Merge tag 'nolibc.2023.06.22a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu

Pull nolibc updates from Paul McKenney:

 - Add stackprotector support

 - Fix RISC-V load-store instruction syntax to support 32-bit binaries,
   plus fixes for generic 32-bit support

 - Fix use of s390 sys_fork()

 - Add my_syscall6() for ARM

 - Support different platforms having different errno definitions

 - Fix ppoll/ppoll_time64 arguments (add the fifth argument)

 - Force use of little endian on MIPS

 - Improved testing, for example, better handling of different compilers
   and compiler versions, comparing nolibc behavior to that of libc, and
   additional test cases

 - Improve syntax and header ordering

 - Use existing <linux/reboot.h> instead of redefining constants

 - Add syscall()

* tag 'nolibc.2023.06.22a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (53 commits)
  selftests/nolibc: make sure gcc always use little endian on MIPS
  selftests/nolibc: also count skipped and failed tests in output
  selftests/nolibc: add new gettimeofday test cases
  selftests/nolibc: remove gettimeofday_bad1/2 completely
  selftests/nolibc: support two errnos with EXPECT_SYSER2()
  tools/nolibc: open: fix up compile warning for arm
  tools/nolibc: arm: add missing my_syscall6
  selftests/nolibc: use INT_MAX instead of __INT_MAX__
  selftests/nolibc: not include limits.h for nolibc
  selftests/nolibc: fix up compile warning with glibc on x86_64
  selftests/nolibc: allow specify extra arguments for qemu
  selftests/nolibc: remove test gettimeofday_null
  tools/nolibc: ensure fast64 integer types have 64 bits
  selftests/nolibc: test_fork: fix up duplicated print
  tools/nolibc: ppoll/ppoll_time64: add a missing argument
  selftests/nolibc: remove the duplicated gettimeofday_bad2
  selftests/nolibc: print name instead of number for EOVERFLOW
  tools/nolibc: support nanoseconds in stat()
  selftests/nolibc: prevent coredumps during test execution
  tools/nolibc: add support for prctl()
  ...

23 files changed, 704 insertions, 313 deletions

diff --git a/tools/include/nolibc/Makefile b/tools/include/nolibc/Makefile
index 9839feafd38a..64d67b080744 100644
--- a/tools/include/nolibc/Makefile
+++ b/tools/include/nolibc/Makefile
@@ -25,8 +25,23 @@ endif
 
 nolibc_arch := $(patsubst arm64,aarch64,$(ARCH))
 arch_file := arch-$(nolibc_arch).h
-all_files := ctype.h errno.h nolibc.h signal.h stackprotector.h std.h stdint.h \
-             stdio.h stdlib.h string.h sys.h time.h types.h unistd.h
+all_files := \
+		compiler.h \
+		ctype.h \
+		errno.h \
+		nolibc.h \
+		signal.h \
+		stackprotector.h \
+		std.h \
+		stdint.h \
+		stdlib.h \
+		string.h \
+		sys.h \
+		time.h \
+		types.h \
+		unistd.h \
+		stdio.h \
+
 
 # install all headers needed to support a bare-metal compiler
 all: headers
diff --git a/tools/include/nolibc/arch-aarch64.h b/tools/include/nolibc/arch-aarch64.h
index 383baddef701..11f294a406b7 100644
--- a/tools/include/nolibc/arch-aarch64.h
+++ b/tools/include/nolibc/arch-aarch64.h
@@ -7,6 +7,8 @@
 #ifndef _NOLIBC_ARCH_AARCH64_H
 #define _NOLIBC_ARCH_AARCH64_H
 
+#include "compiler.h"
+
 /* The struct returned by the newfstatat() syscall. Differs slightly from the
  * x86_64's stat one by field ordering, so be careful.
  */
@@ -173,27 +175,30 @@ char **environ __attribute__((weak));
 const unsigned long *_auxv __attribute__((weak));
 
