// Copyright 2014 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.

// Memory allocator.
//
// This was originally based on tcmalloc, but has diverged quite a bit.
// http://goog-perftools.sourceforge.net/doc/tcmalloc.html

// The main allocator works in runs of pages.
// Small allocation sizes (up to and including 32 kB) are
// rounded to one of about 70 size classes, each of which
// has its own free set of objects of exactly that size.
// Any free page of memory can be split into a set of objects
// of one size class, which are then managed using a free bitmap.
//
// The allocator's data structures are:
//
//	fixalloc: a free-list allocator for fixed-size off-heap objects,
//		used to manage storage used by the allocator.
//	mheap: the malloc heap, managed at page (8192-byte) granularity.
//	mspan: a run of pages managed by the mheap.
//	mcentral: collects all spans of a given size class.
//	mcache: a per-P cache of mspans with free space.
//	mstats: allocation statistics.
//
// Allocating a small object proceeds up a hierarchy of caches:
//
//	1. Round the size up to one of the small size classes
//	   and look in the corresponding mspan in this P's mcache.
//	   Scan the mspan's free bitmap to find a free slot.
//	   If there is a free slot, allocate it.
//	   This can all be done without acquiring a lock.
//
//	2. If the mspan has no free slots, obtain a new mspan
//	   from the mcentral's list of mspans of the required size
//	   class that have free space.
//	   Obtaining a whole span amortizes the cost of locking
//	   the mcentral.
//
//	3. If the mcentral's mspan list is empty, obtain a run
//	   of pages from the mheap to use for the mspan.
//
//	4. If the mheap is empty or has no page runs large enough,
//	   allocate a new group of pages (at least 1MB) from the
//	   operating system. Allocating a large run of pages
//	   amortizes the cost of talking to the operating system.
//
// Sweeping an mspan and freeing objects on it proceeds up a similar
// hierarchy:
//
//	1. If the mspan is being swept in response to allocation, it
//	   is returned to the mcache to satisfy the allocation.
//
//	2. Otherwise, if the mspan still has allocated objects in it,
//	   it is placed on the mcentral free list for the mspan's size
//	   class.
//
//	3. Otherwise, if all objects in the mspan are free, the mspan
//	   is now "idle", so it is returned to the mheap and no longer
//	   has a size class.
//	   This may coalesce it with adjacent idle mspans.
//
//	4. If an mspan remains idle for long enough, return its pages
//	   to the operating system.
//
// Allocating and freeing a large object uses the mheap
// directly, bypassing the mcache and mcentral.
//
// Free object slots in an mspan are zeroed only if mspan.needzero is
// false. If needzero is true, objects are zeroed as they are
// allocated. There are various benefits to delaying zeroing this way:
//
//	1. Stack frame allocation can avoid zeroing altogether.
//
//	2. It exhibits better temporal locality, since the program is
//	   probably about to write to the memory.
//
//	3. We don't zero pages that never get reused.

package runtime

import (
	"runtime/internal/sys"
	"unsafe"
)

const (
	debugMalloc = false

	maxTinySize   = _TinySize
	tinySizeClass = _TinySizeClass
	maxSmallSize  = _MaxSmallSize

	pageShift = _PageShift
	pageSize  = _PageSize
	pageMask  = _PageMask
	// By construction, single page spans of the smallest object class
	// have the most objects per span.
	maxObjsPerSpan = pageSize / 8

	mSpanInUse = _MSpanInUse

	concurrentSweep = _ConcurrentSweep
)

const (
	_PageShift = 13
	_PageSize  = 1 << _PageShift
	_PageMask  = _PageSize - 1
)

const (
	// _64bit = 1 on 64-bit systems, 0 on 32-bit systems
	_64bit = 1 << (^uintptr(0) >> 63) / 2

	// Computed constant. The definition of MaxSmallSize and the
	// algorithm in msize.go produces some number of different allocation
	// size classes. NumSizeClasses is that number. It's needed here
	// because there are static arrays of this length; when msize runs its
	// size choosing algorithm it double-checks that NumSizeClasses agrees.
	_NumSizeClasses = 67

	// Tunable constants.
	_MaxSmallSize = 32 << 10

	// Tiny allocator parameters, see "Tiny allocator" comment in malloc.go.
	_TinySize      = 16
	_TinySizeClass = 2

