mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-24 01:00:52 +07:00
acaab7335b
The zlib inflate code has an old micro-optimization based on the assumption that for pre-increment memory accesses, the compiler will generate code that fits better into the processor's pipeline than what would be generated for post-increment memory accesses. This optimization was already removed in upstream zlib in 2016: https://github.com/madler/zlib/commit/9aaec95e8211 This optimization causes UB according to C99, which says in section 6.5.6 "Additive operators": "If both the pointer operand and the result point to elements of the same array object, or one past the last element of the array object, the evaluation shall not produce an overflow; otherwise, the behavior is undefined". This UB is not only a theoretical concern, but can also cause trouble for future work on compiler-based sanitizers. According to the zlib commit, this optimization also is not optimal anymore with modern compilers. Replace uses of OFF, PUP and UP_UNALIGNED with their definitions in the POSTINC case, and remove the macro definitions, just like in the upstream patch. Signed-off-by: Jann Horn <jannh@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Mikhail Zaslonko <zaslonko@linux.ibm.com> Link: http://lkml.kernel.org/r/20200507123112.252723-1-jannh@google.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
343 lines
12 KiB
C
343 lines
12 KiB
C
/* inffast.c -- fast decoding
|
|
* Copyright (C) 1995-2004 Mark Adler
|
|
* For conditions of distribution and use, see copyright notice in zlib.h
|
|
*/
|
|
|
|
#include <linux/zutil.h>
|
|
#include "inftrees.h"
|
|
#include "inflate.h"
|
|
#include "inffast.h"
|
|
|
|
#ifndef ASMINF
|
|
|
|
union uu {
|
|
unsigned short us;
|
|
unsigned char b[2];
|
|
};
|
|
|
|
/* Endian independed version */
|
|
static inline unsigned short
|
|
get_unaligned16(const unsigned short *p)
|
|
{
|
|
union uu mm;
|
|
unsigned char *b = (unsigned char *)p;
|
|
|
|
mm.b[0] = b[0];
|
|
mm.b[1] = b[1];
|
|
return mm.us;
|
|
}
|
|
|
|
/*
|
|
Decode literal, length, and distance codes and write out the resulting
|
|
literal and match bytes until either not enough input or output is
|
|
available, an end-of-block is encountered, or a data error is encountered.
|
|
When large enough input and output buffers are supplied to inflate(), for
|
|
example, a 16K input buffer and a 64K output buffer, more than 95% of the
|
|
inflate execution time is spent in this routine.
|
|
|
|
Entry assumptions:
|
|
|
|
state->mode == LEN
|
|
strm->avail_in >= 6
|
|
strm->avail_out >= 258
|
|
start >= strm->avail_out
|
|
state->bits < 8
|
|
|
|
On return, state->mode is one of:
|
|
|
|
LEN -- ran out of enough output space or enough available input
|
|
TYPE -- reached end of block code, inflate() to interpret next block
|
|
BAD -- error in block data
|
|
|
|
Notes:
|
|
|
|
- The maximum input bits used by a length/distance pair is 15 bits for the
|
|
length code, 5 bits for the length extra, 15 bits for the distance code,
|
|
and 13 bits for the distance extra. This totals 48 bits, or six bytes.
|
|
Therefore if strm->avail_in >= 6, then there is enough input to avoid
|
|
checking for available input while decoding.
|
|
|
|
- The maximum bytes that a single length/distance pair can output is 258
|
|
bytes, which is the maximum length that can be coded. inflate_fast()
|
|
requires strm->avail_out >= 258 for each loop to avoid checking for
|
|
output space.
