ARCv2: lib: introduce memcpy optimized for unaligned access

Optimise code to use efficient unaligned memory access which is
available on ARCv2. This allows us to really simplify memcpy code
and speed up the code one and a half times (in case of unaligned
source or destination).

Don't wire it up yet !
Signed-off-by: Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>

arch/arc/lib/memcpy-archs-unaligned.S

+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * ARCv2 memcpy implementation optimized for unaligned memory access using.
+ *
+ * Copyright (C) 2019 Synopsys
+ * Author: Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
+ */
+
+#include <linux/linkage.h>
+
+#ifdef CONFIG_ARC_HAS_LL64
+# define LOADX(DST,RX)		ldd.ab	DST, [RX, 8]
+# define STOREX(SRC,RX)		std.ab	SRC, [RX, 8]
+# define ZOLSHFT		5
+# define ZOLAND			0x1F
+#else
+# define LOADX(DST,RX)		ld.ab	DST, [RX, 4]
+# define STOREX(SRC,RX)		st.ab	SRC, [RX, 4]
+# define ZOLSHFT		4
+# define ZOLAND			0xF
+#endif
+
+ENTRY_CFI(memcpy)
+	mov	r3, r0		; don;t clobber ret val
+
+	lsr.f	lp_count, r2, ZOLSHFT
+	lpnz	@.Lcopy32_64bytes
+	;; LOOP START
+	LOADX	(r6, r1)
+	LOADX	(r8, r1)
+	LOADX	(r10, r1)
+	LOADX	(r4, r1)
+	STOREX	(r6, r3)
+	STOREX	(r8, r3)
+	STOREX	(r10, r3)
+	STOREX	(r4, r3)
+.Lcopy32_64bytes:
+
+	and.f	lp_count, r2, ZOLAND ;Last remaining 31 bytes
+	lpnz	@.Lcopyremainingbytes
+	;; LOOP START
+	ldb.ab	r5, [r1, 1]
+	stb.ab	r5, [r3, 1]
+.Lcopyremainingbytes:
+
+	j	[blink]
+END_CFI(memcpy)