Go Map

type hmap struct {
    // Note: the format of the hmap is also encoded in cmd/compile/internal/gc/reflect.go.
    // Make sure this stays in sync with the compiler's definition.
    count     int // # live cells == size of map.  Must be first (used by len() builtin)
    flags     uint8
    B         uint8  // log_2 of # of buckets (can hold up to loadFactor * 2^B items)
    noverflow uint16 // approximate number of overflow buckets; see incrnoverflow for details
    hash0     uint32 // hash seed

    buckets    unsafe.Pointer // array of 2^B Buckets. may be nil if count==0.
    oldbuckets unsafe.Pointer // previous bucket array of half the size, non-nil only when growing
    nevacuate  uintptr        // progress counter for evacuation (buckets less than this have been evacuated)

    extra *mapextra // optional fields
}

const (
    // Maximum number of key/elem pairs a bucket can hold.
    bucketCntBits = 3
    bucketCnt     = 1 << bucketCntBits
)

type bmap struct {
    // tophash generally contains the top byte of the hash value
    // for each key in this bucket. If tophash[0] < minTopHash,
    // tophash[0] is a bucket evacuation state instead.
    tophash [bucketCnt]uint8
    // Followed by bucketCnt keys and then bucketCnt elems.
    // NOTE: packing all the keys together and then all the elems together makes the
    // code a bit more complicated than alternating key/elem/key/elem/... but it allows
    // us to eliminate padding which would be needed for, e.g., map[int64]int8.
    // Followed by an overflow pointer.
}

type bmap struct {
    topbits  [8]uint8
    keys     [8]keytype
    elems    [8]elemtype
    overflow uintptr
}

m1 := make(map[string]int) // makemap_small
m2 := make(map[string]int, 8) // makemap

func schedinit() {
    cpuinit()       // must run before alginit
    alginit()       // maps must not be used before this call
}

func alginit() {
    // Install AES hash algorithms if the instructions needed are present.
    if (GOARCH == "386" || GOARCH == "amd64") &&
        cpu.X86.HasAES && // AESENC
        cpu.X86.HasSSSE3 && // PSHUFB
        cpu.X86.HasSSE41 { // PINSR{D,Q}
        initAlgAES()
        return
    }
    if GOARCH == "arm64" && cpu.ARM64.HasAES {
        initAlgAES()
        return
    }
    getRandomData((*[len(hashkey) * sys.PtrSize]byte)(unsafe.Pointer(&hashkey))[:])
    hashkey[0] |= 1 // make sure these numbers are odd
    hashkey[1] |= 1
    hashkey[2] |= 1
    hashkey[3] |= 1
}

func initAlgAES() {
    useAeshash = true
    // Initialize with random data so hash collisions will be hard to engineer.
    getRandomData(aeskeysched[:])
}

func strhash(p unsafe.Pointer, h uintptr) uintptr

// func strhash(p unsafe.Pointer, h uintptr) uintptr
TEXT runtime·strhash(SB),NOSPLIT,$0-24
    CMPB runtime·useAeshash(SB), $0
    JEQ noaes
    MOVQ p+0(FP), AX // ptr to string struct
    MOVQ 8(AX), CX // length of string
    MOVQ (AX), AX // string data
    LEAQ ret+16(FP), DX
    JMP aeshashbody<>(SB)
noaes:
    JMP runtime·strhashFallback(SB)

k1 := m["k1"] // mapaccess1
_, prs := m["k2"] // mapaccess2

func mapaccess1(t *maptype, h *hmap, key unsafe.Pointer) unsafe.Pointer {
    // a lot of code here
    hash := t.hasher(key, uintptr(h.hash0))
    m := bucketMask(h.B)
    b := (*bmap)(add(h.buckets, (hash&m)*uintptr(t.bucketsize)))
    if c := h.oldbuckets; c != nil {
        if !h.sameSizeGrow() {
            // There used to be half as many buckets; mask down one more power of two.
            m >>= 1
        }
        oldb := (*bmap)(add(c, (hash&m)*uintptr(t.bucketsize)))
        if !evacuated(oldb) {
            b = oldb
        }
    }
    top := tophash(hash)
bucketloop:
    for ; b != nil; b = b.overflow(t) {
        for i := uintptr(0); i < bucketCnt; i++ {
            if b.tophash[i] != top {
                if b.tophash[i] == emptyRest {
                    break bucketloop
                }
                continue
            }
            k := add(unsafe.Pointer(b), dataOffset+i*uintptr(t.keysize))
            if t.indirectkey() {
                k = *((*unsafe.Pointer)(k))
            }
            if t.key.equal(key, k) {
                e := add(unsafe.Pointer(b), dataOffset+bucketCnt*uintptr(t.keysize)+i*uintptr(t.elemsize))
                if t.indirectelem() {
                    e = *((*unsafe.Pointer)(e))
                }
                return e
            }
        }
    }
    return unsafe.Pointer(&zeroVal[0])
}

