Ocfs2 devel - May 2012 - [PATCH 01/10] string: introduce memweight

memweight() is the function that counts the total number of bits set
in memory area.  The memory area doesn't need to be aligned to
long-word boundary unlike bitmap_weight().

Signed-off-by: Akinobu Mita <akinobu.mita at gmail.com>
Cc: Anders Larsen <al at alarsen.net>
Cc: Alasdair Kergon <agk at redhat.com>
Cc: dm-devel at redhat.com
Cc: linux-fsdevel at vger.kernel.org
Cc: Laurent Pinchart <laurent.pinchart at ideasonboard.com>
Cc: linux-media at vger.kernel.org
Cc: Mark Fasheh <mfasheh at suse.com>
Cc: Joel Becker <jlbec at evilplan.org>
Cc: ocfs2-devel at oss.oracle.com
Cc: Jan Kara <jack at suse.cz>
Cc: linux-ext4 at vger.kernel.org
Cc: Andrew Morton <akpm at linux-foundation.org>
Cc: Andreas Dilger <adilger.kernel at dilger.ca>
Cc: "Theodore Ts'o" <tytso at mit.edu>
---
 include/linux/string.h |    3 +++
 lib/string.c           |   37 +++++++++++++++++++++++++++++++++++++
 2 files changed, 40 insertions(+), 0 deletions(-)

diff --git a/include/linux/string.h b/include/linux/string.h
index e033564..ffe0442 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -145,4 +145,7 @@ static inline bool strstarts(const char *str, const char
*prefix)
 	return strncmp(str, prefix, strlen(prefix)) == 0;
 }
 #endif
+
+extern size_t memweight(const void *ptr, size_t bytes);
+
 #endif /* _LINUX_STRING_H_ */
diff --git a/lib/string.c b/lib/string.c
index e5878de..c8b92a0 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -26,6 +26,7 @@
 #include <linux/export.h>
 #include <linux/bug.h>
 #include <linux/errno.h>
+#include <linux/bitmap.h>
 
 #ifndef __HAVE_ARCH_STRNICMP
 /**
@@ -824,3 +825,39 @@ void *memchr_inv(const void *start, int c, size_t bytes)
 	return check_bytes8(start, value, bytes % 8);
 }
 EXPORT_SYMBOL(memchr_inv);
+
+/**
+ * memweight - count the total number of bits set in memory area
+ * @ptr: pointer to the start of the area
+ * @bytes: the size of the area
+ */
+size_t memweight(const void *ptr, size_t bytes)
+{
+	size_t w = 0;
+	size_t longs;
+	union {
+		const void *ptr;
+		const unsigned char *b;
+		unsigned long address;
+	} bitmap;
+
+	for (bitmap.ptr = ptr; bytes > 0 && bitmap.address % sizeof(long);
+			bytes--, bitmap.address++)
+		w += hweight8(*bitmap.b);
+
+	for (longs = bytes / sizeof(long); longs > 0; ) {
+		size_t bits = min_t(size_t, INT_MAX & ~(BITS_PER_LONG - 1),
+					longs * BITS_PER_LONG);
+
+		w += bitmap_weight(bitmap.ptr, bits);
+		bytes -= bits / BITS_PER_BYTE;
+		bitmap.address += bits / BITS_PER_BYTE;
+		longs -= bits / BITS_PER_LONG;
+	}
+
+	for (; bytes > 0; bytes--, bitmap.address++)
+		w += hweight8(*bitmap.b);
+
+	return w;
+}
+EXPORT_SYMBOL(memweight);
-- 
1.7.7.6

Use memweight to count the total number of bits set in memory area.

Signed-off-by: Akinobu Mita <akinobu.mita at gmail.com>
Cc: Mark Fasheh <mfasheh at suse.com>
Cc: Joel Becker <jlbec at evilplan.org>
Cc: ocfs2-devel at oss.oracle.com
---
 fs/ocfs2/localalloc.c |    8 ++------
 1 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 210c352..a9f78c7 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -784,14 +784,10 @@ bail:
 
 static u32 ocfs2_local_alloc_count_bits(struct ocfs2_dinode *alloc)
 {
-	int i;
-	u8 *buffer;
-	u32 count = 0;
+	u32 count;
 	struct ocfs2_local_alloc *la = OCFS2_LOCAL_ALLOC(alloc);
 
-	buffer = la->la_bitmap;
-	for (i = 0; i < le16_to_cpu(la->la_size); i++)
-		count += hweight8(buffer[i]);
+	count = memweight(la->la_bitmap, le16_to_cpu(la->la_size));
 
