linux/lib/lzo/lzo1x_decompress_safe.c
Dave Rodgman 5ee4014af9 lib/lzo: implement run-length encoding
Patch series "lib/lzo: run-length encoding support", v5.

Following on from the previous lzo-rle patchset:

  https://lkml.org/lkml/2018/11/30/972

This patchset contains only the RLE patches, and should be applied on
top of the non-RLE patches ( https://lkml.org/lkml/2019/2/5/366 ).

Previously, some questions were raised around the RLE patches.  I've
done some additional benchmarking to answer these questions.  In short:

 - RLE offers significant additional performance (data-dependent)

 - I didn't measure any regressions that were clearly outside the noise

One concern with this patchset was around performance - specifically,
measuring RLE impact separately from Matt Sealey's patches (CTZ & fast
copy).  I have done some additional benchmarking which I hope clarifies
the benefits of each part of the patchset.

Firstly, I've captured some memory via /dev/fmem from a Chromebook with
many tabs open which is starting to swap, and then split this into 4178
4k pages.  I've excluded the all-zero pages (as zram does), and also the
no-zero pages (which won't tell us anything about RLE performance).
This should give a realistic test dataset for zram.  What I found was
that the data is VERY bimodal: 44% of pages in this dataset contain 5%
or fewer zeros, and 44% contain over 90% zeros (30% if you include the
no-zero pages).  This supports the idea of special-casing zeros in zram.

Next, I've benchmarked four variants of lzo on these pages (on 64-bit
Arm at max frequency): baseline LZO; baseline + Matt Sealey's patches
(aka MS); baseline + RLE only; baseline + MS + RLE.  Numbers are for
weighted roundtrip throughput (the weighting reflects that zram does
more compression than decompression).

  https://drive.google.com/file/d/1VLtLjRVxgUNuWFOxaGPwJYhl_hMQXpHe/view?usp=sharing

Matt's patches help in all cases for Arm (and no effect on Intel), as
expected.

RLE also behaves as expected: with few zeros present, it makes no
difference; above ~75%, it gives a good improvement (50 - 300 MB/s on
top of the benefit from Matt's patches).

Best performance is seen with both MS and RLE patches.

Finally, I have benchmarked the same dataset on an x86-64 device.  Here,
the MS patches make no difference (as expected); RLE helps, similarly as
on Arm.  There were no definite regressions; allowing for observational
error, 0.1% (3/4178) of cases had a regression > 1 standard deviation,
of which the largest was 4.6% (1.2 standard deviations).  I think this
is probably within the noise.

  https://drive.google.com/file/d/1xCUVwmiGD0heEMx5gcVEmLBI4eLaageV/view?usp=sharing

One point to note is that the graphs show RLE appears to help very
slightly with no zeros present! This is because the extra code causes
the clang optimiser to change code layout in a way that happens to have
a significant benefit.  Taking baseline LZO and adding a do-nothing line
like "__builtin_prefetch(out_len);" immediately before the "goto next"
has the same effect.  So this is a real, but basically spurious effect -
it's small enough not to upset the overall findings.

This patch (of 3):

When using zram, we frequently encounter long runs of zero bytes.  This
adds a special case which identifies runs of zeros and encodes them
using run-length encoding.

This is faster for both compression and decompresion.  For high-entropy
data which doesn't hit this case, impact is minimal.

Compression ratio is within a few percent in all cases.

This modifies the bitstream in a way which is backwards compatible
(i.e., we can decompress old bitstreams, but old versions of lzo cannot
decompress new bitstreams).

