AuxXxilium/linux_dsm_epyc7002
1
0
Fork 0
mirror of https://github.com/AuxXxilium/linux_dsm_epyc7002.git synced 2024-12-05 06:26:55 +07:00
Code Issues Actions Packages Projects Releases Wiki Activity
38f6ce45f0
linux_dsm_epyc7002/lib/zlib_inflate/inffast.c
Benjamin Herrenschmidt 6846ee5ca6 zlib: Fix build of powerpc boot wrapper 
Commit ac4c2a3bbe broke the build
of all powerpc boot wrappers.

It attempts to add an include of autoconf.h but used the wrong
path for it. It also adds -D__KERNEL__ to our boot wrapper, both
things that we pretty much didn't do on purpose so far.

We want our boot wrapper to remain independent enough of the kernel
for various reasons, one of them being that you can "wrap" an existing
kernel at distro install time which allows to ship one kernel image
and a set of boot wrappers for different platforms, the wrappers
don't have to be built out of the same kernel build tree.

It's also incorrect to do what the patch does in our boot environment
since we may not have a proper alignment exception handler which means
we may not be able to fixup the few cases where an unaligned access will
need SW emulation (depends on the core variant, could be when crossing
page or segment boundaries for example).

This patch fixes it by putting the old code back in and using the
new "fancy" variant only when CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
is set, which happens not to be set on powerpc since we don't include
autoconf.h. It also reverts the changes to our boot wrapper Makefile.

This means that x86 should, afaik, keep the optimisations since its
boot wrapper does include autoconf.h and define __KERNEL__ (though I
doubt they make that much different outside of slow embedded processors).

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-01-13 16:13:39 -08:00

374 lines
14 KiB
C
Raw Blame History

/* 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"
/* Only do the unaligned "Faster" variant when
* CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is set
*
* On powerpc, it won't be as we don't include autoconf.h
* automatically for the boot wrapper, which is intended as
* we run in an environment where we may not be able to deal
* with (even rare) alignment faults. In addition, we do not
* define __KERNEL__ for arch/powerpc/boot unlike x86
*/
#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
#include <asm/unaligned.h>
#include <asm/byteorder.h>
#endif
#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)++
# define UP_UNALIGNED(a) get_unaligned((a)++)
#else
# define OFF 1
# define PUP(a) *++(a)
# define UP_UNALIGNED(a) get_unaligned(++(a))
#endif
/*
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 - OFF;
last = in + (strm->avail_in - 5);
out = strm->next_out - OFF;
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)(PUP(in)) << bits;
bits += 8;
hold += (unsigned long)(PUP(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 */
PUP(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)(PUP(in)) << bits;
bits += 8;
}
len += (unsigned)hold & ((1U << op) - 1);
hold >>= op;
bits -= op;
}
if (bits < 15) {
hold += (unsigned long)(PUP(in)) << bits;
bits += 8;
hold += (unsigned long)(PUP(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)(PUP(in)) << bits;
bits += 8;
if (bits < op) {
hold += (unsigned long)(PUP(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 - OFF;
if (write == 0) { /* very common case */
from += wsize - op;
if (op < len) { /* some from window */
len -= op;
do {
PUP(out) = PUP(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 {
PUP(out) = PUP(from);
} while (--op);
from = window - OFF;
if (write < len) { /* some from start of window */
op = write;
len -= op;
do {
PUP(out) = PUP(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 {
PUP(out) = PUP(from);
} while (--op);
from = out - dist; /* rest from output */
}
}
while (len > 2) {
PUP(out) = PUP(from);
PUP(out) = PUP(from);
PUP(out) = PUP(from);
len -= 3;
}
if (len) {
PUP(out) = PUP(from);
if (len > 1)
PUP(out) = PUP(from);
}
}
else {
#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
unsigned short *sout;
unsigned long loops;
from = out - dist; /* copy direct from output */
/* minimum length is three */
/* Align out addr */
if (!((long)(out - 1 + OFF) & 1)) {
PUP(out) = PUP(from);
len--;
}
sout = (unsigned short *)(out - OFF);
if (dist > 2) {
unsigned short *sfrom;
sfrom = (unsigned short *)(from - OFF);
loops = len >> 1;
do
PUP(sout) = UP_UNALIGNED(sfrom);
while (--loops);
out = (unsigned char *)sout + OFF;
from = (unsigned char *)sfrom + OFF;
} else { /* dist == 1 or dist == 2 */
unsigned short pat16;
pat16 = *(sout-2+2*OFF);
if (dist == 1)
#if defined(__BIG_ENDIAN)
pat16 = (pat16 & 0xff) | ((pat16 & 0xff) << 8);
#elif defined(__LITTLE_ENDIAN)
pat16 = (pat16 & 0xff00) | ((pat16 & 0xff00) >> 8);
#else
#error __BIG_ENDIAN nor __LITTLE_ENDIAN is defined
#endif
loops = len >> 1;
do
PUP(sout) = pat16;
while (--loops);
out = (unsigned char *)sout + OFF;
}
if (len & 1)
PUP(out) = PUP(from);
#else /* CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */
from = out - dist; /* copy direct from output */
do { /* minimum length is three */
PUP(out) = PUP(from);
PUP(out) = PUP(from);
PUP(out) = PUP(from);
len -= 3;
} while (len > 2);
if (len) {
PUP(out) = PUP(from);
if (len > 1)
PUP(out) = PUP(from);
}
#endif /* !CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */
}
}
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 + OFF;
strm->next_out = out + OFF;
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 */
Reference in New Issue View Git Blame Copy Permalink