Merge branch 'for-next/cortex-strings' into for-next/core

Update our kernel string routines to the latest Cortex Strings
implementation.

* for-next/cortex-strings:
  arm64: update string routine copyrights and URLs
  arm64: Rewrite __arch_clear_user()
  arm64: Better optimised memchr()
  arm64: Import latest memcpy()/memmove() implementation
  arm64: Add assembly annotations for weak-PI-alias madness
  arm64: Import latest version of Cortex Strings' strncmp
  arm64: Import updated version of Cortex Strings' strlen
  arm64: Import latest version of Cortex Strings' strcmp
  arm64: Import latest version of Cortex Strings' memcmp

Author: willdeacon

arch/arm64/include/asm/linkage.h

@@ -56,8 +56,16 @@
 		SYM_FUNC_START_ALIAS(__pi_##x);	\
 		SYM_FUNC_START_WEAK(x)
 
+#define SYM_FUNC_START_WEAK_ALIAS_PI(x)		\
+		SYM_FUNC_START_ALIAS(__pi_##x);	\
+		SYM_START(x, SYM_L_WEAK, SYM_A_ALIGN)
+
 #define SYM_FUNC_END_PI(x)			\
 		SYM_FUNC_END(x);		\
 		SYM_FUNC_END_ALIAS(__pi_##x)
 
+#define SYM_FUNC_END_ALIAS_PI(x)		\
+		SYM_FUNC_END_ALIAS(x);		\
+		SYM_FUNC_END_ALIAS(__pi_##x)
+
 #endif

arch/arm64/lib/Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 lib-y		:= clear_user.o delay.o copy_from_user.o		\
 		   copy_to_user.o copy_in_user.o copy_page.o		\
-		   clear_page.o csum.o memchr.o memcpy.o memmove.o	\
+		   clear_page.o csum.o memchr.o memcpy.o		\
 		   memset.o memcmp.o strcmp.o strncmp.o strlen.o	\
 		   strnlen.o strchr.o strrchr.o tishift.o
 

arch/arm64/lib/clear_user.S

@@ -1,12 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Based on arch/arm/lib/clear_user.S
- *
- * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2021 Arm Ltd.
  */
-#include <linux/linkage.h>
 
-#include <asm/asm-uaccess.h>
+#include <linux/linkage.h>
 #include <asm/assembler.h>
 
 	.text
@@ -19,32 +16,42 @@
  *
  * Alignment fixed up by hardware.
  */
+
+	.p2align 4
+	// Alignment is for the loop, but since the prologue (including BTI)
+	// is also 16 bytes we can keep any padding outside the function
 SYM_FUNC_START(__arch_clear_user)
-	mov	x2, x1			// save the size for fixup return
+	add	x2, x0, x1
 	subs	x1, x1, #8
 	b.mi	2f
 1:
-user_ldst 9f, sttr, xzr, x0, 8
+USER(9f, sttr	xzr, [x0])
+	add	x0, x0, #8
 	subs	x1, x1, #8
-	b.pl	1b
-2:	adds	x1, x1, #4
-	b.mi	3f
-user_ldst 9f, sttr, wzr, x0, 4
-	sub	x1, x1, #4
-3:	adds	x1, x1, #2
-	b.mi	4f
-user_ldst 9f, sttrh, wzr, x0, 2
-	sub	x1, x1, #2
-4:	adds	x1, x1, #1
-	b.mi	5f
-user_ldst 9f, sttrb, wzr, x0, 0
+	b.hi	1b
+USER(9f, sttr	xzr, [x2, #-8])
+	mov	x0, #0
+	ret
+
+2:	tbz	x1, #2, 3f
+USER(9f, sttr	wzr, [x0])
+USER(8f, sttr	wzr, [x2, #-4])
+	mov	x0, #0
+	ret
+
+3:	tbz	x1, #1, 4f
+USER(9f, sttrh	wzr, [x0])
+4:	tbz	x1, #0, 5f
+USER(7f, sttrb	wzr, [x2, #-1])
 5:	mov	x0, #0
 	ret
 SYM_FUNC_END(__arch_clear_user)
 EXPORT_SYMBOL(__arch_clear_user)
 
 	.section .fixup,"ax"
 	.align	2
-9:	mov	x0, x2			// return the original size
+7:	sub	x0, x2, #5	// Adjust for faulting on the final byte...
+8:	add	x0, x0, #4	// ...or the second word of the 4-7 byte case
+9:	sub	x0, x2, x0
 	ret
 	.previous

arch/arm64/lib/memchr.S

@@ -1,9 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Based on arch/arm/lib/memchr.S
- *
- * Copyright (C) 1995-2000 Russell King
- * Copyright (C) 2013 ARM Ltd.
+ * Copyright (C) 2021 Arm Ltd.
  */
 
 #include <linux/linkage.h>
@@ -19,16 +16,60 @@
  * Returns:
  *	x0 - address of first occurrence of 'c' or 0
  */
+
+#define L(label) .L ## label
+
+#define REP8_01 0x0101010101010101
+#define REP8_7f 0x7f7f7f7f7f7f7f7f
+
+#define srcin		x0
+#define chrin		w1
+#define cntin		x2
+
+#define result		x0
+
+#define wordcnt		x3
+#define rep01		x4
+#define repchr		x5
+#define cur_word	x6
+#define cur_byte	w6
+#define tmp		x7
+#define tmp2		x8
+
+	.p2align 4
+	nop
 SYM_FUNC_START_WEAK_PI(memchr)
-	and	w1, w1, #0xff
-1:	subs	x2, x2, #1
-	b.mi	2f
-	ldrb	w3, [x0], #1
-	cmp	w3, w1
-	b.ne	1b
-	sub	x0, x0, #1
+	and	chrin, chrin, #0xff
+	lsr	wordcnt, cntin, #3
+	cbz	wordcnt, L(byte_loop)
+	mov	rep01, #REP8_01
+	mul	repchr, x1, rep01
+	and	cntin, cntin, #7
+L(word_loop):
+	ldr	cur_word, [srcin], #8
+	sub	wordcnt, wordcnt, #1
+	eor	cur_word, cur_word, repchr
+	sub	tmp, cur_word, rep01
+	orr	tmp2, cur_word, #REP8_7f
+	bics	tmp, tmp, tmp2
+	b.ne	L(found_word)
+	cbnz	wordcnt, L(word_loop)
+L(byte_loop):
+	cbz	cntin, L(not_found)
+	ldrb	cur_byte, [srcin], #1
+	sub	cntin, cntin, #1
+	cmp	cur_byte, chrin
+	b.ne	L(byte_loop)
+	sub	srcin, srcin, #1
+	ret
+L(found_word):
+CPU_LE(	rev	tmp, tmp)
+	clz	tmp, tmp
+	sub	tmp, tmp, #64
+	add	result, srcin, tmp, asr #3
 	ret
-2:	mov	x0, #0
+L(not_found):
+	mov	result, #0
 	ret
 SYM_FUNC_END_PI(memchr)
 EXPORT_SYMBOL_NOKASAN(memchr)