// Create a new g running fn.
// Put it on the queue of g's waiting to run.
// The compiler turns a go statement into a call to this.
func newproc(fn *funcval) {
   gp := getg()         // 獲取正在運行的g，初始化時是m0.g0
   pc := getcallerpc()  // 返回的是調(diào)用newproc函數(shù)時由call指令壓棧的函數(shù)的返回地址，即上面匯編語言的第5行`POPQ AX`這條指令的地址
   systemstack(func() { // systemstack函數(shù)的作用是切換到系統(tǒng)棧來執(zhí)行其參數(shù)函數(shù)，也就是`g0`棧，這里當(dāng)然就是m0.g0，所以基本不需要做什么
      newg := newproc1(fn, gp, pc)

      _p_ := getg().m.p.ptr()
      runqput(_p_, newg, true)

      if mainStarted {
         wakep()
      }
   })
}

// Create a new g in state _Grunnable, starting at fn. callerpc is the
// address of the go statement that created this. The caller is responsible
// for adding the new g to the scheduler.
func newproc1(fn *funcval, callergp *g, callerpc uintptr) *g {
   _g_ := getg() // _g_ = g0，即m0.g0

   if fn == nil {
      _g_.m.throwing = -1 // do not dump full stacks
      throw("go of nil func value")
   }
   acquirem() // disable preemption because it can be holding p in a local var

   _p_ := _g_.m.p.ptr()
   newg := gfget(_p_)  // 從本地的已經(jīng)廢棄的g列表中獲取一個g先，此時才剛初始化，所以肯定返回nil
   if newg == nil {
      newg = malg(_StackMin) // new一個g的結(jié)構(gòu)體對象，然后在堆上分配2k的棧大小，并設(shè)置stack和stackguard0/1
      casgstatus(newg, _Gidle, _Gdead)
      allgadd(newg) // publishes with a g->status of Gdead so GC scanner doesn't look at uninitialized stack.
   }
   if newg.stack.hi == 0 {
      throw("newproc1: newg missing stack")
   }

   if readgstatus(newg) != _Gdead {
      throw("newproc1: new g is not Gdead")
   }

   // 調(diào)整棧頂指針
   totalSize := uintptr(4*goarch.PtrSize + sys.MinFrameSize) // extra space in case of reads slightly beyond frame
   totalSize = alignUp(totalSize, sys.StackAlign)
   sp := newg.stack.hi - totalSize
   spArg := sp
   if usesLR {
      // caller's LR
      *(*uintptr)(unsafe.Pointer(sp)) = 0
      prepGoExitFrame(sp)
      spArg += sys.MinFrameSize
   }
   ...
}

memclrNoHeapPointers(unsafe.Pointer(&newg.sched), unsafe.Sizeof(newg.sched))
newg.sched.sp = sp // 設(shè)置newg的棧頂
newg.stktopsp = sp
// newg.sched.pc表示當(dāng)newg運行起來時的運行起始位置，下面一段是類似于代碼注入，就好像每個go func() 
// 函數(shù)都是由goexit函數(shù)引起的一樣，以便后面當(dāng)newg結(jié)束后，
// 完成newg的回收（當(dāng)然這里main goroutine結(jié)束后進程就結(jié)束了，不會被回收）。
newg.sched.pc = abi.FuncPCABI0(goexit) + sys.PCQuantum // +PCQuantum so that previous instruction is in same function
newg.sched.g = guintptr(unsafe.Pointer(newg))
gostartcallfn(&newg.sched, fn) // 調(diào)整sched成員和newg的棧
newg.gopc = callerpc
newg.ancestors = saveAncestors(callergp)
newg.startpc = fn.fn
if isSystemGoroutine(newg, false) {
   atomic.Xadd(&sched.ngsys, +1)
} else {
   // Only user goroutines inherit pprof labels.
   if _g_.m.curg != nil {
      newg.labels = _g_.m.curg.labels
   }
}

// adjust Gobuf as if it executed a call to fn
// and then stopped before the first instruction in fn.
func gostartcallfn(gobuf *gobuf, fv *funcval) {
   var fn unsafe.Pointer
   if fv != nil {
      fn = unsafe.Pointer(fv.fn)
   } else {
      fn = unsafe.Pointer(abi.FuncPCABIInternal(nilfunc))
   }
   gostartcall(gobuf, fn, unsafe.Pointer(fv))
}

