vendor: update buildkit to master@ae9d0f5

Signed-off-by: Justin Chadwell <me@jedevc.com>

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

@@ -12,6 +12,8 @@ The `zstd` package is provided as open source software using a Go standard licen
 
 Currently the package is heavily optimized for 64 bit processors and will be significantly slower on 32 bit processors.
 
+For seekable zstd streams, see [this excellent package](https://github.com/SaveTheRbtz/zstd-seekable-format-go).
+
 ## Installation
 
 Install using `go get -u github.com/klauspost/compress`. The package is located in `github.com/klauspost/compress/zstd`.

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

@@ -10,7 +10,6 @@ import (
 	"errors"
 	"fmt"
 	"io"
-	"io/ioutil"
 	"os"
 	"path/filepath"
 	"sync"
@@ -233,7 +232,7 @@ func (b *blockDec) decodeBuf(hist *history) error {
 			if b.lowMem {
 				b.dst = make([]byte, b.RLESize)
 			} else {
-				b.dst = make([]byte, maxBlockSize)
+				b.dst = make([]byte, maxCompressedBlockSize)
 			}
 		}
 		b.dst = b.dst[:b.RLESize]
@@ -651,7 +650,7 @@ func (b *blockDec) prepareSequences(in []byte, hist *history) (err error) {
 		fatalErr(binary.Write(&buf, binary.LittleEndian, hist.decoders.matchLengths.fse))
 		fatalErr(binary.Write(&buf, binary.LittleEndian, hist.decoders.offsets.fse))
 		buf.Write(in)
-		ioutil.WriteFile(filepath.Join("testdata", "seqs", fn), buf.Bytes(), os.ModePerm)
+		os.WriteFile(filepath.Join("testdata", "seqs", fn), buf.Bytes(), os.ModePerm)
 	}
 
 	return nil

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

@@ -7,7 +7,6 @@ package zstd
 import (
 	"fmt"
 	"io"
-	"io/ioutil"
 )
 
 type byteBuffer interface {
@@ -23,7 +22,7 @@ type byteBuffer interface {
 	readByte() (byte, error)
 
 	// Skip n bytes.
-	skipN(n int) error
+	skipN(n int64) error
 }
 
 // in-memory buffer
@@ -62,9 +61,12 @@ func (b *byteBuf) readByte() (byte, error) {
 	return r, nil
 }
 
-func (b *byteBuf) skipN(n int) error {
+func (b *byteBuf) skipN(n int64) error {
 	bb := *b
-	if len(bb) < n {
+	if n < 0 {
+		return fmt.Errorf("negative skip (%d) requested", n)
+	}
+	if int64(len(bb)) < n {
 		return io.ErrUnexpectedEOF
 	}
 	*b = bb[n:]
@@ -120,9 +122,9 @@ func (r *readerWrapper) readByte() (byte, error) {
 	return r.tmp[0], nil
 }
 
-func (r *readerWrapper) skipN(n int) error {
-	n2, err := io.CopyN(ioutil.Discard, r.r, int64(n))
-	if n2 != int64(n) {
+func (r *readerWrapper) skipN(n int64) error {
+	n2, err := io.CopyN(io.Discard, r.r, n)
+	if n2 != n {
 		err = io.ErrUnexpectedEOF
 	}
 	return err

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

@@ -35,6 +35,7 @@ type Decoder struct {
 		br           readerWrapper
 		enabled      bool
 		inFrame      bool
+		dstBuf       []byte
 	}
 
 	frame *frameDec
@@ -187,21 +188,23 @@ func (d *Decoder) Reset(r io.Reader) error {
 	}
 
 	// If bytes buffer and < 5MB, do sync decoding anyway.
-	if bb, ok := r.(byter); ok && bb.Len() < 5<<20 {
+	if bb, ok := r.(byter); ok && bb.Len() < d.o.decodeBufsBelow && !d.o.limitToCap {
 		bb2 := bb
 		if debugDecoder {
 			println("*bytes.Buffer detected, doing sync decode, len:", bb.Len())
 		}
 		b := bb2.Bytes()
 		var dst []byte
-		if cap(d.current.b) > 0 {
-			dst = d.current.b
+		if cap(d.syncStream.dstBuf) > 0 {
+			dst = d.syncStream.dstBuf[:0]
 		}
 
