arm64: Import latest memcpy()/memmove() implementation

Import the latest implementation of memcpy(), based on the
upstream code of string/aarch64/memcpy.S at commit afd6244 from
https://github.com/ARM-software/optimized-routines, and subsuming
memmove() in the process.

Note that for simplicity Arm have chosen to contribute this code
to Linux under GPLv2 rather than the original MIT license.

Note also that the needs of the usercopy routines vs. regular memcpy()
have now diverged so far that we abandon the shared template idea
and the damage which that incurred to the tuning of LDP/STP loops.
We'll be back to tackle those routines separately in future.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/3c953af43506581b2422f61952261e76949ba711.1622128527.git.robin.murphy@arm.com
Signed-off-by: Will Deacon <will@kernel.org>

3 files changed, 230 insertions, 233 deletions

diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index d31e1169d9b8..01c596aa539c 100644
--- a/arch/arm64/lib/Makefile
+++ b/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
 
diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S
index dc8d2a216a6e..31073a8304fb 100644
--- a/arch/arm64/lib/memcpy.S
+++ b/arch/arm64/lib/memcpy.S
@@ -1,66 +1,252 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (C) 2013 ARM Ltd.
- * Copyright (C) 2013 Linaro.
+ * Copyright (c) 2012-2020, Arm Limited.
  *
- * This code is based on glibc cortex strings work originally authored by Linaro
- * be found @
- *
- * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
- * files/head:/src/aarch64/
+ * Adapted from the original at:
+ * https://github.com/ARM-software/optimized-routines/blob/master/string/aarch64/memcpy.S
  */
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
-#include <asm/cache.h>
 
-/*
- * Copy a buffer from src to dest (alignment handled by the hardware)
+/* Assumptions:
+ *
+ * ARMv8-a, AArch64, unaligned accesses.
  *
- * Parameters:
- *	x0 - dest
- *	x1 - src
- *	x2 - n
- * Returns:
- *	x0 - dest
  */
-	.macro ldrb1 reg, ptr, val
-	ldrb  \reg, [\ptr], \val
-	.endm
-
-	.macro strb1 reg, ptr, val
-	strb \reg, [\ptr], \val
-	.endm
 
-	.macro ldrh1 reg, ptr, val
-	ldrh  \reg, [\ptr], \val
-	.endm
+#define L(label) .L ## label
 
-	.macro strh1 reg, ptr, val
-	strh \reg, [\ptr], \val
-	.endm
+#define dstin	x0
+#define src	x1
+#define count	x2
+#define dst	x3
+#define srcend	x4
+#define dstend	x5
+#define A_l	x6
+#define A_lw	w6
+#define A_h	x7
+#define B_l	x8
+#define B_lw	w8
+#define B_h	x9
+#define C_l	x10
+#define C_lw	w10
+#define C_h	x11
+#define D_l	x12
+#define D_h	x13
+#define E_l	x14
+#define E_h	x15
+#define F_l	x16
+#define F_h	x17
+#define G_l	count
+#define G_h	dst
+#define H_l	src
+#define H_h	srcend
+#define tmp1	x14
 
-	.macro ldr1 reg, ptr, val
-	ldr \reg, [\ptr], \val
-	.endm
+/* This implementation handles overlaps and supports both memcpy and memmove
+   from a single entry point.  It uses unaligned accesses and branchless
+   sequences to keep the code small, simple and improve performance.
 
-	.macro str1 reg, ptr, val
-	str \reg, [\ptr], \val
-	.endm
+   Copies are split into 3 main cases: small copies of up to 32 bytes, medium
+   copies of up to 128 bytes, and large copies.  The overhead of the overlap
+   check is negligible since it is only required for large copies.
 
-	.macro ldp1 reg1, reg2, ptr, val
-	ldp \reg1, \reg2, [\ptr], \val
-	.endm
-
-	.macro stp1 reg1, reg2, ptr, val
-	stp \reg1, \reg2, [\ptr], \val
-	.endm
+   Large copies use a software pipelined loop processing 64 bytes per iteration.
+   The destination pointer is 16-byte aligned to minimize unaligned accesses.
+   The loop tail is handled by always copying 64 bytes from the end.
+*/
 
