3.16.60-rc1 review patch. If anyone has any objections, please let me know.
------------------
From: Chris Metcalf <cmetcalf@xxxxxxxxxx>
commit a6e2f029ae34f41adb6ae3812c32c5d326e1abd2 upstream.
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@xxxxxxxxxx>
[bwh: Backported to 3.16:
- Drop change in arch/nios2
- Adjust context]
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
---
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -49,4 +49,5 @@ generic-y += types.h
generic-y += ucontext.h
generic-y += user.h
generic-y += vga.h
+generic-y += word-at-a-time.h
generic-y += xor.h
--- a/arch/avr32/include/asm/Kbuild
+++ b/arch/avr32/include/asm/Kbuild
@@ -20,4 +20,5 @@ generic-y += sections.h
generic-y += topology.h
generic-y += trace_clock.h
generic-y += vga.h
+generic-y += word-at-a-time.h
generic-y += xor.h
--- a/arch/blackfin/include/asm/Kbuild
+++ b/arch/blackfin/include/asm/Kbuild
@@ -46,4 +46,5 @@ generic-y += types.h
generic-y += ucontext.h
generic-y += unaligned.h
generic-y += user.h
+generic-y += word-at-a-time.h
generic-y += xor.h
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -58,4 +58,5 @@ generic-y += types.h
generic-y += ucontext.h
generic-y += user.h
generic-y += vga.h
+generic-y += word-at-a-time.h
generic-y += xor.h
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -15,4 +15,5 @@ generic-y += module.h
generic-y += preempt.h
generic-y += trace_clock.h
generic-y += vga.h
+generic-y += word-at-a-time.h
generic-y += xor.h
--- a/arch/frv/include/asm/Kbuild
+++ b/arch/frv/include/asm/Kbuild
@@ -6,3 +6,4 @@ generic-y += hash.h
generic-y += mcs_spinlock.h
generic-y += preempt.h
generic-y += trace_clock.h
+generic-y += word-at-a-time.h
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -58,4 +58,5 @@ generic-y += types.h
generic-y += ucontext.h
generic-y += unaligned.h
generic-y += vga.h
+generic-y += word-at-a-time.h
generic-y += xor.h
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -7,3 +7,4 @@ generic-y += mcs_spinlock.h
generic-y += preempt.h
generic-y += trace_clock.h
generic-y += vtime.h
+generic-y += word-at-a-time.h
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -7,3 +7,4 @@ generic-y += mcs_spinlock.h
generic-y += module.h
generic-y += preempt.h
generic-y += trace_clock.h
+generic-y += word-at-a-time.h
--- a/arch/metag/include/asm/Kbuild
+++ b/arch/metag/include/asm/Kbuild
@@ -54,4 +54,5 @@ generic-y += ucontext.h
generic-y += unaligned.h
generic-y += user.h
generic-y += vga.h
+generic-y += word-at-a-time.h
generic-y += xor.h
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -9,3 +9,4 @@ generic-y += mcs_spinlock.h
generic-y += preempt.h
generic-y += syscalls.h
generic-y += trace_clock.h
+generic-y += word-at-a-time.h
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -15,4 +15,5 @@ generic-y += segment.h
generic-y += serial.h
generic-y += trace_clock.h
generic-y += ucontext.h
+generic-y += word-at-a-time.h
generic-y += xor.h
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -7,3 +7,4 @@ generic-y += hash.h
generic-y += mcs_spinlock.h
generic-y += preempt.h
generic-y += trace_clock.h
+generic-y += word-at-a-time.h
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -6,3 +6,4 @@ generic-y += preempt.h
generic-y += rwsem.h
generic-y += trace_clock.h
generic-y += vtime.h
+generic-y += word-at-a-time.h
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -5,3 +5,4 @@ generic-y += hash.h
generic-y += mcs_spinlock.h
generic-y += preempt.h
generic-y += trace_clock.h
+generic-y += word-at-a-time.h
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -10,3 +10,4 @@ generic-y += mcs_spinlock.h
generic-y += preempt.h
generic-y += trace_clock.h
generic-y += xor.h
+generic-y += word-at-a-time.h
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -40,4 +40,5 @@ generic-y += termbits.h
generic-y += termios.h
generic-y += trace_clock.h
generic-y += types.h
+generic-y += word-at-a-time.h
generic-y += xor.h
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -25,4 +25,5 @@ generic-y += sections.h
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
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -62,4 +62,5 @@ generic-y += ucontext.h
generic-y += unaligned.h
generic-y += user.h
generic-y += vga.h
+generic-y += word-at-a-time.h
generic-y += xor.h
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -29,4 +29,5 @@ generic-y += statfs.h
generic-y += termios.h
generic-y += topology.h
generic-y += trace_clock.h
+generic-y += word-at-a-time.h
generic-y += xor.h
--- 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 lon
#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 */
