[PATCH v3 0/5] add s390 support to nolibc and rcutorture

[PATCH v3 0/5] add s390 support to nolibc and rcutorture

[Sven Schnelle]

Hi,

these patches add support for the s390 architecture both to nolibc
and rcutorture. Note that this only adds support for the 64 bit
version, no support for 31 bit (compat) is added. For nolibc it
includes one bugfix to make the fd_set datatype match the kernel
type.

Changes in v3:

- fix envp handling in startup assembly

Changes in v2:

- use __attribute__((unused)) instead of __maybe_unused
- prefer aghi over lay, as lay is not present in all architecure levels
- add -m64 CFLAG to force 64 bit mode for compiler that can do 31bit and 64bit mode

Sven Schnelle (5):
  nolibc: fix fd_set type
  nolibc: add support for s390
  selftests/nolibc: add s390 support
  rcutorture: add support for s390
  rcutorture: build initrd for rcutorture with nolibc

 tools/include/nolibc/arch-s390.h              | 222 ++++++++++++++++++
 tools/include/nolibc/arch.h                   |   2 +
 tools/include/nolibc/sys.h                    |   2 +
 tools/include/nolibc/types.h                  |  53 +++--
 tools/testing/selftests/nolibc/Makefile       |   7 +-
 .../selftests/rcutorture/bin/functions.sh     |   6 +
 .../selftests/rcutorture/bin/mkinitrd.sh      |   2 +-
 7 files changed, 269 insertions(+), 25 deletions(-)
 create mode 100644 tools/include/nolibc/arch-s390.h

-- 
2.34.1

[PATCH v3 1/5] nolibc: fix fd_set type

[Sven Schnelle]

The kernel uses unsigned long for the fd_set bitmap,
but nolibc use u32. This works fine on little endian
machines, but fails on big endian. Convert to unsigned
long to fix this.

Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
---
 tools/include/nolibc/types.h | 53 ++++++++++++++++++++----------------
 1 file changed, 30 insertions(+), 23 deletions(-)

diff --git a/tools/include/nolibc/types.h b/tools/include/nolibc/types.h
index 959997034e55..300e0ff1cd58 100644
--- a/tools/include/nolibc/types.h
+++ b/tools/include/nolibc/types.h
@@ -89,39 +89,46 @@
 #define EXIT_SUCCESS 0
 #define EXIT_FAILURE 1
 
+#define FD_SETIDXMASK (8 * sizeof(unsigned long))
+#define FD_SETBITMASK (8 * sizeof(unsigned long)-1)
+
 /* for select() */
 typedef struct {
-	uint32_t fd32[(FD_SETSIZE + 31) / 32];
+	unsigned long fds[(FD_SETSIZE + FD_SETBITMASK) / FD_SETIDXMASK];
 } fd_set;
 
-#define FD_CLR(fd, set) do {                                            \
-		fd_set *__set = (set);                                  \
-		int __fd = (fd);                                        \
-		if (__fd >= 0)                                          \
-			__set->fd32[__fd / 32] &= ~(1U << (__fd & 31)); \
+#define FD_CLR(fd, set) do {						\
+		fd_set *__set = (set);					\
+		int __fd = (fd);					\
+		if (__fd >= 0)						\
+			__set->fds[__fd / FD_SETIDXMASK] &=		\
+				~(1U << (__fd & FX_SETBITMASK));	\
 	} while (0)
 
-#define FD_SET(fd, set) do {                                            \
-		fd_set *__set = (set);                                  \
-		int __fd = (fd);                                        \
-		if (__fd >= 0)                                          \
-			__set->fd32[__fd / 32] |= 1U << (__fd & 31);    \
+#define FD_SET(fd, set) do {						\
+		fd_set *__set = (set);					\
+		int __fd = (fd);					\
+		if (__fd >= 0)						\
+			__set->fds[__fd / FD_SETIDXMASK] |=		\
+				1 << (__fd & FD_SETBITMASK);		\
 	} while (0)
 
-#define FD_ISSET(fd, set) ({                                                  \
-		fd_set *__set = (set);                                        \
-		int __fd = (fd);                                              \
-		int __r = 0;                                                  \
-		if (__fd >= 0)                                                \
-			__r = !!(__set->fd32[__fd / 32] & 1U << (__fd & 31)); \
-		__r;                                                          \
+#define FD_ISSET(fd, set) ({						\
+			fd_set *__set = (set);				\
+			int __fd = (fd);				\
+		int __r = 0;						\
+		if (__fd >= 0)						\
+			__r = !!(__set->fds[__fd / FD_SETIDXMASK] &	\
+1U << (__fd & FD_SET_BITMASK));						\
+		__r;							\
 	})
 
-#define FD_ZERO(set) do {                                               \
-		fd_set *__set = (set);                                  \
-		int __idx;                                              \
-		for (__idx = 0; __idx < (FD_SETSIZE+31) / 32; __idx ++) \
-			__set->fd32[__idx] = 0;                         \
+#define FD_ZERO(set) do {						\
+		fd_set *__set = (set);					\
+		int __idx;						\
+		int __size = (FD_SETSIZE+FD_SETBITMASK) / FD_SETIDXMASK;\
+		for (__idx = 0; __idx < __size; __idx++)		\
+			__set->fds[__idx] = 0;				\
 	} while (0)
 
 /* for poll() */
-- 
2.34.1

[PATCH v3 2/5] nolibc: add support for s390

[Sven Schnelle]

Use arch-x86_64 as a template. Not really different, but
we have our own mmap syscall which takes a structure instead
of discrete arguments.

Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Acked-by: Heiko Carstens <hca@linux.ibm.com>
---
 tools/include/nolibc/arch-s390.h | 222 +++++++++++++++++++++++++++++++
 tools/include/nolibc/arch.h      |   2 +
 tools/include/nolibc/sys.h       |   2 +
 3 files changed, 226 insertions(+)
 create mode 100644 tools/include/nolibc/arch-s390.h

diff --git a/tools/include/nolibc/arch-s390.h b/tools/include/nolibc/arch-s390.h
new file mode 100644
index 000000000000..76bc8fdaf922
--- /dev/null
+++ b/tools/include/nolibc/arch-s390.h
@@ -0,0 +1,222 @@
+/* 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>
+
+/* O_* macros for fcntl/open are architecture-specific */
+#define O_RDONLY            0
+#define O_WRONLY            1
+#define O_RDWR              2
+#define O_CREAT          0x40
+#define O_EXCL           0x80
+#define O_NOCTTY        0x100
+#define O_TRUNC         0x200
+#define O_APPEND        0x400
+#define O_NONBLOCK      0x800
+#define O_DIRECTORY   0x10000
+
+/* The struct returned by the stat() syscall, equivalent to stat64(). The
+ * syscall returns 116 bytes and stops in the middle of __unused.
+ */
+
+struct sys_stat_struct {
+	unsigned long	st_dev;
+	unsigned long	st_ino;
+	unsigned long	st_nlink;
+	unsigned int	st_mode;
+	unsigned int	st_uid;
+	unsigned int	st_gid;
+	unsigned int	__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;								\
+})
+
+/* startup code */
+__asm__ (".section .text\n"
+	 ".weak _start\n"
+	 "_start:\n"
+	 "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 */
+
+	 "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"
+	 "");
+
+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.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/sys.h b/tools/include/nolibc/sys.h
index ce3ee03aa679..3db1dd8c74ee 100644
--- a/tools/include/nolibc/sys.h
+++ b/tools/include/nolibc/sys.h
@@ -686,6 +686,7 @@ 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 +708,7 @@ 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)
-- 
2.34.1

[PATCH v3 3/5] selftests/nolibc: add s390 support

[Sven Schnelle]

Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Acked-by: Heiko Carstens <hca@linux.ibm.com>
---
 tools/testing/selftests/nolibc/Makefile | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile
index 22f1e1d73fa8..2bf613ee363d 100644
--- a/tools/testing/selftests/nolibc/Makefile
+++ b/tools/testing/selftests/nolibc/Makefile
@@ -19,6 +19,7 @@ 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))
 
@@ -29,6 +30,7 @@ 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)
@@ -41,6 +43,7 @@ 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
@@ -50,6 +53,7 @@ QEMU_ARGS_arm64   = -M virt -cpu cortex-a53 -append "panic=-1 $(TEST:%=NOLIBC_TE
 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 +66,8 @@ 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:
-- 
2.34.1

Re: [PATCH v3 3/5] selftests/nolibc: add s390 support

[Heiko Carstens]

On Tue, Jan 03, 2023 at 08:19:55AM +0100, Sven Schnelle wrote:
> Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
> Acked-by: Heiko Carstens <hca@linux.ibm.com>
> ---
>  tools/testing/selftests/nolibc/Makefile | 7 ++++++-
>  1 file changed, 6 insertions(+), 1 deletion(-)
...
> -CFLAGS  ?= -Os -fno-ident -fno-asynchronous-unwind-tables
> +CFLAGS_s390 = -m64
> +CFLAGS  ?= -Os -fno-ident -fno-asynchronous-unwind-tables $(CFLAGS_$(ARCH))

Since this adds support for architecture specific compile flags, you
might as well want to add -march=z10, since that's the minimum
architecture level for the kernel we support anyway.

That way you won't end up with problems like the lay instruction, and
could also use cghsi for zero comparison. Not that I'm proposing that
you should change the asm code again, it is fine as it is now.

[PATCH v3 4/5] rcutorture: add support for s390

[Sven Schnelle]

Add the required values to identify_qemu() and
identify_bootimage().

Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Acked-by: Heiko Carstens <hca@linux.ibm.com>
---
 tools/testing/selftests/rcutorture/bin/functions.sh | 6 ++++++
 1 file changed, 6 insertions(+)

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
-- 
2.34.1

[PATCH v3 5/5] rcutorture: build initrd for rcutorture with nolibc

[Sven Schnelle]

This reduces the size of init from ~600KB to ~1KB.

Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Acked-by: Heiko Carstens <hca@linux.ibm.com>
---
 tools/testing/selftests/rcutorture/bin/mkinitrd.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

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
-- 
2.34.1

Re: [PATCH v3 0/5] add s390 support to nolibc and rcutorture

[Willy Tarreau]

Hi Sven,

On Tue, Jan 03, 2023 at 08:19:52AM +0100, Sven Schnelle wrote:
> Hi,
> 
> these patches add support for the s390 architecture both to nolibc
> and rcutorture. Note that this only adds support for the 64 bit
> version, no support for 31 bit (compat) is added. For nolibc it
> includes one bugfix to make the fd_set datatype match the kernel
> type.

Perfect, looks clean and works out of the box now. I've queued the
fd_set one for fixes and will submit the rest to Paul for his dev
branch. Thank you!

Willy