m["k1"] = 7

// Like mapaccess, but allocates a slot for the key if it is not present in the map.
func mapassign(t *maptype, h *hmap, key unsafe.Pointer) unsafe.Pointer {
    // a lot of code here
    hash := t.hasher(key, uintptr(h.hash0))

    // Set hashWriting after calling t.hasher, since t.hasher may panic,
    // in which case we have not actually done a write.
    h.flags ^= hashWriting

    if h.buckets == nil {
        h.buckets = newobject(t.bucket) // newarray(t.bucket, 1)
    }

again:
    bucket := hash & bucketMask(h.B)
    if h.growing() {
        growWork(t, h, bucket)
    }
    b := (*bmap)(add(h.buckets, bucket*uintptr(t.bucketsize)))
    top := tophash(hash)

    var inserti *uint8
    var insertk unsafe.Pointer
    var elem unsafe.Pointer
bucketloop:
    for {
        for i := uintptr(0); i < bucketCnt; i++ {
            if b.tophash[i] != top {
                if isEmpty(b.tophash[i]) && inserti == nil {
                    inserti = &b.tophash[i]
                    insertk = add(unsafe.Pointer(b), dataOffset+i*uintptr(t.keysize))
                    elem = add(unsafe.Pointer(b), dataOffset+bucketCnt*uintptr(t.keysize)+i*uintptr(t.elemsize))
                }
                if b.tophash[i] == emptyRest {
                    break bucketloop
                }
                continue
            }
            k := add(unsafe.Pointer(b), dataOffset+i*uintptr(t.keysize))
            if t.indirectkey() {
                k = *((*unsafe.Pointer)(k))
            }
            if !t.key.equal(key, k) {
                continue
            }
            // already have a mapping for key. Update it.
            if t.needkeyupdate() {
                typedmemmove(t.key, k, key)
            }
            elem = add(unsafe.Pointer(b), dataOffset+bucketCnt*uintptr(t.keysize)+i*uintptr(t.elemsize))
            goto done
        }
        ovf := b.overflow(t)
        if ovf == nil {
            break
        }
        b = ovf
    }

    // Did not find mapping for key. Allocate new cell & add entry.

    // If we hit the max load factor or we have too many overflow buckets,
    // and we're not already in the middle of growing, start growing.
    if !h.growing() && (overLoadFactor(h.count+1, h.B) || tooManyOverflowBuckets(h.noverflow, h.B)) {
        hashGrow(t, h)
        goto again // Growing the table invalidates everything, so try again
    }

    if inserti == nil {
        // The current bucket and all the overflow buckets connected to it are full, allocate a new one.
        newb := h.newoverflow(t, b)
        inserti = &newb.tophash[0]
        insertk = add(unsafe.Pointer(newb), dataOffset)
        elem = add(insertk, bucketCnt*uintptr(t.keysize))
    }

    // store new key/elem at insert position
    if t.indirectkey() {
        kmem := newobject(t.key)
        *(*unsafe.Pointer)(insertk) = kmem
        insertk = kmem
    }
    if t.indirectelem() {
        vmem := newobject(t.elem)
        *(*unsafe.Pointer)(elem) = vmem
    }
    typedmemmove(t.key, insertk, key)
    *inserti = top
    h.count++
}