// sys_x86.go
// adjust Gobuf as if it executed a call to fn with context ctxt
// and then stopped before the first instruction in fn.
func gostartcall(buf *gobuf, fn, ctxt unsafe.Pointer) {
   sp := buf.sp
   sp -= goarch.PtrSize
   *(*uintptr)(unsafe.Pointer(sp)) = buf.pc // 插入goexit的第二條指令，返回時可以調(diào)用
   buf.sp = sp                              
   buf.pc = uintptr(fn)                     // 此時才是真正地設(shè)置pc 
   buf.ctxt = ctxt
}

newg := newproc1(fn, gp, pc)

_p_ := getg().m.p.ptr()
runqput(_p_, newg, true)

if mainStarted {
   wakep()
}

func mstart0() {
   _g_ := getg() // _g_ = &g0

   osStack := _g_.stack.lo == 0
   if osStack { // g0的stack.lo已經(jīng)初始化，所以不會走以下邏輯
      // Initialize stack bounds from system stack.
      // Cgo may have left stack size in stack.hi.
      // minit may update the stack bounds.
      //
      // Note: these bounds may not be very accurate.
      // We set hi to &size, but there are things above
      // it. The 1024 is supposed to compensate this,
      // but is somewhat arbitrary.
      size := _g_.stack.hi
      if size == 0 {
         size = 8192 * sys.StackGuardMultiplier
      }
      _g_.stack.hi = uintptr(noescape(unsafe.Pointer(&size)))
      _g_.stack.lo = _g_.stack.hi - size + 1024
   }
   // Initialize stack guard so that we can start calling regular
   // Go code.
   _g_.stackguard0 = _g_.stack.lo + _StackGuard
   // This is the g0, so we can also call go:systemstack
   // functions, which check stackguard1.
   _g_.stackguard1 = _g_.stackguard0
   mstart1()

   // Exit this thread.
   if mStackIsSystemAllocated() {
      // Windows, Solaris, illumos, Darwin, AIX and Plan 9 always system-allocate
      // the stack, but put it in _g_.stack before mstart,
      // so the logic above hasn't set osStack yet.
      osStack = true
   }
   mexit(osStack)
}

func mstart1() {
   _g_ := getg() // _g_ = &g0

   if _g_ != _g_.m.g0 { // _g_ = &g0
      throw("bad runtime·mstart")
   }

   // Set up m.g0.sched as a label returning to just
   // after the mstart1 call in mstart0 above, for use by goexit0 and mcall.
   // We're never coming back to mstart1 after we call schedule,
   // so other calls can reuse the current frame.
   // And goexit0 does a gogo that needs to return from mstart1
   // and let mstart0 exit the thread.
   _g_.sched.g = guintptr(unsafe.Pointer(_g_))
   _g_.sched.pc = getcallerpc() // getcallerpc()獲取mstart1執(zhí)行完的返回地址
   _g_.sched.sp = getcallersp() // getcallersp()獲取調(diào)用mstart1時的棧頂?shù)刂?

   asminit()
   minit() // 信號相關(guān)初始化

   // Install signal handlers; after minit so that minit can
   // prepare the thread to be able to handle the signals.
   if _g_.m == &m0 {
      mstartm0()
   }

   if fn := _g_.m.mstartfn; fn != nil {
      fn()
   }

   if _g_.m != &m0 {
      acquirep(_g_.m.nextp.ptr())
      _g_.m.nextp = 0
   }
   schedule()
}

func schedule() {
   _g_ := getg() // _g_ 是每個工作線程的m的m0，在初始化的場景就是m0.g0

   ...

   var gp *g
   var inheritTime bool

   ...
   
   if gp == nil {
      // 為了保證調(diào)度的公平性，每進行61次調(diào)度就需要優(yōu)先從全局隊列中獲取goroutine
      // Check the global runnable queue once in a while to ensure fairness.
      // Otherwise two goroutines can completely occupy the local runqueue
      // by constantly respawning each other.
      if _g_.m.p.ptr().schedtick%61 == 0 && sched.runqsize > 0 {
         lock(&sched.lock)
         gp = globrunqget(_g_.m.p.ptr(), 1)
         unlock(&sched.lock)
      }
   }
   if gp == nil { // 從p本地的隊列中獲取goroutine
      gp, inheritTime = runqget(_g_.m.p.ptr())
      // We can see gp != nil here even if the M is spinning,
      // if checkTimers added a local goroutine via goready.
   }
   if gp == nil { // 如果以上兩者都沒有，那么就需要從其他p哪里竊取goroutine
      gp, inheritTime = findrunnable() // blocks until work is available
   }

   ...

   execute(gp, inheritTime)
}

func execute(gp *g, inheritTime bool) {
   _g_ := getg()

