diff options
Diffstat (limited to 'vendor/github.com/klauspost')
25 files changed, 201 insertions, 83 deletions
diff --git a/vendor/github.com/klauspost/compress/README.md b/vendor/github.com/klauspost/compress/README.md index ad5c63a82..2d6b01077 100644 --- a/vendor/github.com/klauspost/compress/README.md +++ b/vendor/github.com/klauspost/compress/README.md @@ -17,6 +17,12 @@ This package provides various compression algorithms. # changelog
+* July 21, 2022 (v1.15.9)
+
+ * zstd: Fix decoder crash on amd64 (no BMI) on invalid input https://github.com/klauspost/compress/pull/645
+ * zstd: Disable decoder extended memory copies (amd64) due to possible crashes https://github.com/klauspost/compress/pull/644
+ * zstd: Allow single segments up to "max decoded size" by @klauspost in https://github.com/klauspost/compress/pull/643
+
* July 13, 2022 (v1.15.8)
* gzip: fix stack exhaustion bug in Reader.Read https://github.com/klauspost/compress/pull/641
diff --git a/vendor/github.com/klauspost/compress/flate/deflate.go b/vendor/github.com/klauspost/compress/flate/deflate.go index f8435998e..f00da5b21 100644 --- a/vendor/github.com/klauspost/compress/flate/deflate.go +++ b/vendor/github.com/klauspost/compress/flate/deflate.go @@ -131,7 +131,8 @@ func (d *compressor) fillDeflate(b []byte) int { s := d.state if s.index >= 2*windowSize-(minMatchLength+maxMatchLength) { // shift the window by windowSize - copy(d.window[:], d.window[windowSize:2*windowSize]) + //copy(d.window[:], d.window[windowSize:2*windowSize]) + *(*[windowSize]byte)(d.window) = *(*[windowSize]byte)(d.window[windowSize:]) s.index -= windowSize d.windowEnd -= windowSize if d.blockStart >= windowSize { diff --git a/vendor/github.com/klauspost/compress/flate/dict_decoder.go b/vendor/github.com/klauspost/compress/flate/dict_decoder.go index 71c75a065..bb36351a5 100644 --- a/vendor/github.com/klauspost/compress/flate/dict_decoder.go +++ b/vendor/github.com/klauspost/compress/flate/dict_decoder.go @@ -7,19 +7,19 @@ package flate // dictDecoder implements the LZ77 sliding dictionary as used in decompression. // LZ77 decompresses data through sequences of two forms of commands: // -// * Literal insertions: Runs of one or more symbols are inserted into the data -// stream as is. This is accomplished through the writeByte method for a -// single symbol, or combinations of writeSlice/writeMark for multiple symbols. -// Any valid stream must start with a literal insertion if no preset dictionary -// is used. +// - Literal insertions: Runs of one or more symbols are inserted into the data +// stream as is. This is accomplished through the writeByte method for a +// single symbol, or combinations of writeSlice/writeMark for multiple symbols. +// Any valid stream must start with a literal insertion if no preset dictionary +// is used. // -// * Backward copies: Runs of one or more symbols are copied from previously -// emitted data. Backward copies come as the tuple (dist, length) where dist -// determines how far back in the stream to copy from and length determines how -// many bytes to copy. Note that it is valid for the length to be greater than -// the distance. Since LZ77 uses forward copies, that situation is used to -// perform a form of run-length encoding on repeated runs of symbols. -// The writeCopy and tryWriteCopy are used to implement this command. +// - Backward copies: Runs of one or more symbols are copied from previously +// emitted data. Backward copies come as the tuple (dist, length) where dist +// determines how far back in the stream to copy from and length determines how +// many bytes to copy. Note that it is valid for the length to be greater than +// the distance. Since LZ77 uses forward copies, that situation is used to +// perform a form of run-length encoding on repeated runs of symbols. +// The writeCopy and tryWriteCopy are