-		dst, err := d.DecodeAll(b, dst[:0])
+		dst, err := d.DecodeAll(b, dst)
 		if err == nil {
 			err = io.EOF
 		}
+		// Save output buffer
+		d.syncStream.dstBuf = dst
 		d.current.b = dst
 		d.current.err = err
 		d.current.flushed = true
@@ -216,6 +219,7 @@ func (d *Decoder) Reset(r io.Reader) error {
 	d.current.err = nil
 	d.current.flushed = false
 	d.current.d = nil
+	d.syncStream.dstBuf = nil
 
 	// Ensure no-one else is still running...
 	d.streamWg.Wait()
@@ -312,6 +316,7 @@ func (d *Decoder) DecodeAll(input, dst []byte) ([]byte, error) {
 	// Grab a block decoder and frame decoder.
 	block := <-d.decoders
 	frame := block.localFrame
+	initialSize := len(dst)
 	defer func() {
 		if debugDecoder {
 			printf("re-adding decoder: %p", block)
@@ -348,10 +353,22 @@ func (d *Decoder) DecodeAll(input, dst []byte) ([]byte, error) {
 			frame.history.setDict(&dict)
 		}
 		if frame.WindowSize > d.o.maxWindowSize {
+			if debugDecoder {
+				println("window size exceeded:", frame.WindowSize, ">", d.o.maxWindowSize)
+			}
 			return dst, ErrWindowSizeExceeded
 		}
 		if frame.FrameContentSize != fcsUnknown {
-			if frame.FrameContentSize > d.o.maxDecodedSize-uint64(len(dst)) {
+			if frame.FrameContentSize > d.o.maxDecodedSize-uint64(len(dst)-initialSize) {
+				if debugDecoder {
+					println("decoder size exceeded; fcs:", frame.FrameContentSize, "> mcs:", d.o.maxDecodedSize-uint64(len(dst)-initialSize), "len:", len(dst))
+				}
+				return dst, ErrDecoderSizeExceeded
+			}
+			if d.o.limitToCap && frame.FrameContentSize > uint64(cap(dst)-len(dst)) {
+				if debugDecoder {
+					println("decoder size exceeded; fcs:", frame.FrameContentSize, "> (cap-len)", cap(dst)-len(dst))
+				}
 				return dst, ErrDecoderSizeExceeded
 			}
 			if cap(dst)-len(dst) < int(frame.FrameContentSize) {
@@ -361,7 +378,7 @@ func (d *Decoder) DecodeAll(input, dst []byte) ([]byte, error) {
 			}
 		}
 
-		if cap(dst) == 0 {
+		if cap(dst) == 0 && !d.o.limitToCap {
 			// Allocate len(input) * 2 by default if nothing is provided
 			// and we didn't get frame content size.
 			size := len(input) * 2
@@ -379,6 +396,9 @@ func (d *Decoder) DecodeAll(input, dst []byte) ([]byte, error) {
 		if err != nil {
 			return dst, err
 		}
+		if uint64(len(dst)-initialSize) > d.o.maxDecodedSize {
+			return dst, ErrDecoderSizeExceeded
+		}
 		if len(frame.bBuf) == 0 {
 			if debugDecoder {
 				println("frame dbuf empty")
@@ -664,6 +684,7 @@ func (d *Decoder) startStreamDecoder(ctx context.Context, r io.Reader, output ch
 				if debugDecoder {
 					println("Async 1: new history, recent:", block.async.newHist.recentOffsets)
 				}
+				hist.reset()
 				hist.decoders = block.async.newHist.decoders
 				hist.recentOffsets = block.async.newHist.recentOffsets
 				hist.windowSize = block.async.newHist.windowSize
@@ -695,6 +716,7 @@ func (d *Decoder) startStreamDecoder(ctx context.Context, r io.Reader, output ch
 			seqExecute <- block
 		}
 		close(seqExecute)
+		hist.reset()
 	}()
 
 	var wg sync.WaitGroup
@@ -718,6 +740,7 @@ func (d *Decoder) startStreamDecoder(ctx context.Context, r io.Reader, output ch
 				if debugDecoder {
 					println("Async 2: new history")
 				}
+				hist.reset()
 				hist.windowSize = block.async.newHist.windowSize
 				hist.allocFrameBuffer = block.async.newHist.allocFrameBuffer
 				if block.async.newHist.dict != nil {
@@ -747,7 +770,7 @@ func (d *Decoder) startStreamDecoder(ctx context.Context, r io.Reader, output ch
 					if block.lowMem {
 						block.dst = make([]byte, block.RLESize)
 					} else {
-						block.dst = make([]byte, maxBlockSize)
+						block.dst = make([]byte, maxCompressedBlockSize)
 					}
 				}
 				block.dst = block.dst[:block.RLESize]
@@ -799,13 +822,14 @@ func (d *Decoder) startStreamDecoder(ctx context.Context, r io.Reader, output ch
 		if debugDecoder {
 			println("decoder goroutines finished")
 		}
+		hist.reset()
 	}()
 
