[PATCH 15/17] MIPS: add 64-bit support for optimized string functions

[Denis Orlov <denorl2009@gmail.com>]

This adds macro definitions and a bit of code that allow to properly
utilise doubleword instructions on mips64. These changes are taken
directly from Linux sources. Also switch some o32-specific register
definitions to generic ones for this code to actually compile for n64
ABI.

While at it, this also removes an unused macro define.

Signed-off-by: Denis Orlov <denorl2009@gmail.com>
---
 arch/mips/Kconfig      |  1 -
 arch/mips/lib/memcpy.S | 37 ++++++++++++++++++++++++++++++++-----
 2 files changed, 32 insertions(+), 6 deletions(-)

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index ab8c8cf176..de2f539cc1 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -376,7 +376,6 @@ config NMON_HELP
 
 config MIPS_OPTIMIZED_STRING_FUNCTIONS
 	bool "use assembler optimized string functions"
-	depends on !64BIT
 	default y
 	help
 	  Say yes here to use assembler optimized memcpy / memset functions.
diff --git a/arch/mips/lib/memcpy.S b/arch/mips/lib/memcpy.S
index cee0319dcf..5c01dbdcd3 100644
--- a/arch/mips/lib/memcpy.S
+++ b/arch/mips/lib/memcpy.S
@@ -20,7 +20,26 @@
 #define src a1
 #define len a2
 
-#define LOADK lw /* No exception */
+#ifdef CONFIG_64BIT
+
+#define LOAD(reg, addr)		ld reg, addr
+#define LOADL(reg, addr)	ldl reg, addr
+#define LOADR(reg, addr)	ldr reg, addr
+#define STOREL(reg, addr)	sdl reg, addr
+#define STORER(reg, addr)	sdr reg, addr
+#define STORE(reg, addr)	sd reg, addr
+#define ADD    daddu
+#define SUB    dsubu
+#define SRL    dsrl
+#define SRA    dsra
+#define SLL    dsll
+#define SLLV   dsllv
+#define SRLV   dsrlv
+#define NBYTES 8
+#define LOG_NBYTES 3
+
+#else
+
 #define LOAD(reg, addr)		lw reg, addr
 #define LOADL(reg, addr)	lwl reg, addr
 #define LOADR(reg, addr)	lwr reg, addr
@@ -37,6 +56,8 @@
 #define NBYTES 4
 #define LOG_NBYTES 2
 
+#endif /* CONFIG_64BIT */
+
 #define LOADB(reg, addr)	lb reg, addr
 #define STOREB(reg, addr)	sb reg, addr
 
@@ -101,8 +122,8 @@ LEAF(memcpy)					/* a0=dst a1=src a2=len */
 	LOAD(t2, UNIT(2)(src))
 	LOAD(t3, UNIT(3)(src))
 	SUB	len, len, 8*NBYTES
-	LOAD(t4, UNIT(4)(src))
-	LOAD(t7, UNIT(5)(src))
+	LOAD(ta0, UNIT(4)(src))
+	LOAD(ta3, UNIT(5)(src))
 	STORE(t0, UNIT(0)(dst))
 	STORE(t1, UNIT(1)(dst))
 	LOAD(t0, UNIT(6)(src))
@@ -111,8 +132,8 @@ LEAF(memcpy)					/* a0=dst a1=src a2=len */
 	ADD	dst, dst, 8*NBYTES
 	STORE(t2, UNIT(-6)(dst))
 	STORE(t3, UNIT(-5)(dst))
-	STORE(t4, UNIT(-4)(dst))
-	STORE(t7, UNIT(-3)(dst))
+	STORE(ta0, UNIT(-4)(dst))
+	STORE(ta3, UNIT(-3)(dst))
 	STORE(t0, UNIT(-2)(dst))
 	STORE(t1, UNIT(-1)(dst))
 	bne	len, rem, 1b
@@ -263,6 +284,12 @@ LEAF(memcpy)					/* a0=dst a1=src a2=len */
 
 	COPY_BYTE(0)
 	COPY_BYTE(1)
+#ifdef CONFIG_64BIT
+	COPY_BYTE(2)
+	COPY_BYTE(3)
+	COPY_BYTE(4)
+	COPY_BYTE(5)
+#endif
 	LOADB(t0, NBYTES-2(src))
 	SUB	len, len, 1
 	jr	ra
-- 
2.41.0