Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/lib/lz4/lz4_compress.c b/lib/lz4/lz4_compress.c
index cc7b6d4..90bb679 100644
--- a/lib/lz4/lz4_compress.c
+++ b/lib/lz4/lz4_compress.c
@@ -446,7 +446,7 @@
*op++ = (BYTE)(lastRun << ML_BITS);
}
- memcpy(op, anchor, lastRun);
+ LZ4_memcpy(op, anchor, lastRun);
op += lastRun;
}
@@ -708,7 +708,7 @@
} 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 4d0b59f..8a7724a 100644
--- a/lib/lz4/lz4_decompress.c
+++ b/lib/lz4/lz4_decompress.c
@@ -141,6 +141,9 @@
* 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 @@
&& 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 @@
(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;
@@ -351,7 +354,7 @@
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 */
@@ -361,7 +364,7 @@
while (op < endOfMatch)
*op++ = *copyFrom++;
} else {
- memcpy(op, lowPrefix, restSize);
+ LZ4_memcpy(op, lowPrefix, restSize);
op += restSize;
}
}
@@ -387,7 +390,7 @@
while (op < copyEnd)
*op++ = *match++;
} else {
- memcpy(op, match, mlen);
+ LZ4_memcpy(op, match, mlen);
}
op = copyEnd;
if (op == oend)
@@ -401,7 +404,7 @@
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);
diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h
index 369eb18..673bd20 100644
--- a/lib/lz4/lz4defs.h
+++ b/lib/lz4/lz4defs.h
@@ -137,6 +137,15 @@
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)
diff --git a/lib/lz4/lz4hc_compress.c b/lib/lz4/lz4hc_compress.c
index 1b61d87..e7ac869 100644
--- a/lib/lz4/lz4hc_compress.c
+++ b/lib/lz4/lz4hc_compress.c
@@ -570,7 +570,7 @@
*op++ = (BYTE) lastRun;
} else
*op++ = (BYTE)(lastRun<<ML_BITS);
- memcpy(op, anchor, iend - anchor);
+ LZ4_memcpy(op, anchor, iend - anchor);
op += iend - anchor;
}