src/runtime/runtime2.go

// Copyright 2009 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

package runtime

import (
	"internal/abi"
	"internal/chacha8rand"
	"internal/goarch"
	"internal/runtime/atomic"
	"runtime/internal/sys"
	"unsafe"
)

// defined constants
const (
	// G status
	//
	// Beyond indicating the general state of a G, the G status
	// acts like a lock on the goroutine's stack (and hence its
	// ability to execute user code).
	//
	// If you add to this list, add to the list
	// of "okay during garbage collection" status
	// in mgcmark.go too.
	//
	// TODO(austin): The _Gscan bit could be much lighter-weight.
	// For example, we could choose not to run _Gscanrunnable
	// goroutines found in the run queue, rather than CAS-looping
	// until they become _Grunnable. And transitions like
	// _Gscanwaiting -> _Gscanrunnable are actually okay because
	// they don't affect stack ownership.

	// _Gidle means this goroutine was just allocated and has not
	// yet been initialized.
	_Gidle = iota // 0

	// _Grunnable means this goroutine is on a run queue. It is
	// not currently executing user code. The stack is not owned.
	_Grunnable // 1

	// _Grunning means this goroutine may execute user code. The
	// stack is owned by this goroutine. It is not on a run queue.
	// It is assigned an M and a P (g.m and g.m.p are valid).
	_Grunning // 2

	// _Gsyscall means this goroutine is executing a system call.
	// It is not executing user code. The stack is owned by this
	// goroutine. It is not on a run queue. It is assigned an M.
	_Gsyscall // 3

	// _Gwaiting means this goroutine is blocked in the runtime.
	// It is not executing user code. It is not on a run queue,
	// but should be recorded somewhere (e.g., a channel wait
	// queue) so it can be ready()d when necessary. The stack is
	// not owned *except* that a channel operation may read or
	// write parts of the stack under the appropriate channel
	// lock. Otherwise, it is not safe to access the stack after a
	// goroutine enters _Gwaiting (e.g., it may get moved).
	_Gwaiting // 4

	// _Gmoribund_unused is currently unused, but hardcoded in gdb
	// scripts.
	_Gmoribund_unused // 5

	// _Gdead means this goroutine is currently unused. It may be
	// just exited, on a free list, or just being initialized. It
	// is not executing user code. It may or may not have a stack
	// allocated. The G and its stack (if any) are owned by the M
	// that is exiting the G or that obtained the G from the free
	// list.
	_Gdead // 6

	// _Genqueue_unused is currently unused.
	_Genqueue_unused // 7

	// _Gcopystack means this goroutine's stack is being moved. It
	// is not executing user code and is not on a run queue. The
	// stack is owned by the goroutine that put it in _Gcopystack.
	_Gcopystack // 8

	// _Gpreempted means this goroutine stopped itself for a
	// suspendG preemption. It is like _Gwaiting, but nothing is
	// yet responsible for ready()ing it. Some suspendG must CAS
	// the status to _Gwaiting to take responsibility for
	// ready()ing this G.
	_Gpreempted // 9

	// _Gscan combined with one of the above states other than
	// _Grunning indicates that GC is scanning the stack. The
	// goroutine is not executing user code and the stack is owned
	// by the goroutine that set the _Gscan bit.
	//
	// _Gscanrunning is different: it is used to briefly block
	// state transitions while GC signals the G to scan its own
	// stack. This is otherwise like _Grunning.
	//
	// atomicstatus&~Gscan gives the state the goroutine will
	// return to when the scan completes.
	_Gscan          = 0x1000
	_Gscanrunnable  = _Gscan + _Grunnable  // 0x1001
	_Gscanrunning   = _Gscan + _Grunning   // 0x1002
	_Gscansyscall   = _Gscan + _Gsyscall   // 0x1003
	_Gscanwaiting   = _Gscan + _Gwaiting   // 0x1004
	_Gscanpreempted = _Gscan + _Gpreempted // 0x1009
)

const (
	// P status

	// _Pidle means a P is not being used to run user code or the
	// scheduler. Typically, it's on the idle P list and available
	// to the scheduler, but it may just be transitioning between
	// other states.
	//
	// The P is owned by the idle list or by whatever is
	// transitioning its state. Its run queue is empty.
	_Pidle = iota

	// _Prunning means a P is owned by an M and is being used to
	// run user code or the scheduler. Only the M that owns this P
	// is allowed to change the P's status from _Prunning. The M
	// may transition the P to _Pidle (if it has no more work to
	// do), _Psyscall (when entering a syscall), or _Pgcstop (to
	// halt for the GC). The M may also hand ownership of the P
	// off directly to another M (e.g., to schedule a locked G).
	_Prunning

	// _Psyscall means a P is not running user code. It has
	// affinity to an M in a syscall but is not owned by it and
	// may be stolen by another M. This is similar to _Pidle but
	// uses lightweight transitions and maintains M affinity.
	//
	// Leaving _Psyscall must be done with a CAS, either to steal
	// or retake the P. Note that there's an ABA hazard: even if
	// an M successfully CASes its original P back to _Prunning
	// after a syscall, it must understand the P may have been
	// used by another M in the interim.
	_Psyscall

	// _Pgcstop means a P is halted for STW and owned by the M
	// that stopped the world. The M that stopped the world
	// continues to use its P, even in _Pgcstop. Transitioning
	// from _Prunning to _Pgcstop causes an M to release its P and
	// park.
	//
	// The P retains its run queue and startTheWorld will restart
	// the scheduler on Ps with non-empty run queues.
	_Pgcstop

	// _Pdead means a P is no longer used (GOMAXPROCS shrank). We
	// reuse Ps if GOMAXPROCS increases. A dead P is mostly
	// stripped of its resources, though a few things remain
	// (e.g., trace buffers).
	_Pdead
)

// Mutual exclusion locks.  In the uncontended case,
// as fast as spin locks (just a few user-level instructions),
// but on the contention path they sleep in the kernel.
// A zeroed Mutex is unlocked (no need to initialize each lock).
// Initialization is helpful for static lock ranking, but not required.
type mutex struct {
	// Empty struct if lock ranking is disabled, otherwise includes the lock rank
	lockRankStruct
	// Futex-based impl treats it as uint32 key,
	// while sema-based impl as M* waitm.
	// Used to be a union, but unions break precise GC.
	key uintptr
}

