gcc/libgo/go/runtime/alg.go
Ian Lance Taylor 10172a64ce compiler, runtime, reflect: generate hash functions only for map keys
Right now we generate hash functions for all types, just in case they
    are used as map keys. That's a lot of wasted effort and binary size
    for types which will never be used as a map key. Instead, generate
    hash functions only for types that we know are map keys.
    
    Just doing that is a bit too simple, since maps with an interface type
    as a key might have to hash any concrete key type that implements that
    interface. So for that case, implement hashing of such types at
    runtime (instead of with generated code). It will be slower, but only
    for maps with interface types as keys, and maybe only a bit slower as
    the aeshash time probably dominates the dispatch time.
    
    Reorg where we keep the equals and hash functions. Move the hash function
    from the key type to the map type, saving a field in every non-map type.
    That leaves only one function in the alg structure, so get rid of that and
    just keep the equal function in the type descriptor itself.
    
    While we're here, reorganize the rtype struct to more closely match
    the gc version.
    
    This is the gofrontend version of https://golang.org/cl/191198.
    
    Reviewed-on: https://go-review.googlesource.com/c/gofrontend/+/212843

From-SVN: r279848
2020-01-02 21:55:32 +00:00

508 lines
12 KiB
Go

// 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.
package runtime
import (
"internal/cpu"
"runtime/internal/sys"
"unsafe"
)
// For gccgo, use go:linkname to export compiler-called functions.
//
//go:linkname memhash0
//go:linkname memhash8
//go:linkname memhash16
//go:linkname memhash32
//go:linkname memhash64
//go:linkname memhash128
//go:linkname strhash
//go:linkname f32hash
//go:linkname f64hash
//go:linkname c64hash
//go:linkname c128hash
//go:linkname interhash
//go:linkname nilinterhash
//go:linkname memequal0
//go:linkname memequal8
//go:linkname memequal16
//go:linkname memequal32
//go:linkname memequal64
//go:linkname memequal128
//go:linkname strequal
//go:linkname f32equal
//go:linkname f64equal
//go:linkname c64equal
//go:linkname c128equal
//go:linkname interequal
//go:linkname nilinterequal
//go:linkname efaceeq
//go:linkname ifaceeq
//go:linkname ifacevaleq
//go:linkname ifaceefaceeq
//go:linkname efacevaleq
//go:linkname cmpstring
//
// Temporary to be called from C code.
//go:linkname alginit
const (
c0 = uintptr((8-sys.PtrSize)/4*2860486313 + (sys.PtrSize-4)/4*33054211828000289)
c1 = uintptr((8-sys.PtrSize)/4*3267000013 + (sys.PtrSize-4)/4*23344194077549503)
)
func memhash0(p unsafe.Pointer, h uintptr) uintptr {
return h
}
func memhash8(p unsafe.Pointer, h uintptr) uintptr {
return memhash(p, h, 1)
}
func memhash16(p unsafe.Pointer, h uintptr) uintptr {
return memhash(p, h, 2)
}
func memhash128(p unsafe.Pointer, h uintptr) uintptr {
return memhash(p, h, 16)
}
// runtime variable to check if the processor we're running on
// actually supports the instructions used by the AES-based
// hash implementation.
var useAeshash bool
// in C code
func aeshashbody(p unsafe.Pointer, h, s uintptr, sched []byte) uintptr
func aeshash(p unsafe.Pointer, h, s uintptr) uintptr {
return aeshashbody(p, h, s, aeskeysched[:])
}
