21 files changed, 271 insertions, 8 deletions

diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 69ff9887f724..5540a1638baf 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -5,6 +5,12 @@ lib-y		:= clear_user.o delay.o copy_from_user.o		\
 		   memcmp.o strcmp.o strncmp.o strlen.o strnlen.o	\
 		   strchr.o strrchr.o tishift.o
 
+ifeq ($(CONFIG_KERNEL_MODE_NEON), y)
+obj-$(CONFIG_XOR_BLOCKS)	+= xor-neon.o
+CFLAGS_REMOVE_xor-neon.o	+= -mgeneral-regs-only
+CFLAGS_xor-neon.o		+= -ffreestanding
+endif
+
 # Tell the compiler to treat all general purpose registers (with the
 # exception of the IP registers, which are already handled by the caller
 # in case of a PLT) as callee-saved, which allows for efficient runtime
diff --git a/arch/arm64/lib/clear_page.S b/arch/arm64/lib/clear_page.S
index ef08e905e35b..6d13b0d64ad5 100644
--- a/arch/arm64/lib/clear_page.S
+++ b/arch/arm64/lib/clear_page.S
@@ -37,3 +37,4 @@ ENTRY(clear_page)
 	b.ne	1b
 	ret
 ENDPROC(clear_page)
+EXPORT_SYMBOL(clear_page)
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index 21ba0b29621b..feb225bd4b80 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -18,6 +18,7 @@
 #include <linux/linkage.h>
 
 #include <asm/asm-uaccess.h>
+#include <asm/assembler.h>
 
 	.text
 
@@ -53,6 +54,7 @@ uao_user_alternative 9f, strb, sttrb, wzr, x0, 0
 	uaccess_disable_not_uao x2, x3
 	ret
 ENDPROC(__arch_clear_user)
+EXPORT_SYMBOL(__arch_clear_user)
 
 	.section .fixup,"ax"
 	.align	2
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index 20305d485046..dea6c762d52f 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -16,8 +16,9 @@
 
 #include <linux/linkage.h>
 
-#include <asm/cache.h>
 #include <asm/asm-uaccess.h>
+#include <asm/assembler.h>
+#include <asm/cache.h>
 
 /*
  * Copy from user space to a kernel buffer (alignment handled by the hardware)
@@ -71,6 +72,7 @@ ENTRY(__arch_copy_from_user)
 	mov	x0, #0				// Nothing to copy
 	ret
 ENDPROC(__arch_copy_from_user)
+EXPORT_SYMBOL(__arch_copy_from_user)
 
 	.section .fixup,"ax"
 	.align	2
diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S
index 54b75deb1d16..a84227fbf716 100644
--- a/arch/arm64/lib/copy_in_user.S
+++ b/arch/arm64/lib/copy_in_user.S
@@ -18,8 +18,9 @@
 
 #include <linux/linkage.h>
 
-#include <asm/cache.h>
 #include <asm/asm-uaccess.h>
+#include <asm/assembler.h>
+#include <asm/cache.h>
 
 /*
  * Copy from user space to user space (alignment handled by the hardware)
@@ -73,6 +74,7 @@ ENTRY(__arch_copy_in_user)
 	mov	x0, #0
 	ret
 ENDPROC(__arch_copy_in_user)
+EXPORT_SYMBOL(__arch_copy_in_user)
 
 	.section .fixup,"ax"
 	.align	2
diff --git a/arch/arm64/lib/copy_page.S b/arch/arm64/lib/copy_page.S
index 076c43715e64..98313e24a987 100644
--- a/arch/arm64/lib/copy_page.S
+++ b/arch/arm64/lib/copy_page.S
@@ -87,3 +87,4 @@ alternative_else_nop_endif
 
 	ret
 ENDPROC(copy_page)
+EXPORT_SYMBOL(copy_page)
diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S
index fda6172d6b88..ef44c7ca3ffb 100644
--- a/arch/arm64/lib/copy_to_user.S
+++ b/arch/arm64/lib/copy_to_user.S
@@ -16,8 +16,9 @@
 
