riscv: optimized memset

The generic memset is defined as a byte at time write. This is always
safe, but it's slower than a 4 byte or even 8 byte write.

Write a generic memset which fills the data one byte at time until the
destination is aligned, then fills using the largest size allowed,
and finally fills the remaining data one byte at time.

Signed-off-by: Matteo Croce <mcroce@microsoft.com>

arch/riscv/include/asm/string.h

@@ -6,14 +6,10 @@
 #ifndef _ASM_RISCV_STRING_H
 #define _ASM_RISCV_STRING_H
 
-#include <linux/types.h>
-#include <linux/linkage.h>
-
-#define __HAVE_ARCH_MEMSET
-extern asmlinkage void *memset(void *, int, size_t);
-extern asmlinkage void *__memset(void *, int, size_t);
-
 #ifdef CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE
+#define __HAVE_ARCH_MEMSET
+extern void *memset(void *s, int c, size_t count);
+extern void *__memset(void *s, int c, size_t count);
 #define __HAVE_ARCH_MEMCPY
 extern void *memcpy(void *dest, const void *src, size_t count);
 extern void *__memcpy(void *dest, const void *src, size_t count);

arch/riscv/kernel/Makefile

@@ -31,7 +31,6 @@ obj-y	+= syscall_table.o
 obj-y	+= sys_riscv.o
 obj-y	+= time.o
 obj-y	+= traps.o
-obj-y	+= riscv_ksyms.o
 obj-y	+= stacktrace.o
 obj-y	+= cacheinfo.o
 obj-y	+= patch.o

arch/riscv/lib/Makefile

@@ -1,6 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 lib-y			+= delay.o
-lib-y			+= memset.o
 lib-$(CONFIG_MMU)	+= uaccess.o
 lib-$(CONFIG_64BIT)	+= tishift.o
 lib-$(CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE) += string.o

arch/riscv/lib/string.c

@@ -111,3 +111,44 @@ EXPORT_SYMBOL(__memmove);
 
 void *memmove(void *dest, const void *src, size_t count) __weak __alias(__memmove);
 EXPORT_SYMBOL(memmove);
+
+void *__memset(void *s, int c, size_t count)
+{
+	union types dest = { .as_u8 = s };
+
+	if (count >= MIN_THRESHOLD) {
+		unsigned long cu = (unsigned long)c;
+
+		/* Compose an ulong with 'c' repeated 4/8 times */
+#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
+		cu *= 0x0101010101010101UL;
+#else
+		cu |= cu << 8;
+		cu |= cu << 16;
+		/* Suppress warning on 32 bit machines */
+		cu |= (cu << 16) << 16;
+#endif
+		if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) {
+			/*
+			 * Fill the buffer one byte at time until
+			 * the destination is word aligned.
+			 */
+			for (; count && dest.as_uptr & WORD_MASK; count--)
+				*dest.as_u8++ = c;
+		}
+
+		/* Copy using the largest size allowed */
+		for (; count >= BYTES_LONG; count -= BYTES_LONG)
+			*dest.as_ulong++ = cu;
+	}
+
+	/* copy the remainder */
+	while (count--)
+		*dest.as_u8++ = c;
+
+	return s;
+}
+EXPORT_SYMBOL(__memset);
+
+void *memset(void *s, int c, size_t count) __weak __alias(__memset);
+EXPORT_SYMBOL(memset);