TUN-3090: Upgrade crypto dep

This commit is contained in:
Adam Chalmers
2020-06-12 00:03:09 -05:00
parent ae8d784e36
commit 6e761cb7ae
65 changed files with 5603 additions and 3850 deletions

39
vendor/golang.org/x/crypto/poly1305/bits_compat.go generated vendored Normal file
View File

@@ -0,0 +1,39 @@
// Copyright 2019 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.
// +build !go1.13
package poly1305
// Generic fallbacks for the math/bits intrinsics, copied from
// src/math/bits/bits.go. They were added in Go 1.12, but Add64 and Sum64 had
// variable time fallbacks until Go 1.13.
func bitsAdd64(x, y, carry uint64) (sum, carryOut uint64) {
sum = x + y + carry
carryOut = ((x & y) | ((x | y) &^ sum)) >> 63
return
}
func bitsSub64(x, y, borrow uint64) (diff, borrowOut uint64) {
diff = x - y - borrow
borrowOut = ((^x & y) | (^(x ^ y) & diff)) >> 63
return
}
func bitsMul64(x, y uint64) (hi, lo uint64) {
const mask32 = 1<<32 - 1
x0 := x & mask32
x1 := x >> 32
y0 := y & mask32
y1 := y >> 32
w0 := x0 * y0
t := x1*y0 + w0>>32
w1 := t & mask32
w2 := t >> 32
w1 += x0 * y1
hi = x1*y1 + w2 + w1>>32
lo = x * y
return
}

21
vendor/golang.org/x/crypto/poly1305/bits_go1.13.go generated vendored Normal file
View File

@@ -0,0 +1,21 @@
// Copyright 2019 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.
// +build go1.13
package poly1305
import "math/bits"
func bitsAdd64(x, y, carry uint64) (sum, carryOut uint64) {
return bits.Add64(x, y, carry)
}
func bitsSub64(x, y, borrow uint64) (diff, borrowOut uint64) {
return bits.Sub64(x, y, borrow)
}
func bitsMul64(x, y uint64) (hi, lo uint64) {
return bits.Mul64(x, y)
}

View File

@@ -2,10 +2,8 @@
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// +build !amd64,!ppc64le gccgo appengine
// +build !amd64,!ppc64le,!s390x gccgo purego
package poly1305
type mac struct{ macGeneric }
func newMAC(key *[32]byte) mac { return mac{newMACGeneric(key)} }

View File

@@ -22,8 +22,16 @@ import "crypto/subtle"
// TagSize is the size, in bytes, of a poly1305 authenticator.
const TagSize = 16
// Verify returns true if mac is a valid authenticator for m with the given
// key.
// Sum generates an authenticator for msg using a one-time key and puts the
// 16-byte result into out. Authenticating two different messages with the same
// key allows an attacker to forge messages at will.
func Sum(out *[16]byte, m []byte, key *[32]byte) {
h := New(key)
h.Write(m)
h.Sum(out[:0])
}
// Verify returns true if mac is a valid authenticator for m with the given key.
func Verify(mac *[16]byte, m []byte, key *[32]byte) bool {
var tmp [16]byte
Sum(&tmp, m, key)
@@ -40,10 +48,9 @@ func Verify(mac *[16]byte, m []byte, key *[32]byte) bool {
// two different messages with the same key allows an attacker
// to forge messages at will.
func New(key *[32]byte) *MAC {
return &MAC{
mac: newMAC(key),
finalized: false,
}
m := &MAC{}
initialize(key, &m.macState)
return m
}
// MAC is an io.Writer computing an authentication tag
@@ -52,7 +59,7 @@ func New(key *[32]byte) *MAC {
// MAC cannot be used like common hash.Hash implementations,
// because using a poly1305 key twice breaks its security.
// Therefore writing data to a running MAC after calling
// Sum causes it to panic.
// Sum or Verify causes it to panic.
type MAC struct {
mac // platform-dependent implementation
@@ -65,10 +72,10 @@ func (h *MAC) Size() int { return TagSize }
// Write adds more data to the running message authentication code.
// It never returns an error.
//
// It must not be called after the first call of Sum.
// It must not be called after the first call of Sum or Verify.
func (h *MAC) Write(p []byte) (n int, err error) {
if h.finalized {
panic("poly1305: write to MAC after Sum")
panic("poly1305: write to MAC after Sum or Verify")
}
return h.mac.Write(p)
}
@@ -81,3 +88,12 @@ func (h *MAC) Sum(b []byte) []byte {
h.finalized = true
return append(b, mac[:]...)
}
// Verify returns whether the authenticator of all data written to
// the message authentication code matches the expected value.
func (h *MAC) Verify(expected []byte) bool {
var mac [TagSize]byte
h.mac.Sum(&mac)
h.finalized = true
return subtle.ConstantTimeCompare(expected, mac[:]) == 1
}

View File

@@ -2,67 +2,46 @@
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// +build amd64,!gccgo,!appengine
// +build !gccgo,!purego
package poly1305
//go:noescape
func initialize(state *[7]uint64, key *[32]byte)
func update(state *macState, msg []byte)
//go:noescape
func update(state *[7]uint64, msg []byte)
// mac is a wrapper for macGeneric that redirects calls that would have gone to
// updateGeneric to update.
//
// Its Write and Sum methods are otherwise identical to the macGeneric ones, but
// using function pointers would carry a major performance cost.
type mac struct{ macGeneric }
//go:noescape
func finalize(tag *[TagSize]byte, state *[7]uint64)
// Sum generates an authenticator for m using a one-time key and puts the
// 16-byte result into out. Authenticating two different messages with the same
// key allows an attacker to forge messages at will.
func Sum(out *[16]byte, m []byte, key *[32]byte) {
h := newMAC(key)
h.Write(m)
h.Sum(out)
}
func newMAC(key *[32]byte) (h mac) {
initialize(&h.state, key)
return
}
type mac struct {
state [7]uint64 // := uint64{ h0, h1, h2, r0, r1, pad0, pad1 }
buffer [TagSize]byte
offset int
}
func (h *mac) Write(p []byte) (n int, err error) {
n = len(p)
func (h *mac) Write(p []byte) (int, error) {
nn := len(p)
if h.offset > 0 {
remaining := TagSize - h.offset
if n < remaining {
h.offset += copy(h.buffer[h.offset:], p)
return n, nil
n := copy(h.buffer[h.offset:], p)
if h.offset+n < TagSize {
h.offset += n
return nn, nil
}
copy(h.buffer[h.offset:], p[:remaining])
p = p[remaining:]
p = p[n:]
h.offset = 0
update(&h.state, h.buffer[:])
update(&h.macState, h.buffer[:])
}
if nn := len(p) - (len(p) % TagSize); nn > 0 {
update(&h.state, p[:nn])
p = p[nn:]
if n := len(p) - (len(p) % TagSize); n > 0 {
update(&h.macState, p[:n])
p = p[n:]
}
if len(p) > 0 {
h.offset += copy(h.buffer[h.offset:], p)
}
return n, nil
return nn, nil
}
func (h *mac) Sum(out *[16]byte) {
state := h.state
state := h.macState
if h.offset > 0 {
update(&state, h.buffer[:h.offset])
}
finalize(out, &state)
finalize(out, &state.h, &state.s)
}

View File

@@ -2,7 +2,7 @@
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// +build amd64,!gccgo,!appengine
// +build !gccgo,!purego
#include "textflag.h"
@@ -54,10 +54,6 @@
ADCQ t3, h1; \
ADCQ $0, h2
DATA ·poly1305Mask<>+0x00(SB)/8, $0x0FFFFFFC0FFFFFFF
DATA ·poly1305Mask<>+0x08(SB)/8, $0x0FFFFFFC0FFFFFFC
GLOBL ·poly1305Mask<>(SB), RODATA, $16
// func update(state *[7]uint64, msg []byte)
TEXT ·update(SB), $0-32
MOVQ state+0(FP), DI
@@ -110,39 +106,3 @@ done:
MOVQ R9, 8(DI)
MOVQ R10, 16(DI)
RET
// func initialize(state *[7]uint64, key *[32]byte)
TEXT ·initialize(SB), $0-16
MOVQ state+0(FP), DI
MOVQ key+8(FP), SI
// state[0...7] is initialized with zero
MOVOU 0(SI), X0
MOVOU 16(SI), X1
MOVOU ·poly1305Mask<>(SB), X2
PAND X2, X0
MOVOU X0, 24(DI)
MOVOU X1, 40(DI)
RET
// func finalize(tag *[TagSize]byte, state *[7]uint64)
TEXT ·finalize(SB), $0-16
MOVQ tag+0(FP), DI
MOVQ state+8(FP), SI
MOVQ 0(SI), AX
MOVQ 8(SI), BX
MOVQ 16(SI), CX
MOVQ AX, R8
MOVQ BX, R9
SUBQ $0xFFFFFFFFFFFFFFFB, AX
SBBQ $0xFFFFFFFFFFFFFFFF, BX
SBBQ $3, CX
CMOVQCS R8, AX
CMOVQCS R9, BX
ADDQ 40(SI), AX
ADCQ 48(SI), BX
MOVQ AX, 0(DI)
MOVQ BX, 8(DI)
RET

View File

@@ -1,22 +0,0 @@
// Copyright 2015 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.
// +build arm,!gccgo,!appengine,!nacl
package poly1305
// This function is implemented in sum_arm.s
//go:noescape
func poly1305_auth_armv6(out *[16]byte, m *byte, mlen uint32, key *[32]byte)
// Sum generates an authenticator for m using a one-time key and puts the
// 16-byte result into out. Authenticating two different messages with the same
// key allows an attacker to forge messages at will.
func Sum(out *[16]byte, m []byte, key *[32]byte) {
var mPtr *byte
if len(m) > 0 {
mPtr = &m[0]
}
poly1305_auth_armv6(out, mPtr, uint32(len(m)), key)
}