	_FixAllocChunk  = 16 << 10               // Chunk size for FixAlloc
	_MaxMHeapList   = 1 << (20 - _PageShift) // Maximum page length for fixed-size list in MHeap.
	_HeapAllocChunk = 1 << 20                // Chunk size for heap growth

	// Per-P, per order stack segment cache size.
	_StackCacheSize = 32 * 1024

	// Number of orders that get caching. Order 0 is FixedStack
	// and each successive order is twice as large.
	// We want to cache 2KB, 4KB, 8KB, and 16KB stacks. Larger stacks
	// will be allocated directly.
	// Since FixedStack is different on different systems, we
	// must vary NumStackOrders to keep the same maximum cached size.
	//   OS               | FixedStack | NumStackOrders
	//   -----------------+------------+---------------
	//   linux/darwin/bsd | 2KB        | 4
	//   windows/32       | 4KB        | 3
	//   windows/64       | 8KB        | 2
	//   plan9            | 4KB        | 3
	_NumStackOrders = 4 - sys.PtrSize/4*sys.GoosWindows - 1*sys.GoosPlan9

	// Number of bits in page to span calculations (4k pages).
	// On Windows 64-bit we limit the arena to 32GB or 35 bits.
	// Windows counts memory used by page table into committed memory
	// of the process, so we can't reserve too much memory.
	// See https://golang.org/issue/5402 and https://golang.org/issue/5236.
	// On other 64-bit platforms, we limit the arena to 512GB, or 39 bits.
	// On 32-bit, we don't bother limiting anything, so we use the full 32-bit address.
	// On Darwin/arm64, we cannot reserve more than ~5GB of virtual memory,
	// but as most devices have less than 4GB of physical memory anyway, we
	// try to be conservative here, and only ask for a 2GB heap.
	_MHeapMap_TotalBits = (_64bit*sys.GoosWindows)*35 + (_64bit*(1-sys.GoosWindows)*(1-sys.GoosDarwin*sys.GoarchArm64))*39 + sys.GoosDarwin*sys.GoarchArm64*31 + (1-_64bit)*32
	_MHeapMap_Bits      = _MHeapMap_TotalBits - _PageShift

	_MaxMem = uintptr(1<<_MHeapMap_TotalBits - 1)

	// Max number of threads to run garbage collection.
	// 2, 3, and 4 are all plausible maximums depending
	// on the hardware details of the machine. The garbage
	// collector scales well to 32 cpus.
	_MaxGcproc = 32
)

const _MaxArena32 = 1<<32 - 1

// physPageSize is the size in bytes of the OS's physical pages.
// Mapping and unmapping operations must be done at multiples of
// physPageSize.
//
// This must be set by the OS init code (typically in osinit) before
// mallocinit.
var physPageSize uintptr

// OS-defined helpers:
//
// sysAlloc obtains a large chunk of zeroed memory from the
// operating system, typically on the order of a hundred kilobytes
// or a megabyte.
// NOTE: sysAlloc returns OS-aligned memory, but the heap allocator
// may use larger alignment, so the caller must be careful to realign the
// memory obtained by sysAlloc.
//
// SysUnused notifies the operating system that the contents
// of the memory region are no longer needed and can be reused
// for other purposes.
// SysUsed notifies the operating system that the contents
// of the memory region are needed again.
//
// SysFree returns it unconditionally; this is only used if
// an out-of-memory error has been detected midway through
// an allocation. It is okay if SysFree is a no-op.
//
// SysReserve reserves address space without allocating memory.
// If the pointer passed to it is non-nil, the caller wants the
// reservation there, but SysReserve can still choose another
// location if that one is unavailable. On some systems and in some
// cases SysReserve will simply check that the address space is
// available and not actually reserve it. If SysReserve returns
// non-nil, it sets *reserved to true if the address space is
// reserved, false if it has merely been checked.
// NOTE: SysReserve returns OS-aligned memory, but the heap allocator
// may use larger alignment, so the caller must be careful to realign the
// memory obtained by sysAlloc.
//
// SysMap maps previously reserved address space for use.
// The reserved argument is true if the address space was really
// reserved, not merely checked.
//
// SysFault marks a (already sysAlloc'd) region to fault
// if accessed. Used only for debugging the runtime.

