp, __global_pointer$\n"
-    ".option pop\n"
-    "ld    a0, 0(sp)\n"          // argc (a0) was in the stack
-    "add   a1, sp, "SZREG"\n"    // argv (a1) = sp
-    "slli  a2, a0, "PTRLOG"\n"   // envp (a2) = SZREG*argc ...
-    "add   a2, a2, "SZREG"\n"    //             + SZREG (skip null)
-    "add   a2,a2,a1\n"           //             + argv
-    "andi  sp,a1,-16\n"          // sp must be 16-byte aligned
-    "call  main\n"               // main() returns the status code, we'll exit with it.
-    "li a7, 93\n"                // NR_exit == 93
-    "ecall\n"
-    "");
-
-/* fcntl / open */
-#define O_RDONLY            0
-#define O_WRONLY            1
-#define O_RDWR              2
-#define O_CREAT         0x100
-#define O_EXCL          0x200
-#define O_NOCTTY        0x400
-#define O_TRUNC        0x1000
-#define O_APPEND       0x2000
-#define O_NONBLOCK     0x4000
-#define O_DIRECTORY  0x200000
-
-struct sys_stat_struct {
-	unsigned long	st_dev;		/* Device.  */
-	unsigned long	st_ino;		/* File serial number.  */
-	unsigned int	st_mode;	/* File mode.  */
-	unsigned int	st_nlink;	/* Link count.  */
-	unsigned int	st_uid;		/* User ID of the file's owner.  */
-	unsigned int	st_gid;		/* Group ID of the file's group. */
-	unsigned long	st_rdev;	/* Device number, if device.  */
-	unsigned long	__pad1;
-	long		st_size;	/* Size of file, in bytes.  */
-	int		st_blksize;	/* Optimal block size for I/O.  */
-	int		__pad2;
-	long		st_blocks;	/* Number 512-byte blocks allocated. */
-	long		st_atime;	/* Time of last access.  */
-	unsigned long	st_atime_nsec;
-	long		st_mtime;	/* Time of last modification.  */
-	unsigned long	st_mtime_nsec;
-	long		st_ctime;	/* Time of last status change.  */
-	unsigned long	st_ctime_nsec;
-	unsigned int	__unused4;
-	unsigned int	__unused5;
-};
-
-#endif
-
-
-/* Below are the C functions used to declare the raw syscalls. They try to be
- * architecture-agnostic, and return either a success or -errno. Declaring them
- * static will lead to them being inlined in most cases, but it's still possible
- * to reference them by a pointer if needed.
- */
-static __attribute__((unused))
-void *sys_brk(void *addr)
-{
-	return (void *)my_syscall1(__NR_brk, addr);
-}
-
-static __attribute__((noreturn,unused))
-void sys_exit(int status)
-{
-	my_syscall1(__NR_exit, status & 255);
-	while(1); // shut the "noreturn" warnings.
-}
-
-static __attribute__((unused))
-int sys_chdir(const char *path)
-{
-	return my_syscall1(__NR_chdir, path);
-}
-
-static __attribute__((unused))
-int sys_chmod(const char *path, mode_t mode)
-{
-#ifdef __NR_fchmodat
-	return my_syscall4(__NR_fchmodat, AT_FDCWD, path, mode, 0);
-#elif defined(__NR_chmod)
-	return my_syscall2(__NR_chmod, path, mode);
-#else
-#error Neither __NR_fchmodat nor __NR_chmod defined, cannot implement sys_chmod()
-#endif
-}
-
-static __attribute__((unused))
-int sys_chown(const char *path, uid_t owner, gid_t group)
-{
-#ifdef __NR_fchownat
-	return my_syscall5(__NR_fchownat, AT_FDCWD, path, owner, group, 0);
-#elif defined(__NR_chown)
-	return my_syscall3(__NR_chown, path, owner, group);
-#else
-#error Neither __NR_fchownat nor __NR_chown defined, cannot implement sys_chown()
-#endif
-}
-
-static __attribute__((unused))
-int sys_chroot(const char *path)
-{
-	return my_syscall1(__NR_chroot, path);
-}
-
-static __attribute__((unused))
-int sys_close(int fd)
-{
-	return my_syscall1(__NR_close, fd);
-}
-
-static __attribute__((unused))
-int sys_dup(int fd)
-{
-	return my_syscall1(__NR_dup, fd);
-}
-
-#ifdef __NR_dup3
-static __attribute__((unused))
-int sys_dup3(int old, int new, int flags)
-{
-	return my_syscall3(__NR_dup3, old, new, flags);
-}
-#endif
-
-static __attribute__((unused))
-int sys_dup2(int old, int new)
-{
-#ifdef __NR_dup3
-	return my_syscall3(__NR_dup3, old, new, 0);
-#elif defined(__NR_dup2)
-	return my_syscall2(__NR_dup2, old, new);
-#else
-#error Neither __NR_dup3 nor __NR_dup2 defined, cannot implement sys_dup2()
-#endif
-}
-
-static __attribute__((unused))
-int sys_execve(const char *filename, char *const argv[], char *const envp[])
-{
-	return my_syscall3(__NR_execve, filename, argv, envp);
-}
-
-static __attribute__((unused))
-pid_t sys_fork(void)
-{
-#ifdef __NR_clone
-	/* note: some archs only have clone() and not fork(). Different archs
-	 * have a different API, but most archs have the flags on first arg and
-	 * will not use the rest with no other flag.
-	 */
-	return my_syscall5(__NR_clone, SIGCHLD, 0, 0, 0, 0);
-#elif defined(__NR_fork)
-	return my_syscall0(__NR_fork);
-#else
-#error Neither __NR_clone nor __NR_fork defined, cannot implement sys_fork()
-#endif
-}
-
-static __attribute__((unused))
-int sys_fsync(int fd)
-{
-	return my_syscall1(__NR_fsync, fd);
-}
-
-static __attribute__((unused))
-int sys_getdents64(int fd, struct linux_dirent64 *dirp, int count)
-{
-	return my_syscall3(__NR_getdents64, fd, dirp, count);
-}
-
-static __attribute__((unused))
-pid_t sys_getpgid(pid_t pid)
-{
-	return my_syscall1(__NR_getpgid, pid);
-}
-
-static __attribute__((unused))
-pid_t sys_getpgrp(void)
-{
-	return sys_getpgid(0);
-}
-
-static __attribute__((unused))
-pid_t sys_getpid(void)
-{
-	return my_syscall0(__NR_getpid);
-}
-
-static __attribute__((unused))
-pid_t sys_gettid(void)
-{
-	return my_syscall0(__NR_gettid);
-}
-
-static __attribute__((unused))
-int sys_gettimeofday(struct timeval *tv, struct timezone *tz)
-{
-	return my_syscall2(__NR_gettimeofday, tv, tz);
-}
-
-static __attribute__((unused))
-int sys_ioctl(int fd, unsigned long req, void *value)
-{
-	return my_syscall3(__NR_ioctl, fd, req, value);
-}
-
-static __attribute__((unused))
-int sys_kill(pid_t pid, int signal)
-{
-	return my_syscall2(__NR_kill, pid, signal);
-}
-
-static __attribute__((unused))
-int sys_link(const char *old, const char *new)
-{
-#ifdef __NR_linkat
-	return my_syscall5(__NR_linkat, AT_FDCWD, old, AT_FDCWD, new, 0);
-#elif defined(__NR_link)
-	return my_syscall2(__NR_link, old, new);
-#else
-#error Neither __NR_linkat nor __NR_link defined, cannot implement sys_link()
-#endif
-}
-
-static __attribute__((unused))
-off_t sys_lseek(int fd, off_t offset, int whence)
-{
-	return my_syscall3(__NR_lseek, fd, offset, whence);
-}
-
-static __attribute__((unused))
-int sys_mkdir(const char *path, mode_t mode)
-{
-#ifdef __NR_mkdirat
-	return my_syscall3(__NR_mkdirat, AT_FDCWD, path, mode);
-#elif defined(__NR_mkdir)
-	return my_syscall2(__NR_mkdir, path, mode);
-#else
-#error Neither __NR_mkdirat nor __NR_mkdir defined, cannot implement sys_mkdir()
-#endif
-}
-
-static __attribute__((unused))
-long sys_mknod(const char *path, mode_t mode, dev_t dev)
-{
-#ifdef __NR_mknodat
-	return my_syscall4(__NR_mknodat, AT_FDCWD, path, mode, dev);
-#elif defined(__NR_mknod)
-	return my_syscall3(__NR_mknod, path, mode, dev);
-#else
-#error Neither __NR_mknodat nor __NR_mknod defined, cannot implement sys_mknod()
-#endif
-}
-
-static __attribute__((unused))
-int sys_mount(const char *src, const char *tgt, const char *fst,
-	      unsigned long flags, const void *data)
-{
-	return my_syscall5(__NR_mount, src, tgt, fst, flags, data);
-}
-
-static __attribute__((unused))
-int sys_open(const char *path, int flags, mode_t mode)
-{
-#ifdef __NR_openat
-	return my_syscall4(__NR_openat, AT_FDCWD, path, flags, mode);
-#elif defined(__NR_open)
-	return my_syscall3(__NR_open, path, flags, mode);
-#else
-#error Neither __NR_openat nor __NR_open defined, cannot implement sys_open()
-#endif
-}
-
-static __attribute__((unused))
-int sys_pivot_root(const char *new, const char *old)
-{
-	return my_syscall2(__NR_pivot_root, new, old);
-}
-
-static __attribute__((unused))
-int sys_poll(struct pollfd *fds, int nfds, int timeout)
-{
-#if defined(__NR_ppoll)
-	struct timespec t;
-
-	if (timeout >= 0) {
-		t.tv_sec  = timeout / 1000;
-		t.tv_nsec = (timeout % 1000) * 1000000;
-	}
-	return my_syscall4(__NR_ppoll, fds, nfds, (timeout >= 0) ? &t : NULL, NULL);
-#elif defined(__NR_poll)
-	return my_syscall3(__NR_poll, fds, nfds, timeout);
-#else
-#error Neither __NR_ppoll nor __NR_poll defined, cannot implement sys_poll()
-#endif
-}
-
-static __attribute__((unused))
-ssize_t sys_read(int fd, void *buf, size_t count)
-{
-	return my_syscall3(__NR_read, fd, buf, count);
-}
-
-static __attribute__((unused))
-ssize_t sys_reboot(int magic1, int magic2, int cmd, void *arg)
-{
-	return my_syscall4(__NR_reboot, magic1, magic2, cmd, arg);
-}
-
-static __attribute__((unused))
-int sys_sched_yield(void)
-{
-	return my_syscall0(__NR_sched_yield);
-}
-
-static __attribute__((unused))
-int sys_select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout)
-{
-#if defined(__ARCH_WANT_SYS_OLD_SELECT) && !defined(__NR__newselect)
-	struct sel_arg_struct {
-		unsigned long n;
-		fd_set *r, *w, *e;
-		struct timeval *t;
-	} arg = { .n = nfds, .r = rfds, .w = wfds, .e = efds, .t = timeout };
-	return my_syscall1(__NR_select, &arg);
-#elif defined(__ARCH_WANT_SYS_PSELECT6) && defined(__NR_pselect6)
-	struct timespec t;
-
-	if (timeout) {
-		t.tv_sec  = timeout->tv_sec;
-		t.tv_nsec = timeout->tv_usec * 1000;
-	}
-	return my_syscall6(__NR_pselect6, nfds, rfds, wfds, efds, timeout ? &t : NULL, NULL);
-#elif defined(__NR__newselect) || defined(__NR_select)
-#ifndef __NR__newselect
-#define __NR__newselect __NR_select
-#endif
-	return my_syscall5(__NR__newselect, nfds, rfds, wfds, efds, timeout);
-#else
-#error None of __NR_select, __NR_pselect6, nor __NR__newselect defined, cannot implement sys_select()
-#endif
-}
-
-static __attribute__((unused))
-int sys_setpgid(pid_t pid, pid_t pgid)
-{
-	return my_syscall2(__NR_setpgid, pid, pgid);
-}
-
-static __attribute__((unused))
-pid_t sys_setsid(void)
-{
-	return my_syscall0(__NR_setsid);
-}
-
-static __attribute__((unused))
