riscv: assembler versions of memcpy, memmove, memset

Provide optimized versions of memcpy(), memmove(), memset() copied from
the Linux kernel.

Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Reviewed-by: Leo Yu-Chi Liang <ycliang@andestech.com>

6 files changed, 382 insertions, 21 deletions

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index e8494c2..3f221dc 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -271,4 +271,82 @@ config STACK_SIZE_SHIFT
 config OF_BOARD_FIXUP
 	default y if OF_SEPARATE && RISCV_SMODE
 
+config USE_ARCH_MEMCPY
+	bool "Use an assembly optimized implementation of memcpy"
+	default y
+	help
+	  Enable the generation of an optimized version of memcpy.
+	  Such an implementation may be faster under some conditions
+	  but may increase the binary size.
+
+config SPL_USE_ARCH_MEMCPY
+	bool "Use an assembly optimized implementation of memcpy for SPL"
+	default y if USE_ARCH_MEMCPY
+	depends on SPL
+	help
+	  Enable the generation of an optimized version of memcpy.
+	  Such an implementation may be faster under some conditions
+	  but may increase the binary size.
+
+config TPL_USE_ARCH_MEMCPY
+	bool "Use an assembly optimized implementation of memcpy for TPL"
+	default y if USE_ARCH_MEMCPY
+	depends on TPL
+	help
+	  Enable the generation of an optimized version of memcpy.
+	  Such an implementation may be faster under some conditions
+	  but may increase the binary size.
+
+config USE_ARCH_MEMMOVE
+	bool "Use an assembly optimized implementation of memmove"
+	default y
+	help
+	  Enable the generation of an optimized version of memmove.
+	  Such an implementation may be faster under some conditions
+	  but may increase the binary size.
+
+config SPL_USE_ARCH_MEMMOVE
+	bool "Use an assembly optimized implementation of memmove for SPL"
+	default y if USE_ARCH_MEMCPY
+	depends on SPL
+	help
+	  Enable the generation of an optimized version of memmove.
+	  Such an implementation may be faster under some conditions
+	  but may increase the binary size.
+
+config TPL_USE_ARCH_MEMMOVE
+	bool "Use an assembly optimized implementation of memmove for TPL"
+	default y if USE_ARCH_MEMCPY
+	depends on TPL
+	help
+	  Enable the generation of an optimized version of memmove.
+	  Such an implementation may be faster under some conditions
+	  but may increase the binary size.
+
+config USE_ARCH_MEMSET
+	bool "Use an assembly optimized implementation of memset"
+	default y
+	help
+	  Enable the generation of an optimized version of memset.
+	  Such an implementation may be faster under some conditions
+	  but may increase the binary size.
+
+config SPL_USE_ARCH_MEMSET
+	bool "Use an assembly optimized implementation of memset for SPL"
+	default y if USE_ARCH_MEMSET
+	depends on SPL
+	help
+	  Enable the generation of an optimized version of memset.
+	  Such an implementation may be faster under some conditions
+	  but may increase the binary size.
+
+config TPL_USE_ARCH_MEMSET
+	bool "Use an assembly optimized implementation of memset for TPL"
+	default y if USE_ARCH_MEMSET
+	depends on TPL
+	help
+	  Enable the generation of an optimized version of memset.
+	  Such an implementation may be faster under some conditions
+	  but may increase the binary size.
+
 endmenu
diff --git a/arch/riscv/include/asm/string.h b/arch/riscv/include/asm/string.h
index 0fc3424..7dee3e4 100644
--- a/arch/riscv/include/asm/string.h
+++ b/arch/riscv/include/asm/string.h
@@ -19,31 +19,25 @@
 
 #undef __HAVE_ARCH_STRRCHR
 #undef __HAVE_ARCH_STRCHR
-#undef __HAVE_ARCH_MEMCPY
-#undef __HAVE_ARCH_MEMMOVE
 #undef __HAVE_ARCH_MEMCHR
 #undef __HAVE_ARCH_MEMZERO
-#undef __HAVE_ARCH_MEMSET
 