// sleep and wakeup on one-time events.
// before any calls to notesleep or notewakeup,
// must call noteclear to initialize the Note.
// then, exactly one thread can call notesleep
// and exactly one thread can call notewakeup (once).
// once notewakeup has been called, the notesleep
// will return.  future notesleep will return immediately.
// subsequent noteclear must be called only after
// previous notesleep has returned, e.g. it's disallowed
// to call noteclear straight after notewakeup.
//
// notetsleep is like notesleep but wakes up after
// a given number of nanoseconds even if the event
// has not yet happened.  if a goroutine uses notetsleep to
// wake up early, it must wait to call noteclear until it
// can be sure that no other goroutine is calling
// notewakeup.
//
// notesleep/notetsleep are generally called on g0,
// notetsleepg is similar to notetsleep but is called on user g.
type note struct {
	// Futex-based impl treats it as uint32 key,
	// while sema-based impl as M* waitm.
	// Used to be a union, but unions break precise GC.
	key uintptr
}

type funcval struct {
	fn uintptr
	// variable-size, fn-specific data here
}

type iface struct {
	tab  *itab
	data unsafe.Pointer
}

type eface struct {
	_type *_type
	data  unsafe.Pointer
}

func efaceOf(ep *any) *eface {
	return (*eface)(unsafe.Pointer(ep))
}

// The guintptr, muintptr, and puintptr are all used to bypass write barriers.
// It is particularly important to avoid write barriers when the current P has
// been released, because the GC thinks the world is stopped, and an
// unexpected write barrier would not be synchronized with the GC,
// which can lead to a half-executed write barrier that has marked the object
// but not queued it. If the GC skips the object and completes before the
// queuing can occur, it will incorrectly free the object.
//
// We tried using special assignment functions invoked only when not
// holding a running P, but then some updates to a particular memory
// word went through write barriers and some did not. This breaks the
// write barrier shadow checking mode, and it is also scary: better to have
// a word that is completely ignored by the GC than to have one for which
// only a few updates are ignored.
//
// Gs and Ps are always reachable via true pointers in the
// allgs and allp lists or (during allocation before they reach those lists)
// from stack variables.
//
// Ms are always reachable via true pointers either from allm or
// freem. Unlike Gs and Ps we do free Ms, so it's important that
// nothing ever hold an muintptr across a safe point.

// A guintptr holds a goroutine pointer, but typed as a uintptr
// to bypass write barriers. It is used in the Gobuf goroutine state
// and in scheduling lists that are manipulated without a P.
//
// The Gobuf.g goroutine pointer is almost always updated by assembly code.
// In one of the few places it is updated by Go code - func save - it must be
// treated as a uintptr to avoid a write barrier being emitted at a bad time.
// Instead of figuring out how to emit the write barriers missing in the
// assembly manipulation, we change the type of the field to uintptr,
// so that it does not require write barriers at all.
//
// Goroutine structs are published in the allg list and never freed.
// That will keep the goroutine structs from being collected.
// There is never a time that Gobuf.g's contain the only references
// to a goroutine: the publishing of the goroutine in allg comes first.
// Goroutine pointers are also kept in non-GC-visible places like TLS,
// so I can't see them ever moving. If we did want to start moving data
// in the GC, we'd need to allocate the goroutine structs from an
// alternate arena. Using guintptr doesn't make that problem any worse.
// Note that pollDesc.rg, pollDesc.wg also store g in uintptr form,
// so they would need to be updated too if g's start moving.
type guintptr uintptr

//go:nosplit
func (gp guintptr) ptr() *g { return (*g)(unsafe.Pointer(gp)) }

//go:nosplit
func (gp *guintptr) set(g *g) { *gp = guintptr(unsafe.Pointer(g)) }

//go:nosplit
func (gp *guintptr) cas(old, new guintptr) bool {
	return atomic.Casuintptr((*uintptr)(unsafe.Pointer(gp)), uintptr(old), uintptr(new))
}

//go:nosplit
func (gp *g) guintptr() guintptr {
	return guintptr(unsafe.Pointer(gp))
}

// setGNoWB performs *gp = new without a write barrier.
// For times when it's impractical to use a guintptr.
//
//go:nosplit
//go:nowritebarrier
func setGNoWB(gp **g, new *g) {
	(*guintptr)(unsafe.Pointer(gp)).set(new)
}

type puintptr uintptr

//go:nosplit
func (pp puintptr) ptr() *p { return (*p)(unsafe.Pointer(pp)) }

//go:nosplit
func (pp *puintptr) set(p *p) { *pp = puintptr(unsafe.Pointer(p)) }

// muintptr is a *m that is not tracked by the garbage collector.
//
// Because we do free Ms, there are some additional constrains on
// muintptrs:
//
//  1. Never hold an muintptr locally across a safe point.
//
//  2. Any muintptr in the heap must be owned by the M itself so it can
//     ensure it is not in use when the last true *m is released.
type muintptr uintptr

//go:nosplit
func (mp muintptr) ptr() *m { return (*m)(unsafe.Pointer(mp)) }

//go:nosplit
func (mp *muintptr) set(m *m) { *mp = muintptr(unsafe.Pointer(m)) }

// setMNoWB performs *mp = new without a write barrier.
// For times when it's impractical to use an muintptr.
//
//go:nosplit
//go:nowritebarrier
func setMNoWB(mp **m, new *m) {
	(*muintptr)(unsafe.Pointer(mp)).set(new)
}

type gobuf struct {
	// The offsets of sp, pc, and g are known to (hard-coded in) libmach.
	//
	// ctxt is unusual with respect to GC: it may be a
	// heap-allocated funcval, so GC needs to track it, but it
	// needs to be set and cleared from assembly, where it's
	// difficult to have write barriers. However, ctxt is really a
	// saved, live register, and we only ever exchange it between
	// the real register and the gobuf. Hence, we treat it as a
	// root during stack scanning, which means assembly that saves
	// and restores it doesn't need write barriers. It's still
	// typed as a pointer so that any other writes from Go get
	// write barriers.
	sp   uintptr
	pc   uintptr
	g    guintptr
	ctxt unsafe.Pointer
	ret  uintptr
	lr   uintptr
	bp   uintptr // for framepointer-enabled architectures
}

