[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 at linaro.org>
Signed-off-by: Will Deacon <will.deacon at 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