func mallocinit() {
	initSizes()

	if class_to_size[_TinySizeClass] != _TinySize {
		throw("bad TinySizeClass")
	}

	// Check physPageSize.
	if physPageSize == 0 {
		// The OS init code failed to fetch the physical page size.
		throw("failed to get system page size")
	}
	if physPageSize < minPhysPageSize {
		print("system page size (", physPageSize, ") is smaller than minimum page size (", minPhysPageSize, ")\n")
		throw("bad system page size")
	}
	if physPageSize&(physPageSize-1) != 0 {
		print("system page size (", physPageSize, ") must be a power of 2\n")
		throw("bad system page size")
	}

	var p, bitmapSize, spansSize, pSize, limit uintptr
	var reserved bool

	// limit = runtime.memlimit();
	// See https://golang.org/issue/5049
	// TODO(rsc): Fix after 1.1.
	limit = 0

	// Set up the allocation arena, a contiguous area of memory where
	// allocated data will be found. The arena begins with a bitmap large
	// enough to hold 2 bits per allocated word.
	if sys.PtrSize == 8 && (limit == 0 || limit > 1<<30) {
		// On a 64-bit machine, allocate from a single contiguous reservation.
		// 512 GB (MaxMem) should be big enough for now.
		//
		// The code will work with the reservation at any address, but ask
		// SysReserve to use 0x0000XXc000000000 if possible (XX=00...7f).
		// Allocating a 512 GB region takes away 39 bits, and the amd64
		// doesn't let us choose the top 17 bits, so that leaves the 9 bits
		// in the middle of 0x00c0 for us to choose. Choosing 0x00c0 means
		// that the valid memory addresses will begin 0x00c0, 0x00c1, ..., 0x00df.
		// In little-endian, that's c0 00, c1 00, ..., df 00. None of those are valid
		// UTF-8 sequences, and they are otherwise as far away from
		// ff (likely a common byte) as possible. If that fails, we try other 0xXXc0
		// addresses. An earlier attempt to use 0x11f8 caused out of memory errors
		// on OS X during thread allocations.  0x00c0 causes conflicts with
		// AddressSanitizer which reserves all memory up to 0x0100.
		// These choices are both for debuggability and to reduce the
		// odds of a conservative garbage collector (as is still used in gccgo)
		// not collecting memory because some non-pointer block of memory
		// had a bit pattern that matched a memory address.
		//
		// Actually we reserve 544 GB (because the bitmap ends up being 32 GB)
		// but it hardly matters: e0 00 is not valid UTF-8 either.
		//
		// If this fails we fall back to the 32 bit memory mechanism
		//
		// However, on arm64, we ignore all this advice above and slam the
		// allocation at 0x40 << 32 because when using 4k pages with 3-level
		// translation buffers, the user address space is limited to 39 bits
		// On darwin/arm64, the address space is even smaller.
		arenaSize := round(_MaxMem, _PageSize)
		bitmapSize = arenaSize / (sys.PtrSize * 8 / 2)
		spansSize = arenaSize / _PageSize * sys.PtrSize
		spansSize = round(spansSize, _PageSize)
		for i := 0; i <= 0x7f; i++ {
			switch {
			case GOARCH == "arm64" && GOOS == "darwin":
				p = uintptr(i)<<40 | uintptrMask&(0x0013<<28)
			case GOARCH == "arm64":
				p = uintptr(i)<<40 | uintptrMask&(0x0040<<32)
			default:
				p = uintptr(i)<<40 | uintptrMask&(0x00c0<<32)
			}
			pSize = bitmapSize + spansSize + arenaSize + _PageSize
			p = uintptr(sysReserve(unsafe.Pointer(p), pSize, &reserved))
			if p != 0 {
				break
			}
		}
	}

	if p == 0 {
		// On a 32-bit machine, we can't typically get away
		// with a giant virtual address space reservation.
		// Instead we map the memory information bitmap
		// immediately after the data segment, large enough
		// to handle the entire 4GB address space (256 MB),
		// along with a reservation for an initial arena.
		// When that gets used up, we'll start asking the kernel
		// for any memory anywhere.

