[PATCH] cpumask: bitmap inlining and optimizations

From: Paul Jackson <pj@sgi.com>

These bitmap improvements make it a suitable basis for fully supporting
cpumask_t and nodemask_t.  Inline macros with compile-time checks enable
generating tight code on both small and large systems (large meaning cpumask_t
requires more than one unsigned long's worth of bits).

The existing bitmap_<op> macros in lib/bitmap.c are renamed to __bitmap_<op>,
and wrappers for each bitmap_<op> are exposed in include/linux/bitmap.h

This patch _includes_ Bill Irwins rewrite of the bitmap_shift operators to not
require a fixed length intermediate bitmap.

Improved comments list each available operator for easy browsing.

Signed-off-by: Paul Jackson <pj@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 228 insertions, 36 deletions

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index bc93e0167a81..9dadd08e2b53 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -3,57 +3,249 @@
 
 #ifndef __ASSEMBLY__
 
-#include <linux/config.h>
-#include <linux/compiler.h>
 #include <linux/types.h>
-#include <linux/kernel.h>
 #include <linux/bitops.h>
 #include <linux/string.h>
 
-int bitmap_empty(const unsigned long *bitmap, int bits);
-int bitmap_full(const unsigned long *bitmap, int bits);
-int bitmap_equal(const unsigned long *bitmap1,
+/*
+ * bitmaps provide bit arrays that consume one or more unsigned
+ * longs.  The bitmap interface and available operations are listed
+ * here, in bitmap.h
+ *
+ * Function implementations generic to all architectures are in
+ * lib/bitmap.c.  Functions implementations that are architecture
+ * specific are in various include/asm-<arch>/bitops.h headers
+ * and other arch/<arch> specific files.
+ *
+ * See lib/bitmap.c for more details.
+ */
+
+/*
+ * The available bitmap operations and their rough meaning in the
+ * case that the bitmap is a single unsigned long are thus:
+ *
+ * bitmap_zero(dst, nbits)			*dst = 0UL
+ * bitmap_fill(dst, nbits)			*dst = ~0UL
+ * bitmap_copy(dst, src, nbits)			*dst = *src
+ * bitmap_and(dst, src1, src2, nbits)		*dst = *src1 & *src2
+ * bitmap_or(dst, src1, src2, nbits)		*dst = *src1 | *src2
+ * bitmap_xor(dst, src1, src2, nbits)		*dst = *src1 ^ *src2
+ * bitmap_andnot(dst, src1, src2, nbits)	*dst = *src1 & ~(*src2)
+ * bitmap_complement(dst, src, nbits)		*dst = ~(*src)
+ * bitmap_equal(src1, src2, nbits)		Are *src1 and *src2 equal?
+ * bitmap_intersects(src1, src2, nbits) 	Do *src1 and *src2 overlap?
+ * bitmap_subset(src1, src2, nbits)		Is *src1 a subset of *src2?
+ * bitmap_empty(src, nbits)			Are all bits zero in *src?
+ * bitmap_full(src, nbits)			Are all bits set in *src?
+ * bitmap_weight(src, nbits)			Hamming Weight: number set bits
+ * bitmap_shift_right(dst, src, n, nbits)	*dst = *src >> n
+ * bitmap_shift_left(dst, src, n, nbits)	*dst = *src << n
+ * bitmap_scnprintf(buf, len, src, nbits)	Print bitmap src to buf
+ * bitmap_parse(ubuf, ulen, dst, nbits)		Parse bitmap dst from buf
+ */
+
+/*
+ * Also the following operations in asm/bitops.h apply to bitmaps.
+ *
+ * set_bit(bit, addr)			*addr |= bit
+ * clear_bit(bit, addr)			*addr &= ~bit
+ * change_bit(bit, addr)		*addr ^= bit
+ * test_bit(bit, addr)			Is bit set in *addr?
+ * test_and_set_bit(bit, addr)		Set bit and return old value
+ * test_and_clear_bit(bit, addr)	Clear bit and return old value
+ * test_and_change_bit(bit, addr)	Change bit and return old value
+ * find_first_zero_bit(addr, nbits)	Position first zero bit in *addr
+ * find_first_bit(addr, nbits)		Position first set bit in *addr
+ * find_next_zero_bit(addr, nbits, bit)	Position next zero bit in *addr >= bit
+ * find_next_bit(addr, nbits, bit)	Position next set bit in *addr >= bit
+ */
+
+/*
+ * The DECLARE_BITMAP(name,bits) macro, in linux/types.h, can be used
+ * to declare an array named 'name' of just enough unsigned longs to
+ * contain all bit positions from 0 to 'bits' - 1.
+ */
+
+/*
+ * lib/bitmap.c provides these functions:
+ */
+
+extern int __bitmap_empty(const unsigned long *bitmap, int bits);
+extern int __bitmap_full(const unsigned long *bitmap, int bits);
+extern int __bitmap_equal(const unsigned long *bitmap1,
+                	const unsigned long *bitmap2, int bits);
+extern void __bitmap_complement(unsigned long *dst, const unsigned long *src,
+			int bits);
+extern void __bitmap_shift_right(unsigned long *dst,
+                        const unsigned long *src, int shift, int bits);
+extern void __bitmap_shift_left(unsigned long *dst,
+                        const unsigned long *src, int shift, int bits);
+extern void __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
+			const unsigned long *bitmap2, int bits);
+extern void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
+			const unsigned long *bitmap2, int bits);
+extern void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
 			const unsigned long *bitmap2, int bits);
-void bitmap_complement(unsigned long *dst, const unsigned long *src, int bits);
+extern void __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
+			const unsigned long *bitmap2, int bits);
+extern int __bitmap_intersects(const unsigned long *bitmap1,
+			const unsigned long *bitmap2, int bits);
+extern int __bitmap_subset(const unsigned long *bitmap1,
+			const unsigned long *bitmap2, int bits);
+extern int __bitmap_weight(const unsigned long *bitmap, int bits);
+
+extern int bitmap_scnprintf(char *buf, unsigned int len,
+			const unsigned long *src, int nbits);
+extern int bitmap_parse(const char __user *ubuf, unsigned int ulen,
+			unsigned long *dst, int nbits);
 
