vendor: github.com/klauspost/compress v1.12.3

Remove the replace rule, and use the version as specified by (indirect) dependencies:

full diff: https://github.com/klauspost/compress/compare/v1.11.13...v1.12.3

Signed-off-by: Sebastiaan van Stijn <github@gone.nl>

vendor.mod

@@ -106,6 +106,7 @@ require (
 	github.com/gogo/googleapis v1.4.0 // indirect
 	github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
 	github.com/golang/protobuf v1.5.2 // indirect
+	github.com/golang/snappy v0.0.3 // indirect
 	github.com/google/btree v1.0.1 // indirect
 	github.com/google/certificate-transparency-go v1.0.20 // indirect
 	github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510 // indirect
@@ -166,7 +167,6 @@ replace (
 	github.com/hashicorp/go-multierror => github.com/hashicorp/go-multierror v1.0.0
 	github.com/hashicorp/serf => github.com/hashicorp/serf v0.7.1-0.20160317193612-598c54895cc5
 	github.com/hpcloud/tail => github.com/hpcloud/tail v1.0.0
-	github.com/klauspost/compress => github.com/klauspost/compress v1.11.13
 	github.com/matttproud/golang_protobuf_extensions => github.com/matttproud/golang_protobuf_extensions v1.0.1
 	github.com/onsi/ginkgo => github.com/onsi/ginkgo v1.8.0
 	github.com/onsi/gomega => github.com/onsi/gomega v1.5.0

vendor.sum

@@ -245,6 +245,8 @@ github.com/golang/mock v1.1.1/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfb
 github.com/golang/mock v1.4.3/go.mod h1:UOMv5ysSaYNkG+OFQykRIcU/QvvxJf3p21QfJ2Bt3cw=
 github.com/golang/protobuf v1.3.5 h1:F768QJ1E9tib+q5Sc8MkdJi1RxLTbRcTf8LJV56aRls=
 github.com/golang/protobuf v1.3.5/go.mod h1:6O5/vntMXwX2lRkT1hjjk0nAC1IDOTvTlVgjlRvqsdk=
+github.com/golang/snappy v0.0.3 h1:fHPg5GQYlCeLIPB9BZqMVR5nR9A+IM5zcgeTdjMYmLA=
+github.com/golang/snappy v0.0.3/go.mod h1:/XxbfmMg8lxefKM7IXC3fBNl/7bRcc72aCRzEWrmP2Q=
 github.com/google/btree v0.0.0-20180813153112-4030bb1f1f0c/go.mod h1:lNA+9X1NB3Zf8V7Ke586lFgjr2dZNuvo3lPJSGZ5JPQ=
 github.com/google/btree v1.0.0/go.mod h1:lNA+9X1NB3Zf8V7Ke586lFgjr2dZNuvo3lPJSGZ5JPQ=
 github.com/google/btree v1.0.1 h1:gK4Kx5IaGY9CD5sPJ36FHiBJ6ZXl0kilRiiCj+jdYp4=
@@ -335,8 +337,9 @@ github.com/kisielk/errcheck v1.1.0/go.mod h1:EZBBE59ingxPouuu3KfxchcWSUPOHkagtvW
 github.com/kisielk/errcheck v1.2.0/go.mod h1:/BMXB+zMLi60iA8Vv6Ksmxu/1UDYcXs4uQLJ+jE2L00=
 github.com/kisielk/errcheck v1.5.0/go.mod h1:pFxgyoBC7bSaBwPgfKdkLd5X25qrDl4LWUI2bnpBCr8=
 github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
-github.com/klauspost/compress v1.11.13 h1:eSvu8Tmq6j2psUJqJrLcWH6K3w5Dwc+qipbaA6eVEN4=
 github.com/klauspost/compress v1.11.13/go.mod h1:aoV0uJVorq1K+umq18yTdKaF57EivdYsUV+/s2qKfXs=
+github.com/klauspost/compress v1.12.3 h1:G5AfA94pHPysR56qqrkO2pxEexdDzrpFJ6yt/VqWxVU=
+github.com/klauspost/compress v1.12.3/go.mod h1:8dP1Hq4DHOhN9w426knH3Rhby4rFm6D8eO+e+Dq5Gzg=
 github.com/konsorten/go-windows-terminal-sequences v1.0.1/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
 github.com/konsorten/go-windows-terminal-sequences v1.0.2/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
 github.com/konsorten/go-windows-terminal-sequences v1.0.3/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=

vendor/github.com/klauspost/compress/snappy/AUTHORS → vendor/github.com/golang/snappy/AUTHORS

@@ -8,8 +8,10 @@
 
 # Please keep the list sorted.
 
+Amazon.com, Inc
 Damian Gryski <dgryski@gmail.com>
 Google Inc.
 Jan Mercl <0xjnml@gmail.com>
+Klaus Post <klauspost@gmail.com>
 Rodolfo Carvalho <rhcarvalho@gmail.com>
 Sebastien Binet <seb.binet@gmail.com>

vendor/github.com/klauspost/compress/snappy/CONTRIBUTORS → vendor/github.com/golang/snappy/CONTRIBUTORS

@@ -28,7 +28,9 @@
 
 Damian Gryski <dgryski@gmail.com>
 Jan Mercl <0xjnml@gmail.com>
+Jonathan Swinney <jswinney@amazon.com>
 Kai Backman <kaib@golang.org>
+Klaus Post <klauspost@gmail.com>
 Marc-Antoine Ruel <maruel@chromium.org>
 Nigel Tao <nigeltao@golang.org>
 Rob Pike <r@golang.org>

vendor/github.com/klauspost/compress/snappy/decode.go → vendor/github.com/golang/snappy/decode.go

@@ -52,6 +52,8 @@ const (
 // Otherwise, a newly allocated slice will be returned.
 //
 // The dst and src must not overlap. It is valid to pass a nil dst.
+//
+// Decode handles the Snappy block format, not the Snappy stream format.
 func Decode(dst, src []byte) ([]byte, error) {
 	dLen, s, err := decodedLen(src)
 	if err != nil {
@@ -83,6 +85,8 @@ func NewReader(r io.Reader) *Reader {
 }
 
 // Reader is an io.Reader that can read Snappy-compressed bytes.
+//
+// Reader handles the Snappy stream format, not the Snappy block format.
 type Reader struct {
 	r       io.Reader
 	err     error

vendor/github.com/klauspost/compress/snappy/decode_amd64.s → vendor/github.com/golang/snappy/decode_amd64.s

@@ -184,7 +184,9 @@ tagLit60Plus:
 	// checks. In the asm version, we code it once instead of once per switch case.
 	ADDQ CX, SI
 	SUBQ $58, SI
-	CMPQ SI, R13
+	MOVQ SI, BX
+	SUBQ R11, BX
+	CMPQ BX, R12
 	JA   errCorrupt
 
 	// case x == 60:
@@ -230,7 +232,9 @@ tagCopy4:
 	ADDQ $5, SI
 
 	// if uint(s) > uint(len(src)) { etc }
-	CMPQ SI, R13
+	MOVQ SI, BX
+	SUBQ R11, BX
+	CMPQ BX, R12
 	JA   errCorrupt
 
 	// length = 1 + int(src[s-5])>>2
@@ -247,7 +251,9 @@ tagCopy2:
 	ADDQ $3, SI
 
 	// if uint(s) > uint(len(src)) { etc }
-	CMPQ SI, R13
+	MOVQ SI, BX
+	SUBQ R11, BX
+	CMPQ BX, R12
 	JA   errCorrupt
 
 	// length = 1 + int(src[s-3])>>2
@@ -271,7 +277,9 @@ tagCopy:
 	ADDQ $2, SI
 
 	// if uint(s) > uint(len(src)) { etc }
-	CMPQ SI, R13
+	MOVQ SI, BX
+	SUBQ R11, BX
+	CMPQ BX, R12
 	JA   errCorrupt
 
 	// offset = int(uint32(src[s-2])&0xe0<<3 | uint32(src[s-1]))