View File

@@ -1,427 +0,0 @@
// Copyright 2015 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.
// +build arm,!gccgo,!appengine,!nacl
#include "textflag.h"
// This code was translated into a form compatible with 5a from the public
// domain source by Andrew Moon: github.com/floodyberry/poly1305-opt/blob/master/app/extensions/poly1305.
DATA ·poly1305_init_constants_armv6<>+0x00(SB)/4, $0x3ffffff
DATA ·poly1305_init_constants_armv6<>+0x04(SB)/4, $0x3ffff03
DATA ·poly1305_init_constants_armv6<>+0x08(SB)/4, $0x3ffc0ff
DATA ·poly1305_init_constants_armv6<>+0x0c(SB)/4, $0x3f03fff
DATA ·poly1305_init_constants_armv6<>+0x10(SB)/4, $0x00fffff
GLOBL ·poly1305_init_constants_armv6<>(SB), 8, $20
// Warning: the linker may use R11 to synthesize certain instructions. Please
// take care and verify that no synthetic instructions use it.
TEXT poly1305_init_ext_armv6<>(SB), NOSPLIT, $0
// Needs 16 bytes of stack and 64 bytes of space pointed to by R0. (It
// might look like it's only 60 bytes of space but the final four bytes
// will be written by another function.) We need to skip over four
// bytes of stack because that's saving the value of 'g'.
ADD $4, R13, R8
MOVM.IB [R4-R7], (R8)
MOVM.IA.W (R1), [R2-R5]
MOVW $·poly1305_init_constants_armv6<>(SB), R7
MOVW R2, R8
MOVW R2>>26, R9
MOVW R3>>20, g
MOVW R4>>14, R11
MOVW R5>>8, R12
ORR R3<<6, R9, R9
ORR R4<<12, g, g
ORR R5<<18, R11, R11
MOVM.IA (R7), [R2-R6]
AND R8, R2, R2
AND R9, R3, R3
AND g, R4, R4
AND R11, R5, R5
AND R12, R6, R6
MOVM.IA.W [R2-R6], (R0)
EOR R2, R2, R2
EOR R3, R3, R3
EOR R4, R4, R4
EOR R5, R5, R5
EOR R6, R6, R6
MOVM.IA.W [R2-R6], (R0)
MOVM.IA.W (R1), [R2-R5]
MOVM.IA [R2-R6], (R0)
ADD $20, R13, R0
MOVM.DA (R0), [R4-R7]
RET
#define MOVW_UNALIGNED(Rsrc, Rdst, Rtmp, offset) \
MOVBU (offset+0)(Rsrc), Rtmp; \
MOVBU Rtmp, (offset+0)(Rdst); \
MOVBU (offset+1)(Rsrc), Rtmp; \
MOVBU Rtmp, (offset+1)(Rdst); \
MOVBU (offset+2)(Rsrc), Rtmp; \
MOVBU Rtmp, (offset+2)(Rdst); \
MOVBU (offset+3)(Rsrc), Rtmp; \
MOVBU Rtmp, (offset+3)(Rdst)
TEXT poly1305_blocks_armv6<>(SB), NOSPLIT, $0
// Needs 24 bytes of stack for saved registers and then 88 bytes of
// scratch space after that. We assume that 24 bytes at (R13) have
// already been used: four bytes for the link register saved in the
// prelude of poly1305_auth_armv6, four bytes for saving the value of g
// in that function and 16 bytes of scratch space used around
// poly1305_finish_ext_armv6_skip1.
ADD $24, R13, R12
MOVM.IB [R4-R8, R14], (R12)
MOVW R0, 88(R13)
MOVW R1, 92(R13)
MOVW R2, 96(R13)
MOVW R1, R14
MOVW R2, R12
MOVW 56(R0), R8
WORD $0xe1180008 // TST R8, R8 not working see issue 5921
EOR R6, R6, R6
MOVW.EQ $(1<<24), R6
MOVW R6, 84(R13)
ADD $116, R13, g
MOVM.IA (R0), [R0-R9]
MOVM.IA [R0-R4], (g)
CMP $16, R12
BLO poly1305_blocks_armv6_done
poly1305_blocks_armv6_mainloop:
WORD $0xe31e0003 // TST R14, #3 not working see issue 5921
BEQ poly1305_blocks_armv6_mainloop_aligned
ADD $100, R13, g
MOVW_UNALIGNED(R14, g, R0, 0)
MOVW_UNALIGNED(R14, g, R0, 4)
MOVW_UNALIGNED(R14, g, R0, 8)
MOVW_UNALIGNED(R14, g, R0, 12)
MOVM.IA (g), [R0-R3]
ADD $16, R14
B poly1305_blocks_armv6_mainloop_loaded
poly1305_blocks_armv6_mainloop_aligned:
MOVM.IA.W (R14), [R0-R3]
poly1305_blocks_armv6_mainloop_loaded:
MOVW R0>>26, g
MOVW R1>>20, R11
MOVW R2>>14, R12
MOVW R14, 92(R13)
MOVW R3>>8, R4
ORR R1<<6, g, g
ORR R2<<12, R11, R11
ORR R3<<18, R12, R12
BIC $0xfc000000, R0, R0
BIC $0xfc000000, g, g
MOVW 84(R13), R3
BIC $0xfc000000, R11, R11
BIC $0xfc000000, R12, R12
ADD R0, R5, R5
ADD g, R6, R6
ORR R3, R4, R4
ADD R11, R7, R7
ADD $116, R13, R14
ADD R12, R8, R8
ADD R4, R9, R9
MOVM.IA (R14), [R0-R4]
MULLU R4, R5, (R11, g)
MULLU R3, R5, (R14, R12)
MULALU R3, R6, (R11, g)
MULALU R2, R6, (R14, R12)
MULALU R2, R7, (R11, g)
MULALU R1, R7, (R14, R12)
ADD R4<<2, R4, R4
ADD R3<<2, R3, R3
MULALU R1, R8, (R11, g)
MULALU R0, R8, (R14, R12)
MULALU R0, R9, (R11, g)
MULALU R4, R9, (R14, R12)
MOVW g, 76(R13)
MOVW R11, 80(R13)
MOVW R12, 68(R13)
MOVW R14, 72(R13)
MULLU R2, R5, (R11, g)
MULLU R1, R5, (R14, R12)
MULALU R1, R6, (R11, g)
MULALU R0, R6, (R14, R12)
MULALU R0, R7, (R11, g)
MULALU R4, R7, (R14, R12)
ADD R2<<2, R2, R2
ADD R1<<2, R1, R1
MULALU R4, R8, (R11, g)
MULALU R3, R8, (R14, R12)
MULALU R3, R9, (R11, g)
MULALU R2, R9, (R14, R12)
MOVW g, 60(R13)
MOVW R11, 64(R13)
MOVW R12, 52(R13)
MOVW R14, 56(R13)
MULLU R0, R5, (R11, g)
MULALU R4, R6, (R11, g)
MULALU R3, R7, (R11, g)
MULALU R2, R8, (R11, g)
MULALU R1, R9, (R11, g)
ADD $52, R13, R0
MOVM.IA (R0), [R0-R7]
MOVW g>>26, R12
MOVW R4>>26, R14
ORR R11<<6, R12, R12
ORR R5<<6, R14, R14
BIC $0xfc000000, g, g
BIC $0xfc000000, R4, R4
ADD.S R12, R0, R0
ADC $0, R1, R1
ADD.S R14, R6, R6
ADC $0, R7, R7
MOVW R0>>26, R12
MOVW R6>>26, R14
ORR R1<<6, R12, R12
ORR R7<<6, R14, R14
BIC $0xfc000000, R0, R0
BIC $0xfc000000, R6, R6
ADD R14<<2, R14, R14
ADD.S R12, R2, R2
ADC $0, R3, R3
ADD R14, g, g
MOVW R2>>26, R12
MOVW g>>26, R14
ORR R3<<6, R12, R12
BIC $0xfc000000, g, R5
BIC $0xfc000000, R2, R7
ADD R12, R4, R4
ADD R14, R0, R0
MOVW R4>>26, R12
BIC $0xfc000000, R4, R8
ADD R12, R6, R9
MOVW 96(R13), R12
MOVW 92(R13), R14
MOVW R0, R6
CMP $32, R12
SUB $16, R12, R12
MOVW R12, 96(R13)
BHS poly1305_blocks_armv6_mainloop
poly1305_blocks_armv6_done:
MOVW 88(R13), R12
MOVW R5, 20(R12)
MOVW R6, 24(R12)
MOVW R7, 28(R12)
MOVW R8, 32(R12)
MOVW R9, 36(R12)
ADD $48, R13, R0
MOVM.DA (R0), [R4-R8, R14]
RET
#define MOVHUP_UNALIGNED(Rsrc, Rdst, Rtmp) \
MOVBU.P 1(Rsrc), Rtmp; \
MOVBU.P Rtmp, 1(Rdst); \
MOVBU.P 1(Rsrc), Rtmp; \
MOVBU.P Rtmp, 1(Rdst)
#define MOVWP_UNALIGNED(Rsrc, Rdst, Rtmp) \
MOVHUP_UNALIGNED(Rsrc, Rdst, Rtmp); \
MOVHUP_UNALIGNED(Rsrc, Rdst, Rtmp)
// func poly1305_auth_armv6(out *[16]byte, m *byte, mlen uint32, key *[32]key)
TEXT ·poly1305_auth_armv6(SB), $196-16
// The value 196, just above, is the sum of 64 (the size of the context
// structure) and 132 (the amount of stack needed).
//
// At this point, the stack pointer (R13) has been moved down. It
// points to the saved link register and there's 196 bytes of free
// space above it.
//
// The stack for this function looks like:
//
// +---------------------
// |
// | 64 bytes of context structure
// |
// +---------------------
// |
// | 112 bytes for poly1305_blocks_armv6
// |
// +---------------------
// | 16 bytes of final block, constructed at
// | poly1305_finish_ext_armv6_skip8
// +---------------------
// | four bytes of saved 'g'
// +---------------------
// | lr, saved by prelude <- R13 points here
// +---------------------
MOVW g, 4(R13)
MOVW out+0(FP), R4
MOVW m+4(FP), R5
MOVW mlen+8(FP), R6
MOVW key+12(FP), R7
ADD $136, R13, R0 // 136 = 4 + 4 + 16 + 112
MOVW R7, R1
// poly1305_init_ext_armv6 will write to the stack from R13+4, but
// that's ok because none of the other values have been written yet.
BL poly1305_init_ext_armv6<>(SB)
BIC.S $15, R6, R2
BEQ poly1305_auth_armv6_noblocks
ADD $136, R13, R0
MOVW R5, R1
ADD R2, R5, R5
SUB R2, R6, R6
BL poly1305_blocks_armv6<>(SB)
poly1305_auth_armv6_noblocks:
ADD $136, R13, R0
MOVW R5, R1
MOVW R6, R2
MOVW R4, R3
MOVW R0, R5
MOVW R1, R6
MOVW R2, R7
MOVW R3, R8
AND.S R2, R2, R2
BEQ poly1305_finish_ext_armv6_noremaining
EOR R0, R0
ADD $8, R13, R9 // 8 = offset to 16 byte scratch space
MOVW R0, (R9)
MOVW R0, 4(R9)
MOVW R0, 8(R9)
MOVW R0, 12(R9)
WORD $0xe3110003 // TST R1, #3 not working see issue 5921
BEQ poly1305_finish_ext_armv6_aligned
WORD $0xe3120008 // TST R2, #8 not working see issue 5921
BEQ poly1305_finish_ext_armv6_skip8
MOVWP_UNALIGNED(R1, R9, g)
MOVWP_UNALIGNED(R1, R9, g)
poly1305_finish_ext_armv6_skip8:
WORD $0xe3120004 // TST $4, R2 not working see issue 5921
BEQ poly1305_finish_ext_armv6_skip4
MOVWP_UNALIGNED(R1, R9, g)
poly1305_finish_ext_armv6_skip4:
WORD $0xe3120002 // TST $2, R2 not working see issue 5921
BEQ poly1305_finish_ext_armv6_skip2
MOVHUP_UNALIGNED(R1, R9, g)
B poly1305_finish_ext_armv6_skip2
poly1305_finish_ext_armv6_aligned:
WORD $0xe3120008 // TST R2, #8 not working see issue 5921
BEQ poly1305_finish_ext_armv6_skip8_aligned
MOVM.IA.W (R1), [g-R11]
MOVM.IA.W [g-R11], (R9)
poly1305_finish_ext_armv6_skip8_aligned:
WORD $0xe3120004 // TST $4, R2 not working see issue 5921
BEQ poly1305_finish_ext_armv6_skip4_aligned
MOVW.P 4(R1), g
MOVW.P g, 4(R9)
poly1305_finish_ext_armv6_skip4_aligned:
WORD $0xe3120002 // TST $2, R2 not working see issue 5921
BEQ poly1305_finish_ext_armv6_skip2
MOVHU.P 2(R1), g
MOVH.P g, 2(R9)
poly1305_finish_ext_armv6_skip2:
WORD $0xe3120001 // TST $1, R2 not working see issue 5921
BEQ poly1305_finish_ext_armv6_skip1
MOVBU.P 1(R1), g
MOVBU.P g, 1(R9)
poly1305_finish_ext_armv6_skip1:
MOVW $1, R11
MOVBU R11, 0(R9)
MOVW R11, 56(R5)
MOVW R5, R0
ADD $8, R13, R1
MOVW $16, R2
BL poly1305_blocks_armv6<>(SB)
poly1305_finish_ext_armv6_noremaining:
MOVW 20(R5), R0
MOVW 24(R5), R1
MOVW 28(R5), R2
MOVW 32(R5), R3
MOVW 36(R5), R4
MOVW R4>>26, R12
BIC $0xfc000000, R4, R4
ADD R12<<2, R12, R12
ADD R12, R0, R0
MOVW R0>>26, R12
BIC $0xfc000000, R0, R0
ADD R12, R1, R1
MOVW R1>>26, R12
BIC $0xfc000000, R1, R1
ADD R12, R2, R2
MOVW R2>>26, R12
BIC $0xfc000000, R2, R2
ADD R12, R3, R3
MOVW R3>>26, R12
BIC $0xfc000000, R3, R3
ADD R12, R4, R4
ADD $5, R0, R6
MOVW R6>>26, R12
BIC $0xfc000000, R6, R6
ADD R12, R1, R7
MOVW R7>>26, R12
BIC $0xfc000000, R7, R7
ADD R12, R2, g
MOVW g>>26, R12
BIC $0xfc000000, g, g
ADD R12, R3, R11
MOVW $-(1<<26), R12
ADD R11>>26, R12, R12
BIC $0xfc000000, R11, R11
ADD R12, R4, R9
MOVW R9>>31, R12
SUB $1, R12
AND R12, R6, R6
AND R12, R7, R7
AND R12, g, g
AND R12, R11, R11
AND R12, R9, R9
MVN R12, R12
AND R12, R0, R0
AND R12, R1, R1
AND R12, R2, R2
AND R12, R3, R3
AND R12, R4, R4
ORR R6, R0, R0
ORR R7, R1, R1
ORR g, R2, R2
ORR R11, R3, R3
ORR R9, R4, R4
ORR R1<<26, R0, R0
MOVW R1>>6, R1
ORR R2<<20, R1, R1
MOVW R2>>12, R2
ORR R3<<14, R2, R2
MOVW R3>>18, R3
ORR R4<<8, R3, R3
MOVW 40(R5), R6
MOVW 44(R5), R7
MOVW 48(R5), g
MOVW 52(R5), R11
ADD.S R6, R0, R0
ADC.S R7, R1, R1
ADC.S g, R2, R2
ADC.S R11, R3, R3
MOVM.IA [R0-R3], (R8)
MOVW R5, R12
EOR R0, R0, R0
EOR R1, R1, R1
EOR R2, R2, R2
EOR R3, R3, R3
EOR R4, R4, R4
EOR R5, R5, R5
EOR R6, R6, R6
EOR R7, R7, R7
MOVM.IA.W [R0-R7], (R12)
MOVM.IA [R0-R7], (R12)
MOVW 4(R13), g
RET

