syscall函数
Syscall函数的定义如下,传入4个参数,返回3个参数。
func syscall(fn, a1, a2, a3 uintptr) (r1, r2 uintptr, err Errno)
syscall函数的作用是传入零碎调用的地址和参数,执行实现后返回。流程次要是零碎调用前执行entersyscall,设置g p的状态,而后入参,执行后,写返回值而后执行exitsyscall设置g p的状态。
entersyscall和exitsyscall在g的调用中细讲。
// func Syscall(trap int64, a1, a2, a3 uintptr) (r1, r2, err uintptr);
// Trap # in AX, args in DI SI DX R10 R8 R9, return in AX DX
// Note that this differs from "standard" ABI convention, which
// would pass 4th arg in CX, not R10.
// 4个入参:PC param1 param2 param3
TEXT ·Syscall(SB),NOSPLIT,$0-56
// 调用entersyscall 判断是执行条件是否满足 记录调度信息 切换g p的状态
CALL runtime·entersyscall(SB)
// 将参数存入寄存器中
MOVQ a1+8(FP), DI
MOVQ a2+16(FP), SI
MOVQ a3+24(FP), DX
MOVQ trap+0(FP), AX // syscall entry
SYSCALL
CMPQ AX, $0xfffffffffffff001
JLS ok
// 执行失败时 写返回值
MOVQ $-1, r1+32(FP)
MOVQ $0, r2+40(FP)
NEGQ AX
MOVQ AX, err+48(FP)
// 调用exitsyscall 记录调度信息
CALL runtime·exitsyscall(SB)
RET
ok:
// 执行胜利时 写返回值
MOVQ AX, r1+32(FP)
MOVQ DX, r2+40(FP)
MOVQ $0, err+48(FP)
CALL runtime·exitsyscall(SB)
RET
TEXT ·RawSyscall(SB),NOSPLIT,$0-56
MOVQ a1+8(FP), DI
MOVQ a2+16(FP), SI
MOVQ a3+24(FP), DX
MOVQ trap+0(FP), AX // syscall entry
SYSCALL
JCC ok1
MOVQ $-1, r1+32(FP) // r1
MOVQ $0, r2+40(FP) // r2
MOVQ AX, err+48(FP) // errno
RET
ok1:
MOVQ AX, r1+32(FP) // r1
MOVQ DX, r2+40(FP) // r2
MOVQ $0, err+48(FP) // errno
RET
显著SysCall比RawSyscall多调用了两个办法,entersyscall和exitsyscall,减少这两个函数的调用,让调度器有机会去对行将要进入零碎调用的goroutine进行调整,不便调度。
entersyscall
// 零碎调用的时候调用该函数
// 进入零碎调用,G将会进入_Gsyscall状态,也就是会被临时挂起,直到零碎调用完结。
// 此时M进入零碎调用,那么P也会放弃该M。然而,此时M还指向P,在M从零碎调用返回后还能找到P
func entersyscall() {
reentersyscall(getcallerpc(), getcallersp())
}
// Syscall跟踪:
// 在零碎调用开始时,咱们收回traceGoSysCall来捕捉堆栈跟踪。
// 如果零碎调用未阻止,则咱们不会收回任何其余事件。
// 如果零碎调用被阻止(即,从新获取了P),则retaker会收回traceGoSysBlock;
// 当syscall返回时,咱们收回traceGoSysExit,当goroutine开始运行时
// (可能立刻,如果exitsyscallfast返回true),咱们收回traceGoStart。
// 为了确保在traceGoSysBlock之后严格收回traceGoSysExit,
// 咱们记得syscalltick的以后值以m为单位(_g_.m.syscalltick = _g_.m.p.ptr()。syscalltick),
// 之后收回traceGoSysBlock的人将递增p.syscalltick;
// 咱们在收回traceGoSysExit之前期待增量。
// 请留神,即便未启用跟踪,增量也会实现,
// 因为能够在syscall的两头启用跟踪。 咱们不心愿期待挂起。
//go:nosplit
func reentersyscall(pc, sp uintptr) {
_g_ := getg()
//禁用抢占,因为在此性能期间g处于Gsyscall状态,但g-> sched可能不统一,请勿让GC察看它。
_g_.m.locks++
// Entersyscall must not call any function that might split/grow the stack.