vendor/github.com/golang/snappy/decode_arm64.s

@@ -0,0 +1,494 @@
+// Copyright 2020 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 !appengine
+// +build gc
+// +build !noasm
+
+#include "textflag.h"
+
+// The asm code generally follows the pure Go code in decode_other.go, except
+// where marked with a "!!!".
+
+// func decode(dst, src []byte) int
+//
+// All local variables fit into registers. The non-zero stack size is only to
+// spill registers and push args when issuing a CALL. The register allocation:
+//	- R2	scratch
+//	- R3	scratch
+//	- R4	length or x
+//	- R5	offset
+//	- R6	&src[s]
+//	- R7	&dst[d]
+//	+ R8	dst_base
+//	+ R9	dst_len
+//	+ R10	dst_base + dst_len
+//	+ R11	src_base
+//	+ R12	src_len
+//	+ R13	src_base + src_len
+//	- R14	used by doCopy
+//	- R15	used by doCopy
+//
+// The registers R8-R13 (marked with a "+") are set at the start of the
+// function, and after a CALL returns, and are not otherwise modified.
+//
+// The d variable is implicitly R7 - R8,  and len(dst)-d is R10 - R7.
+// The s variable is implicitly R6 - R11, and len(src)-s is R13 - R6.
+TEXT ·decode(SB), NOSPLIT, $56-56
+	// Initialize R6, R7 and R8-R13.
+	MOVD dst_base+0(FP), R8
+	MOVD dst_len+8(FP), R9
+	MOVD R8, R7
+	MOVD R8, R10
+	ADD  R9, R10, R10
+	MOVD src_base+24(FP), R11
+	MOVD src_len+32(FP), R12
+	MOVD R11, R6
+	MOVD R11, R13
+	ADD  R12, R13, R13
+
+loop:
+	// for s < len(src)
+	CMP R13, R6
+	BEQ end
+
+	// R4 = uint32(src[s])
+	//
+	// switch src[s] & 0x03
+	MOVBU (R6), R4
+	MOVW  R4, R3
+	ANDW  $3, R3
+	MOVW  $1, R1
+	CMPW  R1, R3
+	BGE   tagCopy
+
+	// ----------------------------------------
+	// The code below handles literal tags.
+
+	// case tagLiteral:
+	// x := uint32(src[s] >> 2)
+	// switch
+	MOVW $60, R1
+	LSRW $2, R4, R4
+	CMPW R4, R1
+	BLS  tagLit60Plus
+
+	// case x < 60:
+	// s++
+	ADD $1, R6, R6
+
+doLit:
+	// This is the end of the inner "switch", when we have a literal tag.
+	//
+	// We assume that R4 == x and x fits in a uint32, where x is the variable
+	// used in the pure Go decode_other.go code.
+
+	// length = int(x) + 1
+	//
+	// Unlike the pure Go code, we don't need to check if length <= 0 because
+	// R4 can hold 64 bits, so the increment cannot overflow.
+	ADD $1, R4, R4
+
+	// Prepare to check if copying length bytes will run past the end of dst or
+	// src.
+	//
+	// R2 = len(dst) - d
+	// R3 = len(src) - s
+	MOVD R10, R2
+	SUB  R7, R2, R2
+	MOVD R13, R3
+	SUB  R6, R3, R3
+
+	// !!! Try a faster technique for short (16 or fewer bytes) copies.
+	//
+	// if length > 16 || len(dst)-d < 16 || len(src)-s < 16 {
+	//   goto callMemmove // Fall back on calling runtime·memmove.
+	// }
+	//
+	// The C++ snappy code calls this TryFastAppend. It also checks len(src)-s
+	// against 21 instead of 16, because it cannot assume that all of its input
+	// is contiguous in memory and so it needs to leave enough source bytes to
+	// read the next tag without refilling buffers, but Go's Decode assumes
+	// contiguousness (the src argument is a []byte).
+	CMP $16, R4
+	BGT callMemmove
+	CMP $16, R2
+	BLT callMemmove
+	CMP $16, R3
+	BLT callMemmove
+
+	// !!! Implement the copy from src to dst as a 16-byte load and store.
+	// (Decode's documentation says that dst and src must not overlap.)
+	//
+	// This always copies 16 bytes, instead of only length bytes, but that's
+	// OK. If the input is a valid Snappy encoding then subsequent iterations
+	// will fix up the overrun. Otherwise, Decode returns a nil []byte (and a
+	// non-nil error), so the overrun will be ignored.
+	//
+	// Note that on arm64, it is legal and cheap to issue unaligned 8-byte or
+	// 16-byte loads and stores. This technique probably wouldn't be as
+	// effective on architectures that are fussier about alignment.
+	LDP 0(R6), (R14, R15)
+	STP (R14, R15), 0(R7)
+
+	// d += length
+	// s += length
+	ADD R4, R7, R7
+	ADD R4, R6, R6
+	B   loop
+
+callMemmove:
+	// if length > len(dst)-d || length > len(src)-s { etc }
+	CMP R2, R4
+	BGT errCorrupt
+	CMP R3, R4
+	BGT errCorrupt
+
+	// copy(dst[d:], src[s:s+length])
+	//
+	// This means calling runtime·memmove(&dst[d], &src[s], length), so we push
+	// R7, R6 and R4 as arguments. Coincidentally, we also need to spill those
+	// three registers to the stack, to save local variables across the CALL.
+	MOVD R7, 8(RSP)
+	MOVD R6, 16(RSP)
+	MOVD R4, 24(RSP)
+	MOVD R7, 32(RSP)
+	MOVD R6, 40(RSP)
+	MOVD R4, 48(RSP)
+	CALL runtime·memmove(SB)
+
+	// Restore local variables: unspill registers from the stack and
+	// re-calculate R8-R13.
+	MOVD 32(RSP), R7
+	MOVD 40(RSP), R6
+	MOVD 48(RSP), R4
+	MOVD dst_base+0(FP), R8
+	MOVD dst_len+8(FP), R9
+	MOVD R8, R10
+	ADD  R9, R10, R10
+	MOVD src_base+24(FP), R11
+	MOVD src_len+32(FP), R12
+	MOVD R11, R13
+	ADD  R12, R13, R13
+
+	// d += length
+	// s += length
+	ADD R4, R7, R7
+	ADD R4, R6, R6
+	B   loop
+
+tagLit60Plus:
+	// !!! This fragment does the
+	//
+	// s += x - 58; if uint(s) > uint(len(src)) { etc }
+	//
+	// checks. In the asm version, we code it once instead of once per switch case.
+	ADD  R4, R6, R6
+	SUB  $58, R6, R6
+	MOVD R6, R3
+	SUB  R11, R3, R3
+	CMP  R12, R3
+	BGT  errCorrupt
+
+	// case x == 60:
+	MOVW $61, R1
+	CMPW R1, R4
+	BEQ  tagLit61
+	BGT  tagLit62Plus
+
+	// x = uint32(src[s-1])
+	MOVBU -1(R6), R4
+	B     doLit
+
+tagLit61:
+	// case x == 61:
+	// x = uint32(src[s-2]) | uint32(src[s-1])<<8
+	MOVHU -2(R6), R4
+	B     doLit
+
+tagLit62Plus:
+	CMPW $62, R4
+	BHI  tagLit63
+
+	// case x == 62:
+	// x = uint32(src[s-3]) | uint32(src[s-2])<<8 | uint32(src[s-1])<<16
+	MOVHU -3(R6), R4
+	MOVBU -1(R6), R3
+	ORR   R3<<16, R4
+	B     doLit
+
+tagLit63:
+	// case x == 63:
+	// x = uint32(src[s-4]) | uint32(src[s-3])<<8 | uint32(src[s-2])<<16 | uint32(src[s-1])<<24
+	MOVWU -4(R6), R4
+	B     doLit
+
+	// The code above handles literal tags.
+	// ----------------------------------------
+	// The code below handles copy tags.
+
+tagCopy4:
+	// case tagCopy4:
+	// s += 5
+	ADD $5, R6, R6
+
+	// if uint(s) > uint(len(src)) { etc }
+	MOVD R6, R3
+	SUB  R11, R3, R3
+	CMP  R12, R3
+	BGT  errCorrupt
+
+	// length = 1 + int(src[s-5])>>2
+	MOVD $1, R1
+	ADD  R4>>2, R1, R4
+
+	// offset = int(uint32(src[s-4]) | uint32(src[s-3])<<8 | uint32(src[s-2])<<16 | uint32(src[s-1])<<24)
+	MOVWU -4(R6), R5
+	B     doCopy
+
+tagCopy2:
+	// case tagCopy2:
+	// s += 3
+	ADD $3, R6, R6
+
+	// if uint(s) > uint(len(src)) { etc }
+	MOVD R6, R3
+	SUB  R11, R3, R3
+	CMP  R12, R3
+	BGT  errCorrupt
+
+	// length = 1 + int(src[s-3])>>2
+	MOVD $1, R1
+	ADD  R4>>2, R1, R4
+
+	// offset = int(uint32(src[s-2]) | uint32(src[s-1])<<8)
+	MOVHU -2(R6), R5
+	B     doCopy
+
+tagCopy:
+	// We have a copy tag. We assume that:
+	//	- R3 == src[s] & 0x03
+	//	- R4 == src[s]
+	CMP $2, R3
+	BEQ tagCopy2
+	BGT tagCopy4
+
+	// case tagCopy1:
+	// s += 2
+	ADD $2, R6, R6
+
+	// if uint(s) > uint(len(src)) { etc }
+	MOVD R6, R3
+	SUB  R11, R3, R3
+	CMP  R12, R3
+	BGT  errCorrupt
+
+	// offset = int(uint32(src[s-2])&0xe0<<3 | uint32(src[s-1]))
+	MOVD  R4, R5
+	AND   $0xe0, R5
+	MOVBU -1(R6), R3
+	ORR   R5<<3, R3, R5
+
+	// length = 4 + int(src[s-2])>>2&0x7
+	MOVD $7, R1
+	AND  R4>>2, R1, R4
+	ADD  $4, R4, R4
+
+doCopy:
+	// This is the end of the outer "switch", when we have a copy tag.
+	//
+	// We assume that:
+	//	- R4 == length && R4 > 0
+	//	- R5 == offset
+
+	// if offset <= 0 { etc }
+	MOVD $0, R1
+	CMP  R1, R5
+	BLE  errCorrupt
+
+	// if d < offset { etc }
+	MOVD R7, R3
+	SUB  R8, R3, R3
+	CMP  R5, R3
+	BLT  errCorrupt
+
+	// if length > len(dst)-d { etc }
+	MOVD R10, R3
+	SUB  R7, R3, R3
+	CMP  R3, R4
+	BGT  errCorrupt
+
+	// forwardCopy(dst[d:d+length], dst[d-offset:]); d += length
+	//
+	// Set:
+	//	- R14 = len(dst)-d
+	//	- R15 = &dst[d-offset]
+	MOVD R10, R14
+	SUB  R7, R14, R14
+	MOVD R7, R15
+	SUB  R5, R15, R15
+
+	// !!! Try a faster technique for short (16 or fewer bytes) forward copies.
+	//
+	// First, try using two 8-byte load/stores, similar to the doLit technique
+	// above. Even if dst[d:d+length] and dst[d-offset:] can overlap, this is
+	// still OK if offset >= 8. Note that this has to be two 8-byte load/stores
+	// and not one 16-byte load/store, and the first store has to be before the
+	// second load, due to the overlap if offset is in the range [8, 16).
+	//
+	// if length > 16 || offset < 8 || len(dst)-d < 16 {
+	//   goto slowForwardCopy
+	// }
+	// copy 16 bytes
+	// d += length
+	CMP  $16, R4
+	BGT  slowForwardCopy
+	CMP  $8, R5
+	BLT  slowForwardCopy
+	CMP  $16, R14
+	BLT  slowForwardCopy
+	MOVD 0(R15), R2
+	MOVD R2, 0(R7)
+	MOVD 8(R15), R3
+	MOVD R3, 8(R7)
+	ADD  R4, R7, R7
+	B    loop
+
+slowForwardCopy:
+	// !!! If the forward copy is longer than 16 bytes, or if offset < 8, we
+	// can still try 8-byte load stores, provided we can overrun up to 10 extra
+	// bytes. As above, the overrun will be fixed up by subsequent iterations
+	// of the outermost loop.
+	//
+	// The C++ snappy code calls this technique IncrementalCopyFastPath. Its
+	// commentary says:
+	//
+	// ----
+	//
+	// The main part of this loop is a simple copy of eight bytes at a time
+	// until we've copied (at least) the requested amount of bytes.  However,
+	// if d and d-offset are less than eight bytes apart (indicating a
+	// repeating pattern of length < 8), we first need to expand the pattern in
+	// order to get the correct results. For instance, if the buffer looks like
+	// this, with the eight-byte <d-offset> and <d> patterns marked as
+	// intervals:
+	//
+	//    abxxxxxxxxxxxx
+	//    [------]           d-offset
+	//      [------]         d
+	//
+	// a single eight-byte copy from <d-offset> to <d> will repeat the pattern
+	// once, after which we can move <d> two bytes without moving <d-offset>:
+	//
+	//    ababxxxxxxxxxx
+	//    [------]           d-offset
+	//        [------]       d
+	//
+	// and repeat the exercise until the two no longer overlap.
+	//
+	// This allows us to do very well in the special case of one single byte
+	// repeated many times, without taking a big hit for more general cases.
+	//
+	// The worst case of extra writing past the end of the match occurs when
+	// offset == 1 and length == 1; the last copy will read from byte positions
+	// [0..7] and write to [4..11], whereas it was only supposed to write to
+	// position 1. Thus, ten excess bytes.
+	//
+	// ----
+	//
+	// That "10 byte overrun" worst case is confirmed by Go's
+	// TestSlowForwardCopyOverrun, which also tests the fixUpSlowForwardCopy
+	// and finishSlowForwardCopy algorithm.
+	//
+	// if length > len(dst)-d-10 {
+	//   goto verySlowForwardCopy
+	// }
+	SUB $10, R14, R14
+	CMP R14, R4
+	BGT verySlowForwardCopy
+
+makeOffsetAtLeast8:
+	// !!! As above, expand the pattern so that offset >= 8 and we can use
+	// 8-byte load/stores.
+	//
+	// for offset < 8 {
+	//   copy 8 bytes from dst[d-offset:] to dst[d:]
+	//   length -= offset
+	//   d      += offset
+	//   offset += offset
+	//   // The two previous lines together means that d-offset, and therefore
+	//   // R15, is unchanged.
+	// }
+	CMP  $8, R5
+	BGE  fixUpSlowForwardCopy
+	MOVD (R15), R3
+	MOVD R3, (R7)
+	SUB  R5, R4, R4
+	ADD  R5, R7, R7
+	ADD  R5, R5, R5
+	B    makeOffsetAtLeast8
+
+fixUpSlowForwardCopy:
+	// !!! Add length (which might be negative now) to d (implied by R7 being
+	// &dst[d]) so that d ends up at the right place when we jump back to the
+	// top of the loop. Before we do that, though, we save R7 to R2 so that, if
+	// length is positive, copying the remaining length bytes will write to the
+	// right place.
+	MOVD R7, R2
+	ADD  R4, R7, R7
+
+finishSlowForwardCopy:
+	// !!! Repeat 8-byte load/stores until length <= 0. Ending with a negative
+	// length means that we overrun, but as above, that will be fixed up by
+	// subsequent iterations of the outermost loop.
+	MOVD $0, R1
+	CMP  R1, R4
+	BLE  loop
+	MOVD (R15), R3
+	MOVD R3, (R2)
+	ADD  $8, R15, R15
+	ADD  $8, R2, R2
+	SUB  $8, R4, R4
+	B    finishSlowForwardCopy
+
+verySlowForwardCopy:
+	// verySlowForwardCopy is a simple implementation of forward copy. In C
+	// parlance, this is a do/while loop instead of a while loop, since we know
+	// that length > 0. In Go syntax:
+	//
+	// for {
+	//   dst[d] = dst[d - offset]
+	//   d++
+	//   length--
+	//   if length == 0 {
+	//     break
+	//   }
+	// }
+	MOVB (R15), R3
+	MOVB R3, (R7)
+	ADD  $1, R15, R15
+	ADD  $1, R7, R7
+	SUB  $1, R4, R4
+	CBNZ R4, verySlowForwardCopy
+	B    loop
+
+	// The code above handles copy tags.
+	// ----------------------------------------
+
+end:
+	// This is the end of the "for s < len(src)".
+	//
+	// if d != len(dst) { etc }
+	CMP R10, R7
+	BNE errCorrupt
+
+	// return 0
+	MOVD $0, ret+48(FP)
+	RET
+
+errCorrupt:
+	// return decodeErrCodeCorrupt
+	MOVD $1, R2
+	MOVD R2, ret+48(FP)
+	RET

