[PATCH v2 0/2] Implement word-at-a-time string functions for ARM

[PATCH v2 0/2] Implement word-at-a-time string functions for ARM

[Will Deacon]

Hi all,

This is version 2 of the patches originally posted here:

  http://lists.infradead.org/pipermail/linux-arm-kernel/2012-June/103290.html

There are only cosmetic changes from v1:
	- Added Nico's reviewed-by tags
	- Removed RFC prefix
	- Fixed changelog to echo the fact that we may use clz

I'm still interested in any pathname-heavy benchmarks that people may
have to stress the name hashing code. My simple find test does show an
improvement but I don't know how realistic that is.

Cheers,

Will


Will Deacon (2):
  ARM: use generic strnlen_user and strncpy_from_user functions
  ARM: dcache: select DCACHE_WORD_ACCESS for little-endian ARMv6+ CPUs

 arch/arm/Kconfig                      |    3 +
 arch/arm/include/asm/uaccess.h        |   27 ++-------
 arch/arm/include/asm/word-at-a-time.h |   96 +++++++++++++++++++++++++++++++++
 arch/arm/kernel/armksyms.c            |    4 --
 arch/arm/lib/Makefile                 |    1 -
 arch/arm/lib/strncpy_from_user.S      |   43 ---------------
 arch/arm/lib/strnlen_user.S           |   40 --------------
 7 files changed, 105 insertions(+), 109 deletions(-)
 create mode 100644 arch/arm/include/asm/word-at-a-time.h
 delete mode 100644 arch/arm/lib/strncpy_from_user.S
 delete mode 100644 arch/arm/lib/strnlen_user.S

-- 
1.7.4.1

[PATCH v2 1/2] ARM: use generic strnlen_user and strncpy_from_user functions

[Will Deacon]

This patch implements the word-at-a-time interface for ARM using the
same algorithm as x86. We use the fls macro from ARMv5 onwards, where
we have a clz instruction available which saves us a mov instruction
when targetting Thumb-2. For older CPUs, we use the magic 0x0ff0001
constant. Big-endian configurations make use of the implementation from
asm-generic.

With this implemented, we can replace our byte-at-a-time strnlen_user
and strncpy_from_user functions with the optimised generic versions.

Reviewed-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm/Kconfig                      |    2 +
 arch/arm/include/asm/uaccess.h        |   27 +++------------
 arch/arm/include/asm/word-at-a-time.h |   55 +++++++++++++++++++++++++++++++++
 arch/arm/kernel/armksyms.c            |    4 --
 arch/arm/lib/Makefile                 |    1 -
 arch/arm/lib/strncpy_from_user.S      |   43 -------------------------
 arch/arm/lib/strnlen_user.S           |   40 ------------------------
 7 files changed, 63 insertions(+), 109 deletions(-)
 create mode 100644 arch/arm/include/asm/word-at-a-time.h
 delete mode 100644 arch/arm/lib/strncpy_from_user.S
 delete mode 100644 arch/arm/lib/strnlen_user.S

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 84449dd..77a2fad 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -45,6 +45,8 @@ config ARM
 	select GENERIC_SMP_IDLE_THREAD
 	select KTIME_SCALAR
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+	select GENERIC_STRNCPY_FROM_USER
+	select GENERIC_STRNLEN_USER
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
 	  licensed by ARM Ltd and targeted at embedded applications and
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 71f6536..479a635 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -189,6 +189,9 @@ static inline void set_fs(mm_segment_t fs)
 
 #define access_ok(type,addr,size)	(__range_ok(addr,size) == 0)
 
+#define user_addr_max() \
+	(segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
+
 /*
  * The "__xxx" versions of the user access functions do not verify the
  * address space - it must have been done previously with a separate
@@ -398,9 +401,6 @@ extern unsigned long __must_check __clear_user_std(void __user *addr, unsigned l
 #define __clear_user(addr,n)		(memset((void __force *)addr, 0, n), 0)
 #endif
 
-extern unsigned long __must_check __strncpy_from_user(char *to, const char __user *from, unsigned long count);
-extern unsigned long __must_check __strnlen_user(const char __user *s, long n);
-
 static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	if (access_ok(VERIFY_READ, from, n))
@@ -427,24 +427,9 @@ static inline unsigned long __must_check clear_user(void __user *to, unsigned lo
 	return n;
 }
 
