Merge tag 'nolibc.2023.02.06a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu

Pull nolibc updates from Paul McKenney:

 - Add s390 support

 - Add support for the ARM Thumb1 instruction set

 - Fix O_* flags definitions for open() and fcntl()

 - Make errno a weak symbol instead of a static variable

 - Export environ as a weak symbol

 - Export _auxv as a weak symbol for auxilliary vector retrieval

 - Implement getauxval() and getpagesize()

 - Further improve self tests, including permitting userland testing of
   the nolibc library

* tag 'nolibc.2023.02.06a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (28 commits)
  selftests/nolibc: Add a "run-user" target to test the program in user land
  selftests/nolibc: Support "x86_64" for arch name
  selftests/nolibc: Add `getpagesize(2)` selftest
  nolibc/sys: Implement `getpagesize(2)` function
  nolibc/stdlib: Implement `getauxval(3)` function
  tools/nolibc: add auxiliary vector retrieval for s390
  tools/nolibc: add auxiliary vector retrieval for mips
  tools/nolibc: add auxiliary vector retrieval for riscv
  tools/nolibc: add auxiliary vector retrieval for arm
  tools/nolibc: add auxiliary vector retrieval for arm64
  tools/nolibc: add auxiliary vector retrieval for x86_64
  tools/nolibc: add auxiliary vector retrieval for i386
  tools/nolibc: export environ as a weak symbol on s390
  tools/nolibc: export environ as a weak symbol on riscv
  tools/nolibc: export environ as a weak symbol on mips
  tools/nolibc: export environ as a weak symbol on arm
  tools/nolibc: export environ as a weak symbol on arm64
  tools/nolibc: export environ as a weak symbol on i386
  tools/nolibc: export environ as a weak symbol on x86_64
  tools/nolibc: make errno a weak symbol instead of a static one
  ...

15 files changed, 579 insertions, 202 deletions

diff --git a/tools/include/nolibc/arch-aarch64.h b/tools/include/nolibc/arch-aarch64.h
index f68baf8f395f..383baddef701 100644
--- a/tools/include/nolibc/arch-aarch64.h
+++ b/tools/include/nolibc/arch-aarch64.h
@@ -7,18 +7,6 @@
 #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.
  */
@@ -181,19 +169,31 @@ struct sys_stat_struct {
 	_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"
-    "");
+char **environ __attribute__((weak));
+const unsigned long *_auxv __attribute__((weak));
 
+/* startup code */
+void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _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)
+		"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
+		"svc #0\n"
+	);
+	__builtin_unreachable();
+}
 #endif // _NOLIBC_ARCH_AARCH64_H
diff --git a/tools/include/nolibc/arch-arm.h b/tools/include/nolibc/arch-arm.h
index f31be8e967d6..42499f23e73c 100644
--- a/tools/include/nolibc/arch-arm.h
+++ b/tools/include/nolibc/arch-arm.h
@@ -7,18 +7,6 @@
 #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.
@@ -70,20 +58,44 @@ struct sys_stat_struct {
  *     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).
+ *   - in thumb mode without -fomit-frame-pointer, r7 is also used to store the
+ *     frame pointer, and we cannot directly assign it as a register variable,
+ *     nor can we clobber it. Instead we assign the r6 register and swap it
+ *     with r7 before calling svc, and r6 is marked as clobbered.
+ *     We're just using any regular register which we assign to r7 after saving
+ *     it.
  *
  * Also, ARM supports the old_select syscall if newselect is not available
  */
 #define __ARCH_WANT_SYS_OLD_SELECT
 
