[PATCH] powerpc: Merge bitops.h

Here's a revised version.  This re-introduces the set_bits() function
from ppc64, which I removed because I thought it was unused (it exists
on no other arch).  In fact it is used in the powermac interrupt code
(but not on pSeries).

- We use LARXL/STCXL macros to generate the right (32 or 64 bit)
  instructions, similar to LDL/STL from ppc_asm.h, used in fpu.S

- ppc32 previously used a full "sync" barrier at the end of
  test_and_*_bit(), whereas ppc64 used an "isync".  The merged version
  uses "isync", since I believe that's sufficient.

- The ppc64 versions of then minix_*() bitmap functions have changed
  semantics.  Previously on ppc64, these functions were big-endian
  (that is bit 0 was the LSB in the first 64-bit, big-endian word).
  On ppc32 (and x86, for that matter, they were little-endian.  As far
  as I can tell, the big-endian usage was simply wrong - I guess
  no-one ever tried to use minixfs on ppc64.

- On ppc32 find_next_bit() and find_next_zero_bit() are no longer
  inline (they were already out-of-line on ppc64).

- For ppc64, sched_find_first_bit() has moved from mmu_context.h to
  the merged bitops.  What it was doing in mmu_context.h in the first
  place, I have no idea.

- The fls() function is now implemented using the cntlzw instruction
  on ppc64, instead of generic_fls(), as it already was on ppc32.

- For ARCH=ppc, this patch requires adding arch/powerpc/lib to the
  arch/ppc/Makefile.  This in turn requires some changes to
  arch/powerpc/lib/Makefile which didn't correctly handle ARCH=ppc.

Built and running on G5.

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>

2 files changed, 155 insertions, 4 deletions

diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index dfb3391..34f5c2e 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -3,13 +3,14 @@
 #
 
 ifeq ($(CONFIG_PPC_MERGE),y)
-obj-y			:= string.o
+obj-y			:= string.o strcase.o
+obj-$(CONFIG_PPC32)	+= div64.o copy_32.o checksum_32.o
 endif
 
-obj-y			+= strcase.o
-obj-$(CONFIG_PPC32)	+= div64.o copy_32.o checksum_32.o
+obj-y			+= bitops.o
 obj-$(CONFIG_PPC64)	+= checksum_64.o copypage_64.o copyuser_64.o \
-			   memcpy_64.o usercopy_64.o mem_64.o string.o
+			   memcpy_64.o usercopy_64.o mem_64.o string.o \
+			   strcase.o
 obj-$(CONFIG_PPC_ISERIES) += e2a.o
 obj-$(CONFIG_XMON)	+= sstep.o
 
diff --git a/arch/powerpc/lib/bitops.c b/arch/powerpc/lib/bitops.c
new file mode 100644
index 0000000..b67ce30
--- /dev/null
+++ b/arch/powerpc/lib/bitops.c
@@ -0,0 +1,150 @@
+#include <linux/types.h>
+#include <linux/module.h>
+#include <asm/byteorder.h>
+#include <asm/bitops.h>
+
+/**
+ * find_next_bit - find the next set bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The maximum size to search
+ */
+unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
+			    unsigned long offset)
+{
+	const unsigned long *p = addr + BITOP_WORD(offset);
+	unsigned long result = offset & ~(BITS_PER_LONG-1);
+	unsigned long tmp;
+
+	if (offset >= size)
+		return size;
+	size -= result;
+	offset %= BITS_PER_LONG;
+	if (offset) {
+		tmp = *(p++);
+		tmp &= (~0UL << offset);
+		if (size < BITS_PER_LONG)
+			goto found_first;
+		if (tmp)
+			goto found_middle;
+		size -= BITS_PER_LONG;
+		result += BITS_PER_LONG;
+	}
+	while (size & ~(BITS_PER_LONG-1)) {
+		if ((tmp = *(p++)))
+			goto found_middle;
+		result += BITS_PER_LONG;
+		size -= BITS_PER_LONG;
+	}
+	if (!size)
+		return result;
+	tmp = *p;
+
+found_first:
+	tmp &= (~0UL >> (64 - size));
+	if (tmp == 0UL)		/* Are any bits set? */
+		return result + size;	/* Nope. */
+found_middle:
+	return result + __ffs(tmp);
+}
+EXPORT_SYMBOL(find_next_bit);
+
+/*
+ * This implementation of find_{first,next}_zero_bit was stolen from
+ * Linus' asm-alpha/bitops.h.
+ */
+unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
+				 unsigned long offset)
+{
+	const unsigned long *p = addr + BITOP_WORD(offset);
+	unsigned long result = offset & ~(BITS_PER_LONG-1);
+	unsigned long tmp;
+
+	if (offset >= size)
+		return size;
+	size -= result;
+	offset %= BITS_PER_LONG;
+	if (offset) {
+		tmp = *(p++);
+		tmp |= ~0UL >> (BITS_PER_LONG - offset);
+		if (size < BITS_PER_LONG)
+			goto found_first;
+		if (~tmp)
+			goto found_middle;
+		size -= BITS_PER_LONG;
+		result += BITS_PER_LONG;
+	}
+	while (size & ~(BITS_PER_LONG-1)) {
+		if (~(tmp = *(p++)))
+			goto found_middle;
+		result += BITS_PER_LONG;
+		size -= BITS_PER_LONG;
+	}
+	if (!size)
+		return result;
+	tmp = *p;
+
+found_first:
+	tmp |= ~0UL << size;
+	if (tmp == ~0UL)	/* Are any bits zero? */
+		return result + size;	/* Nope. */
+found_middle:
+	return result + ffz(tmp);
+}
+EXPORT_SYMBOL(find_next_zero_bit);
+
+static inline unsigned int ext2_ilog2(unsigned int x)
+{
+	int lz;
+
+	asm("cntlzw %0,%1": "=r"(lz):"r"(x));
+	return 31 - lz;
+}
+
+static inline unsigned int ext2_ffz(unsigned int x)
+{
+	u32 rc;
+	if ((x = ~x) == 0)
+		return 32;
+	rc = ext2_ilog2(x & -x);
+	return rc;
+}
+
+unsigned long find_next_zero_le_bit(const unsigned long *addr,
+				    unsigned long size, unsigned long offset)
+{
+	const unsigned int *p = ((const unsigned int *)addr) + (offset >> 5);
+	unsigned int result = offset & ~31;
+	unsigned int tmp;
+
+	if (offset >= size)
+		return size;
+	size -= result;
+	offset &= 31;
+	if (offset) {
+		tmp = cpu_to_le32p(p++);
+		tmp |= ~0U >> (32 - offset);	/* bug or feature ? */
+		if (size < 32)
+			goto found_first;
+		if (tmp != ~0)
+			goto found_middle;
+		size -= 32;
+		result += 32;
+	}
+	while (size >= 32) {
+		if ((tmp = cpu_to_le32p(p++)) != ~0)
+			goto found_middle;
+		result += 32;
+		size -= 32;
+	}
+	if (!size)
+		return result;
+	tmp = cpu_to_le32p(p);
+found_first:
+	tmp |= ~0 << size;
+	if (tmp == ~0)		/* Are any bits zero? */
+		return result + size;	/* Nope. */
+found_middle:
+	return result + ext2_ffz(tmp);
+}
+EXPORT_SYMBOL(find_next_zero_le_bit);