summaryrefslogtreecommitdiffstats
path: root/include/asm-generic/word-at-a-time.h
diff options
context:
space:
mode:
authorChris Metcalf <cmetcalf@ezchip.com>2015-04-29 12:48:40 -0400
committerChris Metcalf <cmetcalf@ezchip.com>2015-07-08 16:41:55 -0400
commita6e2f029ae34f41adb6ae3812c32c5d326e1abd2 (patch)
tree17a28881ffaf9b613eb1df580ab6ba6e90cac3bd /include/asm-generic/word-at-a-time.h
parentd770e558e21961ad6cfdf0ff7df0eb5d7d4f0754 (diff)
downloadlinux-a6e2f029ae34f41adb6ae3812c32c5d326e1abd2.tar.bz2
Make asm/word-at-a-time.h available on all architectures
Added the x86 implementation of word-at-a-time to the generic version, which previously only supported big-endian. Omitted the x86-specific load_unaligned_zeropad(), which in any case is also not present for the existing BE-only implementation of a word-at-a-time, and is only used under CONFIG_DCACHE_WORD_ACCESS. Added as a "generic-y" to the Kbuilds of all architectures that didn't previously have it. Signed-off-by: Chris Metcalf <cmetcalf@ezchip.com>
Diffstat (limited to 'include/asm-generic/word-at-a-time.h')
-rw-r--r--include/asm-generic/word-at-a-time.h80
1 files changed, 72 insertions, 8 deletions
diff --git a/include/asm-generic/word-at-a-time.h b/include/asm-generic/word-at-a-time.h
index 94f9ea8abcae..011dde083f23 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 @@ static inline bool has_zero(unsigned long val, unsigned long *data, const struct
#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 */