2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-17 01:34:00 +08:00
linux-next/lib/lz4/lz4defs.h
Nick Terrell b1a3e75e46 lz4: fix kernel decompression speed
This patch replaces all memcpy() calls with LZ4_memcpy() which calls
__builtin_memcpy() so the compiler can inline it.

LZ4 relies heavily on memcpy() with a constant size being inlined.  In x86
and i386 pre-boot environments memcpy() cannot be inlined because memcpy()
doesn't get defined as __builtin_memcpy().

An equivalent patch has been applied upstream so that the next import
won't lose this change [1].

I've measured the kernel decompression speed using QEMU before and after
this patch for the x86_64 and i386 architectures.  The speed-up is about
10x as shown below.

Code	Arch	Kernel Size	Time	Speed
v5.8	x86_64	11504832 B	148 ms	 79 MB/s
patch	x86_64	11503872 B	 13 ms	885 MB/s
v5.8	i386	 9621216 B	 91 ms	106 MB/s
patch	i386	 9620224 B	 10 ms	962 MB/s

I also measured the time to decompress the initramfs on x86_64, i386, and
arm.  All three show the same decompression speed before and after, as
expected.

[1] https://github.com/lz4/lz4/pull/890

Signed-off-by: Nick Terrell <terrelln@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Yann Collet <yann.collet.73@gmail.com>
Cc: Gao Xiang <gaoxiang25@huawei.com>
Cc: Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Arvind Sankar <nivedita@alum.mit.edu>
Link: http://lkml.kernel.org/r/20200803194022.2966806-1-nickrterrell@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-14 19:56:56 -07:00