		// If we fail to allocate, try again with a smaller arena.
		// This is necessary on Android L where we share a process
		// with ART, which reserves virtual memory aggressively.
		// In the worst case, fall back to a 0-sized initial arena,
		// in the hope that subsequent reservations will succeed.
		arenaSizes := []uintptr{
			512 << 20,
			256 << 20,
			128 << 20,
			0,
		}

		for _, arenaSize := range arenaSizes {
			bitmapSize = (_MaxArena32 + 1) / (sys.PtrSize * 8 / 2)
			spansSize = (_MaxArena32 + 1) / _PageSize * sys.PtrSize
			if limit > 0 && arenaSize+bitmapSize+spansSize > limit {
				bitmapSize = (limit / 9) &^ ((1 << _PageShift) - 1)
				arenaSize = bitmapSize * 8
				spansSize = arenaSize / _PageSize * sys.PtrSize
			}
			spansSize = round(spansSize, _PageSize)

			// SysReserve treats the address we ask for, end, as a hint,
			// not as an absolute requirement. If we ask for the end
			// of the data segment but the operating system requires
			// a little more space before we can start allocating, it will
			// give out a slightly higher pointer. Except QEMU, which
			// is buggy, as usual: it won't adjust the pointer upward.
			// So adjust it upward a little bit ourselves: 1/4 MB to get
			// away from the running binary image and then round up
			// to a MB boundary.
			p = round(firstmoduledata.end+(1<<18), 1<<20)
			pSize = bitmapSize + spansSize + arenaSize + _PageSize
			p = uintptr(sysReserve(unsafe.Pointer(p), pSize, &reserved))
			if p != 0 {
				break
			}
		}
		if p == 0 {
			throw("runtime: cannot reserve arena virtual address space")
		}
	}

	// PageSize can be larger than OS definition of page size,
	// so SysReserve can give us a PageSize-unaligned pointer.
	// To overcome this we ask for PageSize more and round up the pointer.
	p1 := round(p, _PageSize)

	mheap_.spans = (**mspan)(unsafe.Pointer(p1))
	mheap_.bitmap = p1 + spansSize + bitmapSize
	if sys.PtrSize == 4 {
		// Set arena_start such that we can accept memory
		// reservations located anywhere in the 4GB virtual space.
		mheap_.arena_start = 0
	} else {
		mheap_.arena_start = p1 + (spansSize + bitmapSize)
	}
	mheap_.arena_end = p + pSize
	mheap_.arena_used = p1 + (spansSize + bitmapSize)
	mheap_.arena_reserved = reserved

	if mheap_.arena_start&(_PageSize-1) != 0 {
		println("bad pagesize", hex(p), hex(p1), hex(spansSize), hex(bitmapSize), hex(_PageSize), "start", hex(mheap_.arena_start))
		throw("misrounded allocation in mallocinit")
	}

	// Initialize the rest of the allocator.
	mheap_.init(spansSize)
	_g_ := getg()
	_g_.m.mcache = allocmcache()
}

// sysAlloc allocates the next n bytes from the heap arena. The
// returned pointer is always _PageSize aligned and between
// h.arena_start and h.arena_end. sysAlloc returns nil on failure.
// There is no corresponding free function.
func (h *mheap) sysAlloc(n uintptr) unsafe.Pointer {
	if n > h.arena_end-h.arena_used {
		// We are in 32-bit mode, maybe we didn't use all possible address space yet.
		// Reserve some more space.
		p_size := round(n+_PageSize, 256<<20)
		new_end := h.arena_end + p_size // Careful: can overflow
		if h.arena_end <= new_end && new_end-h.arena_start-1 <= _MaxArena32 {
			// TODO: It would be bad if part of the arena
			// is reserved and part is not.
			var reserved bool
			p := uintptr(sysReserve(unsafe.Pointer(h.arena_end), p_size, &reserved))
			if p == 0 {
				return nil
			}
			if p == h.arena_end {
				h.arena_end = new_end
				h.arena_reserved = reserved
			} else if h.arena_start <= p && p+p_size-h.arena_start-1 <= _MaxArena32 {
				// Keep everything page-aligned.
				// Our pages are bigger than hardware pages.
				h.arena_end = p + p_size
				used := p + (-p & (_PageSize - 1))
				h.mapBits(used)
				h.mapSpans(used)
				h.arena_used = used
				h.arena_reserved = reserved
			} else {
				// We haven't added this allocation to
				// the stats, so subtract it from a
				// fake stat (but avoid underflow).
				stat := uint64(p_size)
				sysFree(unsafe.Pointer(p), p_size, &stat)
			}
		}
	}

	if n <= h.arena_end-h.arena_used {
		// Keep taking from our reservation.
		p := h.arena_used
		sysMap(unsafe.Pointer(p), n, h.arena_reserved, &memstats.heap_sys)
		h.mapBits(p + n)
		h.mapSpans(p + n)
		h.arena_used = p + n
		if raceenabled {
			racemapshadow(unsafe.Pointer(p), n)
		}

		if p&(_PageSize-1) != 0 {
			throw("misrounded allocation in MHeap_SysAlloc")
		}
		return unsafe.Pointer(p)
	}