vendor/github.com/klauspost/compress/snappy/decode_amd64.go → vendor/github.com/golang/snappy/decode_asm.go

@@ -5,6 +5,7 @@
 // +build !appengine
 // +build gc
 // +build !noasm
+// +build amd64 arm64
 
 package snappy
 

vendor/github.com/klauspost/compress/snappy/decode_other.go → vendor/github.com/golang/snappy/decode_other.go

@@ -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 appengine !gc noasm
+// +build !amd64,!arm64 appengine !gc noasm
 
 package snappy
 
@@ -87,7 +87,7 @@ func decode(dst, src []byte) int {
 		}
 		// Copy from an earlier sub-slice of dst to a later sub-slice.
 		// If no overlap, use the built-in copy:
-		if offset > length {
+		if offset >= length {
 			copy(dst[d:d+length], dst[d-offset:])
 			d += length
 			continue

vendor/github.com/klauspost/compress/snappy/encode.go → vendor/github.com/golang/snappy/encode.go

@@ -15,6 +15,8 @@ import (
 // Otherwise, a newly allocated slice will be returned.
 //
 // The dst and src must not overlap. It is valid to pass a nil dst.
+//
+// Encode handles the Snappy block format, not the Snappy stream format.
 func Encode(dst, src []byte) []byte {
 	if n := MaxEncodedLen(len(src)); n < 0 {
 		panic(ErrTooLarge)
@@ -139,6 +141,8 @@ func NewBufferedWriter(w io.Writer) *Writer {
 }
 
 // Writer is an io.Writer that can write Snappy-compressed bytes.
+//
+// Writer handles the Snappy stream format, not the Snappy block format.
 type Writer struct {
 	w   io.Writer
 	err error

