csky: Library functions

This patch adds string optimize codes and some auxiliary codes.

Signed-off-by: Chen Linfei <linfei_chen@c-sky.com>
Signed-off-by: Mao Han <han_mao@c-sky.com>
Signed-off-by: Guo Ren <ren_guo@c-sky.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>

1 files changed, 347 insertions, 0 deletions

diff --git a/arch/csky/abiv1/memcpy.S b/arch/csky/abiv1/memcpy.S
new file mode 100644
index 000000000000..5078eb5169fa
--- /dev/null
+++ b/arch/csky/abiv1/memcpy.S
@@ -0,0 +1,347 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
+
+#include <linux/linkage.h>
+
+.macro	GET_FRONT_BITS rx y
+#ifdef	__cskyLE__
+	lsri	\rx, \y
+#else
+	lsli	\rx, \y
+#endif
+.endm
+
+.macro	GET_AFTER_BITS rx y
+#ifdef	__cskyLE__
+	lsli	\rx, \y
+#else
+	lsri	\rx, \y
+#endif
+.endm
+
+/* void *memcpy(void *dest, const void *src, size_t n); */
+ENTRY(memcpy)
+	mov	r7, r2
+	cmplti	r4, 4
+	bt	.L_copy_by_byte
+	mov	r6, r2
+	andi	r6, 3
+	cmpnei	r6, 0
+	jbt	.L_dest_not_aligned
+	mov	r6, r3
+	andi	r6, 3
+	cmpnei	r6, 0
+	jbt	.L_dest_aligned_but_src_not_aligned
+.L0:
+	cmplti	r4, 16
+	jbt	.L_aligned_and_len_less_16bytes
+	subi	sp, 8
+	stw	r8, (sp, 0)
+.L_aligned_and_len_larger_16bytes:
+	ldw	r1, (r3, 0)
+	ldw	r5, (r3, 4)
+	ldw	r8, (r3, 8)
+	stw	r1, (r7, 0)
+	ldw	r1, (r3, 12)
+	stw	r5, (r7, 4)
+	stw	r8, (r7, 8)
+	stw	r1, (r7, 12)
+	subi	r4, 16
+	addi	r3, 16
+	addi	r7, 16
+	cmplti	r4, 16
+	jbf	.L_aligned_and_len_larger_16bytes
+	ldw	r8, (sp, 0)
+	addi	sp, 8
+	cmpnei	r4, 0
+	jbf	.L_return
+
+.L_aligned_and_len_less_16bytes:
+	cmplti	r4, 4
+	bt	.L_copy_by_byte
+.L1:
+	ldw	r1, (r3, 0)
+	stw	r1, (r7, 0)
+	subi	r4, 4
+	addi	r3, 4
+	addi	r7, 4
+	cmplti	r4, 4
+	jbf	.L1
+	br	.L_copy_by_byte
+
+.L_return:
+	rts
+
+.L_copy_by_byte:                      /* len less than 4 bytes */
+	cmpnei	r4, 0
+	jbf	.L_return
+.L4:
+	ldb	r1, (r3, 0)
+	stb	r1, (r7, 0)
+	addi	r3, 1
+	addi	r7, 1
+	decne	r4
+	jbt	.L4
+	rts
+
+/*
+ * If dest is not aligned, just copying some bytes makes the dest align.
+ * Afther that, we judge whether the src is aligned.
