Merge branch 'for-4.12/asus' into for-linus

3 files changed, 223 insertions, 1 deletions

diff --git a/arch/openrisc/lib/Makefile b/arch/openrisc/lib/Makefile
index 966f65dbc6f0..17d9d37f32d2 100644
--- a/arch/openrisc/lib/Makefile
+++ b/arch/openrisc/lib/Makefile
@@ -2,4 +2,4 @@
 # Makefile for or32 specific library files..
 #
 
-obj-y  = string.o delay.o
+obj-y	:= delay.o string.o memset.o memcpy.o
diff --git a/arch/openrisc/lib/memcpy.c b/arch/openrisc/lib/memcpy.c
new file mode 100644
index 000000000000..669887a60e27
--- /dev/null
+++ b/arch/openrisc/lib/memcpy.c
@@ -0,0 +1,124 @@
+/*
+ * arch/openrisc/lib/memcpy.c
+ *
+ * Optimized memory copy routines for openrisc.  These are mostly copied
+ * from ohter sources but slightly entended based on ideas discuassed in
+ * #openrisc.
+ *
+ * The word unroll implementation is an extension to the arm byte
+ * unrolled implementation, but using word copies (if things are
+ * properly aligned)
+ *
+ * The great arm loop unroll algorithm can be found at:
+ *  arch/arm/boot/compressed/string.c
+ */
+
+#include <linux/export.h>
+
+#include <linux/string.h>
+
+#ifdef CONFIG_OR1K_1200
+/*
+ * Do memcpy with word copies and loop unrolling. This gives the
+ * best performance on the OR1200 and MOR1KX archirectures
+ */
+void *memcpy(void *dest, __const void *src, __kernel_size_t n)
+{
+	int i = 0;
+	unsigned char *d, *s;
+	uint32_t *dest_w = (uint32_t *)dest, *src_w = (uint32_t *)src;
+
+	/* If both source and dest are word aligned copy words */
+	if (!((unsigned int)dest_w & 3) && !((unsigned int)src_w & 3)) {
+		/* Copy 32 bytes per loop */
+		for (i = n >> 5; i > 0; i--) {
+			*dest_w++ = *src_w++;
+			*dest_w++ = *src_w++;
+			*dest_w++ = *src_w++;
+			*dest_w++ = *src_w++;
+			*dest_w++ = *src_w++;
+			*dest_w++ = *src_w++;
+			*dest_w++ = *src_w++;
+			*dest_w++ = *src_w++;
+		}
+
+		if (n & 1 << 4) {
+			*dest_w++ = *src_w++;
+			*dest_w++ = *src_w++;
+			*dest_w++ = *src_w++;
+			*dest_w++ = *src_w++;
+		}
+
+		if (n & 1 << 3) {
+			*dest_w++ = *src_w++;
+			*dest_w++ = *src_w++;
+		}
+
+		if (n & 1 << 2)
+			*dest_w++ = *src_w++;
+
+		d = (unsigned char *)dest_w;
+		s = (unsigned char *)src_w;
+
+	} else {
+		d = (unsigned char *)dest_w;
+		s = (unsigned char *)src_w;
+
+		for (i = n >> 3; i > 0; i--) {
+			*d++ = *s++;
+			*d++ = *s++;
+			*d++ = *s++;
+			*d++ = *s++;
+			*d++ = *s++;
+			*d++ = *s++;
+			*d++ = *s++;
+			*d++ = *s++;
+		}
+
+		if (n & 1 << 2) {
+			*d++ = *s++;
+			*d++ = *s++;
+			*d++ = *s++;
+			*d++ = *s++;
+		}
+	}
+
+	if (n & 1 << 1) {
+		*d++ = *s++;
+		*d++ = *s++;
+	}
+
+	if (n & 1)
+		*d++ = *s++;
+
+	return dest;
+}
+#else
+/*
+ * Use word copies but no loop unrolling as we cannot assume there
+ * will be benefits on the archirecture
+ */
+void *memcpy(void *dest, __const void *src, __kernel_size_t n)
+{
+	unsigned char *d = (unsigned char *)dest, *s = (unsigned char *)src;
