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] lz4/lz4#890

Signed-off-by: Nick Terrell <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Cc: Yann Collet <[email protected]>
Cc: Gao Xiang <[email protected]>
Cc: Sven Schmidt <[email protected]>
Cc: Greg Kroah-Hartman <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Arvind Sankar <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Linus Torvalds <[email protected]>
Signed-off-by: Diab Neiroukh <[email protected]>
Signed-off-by: Lau <[email protected]>

lib/lz4/lz4_compress.c

@@ -446,7 +446,7 @@ static FORCE_INLINE int LZ4_compress_generic(
 			*op++ = (BYTE)(lastRun << ML_BITS);
 		}
 
-		memcpy(op, anchor, lastRun);
+		LZ4_memcpy(op, anchor, lastRun);
 
 		op += lastRun;
 	}

lib/lz4/lz4_decompress.c

@@ -150,7 +150,7 @@ 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 +169,9 @@ 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;
@@ -260,7 +260,7 @@ static FORCE_INLINE int LZ4_decompress_generic(
 				}
 			}
 
-			memcpy(op, ip, length);
+			LZ4_memcpy(op, ip, length);
 			ip += length;
 			op += length;
 
@@ -383,7 +383,7 @@ static FORCE_INLINE int LZ4_decompress_generic(
 				while (op < copyEnd)
 					*op++ = *match++;
 			} else {
-				memcpy(op, match, mlen);
+				LZ4_memcpy(op, match, mlen);
 			}
 			op = copyEnd;
 			if (op == oend)
@@ -397,7 +397,7 @@ static FORCE_INLINE int LZ4_decompress_generic(
 			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);

lib/lz4/lz4defs.h

@@ -137,6 +137,16 @@ 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

lib/lz4/lz4hc_compress.c

@@ -570,7 +570,7 @@ static int LZ4HC_compress_generic(
 			*op++ = (BYTE) lastRun;
 		} else
 			*op++ = (BYTE)(lastRun<<ML_BITS);
-		memcpy(op, anchor, iend - anchor);
+		LZ4_memcpy(op, anchor, iend - anchor);
 		op += iend - anchor;
 	}