	// If using 64-bit, our reservation is all we have.
	if h.arena_end-h.arena_start > _MaxArena32 {
		return nil
	}

	// On 32-bit, once the reservation is gone we can
	// try to get memory at a location chosen by the OS.
	p_size := round(n, _PageSize) + _PageSize
	p := uintptr(sysAlloc(p_size, &memstats.heap_sys))
	if p == 0 {
		return nil
	}

	if p < h.arena_start || p+p_size-h.arena_start > _MaxArena32 {
		top := ^uintptr(0)
		if top-h.arena_start-1 > _MaxArena32 {
			top = h.arena_start + _MaxArena32 + 1
		}
		print("runtime: memory allocated by OS (", hex(p), ") not in usable range [", hex(h.arena_start), ",", hex(top), ")\n")
		sysFree(unsafe.Pointer(p), p_size, &memstats.heap_sys)
		return nil
	}

	p_end := p + p_size
	p += -p & (_PageSize - 1)
	if p+n > h.arena_used {
		h.mapBits(p + n)
		h.mapSpans(p + n)
		h.arena_used = p + n
		if p_end > h.arena_end {
			h.arena_end = p_end
		}
		if raceenabled {
			racemapshadow(unsafe.Pointer(p), n)
		}
	}

	if p&(_PageSize-1) != 0 {
		throw("misrounded allocation in MHeap_SysAlloc")
	}
	return unsafe.Pointer(p)
}

// base address for all 0-byte allocations
var zerobase uintptr

// nextFreeFast returns the next free object if one is quickly available.
// Otherwise it returns 0.
func nextFreeFast(s *mspan) gclinkptr {
	theBit := sys.Ctz64(s.allocCache) // Is there a free object in the allocCache?
	if theBit < 64 {
		result := s.freeindex + uintptr(theBit)
		if result < s.nelems {
			freeidx := result + 1
			if freeidx%64 == 0 && freeidx != s.nelems {
				return 0
			}
			s.allocCache >>= (theBit + 1)
			s.freeindex = freeidx
			v := gclinkptr(result*s.elemsize + s.base())
			s.allocCount++
			return v
		}
	}
	return 0
}

// nextFree returns the next free object from the cached span if one is available.
// Otherwise it refills the cache with a span with an available object and
// returns that object along with a flag indicating that this was a heavy
// weight allocation. If it is a heavy weight allocation the caller must
// determine whether a new GC cycle needs to be started or if the GC is active
// whether this goroutine needs to assist the GC.
func (c *mcache) nextFree(sizeclass uint8) (v gclinkptr, s *mspan, shouldhelpgc bool) {
	s = c.alloc[sizeclass]
	shouldhelpgc = false
	freeIndex := s.nextFreeIndex()
	if freeIndex == s.nelems {
		// The span is full.
		if uintptr(s.allocCount) != s.nelems {
			println("runtime: s.allocCount=", s.allocCount, "s.nelems=", s.nelems)
			throw("s.allocCount != s.nelems && freeIndex == s.nelems")
		}
		systemstack(func() {
			c.refill(int32(sizeclass))
		})
		shouldhelpgc = true
		s = c.alloc[sizeclass]

		freeIndex = s.nextFreeIndex()
	}

	if freeIndex >= s.nelems {
		throw("freeIndex is not valid")
	}

	v = gclinkptr(freeIndex*s.elemsize + s.base())
	s.allocCount++
	if uintptr(s.allocCount) > s.nelems {
		println("s.allocCount=", s.allocCount, "s.nelems=", s.nelems)
		throw("s.allocCount > s.nelems")
	}
	return
}

// Allocate an object of size bytes.
// Small objects are allocated from the per-P cache's free lists.
// Large objects (> 32 kB) are allocated straight from the heap.
func mallocgc(size uintptr, typ *_type, needzero bool) unsafe.Pointer {
	if gcphase == _GCmarktermination {
		throw("mallocgc called with gcphase == _GCmarktermination")
	}

	if size == 0 {
		return unsafe.Pointer(&zerobase)
	}

	if debug.sbrk != 0 {
		align := uintptr(16)
		if typ != nil {
			align = uintptr(typ.align)
		}
		return persistentalloc(size, align, &memstats.other_sys)
	}