+	var hist history
 decodeStream:
 	for {
-		var hist history
 		var hasErr bool
-
+		hist.reset()
 		decodeBlock := func(block *blockDec) {
 			if hasErr {
 				if block != nil {
@@ -849,6 +873,10 @@ decodeStream:
 			}
 		}
 		if err == nil && d.frame.WindowSize > d.o.maxWindowSize {
+			if debugDecoder {
+				println("decoder size exceeded, fws:", d.frame.WindowSize, "> mws:", d.o.maxWindowSize)
+			}
+
 			err = ErrDecoderSizeExceeded
 		}
 		if err != nil {
@@ -917,5 +945,6 @@ decodeStream:
 	}
 	close(seqDecode)
 	wg.Wait()
+	hist.reset()
 	d.frame.history.b = frameHistCache
 }

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

@@ -14,20 +14,23 @@ type DOption func(*decoderOptions) error
 
 // options retains accumulated state of multiple options.
 type decoderOptions struct {
-	lowMem         bool
-	concurrent     int
-	maxDecodedSize uint64
-	maxWindowSize  uint64
-	dicts          []dict
-	ignoreChecksum bool
+	lowMem          bool
+	concurrent      int
+	maxDecodedSize  uint64
+	maxWindowSize   uint64
+	dicts           []dict
+	ignoreChecksum  bool
+	limitToCap      bool
+	decodeBufsBelow int
 }
 
 func (o *decoderOptions) setDefault() {
 	*o = decoderOptions{
 		// use less ram: true for now, but may change.
-		lowMem:        true,
-		concurrent:    runtime.GOMAXPROCS(0),
-		maxWindowSize: MaxWindowSize,
+		lowMem:          true,
+		concurrent:      runtime.GOMAXPROCS(0),
+		maxWindowSize:   MaxWindowSize,
+		decodeBufsBelow: 128 << 10,
 	}
 	if o.concurrent > 4 {
 		o.concurrent = 4
@@ -114,6 +117,29 @@ func WithDecoderMaxWindow(size uint64) DOption {
 	}
 }
 
+// WithDecodeAllCapLimit will limit DecodeAll to decoding cap(dst)-len(dst) bytes,
+// or any size set in WithDecoderMaxMemory.
+// This can be used to limit decoding to a specific maximum output size.
+// Disabled by default.
+func WithDecodeAllCapLimit(b bool) DOption {
+	return func(o *decoderOptions) error {
+		o.limitToCap = b
+		return nil
+	}
+}
+
+// WithDecodeBuffersBelow will fully decode readers that have a
+// `Bytes() []byte` and `Len() int` interface similar to bytes.Buffer.
+// This typically uses less allocations but will have the full decompressed object in memory.
+// Note that DecodeAllCapLimit will disable this, as well as giving a size of 0 or less.
+// Default is 128KiB.
+func WithDecodeBuffersBelow(size int) DOption {
+	return func(o *decoderOptions) error {
+		o.decodeBufsBelow = size
+		return nil
+	}
+}
+
 // IgnoreChecksum allows to forcibly ignore checksum checking.
 func IgnoreChecksum(b bool) DOption {
 	return func(o *decoderOptions) error {

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

@@ -32,6 +32,7 @@ type match struct {
 	length int32
 	rep    int32
 	est    int32
+	_      [12]byte // Aligned size to cache line: 4+4+4+4+4 bytes + 12 bytes padding = 32 bytes
 }
 
 const highScore = 25000

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

@@ -416,15 +416,23 @@ encodeLoop:
 
