[PATCH v1 1/8] tools/nolibc: add support for powerpc

From: Zhangjin Wu
Date: Tue Jul 18 2023 - 17:11:05 EST


Both syscall declarations and _start code definition are added for
powerpc to nolibc.

Like mips, powerpc uses a register (exactly, the summary overflow bit)
to record the error occurred, and uses another register to return the
value [1]. So, the return value of every syscall declaration must be
normalized to easier the __sysret helper, return -value when there is an
error, otheriwse, return value directly.

Glibc and musl use different methods to check the summary overflow bit,
glibc (sysdeps/unix/sysv/linux/powerpc/sysdep.h) saves the cr register
to r0 at first, and then check the summary overflow bit in cr0:

mfcr r0
r0 & (1 << 28) ? -r3 : r3

-->

10003c14: 7c 00 00 26 mfcr r0
10003c18: 74 09 10 00 andis. r9,r0,4096
10003c1c: 41 82 00 08 beq 0x10003c24
10003c20: 7c 63 00 d0 neg r3,r3

Musl (arch/powerpc/syscall_arch.h) directly checks the summary overflow
bit with the 'bns' instruction:

/* no summary overflow bit means no error, return value directly */
bns+ 1f
/* otherwise, return negated value */
neg r3, r3
1:

-->

10000418: 40 a3 00 08 bns 0x10000420
1000041c: 7c 63 00 d0 neg r3,r3

The later one is smaller, here applies it.

arch/powerpc/include/asm/vdso/gettimeofday.h file uses the smaller
method for do_syscall_2() too.

[1]: https://man7.org/linux/man-pages/man2/syscall.2.html

Signed-off-by: Zhangjin Wu <falcon@xxxxxxxxxxx>
---
tools/include/nolibc/arch-powerpc.h | 156 ++++++++++++++++++++++++++++
1 file changed, 156 insertions(+)
create mode 100644 tools/include/nolibc/arch-powerpc.h

