Как ZFS хранит данные

#include <iostream>
#include <fstream>
#include <cstdint>
#include <cstring>

using namespace std;

static int LZ4_uncompress_unknownOutputSize(const char *source, char *dest,
int isize, int maxOutputSize);


#define BE_IN8(xa) \
        *((uint8_t *)(xa))

#define BE_IN16(xa) \
(((uint16_t)BE_IN8(xa) << 8) | BE_IN8((uint8_t *)(xa)+1))

#define BE_IN32(xa) \
(((uint32_t)BE_IN16(xa) << 16) | BE_IN16((uint8_t *)(xa)+2))


#define COMPRESSIONLEVEL 12
#define NOTCOMPRESSIBLE_CONFIRMATION 6

/*
 *
 * CPU Feature Detection
 */

/* 32 or 64 bits ? */
#if defined(_LP64)
#define LZ4_ARCH64 1
#else
#define LZ4_ARCH64 0
#endif

/*
 * Little Endian or Big Endian?
 * Note: overwrite the below #define if you know your architecture endianess.
 */
#if defined(_BIG_ENDIAN)
#define LZ4_BIG_ENDIAN 1
#else
/*
 * Little Endian assumed. PDP Endian and other very rare endian format
 * are unsupported.
 */
#undef LZ4_BIG_ENDIAN
#endif

/*
 * Unaligned memory access is automatically enabled for "common" CPU,
 * such as x86. For others CPU, the compiler will be more cautious, and
 * insert extra code to ensure aligned access is respected. If you know
 * your target CPU supports unaligned memory access, you may want to
 * force this option manually to improve performance
 */
#if defined(__ARM_FEATURE_UNALIGNED)
#define LZ4_FORCE_UNALIGNED_ACCESS 1
#endif

/*
 * Illumos : we can't use GCC's __builtin_ctz family of builtins in the
 * kernel
 * Linux : we can use GCC's __builtin_ctz family of builtins in the
 * kernel
 */
#undef  LZ4_FORCE_SW_BITCOUNT
#if defined(__sparc)
#define LZ4_FORCE_SW_BITCOUNT
#endif

/*
 * Compiler Options
 */
/* Disable restrict */
#define restrict

/*
 * Linux : GCC_VERSION is defined as of 3.9-rc1, so undefine it.
 * torvalds/linux@3f3f8d2f48acfd8ed3b8e6b7377935da57b27b16
 */
#ifdef GCC_VERSION
#undef GCC_VERSION
#endif

#define GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)

#if (GCC_VERSION >= 302) || (__INTEL_COMPILER >= 800) || defined(__clang__)
#define expect(expr, value)    (__builtin_expect((expr), (value)))
#else
#define expect(expr, value)    (expr)
#endif

#ifndef likely
#define likely(expr)    expect((expr) != 0, 1)
#endif

#ifndef unlikely
#define unlikely(expr)  expect((expr) != 0, 0)
#endif

#define lz4_bswap16(x) ((unsigned short int) ((((x) >> 8) & 0xffu) | \
        (((x) & 0xffu) << 8)))

/* Basic types */
#define BYTE    uint8_t
#define U16     uint16_t
#define U32     uint32_t
#define S32     int32_t
#define U64     uint64_t

#ifndef LZ4_FORCE_UNALIGNED_ACCESS
#pragma pack(1)
#endif

typedef struct _U16_S {
        U16 v;
} U16_S;
typedef struct _U32_S {
        U32 v;
} U32_S;
typedef struct _U64_S {
        U64 v;
} U64_S;

#ifndef LZ4_FORCE_UNALIGNED_ACCESS
#pragma pack()
#endif

#define A64(x) (((U64_S *)(x))->v)
#define A32(x) (((U32_S *)(x))->v)
#define A16(x) (((U16_S *)(x))->v)

/*
 * Constants
 */
#define MINMATCH 4

#define HASH_LOG COMPRESSIONLEVEL
#define HASHTABLESIZE (1 << HASH_LOG)
#define HASH_MASK (HASHTABLESIZE - 1)

#define SKIPSTRENGTH (NOTCOMPRESSIBLE_CONFIRMATION > 2 ? \
        NOTCOMPRESSIBLE_CONFIRMATION : 2)

#define COPYLENGTH 8
#define LASTLITERALS 5
#define MFLIMIT (COPYLENGTH + MINMATCH)
#define MINLENGTH (MFLIMIT + 1)

#define MAXD_LOG 16
#define MAX_DISTANCE ((1 << MAXD_LOG) - 1)