-int sys_stat(const char *path, struct stat *buf)
-{
-	struct sys_stat_struct stat;
-	long ret;
-
-#ifdef __NR_newfstatat
-	/* only solution for arm64 */
-	ret = my_syscall4(__NR_newfstatat, AT_FDCWD, path, &stat, 0);
-#elif defined(__NR_stat)
-	ret = my_syscall2(__NR_stat, path, &stat);
-#else
-#error Neither __NR_newfstatat nor __NR_stat defined, cannot implement sys_stat()
-#endif
-	buf->st_dev     = stat.st_dev;
-	buf->st_ino     = stat.st_ino;
-	buf->st_mode    = stat.st_mode;
-	buf->st_nlink   = stat.st_nlink;
-	buf->st_uid     = stat.st_uid;
-	buf->st_gid     = stat.st_gid;
-	buf->st_rdev    = stat.st_rdev;
-	buf->st_size    = stat.st_size;
-	buf->st_blksize = stat.st_blksize;
-	buf->st_blocks  = stat.st_blocks;
-	buf->st_atime   = stat.st_atime;
-	buf->st_mtime   = stat.st_mtime;
-	buf->st_ctime   = stat.st_ctime;
-	return ret;
-}
-
-
-static __attribute__((unused))
-int sys_symlink(const char *old, const char *new)
-{
-#ifdef __NR_symlinkat
-	return my_syscall3(__NR_symlinkat, old, AT_FDCWD, new);
-#elif defined(__NR_symlink)
-	return my_syscall2(__NR_symlink, old, new);
-#else
-#error Neither __NR_symlinkat nor __NR_symlink defined, cannot implement sys_symlink()
-#endif
-}
-
-static __attribute__((unused))
-mode_t sys_umask(mode_t mode)
-{
-	return my_syscall1(__NR_umask, mode);
-}
-
-static __attribute__((unused))
-int sys_umount2(const char *path, int flags)
-{
-	return my_syscall2(__NR_umount2, path, flags);
-}
-
-static __attribute__((unused))
-int sys_unlink(const char *path)
-{
-#ifdef __NR_unlinkat
-	return my_syscall3(__NR_unlinkat, AT_FDCWD, path, 0);
-#elif defined(__NR_unlink)
-	return my_syscall1(__NR_unlink, path);
-#else
-#error Neither __NR_unlinkat nor __NR_unlink defined, cannot implement sys_unlink()
-#endif
-}
-
-static __attribute__((unused))
-pid_t sys_wait4(pid_t pid, int *status, int options, struct rusage *rusage)
-{
-	return my_syscall4(__NR_wait4, pid, status, options, rusage);
-}
-
-static __attribute__((unused))
-pid_t sys_waitpid(pid_t pid, int *status, int options)
-{
-	return sys_wait4(pid, status, options, 0);
-}
-
-static __attribute__((unused))
-pid_t sys_wait(int *status)
-{
-	return sys_waitpid(-1, status, 0);
-}
-
-static __attribute__((unused))
-ssize_t sys_write(int fd, const void *buf, size_t count)
-{
-	return my_syscall3(__NR_write, fd, buf, count);
-}
-
-
-/* Below are the libc-compatible syscalls which return x or -1 and set errno.
- * They rely on the functions above. Similarly they're marked static so that it
- * is possible to assign pointers to them if needed.
- */
-
-static __attribute__((unused))
-int brk(void *addr)
-{
-	void *ret = sys_brk(addr);
-
-	if (!ret) {
-		SET_ERRNO(ENOMEM);
-		return -1;
-	}
-	return 0;
-}
-
-static __attribute__((noreturn,unused))
-void exit(int status)
-{
-	sys_exit(status);
-}
-
-static __attribute__((unused))
-int chdir(const char *path)
-{
-	int ret = sys_chdir(path);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int chmod(const char *path, mode_t mode)
-{
-	int ret = sys_chmod(path, mode);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int chown(const char *path, uid_t owner, gid_t group)
-{
-	int ret = sys_chown(path, owner, group);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int chroot(const char *path)
-{
-	int ret = sys_chroot(path);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int close(int fd)
-{
-	int ret = sys_close(fd);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int dup(int fd)
-{
-	int ret = sys_dup(fd);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int dup2(int old, int new)
-{
-	int ret = sys_dup2(old, new);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-#ifdef __NR_dup3
-static __attribute__((unused))
-int dup3(int old, int new, int flags)
-{
-	int ret = sys_dup3(old, new, flags);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-#endif
-
-static __attribute__((unused))
-int execve(const char *filename, char *const argv[], char *const envp[])
-{
-	int ret = sys_execve(filename, argv, envp);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-pid_t fork(void)
-{
-	pid_t ret = sys_fork();
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int fsync(int fd)
-{
-	int ret = sys_fsync(fd);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int getdents64(int fd, struct linux_dirent64 *dirp, int count)
-{
-	int ret = sys_getdents64(fd, dirp, count);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-pid_t getpgid(pid_t pid)
-{
-	pid_t ret = sys_getpgid(pid);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-pid_t getpgrp(void)
-{
-	pid_t ret = sys_getpgrp();
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-pid_t getpid(void)
-{
-	pid_t ret = sys_getpid();
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-pid_t gettid(void)
-{
-	pid_t ret = sys_gettid();
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int gettimeofday(struct timeval *tv, struct timezone *tz)
-{
-	int ret = sys_gettimeofday(tv, tz);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int ioctl(int fd, unsigned long req, void *value)
-{
-	int ret = sys_ioctl(fd, req, value);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int kill(pid_t pid, int signal)
-{
-	int ret = sys_kill(pid, signal);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int link(const char *old, const char *new)
-{
-	int ret = sys_link(old, new);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-off_t lseek(int fd, off_t offset, int whence)
-{
-	off_t ret = sys_lseek(fd, offset, whence);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int mkdir(const char *path, mode_t mode)
-{
-	int ret = sys_mkdir(path, mode);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int mknod(const char *path, mode_t mode, dev_t dev)
-{
-	int ret = sys_mknod(path, mode, dev);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int mount(const char *src, const char *tgt,
-	  const char *fst, unsigned long flags,
-	  const void *data)
-{
-	int ret = sys_mount(src, tgt, fst, flags, data);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int open(const char *path, int flags, mode_t mode)
-{
-	int ret = sys_open(path, flags, mode);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int pivot_root(const char *new, const char *old)
-{
-	int ret = sys_pivot_root(new, old);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int poll(struct pollfd *fds, int nfds, int timeout)
-{
-	int ret = sys_poll(fds, nfds, timeout);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-ssize_t read(int fd, void *buf, size_t count)
-{
-	ssize_t ret = sys_read(fd, buf, count);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int reboot(int cmd)
-{
-	int ret = sys_reboot(LINUX_REBOOT_MAGIC1, LINUX_REBOOT_MAGIC2, cmd, 0);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-void *sbrk(intptr_t inc)
-{
-	void *ret;
-
-	/* first call to find current end */
-	if ((ret = sys_brk(0)) && (sys_brk(ret + inc) == ret + inc))
-		return ret + inc;
-
-	SET_ERRNO(ENOMEM);
-	return (void *)-1;
-}
-
-static __attribute__((unused))
-int sched_yield(void)
-{
-	int ret = sys_sched_yield();
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout)
-{
-	int ret = sys_select(nfds, rfds, wfds, efds, timeout);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int setpgid(pid_t pid, pid_t pgid)
-{
-	int ret = sys_setpgid(pid, pgid);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-pid_t setsid(void)
-{
-	pid_t ret = sys_setsid();
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-unsigned int sleep(unsigned int seconds)
-{
-	struct timeval my_timeval = { seconds, 0 };
-
-	if (sys_select(0, 0, 0, 0, &my_timeval) < 0)
-		return my_timeval.tv_sec + !!my_timeval.tv_usec;
-	else
-		return 0;
-}
-
-static __attribute__((unused))
-int msleep(unsigned int msecs)
-{
-	struct timeval my_timeval = { msecs / 1000, (msecs % 1000) * 1000 };
-
-	if (sys_select(0, 0, 0, 0, &my_timeval) < 0)
-		return (my_timeval.tv_sec * 1000) +
-			(my_timeval.tv_usec / 1000) +
-			!!(my_timeval.tv_usec % 1000);
-	else
-		return 0;
-}
-
-static __attribute__((unused))
-int stat(const char *path, struct stat *buf)
-{
-	int ret = sys_stat(path, buf);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int symlink(const char *old, const char *new)
-{
-	int ret = sys_symlink(old, new);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int tcsetpgrp(int fd, pid_t pid)
-{
-	return ioctl(fd, TIOCSPGRP, &pid);
-}
-
-static __attribute__((unused))
-mode_t umask(mode_t mode)
-{
-	return sys_umask(mode);
-}
-
-static __attribute__((unused))
-int umount2(const char *path, int flags)
-{
-	int ret = sys_umount2(path, flags);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-int unlink(const char *path)
-{
-	int ret = sys_unlink(path);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-pid_t wait4(pid_t pid, int *status, int options, struct rusage *rusage)
-{
-	pid_t ret = sys_wait4(pid, status, options, rusage);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-pid_t waitpid(pid_t pid, int *status, int options)
-{
-	pid_t ret = sys_waitpid(pid, status, options);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-pid_t wait(int *status)
-{
-	pid_t ret = sys_wait(status);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-ssize_t write(int fd, const void *buf, size_t count)
-{
-	ssize_t ret = sys_write(fd, buf, count);
-
-	if (ret < 0) {
-		SET_ERRNO(-ret);
-		ret = -1;
-	}
-	return ret;
-}
-
-/* some size-optimized reimplementations of a few common str* and mem*
- * functions. They're marked static, except memcpy() and raise() which are used
- * by libgcc on ARM, so they are marked weak instead in order not to cause an
- * error when building a program made of multiple files (not recommended).