diff --git a/tools/include/nolibc/arch-powerpc.h b/tools/include/nolibc/arch-powerpc.h
new file mode 100644
index 000000000000..100ec0f412dc
--- /dev/null
+++ b/tools/include/nolibc/arch-powerpc.h
@@ -0,0 +1,156 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * PowerPC specific definitions for NOLIBC
+ * Copyright (C) 2023 Zhangjin Wu <falcon@xxxxxxxxxxx>
+ */
+
+#ifndef _NOLIBC_ARCH_POWERPC_H
+#define _NOLIBC_ARCH_POWERPC_H
+
+#include "compiler.h"
+#include "crt.h"
+
+/* Syscalls for PowerPC :
+ * - stack is 16-byte aligned
+ * - syscall number is passed in r0
+ * - arguments are in r3, r4, r5, r6, r7, r8, r9
+ * - the system call is performed by calling "sc"
+ * - syscall return comes in r3, and the summary overflow bit is checked
+ * to know if an error occurred, in which case errno is in r3.
+ * - the arguments are cast to long and assigned into the target
+ * registers which are then simply passed as registers to the asm code,
+ * so that we don't have to experience issues with register constraints.
+ */
+
+#define _NOLIBC_SYSCALL_CLOBBERLIST \
+ "memory", "cr0", "r9", "r10", "r11", "r12"
+
+#define my_syscall0(num) \
+({ \
+ register long r0 __asm__ ("r0") = (num); \
+ register long r3 __asm__ ("r3"); \
+ \
+ __asm__ volatile ( \
+ "sc; bns+ 1f; neg %1, %1; 1:\n" \
+ : "+r"(r0), "=r"(r3) \
+ :: "r4", "r5", "r6", "r7", "r8", _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ r3; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ register long r0 __asm__ ("r0") = (num); \
+ register long r3 __asm__ ("r3") = (long)(arg1); \
+ \
+ __asm__ volatile ( \
+ "sc; bns+ 1f; neg %1, %1; 1:\n" \
+ : "+r"(r0), "+r"(r3) \
+ :: "r4", "r5", "r6", "r7", "r8", _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ r3; \
+})
+
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ register long r0 __asm__ ("r0") = (num); \
+ register long r3 __asm__ ("r3") = (long)(arg1); \
+ register long r4 __asm__ ("r4") = (long)(arg2); \
+ \
+ __asm__ volatile ( \
+ "sc; bns+ 1f; neg %1, %1; 1:\n" \
+ : "+r"(r0), "+r"(r3), \
+ "+r"(r4) \
+ :: "r5", "r6", "r7", "r8", _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ r3; \
+})
+
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ register long r0 __asm__ ("r0") = (num); \
+ register long r3 __asm__ ("r3") = (long)(arg1); \
+ register long r4 __asm__ ("r4") = (long)(arg2); \
+ register long r5 __asm__ ("r5") = (long)(arg3); \
+ \
+ __asm__ volatile ( \
+ "sc; bns+ 1f; neg %1, %1; 1:\n" \
+ : "+r"(r0), "+r"(r3), \
+ "+r"(r4), "+r"(r5) \
+ :: "r6", "r7", "r8", _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ r3; \
+})
+
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ register long r0 __asm__ ("r0") = (num); \
+ register long r3 __asm__ ("r3") = (long)(arg1); \
+ register long r4 __asm__ ("r4") = (long)(arg2); \
+ register long r5 __asm__ ("r5") = (long)(arg3); \
+ register long r6 __asm__ ("r6") = (long)(arg4); \
+ \
+ __asm__ volatile ( \
+ "sc; bns+ 1f; neg %1, %1; 1:\n" \
+ : "+r"(r0), "+r"(r3), \
+ "+r"(r4), "+r"(r5), "+r"(r6) \
+ :: "r7", "r8", _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ r3; \
+})
+
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ register long r0 __asm__ ("r0") = (num); \
+ register long r3 __asm__ ("r3") = (long)(arg1); \
+ register long r4 __asm__ ("r4") = (long)(arg2); \
+ register long r5 __asm__ ("r5") = (long)(arg3); \
+ register long r6 __asm__ ("r6") = (long)(arg4); \
+ register long r7 __asm__ ("r7") = (long)(arg5); \
+ \
+ __asm__ volatile ( \
+ "sc; bns+ 1f; neg %1, %1; 1:\n" \
+ : "+r"(r0), "+r"(r3), \
+ "+r"(r4), "+r"(r5), "+r"(r6), "+r"(r7) \
+ :: "r8", _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ r3; \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \
+({ \
+ register long r0 __asm__ ("r0") = (num); \
+ register long r3 __asm__ ("r3") = (long)(arg1); \
+ register long r4 __asm__ ("r4") = (long)(arg2); \
+ register long r5 __asm__ ("r5") = (long)(arg3); \
+ register long r6 __asm__ ("r6") = (long)(arg4); \
+ register long r7 __asm__ ("r7") = (long)(arg5); \
+ register long r8 __asm__ ("r8") = (long)(arg6); \
+ \
+ __asm__ volatile ( \
+ "sc; bns+ 1f; neg %1, %1; 1:\n" \
+ : "+r"(r0), "+r"(r3), \
+ "+r"(r4), "+r"(r5), "+r"(r6), "+r"(r7), "+r"(r8) \
+ :: _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ r3; \
+})
+
+/* startup code */
+void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void)
+{
+ __asm__ volatile (
+ "mr 3, 1\n" /* save stack pointer to r3, as arg1 of _start_c */
+ "clrrwi 1, 1, 4\n" /* align the stack to 16 bytes */
+ "li 0, 0\n" /* zero the frame pointer */
+ "stwu 1, -16(1)\n" /* the initial stack frame */
+ "bl _start_c\n" /* transfer to c runtime */
+ );
+ __builtin_unreachable();
+}
+
+#endif /* _NOLIBC_ARCH_POWERPC_H */
--
2.25.1