+#if (defined(__THUMBEB__) || defined(__THUMBEL__)) && \
+    !defined(NOLIBC_OMIT_FRAME_POINTER)
+/* swap r6,r7 needed in Thumb mode since we can't use nor clobber r7 */
+#define _NOLIBC_SYSCALL_REG         "r6"
+#define _NOLIBC_THUMB_SET_R7        "eor r7, r6\neor r6, r7\neor r7, r6\n"
+#define _NOLIBC_THUMB_RESTORE_R7    "mov r7, r6\n"
+
+#else  /* we're in ARM mode */
+/* in Arm mode we can directly use r7 */
+#define _NOLIBC_SYSCALL_REG         "r7"
+#define _NOLIBC_THUMB_SET_R7        ""
+#define _NOLIBC_THUMB_RESTORE_R7    ""
+
+#endif /* end THUMB */
+
 #define my_syscall0(num)                                                      \
 ({                                                                            \
-	register long _num __asm__ ("r7") = (num);                            \
+	register long _num  __asm__(_NOLIBC_SYSCALL_REG) = (num);             \
 	register long _arg1 __asm__ ("r0");                                   \
 	                                                                      \
 	__asm__  volatile (                                                   \
+		_NOLIBC_THUMB_SET_R7                                          \
 		"svc #0\n"                                                    \
-		: "=r"(_arg1)                                                 \
-		: "r"(_num)                                                   \
+		_NOLIBC_THUMB_RESTORE_R7                                      \
+		: "=r"(_arg1), "=r"(_num)                                     \
+		: "r"(_arg1),                                                 \
+		  "r"(_num)                                                   \
 		: "memory", "cc", "lr"                                        \
 	);                                                                    \
 	_arg1;                                                                \
@@ -91,12 +103,14 @@ struct sys_stat_struct {
 
 #define my_syscall1(num, arg1)                                                \
 ({                                                                            \
-	register long _num __asm__ ("r7") = (num);                            \
+	register long _num  __asm__(_NOLIBC_SYSCALL_REG) = (num);             \
 	register long _arg1 __asm__ ("r0") = (long)(arg1);                    \
 	                                                                      \
 	__asm__  volatile (                                                   \
+		_NOLIBC_THUMB_SET_R7                                          \
 		"svc #0\n"                                                    \
-		: "=r"(_arg1)                                                 \
+		_NOLIBC_THUMB_RESTORE_R7                                      \
+		: "=r"(_arg1), "=r" (_num)                                    \
 		: "r"(_arg1),                                                 \
 		  "r"(_num)                                                   \
 		: "memory", "cc", "lr"                                        \
@@ -106,13 +120,15 @@ struct sys_stat_struct {
 
 #define my_syscall2(num, arg1, arg2)                                          \
 ({                                                                            \
-	register long _num __asm__ ("r7") = (num);                            \
+	register long _num  __asm__(_NOLIBC_SYSCALL_REG) = (num);             \
 	register long _arg1 __asm__ ("r0") = (long)(arg1);                    \
 	register long _arg2 __asm__ ("r1") = (long)(arg2);                    \
 	                                                                      \
 	__asm__  volatile (                                                   \
+		_NOLIBC_THUMB_SET_R7                                          \
 		"svc #0\n"                                                    \
-		: "=r"(_arg1)                                                 \
+		_NOLIBC_THUMB_RESTORE_R7                                      \
+		: "=r"(_arg1), "=r" (_num)                                    \
 		: "r"(_arg1), "r"(_arg2),                                     \
 		  "r"(_num)                                                   \
 		: "memory", "cc", "lr"                                        \
@@ -122,14 +138,16 @@ struct sys_stat_struct {
 
 #define my_syscall3(num, arg1, arg2, arg3)                                    \
 ({                                                                            \
-	register long _num __asm__ ("r7") = (num);                            \
+	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);                    \
 	                                                                      \
 	__asm__  volatile (                                                   \
+		_NOLIBC_THUMB_SET_R7                                          \
 		"svc #0\n"                                                    \
-		: "=r"(_arg1)                                                 \
+		_NOLIBC_THUMB_RESTORE_R7                                      \
+		: "=r"(_arg1), "=r" (_num)                                    \
 		: "r"(_arg1), "r"(_arg2), "r"(_arg3),                         \
 		  "r"(_num)                                                   \
 		: "memory", "cc", "lr"                                        \
@@ -139,15 +157,17 @@ struct sys_stat_struct {
 
 #define my_syscall4(num, arg1, arg2, arg3, arg4)                              \
 ({                                                                            \
-	register long _num __asm__ ("r7") = (num);                            \
+	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);                    \
 	                                                                      \
 	__asm__  volatile (                                                   \
+		_NOLIBC_THUMB_SET_R7                                          \
 		"svc #0\n"                                                    \
-		: "=r"(_arg1)                                                 \
+		_NOLIBC_THUMB_RESTORE_R7                                      \
+		: "=r"(_arg1), "=r" (_num)                                    \
 		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4),             \
 		  "r"(_num)                                                   \
 		: "memory", "cc", "lr"                                        \
@@ -157,7 +177,7 @@ struct sys_stat_struct {
 
