aboutsummaryrefslogtreecommitdiffstats
path: root/lib/lz4
diff options
context:
space:
mode:
Diffstat (limited to 'lib/lz4')
-rw-r--r--lib/lz4/lz4_compress.c4
-rw-r--r--lib/lz4/lz4_decompress.c41
-rw-r--r--lib/lz4/lz4defs.h13
-rw-r--r--lib/lz4/lz4hc_compress.c2
4 files changed, 42 insertions, 18 deletions
diff --git a/lib/lz4/lz4_compress.c b/lib/lz4/lz4_compress.c
index cc7b6d4cc7c7..90bb67994688 100644
--- a/lib/lz4/lz4_compress.c
+++ b/lib/lz4/lz4_compress.c
@@ -446,7 +446,7 @@ _last_literals:
*op++ = (BYTE)(lastRun << ML_BITS);
}
- memcpy(op, anchor, lastRun);
+ LZ4_memcpy(op, anchor, lastRun);
op += lastRun;
}
@@ -708,7 +708,7 @@ _last_literals:
} else {
*op++ = (BYTE)(lastRunSize<<ML_BITS);
}
- memcpy(op, anchor, lastRunSize);
+ LZ4_memcpy(op, anchor, lastRunSize);
op += lastRunSize;
}
diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
index 0c9d3ad17e0f..59fe69a63800 100644
--- a/lib/lz4/lz4_decompress.c
+++ b/lib/lz4/lz4_decompress.c
@@ -141,6 +141,9 @@ static FORCE_INLINE int LZ4_decompress_generic(
* space in the output for those 18 bytes earlier, upon
* entering the shortcut (in other words, there is a
* combined check for both stages).
+ *
+ * The & in the likely() below is intentionally not && so that
+ * some compilers can produce better parallelized runtime code
*/
if ((endOnInput ? length != RUN_MASK : length <= 8)
/*
@@ -150,7 +153,7 @@ static FORCE_INLINE int LZ4_decompress_generic(
&& likely((endOnInput ? ip < shortiend : 1) &
(op <= shortoend))) {
/* Copy the literals */
- memcpy(op, ip, endOnInput ? 16 : 8);
+ LZ4_memcpy(op, ip, endOnInput ? 16 : 8);
op += length; ip += length;
/*
@@ -169,9 +172,9 @@ static FORCE_INLINE int LZ4_decompress_generic(
(offset >= 8) &&
(dict == withPrefix64k || match >= lowPrefix)) {
/* Copy the match. */
- memcpy(op + 0, match + 0, 8);
- memcpy(op + 8, match + 8, 8);
- memcpy(op + 16, match + 16, 2);
+ LZ4_memcpy(op + 0, match + 0, 8);
+ LZ4_memcpy(op + 8, match + 8, 8);
+ LZ4_memcpy(op + 16, match + 16, 2);
op += length + MINMATCH;
/* Both stages worked, load the next token. */
continue;
@@ -260,12 +263,20 @@ static FORCE_INLINE int LZ4_decompress_generic(
}
}
- memcpy(op, ip, length);
+ /*
+ * supports overlapping memory regions; only matters
+ * for in-place decompression scenarios
+ */
+ LZ4_memmove(op, ip, length);
ip += length;
op += length;
- /* Necessarily EOF, due to parsing restrictions */
- if (!partialDecoding || (cpy == oend))
+ /* Necessarily EOF when !partialDecoding.
+ * When partialDecoding, it is EOF if we've either
+ * filled the output buffer or
+ * can't proceed with reading an offset for following match.
+ */
+ if (!partialDecoding || (cpy == oend) || (ip >= (iend - 2)))
break;
} else {
/* may overwrite up to WILDCOPYLENGTH beyond cpy */
@@ -347,7 +358,7 @@ _copy_match:
size_t const copySize = (size_t)(lowPrefix - match);
size_t const restSize = length - copySize;
- memcpy(op, dictEnd - copySize, copySize);
+ LZ4_memcpy(op, dictEnd - copySize, copySize);
op += copySize;
if (restSize > (size_t)(op - lowPrefix)) {
/* overlap copy */
@@ -357,7 +368,7 @@ _copy_match:
while (op < endOfMatch)
*op++ = *copyFrom++;
} else {
- memcpy(op, lowPrefix, restSize);
+ LZ4_memcpy(op, lowPrefix, restSize);
op += restSize;
}
}
@@ -383,7 +394,7 @@ _copy_match:
while (op < copyEnd)
*op++ = *match++;
} else {
- memcpy(op, match, mlen);
+ LZ4_memcpy(op, match, mlen);
}
op = copyEnd;
if (op == oend)
@@ -397,7 +408,7 @@ _copy_match:
op[2] = match[2];
op[3] = match[3];
match += inc32table[offset];
- memcpy(op + 4, match, 4);
+ LZ4_memcpy(op + 4, match, 4);
match -= dec64table[offset];
} else {
LZ4_copy8(op, match);
@@ -474,7 +485,7 @@ int LZ4_decompress_fast(const char *source, char *dest, int originalSize)
/* ===== Instantiate a few more decoding cases, used more than once. ===== */
-int LZ4_decompress_safe_withPrefix64k(const char *source, char *dest,
+static int LZ4_decompress_safe_withPrefix64k(const char *source, char *dest,
int compressedSize, int maxOutputSize)
{
return LZ4_decompress_generic(source, dest,
@@ -496,9 +507,9 @@ static int LZ4_decompress_safe_withSmallPrefix(const char *source, char *dest,
(BYTE *)dest - prefixSize, NULL, 0);
}
-int LZ4_decompress_safe_forceExtDict(const char *source, char *dest,
- int compressedSize, int maxOutputSize,
- const void *dictStart, size_t dictSize)
+static int LZ4_decompress_safe_forceExtDict(const char *source, char *dest,
+ int compressedSize, int maxOutputSize,
+ const void *dictStart, size_t dictSize)
{
return LZ4_decompress_generic(source, dest,
compressedSize, maxOutputSize,
diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h
index 1a7fa9d9170f..330aa539b46e 100644
--- a/lib/lz4/lz4defs.h
+++ b/lib/lz4/lz4defs.h
@@ -36,6 +36,8 @@
*/
#include <asm/unaligned.h>
+
+#include <linux/bitops.h>
#include <linux/string.h> /* memset, memcpy */
#define FORCE_INLINE __always_inline
@@ -137,6 +139,17 @@ 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
diff --git a/lib/lz4/lz4hc_compress.c b/lib/lz4/lz4hc_compress.c
index 1b61d874e337..e7ac8694b797 100644
--- a/lib/lz4/lz4hc_compress.c
+++ b/lib/lz4/lz4hc_compress.c
@@ -570,7 +570,7 @@ _Search3:
*op++ = (BYTE) lastRun;
} else
*op++ = (BYTE)(lastRun<<ML_BITS);
- memcpy(op, anchor, iend - anchor);
+ LZ4_memcpy(op, anchor, iend - anchor);
op += iend - anchor;
}
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.