 /* startup code */
-void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void)
+void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void)
 {
 	__asm__ volatile (
-		"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
-		"adrp x3, environ\n"          // x3 = &environ (high bits)
-		"str x2, [x3, #:lo12:environ]\n" // store envp into environ
-		"mov x4, x2\n"       // search for auxv (follows NULL after last env)
+#ifdef _NOLIBC_STACKPROTECTOR
+		"bl __stack_chk_init\n"   /* initialize stack protector                     */
+#endif
+		"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                                    */
+		"adrp x3, environ\n"          /* x3 = &environ (high bits)                  */
+		"str x2, [x3, #:lo12:environ]\n" /* store envp into environ                 */
+		"mov x4, x2\n"       /* search for auxv (follows NULL after last env)       */
 		"0:\n"
-		"ldr x5, [x4], 8\n"  // x5 = *x4; x4 += 8
-		"cbnz x5, 0b\n"      // and stop at NULL after last env
-		"adrp x3, _auxv\n"   // x3 = &_auxv (high bits)
-		"str x4, [x3, #:lo12:_auxv]\n" // store x4 into _auxv
-		"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
+		"ldr x5, [x4], 8\n"  /* x5 = *x4; x4 += 8                                   */
+		"cbnz x5, 0b\n"      /* and stop at NULL after last env                     */
+		"adrp x3, _auxv\n"   /* x3 = &_auxv (high bits)                             */
+		"str x4, [x3, #:lo12:_auxv]\n" /* store x4 into _auxv                       */
+		"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"
 	);
 	__builtin_unreachable();
 }
-#endif // _NOLIBC_ARCH_AARCH64_H
+#endif /* _NOLIBC_ARCH_AARCH64_H */
diff --git a/tools/include/nolibc/arch-arm.h b/tools/include/nolibc/arch-arm.h
index 42499f23e73c..ca4c66987497 100644
--- a/tools/include/nolibc/arch-arm.h
+++ b/tools/include/nolibc/arch-arm.h
@@ -7,6 +7,8 @@
 #ifndef _NOLIBC_ARCH_ARM_H
 #define _NOLIBC_ARCH_ARM_H
 
+#include "compiler.h"
+
 /* 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.
@@ -196,41 +198,67 @@ struct sys_stat_struct {
 	_arg1;                                                                \
 })
 
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6)                  \
+({                                                                            \
+	register long _num  __asm__(_NOLIBC_SYSCALL_REG) = (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);                    \
+	register long _arg6 __asm__ ("r5") = (long)(arg6);                    \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		_NOLIBC_THUMB_SET_R7                                          \
+		"svc #0\n"                                                    \
+		_NOLIBC_THUMB_RESTORE_R7                                      \
+		: "=r"(_arg1), "=r" (_num)                                    \
+		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+		  "r"(_arg6), "r"(_num)                                       \
+		: "memory", "cc", "lr"                                        \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+
 char **environ __attribute__((weak));
 const unsigned long *_auxv __attribute__((weak));
 
 /* startup code */
-void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void)
+void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void)
 {
 	__asm__ volatile (
-		"pop {%r0}\n"                 // argc was in the stack
-		"mov %r1, %sp\n"              // argv = sp
+#ifdef _NOLIBC_STACKPROTECTOR
+		"bl __stack_chk_init\n"       /* initialize stack protector                          */
+#endif
+		"pop {%r0}\n"                 /* argc was in the stack                               */
+		"mov %r1, %sp\n"              /* argv = sp                                           */
 
-		"add %r2, %r0, $1\n"          // envp = (argc + 1) ...
-		"lsl %r2, %r2, $2\n"          //        * 4        ...
-		"add %r2, %r2, %r1\n"         //        + argv
-		"ldr %r3, 1f\n"               // r3 = &environ (see below)
-		"str %r2, [r3]\n"             // store envp into environ
+		"add %r2, %r0, $1\n"          /* envp = (argc + 1) ...                               */
+		"lsl %r2, %r2, $2\n"          /*        * 4        ...                               */
+		"add %r2, %r2, %r1\n"         /*        + argv                                       */
+		"ldr %r3, 1f\n"               /* r3 = &environ (see below)                           */
+		"str %r2, [r3]\n"             /* store envp into environ                             */
 
