Linux 0.12中的系统调用。
1. 系统调用_syscalln
在Linux 0.12中，系统调用定义有4类，分别为_syscall0、_syscall1、_syscall2、_syscall3（0-3表示携带的参数个数），定义如下（在linux-0.12/include/unistd.h文件中定义）：
#define _syscall0(type,name) \
type name(void) \
{ \
long __res; \
__asm__ volatile ("int $0x80" \
: "=a" (__res) \
: "0" (__NR_##name)); \
if (__res >= 0) \
return (type) __res; \
errno = -__res; \
return -1; \
}
#define _syscall1(type,name,atype,a) \
type name(atype a) \
{ \
long __res; \
__asm__ volatile ("int $0x80" \
: "=a" (__res) \
: "0" (__NR_##name),"b" ((long)(a))); \
if (__res >= 0) \
return (type) __res; \
errno = -__res; \
return -1; \
}
#define _syscall2(type,name,atype,a,btype,b) \
type name(atype a,btype b) \
{ \
long __res; \
__asm__ volatile ("int $0x80" \
: "=a" (__res) \
: "0" (__NR_##name),"b" ((long)(a)),"c" ((long)(b))); \
if (__res >= 0) \
return (type) __res; \
errno = -__res; \
return -1; \
}
#define _syscall3(type,name,atype,a,btype,b,ctype,c) \
type name(atype a,btype b,ctype c) \
{ \
long __res; \
__asm__ volatile ("int $0x80" \
: "=a" (__res) \
: "0" (__NR_##name),"b" ((long)(a)),"c" ((long)(b)),"d" ((long)(c))); \
if (__res>=0) \
return (type) __res; \
errno=-__res; \
return -1; \
}
1.1 _syscall0
_syscall0定义如下，不带任何参数：
#define _syscall0(type,name) \
type name(void) \
{ \
long __res; \
__asm__ volatile ("int $0x80" \
: "=a" (__res) \ // 输出寄存器列表
: "0" (__NR_##name)); \ // 输入寄存器列表
if (__res >= 0) \
return (type) __res; \
errno = -__res; \
return -1; \
}
__asm__，嵌入汇编，详情见：Extended Asm (Using the GNU Compiler Collection (GCC))，
asm asm-qualifiers ( AssemblerTemplate
: OutputOperands
: InputOperands
: Clobbers
: GotoLabels)
__volatile__，告诉编译器不要优化代码，直接从内存读取数据，而不是从cache__NR_##name，##表示将左侧和右侧的字符连联结在一起，举例，_syscall0(int,fork)，此时为__NR_fork，在Linux 0.12中找到这些系统调用，
// linux-0.12/init/main.c
static inline _syscall0(int,fork)
static inline _syscall0(int,pause)
static inline _syscall0(int,sync)
// linux-0.12/lib/setsid.c
_syscall0(pid_t,setsid)
int $0x80 ...，向内核发出一个中断调用int 0x80，开始执行一个系统调用。- 输出寄存器列表：
"=a" (__res)，=表示这是输出寄存器，a表示使用寄存器eax，执行完汇编写语句后，输出寄存器eax的值放入__res - 输入寄存器列表：
"0" (__NR_##name));，0表示使用与上面相同位置上的输出寄存器，即eax
- 输出寄存器列表：
1.2 _syscall3
以write系统调用为例，
#define __LIBRARY__
#include <unistd.h>
_syscall3(int,write,int,fd,const char *,buf,off_t,count)
_syscall3在linux-0.12/include/unistd.h定义，
#define _syscall3(type,name,atype,a,btype,b,ctype,c) \
type name(atype a,btype b,ctype c) \
{ \
long __res; \
__asm__ volatile ("int $0x80" \
: "=a" (__res) \
: "0" (__NR_##name),"b" ((long)(a)),"c" ((long)(b)),"d" ((long)(c))); \
if (__res>=0) \
return (type) __res; \
errno=-__res; \
return -1; \
}
- 输入寄存器列表：
b表示使用寄存器ebx，c表示使用寄存器ecx，d表示使用寄存器edx
1.3 系统调用功能号
Linux给每个系统调用指派一个唯一的系统调用功能号，在linux-0.12/include/unistd.h定义，以__NR_作为前缀，
#define __NR_setup 0 /* used only by init, to get system going */
#define __NR_exit 1
#define __NR_fork 2
#define __NR_read 3
#define __NR_write 4
#define __NR_open 5
#define __NR_close 6
#define __NR_waitpid 7
#define __NR_creat 8
#define __NR_link 9
#define __NR_unlink 10
#define __NR_execve 11
#define __NR_chdir 12
#define __NR_time 13