// sudog (pseudo-g) represents a g in a wait list, such as for sending/receiving
// on a channel.
//
// sudog is necessary because the g ↔ synchronization object relation
// is many-to-many. A g can be on many wait lists, so there may be
// many sudogs for one g; and many gs may be waiting on the same
// synchronization object, so there may be many sudogs for one object.
//
// sudogs are allocated from a special pool. Use acquireSudog and
// releaseSudog to allocate and free them.
type sudog struct {
	// The following fields are protected by the hchan.lock of the
	// channel this sudog is blocking on. shrinkstack depends on
	// this for sudogs involved in channel ops.

	g *g

	next *sudog
	prev *sudog
	elem unsafe.Pointer // data element (may point to stack)

	// The following fields are never accessed concurrently.
	// For channels, waitlink is only accessed by g.
	// For semaphores, all fields (including the ones above)
	// are only accessed when holding a semaRoot lock.

	acquiretime int64
	releasetime int64
	ticket      uint32

	// isSelect indicates g is participating in a select, so
	// g.selectDone must be CAS'd to win the wake-up race.
	isSelect bool

	// success indicates whether communication over channel c
	// succeeded. It is true if the goroutine was awoken because a
	// value was delivered over channel c, and false if awoken
	// because c was closed.
	success bool

	// waiters is a count of semaRoot waiting list other than head of list,
	// clamped to a uint16 to fit in unused space.
	// Only meaningful at the head of the list.
	// (If we wanted to be overly clever, we could store a high 16 bits
	// in the second entry in the list.)
	waiters uint16

	parent   *sudog // semaRoot binary tree
	waitlink *sudog // g.waiting list or semaRoot
	waittail *sudog // semaRoot
	c        *hchan // channel
}

type libcall struct {
	fn   uintptr
	n    uintptr // number of parameters
	args uintptr // parameters
	r1   uintptr // return values
	r2   uintptr
	err  uintptr // error number
}

// Stack describes a Go execution stack.
// The bounds of the stack are exactly [lo, hi),
// with no implicit data structures on either side.
type stack struct {
	lo uintptr
	hi uintptr
}

// heldLockInfo gives info on a held lock and the rank of that lock
type heldLockInfo struct {
	lockAddr uintptr
	rank     lockRank
}

type g struct {
	// Stack parameters.
	// stack describes the actual stack memory: [stack.lo, stack.hi).
	// stackguard0 is the stack pointer compared in the Go stack growth prologue.
	// It is stack.lo+StackGuard normally, but can be StackPreempt to trigger a preemption.
	// stackguard1 is the stack pointer compared in the //go:systemstack stack growth prologue.
	// It is stack.lo+StackGuard on g0 and gsignal stacks.
	// It is ~0 on other goroutine stacks, to trigger a call to morestackc (and crash).
	stack       stack   // offset known to runtime/cgo
	stackguard0 uintptr // offset known to liblink
	stackguard1 uintptr // offset known to liblink

	_panic    *_panic // innermost panic - offset known to liblink
	_defer    *_defer // innermost defer
	m         *m      // current m; offset known to arm liblink
	sched     gobuf
	syscallsp uintptr // if status==Gsyscall, syscallsp = sched.sp to use during gc
	syscallpc uintptr // if status==Gsyscall, syscallpc = sched.pc to use during gc
	syscallbp uintptr // if status==Gsyscall, syscallbp = sched.bp to use in fpTraceback
	stktopsp  uintptr // expected sp at top of stack, to check in traceback
	// param is a generic pointer parameter field used to pass
	// values in particular contexts where other storage for the
	// parameter would be difficult to find. It is currently used
	// in four ways:
	// 1. When a channel operation wakes up a blocked goroutine, it sets param to
	//    point to the sudog of the completed blocking operation.
	// 2. By gcAssistAlloc1 to signal back to its caller that the goroutine completed
	//    the GC cycle. It is unsafe to do so in any other way, because the goroutine's
	//    stack may have moved in the meantime.
	// 3. By debugCallWrap to pass parameters to a new goroutine because allocating a
	//    closure in the runtime is forbidden.
	// 4. When a panic is recovered and control returns to the respective frame,
	//    param may point to a savedOpenDeferState.
	param        unsafe.Pointer
	atomicstatus atomic.Uint32
	stackLock    uint32 // sigprof/scang lock; TODO: fold in to atomicstatus
	goid         uint64
	schedlink    guintptr
	waitsince    int64      // approx time when the g become blocked
	waitreason   waitReason // if status==Gwaiting

	preempt       bool // preemption signal, duplicates stackguard0 = stackpreempt
	preemptStop   bool // transition to _Gpreempted on preemption; otherwise, just deschedule
	preemptShrink bool // shrink stack at synchronous safe point

	// asyncSafePoint is set if g is stopped at an asynchronous
	// safe point. This means there are frames on the stack
	// without precise pointer information.
	asyncSafePoint bool

	paniconfault bool // panic (instead of crash) on unexpected fault address
	gcscandone   bool // g has scanned stack; protected by _Gscan bit in status
	throwsplit   bool // must not split stack
	// activeStackChans indicates that there are unlocked channels
	// pointing into this goroutine's stack. If true, stack
	// copying needs to acquire channel locks to protect these
	// areas of the stack.
	activeStackChans bool
	// parkingOnChan indicates that the goroutine is about to
	// park on a chansend or chanrecv. Used to signal an unsafe point
	// for stack shrinking.
	parkingOnChan atomic.Bool
	// inMarkAssist indicates whether the goroutine is in mark assist.
	// Used by the execution tracer.
	inMarkAssist bool
	coroexit     bool // argument to coroswitch_m