 #include <linux/linkage.h>
 
-#include <asm/cache.h>
 #include <asm/asm-uaccess.h>
+#include <asm/assembler.h>
+#include <asm/cache.h>
 
 /*
  * Copy to user space from a kernel buffer (alignment handled by the hardware)
@@ -70,6 +71,7 @@ ENTRY(__arch_copy_to_user)
 	mov	x0, #0
 	ret
 ENDPROC(__arch_copy_to_user)
+EXPORT_SYMBOL(__arch_copy_to_user)
 
 	.section .fixup,"ax"
 	.align	2
diff --git a/arch/arm64/lib/crc32.S b/arch/arm64/lib/crc32.S
index 5bc1e85b4e1c..f132f2a7522e 100644
--- a/arch/arm64/lib/crc32.S
+++ b/arch/arm64/lib/crc32.S
@@ -15,15 +15,59 @@
 	.cpu		generic+crc
 
 	.macro		__crc32, c
-0:	subs		x2, x2, #16
-	b.mi		8f
-	ldp		x3, x4, [x1], #16
+	cmp		x2, #16
+	b.lt		8f			// less than 16 bytes
+
+	and		x7, x2, #0x1f
+	and		x2, x2, #~0x1f
+	cbz		x7, 32f			// multiple of 32 bytes
+
+	and		x8, x7, #0xf
+	ldp		x3, x4, [x1]
+	add		x8, x8, x1
+	add		x1, x1, x7
+	ldp		x5, x6, [x8]
 CPU_BE(	rev		x3, x3		)
 CPU_BE(	rev		x4, x4		)
+CPU_BE(	rev		x5, x5		)
+CPU_BE(	rev		x6, x6		)
+
+	tst		x7, #8
+	crc32\c\()x	w8, w0, x3
+	csel		x3, x3, x4, eq
+	csel		w0, w0, w8, eq
+	tst		x7, #4
+	lsr		x4, x3, #32
+	crc32\c\()w	w8, w0, w3
+	csel		x3, x3, x4, eq
+	csel		w0, w0, w8, eq
+	tst		x7, #2
+	lsr		w4, w3, #16
+	crc32\c\()h	w8, w0, w3
+	csel		w3, w3, w4, eq
+	csel		w0, w0, w8, eq
+	tst		x7, #1
+	crc32\c\()b	w8, w0, w3
+	csel		w0, w0, w8, eq
+	tst		x7, #16
+	crc32\c\()x	w8, w0, x5
+	crc32\c\()x	w8, w8, x6
+	csel		w0, w0, w8, eq
+	cbz		x2, 0f
+
+32:	ldp		x3, x4, [x1], #32
+	sub		x2, x2, #32
+	ldp		x5, x6, [x1, #-16]
+CPU_BE(	rev		x3, x3		)
+CPU_BE(	rev		x4, x4		)
+CPU_BE(	rev		x5, x5		)
+CPU_BE(	rev		x6, x6		)
 	crc32\c\()x	w0, w0, x3
 	crc32\c\()x	w0, w0, x4
-	b.ne		0b
-	ret
+	crc32\c\()x	w0, w0, x5
+	crc32\c\()x	w0, w0, x6
+	cbnz		x2, 32b
+0:	ret
 