func aeshashstr(p unsafe.Pointer, h uintptr) uintptr {
ps := (*stringStruct)(p)
return aeshashbody(unsafe.Pointer(ps.str), h, uintptr(ps.len), aeskeysched[:])
}
func strhash(a unsafe.Pointer, h uintptr) uintptr {
x := (*stringStruct)(a)
return memhash(x.str, h, uintptr(x.len))
}
// NOTE: Because NaN != NaN, a map can contain any
// number of (mostly useless) entries keyed with NaNs.
// To avoid long hash chains, we assign a random number
// as the hash value for a NaN.
func f32hash(p unsafe.Pointer, h uintptr) uintptr {
f := *(*float32)(p)
switch {
case f == 0:
return c1 * (c0 ^ h) // +0, -0
case f != f:
return c1 * (c0 ^ h ^ uintptr(fastrand())) // any kind of NaN
default:
return memhash(p, h, 4)
}
}
func f64hash(p unsafe.Pointer, h uintptr) uintptr {
f := *(*float64)(p)
switch {
case f == 0:
return c1 * (c0 ^ h) // +0, -0
case f != f:
return c1 * (c0 ^ h ^ uintptr(fastrand())) // any kind of NaN
default:
return memhash(p, h, 8)
}
}
func c64hash(p unsafe.Pointer, h uintptr) uintptr {
x := (*[2]float32)(p)
return f32hash(unsafe.Pointer(&x[1]), f32hash(unsafe.Pointer(&x[0]), h))
}
func c128hash(p unsafe.Pointer, h uintptr) uintptr {
x := (*[2]float64)(p)
return f64hash(unsafe.Pointer(&x[1]), f64hash(unsafe.Pointer(&x[0]), h))
}
func interhash(p unsafe.Pointer, h uintptr) uintptr {
a := (*iface)(p)
tab := a.tab
if tab == nil {
return h
}
t := *(**_type)(tab)
if t.equal == nil {
// Check hashability here. We could do this check inside
// typehash, but we want to report the topmost type in
// the error text (e.g. in a struct with a field of slice type
// we want to report the struct, not the slice).
panic(errorString("hash of unhashable type " + t.string()))
}
if isDirectIface(t) {
return c1 * typehash(t, unsafe.Pointer(&a.data), h^c0)
} else {
return c1 * typehash(t, a.data, h^c0)
}
}
func nilinterhash(p unsafe.Pointer, h uintptr) uintptr {
a := (*eface)(p)
t := a._type
if t == nil {
return h
}
if t.equal == nil {
// See comment in interhash above.
panic(errorString("hash of unhashable type " + t.string()))
}
if isDirectIface(t) {
return c1 * typehash(t, unsafe.Pointer(&a.data), h^c0)
} else {
return c1 * typehash(t, a.data, h^c0)
}
}
// typehash computes the hash of the object of type t at address p.
// h is the seed.
// This function is seldom used. Most maps use for hashing either
// fixed functions (e.g. f32hash) or compiler-generated functions
// (e.g. for a type like struct { x, y string }). This implementation
// is slower but more general and is used for hashing interface types
// (called from interhash or nilinterhash, above) or for hashing in
// maps generated by reflect.MapOf (reflect_typehash, below).
func typehash(t *_type, p unsafe.Pointer, h uintptr) uintptr {
if t.tflag&tflagRegularMemory != 0 {
return memhash(p, h, t.size)
}
switch t.kind & kindMask {
case kindFloat32:
return f32hash(p, h)
case kindFloat64:
return f64hash(p, h)
case kindComplex64:
return c64hash(p, h)
case kindComplex128:
return c128hash(p, h)
case kindString:
return strhash(p, h)
case kindInterface:
i := (*interfacetype)(unsafe.Pointer(t))
if len(i.methods) == 0 {
return nilinterhash(p, h)
}
return interhash(p, h)
case kindArray:
a := (*arraytype)(unsafe.Pointer(t))
for i := uintptr(0); i < a.len; i++ {
h = typehash(a.elem, add(p, i*a.elem.size), h)
}
return h
case kindStruct:
s := (*structtype)(unsafe.Pointer(t))
for _, f := range s.fields {
// TODO: maybe we could hash several contiguous fields all at once.
if f.name != nil && *f.name == "_" {
continue
}
h = typehash(f.typ, add(p, f.offset()), h)
}
return h
default:
// Should never happen, as typehash should only be called
// with comparable types.
panic(errorString("hash of unhashable type " + t.string()))
}
}
//go:linkname reflect_typehash reflect.typehash
func reflect_typehash(t *_type, p unsafe.Pointer, h uintptr) uintptr {
return typehash(t, p, h)
}
func memequal0(p, q unsafe.Pointer) bool {
return true
}
func memequal8(p, q unsafe.Pointer) bool {
return *(*int8)(p) == *(*int8)(q)
}
func memequal16(p, q unsafe.Pointer) bool {
return *(*int16)(p) == *(*int16)(q)
}
func memequal32(p, q unsafe.Pointer) bool {
return *(*int32)(p) == *(*int32)(q)
}
func memequal64(p, q unsafe.Pointer) bool {
return *(*int64)(p) == *(*int64)(q)
}
func memequal128(p, q unsafe.Pointer) bool {
return *(*[2]int64)(p) == *(*[2]int64)(q)
}
func f32equal(p, q unsafe.Pointer) bool {
return *(*float32)(p) == *(*float32)(q)
}
func f64equal(p, q unsafe.Pointer) bool {
return *(*float64)(p) == *(*float64)(q)
}
func c64equal(p, q unsafe.Pointer) bool {
return *(*complex64)(p) == *(*complex64)(q)
}
func c128equal(p, q unsafe.Pointer) bool {
return *(*complex128)(p) == *(*complex128)(q)
}
func strequal(p, q unsafe.Pointer) bool {
return *(*string)(p) == *(*string)(q)
}
func interequal(p, q unsafe.Pointer) bool {
return ifaceeq(*(*iface)(p), *(*iface)(q))
}
func nilinterequal(p, q unsafe.Pointer) bool {
return efaceeq(*(*eface)(p), *(*eface)(q))
}
func efaceeq(x, y eface) bool {
t := x._type
if t != y._type {
return false
}
if t == nil {
return true
}
eq := t.equal
if eq == nil {
panic(errorString("comparing uncomparable type " + t.string()))
}
if isDirectIface(t) {
return x.data == y.data
}
return eq(x.data, y.data)
}
func ifaceeq(x, y iface) bool {
xtab := x.tab
if xtab == nil && y.tab == nil {
return true
}
if xtab == nil || y.tab == nil {
return false
}
t := *(**_type)(xtab)
if t != *(**_type)(y.tab) {
return false
}
eq := t.equal
if eq == nil {
panic(errorString("comparing uncomparable type " + t.string()))
}
if isDirectIface(t) {
// Direct interface types are ptr, chan, map, func, and single-element structs/arrays thereof.
// Maps and funcs are not comparable, so they can't reach here.
// Ptrs, chans, and single-element items can be compared directly using ==.
return x.data == y.data
}
return eq(x.data, y.data)
}
func ifacevaleq(x iface, t *_type, p unsafe.Pointer) bool {
if x.tab == nil {
return false
}
xt := *(**_type)(x.tab)
if xt != t {
return false
}
eq := t.equal
if eq == nil {
panic(errorString("comparing uncomparable type " + t.string()))
}
if isDirectIface(t) {
return x.data == p
}
return eq(x.data, p)
}
func ifaceefaceeq(x iface, y eface) bool {
if x.tab == nil && y._type == nil {
return true
}
if x.tab == nil || y._type == nil {
return false
}
xt := *(**_type)(x.tab)
if xt != y._type {
return false
}
eq := xt.equal
if eq == nil {
panic(errorString("comparing uncomparable type " + xt.string()))
}
if isDirectIface(xt) {
return x.data == y.data
}
return eq(x.data, y.data)
}
func efacevaleq(x eface, t *_type, p unsafe.Pointer) bool {
if x._type == nil {
return false
}
if x._type != t {
return false