	raceignore    int8  // ignore race detection events
	nocgocallback bool  // whether disable callback from C
	tracking      bool  // whether we're tracking this G for sched latency statistics
	trackingSeq   uint8 // used to decide whether to track this G
	trackingStamp int64 // timestamp of when the G last started being tracked
	runnableTime  int64 // the amount of time spent runnable, cleared when running, only used when tracking
	lockedm       muintptr
	sig           uint32
	writebuf      []byte
	sigcode0      uintptr
	sigcode1      uintptr
	sigpc         uintptr
	parentGoid    uint64          // goid of goroutine that created this goroutine
	gopc          uintptr         // pc of go statement that created this goroutine
	ancestors     *[]ancestorInfo // ancestor information goroutine(s) that created this goroutine (only used if debug.tracebackancestors)
	startpc       uintptr         // pc of goroutine function
	racectx       uintptr
	waiting       *sudog         // sudog structures this g is waiting on (that have a valid elem ptr); in lock order
	cgoCtxt       []uintptr      // cgo traceback context
	labels        unsafe.Pointer // profiler labels
	timer         *timer         // cached timer for time.Sleep
	sleepWhen     int64          // when to sleep until
	selectDone    atomic.Uint32  // are we participating in a select and did someone win the race?

	// goroutineProfiled indicates the status of this goroutine's stack for the
	// current in-progress goroutine profile
	goroutineProfiled goroutineProfileStateHolder

	coroarg *coro // argument during coroutine transfers

	// Per-G tracer state.
	trace gTraceState

	// Per-G GC state

	// gcAssistBytes is this G's GC assist credit in terms of
	// bytes allocated. If this is positive, then the G has credit
	// to allocate gcAssistBytes bytes without assisting. If this
	// is negative, then the G must correct this by performing
	// scan work. We track this in bytes to make it fast to update
	// and check for debt in the malloc hot path. The assist ratio
	// determines how this corresponds to scan work debt.
	gcAssistBytes int64
}

// gTrackingPeriod is the number of transitions out of _Grunning between
// latency tracking runs.
const gTrackingPeriod = 8

const (
	// tlsSlots is the number of pointer-sized slots reserved for TLS on some platforms,
	// like Windows.
	tlsSlots = 6
	tlsSize  = tlsSlots * goarch.PtrSize
)

// Values for m.freeWait.
const (
	freeMStack = 0 // M done, free stack and reference.
	freeMRef   = 1 // M done, free reference.
	freeMWait  = 2 // M still in use.
)

type m struct {
	g0      *g     // goroutine with scheduling stack
	morebuf gobuf  // gobuf arg to morestack
	divmod  uint32 // div/mod denominator for arm - known to liblink
	_       uint32 // align next field to 8 bytes

	// Fields not known to debuggers.
	procid        uint64            // for debuggers, but offset not hard-coded
	gsignal       *g                // signal-handling g
	goSigStack    gsignalStack      // Go-allocated signal handling stack
	sigmask       sigset            // storage for saved signal mask
	tls           [tlsSlots]uintptr // thread-local storage (for x86 extern register)
	mstartfn      func()
	curg          *g       // current running goroutine
	caughtsig     guintptr // goroutine running during fatal signal
	p             puintptr // attached p for executing go code (nil if not executing go code)
	nextp         puintptr
	oldp          puintptr // the p that was attached before executing a syscall
	id            int64
	mallocing     int32
	throwing      throwType
	preemptoff    string // if != "", keep curg running on this m
	locks         int32
	dying         int32
	profilehz     int32
	spinning      bool // m is out of work and is actively looking for work
	blocked       bool // m is blocked on a note
	newSigstack   bool // minit on C thread called sigaltstack
	printlock     int8
	incgo         bool          // m is executing a cgo call
	isextra       bool          // m is an extra m
	isExtraInC    bool          // m is an extra m that is not executing Go code
	isExtraInSig  bool          // m is an extra m in a signal handler
	freeWait      atomic.Uint32 // Whether it is safe to free g0 and delete m (one of freeMRef, freeMStack, freeMWait)
	needextram    bool
	traceback     uint8
	ncgocall      uint64        // number of cgo calls in total
	ncgo          int32         // number of cgo calls currently in progress
	cgoCallersUse atomic.Uint32 // if non-zero, cgoCallers in use temporarily
	cgoCallers    *cgoCallers   // cgo traceback if crashing in cgo call
	park          note
	alllink       *m // on allm
	schedlink     muintptr
	lockedg       guintptr
	createstack   [32]uintptr // stack that created this thread, it's used for StackRecord.Stack0, so it must align with it.
	lockedExt     uint32      // tracking for external LockOSThread
	lockedInt     uint32      // tracking for internal lockOSThread
	nextwaitm     muintptr    // next m waiting for lock

	mLockProfile mLockProfile // fields relating to runtime.lock contention

	// wait* are used to carry arguments from gopark into park_m, because
	// there's no stack to put them on. That is their sole purpose.
	waitunlockf          func(*g, unsafe.Pointer) bool
	waitlock             unsafe.Pointer
	waitTraceSkip        int
	waitTraceBlockReason traceBlockReason

	syscalltick uint32
	freelink    *m // on sched.freem
	trace       mTraceState

	// these are here because they are too large to be on the stack
	// of low-level NOSPLIT functions.
	libcall    libcall
	libcallpc  uintptr // for cpu profiler
	libcallsp  uintptr
	libcallg   guintptr
	winsyscall winlibcall // stores syscall parameters on windows

	vdsoSP uintptr // SP for traceback while in VDSO call (0 if not in call)
	vdsoPC uintptr // PC for traceback while in VDSO call

	// preemptGen counts the number of completed preemption
	// signals. This is used to detect when a preemption is
	// requested, but fails.
	preemptGen atomic.Uint32

	// Whether this is a pending preemption signal on this M.
	signalPending atomic.Uint32