vendor/github.com/golang/snappy/encode_arm64.s

@@ -0,0 +1,722 @@
+// Copyright 2020 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 !appengine
+// +build gc
+// +build !noasm
+
+#include "textflag.h"
+
+// The asm code generally follows the pure Go code in encode_other.go, except
+// where marked with a "!!!".
+
+// ----------------------------------------------------------------------------
+
+// func emitLiteral(dst, lit []byte) int
+//
+// All local variables fit into registers. The register allocation:
+//	- R3	len(lit)
+//	- R4	n
+//	- R6	return value
+//	- R8	&dst[i]
+//	- R10	&lit[0]
+//
+// The 32 bytes of stack space is to call runtime·memmove.
+//
+// The unusual register allocation of local variables, such as R10 for the
+// source pointer, matches the allocation used at the call site in encodeBlock,
+// which makes it easier to manually inline this function.
+TEXT ·emitLiteral(SB), NOSPLIT, $32-56
+	MOVD dst_base+0(FP), R8
+	MOVD lit_base+24(FP), R10
+	MOVD lit_len+32(FP), R3
+	MOVD R3, R6
+	MOVW R3, R4
+	SUBW $1, R4, R4
+
+	CMPW $60, R4
+	BLT  oneByte
+	CMPW $256, R4
+	BLT  twoBytes
+
+threeBytes:
+	MOVD $0xf4, R2
+	MOVB R2, 0(R8)
+	MOVW R4, 1(R8)
+	ADD  $3, R8, R8
+	ADD  $3, R6, R6
+	B    memmove
+
+twoBytes:
+	MOVD $0xf0, R2
+	MOVB R2, 0(R8)
+	MOVB R4, 1(R8)
+	ADD  $2, R8, R8
+	ADD  $2, R6, R6
+	B    memmove
+
+oneByte:
+	LSLW $2, R4, R4
+	MOVB R4, 0(R8)
+	ADD  $1, R8, R8
+	ADD  $1, R6, R6
+
+memmove:
+	MOVD R6, ret+48(FP)
+
+	// copy(dst[i:], lit)
+	//
+	// This means calling runtime·memmove(&dst[i], &lit[0], len(lit)), so we push
+	// R8, R10 and R3 as arguments.
+	MOVD R8, 8(RSP)
+	MOVD R10, 16(RSP)
+	MOVD R3, 24(RSP)
+	CALL runtime·memmove(SB)
+	RET
+
+// ----------------------------------------------------------------------------
+
+// func emitCopy(dst []byte, offset, length int) int
+//
+// All local variables fit into registers. The register allocation:
+//	- R3	length
+//	- R7	&dst[0]
+//	- R8	&dst[i]
+//	- R11	offset
+//
+// The unusual register allocation of local variables, such as R11 for the
+// offset, matches the allocation used at the call site in encodeBlock, which
+// makes it easier to manually inline this function.
+TEXT ·emitCopy(SB), NOSPLIT, $0-48
+	MOVD dst_base+0(FP), R8
+	MOVD R8, R7
+	MOVD offset+24(FP), R11
+	MOVD length+32(FP), R3
+
+loop0:
+	// for length >= 68 { etc }
+	CMPW $68, R3
+	BLT  step1
+
+	// Emit a length 64 copy, encoded as 3 bytes.
+	MOVD $0xfe, R2
+	MOVB R2, 0(R8)
+	MOVW R11, 1(R8)
+	ADD  $3, R8, R8
+	SUB  $64, R3, R3
+	B    loop0
+
+step1:
+	// if length > 64 { etc }
+	CMP $64, R3
+	BLE step2
+
+	// Emit a length 60 copy, encoded as 3 bytes.
+	MOVD $0xee, R2
+	MOVB R2, 0(R8)
+	MOVW R11, 1(R8)
+	ADD  $3, R8, R8
+	SUB  $60, R3, R3
+
+step2:
+	// if length >= 12 || offset >= 2048 { goto step3 }
+	CMP  $12, R3
+	BGE  step3
+	CMPW $2048, R11
+	BGE  step3
+
+	// Emit the remaining copy, encoded as 2 bytes.
+	MOVB R11, 1(R8)
+	LSRW $3, R11, R11
+	AND  $0xe0, R11, R11
+	SUB  $4, R3, R3
+	LSLW $2, R3
+	AND  $0xff, R3, R3
+	ORRW R3, R11, R11
+	ORRW $1, R11, R11
+	MOVB R11, 0(R8)
+	ADD  $2, R8, R8
+
+	// Return the number of bytes written.
+	SUB  R7, R8, R8
+	MOVD R8, ret+40(FP)
+	RET
+
+step3:
+	// Emit the remaining copy, encoded as 3 bytes.
+	SUB  $1, R3, R3
+	AND  $0xff, R3, R3
+	LSLW $2, R3, R3
+	ORRW $2, R3, R3
+	MOVB R3, 0(R8)
+	MOVW R11, 1(R8)
+	ADD  $3, R8, R8
+
+	// Return the number of bytes written.
+	SUB  R7, R8, R8
+	MOVD R8, ret+40(FP)
+	RET
+
+// ----------------------------------------------------------------------------
+
+// func extendMatch(src []byte, i, j int) int
+//
+// All local variables fit into registers. The register allocation:
+//	- R6	&src[0]
+//	- R7	&src[j]
+//	- R13	&src[len(src) - 8]
+//	- R14	&src[len(src)]
+//	- R15	&src[i]
+//
+// The unusual register allocation of local variables, such as R15 for a source
+// pointer, matches the allocation used at the call site in encodeBlock, which
+// makes it easier to manually inline this function.
+TEXT ·extendMatch(SB), NOSPLIT, $0-48
+	MOVD src_base+0(FP), R6
+	MOVD src_len+8(FP), R14
+	MOVD i+24(FP), R15
+	MOVD j+32(FP), R7
+	ADD  R6, R14, R14
+	ADD  R6, R15, R15
+	ADD  R6, R7, R7
+	MOVD R14, R13
+	SUB  $8, R13, R13
+
+cmp8:
+	// As long as we are 8 or more bytes before the end of src, we can load and
+	// compare 8 bytes at a time. If those 8 bytes are equal, repeat.
+	CMP  R13, R7
+	BHI  cmp1
+	MOVD (R15), R3
+	MOVD (R7), R4
+	CMP  R4, R3
+	BNE  bsf
+	ADD  $8, R15, R15
+	ADD  $8, R7, R7
+	B    cmp8
+
+bsf:
+	// If those 8 bytes were not equal, XOR the two 8 byte values, and return
+	// the index of the first byte that differs.
+	// RBIT reverses the bit order, then CLZ counts the leading zeros, the
+	// combination of which finds the least significant bit which is set.
+	// The arm64 architecture is little-endian, and the shift by 3 converts
+	// a bit index to a byte index.
+	EOR  R3, R4, R4
+	RBIT R4, R4
+	CLZ  R4, R4
+	ADD  R4>>3, R7, R7
+
+	// Convert from &src[ret] to ret.
+	SUB  R6, R7, R7
+	MOVD R7, ret+40(FP)
+	RET
+
+cmp1:
+	// In src's tail, compare 1 byte at a time.
+	CMP  R7, R14
+	BLS  extendMatchEnd
+	MOVB (R15), R3
+	MOVB (R7), R4
+	CMP  R4, R3
+	BNE  extendMatchEnd
+	ADD  $1, R15, R15
+	ADD  $1, R7, R7
+	B    cmp1
+
+extendMatchEnd:
+	// Convert from &src[ret] to ret.
+	SUB  R6, R7, R7
+	MOVD R7, ret+40(FP)
+	RET
+
+// ----------------------------------------------------------------------------
+
+// func encodeBlock(dst, src []byte) (d int)
+//
+// All local variables fit into registers, other than "var table". The register
+// allocation:
+//	- R3	.	.
+//	- R4	.	.
+//	- R5	64	shift
+//	- R6	72	&src[0], tableSize
+//	- R7	80	&src[s]
+//	- R8	88	&dst[d]
+//	- R9	96	sLimit
+//	- R10	.	&src[nextEmit]
+//	- R11	104	prevHash, currHash, nextHash, offset
+//	- R12	112	&src[base], skip
+//	- R13	.	&src[nextS], &src[len(src) - 8]
+//	- R14	.	len(src), bytesBetweenHashLookups, &src[len(src)], x
+//	- R15	120	candidate
+//	- R16	.	hash constant, 0x1e35a7bd
+//	- R17	.	&table
+//	- .  	128	table
+//
+// The second column (64, 72, etc) is the stack offset to spill the registers
+// when calling other functions. We could pack this slightly tighter, but it's
+// simpler to have a dedicated spill map independent of the function called.
+//
+// "var table [maxTableSize]uint16" takes up 32768 bytes of stack space. An
+// extra 64 bytes, to call other functions, and an extra 64 bytes, to spill
+// local variables (registers) during calls gives 32768 + 64 + 64 = 32896.
+TEXT ·encodeBlock(SB), 0, $32896-56
+	MOVD dst_base+0(FP), R8
+	MOVD src_base+24(FP), R7
+	MOVD src_len+32(FP), R14
+
+	// shift, tableSize := uint32(32-8), 1<<8
+	MOVD  $24, R5
+	MOVD  $256, R6
+	MOVW  $0xa7bd, R16
+	MOVKW $(0x1e35<<16), R16
+
+calcShift:
+	// for ; tableSize < maxTableSize && tableSize < len(src); tableSize *= 2 {
+	//	shift--
+	// }
+	MOVD $16384, R2
+	CMP  R2, R6
+	BGE  varTable
+	CMP  R14, R6
+	BGE  varTable
+	SUB  $1, R5, R5
+	LSL  $1, R6, R6
+	B    calcShift
+
+varTable:
+	// var table [maxTableSize]uint16
+	//
+	// In the asm code, unlike the Go code, we can zero-initialize only the
+	// first tableSize elements. Each uint16 element is 2 bytes and each
+	// iterations writes 64 bytes, so we can do only tableSize/32 writes
+	// instead of the 2048 writes that would zero-initialize all of table's
+	// 32768 bytes. This clear could overrun the first tableSize elements, but
+	// it won't overrun the allocated stack size.
+	ADD  $128, RSP, R17
+	MOVD R17, R4
+
+	// !!! R6 = &src[tableSize]
+	ADD R6<<1, R17, R6
+
+memclr:
+	STP.P (ZR, ZR), 64(R4)
+	STP   (ZR, ZR), -48(R4)
+	STP   (ZR, ZR), -32(R4)
+	STP   (ZR, ZR), -16(R4)
+	CMP   R4, R6
+	BHI   memclr
+
+	// !!! R6 = &src[0]
+	MOVD R7, R6
+
+	// sLimit := len(src) - inputMargin
+	MOVD R14, R9
+	SUB  $15, R9, R9
+
+	// !!! Pre-emptively spill R5, R6 and R9 to the stack. Their values don't
+	// change for the rest of the function.
+	MOVD R5, 64(RSP)
+	MOVD R6, 72(RSP)
+	MOVD R9, 96(RSP)
+
+	// nextEmit := 0
+	MOVD R6, R10
+
+	// s := 1
+	ADD $1, R7, R7
+
+	// nextHash := hash(load32(src, s), shift)
+	MOVW 0(R7), R11
+	MULW R16, R11, R11
+	LSRW R5, R11, R11
+
+outer:
+	// for { etc }
+
+	// skip := 32
+	MOVD $32, R12
+
+	// nextS := s
+	MOVD R7, R13
+
+	// candidate := 0
+	MOVD $0, R15
+
+inner0:
+	// for { etc }
+
+	// s := nextS
+	MOVD R13, R7
+
+	// bytesBetweenHashLookups := skip >> 5
+	MOVD R12, R14
+	LSR  $5, R14, R14
+
+	// nextS = s + bytesBetweenHashLookups
+	ADD R14, R13, R13
+
+	// skip += bytesBetweenHashLookups
+	ADD R14, R12, R12
+
+	// if nextS > sLimit { goto emitRemainder }
+	MOVD R13, R3
+	SUB  R6, R3, R3
+	CMP  R9, R3
+	BHI  emitRemainder
+
+	// candidate = int(table[nextHash])
+	MOVHU 0(R17)(R11<<1), R15
+
+	// table[nextHash] = uint16(s)
+	MOVD R7, R3
+	SUB  R6, R3, R3
+
+	MOVH R3, 0(R17)(R11<<1)
+
+	// nextHash = hash(load32(src, nextS), shift)
+	MOVW 0(R13), R11
+	MULW R16, R11
+	LSRW R5, R11, R11
+
+	// if load32(src, s) != load32(src, candidate) { continue } break
+	MOVW 0(R7), R3
+	MOVW (R6)(R15*1), R4
+	CMPW R4, R3
+	BNE  inner0
+
+fourByteMatch:
+	// As per the encode_other.go code:
+	//
+	// A 4-byte match has been found. We'll later see etc.
+
+	// !!! Jump to a fast path for short (<= 16 byte) literals. See the comment
+	// on inputMargin in encode.go.
+	MOVD R7, R3
+	SUB  R10, R3, R3
+	CMP  $16, R3
+	BLE  emitLiteralFastPath
+
+	// ----------------------------------------
+	// Begin inline of the emitLiteral call.
+	//
+	// d += emitLiteral(dst[d:], src[nextEmit:s])
+
+	MOVW R3, R4
+	SUBW $1, R4, R4
+
+	MOVW $60, R2
+	CMPW R2, R4
+	BLT  inlineEmitLiteralOneByte
+	MOVW $256, R2
+	CMPW R2, R4
+	BLT  inlineEmitLiteralTwoBytes
+
+inlineEmitLiteralThreeBytes:
+	MOVD $0xf4, R1
+	MOVB R1, 0(R8)
+	MOVW R4, 1(R8)
+	ADD  $3, R8, R8
+	B    inlineEmitLiteralMemmove
+
+inlineEmitLiteralTwoBytes:
+	MOVD $0xf0, R1
+	MOVB R1, 0(R8)
+	MOVB R4, 1(R8)
+	ADD  $2, R8, R8
+	B    inlineEmitLiteralMemmove
+
+inlineEmitLiteralOneByte:
+	LSLW $2, R4, R4
+	MOVB R4, 0(R8)
+	ADD  $1, R8, R8
+
+inlineEmitLiteralMemmove:
+	// Spill local variables (registers) onto the stack; call; unspill.
+	//
+	// copy(dst[i:], lit)
+	//
+	// This means calling runtime·memmove(&dst[i], &lit[0], len(lit)), so we push
+	// R8, R10 and R3 as arguments.
+	MOVD R8, 8(RSP)
+	MOVD R10, 16(RSP)
+	MOVD R3, 24(RSP)
+
+	// Finish the "d +=" part of "d += emitLiteral(etc)".
+	ADD   R3, R8, R8
+	MOVD  R7, 80(RSP)
+	MOVD  R8, 88(RSP)
+	MOVD  R15, 120(RSP)
+	CALL  runtime·memmove(SB)
+	MOVD  64(RSP), R5
+	MOVD  72(RSP), R6
+	MOVD  80(RSP), R7
+	MOVD  88(RSP), R8
+	MOVD  96(RSP), R9
+	MOVD  120(RSP), R15
+	ADD   $128, RSP, R17
+	MOVW  $0xa7bd, R16
+	MOVKW $(0x1e35<<16), R16
+	B     inner1
+
+inlineEmitLiteralEnd:
+	// End inline of the emitLiteral call.
+	// ----------------------------------------
+
+emitLiteralFastPath:
+	// !!! Emit the 1-byte encoding "uint8(len(lit)-1)<<2".
+	MOVB R3, R4
+	SUBW $1, R4, R4
+	AND  $0xff, R4, R4
+	LSLW $2, R4, R4
+	MOVB R4, (R8)
+	ADD  $1, R8, R8
+
+	// !!! Implement the copy from lit to dst as a 16-byte load and store.
+	// (Encode's documentation says that dst and src must not overlap.)
+	//
+	// This always copies 16 bytes, instead of only len(lit) bytes, but that's
+	// OK. Subsequent iterations will fix up the overrun.
+	//
+	// Note that on arm64, it is legal and cheap to issue unaligned 8-byte or
+	// 16-byte loads and stores. This technique probably wouldn't be as
+	// effective on architectures that are fussier about alignment.
+	LDP 0(R10), (R0, R1)
+	STP (R0, R1), 0(R8)
+	ADD R3, R8, R8
+
+inner1:
+	// for { etc }
+
+	// base := s
+	MOVD R7, R12
+
+	// !!! offset := base - candidate
+	MOVD R12, R11
+	SUB  R15, R11, R11
+	SUB  R6, R11, R11
+
+	// ----------------------------------------
+	// Begin inline of the extendMatch call.
+	//
+	// s = extendMatch(src, candidate+4, s+4)
+
+	// !!! R14 = &src[len(src)]
+	MOVD src_len+32(FP), R14
+	ADD  R6, R14, R14
+
+	// !!! R13 = &src[len(src) - 8]
+	MOVD R14, R13
+	SUB  $8, R13, R13
+
+	// !!! R15 = &src[candidate + 4]
+	ADD $4, R15, R15
+	ADD R6, R15, R15
+
+	// !!! s += 4
+	ADD $4, R7, R7
+
+inlineExtendMatchCmp8:
+	// As long as we are 8 or more bytes before the end of src, we can load and
+	// compare 8 bytes at a time. If those 8 bytes are equal, repeat.
+	CMP  R13, R7
+	BHI  inlineExtendMatchCmp1
+	MOVD (R15), R3
+	MOVD (R7), R4
+	CMP  R4, R3
+	BNE  inlineExtendMatchBSF
+	ADD  $8, R15, R15
+	ADD  $8, R7, R7
+	B    inlineExtendMatchCmp8
+
+inlineExtendMatchBSF:
+	// If those 8 bytes were not equal, XOR the two 8 byte values, and return
+	// the index of the first byte that differs.
+	// RBIT reverses the bit order, then CLZ counts the leading zeros, the
+	// combination of which finds the least significant bit which is set.
+	// The arm64 architecture is little-endian, and the shift by 3 converts
+	// a bit index to a byte index.
+	EOR  R3, R4, R4
+	RBIT R4, R4
+	CLZ  R4, R4
+	ADD  R4>>3, R7, R7
+	B    inlineExtendMatchEnd
+
+inlineExtendMatchCmp1:
+	// In src's tail, compare 1 byte at a time.
+	CMP  R7, R14
+	BLS  inlineExtendMatchEnd
+	MOVB (R15), R3
+	MOVB (R7), R4
+	CMP  R4, R3
+	BNE  inlineExtendMatchEnd
+	ADD  $1, R15, R15
+	ADD  $1, R7, R7
+	B    inlineExtendMatchCmp1
+
+inlineExtendMatchEnd:
+	// End inline of the extendMatch call.
+	// ----------------------------------------
+
+	// ----------------------------------------
+	// Begin inline of the emitCopy call.
+	//
+	// d += emitCopy(dst[d:], base-candidate, s-base)
+
+	// !!! length := s - base
+	MOVD R7, R3
+	SUB  R12, R3, R3
+
+inlineEmitCopyLoop0:
+	// for length >= 68 { etc }
+	MOVW $68, R2
+	CMPW R2, R3
+	BLT  inlineEmitCopyStep1
+
+	// Emit a length 64 copy, encoded as 3 bytes.
+	MOVD $0xfe, R1
+	MOVB R1, 0(R8)
+	MOVW R11, 1(R8)
+	ADD  $3, R8, R8
+	SUBW $64, R3, R3
+	B    inlineEmitCopyLoop0
+
+inlineEmitCopyStep1:
+	// if length > 64 { etc }
+	MOVW $64, R2
+	CMPW R2, R3
+	BLE  inlineEmitCopyStep2
+
+	// Emit a length 60 copy, encoded as 3 bytes.
+	MOVD $0xee, R1
+	MOVB R1, 0(R8)
+	MOVW R11, 1(R8)
+	ADD  $3, R8, R8
+	SUBW $60, R3, R3
+
+inlineEmitCopyStep2:
+	// if length >= 12 || offset >= 2048 { goto inlineEmitCopyStep3 }
+	MOVW $12, R2
+	CMPW R2, R3
+	BGE  inlineEmitCopyStep3
+	MOVW $2048, R2
+	CMPW R2, R11
+	BGE  inlineEmitCopyStep3
+
+	// Emit the remaining copy, encoded as 2 bytes.
+	MOVB R11, 1(R8)
+	LSRW $8, R11, R11
+	LSLW $5, R11, R11
+	SUBW $4, R3, R3
+	AND  $0xff, R3, R3
+	LSLW $2, R3, R3
+	ORRW R3, R11, R11
+	ORRW $1, R11, R11
+	MOVB R11, 0(R8)
+	ADD  $2, R8, R8
+	B    inlineEmitCopyEnd
+
+inlineEmitCopyStep3:
+	// Emit the remaining copy, encoded as 3 bytes.
+	SUBW $1, R3, R3
+	LSLW $2, R3, R3
+	ORRW $2, R3, R3
+	MOVB R3, 0(R8)
+	MOVW R11, 1(R8)
+	ADD  $3, R8, R8
+
+inlineEmitCopyEnd:
+	// End inline of the emitCopy call.
+	// ----------------------------------------
+
+	// nextEmit = s
+	MOVD R7, R10
+
+	// if s >= sLimit { goto emitRemainder }
+	MOVD R7, R3
+	SUB  R6, R3, R3
+	CMP  R3, R9
+	BLS  emitRemainder
+
+	// As per the encode_other.go code:
+	//
+	// We could immediately etc.
+
+	// x := load64(src, s-1)
+	MOVD -1(R7), R14
+
+	// prevHash := hash(uint32(x>>0), shift)
+	MOVW R14, R11
+	MULW R16, R11, R11
+	LSRW R5, R11, R11
+
+	// table[prevHash] = uint16(s-1)
+	MOVD R7, R3
+	SUB  R6, R3, R3
+	SUB  $1, R3, R3
+
+	MOVHU R3, 0(R17)(R11<<1)
+
+	// currHash := hash(uint32(x>>8), shift)
+	LSR  $8, R14, R14
+	MOVW R14, R11
+	MULW R16, R11, R11
+	LSRW R5, R11, R11
+
+	// candidate = int(table[currHash])
+	MOVHU 0(R17)(R11<<1), R15
+
+	// table[currHash] = uint16(s)
+	ADD   $1, R3, R3
+	MOVHU R3, 0(R17)(R11<<1)
+
+	// if uint32(x>>8) == load32(src, candidate) { continue }
+	MOVW (R6)(R15*1), R4
+	CMPW R4, R14
+	BEQ  inner1
+
+	// nextHash = hash(uint32(x>>16), shift)
+	LSR  $8, R14, R14
+	MOVW R14, R11
+	MULW R16, R11, R11
+	LSRW R5, R11, R11
+
+	// s++
+	ADD $1, R7, R7
+
+	// break out of the inner1 for loop, i.e. continue the outer loop.
+	B outer
+
+emitRemainder:
+	// if nextEmit < len(src) { etc }
+	MOVD src_len+32(FP), R3
+	ADD  R6, R3, R3
+	CMP  R3, R10
+	BEQ  encodeBlockEnd
+
+	// d += emitLiteral(dst[d:], src[nextEmit:])
+	//
+	// Push args.
+	MOVD R8, 8(RSP)
+	MOVD $0, 16(RSP)  // Unnecessary, as the callee ignores it, but conservative.
+	MOVD $0, 24(RSP)  // Unnecessary, as the callee ignores it, but conservative.
+	MOVD R10, 32(RSP)
+	SUB  R10, R3, R3
+	MOVD R3, 40(RSP)
+	MOVD R3, 48(RSP)  // Unnecessary, as the callee ignores it, but conservative.
+
+	// Spill local variables (registers) onto the stack; call; unspill.
+	MOVD R8, 88(RSP)
+	CALL ·emitLiteral(SB)
+	MOVD 88(RSP), R8
+
+	// Finish the "d +=" part of "d += emitLiteral(etc)".
+	MOVD 56(RSP), R1
+	ADD  R1, R8, R8
+
+encodeBlockEnd:
+	MOVD dst_base+0(FP), R3
+	SUB  R3, R8, R8
+	MOVD R8, d+48(FP)
+	RET