|
|
|
|
- @start: inflate()'s starting value for strm->avail_out
|
|
*/
|
|
void inflate_fast(z_streamp strm, unsigned start)
|
|
{
|
|
struct inflate_state *state;
|
|
const unsigned char *in; /* local strm->next_in */
|
|
const unsigned char *last; /* while in < last, enough input available */
|
|
unsigned char *out; /* local strm->next_out */
|
|
unsigned char *beg; /* inflate()'s initial strm->next_out */
|
|
unsigned char *end; /* while out < end, enough space available */
|
|
#ifdef INFLATE_STRICT
|
|
unsigned dmax; /* maximum distance from zlib header */
|
|
#endif
|
|
unsigned wsize; /* window size or zero if not using window */
|
|
unsigned whave; /* valid bytes in the window */
|
|
unsigned write; /* window write index */
|
|
unsigned char *window; /* allocated sliding window, if wsize != 0 */
|
|
unsigned long hold; /* local strm->hold */
|
|
unsigned bits; /* local strm->bits */
|
|
code const *lcode; /* local strm->lencode */
|
|
code const *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 */
|
|
unsigned op; /* code bits, operation, extra bits, or */
|
|
/* window position, window bytes to copy */
|
|
unsigned len; /* match length, unused bytes */
|
|
unsigned dist; /* match distance */
|
|
unsigned char *from; /* where to copy match from */
|
|
|
|
/* copy state to local variables */
|
|
state = (struct inflate_state *)strm->state;
|
|
in = strm->next_in;
|
|
last = in + (strm->avail_in - 5);
|
|
out = strm->next_out;
|
|
beg = out - (start - strm->avail_out);
|
|
end = out + (strm->avail_out - 257);
|
|
#ifdef INFLATE_STRICT
|
|
dmax = state->dmax;
|
|
#endif
|
|
wsize = state->wsize;
|
|
whave = state->whave;
|
|
write = state->write;
|
|
window = state->window;
|
|
hold = state->hold;
|
|
bits = state->bits;
|
|
lcode = state->lencode;
|
|
dcode = state->distcode;
|
|
lmask = (1U << state->lenbits) - 1;
|
|
dmask = (1U << state->distbits) - 1;
|
|
|
|
/* decode literals and length/distances until end-of-block or not enough
|
|
input data or output space */
|
|
do {
|
|
if (bits < 15) {
|
|
hold += (unsigned long)(*in++) << bits;
|
|
bits += 8;
|
|
hold += (unsigned long)(*in++) << bits;
|
|
bits += 8;
|
|
}
|
|
this = lcode[hold & lmask];
|
|
dolen:
|
|
op = (unsigned)(this.bits);
|
|
hold >>= op;
|
|
bits -= op;
|
|
op = (unsigned)(this.op);
|
|
if (op == 0) { /* literal */
|
|
*out++ = (unsigned char)(this.val);
|
|
}
|
|
else if (op & 16) { /* length base */
|
|
len = (unsigned)(this.val);
|
|
op &= 15; /* number of extra bits */
|
|
if (op) {
|
|
if (bits < op) {
|
|
hold += (unsigned long)(*in++) << bits;
|
|
bits += 8;
|
|
}
|
|
len += (unsigned)hold & ((1U << op) - 1);
|
|
hold >>= op;
|
|
bits -= op;
|
|
}
|
|
if (bits < 15) {
|
|
hold += (unsigned long)(*in++) << bits;
|
|
bits += 8;
|
|
hold += (unsigned long)(*in++) << bits;
|
|
bits += 8;
|
|
}
|
|
this = dcode[hold & dmask];
|
|
dodist:
|
|
op = (unsigned)(this.bits);
|
|
hold >>= op;
|
|
bits -= op;
|
|
op = (unsigned)(this.op);
|
|
if (op & 16) { /* distance base */
|
|
dist = (unsigned)(this.val);
|
|
op &= 15; /* number of extra bits */
|
|
if (bits < op) {
|
|
hold += (unsigned long)(*in++) << bits;
|
|
bits += 8;
|
|
if (bits < op) {
|
|
hold += (unsigned long)(*in++) << bits;
|
|
bits += 8;
|
|
}
|
|
}
|
|
dist += (unsigned)hold & ((1U << op) - 1);
|
|
#ifdef INFLATE_STRICT
|
|
if (dist > dmax) {
|
|
strm->msg = (char *)"invalid distance too far back";
|
|
state->mode = BAD;
|
|
break;
|
|
}
|
|
#endif
|
|
hold >>= op;
|
|
bits -= op;
|
|
op = (unsigned)(out - beg); /* max distance in output */
