21 files changed, 198 insertions, 72 deletions

diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index c21b936dc01d..2fc253466dbf 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -1,9 +1,9 @@
 # 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 memchr.o memcpy.o memmove.o memset.o	\
-		   memcmp.o strcmp.o strncmp.o strlen.o strnlen.o	\
-		   strchr.o strrchr.o tishift.o
+		   clear_page.o csum.o memchr.o memcpy.o memmove.o	\
+		   memset.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
diff --git a/arch/arm64/lib/clear_page.S b/arch/arm64/lib/clear_page.S
index 78a9ef66288a..073acbf02a7c 100644
--- a/arch/arm64/lib/clear_page.S
+++ b/arch/arm64/lib/clear_page.S
@@ -14,7 +14,7 @@
  * Parameters:
  *	x0 - dest
  */
-ENTRY(clear_page)
+SYM_FUNC_START(clear_page)
 	mrs	x1, dczid_el0
 	and	w1, w1, #0xf
 	mov	x2, #4
@@ -25,5 +25,5 @@ ENTRY(clear_page)
 	tst	x0, #(PAGE_SIZE - 1)
 	b.ne	1b
 	ret
-ENDPROC(clear_page)
+SYM_FUNC_END(clear_page)
 EXPORT_SYMBOL(clear_page)
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index aeafc03e961a..48a3a26eff66 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -19,7 +19,7 @@
  *
  * Alignment fixed up by hardware.
  */
-ENTRY(__arch_clear_user)
+SYM_FUNC_START(__arch_clear_user)
 	mov	x2, x1			// save the size for fixup return
 	subs	x1, x1, #8
 	b.mi	2f
@@ -40,7 +40,7 @@ uao_user_alternative 9f, strh, sttrh, wzr, x0, 2
 uao_user_alternative 9f, strb, sttrb, wzr, x0, 0
 5:	mov	x0, #0
 	ret
-ENDPROC(__arch_clear_user)
+SYM_FUNC_END(__arch_clear_user)
 EXPORT_SYMBOL(__arch_clear_user)
 
 	.section .fixup,"ax"
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index ebb3c06cbb5d..8e25e89ad01f 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -53,12 +53,12 @@
 	.endm
 
 end	.req	x5
-ENTRY(__arch_copy_from_user)
+SYM_FUNC_START(__arch_copy_from_user)
 	add	end, x0, x2
 #include "copy_template.S"
 	mov	x0, #0				// Nothing to copy
 	ret
-ENDPROC(__arch_copy_from_user)
+SYM_FUNC_END(__arch_copy_from_user)
 EXPORT_SYMBOL(__arch_copy_from_user)
 
 	.section .fixup,"ax"
diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S
index 3d8153a1ebce..667139013ed1 100644
--- a/arch/arm64/lib/copy_in_user.S
+++ b/arch/arm64/lib/copy_in_user.S
@@ -55,12 +55,12 @@
 
 end	.req	x5
 
-ENTRY(__arch_copy_in_user)
+SYM_FUNC_START(__arch_copy_in_user)
 	add	end, x0, x2
 #include "copy_template.S"
 	mov	x0, #0
 	ret
-ENDPROC(__arch_copy_in_user)
+SYM_FUNC_END(__arch_copy_in_user)
 EXPORT_SYMBOL(__arch_copy_in_user)
 
 	.section .fixup,"ax"
diff --git a/arch/arm64/lib/copy_page.S b/arch/arm64/lib/copy_page.S
index bbb8562396af..e7a793961408 100644
--- a/arch/arm64/lib/copy_page.S
+++ b/arch/arm64/lib/copy_page.S
@@ -17,7 +17,7 @@
  *	x0 - dest
  *	x1 - src
  */
-ENTRY(copy_page)
+SYM_FUNC_START(copy_page)
 alternative_if ARM64_HAS_NO_HW_PREFETCH
 	// Prefetch three cache lines ahead.
 	prfm	pldl1strm, [x1, #128]
@@ -34,46 +34,46 @@ alternative_else_nop_endif
 	ldp	x14, x15, [x1, #96]
 	ldp	x16, x17, [x1, #112]
 