vendor/github.com/klauspost/compress/snappy/encode_amd64.go → vendor/github.com/golang/snappy/encode_asm.go

@@ -5,6 +5,7 @@
 // +build !appengine
 // +build gc
 // +build !noasm
+// +build amd64 arm64
 
 package snappy
 

vendor/github.com/klauspost/compress/snappy/encode_other.go → vendor/github.com/golang/snappy/encode_other.go

@@ -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 appengine !gc noasm
+// +build !amd64,!arm64 appengine !gc noasm
 
 package snappy
 

vendor/github.com/klauspost/compress/snappy/snappy.go → vendor/github.com/golang/snappy/snappy.go

@@ -17,7 +17,7 @@
 //
 // The canonical, C++ implementation is at https://github.com/google/snappy and
 // it only implements the block format.
-package snappy
+package snappy // import "github.com/golang/snappy"
 
 import (
 	"hash/crc32"
@@ -94,5 +94,5 @@ var crcTable = crc32.MakeTable(crc32.Castagnoli)
 // https://github.com/google/snappy/blob/master/framing_format.txt
 func crc(b []byte) uint32 {
 	c := crc32.Update(0, crcTable, b)
-	return c>>15 | c<<17 + 0xa282ead8
+	return uint32(c>>15|c<<17) + 0xa282ead8
 }

vendor/github.com/klauspost/compress/fse/compress.go

@@ -92,7 +92,6 @@ func (c *cState) init(bw *bitWriter, ct *cTable, tableLog uint8, first symbolTra
 	im := int32((nbBitsOut << 16) - first.deltaNbBits)
 	lu := (im >> nbBitsOut) + first.deltaFindState
 	c.state = c.stateTable[lu]
-	return
 }
 
 // encode the output symbol provided and write it to the bitstream.

vendor/github.com/klauspost/compress/huff0/compress.go

@@ -536,7 +536,6 @@ func (s *Scratch) huffSort() {
 		}
 		nodes[pos&huffNodesMask] = nodeElt{count: c, symbol: byte(n)}
 	}
-	return
 }
 
 func (s *Scratch) setMaxHeight(lastNonNull int) uint8 {

vendor/github.com/klauspost/compress/snappy/runbench.cmd

@@ -1,2 +0,0 @@
-del old.txt
-go test -bench=. >>old.txt && go test -bench=. >>old.txt && go test -bench=. >>old.txt && benchstat -delta-test=ttest old.txt new.txt

vendor/github.com/klauspost/compress/zstd/README.md

@@ -16,8 +16,7 @@ Currently the package is heavily optimized for 64 bit processors and will be sig
 
 Install using `go get -u github.com/klauspost/compress`. The package is located in `github.com/klauspost/compress/zstd`.
 
