x86, generic: optimize find_next_(zero_)bit for small constant-size bitmaps

This moves an optimization for searching constant-sized small
bitmaps form x86_64-specific to generic code.

On an i386 defconfig (the x86#testing one), the size of vmlinux hardly
changes with this applied. I have observed only four places where this
optimization avoids a call into find_next_bit:

In the functions return_unused_surplus_pages, alloc_fresh_huge_page,
and adjust_pool_surplus, this patch avoids a call for a 1-bit bitmap.
In __next_cpu a call is avoided for a 32-bit bitmap. That's it.

On x86_64, 52 locations are optimized with a minimal increase in
code size:

Current #testing defconfig:
	146 x bsf, 27 x find_next_*bit
   text    data     bss     dec     hex filename
   5392637  846592  724424 6963653  6a41c5 vmlinux

After removing the x86_64 specific optimization for find_next_*bit:
	94 x bsf, 79 x find_next_*bit
   text    data     bss     dec     hex filename
   5392358  846592  724424 6963374  6a40ae vmlinux

After this patch (making the optimization generic):
	146 x bsf, 27 x find_next_*bit
   text    data     bss     dec     hex filename
   5392396  846592  724424 6963412  6a40d4 vmlinux

[ tglx@linutronix.de: build fixes ]

Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 77 insertions, 0 deletions

diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 40d5473..3865f2c 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -112,4 +112,81 @@ static inline unsigned fls_long(unsigned long l)
 	return fls64(l);
 }
 
+#ifdef __KERNEL__
+#ifdef CONFIG_GENERIC_FIND_NEXT_BIT
+extern unsigned long __find_next_bit(const unsigned long *addr,
+		unsigned long size, unsigned long offset);
+
+/**
+ * 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 bitmap size in bits
+ */
+static __always_inline unsigned long
+find_next_bit(const unsigned long *addr, unsigned long size,
+		unsigned long offset)
+{
+	unsigned long value;
+
+	/* Avoid a function call if the bitmap size is a constant */
+	/* and not bigger than BITS_PER_LONG. */
+
+	/* insert a sentinel so that __ffs returns size if there */
+	/* are no set bits in the bitmap */
+	if (__builtin_constant_p(size) && (size < BITS_PER_LONG)) {
+		value = (*addr) & ((~0ul) << offset);
+		value |= (1ul << size);
+		return __ffs(value);
+	}
+
+	/* the result of __ffs(0) is undefined, so it needs to be */
+	/* handled separately */
+	if (__builtin_constant_p(size) && (size == BITS_PER_LONG)) {
+		value = (*addr) & ((~0ul) << offset);
+		return (value == 0) ? BITS_PER_LONG : __ffs(value);
+	}
+
+	/* size is not constant or too big */
+	return __find_next_bit(addr, size, offset);
+}
+
+extern unsigned long __find_next_zero_bit(const unsigned long *addr,
+		unsigned long size, unsigned long offset);
+
+/**
+ * find_next_zero_bit - find the next cleared bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The bitmap size in bits
+ */
+static __always_inline unsigned long
+find_next_zero_bit(const unsigned long *addr, unsigned long size,
+		unsigned long offset)
+{
+	unsigned long value;
+
+	/* Avoid a function call if the bitmap size is a constant */
+	/* and not bigger than BITS_PER_LONG. */
+
+	/* insert a sentinel so that __ffs returns size if there */
+	/* are no set bits in the bitmap */
+	if (__builtin_constant_p(size) && (size < BITS_PER_LONG)) {
+		value = (~(*addr)) & ((~0ul) << offset);
+		value |= (1ul << size);
+		return __ffs(value);
+	}
+
+	/* the result of __ffs(0) is undefined, so it needs to be */
+	/* handled separately */
+	if (__builtin_constant_p(size) && (size == BITS_PER_LONG)) {
+		value = (~(*addr)) & ((~0ul) << offset);
+		return (value == 0) ? BITS_PER_LONG : __ffs(value);
+	}
+
+	/* size is not constant or too big */
+	return __find_next_zero_bit(addr, size, offset);
+}
+#endif /* CONFIG_GENERIC_FIND_NEXT_BIT */
+#endif /* __KERNEL__ */
 #endif