 		// Try to find a better match by searching for a long match at the end of the current best match
 		if s+matched < sLimit {
+			// Allow some bytes at the beginning to mismatch.
+			// Sweet spot is around 3 bytes, but depends on input.
+			// The skipped bytes are tested in Extend backwards,
+			// and still picked up as part of the match if they do.
+			const skipBeginning = 3
+
 			nextHashL := hashLen(load6432(src, s+matched), betterLongTableBits, betterLongLen)
-			cv := load3232(src, s)
+			s2 := s + skipBeginning
+			cv := load3232(src, s2)
 			candidateL := e.longTable[nextHashL]
-			coffsetL := candidateL.offset - e.cur - matched
-			if coffsetL >= 0 && coffsetL < s && s-coffsetL < e.maxMatchOff && cv == load3232(src, coffsetL) {
+			coffsetL := candidateL.offset - e.cur - matched + skipBeginning
+			if coffsetL >= 0 && coffsetL < s2 && s2-coffsetL < e.maxMatchOff && cv == load3232(src, coffsetL) {
 				// Found a long match, at least 4 bytes.
-				matchedNext := e.matchlen(s+4, coffsetL+4, src) + 4
+				matchedNext := e.matchlen(s2+4, coffsetL+4, src) + 4
 				if matchedNext > matched {
 					t = coffsetL
+					s = s2
 					matched = matchedNext
 					if debugMatches {
 						println("long match at end-of-match")
@@ -434,12 +442,13 @@ encodeLoop:
 
 			// Check prev long...
 			if true {
-				coffsetL = candidateL.prev - e.cur - matched
-				if coffsetL >= 0 && coffsetL < s && s-coffsetL < e.maxMatchOff && cv == load3232(src, coffsetL) {
+				coffsetL = candidateL.prev - e.cur - matched + skipBeginning
+				if coffsetL >= 0 && coffsetL < s2 && s2-coffsetL < e.maxMatchOff && cv == load3232(src, coffsetL) {
 					// Found a long match, at least 4 bytes.
-					matchedNext := e.matchlen(s+4, coffsetL+4, src) + 4
+					matchedNext := e.matchlen(s2+4, coffsetL+4, src) + 4
 					if matchedNext > matched {
 						t = coffsetL
+						s = s2
 						matched = matchedNext
 						if debugMatches {
 							println("prev long match at end-of-match")

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

@@ -1103,7 +1103,8 @@ func (e *doubleFastEncoderDict) Reset(d *dict, singleBlock bool) {
 	}
 
 	if allDirty || dirtyShardCnt > dLongTableShardCnt/2 {
-		copy(e.longTable[:], e.dictLongTable)
+		//copy(e.longTable[:], e.dictLongTable)
+		e.longTable = *(*[dFastLongTableSize]tableEntry)(e.dictLongTable)
 		for i := range e.longTableShardDirty {
 			e.longTableShardDirty[i] = false
 		}
@@ -1114,7 +1115,9 @@ func (e *doubleFastEncoderDict) Reset(d *dict, singleBlock bool) {
 			continue
 		}
 
-		copy(e.longTable[i*dLongTableShardSize:(i+1)*dLongTableShardSize], e.dictLongTable[i*dLongTableShardSize:(i+1)*dLongTableShardSize])
+		// copy(e.longTable[i*dLongTableShardSize:(i+1)*dLongTableShardSize], e.dictLongTable[i*dLongTableShardSize:(i+1)*dLongTableShardSize])
+		*(*[dLongTableShardSize]tableEntry)(e.longTable[i*dLongTableShardSize:]) = *(*[dLongTableShardSize]tableEntry)(e.dictLongTable[i*dLongTableShardSize:])
+
 		e.longTableShardDirty[i] = false
 	}
 }

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

@@ -304,7 +304,7 @@ func (e *fastEncoder) EncodeNoHist(blk *blockEnc, src []byte) {
 		minNonLiteralBlockSize = 1 + 1 + inputMargin
 	)
 	if debugEncoder {
-		if len(src) > maxBlockSize {
+		if len(src) > maxCompressedBlockSize {
 			panic("src too big")
 		}
 	}
@@ -871,7 +871,8 @@ func (e *fastEncoderDict) Reset(d *dict, singleBlock bool) {
 	const shardCnt = tableShardCnt
 	const shardSize = tableShardSize
 	if e.allDirty || dirtyShardCnt > shardCnt*4/6 {
-		copy(e.table[:], e.dictTable)
+		//copy(e.table[:], e.dictTable)
+		e.table = *(*[tableSize]tableEntry)(e.dictTable)
 		for i := range e.tableShardDirty {
 			e.tableShardDirty[i] = false
 		}
@@ -883,7 +884,8 @@ func (e *fastEncoderDict) Reset(d *dict, singleBlock bool) {
 			continue
 		}
 
-		copy(e.table[i*shardSize:(i+1)*shardSize], e.dictTable[i*shardSize:(i+1)*shardSize])
+		//copy(e.table[i*shardSize:(i+1)*shardSize], e.dictTable[i*shardSize:(i+1)*shardSize])
+		*(*[shardSize]tableEntry)(e.table[i*shardSize:]) = *(*[shardSize]tableEntry)(e.dictTable[i*shardSize:])
 		e.tableShardDirty[i] = false
 	}
 	e.allDirty = false