-#ifdef CONFIG_MARCO_MEMSET
-#define memset(_p, _v, _n)	\
-	(typeof(_p) (p) = (_p); \
-	 typeof(_v) (v) = (_v); \
-	 typeof(_n) (n) = (_n); \
-	 {								\
-		if ((n) != 0) {						\
-			if (__builtin_constant_p((v)) && (v) == 0)	\
-				__memzero((p), (n));			\
-			else						\
-				memset((p), (v), (n));			\
-		}							\
-		(p);							\
-	})
+#undef __HAVE_ARCH_MEMCPY
+#if CONFIG_IS_ENABLED(USE_ARCH_MEMCPY)
+#define __HAVE_ARCH_MEMCPY
+#endif
+extern void *memcpy(void *, const void *, __kernel_size_t);
+
+#undef __HAVE_ARCH_MEMMOVE
+#if CONFIG_IS_ENABLED(USE_ARCH_MEMMOVE)
+#define __HAVE_ARCH_MEMMOVE
+#endif
+extern void *memmove(void *, const void *, __kernel_size_t);
 
-#define memzero(_p, _n) \
-	(typeof(_p) (p) = (_p); \
-	 typeof(_n) (n) = (_n); \
-	 { if ((n) != 0) __memzero((p), (n)); (p); })
+#undef __HAVE_ARCH_MEMZERO
+#if CONFIG_IS_ENABLED(USE_ARCH_MEMSET)
+#define __HAVE_ARCH_MEMSET
 #endif
+extern void *memset(void *, int, __kernel_size_t);
 