 #define my_syscall5(num, arg1, arg2, arg3, arg4, arg5)                        \
 ({                                                                            \
-	register long _num __asm__ ("r7") = (num);                            \
+	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);                    \
@@ -165,8 +185,10 @@ struct sys_stat_struct {
 	register long _arg5 __asm__ ("r4") = (long)(arg5);                    \
 	                                                                      \
 	__asm__  volatile (                                                   \
+		_NOLIBC_THUMB_SET_R7                                          \
 		"svc #0\n"                                                    \
-		: "=r" (_arg1)                                                \
+		_NOLIBC_THUMB_RESTORE_R7                                      \
+		: "=r"(_arg1), "=r" (_num)                                    \
 		: "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
 		  "r"(_num)                                                   \
 		: "memory", "cc", "lr"                                        \
@@ -174,31 +196,47 @@ struct sys_stat_struct {
 	_arg1;                                                                \
 })
 
+char **environ __attribute__((weak));
+const unsigned long *_auxv __attribute__((weak));
+
 /* 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"
-    "");
+void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void)
+{
+	__asm__ volatile (
+		"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
+
+		"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
+		"bne 0b\n"
+		"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"              //
+
+		"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
+		"1:\n"
+		".word environ\n"
+		"2:\n"
+		".word _auxv\n"
+	);
+	__builtin_unreachable();
+}
 
 #endif // _NOLIBC_ARCH_ARM_H
diff --git a/tools/include/nolibc/arch-i386.h b/tools/include/nolibc/arch-i386.h
index d7e7212346e2..e8d0cf545bf1 100644
--- a/tools/include/nolibc/arch-i386.h
+++ b/tools/include/nolibc/arch-i386.h
@@ -7,18 +7,6 @@
 #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).
  */
@@ -190,6 +178,9 @@ struct sys_stat_struct {
 	_eax;							\
 })
 
+char **environ __attribute__((weak));
+const unsigned long *_auxv __attribute__((weak));
+
 /* startup code */
 /*
  * i386 System V ABI mandates:
@@ -197,23 +188,32 @@ struct sys_stat_struct {
  * 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
-    "");
+void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void)
+{
+	__asm__ volatile (
+		"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)
+		"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
+		"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
+	);
+	__builtin_unreachable();
+}
 
 #endif // _NOLIBC_ARCH_I386_H
diff --git a/tools/include/nolibc/arch-mips.h b/tools/include/nolibc/arch-mips.h
index 7380093ba9e7..bf83432d23ed 100644
--- a/tools/include/nolibc/arch-mips.h
+++ b/tools/include/nolibc/arch-mips.h
@@ -7,18 +7,6 @@
 #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.
  */
@@ -188,30 +176,49 @@ struct sys_stat_struct {
 	_arg4 ? -_num : _num;                                                 \
 })
 
+char **environ __attribute__((weak));
+const unsigned long *_auxv __attribute__((weak));
+
 /* startup code, note that it's called __start on MIPS */
-__asm__ (".section .text\n"
-    ".weak __start\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
-    "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"
-    ".set pop\n"
-    "");
+void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __start(void)
+{
+	__asm__ volatile (
+		//".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
+
+		"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"
+		".set pop\n"
+	);
+	__builtin_unreachable();
+}
 
 #endif // _NOLIBC_ARCH_MIPS_H
diff --git a/tools/include/nolibc/arch-riscv.h b/tools/include/nolibc/arch-riscv.h
index a3bdd9803f8c..e197fcb10ac0 100644
--- a/tools/include/nolibc/arch-riscv.h
+++ b/tools/include/nolibc/arch-riscv.h
@@ -7,18 +7,6 @@
 #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          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
-
 struct sys_stat_struct {
 	unsigned long	st_dev;		/* Device.  */
 	unsigned long	st_ino;		/* File serial number.  */
@@ -182,23 +170,39 @@ struct sys_stat_struct {
 	_arg1;                                                                \
 })
 