-		"mov r4, r2\n"                // search for auxv (follows NULL after last env)
+		"mov r4, r2\n"                /* search for auxv (follows NULL after last env)       */
 		"0:\n"
-		"mov r5, r4\n"                // r5 = r4
-		"add r4, r4, #4\n"            // r4 += 4
-		"ldr r5,[r5]\n"               // r5 = *r5 = *(r4-4)
-		"cmp r5, #0\n"                // and stop at NULL after last env
+		"mov r5, r4\n"                /* r5 = r4                                             */
+		"add r4, r4, #4\n"            /* r4 += 4                                             */
+		"ldr r5,[r5]\n"               /* r5 = *r5 = *(r4-4)                                  */
+		"cmp r5, #0\n"                /* and stop at NULL after last env                     */
 		"bne 0b\n"
-		"ldr %r3, 2f\n"               // r3 = &_auxv (low bits)
-		"str r4, [r3]\n"              // store r4 into _auxv
+		"ldr %r3, 2f\n"               /* r3 = &_auxv (low bits)                              */
+		"str r4, [r3]\n"              /* store r4 into _auxv                                 */
 
-		"mov %r3, $8\n"               // AAPCS : sp must be 8-byte aligned in the
-		"neg %r3, %r3\n"              //         callee, and bl doesn't push (lr=pc)
-		"and %r3, %r3, %r1\n"         // so we do sp = r1(=sp) & r3(=-8);
-		"mov %sp, %r3\n"              //
+		"mov %r3, $8\n"               /* AAPCS : sp must be 8-byte aligned in the            */
+		"neg %r3, %r3\n"              /*         callee, and bl doesn't push (lr=pc)         */
+		"and %r3, %r3, %r1\n"         /* so we do sp = r1(=sp) & r3(=-8);                    */
+		"mov %sp, %r3\n"
 
-		"bl main\n"                   // main() returns the status code, we'll exit with it.
-		"movs r7, $1\n"               // NR_exit == 1
+		"bl main\n"                   /* main() returns the status code, we'll exit with it. */
+		"movs r7, $1\n"               /* NR_exit == 1                                        */
 		"svc $0x00\n"
-		".align 2\n"                  // below are the pointers to a few variables
+		".align 2\n"                  /* below are the pointers to a few variables           */
 		"1:\n"
 		".word environ\n"
 		"2:\n"
@@ -239,4 +267,4 @@ void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void)
 	__builtin_unreachable();
 }
 
-#endif // _NOLIBC_ARCH_ARM_H
+#endif /* _NOLIBC_ARCH_ARM_H */
diff --git a/tools/include/nolibc/arch-i386.h b/tools/include/nolibc/arch-i386.h
index 2d98d78fd3f3..3d672d925e9e 100644
--- a/tools/include/nolibc/arch-i386.h
+++ b/tools/include/nolibc/arch-i386.h
@@ -7,6 +7,8 @@
 #ifndef _NOLIBC_ARCH_I386_H
 #define _NOLIBC_ARCH_I386_H
 
+#include "compiler.h"
+
 /* The struct returned by the stat() syscall, 32-bit only, the syscall returns
  * exactly 56 bytes (stops before the unused array).
  */
@@ -181,8 +183,6 @@ struct sys_stat_struct {
 char **environ __attribute__((weak));
 const unsigned long *_auxv __attribute__((weak));
 
-#define __ARCH_SUPPORTS_STACK_PROTECTOR
-
 /* startup code */
 /*
  * i386 System V ABI mandates:
@@ -190,35 +190,35 @@ const unsigned long *_auxv __attribute__((weak));
  * 2) The deepest stack frame should be set to zero
  *
  */
-void __attribute__((weak,noreturn,optimize("omit-frame-pointer"),no_stack_protector)) _start(void)
+void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void)
 {
 	__asm__ volatile (
-#ifdef NOLIBC_STACKPROTECTOR
-		"call __stack_chk_init\n"   // initialize stack protector
+#ifdef _NOLIBC_STACKPROTECTOR
+		"call __stack_chk_init\n"   /* initialize stack protector                    */
 #endif
-		"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)
-		"mov %ecx, environ\n"       // save environ
-		"xor %ebp, %ebp\n"          // zero the stack frame
-		"mov %ecx, %edx\n"          // search for auxv (follows NULL after last env)
+		"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)       */
+		"mov %ecx, environ\n"       /* save environ                                  */
+		"xor %ebp, %ebp\n"          /* zero the stack frame                          */
+		"mov %ecx, %edx\n"          /* search for auxv (follows NULL after last env) */
 		"0:\n"
-		"add $4, %edx\n"            // search for auxv using edx, it follows the
-		"cmp -4(%edx), %ebp\n"      // ... NULL after last env (ebp is zero here)
+		"add $4, %edx\n"            /* search for auxv using edx, it follows the     */
+		"cmp -4(%edx), %ebp\n"      /* ... NULL after last env (ebp is zero here)    */
 		"jnz 0b\n"
-		"mov %edx, _auxv\n"         // save it into _auxv
-		"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
+		"mov %edx, _auxv\n"         /* save it into _auxv                            */
+		"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
+		"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                            */
 	);
 	__builtin_unreachable();
 }
 