-	mov	x18, #(PAGE_SIZE - 128)
+	add	x0, x0, #256
 	add	x1, x1, #128
 1:
-	subs	x18, x18, #128
+	tst	x0, #(PAGE_SIZE - 1)
 
 alternative_if ARM64_HAS_NO_HW_PREFETCH
 	prfm	pldl1strm, [x1, #384]
 alternative_else_nop_endif
 
-	stnp	x2, x3, [x0]
+	stnp	x2, x3, [x0, #-256]
 	ldp	x2, x3, [x1]
-	stnp	x4, x5, [x0, #16]
+	stnp	x4, x5, [x0, #16 - 256]
 	ldp	x4, x5, [x1, #16]
-	stnp	x6, x7, [x0, #32]
+	stnp	x6, x7, [x0, #32 - 256]
 	ldp	x6, x7, [x1, #32]
-	stnp	x8, x9, [x0, #48]
+	stnp	x8, x9, [x0, #48 - 256]
 	ldp	x8, x9, [x1, #48]
-	stnp	x10, x11, [x0, #64]
+	stnp	x10, x11, [x0, #64 - 256]
 	ldp	x10, x11, [x1, #64]
-	stnp	x12, x13, [x0, #80]
+	stnp	x12, x13, [x0, #80 - 256]
 	ldp	x12, x13, [x1, #80]
-	stnp	x14, x15, [x0, #96]
+	stnp	x14, x15, [x0, #96 - 256]
 	ldp	x14, x15, [x1, #96]
-	stnp	x16, x17, [x0, #112]
+	stnp	x16, x17, [x0, #112 - 256]
 	ldp	x16, x17, [x1, #112]
 
 	add	x0, x0, #128
 	add	x1, x1, #128
 
-	b.gt	1b
+	b.ne	1b
 
-	stnp	x2, x3, [x0]
-	stnp	x4, x5, [x0, #16]
-	stnp	x6, x7, [x0, #32]
-	stnp	x8, x9, [x0, #48]
-	stnp	x10, x11, [x0, #64]
-	stnp	x12, x13, [x0, #80]
-	stnp	x14, x15, [x0, #96]
-	stnp	x16, x17, [x0, #112]
+	stnp	x2, x3, [x0, #-256]
+	stnp	x4, x5, [x0, #16 - 256]
+	stnp	x6, x7, [x0, #32 - 256]
+	stnp	x8, x9, [x0, #48 - 256]
+	stnp	x10, x11, [x0, #64 - 256]
+	stnp	x12, x13, [x0, #80 - 256]
+	stnp	x14, x15, [x0, #96 - 256]
+	stnp	x16, x17, [x0, #112 - 256]
 
 	ret
-ENDPROC(copy_page)
+SYM_FUNC_END(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 357eae2c18eb..1a104d0089f3 100644
--- a/arch/arm64/lib/copy_to_user.S
+++ b/arch/arm64/lib/copy_to_user.S
@@ -52,12 +52,12 @@
 	.endm
 
 end	.req	x5
-ENTRY(__arch_copy_to_user)
+SYM_FUNC_START(__arch_copy_to_user)
 	add	end, x0, x2
 #include "copy_template.S"
 	mov	x0, #0
 	ret
-ENDPROC(__arch_copy_to_user)
+SYM_FUNC_END(__arch_copy_to_user)
 EXPORT_SYMBOL(__arch_copy_to_user)
 
 	.section .fixup,"ax"
diff --git a/arch/arm64/lib/crc32.S b/arch/arm64/lib/crc32.S
index e6135f16649b..243e107e9896 100644
--- a/arch/arm64/lib/crc32.S
+++ b/arch/arm64/lib/crc32.S
@@ -85,17 +85,17 @@ CPU_BE(	rev16		w3, w3		)
 	.endm
 
 	.align		5
-ENTRY(crc32_le)
+SYM_FUNC_START(crc32_le)
 alternative_if_not ARM64_HAS_CRC32
 	b		crc32_le_base
 alternative_else_nop_endif
 	__crc32
-ENDPROC(crc32_le)
+SYM_FUNC_END(crc32_le)
 