	// assistG is the G to charge for this allocation, or nil if
	// GC is not currently active.
	var assistG *g
	if gcBlackenEnabled != 0 {
		// Charge the current user G for this allocation.
		assistG = getg()
		if assistG.m.curg != nil {
			assistG = assistG.m.curg
		}
		// Charge the allocation against the G. We'll account
		// for internal fragmentation at the end of mallocgc.
		assistG.gcAssistBytes -= int64(size)

		if assistG.gcAssistBytes < 0 {
			// This G is in debt. Assist the GC to correct
			// this before allocating. This must happen
			// before disabling preemption.
			gcAssistAlloc(assistG)
		}
	}

	// Set mp.mallocing to keep from being preempted by GC.
	mp := acquirem()
	if mp.mallocing != 0 {
		throw("malloc deadlock")
	}
	if mp.gsignal == getg() {
		throw("malloc during signal")
	}
	mp.mallocing = 1

	shouldhelpgc := false
	dataSize := size
	c := gomcache()
	var x unsafe.Pointer
	noscan := typ == nil || typ.kind&kindNoPointers != 0
	if size <= maxSmallSize {
		if noscan && size < maxTinySize {
			// Tiny allocator.
			//
			// Tiny allocator combines several tiny allocation requests
			// into a single memory block. The resulting memory block
			// is freed when all subobjects are unreachable. The subobjects
			// must be noscan (don't have pointers), this ensures that
			// the amount of potentially wasted memory is bounded.
			//
			// Size of the memory block used for combining (maxTinySize) is tunable.
			// Current setting is 16 bytes, which relates to 2x worst case memory
			// wastage (when all but one subobjects are unreachable).
			// 8 bytes would result in no wastage at all, but provides less
			// opportunities for combining.
			// 32 bytes provides more opportunities for combining,
			// but can lead to 4x worst case wastage.
			// The best case winning is 8x regardless of block size.
			//
			// Objects obtained from tiny allocator must not be freed explicitly.
			// So when an object will be freed explicitly, we ensure that
			// its size >= maxTinySize.
			//
			// SetFinalizer has a special case for objects potentially coming
			// from tiny allocator, it such case it allows to set finalizers
			// for an inner byte of a memory block.
			//
			// The main targets of tiny allocator are small strings and
			// standalone escaping variables. On a json benchmark
			// the allocator reduces number of allocations by ~12% and
			// reduces heap size by ~20%.
			off := c.tinyoffset
			// Align tiny pointer for required (conservative) alignment.
			if size&7 == 0 {
				off = round(off, 8)
			} else if size&3 == 0 {
				off = round(off, 4)
			} else if size&1 == 0 {
				off = round(off, 2)
			}
			if off+size <= maxTinySize && c.tiny != 0 {
				// The object fits into existing tiny block.
				x = unsafe.Pointer(c.tiny + off)
				c.tinyoffset = off + size
				c.local_tinyallocs++
				mp.mallocing = 0
				releasem(mp)
				return x
			}
			// Allocate a new maxTinySize block.
			span := c.alloc[tinySizeClass]
			v := nextFreeFast(span)
			if v == 0 {
				v, _, shouldhelpgc = c.nextFree(tinySizeClass)
			}
			x = unsafe.Pointer(v)
			(*[2]uint64)(x)[0] = 0
			(*[2]uint64)(x)[1] = 0
			// See if we need to replace the existing tiny block with the new one
			// based on amount of remaining free space.
			if size < c.tinyoffset || c.tiny == 0 {
				c.tiny = uintptr(x)
				c.tinyoffset = size
			}
			size = maxTinySize
		} else {
			var sizeclass uint8
			if size <= smallSizeMax-8 {
				sizeclass = size_to_class8[(size+smallSizeDiv-1)/smallSizeDiv]
			} else {
				sizeclass = size_to_class128[(size-smallSizeMax+largeSizeDiv-1)/largeSizeDiv]
			}
			size = uintptr(class_to_size[sizeclass])
			span := c.alloc[sizeclass]
			v := nextFreeFast(span)
			if v == 0 {
				v, span, shouldhelpgc = c.nextFree(sizeclass)
			}
			x = unsafe.Pointer(v)
			if needzero && span.needzero != 0 {
				memclr(unsafe.Pointer(v), size)
			}
		}
	} else {
		var s *mspan
		shouldhelpgc = true
		systemstack(func() {
			s = largeAlloc(size, needzero)
		})
		s.freeindex = 1
		s.allocCount = 1
		x = unsafe.Pointer(s.base())
		size = s.elemsize
	}

