系统调用是操作系统提供给用户(应用程序)的一组接口,每个系统调用都有一个对应的系统调用函数来完成相应的工作。用户通过这个接口向操作系统申请服务,如访问硬件,管理进程等等。但是因为用户程序运行在用户空间,而系统调用运行在内核空间,因此用户程序不能直接调用系统调用函数,我们经常看到的比如fork、open、write 等等函数实际上并不是真正的系统调用函数,他们都只是c库,在这些函数里将执行一个软中断 swi 指令,产生一个软中断,使CPU 陷入内核态,接着在内核中进行一系列的判断,判断出是哪个系统调用,再转到真正的系统调用函数,完成相应的功能。下面举一个简单的例子说明从用户态调用一个“系统调用”,到内核处理的整个执行流程。
用户态程序如下:
void pk()
{
__asm__(
"ldrr7=365 \n"
"swi \n"
:
:
:
);
}
int main()
{
pk();
retrun 0;
}
上面的代码中,我自己实现了一个新的系统调用,具体怎么做,后面再具体描述。pk()事实上就可以类比于平时我们在用户程序里调用的 open() 等函数,这个函数只做了一件简单的事:将系统调用号传给 r7 ,,然后产生一软中断。接着CPU陷入内核
内核态:
CPU相应这个软中断以后,PC指针会到相应的中断向量表中取指,中断向量表在内核代码中:arch/arm/kernel/entry-armv.S中定义
.LCvswi:
.word vector_swi
.globl __stubs_end
__stubs_end:
.equ stubs_offset, __vectors_start + 0x200 - __stubs_start
.globl __vectors_start
__vectors_start:
ARM( swi SYS_ERROR0 )
THUMB( svc #0)
THUMB( nop )
W(b) vector_und + stubs_offset
W(ldr) pc, .LCvswi + stubs_offset#响应中断后pc指向这里
W(b) vector_pabt + stubs_offset
W(b) vector_dabt + stubs_offset
W(b) vector_addrexcptn + stubs_offset
W(b) vector_irq + stubs_offset
W(b) vector_fiq + stubs_offset
.globl __vectors_end
__vectors_end:
当pc取到如上的指令后,会跳到 vector_swi 这个标号,这个标号在arch/arm/kernel/entry-commen.S 中定义。
.align 5
ENTRY(vector_swi)
sub sp, sp, #S_FRAME_SIZE
stmia sp, {r0 - r12} @ Calling r0 - r12
ARM( add r8, sp, #S_PC)
ARM( stmdb r8, {sp, lr}^) @ Calling sp, lr
THUMB( mov r8, sp )
THUMB( store_user_sp_lr r8, r10, S_SP ) @ calling sp, lr
mrs r8, spsr @ called from non-FIQ mode, so ok.
str lr, [sp, #S_PC] @ Save calling PC
str r8, [sp, #S_PSR]@ Save CPSR
str r0, [sp, #S_OLD_R0]@ Save OLD_R0
zero_fp
/*
* Get the system call number.#取出系统调用号
*/
#if defined(CONFIG_OABI_COMPAT)
/*
* If we have CONFIG_OABI_COMPAT then we need to look at the swi
* value to determine if it is an EABI or an old ABI call.
*/
#ifdef CONFIG_ARM_THUMB
tst r8, #PSR_T_BIT
movne r10, #0@ no thumb OABI emulation
ldreq r10, [lr, #-4] @ get SWI instruction
#else
ldr r10, [lr, #-4] @ get SWI instruction
A710( and ip, r10, #0x0f000000@ check for SWI)
A710( teq ip, #0x0f000000)
A710( bne .Larm710bug)
#endif
#ifdef CONFIG_CPU_ENDIAN_BE8
rev r10, r10 @ little endian instruction
#endif
#elif defined(CONFIG_AEABI)
/*
* Pure EABI user space always put syscall number into scno (r7).
*/
A710( ldr ip, [lr, #-4] @ get SWI instruction )
A710( and ip, ip, #0x0f000000@ check for SWI)
A710( teq ip, #0x0f000000)
A710( bne .Larm710bug)
#elif defined(CONFIG_ARM_THUMB)
/* Legacy ABI only, possibly thumb mode. */
tst r8, #PSR_T_BIT @ this is SPSR from save_user_regs
addne scno, r7, #__NR_SYSCALL_BASE @ put OS number in
ldreq scno, [lr, #-4]
#else
/* Legacy ABI only. */
ldr scno, [lr, #-4] @ get SWI instruction
A710( and ip, scno, #0x0f000000@ check for SWI)
A710( teq ip, #0x0f000000)
A710( bne .Larm710bug)
#endif
#ifdef CONFIG_ALIGNMENT_TRAP
ldr ip, __cr_alignment
ldr ip, [ip]
mcr p15, 0, ip, c1, c0@ update control register
#endif
enable_irq
get_thread_info tsk
adr tbl, sys_call_table@ load syscall table pointer#获取系统调用表的基地址
ldr ip, [tsk, #TI_FLAGS]@ check for syscall tracing
#if defined(CONFIG_OABI_COMPAT)
/*
* If the swi argument is zero, this is an EABI call and we do nothing.
*
* If this is an old ABI call, get the syscall number into scno and
* get the old ABI syscall table address.