 #endif /* __ASM_RISCV_STRING_H */
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
index 12c14f2..ff0677a 100644
--- a/arch/riscv/lib/Makefile
+++ b/arch/riscv/lib/Makefile
@@ -36,3 +36,7 @@ CFLAGS_REMOVE_$(EFI_RELOC) := $(CFLAGS_NON_EFI)
 extra-$(CONFIG_CMD_BOOTEFI_HELLO_COMPILE) += $(EFI_CRT0) $(EFI_RELOC)
 extra-$(CONFIG_CMD_BOOTEFI_SELFTEST) += $(EFI_CRT0) $(EFI_RELOC)
 extra-$(CONFIG_EFI) += $(EFI_CRT0) $(EFI_RELOC)
+
+obj-$(CONFIG_$(SPL_TPL_)USE_ARCH_MEMSET) += memset.o
+obj-$(CONFIG_$(SPL_TPL_)USE_ARCH_MEMMOVE) += memmove.o
+obj-$(CONFIG_$(SPL_TPL_)USE_ARCH_MEMCPY) += memcpy.o
diff --git a/arch/riscv/lib/memcpy.S b/arch/riscv/lib/memcpy.S
new file mode 100644
index 0000000..51ab716
--- /dev/null
+++ b/arch/riscv/lib/memcpy.S
@@ -0,0 +1,108 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013 Regents of the University of California
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+/* void *memcpy(void *, const void *, size_t) */
+ENTRY(__memcpy)
+WEAK(memcpy)
+	move t6, a0  /* Preserve return value */
+
+	/* Defer to byte-oriented copy for small sizes */
+	sltiu a3, a2, 128
+	bnez a3, 4f
+	/* Use word-oriented copy only if low-order bits match */
+	andi a3, t6, SZREG-1
+	andi a4, a1, SZREG-1
+	bne a3, a4, 4f
+
+	beqz a3, 2f  /* Skip if already aligned */
+	/*
+	 * Round to nearest double word-aligned address
+	 * greater than or equal to start address
+	 */
+	andi a3, a1, ~(SZREG-1)
+	addi a3, a3, SZREG
+	/* Handle initial misalignment */
+	sub a4, a3, a1
+1:
+	lb a5, 0(a1)
+	addi a1, a1, 1
+	sb a5, 0(t6)
+	addi t6, t6, 1
+	bltu a1, a3, 1b
+	sub a2, a2, a4  /* Update count */
+
+2:
+	andi a4, a2, ~((16*SZREG)-1)
+	beqz a4, 4f
+	add a3, a1, a4
+3:
+	REG_L a4,       0(a1)
+	REG_L a5,   SZREG(a1)
+	REG_L a6, 2*SZREG(a1)
+	REG_L a7, 3*SZREG(a1)
+	REG_L t0, 4*SZREG(a1)
+	REG_L t1, 5*SZREG(a1)
+	REG_L t2, 6*SZREG(a1)
+	REG_L t3, 7*SZREG(a1)
+	REG_L t4, 8*SZREG(a1)
+	REG_L t5, 9*SZREG(a1)
+	REG_S a4,       0(t6)
+	REG_S a5,   SZREG(t6)
+	REG_S a6, 2*SZREG(t6)
+	REG_S a7, 3*SZREG(t6)
+	REG_S t0, 4*SZREG(t6)
+	REG_S t1, 5*SZREG(t6)
+	REG_S t2, 6*SZREG(t6)
+	REG_S t3, 7*SZREG(t6)
+	REG_S t4, 8*SZREG(t6)
+	REG_S t5, 9*SZREG(t6)
+	REG_L a4, 10*SZREG(a1)
+	REG_L a5, 11*SZREG(a1)
+	REG_L a6, 12*SZREG(a1)
+	REG_L a7, 13*SZREG(a1)
+	REG_L t0, 14*SZREG(a1)
+	REG_L t1, 15*SZREG(a1)
+	addi a1, a1, 16*SZREG
+	REG_S a4, 10*SZREG(t6)
+	REG_S a5, 11*SZREG(t6)
+	REG_S a6, 12*SZREG(t6)
+	REG_S a7, 13*SZREG(t6)
+	REG_S t0, 14*SZREG(t6)
+	REG_S t1, 15*SZREG(t6)
+	addi t6, t6, 16*SZREG
+	bltu a1, a3, 3b
+	andi a2, a2, (16*SZREG)-1  /* Update count */
+
+4:
+	/* Handle trailing misalignment */
+	beqz a2, 6f
+	add a3, a1, a2
+
+	/* Use word-oriented copy if co-aligned to word boundary */
+	or a5, a1, t6
+	or a5, a5, a3
+	andi a5, a5, 3
+	bnez a5, 5f
+7:
+	lw a4, 0(a1)
+	addi a1, a1, 4
+	sw a4, 0(t6)
+	addi t6, t6, 4
+	bltu a1, a3, 7b
+
+	ret
+
+5:
+	lb a4, 0(a1)
+	addi a1, a1, 1
+	sb a4, 0(t6)
+	addi t6, t6, 1
+	bltu a1, a3, 5b
+6:
+	ret
+END(__memcpy)
diff --git a/arch/riscv/lib/memmove.S b/arch/riscv/lib/memmove.S
new file mode 100644
index 0000000..07d1d21
--- /dev/null
+++ b/arch/riscv/lib/memmove.S
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+ENTRY(__memmove)
+WEAK(memmove)
+        move    t0, a0
+        move    t1, a1
+
+        beq     a0, a1, exit_memcpy
+        beqz    a2, exit_memcpy
+        srli    t2, a2, 0x2
+
+        slt     t3, a0, a1
+        beqz    t3, do_reverse
+
+        andi    a2, a2, 0x3
+        li      t4, 1
+        beqz    t2, byte_copy
+
+word_copy:
+        lw      t3, 0(a1)