Link: http://lkml.kernel.org/r/20190205155944.16007-2-dave.rodgman@arm.com
Signed-off-by: Dave Rodgman <dave.rodgman@arm.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Markus F.X.J. Oberhumer <markus@oberhumer.com>
Cc: Matt Sealey <matt.sealey@arm.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <nitingupta910@gmail.com>
Cc: Richard Purdie <rpurdie@openedhand.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Cc: Sonny Rao <sonnyrao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-07 18:32:02 -08:00

297 lines
6.3 KiB
C

/*
* LZO1X Decompressor from LZO
*
* Copyright (C) 1996-2012 Markus F.X.J. Oberhumer <markus@oberhumer.com>
*
* The full LZO package can be found at:
* http://www.oberhumer.com/opensource/lzo/
*
* Changed for Linux kernel use by:
* Nitin Gupta <nitingupta910@gmail.com>
* Richard Purdie <rpurdie@openedhand.com>
*/
#ifndef STATIC
#include <linux/module.h>
#include <linux/kernel.h>
#endif
#include <asm/unaligned.h>
#include <linux/lzo.h>
#include "lzodefs.h"
#define HAVE_IP(x) ((size_t)(ip_end - ip) >= (size_t)(x))
#define HAVE_OP(x) ((size_t)(op_end - op) >= (size_t)(x))
#define NEED_IP(x) if (!HAVE_IP(x)) goto input_overrun
#define NEED_OP(x) if (!HAVE_OP(x)) goto output_overrun
#define TEST_LB(m_pos) if ((m_pos) < out) goto lookbehind_overrun
/* This MAX_255_COUNT is the maximum number of times we can add 255 to a base
* count without overflowing an integer. The multiply will overflow when
* multiplying 255 by more than MAXINT/255. The sum will overflow earlier
* depending on the base count. Since the base count is taken from a u8
* and a few bits, it is safe to assume that it will always be lower than
* or equal to 2*255, thus we can always prevent any overflow by accepting
* two less 255 steps. See Documentation/lzo.txt for more information.
*/
#define MAX_255_COUNT ((((size_t)~0) / 255) - 2)
int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
unsigned char *out, size_t *out_len)
{
unsigned char *op;
const unsigned char *ip;
size_t t, next;
size_t state = 0;
const unsigned char *m_pos;
const unsigned char * const ip_end = in + in_len;
unsigned char * const op_end = out + *out_len;
unsigned char bitstream_version;
op = out;
ip = in;
if (unlikely(in_len < 3))
goto input_overrun;
if (likely(*ip == 17)) {
bitstream_version = ip[1];
ip += 2;
if (unlikely(in_len < 5))
goto input_overrun;
} else {
bitstream_version = 0;
}
if (*ip > 17) {
t = *ip++ - 17;
if (t < 4) {
next = t;
goto match_next;
}
goto copy_literal_run;
}
for (;;) {
t = *ip++;
if (t < 16) {
if (likely(state == 0)) {
if (unlikely(t == 0)) {
size_t offset;
const unsigned char *ip_last = ip;
while (unlikely(*ip == 0)) {
ip++;
NEED_IP(1);
}
offset = ip - ip_last;
if (unlikely(offset > MAX_255_COUNT))
return LZO_E_ERROR;
offset = (offset << 8) - offset;
t += offset + 15 + *ip++;
}
t += 3;
copy_literal_run:
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
if (likely(HAVE_IP(t + 15) && HAVE_OP(t + 15))) {
const unsigned char *ie = ip + t;
unsigned char *oe = op + t;
do {
COPY8(op, ip);
op += 8;
ip += 8;