+char **environ __attribute__((weak));
+const unsigned long *_auxv __attribute__((weak));
+
 /* startup code */
-__asm__ (".section .text\n"
-    ".weak _start\n"
-    "_start:\n"
-    ".option push\n"
-    ".option norelax\n"
-    "lla   gp, __global_pointer$\n"
-    ".option pop\n"
-    "lw    a0, 0(sp)\n"          // argc (a0) was in the stack
-    "add   a1, sp, "SZREG"\n"    // argv (a1) = sp
-    "slli  a2, a0, "PTRLOG"\n"   // envp (a2) = SZREG*argc ...
-    "add   a2, a2, "SZREG"\n"    //             + SZREG (skip null)
-    "add   a2,a2,a1\n"           //             + argv
-    "andi  sp,a1,-16\n"          // sp must be 16-byte aligned
-    "call  main\n"               // main() returns the status code, we'll exit with it.
-    "li a7, 93\n"                // NR_exit == 93
-    "ecall\n"
-    "");
+void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void)
+{
+	__asm__ volatile (
+		".option push\n"
+		".option norelax\n"
+		"lla   gp, __global_pointer$\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
+		"ecall\n"
+	);
+	__builtin_unreachable();
+}
 
 #endif // _NOLIBC_ARCH_RISCV_H
diff --git a/tools/include/nolibc/arch-s390.h b/tools/include/nolibc/arch-s390.h
new file mode 100644
index 000000000000..6b0e54ed543d
--- /dev/null
+++ b/tools/include/nolibc/arch-s390.h
@@ -0,0 +1,226 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * s390 specific definitions for NOLIBC
+ */
+
+#ifndef _NOLIBC_ARCH_S390_H
+#define _NOLIBC_ARCH_S390_H
+#include <asm/unistd.h>
+
+/* 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	__pad1;
+	unsigned long	st_rdev;
+	unsigned long	st_size;
+	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	st_blksize;
+	long		st_blocks;
+	unsigned long	__unused[3];
+};
+
+/* Syscalls for s390:
+ *   - registers are 64-bit
+ *   - syscall number is passed in r1
+ *   - arguments are in r2-r7
+ *   - the system call is performed by calling the svc instruction
+ *   - syscall return value is in r2
+ *   - r1 and r2 are clobbered, others are preserved.
+ *
+ * Link s390 ABI: https://github.com/IBM/s390x-abi
+ *
+ */
+
+#define my_syscall0(num)						\
+({									\
+	register long _num __asm__ ("1") = (num);			\
+	register long _rc __asm__ ("2");				\
+									\
+	__asm__  volatile (						\
+		"svc 0\n"						\
+		: "=d"(_rc)						\
+		: "d"(_num)						\
+		: "memory", "cc"					\
+		);							\
+	_rc;								\
+})
+
+#define my_syscall1(num, arg1)						\
+({									\
+	register long _num __asm__ ("1") = (num);			\
+	register long _arg1 __asm__ ("2") = (long)(arg1);		\
+									\
+	__asm__  volatile (						\
+		"svc 0\n"						\
+		: "+d"(_arg1)						\
+		: "d"(_num)						\
+		: "memory", "cc"					\
+		);							\
+	_arg1;								\
+})
+
+#define my_syscall2(num, arg1, arg2)					\
+({									\
+	register long _num __asm__ ("1") = (num);			\
+	register long _arg1 __asm__ ("2") = (long)(arg1);		\
+	register long _arg2 __asm__ ("3") = (long)(arg2);		\
+									\
+	__asm__  volatile (						\
+		"svc 0\n"						\
+		: "+d"(_arg1)						\
+		: "d"(_arg2), "d"(_num)					\
+		: "memory", "cc"					\
+		);							\
+	_arg1;								\
+})
+
+#define my_syscall3(num, arg1, arg2, arg3)				\
+({									\
+	register long _num __asm__ ("1") = (num);			\
+	register long _arg1 __asm__ ("2") = (long)(arg1);		\
+	register long _arg2 __asm__ ("3") = (long)(arg2);		\
+	register long _arg3 __asm__ ("4") = (long)(arg3);		\
+									\
+	__asm__  volatile (						\
+		"svc 0\n"						\
+		: "+d"(_arg1)						\
+		: "d"(_arg2), "d"(_arg3), "d"(_num)			\
+		: "memory", "cc"					\
+		);							\
+	_arg1;								\
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4)			\
+({									\
+	register long _num __asm__ ("1") = (num);			\
+	register long _arg1 __asm__ ("2") = (long)(arg1);		\
+	register long _arg2 __asm__ ("3") = (long)(arg2);		\
