mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-24 13:00:54 +07:00
f20eef4d06
commit 89b158635ad79574bde8e94d45dad33f8cf09549 upstream. LZ4 final literal copy could be overlapped when doing in-place decompression, so it's unsafe to just use memcpy() on an optimized memcpy approach but memmove() instead. Upstream LZ4 has updated this years ago [1] (and the impact is non-sensible [2] plus only a few bytes remain), this commit just synchronizes LZ4 upstream code to the kernel side as well. It can be observed as EROFS in-place decompression failure on specific files when X86_FEATURE_ERMS is unsupported, memcpy() optimization of commit59daa706fb
("x86, mem: Optimize memcpy by avoiding memory false dependece") will be enabled then. Currently most modern x86-CPUs support ERMS, these CPUs just use "rep movsb" approach so no problem at all. However, it can still be verified with forcely disabling ERMS feature... arch/x86/lib/memcpy_64.S: ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ - "jmp memcpy_erms", X86_FEATURE_ERMS + "jmp memcpy_orig", X86_FEATURE_ERMS We didn't observe any strange on arm64/arm/x86 platform before since most memcpy() would behave in an increasing address order ("copy upwards" [3]) and it's the correct order of in-place decompression but it really needs an update to memmove() for sure considering it's an undefined behavior according to the standard and some unique optimization already exists in the kernel. [1]33cb8518ac
[2] https://github.com/lz4/lz4/pull/717#issuecomment-497818921 [3] https://sourceware.org/bugzilla/show_bug.cgi?id=12518 Link: https://lkml.kernel.org/r/20201122030749.2698994-1-hsiangkao@redhat.com Signed-off-by: Gao Xiang <hsiangkao@redhat.com> Reviewed-by: Nick Terrell <terrelln@fb.com> Cc: Yann Collet <yann.collet.73@gmail.com> Cc: Miao Xie <miaoxie@huawei.com> Cc: Chao Yu <yuchao0@huawei.com> Cc: Li Guifu <bluce.liguifu@huawei.com> Cc: Guo Xuenan <guoxuenan@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
246 lines
6.6 KiB
C
246 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)
|
|
#define LZ4_memmove(dst, src, size) __builtin_memmove(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
|