- */
-
-static __attribute__((unused))
-void *memmove(void *dst, const void *src, size_t len)
-{
-	ssize_t pos = (dst <= src) ? -1 : (long)len;
-	void *ret = dst;
-
-	while (len--) {
-		pos += (dst <= src) ? 1 : -1;
-		((char *)dst)[pos] = ((char *)src)[pos];
-	}
-	return ret;
-}
-
-static __attribute__((unused))
-void *memset(void *dst, int b, size_t len)
-{
-	char *p = dst;
-
-	while (len--)
-		*(p++) = b;
-	return dst;
-}
-
-static __attribute__((unused))
-int memcmp(const void *s1, const void *s2, size_t n)
-{
-	size_t ofs = 0;
-	char c1 = 0;
-
-	while (ofs < n && !(c1 = ((char *)s1)[ofs] - ((char *)s2)[ofs])) {
-		ofs++;
-	}
-	return c1;
-}
-
-static __attribute__((unused))
-char *strcpy(char *dst, const char *src)
-{
-	char *ret = dst;
-
-	while ((*dst++ = *src++));
-	return ret;
-}
-
-static __attribute__((unused))
-char *strchr(const char *s, int c)
-{
-	while (*s) {
-		if (*s == (char)c)
-			return (char *)s;
-		s++;
-	}
-	return NULL;
-}
-
-static __attribute__((unused))
-char *strrchr(const char *s, int c)
-{
-	const char *ret = NULL;
-
-	while (*s) {
-		if (*s == (char)c)
-			ret = s;
-		s++;
-	}
-	return (char *)ret;
-}
-
-static __attribute__((unused))
-size_t nolibc_strlen(const char *str)
-{
-	size_t len;
-
-	for (len = 0; str[len]; len++);
-	return len;
-}
-
-#define strlen(str) ({                          \
-	__builtin_constant_p((str)) ?           \
-		__builtin_strlen((str)) :       \
-		nolibc_strlen((str));           \
-})
-
-static __attribute__((unused))
-int isdigit(int c)
-{
-	return (unsigned int)(c - '0') <= 9;
-}
-
-static __attribute__((unused))
-long atol(const char *s)
-{
-	unsigned long ret = 0;
-	unsigned long d;
-	int neg = 0;
-
-	if (*s == '-') {
-		neg = 1;
-		s++;
-	}
-
-	while (1) {
-		d = (*s++) - '0';
-		if (d > 9)
-			break;
-		ret *= 10;
-		ret += d;
-	}
-
-	return neg ? -ret : ret;
-}
-
-static __attribute__((unused))
-int atoi(const char *s)
-{
-	return atol(s);
-}
-
-static __attribute__((unused))
-const char *ltoa(long in)
-{
-	/* large enough for -9223372036854775808 */
-	static char buffer[21];
-	char       *pos = buffer + sizeof(buffer) - 1;
-	int         neg = in < 0;
-	unsigned long n = neg ? -in : in;
-
-	*pos-- = '\0';
-	do {
-		*pos-- = '0' + n % 10;
-		n /= 10;
-		if (pos < buffer)
-			return pos + 1;
-	} while (n);
-
-	if (neg)
-		*pos-- = '-';
-	return pos + 1;
-}
-
-__attribute__((weak,unused))
-void *memcpy(void *dst, const void *src, size_t len)
-{
-	return memmove(dst, src, len);
-}
-
-/* needed by libgcc for divide by zero */
-__attribute__((weak,unused))
-int raise(int signal)
-{
-	return kill(getpid(), signal);
-}
-
-/* Here come a few helper functions */
-
-static __attribute__((unused))
-void FD_ZERO(fd_set *set)
-{
-	memset(set, 0, sizeof(*set));
-}
-
-static __attribute__((unused))
-void FD_SET(int fd, fd_set *set)
-{
-	if (fd < 0 || fd >= FD_SETSIZE)
-		return;
-	set->fd32[fd / 32] |= 1 << (fd & 31);
-}
-
-/* WARNING, it only deals with the 4096 first majors and 256 first minors */
-static __attribute__((unused))
-dev_t makedev(unsigned int major, unsigned int minor)
-{
-	return ((major & 0xfff) << 8) | (minor & 0xff);
-}
+#endif /* _NOLIBC_H */
diff --git a/tools/include/nolibc/signal.h b/tools/include/nolibc/signal.h
new file mode 100644
index 000000000000..ef47e71e2be3
--- /dev/null
+++ b/tools/include/nolibc/signal.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * signal function definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_SIGNAL_H
+#define _NOLIBC_SIGNAL_H
+
+#include "std.h"
+#include "arch.h"
+#include "types.h"
+#include "sys.h"
+
+/* This one is not marked static as it's needed by libgcc for divide by zero */
+__attribute__((weak,unused,section(".text.nolibc_raise")))
+int raise(int signal)
+{
+	return sys_kill(sys_getpid(), signal);
+}
+
+#endif /* _NOLIBC_SIGNAL_H */
diff --git a/tools/include/nolibc/std.h b/tools/include/nolibc/std.h
new file mode 100644
index 000000000000..1747ae125392
--- /dev/null
+++ b/tools/include/nolibc/std.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Standard definitions and types for NOLIBC
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_STD_H
+#define _NOLIBC_STD_H
+
+/* Declare a few quite common macros and types that usually are in stdlib.h,
+ * stdint.h, ctype.h, unistd.h and a few other common locations. Please place
+ * integer type definitions and generic macros here, but avoid OS-specific and
+ * syscall-specific stuff, as this file is expected to be included very early.
+ */
+
+/* note: may already be defined */
+#ifndef NULL
+#define NULL ((void *)0)
+#endif
+
+/* stdint types */
+typedef unsigned char       uint8_t;
+typedef   signed char        int8_t;
+typedef unsigned short     uint16_t;
+typedef   signed short      int16_t;
+typedef unsigned int       uint32_t;
+typedef   signed int        int32_t;
+typedef unsigned long long uint64_t;
+typedef   signed long long  int64_t;
+typedef unsigned long        size_t;
+typedef   signed long       ssize_t;
+typedef unsigned long     uintptr_t;
+typedef   signed long      intptr_t;
+typedef   signed long     ptrdiff_t;
+
+/* those are commonly provided by sys/types.h */
+typedef unsigned int          dev_t;
+typedef unsigned long         ino_t;
+typedef unsigned int         mode_t;
+typedef   signed int          pid_t;
+typedef unsigned int          uid_t;
+typedef unsigned int          gid_t;
+typedef unsigned long       nlink_t;
+typedef   signed long         off_t;
+typedef   signed long     blksize_t;
+typedef   signed long      blkcnt_t;
+typedef   signed long        time_t;
+
+#endif /* _NOLIBC_STD_H */
diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h
new file mode 100644
index 000000000000..15dedf8d0902
--- /dev/null
+++ b/tools/include/nolibc/stdio.h
@@ -0,0 +1,306 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * minimal stdio function definitions for NOLIBC
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_STDIO_H
+#define _NOLIBC_STDIO_H
+
+#include <stdarg.h>
+
+#include "std.h"
+#include "arch.h"
+#include "errno.h"
+#include "types.h"
+#include "sys.h"
+#include "stdlib.h"
+#include "string.h"
+
+#ifndef EOF
+#define EOF (-1)
+#endif
+
+/* just define FILE as a non-empty type */
+typedef struct FILE {
+	char dummy[1];
+} FILE;
+
+/* We define the 3 common stdio files as constant invalid pointers that
+ * are easily recognized.
+ */
+static __attribute__((unused)) FILE* const stdin  = (FILE*)-3;
+static __attribute__((unused)) FILE* const stdout = (FILE*)-2;
+static __attribute__((unused)) FILE* const stderr = (FILE*)-1;
+
+/* getc(), fgetc(), getchar() */
+
+#define getc(stream) fgetc(stream)
+
+static __attribute__((unused))
+int fgetc(FILE* stream)
+{
+	unsigned char ch;
+	int fd;
+
+	if (stream < stdin || stream > stderr)
+		return EOF;
+
+	fd = 3 + (long)stream;
+
+	if (read(fd, &ch, 1) <= 0)
+		return EOF;
+	return ch;
+}
+
+static __attribute__((unused))
+int getchar(void)
+{
+	return fgetc(stdin);
+}
+
+
+/* putc(), fputc(), putchar() */
+
+#define putc(c, stream) fputc(c, stream)
+
+static __attribute__((unused))
+int fputc(int c, FILE* stream)
+{
+	unsigned char ch = c;
+	int fd;
+
+	if (stream < stdin || stream > stderr)
+		return EOF;
+
+	fd = 3 + (long)stream;
+
+	if (write(fd, &ch, 1) <= 0)
+		return EOF;
+	return ch;
+}
+
+static __attribute__((unused))
+int putchar(int c)
+{
+	return fputc(c, stdout);
+}
+
+
+/* fwrite(), puts(), fputs(). Note that puts() emits '\n' but not fputs(). */
+
+/* internal fwrite()-like function which only takes a size and returns 0 on
+ * success or EOF on error. It automatically retries on short writes.
+ */
+static __attribute__((unused))
+int _fwrite(const void *buf, size_t size, FILE *stream)
+{
+	ssize_t ret;
+	int fd;
+
+	if (stream < stdin || stream > stderr)
+		return EOF;
+
+	fd = 3 + (long)stream;
+
+	while (size) {
+		ret = write(fd, buf, size);
+		if (ret <= 0)
+			return EOF;
+		size -= ret;
+		buf += ret;
+	}
+	return 0;
+}
+
+static __attribute__((unused))
+size_t fwrite(const void *s, size_t size, size_t nmemb, FILE *stream)
+{
+	size_t written;
+
+	for (written = 0; written < nmemb; written++) {
+		if (_fwrite(s, size, stream) != 0)
+			break;
+		s += size;
+	}
+	return written;
+}
+
+static __attribute__((unused))
+int fputs(const char *s, FILE *stream)
+{
+	return _fwrite(s, strlen(s), stream);
+}
+
+static __attribute__((unused))
+int puts(const char *s)
+{
+	if (fputs(s, stdout) == EOF)
+		return EOF;
+	return putchar('\n');
+}
+
+
+/* fgets() */
+static __attribute__((unused))
+char *fgets(char *s, int size, FILE *stream)
+{
+	int ofs;
+	int c;
+
+	for (ofs = 0; ofs + 1 < size;) {
+		c = fgetc(stream);
+		if (c == EOF)
+			break;
+		s[ofs++] = c;
+		if (c == '\n')
+			break;
+	}
+	if (ofs < size)
+		s[ofs] = 0;
+	return ofs ? s : NULL;
+}
+
+
+/* minimal vfprintf(). It supports the following formats:
+ *  - %[l*]{d,u,c,x,p}
+ *  - %s
+ *  - unknown modifiers are ignored.
+ */
+static __attribute__((unused))
+int vfprintf(FILE *stream, const char *fmt, va_list args)
+{
+	char escape, lpref, c;
+	unsigned long long v;
+	unsigned int written;
+	size_t len, ofs;
+	char tmpbuf[21];
+	const char *outstr;
+
+	written = ofs = escape = lpref = 0;
+	while (1) {
+		c = fmt[ofs++];
+
+		if (escape) {
+			/* we're in an escape sequence, ofs == 1 */
+			escape = 0;
+			if (c == 'c' || c == 'd' || c == 'u' || c == 'x' || c == 'p') {
+				char *out = tmpbuf;
+
+				if (c == 'p')
+					v = va_arg(args, unsigned long);
+				else if (lpref) {
+					if (lpref > 1)
+						v = va_arg(args, unsigned long long);
+					else
+						v = va_arg(args, unsigned long);
+				} else
+					v = va_arg(args, unsigned int);
+
+				if (c == 'd') {
+					/* sign-extend the value */
+					if (lpref == 0)
+						v = (long long)(int)v;
+					else if (lpref == 1)
+						v = (long long)(long)v;
+				}
+
+				switch (c) {
+				case 'c':
+					out[0] = v;
+					out[1] = 0;
+					break;
+				case 'd':
+					i64toa_r(v, out);
+					break;
+				case 'u':
+					u64toa_r(v, out);
+					break;
+				case 'p':
+					*(out++) = '0';
+					*(out++) = 'x';
+					/* fall through */
+				default: /* 'x' and 'p' above */
+					u64toh_r(v, out);
+					break;
+				}
+				outstr = tmpbuf;
+			}
+			else if (c == 's') {
+				outstr = va_arg(args, char *);
+				if (!outstr)
+					outstr="(null)";
+			}
+			else if (c == '%') {
+				/* queue it verbatim */
+				continue;
+			}
+			else {
+				/* modifiers or final 0 */
+				if (c == 'l') {
+					/* long format prefix, maintain the escape */
+					lpref++;
+				}
+				escape = 1;
+				goto do_escape;
+			}
+			len = strlen(outstr);
+			goto flush_str;
+		}
+
+		/* not an escape sequence */
+		if (c == 0 || c == '%') {
+			/* flush pending data on escape or end */
+			escape = 1;
+			lpref = 0;
+			outstr = fmt;
+			len = ofs - 1;
+		flush_str:
+			if (_fwrite(outstr, len, stream) != 0)
+				break;
+
+			written += len;
+		do_escape:
+			if (c == 0)
+				break;
+			fmt += ofs;
+			ofs = 0;
+			continue;
+		}
+
+		/* literal char, just queue it */
+	}
+	return written;
+}
+
+static __attribute__((unused))
+int fprintf(FILE *stream, const char *fmt, ...)