 	.align		5
-ENTRY(__crc32c_le)
+SYM_FUNC_START(__crc32c_le)
 alternative_if_not ARM64_HAS_CRC32
 	b		__crc32c_le_base
 alternative_else_nop_endif
 	__crc32		c
-ENDPROC(__crc32c_le)
+SYM_FUNC_END(__crc32c_le)
diff --git a/arch/arm64/lib/csum.c b/arch/arm64/lib/csum.c
new file mode 100644
index 000000000000..1f82c66b32ea
--- /dev/null
+++ b/arch/arm64/lib/csum.c
@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2019-2020 Arm Ltd.
+
+#include <linux/compiler.h>
+#include <linux/kasan-checks.h>
+#include <linux/kernel.h>
+
+#include <net/checksum.h>
+
+/* Looks dumb, but generates nice-ish code */
+static u64 accumulate(u64 sum, u64 data)
+{
+	__uint128_t tmp = (__uint128_t)sum + data;
+	return tmp + (tmp >> 64);
+}
+
+unsigned int do_csum(const unsigned char *buff, int len)
+{
+	unsigned int offset, shift, sum;
+	const u64 *ptr;
+	u64 data, sum64 = 0;
+
+	if (unlikely(len == 0))
+		return 0;
+
+	offset = (unsigned long)buff & 7;
+	/*
+	 * This is to all intents and purposes safe, since rounding down cannot
+	 * result in a different page or cache line being accessed, and @buff
+	 * should absolutely not be pointing to anything read-sensitive. We do,
+	 * however, have to be careful not to piss off KASAN, which means using
+	 * unchecked reads to accommodate the head and tail, for which we'll
+	 * compensate with an explicit check up-front.
+	 */
+	kasan_check_read(buff, len);
+	ptr = (u64 *)(buff - offset);
+	len = len + offset - 8;
+
+	/*
+	 * Head: zero out any excess leading bytes. Shifting back by the same
+	 * amount should be at least as fast as any other way of handling the
+	 * odd/even alignment, and means we can ignore it until the very end.
+	 */
+	shift = offset * 8;
+	data = READ_ONCE_NOCHECK(*ptr++);
+#ifdef __LITTLE_ENDIAN
+	data = (data >> shift) << shift;
+#else
+	data = (data << shift) >> shift;
+#endif
+
+	/*
+	 * Body: straightforward aligned loads from here on (the paired loads
+	 * underlying the quadword type still only need dword alignment). The
+	 * main loop strictly excludes the tail, so the second loop will always
+	 * run at least once.
+	 */
+	while (unlikely(len > 64)) {
+		__uint128_t tmp1, tmp2, tmp3, tmp4;
+
+		tmp1 = READ_ONCE_NOCHECK(*(__uint128_t *)ptr);
+		tmp2 = READ_ONCE_NOCHECK(*(__uint128_t *)(ptr + 2));
+		tmp3 = READ_ONCE_NOCHECK(*(__uint128_t *)(ptr + 4));
+		tmp4 = READ_ONCE_NOCHECK(*(__uint128_t *)(ptr + 6));
+
+		len -= 64;
+		ptr += 8;
+
+		/* This is the "don't dump the carry flag into a GPR" idiom */
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		tmp2 += (tmp2 >> 64) | (tmp2 << 64);
+		tmp3 += (tmp3 >> 64) | (tmp3 << 64);
+		tmp4 += (tmp4 >> 64) | (tmp4 << 64);
+		tmp1 = ((tmp1 >> 64) << 64) | (tmp2 >> 64);
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		tmp3 = ((tmp3 >> 64) << 64) | (tmp4 >> 64);
+		tmp3 += (tmp3 >> 64) | (tmp3 << 64);
+		tmp1 = ((tmp1 >> 64) << 64) | (tmp3 >> 64);
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		tmp1 = ((tmp1 >> 64) << 64) | sum64;
+		tmp1 += (tmp1 >> 64) | (tmp1 << 64);
+		sum64 = tmp1 >> 64;
+	}
+	while (len > 8) {
+		__uint128_t tmp;
+
+		sum64 = accumulate(sum64, data);
+		tmp = READ_ONCE_NOCHECK(*(__uint128_t *)ptr);
+
+		len -= 16;
+		ptr += 2;
+
+#ifdef __LITTLE_ENDIAN
+		data = tmp >> 64;
+		sum64 = accumulate(sum64, tmp);
+#else
+		data = tmp;
+		sum64 = accumulate(sum64, tmp >> 64);
+#endif
+	}
+	if (len > 0) {
+		sum64 = accumulate(sum64, data);
+		data = READ_ONCE_NOCHECK(*ptr);
+		len -= 8;
+	}
+	/*
+	 * Tail: zero any over-read bytes similarly to the head, again
+	 * preserving odd/even alignment.
+	 */
+	shift = len * -8;
+#ifdef __LITTLE_ENDIAN
+	data = (data << shift) >> shift;
+#else
+	data = (data >> shift) << shift;
+#endif
+	sum64 = accumulate(sum64, data);
+
+	/* Finally, folding */
+	sum64 += (sum64 >> 32) | (sum64 << 32);
+	sum = sum64 >> 32;
+	sum += (sum >> 16) | (sum << 16);
+	if (offset & 1)
+		return (u16)swab32(sum);
+
+	return sum >> 16;
+}
diff --git a/arch/arm64/lib/memchr.S b/arch/arm64/lib/memchr.S
index 48a3ab636e4f..edf6b970a277 100644
--- a/arch/arm64/lib/memchr.S
+++ b/arch/arm64/lib/memchr.S
@@ -19,7 +19,7 @@
  * Returns:
  *	x0 - address of first occurrence of 'c' or 0
  */
-WEAK(memchr)
+SYM_FUNC_START_WEAK_PI(memchr)
 	and	w1, w1, #0xff
 1:	subs	x2, x2, #1
 	b.mi	2f
@@ -30,5 +30,5 @@ WEAK(memchr)
 	ret
 2:	mov	x0, #0
 	ret
-ENDPIPROC(memchr)
+SYM_FUNC_END_PI(memchr)
 EXPORT_SYMBOL_NOKASAN(memchr)
diff --git a/arch/arm64/lib/memcmp.S b/arch/arm64/lib/memcmp.S
index b297bdaaf549..c0671e793ea9 100644
--- a/arch/arm64/lib/memcmp.S
+++ b/arch/arm64/lib/memcmp.S
@@ -46,7 +46,7 @@ pos		.req	x11
 limit_wd	.req	x12
 mask		.req	x13
 