used to implement this command. // // For performance reasons, this implementation performs little to no sanity // checks about the arguments. As such, the invariants documented for each diff --git a/vendor/github.com/klauspost/compress/flate/fast_encoder.go b/vendor/github.com/klauspost/compress/flate/fast_encoder.go index f781aaa62..cd77a2cc4 100644 --- a/vendor/github.com/klauspost/compress/flate/fast_encoder.go +++ b/vendor/github.com/klauspost/compress/flate/fast_encoder.go @@ -104,7 +104,8 @@ func (e *fastGen) addBlock(src []byte) int32 { } // Move down offset := int32(len(e.hist)) - maxMatchOffset - copy(e.hist[0:maxMatchOffset], e.hist[offset:]) + // copy(e.hist[0:maxMatchOffset], e.hist[offset:]) + *(*[maxMatchOffset]byte)(e.hist) = *(*[maxMatchOffset]byte)(e.hist[offset:]) e.cur += offset e.hist = e.hist[:maxMatchOffset] } diff --git a/vendor/github.com/klauspost/compress/flate/huffman_bit_writer.go b/vendor/github.com/klauspost/compress/flate/huffman_bit_writer.go index 40ef45c2f..89a5dd89f 100644 --- a/vendor/github.com/klauspost/compress/flate/huffman_bit_writer.go +++ b/vendor/github.com/klauspost/compress/flate/huffman_bit_writer.go @@ -265,9 +265,9 @@ func (w *huffmanBitWriter) writeBytes(bytes []byte) { // Codes 0-15 are single byte codes. Codes 16-18 are followed by additional // information. Code badCode is an end marker // -// numLiterals The number of literals in literalEncoding -// numOffsets The number of offsets in offsetEncoding -// litenc, offenc The literal and offset encoder to use +// numLiterals The number of literals in literalEncoding +// numOffsets The number of offsets in offsetEncoding +// litenc, offenc The literal and offset encoder to use func (w *huffmanBitWriter) generateCodegen(numLiterals int, numOffsets int, litEnc, offEnc *huffmanEncoder) { for i := range w.codegenFreq { w.codegenFreq[i] = 0 @@ -460,9 +460,9 @@ func (w *huffmanBitWriter) writeOutBits() { // Write the header of a dynamic Huffman block to the output stream. // -// numLiterals The number of literals specified in codegen -// numOffsets The number of offsets specified in codegen -// numCodegens The number of codegens used in codegen +// numLiterals The number of literals specified in codegen +// numOffsets The number of offsets specified in codegen +// numCodegens The number of codegens used in codegen func (w *huffmanBitWriter) writeDynamicHeader(numLiterals int, numOffsets int, numCodegens int, isEof bool) { if w.err != nil { return @@ -790,9 +790,11 @@ func (w *huffmanBitWriter) fillTokens() { // and offsetEncoding. // The number of literal and offset tokens is returned. func (w *huffmanBitWriter) indexTokens(t *tokens, filled bool) (numLiterals, numOffsets int) { - copy(w.literalFreq[:], t.litHist[:]) - copy(w.literalFreq[256:], t.extraHist[:]) - copy(w.offsetFreq[:], t.offHist[:offsetCodeCount]) + //copy(w.literalFreq[:], t.litHist[:]) + *(*[256]uint16)(w.literalFreq[:]) = t.litHist + //copy(w.literalFreq[256:], t.extraHist[:]) + *(*[32]uint16)(w.literalFreq[256:]) = t.extraHist + w.offsetFreq = t.offHist if t.n == 0 { return diff --git a/vendor/github.com/klauspost/compress/flate/huffman_code.go b/vendor/github.com/klauspost/compress/flate/huffman_code.go index 5ac144f28..be7b58b47 100644 --- a/vendor/github.com/klauspost/compress/flate/huffman_code.go +++ b/vendor/github.com/klauspost/compress/flate/huffman_code.go @@ -168,13 +168,18 @@ func (h *huffmanEncoder) canReuseBits(freq []uint16) int { // The cases of 0, 1, and 2 literals are handled by special case code. // // list An array of the literals with non-zero frequencies -// and their associated frequencies. The array is in order of increasing -// frequency, and has as its last element a special element with frequency -// MaxInt32 +// +// and their associated frequencies. The array is in order of increasing +// frequency, and has