245 lines
6.6 KiB
C

#ifndef __LZ4DEFS_H__
#define __LZ4DEFS_H__
/*
* lz4defs.h -- common and architecture specific defines for the kernel usage
* LZ4 - Fast LZ compression algorithm
* Copyright (C) 2011-2016, Yann Collet.
* BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are
* met:
* * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following disclaimer
* in the documentation and/or other materials provided with the
* distribution.
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
* You can contact the author at :
* - LZ4 homepage : http://www.lz4.org
* - LZ4 source repository : https://github.com/lz4/lz4
*
* Changed for kernel usage by:
* Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
*/
#include <asm/unaligned.h>
#include <linux/string.h> /* memset, memcpy */
#define FORCE_INLINE __always_inline
/*-************************************
* Basic Types
**************************************/
#include <linux/types.h>
typedef uint8_t BYTE;
typedef uint16_t U16;
typedef uint32_t U32;
typedef int32_t S32;
typedef uint64_t U64;
typedef uintptr_t uptrval;
/*-************************************
* Architecture specifics
**************************************/
#if defined(CONFIG_64BIT)
#define LZ4_ARCH64 1
#else
#define LZ4_ARCH64 0
#endif
#if defined(__LITTLE_ENDIAN)
#define LZ4_LITTLE_ENDIAN 1
#else
#define LZ4_LITTLE_ENDIAN 0
#endif
/*-************************************
* Constants
**************************************/
#define MINMATCH 4
#define WILDCOPYLENGTH 8
#define LASTLITERALS 5
#define MFLIMIT (WILDCOPYLENGTH + MINMATCH)
/*
* ensure it's possible to write 2 x wildcopyLength
* without overflowing output buffer
*/
#define MATCH_SAFEGUARD_DISTANCE ((2 * WILDCOPYLENGTH) - MINMATCH)
/* Increase this value ==> compression run slower on incompressible data */
#define LZ4_SKIPTRIGGER 6
#define HASH_UNIT sizeof(size_t)
#define KB (1 << 10)
#define MB (1 << 20)
#define GB (1U << 30)
#define MAXD_LOG 16
#define MAX_DISTANCE ((1 << MAXD_LOG) - 1)
#define STEPSIZE sizeof(size_t)
#define ML_BITS 4
#define ML_MASK ((1U << ML_BITS) - 1)
#define RUN_BITS (8 - ML_BITS)
#define RUN_MASK ((1U << RUN_BITS) - 1)
/*-************************************
* Reading and writing into memory
**************************************/
static FORCE_INLINE U16 LZ4_read16(const void *ptr)
{
return get_unaligned((const U16 *)ptr);
}
static FORCE_INLINE U32 LZ4_read32(const void *ptr)
{
return get_unaligned((const U32 *)ptr);
}
static FORCE_INLINE size_t LZ4_read_ARCH(const void *ptr)
{
return get_unaligned((const size_t *)ptr);
}
static FORCE_INLINE void LZ4_write16(void *memPtr, U16 value)
{
put_unaligned(value, (U16 *)memPtr);
}
static FORCE_INLINE void LZ4_write32(void *memPtr, U32 value)
{
put_unaligned(value, (U32 *)memPtr);
}
static FORCE_INLINE U16 LZ4_readLE16(const void *memPtr)
{
return get_unaligned_le16(memPtr);
}
static FORCE_INLINE void LZ4_writeLE16(void *memPtr, U16 value)
{
return put_unaligned_le16(value, memPtr);
}
/*
* LZ4 relies on memcpy with a constant size being inlined. In freestanding
* environments, the compiler can't assume the implementation of memcpy() is
* standard compliant, so apply its specialized memcpy() inlining logic. When
* possible, use __builtin_memcpy() to tell the compiler to analyze memcpy()
* as-if it were standard compliant, so it can inline it in freestanding
* environments. This is needed when decompressing the Linux Kernel, for example.
*/
#define LZ4_memcpy(dst, src, size) __builtin_memcpy(dst, src, size)
static FORCE_INLINE void LZ4_copy8(void *dst, const void *src)
{
#if LZ4_ARCH64
U64 a = get_unaligned((const U64 *)src);
put_unaligned(a, (U64 *)dst);
#else
U32 a = get_unaligned((const U32 *)src);
U32 b = get_unaligned((const U32 *)src + 1);
put_unaligned(a, (U32 *)dst);
put_unaligned(b, (U32 *)dst + 1);
#endif
}
/*
* customized variant of memcpy,
* which can overwrite up to 7 bytes beyond dstEnd
*/
static FORCE_INLINE void LZ4_wildCopy(void *dstPtr,
const void *srcPtr, void *dstEnd)
{
BYTE *d = (BYTE *)dstPtr;
const BYTE *s = (const BYTE *)srcPtr;
BYTE *const e = (BYTE *)dstEnd;
do {
LZ4_copy8(d, s);
d += 8;
s += 8;
} while (d < e);
}
static FORCE_INLINE unsigned int LZ4_NbCommonBytes(register size_t val)
{
#if LZ4_LITTLE_ENDIAN
return __ffs(val) >> 3;
#else
return (BITS_PER_LONG - 1 - __fls(val)) >> 3;
#endif
}
static FORCE_INLINE unsigned int LZ4_count(
const BYTE *pIn,
const BYTE *pMatch,
const BYTE *pInLimit)
{
const BYTE *const pStart = pIn;
while (likely(pIn < pInLimit - (STEPSIZE - 1))) {
size_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn);
if (!diff) {
pIn += STEPSIZE;
pMatch += STEPSIZE;
continue;
}
pIn += LZ4_NbCommonBytes(diff);
return (unsigned int)(pIn - pStart);
}
#if LZ4_ARCH64
if ((pIn < (pInLimit - 3))
&& (LZ4_read32(pMatch) == LZ4_read32(pIn))) {
pIn += 4;
pMatch += 4;
}
#endif
if ((pIn < (pInLimit - 1))
&& (LZ4_read16(pMatch) == LZ4_read16(pIn))) {
pIn += 2;
pMatch += 2;
}
if ((pIn < pInLimit) && (*pMatch == *pIn))
pIn++;
return (unsigned int)(pIn - pStart);
}
typedef enum { noLimit = 0, limitedOutput = 1 } limitedOutput_directive;
typedef enum { byPtr, byU32, byU16 } tableType_t;
typedef enum { noDict = 0, withPrefix64k, usingExtDict } dict_directive;
typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive;
typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;
typedef enum { decode_full_block = 0, partial_decode = 1 } earlyEnd_directive;
#define LZ4_STATIC_ASSERT(c) BUILD_BUG_ON(!(c))
#endif