-WEAK(memcmp)
+SYM_FUNC_START_WEAK_PI(memcmp)
 	cbz	limit, .Lret0
 	eor	tmp1, src1, src2
 	tst	tmp1, #7
@@ -243,5 +243,5 @@ CPU_LE( rev	data2, data2 )
 .Lret0:
 	mov	result, #0
 	ret
-ENDPIPROC(memcmp)
+SYM_FUNC_END_PI(memcmp)
 EXPORT_SYMBOL_NOKASAN(memcmp)
diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S
index d79f48994dbb..9f382adfa88a 100644
--- a/arch/arm64/lib/memcpy.S
+++ b/arch/arm64/lib/memcpy.S
@@ -57,11 +57,11 @@
 	.endm
 
 	.weak memcpy
-ENTRY(__memcpy)
-ENTRY(memcpy)
+SYM_FUNC_START_ALIAS(__memcpy)
+SYM_FUNC_START_PI(memcpy)
 #include "copy_template.S"
 	ret
-ENDPIPROC(memcpy)
+SYM_FUNC_END_PI(memcpy)
 EXPORT_SYMBOL(memcpy)
-ENDPROC(__memcpy)
+SYM_FUNC_END_ALIAS(__memcpy)
 EXPORT_SYMBOL(__memcpy)
diff --git a/arch/arm64/lib/memmove.S b/arch/arm64/lib/memmove.S
index 784775136480..02cda2e33bde 100644
--- a/arch/arm64/lib/memmove.S
+++ b/arch/arm64/lib/memmove.S
@@ -46,8 +46,8 @@ D_l	.req	x13
 D_h	.req	x14
 
 	.weak memmove
-ENTRY(__memmove)
-ENTRY(memmove)
+SYM_FUNC_START_ALIAS(__memmove)
+SYM_FUNC_START_PI(memmove)
 	cmp	dstin, src
 	b.lo	__memcpy
 	add	tmp1, src, count
@@ -184,7 +184,7 @@ ENTRY(memmove)
 	tst	count, #0x3f
 	b.ne	.Ltail63
 	ret
-ENDPIPROC(memmove)
+SYM_FUNC_END_PI(memmove)
 EXPORT_SYMBOL(memmove)
-ENDPROC(__memmove)
+SYM_FUNC_END_ALIAS(__memmove)
 EXPORT_SYMBOL(__memmove)
diff --git a/arch/arm64/lib/memset.S b/arch/arm64/lib/memset.S
index 9fb97e6bc560..77c3c7ba0084 100644
--- a/arch/arm64/lib/memset.S
+++ b/arch/arm64/lib/memset.S
@@ -43,8 +43,8 @@ tmp3w		.req	w9
 tmp3		.req	x9
 