 8:	tbz		x2, #3, 4f
 	ldr		x3, [x1], #8
diff --git a/arch/arm64/lib/memchr.S b/arch/arm64/lib/memchr.S
index 0f164a4baf52..f146b7ecd28f 100644
--- a/arch/arm64/lib/memchr.S
+++ b/arch/arm64/lib/memchr.S
@@ -42,3 +42,4 @@ WEAK(memchr)
 2:	mov	x0, #0
 	ret
 ENDPIPROC(memchr)
+EXPORT_SYMBOL_NOKASAN(memchr)
diff --git a/arch/arm64/lib/memcmp.S b/arch/arm64/lib/memcmp.S
index fb295f52e9f8..e2e629b09049 100644
--- a/arch/arm64/lib/memcmp.S
+++ b/arch/arm64/lib/memcmp.S
@@ -256,3 +256,4 @@ CPU_LE( rev	data2, data2 )
 	mov	result, #0
 	ret
 ENDPIPROC(memcmp)
+EXPORT_SYMBOL_NOKASAN(memcmp)
diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S
index 67613937711f..b4f82888ed60 100644
--- a/arch/arm64/lib/memcpy.S
+++ b/arch/arm64/lib/memcpy.S
@@ -74,4 +74,6 @@ ENTRY(memcpy)
 #include "copy_template.S"
 	ret
 ENDPIPROC(memcpy)
+EXPORT_SYMBOL(memcpy)
 ENDPROC(__memcpy)
+EXPORT_SYMBOL(__memcpy)
diff --git a/arch/arm64/lib/memmove.S b/arch/arm64/lib/memmove.S
index a5a4459013b1..ef12f719d99d 100644
--- a/arch/arm64/lib/memmove.S
+++ b/arch/arm64/lib/memmove.S
@@ -197,4 +197,6 @@ ENTRY(memmove)
 	b.ne	.Ltail63
 	ret
 ENDPIPROC(memmove)
+EXPORT_SYMBOL(memmove)
 ENDPROC(__memmove)
+EXPORT_SYMBOL(__memmove)
diff --git a/arch/arm64/lib/memset.S b/arch/arm64/lib/memset.S
index f2670a9f218c..a79cf118d6d0 100644
--- a/arch/arm64/lib/memset.S
+++ b/arch/arm64/lib/memset.S
@@ -216,4 +216,6 @@ ENTRY(memset)
 	b.ne	.Ltail_maybe_long
 	ret
 ENDPIPROC(memset)
+EXPORT_SYMBOL(memset)
 ENDPROC(__memset)
+EXPORT_SYMBOL(__memset)
diff --git a/arch/arm64/lib/strchr.S b/arch/arm64/lib/strchr.S
index 7c83091d1bcd..b179421f46c7 100644
--- a/arch/arm64/lib/strchr.S
+++ b/arch/arm64/lib/strchr.S
@@ -40,3 +40,4 @@ WEAK(strchr)
 	csel	x0, x0, xzr, eq
 	ret
 ENDPROC(strchr)
+EXPORT_SYMBOL_NOKASAN(strchr)
diff --git a/arch/arm64/lib/strcmp.S b/arch/arm64/lib/strcmp.S
index 7d5d15398bfb..c306c7b88574 100644
--- a/arch/arm64/lib/strcmp.S
+++ b/arch/arm64/lib/strcmp.S
@@ -232,3 +232,4 @@ CPU_BE(	orr	syndrome, diff, has_nul )
 	sub	result, data1, data2, lsr #56
 	ret
 ENDPIPROC(strcmp)
+EXPORT_SYMBOL_NOKASAN(strcmp)
diff --git a/arch/arm64/lib/strlen.S b/arch/arm64/lib/strlen.S
index 8e0b14205dcb..2a0240937416 100644
--- a/arch/arm64/lib/strlen.S
+++ b/arch/arm64/lib/strlen.S
@@ -124,3 +124,4 @@ CPU_LE( lsr	tmp2, tmp2, tmp1 )	/* Shift (tmp1 & 63).  */
 	csel	data2, data2, data2a, le
 	b	.Lrealigned
 ENDPIPROC(strlen)
+EXPORT_SYMBOL_NOKASAN(strlen)
diff --git a/arch/arm64/lib/strncmp.S b/arch/arm64/lib/strncmp.S
index 66bd145935d9..c5d567afb039 100644
--- a/arch/arm64/lib/strncmp.S
+++ b/arch/arm64/lib/strncmp.S
@@ -308,3 +308,4 @@ CPU_BE( orr	syndrome, diff, has_nul )
 	mov	result, #0
 	ret
 ENDPIPROC(strncmp)
+EXPORT_SYMBOL_NOKASAN(strncmp)
diff --git a/arch/arm64/lib/strnlen.S b/arch/arm64/lib/strnlen.S
index 355be04441fe..e21e536d420e 100644
--- a/arch/arm64/lib/strnlen.S
+++ b/arch/arm64/lib/strnlen.S
@@ -169,3 +169,4 @@ CPU_LE( lsr	tmp2, tmp2, tmp4 )	/* Shift (tmp1 & 63).  */
 	mov	len, limit
 	ret
 ENDPIPROC(strnlen)
+EXPORT_SYMBOL_NOKASAN(strnlen)
diff --git a/arch/arm64/lib/strrchr.S b/arch/arm64/lib/strrchr.S
index ea84924d5990..47e1593016dc 100644
--- a/arch/arm64/lib/strrchr.S
+++ b/arch/arm64/lib/strrchr.S
@@ -41,3 +41,4 @@ WEAK(strrchr)
 2:	mov	x0, x3
 	ret
 ENDPIPROC(strrchr)
+EXPORT_SYMBOL_NOKASAN(strrchr)
diff --git a/arch/arm64/lib/tishift.S b/arch/arm64/lib/tishift.S
index 0fdff97794de..047622536535 100644
--- a/arch/arm64/lib/tishift.S
+++ b/arch/arm64/lib/tishift.S
@@ -5,6 +5,8 @@
 