COPY8(op, ip);
op += 8;
ip += 8;
} while (ip < ie);
ip = ie;
op = oe;
} else
#endif
{
NEED_OP(t);
NEED_IP(t + 3);
do {
*op++ = *ip++;
} while (--t > 0);
}
state = 4;
continue;
} else if (state != 4) {
next = t & 3;
m_pos = op - 1;
m_pos -= t >> 2;
m_pos -= *ip++ << 2;
TEST_LB(m_pos);
NEED_OP(2);
op[0] = m_pos[0];
op[1] = m_pos[1];
op += 2;
goto match_next;
} else {
next = t & 3;
m_pos = op - (1 + M2_MAX_OFFSET);
m_pos -= t >> 2;
m_pos -= *ip++ << 2;
t = 3;
}
} else if (t >= 64) {
next = t & 3;
m_pos = op - 1;
m_pos -= (t >> 2) & 7;
m_pos -= *ip++ << 3;
t = (t >> 5) - 1 + (3 - 1);
} else if (t >= 32) {
t = (t & 31) + (3 - 1);
if (unlikely(t == 2)) {
size_t offset;
const unsigned char *ip_last = ip;
while (unlikely(*ip == 0)) {
ip++;
NEED_IP(1);
}
offset = ip - ip_last;
if (unlikely(offset > MAX_255_COUNT))
return LZO_E_ERROR;
offset = (offset << 8) - offset;
t += offset + 31 + *ip++;
NEED_IP(2);
}
m_pos = op - 1;
next = get_unaligned_le16(ip);
ip += 2;
m_pos -= next >> 2;
next &= 3;
} else {
NEED_IP(2);
next = get_unaligned_le16(ip);
if (((next & 0xfffc) == 0xfffc) &&
((t & 0xf8) == 0x18) &&
likely(bitstream_version)) {
NEED_IP(3);
t &= 7;
t |= ip[2] << 3;
t += MIN_ZERO_RUN_LENGTH;
NEED_OP(t);
memset(op, 0, t);
op += t;
next &= 3;
ip += 3;
goto match_next;
} else {
m_pos = op;
m_pos -= (t & 8) << 11;
t = (t & 7) + (3 - 1);
if (unlikely(t == 2)) {
size_t offset;
const unsigned char *ip_last = ip;
while (unlikely(*ip == 0)) {
ip++;
NEED_IP(1);
}
offset = ip - ip_last;
if (unlikely(offset > MAX_255_COUNT))
return LZO_E_ERROR;
offset = (offset << 8) - offset;
t += offset + 7 + *ip++;
NEED_IP(2);
next = get_unaligned_le16(ip);
}
ip += 2;
m_pos -= next >> 2;
next &= 3;
if (m_pos == op)
goto eof_found;
m_pos -= 0x4000;
}
}
TEST_LB(m_pos);
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
if (op - m_pos >= 8) {
unsigned char *oe = op + t;
if (likely(HAVE_OP(t + 15))) {
do {
COPY8(op, m_pos);
op += 8;
m_pos += 8;
COPY8(op, m_pos);
op += 8;
m_pos += 8;
} while (op < oe);
op = oe;
if (HAVE_IP(6)) {
state = next;
COPY4(op, ip);
op += next;
ip += next;
continue;
}
} else {
NEED_OP(t);
do {
*op++ = *m_pos++;
} while (op < oe);
}
} else
#endif
{
unsigned char *oe = op + t;
NEED_OP(t);
op[0] = m_pos[0];
op[1] = m_pos[1];
op += 2;
m_pos += 2;
do {
*op++ = *m_pos++;
} while (op < oe);
}
match_next:
state = next;
t = next;
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
if (likely(HAVE_IP(6) && HAVE_OP(4))) {
COPY4(op, ip);
op += t;
ip += t;
} else
#endif
{
NEED_IP(t + 3);
NEED_OP(t);
while (t > 0) {
*op++ = *ip++;
t--;
}
}
}
eof_found:
*out_len = op - out;
return (t != 3 ? LZO_E_ERROR :
ip == ip_end ? LZO_E_OK :
ip < ip_end ? LZO_E_INPUT_NOT_CONSUMED : LZO_E_INPUT_OVERRUN);
input_overrun:
*out_len = op - out;
return LZO_E_INPUT_OVERRUN;
output_overrun:
*out_len = op - out;
return LZO_E_OUTPUT_OVERRUN;
lookbehind_overrun:
*out_len = op - out;
return LZO_E_LOOKBEHIND_OVERRUN;
}
#ifndef STATIC
EXPORT_SYMBOL_GPL(lzo1x_decompress_safe);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("LZO1X Decompressor");
#endif