 	.weak memset
-ENTRY(__memset)
-ENTRY(memset)
+SYM_FUNC_START_ALIAS(__memset)
+SYM_FUNC_START_PI(memset)
 	mov	dst, dstin	/* Preserve return value.  */
 	and	A_lw, val, #255
 	orr	A_lw, A_lw, A_lw, lsl #8
@@ -203,7 +203,7 @@ ENTRY(memset)
 	ands	count, count, zva_bits_x
 	b.ne	.Ltail_maybe_long
 	ret
-ENDPIPROC(memset)
+SYM_FUNC_END_PI(memset)
 EXPORT_SYMBOL(memset)
-ENDPROC(__memset)
+SYM_FUNC_END_ALIAS(__memset)
 EXPORT_SYMBOL(__memset)
diff --git a/arch/arm64/lib/strchr.S b/arch/arm64/lib/strchr.S
index ca3ec18171a4..1f47eae3b0d6 100644
--- a/arch/arm64/lib/strchr.S
+++ b/arch/arm64/lib/strchr.S
@@ -18,7 +18,7 @@
  * Returns:
  *	x0 - address of first occurrence of 'c' or 0
  */
-WEAK(strchr)
+SYM_FUNC_START_WEAK(strchr)
 	and	w1, w1, #0xff
 1:	ldrb	w2, [x0], #1
 	cmp	w2, w1
@@ -28,5 +28,5 @@ WEAK(strchr)
 	cmp	w2, w1
 	csel	x0, x0, xzr, eq
 	ret
-ENDPROC(strchr)
+SYM_FUNC_END(strchr)
 EXPORT_SYMBOL_NOKASAN(strchr)
diff --git a/arch/arm64/lib/strcmp.S b/arch/arm64/lib/strcmp.S
index e9aefbe0b740..4767540d1b94 100644
--- a/arch/arm64/lib/strcmp.S
+++ b/arch/arm64/lib/strcmp.S
@@ -48,7 +48,7 @@ tmp3		.req	x9
 zeroones	.req	x10
 pos		.req	x11
 
-WEAK(strcmp)
+SYM_FUNC_START_WEAK_PI(strcmp)
 	eor	tmp1, src1, src2
 	mov	zeroones, #REP8_01
 	tst	tmp1, #7
@@ -219,5 +219,5 @@ CPU_BE(	orr	syndrome, diff, has_nul )
 	lsr	data1, data1, #56
 	sub	result, data1, data2, lsr #56
 	ret
-ENDPIPROC(strcmp)
+SYM_FUNC_END_PI(strcmp)
 EXPORT_SYMBOL_NOKASAN(strcmp)
diff --git a/arch/arm64/lib/strlen.S b/arch/arm64/lib/strlen.S
index 87b0cb066915..ee3ed882dd79 100644
--- a/arch/arm64/lib/strlen.S
+++ b/arch/arm64/lib/strlen.S
@@ -44,7 +44,7 @@ pos		.req	x12
 #define REP8_7f 0x7f7f7f7f7f7f7f7f
 #define REP8_80 0x8080808080808080
 
-WEAK(strlen)
+SYM_FUNC_START_WEAK_PI(strlen)
 	mov	zeroones, #REP8_01
 	bic	src, srcin, #15
 	ands	tmp1, srcin, #15
@@ -111,5 +111,5 @@ CPU_LE( lsr	tmp2, tmp2, tmp1 )	/* Shift (tmp1 & 63).  */
 	csinv	data1, data1, xzr, le
 	csel	data2, data2, data2a, le
 	b	.Lrealigned
-ENDPIPROC(strlen)
+SYM_FUNC_END_PI(strlen)
 EXPORT_SYMBOL_NOKASAN(strlen)
diff --git a/arch/arm64/lib/strncmp.S b/arch/arm64/lib/strncmp.S
index f571581888fa..2a7ee949ed47 100644
--- a/arch/arm64/lib/strncmp.S
+++ b/arch/arm64/lib/strncmp.S
@@ -52,7 +52,7 @@ limit_wd	.req	x13
 mask		.req	x14
 endloop		.req	x15
 