 #include <linux/linkage.h>
 
+#include <asm/assembler.h>
+
 ENTRY(__ashlti3)
 	cbz	x2, 1f
 	mov	x3, #64
@@ -25,6 +27,7 @@ ENTRY(__ashlti3)
 	mov	x0, x2
 	ret
 ENDPROC(__ashlti3)
+EXPORT_SYMBOL(__ashlti3)
 
 ENTRY(__ashrti3)
 	cbz	x2, 1f
@@ -46,6 +49,7 @@ ENTRY(__ashrti3)
 	mov	x1, x2
 	ret
 ENDPROC(__ashrti3)
+EXPORT_SYMBOL(__ashrti3)
 
 ENTRY(__lshrti3)
 	cbz	x2, 1f
@@ -67,3 +71,4 @@ ENTRY(__lshrti3)
 	mov	x1, x2
 	ret
 ENDPROC(__lshrti3)
+EXPORT_SYMBOL(__lshrti3)
diff --git a/arch/arm64/lib/xor-neon.c b/arch/arm64/lib/xor-neon.c
new file mode 100644
index 000000000000..131c60c27dff
--- /dev/null
+++ b/arch/arm64/lib/xor-neon.c
@@ -0,0 +1,184 @@
+/*
+ * arch/arm64/lib/xor-neon.c
+ *
+ * Authors: Jackie Liu <liuyun01@kylinos.cn>
+ * Copyright (C) 2018,Tianjin KYLIN Information Technology Co., Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/raid/xor.h>
+#include <linux/module.h>
+#include <asm/neon-intrinsics.h>
+
+void xor_arm64_neon_2(unsigned long bytes, unsigned long *p1,
+	unsigned long *p2)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 */
+		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
+		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
+		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
+		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));
+
+		/* store */
+		vst1q_u64(dp1 +  0, v0);
+		vst1q_u64(dp1 +  2, v1);
+		vst1q_u64(dp1 +  4, v2);
+		vst1q_u64(dp1 +  6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+	} while (--lines > 0);
+}
+
+void xor_arm64_neon_3(unsigned long bytes, unsigned long *p1,
+	unsigned long *p2, unsigned long *p3)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+	uint64_t *dp3 = (uint64_t *)p3;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 */
+		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
+		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
+		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
+		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));
+
+		/* p1 ^= p3 */
+		v0 = veorq_u64(v0, vld1q_u64(dp3 +  0));
+		v1 = veorq_u64(v1, vld1q_u64(dp3 +  2));
+		v2 = veorq_u64(v2, vld1q_u64(dp3 +  4));
+		v3 = veorq_u64(v3, vld1q_u64(dp3 +  6));
+
+		/* store */
+		vst1q_u64(dp1 +  0, v0);
+		vst1q_u64(dp1 +  2, v1);
+		vst1q_u64(dp1 +  4, v2);
+		vst1q_u64(dp1 +  6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+		dp3 += 8;
+	} while (--lines > 0);
+}
+
+void xor_arm64_neon_4(unsigned long bytes, unsigned long *p1,
+	unsigned long *p2, unsigned long *p3, unsigned long *p4)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+	uint64_t *dp3 = (uint64_t *)p3;
+	uint64_t *dp4 = (uint64_t *)p4;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 */