+{
+	va_list args;
+	int ret;
+
+	va_start(args, fmt);
+	ret = vfprintf(stream, fmt, args);
+	va_end(args);
+	return ret;
+}
+
+static __attribute__((unused))
+int printf(const char *fmt, ...)
+{
+	va_list args;
+	int ret;
+
+	va_start(args, fmt);
+	ret = vfprintf(stdout, fmt, args);
+	va_end(args);
+	return ret;
+}
+
+static __attribute__((unused))
+void perror(const char *msg)
+{
+	fprintf(stderr, "%s%serrno=%d\n", (msg && *msg) ? msg : "", (msg && *msg) ? ": " : "", errno);
+}
+
+#endif /* _NOLIBC_STDIO_H */
diff --git a/tools/include/nolibc/stdlib.h b/tools/include/nolibc/stdlib.h
new file mode 100644
index 000000000000..8fd32eaf8037
--- /dev/null
+++ b/tools/include/nolibc/stdlib.h
@@ -0,0 +1,423 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * stdlib function definitions for NOLIBC
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_STDLIB_H
+#define _NOLIBC_STDLIB_H
+
+#include "std.h"
+#include "arch.h"
+#include "types.h"
+#include "sys.h"
+#include "string.h"
+
+struct nolibc_heap {
+	size_t	len;
+	char	user_p[] __attribute__((__aligned__));
+};
+
+/* Buffer used to store int-to-ASCII conversions. Will only be implemented if
+ * any of the related functions is implemented. The area is large enough to
+ * store "18446744073709551615" or "-9223372036854775808" and the final zero.
+ */
+static __attribute__((unused)) char itoa_buffer[21];
+
+/*
+ * As much as possible, please keep functions alphabetically sorted.
+ */
+
+/* must be exported, as it's used by libgcc for various divide functions */
+__attribute__((weak,unused,noreturn,section(".text.nolibc_abort")))
+void abort(void)
+{
+	sys_kill(sys_getpid(), SIGABRT);
+	for (;;);
+}
+
+static __attribute__((unused))
+long atol(const char *s)
+{
+	unsigned long ret = 0;
+	unsigned long d;
+	int neg = 0;
+
+	if (*s == '-') {
+		neg = 1;
+		s++;
+	}
+
+	while (1) {
+		d = (*s++) - '0';
+		if (d > 9)
+			break;
+		ret *= 10;
+		ret += d;
+	}
+
+	return neg ? -ret : ret;
+}
+
+static __attribute__((unused))
+int atoi(const char *s)
+{
+	return atol(s);
+}
+
+static __attribute__((unused))
+void free(void *ptr)
+{
+	struct nolibc_heap *heap;
+
+	if (!ptr)
+		return;
+
+	heap = container_of(ptr, struct nolibc_heap, user_p);
+	munmap(heap, heap->len);
+}
+
+/* getenv() tries to find the environment variable named <name> in the
+ * environment array pointed to by global variable "environ" which must be
+ * declared as a char **, and must be terminated by a NULL (it is recommended
+ * to set this variable to the "envp" argument of main()). If the requested
+ * environment variable exists its value is returned otherwise NULL is
+ * returned. getenv() is forcefully inlined so that the reference to "environ"
+ * will be dropped if unused, even at -O0.
+ */
+static __attribute__((unused))
+char *_getenv(const char *name, char **environ)
+{
+	int idx, i;
+
+	if (environ) {
+		for (idx = 0; environ[idx]; idx++) {
+			for (i = 0; name[i] && name[i] == environ[idx][i];)
+				i++;
+			if (!name[i] && environ[idx][i] == '=')
+				return &environ[idx][i+1];
+		}
+	}
+	return NULL;
+}
+
+static inline __attribute__((unused,always_inline))
+char *getenv(const char *name)
+{
+	extern char **environ;
+	return _getenv(name, environ);
+}
+
+static __attribute__((unused))
+void *malloc(size_t len)
+{
+	struct nolibc_heap *heap;
+
+	/* Always allocate memory with size multiple of 4096. */
+	len  = sizeof(*heap) + len;
+	len  = (len + 4095UL) & -4096UL;
+	heap = mmap(NULL, len, PROT_READ|PROT_WRITE, MAP_ANONYMOUS|MAP_PRIVATE,
+		    -1, 0);
+	if (__builtin_expect(heap == MAP_FAILED, 0))
+		return NULL;
+
+	heap->len = len;
+	return heap->user_p;
+}
+
+static __attribute__((unused))
+void *calloc(size_t size, size_t nmemb)
+{
+	void *orig;
+	size_t res = 0;
+
+	if (__builtin_expect(__builtin_mul_overflow(nmemb, size, &res), 0)) {
+		SET_ERRNO(ENOMEM);
+		return NULL;
+	}
+
+	/*
+	 * No need to zero the heap, the MAP_ANONYMOUS in malloc()
+	 * already does it.
+	 */
+	return malloc(res);
+}
+
+static __attribute__((unused))
+void *realloc(void *old_ptr, size_t new_size)
+{
+	struct nolibc_heap *heap;
+	size_t user_p_len;
+	void *ret;
+
+	if (!old_ptr)
+		return malloc(new_size);
+
+	heap = container_of(old_ptr, struct nolibc_heap, user_p);
+	user_p_len = heap->len - sizeof(*heap);
+	/*
+	 * Don't realloc() if @user_p_len >= @new_size, this block of
+	 * memory is still enough to handle the @new_size. Just return
+	 * the same pointer.
+	 */
+	if (user_p_len >= new_size)
+		return old_ptr;
+
+	ret = malloc(new_size);
+	if (__builtin_expect(!ret, 0))
+		return NULL;
+
+	memcpy(ret, heap->user_p, heap->len);
+	munmap(heap, heap->len);
+	return ret;
+}
+
+/* Converts the unsigned long integer <in> to its hex representation into
+ * buffer <buffer>, which must be long enough to store the number and the
+ * trailing zero (17 bytes for "ffffffffffffffff" or 9 for "ffffffff"). The
+ * buffer is filled from the first byte, and the number of characters emitted
+ * (not counting the trailing zero) is returned. The function is constructed
+ * in a way to optimize the code size and avoid any divide that could add a
+ * dependency on large external functions.
+ */
+static __attribute__((unused))
+int utoh_r(unsigned long in, char *buffer)
+{
+	signed char pos = (~0UL > 0xfffffffful) ? 60 : 28;
+	int digits = 0;
+	int dig;
+
+	do {
+		dig = in >> pos;
+		in -= (uint64_t)dig << pos;
+		pos -= 4;
+		if (dig || digits || pos < 0) {
+			if (dig > 9)
+				dig += 'a' - '0' - 10;
+			buffer[digits++] = '0' + dig;
+		}
+	} while (pos >= 0);
+
+	buffer[digits] = 0;
+	return digits;
+}
+
+/* converts unsigned long <in> to an hex string using the static itoa_buffer
+ * and returns the pointer to that string.
+ */
+static inline __attribute__((unused))
+char *utoh(unsigned long in)
+{
+	utoh_r(in, itoa_buffer);
+	return itoa_buffer;
+}
+
+/* Converts the unsigned long integer <in> to its string representation into
+ * buffer <buffer>, which must be long enough to store the number and the
+ * trailing zero (21 bytes for 18446744073709551615 in 64-bit, 11 for
+ * 4294967295 in 32-bit). The buffer is filled from the first byte, and the
+ * number of characters emitted (not counting the trailing zero) is returned.
+ * The function is constructed in a way to optimize the code size and avoid
+ * any divide that could add a dependency on large external functions.
+ */
+static __attribute__((unused))
+int utoa_r(unsigned long in, char *buffer)
+{
+	unsigned long lim;
+	int digits = 0;
+	int pos = (~0UL > 0xfffffffful) ? 19 : 9;
+	int dig;
+
+	do {
+		for (dig = 0, lim = 1; dig < pos; dig++)
+			lim *= 10;
+
+		if (digits || in >= lim || !pos) {
+			for (dig = 0; in >= lim; dig++)
+				in -= lim;
+			buffer[digits++] = '0' + dig;
+		}
+	} while (pos--);
+
+	buffer[digits] = 0;
+	return digits;
+}
+
+/* Converts the signed long integer <in> to its string representation into
+ * buffer <buffer>, which must be long enough to store the number and the
+ * trailing zero (21 bytes for -9223372036854775808 in 64-bit, 12 for
+ * -2147483648 in 32-bit). The buffer is filled from the first byte, and the
+ * number of characters emitted (not counting the trailing zero) is returned.
+ */
+static __attribute__((unused))
+int itoa_r(long in, char *buffer)
+{
+	char *ptr = buffer;
+	int len = 0;
+
+	if (in < 0) {
+		in = -in;
+		*(ptr++) = '-';
+		len++;
+	}
+	len += utoa_r(in, ptr);
+	return len;
+}
+
+/* for historical compatibility, same as above but returns the pointer to the
+ * buffer.
+ */
+static inline __attribute__((unused))
+char *ltoa_r(long in, char *buffer)
+{
+	itoa_r(in, buffer);
+	return buffer;
+}
+
+/* converts long integer <in> to a string using the static itoa_buffer and
+ * returns the pointer to that string.
+ */
+static inline __attribute__((unused))
+char *itoa(long in)
+{
+	itoa_r(in, itoa_buffer);
+	return itoa_buffer;
+}
+
+/* converts long integer <in> to a string using the static itoa_buffer and
+ * returns the pointer to that string. Same as above, for compatibility.
+ */
+static inline __attribute__((unused))
+char *ltoa(long in)
+{
+	itoa_r(in, itoa_buffer);
+	return itoa_buffer;
+}
+
+/* converts unsigned long integer <in> to a string using the static itoa_buffer
+ * and returns the pointer to that string.
+ */
+static inline __attribute__((unused))
+char *utoa(unsigned long in)
+{
+	utoa_r(in, itoa_buffer);
+	return itoa_buffer;
+}
+
+/* Converts the unsigned 64-bit integer <in> to its hex representation into
+ * buffer <buffer>, which must be long enough to store the number and the
+ * trailing zero (17 bytes for "ffffffffffffffff"). The buffer is filled from
+ * the first byte, and the number of characters emitted (not counting the
+ * trailing zero) is returned. The function is constructed in a way to optimize
+ * the code size and avoid any divide that could add a dependency on large
+ * external functions.