+SYM_FUNC_START_ALIAS(__memmove)
+SYM_FUNC_START_WEAK_ALIAS_PI(memmove)
 SYM_FUNC_START_ALIAS(__memcpy)
 SYM_FUNC_START_WEAK_PI(memcpy)
-#include "copy_template.S"
+	add	srcend, src, count
+	add	dstend, dstin, count
+	cmp	count, 128
+	b.hi	L(copy_long)
+	cmp	count, 32
+	b.hi	L(copy32_128)
+
+	/* Small copies: 0..32 bytes.  */
+	cmp	count, 16
+	b.lo	L(copy16)
+	ldp	A_l, A_h, [src]
+	ldp	D_l, D_h, [srcend, -16]
+	stp	A_l, A_h, [dstin]
+	stp	D_l, D_h, [dstend, -16]
+	ret
+
+	/* Copy 8-15 bytes.  */
+L(copy16):
+	tbz	count, 3, L(copy8)
+	ldr	A_l, [src]
+	ldr	A_h, [srcend, -8]
+	str	A_l, [dstin]
+	str	A_h, [dstend, -8]
+	ret
+
+	.p2align 3
+	/* Copy 4-7 bytes.  */
+L(copy8):
+	tbz	count, 2, L(copy4)
+	ldr	A_lw, [src]
+	ldr	B_lw, [srcend, -4]
+	str	A_lw, [dstin]
+	str	B_lw, [dstend, -4]
+	ret
+
+	/* Copy 0..3 bytes using a branchless sequence.  */
+L(copy4):
+	cbz	count, L(copy0)
+	lsr	tmp1, count, 1
+	ldrb	A_lw, [src]
+	ldrb	C_lw, [srcend, -1]
+	ldrb	B_lw, [src, tmp1]
+	strb	A_lw, [dstin]
+	strb	B_lw, [dstin, tmp1]
+	strb	C_lw, [dstend, -1]
+L(copy0):
+	ret
+
+	.p2align 4
+	/* Medium copies: 33..128 bytes.  */
+L(copy32_128):
+	ldp	A_l, A_h, [src]
+	ldp	B_l, B_h, [src, 16]
+	ldp	C_l, C_h, [srcend, -32]
+	ldp	D_l, D_h, [srcend, -16]
+	cmp	count, 64
+	b.hi	L(copy128)
+	stp	A_l, A_h, [dstin]
+	stp	B_l, B_h, [dstin, 16]
+	stp	C_l, C_h, [dstend, -32]
+	stp	D_l, D_h, [dstend, -16]
 	ret
+
+	.p2align 4
+	/* Copy 65..128 bytes.  */
+L(copy128):
+	ldp	E_l, E_h, [src, 32]
+	ldp	F_l, F_h, [src, 48]
+	cmp	count, 96
+	b.ls	L(copy96)
+	ldp	G_l, G_h, [srcend, -64]
+	ldp	H_l, H_h, [srcend, -48]
+	stp	G_l, G_h, [dstend, -64]
+	stp	H_l, H_h, [dstend, -48]
+L(copy96):
+	stp	A_l, A_h, [dstin]
+	stp	B_l, B_h, [dstin, 16]
+	stp	E_l, E_h, [dstin, 32]
+	stp	F_l, F_h, [dstin, 48]
+	stp	C_l, C_h, [dstend, -32]
+	stp	D_l, D_h, [dstend, -16]
+	ret
+
+	.p2align 4
+	/* Copy more than 128 bytes.  */
+L(copy_long):
+	/* Use backwards copy if there is an overlap.  */
+	sub	tmp1, dstin, src
+	cbz	tmp1, L(copy0)
+	cmp	tmp1, count
+	b.lo	L(copy_long_backwards)
+
+	/* Copy 16 bytes and then align dst to 16-byte alignment.  */
+
+	ldp	D_l, D_h, [src]
+	and	tmp1, dstin, 15
+	bic	dst, dstin, 15
+	sub	src, src, tmp1
+	add	count, count, tmp1	/* Count is now 16 too large.  */
+	ldp	A_l, A_h, [src, 16]
+	stp	D_l, D_h, [dstin]
+	ldp	B_l, B_h, [src, 32]
+	ldp	C_l, C_h, [src, 48]
+	ldp	D_l, D_h, [src, 64]!
+	subs	count, count, 128 + 16	/* Test and readjust count.  */
+	b.ls	L(copy64_from_end)
+
+L(loop64):
+	stp	A_l, A_h, [dst, 16]
+	ldp	A_l, A_h, [src, 16]
+	stp	B_l, B_h, [dst, 32]
+	ldp	B_l, B_h, [src, 32]
+	stp	C_l, C_h, [dst, 48]
+	ldp	C_l, C_h, [src, 48]
+	stp	D_l, D_h, [dst, 64]!
+	ldp	D_l, D_h, [src, 64]!
+	subs	count, count, 64
+	b.hi	L(loop64)
+
+	/* Write the last iteration and copy 64 bytes from the end.  */
+L(copy64_from_end):
+	ldp	E_l, E_h, [srcend, -64]
+	stp	A_l, A_h, [dst, 16]
+	ldp	A_l, A_h, [srcend, -48]
+	stp	B_l, B_h, [dst, 32]