as its last element a special element with frequency +// MaxInt32 +// // maxBits The maximum number of bits that should be used to encode any literal. -// Must be less than 16. +// +// Must be less than 16. +// // return An integer array in which array[i] indicates the number of literals -// that should be encoded in i bits. +// +// that should be encoded in i bits. func (h *huffmanEncoder) bitCounts(list []literalNode, maxBits int32) []int32 { if maxBits >= maxBitsLimit { panic("flate: maxBits too large") diff --git a/vendor/github.com/klauspost/compress/flate/level5.go b/vendor/github.com/klauspost/compress/flate/level5.go index 4b97576bd..ef6339d95 100644 --- a/vendor/github.com/klauspost/compress/flate/level5.go +++ b/vendor/github.com/klauspost/compress/flate/level5.go @@ -191,14 +191,21 @@ func (e *fastEncL5) Encode(dst *tokens, src []byte) { // Try to locate a better match by checking the end of best match... if sAt := s + l; l < 30 && sAt < sLimit { + // Allow some bytes at the beginning to mismatch. + // Sweet spot is 2/3 bytes depending on input. + // 3 is only a little better when it is but sometimes a lot worse. + // The skipped bytes are tested in Extend backwards, + // and still picked up as part of the match if they do. + const skipBeginning = 2 eLong := e.bTable[hash7(load6432(src, sAt), tableBits)].Cur.offset - // Test current - t2 := eLong - e.cur - l - off := s - t2 + t2 := eLong - e.cur - l + skipBeginning + s2 := s + skipBeginning + off := s2 - t2 if t2 >= 0 && off < maxMatchOffset && off > 0 { - if l2 := e.matchlenLong(s, t2, src); l2 > l { + if l2 := e.matchlenLong(s2, t2, src); l2 > l { t = t2 l = l2 + s = s2 } } } diff --git a/vendor/github.com/klauspost/compress/flate/level6.go b/vendor/github.com/klauspost/compress/flate/level6.go index 62888edf3..85e4b2095 100644 --- a/vendor/github.com/klauspost/compress/flate/level6.go +++ b/vendor/github.com/klauspost/compress/flate/level6.go @@ -213,24 +213,33 @@ func (e *fastEncL6) Encode(dst *tokens, src []byte) { // Try to locate a better match by checking the end-of-match... if sAt := s + l; sAt < sLimit { + // Allow some bytes at the beginning to mismatch. + // Sweet spot is 2/3 bytes depending on input. + // 3 is only a little better when it is but sometimes a lot worse. + // The skipped bytes are tested in Extend backwards, + // and still picked up as part of the match if they do. + const skipBeginning = 2 eLong := &e.bTable[hash7(load6432(src, sAt), tableBits)] // Test current - t2 := eLong.Cur.offset - e.cur - l - off := s - t2 + t2 := eLong.Cur.offset - e.cur - l + skipBeginning + s2 := s + skipBeginning + off := s2 - t2 if off < maxMatchOffset { if off > 0 && t2 >= 0 { - if l2 := e.matchlenLong(s, t2, src); l2 > l { + if l2 := e.matchlenLong(s2, t2, src); l2 > l { t = t2 l = l2 + s = s2 } } // Test next: - t2 = eLong.Prev.offset - e.cur - l - off := s - t2 + t2 = eLong.Prev.offset - e.cur - l + skipBeginning + off := s2 - t2 if off > 0 && off < maxMatchOffset && t2 >= 0 { - if l2 := e.matchlenLong(s, t2, src); l2 > l { + if l2 := e.matchlenLong(s2, t2, src); l2 > l { t = t2 l = l2 + s = s2 } } } diff --git a/vendor/github.com/klauspost/compress/huff0/decompress.go b/vendor/github.com/klauspost/compress/huff0/decompress.go index c0c48bd70..42a237eac 100644 --- a/vendor/github.com/klauspost/compress/huff0/decompress.go +++ b/vendor/github.com/klauspost/compress/huff0/decompress.go @@ -763,17 +763,20 @@ func (d *Decoder) decompress4X8bit(dst, src []byte) ([]byte, error) { d.bufs.Put(buf) return nil, errors.New("corruption detected: stream overrun 1") } - copy(out, buf[0][:]) - copy(out[dstEvery:], buf[1][:]) - copy(out[dstEvery*2:], buf[2][:]) - copy(out[dstEvery*3:], buf[3][:]) - out = out[bufoff:] - decoded += bufoff * 4 // There must at least be 3 buffers left. - if len(out) < dstEvery*3 { + if len(out)-bufoff < dstEvery*3 { d.bufs.Put(buf) return nil, errors.New("corruption detected: stream overrun 2") } + //copy(out, buf[0][:]) + //copy(out[dstEvery:], buf[1][:]) + //copy(out[dstEvery*2:], buf[2][:]) + *(*[bufoff]byte)(out) = buf[0] + *(*[bufoff]byte)(out[dstEvery:]) = buf[1] + *(*[bufoff]byte)(out[dstEvery*2:]) = buf[2] + *(*[bufoff]byte)(out[dstEvery*3:]) = buf[3] + out = out[bufoff:] + decoded += bufoff * 4 } } if off > 0 { @@ -997,17 +1000,22 @@ func (d *Decoder) decompress4X8bitExactly(dst, src []byte) ([]byte, error) { d.bufs.Put(buf) return nil, errors.New("corruption detected: stream overrun 1") } - copy(out, buf[0][:]) - copy(out[dstEvery:], buf[1][:]) - copy(out[dstEvery*2:], buf[2][:]) - copy(out[dstEvery*3:], buf[3][:]) - out = out[bufoff:] - decoded += bufoff * 4 // There must at least be 3 buffers left. - if len(out) < dstEvery*3 { + if len(out)-bufoff < dstEvery*3 { d.bufs.Put(buf) return nil, errors.New("corruption detected: stream overrun 2") } + + //copy(out, buf[0][:]) + //copy(out[dstEvery:], buf[1][:]) + //copy(out[dstEvery*2:], buf[2][:]) + // copy(out[dstEvery*3:], buf[3][:]) + *(*[bufoff]byte)(out) = buf[0] + *(*[bufoff]byte)(out[dstEvery:]) = buf[1] + *(*[bufoff]byte)(out[dstEvery*2:]) = buf[2] + *(*[bufoff]byte)(out[dstEvery*3:]) = buf[3] + out = out[bufoff:] + decoded += bufoff * 4 } } if off > 0 { diff --git a/vendor/github.com/klauspost/compress/huff0/decompress_amd64.go b/vendor/github.com/klauspost/compress/huff0/decompress_amd64.go index 9f3e9f79e..ba7e8e6b0 100644 --- a/vendor/github.com/klauspost/compress/huff0/decompress_amd64.go +++ b/vendor/github.com/klauspost/compress/huff0/decompress_amd64.go @@ -14,12 +14,14 @@ import ( // decompress4x_main_loop_x86 is an x86 assembler implementation // of Decompress4X when tablelog > 8. +// //go:noescape func decompress4x_main_loop_amd64(ctx *decompress4xContext) // decompress4x_8b_loop_x86 is an x86 assembler implementation // of Decompress4X when tablelog <= 8 which decodes 4 entries // per loop. +// //go:noescape func decompress4x_8b_main_loop_amd64(ctx *decompress4xContext) @@ -145,11 +147,13 @@ func (d *Decoder) Decompress4X(dst, src []byte) ([]byte, error) { // decompress4x_main_loop_x86 is an x86 assembler implementation // of Decompress1X when tablelog > 8. +// //go:noescape func decompress1x_main_loop_amd64(ctx *decompress1xContext) // decompress4x_main_loop_x86 is an x86 with BMI2 assembler implementation // of Decompress1X when tablelog > 8. +// //go:noescape func decompress1x_main_loop_bmi2(ctx *decompress1xContext) diff --git a/vendor/github.com/klauspost/compress/huff0/decompress_amd64.s b/vendor/github.com/klauspost/compress/huff0/decompress_amd64.s index dd1a5aecd..8d2187a2c 100644 --- a/vendor/github.com/klauspost/compress/huff0/decompress_amd64.s +++ b/vendor/github.com/klauspost/compress/huff0/decompress_amd64.s @@ -1,7 +1,6 @@ // Code generated by command: go run gen.go -out ../decompress_amd64.s -pkg=huff0. DO NOT EDIT. //go:build amd64 && !appengine && !noasm && gc -// +build amd64,!appengine,!noasm,gc // func decompress4x_main_loop_amd64(ctx *decompress4xContext) TEXT ·decompress4x_main_loop_amd64(SB), $0-8 diff --git a/vendor/github.com/klauspost/compress/huff0/decompress_generic.go b/vendor/github.com/klauspost/compress/huff0/decompress_generic.go index 4f6f37cb2..908c17de6 100644 --- a/vendor/github.com/klauspost/compress/huff0/decompress_generic.go +++ b/vendor/github.com/klauspost/compress/huff0/decompress_generic.go @@ -122,17 +122,21 @@ func (d *Decoder) Decompress4X(dst, src []byte) ([]byte, error) { d.bufs.Put(buf) return nil, errors.New("corruption detected: stream overrun 1") } - copy(out, buf[0][:]) - copy(out[dstEvery:], buf[1][:]) - copy(out[dstEvery*2:], buf[2][:]) - copy(out[dstEvery*3:], buf[3][:]) - out = out[bufoff:] - decoded += bufoff * 4 // There must at least be 3 buffers left. - if