-#endif // _NOLIBC_ARCH_I386_H
+#endif /* _NOLIBC_ARCH_I386_H */
diff --git a/tools/include/nolibc/arch-loongarch.h b/tools/include/nolibc/arch-loongarch.h
index 029ee3cd6baf..ad3f266e7093 100644
--- a/tools/include/nolibc/arch-loongarch.h
+++ b/tools/include/nolibc/arch-loongarch.h
@@ -7,6 +7,8 @@
 #ifndef _NOLIBC_ARCH_LOONGARCH_H
 #define _NOLIBC_ARCH_LOONGARCH_H
 
+#include "compiler.h"
+
 /* Syscalls for LoongArch :
  *   - stack is 16-byte aligned
  *   - syscall number is passed in a7
@@ -158,7 +160,7 @@ const unsigned long *_auxv __attribute__((weak));
 #define LONG_ADDI    "addi.w"
 #define LONG_SLL     "slli.w"
 #define LONG_BSTRINS "bstrins.w"
-#else // __loongarch_grlen == 64
+#else /* __loongarch_grlen == 64 */
 #define LONGLOG      "3"
 #define SZREG        "8"
 #define REG_L        "ld.d"
@@ -170,31 +172,34 @@ const unsigned long *_auxv __attribute__((weak));
 #endif
 
 /* startup code */
-void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void)
+void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void)
 {
 	__asm__ volatile (
-		REG_L        " $a0, $sp, 0\n"         // argc (a0) was in the stack
-		LONG_ADDI    " $a1, $sp, "SZREG"\n"   // argv (a1) = sp + SZREG
-		LONG_SLL     " $a2, $a0, "LONGLOG"\n" // envp (a2) = SZREG*argc ...
-		LONG_ADDI    " $a2, $a2, "SZREG"\n"   //             + SZREG (skip null)
-		LONG_ADD     " $a2, $a2, $a1\n"       //             + argv
-
-		"move          $a3, $a2\n"            // iterate a3 over envp to find auxv (after NULL)
-		"0:\n"                                // do {
-		REG_L        " $a4, $a3, 0\n"         //   a4 = *a3;
-		LONG_ADDI    " $a3, $a3, "SZREG"\n"   //   a3 += sizeof(void*);
-		"bne           $a4, $zero, 0b\n"      // } while (a4);
-		"la.pcrel      $a4, _auxv\n"          // a4 = &_auxv
-		LONG_S       " $a3, $a4, 0\n"         // store a3 into _auxv
-
-		"la.pcrel      $a3, environ\n"        // a3 = &environ
-		LONG_S       " $a2, $a3, 0\n"         // store envp(a2) into environ
-		LONG_BSTRINS " $sp, $zero, 3, 0\n"    // sp must be 16-byte aligned
-		"bl            main\n"                // main() returns the status code, we'll exit with it.
-		"li.w          $a7, 93\n"             // NR_exit == 93
+#ifdef _NOLIBC_STACKPROTECTOR
+		"bl __stack_chk_init\n"               /* initialize stack protector                          */
+#endif
+		REG_L        " $a0, $sp, 0\n"         /* argc (a0) was in the stack                          */
+		LONG_ADDI    " $a1, $sp, "SZREG"\n"   /* argv (a1) = sp + SZREG                              */
+		LONG_SLL     " $a2, $a0, "LONGLOG"\n" /* envp (a2) = SZREG*argc ...                          */
+		LONG_ADDI    " $a2, $a2, "SZREG"\n"   /*             + SZREG (skip null)                     */
+		LONG_ADD     " $a2, $a2, $a1\n"       /*             + argv                                  */
+
+		"move          $a3, $a2\n"            /* iterate a3 over envp to find auxv (after NULL)      */
+		"0:\n"                                /* do {                                                */
+		REG_L        " $a4, $a3, 0\n"         /*   a4 = *a3;                                         */
+		LONG_ADDI    " $a3, $a3, "SZREG"\n"   /*   a3 += sizeof(void*);                              */
+		"bne           $a4, $zero, 0b\n"      /* } while (a4);                                       */
+		"la.pcrel      $a4, _auxv\n"          /* a4 = &_auxv                                         */
+		LONG_S       " $a3, $a4, 0\n"         /* store a3 into _auxv                                 */
+
+		"la.pcrel      $a3, environ\n"        /* a3 = &environ                                       */
+		LONG_S       " $a2, $a3, 0\n"         /* store envp(a2) into environ                         */
+		LONG_BSTRINS " $sp, $zero, 3, 0\n"    /* sp must be 16-byte aligned                          */
+		"bl            main\n"                /* main() returns the status code, we'll exit with it. */
+		"li.w          $a7, 93\n"             /* NR_exit == 93                                       */
 		"syscall       0\n"
 	);
 	__builtin_unreachable();
 }
 