-static inline void bitmap_zero(unsigned long *bitmap, int bits)
+#define BITMAP_LAST_WORD_MASK(nbits)					\
+(									\
+	((nbits) % BITS_PER_LONG) ?					\
+		(1UL<<((nbits) % BITS_PER_LONG))-1 : ~0UL		\
+)
+
+static inline void bitmap_zero(unsigned long *dst, int nbits)
 {
-	memset(bitmap, 0, BITS_TO_LONGS(bits)*sizeof(unsigned long));
+	if (nbits <= BITS_PER_LONG)
+		*dst = 0UL;
+	else {
+		int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+		memset(dst, 0, len);
+	}
 }
 
-static inline void bitmap_fill(unsigned long *bitmap, int bits)
+static inline void bitmap_fill(unsigned long *dst, int nbits)
 {
-	memset(bitmap, 0xff, BITS_TO_LONGS(bits)*sizeof(unsigned long));
+	size_t nlongs = BITS_TO_LONGS(nbits);
+	if (nlongs > 1) {
+		int len = (nlongs - 1) * sizeof(unsigned long);
+		memset(dst, 0xff,  len);
+	}
+	dst[nlongs - 1] = BITMAP_LAST_WORD_MASK(nbits);
 }
 
-static inline void bitmap_copy(unsigned long *dst,
-			const unsigned long *src, int bits)
+static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
+			int nbits)
 {
-	int len = BITS_TO_LONGS(bits)*sizeof(unsigned long);
-	memcpy(dst, src, len);
+	if (nbits <= BITS_PER_LONG)
+		*dst = *src;
+	else {
+		int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+		memcpy(dst, src, len);
+	}
 }
 