-static inline long __must_check strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res = -EFAULT;
-	if (access_ok(VERIFY_READ, src, 1))
-		res = __strncpy_from_user(dst, src, count);
-	return res;
-}
-
-#define strlen_user(s)	strnlen_user(s, ~0UL >> 1)
+extern long strncpy_from_user(char *dest, const char __user *src, long count);
 
-static inline long __must_check strnlen_user(const char __user *s, long n)
-{
-	unsigned long res = 0;
-
-	if (__addr_ok(s))
-		res = __strnlen_user(s, n);
-
-	return res;
-}
+extern __must_check long strlen_user(const char __user *str);
+extern __must_check long strnlen_user(const char __user *str, long n);
 
 #endif /* _ASMARM_UACCESS_H */
diff --git a/arch/arm/include/asm/word-at-a-time.h b/arch/arm/include/asm/word-at-a-time.h
new file mode 100644
index 0000000..74b2d45
--- /dev/null
+++ b/arch/arm/include/asm/word-at-a-time.h
@@ -0,0 +1,55 @@
+#ifndef __ASM_ARM_WORD_AT_A_TIME_H
+#define __ASM_ARM_WORD_AT_A_TIME_H
+
+#ifndef __ARMEB__
+
+/*
+ * Little-endian word-at-a-time zero byte handling.
+ * Heavily based on the x86 algorithm.
+ */
+#include <linux/kernel.h>
+
+struct word_at_a_time {
+	const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+
+static inline unsigned long has_zero(unsigned long a, unsigned long *bits,
+				     const struct word_at_a_time *c)
+{
+	unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits;
+	*bits = mask;
+	return mask;
+}
+
+#define prep_zero_mask(a, bits, c) (bits)
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+	bits = (bits - 1) & ~bits;
+	return bits >> 7;
+}
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+	unsigned long ret;
+
+#if __LINUX_ARM_ARCH__ >= 5
+	/* We have clz available. */
+	ret = fls(mask) >> 3;
+#else
+	/* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+	ret = (0x0ff0001 + mask) >> 23;
+	/* Fix the 1 for 00 case */
+	ret &= mask;
+#endif
+
+	return ret;
+}
+
+#else	/* __ARMEB__ */
+#include <asm-generic/word-at-a-time.h>
+#endif
+
+#endif /* __ASM_ARM_WORD_AT_A_TIME_H */
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index b57c75e..c3dff6a 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -87,10 +87,6 @@ EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(memchr);
 EXPORT_SYMBOL(__memzero);
 
-	/* user mem (segment) */
-EXPORT_SYMBOL(__strnlen_user);
-EXPORT_SYMBOL(__strncpy_from_user);
-
 #ifdef CONFIG_MMU
 EXPORT_SYMBOL(copy_page);
 
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index 992769a..d5060da 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -8,7 +8,6 @@ lib-y		:= backtrace.o changebit.o csumipv6.o csumpartial.o   \
 		   csumpartialcopy.o csumpartialcopyuser.o clearbit.o \
 		   delay.o findbit.o memchr.o memcpy.o		      \
 		   memmove.o memset.o memzero.o setbit.o              \
-		   strncpy_from_user.o strnlen_user.o                 \
 		   strchr.o strrchr.o                                 \
 		   testchangebit.o testclearbit.o testsetbit.o        \
 		   ashldi3.o ashrdi3.o lshrdi3.o muldi3.o             \
diff --git a/arch/arm/lib/strncpy_from_user.S b/arch/arm/lib/strncpy_from_user.S
deleted file mode 100644
index f202d7b..0000000
--- a/arch/arm/lib/strncpy_from_user.S
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- *  linux/arch/arm/lib/strncpy_from_user.S
- *
- *  Copyright (C) 1995-2000 Russell King
- *
- * 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>
-#include <asm/errno.h>
-
-	.text
-	.align	5
-
-/*
- * Copy a string from user space to kernel space.
- *  r0 = dst, r1 = src, r2 = byte length
- * returns the number of characters copied (strlen of copied string),
- *  -EFAULT on exception, or "len" if we fill the whole buffer
- */
-ENTRY(__strncpy_from_user)
-	mov	ip, r1
-1:	subs	r2, r2, #1
-	ldrusr	r3, r1, 1, pl
-	bmi	2f
-	strb	r3, [r0], #1
-	teq	r3, #0
-	bne	1b
-	sub	r1, r1, #1	@ take NUL character out of count
-2:	sub	r0, r1, ip
-	mov	pc, lr
-ENDPROC(__strncpy_from_user)
-
-	.pushsection .fixup,"ax"
-	.align	0
-9001:	mov	r3, #0
-	strb	r3, [r0, #0]	@ null terminate
-	mov	r0, #-EFAULT
-	mov	pc, lr
-	.popsection
-
diff --git a/arch/arm/lib/strnlen_user.S b/arch/arm/lib/strnlen_user.S
deleted file mode 100644
index 0ecbb45..0000000
--- a/arch/arm/lib/strnlen_user.S
+++ /dev/null
@@ -1,40 +0,0 @@
-/*
- *  linux/arch/arm/lib/strnlen_user.S
- *
- *  Copyright (C) 1995-2000 Russell King
- *
- * 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>
-#include <asm/errno.h>
-
-	.text
-	.align	5
-
-/* Prototype: unsigned long __strnlen_user(const char *str, long n)
- * Purpose  : get length of a string in user memory
- * Params   : str - address of string in user memory
- * Returns  : length of string *including terminator*
- *	      or zero on exception, or n + 1 if too long
- */
-ENTRY(__strnlen_user)
-	mov	r2, r0
-1:
-	ldrusr	r3, r0, 1
-	teq	r3, #0
-	beq	2f
-	subs	r1, r1, #1
-	bne	1b
-	add	r0, r0, #1
-2:	sub	r0, r0, r2
-	mov	pc, lr
-ENDPROC(__strnlen_user)
-
-	.pushsection .fixup,"ax"
-	.align	0
-9001:	mov	r0, #0
-	mov	pc, lr
-	.popsection
-- 
1.7.4.1