View File

@@ -2,171 +2,309 @@
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// This file provides the generic implementation of Sum and MAC. Other files
// might provide optimized assembly implementations of some of this code.
package poly1305
import "encoding/binary"
const (
msgBlock = uint32(1 << 24)
finalBlock = uint32(0)
)
// Poly1305 [RFC 7539] is a relatively simple algorithm: the authentication tag
// for a 64 bytes message is approximately
//
// s + m[0:16] * r⁴ + m[16:32] * r³ + m[32:48] * r² + m[48:64] * r mod 2¹³⁰ - 5
//
// for some secret r and s. It can be computed sequentially like
//
// for len(msg) > 0:
// h += read(msg, 16)
// h *= r
// h %= 2¹³⁰ - 5
// return h + s
//
// All the complexity is about doing performant constant-time math on numbers
// larger than any available numeric type.
// sumGeneric generates an authenticator for msg using a one-time key and
// puts the 16-byte result into out. This is the generic implementation of
// Sum and should be called if no assembly implementation is available.
func sumGeneric(out *[TagSize]byte, msg []byte, key *[32]byte) {
h := newMACGeneric(key)
h.Write(msg)
h.Sum(out)
}
func newMACGeneric(key *[32]byte) (h macGeneric) {
h.r[0] = binary.LittleEndian.Uint32(key[0:]) & 0x3ffffff
h.r[1] = (binary.LittleEndian.Uint32(key[3:]) >> 2) & 0x3ffff03
h.r[2] = (binary.LittleEndian.Uint32(key[6:]) >> 4) & 0x3ffc0ff
h.r[3] = (binary.LittleEndian.Uint32(key[9:]) >> 6) & 0x3f03fff
h.r[4] = (binary.LittleEndian.Uint32(key[12:]) >> 8) & 0x00fffff
func newMACGeneric(key *[32]byte) macGeneric {
m := macGeneric{}
initialize(key, &m.macState)
return m
}
h.s[0] = binary.LittleEndian.Uint32(key[16:])
h.s[1] = binary.LittleEndian.Uint32(key[20:])
h.s[2] = binary.LittleEndian.Uint32(key[24:])
h.s[3] = binary.LittleEndian.Uint32(key[28:])
return
// macState holds numbers in saturated 64-bit little-endian limbs. That is,
// the value of [x0, x1, x2] is x[0] + x[1] * 2⁶⁴ + x[2] * 2¹²⁸.
type macState struct {
// h is the main accumulator. It is to be interpreted modulo 2¹³⁰ - 5, but
// can grow larger during and after rounds. It must, however, remain below
// 2 * (2¹³⁰ - 5).
h [3]uint64
// r and s are the private key components.
r [2]uint64
s [2]uint64
}
type macGeneric struct {
h, r [5]uint32
s [4]uint32
macState
buffer [TagSize]byte
offset int
}
func (h *macGeneric) Write(p []byte) (n int, err error) {
n = len(p)
// Write splits the incoming message into TagSize chunks, and passes them to
// update. It buffers incomplete chunks.
func (h *macGeneric) Write(p []byte) (int, error) {
nn := len(p)
if h.offset > 0 {
remaining := TagSize - h.offset
if n < remaining {
h.offset += copy(h.buffer[h.offset:], p)
return n, nil
n := copy(h.buffer[h.offset:], p)
if h.offset+n < TagSize {
h.offset += n
return nn, nil
}
copy(h.buffer[h.offset:], p[:remaining])
p = p[remaining:]
p = p[n:]
h.offset = 0
updateGeneric(h.buffer[:], msgBlock, &(h.h), &(h.r))
updateGeneric(&h.macState, h.buffer[:])
}
if nn := len(p) - (len(p) % TagSize); nn > 0 {
updateGeneric(p, msgBlock, &(h.h), &(h.r))
p = p[nn:]
if n := len(p) - (len(p) % TagSize); n > 0 {
updateGeneric(&h.macState, p[:n])
p = p[n:]
}
if len(p) > 0 {
h.offset += copy(h.buffer[h.offset:], p)
}
return n, nil
return nn, nil
}
func (h *macGeneric) Sum(out *[16]byte) {
H, R := h.h, h.r
// Sum flushes the last incomplete chunk from the buffer, if any, and generates
// the MAC output. It does not modify its state, in order to allow for multiple
// calls to Sum, even if no Write is allowed after Sum.
func (h *macGeneric) Sum(out *[TagSize]byte) {
state := h.macState
if h.offset > 0 {
var buffer [TagSize]byte
copy(buffer[:], h.buffer[:h.offset])
buffer[h.offset] = 1 // invariant: h.offset < TagSize
updateGeneric(buffer[:], finalBlock, &H, &R)
updateGeneric(&state, h.buffer[:h.offset])
}
finalizeGeneric(out, &H, &(h.s))
finalize(out, &state.h, &state.s)
}
func updateGeneric(msg []byte, flag uint32, h, r *[5]uint32) {
h0, h1, h2, h3, h4 := h[0], h[1], h[2], h[3], h[4]
r0, r1, r2, r3, r4 := uint64(r[0]), uint64(r[1]), uint64(r[2]), uint64(r[3]), uint64(r[4])
R1, R2, R3, R4 := r1*5, r2*5, r3*5, r4*5
// [rMask0, rMask1] is the specified Poly1305 clamping mask in little-endian. It
// clears some bits of the secret coefficient to make it possible to implement
// multiplication more efficiently.
const (
rMask0 = 0x0FFFFFFC0FFFFFFF
rMask1 = 0x0FFFFFFC0FFFFFFC
)
for len(msg) >= TagSize {
// h += msg
h0 += binary.LittleEndian.Uint32(msg[0:]) & 0x3ffffff
h1 += (binary.LittleEndian.Uint32(msg[3:]) >> 2) & 0x3ffffff
h2 += (binary.LittleEndian.Uint32(msg[6:]) >> 4) & 0x3ffffff
h3 += (binary.LittleEndian.Uint32(msg[9:]) >> 6) & 0x3ffffff
h4 += (binary.LittleEndian.Uint32(msg[12:]) >> 8) | flag
// initialize loads the 256-bit key into the two 128-bit secret values r and s.
func initialize(key *[32]byte, m *macState) {
m.r[0] = binary.LittleEndian.Uint64(key[0:8]) & rMask0
m.r[1] = binary.LittleEndian.Uint64(key[8:16]) & rMask1
m.s[0] = binary.LittleEndian.Uint64(key[16:24])
m.s[1] = binary.LittleEndian.Uint64(key[24:32])
}
// h *= r
d0 := (uint64(h0) * r0) + (uint64(h1) * R4) + (uint64(h2) * R3) + (uint64(h3) * R2) + (uint64(h4) * R1)
d1 := (d0 >> 26) + (uint64(h0) * r1) + (uint64(h1) * r0) + (uint64(h2) * R4) + (uint64(h3) * R3) + (uint64(h4) * R2)
d2 := (d1 >> 26) + (uint64(h0) * r2) + (uint64(h1) * r1) + (uint64(h2) * r0) + (uint64(h3) * R4) + (uint64(h4) * R3)
d3 := (d2 >> 26) + (uint64(h0) * r3) + (uint64(h1) * r2) + (uint64(h2) * r1) + (uint64(h3) * r0) + (uint64(h4) * R4)
d4 := (d3 >> 26) + (uint64(h0) * r4) + (uint64(h1) * r3) + (uint64(h2) * r2) + (uint64(h3) * r1) + (uint64(h4) * r0)
// uint128 holds a 128-bit number as two 64-bit limbs, for use with the
// bits.Mul64 and bits.Add64 intrinsics.
type uint128 struct {
lo, hi uint64
}
// h %= p
h0 = uint32(d0) & 0x3ffffff
h1 = uint32(d1) & 0x3ffffff
h2 = uint32(d2) & 0x3ffffff
h3 = uint32(d3) & 0x3ffffff
h4 = uint32(d4) & 0x3ffffff
func mul64(a, b uint64) uint128 {
hi, lo := bitsMul64(a, b)
return uint128{lo, hi}
}
h0 += uint32(d4>>26) * 5
h1 += h0 >> 26
h0 = h0 & 0x3ffffff
func add128(a, b uint128) uint128 {
lo, c := bitsAdd64(a.lo, b.lo, 0)
hi, c := bitsAdd64(a.hi, b.hi, c)
if c != 0 {
panic("poly1305: unexpected overflow")
}
return uint128{lo, hi}
}
msg = msg[TagSize:]
func shiftRightBy2(a uint128) uint128 {
a.lo = a.lo>>2 | (a.hi&3)<<62
a.hi = a.hi >> 2
return a
}
// updateGeneric absorbs msg into the state.h accumulator. For each chunk m of
// 128 bits of message, it computes
//
// h₊ = (h + m) * r mod 2¹³⁰ - 5
//
// If the msg length is not a multiple of TagSize, it assumes the last
// incomplete chunk is the final one.
func updateGeneric(state *macState, msg []byte) {
h0, h1, h2 := state.h[0], state.h[1], state.h[2]
r0, r1 := state.r[0], state.r[1]
for len(msg) > 0 {
var c uint64
// For the first step, h + m, we use a chain of bits.Add64 intrinsics.
// The resulting value of h might exceed 2¹³⁰ - 5, but will be partially
// reduced at the end of the multiplication below.
//
// The spec requires us to set a bit just above the message size, not to
// hide leading zeroes. For full chunks, that's 1 << 128, so we can just
// add 1 to the most significant (2¹²⁸) limb, h2.
if len(msg) >= TagSize {
h0, c = bitsAdd64(h0, binary.LittleEndian.Uint64(msg[0:8]), 0)
h1, c = bitsAdd64(h1, binary.LittleEndian.Uint64(msg[8:16]), c)
h2 += c + 1
msg = msg[TagSize:]
} else {
var buf [TagSize]byte
copy(buf[:], msg)
buf[len(msg)] = 1
h0, c = bitsAdd64(h0, binary.LittleEndian.Uint64(buf[0:8]), 0)
h1, c = bitsAdd64(h1, binary.LittleEndian.Uint64(buf[8:16]), c)
h2 += c
msg = nil
}
// Multiplication of big number limbs is similar to elementary school
// columnar multiplication. Instead of digits, there are 64-bit limbs.
//
// We are multiplying a 3 limbs number, h, by a 2 limbs number, r.
//
// h2 h1 h0 x
// r1 r0 =
// ----------------
// h2r0 h1r0 h0r0 <-- individual 128-bit products
// + h2r1 h1r1 h0r1
// ------------------------
// m3 m2 m1 m0 <-- result in 128-bit overlapping limbs
// ------------------------
// m3.hi m2.hi m1.hi m0.hi <-- carry propagation
// + m3.lo m2.lo m1.lo m0.lo
// -------------------------------
// t4 t3 t2 t1 t0 <-- final result in 64-bit limbs
//
// The main difference from pen-and-paper multiplication is that we do
// carry propagation in a separate step, as if we wrote two digit sums
// at first (the 128-bit limbs), and then carried the tens all at once.
h0r0 := mul64(h0, r0)
h1r0 := mul64(h1, r0)
h2r0 := mul64(h2, r0)
h0r1 := mul64(h0, r1)
h1r1 := mul64(h1, r1)
h2r1 := mul64(h2, r1)
// Since h2 is known to be at most 7 (5 + 1 + 1), and r0 and r1 have their
// top 4 bits cleared by rMask{0,1}, we know that their product is not going
// to overflow 64 bits, so we can ignore the high part of the products.
//
// This also means that the product doesn't have a fifth limb (t4).
if h2r0.hi != 0 {
panic("poly1305: unexpected overflow")
}
if h2r1.hi != 0 {
panic("poly1305: unexpected overflow")
}
m0 := h0r0
m1 := add128(h1r0, h0r1) // These two additions don't overflow thanks again
m2 := add128(h2r0, h1r1) // to the 4 masked bits at the top of r0 and r1.
m3 := h2r1
t0 := m0.lo
t1, c := bitsAdd64(m1.lo, m0.hi, 0)
t2, c := bitsAdd64(m2.lo, m1.hi, c)
t3, _ := bitsAdd64(m3.lo, m2.hi, c)
// Now we have the result as 4 64-bit limbs, and we need to reduce it
// modulo 2¹³⁰ - 5. The special shape of this Crandall prime lets us do
// a cheap partial reduction according to the reduction identity
//
// c * 2¹³⁰ + n = c * 5 + n mod 2¹³⁰ - 5
//
// because 2¹³⁰ = 5 mod 2¹³⁰ - 5. Partial reduction since the result is
// likely to be larger than 2¹³⁰ - 5, but still small enough to fit the
// assumptions we make about h in the rest of the code.
//
// See also https://speakerdeck.com/gtank/engineering-prime-numbers?slide=23
// We split the final result at the 2¹³⁰ mark into h and cc, the carry.
// Note that the carry bits are effectively shifted left by 2, in other
// words, cc = c * 4 for the c in the reduction identity.
h0, h1, h2 = t0, t1, t2&maskLow2Bits
cc := uint128{t2 & maskNotLow2Bits, t3}
// To add c * 5 to h, we first add cc = c * 4, and then add (cc >> 2) = c.
h0, c = bitsAdd64(h0, cc.lo, 0)
h1, c = bitsAdd64(h1, cc.hi, c)
h2 += c
cc = shiftRightBy2(cc)
h0, c = bitsAdd64(h0, cc.lo, 0)
h1, c = bitsAdd64(h1, cc.hi, c)
h2 += c
// h2 is at most 3 + 1 + 1 = 5, making the whole of h at most
//
// 5 * 2¹²⁸ + (2¹²⁸ - 1) = 6 * 2¹²⁸ - 1
}
h[0], h[1], h[2], h[3], h[4] = h0, h1, h2, h3, h4
state.h[0], state.h[1], state.h[2] = h0, h1, h2
}
func finalizeGeneric(out *[TagSize]byte, h *[5]uint32, s *[4]uint32) {
h0, h1, h2, h3, h4 := h[0], h[1], h[2], h[3], h[4]
const (
maskLow2Bits uint64 = 0x0000000000000003
maskNotLow2Bits uint64 = ^maskLow2Bits
)
// h %= p reduction
h2 += h1 >> 26
h1 &= 0x3ffffff
h3 += h2 >> 26
h2 &= 0x3ffffff
h4 += h3 >> 26
h3 &= 0x3ffffff
h0 += 5 * (h4 >> 26)
h4 &= 0x3ffffff
h1 += h0 >> 26
h0 &= 0x3ffffff
// select64 returns x if v == 1 and y if v == 0, in constant time.
func select64(v, x, y uint64) uint64 { return ^(v-1)&x | (v-1)&y }
// h - p
t0 := h0 + 5
t1 := h1 + (t0 >> 26)
t2 := h2 + (t1 >> 26)
t3 := h3 + (t2 >> 26)
t4 := h4 + (t3 >> 26) - (1 << 26)
t0 &= 0x3ffffff
t1 &= 0x3ffffff
t2 &= 0x3ffffff
t3 &= 0x3ffffff
// [p0, p1, p2] is 2¹³⁰ - 5 in little endian order.
const (
p0 = 0xFFFFFFFFFFFFFFFB
p1 = 0xFFFFFFFFFFFFFFFF
p2 = 0x0000000000000003
)
// select h if h < p else h - p
t_mask := (t4 >> 31) - 1
h_mask := ^t_mask
h0 = (h0 & h_mask) | (t0 & t_mask)
h1 = (h1 & h_mask) | (t1 & t_mask)
h2 = (h2 & h_mask) | (t2 & t_mask)
h3 = (h3 & h_mask) | (t3 & t_mask)
h4 = (h4 & h_mask) | (t4 & t_mask)
// finalize completes the modular reduction of h and computes
//
// out = h + s mod 2¹²⁸
//
func finalize(out *[TagSize]byte, h *[3]uint64, s *[2]uint64) {
h0, h1, h2 := h[0], h[1], h[2]
// h %= 2^128
h0 |= h1 << 26
h1 = ((h1 >> 6) | (h2 << 20))
h2 = ((h2 >> 12) | (h3 << 14))
h3 = ((h3 >> 18) | (h4 << 8))
// After the partial reduction in updateGeneric, h might be more than
// 2¹³⁰ - 5, but will be less than 2 * (2¹³⁰ - 5). To complete the reduction
// in constant time, we compute t = h - (2¹³⁰ - 5), and select h as the
// result if the subtraction underflows, and t otherwise.
// s: the s part of the key
// tag = (h + s) % (2^128)
t := uint64(h0) + uint64(s[0])
h0 = uint32(t)
t = uint64(h1) + uint64(s[1]) + (t >> 32)
h1 = uint32(t)
t = uint64(h2) + uint64(s[2]) + (t >> 32)
h2 = uint32(t)
t = uint64(h3) + uint64(s[3]) + (t >> 32)
h3 = uint32(t)
hMinusP0, b := bitsSub64(h0, p0, 0)
hMinusP1, b := bitsSub64(h1, p1, b)
_, b = bitsSub64(h2, p2, b)
binary.LittleEndian.PutUint32(out[0:], h0)
binary.LittleEndian.PutUint32(out[4:], h1)
binary.LittleEndian.PutUint32(out[8:], h2)
binary.LittleEndian.PutUint32(out[12:], h3)
// h = h if h < p else h - p
h0 = select64(b, h0, hMinusP0)
h1 = select64(b, h1, hMinusP1)
// Finally, we compute the last Poly1305 step
//
// tag = h + s mod 2¹²⁸
//
// by just doing a wide addition with the 128 low bits of h and discarding
// the overflow.
h0, c := bitsAdd64(h0, s[0], 0)
h1, _ = bitsAdd64(h1, s[1], c)
binary.LittleEndian.PutUint64(out[0:8], h0)
binary.LittleEndian.PutUint64(out[8:16], h1)
}

View File

@@ -1,16 +0,0 @@
// Copyright 2018 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.
// +build s390x,!go1.11 !arm,!amd64,!s390x,!ppc64le gccgo appengine nacl
package poly1305
// Sum generates an authenticator for msg using a one-time key and puts the
// 16-byte result into out. Authenticating two different messages with the same
// key allows an attacker to forge messages at will.
func Sum(out *[TagSize]byte, msg []byte, key *[32]byte) {
h := newMAC(key)
h.Write(msg)
h.Sum(out)
}

