ARM: 7449/1: use generic strnlen_user and strncpy_from_user functions

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>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

arch/arm/Kconfig

@@ -46,6 +46,8 @@ 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

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 */

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 */

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);
 

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             \