+ */
+static __attribute__((unused))
+int u64toh_r(uint64_t in, char *buffer)
+{
+	signed char pos = 60;
+	int digits = 0;
+	int dig;
+
+	do {
+		if (sizeof(long) >= 8) {
+			dig = (in >> pos) & 0xF;
+		} else {
+			/* 32-bit platforms: avoid a 64-bit shift */
+			uint32_t d = (pos >= 32) ? (in >> 32) : in;
+			dig = (d >> (pos & 31)) & 0xF;
+		}
+		if (dig > 9)
+			dig += 'a' - '0' - 10;
+		pos -= 4;
+		if (dig || digits || pos < 0)
+			buffer[digits++] = '0' + dig;
+	} while (pos >= 0);
+
+	buffer[digits] = 0;
+	return digits;
+}
+
+/* converts uint64_t <in> to an hex string using the static itoa_buffer and
+ * returns the pointer to that string.
+ */
+static inline __attribute__((unused))
+char *u64toh(uint64_t in)
+{
+	u64toh_r(in, itoa_buffer);
+	return itoa_buffer;
+}
+
+/* Converts the unsigned 64-bit integer <in> to its string representation into
+ * buffer <buffer>, which must be long enough to store the number and the
+ * trailing zero (21 bytes for 18446744073709551615). The buffer is filled from
+ * the first byte, and the number of characters emitted (not counting the
+ * trailing zero) is returned. The function is constructed in a way to optimize
+ * the code size and avoid any divide that could add a dependency on large
+ * external functions.
+ */
+static __attribute__((unused))
+int u64toa_r(uint64_t in, char *buffer)
+{
+	unsigned long long lim;
+	int digits = 0;
+	int pos = 19; /* start with the highest possible digit */
+	int dig;
+
+	do {
+		for (dig = 0, lim = 1; dig < pos; dig++)
+			lim *= 10;
+
+		if (digits || in >= lim || !pos) {
+			for (dig = 0; in >= lim; dig++)
+				in -= lim;
+			buffer[digits++] = '0' + dig;
+		}
+	} while (pos--);
+
+	buffer[digits] = 0;
+	return digits;
+}
+
+/* Converts the signed 64-bit integer <in> to its string representation into
+ * buffer <buffer>, which must be long enough to store the number and the
+ * trailing zero (21 bytes for -9223372036854775808). The buffer is filled from
+ * the first byte, and the number of characters emitted (not counting the
+ * trailing zero) is returned.
+ */
+static __attribute__((unused))
+int i64toa_r(int64_t in, char *buffer)
+{
+	char *ptr = buffer;
+	int len = 0;
+
+	if (in < 0) {
+		in = -in;
+		*(ptr++) = '-';
+		len++;
+	}
+	len += u64toa_r(in, ptr);
+	return len;
+}
+
+/* converts int64_t <in> to a string using the static itoa_buffer and returns
+ * the pointer to that string.
+ */
+static inline __attribute__((unused))
+char *i64toa(int64_t in)
+{
+	i64toa_r(in, itoa_buffer);
+	return itoa_buffer;
+}
+
+/* converts uint64_t <in> to a string using the static itoa_buffer and returns
+ * the pointer to that string.
+ */
+static inline __attribute__((unused))
+char *u64toa(uint64_t in)
+{
+	u64toa_r(in, itoa_buffer);
+	return itoa_buffer;
+}
+
+#endif /* _NOLIBC_STDLIB_H */
diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h
new file mode 100644
index 000000000000..bef35bee9c44
--- /dev/null
+++ b/tools/include/nolibc/string.h
@@ -0,0 +1,285 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * string function definitions for NOLIBC
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_STRING_H
+#define _NOLIBC_STRING_H
+
+#include "std.h"
+
+static void *malloc(size_t len);
+
+/*
+ * As much as possible, please keep functions alphabetically sorted.
+ */
+
+static __attribute__((unused))
+int memcmp(const void *s1, const void *s2, size_t n)
+{
+	size_t ofs = 0;
+	char c1 = 0;
+
+	while (ofs < n && !(c1 = ((char *)s1)[ofs] - ((char *)s2)[ofs])) {
+		ofs++;
+	}
+	return c1;
+}
+
+static __attribute__((unused))
+void *_nolibc_memcpy_up(void *dst, const void *src, size_t len)
+{
+	size_t pos = 0;
+
+	while (pos < len) {
+		((char *)dst)[pos] = ((const char *)src)[pos];
+		pos++;
+	}
+	return dst;
+}
+
+static __attribute__((unused))
+void *_nolibc_memcpy_down(void *dst, const void *src, size_t len)
+{
+	while (len) {
+		len--;
+		((char *)dst)[len] = ((const char *)src)[len];
+	}
+	return dst;
+}
+
+/* might be ignored by the compiler without -ffreestanding, then found as
+ * missing.
+ */
+__attribute__((weak,unused,section(".text.nolibc_memmove")))
+void *memmove(void *dst, const void *src, size_t len)
+{
+	size_t dir, pos;
+
+	pos = len;
+	dir = -1;
+
+	if (dst < src) {
+		pos = -1;
+		dir = 1;
+	}
+
+	while (len) {
+		pos += dir;
+		((char *)dst)[pos] = ((const char *)src)[pos];
+		len--;
+	}
+	return dst;
+}
+
+/* must be exported, as it's used by libgcc on ARM */
+__attribute__((weak,unused,section(".text.nolibc_memcpy")))
+void *memcpy(void *dst, const void *src, size_t len)
+{
+	return _nolibc_memcpy_up(dst, src, len);
+}
+
+/* might be ignored by the compiler without -ffreestanding, then found as
+ * missing.
+ */
+__attribute__((weak,unused,section(".text.nolibc_memset")))
+void *memset(void *dst, int b, size_t len)
+{
+	char *p = dst;
+
+	while (len--)
+		*(p++) = b;
+	return dst;
+}
+
+static __attribute__((unused))
+char *strchr(const char *s, int c)
+{
+	while (*s) {
+		if (*s == (char)c)
+			return (char *)s;
+		s++;
+	}
+	return NULL;
+}
+
+static __attribute__((unused))
+int strcmp(const char *a, const char *b)
+{
+	unsigned int c;
+	int diff;
+
+	while (!(diff = (unsigned char)*a++ - (c = (unsigned char)*b++)) && c)
+		;
+	return diff;
+}
+
+static __attribute__((unused))
+char *strcpy(char *dst, const char *src)
+{
+	char *ret = dst;
+
+	while ((*dst++ = *src++));
+	return ret;
+}
+
+/* this function is only used with arguments that are not constants or when
+ * it's not known because optimizations are disabled.
+ */
+static __attribute__((unused))
+size_t nolibc_strlen(const char *str)
+{
+	size_t len;
+
+	for (len = 0; str[len]; len++);
+	return len;
+}
+
+/* do not trust __builtin_constant_p() at -O0, as clang will emit a test and
+ * the two branches, then will rely on an external definition of strlen().
+ */
+#if defined(__OPTIMIZE__)
+#define strlen(str) ({                          \
+	__builtin_constant_p((str)) ?           \
+		__builtin_strlen((str)) :       \
+		nolibc_strlen((str));           \
+})
+#else
+#define strlen(str) nolibc_strlen((str))
+#endif
+
+static __attribute__((unused))
+size_t strnlen(const char *str, size_t maxlen)
+{
+	size_t len;
+
+	for (len = 0; (len < maxlen) && str[len]; len++);
+	return len;
+}
+
+static __attribute__((unused))
+char *strdup(const char *str)
+{
+	size_t len;
+	char *ret;
+
+	len = strlen(str);
+	ret = malloc(len + 1);
+	if (__builtin_expect(ret != NULL, 1))
+		memcpy(ret, str, len + 1);
+
+	return ret;
+}
+
+static __attribute__((unused))
+char *strndup(const char *str, size_t maxlen)
+{
+	size_t len;
+	char *ret;
+
+	len = strnlen(str, maxlen);
+	ret = malloc(len + 1);
+	if (__builtin_expect(ret != NULL, 1)) {
+		memcpy(ret, str, len);
+		ret[len] = '\0';
+	}
+
+	return ret;
+}
+
+static __attribute__((unused))
+size_t strlcat(char *dst, const char *src, size_t size)
+{
+	size_t len;
+	char c;
+
+	for (len = 0; dst[len];	len++)
+		;
+
+	for (;;) {
+		c = *src;
+		if (len < size)
+			dst[len] = c;
+		if (!c)
+			break;
+		len++;
+		src++;
+	}
+
+	return len;
+}
+
+static __attribute__((unused))
+size_t strlcpy(char *dst, const char *src, size_t size)
+{
+	size_t len;
+	char c;
+
+	for (len = 0;;) {
+		c = src[len];
+		if (len < size)
+			dst[len] = c;
+		if (!c)
+			break;
+		len++;
+	}
+	return len;
+}
+
+static __attribute__((unused))
+char *strncat(char *dst, const char *src, size_t size)
+{
+	char *orig = dst;
+
+	while (*dst)
+		dst++;
+
+	while (size && (*dst = *src)) {
+		src++;
+		dst++;
+		size--;
+	}
+
+	*dst = 0;
+	return orig;
+}
+
+static __attribute__((unused))
+int strncmp(const char *a, const char *b, size_t size)
+{
+	unsigned int c;
+	int diff = 0;
+
+	while (size-- &&
+	       !(diff = (unsigned char)*a++ - (c = (unsigned char)*b++)) && c)
+		;
+
+	return diff;
+}
+
+static __attribute__((unused))
+char *strncpy(char *dst, const char *src, size_t size)
+{
+	size_t len;
+
+	for (len = 0; len < size; len++)
+		if ((dst[len] = *src))
+			src++;
+	return dst;
+}
+
+static __attribute__((unused))
+char *strrchr(const char *s, int c)
+{
+	const char *ret = NULL;
+
+	while (*s) {
+		if (*s == (char)c)
+			ret = s;
+		s++;
+	}
+	return (char *)ret;
+}
+
+#endif /* _NOLIBC_STRING_H */
diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h
new file mode 100644
index 000000000000..08491070387b
--- /dev/null
+++ b/tools/include/nolibc/sys.h
@@ -0,0 +1,1247 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Syscall definitions for NOLIBC (those in man(2))
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_SYS_H
+#define _NOLIBC_SYS_H
+
+#include <stdarg.h>
+#include "std.h"
+
+/* system includes */
+#include <asm/unistd.h>
+#include <asm/signal.h>  // for SIGCHLD
+#include <asm/ioctls.h>
+#include <asm/mman.h>
+#include <linux/fs.h>
+#include <linux/loop.h>
+#include <linux/time.h>
+
+#include "arch.h"
+#include "errno.h"
+#include "types.h"
+
+
+/* Functions in this file only describe syscalls. They're declared static so
+ * that the compiler usually decides to inline them while still being allowed
+ * to pass a pointer to one of their instances. Each syscall exists in two
+ * versions:
+ *   - the "internal" ones, which matches the raw syscall interface at the
+ *     kernel level, which may sometimes slightly differ from the documented
+ *     libc-level ones. For example most of them return either a valid value
+ *     or -errno. All of these are prefixed with "sys_". They may be called
+ *     by non-portable applications if desired.