// (See details in comment above.)
// 捕捉可能产生的调用,办法是将堆栈爱护替换为会使任何堆栈查看失败的内容,并留下一个标记来告诉newstack终止。
_g_.stackguard0 = stackPreempt
_g_.throwsplit = true
// Leave SP around for GC and traceback.
save(pc, sp)
_g_.syscallsp = sp
_g_.syscallpc = pc
// 让G进入_Gsyscall状态,此时G曾经被挂起了,直到零碎调用完结,才会让G从新写进入running
casgstatus(_g_, _Grunning, _Gsyscall)
if _g_.syscallsp < _g_.stack.lo || _g_.stack.hi < _g_.syscallsp {
systemstack(func() {
print("entersyscall inconsistent ", hex(_g_.syscallsp), " [", hex(_g_.stack.lo), ",", hex(_g_.stack.hi), "]\n")
throw("entersyscall")
})
}
if trace.enabled {
systemstack(traceGoSysCall)
// systemstack itself clobbers g.sched.{pc,sp} and we might
// need them later when the G is genuinely blocked in a
// syscall
save(pc, sp)
}
if atomic.Load(&sched.sysmonwait) != 0 {
systemstack(entersyscall_sysmon)
save(pc, sp)
}
if _g_.m.p.ptr().runSafePointFn != 0 {
// runSafePointFn may stack split if run on this stack
systemstack(runSafePointFn)
save(pc, sp)
}
_g_.m.syscalltick = _g_.m.p.ptr().syscalltick
_g_.sysblocktraced = true
// 这里很要害:P的M曾经陷入零碎调用,于是P忍痛放弃该M
// 然而请留神:此时M还指向P,在M从零碎调用返回后还能找到P
pp := _g_.m.p.ptr()
pp.m = 0
_g_.m.oldp.set(pp)
_g_.m.p = 0
// P的状态变为Psyscall
atomic.Store(&pp.status, _Psyscall)
if sched.gcwaiting != 0 {
systemstack(entersyscall_gcwait)
save(pc, sp)
}
_g_.m.locks--
}
该办法次要是为零碎调用前做了筹备工作:
- 批改g的状态为_Gsyscall
- 查看sysmon线程是否在执行,睡眠须要唤醒
- p放弃m,然而m仍旧持有p的指针,完结调用后优先选择p
- 批改p的状态为_Psyscal
做好这些筹备工作便能够真正的执行零碎调用了。当该线程m长时间阻塞在零碎调用的时候,始终在运行的sysmon线程会检测到该p的状态,并将其剥离,驱动其余的m(新建或获取)来调度执行该p上的工作,这其中次要是在retake办法中实现的,该办法还解决了goroutine抢占调度,这里省略,前面介绍抢占调度在介绍:
exitsyscall
当零碎Syscall返回的时,会调用exitsyscall办法复原调度:
//go:nosplit
//go:nowritebarrierrec
//go:linkname exitsyscall
func exitsyscall() {
_g_ := getg()
_g_.m.locks++ // see comment in entersyscall
if getcallersp() > _g_.syscallsp {
throw("exitsyscall: syscall frame is no longer valid")
}
_g_.waitsince = 0
oldp := _g_.m.oldp.ptr()
_g_.m.oldp = 0
// 从新获取p
if exitsyscallfast(oldp) {
if trace.enabled {
if oldp != _g_.m.p.ptr() || _g_.m.syscalltick != _g_.m.p.ptr().syscalltick {
systemstack(traceGoStart)
}
}
// There's a cpu for us, so we can run.
_g_.m.p.ptr().syscalltick++
// We need to cas the status and scan before resuming...
casgstatus(_g_, _Gsyscall, _Grunning)
// Garbage collector isn't running (since we are),
// so okay to clear syscallsp.
_g_.syscallsp = 0
_g_.m.locks--
if _g_.preempt {
// restore the preemption request in case we've cleared it in newstack
_g_.stackguard0 = stackPreempt
} else {
// otherwise restore the real _StackGuard, we've spoiled it in entersyscall/entersyscallblock
_g_.stackguard0 = _g_.stack.lo + _StackGuard
}
_g_.throwsplit = false
if sched.disable.user && !schedEnabled(_g_) {
// Scheduling of this goroutine is disabled.
