[ARM] 2947/1: copy template with new memcpy/memmove

Patch from Nicolas Pitre

This patch provides a new implementation for optimized memory copy
functions on ARM.  It is made of two levels: a template that consists of
the core copy code and separate files that define macros to be used with
the core code depending on the type of copy needed. This allows for best
performances while sharing the same core for implementing memcpy(),
copy_from_user() and copy_to_user() for instance.

Two reasons for this work:

1) the current copy_to_user/copy_from_user implementation assumes no
   task switch will ever occur in the middle of each copied page making
   it completely unsafe with CONFIG_PREEMPT=y.

2) current copy implementations are measurably suboptimal and optimizing
   different implementations separately is a pain and more opportunities
   for bugs.

The reason for (1) is the fact that copy inside user pages are performed
with the ldm instruction which has no mean for testing user protections
and could possibly race with process preemption bypassing the COW mechanism
for example.  This is a longstanding issue that we said ought to be fixed
for about two years now.  The solution is to substitute those ldm insns
with a series of ldrt or strt insns to enforce user memory protection.
At least on StrongARM and XScale cores the ldm is not faster than the
equivalent ldr/str insns with a warm i-cache so there is no measurable
performance degradation with that change. The fact that the copy code is
a template makes it pretty easy to reuse the same core code as for memcpy
and benefit from the same performance optimizations.

Now (2) is best demonstrated with actual throughput measurements.
First, here is a summary of memcopy tests performed on a StrongARM core:

	PTR alignment	buffer size	kernel version	this version
	------------------------------------------------------------
	  aligned	     32		 59.73		107.43
	unaligned	     32		 61.31		 74.72
	  aligned	    100		132.47		136.15
	unaligned	    100	    	103.84		123.76
	  aligned	   4096		130.67		130.80
	unaligned	   4096	    	130.68		130.64
	  aligned	1048576		 68.03		68.18
	unaligned	1048576		 68.03		68.18

The buffer size is in bytes and the measured speed in MB/s.  The copy
was performed repeatedly with given buffer and throughput averaged over
3 seconds.

Here we can see that the current kernel version has a higher entry cost
that shows up with small buffers.  As buffer size grows both implementation
converge to the same throughput.

Now here's the exact same test performed on an XScale core (PXA255):

	PTR alignment	buffer size	kernel version	this version
	------------------------------------------------------------
	  aligned	     32		 46.99		 77.58
	unaligned	     32		 53.61		 59.59
	  aligned	    100		107.19		136.59
	unaligned	    100		 83.61		 97.58
	  aligned	   4096		129.13		129.98
	unaligned	   4096		128.36		128.53
	  aligned	1048576		 53.76		 59.41
	unaligned	1048576		 33.67		 56.96

Again we can see the entry setup cost being higher for the current kernel
before getting to the main copy loop.  Then throughput results converge
as long as the buffer remains in the cache. Then the 1MB case shows more
differences probably due to better pld placement and/or less instruction
interlocks in this proposed implementation.

Disclaimer: The PXA system was running with slower clocks than the
StrongARM system so trying to infer any conclusion by comparing those
separate sets of results side by side would be completely inappropriate.

So...  What this patch does is to replace both memcpy and memmove with
an implementation based on the provided copy code template.  The memmove
code is kept separate since it is used only if the memory areas involved
do overlap in which case the code is a transposition of the template but
with the copy occurring in the opposite direction (trying to fit that
mode into the template turned it into a mess not worth it for memmove
alone).  And obviously both memcpy and memmove were tested with all kinds
of pointer alignments and buffer sizes to exercise all code paths for
correctness.

The next patch will provide the now trivial replacement implementation
copy_to_user and copy_from_user.

Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S
new file mode 100644
index 0000000..ef7fddc
--- /dev/null
+++ b/arch/arm/lib/memmove.S
@@ -0,0 +1,206 @@
+/*
+ *  linux/arch/arm/lib/memmove.S
+ *
+ *  Author:	Nicolas Pitre
+ *  Created:	Sep 28, 2005
+ *  Copyright:	(C) MontaVista Software Inc.
+ *
+ *  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/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * This can be used to enable code to cacheline align the source pointer.
+ * Experiments on tested architectures (StrongARM and XScale) didn't show
+ * this a worthwhile thing to do.  That might be different in the future.
+ */
+//#define CALGN(code...)        code
+#define CALGN(code...)
+
+		.text
+
+/*
+ * Prototype: void *memmove(void *dest, const void *src, size_t n);
+ *
+ * Note:
+ *
+ * If the memory regions don't overlap, we simply branch to memcpy which is
+ * normally a bit faster. Otherwise the copy is done going downwards.  This
+ * is a transposition of the code from copy_template.S but with the copy
+ * occurring in the opposite direction.
+ */
+
+ENTRY(memmove)
+
+		subs	ip, r0, r1
+		cmphi	r2, ip
+		bls	memcpy
+
+		stmfd	sp!, {r0, r4, lr}
+		add	r1, r1, r2
+		add	r0, r0, r2
+		subs	r2, r2, #4
+		blt	8f
+		ands	ip, r0, #3
+	PLD(	pld	[r1, #-4]		)
+		bne	9f
+		ands	ip, r1, #3
+		bne	10f
+
+1:		subs	r2, r2, #(28)
+		stmfd	sp!, {r5 - r8}
+		blt	5f
+
+	CALGN(	ands	ip, r1, #31		)
+	CALGN(	sbcnes	r4, ip, r2		)  @ C is always set here
+	CALGN(	bcs	2f			)
+	CALGN(	adr	r4, 6f			)
+	CALGN(	subs	r2, r2, ip		)  @ C is set here
+	CALGN(	add	pc, r4, ip		)
+
+	PLD(	pld	[r1, #-4]		)
+2:	PLD(	subs	r2, r2, #96		)
+	PLD(	pld	[r1, #-32]		)
+	PLD(	blt	4f			)
+	PLD(	pld	[r1, #-64]		)
+	PLD(	pld	[r1, #-96]		)
+
+3:	PLD(	pld	[r1, #-128]		)
+4:		ldmdb	r1!, {r3, r4, r5, r6, r7, r8, ip, lr}
+		subs	r2, r2, #32
+		stmdb	r0!, {r3, r4, r5, r6, r7, r8, ip, lr}
+		bge	3b
+	PLD(	cmn	r2, #96			)
+	PLD(	bge	4b			)
+
+5:		ands	ip, r2, #28
+		rsb	ip, ip, #32
+		addne	pc, pc, ip		@ C is always clear here
+		b	7f
+6:		nop
+		ldr	r3, [r1, #-4]!
+		ldr	r4, [r1, #-4]!
+		ldr	r5, [r1, #-4]!
+		ldr	r6, [r1, #-4]!
+		ldr	r7, [r1, #-4]!
+		ldr	r8, [r1, #-4]!
+		ldr	lr, [r1, #-4]!
+
+		add	pc, pc, ip
+		nop
+		nop
+		str	r3, [r0, #-4]!
+		str	r4, [r0, #-4]!
+		str	r5, [r0, #-4]!
+		str	r6, [r0, #-4]!
+		str	r7, [r0, #-4]!
+		str	r8, [r0, #-4]!
+		str	lr, [r0, #-4]!
+
+	CALGN(	bcs	2b			)
+
+7:		ldmfd	sp!, {r5 - r8}
+
+8:		movs	r2, r2, lsl #31
+		ldrneb	r3, [r1, #-1]!
+		ldrcsb	r4, [r1, #-1]!
+		ldrcsb	ip, [r1, #-1]
+		strneb	r3, [r0, #-1]!
+		strcsb	r4, [r0, #-1]!
+		strcsb	ip, [r0, #-1]
+		ldmfd	sp!, {r0, r4, pc}
+
+9:		cmp	ip, #2
+		ldrgtb	r3, [r1, #-1]!
+		ldrgeb	r4, [r1, #-1]!
+		ldrb	lr, [r1, #-1]!
+		strgtb	r3, [r0, #-1]!
+		strgeb	r4, [r0, #-1]!
+		subs	r2, r2, ip
+		strb	lr, [r0, #-1]!
+		blt	8b
+		ands	ip, r1, #3
+		beq	1b
+
+10:		bic	r1, r1, #3
+		cmp	ip, #2
+		ldr	r3, [r1, #0]
+		beq	17f
+		blt	18f
+
+
+		.macro	backward_copy_shift push pull
+
+		subs	r2, r2, #28
+		blt	14f
+
+	CALGN(	ands	ip, r1, #31		)
+	CALGN(	rsb	ip, ip, #32		)
+	CALGN(	sbcnes	r4, ip, r2		)  @ C is always set here
+	CALGN(	subcc	r2, r2, ip		)
+	CALGN(	bcc	15f			)
+
+11:		stmfd	sp!, {r5 - r9}
+
+	PLD(	pld	[r1, #-4]		)
+	PLD(	subs	r2, r2, #96		)
+	PLD(	pld	[r1, #-32]		)
+	PLD(	blt	13f			)
+	PLD(	pld	[r1, #-64]		)
+	PLD(	pld	[r1, #-96]		)
+
+12:	PLD(	pld	[r1, #-128]		)
+13:		ldmdb   r1!, {r7, r8, r9, ip}
+		mov     lr, r3, push #\push
+		subs    r2, r2, #32
+		ldmdb   r1!, {r3, r4, r5, r6}
+		orr     lr, lr, ip, pull #\pull
+		mov     ip, ip, push #\push
+		orr     ip, ip, r9, pull #\pull
+		mov     r9, r9, push #\push
+		orr     r9, r9, r8, pull #\pull
+		mov     r8, r8, push #\push
+		orr     r8, r8, r7, pull #\pull
+		mov     r7, r7, push #\push
+		orr     r7, r7, r6, pull #\pull
+		mov     r6, r6, push #\push
+		orr     r6, r6, r5, pull #\pull
+		mov     r5, r5, push #\push
+		orr     r5, r5, r4, pull #\pull
+		mov     r4, r4, push #\push
+		orr     r4, r4, r3, pull #\pull
+		stmdb   r0!, {r4 - r9, ip, lr}
+		bge	12b
+	PLD(	cmn	r2, #96			)
+	PLD(	bge	13b			)
+
+		ldmfd	sp!, {r5 - r9}
+
+14:		ands	ip, r2, #28
+		beq	16f
+
+15:		mov     lr, r3, push #\push
+		ldr	r3, [r1, #-4]!
+		subs	ip, ip, #4
+		orr	lr, lr, r3, pull #\pull
+		str	lr, [r0, #-4]!
+		bgt	15b
+	CALGN(	cmp	r2, #0			)
+	CALGN(	bge	11b			)
+
+16:		add	r1, r1, #(\pull / 8)
+		b	8b
+
+		.endm
+
+
+		backward_copy_shift	push=8	pull=24
+
+17:		backward_copy_shift	push=16	pull=16
+
+18:		backward_copy_shift	push=24	pull=8
+