+ *
+ *   - the "exported" ones, whose interface must closely match the one
+ *     documented in man(2), that applications are supposed to expect. These
+ *     ones rely on the internal ones, and set errno.
+ *
+ * Each syscall will be defined with the two functions, sorted in alphabetical
+ * order applied to the exported names.
+ *
+ * In case of doubt about the relevance of a function here, only those which
+ * set errno should be defined here. Wrappers like those appearing in man(3)
+ * should not be placed here.
+ */
+
+
+/*
+ * int brk(void *addr);
+ * void *sbrk(intptr_t inc)
+ */
+
+static __attribute__((unused))
+void *sys_brk(void *addr)
+{
+	return (void *)my_syscall1(__NR_brk, addr);
+}
+
+static __attribute__((unused))
+int brk(void *addr)
+{
+	void *ret = sys_brk(addr);
+
+	if (!ret) {
+		SET_ERRNO(ENOMEM);
+		return -1;
+	}
+	return 0;
+}
+
+static __attribute__((unused))
+void *sbrk(intptr_t inc)
+{
+	void *ret;
+
+	/* first call to find current end */
+	if ((ret = sys_brk(0)) && (sys_brk(ret + inc) == ret + inc))
+		return ret + inc;
+
+	SET_ERRNO(ENOMEM);
+	return (void *)-1;
+}
+
+
+/*
+ * int chdir(const char *path);
+ */
+
+static __attribute__((unused))
+int sys_chdir(const char *path)
+{
+	return my_syscall1(__NR_chdir, path);
+}
+
+static __attribute__((unused))
+int chdir(const char *path)
+{
+	int ret = sys_chdir(path);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int chmod(const char *path, mode_t mode);
+ */
+
+static __attribute__((unused))
+int sys_chmod(const char *path, mode_t mode)
+{
+#ifdef __NR_fchmodat
+	return my_syscall4(__NR_fchmodat, AT_FDCWD, path, mode, 0);
+#elif defined(__NR_chmod)
+	return my_syscall2(__NR_chmod, path, mode);
+#else
+#error Neither __NR_fchmodat nor __NR_chmod defined, cannot implement sys_chmod()
+#endif
+}
+
+static __attribute__((unused))
+int chmod(const char *path, mode_t mode)
+{
+	int ret = sys_chmod(path, mode);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int chown(const char *path, uid_t owner, gid_t group);
+ */
+
+static __attribute__((unused))
+int sys_chown(const char *path, uid_t owner, gid_t group)
+{
+#ifdef __NR_fchownat
+	return my_syscall5(__NR_fchownat, AT_FDCWD, path, owner, group, 0);
+#elif defined(__NR_chown)
+	return my_syscall3(__NR_chown, path, owner, group);
+#else
+#error Neither __NR_fchownat nor __NR_chown defined, cannot implement sys_chown()
+#endif
+}
+
+static __attribute__((unused))
+int chown(const char *path, uid_t owner, gid_t group)
+{
+	int ret = sys_chown(path, owner, group);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int chroot(const char *path);
+ */
+
+static __attribute__((unused))
+int sys_chroot(const char *path)
+{
+	return my_syscall1(__NR_chroot, path);
+}
+
+static __attribute__((unused))
+int chroot(const char *path)
+{
+	int ret = sys_chroot(path);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int close(int fd);
+ */
+
+static __attribute__((unused))
+int sys_close(int fd)
+{
+	return my_syscall1(__NR_close, fd);
+}
+
+static __attribute__((unused))
+int close(int fd)
+{
+	int ret = sys_close(fd);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int dup(int fd);
+ */
+
+static __attribute__((unused))
+int sys_dup(int fd)
+{
+	return my_syscall1(__NR_dup, fd);
+}
+
+static __attribute__((unused))
+int dup(int fd)
+{
+	int ret = sys_dup(fd);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int dup2(int old, int new);
+ */
+
+static __attribute__((unused))
+int sys_dup2(int old, int new)
+{
+#ifdef __NR_dup3
+	return my_syscall3(__NR_dup3, old, new, 0);
+#elif defined(__NR_dup2)
+	return my_syscall2(__NR_dup2, old, new);
+#else
+#error Neither __NR_dup3 nor __NR_dup2 defined, cannot implement sys_dup2()
+#endif
+}
+
+static __attribute__((unused))
+int dup2(int old, int new)
+{
+	int ret = sys_dup2(old, new);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int dup3(int old, int new, int flags);
+ */
+
+#ifdef __NR_dup3
+static __attribute__((unused))
+int sys_dup3(int old, int new, int flags)
+{
+	return my_syscall3(__NR_dup3, old, new, flags);
+}
+
+static __attribute__((unused))
+int dup3(int old, int new, int flags)
+{
+	int ret = sys_dup3(old, new, flags);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+#endif
+
+
+/*
+ * int execve(const char *filename, char *const argv[], char *const envp[]);
+ */
+
+static __attribute__((unused))
+int sys_execve(const char *filename, char *const argv[], char *const envp[])
+{
+	return my_syscall3(__NR_execve, filename, argv, envp);
+}
+
+static __attribute__((unused))
+int execve(const char *filename, char *const argv[], char *const envp[])
+{
+	int ret = sys_execve(filename, argv, envp);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * void exit(int status);
+ */
+
+static __attribute__((noreturn,unused))
+void sys_exit(int status)
+{
+	my_syscall1(__NR_exit, status & 255);
+	while(1); // shut the "noreturn" warnings.
+}
+
+static __attribute__((noreturn,unused))
+void exit(int status)
+{
+	sys_exit(status);
+}
+
+
+/*
+ * pid_t fork(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_fork(void)
+{
+#ifdef __NR_clone
+	/* note: some archs only have clone() and not fork(). Different archs
+	 * have a different API, but most archs have the flags on first arg and
+	 * will not use the rest with no other flag.
+	 */
+	return my_syscall5(__NR_clone, SIGCHLD, 0, 0, 0, 0);
+#elif defined(__NR_fork)
+	return my_syscall0(__NR_fork);
+#else
+#error Neither __NR_clone nor __NR_fork defined, cannot implement sys_fork()
+#endif
+}
+
+static __attribute__((unused))
+pid_t fork(void)
+{
+	pid_t ret = sys_fork();
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int fsync(int fd);
+ */
+
+static __attribute__((unused))
+int sys_fsync(int fd)
+{
+	return my_syscall1(__NR_fsync, fd);
+}
+
+static __attribute__((unused))
+int fsync(int fd)
+{
+	int ret = sys_fsync(fd);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int getdents64(int fd, struct linux_dirent64 *dirp, int count);
+ */
+
+static __attribute__((unused))
+int sys_getdents64(int fd, struct linux_dirent64 *dirp, int count)
+{
+	return my_syscall3(__NR_getdents64, fd, dirp, count);
+}
+
+static __attribute__((unused))
+int getdents64(int fd, struct linux_dirent64 *dirp, int count)
+{
+	int ret = sys_getdents64(fd, dirp, count);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * pid_t getpgid(pid_t pid);
+ */
+
+static __attribute__((unused))
+pid_t sys_getpgid(pid_t pid)
+{
+	return my_syscall1(__NR_getpgid, pid);
+}
+
+static __attribute__((unused))
+pid_t getpgid(pid_t pid)
+{
+	pid_t ret = sys_getpgid(pid);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * pid_t getpgrp(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_getpgrp(void)
+{
+	return sys_getpgid(0);
+}
+
+static __attribute__((unused))
+pid_t getpgrp(void)
+{
+	return sys_getpgrp();
+}
+
+
+/*
+ * pid_t getpid(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_getpid(void)
+{
+	return my_syscall0(__NR_getpid);
+}
+
+static __attribute__((unused))
+pid_t getpid(void)
+{
+	return sys_getpid();
+}
+
+
+/*
+ * pid_t getppid(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_getppid(void)
+{
+	return my_syscall0(__NR_getppid);
+}
+
+static __attribute__((unused))
+pid_t getppid(void)
+{
+	return sys_getppid();
+}
+
+
+/*
+ * pid_t gettid(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_gettid(void)
+{
+	return my_syscall0(__NR_gettid);
+}
+
+static __attribute__((unused))
+pid_t gettid(void)
+{
+	return sys_gettid();
+}
+
+
+/*
+ * int gettimeofday(struct timeval *tv, struct timezone *tz);
+ */
+
+static __attribute__((unused))
+int sys_gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+	return my_syscall2(__NR_gettimeofday, tv, tz);
+}
+
+static __attribute__((unused))
+int gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+	int ret = sys_gettimeofday(tv, tz);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int ioctl(int fd, unsigned long req, void *value);
+ */
+
+static __attribute__((unused))
+int sys_ioctl(int fd, unsigned long req, void *value)
+{
+	return my_syscall3(__NR_ioctl, fd, req, value);
+}
+
+static __attribute__((unused))
+int ioctl(int fd, unsigned long req, void *value)
+{
+	int ret = sys_ioctl(fd, req, value);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+/*
+ * int kill(pid_t pid, int signal);
+ */
+
+static __attribute__((unused))
+int sys_kill(pid_t pid, int signal)
+{
+	return my_syscall2(__NR_kill, pid, signal);
+}
+
+static __attribute__((unused))
+int kill(pid_t pid, int signal)
+{
+	int ret = sys_kill(pid, signal);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int link(const char *old, const char *new);
+ */
+
+static __attribute__((unused))
+int sys_link(const char *old, const char *new)
+{
+#ifdef __NR_linkat
+	return my_syscall5(__NR_linkat, AT_FDCWD, old, AT_FDCWD, new, 0);
+#elif defined(__NR_link)
+	return my_syscall2(__NR_link, old, new);
+#else
+#error Neither __NR_linkat nor __NR_link defined, cannot implement sys_link()
+#endif
+}
+
+static __attribute__((unused))
+int link(const char *old, const char *new)
+{
+	int ret = sys_link(old, new);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * off_t lseek(int fd, off_t offset, int whence);
+ */
+
+static __attribute__((unused))
+off_t sys_lseek(int fd, off_t offset, int whence)
+{
+	return my_syscall3(__NR_lseek, fd, offset, whence);
+}
+
+static __attribute__((unused))
+off_t lseek(int fd, off_t offset, int whence)
+{
+	off_t ret = sys_lseek(fd, offset, whence);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int mkdir(const char *path, mode_t mode);
+ */
+
+static __attribute__((unused))
+int sys_mkdir(const char *path, mode_t mode)
+{
+#ifdef __NR_mkdirat
+	return my_syscall3(__NR_mkdirat, AT_FDCWD, path, mode);
+#elif defined(__NR_mkdir)
+	return my_syscall2(__NR_mkdir, path, mode);
+#else
+#error Neither __NR_mkdirat nor __NR_mkdir defined, cannot implement sys_mkdir()
+#endif
+}
+
+static __attribute__((unused))
+int mkdir(const char *path, mode_t mode)
+{
+	int ret = sys_mkdir(path, mode);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int mknod(const char *path, mode_t mode, dev_t dev);
+ */
+
+static __attribute__((unused))
+long sys_mknod(const char *path, mode_t mode, dev_t dev)
+{
+#ifdef __NR_mknodat
+	return my_syscall4(__NR_mknodat, AT_FDCWD, path, mode, dev);
+#elif defined(__NR_mknod)
+	return my_syscall3(__NR_mknod, path, mode, dev);
+#else
+#error Neither __NR_mknodat nor __NR_mknod defined, cannot implement sys_mknod()
+#endif
+}
+
+static __attribute__((unused))
+int mknod(const char *path, mode_t mode, dev_t dev)
+{
+	int ret = sys_mknod(path, mode, dev);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+#ifndef MAP_SHARED
+#define MAP_SHARED		0x01	/* Share changes */
+#define MAP_PRIVATE		0x02	/* Changes are private */
+#define MAP_SHARED_VALIDATE	0x03	/* share + validate extension flags */
+#endif
+
+#ifndef MAP_FAILED
+#define MAP_FAILED ((void *)-1)
+#endif
+
+static __attribute__((unused))
+void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd,
+	       off_t offset)
+{
+#ifndef my_syscall6
+	/* Function not implemented. */
+	return -ENOSYS;
+#else
+
+	int n;
+
+#if defined(__i386__)
+	n = __NR_mmap2;
+	offset >>= 12;
+#else
+	n = __NR_mmap;
+#endif
+
+	return (void *)my_syscall6(n, addr, length, prot, flags, fd, offset);
+#endif
+}
+
+static __attribute__((unused))
+void *mmap(void *addr, size_t length, int prot, int flags, int fd, off_t offset)
+{
+	void *ret = sys_mmap(addr, length, prot, flags, fd, offset);
+
+	if ((unsigned long)ret >= -4095UL) {
+		SET_ERRNO(-(long)ret);
+		ret = MAP_FAILED;
+	}
+	return ret;
+}
+
+static __attribute__((unused))
+int sys_munmap(void *addr, size_t length)
+{
+	return my_syscall2(__NR_munmap, addr, length);
+}
+
+static __attribute__((unused))
+int munmap(void *addr, size_t length)
+{
+	int ret = sys_munmap(addr, length);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+/*
+ * int mount(const char *source, const char *target,
+ *           const char *fstype, unsigned long flags,
+ *           const void *data);
+ */
+static __attribute__((unused))
+int sys_mount(const char *src, const char *tgt, const char *fst,
+                     unsigned long flags, const void *data)
+{
+	return my_syscall5(__NR_mount, src, tgt, fst, flags, data);
+}
+
+static __attribute__((unused))
+int mount(const char *src, const char *tgt,
+          const char *fst, unsigned long flags,
+          const void *data)
+{
+	int ret = sys_mount(src, tgt, fst, flags, data);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int open(const char *path, int flags[, mode_t mode]);
+ */
+
+static __attribute__((unused))
+int sys_open(const char *path, int flags, mode_t mode)
+{
+#ifdef __NR_openat
+	return my_syscall4(__NR_openat, AT_FDCWD, path, flags, mode);
+#elif defined(__NR_open)
+	return my_syscall3(__NR_open, path, flags, mode);
+#else
+#error Neither __NR_openat nor __NR_open defined, cannot implement sys_open()
+#endif
+}
+
+static __attribute__((unused))
+int open(const char *path, int flags, ...)