 	trace_ocfs2_local_alloc_count_bits(count);
 	return count;
-- 
1.7.7.6

2012/5/23 Jan Kara <jack at suse.cz>:
> On Sun 20-05-12 22:23:14, Akinobu Mita wrote:
>> memweight() is the function that counts the total number of bits set
>> in memory area. ?The memory area doesn't need to be aligned to
>> long-word boundary unlike bitmap_weight().
> ?Thanks for the patch. I have some comments below.
Thanks for the review.
>> @@ -824,3 +825,39 @@ void *memchr_inv(const void *start, int c, size_t
bytes)
>> ? ? ? return check_bytes8(start, value, bytes % 8);
>> ?}
>> ?EXPORT_SYMBOL(memchr_inv);
>> +
>> +/**
>> + * memweight - count the total number of bits set in memory area
>> + * @ptr: pointer to the start of the area
>> + * @bytes: the size of the area
>> + */
>> +size_t memweight(const void *ptr, size_t bytes)
>> +{
>> + ? ? size_t w = 0;
>> + ? ? size_t longs;
>> + ? ? union {
>> + ? ? ? ? ? ? const void *ptr;
>> + ? ? ? ? ? ? const unsigned char *b;
>> + ? ? ? ? ? ? unsigned long address;
>> + ? ? } bitmap;
> ?Ugh, this is ugly and mostly unnecessary. Just use "const unsigned
char
> *bitmap".
>
>> +
>> + ? ? for (bitmap.ptr = ptr; bytes > 0 && bitmap.address %
sizeof(long);
>> + ? ? ? ? ? ? ? ? ? ? bytes--, bitmap.address++)
>> + ? ? ? ? ? ? w += hweight8(*bitmap.b);
> ?This can be:
> ? ? ? ?count = ((unsigned long)bitmap) % sizeof(long);
The count should be the size of unaligned area and it can be greater than
bytes. So

        count = min(bytes,
                    sizeof(long) - ((unsigned long)bitmap) % sizeof(long));
> ? ? ? ?while (count--) {
> ? ? ? ? ? ? ? ?w += hweight(*bitmap);
> ? ? ? ? ? ? ? ?bitmap++;
> ? ? ? ? ? ? ? ?bytes--;
> ? ? ? ?}
>> +
>> + ? ? for (longs = bytes / sizeof(long); longs > 0; ) {
>> + ? ? ? ? ? ? size_t bits = min_t(size_t, INT_MAX & ~(BITS_PER_LONG
- 1),
>> + ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? longs * BITS_PER_LONG);
> ?I find it highly unlikely that someone would have such a large bitmap
> (256 MB or more on 32-bit). Also the condition as you wrote it can just
> overflow so it won't have the desired effect. Just do
> ? ? ? ?BUG_ON(longs >= ULONG_MAX / BITS_PER_LONG);
The bits argument of bitmap_weight() is int type. So this should be

        BUG_ON(longs >= INT_MAX / BITS_PER_LONG);
> and remove the loop completely. If someone comes with such a huge bitmap,
> the code can be modified easily (after really closely inspecting whether
> such a huge bitmap is really well justified).
size_t memweight(const void *ptr, size_t bytes)
{
	size_t w = 0;
	size_t longs;
	const unsigned char *bitmap = ptr;

	for (; bytes > 0 && ((unsigned long)bitmap) % sizeof(long);
			bytes--, bitmap++)
		w += hweight8(*bitmap);

	longs = bytes / sizeof(long);
	BUG_ON(longs >= INT_MAX / BITS_PER_LONG);
	w += bitmap_weight((unsigned long *)bitmap, longs * BITS_PER_LONG);
	bytes -= longs * sizeof(long);
	bitmap += longs * sizeof(long);

	for (; bytes > 0; bytes--, bitmap++)
		w += hweight8(*bitmap);

	return w;
}

2012/5/23 Matthew Wilcox <matthew at wil.cx>:
> On Wed, May 23, 2012 at 09:12:18PM +0900, Akinobu Mita wrote:
>> size_t memweight(const void *ptr, size_t bytes)
>
> Why should this return size_t instead of unsigned long?
I just use the same type as the bytes argument without mature
consideration.  If unsigned long is better than size_t, I'll
change the return type.
>> {
>> ? ? ? size_t w = 0;
>> ? ? ? size_t longs;
>> ? ? ? const unsigned char *bitmap = ptr;
>>
>> ? ? ? for (; bytes > 0 && ((unsigned long)bitmap) %
sizeof(long);
>> ? ? ? ? ? ? ? ? ? ? ? bytes--, bitmap++)
>> ? ? ? ? ? ? ? w += hweight8(*bitmap);
>>
>> ? ? ? longs = bytes / sizeof(long);
>> ? ? ? BUG_ON(longs >= INT_MAX / BITS_PER_LONG);
>> ? ? ? w += bitmap_weight((unsigned long *)bitmap, longs *
BITS_PER_LONG);
>> ? ? ? bytes -= longs * sizeof(long);
>> ? ? ? bitmap += longs * sizeof(long);
>>
>> ? ? ? for (; bytes > 0; bytes--, bitmap++)
>> ? ? ? ? ? ? ? w += hweight8(*bitmap);
>>
>> ? ? ? return w;
>> }
>
> bitmap_weight copes with a bitmask that isn't a multiple of
BITS_PER_LONG
> in size already. ?So I think this can be done as:
>
> unsigned long memweight(const void *s, size_t n)
> {
> ? ? ? ?const unsigned char *ptr = s;
> ? ? ? ?unsigned long r = 0;
>
> ? ? ? ?while (n > 0 && (unsigned long)ptr % sizeof(long)) {
> ? ? ? ? ? ? ? ?r += hweight8(*ptr);
> ? ? ? ? ? ? ? ?n--;
> ? ? ? ? ? ? ? ?ptr++;
> ? ? ? ?}
>
> ? ? ? ?BUG_ON(n >= INT_MAX / 8)
>
> ? ? ? ?return r + bitmap_weight((unsigned long *)ptr, n * 8);
> }
This works perfectly on little-endian machines.  But it doesn't work
on big-endian machines, if the bottom edge of memory area is not
aligned on long word boundary.