-Godoc Documentation: https://godoc.org/github.com/klauspost/compress/zstd
-
+[![Go Reference](https://pkg.go.dev/badge/github.com/klauspost/compress/zstd.svg)](https://pkg.go.dev/github.com/klauspost/compress/zstd)
 
 ## Compressor
 
@@ -152,8 +151,8 @@ This package:
 file    out     level   insize      outsize     millis  mb/s
 silesia.tar zskp    1   211947520   73101992    643     313.87
 silesia.tar zskp    2   211947520   67504318    969     208.38
-silesia.tar zskp    3   211947520   65177448    1899    106.44
-silesia.tar zskp    4   211947520   61381950    8115    24.91
+silesia.tar zskp    3   211947520   64595893    2007    100.68
+silesia.tar zskp    4   211947520   60995370    7691    26.28
 
 cgo zstd:
 silesia.tar zstd    1   211947520   73605392    543     371.56
@@ -171,8 +170,8 @@ https://files.klauspost.com/compress/gob-stream.7z
 file        out     level   insize  outsize     millis  mb/s
 gob-stream  zskp    1   1911399616  235022249   3088    590.30
 gob-stream  zskp    2   1911399616  205669791   3786    481.34
-gob-stream  zskp    3   1911399616  185792019   9324    195.48
-gob-stream  zskp    4   1911399616  171537212   32113   56.76
+gob-stream  zskp    3   1911399616  175034659   9636    189.17
+gob-stream  zskp    4   1911399616  167273881   29337   62.13
 gob-stream  zstd    1   1911399616  249810424   2637    691.26
 gob-stream  zstd    3   1911399616  208192146   3490    522.31
 gob-stream  zstd    6   1911399616  193632038   6687    272.56
@@ -187,8 +186,8 @@ http://mattmahoney.net/dc/textdata.html
 file    out level   insize      outsize     millis  mb/s
 enwik9  zskp    1   1000000000  343848582   3609    264.18
 enwik9  zskp    2   1000000000  317276632   5746    165.97
-enwik9  zskp    3   1000000000  294540704   11725   81.34
-enwik9  zskp    4   1000000000  276609671   44029   21.66
+enwik9  zskp    3   1000000000  292243069   12162   78.41
+enwik9  zskp    4   1000000000  275241169   36430   26.18
 enwik9  zstd    1   1000000000  358072021   3110    306.65
 enwik9  zstd    3   1000000000  313734672   4784    199.35
 enwik9  zstd    6   1000000000  295138875   10290   92.68
@@ -202,8 +201,8 @@ https://files.klauspost.com/compress/github-june-2days-2019.json.zst
 file                        out level   insize      outsize     millis  mb/s
 github-june-2days-2019.json zskp    1   6273951764  699045015   10620   563.40
 github-june-2days-2019.json zskp    2   6273951764  617881763   11687   511.96
-github-june-2days-2019.json zskp    3   6273951764  537511906   29252   204.54
-github-june-2days-2019.json zskp    4   6273951764  512796117   97791   61.18
+github-june-2days-2019.json zskp    3   6273951764  524340691   34043   175.75
+github-june-2days-2019.json zskp    4   6273951764  503314661   93811   63.78
 github-june-2days-2019.json zstd    1   6273951764  766284037   8450    708.00
 github-june-2days-2019.json zstd    3   6273951764  661889476   10927   547.57
 github-june-2days-2019.json zstd    6   6273951764  642756859   22996   260.18
@@ -217,8 +216,8 @@ https://files.klauspost.com/compress/rawstudio-mint14.7z
 file                    out level   insize      outsize     millis  mb/s
 rawstudio-mint14.tar    zskp    1   8558382592  3667489370  20210   403.84
 rawstudio-mint14.tar    zskp    2   8558382592  3364592300  31873   256.07
-rawstudio-mint14.tar    zskp    3   8558382592  3224594213  71751   113.75
-rawstudio-mint14.tar    zskp    4   8558382592  3027332295  486243  16.79
+rawstudio-mint14.tar    zskp    3   8558382592  3158085214  77675   105.08
+rawstudio-mint14.tar    zskp    4   8558382592  3020370044  404956  20.16
 rawstudio-mint14.tar    zstd    1   8558382592  3609250104  17136   476.27
 rawstudio-mint14.tar    zstd    3   8558382592  3341679997  29262   278.92
 rawstudio-mint14.tar    zstd    6   8558382592  3235846406  77904   104.77
@@ -232,8 +231,8 @@ https://files.klauspost.com/compress/nyc-taxi-data-10M.csv.zst
 file                    out level   insize      outsize     millis  mb/s
 nyc-taxi-data-10M.csv   zskp    1   3325605752  641339945   8925    355.35
 nyc-taxi-data-10M.csv   zskp    2   3325605752  591748091   11268   281.44
-nyc-taxi-data-10M.csv   zskp    3   3325605752  538490114   19880   159.53
-nyc-taxi-data-10M.csv   zskp    4   3325605752  495986829   89368   35.49
+nyc-taxi-data-10M.csv   zskp    3   3325605752  530289687   25239   125.66
+nyc-taxi-data-10M.csv   zskp    4   3325605752  490907191   65939   48.10
 nyc-taxi-data-10M.csv   zstd    1   3325605752  687399637   8233    385.18
 nyc-taxi-data-10M.csv   zstd    3   3325605752  598514411   10065   315.07
 nyc-taxi-data-10M.csv   zstd    6   3325605752  570522953   20038   158.27
@@ -405,13 +404,28 @@ BenchmarkDecoder_DecodeAllParallelCgo/comp-data.bin.zst-16        749938
 
 This reflects the performance around May 2020, but this may be out of date.
 
+## Zstd inside ZIP files
+
+It is possible to use zstandard to compress individual files inside zip archives.
+While this isn't widely supported it can be useful for internal files.
+
+To support the compression and decompression of these files you must register a compressor and decompressor.
+
+It is highly recommended registering the (de)compressors on individual zip Reader/Writer and NOT
+use the global registration functions. The main reason for this is that 2 registrations from 
+different packages will result in a panic.
+
+It is a good idea to only have a single compressor and decompressor, since they can be used for multiple zip
+files concurrently, and using a single instance will allow reusing some resources.
+
+See [this example](https://pkg.go.dev/github.com/klauspost/compress/zstd#example-ZipCompressor) for 
+how to compress and decompress files inside zip archives.
+
 # Contributions
 
 Contributions are always welcome. 
 For new features/fixes, remember to add tests and for performance enhancements include benchmarks.
 
-For sending files for reproducing errors use a service like [goobox](https://goobox.io/#/upload) or similar to share your files.
-
 For general feedback and experience reports, feel free to open an issue or write me on [Twitter](https://twitter.com/sh0dan).
 
 This package includes the excellent [`github.com/cespare/xxhash`](https://github.com/cespare/xxhash) package Copyright (c) 2016 Caleb Spare.

vendor/github.com/klauspost/compress/zstd/blockdec.go

@@ -123,12 +123,10 @@ func newBlockDec(lowMem bool) *blockDec {
 // Input must be a start of a block and will be at the end of the block when returned.
 func (b *blockDec) reset(br byteBuffer, windowSize uint64) error {
 	b.WindowSize = windowSize
-	tmp := br.readSmall(3)
-	if tmp == nil {
-		if debug {
-			println("Reading block header:", io.ErrUnexpectedEOF)
-		}
-		return io.ErrUnexpectedEOF
+	tmp, err := br.readSmall(3)
+	if err != nil {
+		println("Reading block header:", err)
+		return err
 	}
 	bh := uint32(tmp[0]) | (uint32(tmp[1]) << 8) | (uint32(tmp[2]) << 16)
 	b.Last = bh&1 != 0
@@ -179,7 +177,6 @@ func (b *blockDec) reset(br byteBuffer, windowSize uint64) error {
 	if cap(b.dst) <= maxSize {
 		b.dst = make([]byte, 0, maxSize+1)
 	}
-	var err error
 	b.data, err = br.readBig(cSize, b.dataStorage)
 	if err != nil {
 		if debug {

vendor/github.com/klauspost/compress/zstd/blockenc.go

@@ -386,9 +386,9 @@ func (b *blockEnc) encodeLits(lits []byte, raw bool) error {
 		b.output = bh.appendTo(b.output)
 		b.output = append(b.output, lits[0])
 		return nil
+	case nil:
 	default:
 		return err
-	case nil:
 	}
 	// Compressed...
 	// Now, allow reuse
@@ -528,11 +528,6 @@ func (b *blockEnc) encode(org []byte, raw, rawAllLits bool) error {
 		if debug {
 			println("Adding literals RLE")
 		}
-	default:
-		if debug {
-			println("Adding literals ERROR:", err)
-		}
-		return err
 	case nil:
 		// Compressed litLen...
 		if reUsed {
@@ -563,6 +558,11 @@ func (b *blockEnc) encode(org []byte, raw, rawAllLits bool) error {
 		if debug {
 			println("Adding literals compressed")
 		}
+	default:
+		if debug {
+			println("Adding literals ERROR:", err)
+		}
+		return err
 	}
 	// Sequence compression
 

vendor/github.com/klauspost/compress/zstd/bytebuf.go

@@ -12,8 +12,8 @@ import (
 
 type byteBuffer interface {
 	// Read up to 8 bytes.
-	// Returns nil if no more input is available.
-	readSmall(n int) []byte
+	// Returns io.ErrUnexpectedEOF if this cannot be satisfied.
+	readSmall(n int) ([]byte, error)
 
 	// Read >8 bytes.
 	// MAY use the destination slice.
@@ -29,17 +29,17 @@ type byteBuffer interface {
 // in-memory buffer
 type byteBuf []byte
 
-func (b *byteBuf) readSmall(n int) []byte {
+func (b *byteBuf) readSmall(n int) ([]byte, error) {
 	if debugAsserts && n > 8 {
 		panic(fmt.Errorf("small read > 8 (%d). use readBig", n))
 	}
 	bb := *b
 	if len(bb) < n {
-		return nil
+		return nil, io.ErrUnexpectedEOF
 	}
 	r := bb[:n]
 	*b = bb[n:]
-	return r
+	return r, nil
 }
 
 func (b *byteBuf) readBig(n int, dst []byte) ([]byte, error) {
@@ -81,19 +81,22 @@ type readerWrapper struct {
 	tmp [8]byte
 }
 
-func (r *readerWrapper) readSmall(n int) []byte {
+func (r *readerWrapper) readSmall(n int) ([]byte, error) {
 	if debugAsserts && n > 8 {
 		panic(fmt.Errorf("small read > 8 (%d). use readBig", n))
 	}
 	n2, err := io.ReadFull(r.r, r.tmp[:n])
 	// We only really care about the actual bytes read.
-	if n2 != n {
+	if err != nil {
+		if err == io.EOF {
+			return nil, io.ErrUnexpectedEOF
+		}
 		if debug {
 			println("readSmall: got", n2, "want", n, "err", err)
 		}
-		return nil
+		return nil, err
 	}
-	return r.tmp[:n]
+	return r.tmp[:n], nil
 }
 
 func (r *readerWrapper) readBig(n int, dst []byte) ([]byte, error) {

vendor/github.com/klauspost/compress/zstd/decodeheader.go

@@ -93,7 +93,7 @@ func (h *Header) Decode(in []byte) error {
 	h.HasCheckSum = fhd&(1<<2) != 0
 
 	if fhd&(1<<3) != 0 {
-		return errors.New("Reserved bit set on frame header")
+		return errors.New("reserved bit set on frame header")
 	}
 