+{
+	mode_t mode = 0;
+	int ret;
+
+	if (flags & O_CREAT) {
+		va_list args;
+
+		va_start(args, flags);
+		mode = va_arg(args, mode_t);
+		va_end(args);
+	}
+
+	ret = sys_open(path, flags, mode);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int pivot_root(const char *new, const char *old);
+ */
+
+static __attribute__((unused))
+int sys_pivot_root(const char *new, const char *old)
+{
+	return my_syscall2(__NR_pivot_root, new, old);
+}
+
+static __attribute__((unused))
+int pivot_root(const char *new, const char *old)
+{
+	int ret = sys_pivot_root(new, old);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int poll(struct pollfd *fds, int nfds, int timeout);
+ */
+
+static __attribute__((unused))
+int sys_poll(struct pollfd *fds, int nfds, int timeout)
+{
+#if defined(__NR_ppoll)
+	struct timespec t;
+
+	if (timeout >= 0) {
+		t.tv_sec  = timeout / 1000;
+		t.tv_nsec = (timeout % 1000) * 1000000;
+	}
+	return my_syscall4(__NR_ppoll, fds, nfds, (timeout >= 0) ? &t : NULL, NULL);
+#elif defined(__NR_poll)
+	return my_syscall3(__NR_poll, fds, nfds, timeout);
+#else
+#error Neither __NR_ppoll nor __NR_poll defined, cannot implement sys_poll()
+#endif
+}
+
+static __attribute__((unused))
+int poll(struct pollfd *fds, int nfds, int timeout)
+{
+	int ret = sys_poll(fds, nfds, timeout);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * ssize_t read(int fd, void *buf, size_t count);
+ */
+
+static __attribute__((unused))
+ssize_t sys_read(int fd, void *buf, size_t count)
+{
+	return my_syscall3(__NR_read, fd, buf, count);
+}
+
+static __attribute__((unused))
+ssize_t read(int fd, void *buf, size_t count)
+{
+	ssize_t ret = sys_read(fd, buf, count);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int reboot(int cmd);
+ * <cmd> is among LINUX_REBOOT_CMD_*
+ */
+
+static __attribute__((unused))
+ssize_t sys_reboot(int magic1, int magic2, int cmd, void *arg)
+{
+	return my_syscall4(__NR_reboot, magic1, magic2, cmd, arg);
+}
+
+static __attribute__((unused))
+int reboot(int cmd)
+{
+	int ret = sys_reboot(LINUX_REBOOT_MAGIC1, LINUX_REBOOT_MAGIC2, cmd, 0);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int sched_yield(void);
+ */
+
+static __attribute__((unused))
+int sys_sched_yield(void)
+{
+	return my_syscall0(__NR_sched_yield);
+}
+
+static __attribute__((unused))
+int sched_yield(void)
+{
+	int ret = sys_sched_yield();
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int select(int nfds, fd_set *read_fds, fd_set *write_fds,
+ *            fd_set *except_fds, struct timeval *timeout);
+ */
+
+static __attribute__((unused))
+int sys_select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout)
+{
+#if defined(__ARCH_WANT_SYS_OLD_SELECT) && !defined(__NR__newselect)
+	struct sel_arg_struct {
+		unsigned long n;
+		fd_set *r, *w, *e;
+		struct timeval *t;
+	} arg = { .n = nfds, .r = rfds, .w = wfds, .e = efds, .t = timeout };
+	return my_syscall1(__NR_select, &arg);
+#elif defined(__ARCH_WANT_SYS_PSELECT6) && defined(__NR_pselect6)
+	struct timespec t;
+
+	if (timeout) {
+		t.tv_sec  = timeout->tv_sec;
+		t.tv_nsec = timeout->tv_usec * 1000;
+	}
+	return my_syscall6(__NR_pselect6, nfds, rfds, wfds, efds, timeout ? &t : NULL, NULL);
+#elif defined(__NR__newselect) || defined(__NR_select)
+#ifndef __NR__newselect
+#define __NR__newselect __NR_select
+#endif
+	return my_syscall5(__NR__newselect, nfds, rfds, wfds, efds, timeout);
+#else
+#error None of __NR_select, __NR_pselect6, nor __NR__newselect defined, cannot implement sys_select()
+#endif
+}
+
+static __attribute__((unused))
+int select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout)
+{
+	int ret = sys_select(nfds, rfds, wfds, efds, timeout);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int setpgid(pid_t pid, pid_t pgid);
+ */
+
+static __attribute__((unused))
+int sys_setpgid(pid_t pid, pid_t pgid)
+{
+	return my_syscall2(__NR_setpgid, pid, pgid);
+}
+
+static __attribute__((unused))
+int setpgid(pid_t pid, pid_t pgid)
+{
+	int ret = sys_setpgid(pid, pgid);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * pid_t setsid(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_setsid(void)
+{
+	return my_syscall0(__NR_setsid);
+}
+
+static __attribute__((unused))
+pid_t setsid(void)
+{
+	pid_t ret = sys_setsid();
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int stat(const char *path, struct stat *buf);
+ * Warning: the struct stat's layout is arch-dependent.
+ */
+
+static __attribute__((unused))
+int sys_stat(const char *path, struct stat *buf)
+{
+	struct sys_stat_struct stat;
+	long ret;
+
+#ifdef __NR_newfstatat
+	/* only solution for arm64 */
+	ret = my_syscall4(__NR_newfstatat, AT_FDCWD, path, &stat, 0);
+#elif defined(__NR_stat)
+	ret = my_syscall2(__NR_stat, path, &stat);
+#else
+#error Neither __NR_newfstatat nor __NR_stat defined, cannot implement sys_stat()
+#endif
+	buf->st_dev     = stat.st_dev;
+	buf->st_ino     = stat.st_ino;
+	buf->st_mode    = stat.st_mode;
+	buf->st_nlink   = stat.st_nlink;
+	buf->st_uid     = stat.st_uid;
+	buf->st_gid     = stat.st_gid;
+	buf->st_rdev    = stat.st_rdev;
+	buf->st_size    = stat.st_size;
+	buf->st_blksize = stat.st_blksize;
+	buf->st_blocks  = stat.st_blocks;
+	buf->st_atime   = stat.st_atime;
+	buf->st_mtime   = stat.st_mtime;
+	buf->st_ctime   = stat.st_ctime;
+	return ret;
+}
+
+static __attribute__((unused))
+int stat(const char *path, struct stat *buf)
+{
+	int ret = sys_stat(path, buf);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int symlink(const char *old, const char *new);
+ */
+
+static __attribute__((unused))
+int sys_symlink(const char *old, const char *new)
+{
+#ifdef __NR_symlinkat
+	return my_syscall3(__NR_symlinkat, old, AT_FDCWD, new);
+#elif defined(__NR_symlink)
+	return my_syscall2(__NR_symlink, old, new);
+#else
+#error Neither __NR_symlinkat nor __NR_symlink defined, cannot implement sys_symlink()
+#endif
+}
+
+static __attribute__((unused))
+int symlink(const char *old, const char *new)
+{
+	int ret = sys_symlink(old, new);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * mode_t umask(mode_t mode);
+ */
+
+static __attribute__((unused))
+mode_t sys_umask(mode_t mode)
+{
+	return my_syscall1(__NR_umask, mode);
+}
+
+static __attribute__((unused))
+mode_t umask(mode_t mode)
+{
+	return sys_umask(mode);
+}
+
+
+/*
+ * int umount2(const char *path, int flags);
+ */
+
+static __attribute__((unused))
+int sys_umount2(const char *path, int flags)
+{
+	return my_syscall2(__NR_umount2, path, flags);
+}
+
+static __attribute__((unused))
+int umount2(const char *path, int flags)
+{
+	int ret = sys_umount2(path, flags);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * int unlink(const char *path);
+ */
+
+static __attribute__((unused))
+int sys_unlink(const char *path)
+{
+#ifdef __NR_unlinkat
+	return my_syscall3(__NR_unlinkat, AT_FDCWD, path, 0);
+#elif defined(__NR_unlink)
+	return my_syscall1(__NR_unlink, path);
+#else
+#error Neither __NR_unlinkat nor __NR_unlink defined, cannot implement sys_unlink()
+#endif
+}
+
+static __attribute__((unused))
+int unlink(const char *path)
+{
+	int ret = sys_unlink(path);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * pid_t wait(int *status);
+ * pid_t wait4(pid_t pid, int *status, int options, struct rusage *rusage);
+ * pid_t waitpid(pid_t pid, int *status, int options);
+ */
+
+static __attribute__((unused))
+pid_t sys_wait4(pid_t pid, int *status, int options, struct rusage *rusage)
+{
+	return my_syscall4(__NR_wait4, pid, status, options, rusage);
+}
+
+static __attribute__((unused))
+pid_t wait(int *status)
+{
+	pid_t ret = sys_wait4(-1, status, 0, NULL);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+static __attribute__((unused))
+pid_t wait4(pid_t pid, int *status, int options, struct rusage *rusage)
+{
+	pid_t ret = sys_wait4(pid, status, options, rusage);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+static __attribute__((unused))
+pid_t waitpid(pid_t pid, int *status, int options)
+{
+	pid_t ret = sys_wait4(pid, status, options, NULL);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+/*
+ * ssize_t write(int fd, const void *buf, size_t count);
+ */
+
+static __attribute__((unused))
+ssize_t sys_write(int fd, const void *buf, size_t count)
+{
+	return my_syscall3(__NR_write, fd, buf, count);
+}
+
+static __attribute__((unused))
+ssize_t write(int fd, const void *buf, size_t count)
+{
+	ssize_t ret = sys_write(fd, buf, count);
+
+	if (ret < 0) {
+		SET_ERRNO(-ret);
+		ret = -1;
+	}
+	return ret;
+}
+
+
+#endif /* _NOLIBC_SYS_H */
diff --git a/tools/include/nolibc/time.h b/tools/include/nolibc/time.h
new file mode 100644
index 000000000000..d18b7661fdd7
--- /dev/null
+++ b/tools/include/nolibc/time.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * time function definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_TIME_H
+#define _NOLIBC_TIME_H
+
+#include "std.h"
+#include "arch.h"
+#include "types.h"
+#include "sys.h"
+
+static __attribute__((unused))
+time_t time(time_t *tptr)
+{
+	struct timeval tv;
+
+	/* note, cannot fail here */
+	sys_gettimeofday(&tv, NULL);
+
+	if (tptr)
+		*tptr = tv.tv_sec;
+	return tv.tv_sec;
+}
+
+#endif /* _NOLIBC_TIME_H */
diff --git a/tools/include/nolibc/types.h b/tools/include/nolibc/types.h
new file mode 100644
index 000000000000..959997034e55
--- /dev/null
+++ b/tools/include/nolibc/types.h
@@ -0,0 +1,205 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Special types used by various syscalls for NOLIBC
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_TYPES_H
+#define _NOLIBC_TYPES_H
+
+#include "std.h"
+#include <linux/time.h>
+
+
+/* Only the generic macros and types may be defined here. The arch-specific
+ * ones such as the O_RDONLY and related macros used by fcntl() and open(), or
+ * the layout of sys_stat_struct must not be defined here.
