puma-plus-core 0.1.0

data/go/vendor/golang.org/x/crypto/chacha20/chacha_s390x.s

@@ -0,0 +1,224 @@
+// 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.
+
+//go:build gc && !purego
+
+#include "go_asm.h"
+#include "textflag.h"
+
+// This is an implementation of the ChaCha20 encryption algorithm as
+// specified in RFC 7539. It uses vector instructions to compute
+// 4 keystream blocks in parallel (256 bytes) which are then XORed
+// with the bytes in the input slice.
+
+GLOBL ·constants<>(SB), RODATA|NOPTR, $32
+// BSWAP: swap bytes in each 4-byte element
+DATA ·constants<>+0x00(SB)/4, $0x03020100
+DATA ·constants<>+0x04(SB)/4, $0x07060504
+DATA ·constants<>+0x08(SB)/4, $0x0b0a0908
+DATA ·constants<>+0x0c(SB)/4, $0x0f0e0d0c
+// J0: [j0, j1, j2, j3]
+DATA ·constants<>+0x10(SB)/4, $0x61707865
+DATA ·constants<>+0x14(SB)/4, $0x3320646e
+DATA ·constants<>+0x18(SB)/4, $0x79622d32
+DATA ·constants<>+0x1c(SB)/4, $0x6b206574
+
+#define BSWAP V5
+#define J0    V6
+#define KEY0  V7
+#define KEY1  V8
+#define NONCE V9
+#define CTR   V10
+#define M0    V11
+#define M1    V12
+#define M2    V13
+#define M3    V14
+#define INC   V15
+#define X0    V16
+#define X1    V17
+#define X2    V18
+#define X3    V19
+#define X4    V20
+#define X5    V21
+#define X6    V22
+#define X7    V23
+#define X8    V24
+#define X9    V25
+#define X10   V26
+#define X11   V27
+#define X12   V28
+#define X13   V29
+#define X14   V30
+#define X15   V31
+
+#define NUM_ROUNDS 20
+
+#define ROUND4(a0, a1, a2, a3, b0, b1, b2, b3, c0, c1, c2, c3, d0, d1, d2, d3) \
+	VAF    a1, a0, a0  \
+	VAF    b1, b0, b0  \
+	VAF    c1, c0, c0  \
+	VAF    d1, d0, d0  \
+	VX     a0, a2, a2  \
+	VX     b0, b2, b2  \
+	VX     c0, c2, c2  \
+	VX     d0, d2, d2  \
+	VERLLF $16, a2, a2 \
+	VERLLF $16, b2, b2 \
+	VERLLF $16, c2, c2 \
+	VERLLF $16, d2, d2 \
+	VAF    a2, a3, a3  \
+	VAF    b2, b3, b3  \
+	VAF    c2, c3, c3  \
+	VAF    d2, d3, d3  \
+	VX     a3, a1, a1  \
+	VX     b3, b1, b1  \
+	VX     c3, c1, c1  \
+	VX     d3, d1, d1  \
+	VERLLF $12, a1, a1 \
+	VERLLF $12, b1, b1 \
+	VERLLF $12, c1, c1 \
+	VERLLF $12, d1, d1 \
+	VAF    a1, a0, a0  \
+	VAF    b1, b0, b0  \
+	VAF    c1, c0, c0  \
+	VAF    d1, d0, d0  \
+	VX     a0, a2, a2  \
+	VX     b0, b2, b2  \
+	VX     c0, c2, c2  \
+	VX     d0, d2, d2  \
+	VERLLF $8, a2, a2  \
+	VERLLF $8, b2, b2  \
+	VERLLF $8, c2, c2  \
+	VERLLF $8, d2, d2  \
+	VAF    a2, a3, a3  \
+	VAF    b2, b3, b3  \
+	VAF    c2, c3, c3  \
+	VAF    d2, d3, d3  \
+	VX     a3, a1, a1  \
+	VX     b3, b1, b1  \
+	VX     c3, c1, c1  \
+	VX     d3, d1, d1  \
+	VERLLF $7, a1, a1  \
+	VERLLF $7, b1, b1  \
+	VERLLF $7, c1, c1  \
+	VERLLF $7, d1, d1
+
+#define PERMUTE(mask, v0, v1, v2, v3) \
+	VPERM v0, v0, mask, v0 \
+	VPERM v1, v1, mask, v1 \
+	VPERM v2, v2, mask, v2 \
+	VPERM v3, v3, mask, v3
+
+#define ADDV(x, v0, v1, v2, v3) \