 	// Read Window_Descriptor
@@ -174,7 +174,7 @@ func (h *Header) Decode(in []byte) error {
 	if len(in) < 3 {
 		return nil
 	}
-	tmp, in := in[:3], in[3:]
+	tmp := in[:3]
 	bh := uint32(tmp[0]) | (uint32(tmp[1]) << 8) | (uint32(tmp[2]) << 16)
 	h.FirstBlock.Last = bh&1 != 0
 	blockType := blockType((bh >> 1) & 3)

vendor/github.com/klauspost/compress/zstd/decoder.go

@@ -179,8 +179,7 @@ func (d *Decoder) Reset(r io.Reader) error {
 
 	// If bytes buffer and < 1MB, do sync decoding anyway.
 	if bb, ok := r.(byter); ok && bb.Len() < 1<<20 {
-		var bb2 byter
-		bb2 = bb
+		bb2 := bb
 		if debug {
 			println("*bytes.Buffer detected, doing sync decode, len:", bb.Len())
 		}
@@ -237,20 +236,17 @@ func (d *Decoder) drainOutput() {
 		println("current already flushed")
 		return
 	}
-	for {
-		select {
-		case v := <-d.current.output:
-			if v.d != nil {
-				if debug {
-					printf("re-adding decoder %p", v.d)
-				}
-				d.decoders <- v.d
-			}
-			if v.err == errEndOfStream {
-				println("current flushed")
-				d.current.flushed = true
-				return
+	for v := range d.current.output {
+		if v.d != nil {
+			if debug {
+				printf("re-adding decoder %p", v.d)
 			}
+			d.decoders <- v.d
+		}
+		if v.err == errEndOfStream {
+			println("current flushed")
+			d.current.flushed = true
+			return
 		}
 	}
 }

vendor/github.com/klauspost/compress/zstd/decoder_options.go

@@ -6,7 +6,6 @@ package zstd
 
 import (
 	"errors"
-	"fmt"
 	"runtime"
 )
 
@@ -43,7 +42,7 @@ func WithDecoderLowmem(b bool) DOption {
 func WithDecoderConcurrency(n int) DOption {
 	return func(o *decoderOptions) error {
 		if n <= 0 {
-			return fmt.Errorf("Concurrency must be at least 1")
+			return errors.New("concurrency must be at least 1")
 		}
 		o.concurrent = n
 		return nil
@@ -61,7 +60,7 @@ func WithDecoderMaxMemory(n uint64) DOption {
 			return errors.New("WithDecoderMaxMemory must be at least 1")
 		}
 		if n > 1<<63 {
-			return fmt.Errorf("WithDecoderMaxmemory must be less than 1 << 63")
+			return errors.New("WithDecoderMaxmemory must be less than 1 << 63")
 		}
 		o.maxDecodedSize = n
 		return nil

vendor/github.com/klauspost/compress/zstd/enc_base.go

@@ -150,14 +150,15 @@ func (e *fastBase) resetBase(d *dict, singleBlock bool) {
 	} else {
 		e.crc.Reset()
 	}
-	if (!singleBlock || d.DictContentSize() > 0) && cap(e.hist) < int(e.maxMatchOff*2)+d.DictContentSize() {
-		l := e.maxMatchOff*2 + int32(d.DictContentSize())
-		// Make it at least 1MB.
-		if l < 1<<20 {
-			l = 1 << 20
+	if d != nil {
+		low := e.lowMem
+		if singleBlock {
+			e.lowMem = true
 		}
-		e.hist = make([]byte, 0, l)
+		e.ensureHist(d.DictContentSize() + maxCompressedBlockSize)
+		e.lowMem = low
 	}
+
 	// We offset current position so everything will be out of reach.
 	// If above reset line, history will be purged.
 	if e.cur < bufferReset {

vendor/github.com/klauspost/compress/zstd/enc_best.go

@@ -220,6 +220,20 @@ encodeLoop:
 			best = bestOf(best, matchAt(candidateL.prev-e.cur, s, uint32(cv), -1))
 			best = bestOf(best, matchAt(candidateL2.offset-e.cur, s+1, uint32(cv2), -1))
 			best = bestOf(best, matchAt(candidateL2.prev-e.cur, s+1, uint32(cv2), -1))
+
+			// See if we can find a better match by checking where the current best ends.
+			// Use that offset to see if we can find a better full match.
+			if sAt := best.s + best.length; sAt < sLimit {
+				nextHashL := hash8(load6432(src, sAt), bestLongTableBits)
+				candidateEnd := e.longTable[nextHashL]
+				if pos := candidateEnd.offset - e.cur - best.length; pos >= 0 {
+					bestEnd := bestOf(best, matchAt(pos, best.s, load3232(src, best.s), -1))
+					if pos := candidateEnd.prev - e.cur - best.length; pos >= 0 {
+						bestEnd = bestOf(bestEnd, matchAt(pos, best.s, load3232(src, best.s), -1))
+					}
+					best = bestEnd
+				}
+			}
 		}
 
 		// We have a match, we can store the forward value

vendor/github.com/klauspost/compress/zstd/enc_better.go

@@ -412,8 +412,41 @@ encodeLoop:
 			cv = load6432(src, s)
 		}
 
-		// A 4-byte match has been found. Update recent offsets.
-		// We'll later see if more than 4 bytes.
+		// Try to find a better match by searching for a long match at the end of the current best match
+		if true && s+matched < sLimit {
+			nextHashL := hash8(load6432(src, s+matched), betterLongTableBits)
+			cv := load3232(src, s)
+			candidateL := e.longTable[nextHashL]
+			coffsetL := candidateL.offset - e.cur - matched
+			if coffsetL >= 0 && coffsetL < s && s-coffsetL < e.maxMatchOff && cv == load3232(src, coffsetL) {
+				// Found a long match, at least 4 bytes.
+				matchedNext := e.matchlen(s+4, coffsetL+4, src) + 4
+				if matchedNext > matched {
+					t = coffsetL
+					matched = matchedNext
+					if debugMatches {
+						println("long match at end-of-match")
+					}
+				}
+			}
+
+			// Check prev long...
+			if true {
+				coffsetL = candidateL.prev - e.cur - matched
+				if coffsetL >= 0 && coffsetL < s && s-coffsetL < e.maxMatchOff && cv == load3232(src, coffsetL) {
+					// Found a long match, at least 4 bytes.
+					matchedNext := e.matchlen(s+4, coffsetL+4, src) + 4
+					if matchedNext > matched {
+						t = coffsetL
+						matched = matchedNext
+						if debugMatches {
+							println("prev long match at end-of-match")
+						}
+					}
+				}
+			}
+		}
+		// A match has been found. Update recent offsets.
 		offset2 = offset1
 		offset1 = s - t
 
@@ -905,9 +938,41 @@ encodeLoop:
 			}
 			cv = load6432(src, s)
 		}
+		// Try to find a better match by searching for a long match at the end of the current best match
+		if s+matched < sLimit {
+			nextHashL := hash8(load6432(src, s+matched), betterLongTableBits)
+			cv := load3232(src, s)
+			candidateL := e.longTable[nextHashL]
+			coffsetL := candidateL.offset - e.cur - matched
+			if coffsetL >= 0 && coffsetL < s && s-coffsetL < e.maxMatchOff && cv == load3232(src, coffsetL) {
+				// Found a long match, at least 4 bytes.
+				matchedNext := e.matchlen(s+4, coffsetL+4, src) + 4
+				if matchedNext > matched {
+					t = coffsetL
+					matched = matchedNext
+					if debugMatches {
+						println("long match at end-of-match")
+					}
+				}
+			}
 
-		// A 4-byte match has been found. Update recent offsets.
-		// We'll later see if more than 4 bytes.
+			// Check prev long...
+			if true {
+				coffsetL = candidateL.prev - e.cur - matched
+				if coffsetL >= 0 && coffsetL < s && s-coffsetL < e.maxMatchOff && cv == load3232(src, coffsetL) {
+					// Found a long match, at least 4 bytes.
+					matchedNext := e.matchlen(s+4, coffsetL+4, src) + 4
+					if matchedNext > matched {
+						t = coffsetL
+						matched = matchedNext
+						if debugMatches {
+							println("prev long match at end-of-match")
+						}
+					}
+				}
+			}
+		}
+		// A match has been found. Update recent offsets.
 		offset2 = offset1
 		offset1 = s - t
 

vendor/github.com/klauspost/compress/zstd/encoder.go

@@ -340,13 +340,13 @@ func (e *Encoder) ReadFrom(r io.Reader) (n int64, err error) {
 				println("ReadFrom: got EOF final block:", len(e.state.filling))
 			}
 			return n, nil
+		case nil:
 		default:
 			if debug {
 				println("ReadFrom: got error:", err)
 			}
 			e.state.err = err
 			return n, err
-		case nil:
 		}
 		if len(src) > 0 {
 			if debug {

vendor/github.com/klauspost/compress/zstd/encoder_options.go

@@ -73,7 +73,7 @@ func WithEncoderCRC(b bool) EOption {
 }
 
 // WithEncoderConcurrency will set the concurrency,
-// meaning the maximum number of decoders to run concurrently.
+// meaning the maximum number of encoders to run concurrently.
 // The value supplied must be at least 1.
 // By default this will be set to GOMAXPROCS.
 func WithEncoderConcurrency(n int) EOption {

vendor/github.com/klauspost/compress/zstd/framedec.go

@@ -80,9 +80,14 @@ func (d *frameDec) reset(br byteBuffer) error {
 	d.WindowSize = 0
 	var b []byte
 	for {
-		b = br.readSmall(4)
-		if b == nil {
+		var err error
+		b, err = br.readSmall(4)
+		switch err {
+		case io.EOF, io.ErrUnexpectedEOF:
 			return io.EOF
+		default:
+			return err
+		case nil:
 		}
 		if !bytes.Equal(b[1:4], skippableFrameMagic) || b[0]&0xf0 != 0x50 {
 			if debug {
@@ -92,14 +97,14 @@ func (d *frameDec) reset(br byteBuffer) error {
 			break
 		}
 		// Read size to skip
-		b = br.readSmall(4)
-		if b == nil {
-			println("Reading Frame Size EOF")
-			return io.ErrUnexpectedEOF
+		b, err = br.readSmall(4)
+		if err != nil {
+			println("Reading Frame Size", err)
+			return err
 		}
 		n := uint32(b[0]) | (uint32(b[1]) << 8) | (uint32(b[2]) << 16) | (uint32(b[3]) << 24)
 		println("Skipping frame with", n, "bytes.")
-		err := br.skipN(int(n))
+		err = br.skipN(int(n))
 		if err != nil {
 			if debug {
 				println("Reading discarded frame", err)
@@ -121,7 +126,7 @@ func (d *frameDec) reset(br byteBuffer) error {
 	d.SingleSegment = fhd&(1<<5) != 0
 
 	if fhd&(1<<3) != 0 {
-		return errors.New("Reserved bit set on frame header")
+		return errors.New("reserved bit set on frame header")
 	}
 