+ */
+
+/* stat flags (WARNING, octal here) */
+#define S_IFDIR        0040000
+#define S_IFCHR        0020000
+#define S_IFBLK        0060000
+#define S_IFREG        0100000
+#define S_IFIFO        0010000
+#define S_IFLNK        0120000
+#define S_IFSOCK       0140000
+#define S_IFMT         0170000
+
+#define S_ISDIR(mode)  (((mode) & S_IFDIR)  == S_IFDIR)
+#define S_ISCHR(mode)  (((mode) & S_IFCHR)  == S_IFCHR)
+#define S_ISBLK(mode)  (((mode) & S_IFBLK)  == S_IFBLK)
+#define S_ISREG(mode)  (((mode) & S_IFREG)  == S_IFREG)
+#define S_ISFIFO(mode) (((mode) & S_IFIFO)  == S_IFIFO)
+#define S_ISLNK(mode)  (((mode) & S_IFLNK)  == S_IFLNK)
+#define S_ISSOCK(mode) (((mode) & S_IFSOCK) == S_IFSOCK)
+
+/* dirent types */
+#define DT_UNKNOWN     0x0
+#define DT_FIFO        0x1
+#define DT_CHR         0x2
+#define DT_DIR         0x4
+#define DT_BLK         0x6
+#define DT_REG         0x8
+#define DT_LNK         0xa
+#define DT_SOCK        0xc
+
+/* commonly an fd_set represents 256 FDs */
+#ifndef FD_SETSIZE
+#define FD_SETSIZE     256
+#endif
+
+/* PATH_MAX and MAXPATHLEN are often used and found with plenty of different
+ * values.
+ */
+#ifndef PATH_MAX
+#define PATH_MAX       4096
+#endif
+
+#ifndef MAXPATHLEN
+#define MAXPATHLEN     (PATH_MAX)
+#endif
+
+/* Special FD used by all the *at functions */
+#ifndef AT_FDCWD
+#define AT_FDCWD       (-100)
+#endif
+
+/* whence values for lseek() */
+#define SEEK_SET       0
+#define SEEK_CUR       1
+#define SEEK_END       2
+
+/* cmd for reboot() */
+#define LINUX_REBOOT_MAGIC1         0xfee1dead
+#define LINUX_REBOOT_MAGIC2         0x28121969
+#define LINUX_REBOOT_CMD_HALT       0xcdef0123
+#define LINUX_REBOOT_CMD_POWER_OFF  0x4321fedc
+#define LINUX_REBOOT_CMD_RESTART    0x01234567
+#define LINUX_REBOOT_CMD_SW_SUSPEND 0xd000fce2
+
+/* Macros used on waitpid()'s return status */
+#define WEXITSTATUS(status) (((status) & 0xff00) >> 8)
+#define WIFEXITED(status)   (((status) & 0x7f) == 0)
+
+/* waitpid() flags */
+#define WNOHANG      1
+
+/* standard exit() codes */
+#define EXIT_SUCCESS 0
+#define EXIT_FAILURE 1
+
+/* for select() */
+typedef struct {
+	uint32_t fd32[(FD_SETSIZE + 31) / 32];
+} fd_set;
+
+#define FD_CLR(fd, set) do {                                            \
+		fd_set *__set = (set);                                  \
+		int __fd = (fd);                                        \
+		if (__fd >= 0)                                          \
+			__set->fd32[__fd / 32] &= ~(1U << (__fd & 31)); \
+	} while (0)
+
+#define FD_SET(fd, set) do {                                            \
+		fd_set *__set = (set);                                  \
+		int __fd = (fd);                                        \
+		if (__fd >= 0)                                          \
+			__set->fd32[__fd / 32] |= 1U << (__fd & 31);    \
+	} while (0)
+
+#define FD_ISSET(fd, set) ({                                                  \
+		fd_set *__set = (set);                                        \
+		int __fd = (fd);                                              \
+		int __r = 0;                                                  \
+		if (__fd >= 0)                                                \
+			__r = !!(__set->fd32[__fd / 32] & 1U << (__fd & 31)); \
+		__r;                                                          \
+	})
+
+#define FD_ZERO(set) do {                                               \
+		fd_set *__set = (set);                                  \
+		int __idx;                                              \
+		for (__idx = 0; __idx < (FD_SETSIZE+31) / 32; __idx ++) \
+			__set->fd32[__idx] = 0;                         \
+	} while (0)
+
+/* for poll() */
+#define POLLIN          0x0001
+#define POLLPRI         0x0002
+#define POLLOUT         0x0004
+#define POLLERR         0x0008
+#define POLLHUP         0x0010
+#define POLLNVAL        0x0020
+
+struct pollfd {
+	int fd;
+	short int events;
+	short int revents;
+};
+
+/* for getdents64() */
+struct linux_dirent64 {
+	uint64_t       d_ino;
+	int64_t        d_off;
+	unsigned short d_reclen;
+	unsigned char  d_type;
+	char           d_name[];
+};
+
+/* needed by wait4() */
+struct rusage {
+	struct timeval ru_utime;
+	struct timeval ru_stime;
+	long   ru_maxrss;
+	long   ru_ixrss;
+	long   ru_idrss;
+	long   ru_isrss;
+	long   ru_minflt;
+	long   ru_majflt;
+	long   ru_nswap;
+	long   ru_inblock;
+	long   ru_oublock;
+	long   ru_msgsnd;
+	long   ru_msgrcv;
+	long   ru_nsignals;
+	long   ru_nvcsw;
+	long   ru_nivcsw;
+};
+
+/* The format of the struct as returned by the libc to the application, which
+ * significantly differs from the format returned by the stat() syscall flavours.
+ */
+struct stat {
+	dev_t     st_dev;     /* ID of device containing file */
+	ino_t     st_ino;     /* inode number */
+	mode_t    st_mode;    /* protection */
+	nlink_t   st_nlink;   /* number of hard links */
+	uid_t     st_uid;     /* user ID of owner */
+	gid_t     st_gid;     /* group ID of owner */
+	dev_t     st_rdev;    /* device ID (if special file) */
+	off_t     st_size;    /* total size, in bytes */
+	blksize_t st_blksize; /* blocksize for file system I/O */
+	blkcnt_t  st_blocks;  /* number of 512B blocks allocated */
+	time_t    st_atime;   /* time of last access */
+	time_t    st_mtime;   /* time of last modification */
+	time_t    st_ctime;   /* time of last status change */
+};
+
+/* WARNING, it only deals with the 4096 first majors and 256 first minors */
+#define makedev(major, minor) ((dev_t)((((major) & 0xfff) << 8) | ((minor) & 0xff)))
+#define major(dev) ((unsigned int)(((dev) >> 8) & 0xfff))
+#define minor(dev) ((unsigned int)(((dev) & 0xff))
+
+#ifndef offsetof
+#define offsetof(TYPE, FIELD) ((size_t) &((TYPE *)0)->FIELD)
+#endif
+
+#ifndef container_of
+#define container_of(PTR, TYPE, FIELD) ({			\
+	__typeof__(((TYPE *)0)->FIELD) *__FIELD_PTR = (PTR);	\
+	(TYPE *)((char *) __FIELD_PTR - offsetof(TYPE, FIELD));	\
+})
+#endif
+
+#endif /* _NOLIBC_TYPES_H */
diff --git a/tools/include/nolibc/unistd.h b/tools/include/nolibc/unistd.h
new file mode 100644
index 000000000000..1c25e20ee360
--- /dev/null
+++ b/tools/include/nolibc/unistd.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * unistd function definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_UNISTD_H
+#define _NOLIBC_UNISTD_H
+
+#include "std.h"
+#include "arch.h"
+#include "types.h"
+#include "sys.h"
+
+
+static __attribute__((unused))
+int msleep(unsigned int msecs)
+{
+	struct timeval my_timeval = { msecs / 1000, (msecs % 1000) * 1000 };
+
+	if (sys_select(0, 0, 0, 0, &my_timeval) < 0)
+		return (my_timeval.tv_sec * 1000) +
+			(my_timeval.tv_usec / 1000) +
+			!!(my_timeval.tv_usec % 1000);
+	else
+		return 0;
+}
+
+static __attribute__((unused))
+unsigned int sleep(unsigned int seconds)
+{
+	struct timeval my_timeval = { seconds, 0 };
+
+	if (sys_select(0, 0, 0, 0, &my_timeval) < 0)
+		return my_timeval.tv_sec + !!my_timeval.tv_usec;
+	else
+		return 0;
+}
+
+static __attribute__((unused))
+int usleep(unsigned int usecs)
+{
+	struct timeval my_timeval = { usecs / 1000000, usecs % 1000000 };
+
+	return sys_select(0, 0, 0, 0, &my_timeval);
+}
+
+static __attribute__((unused))
+int tcsetpgrp(int fd, pid_t pid)
+{
+	return ioctl(fd, TIOCSPGRP, &pid);
+}
+
+#endif /* _NOLIBC_UNISTD_H */