+	uint32_t *dest_w = (uint32_t *)dest, *src_w = (uint32_t *)src;
+
+	/* If both source and dest are word aligned copy words */
+	if (!((unsigned int)dest_w & 3) && !((unsigned int)src_w & 3)) {
+		for (; n >= 4; n -= 4)
+			*dest_w++ = *src_w++;
+	}
+
+	d = (unsigned char *)dest_w;
+	s = (unsigned char *)src_w;
+
+	/* For remaining or if not aligned, copy bytes */
+	for (; n >= 1; n -= 1)
+		*d++ = *s++;
+
+	return dest;
+
+}
+#endif
+
+EXPORT_SYMBOL(memcpy);
diff --git a/arch/openrisc/lib/memset.S b/arch/openrisc/lib/memset.S
new file mode 100644
index 000000000000..92cc2eac26fa
--- /dev/null
+++ b/arch/openrisc/lib/memset.S
@@ -0,0 +1,98 @@
+/*
+ * OpenRISC memset.S
+ *
+ * Hand-optimized assembler version of memset for OpenRISC.
+ * Algorithm inspired by several other arch-specific memset routines
+ * in the kernel tree
+ *
+ * Copyright (C) 2015 Olof Kindgren <olof.kindgren@gmail.com>
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+
+	.global memset
+	.type	memset, @function
+memset:
+	/* arguments:
+	 * r3 = *s
+	 * r4 = c
+	 * r5 = n
+	 * r13, r15, r17, r19 used as temp regs
+	*/
+
+	/* Exit if n == 0 */
+	l.sfeqi		r5, 0
+	l.bf		4f
+
+	/* Truncate c to char */
+	l.andi  	r13, r4, 0xff
+
+	/* Skip word extension if c is 0 */
+	l.sfeqi		r13, 0
+	l.bf		1f
+	/* Check for at least two whole words (8 bytes) */
+	 l.sfleui	r5, 7
+
+	/* Extend char c to 32-bit word cccc in r13 */
+	l.slli		r15, r13, 16  // r13 = 000c, r15 = 0c00
+	l.or		r13, r13, r15 // r13 = 0c0c, r15 = 0c00
+	l.slli		r15, r13, 8   // r13 = 0c0c, r15 = c0c0
+	l.or		r13, r13, r15 // r13 = cccc, r15 = c0c0
+
+1:	l.addi		r19, r3, 0 // Set r19 = src
+	/* Jump to byte copy loop if less than two words */
+	l.bf		3f
+	 l.or		r17, r5, r0 // Set r17 = n
+
+	/* Mask out two LSBs to check alignment */
+	l.andi		r15, r3, 0x3
+
+	/* lsb == 00, jump to word copy loop */
+	l.sfeqi		r15, 0
+	l.bf		2f
+	 l.addi		r19, r3, 0 // Set r19 = src
+
+	/* lsb == 01,10 or 11 */
+	l.sb		0(r3), r13   // *src = c
+	l.addi		r17, r17, -1 // Decrease n
+
+	l.sfeqi		r15, 3
+	l.bf		2f
+	 l.addi		r19, r3, 1  // src += 1
+
+	/* lsb == 01 or 10 */
+	l.sb		1(r3), r13   // *(src+1) = c
+	l.addi		r17, r17, -1 // Decrease n
+
+	l.sfeqi		r15, 2
+	l.bf		2f
+	 l.addi		r19, r3, 2  // src += 2
+
+	/* lsb == 01 */
+	l.sb		2(r3), r13   // *(src+2) = c
+	l.addi		r17, r17, -1 // Decrease n
+	l.addi		r19, r3, 3   // src += 3
+
+	/* Word copy loop */
+2:	l.sw		0(r19), r13  // *src = cccc
+	l.addi		r17, r17, -4 // Decrease n
+	l.sfgeui	r17, 4
+	l.bf		2b
+	 l.addi		r19, r19, 4  // Increase src
+
+	/* When n > 0, copy the remaining bytes, otherwise jump to exit */
+	l.sfeqi		r17, 0
+	l.bf		4f
+
+	/* Byte copy loop */
+3:	l.addi		r17, r17, -1 // Decrease n
+	l.sb		0(r19), r13  // *src = cccc
+	l.sfnei		r17, 0
+	l.bf		3b
+	 l.addi		r19, r19, 1  // Increase src
+
+4:	l.jr		r9
+	 l.ori		r11, r3, 0