 	// Read Window_Descriptor
@@ -147,12 +152,11 @@ func (d *frameDec) reset(br byteBuffer) error {
 		if size == 3 {
 			size = 4
 		}
-		b = br.readSmall(int(size))
-		if b == nil {
-			if debug {
-				println("Reading Dictionary_ID", io.ErrUnexpectedEOF)
-			}
-			return io.ErrUnexpectedEOF
+
+		b, err = br.readSmall(int(size))
+		if err != nil {
+			println("Reading Dictionary_ID", err)
+			return err
 		}
 		var id uint32
 		switch size {
@@ -187,10 +191,10 @@ func (d *frameDec) reset(br byteBuffer) error {
 	}
 	d.FrameContentSize = 0
 	if fcsSize > 0 {
-		b := br.readSmall(fcsSize)
-		if b == nil {
-			println("Reading Frame content", io.ErrUnexpectedEOF)
-			return io.ErrUnexpectedEOF
+		b, err = br.readSmall(fcsSize)
+		if err != nil {
+			println("Reading Frame content", err)
+			return err
 		}
 		switch fcsSize {
 		case 1:
@@ -307,10 +311,10 @@ func (d *frameDec) checkCRC() error {
 	tmp[3] = byte(got >> 24)
 
 	// We can overwrite upper tmp now
-	want := d.rawInput.readSmall(4)
-	if want == nil {
-		println("CRC missing?")
-		return io.ErrUnexpectedEOF
+	want, err := d.rawInput.readSmall(4)
+	if err != nil {
+		println("CRC missing?", err)
+		return err
 	}
 
 	if !bytes.Equal(tmp[:], want) {

vendor/github.com/klauspost/compress/zstd/fse_encoder.go

@@ -708,7 +708,6 @@ func (c *cState) init(bw *bitWriter, ct *cTable, first symbolTransform) {
 	im := int32((nbBitsOut << 16) - first.deltaNbBits)
 	lu := (im >> nbBitsOut) + int32(first.deltaFindState)
 	c.state = c.stateTable[lu]
-	return
 }
 
 // encode the output symbol provided and write it to the bitstream.

vendor/github.com/klauspost/compress/zstd/fse_predefined.go

@@ -59,7 +59,7 @@ func fillBase(dst []baseOffset, base uint32, bits ...uint8) {
 	}
 	for i, bit := range bits {
 		if base > math.MaxInt32 {
-			panic(fmt.Sprintf("invalid decoding table, base overflows int32"))
+			panic("invalid decoding table, base overflows int32")
 		}
 
 		dst[i] = baseOffset{

vendor/github.com/klauspost/compress/zstd/seqenc.go

@@ -35,7 +35,6 @@ func (s *seqCoders) setPrev(ll, ml, of *fseEncoder) {
 		// Ensure we cannot reuse by accident
 		prevEnc := *prev
 		prevEnc.symbolLen = 0
-		return
 	}
 	compareSwap(ll, &s.llEnc, &s.llPrev)
 	compareSwap(ml, &s.mlEnc, &s.mlPrev)

vendor/github.com/klauspost/compress/zstd/snappy.go

@@ -10,8 +10,8 @@ import (
 	"hash/crc32"
 	"io"
 
+	"github.com/golang/snappy"
 	"github.com/klauspost/compress/huff0"
-	"github.com/klauspost/compress/snappy"
 )
 
 const (
@@ -185,7 +185,6 @@ func (r *SnappyConverter) Convert(in io.Reader, w io.Writer) (int64, error) {
 				r.block.reset(nil)
 				r.block.literals, err = snappy.Decode(r.block.literals[:n], r.buf[snappyChecksumSize:chunkLen])
 				if err != nil {
-					println("snappy.Decode:", err)
 					return written, err
 				}
 				err = r.block.encodeLits(r.block.literals, false)

vendor/github.com/klauspost/compress/zstd/zip.go

@@ -0,0 +1,121 @@
+// Copyright 2019+ Klaus Post. All rights reserved.
+// License information can be found in the LICENSE file.
+
+package zstd
+
+import (
+	"errors"
+	"io"
+	"sync"
+)
+
+// ZipMethodWinZip is the method for Zstandard compressed data inside Zip files for WinZip.
+// See https://www.winzip.com/win/en/comp_info.html
+const ZipMethodWinZip = 93
+
+// ZipMethodPKWare is the original method number used by PKWARE to indicate Zstandard compression.
+// Deprecated: This has been deprecated by PKWARE, use ZipMethodWinZip instead for compression.
+// See https://pkware.cachefly.net/webdocs/APPNOTE/APPNOTE-6.3.9.TXT
+const ZipMethodPKWare = 20
+
+var zipReaderPool sync.Pool
+
+// newZipReader cannot be used since we would leak goroutines...
+func newZipReader(r io.Reader) io.ReadCloser {
+	dec, ok := zipReaderPool.Get().(*Decoder)
+	if ok {
+		dec.Reset(r)
+	} else {
+		d, err := NewReader(r, WithDecoderConcurrency(1), WithDecoderLowmem(true))
+		if err != nil {
+			panic(err)
+		}
+		dec = d
+	}
+	return &pooledZipReader{dec: dec}
+}
+
+type pooledZipReader struct {
+	mu  sync.Mutex // guards Close and Read
+	dec *Decoder
+}
+
+func (r *pooledZipReader) Read(p []byte) (n int, err error) {
+	r.mu.Lock()
+	defer r.mu.Unlock()
+	if r.dec == nil {
+		return 0, errors.New("Read after Close")
+	}
+	dec, err := r.dec.Read(p)
+
+	return dec, err
+}
+
+func (r *pooledZipReader) Close() error {
+	r.mu.Lock()
+	defer r.mu.Unlock()
+	var err error
+	if r.dec != nil {
+		err = r.dec.Reset(nil)
+		zipReaderPool.Put(r.dec)
+		r.dec = nil
+	}
+	return err
+}
+
+type pooledZipWriter struct {
+	mu  sync.Mutex // guards Close and Read
+	enc *Encoder
+}
+
+func (w *pooledZipWriter) Write(p []byte) (n int, err error) {
+	w.mu.Lock()
+	defer w.mu.Unlock()
+	if w.enc == nil {
+		return 0, errors.New("Write after Close")
+	}
+	return w.enc.Write(p)
+}
+
+func (w *pooledZipWriter) Close() error {
+	w.mu.Lock()
+	defer w.mu.Unlock()
+	var err error
+	if w.enc != nil {
+		err = w.enc.Close()
+		zipReaderPool.Put(w.enc)
+		w.enc = nil
+	}
+	return err
+}
+
+// ZipCompressor returns a compressor that can be registered with zip libraries.
+// The provided encoder options will be used on all encodes.
+func ZipCompressor(opts ...EOption) func(w io.Writer) (io.WriteCloser, error) {
+	var pool sync.Pool
+	return func(w io.Writer) (io.WriteCloser, error) {
+		enc, ok := pool.Get().(*Encoder)
+		if ok {
+			enc.Reset(w)
+		} else {
+			var err error
+			enc, err = NewWriter(w, opts...)
+			if err != nil {
+				return nil, err
+			}
+		}
+		return &pooledZipWriter{enc: enc}, nil
+	}
+}
+
+// ZipDecompressor returns a decompressor that can be registered with zip libraries.
+// See ZipCompressor for example.
+func ZipDecompressor() func(r io.Reader) io.ReadCloser {
+	return func(r io.Reader) io.ReadCloser {
+		d, err := NewReader(r, WithDecoderConcurrency(1), WithDecoderLowmem(true))
+		if err != nil {
+			panic(err)
+		}
+		return d.IOReadCloser()
+	}
+}

vendor/github.com/klauspost/compress/zstd/zstd.go

@@ -5,6 +5,7 @@ package zstd
 
 import (
 	"bytes"
+	"encoding/binary"
 	"errors"
 	"log"
 	"math"
@@ -126,26 +127,15 @@ func matchLen(a, b []byte) int {
 }
 
 func load3232(b []byte, i int32) uint32 {
-	// Help the compiler eliminate bounds checks on the read so it can be done in a single read.
-	b = b[i:]
-	b = b[:4]
-	return uint32(b[0]) | uint32(b[1])<<8 | uint32(b[2])<<16 | uint32(b[3])<<24
+	return binary.LittleEndian.Uint32(b[i:])
 }
 
 func load6432(b []byte, i int32) uint64 {
-	// Help the compiler eliminate bounds checks on the read so it can be done in a single read.
-	b = b[i:]
-	b = b[:8]
-	return uint64(b[0]) | uint64(b[1])<<8 | uint64(b[2])<<16 | uint64(b[3])<<24 |
-		uint64(b[4])<<32 | uint64(b[5])<<40 | uint64(b[6])<<48 | uint64(b[7])<<56
+	return binary.LittleEndian.Uint64(b[i:])
 }
 
 func load64(b []byte, i int) uint64 {
-	// Help the compiler eliminate bounds checks on the read so it can be done in a single read.
-	b = b[i:]
-	b = b[:8]
-	return uint64(b[0]) | uint64(b[1])<<8 | uint64(b[2])<<16 | uint64(b[3])<<24 |
-		uint64(b[4])<<32 | uint64(b[5])<<40 | uint64(b[6])<<48 | uint64(b[7])<<56
+	return binary.LittleEndian.Uint64(b[i:])
 }
 
 type byter interface {

vendor/modules.txt

@@ -429,6 +429,9 @@ github.com/golang/protobuf/ptypes/duration
 github.com/golang/protobuf/ptypes/empty
 github.com/golang/protobuf/ptypes/struct
 github.com/golang/protobuf/ptypes/timestamp
+# github.com/golang/snappy v0.0.3
+## explicit
+github.com/golang/snappy
 # github.com/google/btree v1.0.1
 ## explicit; go 1.12
 github.com/google/btree
@@ -515,11 +518,10 @@ github.com/jmespath/go-jmespath
 github.com/jstemmer/go-junit-report
 github.com/jstemmer/go-junit-report/formatter
 github.com/jstemmer/go-junit-report/parser
-# github.com/klauspost/compress v1.12.3 => github.com/klauspost/compress v1.11.13
+# github.com/klauspost/compress v1.12.3
 ## explicit; go 1.13
 github.com/klauspost/compress/fse
 github.com/klauspost/compress/huff0
-github.com/klauspost/compress/snappy
 github.com/klauspost/compress/zstd
 github.com/klauspost/compress/zstd/internal/xxhash
 # github.com/matttproud/golang_protobuf_extensions v1.0.2-0.20181231171920-c182affec369 => github.com/matttproud/golang_protobuf_extensions v1.0.1
@@ -1001,7 +1003,6 @@ gotest.tools/v3/skip
 # github.com/hashicorp/go-multierror => github.com/hashicorp/go-multierror v1.0.0
 # github.com/hashicorp/serf => github.com/hashicorp/serf v0.7.1-0.20160317193612-598c54895cc5
 # github.com/hpcloud/tail => github.com/hpcloud/tail v1.0.0
-# github.com/klauspost/compress => github.com/klauspost/compress v1.11.13
 # github.com/matttproud/golang_protobuf_extensions => github.com/matttproud/golang_protobuf_extensions v1.0.1
 # github.com/onsi/ginkgo => github.com/onsi/ginkgo v1.8.0
 # github.com/onsi/gomega => github.com/onsi/gomega v1.5.0