#define __NR_mknod 14
#define __NR_chmod 15
#define __NR_chown 16
#define __NR_break 17
#define __NR_stat 18
#define __NR_lseek 19
#define __NR_getpid 20
#define __NR_mount 21
#define __NR_umount 22
#define __NR_setuid 23
#define __NR_getuid 24
#define __NR_stime 25
#define __NR_ptrace 26
#define __NR_alarm 27
#define __NR_fstat 28
#define __NR_pause 29
#define __NR_utime 30
#define __NR_stty 31
#define __NR_gtty 32
#define __NR_access 33
#define __NR_nice 34
#define __NR_ftime 35
#define __NR_sync 36
#define __NR_kill 37
#define __NR_rename 38
#define __NR_mkdir 39
#define __NR_rmdir 40
#define __NR_dup 41
#define __NR_pipe 42
#define __NR_times 43
#define __NR_prof 44
#define __NR_brk 45
#define __NR_setgid 46
#define __NR_getgid 47
#define __NR_signal 48
#define __NR_geteuid 49
#define __NR_getegid 50
#define __NR_acct 51
#define __NR_phys 52
#define __NR_lock 53
#define __NR_ioctl 54
#define __NR_fcntl 55
#define __NR_mpx 56
#define __NR_setpgid 57
#define __NR_ulimit 58
#define __NR_uname 59
#define __NR_umask 60
#define __NR_chroot 61
#define __NR_ustat 62
#define __NR_dup2 63
#define __NR_getppid 64
#define __NR_getpgrp 65
#define __NR_setsid 66
#define __NR_sigaction 67
#define __NR_sgetmask 68
#define __NR_ssetmask 69
#define __NR_setreuid 70
#define __NR_setregid 71
#define __NR_sigsuspend 72
#define __NR_sigpending 73
#define __NR_sethostname 74
#define __NR_setrlimit 75
#define __NR_getrlimit 76
#define __NR_getrusage 77
#define __NR_gettimeofday 78
#define __NR_settimeofday 79
#define __NR_getgroups 80
#define __NR_setgroups 81
#define __NR_select 82
#define __NR_symlink 83
#define __NR_lstat 84
#define __NR_readlink 85
#define __NR_uselib 86
这些系统调用号对应于调用处理程序指针数组表sys_call_table[]（在linux-0.12/include/linux/sys.h中定义），
extern int sys_setup();
extern int sys_exit();
extern int sys_fork();
extern int sys_read();
extern int sys_write();
extern int sys_open();
extern int sys_close();
extern int sys_waitpid();
extern int sys_creat();
extern int sys_link();
extern int sys_unlink();
extern int sys_execve();
extern int sys_chdir();
extern int sys_time();
extern int sys_mknod();
extern int sys_chmod();
extern int sys_chown();
extern int sys_break();
extern int sys_stat();
extern int sys_lseek();
extern int sys_getpid();
extern int sys_mount();
extern int sys_umount();
extern int sys_setuid();
extern int sys_getuid();
extern int sys_stime();
extern int sys_ptrace();
extern int sys_alarm();
extern int sys_fstat();
extern int sys_pause();
extern int sys_utime();
extern int sys_stty();
extern int sys_gtty();
extern int sys_access();
extern int sys_nice();
extern int sys_ftime();
extern int sys_sync();
extern int sys_kill();
extern int sys_rename();
extern int sys_mkdir();
extern int sys_rmdir();
extern int sys_dup();
extern int sys_pipe();
extern int sys_times();
extern int sys_prof();
extern int sys_brk();
extern int sys_setgid();
extern int sys_getgid();
extern int sys_signal();
extern int sys_geteuid();
extern int sys_getegid();
extern int sys_acct();
extern int sys_phys();
extern int sys_lock();