View File

@@ -2,67 +2,46 @@
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// +build ppc64le,!gccgo,!appengine
// +build !gccgo,!purego
package poly1305
//go:noescape
func initialize(state *[7]uint64, key *[32]byte)
func update(state *macState, msg []byte)
//go:noescape
func update(state *[7]uint64, msg []byte)
// mac is a wrapper for macGeneric that redirects calls that would have gone to
// updateGeneric to update.
//
// Its Write and Sum methods are otherwise identical to the macGeneric ones, but
// using function pointers would carry a major performance cost.
type mac struct{ macGeneric }
//go:noescape
func finalize(tag *[TagSize]byte, state *[7]uint64)
// Sum generates an authenticator for m using a one-time key and puts the
// 16-byte result into out. Authenticating two different messages with the same
// key allows an attacker to forge messages at will.
func Sum(out *[16]byte, m []byte, key *[32]byte) {
h := newMAC(key)
h.Write(m)
h.Sum(out)
}
func newMAC(key *[32]byte) (h mac) {
initialize(&h.state, key)
return
}
type mac struct {
state [7]uint64 // := uint64{ h0, h1, h2, r0, r1, pad0, pad1 }
buffer [TagSize]byte
offset int
}
func (h *mac) Write(p []byte) (n int, err error) {
n = len(p)
func (h *mac) Write(p []byte) (int, error) {
nn := len(p)
if h.offset > 0 {
remaining := TagSize - h.offset
if n < remaining {
h.offset += copy(h.buffer[h.offset:], p)
return n, nil
n := copy(h.buffer[h.offset:], p)
if h.offset+n < TagSize {
h.offset += n
return nn, nil
}
copy(h.buffer[h.offset:], p[:remaining])
p = p[remaining:]
p = p[n:]
h.offset = 0
update(&h.state, h.buffer[:])
update(&h.macState, h.buffer[:])
}
if nn := len(p) - (len(p) % TagSize); nn > 0 {
update(&h.state, p[:nn])
p = p[nn:]
if n := len(p) - (len(p) % TagSize); n > 0 {
update(&h.macState, p[:n])
p = p[n:]
}
if len(p) > 0 {
h.offset += copy(h.buffer[h.offset:], p)
}
return n, nil
return nn, nil
}
func (h *mac) Sum(out *[16]byte) {
state := h.state
state := h.macState
if h.offset > 0 {
update(&state, h.buffer[:h.offset])
}
finalize(out, &state)
finalize(out, &state.h, &state.s)
}

View File

@@ -2,7 +2,7 @@
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// +build ppc64le,!gccgo,!appengine
// +build !gccgo,!purego
#include "textflag.h"
@@ -58,7 +58,6 @@ DATA ·poly1305Mask<>+0x08(SB)/8, $0x0FFFFFFC0FFFFFFC
GLOBL ·poly1305Mask<>(SB), RODATA, $16
// func update(state *[7]uint64, msg []byte)
TEXT ·update(SB), $0-32
MOVD state+0(FP), R3
MOVD msg_base+8(FP), R4
@@ -180,68 +179,3 @@ done:
MOVD R9, 8(R3)
MOVD R10, 16(R3)
RET
// func initialize(state *[7]uint64, key *[32]byte)
TEXT ·initialize(SB), $0-16
MOVD state+0(FP), R3
MOVD key+8(FP), R4
// state[0...7] is initialized with zero
// Load key
MOVD 0(R4), R5
MOVD 8(R4), R6
MOVD 16(R4), R7
MOVD 24(R4), R8
// Address of key mask
MOVD $·poly1305Mask<>(SB), R9
// Save original key in state
MOVD R7, 40(R3)
MOVD R8, 48(R3)
// Get mask
MOVD (R9), R7
MOVD 8(R9), R8
// And with key
AND R5, R7, R5
AND R6, R8, R6
// Save masked key in state
MOVD R5, 24(R3)
MOVD R6, 32(R3)
RET
// func finalize(tag *[TagSize]byte, state *[7]uint64)
TEXT ·finalize(SB), $0-16
MOVD tag+0(FP), R3
MOVD state+8(FP), R4
// Get h0, h1, h2 from state
MOVD 0(R4), R5
MOVD 8(R4), R6
MOVD 16(R4), R7
// Save h0, h1
MOVD R5, R8
MOVD R6, R9
MOVD $3, R20
MOVD $-1, R21
SUBC $-5, R5
SUBE R21, R6
SUBE R20, R7
MOVD $0, R21
SUBZE R21
// Check for carry
CMP $0, R21
ISEL $2, R5, R8, R5
ISEL $2, R6, R9, R6
MOVD 40(R4), R8
MOVD 48(R4), R9
ADDC R8, R5
ADDE R9, R6
MOVD R5, 0(R3)
MOVD R6, 8(R3)
RET

View File

@@ -2,7 +2,7 @@
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// +build s390x,go1.11,!gccgo,!appengine
// +build !gccgo,!purego
package poly1305
@@ -10,33 +10,66 @@ import (
"golang.org/x/sys/cpu"
)
// poly1305vx is an assembly implementation of Poly1305 that uses vector
// updateVX is an assembly implementation of Poly1305 that uses vector
// instructions. It must only be called if the vector facility (vx) is
// available.
//go:noescape
func poly1305vx(out *[16]byte, m *byte, mlen uint64, key *[32]byte)
func updateVX(state *macState, msg []byte)
// poly1305vmsl is an assembly implementation of Poly1305 that uses vector
// instructions, including VMSL. It must only be called if the vector facility (vx) is
// available and if VMSL is supported.
//go:noescape
func poly1305vmsl(out *[16]byte, m *byte, mlen uint64, key *[32]byte)
// mac is a replacement for macGeneric that uses a larger buffer and redirects
// calls that would have gone to updateGeneric to updateVX if the vector
// facility is installed.
//
// A larger buffer is required for good performance because the vector
// implementation has a higher fixed cost per call than the generic
// implementation.
type mac struct {
macState
// Sum generates an authenticator for m using a one-time key and puts the
// 16-byte result into out. Authenticating two different messages with the same
// key allows an attacker to forge messages at will.
func Sum(out *[16]byte, m []byte, key *[32]byte) {
if cpu.S390X.HasVX {
var mPtr *byte
if len(m) > 0 {
mPtr = &m[0]
}
if cpu.S390X.HasVXE && len(m) > 256 {
poly1305vmsl(out, mPtr, uint64(len(m)), key)
} else {
poly1305vx(out, mPtr, uint64(len(m)), key)
}
} else {
sumGeneric(out, m, key)
}
buffer [16 * TagSize]byte // size must be a multiple of block size (16)
offset int
}
func (h *mac) Write(p []byte) (int, error) {
nn := len(p)
if h.offset > 0 {
n := copy(h.buffer[h.offset:], p)
if h.offset+n < len(h.buffer) {
h.offset += n
return nn, nil
}
p = p[n:]
h.offset = 0
if cpu.S390X.HasVX {
updateVX(&h.macState, h.buffer[:])
} else {
updateGeneric(&h.macState, h.buffer[:])
}
}
tail := len(p) % len(h.buffer) // number of bytes to copy into buffer
body := len(p) - tail // number of bytes to process now
if body > 0 {
if cpu.S390X.HasVX {
updateVX(&h.macState, p[:body])
} else {
updateGeneric(&h.macState, p[:body])
}
}
h.offset = copy(h.buffer[:], p[body:]) // copy tail bytes - can be 0
return nn, nil
}
func (h *mac) Sum(out *[TagSize]byte) {
state := h.macState
remainder := h.buffer[:h.offset]
// Use the generic implementation if we have 2 or fewer blocks left
// to sum. The vector implementation has a higher startup time.
if cpu.S390X.HasVX && len(remainder) > 2*TagSize {
updateVX(&state, remainder)
} else if len(remainder) > 0 {
updateGeneric(&state, remainder)
}
finalize(out, &state.h, &state.s)
}

