s390/bitops: use generic find bit functions / reimplement _left variant

Just like all other architectures we should use out-of-line find bit
operations, since the inline variant bloat the size of the kernel image.
And also like all other architecures we should only supply optimized
variants of the __ffs, ffs, etc. primitives.

Therefore this patch removes the inlined s390 find bit functions and uses
the generic out-of-line variants instead.

The optimization of the primitives follows with the next patch.

With this patch also the functions find_first_bit_left() and
find_next_bit_left() have been reimplemented, since logically, they are
nothing else but a find_first_bit()/find_next_bit() implementation that
use an inverted __fls() instead of __ffs().
Also the restriction that these functions only work on machines which
support the "flogr" instruction is gone now.

This reduces the size of the kernel image (defconfig, -march=z9-109)
by 144,482 bytes.
Alone the size of the function build_sched_domains() gets reduced from
7 KB to 3,5 KB.

We also git rid of unused functions like find_first_bit_le()...

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

2 files changed, 78 insertions, 1 deletions

diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile
index 20b0e97a7df2..e506c5fb6f6a 100644
--- a/arch/s390/lib/Makefile
+++ b/arch/s390/lib/Makefile
@@ -2,7 +2,7 @@
 # Makefile for s390-specific library files..
 #
 
-lib-y += delay.o string.o uaccess_std.o uaccess_pt.o
+lib-y += delay.o string.o uaccess_std.o uaccess_pt.o find.o
 obj-$(CONFIG_32BIT) += div64.o qrnnd.o ucmpdi2.o mem32.o
 obj-$(CONFIG_64BIT) += mem64.o
 lib-$(CONFIG_64BIT) += uaccess_mvcos.o
diff --git a/arch/s390/lib/find.c b/arch/s390/lib/find.c
new file mode 100644
index 000000000000..8963929b06b9
--- /dev/null
+++ b/arch/s390/lib/find.c
@@ -0,0 +1,77 @@
+/*
+ * MSB0 numbered special bitops handling.
+ *
+ * On s390x the bits are numbered:
+ *   |0..............63|64............127|128...........191|192...........255|
+ * and on s390:
+ *   |0.....31|31....63|64....95|96...127|128..159|160..191|192..223|224..255|
+ *
+ * The reason for this bit numbering is the fact that the hardware sets bits
+ * in a bitmap starting at bit 0 (MSB) and we don't want to scan the bitmap
+ * from the 'wrong end'.
+ */
+
+#include <linux/compiler.h>
+#include <linux/bitops.h>
+#include <linux/export.h>
+
+unsigned long find_first_bit_left(const unsigned long *addr, unsigned long size)
+{
+	const unsigned long *p = addr;
+	unsigned long result = 0;
+	unsigned long tmp;
+
+	while (size & ~(BITS_PER_LONG - 1)) {
+		if ((tmp = *(p++)))
+			goto found;
+		result += BITS_PER_LONG;
+		size -= BITS_PER_LONG;
+	}
+	if (!size)
+		return result;
+	tmp = (*p) & (~0UL << (BITS_PER_LONG - size));
+	if (!tmp)		/* Are any bits set? */
+		return result + size;	/* Nope. */
+found:
+	return result + (__fls(tmp) ^ (BITS_PER_LONG - 1));
+}
+EXPORT_SYMBOL(find_first_bit_left);
+
+unsigned long find_next_bit_left(const unsigned long *addr, unsigned long size,
+				 unsigned long offset)
+{
+	const unsigned long *p = addr + (offset / BITS_PER_LONG);
+	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 << (BITS_PER_LONG - size));
+	if (!tmp)		/* Are any bits set? */
+		return result + size;	/* Nope. */
+found_middle:
+	return result + (__fls(tmp) ^ (BITS_PER_LONG - 1));
+}
+EXPORT_SYMBOL(find_next_bit_left);