[PATCH v2 2/2] ARM: dcache: select DCACHE_WORD_ACCESS for little-endian ARMv6+ CPUs

[Will Deacon]

DCACHE_WORD_ACCESS uses the word-at-a-time API for optimised string
comparisons in the vfs layer.

This patch implements support for load_unaligned_zeropad for ARM CPUs
with native support for unaligned memory accesses (v6+) when running
little-endian.

Reviewed-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm/Kconfig                      |    1 +
 arch/arm/include/asm/word-at-a-time.h |   41 +++++++++++++++++++++++++++++++++
 2 files changed, 42 insertions(+), 0 deletions(-)

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 77a2fad..bba8a56 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -47,6 +47,7 @@ config ARM
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
+	select DCACHE_WORD_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && !CPU_BIG_ENDIAN
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
 	  licensed by ARM Ltd and targeted at embedded applications and
diff --git a/arch/arm/include/asm/word-at-a-time.h b/arch/arm/include/asm/word-at-a-time.h
index 74b2d45..4d52f92 100644
--- a/arch/arm/include/asm/word-at-a-time.h
+++ b/arch/arm/include/asm/word-at-a-time.h
@@ -48,6 +48,47 @@ static inline unsigned long find_zero(unsigned long mask)
 	return ret;
 }
 
+#ifdef CONFIG_DCACHE_WORD_ACCESS
+
+#define zero_bytemask(mask) (mask)
+
+/*
+ * Load an unaligned word from kernel space.
+ *
+ * In the (very unlikely) case of the word being a page-crosser
+ * and the next page not being mapped, take the exception and
+ * return zeroes in the non-existing part.
+ */
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+	unsigned long ret, offset;
+
+	/* Load word from unaligned pointer addr */
+	asm(
+	"1:	ldr	%0, [%2]\n"
+	"2:\n"
+	"	.pushsection .fixup,\"ax\"\n"
+	"	.align 2\n"
+	"3:	and	%1, %2, #0x3\n"
+	"	bic	%2, %2, #0x3\n"
+	"	ldr	%0, [%2]\n"
+	"	lsl	%1, %1, #0x3\n"
+	"	lsr	%0, %0, %1\n"
+	"	b	2b\n"
+	"	.popsection\n"
+	"	.pushsection __ex_table,\"a\"\n"
+	"	.align	3\n"
+	"	.long	1b, 3b\n"
+	"	.popsection"
+	: "=&r" (ret), "=&r" (offset)
+	: "r" (addr), "Qo" (*(unsigned long *)addr));
+
+	return ret;
+}
+
+
+#endif	/* DCACHE_WORD_ACCESS */
+
 #else	/* __ARMEB__ */
 #include <asm-generic/word-at-a-time.h>
 #endif
-- 
1.7.4.1