Gosched()
}
return
}
_g_.sysexitticks = 0
if trace.enabled {
// Wait till traceGoSysBlock event is emitted.
// This ensures consistency of the trace (the goroutine is started after it is blocked).
for oldp != nil && oldp.syscalltick == _g_.m.syscalltick {
osyield()
}
// We can't trace syscall exit right now because we don't have a P.
// Tracing code can invoke write barriers that cannot run without a P.
// So instead we remember the syscall exit time and emit the event
// in execute when we have a P.
_g_.sysexitticks = cputicks()
}
_g_.m.locks--
// 没有获取到p,只能解绑以后g,从新调度该m了
mcall(exitsyscall0)
// Scheduler returned, so we're allowed to run now.
// Delete the syscallsp information that we left for
// the garbage collector during the system call.
// Must wait until now because until gosched returns
// we don't know for sure that the garbage collector
// is not running.
_g_.syscallsp = 0
_g_.m.p.ptr().syscalltick++
_g_.throwsplit = false
}
exitsyscallfast
exitsyscall会尝试从新绑定p,优先选择之前m绑定的p(进入零碎的调用的时候,p只是单方面解绑了和m的关系,通过m仍旧能够找到p):
//go:nosplit
func exitsyscallfast(oldp *p) bool {
_g_ := getg()
// Freezetheworld sets stopwait but does not retake P's.
//stw,间接解绑p,而后退出
if sched.stopwait == freezeStopWait {
return false
}
// Try to re-acquire the last P.
// 如果之前从属的P尚未被其余M,尝试绑定该P
if oldp != nil && oldp.status == _Psyscall && atomic.Cas(&oldp.status, _Psyscall, _Pidle) {
// There's a cpu for us, so we can run.
wirep(oldp)
exitsyscallfast_reacquired()
return true
}
// 否则从闲暇P列表中取出一个来
// Try to get any other idle P.
if sched.pidle != 0 {
var ok bool
systemstack(func() {
ok = exitsyscallfast_pidle()
if ok && trace.enabled {
if oldp != nil {
// Wait till traceGoSysBlock event is emitted.
// This ensures consistency of the trace (the goroutine is started after it is blocked).
for oldp.syscalltick == _g_.m.syscalltick {
osyield()
}
}
traceGoSysExit(0)
}
})
if ok {
return true
}
}
return false
}
exitsyscall0
func exitsyscall0(gp *g) {
_g_ := getg()
//批改g状态为 _Grunable
casgstatus(gp, _Gsyscall, _Grunnable)
dropg() //解绑
lock(&sched.lock)
var _p_ *p
//尝试获取p
if schedEnabled(_g_) {
_p_ = pidleget()
}
if _p_ == nil {
// 未获取到p,g进入全局队列期待调度
globrunqput(gp)
} else if atomic.Load(&sched.sysmonwait) != 0 {
atomic.Store(&sched.sysmonwait, 0)
notewakeup(&sched.sysmonnote)
}
unlock(&sched.lock)
// 获取到p,绑定,而后执行
if _p_ != nil {
acquirep(_p_)
execute(gp, false) // Never returns.
}
// // m有绑定的g,解绑p而后绑定的g来唤醒,执行
if _g_.m.lockedg != 0 {
// Wait until another thread schedules gp and so m again.
stoplockedm()
execute(gp, false) // Never returns.
}
// 关联p失败了,休眠,期待唤醒,在进行调度。
stopm()
schedule() // Never returns.
}
总结
上述便是golang零碎调用的整个流程,大抵如下:
- 业务调用封装好的零碎调用函数,编译器翻译到Syscall
- 执行entersyscall()办法,批改g,p的状态,p单方面解绑m,并查看唤醒sysmon线程,检测零碎调用。
- 当sysmon线程检测到零碎调用阻塞工夫过长的时候,调用retake,从新调度该p,让p上可执行的得以执行,不浪费资源
- 零碎调用返回,进入exitsyscall办法,优先获取之前的p,如果该p曾经被占有,从新获取闲暇的p,绑定,而后继续执行该g。当获取不到p的时候,调用exitsyscall0,解绑g,休眠,期待下次唤醒调度。
发表回复