// If we hit the max load factor or we have too many overflow buckets,
// and we're not already in the middle of growing, start growing.
if !h.growing() && (overLoadFactor(h.count+1, h.B) || tooManyOverflowBuckets(h.noverflow, h.B)) {
    hashGrow(t, h)
    goto again // Growing the table invalidates everything, so try again
}

func hashGrow(t *maptype, h *hmap) {
    // If we've hit the load factor, get bigger.
    // Otherwise, there are too many overflow buckets,
    // so keep the same number of buckets and "grow" laterally.
    bigger := uint8(1)
    if !overLoadFactor(h.count+1, h.B) {
        bigger = 0
        h.flags |= sameSizeGrow
    }
    oldbuckets := h.buckets
    newbuckets, nextOverflow := makeBucketArray(t, h.B+bigger, nil)

    flags := h.flags &^ (iterator | oldIterator)
    if h.flags&iterator != 0 {
        flags |= oldIterator
    }
    // commit the grow (atomic wrt gc)
    h.B += bigger
    h.flags = flags
    h.oldbuckets = oldbuckets
    h.buckets = newbuckets
    h.nevacuate = 0
    h.noverflow = 0

    if h.extra != nil && h.extra.overflow != nil {
        // Promote current overflow buckets to the old generation.
        if h.extra.oldoverflow != nil {
            throw("oldoverflow is not nil")
        }
        h.extra.oldoverflow = h.extra.overflow
        h.extra.overflow = nil
    }
    if nextOverflow != nil {
        if h.extra == nil {
            h.extra = new(mapextra)
        }
        h.extra.nextOverflow = nextOverflow
    }

    // the actual copying of the hash table data is done incrementally
    // by growWork() and evacuate().
}

for k, v := range m1 {
    // do something
}

func mapiterinit(t *maptype, h *hmap, it *hiter) {
    if raceenabled && h != nil {
        callerpc := getcallerpc()
        racereadpc(unsafe.Pointer(h), callerpc, funcPC(mapiterinit))
    }

    if h == nil || h.count == 0 {
        return
    }

    if unsafe.Sizeof(hiter{})/sys.PtrSize != 12 {
        throw("hash_iter size incorrect") // see cmd/compile/internal/gc/reflect.go
    }
    it.t = t
    it.h = h

    // grab snapshot of bucket state
    it.B = h.B
    it.buckets = h.buckets
    if t.bucket.ptrdata == 0 {
        // Allocate the current slice and remember pointers to both current and old.
        // This preserves all relevant overflow buckets alive even if
        // the table grows and/or overflow buckets are added to the table
        // while we are iterating.
        h.createOverflow()
        it.overflow = h.extra.overflow
        it.oldoverflow = h.extra.oldoverflow
    }

    // decide where to start
    r := uintptr(fastrand())
    if h.B > 31-bucketCntBits {
        r += uintptr(fastrand()) << 31
    }
    it.startBucket = r & bucketMask(h.B)
    it.offset = uint8(r >> h.B & (bucketCnt - 1))

    // iterator state
    it.bucket = it.startBucket

    // Remember we have an iterator.
    // Can run concurrently with another mapiterinit().
    if old := h.flags; old&(iterator|oldIterator) != iterator|oldIterator {
        atomic.Or8(&h.flags, iterator|oldIterator)
    }

    mapiternext(it)
}

type hiter struct {
    key         unsafe.Pointer // Must be in first position.  Write nil to indicate iteration end (see cmd/compile/internal/gc/range.go).
    elem        unsafe.Pointer // Must be in second position (see cmd/compile/internal/gc/range.go).
    t           *maptype
    h           *hmap
    buckets     unsafe.Pointer // bucket ptr at hash_iter initialization time
    bptr        *bmap          // current bucket
    overflow    *[]*bmap       // keeps overflow buckets of hmap.buckets alive
    oldoverflow *[]*bmap       // keeps overflow buckets of hmap.oldbuckets alive
    startBucket uintptr        // bucket iteration started at
    offset      uint8          // intra-bucket offset to start from during iteration (should be big enough to hold bucketCnt-1)
    wrapped     bool           // already wrapped around from end of bucket array to beginning
    B           uint8
    i           uint8
    bucket      uintptr
    checkBucket uintptr
}

    // decide where to start
    r := uintptr(fastrand())
    if h.B > 31-bucketCntBits {
        r += uintptr(fastrand()) << 31
    }
    it.startBucket = r & bucketMask(h.B)
    it.offset = uint8(r >> h.B & (bucketCnt - 1))