+	VAF x, v0, v0 \
+	VAF x, v1, v1 \
+	VAF x, v2, v2 \
+	VAF x, v3, v3
+
+#define XORV(off, dst, src, v0, v1, v2, v3) \
+	VLM  off(src), M0, M3          \
+	PERMUTE(BSWAP, v0, v1, v2, v3) \
+	VX   v0, M0, M0                \
+	VX   v1, M1, M1                \
+	VX   v2, M2, M2                \
+	VX   v3, M3, M3                \
+	VSTM M0, M3, off(dst)
+
+#define SHUFFLE(a, b, c, d, t, u, v, w) \
+	VMRHF a, c, t \ // t = {a[0], c[0], a[1], c[1]}
+	VMRHF b, d, u \ // u = {b[0], d[0], b[1], d[1]}
+	VMRLF a, c, v \ // v = {a[2], c[2], a[3], c[3]}
+	VMRLF b, d, w \ // w = {b[2], d[2], b[3], d[3]}
+	VMRHF t, u, a \ // a = {a[0], b[0], c[0], d[0]}
+	VMRLF t, u, b \ // b = {a[1], b[1], c[1], d[1]}
+	VMRHF v, w, c \ // c = {a[2], b[2], c[2], d[2]}
+	VMRLF v, w, d // d = {a[3], b[3], c[3], d[3]}
+
+// func xorKeyStreamVX(dst, src []byte, key *[8]uint32, nonce *[3]uint32, counter *uint32)
+TEXT ·xorKeyStreamVX(SB), NOSPLIT, $0
+	MOVD $·constants<>(SB), R1
+	MOVD dst+0(FP), R2         // R2=&dst[0]
+	LMG  src+24(FP), R3, R4    // R3=&src[0] R4=len(src)
+	MOVD key+48(FP), R5        // R5=key
+	MOVD nonce+56(FP), R6      // R6=nonce
+	MOVD counter+64(FP), R7    // R7=counter
+
+	// load BSWAP and J0
+	VLM (R1), BSWAP, J0
+
+	// setup
+	MOVD  $95, R0
+	VLM   (R5), KEY0, KEY1
+	VLL   R0, (R6), NONCE
+	VZERO M0
+	VLEIB $7, $32, M0
+	VSRLB M0, NONCE, NONCE
+
+	// initialize counter values
+	VLREPF (R7), CTR
+	VZERO  INC
+	VLEIF  $1, $1, INC
+	VLEIF  $2, $2, INC
+	VLEIF  $3, $3, INC
+	VAF    INC, CTR, CTR
+	VREPIF $4, INC
+
+chacha:
+	VREPF $0, J0, X0
+	VREPF $1, J0, X1
+	VREPF $2, J0, X2
+	VREPF $3, J0, X3
+	VREPF $0, KEY0, X4
+	VREPF $1, KEY0, X5
+	VREPF $2, KEY0, X6
+	VREPF $3, KEY0, X7
+	VREPF $0, KEY1, X8
+	VREPF $1, KEY1, X9
+	VREPF $2, KEY1, X10
+	VREPF $3, KEY1, X11
+	VLR   CTR, X12
+	VREPF $1, NONCE, X13
+	VREPF $2, NONCE, X14
+	VREPF $3, NONCE, X15
+
+	MOVD $(NUM_ROUNDS/2), R1
+
+loop:
+	ROUND4(X0, X4, X12,  X8, X1, X5, X13,  X9, X2, X6, X14, X10, X3, X7, X15, X11)
+	ROUND4(X0, X5, X15, X10, X1, X6, X12, X11, X2, X7, X13, X8,  X3, X4, X14, X9)
+
+	ADD $-1, R1
+	BNE loop
+
+	// decrement length
+	ADD $-256, R4
+
+	// rearrange vectors
+	SHUFFLE(X0, X1, X2, X3, M0, M1, M2, M3)
+	ADDV(J0, X0, X1, X2, X3)
+	SHUFFLE(X4, X5, X6, X7, M0, M1, M2, M3)
+	ADDV(KEY0, X4, X5, X6, X7)
+	SHUFFLE(X8, X9, X10, X11, M0, M1, M2, M3)
+	ADDV(KEY1, X8, X9, X10, X11)
+	VAF CTR, X12, X12
+	SHUFFLE(X12, X13, X14, X15, M0, M1, M2, M3)
+	ADDV(NONCE, X12, X13, X14, X15)
+
+	// increment counters
+	VAF INC, CTR, CTR
+
+	// xor keystream with plaintext
+	XORV(0*64, R2, R3, X0, X4,  X8, X12)
+	XORV(1*64, R2, R3, X1, X5,  X9, X13)
+	XORV(2*64, R2, R3, X2, X6, X10, X14)
+	XORV(3*64, R2, R3, X3, X7, X11, X15)
+
+	// increment pointers
+	MOVD $256(R2), R2
+	MOVD $256(R3), R3
+
+	CMPBNE  R4, $0, chacha
+
+	VSTEF $0, CTR, (R7)
+	RET