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

@@ -528,8 +528,8 @@ func (e *Encoder) EncodeAll(src, dst []byte) []byte {
 		// If a non-single block is needed the encoder will reset again.
 		e.encoders <- enc
 	}()
-	// Use single segments when above minimum window and below 1MB.
-	single := len(src) < 1<<20 && len(src) > MinWindowSize
+	// Use single segments when above minimum window and below window size.
+	single := len(src) <= e.o.windowSize && len(src) > MinWindowSize
 	if e.o.single != nil {
 		single = *e.o.single
 	}

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

@@ -283,7 +283,7 @@ func WithNoEntropyCompression(b bool) EOption {
 // a decoder is allowed to reject a compressed frame which requests a memory size beyond decoder's authorized range.
 // For broader compatibility, decoders are recommended to support memory sizes of at least 8 MB.
 // This is only a recommendation, each decoder is free to support higher or lower limits, depending on local limitations.
-// If this is not specified, block encodes will automatically choose this based on the input size.
+// If this is not specified, block encodes will automatically choose this based on the input size and the window size.
 // This setting has no effect on streamed encodes.
 func WithSingleSegment(b bool) EOption {
 	return func(o *encoderOptions) error {

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

@@ -106,7 +106,7 @@ func (d *frameDec) reset(br byteBuffer) error {
 		}
 		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(int64(n))
 		if err != nil {
 			if debugDecoder {
 				println("Reading discarded frame", err)
@@ -231,20 +231,27 @@ func (d *frameDec) reset(br byteBuffer) error {
 		d.crc.Reset()
 	}
 
+	if d.WindowSize > d.o.maxWindowSize {
+		if debugDecoder {
+			printf("window size %d > max %d\n", d.WindowSize, d.o.maxWindowSize)
+		}
+		return ErrWindowSizeExceeded
+	}
+
 	if d.WindowSize == 0 && d.SingleSegment {
 		// We may not need window in this case.
 		d.WindowSize = d.FrameContentSize
 		if d.WindowSize < MinWindowSize {
 			d.WindowSize = MinWindowSize
 		}
+		if d.WindowSize > d.o.maxDecodedSize {
+			if debugDecoder {
+				printf("window size %d > max %d\n", d.WindowSize, d.o.maxWindowSize)
+			}
+			return ErrDecoderSizeExceeded
+		}
 	}
 
-	if d.WindowSize > uint64(d.o.maxWindowSize) {
-		if debugDecoder {
-			printf("window size %d > max %d\n", d.WindowSize, d.o.maxWindowSize)
-		}
-		return ErrWindowSizeExceeded
-	}
 	// The minimum Window_Size is 1 KB.
 	if d.WindowSize < MinWindowSize {
 		if debugDecoder {
@@ -254,11 +261,16 @@ func (d *frameDec) reset(br byteBuffer) error {
 	}
 	d.history.windowSize = int(d.WindowSize)
 	if !d.o.lowMem || d.history.windowSize < maxBlockSize {
-		// Alloc 2x window size if not low-mem, or very small window size.
+		// Alloc 2x window size if not low-mem, or window size below 2MB.
 		d.history.allocFrameBuffer = d.history.windowSize * 2
 	} else {
-		// Alloc with one additional block
-		d.history.allocFrameBuffer = d.history.windowSize + maxBlockSize
+		if d.o.lowMem {
+			// Alloc with 1MB extra.
+			d.history.allocFrameBuffer = d.history.windowSize + maxBlockSize/2
+		} else {
+			// Alloc with 2MB extra.
+			d.history.allocFrameBuffer = d.history.windowSize + maxBlockSize
+		}
 	}
 
 	if debugDecoder {
@@ -336,7 +348,7 @@ func (d *frameDec) consumeCRC() error {
 	return nil
 }
 
-// runDecoder will create a sync decoder that will decode a block of data.
+// runDecoder will run the decoder for the remainder of the frame.
 func (d *frameDec) runDecoder(dst []byte, dec *blockDec) ([]byte, error) {
 	saved := d.history.b
 
