diff options
Diffstat (limited to 'zlib/inffast.c')
-rw-r--r-- | zlib/inffast.c | 159 |
1 files changed, 82 insertions, 77 deletions
diff --git a/zlib/inffast.c b/zlib/inffast.c index bbee92ed1e6..0dbd1dbc09f 100644 --- a/zlib/inffast.c +++ b/zlib/inffast.c @@ -1,5 +1,5 @@ /* inffast.c -- fast decoding - * Copyright (C) 1995-2004 Mark Adler + * Copyright (C) 1995-2017 Mark Adler * For conditions of distribution and use, see copyright notice in zlib.h */ @@ -8,26 +8,9 @@ #include "inflate.h" #include "inffast.h" -#ifndef ASMINF - -/* Allow machine dependent optimization for post-increment or pre-increment. - Based on testing to date, - Pre-increment preferred for: - - PowerPC G3 (Adler) - - MIPS R5000 (Randers-Pehrson) - Post-increment preferred for: - - none - No measurable difference: - - Pentium III (Anderson) - - M68060 (Nikl) - */ -#ifdef POSTINC -# define OFF 0 -# define PUP(a) *(a)++ +#ifdef ASMINF +# pragma message("Assembler code may have bugs -- use at your own risk") #else -# define OFF 1 -# define PUP(a) *++(a) -#endif /* Decode literal, length, and distance codes and write out the resulting @@ -64,13 +47,13 @@ requires strm->avail_out >= 258 for each loop to avoid checking for output space. */ -void inflate_fast(strm, start) +void ZLIB_INTERNAL inflate_fast(strm, start) z_streamp strm; unsigned start; /* inflate()'s starting value for strm->avail_out */ { struct inflate_state FAR *state; - unsigned char FAR *in; /* local strm->next_in */ - unsigned char FAR *last; /* while in < last, enough input available */ + z_const unsigned char FAR *in; /* local strm->next_in */ + z_const unsigned char FAR *last; /* have enough input while in < last */ unsigned char FAR *out; /* local strm->next_out */ unsigned char FAR *beg; /* inflate()'s initial strm->next_out */ unsigned char FAR *end; /* while out < end, enough space available */ @@ -79,7 +62,7 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ #endif unsigned wsize; /* window size or zero if not using window */ unsigned whave; /* valid bytes in the window */ - unsigned write; /* window write index */ + unsigned wnext; /* window write index */ unsigned char FAR *window; /* allocated sliding window, if wsize != 0 */ unsigned long hold; /* local strm->hold */ unsigned bits; /* local strm->bits */ @@ -87,7 +70,7 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ code const FAR *dcode; /* local strm->distcode */ unsigned lmask; /* mask for first level of length codes */ unsigned dmask; /* mask for first level of distance codes */ - code this; /* retrieved table entry */ + code here; /* retrieved table entry */ unsigned op; /* code bits, operation, extra bits, or */ /* window position, window bytes to copy */ unsigned len; /* match length, unused bytes */ @@ -96,9 +79,9 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ /* copy state to local variables */ state = (struct inflate_state FAR *)strm->state; - in = strm->next_in - OFF; + in = strm->next_in; last = in + (strm->avail_in - 5); - out = strm->next_out - OFF; + out = strm->next_out; beg = out - (start - strm->avail_out); end = out + (strm->avail_out - 257); #ifdef INFLATE_STRICT @@ -106,7 +89,7 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ #endif wsize = state->wsize; whave = state->whave; - write = state->write; + wnext = state->wnext; window = state->window; hold = state->hold; bits = state->bits; @@ -119,29 +102,29 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ input data or output space */ do { if (bits < 15) { - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; } - this = lcode[hold & lmask]; + here = lcode[hold & lmask]; dolen: - op = (unsigned)(this.bits); + op = (unsigned)(here.bits); hold >>= op; bits -= op; - op = (unsigned)(this.op); + op = (unsigned)(here.op); if (op == 0) { /* literal */ - Tracevv((stderr, this.val >= 0x20 && this.val < 0x7f ? + Tracevv((stderr, here.val >= 0x20 && here.val < 0x7f ? "inflate: literal '%c'\n" : - "inflate: literal 0x%02x\n", this.val)); - PUP(out) = (unsigned char)(this.val); + "inflate: literal 0x%02x\n", here.val)); + *out++ = (unsigned char)(here.val); } else if (op & 16) { /* length base */ - len = (unsigned)(this.val); + len = (unsigned)(here.val); op &= 15; /* number of extra bits */ if (op) { if (bits < op) { - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; } len += (unsigned)hold & ((1U << op) - 1); @@ -150,25 +133,25 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ } Tracevv((stderr, "inflate: length %u\n", len)); if (bits < 15) { - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; } - this = dcode[hold & dmask]; + here = dcode[hold & dmask]; dodist: - op = (unsigned)(this.bits); + op = (unsigned)(here.bits); hold >>= op; bits -= op; - op = (unsigned)(this.op); + op = (unsigned)(here.op); if (op & 16) { /* distance base */ - dist = (unsigned)(this.val); + dist = (unsigned)(here.val); op &= 15; /* number of extra bits */ if (bits < op) { - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; if (bits < op) { - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; } } @@ -187,79 +170,101 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ if (dist > op) { /* see if copy from window */ op = dist - op; /* distance back in window */ if (op > whave) { - strm->msg = (char *)"invalid distance too far back"; - state->mode = BAD; - break; + if (state->sane) { + strm->msg = + (char *)"invalid distance too far back"; + state->mode = BAD; + break; + } +#ifdef INFLATE_ALLOW_INVALID_DISTANCE_TOOFAR_ARRR + if (len <= op - whave) { + do { + *out++ = 0; + } while (--len); + continue; + } + len -= op - whave; + do { + *out++ = 0; + } while (--op > whave); + if (op == 0) { + from = out - dist; + do { + *out++ = *from++; + } while (--len); + continue; + } +#endif } - from = window - OFF; - if (write == 0) { /* very common case */ + from = window; + if (wnext == 0) { /* very common case */ from += wsize - op; if (op < len) { /* some from window */ len -= op; do { - PUP(out) = PUP(from); + *out++ = *from++; } while (--op); from = out - dist; /* rest from output */ } } - else if (write < op) { /* wrap around window */ - from += wsize + write - op; - op -= write; + else if (wnext < op) { /* wrap around window */ + from += wsize + wnext - op; + op -= wnext; if (op < len) { /* some from end of window */ len -= op; do { - PUP(out) = PUP(from); + *out++ = *from++; } while (--op); - from = window - OFF; - if (write < len) { /* some from start of window */ - op = write; + from = window; + if (wnext < len) { /* some from start of window */ + op = wnext; len -= op; do { - PUP(out) = PUP(from); + *out++ = *from++; } while (--op); from = out - dist; /* rest from output */ } } } else { /* contiguous in window */ - from += write - op; + from += wnext - op; if (op < len) { /* some from window */ len -= op; do { - PUP(out) = PUP(from); + *out++ = *from++; } while (--op); from = out - dist; /* rest from output */ } } while (len > 2) { - PUP(out) = PUP(from); - PUP(out) = PUP(from); - PUP(out) = PUP(from); + *out++ = *from++; + *out++ = *from++; + *out++ = *from++; len -= 3; } if (len) { - PUP(out) = PUP(from); + *out++ = *from++; if (len > 1) - PUP(out) = PUP(from); + *out++ = *from++; } } else { from = out - dist; /* copy direct from output */ do { /* minimum length is three */ - PUP(out) = PUP(from); - PUP(out) = PUP(from); - PUP(out) = PUP(from); + *out++ = *from++; + *out++ = *from++; + *out++ = *from++; len -= 3; } while (len > 2); if (len) { - PUP(out) = PUP(from); + *out++ = *from++; if (len > 1) - PUP(out) = PUP(from); + *out++ = *from++; } } } else if ((op & 64) == 0) { /* 2nd level distance code */ - this = dcode[this.val + (hold & ((1U << op) - 1))]; + here = dcode[here.val + (hold & ((1U << op) - 1))]; goto dodist; } else { @@ -269,7 +274,7 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ } } else if ((op & 64) == 0) { /* 2nd level length code */ - this = lcode[this.val + (hold & ((1U << op) - 1))]; + here = lcode[here.val + (hold & ((1U << op) - 1))]; goto dolen; } else if (op & 32) { /* end-of-block */ @@ -291,8 +296,8 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ hold &= (1U << bits) - 1; /* update state and return */ - strm->next_in = in + OFF; - strm->next_out = out + OFF; + strm->next_in = in; + strm->next_out = out; strm->avail_in = (unsigned)(in < last ? 5 + (last - in) : 5 - (in - last)); strm->avail_out = (unsigned)(out < end ? 257 + (end - out) : 257 - (out - end)); @@ -305,7 +310,7 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ inflate_fast() speedups that turned out slower (on a PowerPC G3 750CXe): - Using bit fields for code structure - Different op definition to avoid & for extra bits (do & for table bits) - - Three separate decoding do-loops for direct, window, and write == 0 + - Three separate decoding do-loops for direct, window, and wnext == 0 - Special case for distance > 1 copies to do overlapped load and store copy - Explicit branch predictions (based on measured branch probabilities) - Deferring match copy and interspersed it with decoding subsequent codes |