-#endif // _NOLIBC_ARCH_LOONGARCH_H
+#endif /* _NOLIBC_ARCH_LOONGARCH_H */
diff --git a/tools/include/nolibc/arch-mips.h b/tools/include/nolibc/arch-mips.h
index bf83432d23ed..db24e0837a39 100644
--- a/tools/include/nolibc/arch-mips.h
+++ b/tools/include/nolibc/arch-mips.h
@@ -7,6 +7,8 @@
 #ifndef _NOLIBC_ARCH_MIPS_H
 #define _NOLIBC_ARCH_MIPS_H
 
+#include "compiler.h"
+
 /* The struct returned by the stat() syscall. 88 bytes are returned by the
  * syscall.
  */
@@ -180,45 +182,49 @@ char **environ __attribute__((weak));
 const unsigned long *_auxv __attribute__((weak));
 
 /* startup code, note that it's called __start on MIPS */
-void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __start(void)
+void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector __start(void)
 {
 	__asm__ volatile (
-		//".set nomips16\n"
+		/*".set nomips16\n"*/
 		".set push\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
-		"lui $a3, %hi(environ)\n"     // load environ into a3 (hi)
-		"addiu $a3, %lo(environ)\n"   // load environ into a3 (lo)
-		"sw $a2,($a3)\n"              // store envp(a2) into environ
-
-		"move $t0, $a2\n"             // iterate t0 over envp, look for NULL
-		"0:"                          // do {
-		"lw $a3, ($t0)\n"             //   a3=*(t0);
-		"bne $a3, $0, 0b\n"           // } while (a3);
-		"addiu $t0, $t0, 4\n"         // delayed slot: t0+=4;
-		"lui $a3, %hi(_auxv)\n"       // load _auxv into a3 (hi)
-		"addiu $a3, %lo(_auxv)\n"     // load _auxv into a3 (lo)
-		"sw $t0, ($a3)\n"             // store t0 into _auxv
+#ifdef _NOLIBC_STACKPROTECTOR
+		"jal __stack_chk_init\n" /* initialize stack protector                         */
+		"nop\n"                  /* delayed slot                                       */
+#endif
+		/*".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                                      */
+		"lui $a3, %hi(environ)\n"     /* load environ into a3 (hi)                     */
+		"addiu $a3, %lo(environ)\n"   /* load environ into a3 (lo)                     */
+		"sw $a2,($a3)\n"              /* store envp(a2) into environ                   */
+
+		"move $t0, $a2\n"             /* iterate t0 over envp, look for NULL           */
+		"0:"                          /* do {                                          */
+		"lw $a3, ($t0)\n"             /*   a3=*(t0);                                   */
+		"bne $a3, $0, 0b\n"           /* } while (a3);                                 */
+		"addiu $t0, $t0, 4\n"         /* delayed slot: t0+=4;                          */
+		"lui $a3, %hi(_auxv)\n"       /* load _auxv into a3 (hi)                       */
+		"addiu $a3, %lo(_auxv)\n"     /* load _auxv into a3 (lo)                       */
+		"sw $t0, ($a3)\n"             /* store t0 into _auxv                           */
 