@@ -346,12 +358,23 @@ func (d *frameDec) runDecoder(dst []byte, dec *blockDec) ([]byte, error) {
 	// Store input length, so we only check new data.
 	crcStart := len(dst)
 	d.history.decoders.maxSyncLen = 0
+	if d.o.limitToCap {
+		d.history.decoders.maxSyncLen = uint64(cap(dst) - len(dst))
+	}
 	if d.FrameContentSize != fcsUnknown {
-		d.history.decoders.maxSyncLen = d.FrameContentSize + uint64(len(dst))
+		if !d.o.limitToCap || d.FrameContentSize+uint64(len(dst)) < d.history.decoders.maxSyncLen {
+			d.history.decoders.maxSyncLen = d.FrameContentSize + uint64(len(dst))
+		}
 		if d.history.decoders.maxSyncLen > d.o.maxDecodedSize {
+			if debugDecoder {
+				println("maxSyncLen:", d.history.decoders.maxSyncLen, "> maxDecodedSize:", d.o.maxDecodedSize)
+			}
 			return dst, ErrDecoderSizeExceeded
 		}
-		if uint64(cap(dst)) < d.history.decoders.maxSyncLen {
+		if debugDecoder {
+			println("maxSyncLen:", d.history.decoders.maxSyncLen)
+		}
+		if !d.o.limitToCap && uint64(cap(dst)) < d.history.decoders.maxSyncLen {
 			// Alloc for output
 			dst2 := make([]byte, len(dst), d.history.decoders.maxSyncLen+compressedBlockOverAlloc)
 			copy(dst2, dst)
@@ -371,7 +394,13 @@ func (d *frameDec) runDecoder(dst []byte, dec *blockDec) ([]byte, error) {
 		if err != nil {
 			break
 		}
-		if uint64(len(d.history.b)) > d.o.maxDecodedSize {
+		if uint64(len(d.history.b)-crcStart) > d.o.maxDecodedSize {
+			println("runDecoder: maxDecodedSize exceeded", uint64(len(d.history.b)-crcStart), ">", d.o.maxDecodedSize)
+			err = ErrDecoderSizeExceeded
+			break
+		}
+		if d.o.limitToCap && len(d.history.b) > cap(dst) {
+			println("runDecoder: cap exceeded", uint64(len(d.history.b)), ">", cap(dst))
 			err = ErrDecoderSizeExceeded
 			break
 		}

vendor/github.com/klauspost/compress/zstd/fse_decoder_amd64.go

@@ -21,7 +21,8 @@ type buildDtableAsmContext struct {
 
 // buildDtable_asm is an x86 assembly implementation of fseDecoder.buildDtable.
 // Function returns non-zero exit code on error.
-// go:noescape
+//
+//go:noescape
 func buildDtable_asm(s *fseDecoder, ctx *buildDtableAsmContext) int
 
 // please keep in sync with _generate/gen_fse.go
@@ -34,8 +35,8 @@ const (
 // buildDtable will build the decoding table.
 func (s *fseDecoder) buildDtable() error {
 	ctx := buildDtableAsmContext{
-		stateTable: (*uint16)(&s.stateTable[0]),
-		norm:       (*int16)(&s.norm[0]),
+		stateTable: &s.stateTable[0],
+		norm:       &s.norm[0],
 		dt:         (*uint64)(&s.dt[0]),
 	}
 	code := buildDtable_asm(s, &ctx)

vendor/github.com/klauspost/compress/zstd/fse_decoder_amd64.s

@@ -1,7 +1,6 @@
 // Code generated by command: go run gen_fse.go -out ../fse_decoder_amd64.s -pkg=zstd. DO NOT EDIT.
 
 //go:build !appengine && !noasm && gc && !noasm
-// +build !appengine,!noasm,gc,!noasm
 
 // func buildDtable_asm(s *fseDecoder, ctx *buildDtableAsmContext) int
 TEXT ·buildDtable_asm(SB), $0-24

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

@@ -37,26 +37,23 @@ func (h *history) reset() {
 	h.ignoreBuffer = 0
 	h.error = false
 	h.recentOffsets = [3]int{1, 4, 8}
-	if f := h.decoders.litLengths.fse; f != nil && !f.preDefined {
-		fseDecoderPool.Put(f)
-	}
-	if f := h.decoders.offsets.fse; f != nil && !f.preDefined {
-		fseDecoderPool.Put(f)
-	}
-	if f := h.decoders.matchLengths.fse; f != nil && !f.preDefined {
-		fseDecoderPool.Put(f)
-	}
+	h.decoders.freeDecoders()
 	h.decoders = sequenceDecs{br: h.decoders.br}
-	if h.huffTree != nil {
-		if h.dict == nil || h.dict.litEnc != h.huffTree {
-			huffDecoderPool.Put(h.huffTree)
-		}
-	}
+	h.freeHuffDecoder()
 	h.huffTree = nil
 	h.dict = nil
 	//printf("history created: %+v (l: %d, c: %d)", *h, len(h.b), cap(h.b))
 }
 