	// pcvalue lookup cache
	pcvalueCache pcvalueCache

	dlogPerM

	mOS

	chacha8   chacha8rand.State
	cheaprand uint64

	// Up to 10 locks held by this m, maintained by the lock ranking code.
	locksHeldLen int
	locksHeld    [10]heldLockInfo
}

type p struct {
	id          int32
	status      uint32 // one of pidle/prunning/...
	link        puintptr
	schedtick   uint32     // incremented on every scheduler call
	syscalltick uint32     // incremented on every system call
	sysmontick  sysmontick // last tick observed by sysmon
	m           muintptr   // back-link to associated m (nil if idle)
	mcache      *mcache
	pcache      pageCache
	raceprocctx uintptr

	deferpool    []*_defer // pool of available defer structs (see panic.go)
	deferpoolbuf [32]*_defer

	// Cache of goroutine ids, amortizes accesses to runtime·sched.goidgen.
	goidcache    uint64
	goidcacheend uint64

	// Queue of runnable goroutines. Accessed without lock.
	runqhead uint32
	runqtail uint32
	runq     [256]guintptr
	// runnext, if non-nil, is a runnable G that was ready'd by
	// the current G and should be run next instead of what's in
	// runq if there's time remaining in the running G's time
	// slice. It will inherit the time left in the current time
	// slice. If a set of goroutines is locked in a
	// communicate-and-wait pattern, this schedules that set as a
	// unit and eliminates the (potentially large) scheduling
	// latency that otherwise arises from adding the ready'd
	// goroutines to the end of the run queue.
	//
	// Note that while other P's may atomically CAS this to zero,
	// only the owner P can CAS it to a valid G.
	runnext guintptr

	// Available G's (status == Gdead)
	gFree struct {
		gList
		n int32
	}

	sudogcache []*sudog
	sudogbuf   [128]*sudog

	// Cache of mspan objects from the heap.
	mspancache struct {
		// We need an explicit length here because this field is used
		// in allocation codepaths where write barriers are not allowed,
		// and eliminating the write barrier/keeping it eliminated from
		// slice updates is tricky, more so than just managing the length
		// ourselves.
		len int
		buf [128]*mspan
	}

	// Cache of a single pinner object to reduce allocations from repeated
	// pinner creation.
	pinnerCache *pinner

	trace pTraceState

	palloc persistentAlloc // per-P to avoid mutex

	// Per-P GC state
	gcAssistTime         int64 // Nanoseconds in assistAlloc
	gcFractionalMarkTime int64 // Nanoseconds in fractional mark worker (atomic)

	// limiterEvent tracks events for the GC CPU limiter.
	limiterEvent limiterEvent

	// gcMarkWorkerMode is the mode for the next mark worker to run in.
	// That is, this is used to communicate with the worker goroutine
	// selected for immediate execution by
	// gcController.findRunnableGCWorker. When scheduling other goroutines,
	// this field must be set to gcMarkWorkerNotWorker.
	gcMarkWorkerMode gcMarkWorkerMode
	// gcMarkWorkerStartTime is the nanotime() at which the most recent
	// mark worker started.
	gcMarkWorkerStartTime int64

	// gcw is this P's GC work buffer cache. The work buffer is
	// filled by write barriers, drained by mutator assists, and
	// disposed on certain GC state transitions.
	gcw gcWork

	// wbBuf is this P's GC write barrier buffer.
	//
	// TODO: Consider caching this in the running G.
	wbBuf wbBuf

	runSafePointFn uint32 // if 1, run sched.safePointFn at next safe point

	// statsSeq is a counter indicating whether this P is currently
	// writing any stats. Its value is even when not, odd when it is.
	statsSeq atomic.Uint32

	// Timer heap.
	timers timers

	// maxStackScanDelta accumulates the amount of stack space held by
	// live goroutines (i.e. those eligible for stack scanning).
	// Flushed to gcController.maxStackScan once maxStackScanSlack
	// or -maxStackScanSlack is reached.
	maxStackScanDelta int64

	// gc-time statistics about current goroutines
	// Note that this differs from maxStackScan in that this
	// accumulates the actual stack observed to be used at GC time (hi - sp),
	// not an instantaneous measure of the total stack size that might need
	// to be scanned (hi - lo).
	scannedStackSize uint64 // stack size of goroutines scanned by this P
	scannedStacks    uint64 // number of goroutines scanned by this P

	// preempt is set to indicate that this P should be enter the
	// scheduler ASAP (regardless of what G is running on it).
	preempt bool

	// gcStopTime is the nanotime timestamp that this P last entered _Pgcstop.
	gcStopTime int64

	// pageTraceBuf is a buffer for writing out page allocation/free/scavenge traces.
	//
	// Used only if GOEXPERIMENT=pagetrace.
	pageTraceBuf pageTraceBuf

	// Padding is no longer needed. False sharing is now not a worry because p is large enough
	// that its size class is an integer multiple of the cache line size (for any of our architectures).
}

type schedt struct {
	goidgen   atomic.Uint64
	lastpoll  atomic.Int64 // time of last network poll, 0 if currently polling
	pollUntil atomic.Int64 // time to which current poll is sleeping

	lock mutex

	// When increasing nmidle, nmidlelocked, nmsys, or nmfreed, be
	// sure to call checkdead().

	midle        muintptr // idle m's waiting for work
	nmidle       int32    // number of idle m's waiting for work
	nmidlelocked int32    // number of locked m's waiting for work
	mnext        int64    // number of m's that have been created and next M ID
	maxmcount    int32    // maximum number of m's allowed (or die)
	nmsys        int32    // number of system m's not counted for deadlock
	nmfreed      int64    // cumulative number of freed m's

	ngsys atomic.Int32 // number of system goroutines

	pidle        puintptr // idle p's
	npidle       atomic.Int32
	nmspinning   atomic.Int32  // See "Worker thread parking/unparking" comment in proc.go.
	needspinning atomic.Uint32 // See "Delicate dance" comment in proc.go. Boolean. Must hold sched.lock to set to 1.