	var scanSize uintptr
	if noscan {
		heapBitsSetTypeNoScan(uintptr(x))
	} else {
		// If allocating a defer+arg block, now that we've picked a malloc size
		// large enough to hold everything, cut the "asked for" size down to
		// just the defer header, so that the GC bitmap will record the arg block
		// as containing nothing at all (as if it were unused space at the end of
		// a malloc block caused by size rounding).
		// The defer arg areas are scanned as part of scanstack.
		if typ == deferType {
			dataSize = unsafe.Sizeof(_defer{})
		}
		heapBitsSetType(uintptr(x), size, dataSize, typ)
		if dataSize > typ.size {
			// Array allocation. If there are any
			// pointers, GC has to scan to the last
			// element.
			if typ.ptrdata != 0 {
				scanSize = dataSize - typ.size + typ.ptrdata
			}
		} else {
			scanSize = typ.ptrdata
		}
		c.local_scan += scanSize
	}

	// Ensure that the stores above that initialize x to
	// type-safe memory and set the heap bits occur before
	// the caller can make x observable to the garbage
	// collector. Otherwise, on weakly ordered machines,
	// the garbage collector could follow a pointer to x,
	// but see uninitialized memory or stale heap bits.
	publicationBarrier()

	// Allocate black during GC.
	// All slots hold nil so no scanning is needed.
	// This may be racing with GC so do it atomically if there can be
	// a race marking the bit.
	if gcphase != _GCoff {
		gcmarknewobject(uintptr(x), size, scanSize)
	}

	if raceenabled {
		racemalloc(x, size)
	}

	if msanenabled {
		msanmalloc(x, size)
	}

	mp.mallocing = 0
	releasem(mp)

	if debug.allocfreetrace != 0 {
		tracealloc(x, size, typ)
	}

	if rate := MemProfileRate; rate > 0 {
		if size < uintptr(rate) && int32(size) < c.next_sample {
			c.next_sample -= int32(size)
		} else {
			mp := acquirem()
			profilealloc(mp, x, size)
			releasem(mp)
		}
	}

	if assistG != nil {
		// Account for internal fragmentation in the assist
		// debt now that we know it.
		assistG.gcAssistBytes -= int64(size - dataSize)
	}

	if shouldhelpgc && gcShouldStart(false) {
		gcStart(gcBackgroundMode, false)
	}

	return x
}

func largeAlloc(size uintptr, needzero bool) *mspan {
	// print("largeAlloc size=", size, "\n")

	if size+_PageSize < size {
		throw("out of memory")
	}
	npages := size >> _PageShift
	if size&_PageMask != 0 {
		npages++
	}

	// Deduct credit for this span allocation and sweep if
	// necessary. mHeap_Alloc will also sweep npages, so this only
	// pays the debt down to npage pages.
	deductSweepCredit(npages*_PageSize, npages)

	s := mheap_.alloc(npages, 0, true, needzero)
	if s == nil {
		throw("out of memory")
	}
	s.limit = s.base() + size
	heapBitsForSpan(s.base()).initSpan(s)
	return s
}

// implementation of new builtin
// compiler (both frontend and SSA backend) knows the signature
// of this function
func newobject(typ *_type) unsafe.Pointer {
	return mallocgc(typ.size, typ, true)
}

//go:linkname reflect_unsafe_New reflect.unsafe_New
func reflect_unsafe_New(typ *_type) unsafe.Pointer {
	return newobject(typ)
}

// newarray allocates an array of n elements of type typ.
func newarray(typ *_type, n int) unsafe.Pointer {
	if n < 0 || uintptr(n) > maxSliceCap(typ.size) {
		panic(plainError("runtime: allocation size out of range"))
	}
	return mallocgc(typ.size*uintptr(n), typ, true)
}