-WEAK(strncmp)
+SYM_FUNC_START_WEAK_PI(strncmp)
 	cbz	limit, .Lret0
 	eor	tmp1, src1, src2
 	mov	zeroones, #REP8_01
@@ -295,5 +295,5 @@ CPU_BE( orr	syndrome, diff, has_nul )
 .Lret0:
 	mov	result, #0
 	ret
-ENDPIPROC(strncmp)
+SYM_FUNC_END_PI(strncmp)
 EXPORT_SYMBOL_NOKASAN(strncmp)
diff --git a/arch/arm64/lib/strnlen.S b/arch/arm64/lib/strnlen.S
index c0bac9493c68..b72913a99038 100644
--- a/arch/arm64/lib/strnlen.S
+++ b/arch/arm64/lib/strnlen.S
@@ -47,7 +47,7 @@ limit_wd	.req	x14
 #define REP8_7f 0x7f7f7f7f7f7f7f7f
 #define REP8_80 0x8080808080808080
 
-WEAK(strnlen)
+SYM_FUNC_START_WEAK_PI(strnlen)
 	cbz	limit, .Lhit_limit
 	mov	zeroones, #REP8_01
 	bic	src, srcin, #15
@@ -156,5 +156,5 @@ CPU_LE( lsr	tmp2, tmp2, tmp4 )	/* Shift (tmp1 & 63).  */
 .Lhit_limit:
 	mov	len, limit
 	ret
-ENDPIPROC(strnlen)
+SYM_FUNC_END_PI(strnlen)
 EXPORT_SYMBOL_NOKASAN(strnlen)
diff --git a/arch/arm64/lib/strrchr.S b/arch/arm64/lib/strrchr.S
index 794ac49ea433..13132d1ed6d1 100644
--- a/arch/arm64/lib/strrchr.S
+++ b/arch/arm64/lib/strrchr.S
@@ -18,7 +18,7 @@
  * Returns:
  *	x0 - address of last occurrence of 'c' or 0
  */
-WEAK(strrchr)
+SYM_FUNC_START_WEAK_PI(strrchr)
 	mov	x3, #0
 	and	w1, w1, #0xff
 1:	ldrb	w2, [x0], #1
@@ -29,5 +29,5 @@ WEAK(strrchr)
 	b	1b
 2:	mov	x0, x3
 	ret
-ENDPIPROC(strrchr)
+SYM_FUNC_END_PI(strrchr)
 EXPORT_SYMBOL_NOKASAN(strrchr)
diff --git a/arch/arm64/lib/tishift.S b/arch/arm64/lib/tishift.S
index 047622536535..a88613834fb0 100644
--- a/arch/arm64/lib/tishift.S
+++ b/arch/arm64/lib/tishift.S
@@ -7,7 +7,7 @@
 
 #include <asm/assembler.h>
 
-ENTRY(__ashlti3)
+SYM_FUNC_START(__ashlti3)
 	cbz	x2, 1f
 	mov	x3, #64
 	sub	x3, x3, x2
@@ -26,10 +26,10 @@ ENTRY(__ashlti3)
 	lsl	x1, x0, x1
 	mov	x0, x2
 	ret
-ENDPROC(__ashlti3)
+SYM_FUNC_END(__ashlti3)
 EXPORT_SYMBOL(__ashlti3)
 
-ENTRY(__ashrti3)
+SYM_FUNC_START(__ashrti3)
 	cbz	x2, 1f
 	mov	x3, #64
 	sub	x3, x3, x2
@@ -48,10 +48,10 @@ ENTRY(__ashrti3)
 	asr	x0, x1, x0
 	mov	x1, x2
 	ret
-ENDPROC(__ashrti3)
+SYM_FUNC_END(__ashrti3)
 EXPORT_SYMBOL(__ashrti3)
 
-ENTRY(__lshrti3)
+SYM_FUNC_START(__lshrti3)
 	cbz	x2, 1f
 	mov	x3, #64
 	sub	x3, x3, x2
@@ -70,5 +70,5 @@ ENTRY(__lshrti3)
 	lsr	x0, x1, x0
 	mov	x1, x2
 	ret
-ENDPROC(__lshrti3)
+SYM_FUNC_END(__lshrti3)
 EXPORT_SYMBOL(__lshrti3)