	// Global runnable queue.
	runq     gQueue
	runqsize int32

	// disable controls selective disabling of the scheduler.
	//
	// Use schedEnableUser to control this.
	//
	// disable is protected by sched.lock.
	disable struct {
		// user disables scheduling of user goroutines.
		user     bool
		runnable gQueue // pending runnable Gs
		n        int32  // length of runnable
	}

	// Global cache of dead G's.
	gFree struct {
		lock    mutex
		stack   gList // Gs with stacks
		noStack gList // Gs without stacks
		n       int32
	}

	// Central cache of sudog structs.
	sudoglock  mutex
	sudogcache *sudog

	// Central pool of available defer structs.
	deferlock mutex
	deferpool *_defer

	// freem is the list of m's waiting to be freed when their
	// m.exited is set. Linked through m.freelink.
	freem *m

	gcwaiting  atomic.Bool // gc is waiting to run
	stopwait   int32
	stopnote   note
	sysmonwait atomic.Bool
	sysmonnote note

	// safePointFn should be called on each P at the next GC
	// safepoint if p.runSafePointFn is set.
	safePointFn   func(*p)
	safePointWait int32
	safePointNote note

	profilehz int32 // cpu profiling rate

	procresizetime int64 // nanotime() of last change to gomaxprocs
	totaltime      int64 // ∫gomaxprocs dt up to procresizetime

	// sysmonlock protects sysmon's actions on the runtime.
	//
	// Acquire and hold this mutex to block sysmon from interacting
	// with the rest of the runtime.
	sysmonlock mutex

	// timeToRun is a distribution of scheduling latencies, defined
	// as the sum of time a G spends in the _Grunnable state before
	// it transitions to _Grunning.
	timeToRun timeHistogram

	// idleTime is the total CPU time Ps have "spent" idle.
	//
	// Reset on each GC cycle.
	idleTime atomic.Int64

	// totalMutexWaitTime is the sum of time goroutines have spent in _Gwaiting
	// with a waitreason of the form waitReasonSync{RW,}Mutex{R,}Lock.
	totalMutexWaitTime atomic.Int64

	// stwStoppingTimeGC/Other are distributions of stop-the-world stopping
	// latencies, defined as the time taken by stopTheWorldWithSema to get
	// all Ps to stop. stwStoppingTimeGC covers all GC-related STWs,
	// stwStoppingTimeOther covers the others.
	stwStoppingTimeGC    timeHistogram
	stwStoppingTimeOther timeHistogram

	// stwTotalTimeGC/Other are distributions of stop-the-world total
	// latencies, defined as the total time from stopTheWorldWithSema to
	// startTheWorldWithSema. This is a superset of
	// stwStoppingTimeGC/Other. stwTotalTimeGC covers all GC-related STWs,
	// stwTotalTimeOther covers the others.
	stwTotalTimeGC    timeHistogram
	stwTotalTimeOther timeHistogram

	// totalRuntimeLockWaitTime (plus the value of lockWaitTime on each M in
	// allm) is the sum of time goroutines have spent in _Grunnable and with an
	// M, but waiting for locks within the runtime. This field stores the value
	// for Ms that have exited.
	totalRuntimeLockWaitTime atomic.Int64
}

// Values for the flags field of a sigTabT.
const (
	_SigNotify   = 1 << iota // let signal.Notify have signal, even if from kernel
	_SigKill                 // if signal.Notify doesn't take it, exit quietly
	_SigThrow                // if signal.Notify doesn't take it, exit loudly
	_SigPanic                // if the signal is from the kernel, panic
	_SigDefault              // if the signal isn't explicitly requested, don't monitor it
	_SigGoExit               // cause all runtime procs to exit (only used on Plan 9).
	_SigSetStack             // Don't explicitly install handler, but add SA_ONSTACK to existing libc handler
	_SigUnblock              // always unblock; see blockableSig
	_SigIgn                  // _SIG_DFL action is to ignore the signal
)

// Layout of in-memory per-function information prepared by linker
// See https://golang.org/s/go12symtab.
// Keep in sync with linker (../cmd/link/internal/ld/pcln.go:/pclntab)
// and with package debug/gosym and with symtab.go in package runtime.
type _func struct {
	sys.NotInHeap // Only in static data

	entryOff uint32 // start pc, as offset from moduledata.text/pcHeader.textStart
	nameOff  int32  // function name, as index into moduledata.funcnametab.

	args        int32  // in/out args size
	deferreturn uint32 // offset of start of a deferreturn call instruction from entry, if any.

	pcsp      uint32
	pcfile    uint32
	pcln      uint32
	npcdata   uint32
	cuOffset  uint32     // runtime.cutab offset of this function's CU
	startLine int32      // line number of start of function (func keyword/TEXT directive)
	funcID    abi.FuncID // set for certain special runtime functions
	flag      abi.FuncFlag
	_         [1]byte // pad
	nfuncdata uint8   // must be last, must end on a uint32-aligned boundary

	// The end of the struct is followed immediately by two variable-length
	// arrays that reference the pcdata and funcdata locations for this
	// function.

	// pcdata contains the offset into moduledata.pctab for the start of
	// that index's table. e.g.,
	// &moduledata.pctab[_func.pcdata[_PCDATA_UnsafePoint]] is the start of
	// the unsafe point table.
	//
	// An offset of 0 indicates that there is no table.
	//
	// pcdata [npcdata]uint32

	// funcdata contains the offset past moduledata.gofunc which contains a
	// pointer to that index's funcdata. e.g.,
	// *(moduledata.gofunc +  _func.funcdata[_FUNCDATA_ArgsPointerMaps]) is
	// the argument pointer map.
	//
	// An offset of ^uint32(0) indicates that there is no entry.
	//
	// funcdata [nfuncdata]uint32
}

// Pseudo-Func that is returned for PCs that occur in inlined code.
// A *Func can be either a *_func or a *funcinl, and they are distinguished
// by the first uintptr.
//
// TODO(austin): Can we merge this with inlinedCall?
type funcinl struct {
	ones      uint32  // set to ^0 to distinguish from _func
	entry     uintptr // entry of the real (the "outermost") frame
	name      string
	file      string
	line      int32
	startLine int32
}

type itab = abi.ITab

// Lock-free stack node.
// Also known to export_test.go.
type lfnode struct {
	next    uint64
	pushcnt uintptr
}

type forcegcstate struct {
	lock mutex
	g    *g
	idle atomic.Bool
}

// A _defer holds an entry on the list of deferred calls.
// If you add a field here, add code to clear it in deferProcStack.
// This struct must match the code in cmd/compile/internal/ssagen/ssa.go:deferstruct
// and cmd/compile/internal/ssagen/ssa.go:(*state).call.
// Some defers will be allocated on the stack and some on the heap.
// All defers are logically part of the stack, so write barriers to
// initialize them are not required. All defers must be manually scanned,
// and for heap defers, marked.
type _defer struct {
	heap      bool
	rangefunc bool    // true for rangefunc list
	sp        uintptr // sp at time of defer
	pc        uintptr // pc at time of defer
	fn        func()  // can be nil for open-coded defers
	link      *_defer // next defer on G; can point to either heap or stack!