+	register long _arg3 __asm__ ("4") = (long)(arg3);		\
+	register long _arg4 __asm__ ("5") = (long)(arg4);		\
+									\
+	__asm__  volatile (						\
+		"svc 0\n"						\
+		: "+d"(_arg1)						\
+		: "d"(_arg2), "d"(_arg3), "d"(_arg4), "d"(_num)		\
+		: "memory", "cc"					\
+		);							\
+	_arg1;								\
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5)			\
+({									\
+	register long _num __asm__ ("1") = (num);			\
+	register long _arg1 __asm__ ("2") = (long)(arg1);		\
+	register long _arg2 __asm__ ("3") = (long)(arg2);		\
+	register long _arg3 __asm__ ("4") = (long)(arg3);		\
+	register long _arg4 __asm__ ("5") = (long)(arg4);		\
+	register long _arg5 __asm__ ("6") = (long)(arg5);		\
+									\
+	__asm__  volatile (						\
+		"svc 0\n"						\
+		: "+d"(_arg1)						\
+		: "d"(_arg2), "d"(_arg3), "d"(_arg4), "d"(_arg5),	\
+		  "d"(_num)						\
+		: "memory", "cc"					\
+		);							\
+	_arg1;								\
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6)		\
+({									\
+	register long _num __asm__ ("1") = (num);			\
+	register long _arg1 __asm__ ("2") = (long)(arg1);		\
+	register long _arg2 __asm__ ("3") = (long)(arg2);		\
+	register long _arg3 __asm__ ("4") = (long)(arg3);		\
+	register long _arg4 __asm__ ("5") = (long)(arg4);		\
+	register long _arg5 __asm__ ("6") = (long)(arg5);		\
+	register long _arg6 __asm__ ("7") = (long)(arg6);		\
+									\
+	__asm__  volatile (						\
+		"svc 0\n"						\
+		: "+d"(_arg1)						\
+		: "d"(_arg2), "d"(_arg3), "d"(_arg4), "d"(_arg5),	\
+		  "d"(_arg6), "d"(_num)					\
+		: "memory", "cc"					\
+		);							\
+	_arg1;								\
+})
+
+char **environ __attribute__((weak));
+const unsigned long *_auxv __attribute__((weak));
+
+/* startup code */
+void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void)
+{
+	__asm__ volatile (
+		"lg	%r2,0(%r15)\n"		/* argument count */
+		"la	%r3,8(%r15)\n"		/* argument pointers */
+
+		"xgr	%r0,%r0\n"		/* r0 will be our NULL value */
+		/* search for envp */
+		"lgr	%r4,%r3\n"		/* start at argv */
+		"0:\n"
+		"clg	%r0,0(%r4)\n"		/* entry zero? */
+		"la	%r4,8(%r4)\n"		/* advance pointer */
+		"jnz	0b\n"			/* no -> test next pointer */
+						/* yes -> r4 now contains start of envp */
+		"larl	%r1,environ\n"
+		"stg	%r4,0(%r1)\n"
+
+		/* search for auxv */
+		"lgr	%r5,%r4\n"		/* start at envp */
+		"1:\n"
+		"clg	%r0,0(%r5)\n"		/* entry zero? */
+		"la	%r5,8(%r5)\n"		/* advance pointer */
+		"jnz	1b\n"			/* no -> test next pointer */
+		"larl	%r1,_auxv\n"		/* yes -> store value in _auxv */
+		"stg	%r5,0(%r1)\n"
+
+		"aghi	%r15,-160\n"		/* allocate new stackframe */
+		"xc	0(8,%r15),0(%r15)\n"	/* clear backchain */
+		"brasl	%r14,main\n"		/* ret value of main is arg to exit */
+		"lghi	%r1,1\n"		/* __NR_exit */
+		"svc	0\n"
+	);
+	__builtin_unreachable();
+}
+
+struct s390_mmap_arg_struct {
+	unsigned long addr;
+	unsigned long len;
+	unsigned long prot;
+	unsigned long flags;
+	unsigned long fd;
+	unsigned long offset;
+};
+
+static __attribute__((unused))
+void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd,
+	       off_t offset)
+{
+	struct s390_mmap_arg_struct args = {
+		.addr = (unsigned long)addr,
+		.len = (unsigned long)length,
+		.prot = prot,
+		.flags = flags,
+		.fd = fd,
+		.offset = (unsigned long)offset
+	};
+
+	return (void *)my_syscall1(__NR_mmap, &args);
+}
+#define sys_mmap sys_mmap
+#endif // _NOLIBC_ARCH_S390_H
diff --git a/tools/include/nolibc/arch-x86_64.h b/tools/include/nolibc/arch-x86_64.h
index 0e1e9eb8545d..17f6751208e7 100644
--- a/tools/include/nolibc/arch-x86_64.h
+++ b/tools/include/nolibc/arch-x86_64.h
@@ -7,18 +7,6 @@
 #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.
  */
@@ -190,6 +178,9 @@ struct sys_stat_struct {
 	_ret;                                                                 \
 })
 