+func (h *history) freeHuffDecoder() {
+	if h.huffTree != nil {
+		if h.dict == nil || h.dict.litEnc != h.huffTree {
+			huffDecoderPool.Put(h.huffTree)
+			h.huffTree = nil
+		}
+	}
+}
+
 func (h *history) setDict(dict *dict) {
 	if dict == nil {
 		return

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

@@ -99,6 +99,21 @@ func (s *sequenceDecs) initialize(br *bitReader, hist *history, out []byte) erro
 	return nil
 }
 
+func (s *sequenceDecs) freeDecoders() {
+	if f := s.litLengths.fse; f != nil && !f.preDefined {
+		fseDecoderPool.Put(f)
+		s.litLengths.fse = nil
+	}
+	if f := s.offsets.fse; f != nil && !f.preDefined {
+		fseDecoderPool.Put(f)
+		s.offsets.fse = nil
+	}
+	if f := s.matchLengths.fse; f != nil && !f.preDefined {
+		fseDecoderPool.Put(f)
+		s.matchLengths.fse = nil
+	}
+}
+
 // execute will execute the decoded sequence with the provided history.
 // The sequence must be evaluated before being sent.
 func (s *sequenceDecs) execute(seqs []seqVals, hist []byte) error {
@@ -299,7 +314,10 @@ func (s *sequenceDecs) decodeSync(hist []byte) error {
 		}
 		size := ll + ml + len(out)
 		if size-startSize > maxBlockSize {
-			return fmt.Errorf("output (%d) bigger than max block size (%d)", size-startSize, maxBlockSize)
+			if size-startSize == 424242 {
+				panic("here")
+			}
+			return fmt.Errorf("output bigger than max block size (%d)", maxBlockSize)
 		}
 		if size > cap(out) {
 			// Not enough size, which can happen under high volume block streaming conditions
@@ -411,7 +429,7 @@ func (s *sequenceDecs) decodeSync(hist []byte) error {
 
 	// Check if space for literals
 	if size := len(s.literals) + len(s.out) - startSize; size > maxBlockSize {
-		return fmt.Errorf("output (%d) bigger than max block size (%d)", size, maxBlockSize)
+		return fmt.Errorf("output bigger than max block size (%d)", maxBlockSize)
 	}
 
 	// Add final literals

vendor/github.com/klauspost/compress/zstd/seqdec_amd64.go

@@ -32,18 +32,22 @@ type decodeSyncAsmContext struct {
 // sequenceDecs_decodeSync_amd64 implements the main loop of sequenceDecs.decodeSync in x86 asm.
 //
 // Please refer to seqdec_generic.go for the reference implementation.
+//
 //go:noescape
 func sequenceDecs_decodeSync_amd64(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int
 
 // sequenceDecs_decodeSync_bmi2 implements the main loop of sequenceDecs.decodeSync in x86 asm with BMI2 extensions.
+//
 //go:noescape
 func sequenceDecs_decodeSync_bmi2(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int
 
 // sequenceDecs_decodeSync_safe_amd64 does the same as above, but does not write more than output buffer.
+//
 //go:noescape
 func sequenceDecs_decodeSync_safe_amd64(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int
 
 // sequenceDecs_decodeSync_safe_bmi2 does the same as above, but does not write more than output buffer.
+//
 //go:noescape
 func sequenceDecs_decodeSync_safe_bmi2(s *sequenceDecs, br *bitReader, ctx *decodeSyncAsmContext) int
 
@@ -55,16 +59,22 @@ func (s *sequenceDecs) decodeSyncSimple(hist []byte) (bool, error) {
 	if s.maxSyncLen == 0 && cap(s.out)-len(s.out) < maxCompressedBlockSize {
 		return false, nil
 	}
-	useSafe := false
-	if s.maxSyncLen == 0 && cap(s.out)-len(s.out) < maxCompressedBlockSizeAlloc {
-		useSafe = true
-	}
-	if s.maxSyncLen > 0 && cap(s.out)-len(s.out)-compressedBlockOverAlloc < int(s.maxSyncLen) {
-		useSafe = true
-	}
-	if cap(s.literals) < len(s.literals)+compressedBlockOverAlloc {
-		useSafe = true
-	}
+
+	// FIXME: Using unsafe memory copies leads to rare, random crashes
+	// with fuzz testing. It is therefore disabled for now.
+	const useSafe = true
+	/*
+		useSafe := false
+		if s.maxSyncLen == 0 && cap(s.out)-len(s.out) < maxCompressedBlockSizeAlloc {
+			useSafe = true
+		}
+		if s.maxSyncLen > 0 && cap(s.out)-len(s.out)-compressedBlockOverAlloc < int(s.maxSyncLen) {
+			useSafe = true
+		}
+		if cap(s.literals) < len(s.literals)+compressedBlockOverAlloc {
+			useSafe = true
+		}
+	*/
 