#define ML_BITS 4
#define ML_MASK ((1U<<ML_BITS)-1)
#define RUN_BITS (8-ML_BITS)
#define RUN_MASK ((1U<<RUN_BITS)-1)

/*
 * Architecture-specific macros
 */
#if LZ4_ARCH64
#define STEPSIZE 8
#define UARCH U64
#define AARCH A64
#define LZ4_COPYSTEP(s, d)      A64(d) = A64(s); d += 8; s += 8;
#define LZ4_COPYPACKET(s, d)    LZ4_COPYSTEP(s, d)
#define LZ4_SECURECOPY(s, d, e) if (d < e) LZ4_WILDCOPY(s, d, e)
#define HTYPE U32
#define INITBASE(base)          const BYTE* const base = ip
#else /* !LZ4_ARCH64 */
#define STEPSIZE 4
#define UARCH U32
#define AARCH A32
#define LZ4_COPYSTEP(s, d)      A32(d) = A32(s); d += 4; s += 4;
#define LZ4_COPYPACKET(s, d)    LZ4_COPYSTEP(s, d); LZ4_COPYSTEP(s, d);
#define LZ4_SECURECOPY          LZ4_WILDCOPY
#define HTYPE const BYTE *
#define INITBASE(base)          const int base = 0
#endif /* !LZ4_ARCH64 */

#if (defined(LZ4_BIG_ENDIAN) && !defined(BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE))
#define LZ4_READ_LITTLEENDIAN_16(d, s, p) \
        { U16 v = A16(p); v = lz4_bswap16(v); d = (s) - v; }
#define LZ4_WRITE_LITTLEENDIAN_16(p, i) \
        { U16 v = (U16)(i); v = lz4_bswap16(v); A16(p) = v; p += 2; }
#else
#define LZ4_READ_LITTLEENDIAN_16(d, s, p) { d = (s) - A16(p); }
#define LZ4_WRITE_LITTLEENDIAN_16(p, v)  { A16(p) = v; p += 2; }
#endif


/* Local structures */
struct refTables {
        HTYPE hashTable[HASHTABLESIZE];
};


/* Macros */
#define LZ4_HASH_FUNCTION(i) (((i) * 2654435761U) >> ((MINMATCH * 8) - \
        HASH_LOG))
#define LZ4_HASH_VALUE(p) LZ4_HASH_FUNCTION(A32(p))
#define LZ4_WILDCOPY(s, d, e) do { LZ4_COPYPACKET(s, d) } while (d < e);
#define LZ4_BLINDCOPY(s, d, l) { BYTE* e = (d) + l; LZ4_WILDCOPY(s, d, e); \
d = e; }



static int
LZ4_uncompress_unknownOutputSize(const char *source, char *dest, int isize,
    int maxOutputSize)
{
        /* Local Variables */
        const BYTE *restrict ip = (const BYTE *) source;
        const BYTE *const iend = ip + isize;
        const BYTE *ref;

        BYTE *op = (BYTE *) dest;
        BYTE *const oend = op + maxOutputSize;
        BYTE *cpy;

        size_t dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0};
#if LZ4_ARCH64
        size_t dec64table[] = {0, 0, 0, (size_t)-1, 0, 1, 2, 3};
#endif

        /* Main Loop */
        while (ip < iend) {
                unsigned token;
                size_t length;

                /* get runlength */
                token = *ip++;
                if ((length = (token >> ML_BITS)) == RUN_MASK) {
                        int s = 255;
                        while ((ip < iend) && (s == 255)) {
                                s = *ip++;
                                length += s;
                        }
                }
                /* copy literals */
                cpy = op + length;
                /* CORNER-CASE: cpy might overflow. */
                if (cpy < op)
                        goto _output_error;     /* cpy was overflowed, bail! */
                if ((cpy > oend - COPYLENGTH) ||
                    (ip + length > iend - COPYLENGTH)) {
                        if (cpy > oend)
                                /* Error: writes beyond output buffer */
                                goto _output_error;
                        if (ip + length != iend)
                                /*
                                 * Error: LZ4 format requires to consume all
                                 * input at this stage
                                 */
                                goto _output_error;
                        (void) memcpy(op, ip, length);
                        op += length;
                        /* Necessarily EOF, due to parsing restrictions */
                        break;
                }
                LZ4_WILDCOPY(ip, op, cpy);
                ip -= (op - cpy);
                op = cpy;