extern int sys_ioctl();
extern int sys_fcntl();
extern int sys_mpx();
extern int sys_setpgid();
extern int sys_ulimit();
extern int sys_uname();
extern int sys_umask();
extern int sys_chroot();
extern int sys_ustat();
extern int sys_dup2();
extern int sys_getppid();
extern int sys_getpgrp();
extern int sys_setsid();
extern int sys_sigaction();
extern int sys_sgetmask();
extern int sys_ssetmask();
extern int sys_setreuid();
extern int sys_setregid();
extern int sys_sigpending();
extern int sys_sigsuspend();
extern int sys_sethostname();
extern int sys_setrlimit();
extern int sys_getrlimit();
extern int sys_getrusage();
extern int sys_gettimeofday();
extern int sys_settimeofday();
extern int sys_getgroups();
extern int sys_setgroups();
extern int sys_select();
extern int sys_symlink();
extern int sys_lstat();
extern int sys_readlink();
extern int sys_uselib();
fn_ptr sys_call_table[] = { sys_setup, sys_exit, sys_fork, sys_read,
sys_write, sys_open, sys_close, sys_waitpid, sys_creat, sys_link,
sys_unlink, sys_execve, sys_chdir, sys_time, sys_mknod, sys_chmod,
sys_chown, sys_break, sys_stat, sys_lseek, sys_getpid, sys_mount,
sys_umount, sys_setuid, sys_getuid, sys_stime, sys_ptrace, sys_alarm,
sys_fstat, sys_pause, sys_utime, sys_stty, sys_gtty, sys_access,
sys_nice, sys_ftime, sys_sync, sys_kill, sys_rename, sys_mkdir,
sys_rmdir, sys_dup, sys_pipe, sys_times, sys_prof, sys_brk, sys_setgid,
sys_getgid, sys_signal, sys_geteuid, sys_getegid, sys_acct, sys_phys,
sys_lock, sys_ioctl, sys_fcntl, sys_mpx, sys_setpgid, sys_ulimit,
sys_uname, sys_umask, sys_chroot, sys_ustat, sys_dup2, sys_getppid,
sys_getpgrp, sys_setsid, sys_sigaction, sys_sgetmask, sys_ssetmask,
sys_setreuid,sys_setregid, sys_sigsuspend, sys_sigpending, sys_sethostname,
sys_setrlimit, sys_getrlimit, sys_getrusage, sys_gettimeofday,
sys_settimeofday, sys_getgroups, sys_setgroups, sys_select, sys_symlink,
sys_lstat, sys_readlink, sys_uselib };
fn_ptr实为函数指针，在linux-0.12/include/linux/sched.h中定义typedef int (*fn_ptr)();。
2. 系统调用处理
系统调用处理程序，linux-0.12/kernel/sys_call.s，
_system_call:
push %ds
push %es
push %fs
pushl %eax # save the orig_eax
pushl %edx
pushl %ecx # push %ebx,%ecx,%edx as parameters
pushl %ebx # to the system call
movl $0x10,%edx # set up ds,es to kernel space
mov %dx,%ds
mov %dx,%es
movl $0x17,%edx # fs points to local data space
mov %dx,%fs
cmpl _NR_syscalls,%eax
jae bad_sys_call
call _sys_call_table(,%eax,4)
pushl %eax
call _sys_call_table(,%eax,4)，实现程序跳转，跳转地址为_sys_call_table + %eax * 4，eax存放的是系统调用功能号。
系统中断调用处理流程如下（图片来源于赵炯《Linux内核完全剖析——基于0.12内核》）：
2.1 系统调用返回后
从系统调用返回，对信号进行识别处理，处理后才退出中断过程。P286
ret_from_sys_call:
movl _current,%eax
cmpl _task,%eax # task[0] cannot have signals
je 3f
cmpw $0x0f,CS(%esp) # was old code segment supervisor ?
jne 3f
cmpw $0x17,OLDSS(%esp) # was stack segment = 0x17 ?
jne 3f
movl signal(%eax),%ebx
movl blocked(%eax),%ecx
notl %ecx
andl %ebx,%ecx
bsfl %ecx,%ecx
je 3f
btrl %ecx,%ebx
movl %ebx,signal(%eax)
incl %ecx
pushl %ecx
call _do_signal
popl %ecx
testl %eax, %eax
jne 2b # see if we need to switch tasks, or do more signals