View File

@@ -2,115 +2,187 @@
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// +build s390x,go1.11,!gccgo,!appengine
// +build !gccgo,!purego
#include "textflag.h"
// Implementation of Poly1305 using the vector facility (vx).
// This implementation of Poly1305 uses the vector facility (vx)
// to process up to 2 blocks (32 bytes) per iteration using an
// algorithm based on the one described in:
//
// NEON crypto, Daniel J. Bernstein & Peter Schwabe
// https://cryptojedi.org/papers/neoncrypto-20120320.pdf
//
// This algorithm uses 5 26-bit limbs to represent a 130-bit
// value. These limbs are, for the most part, zero extended and
// placed into 64-bit vector register elements. Each vector
// register is 128-bits wide and so holds 2 of these elements.
// Using 26-bit limbs allows us plenty of headroom to accomodate
// accumulations before and after multiplication without
// overflowing either 32-bits (before multiplication) or 64-bits
// (after multiplication).
//
// In order to parallelise the operations required to calculate
// the sum we use two separate accumulators and then sum those
// in an extra final step. For compatibility with the generic
// implementation we perform this summation at the end of every
// updateVX call.
//
// To use two accumulators we must multiply the message blocks
// by r² rather than r. Only the final message block should be
// multiplied by r.
//
// Example:
//
// We want to calculate the sum (h) for a 64 byte message (m):
//
// h = m[0:16]r + m[16:32]r³ + m[32:48]r² + m[48:64]r
//
// To do this we split the calculation into the even indices
// and odd indices of the message. These form our SIMD 'lanes':
//
// h = m[ 0:16]r + m[32:48]r² + <- lane 0
// m[16:32]r³ + m[48:64]r <- lane 1
//
// To calculate this iteratively we refactor so that both lanes
// are written in terms of r² and r:
//
// h = (m[ 0:16]r² + m[32:48])r² + <- lane 0
// (m[16:32]r² + m[48:64])r <- lane 1
// ^ ^
// | coefficients for second iteration
// coefficients for first iteration
//
// So in this case we would have two iterations. In the first
// both lanes are multiplied by r². In the second only the
// first lane is multiplied by r² and the second lane is
// instead multiplied by r. This gives use the odd and even
// powers of r that we need from the original equation.
//
// Notation:
//
// h - accumulator
// r - key
// m - message
//
// [a, b] - SIMD register holding two 64-bit values
// [a, b, c, d] - SIMD register holding four 32-bit values
// x[n] - limb n of variable x with bit width i
//
// Limbs are expressed in little endian order, so for 26-bit
// limbs x[4] will be the most significant limb and x[0]
// will be the least significant limb.
// constants
#define MOD26 V0
#define EX0 V1
#define EX1 V2
#define EX2 V3
// masking constants
#define MOD24 V0 // [0x0000000000ffffff, 0x0000000000ffffff] - mask low 24-bits
#define MOD26 V1 // [0x0000000003ffffff, 0x0000000003ffffff] - mask low 26-bits
// temporaries
#define T_0 V4
#define T_1 V5
#define T_2 V6
#define T_3 V7
#define T_4 V8
// expansion constants (see EXPAND macro)
#define EX0 V2
#define EX1 V3
#define EX2 V4
// key (r)
#define R_0 V9
#define R_1 V10
#define R_2 V11
#define R_3 V12
#define R_4 V13
#define R5_1 V14
#define R5_2 V15
#define R5_3 V16
#define R5_4 V17
#define RSAVE_0 R5
#define RSAVE_1 R6
#define RSAVE_2 R7
#define RSAVE_3 R8
#define RSAVE_4 R9
#define R5SAVE_1 V28
#define R5SAVE_2 V29
#define R5SAVE_3 V30
#define R5SAVE_4 V31
// key (r², r or 1 depending on context)
#define R_0 V5
#define R_1 V6
#define R_2 V7
#define R_3 V8
#define R_4 V9
// message block
#define F_0 V18
#define F_1 V19
#define F_2 V20
#define F_3 V21
#define F_4 V22
// precalculated coefficients (5r², 5r or 0 depending on context)
#define R5_1 V10
#define R5_2 V11
#define R5_3 V12
#define R5_4 V13
// accumulator
#define H_0 V23
#define H_1 V24
#define H_2 V25
#define H_3 V26
#define H_4 V27
// message block (m)
#define M_0 V14
#define M_1 V15
#define M_2 V16
#define M_3 V17
#define M_4 V18
GLOBL ·keyMask<>(SB), RODATA, $16
DATA ·keyMask<>+0(SB)/8, $0xffffff0ffcffff0f
DATA ·keyMask<>+8(SB)/8, $0xfcffff0ffcffff0f
// accumulator (h)
#define H_0 V19
#define H_1 V20
#define H_2 V21
#define H_3 V22
#define H_4 V23
GLOBL ·bswapMask<>(SB), RODATA, $16
DATA ·bswapMask<>+0(SB)/8, $0x0f0e0d0c0b0a0908
DATA ·bswapMask<>+8(SB)/8, $0x0706050403020100
// temporary registers (for short-lived values)
#define T_0 V24
#define T_1 V25
#define T_2 V26
#define T_3 V27
#define T_4 V28
GLOBL ·constants<>(SB), RODATA, $64
// MOD26
DATA ·constants<>+0(SB)/8, $0x3ffffff
DATA ·constants<>+8(SB)/8, $0x3ffffff
GLOBL ·constants<>(SB), RODATA, $0x30
// EX0
DATA ·constants<>+16(SB)/8, $0x0006050403020100
DATA ·constants<>+24(SB)/8, $0x1016151413121110
DATA ·constants<>+0x00(SB)/8, $0x0006050403020100
DATA ·constants<>+0x08(SB)/8, $0x1016151413121110
// EX1
DATA ·constants<>+32(SB)/8, $0x060c0b0a09080706
DATA ·constants<>+40(SB)/8, $0x161c1b1a19181716
DATA ·constants<>+0x10(SB)/8, $0x060c0b0a09080706
DATA ·constants<>+0x18(SB)/8, $0x161c1b1a19181716
// EX2
DATA ·constants<>+48(SB)/8, $0x0d0d0d0d0d0f0e0d
DATA ·constants<>+56(SB)/8, $0x1d1d1d1d1d1f1e1d
DATA ·constants<>+0x20(SB)/8, $0x0d0d0d0d0d0f0e0d
DATA ·constants<>+0x28(SB)/8, $0x1d1d1d1d1d1f1e1d
// h = (f*g) % (2**130-5) [partial reduction]
// MULTIPLY multiplies each lane of f and g, partially reduced
// modulo 2¹³ - 5. The result, h, consists of partial products
// in each lane that need to be reduced further to produce the
// final result.
//
// h = (fg) % 2¹³ + (5fg) / 2¹³
//
// Note that the multiplication by 5 of the high bits is
// achieved by precalculating the multiplication of four of the
// g coefficients by 5. These are g51-g54.
#define MULTIPLY(f0, f1, f2, f3, f4, g0, g1, g2, g3, g4, g51, g52, g53, g54, h0, h1, h2, h3, h4) \
VMLOF f0, g0, h0 \
VMLOF f0, g1, h1 \
VMLOF f0, g2, h2 \
VMLOF f0, g3, h3 \
VMLOF f0, g1, h1 \
VMLOF f0, g4, h4 \
VMLOF f0, g2, h2 \
VMLOF f1, g54, T_0 \
VMLOF f1, g0, T_1 \
VMLOF f1, g1, T_2 \
VMLOF f1, g2, T_3 \
VMLOF f1, g0, T_1 \
VMLOF f1, g3, T_4 \
VMLOF f1, g1, T_2 \
VMALOF f2, g53, h0, h0 \
VMALOF f2, g54, h1, h1 \
VMALOF f2, g0, h2, h2 \
VMALOF f2, g1, h3, h3 \
VMALOF f2, g54, h1, h1 \
VMALOF f2, g2, h4, h4 \
VMALOF f2, g0, h2, h2 \
VMALOF f3, g52, T_0, T_0 \
VMALOF f3, g53, T_1, T_1 \
VMALOF f3, g54, T_2, T_2 \
VMALOF f3, g0, T_3, T_3 \
VMALOF f3, g53, T_1, T_1 \
VMALOF f3, g1, T_4, T_4 \
VMALOF f3, g54, T_2, T_2 \
VMALOF f4, g51, h0, h0 \
VMALOF f4, g52, h1, h1 \
VMALOF f4, g53, h2, h2 \
VMALOF f4, g54, h3, h3 \
VMALOF f4, g52, h1, h1 \
VMALOF f4, g0, h4, h4 \
VMALOF f4, g53, h2, h2 \
VAG T_0, h0, h0 \
VAG T_1, h1, h1 \
VAG T_2, h2, h2 \
VAG T_3, h3, h3 \
VAG T_4, h4, h4
VAG T_1, h1, h1 \
VAG T_4, h4, h4 \
VAG T_2, h2, h2
// carry h0->h1 h3->h4, h1->h2 h4->h0, h0->h1 h2->h3, h3->h4
// REDUCE performs the following carry operations in four
// stages, as specified in Bernstein & Schwabe:
//
// 1: h[0]->h[1] h[3]->h[4]
// 2: h[1]->h[2] h[4]->h[0]
// 3: h[0]->h[1] h[2]->h[3]
// 4: h[3]->h[4]
//
// The result is that all of the limbs are limited to 26-bits
// except for h[1] and h[4] which are limited to 27-bits.
//
// Note that although each limb is aligned at 26-bit intervals
// they may contain values that exceed 2² - 1, hence the need
// to carry the excess bits in each limb.
#define REDUCE(h0, h1, h2, h3, h4) \
VESRLG $26, h0, T_0 \
VESRLG $26, h3, T_1 \
@@ -136,144 +208,155 @@ DATA ·constants<>+56(SB)/8, $0x1d1d1d1d1d1f1e1d
VN MOD26, h3, h3 \
VAG T_2, h4, h4
// expand in0 into d[0] and in1 into d[1]
// EXPAND splits the 128-bit little-endian values in0 and in1
// into 26-bit big-endian limbs and places the results into
// the first and second lane of d[0:4] respectively.
//
// The EX0, EX1 and EX2 constants are arrays of byte indices
// for permutation. The permutation both reverses the bytes
// in the input and ensures the bytes are copied into the
// destination limb ready to be shifted into their final
// position.
#define EXPAND(in0, in1, d0, d1, d2, d3, d4) \
VGBM $0x0707, d1 \ // d1=tmp
VPERM in0, in1, EX2, d4 \
VPERM in0, in1, EX0, d0 \
VPERM in0, in1, EX1, d2 \
VN d1, d4, d4 \
VPERM in0, in1, EX2, d4 \
VESRLG $26, d0, d1 \
VESRLG $30, d2, d3 \
VESRLG $4, d2, d2 \
VN MOD26, d0, d0 \
VN MOD26, d1, d1 \
VN MOD26, d2, d2 \
VN MOD26, d3, d3
VN MOD26, d0, d0 \ // [in0[0], in1[0]]
VN MOD26, d3, d3 \ // [in0[3], in1[3]]
VN MOD26, d1, d1 \ // [in0[1], in1[1]]
VN MOD24, d4, d4 \ // [in0[4], in1[4]]
VN MOD26, d2, d2 // [in0[2], in1[2]]
// pack h4:h0 into h1:h0 (no carry)
#define PACK(h0, h1, h2, h3, h4) \
VESLG $26, h1, h1 \
VESLG $26, h3, h3 \
VO h0, h1, h0 \
VO h2, h3, h2 \
VESLG $4, h2, h2 \
VLEIB $7, $48, h1 \
VSLB h1, h2, h2 \
VO h0, h2, h0 \
VLEIB $7, $104, h1 \
VSLB h1, h4, h3 \
VO h3, h0, h0 \
VLEIB $7, $24, h1 \
VSRLB h1, h4, h1
// func updateVX(state *macState, msg []byte)
TEXT ·updateVX(SB), NOSPLIT, $0
MOVD state+0(FP), R1
LMG msg+8(FP), R2, R3 // R2=msg_base, R3=msg_len
// if h > 2**130-5 then h -= 2**130-5
#define MOD(h0, h1, t0, t1, t2) \
VZERO t0 \
VLEIG $1, $5, t0 \
VACCQ h0, t0, t1 \
VAQ h0, t0, t0 \
VONE t2 \
VLEIG $1, $-4, t2 \
VAQ t2, t1, t1 \
VACCQ h1, t1, t1 \
VONE t2 \
VAQ t2, t1, t1 \
VN h0, t1, t2 \
VNC t0, t1, t1 \
VO t1, t2, h0
// func poly1305vx(out *[16]byte, m *byte, mlen uint64, key *[32]key)
TEXT ·poly1305vx(SB), $0-32
// This code processes up to 2 blocks (32 bytes) per iteration
// using the algorithm described in:
// NEON crypto, Daniel J. Bernstein & Peter Schwabe
// https://cryptojedi.org/papers/neoncrypto-20120320.pdf
LMG out+0(FP), R1, R4 // R1=out, R2=m, R3=mlen, R4=key
// load MOD26, EX0, EX1 and EX2
// load EX0, EX1 and EX2
MOVD $·constants<>(SB), R5
VLM (R5), MOD26, EX2
VLM (R5), EX0, EX2
// setup r
VL (R4), T_0
MOVD $·keyMask<>(SB), R6
VL (R6), T_1
VN T_0, T_1, T_0
EXPAND(T_0, T_0, R_0, R_1, R_2, R_3, R_4)
// generate masks
VGMG $(64-24), $63, MOD24 // [0x00ffffff, 0x00ffffff]
VGMG $(64-26), $63, MOD26 // [0x03ffffff, 0x03ffffff]
// setup r*5
VLEIG $0, $5, T_0
VLEIG $1, $5, T_0
// load h (accumulator) and r (key) from state
VZERO T_1 // [0, 0]
VL 0(R1), T_0 // [h[0], h[1]]
VLEG $0, 16(R1), T_1 // [h[2], 0]
VL 24(R1), T_2 // [r[0], r[1]]
VPDI $0, T_0, T_2, T_3 // [h[0], r[0]]
VPDI $5, T_0, T_2, T_4 // [h[1], r[1]]
// store r (for final block)
VMLOF T_0, R_1, R5SAVE_1
VMLOF T_0, R_2, R5SAVE_2
VMLOF T_0, R_3, R5SAVE_3
VMLOF T_0, R_4, R5SAVE_4
VLGVG $0, R_0, RSAVE_0
VLGVG $0, R_1, RSAVE_1
VLGVG $0, R_2, RSAVE_2
VLGVG $0, R_3, RSAVE_3
VLGVG $0, R_4, RSAVE_4