+        addi    t2, t2, -1
+        addi    a1, a1, 4
+        sw      t3, 0(a0)
+        addi    a0, a0, 4
+        bnez    t2, word_copy
+        beqz    a2, exit_memcpy
+        j       byte_copy
+
+do_reverse:
+        add     a0, a0, a2
+        add     a1, a1, a2
+        andi    a2, a2, 0x3
+        li      t4, -1
+        beqz    t2, reverse_byte_copy
+
+reverse_word_copy:
+        addi    a1, a1, -4
+        addi    t2, t2, -1
+        lw      t3, 0(a1)
+        addi    a0, a0, -4
+        sw      t3, 0(a0)
+        bnez    t2, reverse_word_copy
+        beqz    a2, exit_memcpy
+
+reverse_byte_copy:
+        addi    a0, a0, -1
+        addi    a1, a1, -1
+
+byte_copy:
+        lb      t3, 0(a1)
+        addi    a2, a2, -1
+        sb      t3, 0(a0)
+        add     a1, a1, t4
+        add     a0, a0, t4
+        bnez    a2, byte_copy
+
+exit_memcpy:
+        move a0, t0
+        move a1, t1
+        ret
+END(__memmove)
diff --git a/arch/riscv/lib/memset.S b/arch/riscv/lib/memset.S
new file mode 100644
index 0000000..34c5360
--- /dev/null
+++ b/arch/riscv/lib/memset.S
@@ -0,0 +1,113 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013 Regents of the University of California
+ */
+
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+/* void *memset(void *, int, size_t) */
+ENTRY(__memset)
+WEAK(memset)
+	move t0, a0  /* Preserve return value */
+
+	/* Defer to byte-oriented fill for small sizes */
+	sltiu a3, a2, 16
+	bnez a3, 4f
+
+	/*
+	 * Round to nearest XLEN-aligned address
+	 * greater than or equal to start address
+	 */
+	addi a3, t0, SZREG-1
+	andi a3, a3, ~(SZREG-1)
+	beq a3, t0, 2f  /* Skip if already aligned */
+	/* Handle initial misalignment */
+	sub a4, a3, t0
+1:
+	sb a1, 0(t0)
+	addi t0, t0, 1
+	bltu t0, a3, 1b
+	sub a2, a2, a4  /* Update count */
+
+2: /* Duff's device with 32 XLEN stores per iteration */
+	/* Broadcast value into all bytes */
+	andi a1, a1, 0xff
+	slli a3, a1, 8
+	or a1, a3, a1
+	slli a3, a1, 16
+	or a1, a3, a1
+#ifdef CONFIG_64BIT
+	slli a3, a1, 32
+	or a1, a3, a1
+#endif
+
+	/* Calculate end address */
+	andi a4, a2, ~(SZREG-1)
+	add a3, t0, a4
+
+	andi a4, a4, 31*SZREG  /* Calculate remainder */
+	beqz a4, 3f            /* Shortcut if no remainder */
+	neg a4, a4
+	addi a4, a4, 32*SZREG  /* Calculate initial offset */
+
+	/* Adjust start address with offset */
+	sub t0, t0, a4
+
+	/* Jump into loop body */
+	/* Assumes 32-bit instruction lengths */
+	la a5, 3f
+#ifdef CONFIG_64BIT
+	srli a4, a4, 1
+#endif
+	add a5, a5, a4
+	jr a5
+3:
+	REG_S a1,        0(t0)
+	REG_S a1,    SZREG(t0)
+	REG_S a1,  2*SZREG(t0)
+	REG_S a1,  3*SZREG(t0)
+	REG_S a1,  4*SZREG(t0)
+	REG_S a1,  5*SZREG(t0)
+	REG_S a1,  6*SZREG(t0)
+	REG_S a1,  7*SZREG(t0)
+	REG_S a1,  8*SZREG(t0)
+	REG_S a1,  9*SZREG(t0)
+	REG_S a1, 10*SZREG(t0)
+	REG_S a1, 11*SZREG(t0)
+	REG_S a1, 12*SZREG(t0)
+	REG_S a1, 13*SZREG(t0)
+	REG_S a1, 14*SZREG(t0)
+	REG_S a1, 15*SZREG(t0)
+	REG_S a1, 16*SZREG(t0)
+	REG_S a1, 17*SZREG(t0)
+	REG_S a1, 18*SZREG(t0)
+	REG_S a1, 19*SZREG(t0)
+	REG_S a1, 20*SZREG(t0)
+	REG_S a1, 21*SZREG(t0)
+	REG_S a1, 22*SZREG(t0)
+	REG_S a1, 23*SZREG(t0)
+	REG_S a1, 24*SZREG(t0)
+	REG_S a1, 25*SZREG(t0)
+	REG_S a1, 26*SZREG(t0)
+	REG_S a1, 27*SZREG(t0)
+	REG_S a1, 28*SZREG(t0)
+	REG_S a1, 29*SZREG(t0)
+	REG_S a1, 30*SZREG(t0)
+	REG_S a1, 31*SZREG(t0)
+	addi t0, t0, 32*SZREG
+	bltu t0, a3, 3b
+	andi a2, a2, SZREG-1  /* Update count */
+
+4:
+	/* Handle trailing misalignment */
+	beqz a2, 6f
+	add a3, t0, a2
+5:
+	sb a1, 0(t0)
+	addi t0, t0, 1
+	bltu t0, a3, 5b
+6:
+	ret
+END(__memset)