+		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
+		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
+		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
+		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));
+
+		/* p1 ^= p3 */
+		v0 = veorq_u64(v0, vld1q_u64(dp3 +  0));
+		v1 = veorq_u64(v1, vld1q_u64(dp3 +  2));
+		v2 = veorq_u64(v2, vld1q_u64(dp3 +  4));
+		v3 = veorq_u64(v3, vld1q_u64(dp3 +  6));
+
+		/* p1 ^= p4 */
+		v0 = veorq_u64(v0, vld1q_u64(dp4 +  0));
+		v1 = veorq_u64(v1, vld1q_u64(dp4 +  2));
+		v2 = veorq_u64(v2, vld1q_u64(dp4 +  4));
+		v3 = veorq_u64(v3, vld1q_u64(dp4 +  6));
+
+		/* store */
+		vst1q_u64(dp1 +  0, v0);
+		vst1q_u64(dp1 +  2, v1);
+		vst1q_u64(dp1 +  4, v2);
+		vst1q_u64(dp1 +  6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+		dp3 += 8;
+		dp4 += 8;
+	} while (--lines > 0);
+}
+
+void xor_arm64_neon_5(unsigned long bytes, unsigned long *p1,
+	unsigned long *p2, unsigned long *p3,
+	unsigned long *p4, unsigned long *p5)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+	uint64_t *dp3 = (uint64_t *)p3;
+	uint64_t *dp4 = (uint64_t *)p4;
+	uint64_t *dp5 = (uint64_t *)p5;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 */
+		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
+		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
+		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
+		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));
+
+		/* p1 ^= p3 */
+		v0 = veorq_u64(v0, vld1q_u64(dp3 +  0));
+		v1 = veorq_u64(v1, vld1q_u64(dp3 +  2));
+		v2 = veorq_u64(v2, vld1q_u64(dp3 +  4));
+		v3 = veorq_u64(v3, vld1q_u64(dp3 +  6));
+
+		/* p1 ^= p4 */
+		v0 = veorq_u64(v0, vld1q_u64(dp4 +  0));
+		v1 = veorq_u64(v1, vld1q_u64(dp4 +  2));
+		v2 = veorq_u64(v2, vld1q_u64(dp4 +  4));
+		v3 = veorq_u64(v3, vld1q_u64(dp4 +  6));
+
+		/* p1 ^= p5 */
+		v0 = veorq_u64(v0, vld1q_u64(dp5 +  0));
+		v1 = veorq_u64(v1, vld1q_u64(dp5 +  2));
+		v2 = veorq_u64(v2, vld1q_u64(dp5 +  4));
+		v3 = veorq_u64(v3, vld1q_u64(dp5 +  6));
+
+		/* store */
+		vst1q_u64(dp1 +  0, v0);
+		vst1q_u64(dp1 +  2, v1);
+		vst1q_u64(dp1 +  4, v2);
+		vst1q_u64(dp1 +  6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+		dp3 += 8;
+		dp4 += 8;
+		dp5 += 8;
+	} while (--lines > 0);
+}
+
+struct xor_block_template const xor_block_inner_neon = {
+	.name	= "__inner_neon__",
+	.do_2	= xor_arm64_neon_2,
+	.do_3	= xor_arm64_neon_3,
+	.do_4	= xor_arm64_neon_4,
+	.do_5	= xor_arm64_neon_5,
+};
+EXPORT_SYMBOL(xor_block_inner_neon);
+
+MODULE_AUTHOR("Jackie Liu <liuyun01@kylinos.cn>");
+MODULE_DESCRIPTION("ARMv8 XOR Extensions");
+MODULE_LICENSE("GPL");