len(out) < dstEvery*3 { + if len(out)-bufoff < dstEvery*3 { d.bufs.Put(buf) return nil, errors.New("corruption detected: stream overrun 2") } + //copy(out, buf[0][:]) + //copy(out[dstEvery:], buf[1][:]) + //copy(out[dstEvery*2:], buf[2][:]) + //copy(out[dstEvery*3:], buf[3][:]) + *(*[bufoff]byte)(out) = buf[0] + *(*[bufoff]byte)(out[dstEvery:]) = buf[1] + *(*[bufoff]byte)(out[dstEvery*2:]) = buf[2] + *(*[bufoff]byte)(out[dstEvery*3:]) = buf[3] + out = out[bufoff:] + decoded += bufoff * 4 } } if off > 0 { diff --git a/vendor/github.com/klauspost/compress/internal/snapref/encode_other.go b/vendor/github.com/klauspost/compress/internal/snapref/encode_other.go index 511bba65d..298c4f8e9 100644 --- a/vendor/github.com/klauspost/compress/internal/snapref/encode_other.go +++ b/vendor/github.com/klauspost/compress/internal/snapref/encode_other.go @@ -18,6 +18,7 @@ func load64(b []byte, i int) uint64 { // emitLiteral writes a literal chunk and returns the number of bytes written. // // It assumes that: +// // dst is long enough to hold the encoded bytes // 1 <= len(lit) && len(lit) <= 65536 func emitLiteral(dst, lit []byte) int { @@ -42,6 +43,7 @@ func emitLiteral(dst, lit []byte) int { // emitCopy writes a copy chunk and returns the number of bytes written. // // It assumes that: +// // dst is long enough to hold the encoded bytes // 1 <= offset && offset <= 65535 // 4 <= length && length <= 65535 @@ -89,6 +91,7 @@ func emitCopy(dst []byte, offset, length int) int { // src[i:i+k-j] and src[j:k] have the same contents. // // It assumes that: +// // 0 <= i && i < j && j <= len(src) func extendMatch(src []byte, i, j int) int { for ; j < len(src) && src[i] == src[j]; i, j = i+1, j+1 { @@ -105,8 +108,9 @@ func hash(u, shift uint32) uint32 { // been written. // // It also assumes that: +// // len(dst) >= MaxEncodedLen(len(src)) && -// minNonLiteralBlockSize <= len(src) && len(src) <= maxBlockSize +// minNonLiteralBlockSize <= len(src) && len(src) <= maxBlockSize func encodeBlock(dst, src []byte) (d int) { // Initialize the hash table. Its size ranges from 1<<8 to 1<<14 inclusive. // The table element type is uint16, as s < sLimit and sLimit < len(src) diff --git a/vendor/github.com/klauspost/compress/zstd/README.md b/vendor/github.com/klauspost/compress/zstd/README.md index beb7fa872..65b38abed 100644 --- a/vendor/github.com/klauspost/compress/zstd/README.md +++ b/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`. diff --git a/vendor/github.com/klauspost/compress/zstd/blockdec.go b/vendor/github.com/klauspost/compress/zstd/blockdec.go index 7eed729be..f52d1aed6 100644 --- a/vendor/github.com/klauspost/compress/zstd/blockdec.go +++ b/vendor/github.com/klauspost/compress/zstd/blockdec.go @@ -10,7 +10,6 @@ import ( "errors" "fmt" "io" - "io/ioutil" "os" "path/filepath" "sync" @@ -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 diff --git a/vendor/github.com/klauspost/compress/zstd/bytebuf.go b/vendor/github.com/klauspost/compress/zstd/bytebuf.go index 2ad02070d..176788f25 100644 --- a/vendor/github.com/klauspost/compress/zstd/bytebuf.go +++ b/vendor/github.com/klauspost/compress/zstd/bytebuf.go @@ -7,7 +7,6 @@ package zstd import ( "fmt" "io" - "io/ioutil" ) type byteBuffer interface { @@ -124,7 +123,7 @@ func (r *readerWrapper) readByte() (byte, error) { } func (r *readerWrapper) skipN(n int64) error { - n2, err := io.CopyN(ioutil.Discard, r.r, n) + n2, err := io.CopyN(io.Discard, r.r, n) if n2 != n { err = io.ErrUnexpectedEOF } diff --git a/vendor/github.com/klauspost/compress/zstd/decoder.go b/vendor/github.com/klauspost/compress/zstd/decoder.go index d212f4737..6104eb793 100644 --- a/vendor/github.com/klauspost/compress/zstd/decoder.go +++ b/vendor/github.com/klauspost/compress/zstd/decoder.go @@ -312,6 +312,7 @@ 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) @@ -354,7 +355,16 @@ func (d *Decoder) DecodeAll(input, dst []byte) ([]byte, error) { 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) { @@ -364,7 +374,7 @@ 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 @@ -382,6 +392,9 @@ 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") @@ -852,6 +865,10 @@ 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 { diff --git a/vendor/github.com/klauspost/compress/zstd/decoder_options.go b/vendor/github.com/klauspost/compress/zstd/decoder_options.go index c70e6fa0f..666c2715f 100644 --- a/vendor/github.com/klauspost/compress/zstd/decoder_options.go +++ b/vendor/github.com/klauspost/compress/zstd/decoder_options.go @@ -20,6 +20,7 @@ type decoderOptions struct { maxWindowSize uint64 dicts []dict ignoreChecksum bool + limitToCap bool } func (o *decoderOptions) setDefault() { @@ -114,6 +115,17 @@ 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 + } +} + // IgnoreChecksum allows to forcibly ignore checksum checking. func IgnoreChecksum(b bool) DOption { return func(o *decoderOptions) error { diff --git a/vendor/github.com/klauspost/compress/zstd/enc_better.go b/vendor/github.com/klauspost/compress/zstd/enc_better.go index c769f6941..d70e3fd3d 100644 --- a/vendor/github.com/klauspost/compress/zstd/enc_better.go +++ b/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") diff --git a/vendor/github.com/klauspost/compress/zstd/enc_dfast.go b/vendor/github.com/klauspost/compress/zstd/enc_dfast.go index 7ff0c64fa..1f4a9a245 100644 --- a/vendor/github.com/klauspost/compress/zstd/enc_dfast.go +++ b/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 } } diff --git a/vendor/github.com/klauspost/compress/zstd/enc_fast.go b/vendor/github.com/klauspost/compress/zstd/enc_fast.go index f51ab529a..181edc02b 100644 --- a/vendor/github.com/klauspost/compress/zstd/enc_fast.go +++ b/vendor/github.com/klauspost/compress/zstd/enc_fast.go @@ -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 diff --git a/vendor/github.com/klauspost/compress/zstd/framedec.go b/vendor/github.com/klauspost/compress/zstd/framedec.go index 9568a4ba3..1559a2038 100644 --- a/vendor/github.com/klauspost/compress/zstd/framedec.go +++ b/vendor/github.com/klauspost/compress/zstd/framedec.go @@ -353,12 +353,23 @@ 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)-len(dst)) < d.history.decoders.maxSyncLen { // Alloc for output dst2 := make([]byte, len(dst), d.history.decoders.maxSyncLen+compressedBlockOverAlloc) copy(dst2, dst) @@ -378,7 +389,13 @@ 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 } diff --git a/vendor/github.com/klauspost/compress/zstd/fse_decoder_amd64.s b/vendor/github.com/klauspost/compress/zstd/fse_decoder_amd64.s index da32b4420..bcde39869 100644 --- a/vendor/github.com/klauspost/compress/zstd/fse_decoder_amd64.s +++ b/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 diff --git a/vendor/github.com/klauspost/compress/zstd/seqdec_amd64.go b/vendor/github.com/klauspost/compress/zstd/seqdec_amd64.go index 7598c1018..1c704d30c 100644 --- a/vendor/github.com/klauspost/compress/zstd/seqdec_amd64.go +++ b/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 @@ -201,20 +205,24 @@ 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 @@ -308,10 +316,12 @@ 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 diff --git a/vendor/github.com/klauspost/compress/zstd/seqdec_amd64.s b/vendor/github.com/klauspost/compress/zstd/seqdec_amd64.s index 27e76774c..52e5703c2 100644 --- a/vendor/github.com/klauspost/compress/zstd/seqdec_amd64.s +++ b/vendor/github.com/klauspost/compress/zstd/seqdec_amd64.s @@ -1,7 +1,6 @@ // Code generated by command: go run gen.go -out ../seqdec_amd64.s -pkg=zstd. DO NOT EDIT. //go:build !appengine && !noasm && gc && !noasm -// +build !appengine,!noasm,gc,!noasm // func sequenceDecs_decode_amd64(s *sequenceDecs, br *bitReader, ctx *decodeAsmContext) int // Requires: CMOV |