data/go/vendor/golang.org/x/crypto/chacha20/xor.go

@@ -0,0 +1,42 @@
+// Copyright 2018 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found src the LICENSE file.
+
+package chacha20
+
+import "runtime"
+
+// Platforms that have fast unaligned 32-bit little endian accesses.
+const unaligned = runtime.GOARCH == "386" ||
+	runtime.GOARCH == "amd64" ||
+	runtime.GOARCH == "arm64" ||
+	runtime.GOARCH == "ppc64le" ||
+	runtime.GOARCH == "s390x"
+
+// addXor reads a little endian uint32 from src, XORs it with (a + b) and
+// places the result in little endian byte order in dst.
+func addXor(dst, src []byte, a, b uint32) {
+	_, _ = src[3], dst[3] // bounds check elimination hint
+	if unaligned {
+		// The compiler should optimize this code into
+		// 32-bit unaligned little endian loads and stores.
+		// TODO: delete once the compiler does a reliably
+		// good job with the generic code below.
+		// See issue #25111 for more details.
+		v := uint32(src[0])
+		v |= uint32(src[1]) << 8
+		v |= uint32(src[2]) << 16
+		v |= uint32(src[3]) << 24
+		v ^= a + b
+		dst[0] = byte(v)
+		dst[1] = byte(v >> 8)
+		dst[2] = byte(v >> 16)
+		dst[3] = byte(v >> 24)
+	} else {
+		a += b
+		dst[0] = src[0] ^ byte(a)
+		dst[1] = src[1] ^ byte(a>>8)
+		dst[2] = src[2] ^ byte(a>>16)
+		dst[3] = src[3] ^ byte(a>>24)
+	}
+}

data/go/vendor/golang.org/x/crypto/chacha20poly1305/chacha20poly1305.go

@@ -0,0 +1,101 @@
+// Copyright 2016 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 chacha20poly1305 implements the ChaCha20-Poly1305 AEAD and its
+// extended nonce variant XChaCha20-Poly1305, as specified in RFC 8439 and
+// draft-irtf-cfrg-xchacha-01.
+package chacha20poly1305
+
+import (
+	"crypto/cipher"
+	"errors"
+)
+
+const (
+	// KeySize is the size of the key used by this AEAD, in bytes.
+	KeySize = 32
+
+	// NonceSize is the size of the nonce used with the standard variant of this
+	// AEAD, in bytes.
+	//
+	// Note that this is too short to be safely generated at random if the same
+	// key is reused more than 2³² times.
+	NonceSize = 12
+
+	// NonceSizeX is the size of the nonce used with the XChaCha20-Poly1305
+	// variant of this AEAD, in bytes.
+	NonceSizeX = 24
+
+	// Overhead is the size of the Poly1305 authentication tag, and the
+	// difference between a ciphertext length and its plaintext.
+	Overhead = 16
+)
+
+type chacha20poly1305 struct {
+	key [KeySize]byte
+}
+
+// New returns a ChaCha20-Poly1305 AEAD that uses the given 256-bit key.
+func New(key []byte) (cipher.AEAD, error) {
+	if fips140Enforced() {
+		return nil, errors.New("chacha20poly1305: use of ChaCha20Poly1305 is not allowed in FIPS 140-only mode")
+	}
+	if len(key) != KeySize {
+		return nil, errors.New("chacha20poly1305: bad key length")
+	}
+	ret := new(chacha20poly1305)
+	copy(ret.key[:], key)
+	return ret, nil
+}
+
+func (c *chacha20poly1305) NonceSize() int {
+	return NonceSize
+}
+
+func (c *chacha20poly1305) Overhead() int {
+	return Overhead
+}
+
+func (c *chacha20poly1305) Seal(dst, nonce, plaintext, additionalData []byte) []byte {
+	if len(nonce) != NonceSize {
+		panic("chacha20poly1305: bad nonce length passed to Seal")
+	}
+
+	if uint64(len(plaintext)) > (1<<38)-64 {
+		panic("chacha20poly1305: plaintext too large")
+	}
+
+	return c.seal(dst, nonce, plaintext, additionalData)
+}
+
+var errOpen = errors.New("chacha20poly1305: message authentication failed")
+
+func (c *chacha20poly1305) Open(dst, nonce, ciphertext, additionalData []byte) ([]byte, error) {
+	if len(nonce) != NonceSize {
+		panic("chacha20poly1305: bad nonce length passed to Open")
+	}
+	if len(ciphertext) < 16 {
+		return nil, errOpen
+	}
+	if uint64(len(ciphertext)) > (1<<38)-48 {
+		panic("chacha20poly1305: ciphertext too large")
+	}
+
+	return c.open(dst, nonce, ciphertext, additionalData)
+}
+
+// sliceForAppend takes a slice and a requested number of bytes. It returns a
+// slice with the contents of the given slice followed by that many bytes and a
+// second slice that aliases into it and contains only the extra bytes. If the
+// original slice has sufficient capacity then no allocation is performed.
+func sliceForAppend(in []byte, n int) (head, tail []byte) {
+	if total := len(in) + n; cap(in) >= total {
+		head = in[:total]
+	} else {
+		head = make([]byte, total)
+		copy(head, in)
+	}
+	tail = head[len(in):]
+	return
+}