	// If rangefunc is true, *head is the head of the atomic linked list
	// during a range-over-func execution.
	head *atomic.Pointer[_defer]
}

// A _panic holds information about an active panic.
//
// A _panic value must only ever live on the stack.
//
// The argp and link fields are stack pointers, but don't need special
// handling during stack growth: because they are pointer-typed and
// _panic values only live on the stack, regular stack pointer
// adjustment takes care of them.
type _panic struct {
	argp unsafe.Pointer // pointer to arguments of deferred call run during panic; cannot move - known to liblink
	arg  any            // argument to panic
	link *_panic        // link to earlier panic

	// startPC and startSP track where _panic.start was called.
	startPC uintptr
	startSP unsafe.Pointer

	// The current stack frame that we're running deferred calls for.
	sp unsafe.Pointer
	lr uintptr
	fp unsafe.Pointer

	// retpc stores the PC where the panic should jump back to, if the
	// function last returned by _panic.next() recovers the panic.
	retpc uintptr

	// Extra state for handling open-coded defers.
	deferBitsPtr *uint8
	slotsPtr     unsafe.Pointer

	recovered   bool // whether this panic has been recovered
	goexit      bool
	deferreturn bool
}

// savedOpenDeferState tracks the extra state from _panic that's
// necessary for deferreturn to pick up where gopanic left off,
// without needing to unwind the stack.
type savedOpenDeferState struct {
	retpc           uintptr
	deferBitsOffset uintptr
	slotsOffset     uintptr
}

// ancestorInfo records details of where a goroutine was started.
type ancestorInfo struct {
	pcs  []uintptr // pcs from the stack of this goroutine
	goid uint64    // goroutine id of this goroutine; original goroutine possibly dead
	gopc uintptr   // pc of go statement that created this goroutine
}

// A waitReason explains why a goroutine has been stopped.
// See gopark. Do not re-use waitReasons, add new ones.
type waitReason uint8

const (
	waitReasonZero                  waitReason = iota // ""
	waitReasonGCAssistMarking                         // "GC assist marking"
	waitReasonIOWait                                  // "IO wait"
	waitReasonChanReceiveNilChan                      // "chan receive (nil chan)"
	waitReasonChanSendNilChan                         // "chan send (nil chan)"
	waitReasonDumpingHeap                             // "dumping heap"
	waitReasonGarbageCollection                       // "garbage collection"
	waitReasonGarbageCollectionScan                   // "garbage collection scan"
	waitReasonPanicWait                               // "panicwait"
	waitReasonSelect                                  // "select"
	waitReasonSelectNoCases                           // "select (no cases)"
	waitReasonGCAssistWait                            // "GC assist wait"
	waitReasonGCSweepWait                             // "GC sweep wait"
	waitReasonGCScavengeWait                          // "GC scavenge wait"
	waitReasonChanReceive                             // "chan receive"
	waitReasonChanSend                                // "chan send"
	waitReasonFinalizerWait                           // "finalizer wait"
	waitReasonForceGCIdle                             // "force gc (idle)"
	waitReasonSemacquire                              // "semacquire"
	waitReasonSleep                                   // "sleep"
	waitReasonSyncCondWait                            // "sync.Cond.Wait"
	waitReasonSyncMutexLock                           // "sync.Mutex.Lock"
	waitReasonSyncRWMutexRLock                        // "sync.RWMutex.RLock"
	waitReasonSyncRWMutexLock                         // "sync.RWMutex.Lock"
	waitReasonTraceReaderBlocked                      // "trace reader (blocked)"
	waitReasonWaitForGCCycle                          // "wait for GC cycle"
	waitReasonGCWorkerIdle                            // "GC worker (idle)"
	waitReasonGCWorkerActive                          // "GC worker (active)"
	waitReasonPreempted                               // "preempted"
	waitReasonDebugCall                               // "debug call"
	waitReasonGCMarkTermination                       // "GC mark termination"
	waitReasonStoppingTheWorld                        // "stopping the world"
	waitReasonFlushProcCaches                         // "flushing proc caches"
	waitReasonTraceGoroutineStatus                    // "trace goroutine status"
	waitReasonTraceProcStatus                         // "trace proc status"
	waitReasonPageTraceFlush                          // "page trace flush"
	waitReasonCoroutine                               // "coroutine"
)