// unpack h and r into 26-bit limbs
// note: h[2] may have the low 3 bits set, so h[4] is a 27-bit value
VN MOD26, T_3, H_0 // [h[0], r[0]]
VZERO H_1 // [0, 0]
VZERO H_3 // [0, 0]
VGMG $(64-12-14), $(63-12), T_0 // [0x03fff000, 0x03fff000] - 26-bit mask with low 12 bits masked out
VESLG $24, T_1, T_1 // [h[2]<<24, 0]
VERIMG $-26&63, T_3, MOD26, H_1 // [h[1], r[1]]
VESRLG $+52&63, T_3, H_2 // [h[2], r[2]] - low 12 bits only
VERIMG $-14&63, T_4, MOD26, H_3 // [h[1], r[1]]
VESRLG $40, T_4, H_4 // [h[4], r[4]] - low 24 bits only
VERIMG $+12&63, T_4, T_0, H_2 // [h[2], r[2]] - complete
VO T_1, H_4, H_4 // [h[4], r[4]] - complete
// skip r**2 calculation
// replicate r across all 4 vector elements
VREPF $3, H_0, R_0 // [r[0], r[0], r[0], r[0]]
VREPF $3, H_1, R_1 // [r[1], r[1], r[1], r[1]]
VREPF $3, H_2, R_2 // [r[2], r[2], r[2], r[2]]
VREPF $3, H_3, R_3 // [r[3], r[3], r[3], r[3]]
VREPF $3, H_4, R_4 // [r[4], r[4], r[4], r[4]]
// zero out lane 1 of h
VLEIG $1, $0, H_0 // [h[0], 0]
VLEIG $1, $0, H_1 // [h[1], 0]
VLEIG $1, $0, H_2 // [h[2], 0]
VLEIG $1, $0, H_3 // [h[3], 0]
VLEIG $1, $0, H_4 // [h[4], 0]
// calculate 5r (ignore least significant limb)
VREPIF $5, T_0
VMLF T_0, R_1, R5_1 // [5r[1], 5r[1], 5r[1], 5r[1]]
VMLF T_0, R_2, R5_2 // [5r[2], 5r[2], 5r[2], 5r[2]]
VMLF T_0, R_3, R5_3 // [5r[3], 5r[3], 5r[3], 5r[3]]
VMLF T_0, R_4, R5_4 // [5r[4], 5r[4], 5r[4], 5r[4]]
// skip r² calculation if we are only calculating one block
CMPBLE R3, $16, skip
// calculate r**2
MULTIPLY(R_0, R_1, R_2, R_3, R_4, R_0, R_1, R_2, R_3, R_4, R5SAVE_1, R5SAVE_2, R5SAVE_3, R5SAVE_4, H_0, H_1, H_2, H_3, H_4)
REDUCE(H_0, H_1, H_2, H_3, H_4)
VLEIG $0, $5, T_0
VLEIG $1, $5, T_0
VMLOF T_0, H_1, R5_1
VMLOF T_0, H_2, R5_2
VMLOF T_0, H_3, R5_3
VMLOF T_0, H_4, R5_4
VLR H_0, R_0
VLR H_1, R_1
VLR H_2, R_2
VLR H_3, R_3
VLR H_4, R_4
// calculate r²
MULTIPLY(R_0, R_1, R_2, R_3, R_4, R_0, R_1, R_2, R_3, R_4, R5_1, R5_2, R5_3, R5_4, M_0, M_1, M_2, M_3, M_4)
REDUCE(M_0, M_1, M_2, M_3, M_4)
VGBM $0x0f0f, T_0
VERIMG $0, M_0, T_0, R_0 // [r[0], r²[0], r[0], r²[0]]
VERIMG $0, M_1, T_0, R_1 // [r[1], r²[1], r[1], r²[1]]
VERIMG $0, M_2, T_0, R_2 // [r[2], r²[2], r[2], r²[2]]
VERIMG $0, M_3, T_0, R_3 // [r[3], r²[3], r[3], r²[3]]
VERIMG $0, M_4, T_0, R_4 // [r[4], r²[4], r[4], r²[4]]
// initialize h
VZERO H_0
VZERO H_1
VZERO H_2
VZERO H_3
VZERO H_4
// calculate 5r² (ignore least significant limb)
VREPIF $5, T_0
VMLF T_0, R_1, R5_1 // [5r[1], 5r²[1], 5r[1], 5r²[1]]
VMLF T_0, R_2, R5_2 // [5r[2], 5r²[2], 5r[2], 5r²[2]]
VMLF T_0, R_3, R5_3 // [5r[3], 5r²[3], 5r[3], 5r²[3]]
VMLF T_0, R_4, R5_4 // [5r[4], 5r²[4], 5r[4], 5r²[4]]
loop:
CMPBLE R3, $32, b2
VLM (R2), T_0, T_1
SUB $32, R3
MOVD $32(R2), R2
EXPAND(T_0, T_1, F_0, F_1, F_2, F_3, F_4)
VLEIB $4, $1, F_4
VLEIB $12, $1, F_4
CMPBLE R3, $32, b2 // 2 or fewer blocks remaining, need to change key coefficients
// load next 2 blocks from message
VLM (R2), T_0, T_1
// update message slice
SUB $32, R3
MOVD $32(R2), R2
// unpack message blocks into 26-bit big-endian limbs
EXPAND(T_0, T_1, M_0, M_1, M_2, M_3, M_4)
// add 2¹² to each message block value
VLEIB $4, $1, M_4
VLEIB $12, $1, M_4
multiply:
VAG H_0, F_0, F_0
VAG H_1, F_1, F_1
VAG H_2, F_2, F_2
VAG H_3, F_3, F_3
VAG H_4, F_4, F_4
MULTIPLY(F_0, F_1, F_2, F_3, F_4, R_0, R_1, R_2, R_3, R_4, R5_1, R5_2, R5_3, R5_4, H_0, H_1, H_2, H_3, H_4)
// accumulate the incoming message
VAG H_0, M_0, M_0
VAG H_3, M_3, M_3
VAG H_1, M_1, M_1
VAG H_4, M_4, M_4
VAG H_2, M_2, M_2
// multiply the accumulator by the key coefficient
MULTIPLY(M_0, M_1, M_2, M_3, M_4, R_0, R_1, R_2, R_3, R_4, R5_1, R5_2, R5_3, R5_4, H_0, H_1, H_2, H_3, H_4)
// carry and partially reduce the partial products
REDUCE(H_0, H_1, H_2, H_3, H_4)
CMPBNE R3, $0, loop
finish:
// sum vectors
// sum lane 0 and lane 1 and put the result in lane 1
VZERO T_0
VSUMQG H_0, T_0, H_0
VSUMQG H_1, T_0, H_1
VSUMQG H_2, T_0, H_2
VSUMQG H_3, T_0, H_3
VSUMQG H_1, T_0, H_1
VSUMQG H_4, T_0, H_4
VSUMQG H_2, T_0, H_2
// h may be >= 2*(2**130-5) so we need to reduce it again
// reduce again after summation
// TODO(mundaym): there might be a more efficient way to do this
// now that we only have 1 active lane. For example, we could
// simultaneously pack the values as we reduce them.
REDUCE(H_0, H_1, H_2, H_3, H_4)
// carry h1->h4
// carry h[1] through to h[4] so that only h[4] can exceed 2² - 1
// TODO(mundaym): in testing this final carry was unnecessary.
// Needs a proof before it can be removed though.
VESRLG $26, H_1, T_1
VN MOD26, H_1, H_1
VAQ T_1, H_2, H_2
@@ -284,95 +367,137 @@ finish:
VN MOD26, H_3, H_3
VAQ T_3, H_4, H_4
// h is now < 2*(2**130-5)
// pack h into h1 (hi) and h0 (lo)
PACK(H_0, H_1, H_2, H_3, H_4)
// if h > 2**130-5 then h -= 2**130-5
MOD(H_0, H_1, T_0, T_1, T_2)
// h += s
MOVD $·bswapMask<>(SB), R5
VL (R5), T_1
VL 16(R4), T_0
VPERM T_0, T_0, T_1, T_0 // reverse bytes (to big)
VAQ T_0, H_0, H_0
VPERM H_0, H_0, T_1, H_0 // reverse bytes (to little)
VST H_0, (R1)
// h is now < 2(2¹³ - 5)
// Pack each lane in h[0:4] into h[0:1].
VESLG $26, H_1, H_1
VESLG $26, H_3, H_3
VO H_0, H_1, H_0
VO H_2, H_3, H_2
VESLG $4, H_2, H_2
VLEIB $7, $48, H_1
VSLB H_1, H_2, H_2
VO H_0, H_2, H_0
VLEIB $7, $104, H_1
VSLB H_1, H_4, H_3
VO H_3, H_0, H_0
VLEIB $7, $24, H_1
VSRLB H_1, H_4, H_1
// update state
VSTEG $1, H_0, 0(R1)
VSTEG $0, H_0, 8(R1)
VSTEG $1, H_1, 16(R1)
RET
b2:
b2: // 2 or fewer blocks remaining
CMPBLE R3, $16, b1
// 2 blocks remaining
SUB $17, R3
VL (R2), T_0
VLL R3, 16(R2), T_1
ADD $1, R3
MOVBZ $1, R0
CMPBEQ R3, $16, 2(PC)
VLVGB R3, R0, T_1
EXPAND(T_0, T_1, F_0, F_1, F_2, F_3, F_4)
CMPBNE R3, $16, 2(PC)
VLEIB $12, $1, F_4
VLEIB $4, $1, F_4
// Load the 2 remaining blocks (17-32 bytes remaining).
MOVD $-17(R3), R0 // index of final byte to load modulo 16
VL (R2), T_0 // load full 16 byte block
VLL R0, 16(R2), T_1 // load final (possibly partial) block and pad with zeros to 16 bytes
// setup [r²,r]
VLVGG $1, RSAVE_0, R_0
VLVGG $1, RSAVE_1, R_1
VLVGG $1, RSAVE_2, R_2
VLVGG $1, RSAVE_3, R_3
VLVGG $1, RSAVE_4, R_4
VPDI $0, R5_1, R5SAVE_1, R5_1
VPDI $0, R5_2, R5SAVE_2, R5_2
VPDI $0, R5_3, R5SAVE_3, R5_3
VPDI $0, R5_4, R5SAVE_4, R5_4
// The Poly1305 algorithm requires that a 1 bit be appended to
// each message block. If the final block is less than 16 bytes
// long then it is easiest to insert the 1 before the message
// block is split into 26-bit limbs. If, on the other hand, the
// final message block is 16 bytes long then we append the 1 bit
// after expansion as normal.
MOVBZ $1, R0
MOVD $-16(R3), R3 // index of byte in last block to insert 1 at (could be 16)
CMPBEQ R3, $16, 2(PC) // skip the insertion if the final block is 16 bytes long
VLVGB R3, R0, T_1 // insert 1 into the byte at index R3
// Split both blocks into 26-bit limbs in the appropriate lanes.
EXPAND(T_0, T_1, M_0, M_1, M_2, M_3, M_4)
// Append a 1 byte to the end of the second to last block.
VLEIB $4, $1, M_4
// Append a 1 byte to the end of the last block only if it is a
// full 16 byte block.
CMPBNE R3, $16, 2(PC)
VLEIB $12, $1, M_4
// Finally, set up the coefficients for the final multiplication.
// We have previously saved r and 5r in the 32-bit even indexes
// of the R_[0-4] and R5_[1-4] coefficient registers.
//
// We want lane 0 to be multiplied by r² so that can be kept the
// same. We want lane 1 to be multiplied by r so we need to move
// the saved r value into the 32-bit odd index in lane 1 by
// rotating the 64-bit lane by 32.
VGBM $0x00ff, T_0 // [0, 0xffffffffffffffff] - mask lane 1 only
VERIMG $32, R_0, T_0, R_0 // [_, r²[0], _, r[0]]
VERIMG $32, R_1, T_0, R_1 // [_, r²[1], _, r[1]]
VERIMG $32, R_2, T_0, R_2 // [_, r²[2], _, r[2]]
VERIMG $32, R_3, T_0, R_3 // [_, r²[3], _, r[3]]
VERIMG $32, R_4, T_0, R_4 // [_, r²[4], _, r[4]]
VERIMG $32, R5_1, T_0, R5_1 // [_, 5r²[1], _, 5r[1]]
VERIMG $32, R5_2, T_0, R5_2 // [_, 5r²[2], _, 5r[2]]
VERIMG $32, R5_3, T_0, R5_3 // [_, 5r²[3], _, 5r[3]]
VERIMG $32, R5_4, T_0, R5_4 // [_, 5r²[4], _, 5r[4]]
MOVD $0, R3
BR multiply
skip:
VZERO H_0
VZERO H_1
VZERO H_2
VZERO H_3
VZERO H_4
CMPBEQ R3, $0, finish
b1:
// 1 block remaining
SUB $1, R3
VLL R3, (R2), T_0
ADD $1, R3
b1: // 1 block remaining
// Load the final block (1-16 bytes). This will be placed into
// lane 0.
MOVD $-1(R3), R0
VLL R0, (R2), T_0 // pad to 16 bytes with zeros
// The Poly1305 algorithm requires that a 1 bit be appended to
// each message block. If the final block is less than 16 bytes
// long then it is easiest to insert the 1 before the message
// block is split into 26-bit limbs. If, on the other hand, the
// final message block is 16 bytes long then we append the 1 bit
// after expansion as normal.
MOVBZ $1, R0
CMPBEQ R3, $16, 2(PC)
VLVGB R3, R0, T_0
VZERO T_1
EXPAND(T_0, T_1, F_0, F_1, F_2, F_3, F_4)
CMPBNE R3, $16, 2(PC)
VLEIB $4, $1, F_4
VLEIG $1, $1, R_0
VZERO R_1
VZERO R_2
VZERO R_3
VZERO R_4
VZERO R5_1
VZERO R5_2
VZERO R5_3
VZERO R5_4
// setup [r, 1]
VLVGG $0, RSAVE_0, R_0
VLVGG $0, RSAVE_1, R_1
VLVGG $0, RSAVE_2, R_2
VLVGG $0, RSAVE_3, R_3
VLVGG $0, RSAVE_4, R_4
VPDI $0, R5SAVE_1, R5_1, R5_1
VPDI $0, R5SAVE_2, R5_2, R5_2
VPDI $0, R5SAVE_3, R5_3, R5_3
VPDI $0, R5SAVE_4, R5_4, R5_4
// Set the message block in lane 1 to the value 0 so that it
// can be accumulated without affecting the final result.
VZERO T_1
// Split the final message block into 26-bit limbs in lane 0.
// Lane 1 will be contain 0.
EXPAND(T_0, T_1, M_0, M_1, M_2, M_3, M_4)
// Append a 1 byte to the end of the last block only if it is a
// full 16 byte block.
CMPBNE R3, $16, 2(PC)
VLEIB $4, $1, M_4
// We have previously saved r and 5r in the 32-bit even indexes
// of the R_[0-4] and R5_[1-4] coefficient registers.
//
// We want lane 0 to be multiplied by r so we need to move the
// saved r value into the 32-bit odd index in lane 0. We want
// lane 1 to be set to the value 1. This makes multiplication
// a no-op. We do this by setting lane 1 in every register to 0
// and then just setting the 32-bit index 3 in R_0 to 1.
VZERO T_0
MOVD $0, R0
MOVD $0x10111213, R12
VLVGP R12, R0, T_1 // [_, 0x10111213, _, 0x00000000]
VPERM T_0, R_0, T_1, R_0 // [_, r[0], _, 0]
VPERM T_0, R_1, T_1, R_1 // [_, r[1], _, 0]
VPERM T_0, R_2, T_1, R_2 // [_, r[2], _, 0]
VPERM T_0, R_3, T_1, R_3 // [_, r[3], _, 0]
VPERM T_0, R_4, T_1, R_4 // [_, r[4], _, 0]
VPERM T_0, R5_1, T_1, R5_1 // [_, 5r[1], _, 0]
VPERM T_0, R5_2, T_1, R5_2 // [_, 5r[2], _, 0]
VPERM T_0, R5_3, T_1, R5_3 // [_, 5r[3], _, 0]
VPERM T_0, R5_4, T_1, R5_4 // [_, 5r[4], _, 0]
// Set the value of lane 1 to be 1.
VLEIF $3, $1, R_0 // [_, r[0], _, 1]
MOVD $0, R3
BR multiply