   // Assign gp.m before entering _Grunning so running Gs have an
   // M.
   _g_.m.curg = gp
   gp.m = _g_.m
   casgstatus(gp, _Grunnable, _Grunning) // 設(shè)置gp的狀態(tài)
   gp.waitsince = 0
   gp.preempt = false
   gp.stackguard0 = gp.stack.lo + _StackGuard
   
   ...

   gogo(&gp.sched)
}

func main() {
   g := getg() // _g_ = main_goroutine

   // Racectx of m0->g0 is used only as the parent of the main goroutine.
   // It must not be used for anything else.
   g.m.g0.racectx = 0

   // golang棧的最大值
   // Max stack size is 1 GB on 64-bit, 250 MB on 32-bit.
   // Using decimal instead of binary GB and MB because
   // they look nicer in the stack overflow failure message.
   if goarch.PtrSize == 8 {
      maxstacksize = 1000000000
   } else {
      maxstacksize = 250000000
   }

   // An upper limit for max stack size. Used to avoid random crashes
   // after calling SetMaxStack and trying to allocate a stack that is too big,
   // since stackalloc works with 32-bit sizes.
   maxstackceiling = 2 * maxstacksize

   // Allow newproc to start new Ms.
   mainStarted = true

   // 需要切換到g0棧去執(zhí)行newm
   // 創(chuàng)建監(jiān)控線程，該線程獨立于調(diào)度器，無需與P關(guān)聯(lián)
   if GOARCH != "wasm" { // no threads on wasm yet, so no sysmon
      systemstack(func() {
         newm(sysmon, nil, -1)
      })
   }

   // Lock the main goroutine onto this, the main OS thread,
   // during initialization. Most programs won't care, but a few
   // do require certain calls to be made by the main thread.
   // Those can arrange for main.main to run in the main thread
   // by calling runtime.LockOSThread during initialization
   // to preserve the lock.
   lockOSThread()

   if g.m != &m0 {
      throw("runtime.main not on m0")
   }

   // Record when the world started.
   // Must be before doInit for tracing init.
   runtimeInitTime = nanotime()
   if runtimeInitTime == 0 {
      throw("nanotime returning zero")
   }

   if debug.inittrace != 0 {
      inittrace.id = getg().goid
      inittrace.active = true
   }

   // runtime包的init
   doInit(&runtime_inittask) // Must be before defer.

   // Defer unlock so that runtime.Goexit during init does the unlock too.
   needUnlock := true
   defer func() {
      if needUnlock {
         unlockOSThread()
      }
   }()

   gcenable()

   main_init_done = make(chan bool)
   if iscgo {
      if _cgo_thread_start == nil {
         throw("_cgo_thread_start missing")
      }
      if GOOS != "windows" {
         if _cgo_setenv == nil {
            throw("_cgo_setenv missing")
         }
         if _cgo_unsetenv == nil {
            throw("_cgo_unsetenv missing")
         }
      }
      if _cgo_notify_runtime_init_done == nil {
         throw("_cgo_notify_runtime_init_done missing")
      }
      // Start the template thread in case we enter Go from
      // a C-created thread and need to create a new thread.
      startTemplateThread()
      cgocall(_cgo_notify_runtime_init_done, nil)
   }

   doInit(&main_inittask) // main包的init，會遞歸調(diào)用import的包的初始化函數(shù)

   // Disable init tracing after main init done to avoid overhead
   // of collecting statistics in malloc and newproc
   inittrace.active = false

   close(main_init_done)

   needUnlock = false
   unlockOSThread()

   if isarchive || islibrary {
      // A program compiled with -buildmode=c-archive or c-shared
      // has a main, but it is not executed.
      return
   }
   fn := main_main // make an indirect call, as the linker doesn't know the address of the main package when laying down the runtime
   fn() // 執(zhí)行main函數(shù)
   if raceenabled {
      racefini()
   }

   // Make racy client program work: if panicking on
   // another goroutine at the same time as main returns,
   // let the other goroutine finish printing the panic trace.
   // Once it does, it will exit. See issues 3934 and 20018.
   if atomic.Load(&runningPanicDefers) != 0 {
      // Running deferred functions should not take long.
      for c := 0; c < 1000; c++ {
         if atomic.Load(&runningPanicDefers) == 0 {
            break
         }
         Gosched()
      }
   }
   if atomic.Load(&panicking) != 0 {
      gopark(nil, nil, waitReasonPanicWait, traceEvGoStop, 1)
   }

   exit(0)
   for {
      var x *int32
      *x = 0
   }
}