*/
bics r10, r10, #0xff000000
eorne scno, r10, #__NR_OABI_SYSCALL_BASE
ldrne tbl, =sys_oabi_call_table
#elif !defined(CONFIG_AEABI)
bic scno, scno, #0xff000000@ mask off SWI op-code
eor scno, scno, #__NR_SYSCALL_BASE @ check OS number
#endif
stmdb sp!, {r4, r5} @ push fifth and sixth args
tst ip, #_TIF_SYSCALL_TRACE@ are we tracing syscalls?
bne __sys_trace
cmp scno, #NR_syscalls@ check upper syscall limit
adr lr, BSYM(ret_fast_syscall) @ return address
ldrcc pc, [tbl, scno, lsl #2]@ call sys_* routine#跳到系统调用函数
add r1, sp, #S_OFF
2: mov why, #0@ no longer a real syscall
cmp scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE)
eor r0, scno, #__NR_SYSCALL_BASE @ put OS number back
bcs arm_syscall
b sys_ni_syscall @ not private func
从上面可以看出,当CPU从中断向量表转到vector_swi 之后,完成了几件事情:1.取出系统调用号 2.根据系统调用号取出系统调用函数在系统调用表的基地址,得到一个系统调用函数的函数指针 3. 根据系统调用表的基地址和系统调用号,得到这个系统调用表里的项,每一个表项都是一个函数指针,把这个函数指针赋给PC , 则实现了跳转到系统调用函数。
系统调用表定义在:arch/arm/kernel/Calls.S
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
*This file is included thrice in entry-common.S
*/
/* 0 */CALL(sys_restart_syscall)
CALL(sys_exit)
CALL(sys_fork_wrapper)
CALL(sys_read)
CALL(sys_write)
/* 5 */CALL(sys_open)
CALL(sys_close)
CALL(sys_ni_syscall)/* was sys_waitpid */
CALL(sys_creat)
CALL(sys_link)
/* 10 */ CALL(sys_unlink)
CALL(sys_execve_wrapper)
CALL(sys_chdir)
CALL(OBSOLETE(sys_time)) /* used by libc4 */
CALL(sys_mknod)
/* 15 */ CALL(sys_chmod)
CALL(sys_lchown16)
CALL(sys_ni_syscall)/* was sys_break */
CALL(sys_ni_syscall)/* was sys_stat */
CALL(sys_lseek)
/* 20 */ CALL(sys_getpid)
CALL(sys_mount)
CALL(OBSOLETE(sys_oldumount)) /* used by libc4 */
CALL(sys_setuid16)
CALL(sys_getuid16)
/* 25 */ CALL(OBSOLETE(sys_stime))
CALL(sys_ptrace)
CALL(OBSOLETE(sys_alarm)) /* used by libc4 */
CALL(sys_ni_syscall)/* was sys_fstat */
CALL(sys_pause)
/* 30 */ CALL(OBSOLETE(sys_utime)) /* used by libc4 */
CALL(sys_ni_syscall)/* was sys_stty */
CALL(sys_ni_syscall)/* was sys_getty */
CALL(sys_access)
CALL(sys_nice)
/* 35 */ CALL(sys_ni_syscall)/* was sys_ftime */
CALL(sys_sync)
CALL(sys_kill)
CALL(sys_rename)
CALL(sys_mkdir)
/* 40 */ CALL(sys_rmdir)
CALL(sys_dup)
CALL(sys_pipe)
CALL(sys_times)
CALL(sys_ni_syscall)/* was sys_prof */
/* 45 */ CALL(sys_brk)
CALL(sys_setgid16)
CALL(sys_getgid16)
CALL(sys_ni_syscall)/* was sys_signal */
CALL(sys_geteuid16)
/* 50 */ CALL(sys_getegid16)
CALL(sys_acct)
CALL(sys_umount)
CALL(sys_ni_syscall)/* was sys_lock */
CALL(sys_ioctl)
/* 55 */ CALL(sys_fcntl)
.......
CALL(sys_eventfd2)
CALL(sys_epoll_create1)
CALL(sys_dup3)
CALL(sys_pipe2)
/* 360 */ CALL(sys_inotify_init1)
CALL(sys_preadv)
CALL(sys_pwritev)
CALL(sys_rt_tgsigqueueinfo)
CALL(sys_perf_event_open)
CALL(sys_pk)#我自己加的系统调用
了解了一个系统调用的执行过程就可以试着添加一个自己的系统调用了:
内核:
1. 在内核代码实现一个系统调用函数,即 sys_xxx()函数,如我在 kernel/printk.c 中添加了
void pk()
{
printk(KERN_WARNING"this is my first sys call !\n");
}
2. 添加系统调用号 在 arch/arm/include/asm/Unistd.h
添加#define __NR_pk(__NR_SYSCALL_BASE+365)
3. 添加调用函数指针列表 在arch/arm/keenel/Calls.S
添加 CALL(sys_pk)
4.声明自己的系统调用函数 在include/linux/syscall.h
添加asmlinkage long sys_pk()
用户空间:
void pk()
{
__asm__(
"ldrr7=365 \n"
"swi \n"
:
:
:
);
}
int main()
{
pk();
retrun 0;
}
完成上面的编写以后就可以编译内核和应用程序了。
将生成的文件在arm开发板上运行可以打印出: This is my first sys call!
说明我添加的系统调用可以使用。
至此,描述系统调用的实现机制和添加一个新的系统调用就完成了。