+ */
+.L_dest_not_aligned:
+	mov	r5, r3
+	rsub	r5, r5, r7
+	abs	r5, r5
+	cmplt	r5, r4
+	bt	.L_copy_by_byte
+	mov	r5, r7
+	sub	r5, r3
+	cmphs	r5, r4
+	bf	.L_copy_by_byte
+	mov	r5, r6
+.L5:
+	ldb	r1, (r3, 0)              /* makes the dest align. */
+	stb	r1, (r7, 0)
+	addi	r5, 1
+	subi	r4, 1
+	addi	r3, 1
+	addi	r7, 1
+	cmpnei	r5, 4
+	jbt	.L5
+	cmplti	r4, 4
+	jbt	.L_copy_by_byte
+	mov	r6, r3                   /* judge whether the src is aligned. */
+	andi	r6, 3
+	cmpnei	r6, 0
+	jbf	.L0
+
+/* Judge the number of misaligned, 1, 2, 3? */
+.L_dest_aligned_but_src_not_aligned:
+	mov	r5, r3
+	rsub	r5, r5, r7
+	abs	r5, r5
+	cmplt	r5, r4
+	bt	.L_copy_by_byte
+	bclri	r3, 0
+	bclri	r3, 1
+	ldw	r1, (r3, 0)
+	addi	r3, 4
+	cmpnei	r6, 2
+	bf	.L_dest_aligned_but_src_not_aligned_2bytes
+	cmpnei	r6, 3
+	bf	.L_dest_aligned_but_src_not_aligned_3bytes
+
+.L_dest_aligned_but_src_not_aligned_1byte:
+	mov	r5, r7
+	sub	r5, r3
+	cmphs	r5, r4
+	bf	.L_copy_by_byte
+	cmplti	r4, 16
+	bf	.L11
+.L10:                                     /* If the len is less than 16 bytes */
+	GET_FRONT_BITS r1 8
+	mov	r5, r1
+	ldw	r6, (r3, 0)
+	mov	r1, r6
+	GET_AFTER_BITS r6 24
+	or	r5, r6
+	stw	r5, (r7, 0)
+	subi	r4, 4
+	addi	r3, 4
+	addi	r7, 4
+	cmplti	r4, 4
+	bf	.L10
+	subi	r3, 3
+	br	.L_copy_by_byte
+.L11:
+	subi	sp, 16
+	stw	r8, (sp, 0)
+	stw	r9, (sp, 4)
+	stw	r10, (sp, 8)
+	stw	r11, (sp, 12)
+.L12:
+	ldw	r5, (r3, 0)
+	ldw	r11, (r3, 4)
+	ldw	r8, (r3, 8)
+	ldw	r9, (r3, 12)
+
+	GET_FRONT_BITS r1 8               /* little or big endian? */
+	mov	r10, r5
+	GET_AFTER_BITS r5 24
+	or	r5, r1
+
+	GET_FRONT_BITS r10 8
+	mov	r1, r11
+	GET_AFTER_BITS r11 24
+	or	r11, r10
+
+	GET_FRONT_BITS r1 8
+	mov	r10, r8
+	GET_AFTER_BITS r8 24
+	or	r8, r1
+
+	GET_FRONT_BITS r10 8
+	mov	r1, r9
+	GET_AFTER_BITS r9 24
+	or	r9, r10
+
+	stw	r5, (r7, 0)
+	stw	r11, (r7, 4)
+	stw	r8, (r7, 8)
+	stw	r9, (r7, 12)
+	subi	r4, 16
+	addi	r3, 16
+	addi	r7, 16
+	cmplti	r4, 16
+	jbf	.L12
+	ldw	r8, (sp, 0)
+	ldw	r9, (sp, 4)
+	ldw	r10, (sp, 8)
+	ldw	r11, (sp, 12)
+	addi	sp , 16
+	cmplti	r4, 4
+	bf	.L10
+	subi	r3, 3
+	br	.L_copy_by_byte
+
+.L_dest_aligned_but_src_not_aligned_2bytes:
+	cmplti	r4, 16
+	bf	.L21
+.L20:
+	GET_FRONT_BITS r1 16
+	mov	r5, r1
+	ldw	r6, (r3, 0)
+	mov	r1, r6
+	GET_AFTER_BITS r6 16
+	or	r5, r6
+	stw	r5, (r7, 0)
+	subi	r4, 4
+	addi	r3, 4
+	addi	r7, 4
+	cmplti	r4, 4
+	bf	.L20
+	subi	r3, 2
+	br	.L_copy_by_byte
+	rts
+
+.L21:	/* n > 16 */
+	subi 	sp, 16
+	stw	r8, (sp, 0)
+	stw	r9, (sp, 4)
+	stw	r10, (sp, 8)
+	stw	r11, (sp, 12)
+
+.L22:
+	ldw	r5, (r3, 0)
+	ldw	r11, (r3, 4)
+	ldw	r8, (r3, 8)
+	ldw	r9, (r3, 12)
+
+	GET_FRONT_BITS r1 16
+	mov	r10, r5
+	GET_AFTER_BITS r5 16
+	or	r5, r1
+
+	GET_FRONT_BITS r10 16
+	mov	r1, r11
+	GET_AFTER_BITS r11 16
+	or	r11, r10
+
+	GET_FRONT_BITS r1 16
+	mov	r10, r8
+	GET_AFTER_BITS r8 16
+	or	r8, r1
+
+	GET_FRONT_BITS r10 16
+	mov	r1, r9
+	GET_AFTER_BITS r9 16
+	or	r9, r10
+
+	stw	r5, (r7, 0)
+	stw	r11, (r7, 4)
+	stw	r8, (r7, 8)
+	stw	r9, (r7, 12)
+	subi	r4, 16
+	addi	r3, 16
+	addi	r7, 16
+	cmplti	r4, 16
+	jbf	.L22
+	ldw	r8, (sp, 0)
+	ldw	r9, (sp, 4)
+	ldw	r10, (sp, 8)
+	ldw	r11, (sp, 12)
+	addi	sp, 16
+	cmplti	r4, 4
+	bf	.L20
+	subi	r3, 2
+	br	.L_copy_by_byte
+
+
+.L_dest_aligned_but_src_not_aligned_3bytes:
+	cmplti	r4, 16
+	bf	.L31
+.L30:
+	GET_FRONT_BITS r1 24
+	mov	r5, r1
+	ldw	r6, (r3, 0)
+	mov	r1, r6
+	GET_AFTER_BITS r6 8
+	or	r5, r6
+	stw	r5, (r7, 0)
+	subi	r4, 4
+	addi	r3, 4
+	addi	r7, 4
+	cmplti	r4, 4
+	bf	.L30
+	subi	r3, 1
+	br	.L_copy_by_byte
+.L31:
+	subi	sp, 16
+	stw	r8, (sp, 0)
+	stw	r9, (sp, 4)
+	stw	r10, (sp, 8)
+	stw	r11, (sp, 12)
+.L32:
+	ldw	r5, (r3, 0)
+	ldw	r11, (r3, 4)
+	ldw	r8, (r3, 8)
+	ldw	r9, (r3, 12)
+
+	GET_FRONT_BITS r1 24
+	mov	r10, r5
+	GET_AFTER_BITS r5 8
+	or	r5, r1
+
+	GET_FRONT_BITS r10 24
+	mov	r1, r11
+	GET_AFTER_BITS r11 8
+	or	r11, r10
+
+	GET_FRONT_BITS r1 24
+	mov	r10, r8
+	GET_AFTER_BITS r8 8
+	or	r8, r1
+
+	GET_FRONT_BITS r10 24
+	mov	r1, r9
+	GET_AFTER_BITS r9 8
+	or	r9, r10
+
+	stw	r5, (r7, 0)
+	stw	r11, (r7, 4)
+	stw	r8, (r7, 8)
+	stw	r9, (r7, 12)
+	subi	r4, 16
+	addi	r3, 16
+	addi	r7, 16
+	cmplti	r4, 16
+	jbf	.L32
+	ldw	r8, (sp, 0)
+	ldw	r9, (sp, 4)
+	ldw	r10, (sp, 8)
+	ldw	r11, (sp, 12)
+	addi	sp, 16
+	cmplti	r4, 4
+	bf	.L30
+	subi	r3, 1
+	br	.L_copy_by_byte