var waitReasonStrings = [...]string{
	waitReasonZero:                  "",
	waitReasonGCAssistMarking:       "GC assist marking",
	waitReasonIOWait:                "IO wait",
	waitReasonChanReceiveNilChan:    "chan receive (nil chan)",
	waitReasonChanSendNilChan:       "chan send (nil chan)",
	waitReasonDumpingHeap:           "dumping heap",
	waitReasonGarbageCollection:     "garbage collection",
	waitReasonGarbageCollectionScan: "garbage collection scan",
	waitReasonPanicWait:             "panicwait",
	waitReasonSelect:                "select",
	waitReasonSelectNoCases:         "select (no cases)",
	waitReasonGCAssistWait:          "GC assist wait",
	waitReasonGCSweepWait:           "GC sweep wait",
	waitReasonGCScavengeWait:        "GC scavenge wait",
	waitReasonChanReceive:           "chan receive",
	waitReasonChanSend:              "chan send",
	waitReasonFinalizerWait:         "finalizer wait",
	waitReasonForceGCIdle:           "force gc (idle)",
	waitReasonSemacquire:            "semacquire",
	waitReasonSleep:                 "sleep",
	waitReasonSyncCondWait:          "sync.Cond.Wait",
	waitReasonSyncMutexLock:         "sync.Mutex.Lock",
	waitReasonSyncRWMutexRLock:      "sync.RWMutex.RLock",
	waitReasonSyncRWMutexLock:       "sync.RWMutex.Lock",
	waitReasonTraceReaderBlocked:    "trace reader (blocked)",
	waitReasonWaitForGCCycle:        "wait for GC cycle",
	waitReasonGCWorkerIdle:          "GC worker (idle)",
	waitReasonGCWorkerActive:        "GC worker (active)",
	waitReasonPreempted:             "preempted",
	waitReasonDebugCall:             "debug call",
	waitReasonGCMarkTermination:     "GC mark termination",
	waitReasonStoppingTheWorld:      "stopping the world",
	waitReasonFlushProcCaches:       "flushing proc caches",
	waitReasonTraceGoroutineStatus:  "trace goroutine status",
	waitReasonTraceProcStatus:       "trace proc status",
	waitReasonPageTraceFlush:        "page trace flush",
	waitReasonCoroutine:             "coroutine",
}

func (w waitReason) String() string {
	if w < 0 || w >= waitReason(len(waitReasonStrings)) {
		return "unknown wait reason"
	}
	return waitReasonStrings[w]
}

func (w waitReason) isMutexWait() bool {
	return w == waitReasonSyncMutexLock ||
		w == waitReasonSyncRWMutexRLock ||
		w == waitReasonSyncRWMutexLock
}

func (w waitReason) isWaitingForGC() bool {
	return isWaitingForGC[w]
}

// isWaitingForGC indicates that a goroutine is only entering _Gwaiting and
// setting a waitReason because it needs to be able to let the GC take ownership
// of its stack. The G is always actually executing on the system stack, in
// these cases.
//
// TODO(mknyszek): Consider replacing this with a new dedicated G status.
var isWaitingForGC = [len(waitReasonStrings)]bool{
	waitReasonStoppingTheWorld:      true,
	waitReasonGCMarkTermination:     true,
	waitReasonGarbageCollection:     true,
	waitReasonGarbageCollectionScan: true,
	waitReasonTraceGoroutineStatus:  true,
	waitReasonTraceProcStatus:       true,
	waitReasonPageTraceFlush:        true,
	waitReasonGCAssistMarking:       true,
	waitReasonGCWorkerActive:        true,
	waitReasonFlushProcCaches:       true,
}

var (
	allm       *m
	gomaxprocs int32
	ncpu       int32
	forcegc    forcegcstate
	sched      schedt
	newprocs   int32
)

var (
	// allpLock protects P-less reads and size changes of allp, idlepMask,
	// and timerpMask, and all writes to allp.
	allpLock mutex

	// len(allp) == gomaxprocs; may change at safe points, otherwise
	// immutable.
	allp []*p

	// Bitmask of Ps in _Pidle list, one bit per P. Reads and writes must
	// be atomic. Length may change at safe points.
	//
	// Each P must update only its own bit. In order to maintain
	// consistency, a P going idle must the idle mask simultaneously with
	// updates to the idle P list under the sched.lock, otherwise a racing
	// pidleget may clear the mask before pidleput sets the mask,
	// corrupting the bitmap.
	//
	// N.B., procresize takes ownership of all Ps in stopTheWorldWithSema.
	idlepMask pMask

	// Bitmask of Ps that may have a timer, one bit per P. Reads and writes
	// must be atomic. Length may change at safe points.
	//
	// Ideally, the timer mask would be kept immediately consistent on any timer
	// operations. Unfortunately, updating a shared global data structure in the
	// timer hot path adds too much overhead in applications frequently switching
	// between no timers and some timers.
	//
	// As a compromise, the timer mask is updated only on pidleget / pidleput. A
	// running P (returned by pidleget) may add a timer at any time, so its mask
	// must be set. An idle P (passed to pidleput) cannot add new timers while
	// idle, so if it has no timers at that time, its mask may be cleared.
	//
	// Thus, we get the following effects on timer-stealing in findrunnable:
	//
	//   - Idle Ps with no timers when they go idle are never checked in findrunnable
	//     (for work- or timer-stealing; this is the ideal case).
	//   - Running Ps must always be checked.
	//   - Idle Ps whose timers are stolen must continue to be checked until they run
	//     again, even after timer expiration.
	//
	// When the P starts running again, the mask should be set, as a timer may be
	// added at any time.
	//
	// TODO(prattmic): Additional targeted updates may improve the above cases.
	// e.g., updating the mask when stealing a timer.
	timerpMask pMask
)

var (
	// Pool of GC parked background workers. Entries are type
	// *gcBgMarkWorkerNode.
	gcBgMarkWorkerPool lfstack

	// Total number of gcBgMarkWorker goroutines. Protected by worldsema.
	gcBgMarkWorkerCount int32

	// Information about what cpu features are available.
	// Packages outside the runtime should not use these
	// as they are not an external api.
	// Set on startup in asm_{386,amd64}.s
	processorVersionInfo uint32
	isIntel              bool

	// set by cmd/link on arm systems
	goarm       uint8
	goarmsoftfp uint8
)

// Set by the linker so the runtime can determine the buildmode.
var (
	islibrary bool // -buildmode=c-shared
	isarchive bool // -buildmode=c-archive
)

// Must agree with internal/buildcfg.FramePointerEnabled.
const framepointer_enabled = GOARCH == "amd64" || GOARCH == "arm64"

// getcallerfp returns the frame pointer of the caller of the caller
// of this function.
//
//go:nosplit
//go:noinline
func getcallerfp() uintptr {
	fp := getfp() // This frame's FP.
	if fp != 0 {
		fp = *(*uintptr)(unsafe.Pointer(fp)) // The caller's FP.
		fp = *(*uintptr)(unsafe.Pointer(fp)) // The caller's caller's FP.
	}
	return fp
}