View File

@@ -1,909 +0,0 @@
// Copyright 2018 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.
// +build s390x,go1.11,!gccgo,!appengine
#include "textflag.h"
// Implementation of Poly1305 using the vector facility (vx) and the VMSL instruction.
// constants
#define EX0 V1
#define EX1 V2
#define EX2 V3
// temporaries
#define T_0 V4
#define T_1 V5
#define T_2 V6
#define T_3 V7
#define T_4 V8
#define T_5 V9
#define T_6 V10
#define T_7 V11
#define T_8 V12
#define T_9 V13
#define T_10 V14
// r**2 & r**4
#define R_0 V15
#define R_1 V16
#define R_2 V17
#define R5_1 V18
#define R5_2 V19
// key (r)
#define RSAVE_0 R7
#define RSAVE_1 R8
#define RSAVE_2 R9
#define R5SAVE_1 R10
#define R5SAVE_2 R11
// message block
#define M0 V20
#define M1 V21
#define M2 V22
#define M3 V23
#define M4 V24
#define M5 V25
// accumulator
#define H0_0 V26
#define H1_0 V27
#define H2_0 V28
#define H0_1 V29
#define H1_1 V30
#define H2_1 V31
GLOBL ·keyMask<>(SB), RODATA, $16
DATA ·keyMask<>+0(SB)/8, $0xffffff0ffcffff0f
DATA ·keyMask<>+8(SB)/8, $0xfcffff0ffcffff0f
GLOBL ·bswapMask<>(SB), RODATA, $16
DATA ·bswapMask<>+0(SB)/8, $0x0f0e0d0c0b0a0908
DATA ·bswapMask<>+8(SB)/8, $0x0706050403020100
GLOBL ·constants<>(SB), RODATA, $48
// EX0
DATA ·constants<>+0(SB)/8, $0x18191a1b1c1d1e1f
DATA ·constants<>+8(SB)/8, $0x0000050403020100
// EX1
DATA ·constants<>+16(SB)/8, $0x18191a1b1c1d1e1f
DATA ·constants<>+24(SB)/8, $0x00000a0908070605
// EX2
DATA ·constants<>+32(SB)/8, $0x18191a1b1c1d1e1f
DATA ·constants<>+40(SB)/8, $0x0000000f0e0d0c0b
GLOBL ·c<>(SB), RODATA, $48
// EX0
DATA ·c<>+0(SB)/8, $0x0000050403020100
DATA ·c<>+8(SB)/8, $0x0000151413121110
// EX1
DATA ·c<>+16(SB)/8, $0x00000a0908070605
DATA ·c<>+24(SB)/8, $0x00001a1918171615
// EX2
DATA ·c<>+32(SB)/8, $0x0000000f0e0d0c0b
DATA ·c<>+40(SB)/8, $0x0000001f1e1d1c1b
GLOBL ·reduce<>(SB), RODATA, $32
// 44 bit
DATA ·reduce<>+0(SB)/8, $0x0
DATA ·reduce<>+8(SB)/8, $0xfffffffffff
// 42 bit
DATA ·reduce<>+16(SB)/8, $0x0
DATA ·reduce<>+24(SB)/8, $0x3ffffffffff
// h = (f*g) % (2**130-5) [partial reduction]
// uses T_0...T_9 temporary registers
// input: m02_0, m02_1, m02_2, m13_0, m13_1, m13_2, r_0, r_1, r_2, r5_1, r5_2, m4_0, m4_1, m4_2, m5_0, m5_1, m5_2
// temp: t0, t1, t2, t3, t4, t5, t6, t7, t8, t9
// output: m02_0, m02_1, m02_2, m13_0, m13_1, m13_2
#define MULTIPLY(m02_0, m02_1, m02_2, m13_0, m13_1, m13_2, r_0, r_1, r_2, r5_1, r5_2, m4_0, m4_1, m4_2, m5_0, m5_1, m5_2, t0, t1, t2, t3, t4, t5, t6, t7, t8, t9) \
\ // Eliminate the dependency for the last 2 VMSLs
VMSLG m02_0, r_2, m4_2, m4_2 \
VMSLG m13_0, r_2, m5_2, m5_2 \ // 8 VMSLs pipelined
VMSLG m02_0, r_0, m4_0, m4_0 \
VMSLG m02_1, r5_2, V0, T_0 \
VMSLG m02_0, r_1, m4_1, m4_1 \
VMSLG m02_1, r_0, V0, T_1 \
VMSLG m02_1, r_1, V0, T_2 \
VMSLG m02_2, r5_1, V0, T_3 \
VMSLG m02_2, r5_2, V0, T_4 \
VMSLG m13_0, r_0, m5_0, m5_0 \
VMSLG m13_1, r5_2, V0, T_5 \
VMSLG m13_0, r_1, m5_1, m5_1 \
VMSLG m13_1, r_0, V0, T_6 \
VMSLG m13_1, r_1, V0, T_7 \
VMSLG m13_2, r5_1, V0, T_8 \
VMSLG m13_2, r5_2, V0, T_9 \
VMSLG m02_2, r_0, m4_2, m4_2 \
VMSLG m13_2, r_0, m5_2, m5_2 \
VAQ m4_0, T_0, m02_0 \
VAQ m4_1, T_1, m02_1 \
VAQ m5_0, T_5, m13_0 \
VAQ m5_1, T_6, m13_1 \
VAQ m02_0, T_3, m02_0 \
VAQ m02_1, T_4, m02_1 \
VAQ m13_0, T_8, m13_0 \
VAQ m13_1, T_9, m13_1 \
VAQ m4_2, T_2, m02_2 \
VAQ m5_2, T_7, m13_2 \
// SQUARE uses three limbs of r and r_2*5 to output square of r
// uses T_1, T_5 and T_7 temporary registers
// input: r_0, r_1, r_2, r5_2
// temp: TEMP0, TEMP1, TEMP2
// output: p0, p1, p2
#define SQUARE(r_0, r_1, r_2, r5_2, p0, p1, p2, TEMP0, TEMP1, TEMP2) \
VMSLG r_0, r_0, p0, p0 \
VMSLG r_1, r5_2, V0, TEMP0 \
VMSLG r_2, r5_2, p1, p1 \
VMSLG r_0, r_1, V0, TEMP1 \
VMSLG r_1, r_1, p2, p2 \
VMSLG r_0, r_2, V0, TEMP2 \
VAQ TEMP0, p0, p0 \
VAQ TEMP1, p1, p1 \
VAQ TEMP2, p2, p2 \
VAQ TEMP0, p0, p0 \
VAQ TEMP1, p1, p1 \
VAQ TEMP2, p2, p2 \
// carry h0->h1->h2->h0 || h3->h4->h5->h3
// uses T_2, T_4, T_5, T_7, T_8, T_9
// t6, t7, t8, t9, t10, t11
// input: h0, h1, h2, h3, h4, h5
// temp: t0, t1, t2, t3, t4, t5, t6, t7, t8, t9, t10, t11
// output: h0, h1, h2, h3, h4, h5
#define REDUCE(h0, h1, h2, h3, h4, h5, t0, t1, t2, t3, t4, t5, t6, t7, t8, t9, t10, t11) \
VLM (R12), t6, t7 \ // 44 and 42 bit clear mask
VLEIB $7, $0x28, t10 \ // 5 byte shift mask
VREPIB $4, t8 \ // 4 bit shift mask
VREPIB $2, t11 \ // 2 bit shift mask
VSRLB t10, h0, t0 \ // h0 byte shift
VSRLB t10, h1, t1 \ // h1 byte shift
VSRLB t10, h2, t2 \ // h2 byte shift
VSRLB t10, h3, t3 \ // h3 byte shift
VSRLB t10, h4, t4 \ // h4 byte shift
VSRLB t10, h5, t5 \ // h5 byte shift
VSRL t8, t0, t0 \ // h0 bit shift
VSRL t8, t1, t1 \ // h2 bit shift
VSRL t11, t2, t2 \ // h2 bit shift
VSRL t8, t3, t3 \ // h3 bit shift
VSRL t8, t4, t4 \ // h4 bit shift
VESLG $2, t2, t9 \ // h2 carry x5
VSRL t11, t5, t5 \ // h5 bit shift
VN t6, h0, h0 \ // h0 clear carry
VAQ t2, t9, t2 \ // h2 carry x5
VESLG $2, t5, t9 \ // h5 carry x5
VN t6, h1, h1 \ // h1 clear carry
VN t7, h2, h2 \ // h2 clear carry
VAQ t5, t9, t5 \ // h5 carry x5
VN t6, h3, h3 \ // h3 clear carry
VN t6, h4, h4 \ // h4 clear carry
VN t7, h5, h5 \ // h5 clear carry
VAQ t0, h1, h1 \ // h0->h1
VAQ t3, h4, h4 \ // h3->h4
VAQ t1, h2, h2 \ // h1->h2
VAQ t4, h5, h5 \ // h4->h5
VAQ t2, h0, h0 \ // h2->h0
VAQ t5, h3, h3 \ // h5->h3
VREPG $1, t6, t6 \ // 44 and 42 bit masks across both halves
VREPG $1, t7, t7 \
VSLDB $8, h0, h0, h0 \ // set up [h0/1/2, h3/4/5]
VSLDB $8, h1, h1, h1 \
VSLDB $8, h2, h2, h2 \
VO h0, h3, h3 \
VO h1, h4, h4 \
VO h2, h5, h5 \
VESRLG $44, h3, t0 \ // 44 bit shift right
VESRLG $44, h4, t1 \
VESRLG $42, h5, t2 \
VN t6, h3, h3 \ // clear carry bits
VN t6, h4, h4 \
VN t7, h5, h5 \
VESLG $2, t2, t9 \ // multiply carry by 5
VAQ t9, t2, t2 \
VAQ t0, h4, h4 \
VAQ t1, h5, h5 \
VAQ t2, h3, h3 \
// carry h0->h1->h2->h0
// input: h0, h1, h2
// temp: t0, t1, t2, t3, t4, t5, t6, t7, t8
// output: h0, h1, h2
#define REDUCE2(h0, h1, h2, t0, t1, t2, t3, t4, t5, t6, t7, t8) \
VLEIB $7, $0x28, t3 \ // 5 byte shift mask
VREPIB $4, t4 \ // 4 bit shift mask
VREPIB $2, t7 \ // 2 bit shift mask
VGBM $0x003F, t5 \ // mask to clear carry bits
VSRLB t3, h0, t0 \
VSRLB t3, h1, t1 \
VSRLB t3, h2, t2 \
VESRLG $4, t5, t5 \ // 44 bit clear mask
VSRL t4, t0, t0 \
VSRL t4, t1, t1 \
VSRL t7, t2, t2 \
VESRLG $2, t5, t6 \ // 42 bit clear mask
VESLG $2, t2, t8 \
VAQ t8, t2, t2 \
VN t5, h0, h0 \
VN t5, h1, h1 \
VN t6, h2, h2 \
VAQ t0, h1, h1 \
VAQ t1, h2, h2 \
VAQ t2, h0, h0 \
VSRLB t3, h0, t0 \
VSRLB t3, h1, t1 \
VSRLB t3, h2, t2 \
VSRL t4, t0, t0 \
VSRL t4, t1, t1 \
VSRL t7, t2, t2 \
VN t5, h0, h0 \
VN t5, h1, h1 \
VESLG $2, t2, t8 \
VN t6, h2, h2 \
VAQ t0, h1, h1 \
VAQ t8, t2, t2 \
VAQ t1, h2, h2 \
VAQ t2, h0, h0 \
// expands two message blocks into the lower halfs of the d registers
// moves the contents of the d registers into upper halfs
// input: in1, in2, d0, d1, d2, d3, d4, d5
// temp: TEMP0, TEMP1, TEMP2, TEMP3
// output: d0, d1, d2, d3, d4, d5
#define EXPACC(in1, in2, d0, d1, d2, d3, d4, d5, TEMP0, TEMP1, TEMP2, TEMP3) \
VGBM $0xff3f, TEMP0 \
VGBM $0xff1f, TEMP1 \
VESLG $4, d1, TEMP2 \
VESLG $4, d4, TEMP3 \
VESRLG $4, TEMP0, TEMP0 \
VPERM in1, d0, EX0, d0 \
VPERM in2, d3, EX0, d3 \
VPERM in1, d2, EX2, d2 \
VPERM in2, d5, EX2, d5 \
VPERM in1, TEMP2, EX1, d1 \
VPERM in2, TEMP3, EX1, d4 \
VN TEMP0, d0, d0 \
VN TEMP0, d3, d3 \
VESRLG $4, d1, d1 \
VESRLG $4, d4, d4 \
VN TEMP1, d2, d2 \
VN TEMP1, d5, d5 \
VN TEMP0, d1, d1 \
VN TEMP0, d4, d4 \
// expands one message block into the lower halfs of the d registers
// moves the contents of the d registers into upper halfs
// input: in, d0, d1, d2
// temp: TEMP0, TEMP1, TEMP2
// output: d0, d1, d2
#define EXPACC2(in, d0, d1, d2, TEMP0, TEMP1, TEMP2) \
VGBM $0xff3f, TEMP0 \
VESLG $4, d1, TEMP2 \
VGBM $0xff1f, TEMP1 \
VPERM in, d0, EX0, d0 \
VESRLG $4, TEMP0, TEMP0 \
VPERM in, d2, EX2, d2 \
VPERM in, TEMP2, EX1, d1 \
VN TEMP0, d0, d0 \
VN TEMP1, d2, d2 \
VESRLG $4, d1, d1 \
VN TEMP0, d1, d1 \
// pack h2:h0 into h1:h0 (no carry)
// input: h0, h1, h2
// output: h0, h1, h2
#define PACK(h0, h1, h2) \
VMRLG h1, h2, h2 \ // copy h1 to upper half h2
VESLG $44, h1, h1 \ // shift limb 1 44 bits, leaving 20
VO h0, h1, h0 \ // combine h0 with 20 bits from limb 1
VESRLG $20, h2, h1 \ // put top 24 bits of limb 1 into h1
VLEIG $1, $0, h1 \ // clear h2 stuff from lower half of h1
VO h0, h1, h0 \ // h0 now has 88 bits (limb 0 and 1)
VLEIG $0, $0, h2 \ // clear upper half of h2
VESRLG $40, h2, h1 \ // h1 now has upper two bits of result
VLEIB $7, $88, h1 \ // for byte shift (11 bytes)
VSLB h1, h2, h2 \ // shift h2 11 bytes to the left
VO h0, h2, h0 \ // combine h0 with 20 bits from limb 1
VLEIG $0, $0, h1 \ // clear upper half of h1
// if h > 2**130-5 then h -= 2**130-5
// input: h0, h1
// temp: t0, t1, t2
// output: h0
#define MOD(h0, h1, t0, t1, t2) \
VZERO t0 \
VLEIG $1, $5, t0 \
VACCQ h0, t0, t1 \
VAQ h0, t0, t0 \
VONE t2 \
VLEIG $1, $-4, t2 \
VAQ t2, t1, t1 \
VACCQ h1, t1, t1 \
VONE t2 \
VAQ t2, t1, t1 \
VN h0, t1, t2 \
VNC t0, t1, t1 \
VO t1, t2, h0 \
// func poly1305vmsl(out *[16]byte, m *byte, mlen uint64, key *[32]key)
TEXT ·poly1305vmsl(SB), $0-32
// This code processes 6 + up to 4 blocks (32 bytes) per iteration
// using the algorithm described in:
// NEON crypto, Daniel J. Bernstein & Peter Schwabe
// https://cryptojedi.org/papers/neoncrypto-20120320.pdf
// And as moddified for VMSL as described in
// Accelerating Poly1305 Cryptographic Message Authentication on the z14
// O'Farrell et al, CASCON 2017, p48-55
// https://ibm.ent.box.com/s/jf9gedj0e9d2vjctfyh186shaztavnht
LMG out+0(FP), R1, R4 // R1=out, R2=m, R3=mlen, R4=key
VZERO V0 // c
// load EX0, EX1 and EX2
MOVD $·constants<>(SB), R5
VLM (R5), EX0, EX2 // c
// setup r
VL (R4), T_0
MOVD $·keyMask<>(SB), R6
VL (R6), T_1
VN T_0, T_1, T_0
VZERO T_2 // limbs for r
VZERO T_3
VZERO T_4
EXPACC2(T_0, T_2, T_3, T_4, T_1, T_5, T_7)
// T_2, T_3, T_4: [0, r]
// setup r*20
VLEIG $0, $0, T_0
VLEIG $1, $20, T_0 // T_0: [0, 20]
VZERO T_5
VZERO T_6
VMSLG T_0, T_3, T_5, T_5
VMSLG T_0, T_4, T_6, T_6
// store r for final block in GR
VLGVG $1, T_2, RSAVE_0 // c
VLGVG $1, T_3, RSAVE_1 // c
VLGVG $1, T_4, RSAVE_2 // c
VLGVG $1, T_5, R5SAVE_1 // c
VLGVG $1, T_6, R5SAVE_2 // c
// initialize h
VZERO H0_0
VZERO H1_0
VZERO H2_0
VZERO H0_1
VZERO H1_1
VZERO H2_1
// initialize pointer for reduce constants
MOVD $·reduce<>(SB), R12
// calculate r**2 and 20*(r**2)
VZERO R_0
VZERO R_1
VZERO R_2
SQUARE(T_2, T_3, T_4, T_6, R_0, R_1, R_2, T_1, T_5, T_7)
REDUCE2(R_0, R_1, R_2, M0, M1, M2, M3, M4, R5_1, R5_2, M5, T_1)
VZERO R5_1
VZERO R5_2
VMSLG T_0, R_1, R5_1, R5_1
VMSLG T_0, R_2, R5_2, R5_2
// skip r**4 calculation if 3 blocks or less