}
eq := t.equal
if eq == nil {
panic(errorString("comparing uncomparable type " + t.string()))
}
if isDirectIface(t) {
// See comment in efaceeq.
return x.data == p
}
return eq(x.data, p)
}
func cmpstring(x, y string) int {
a := stringStructOf(&x)
b := stringStructOf(&y)
l := a.len
if l > b.len {
l = b.len
}
i := memcmp(unsafe.Pointer(a.str), unsafe.Pointer(b.str), uintptr(l))
if i != 0 {
return int(i)
}
if a.len < b.len {
return -1
} else if a.len > b.len {
return 1
}
return 0
}
// For the unsafe.Pointer type descriptor in libgo/runtime/go-unsafe-pointer.c.
func pointerhash(p unsafe.Pointer, h uintptr) uintptr {
return memhash(p, h, unsafe.Sizeof(unsafe.Pointer))
}
func pointerequal(p, q unsafe.Pointer) bool {
return *(*unsafe.Pointer)(p) == *(*unsafe.Pointer)(q)
}
// Force the creation of function descriptors for equality and hash
// functions. These will be referenced directly by the compiler.
var _ = memhash
var _ = memhash0
var _ = memhash8
var _ = memhash16
var _ = memhash32
var _ = memhash64
var _ = memhash128
var _ = strhash
var _ = f32hash
var _ = f64hash
var _ = c64hash
var _ = c128hash
var _ = interhash
var _ = nilinterhash
var _ = memequal0
var _ = memequal8
var _ = memequal16
var _ = memequal32
var _ = memequal64
var _ = memequal128
var _ = f32equal
var _ = f64equal
var _ = c64equal
var _ = c128equal
var _ = strequal
var _ = interequal
var _ = nilinterequal
var _ = pointerhash
var _ = pointerequal
// Testing adapters for hash quality tests (see hash_test.go)
func stringHash(s string, seed uintptr) uintptr {
return strhash(noescape(unsafe.Pointer(&s)), seed)
}
func bytesHash(b []byte, seed uintptr) uintptr {
s := (*slice)(unsafe.Pointer(&b))
return memhash(s.array, seed, uintptr(s.len))
}
func int32Hash(i uint32, seed uintptr) uintptr {
return memhash32(noescape(unsafe.Pointer(&i)), seed)
}
func int64Hash(i uint64, seed uintptr) uintptr {
return memhash64(noescape(unsafe.Pointer(&i)), seed)
}
func efaceHash(i interface{}, seed uintptr) uintptr {
return nilinterhash(noescape(unsafe.Pointer(&i)), seed)
}
func ifaceHash(i interface {
F()
}, seed uintptr) uintptr {
return interhash(noescape(unsafe.Pointer(&i)), seed)
}
const hashRandomBytes = sys.PtrSize / 4 * 64
// used in asm_{386,amd64,arm64}.s to seed the hash function
var aeskeysched [hashRandomBytes]byte
// used in hash{32,64}.go to seed the hash function
var hashkey [4]uintptr
func alginit() {
// Install AES hash algorithms if the instructions needed are present.
if (GOARCH == "386" || GOARCH == "amd64") &&
GOOS != "nacl" &&
support_aes &&
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[:])
}
// Note: These routines perform the read with an native endianness.
func readUnaligned32(p unsafe.Pointer) uint32 {
q := (*[4]byte)(p)
if sys.BigEndian {
return uint32(q[3]) | uint32(q[2])<<8 | uint32(q[1])<<16 | uint32(q[0])<<24
}
return uint32(q[0]) | uint32(q[1])<<8 | uint32(q[2])<<16 | uint32(q[3])<<24
}
func readUnaligned64(p unsafe.Pointer) uint64 {
q := (*[8]byte)(p)
if sys.BigEndian {
return uint64(q[7]) | uint64(q[6])<<8 | uint64(q[5])<<16 | uint64(q[4])<<24 |
uint64(q[3])<<32 | uint64(q[2])<<40 | uint64(q[1])<<48 | uint64(q[0])<<56
}
return uint64(q[0]) | uint64(q[1])<<8 | uint64(q[2])<<16 | uint64(q[3])<<24 | uint64(q[4])<<32 | uint64(q[5])<<40 | uint64(q[6])<<48 | uint64(q[7])<<56
}