+char **environ __attribute__((weak));
+const unsigned long *_auxv __attribute__((weak));
+
 /* startup code */
 /*
  * x86-64 System V ABI mandates:
@@ -197,19 +188,28 @@ struct sys_stat_struct {
  * 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
-    "");
+void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void)
+{
+	__asm__ volatile (
+		"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)
+		"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 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
+	);
+	__builtin_unreachable();
+}
 
 #endif // _NOLIBC_ARCH_X86_64_H
diff --git a/tools/include/nolibc/arch.h b/tools/include/nolibc/arch.h
index 4c6992321b0d..78b067a4fa47 100644
--- a/tools/include/nolibc/arch.h
+++ b/tools/include/nolibc/arch.h
@@ -27,6 +27,8 @@
 #include "arch-mips.h"
 #elif defined(__riscv)
 #include "arch-riscv.h"
+#elif defined(__s390x__)
+#include "arch-s390.h"
 #endif
 
 #endif /* _NOLIBC_ARCH_H */
diff --git a/tools/include/nolibc/errno.h b/tools/include/nolibc/errno.h
index 9dc4919c769b..a44486ff0477 100644
--- a/tools/include/nolibc/errno.h
+++ b/tools/include/nolibc/errno.h
@@ -9,11 +9,9 @@
 
 #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)
+int errno __attribute__((weak));
 #else
 #define SET_ERRNO(v) do { } while (0)
 #endif
diff --git a/tools/include/nolibc/stdlib.h b/tools/include/nolibc/stdlib.h
index a24000d1e822..894c955d027e 100644
--- a/tools/include/nolibc/stdlib.h
+++ b/tools/include/nolibc/stdlib.h
@@ -12,6 +12,7 @@
 #include "types.h"
 #include "sys.h"
 #include "string.h"
+#include <linux/auxvec.h>
 
 struct nolibc_heap {
 	size_t	len;
@@ -109,6 +110,32 @@ char *getenv(const char *name)
 }
 
 static __attribute__((unused))
+unsigned long getauxval(unsigned long type)
+{
+	const unsigned long *auxv = _auxv;
+	unsigned long ret;
+
+	if (!auxv)
+		return 0;
+
+	while (1) {
+		if (!auxv[0] && !auxv[1]) {
+			ret = 0;
+			break;
+		}
+
+		if (auxv[0] == type) {
+			ret = auxv[1];
+			break;
+		}
+
+		auxv += 2;
+	}
+
+	return ret;
+}
+
+static __attribute__((unused))
 void *malloc(size_t len)
 {
 	struct nolibc_heap *heap;
diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h
index 78473d34e27c..b5f8cd35c03b 100644
--- a/tools/include/nolibc/sys.h
+++ b/tools/include/nolibc/sys.h
@@ -11,6 +11,7 @@
 #include "std.h"
 
 /* system includes */
+#include <asm/fcntl.h>   // for O_*
 #include <asm/unistd.h>
 #include <asm/signal.h>  // for SIGCHLD
 #include <asm/ioctls.h>
@@ -18,6 +19,7 @@
 #include <linux/fs.h>
 #include <linux/loop.h>
 #include <linux/time.h>
+#include <linux/auxvec.h>
 
 #include "arch.h"
 #include "errno.h"
@@ -498,6 +500,26 @@ pid_t gettid(void)
 	return sys_gettid();
 }
 
+static unsigned long getauxval(unsigned long key);
+
+/*
+ * long getpagesize(void);
+ */
+
+static __attribute__((unused))
+long getpagesize(void)
+{
+	long ret;
+
+	ret = getauxval(AT_PAGESZ);
+	if (!ret) {
+		SET_ERRNO(ENOENT);
+		return -1;
+	}
+
+	return ret;
+}
+
 
 /*
  * int gettimeofday(struct timeval *tv, struct timezone *tz);
@@ -686,6 +708,7 @@ int mknod(const char *path, mode_t mode, dev_t dev)
 #define MAP_FAILED ((void *)-1)
 #endif
 
