diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index 1a80cc9..c8f07ce 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -47,4 +47,5 @@
 generic-y += ucontext.h
 generic-y += user.h
 generic-y += vga.h
+generic-y += word-at-a-time.h
 generic-y += xor.h
diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild
index 1d66afd..519810d 100644
--- a/arch/avr32/include/asm/Kbuild
+++ b/arch/avr32/include/asm/Kbuild
@@ -19,4 +19,5 @@
 generic-y += topology.h
 generic-y += trace_clock.h
 generic-y += vga.h
+generic-y += word-at-a-time.h
 generic-y += xor.h
diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild
index 07051a6..c80181e 100644
--- a/arch/blackfin/include/asm/Kbuild
+++ b/arch/blackfin/include/asm/Kbuild
@@ -45,4 +45,5 @@
 generic-y += ucontext.h
 generic-y += unaligned.h
 generic-y += user.h
+generic-y += word-at-a-time.h
 generic-y += xor.h
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index 7aeb322..2f697020 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -58,4 +58,5 @@
 generic-y += ucontext.h
 generic-y += user.h
 generic-y += vga.h
+generic-y += word-at-a-time.h
 generic-y += xor.h
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index d294f6a..09916c8 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -25,4 +25,5 @@
 generic-y += topology.h
 generic-y += trace_clock.h
 generic-y += vga.h
+generic-y += word-at-a-time.h
 generic-y += xor.h
diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild
index 30edce3..2c987dc 100644
--- a/arch/frv/include/asm/Kbuild
+++ b/arch/frv/include/asm/Kbuild
@@ -6,3 +6,4 @@
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += trace_clock.h
+generic-y += word-at-a-time.h
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index 5ade4a1..0988816 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -57,4 +57,5 @@
 generic-y += ucontext.h
 generic-y += unaligned.h
 generic-y += vga.h
+generic-y += word-at-a-time.h
 generic-y += xor.h
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index ccff13d..dc05773 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -7,3 +7,4 @@
 generic-y += preempt.h
 generic-y += trace_clock.h
 generic-y += vtime.h
+generic-y += word-at-a-time.h
diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index ba1cdc0..219e54b 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -8,3 +8,4 @@
 generic-y += preempt.h
 generic-y += sections.h
 generic-y += trace_clock.h
+generic-y += word-at-a-time.h
diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild
index 199320f..611c0df 100644
--- a/arch/metag/include/asm/Kbuild
+++ b/arch/metag/include/asm/Kbuild
@@ -53,4 +53,5 @@
 generic-y += unaligned.h
 generic-y += user.h
 generic-y += vga.h
+generic-y += word-at-a-time.h
 generic-y += xor.h
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 9989ddb..cefeaba 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -9,3 +9,4 @@
 generic-y += preempt.h
 generic-y += syscalls.h
 generic-y += trace_clock.h
+generic-y += word-at-a-time.h
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 7fe5c61..dee810f 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -17,4 +17,5 @@
 generic-y += trace_clock.h
 generic-y += ucontext.h
 generic-y += user.h
+generic-y += word-at-a-time.h
 generic-y += xor.h
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index de30b0c..27cbc02 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -8,3 +8,4 @@
 generic-y += preempt.h
 generic-y += sections.h
 generic-y += trace_clock.h
+generic-y += word-at-a-time.h
diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild
index 434639d..e224789 100644
--- a/arch/nios2/include/asm/Kbuild
+++ b/arch/nios2/include/asm/Kbuild
@@ -60,4 +60,5 @@
 generic-y += unaligned.h
 generic-y += user.h
 generic-y += vga.h
+generic-y += word-at-a-time.h
 generic-y += xor.h
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 050712e..d9c0b44 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -8,3 +8,4 @@
 generic-y += rwsem.h
 generic-y += trace_clock.h
 generic-y += vtime.h
+generic-y += word-at-a-time.h
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index dc5385e..9e8089b 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -5,3 +5,4 @@
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += trace_clock.h
+generic-y += word-at-a-time.h
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index 138fb3d..ff19975 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -12,3 +12,4 @@
 generic-y += trace_clock.h
 generic-y += xor.h
 generic-y += serial.h
+generic-y += word-at-a-time.h
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index d536544..ea59330 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -38,4 +38,5 @@
 generic-y += termios.h
 generic-y += trace_clock.h
 generic-y += types.h
+generic-y += word-at-a-time.h
 generic-y += xor.h
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 3d63ff6..33c1d3e 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -24,4 +24,5 @@
 generic-y += switch_to.h
 generic-y += topology.h
 generic-y += trace_clock.h
+generic-y += word-at-a-time.h
 generic-y += xor.h
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index d12b377..932070c 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -61,4 +61,5 @@
 generic-y += unaligned.h
 generic-y += user.h
 generic-y += vga.h
+generic-y += word-at-a-time.h
 generic-y += xor.h
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 14d15bf..85acffd 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -28,4 +28,5 @@
 generic-y += termios.h
 generic-y += topology.h
 generic-y += trace_clock.h
+generic-y += word-at-a-time.h
 generic-y += xor.h
diff --git a/include/asm-generic/word-at-a-time.h b/include/asm-generic/word-at-a-time.h
index 94f9ea8..011dde0 100644
--- a/include/asm-generic/word-at-a-time.h
+++ b/include/asm-generic/word-at-a-time.h
@@ -1,15 +1,10 @@
 #ifndef _ASM_WORD_AT_A_TIME_H
 #define _ASM_WORD_AT_A_TIME_H
 
-/*
- * This says "generic", but it's actually big-endian only.
- * Little-endian can use more efficient versions of these
- * interfaces, see for example
- *	 arch/x86/include/asm/word-at-a-time.h
- * for those.
- */
-
 #include <linux/kernel.h>
+#include <asm/byteorder.h>
+
+#ifdef __BIG_ENDIAN
 
 struct word_at_a_time {
 	const unsigned long high_bits, low_bits;
@@ -53,4 +48,73 @@
 #define zero_bytemask(mask) (~1ul << __fls(mask))
 #endif
 
+#else
+
+/*
+ * The optimal byte mask counting is probably going to be something
+ * that is architecture-specific. If you have a reliably fast
+ * bit count instruction, that might be better than the multiply
+ * and shift, for example.
+ */
+struct word_at_a_time {
+	const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+
+#ifdef CONFIG_64BIT
+
+/*
+ * Jan Achrenius on G+: microoptimized version of
+ * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56"
+ * that works for the bytemasks without having to
+ * mask them first.
+ */
+static inline long count_masked_bytes(unsigned long mask)
+{
+	return mask*0x0001020304050608ul >> 56;
+}
+
+#else	/* 32-bit case */
+
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
+static inline long count_masked_bytes(long mask)
+{
+	/* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+	long a = (0x0ff0001+mask) >> 23;
+	/* Fix the 1 for 00 case */
+	return a & mask;
+}
+
+#endif
+
+/* Return nonzero if it has a zero */
+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;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c)
+{
+	return bits;
+}
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+	bits = (bits - 1) & ~bits;
+	return bits >> 7;
+}
+
+/* The mask we created is directly usable as a bytemask */
+#define zero_bytemask(mask) (mask)
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+	return count_masked_bytes(mask);
+}
+
+#endif /* __BIG_ENDIAN */
+
 #endif /* _ASM_WORD_AT_A_TIME_H */