-void bitmap_shift_right(unsigned long *dst,
-			const unsigned long *src, int shift, int bits);
-void bitmap_shift_left(unsigned long *dst,
-			const unsigned long *src, int shift, int bits);
-void bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
-			const unsigned long *bitmap2, int bits);
-void bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
-			const unsigned long *bitmap2, int bits);
-void bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
-			const unsigned long *bitmap2, int bits);
-void bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
-			const unsigned long *bitmap2, int bits);
-int bitmap_intersects(const unsigned long *bitmap1,
-			const unsigned long *bitmap2, int bits);
-int bitmap_subset(const unsigned long *bitmap1,
-			const unsigned long *bitmap2, int bits);
-int bitmap_weight(const unsigned long *bitmap, int bits);
-int bitmap_scnprintf(char *buf, unsigned int buflen,
-			const unsigned long *maskp, int bits);
-int bitmap_parse(const char __user *ubuf, unsigned int ubuflen,
-			unsigned long *maskp, int bits);
+static inline void bitmap_and(unsigned long *dst, const unsigned long *src1,
+			const unsigned long *src2, int nbits)
+{
+	if (nbits <= BITS_PER_LONG)
+		*dst = *src1 & *src2;
+	else
+		__bitmap_and(dst, src1, src2, nbits);
+}
+
+static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
+			const unsigned long *src2, int nbits)
+{
+	if (nbits <= BITS_PER_LONG)
+		*dst = *src1 | *src2;
+	else
+		__bitmap_or(dst, src1, src2, nbits);
+}
+
+static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1,
+			const unsigned long *src2, int nbits)
+{
+	if (nbits <= BITS_PER_LONG)
+		*dst = *src1 ^ *src2;
+	else
+		__bitmap_xor(dst, src1, src2, nbits);
+}
+
+static inline void bitmap_andnot(unsigned long *dst, const unsigned long *src1,
+			const unsigned long *src2, int nbits)
+{
+	if (nbits <= BITS_PER_LONG)
+		*dst = *src1 & ~(*src2);
+	else
+		__bitmap_andnot(dst, src1, src2, nbits);
+}
+
+static inline void bitmap_complement(unsigned long *dst, const unsigned long *src,
+			int nbits)
+{
+	if (nbits <= BITS_PER_LONG)
+		*dst = ~(*src) & BITMAP_LAST_WORD_MASK(nbits);
+	else
+		__bitmap_complement(dst, src, nbits);
+}
+
+static inline int bitmap_equal(const unsigned long *src1,
+			const unsigned long *src2, int nbits)
+{
+	if (nbits <= BITS_PER_LONG)
+		return ! ((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits));
+	else
+		return __bitmap_equal(src1, src2, nbits);
+}
+
+static inline int bitmap_intersects(const unsigned long *src1,
+			const unsigned long *src2, int nbits)
+{
+	if (nbits <= BITS_PER_LONG)
+		return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
+	else
+		return __bitmap_intersects(src1, src2, nbits);
+}
+
+static inline int bitmap_subset(const unsigned long *src1,
+			const unsigned long *src2, int nbits)
+{
+	if (nbits <= BITS_PER_LONG)
+		return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits));
+	else
+		return __bitmap_subset(src1, src2, nbits);
+}
+
+static inline int bitmap_empty(const unsigned long *src, int nbits)
+{
+	if (nbits <= BITS_PER_LONG)
+		return ! (*src & BITMAP_LAST_WORD_MASK(nbits));
+	else
+		return __bitmap_empty(src, nbits);
+}
+
+static inline int bitmap_full(const unsigned long *src, int nbits)
+{
+	if (nbits <= BITS_PER_LONG)
+		return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits));
+	else
+		return __bitmap_full(src, nbits);
+}
+
+static inline int bitmap_weight(const unsigned long *src, int nbits)
+{
+	return __bitmap_weight(src, nbits);
+}
+
+static inline void bitmap_shift_right(unsigned long *dst,
+			const unsigned long *src, int n, int nbits)
+{
+	if (nbits <= BITS_PER_LONG)
+		*dst = *src >> n;
+	else
+		__bitmap_shift_right(dst, src, n, nbits);
+}
+
+static inline void bitmap_shift_left(unsigned long *dst,
+			const unsigned long *src, int n, int nbits)
+{
+	if (nbits <= BITS_PER_LONG)
+		*dst = (*src << n) & BITMAP_LAST_WORD_MASK(nbits);
+	else
+		__bitmap_shift_left(dst, src, n, nbits);
+}
 
 #endif /* __ASSEMBLY__ */