data/go/vendor/golang.org/x/crypto/chacha20poly1305/chacha20poly1305_amd64.go

@@ -0,0 +1,92 @@
+// Copyright 2016 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.
+
+//go:build gc && !purego
+
+package chacha20poly1305
+
+import (
+	"encoding/binary"
+
+	"golang.org/x/crypto/internal/alias"
+	"golang.org/x/sys/cpu"
+)
+
+//go:noescape
+func chacha20Poly1305Open(dst []byte, key []uint32, src, ad []byte) bool
+
+//go:noescape
+func chacha20Poly1305Seal(dst []byte, key []uint32, src, ad []byte)
+
+var (
+	useAVX2 = cpu.X86.HasSSSE3 && cpu.X86.HasAVX2 && cpu.X86.HasBMI2
+)
+
+// setupState writes a ChaCha20 input matrix to state. See
+// https://tools.ietf.org/html/rfc7539#section-2.3.
+func setupState(state *[16]uint32, key *[32]byte, nonce []byte) {
+	state[0] = 0x61707865
+	state[1] = 0x3320646e
+	state[2] = 0x79622d32
+	state[3] = 0x6b206574
+
+	state[4] = binary.LittleEndian.Uint32(key[0:4])
+	state[5] = binary.LittleEndian.Uint32(key[4:8])
+	state[6] = binary.LittleEndian.Uint32(key[8:12])
+	state[7] = binary.LittleEndian.Uint32(key[12:16])
+	state[8] = binary.LittleEndian.Uint32(key[16:20])
+	state[9] = binary.LittleEndian.Uint32(key[20:24])
+	state[10] = binary.LittleEndian.Uint32(key[24:28])
+	state[11] = binary.LittleEndian.Uint32(key[28:32])
+
+	state[12] = 0
+	state[13] = binary.LittleEndian.Uint32(nonce[0:4])
+	state[14] = binary.LittleEndian.Uint32(nonce[4:8])
+	state[15] = binary.LittleEndian.Uint32(nonce[8:12])
+}
+
+func (c *chacha20poly1305) seal(dst, nonce, plaintext, additionalData []byte) []byte {
+	if !useAVX2 {
+		return c.sealGeneric(dst, nonce, plaintext, additionalData)
+	}
+
+	var state [16]uint32
+	setupState(&state, &c.key, nonce)
+
+	ret, out := sliceForAppend(dst, len(plaintext)+16)
+	if alias.InexactOverlap(out, plaintext) {
+		panic("chacha20poly1305: invalid buffer overlap of output and input")
+	}
+	if alias.AnyOverlap(out, additionalData) {
+		panic("chacha20poly1305: invalid buffer overlap of output and additional data")
+	}
+	chacha20Poly1305Seal(out[:], state[:], plaintext, additionalData)
+	return ret
+}
+
+func (c *chacha20poly1305) open(dst, nonce, ciphertext, additionalData []byte) ([]byte, error) {
+	if !useAVX2 {
+		return c.openGeneric(dst, nonce, ciphertext, additionalData)
+	}
+
+	var state [16]uint32
+	setupState(&state, &c.key, nonce)
+
+	ciphertext = ciphertext[:len(ciphertext)-16]
+	ret, out := sliceForAppend(dst, len(ciphertext))
+	if alias.InexactOverlap(out, ciphertext) {
+		panic("chacha20poly1305: invalid buffer overlap of output and input")
+	}
+	if alias.AnyOverlap(out, additionalData) {
+		panic("chacha20poly1305: invalid buffer overlap of output and additional data")
+	}
+	if !chacha20Poly1305Open(out, state[:], ciphertext, additionalData) {
+		for i := range out {
+			out[i] = 0
+		}
+		return nil, errOpen
+	}
+
+	return ret, nil
+}