CMPBLE R3, $48, b4
// calculate r**4 and 20*(r**4)
VZERO T_8
VZERO T_9
VZERO T_10
SQUARE(R_0, R_1, R_2, R5_2, T_8, T_9, T_10, T_1, T_5, T_7)
REDUCE2(T_8, T_9, T_10, M0, M1, M2, M3, M4, T_2, T_3, M5, T_1)
VZERO T_2
VZERO T_3
VMSLG T_0, T_9, T_2, T_2
VMSLG T_0, T_10, T_3, T_3
// put r**2 to the right and r**4 to the left of R_0, R_1, R_2
VSLDB $8, T_8, T_8, T_8
VSLDB $8, T_9, T_9, T_9
VSLDB $8, T_10, T_10, T_10
VSLDB $8, T_2, T_2, T_2
VSLDB $8, T_3, T_3, T_3
VO T_8, R_0, R_0
VO T_9, R_1, R_1
VO T_10, R_2, R_2
VO T_2, R5_1, R5_1
VO T_3, R5_2, R5_2
CMPBLE R3, $80, load // less than or equal to 5 blocks in message
// 6(or 5+1) blocks
SUB $81, R3
VLM (R2), M0, M4
VLL R3, 80(R2), M5
ADD $1, R3
MOVBZ $1, R0
CMPBGE R3, $16, 2(PC)
VLVGB R3, R0, M5
MOVD $96(R2), R2
EXPACC(M0, M1, H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_0, T_1, T_2, T_3)
EXPACC(M2, M3, H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_0, T_1, T_2, T_3)
VLEIB $2, $1, H2_0
VLEIB $2, $1, H2_1
VLEIB $10, $1, H2_0
VLEIB $10, $1, H2_1
VZERO M0
VZERO M1
VZERO M2
VZERO M3
VZERO T_4
VZERO T_10
EXPACC(M4, M5, M0, M1, M2, M3, T_4, T_10, T_0, T_1, T_2, T_3)
VLR T_4, M4
VLEIB $10, $1, M2
CMPBLT R3, $16, 2(PC)
VLEIB $10, $1, T_10
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, T_10, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
REDUCE(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_10, M0, M1, M2, M3, M4, T_4, T_5, T_2, T_7, T_8, T_9)
VMRHG V0, H0_1, H0_0
VMRHG V0, H1_1, H1_0
VMRHG V0, H2_1, H2_0
VMRLG V0, H0_1, H0_1
VMRLG V0, H1_1, H1_1
VMRLG V0, H2_1, H2_1
SUB $16, R3
CMPBLE R3, $0, square
load:
// load EX0, EX1 and EX2
MOVD $·c<>(SB), R5
VLM (R5), EX0, EX2
loop:
CMPBLE R3, $64, add // b4 // last 4 or less blocks left
// next 4 full blocks
VLM (R2), M2, M5
SUB $64, R3
MOVD $64(R2), R2
REDUCE(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_10, M0, M1, T_0, T_1, T_3, T_4, T_5, T_2, T_7, T_8, T_9)
// expacc in-lined to create [m2, m3] limbs
VGBM $0x3f3f, T_0 // 44 bit clear mask
VGBM $0x1f1f, T_1 // 40 bit clear mask
VPERM M2, M3, EX0, T_3
VESRLG $4, T_0, T_0 // 44 bit clear mask ready
VPERM M2, M3, EX1, T_4
VPERM M2, M3, EX2, T_5
VN T_0, T_3, T_3
VESRLG $4, T_4, T_4
VN T_1, T_5, T_5
VN T_0, T_4, T_4
VMRHG H0_1, T_3, H0_0
VMRHG H1_1, T_4, H1_0
VMRHG H2_1, T_5, H2_0
VMRLG H0_1, T_3, H0_1
VMRLG H1_1, T_4, H1_1
VMRLG H2_1, T_5, H2_1
VLEIB $10, $1, H2_0
VLEIB $10, $1, H2_1
VPERM M4, M5, EX0, T_3
VPERM M4, M5, EX1, T_4
VPERM M4, M5, EX2, T_5
VN T_0, T_3, T_3
VESRLG $4, T_4, T_4
VN T_1, T_5, T_5
VN T_0, T_4, T_4
VMRHG V0, T_3, M0
VMRHG V0, T_4, M1
VMRHG V0, T_5, M2
VMRLG V0, T_3, M3
VMRLG V0, T_4, M4
VMRLG V0, T_5, M5
VLEIB $10, $1, M2
VLEIB $10, $1, M5
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
CMPBNE R3, $0, loop
REDUCE(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_10, M0, M1, M3, M4, M5, T_4, T_5, T_2, T_7, T_8, T_9)
VMRHG V0, H0_1, H0_0
VMRHG V0, H1_1, H1_0
VMRHG V0, H2_1, H2_0
VMRLG V0, H0_1, H0_1
VMRLG V0, H1_1, H1_1
VMRLG V0, H2_1, H2_1
// load EX0, EX1, EX2
MOVD $·constants<>(SB), R5
VLM (R5), EX0, EX2
// sum vectors
VAQ H0_0, H0_1, H0_0
VAQ H1_0, H1_1, H1_0
VAQ H2_0, H2_1, H2_0
// h may be >= 2*(2**130-5) so we need to reduce it again
// M0...M4 are used as temps here
REDUCE2(H0_0, H1_0, H2_0, M0, M1, M2, M3, M4, T_9, T_10, H0_1, M5)
next: // carry h1->h2
VLEIB $7, $0x28, T_1
VREPIB $4, T_2
VGBM $0x003F, T_3
VESRLG $4, T_3
// byte shift
VSRLB T_1, H1_0, T_4
// bit shift
VSRL T_2, T_4, T_4
// clear h1 carry bits
VN T_3, H1_0, H1_0
// add carry
VAQ T_4, H2_0, H2_0
// h is now < 2*(2**130-5)
// pack h into h1 (hi) and h0 (lo)
PACK(H0_0, H1_0, H2_0)
// if h > 2**130-5 then h -= 2**130-5
MOD(H0_0, H1_0, T_0, T_1, T_2)
// h += s
MOVD $·bswapMask<>(SB), R5
VL (R5), T_1
VL 16(R4), T_0
VPERM T_0, T_0, T_1, T_0 // reverse bytes (to big)
VAQ T_0, H0_0, H0_0
VPERM H0_0, H0_0, T_1, H0_0 // reverse bytes (to little)
VST H0_0, (R1)
RET
add:
// load EX0, EX1, EX2
MOVD $·constants<>(SB), R5
VLM (R5), EX0, EX2
REDUCE(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_10, M0, M1, M3, M4, M5, T_4, T_5, T_2, T_7, T_8, T_9)
VMRHG V0, H0_1, H0_0
VMRHG V0, H1_1, H1_0
VMRHG V0, H2_1, H2_0
VMRLG V0, H0_1, H0_1
VMRLG V0, H1_1, H1_1
VMRLG V0, H2_1, H2_1
CMPBLE R3, $64, b4
b4:
CMPBLE R3, $48, b3 // 3 blocks or less
// 4(3+1) blocks remaining
SUB $49, R3
VLM (R2), M0, M2
VLL R3, 48(R2), M3
ADD $1, R3
MOVBZ $1, R0
CMPBEQ R3, $16, 2(PC)
VLVGB R3, R0, M3
MOVD $64(R2), R2
EXPACC(M0, M1, H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_0, T_1, T_2, T_3)
VLEIB $10, $1, H2_0
VLEIB $10, $1, H2_1
VZERO M0
VZERO M1
VZERO M4
VZERO M5
VZERO T_4
VZERO T_10
EXPACC(M2, M3, M0, M1, M4, M5, T_4, T_10, T_0, T_1, T_2, T_3)
VLR T_4, M2
VLEIB $10, $1, M4
CMPBNE R3, $16, 2(PC)
VLEIB $10, $1, T_10
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M4, M5, M2, T_10, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
REDUCE(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_10, M0, M1, M3, M4, M5, T_4, T_5, T_2, T_7, T_8, T_9)
VMRHG V0, H0_1, H0_0
VMRHG V0, H1_1, H1_0
VMRHG V0, H2_1, H2_0
VMRLG V0, H0_1, H0_1
VMRLG V0, H1_1, H1_1
VMRLG V0, H2_1, H2_1
SUB $16, R3
CMPBLE R3, $0, square // this condition must always hold true!
b3:
CMPBLE R3, $32, b2
// 3 blocks remaining
// setup [r²,r]
VSLDB $8, R_0, R_0, R_0
VSLDB $8, R_1, R_1, R_1
VSLDB $8, R_2, R_2, R_2
VSLDB $8, R5_1, R5_1, R5_1
VSLDB $8, R5_2, R5_2, R5_2
VLVGG $1, RSAVE_0, R_0
VLVGG $1, RSAVE_1, R_1
VLVGG $1, RSAVE_2, R_2
VLVGG $1, R5SAVE_1, R5_1
VLVGG $1, R5SAVE_2, R5_2
// setup [h0, h1]
VSLDB $8, H0_0, H0_0, H0_0
VSLDB $8, H1_0, H1_0, H1_0
VSLDB $8, H2_0, H2_0, H2_0
VO H0_1, H0_0, H0_0
VO H1_1, H1_0, H1_0
VO H2_1, H2_0, H2_0
VZERO H0_1
VZERO H1_1
VZERO H2_1
VZERO M0
VZERO M1
VZERO M2
VZERO M3
VZERO M4
VZERO M5
// H*[r**2, r]
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
REDUCE2(H0_0, H1_0, H2_0, M0, M1, M2, M3, M4, H0_1, H1_1, T_10, M5)
SUB $33, R3
VLM (R2), M0, M1
VLL R3, 32(R2), M2
ADD $1, R3
MOVBZ $1, R0
CMPBEQ R3, $16, 2(PC)
VLVGB R3, R0, M2
// H += m0
VZERO T_1
VZERO T_2
VZERO T_3
EXPACC2(M0, T_1, T_2, T_3, T_4, T_5, T_6)
VLEIB $10, $1, T_3
VAG H0_0, T_1, H0_0
VAG H1_0, T_2, H1_0
VAG H2_0, T_3, H2_0
VZERO M0
VZERO M3
VZERO M4
VZERO M5
VZERO T_10
// (H+m0)*r
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M3, M4, M5, V0, T_10, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
REDUCE2(H0_0, H1_0, H2_0, M0, M3, M4, M5, T_10, H0_1, H1_1, H2_1, T_9)
// H += m1
VZERO V0
VZERO T_1
VZERO T_2
VZERO T_3
EXPACC2(M1, T_1, T_2, T_3, T_4, T_5, T_6)
VLEIB $10, $1, T_3
VAQ H0_0, T_1, H0_0
VAQ H1_0, T_2, H1_0
VAQ H2_0, T_3, H2_0
REDUCE2(H0_0, H1_0, H2_0, M0, M3, M4, M5, T_9, H0_1, H1_1, H2_1, T_10)
// [H, m2] * [r**2, r]
EXPACC2(M2, H0_0, H1_0, H2_0, T_1, T_2, T_3)
CMPBNE R3, $16, 2(PC)
VLEIB $10, $1, H2_0
VZERO M0
VZERO M1
VZERO M2
VZERO M3
VZERO M4
VZERO M5
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
REDUCE2(H0_0, H1_0, H2_0, M0, M1, M2, M3, M4, H0_1, H1_1, M5, T_10)
SUB $16, R3
CMPBLE R3, $0, next // this condition must always hold true!
b2:
CMPBLE R3, $16, b1
// 2 blocks remaining
// setup [r²,r]
VSLDB $8, R_0, R_0, R_0
VSLDB $8, R_1, R_1, R_1
VSLDB $8, R_2, R_2, R_2
VSLDB $8, R5_1, R5_1, R5_1
VSLDB $8, R5_2, R5_2, R5_2
VLVGG $1, RSAVE_0, R_0
VLVGG $1, RSAVE_1, R_1
VLVGG $1, RSAVE_2, R_2
VLVGG $1, R5SAVE_1, R5_1
VLVGG $1, R5SAVE_2, R5_2
// setup [h0, h1]
VSLDB $8, H0_0, H0_0, H0_0
VSLDB $8, H1_0, H1_0, H1_0
VSLDB $8, H2_0, H2_0, H2_0
VO H0_1, H0_0, H0_0
VO H1_1, H1_0, H1_0
VO H2_1, H2_0, H2_0
VZERO H0_1
VZERO H1_1
VZERO H2_1
VZERO M0
VZERO M1
VZERO M2
VZERO M3
VZERO M4
VZERO M5
// H*[r**2, r]
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
REDUCE(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_10, M0, M1, M2, M3, M4, T_4, T_5, T_2, T_7, T_8, T_9)
VMRHG V0, H0_1, H0_0
VMRHG V0, H1_1, H1_0
VMRHG V0, H2_1, H2_0
VMRLG V0, H0_1, H0_1
VMRLG V0, H1_1, H1_1
VMRLG V0, H2_1, H2_1
// move h to the left and 0s at the right
VSLDB $8, H0_0, H0_0, H0_0
VSLDB $8, H1_0, H1_0, H1_0
VSLDB $8, H2_0, H2_0, H2_0
// get message blocks and append 1 to start
SUB $17, R3
VL (R2), M0
VLL R3, 16(R2), M1
ADD $1, R3
MOVBZ $1, R0
CMPBEQ R3, $16, 2(PC)
VLVGB R3, R0, M1
VZERO T_6
VZERO T_7
VZERO T_8
EXPACC2(M0, T_6, T_7, T_8, T_1, T_2, T_3)
EXPACC2(M1, T_6, T_7, T_8, T_1, T_2, T_3)
VLEIB $2, $1, T_8
CMPBNE R3, $16, 2(PC)
VLEIB $10, $1, T_8
// add [m0, m1] to h
VAG H0_0, T_6, H0_0
VAG H1_0, T_7, H1_0
VAG H2_0, T_8, H2_0
VZERO M2
VZERO M3
VZERO M4
VZERO M5
VZERO T_10
VZERO M0
// at this point R_0 .. R5_2 look like [r**2, r]
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M2, M3, M4, M5, T_10, M0, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
REDUCE2(H0_0, H1_0, H2_0, M2, M3, M4, M5, T_9, H0_1, H1_1, H2_1, T_10)
SUB $16, R3, R3
CMPBLE R3, $0, next
b1:
CMPBLE R3, $0, next
// 1 block remaining
// setup [r²,r]
VSLDB $8, R_0, R_0, R_0
VSLDB $8, R_1, R_1, R_1
VSLDB $8, R_2, R_2, R_2
VSLDB $8, R5_1, R5_1, R5_1
VSLDB $8, R5_2, R5_2, R5_2
VLVGG $1, RSAVE_0, R_0
VLVGG $1, RSAVE_1, R_1
VLVGG $1, RSAVE_2, R_2
VLVGG $1, R5SAVE_1, R5_1
VLVGG $1, R5SAVE_2, R5_2
// setup [h0, h1]
VSLDB $8, H0_0, H0_0, H0_0
VSLDB $8, H1_0, H1_0, H1_0
VSLDB $8, H2_0, H2_0, H2_0
VO H0_1, H0_0, H0_0
VO H1_1, H1_0, H1_0
VO H2_1, H2_0, H2_0
VZERO H0_1
VZERO H1_1
VZERO H2_1
VZERO M0
VZERO M1
VZERO M2
VZERO M3
VZERO M4
VZERO M5
// H*[r**2, r]
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
REDUCE2(H0_0, H1_0, H2_0, M0, M1, M2, M3, M4, T_9, T_10, H0_1, M5)
// set up [0, m0] limbs
SUB $1, R3
VLL R3, (R2), M0
ADD $1, R3
MOVBZ $1, R0
CMPBEQ R3, $16, 2(PC)
VLVGB R3, R0, M0
VZERO T_1
VZERO T_2
VZERO T_3
EXPACC2(M0, T_1, T_2, T_3, T_4, T_5, T_6)// limbs: [0, m]
CMPBNE R3, $16, 2(PC)
VLEIB $10, $1, T_3
// h+m0
VAQ H0_0, T_1, H0_0
VAQ H1_0, T_2, H1_0
VAQ H2_0, T_3, H2_0
VZERO M0
VZERO M1
VZERO M2
VZERO M3
VZERO M4
VZERO M5
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
REDUCE2(H0_0, H1_0, H2_0, M0, M1, M2, M3, M4, T_9, T_10, H0_1, M5)
BR next
square:
// setup [r²,r]
VSLDB $8, R_0, R_0, R_0
VSLDB $8, R_1, R_1, R_1
VSLDB $8, R_2, R_2, R_2
VSLDB $8, R5_1, R5_1, R5_1
VSLDB $8, R5_2, R5_2, R5_2
VLVGG $1, RSAVE_0, R_0
VLVGG $1, RSAVE_1, R_1
VLVGG $1, RSAVE_2, R_2
VLVGG $1, R5SAVE_1, R5_1
VLVGG $1, R5SAVE_2, R5_2
// setup [h0, h1]
VSLDB $8, H0_0, H0_0, H0_0
VSLDB $8, H1_0, H1_0, H1_0
VSLDB $8, H2_0, H2_0, H2_0
VO H0_1, H0_0, H0_0
VO H1_1, H1_0, H1_0
VO H2_1, H2_0, H2_0
VZERO H0_1
VZERO H1_1
VZERO H2_1
VZERO M0
VZERO M1
VZERO M2
VZERO M3
VZERO M4
VZERO M5
// (h0*r**2) + (h1*r)
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
REDUCE2(H0_0, H1_0, H2_0, M0, M1, M2, M3, M4, T_9, T_10, H0_1, M5)
BR next