Init
在trap_init中对SYSCALL_VECTOR（编号0x80）的向量进行初始化。
set_system_trap_gate(SYSCALL_VECTOR, &system_call);
将system call初始化为trap门，加入到IDT table中，发生中断以后，会跳转到对应system_call的地址去执行后续的中断流程。发生中断到跳转执行中断向量的过程在kernel 中断分析三——中断处理流程有详细解释，本篇只关注system_call的运行过程。
ENTRY(system_call)
/*
* syscall stub including irq exit should be protected against kprobes
*/
.pushsection .kprobes.text, "ax"
# system call handler stub
ENTRY(system_call)
RING0_INT_FRAME # can't unwind into user space anyway
ASM_CLAC
pushl_cfi %eax # save orig_eax --------------1
SAVE_ALL -----------
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,)
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
- RING0_INT_FRAME设置esp、eip指向内核态，然后将eax中的系统调用号入栈
- 保存现场，即用户态的一些寄存器值
- 将thread_info的地址保存到ebp寄存器
- 当前进程是否有被trace，如果有就执行相关的动作保存当时的追踪信息
- 调用对应的系统调用函数
- 将返回值入栈
- 屏蔽其他中断。检测当前进程是否还有工作没有完成，如果有，那么跳转到syscall_exit_work
- 然后恢复userspace被压入栈的寄存器，返回userspace
restore_all:
TRACE_IRQS_IRET
restore_all_notrace:
#ifdef CONFIG_X86_ESPFIX32
movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS ------------1
# Warning: PT_OLDSS(%esp) contains the wrong/random values if we
# are returning to the kernel.
# See comments in process.c:copy_thread() for details.
movb PT_OLDSS(%esp), %ah
movb PT_CS(%esp), %al
andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << ) | SEGMENT_RPL_MASK), %eax
cmpl $((SEGMENT_LDT << ) | USER_RPL), %eax
CFI_REMEMBER_STATE
je ldt_ss # returning to user-space with LDT SS
#endif
restore_nocheck:
RESTORE_REGS # skip orig_eax/error_code
irq_return:
INTERRUPT_RETURN ----------
.section .fixup,"ax"
ENTRY(iret_exc)
pushl $ # no error code
pushl $do_iret_error
jmp error_code
.previous
_ASM_EXTABLE(irq_return,iret_exc)
#ifdef CONFIG_X86_ESPFIX32
CFI_RESTORE_STATE
ldt_ss:
#ifdef CONFIG_PARAVIRT
/*
* The kernel can't run on a non-flat stack if paravirt mode
* is active. Rather than try to fixup the high bits of
* ESP, bypass this code entirely. This may break DOSemu
* and/or Wine support in a paravirt VM, although the option
* is still available to implement the setting of the high
* -bits in the INTERRUPT_RETURN paravirt-op.
*/
cmpl $, pv_info+PARAVIRT_enabled
jne restore_nocheck
#endif
/*
* Setup and switch to ESPFIX stack
*
* We're returning to userspace with a bit stack. The CPU will not
* restore the high word of ESP for us on executing iret... This is an
* "official" bug of all the x86-compatible CPUs, which we can work
* around to make dosemu and wine happy. We do this by preloading the
* high word of ESP with the high word of the userspace ESP while
* compensating for the offset by changing to the ESPFIX segment with
* a base address that matches for the difference.
*/
#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
mov %esp, %edx /* load kernel esp */
mov PT_OLDESP(%esp), %eax /* load userspace esp */
mov %dx, %ax /* eax: new kernel esp */
sub %eax, %edx /* offset (low word is ) */
shr $, %edx
mov %dl, GDT_ESPFIX_SS + /* bits */
mov %dh, GDT_ESPFIX_SS + /* bits */
pushl_cfi $__ESPFIX_SS
pushl_cfi %eax /* new kernel esp */
/* Disable interrupts, but do not irqtrace this section: we
* will soon execute iret and the tracer was already set to
* the irqstate after the iret */
DISABLE_INTERRUPTS(CLBR_EAX)
lss (%esp), %esp /* switch to espfix segment */
CFI_ADJUST_CFA_OFFSET -
jmp restore_nocheck
#endif
CFI_ENDPROC
ENDPROC(system_call)
syscall_exit_work
_TIF_ALLWORK_MASK 的定义如下：
/* Work to do on any return to user space. */
#define _TIF_ALLWORK_MASK \
(_TIF_SIGPENDING|_TIF_NEED_RESCHED|_TIF_SINGLESTEP|\
_TIF_ASYNC_TLB|_TIF_NOTIFY_RESUME)
当以下情况之一发生时，返回用户态之前需要进入syscall_exit_work处理：
1. 当前进程有信号pending
2. 当前进程需要被重新调度
3. 设置了_TIF_SINGLESTEP，restore singlestep on return to user mode
4. got an async TLB fault in kernel
5. callback before returning to user
syscall_exit_work:
testl $_TIF_WORK_SYSCALL_EXIT, %ecx----------
jz work_pending
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)
- 检测是否有work pending
- 否则开中断然后返回用户态
work_pending:
testb $_TIF_NEED_RESCHED, %cl -------------
jz work_notifysig -------------
work_resched: -------------
call schedule
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-------------------4
# 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
:
#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 b
#endif
END(work_pending)
- 检测_TIF_NEED_RESCHED，若被设置，跳转到work_resched，否则跳转到work_notifysig，进行信号处理
- 调用schedule主动让出CPU
- 处理pending的信号，具体的处理流程在do_notify_resume 中的do_signal
整个处理流程用流程图表现得更加直观：
![大话Linux内核中锁机制之原子操作、自旋锁[图]](data:image/gif;base64,R0lGODlhAQABAIAAAP///wAAACwAAAAAAQABAAACAkQBADs=)