 		"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
+		"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"
+		/*".end __start\n"*/
 		".set pop\n"
 	);
 	__builtin_unreachable();
 }
 
-#endif // _NOLIBC_ARCH_MIPS_H
+#endif /* _NOLIBC_ARCH_MIPS_H */
diff --git a/tools/include/nolibc/arch-riscv.h b/tools/include/nolibc/arch-riscv.h
index e197fcb10ac0..a2e8564e66d6 100644
--- a/tools/include/nolibc/arch-riscv.h
+++ b/tools/include/nolibc/arch-riscv.h
@@ -7,6 +7,8 @@
 #ifndef _NOLIBC_ARCH_RISCV_H
 #define _NOLIBC_ARCH_RISCV_H
 
+#include "compiler.h"
+
 struct sys_stat_struct {
 	unsigned long	st_dev;		/* Device.  */
 	unsigned long	st_ino;		/* File serial number.  */
@@ -33,9 +35,13 @@ struct sys_stat_struct {
 #if   __riscv_xlen == 64
 #define PTRLOG "3"
 #define SZREG  "8"
+#define REG_L  "ld"
+#define REG_S  "sd"
 #elif __riscv_xlen == 32
 #define PTRLOG "2"
 #define SZREG  "4"
+#define REG_L  "lw"
+#define REG_S  "sw"
 #endif
 
 /* Syscalls for RISCV :
@@ -174,35 +180,38 @@ char **environ __attribute__((weak));
 const unsigned long *_auxv __attribute__((weak));
 
 /* startup code */
-void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void)
+void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void)
 {
 	__asm__ volatile (
 		".option push\n"
 		".option norelax\n"
 		"lla   gp, __global_pointer$\n"
 		".option pop\n"
-		"lw    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
-
-		"add   a3, a2, zero\n"       // iterate a3 over envp to find auxv (after NULL)
-		"0:\n"                       // do {
-		"ld    a4, 0(a3)\n"          //   a4 = *a3;
-		"add   a3, a3, "SZREG"\n"    //   a3 += sizeof(void*);
-		"bne   a4, zero, 0b\n"       // } while (a4);
-		"lui   a4, %hi(_auxv)\n"     // a4 = &_auxv (high bits)
-		"sd    a3, %lo(_auxv)(a4)\n" // store a3 into _auxv
-
-		"lui a3, %hi(environ)\n"     // a3 = &environ (high bits)
-		"sd a2,%lo(environ)(a3)\n"   // store envp(a2) into environ
-		"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
+#ifdef _NOLIBC_STACKPROTECTOR
+		"call __stack_chk_init\n"    /* initialize stack protector                          */
+#endif
+		REG_L" 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                                  */
+
+		"add   a3, a2, zero\n"       /* iterate a3 over envp to find auxv (after NULL)      */
+		"0:\n"                       /* do {                                                */
+		REG_L" a4, 0(a3)\n"          /*   a4 = *a3;                                         */
+		"add   a3, a3, "SZREG"\n"    /*   a3 += sizeof(void*);                              */
+		"bne   a4, zero, 0b\n"       /* } while (a4);                                       */
+		"lui   a4, %hi(_auxv)\n"     /* a4 = &_auxv (high bits)                             */
+		REG_S" a3, %lo(_auxv)(a4)\n" /* store a3 into _auxv                                 */
+
+		"lui   a3, %hi(environ)\n"   /* a3 = &environ (high bits)                           */
+		REG_S" a2,%lo(environ)(a3)\n"/* store envp(a2) into environ                         */
+		"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"
 	);
 	__builtin_unreachable();
 }
 