|
|
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;
|
|
}
|
|
from = window;
|
|
if (write == 0) { /* very common case */
|
|
from += wsize - op;
|
|
if (op < len) { /* some from window */
|
|
len -= op;
|
|
do {
|
|
*out++ = *from++;
|
|
} while (--op);
|
|
from = out - dist; /* rest from output */
|
|
}
|
|
}
|
|
else if (write < op) { /* wrap around window */
|
|
from += wsize + write - op;
|
|
op -= write;
|
|
if (op < len) { /* some from end of window */
|
|
len -= op;
|
|
do {
|
|
*out++ = *from++;
|
|
} while (--op);
|
|
from = window;
|
|
if (write < len) { /* some from start of window */
|
|
op = write;
|
|
len -= op;
|
|
do {
|
|
*out++ = *from++;
|
|
} while (--op);
|
|
from = out - dist; /* rest from output */
|
|
}
|
|
}
|
|
}
|
|
else { /* contiguous in window */
|
|
from += write - op;
|
|
if (op < len) { /* some from window */
|
|
len -= op;
|
|
do {
|
|
*out++ = *from++;
|
|
} while (--op);
|
|
from = out - dist; /* rest from output */
|
|
}
|
|
}
|
|
while (len > 2) {
|
|
*out++ = *from++;
|
|
*out++ = *from++;
|
|
*out++ = *from++;
|
|
len -= 3;
|
|
}
|
|
if (len) {
|
|
*out++ = *from++;
|
|
if (len > 1)
|
|
*out++ = *from++;
|
|
}
|
|
}
|
|
else {
|
|
unsigned short *sout;
|
|
unsigned long loops;
|
|
|
|
from = out - dist; /* copy direct from output */
|
|
/* minimum length is three */
|
|
/* Align out addr */
|
|
if (!((long)(out - 1) & 1)) {
|
|
*out++ = *from++;
|
|
len--;
|
|
}
|
|
sout = (unsigned short *)(out);
|
|
if (dist > 2) {
|
|
unsigned short *sfrom;
|
|
|
|
sfrom = (unsigned short *)(from);
|
|
loops = len >> 1;
|
|
do
|
|
#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
|
|
*sout++ = *sfrom++;
|
|
#else
|
|
*sout++ = get_unaligned16(sfrom++);
|
|
#endif
|
|
while (--loops);
|
|
out = (unsigned char *)sout;
|
|
from = (unsigned char *)sfrom;
|
|
} else { /* dist == 1 or dist == 2 */
|
|
unsigned short pat16;
|
|
|
|
pat16 = *(sout-1);
|
|
if (dist == 1) {
|
|
union uu mm;
|
|
/* copy one char pattern to both bytes */
|
|
mm.us = pat16;
|
|
mm.b[0] = mm.b[1];
|
|
pat16 = mm.us;
|
|
}
|
|
loops = len >> 1;
|
|
do
|
|
*sout++ = pat16;
|
|
while (--loops);
|
|
out = (unsigned char *)sout;
|
|
}
|
|
if (len & 1)
|
|
*out++ = *from++;
|
|
}
|
|
}
|
|
else if ((op & 64) == 0) { /* 2nd level distance code */
|
|
this = dcode[this.val + (hold & ((1U << op) - 1))];
|
|
goto dodist;
|
|
}
|
|
else {
|
|
strm->msg = (char *)"invalid distance code";
|
|
state->mode = BAD;
|
|
break;
|
|
}
|
|
}
|
|
else if ((op & 64) == 0) { /* 2nd level length code */
|
|
this = lcode[this.val + (hold & ((1U << op) - 1))];
|
|
goto dolen;
|
|
}
|
|
else if (op & 32) { /* end-of-block */
|
|
state->mode = TYPE;
|
|
break;
|
|
}
|
|
else {
|
|
strm->msg = (char *)"invalid literal/length code";
|
|
state->mode = BAD;
|
|
break;
|
|
}
|
|
} while (in < last && out < end);
|
|
|
|
/* return unused bytes (on entry, bits < 8, so in won't go too far back) */
|
|
len = bits >> 3;
|
|
in -= len;
|
|
bits -= len << 3;
|
|
hold &= (1U << bits) - 1;
|
|
|
|
/* update state and return */
|
|
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));
|
|
state->hold = hold;
|
|
state->bits = bits;
|
|
return;
|
|
}
|
|
|
|
/*
|
|
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
|
|
- 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
|
|
- Swapping literal/length else
|
|
- Swapping window/direct else
|
|
- Larger unrolled copy loops (three is about right)
|
|
- Moving len -= 3 statement into middle of loop
|
|
*/
|
|
|
|
#endif /* !ASMINF */
|