+#ifndef sys_mmap
 static __attribute__((unused))
 void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd,
 	       off_t offset)
@@ -707,6 +730,7 @@ void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd,
 	return (void *)my_syscall6(n, addr, length, prot, flags, fd, offset);
 #endif
 }
+#endif
 
 static __attribute__((unused))
 void *mmap(void *addr, size_t length, int prot, int flags, int fd, off_t offset)
diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile
index 22f1e1d73fa8..8fe61d3e3cce 100644
--- a/tools/testing/selftests/nolibc/Makefile
+++ b/tools/testing/selftests/nolibc/Makefile
@@ -14,21 +14,25 @@ endif
 
 # kernel image names by architecture
 IMAGE_i386    = arch/x86/boot/bzImage
+IMAGE_x86_64  = arch/x86/boot/bzImage
 IMAGE_x86     = arch/x86/boot/bzImage
 IMAGE_arm64   = arch/arm64/boot/Image
 IMAGE_arm     = arch/arm/boot/zImage
 IMAGE_mips    = vmlinuz
 IMAGE_riscv   = arch/riscv/boot/Image
+IMAGE_s390    = arch/s390/boot/bzImage
 IMAGE         = $(IMAGE_$(ARCH))
 IMAGE_NAME    = $(notdir $(IMAGE))
 
 # default kernel configurations that appear to be usable
 DEFCONFIG_i386    = defconfig
+DEFCONFIG_x86_64  = defconfig
 DEFCONFIG_x86     = defconfig
 DEFCONFIG_arm64   = defconfig
 DEFCONFIG_arm     = multi_v7_defconfig
 DEFCONFIG_mips    = malta_defconfig
 DEFCONFIG_riscv   = defconfig
+DEFCONFIG_s390    = defconfig
 DEFCONFIG         = $(DEFCONFIG_$(ARCH))
 
 # optional tests to run (default = all)
@@ -36,20 +40,24 @@ TEST =
 
 # QEMU_ARCH: arch names used by qemu
 QEMU_ARCH_i386    = i386
+QEMU_ARCH_x86_64  = x86_64
 QEMU_ARCH_x86     = x86_64
 QEMU_ARCH_arm64   = aarch64
 QEMU_ARCH_arm     = arm
 QEMU_ARCH_mips    = mipsel  # works with malta_defconfig
 QEMU_ARCH_riscv   = riscv64
+QEMU_ARCH_s390    = s390x
 QEMU_ARCH         = $(QEMU_ARCH_$(ARCH))
 
 # QEMU_ARGS : some arch-specific args to pass to qemu
 QEMU_ARGS_i386    = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)"
+QEMU_ARGS_x86_64  = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)"
 QEMU_ARGS_x86     = -M pc -append "console=ttyS0,9600 i8042.noaux panic=-1 $(TEST:%=NOLIBC_TEST=%)"
 QEMU_ARGS_arm64   = -M virt -cpu cortex-a53 -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)"
 QEMU_ARGS_arm     = -M virt -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)"
 QEMU_ARGS_mips    = -M malta -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)"
 QEMU_ARGS_riscv   = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)"
+QEMU_ARGS_s390    = -M s390-ccw-virtio -m 1G -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)"
 QEMU_ARGS         = $(QEMU_ARGS_$(ARCH))
 
 # OUTPUT is only set when run from the main makefile, otherwise
@@ -62,7 +70,8 @@ else
 Q=@
 endif
 
-CFLAGS  ?= -Os -fno-ident -fno-asynchronous-unwind-tables
+CFLAGS_s390 = -m64
+CFLAGS  ?= -Os -fno-ident -fno-asynchronous-unwind-tables $(CFLAGS_$(ARCH))
 LDFLAGS := -s
 
 help:
@@ -71,6 +80,7 @@ help:
 	@echo "  help         this help"
 	@echo "  sysroot      create the nolibc sysroot here (uses \$$ARCH)"
 	@echo "  nolibc-test  build the executable (uses \$$CC and \$$CROSS_COMPILE)"
+	@echo "  run-user     runs the executable under QEMU (uses \$$ARCH, \$$TEST)"
 	@echo "  initramfs    prepare the initramfs with nolibc-test"
 	@echo "  defconfig    create a fresh new default config (uses \$$ARCH)"
 	@echo "  kernel       (re)build the kernel with the initramfs (uses \$$ARCH)"
@@ -104,6 +114,11 @@ nolibc-test: nolibc-test.c sysroot/$(ARCH)/include
 	$(QUIET_CC)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ \
 	  -nostdlib -static -Isysroot/$(ARCH)/include $< -lgcc
 
