系统调用system_call的处理过程

本周分析linux源码中系统调用system_call的处理过程

syttem_call位于/linux-3.18.6/arch/x86/kernel/entry_32.S中，源码如下：

<pre name="code" class="plain">ENTRY(system_call)
	RING0_INT_FRAME			# can't unwind into user space anyway
	ASM_CLAC
	pushl_cfi %eax			# save orig_eax
	SAVE_ALL                        #对所有的寄存器进行保存
	GET_THREAD_INFO(%ebp)	# system call tracing in operation / emulation
	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
	jnz syscall_trace_entry
	cmpl $(NR_syscalls), %eax
	jae syscall_badsys
syscall_call:
	call *sys_call_table(,%eax,4)    #根据系统调用表查找相应的系统调用函数，比如我们调用
gitpid(),其对于系统调用函数好为20，系统调用号20通过eax传递过去
syscall_after_call:
	movl %eax,PT_EAX(%esp)		# store the return value
syscall_exit:
	LOCKDEP_SYS_EXIT
	DISABLE_INTERRUPTS(CLBR_ANY)	# make sure we don't miss an interrupt
					# setting need_resched or sigpending
					# between sampling and the iret
	TRACE_IRQS_OFF
	movl TI_flags(%ebp), %ecx
	testl $_TIF_ALLWORK_MASK, %ecx	# current->work
	jne syscall_exit_work           #系统调用过程中可能会发生进程调度，这个函数比较有意思，下面会贴出主要源码分析
restore_all:
	TRACE_IRQS_IRET
restore_all_notrace:

syscall _exit_work主要源码如下，我们会详细分析下

work_pending:
	testb $_TIF_NEED_RESCHED, %cl   #需要重新进程调度吗？
	jz work_notifysig               #是，进行信号处理工作，其源码见下面
work_resched:
	call schedule                   #调用调度器，进行进程的调度工作
	LOCKDEP_SYS_EXIT
	DISABLE_INTERRUPTS(CLBR_ANY)	# make sure we don't miss an interrupt
					# setting need_resched or sigpending
					# between sampling and the iret
	TRACE_IRQS_OFF
	movl TI_flags(%ebp), %ecx
	andl $_TIF_WORK_MASK, %ecx	# is there any work to be done other
					# than syscall tracing?
	jz restore_all
	testb $_TIF_NEED_RESCHED, %cl
	jnz work_resched

work_notifysig:				# deal with pending signals and
					# notify-resume requests
#ifdef CONFIG_VM86
	testl $X86_EFLAGS_VM, PT_EFLAGS(%esp)
	movl %esp, %eax
	jne work_notifysig_v86		# returning to kernel-space or
					# vm86-space
1:
#else
	movl %esp, %eax
#endif
	TRACE_IRQS_ON
	ENABLE_INTERRUPTS(CLBR_NONE)
	movb PT_CS(%esp), %bl
	andb $SEGMENT_RPL_MASK, %bl
	cmpb $USER_RPL, %bl
	jb resume_kernel
	xorl %edx, %edx
	call do_notify_resume
	jmp resume_userspace

#ifdef CONFIG_VM86
	ALIGN
work_notifysig_v86:
	pushl_cfi %ecx			# save ti_flags for do_notify_resume
	call save_v86_state		# %eax contains pt_regs pointer
	popl_cfi %ecx
	movl %eax, %esp
	jmp 1b
#endif
END(work_pending)

	# perform syscall exit tracing
	ALIGN
syscall_trace_entry:
	movl $-ENOSYS,PT_EAX(%esp)
	movl %esp, %eax
	call syscall_trace_enter
	/* What it returned is what we'll actually use.  */
	cmpl $(NR_syscalls), %eax
	jnae syscall_call
	jmp syscall_exit
END(syscall_trace_entry)

	# perform syscall exit tracing
	ALIGN
syscall_exit_work:
	testl $_TIF_WORK_SYSCALL_EXIT, %ecx
	jz work_pending              #在syscall_exit_work过程中有可能会发生进程调度，见上面的work_pending分析
	TRACE_IRQS_ON
	ENABLE_INTERRUPTS(CLBR_ANY)	# could let syscall_trace_leave() call
					# schedule() instead
	movl %esp, %eax
	call syscall_trace_leave
	jmp resume_userspace
END(syscall_exit_work)

小结：system_call进入内核进行系统调用，调用完毕退出的过程中会有进程调度的处理工作

“codeyangjun + 原创作品转载请注明出处 + 《Linux内核分析》MOOC课程http://mooc.study.163.com/course/USTC-1000029000 ”