                /* get offset */
                LZ4_READ_LITTLEENDIAN_16(ref, cpy, ip);
                ip += 2;
                if (ref < (BYTE * const) dest)
                        /*
                         * Error: offset creates reference outside of
                         * destination buffer
                         */
                        goto _output_error;

                /* get matchlength */
                if ((length = (token & ML_MASK)) == ML_MASK) {
                        while (ip < iend) {
                                int s = *ip++;
                                length += s;
                                if (s == 255)
                                        continue;
                                break;
                        }
                }
                /* copy repeated sequence */
                if (unlikely(op - ref < STEPSIZE)) {
#if LZ4_ARCH64
                        size_t dec64 = dec64table[op-ref];
#else
                        const int dec64 = 0;
#endif
                        op[0] = ref[0];
                        op[1] = ref[1];
                        op[2] = ref[2];
                        op[3] = ref[3];
                        op += 4;
                        ref += 4;
                        ref -= dec32table[op-ref];
                        A32(op) = A32(ref);
                        op += STEPSIZE - 4;
                        ref -= dec64;
                } else {
                        LZ4_COPYSTEP(ref, op);
                }
                cpy = op + length - (STEPSIZE - 4);
                if (cpy > oend - COPYLENGTH) {
                        if (cpy > oend)
                                /*
                                 * Error: request to write outside of
                                 * destination buffer
                                 */
                                goto _output_error;
                        LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH));
                        while (op < cpy)
                                *op++ = *ref++;
                        op = cpy;
                        if (op == oend)
                                /*
                                 * Check EOF (should never happen, since
                                 * last 5 bytes are supposed to be literals)
                                 */
                                goto _output_error;
                        continue;
                }
                LZ4_SECURECOPY(ref, op, cpy);
                op = cpy;       /* correction */
        }

        /* end of decoding */
        return (int)(((char *)op) - dest);

        /* write overflow error detected */
        _output_error:
        return (int)(-(((char *)ip) - source));
}

/*ARGSUSED*/
int
lz4_decompress_zfs(void *s_start, void *d_start, size_t s_len,
    size_t d_len, int n)
{
        const char *src = (const char*) s_start;
        uint32_t bufsiz = BE_IN32(src);

        /* invalid compressed buffer size encoded at start */
        if (bufsiz + sizeof (bufsiz) > s_len)
                return (1);

        std::cout << "Real input size: " << bufsiz << std::endl;
        /*
         * Returns 0 on success (decompression function returned non-negative)
         * and non-zero on failure (decompression function returned negative.
         */
        return (LZ4_uncompress_unknownOutputSize(&src[sizeof (bufsiz)],
            (char*)d_start, bufsiz, d_len) < 0);
}

int main( int argc, char **argv )
{
        if (argc < 4) {
                std::cout << argv[0] << " <in> <out> <out_size>" << std::endl;

                return 1;
        }

        char* szInput = argv[1];
        char* szOutput = argv[2];
        int nOutSize = atoi(argv[3]);

        std::cout << "Input: \t\t" << szInput << std::endl;
        std::cout << "Output: \t" << szOutput << std::endl;
        std::cout << "Out size: \t" << nOutSize << std::endl;
        std::cout << "-----------------------------" << std::endl;

// READ INPUT
        fstream fs(szInput, fstream::in);
        if (!fs.is_open()) {
                std::cout << "Open error";
                return 1;
        }

        fs.seekg(0, ios::end);
        int fileSize = fs.tellg();
        std::cout << "Input size: \t" << fileSize << std::endl;

        char* src = new char[fileSize];

        fs.seekg(0, ios::beg);

        fs.read(src, fileSize);
        if (!fs) {
                std::cout << "error: only " << fs.gcount() << " could be read";
                fs.close();
                return 1;
        }
        fs.close();
// END READ INPUT

// DECOMPRESS
        char* dst = new char[nOutSize];
        std::memset(dst, 0, nOutSize);

        int nRes = lz4_decompress_zfs(src, dst, fileSize, nOutSize, 0);
        std::cout << "Decompress result: " << nRes << std::endl;
        if (nRes) {
                std::cout << "Decompress error" << std::endl;
//              return 1;
        }
// END DECOMPRESS

// OUTPUT
        fstream out(szOutput, fstream::out);
        if (!out.is_open()) {
                std::cout << "Open error";
                return 1;
        }

        out.write(dst, nOutSize);
        if (!out) {
                std::cout << "error: only " << out.gcount() << " could be write";
                out.close();
                return 1;
        }
        out.close();

// END OUTPUT

        delete[] src;
        delete[] dst;

        return 0;
}