//go:linkname reflect_unsafe_NewArray reflect.unsafe_NewArray
func reflect_unsafe_NewArray(typ *_type, n int) unsafe.Pointer {
	return newarray(typ, n)
}

func profilealloc(mp *m, x unsafe.Pointer, size uintptr) {
	mp.mcache.next_sample = nextSample()
	mProf_Malloc(x, size)
}

// nextSample returns the next sampling point for heap profiling.
// It produces a random variable with a geometric distribution and
// mean MemProfileRate. This is done by generating a uniformly
// distributed random number and applying the cumulative distribution
// function for an exponential.
func nextSample() int32 {
	if GOOS == "plan9" {
		// Plan 9 doesn't support floating point in note handler.
		if g := getg(); g == g.m.gsignal {
			return nextSampleNoFP()
		}
	}

	period := MemProfileRate

	// make nextSample not overflow. Maximum possible step is
	// -ln(1/(1<<kRandomBitCount)) * period, approximately 20 * period.
	switch {
	case period > 0x7000000:
		period = 0x7000000
	case period == 0:
		return 0
	}

	// Let m be the sample rate,
	// the probability distribution function is m*exp(-mx), so the CDF is
	// p = 1 - exp(-mx), so
	// q = 1 - p == exp(-mx)
	// log_e(q) = -mx
	// -log_e(q)/m = x
	// x = -log_e(q) * period
	// x = log_2(q) * (-log_e(2)) * period    ; Using log_2 for efficiency
	const randomBitCount = 26
	q := fastrand()%(1<<randomBitCount) + 1
	qlog := fastlog2(float64(q)) - randomBitCount
	if qlog > 0 {
		qlog = 0
	}
	const minusLog2 = -0.6931471805599453 // -ln(2)
	return int32(qlog*(minusLog2*float64(period))) + 1
}

// nextSampleNoFP is similar to nextSample, but uses older,
// simpler code to avoid floating point.
func nextSampleNoFP() int32 {
	// Set first allocation sample size.
	rate := MemProfileRate
	if rate > 0x3fffffff { // make 2*rate not overflow
		rate = 0x3fffffff
	}
	if rate != 0 {
		return int32(int(fastrand()) % (2 * rate))
	}
	return 0
}

type persistentAlloc struct {
	base unsafe.Pointer
	off  uintptr
}

var globalAlloc struct {
	mutex
	persistentAlloc
}

// Wrapper around sysAlloc that can allocate small chunks.
// There is no associated free operation.
// Intended for things like function/type/debug-related persistent data.
// If align is 0, uses default align (currently 8).
func persistentalloc(size, align uintptr, sysStat *uint64) unsafe.Pointer {
	var p unsafe.Pointer
	systemstack(func() {
		p = persistentalloc1(size, align, sysStat)
	})
	return p
}

// Must run on system stack because stack growth can (re)invoke it.
// See issue 9174.
//go:systemstack
func persistentalloc1(size, align uintptr, sysStat *uint64) unsafe.Pointer {
	const (
		chunk    = 256 << 10
		maxBlock = 64 << 10 // VM reservation granularity is 64K on windows
	)

	if size == 0 {
		throw("persistentalloc: size == 0")
	}
	if align != 0 {
		if align&(align-1) != 0 {
			throw("persistentalloc: align is not a power of 2")
		}
		if align > _PageSize {
			throw("persistentalloc: align is too large")
		}
	} else {
		align = 8
	}

	if size >= maxBlock {
		return sysAlloc(size, sysStat)
	}

	mp := acquirem()
	var persistent *persistentAlloc
	if mp != nil && mp.p != 0 {
		persistent = &mp.p.ptr().palloc
	} else {
		lock(&globalAlloc.mutex)
		persistent = &globalAlloc.persistentAlloc
	}
	persistent.off = round(persistent.off, align)
	if persistent.off+size > chunk || persistent.base == nil {
		persistent.base = sysAlloc(chunk, &memstats.other_sys)
		if persistent.base == nil {
			if persistent == &globalAlloc.persistentAlloc {
				unlock(&globalAlloc.mutex)
			}
			throw("runtime: cannot allocate memory")
		}
		persistent.off = 0
	}
	p := add(persistent.base, persistent.off)
	persistent.off += size
	releasem(mp)
	if persistent == &globalAlloc.persistentAlloc {
		unlock(&globalAlloc.mutex)
	}

	if sysStat != &memstats.other_sys {
		mSysStatInc(sysStat, size)
		mSysStatDec(&memstats.other_sys, size)
	}
	return p
}