+	ldp	B_l, B_h, [srcend, -32]
+	stp	C_l, C_h, [dst, 48]
+	ldp	C_l, C_h, [srcend, -16]
+	stp	D_l, D_h, [dst, 64]
+	stp	E_l, E_h, [dstend, -64]
+	stp	A_l, A_h, [dstend, -48]
+	stp	B_l, B_h, [dstend, -32]
+	stp	C_l, C_h, [dstend, -16]
+	ret
+
+	.p2align 4
+
+	/* Large backwards copy for overlapping copies.
+	   Copy 16 bytes and then align dst to 16-byte alignment.  */
+L(copy_long_backwards):
+	ldp	D_l, D_h, [srcend, -16]
+	and	tmp1, dstend, 15
+	sub	srcend, srcend, tmp1
+	sub	count, count, tmp1
+	ldp	A_l, A_h, [srcend, -16]
+	stp	D_l, D_h, [dstend, -16]
+	ldp	B_l, B_h, [srcend, -32]
+	ldp	C_l, C_h, [srcend, -48]
+	ldp	D_l, D_h, [srcend, -64]!
+	sub	dstend, dstend, tmp1
+	subs	count, count, 128
+	b.ls	L(copy64_from_start)
+
+L(loop64_backwards):
+	stp	A_l, A_h, [dstend, -16]
+	ldp	A_l, A_h, [srcend, -16]
+	stp	B_l, B_h, [dstend, -32]
+	ldp	B_l, B_h, [srcend, -32]
+	stp	C_l, C_h, [dstend, -48]
+	ldp	C_l, C_h, [srcend, -48]
+	stp	D_l, D_h, [dstend, -64]!
+	ldp	D_l, D_h, [srcend, -64]!
+	subs	count, count, 64
+	b.hi	L(loop64_backwards)
+
+	/* Write the last iteration and copy 64 bytes from the start.  */
+L(copy64_from_start):
+	ldp	G_l, G_h, [src, 48]
+	stp	A_l, A_h, [dstend, -16]
+	ldp	A_l, A_h, [src, 32]
+	stp	B_l, B_h, [dstend, -32]
+	ldp	B_l, B_h, [src, 16]
+	stp	C_l, C_h, [dstend, -48]
+	ldp	C_l, C_h, [src]
+	stp	D_l, D_h, [dstend, -64]
+	stp	G_l, G_h, [dstin, 48]
+	stp	A_l, A_h, [dstin, 32]
+	stp	B_l, B_h, [dstin, 16]
+	stp	C_l, C_h, [dstin]
+	ret
+
 SYM_FUNC_END_PI(memcpy)
 EXPORT_SYMBOL(memcpy)
 SYM_FUNC_END_ALIAS(__memcpy)
 EXPORT_SYMBOL(__memcpy)
+SYM_FUNC_END_ALIAS_PI(memmove)
+EXPORT_SYMBOL(memmove)
+SYM_FUNC_END_ALIAS(__memmove)
+EXPORT_SYMBOL(__memmove)
\ No newline at end of file
diff --git a/arch/arm64/lib/memmove.S b/arch/arm64/lib/memmove.S
deleted file mode 100644
index 1035dce4bdaf..000000000000
--- a/arch/arm64/lib/memmove.S
+++ /dev/null
@@ -1,189 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2013 ARM Ltd.
- * Copyright (C) 2013 Linaro.
- *
- * This code is based on glibc cortex strings work originally authored by Linaro
- * be found @
- *
- * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
- * files/head:/src/aarch64/
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/cache.h>
-
-/*
- * Move a buffer from src to test (alignment handled by the hardware).
- * If dest <= src, call memcpy, otherwise copy in reverse order.
- *
- * Parameters:
- *	x0 - dest
- *	x1 - src
- *	x2 - n
- * Returns:
- *	x0 - dest
- */
-dstin	.req	x0
-src	.req	x1
-count	.req	x2
-tmp1	.req	x3
-tmp1w	.req	w3
-tmp2	.req	x4
-tmp2w	.req	w4
-tmp3	.req	x5
-tmp3w	.req	w5
-dst	.req	x6
-
-A_l	.req	x7
-A_h	.req	x8
-B_l	.req	x9
-B_h	.req	x10
-C_l	.req	x11
-C_h	.req	x12
-D_l	.req	x13
-D_h	.req	x14
-
-SYM_FUNC_START_ALIAS(__memmove)
-SYM_FUNC_START_WEAK_PI(memmove)
-	cmp	dstin, src
-	b.lo	__memcpy
-	add	tmp1, src, count
-	cmp	dstin, tmp1
-	b.hs	__memcpy		/* No overlap.  */
-
-	add	dst, dstin, count
-	add	src, src, count