+# qemu user-land test
+run-user: nolibc-test
+	$(Q)qemu-$(QEMU_ARCH) ./nolibc-test > "$(CURDIR)/run.out" || :
+	$(Q)grep -w FAIL "$(CURDIR)/run.out" && echo "See all results in $(CURDIR)/run.out" || echo "$$(grep -c ^[0-9].*OK $(CURDIR)/run.out) test(s) passed."
+
 initramfs: nolibc-test
 	$(QUIET_MKDIR)mkdir -p initramfs
 	$(call QUIET_INSTALL, initramfs/init)
diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c
index f14f5076fb6d..c4a0c915139c 100644
--- a/tools/testing/selftests/nolibc/nolibc-test.c
+++ b/tools/testing/selftests/nolibc/nolibc-test.c
@@ -442,6 +442,35 @@ int test_getdents64(const char *dir)
 	return ret;
 }
 
+static int test_getpagesize(void)
+{
+	long x = getpagesize();
+	int c;
+
+	if (x < 0)
+		return x;
+
+#if defined(__x86_64__) || defined(__i386__) || defined(__i486__) || defined(__i586__) || defined(__i686__)
+	/*
+	 * x86 family is always 4K page.
+	 */
+	c = (x == 4096);
+#elif defined(__aarch64__)
+	/*
+	 * Linux aarch64 supports three values of page size: 4K, 16K, and 64K
+	 * which are selected at kernel compilation time.
+	 */
+	c = (x == 4096 || x == (16 * 1024) || x == (64 * 1024));
+#else
+	/*
+	 * Assuming other architectures must have at least 4K page.
+	 */
+	c = (x >= 4096);
+#endif
+
+	return !c;
+}
+
 /* Run syscall tests between IDs <min> and <max>.
  * Return 0 on success, non-zero on failure.
  */
@@ -502,6 +531,7 @@ int run_syscall(int min, int max)
 		CASE_TEST(gettimeofday_bad2); EXPECT_SYSER(1, gettimeofday(NULL, (void *)1), -1, EFAULT); break;
 		CASE_TEST(gettimeofday_bad2); EXPECT_SYSER(1, gettimeofday(NULL, (void *)1), -1, EFAULT); break;
 #endif
+		CASE_TEST(getpagesize);       EXPECT_SYSZR(1, test_getpagesize()); break;
 		CASE_TEST(ioctl_tiocinq);     EXPECT_SYSZR(1, ioctl(0, TIOCINQ, &tmp)); break;
 		CASE_TEST(ioctl_tiocinq);     EXPECT_SYSZR(1, ioctl(0, TIOCINQ, &tmp)); break;
 		CASE_TEST(link_root1);        EXPECT_SYSER(1, link("/", "/"), -1, EEXIST); break;
diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index 66d0414d8e4b..b52d5069563c 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -159,6 +159,9 @@ identify_boot_image () {
 		qemu-system-aarch64)
 			echo arch/arm64/boot/Image
 			;;
+		qemu-system-s390x)
+			echo arch/s390/boot/bzImage
+			;;
 		*)
 			echo vmlinux
 			;;
@@ -184,6 +187,9 @@ identify_qemu () {
 	elif echo $u | grep -q aarch64
 	then
 		echo qemu-system-aarch64
+	elif echo $u | grep -q 'IBM S/390'
+	then
+		echo qemu-system-s390x
 	elif uname -a | grep -q ppc64
 	then
 		echo qemu-system-ppc64
diff --git a/tools/testing/selftests/rcutorture/bin/mkinitrd.sh b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh
index 70d62fd0d31d..71f0dfbb2a6d 100755
--- a/tools/testing/selftests/rcutorture/bin/mkinitrd.sh
+++ b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh
@@ -64,7 +64,7 @@ ___EOF___
 # build using nolibc on supported archs (smaller executable) and fall
 # back to regular glibc on other ones.
 if echo -e "#if __x86_64__||__i386__||__i486__||__i586__||__i686__" \
-           "||__ARM_EABI__||__aarch64__\nyes\n#endif" \
+           "||__ARM_EABI__||__aarch64__||__s390x__\nyes\n#endif" \
    | ${CROSS_COMPILE}gcc -E -nostdlib -xc - \
    | grep -q '^yes'; then
 	# architecture supported by nolibc