 	br := s.br
 
@@ -129,7 +139,7 @@ func (s *sequenceDecs) decodeSyncSimple(hist []byte) (bool, error) {
 		if debugDecoder {
 			println("msl:", s.maxSyncLen, "cap", cap(s.out), "bef:", startSize, "sz:", size-startSize, "mbs:", maxBlockSize, "outsz:", cap(s.out)-startSize)
 		}
-		return true, fmt.Errorf("output (%d) bigger than max block size (%d)", size-startSize, maxBlockSize)
+		return true, fmt.Errorf("output bigger than max block size (%d)", maxBlockSize)
 
 	default:
 		return true, fmt.Errorf("sequenceDecs_decode returned erronous code %d", errCode)
@@ -137,7 +147,8 @@ func (s *sequenceDecs) decodeSyncSimple(hist []byte) (bool, error) {
 
 	s.seqSize += ctx.litRemain
 	if s.seqSize > maxBlockSize {
-		return true, fmt.Errorf("output (%d) bigger than max block size (%d)", s.seqSize, maxBlockSize)
+		return true, fmt.Errorf("output bigger than max block size (%d)", maxBlockSize)
+
 	}
 	err := br.close()
 	if err != nil {
@@ -195,20 +206,24 @@ const errorNotEnoughSpace = 5
 // sequenceDecs_decode implements the main loop of sequenceDecs in x86 asm.
 //
 // Please refer to seqdec_generic.go for the reference implementation.
+//
 //go:noescape
 func sequenceDecs_decode_amd64(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int
 
 // sequenceDecs_decode implements the main loop of sequenceDecs in x86 asm.
 //
 // Please refer to seqdec_generic.go for the reference implementation.
+//
 //go:noescape
 func sequenceDecs_decode_56_amd64(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int
 
 // sequenceDecs_decode implements the main loop of sequenceDecs in x86 asm with BMI2 extensions.
+//
 //go:noescape
 func sequenceDecs_decode_bmi2(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int
 
 // sequenceDecs_decode implements the main loop of sequenceDecs in x86 asm with BMI2 extensions.
+//
 //go:noescape
 func sequenceDecs_decode_56_bmi2(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int
 
@@ -275,7 +290,7 @@ func (s *sequenceDecs) decode(seqs []seqVals) error {
 
 	s.seqSize += ctx.litRemain
 	if s.seqSize > maxBlockSize {
-		return fmt.Errorf("output (%d) bigger than max block size (%d)", s.seqSize, maxBlockSize)
+		return fmt.Errorf("output bigger than max block size (%d)", maxBlockSize)
 	}
 	err := br.close()
 	if err != nil {
@@ -302,10 +317,12 @@ type executeAsmContext struct {
 // Returns false if a match offset is too big.
 //
 // Please refer to seqdec_generic.go for the reference implementation.
+//
 //go:noescape
 func sequenceDecs_executeSimple_amd64(ctx *executeAsmContext) bool
 
 // Same as above, but with safe memcopies
+//
 //go:noescape
 func sequenceDecs_executeSimple_safe_amd64(ctx *executeAsmContext) bool
 

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

@@ -111,7 +111,7 @@ func (s *sequenceDecs) decode(seqs []seqVals) error {
 		}
 		s.seqSize += ll + ml
 		if s.seqSize > maxBlockSize {
-			return fmt.Errorf("output (%d) bigger than max block size (%d)", s.seqSize, maxBlockSize)
+			return fmt.Errorf("output bigger than max block size (%d)", maxBlockSize)
 		}
 		litRemain -= ll
 		if litRemain < 0 {
@@ -149,7 +149,7 @@ func (s *sequenceDecs) decode(seqs []seqVals) error {
 	}
 	s.seqSize += litRemain
 	if s.seqSize > maxBlockSize {
-		return fmt.Errorf("output (%d) bigger than max block size (%d)", s.seqSize, maxBlockSize)
+		return fmt.Errorf("output bigger than max block size (%d)", maxBlockSize)
 	}
 	err := br.close()
 	if err != nil {