tools headers: Move the nolibc header from rcutorture to tools/include/nolibc/

As suggested by Ingo, this header file might benefit other tools than
just rcutorture. For now it's quite limited, but is easy to extend, so
exposing it into tools/include/nolibc/ will make it much easier to
adopt by other tools.

The mkinitrd.sh script in rcutorture was updated to use this new location.

Cc: Ingo Molnar <mingo@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>

1 files changed, 2263 insertions, 0 deletions

diff --git a/tools/include/nolibc/nolibc.h b/tools/include/nolibc/nolibc.h
new file mode 100644
index 000000000000..1708e9f9f8aa
--- /dev/null
+++ b/tools/include/nolibc/nolibc.h
@@ -0,0 +1,2263 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/* nolibc.h
+ * Copyright (C) 2017-2018 Willy Tarreau <w@1wt.eu>
+ */
+
+/*
+ * This file is designed to be used as a libc alternative for minimal programs
+ * with very limited requirements. It consists of a small number of syscall and
+ * type definitions, and the minimal startup code needed to call main().
+ * All syscalls are declared as static functions so that they can be optimized
+ * away by the compiler when not used.
+ *
+ * Syscalls are split into 3 levels:
+ *   - The lower level is the arch-specific syscall() definition, consisting in
+ *     assembly code in compound expressions. These are called my_syscall0() to
+ *     my_syscall6() depending on the number of arguments. The MIPS
+ *     implementation is limited to 5 arguments. All input arguments are cast
+ *     to a long stored in a register. These expressions always return the
+ *     syscall's return value as a signed long value which is often either a
+ *     pointer or the negated errno value.
+ *
+ *   - The second level is mostly architecture-independent. It is made of
+ *     static functions called sys_<name>() which rely on my_syscallN()
+ *     depending on the syscall definition. These functions are responsible
+ *     for exposing the appropriate types for the syscall arguments (int,
+ *     pointers, etc) and for setting the appropriate return type (often int).
+ *     A few of them are architecture-specific because the syscalls are not all
+ *     mapped exactly the same among architectures. For example, some archs do
+ *     not implement select() and need pselect6() instead, so the sys_select()
+ *     function will have to abstract this.
+ *
+ *   - The third level is the libc call definition. It exposes the lower raw
+ *     sys_<name>() calls in a way that looks like what a libc usually does,
+ *     takes care of specific input values, and of setting errno upon error.
+ *     There can be minor variations compared to standard libc calls. For
+ *     example the open() call always takes 3 args here.
+ *
+ * The errno variable is declared static and unused. This way it can be
+ * optimized away if not used. However this means that a program made of
+ * multiple C files may observe different errno values (one per C file). For
+ * the type of programs this project targets it usually is not a problem. The
+ * resulting program may even be reduced by defining the NOLIBC_IGNORE_ERRNO
+ * macro, in which case the errno value will never be assigned.
+ *
+ * Some stdint-like integer types are defined. These are valid on all currently
+ * supported architectures, because signs are enforced, ints are assumed to be
+ * 32 bits, longs the size of a pointer and long long 64 bits. If more
+ * architectures have to be supported, this may need to be adapted.
+ *
+ * Some macro definitions like the O_* values passed to open(), and some
+ * structures like the sys_stat struct depend on the architecture.
+ *
+ * The definitions start with the architecture-specific parts, which are picked
+ * based on what the compiler knows about the target architecture, and are
+ * completed with the generic code. Since it is the compiler which sets the
+ * target architecture, cross-compiling normally works out of the box without
+ * 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.
+ *
+ * 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.
+ *
+ * A simple static executable may be built this way :
+ *      $ gcc -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
+ *            -static -include nolibc.h -lgcc -o hello hello.c
+ *
+ * A very useful calling convention table may be found here :
+ *      http://man7.org/linux/man-pages/man2/syscall.2.html
+ *
+ * This doc is quite convenient though not necessarily up to date :
+ *      https://w3challs.com/syscalls/
+ *
+ */
+
+/* Some archs (at least aarch64) don't expose the regular syscalls anymore by
+ * default, either because they have an "_at" replacement, or because there are
+ * more modern alternatives. For now we'd rather still use them.
+ */
+#define __ARCH_WANT_SYSCALL_NO_AT
+#define __ARCH_WANT_SYSCALL_NO_FLAGS
+#define __ARCH_WANT_SYSCALL_DEPRECATED
+
+#include <asm/unistd.h>
+#include <asm/ioctls.h>
+#include <asm/errno.h>
+#include <linux/fs.h>
+#include <linux/loop.h>
+
+#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 memry 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 select() */
+struct timeval {
+	long    tv_sec;
+	long    tv_usec;
+};
+
+/* for pselect() */
+struct timespec {
+	long    tv_sec;
+	long    tv_nsec;
+};
+
+/* for gettimeofday() */
+struct timezone {
+	int tz_minuteswest;
+	int tz_dsttime;
+};
+
+/* 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_FDWCD
+#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)
+
+
+/* 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 r8..r11 may be 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).
+ */
+
+#define my_syscall0(num)                                                      \
+({                                                                            \
+	long _ret;                                                            \
+	register long _num  asm("rax") = (num);                               \
+									      \
+	asm volatile (                                                        \
+		"syscall\n"                                                   \
+		: "=a" (_ret)                                                 \
+		: "0"(_num)                                                   \
+		: "rcx", "r8", "r9", "r10", "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", "r8", "r9", "r10", "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", "r8", "r9", "r10", "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", "r8", "r9", "r10", "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"(_arg4)                                    \
+		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4),             \
+		  "0"(_num)                                                   \
+		: "rcx", "r8", "r9", "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"(_arg4), "=r"(_arg5)                       \
+		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+		  "0"(_num)                                                   \
+		: "rcx", "r9", "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"(_arg4), "=r"(_arg5)                       \
+		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+		  "r"(_arg6), "0"(_num)                                       \
+		: "rcx", "r11", "memory", "cc"                                \
+	);                                                                    \
+	_ret;                                                                 \
+})
+
+/* startup code */
+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)
+    "and $-16, %rsp\n"          // x86 ABI : esp must be 16-byte aligned when
+    "sub $8, %rsp\n"            // entering the callee
+    "call main\n"               // main() returns the status code, we'll exit with it.
+    "movzb %al, %rdi\n"         // retrieve exit code from 8 lower bits
+    "mov $60, %rax\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 */
+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)
+    "and $-16, %esp\n"          // x86 ABI : esp must be 16-byte aligned when
+    "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
+    "movzbl %al, %ebx\n"        // retrieve exit code from lower 8 bits
+    "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.
+    "and %r0, %r0, $0xff\n"       // limit exit code to 8 bits
+    "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__)