-	cmp	count, #16
-	b.lo	.Ltail15  /*probably non-alignment accesses.*/
-
-	ands	tmp2, src, #15     /* Bytes to reach alignment.  */
-	b.eq	.LSrcAligned
-	sub	count, count, tmp2
-	/*
-	* process the aligned offset length to make the src aligned firstly.
-	* those extra instructions' cost is acceptable. It also make the
-	* coming accesses are based on aligned address.
-	*/
-	tbz	tmp2, #0, 1f
-	ldrb	tmp1w, [src, #-1]!
-	strb	tmp1w, [dst, #-1]!
-1:
-	tbz	tmp2, #1, 2f
-	ldrh	tmp1w, [src, #-2]!
-	strh	tmp1w, [dst, #-2]!
-2:
-	tbz	tmp2, #2, 3f
-	ldr	tmp1w, [src, #-4]!
-	str	tmp1w, [dst, #-4]!
-3:
-	tbz	tmp2, #3, .LSrcAligned
-	ldr	tmp1, [src, #-8]!
-	str	tmp1, [dst, #-8]!
-
-.LSrcAligned:
-	cmp	count, #64
-	b.ge	.Lcpy_over64
-
-	/*
-	* Deal with small copies quickly by dropping straight into the
-	* exit block.
-	*/
-.Ltail63:
-	/*
-	* Copy up to 48 bytes of data. At this point we only need the
-	* bottom 6 bits of count to be accurate.
-	*/
-	ands	tmp1, count, #0x30
-	b.eq	.Ltail15
-	cmp	tmp1w, #0x20
-	b.eq	1f
-	b.lt	2f
-	ldp	A_l, A_h, [src, #-16]!
-	stp	A_l, A_h, [dst, #-16]!
-1:
-	ldp	A_l, A_h, [src, #-16]!
-	stp	A_l, A_h, [dst, #-16]!
-2:
-	ldp	A_l, A_h, [src, #-16]!
-	stp	A_l, A_h, [dst, #-16]!
-
-.Ltail15:
-	tbz	count, #3, 1f
-	ldr	tmp1, [src, #-8]!
-	str	tmp1, [dst, #-8]!
-1:
-	tbz	count, #2, 2f
-	ldr	tmp1w, [src, #-4]!
-	str	tmp1w, [dst, #-4]!
-2:
-	tbz	count, #1, 3f
-	ldrh	tmp1w, [src, #-2]!
-	strh	tmp1w, [dst, #-2]!
-3:
-	tbz	count, #0, .Lexitfunc
-	ldrb	tmp1w, [src, #-1]
-	strb	tmp1w, [dst, #-1]
-
-.Lexitfunc:
-	ret
-
-.Lcpy_over64:
-	subs	count, count, #128
-	b.ge	.Lcpy_body_large
-	/*
-	* Less than 128 bytes to copy, so handle 64 bytes here and then jump
-	* to the tail.
-	*/
-	ldp	A_l, A_h, [src, #-16]
-	stp	A_l, A_h, [dst, #-16]
-	ldp	B_l, B_h, [src, #-32]
-	ldp	C_l, C_h, [src, #-48]
-	stp	B_l, B_h, [dst, #-32]
-	stp	C_l, C_h, [dst, #-48]
-	ldp	D_l, D_h, [src, #-64]!
-	stp	D_l, D_h, [dst, #-64]!
-
-	tst	count, #0x3f
-	b.ne	.Ltail63
-	ret
-
-	/*
-	* Critical loop. Start at a new cache line boundary. Assuming
-	* 64 bytes per line this ensures the entire loop is in one line.
-	*/
-	.p2align	L1_CACHE_SHIFT
-.Lcpy_body_large:
-	/* pre-load 64 bytes data. */
-	ldp	A_l, A_h, [src, #-16]
-	ldp	B_l, B_h, [src, #-32]
-	ldp	C_l, C_h, [src, #-48]
-	ldp	D_l, D_h, [src, #-64]!
-1:
-	/*
-	* interlace the load of next 64 bytes data block with store of the last
-	* loaded 64 bytes data.
-	*/
-	stp	A_l, A_h, [dst, #-16]
-	ldp	A_l, A_h, [src, #-16]
-	stp	B_l, B_h, [dst, #-32]
-	ldp	B_l, B_h, [src, #-32]
-	stp	C_l, C_h, [dst, #-48]
-	ldp	C_l, C_h, [src, #-48]
-	stp	D_l, D_h, [dst, #-64]!
-	ldp	D_l, D_h, [src, #-64]!
-	subs	count, count, #64
-	b.ge	1b
-	stp	A_l, A_h, [dst, #-16]
-	stp	B_l, B_h, [dst, #-32]
-	stp	C_l, C_h, [dst, #-48]
-	stp	D_l, D_h, [dst, #-64]!
-
-	tst	count, #0x3f
-	b.ne	.Ltail63
-	ret
-SYM_FUNC_END_PI(memmove)
-EXPORT_SYMBOL(memmove)
-SYM_FUNC_END_ALIAS(__memmove)
-EXPORT_SYMBOL(__memmove)