-#endif // _NOLIBC_ARCH_RISCV_H
+#endif /* _NOLIBC_ARCH_RISCV_H */
diff --git a/tools/include/nolibc/arch-s390.h b/tools/include/nolibc/arch-s390.h
index 6b0e54ed543d..516dff5bff8b 100644
--- a/tools/include/nolibc/arch-s390.h
+++ b/tools/include/nolibc/arch-s390.h
@@ -5,8 +5,11 @@
 
 #ifndef _NOLIBC_ARCH_S390_H
 #define _NOLIBC_ARCH_S390_H
+#include <asm/signal.h>
 #include <asm/unistd.h>
 
+#include "compiler.h"
+
 /* The struct returned by the stat() syscall, equivalent to stat64(). The
  * syscall returns 116 bytes and stops in the middle of __unused.
  */
@@ -163,7 +166,7 @@ char **environ __attribute__((weak));
 const unsigned long *_auxv __attribute__((weak));
 
 /* startup code */
-void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void)
+void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void)
 {
 	__asm__ volatile (
 		"lg	%r2,0(%r15)\n"		/* argument count */
@@ -223,4 +226,12 @@ void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd,
 	return (void *)my_syscall1(__NR_mmap, &args);
 }
 #define sys_mmap sys_mmap
-#endif // _NOLIBC_ARCH_S390_H
+
+static __attribute__((unused))
+pid_t sys_fork(void)
+{
+	return my_syscall5(__NR_clone, 0, SIGCHLD, 0, 0, 0);
+}
+#define sys_fork sys_fork
+
+#endif /* _NOLIBC_ARCH_S390_H */
diff --git a/tools/include/nolibc/arch-x86_64.h b/tools/include/nolibc/arch-x86_64.h
index f7f2a11d4c3b..6fc4d8392742 100644
--- a/tools/include/nolibc/arch-x86_64.h
+++ b/tools/include/nolibc/arch-x86_64.h
@@ -7,6 +7,8 @@
 #ifndef _NOLIBC_ARCH_X86_64_H
 #define _NOLIBC_ARCH_X86_64_H
 
+#include "compiler.h"
+
 /* The struct returned by the stat() syscall, equivalent to stat64(). The
  * syscall returns 116 bytes and stops in the middle of __unused.
  */
@@ -181,8 +183,6 @@ struct sys_stat_struct {
 char **environ __attribute__((weak));
 const unsigned long *_auxv __attribute__((weak));
 
-#define __ARCH_SUPPORTS_STACK_PROTECTOR
-
 /* startup code */
 /*
  * x86-64 System V ABI mandates:
@@ -190,31 +190,31 @@ const unsigned long *_auxv __attribute__((weak));
  * 2) The deepest stack frame should be zero (the %rbp).
  *
  */
-void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void)
+void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void)
 {
 	__asm__ volatile (
-#ifdef NOLIBC_STACKPROTECTOR
-		"call __stack_chk_init\n"   // initialize stack protector
+#ifdef _NOLIBC_STACKPROTECTOR
+		"call __stack_chk_init\n"   /* initialize stack protector                          */
 #endif
-		"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)
-		"mov %rdx, environ\n"       // save environ
-		"xor %ebp, %ebp\n"          // zero the stack frame
-		"mov %rdx, %rax\n"          // search for auxv (follows NULL after last env)
+		"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)             */
+		"mov %rdx, environ\n"       /* save environ                                        */
+		"xor %ebp, %ebp\n"          /* zero the stack frame                                */
+		"mov %rdx, %rax\n"          /* search for auxv (follows NULL after last env)       */
 		"0:\n"
-		"add $8, %rax\n"            // search for auxv using rax, it follows the
-		"cmp -8(%rax), %rbp\n"      // ... NULL after last env (rbp is zero here)
+		"add $8, %rax\n"            /* search for auxv using rax, it follows the           */
+		"cmp -8(%rax), %rbp\n"      /* ... NULL after last env (rbp is zero here)          */
 		"jnz 0b\n"
-		"mov %rax, _auxv\n"         // save it into _auxv
-		"and $-16, %rsp\n"          // x86 ABI : esp must be 16-byte aligned before call
-		"call main\n"               // main() returns the status code, we'll ex