diff mbox series

[2/4] lib: add bitmap_{from,to}_arr64

Message ID 20220420222530.910125-3-yury.norov@gmail.com (mailing list archive)
State New, archived
Headers show
Series bitmap: fix conversion from/to fix-sized arrays | expand

Commit Message

Yury Norov April 20, 2022, 10:25 p.m. UTC
Manipulating 64-bit arrays with bitmap functions is potentially dangerous
because on 32-bit BE machines the order of halfwords doesn't match. Another
issue is that compiler may throw a warning about out-of-boundary access.

This patch adds bitmap_{from,to}_arr64 functions in addition to existing
bitmap_{from,to}_arr32.

Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
 include/linux/bitmap.h | 23 +++++++++++++++++----
 lib/bitmap.c           | 47 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 66 insertions(+), 4 deletions(-)

Comments

David Laight April 21, 2022, 7:40 a.m. UTC | #1
From: Yury Norov
> Sent: 20 April 2022 23:25
> 
> Manipulating 64-bit arrays with bitmap functions is potentially dangerous
> because on 32-bit BE machines the order of halfwords doesn't match. Another
> issue is that compiler may throw a warning about out-of-boundary access.
> 
> This patch adds bitmap_{from,to}_arr64 functions in addition to existing
> bitmap_{from,to}_arr32.
> 
> Signed-off-by: Yury Norov <yury.norov@gmail.com>
> ---
>  include/linux/bitmap.h | 23 +++++++++++++++++----
>  lib/bitmap.c           | 47 ++++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 66 insertions(+), 4 deletions(-)
> 
> diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
> index 10d805c2893c..f78c534fb814 100644
> --- a/include/linux/bitmap.h
> +++ b/include/linux/bitmap.h
> @@ -292,6 +292,24 @@ void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap,
>  			(const unsigned long *) (bitmap), (nbits))
>  #endif
> 
> +/*
> + * On 64-bit systems bitmaps are represented as u64 arrays internally. On LE32
> + * machines the order of hi and lo parts of nubmers match the bitmap structure.
> + * In both cases conversion is not needed when copying data from/to arrays of
> + * u64.
> + */
> +#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN)

I think I'd change the condition to (inverting it):
#if (BITS_PER_LONG == 64) || defined(__LITTLE_ENDIAN)
since that is the condition when the layout matches.

> +void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits);
> +void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits);
> +#else
> +#define bitmap_from_arr64(bitmap, buf, nbits)			\
> +	bitmap_copy_clear_tail((unsigned long *) (bitmap),	\
> +			(const unsigned long *) (buf), (nbits))
> +#define bitmap_to_arr64(buf, bitmap, nbits)			\
> +	bitmap_copy_clear_tail((unsigned long *) (buf),		\
> +			(const unsigned long *) (bitmap), (nbits))
> +#endif
> +
>  static inline int bitmap_and(unsigned long *dst, const unsigned long *src1,
>  			const unsigned long *src2, unsigned int nbits)
>  {
> @@ -596,10 +614,7 @@ static inline void bitmap_next_set_region(unsigned long *bitmap,
>   */
>  static inline void bitmap_from_u64(unsigned long *dst, u64 mask)
>  {
> -	dst[0] = mask & ULONG_MAX;
> -
> -	if (sizeof(mask) > sizeof(unsigned long))
> -		dst[1] = mask >> 32;
> +	bitmap_from_arr64(dst, &mask, 64);
>  }

I'd leave this alone.

> 
>  /**
> diff --git a/lib/bitmap.c b/lib/bitmap.c
> index d9a4480af5b9..aea9493f4216 100644
> --- a/lib/bitmap.c
> +++ b/lib/bitmap.c
> @@ -1533,5 +1533,52 @@ void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, unsigned int nbits)
>  		buf[halfwords - 1] &= (u32) (UINT_MAX >> ((-nbits) & 31));
>  }
>  EXPORT_SYMBOL(bitmap_to_arr32);
> +#endif
> +
> +#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN)
> +/**
> + * bitmap_from_arr64 - copy the contents of u64 array of bits to bitmap
> + *	@bitmap: array of unsigned longs, the destination bitmap
> + *	@buf: array of u64 (in host byte order), the source bitmap
> + *	@nbits: number of bits in @bitmap
> + */
> +void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits)
> +{
> +	while (nbits > 0) {

This looks like a for look to me...

> +		u64 val = *buf++;
> +
> +		*bitmap++ = (unsigned long)val;
> +		if (nbits > 32)
> +			*bitmap++ = (unsigned long)(val >> 32);

No need for either cast.

> +		nbits -= 64;
> +	}
> 
> +	/* Clear tail bits in last word beyond nbits. */
> +	if (nbits % BITS_PER_LONG)
> +		bitmap[-1] &= BITMAP_LAST_WORD_MASK(nbits);
> +}
> +EXPORT_SYMBOL(bitmap_from_arr64);
> +
> +/**
> + * bitmap_to_arr64 - copy the contents of bitmap to a u64 array of bits
> + *	@buf: array of u64 (in host byte order), the dest bitmap
> + *	@bitmap: array of unsigned longs, the source bitmap
> + *	@nbits: number of bits in @bitmap
> + */
> +void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits)
> +{
> +	unsigned long *end = bitmap + BITS_TO_LONGS(nbits);
> +
> +	while (bitmap < end) {

Another for loop...

> +		*buf = *bitmap++;
> +		if (bitmap < end)
> +			*buf |= *bitmap++ << 32;

That is UB.
Did you even compile this??

	David

> +		buf++;
> +	}
> +
> +	/* Clear tail bits in last element of array beyond nbits. */
> +	if (nbits % 64)
> +		buf[-1] &= GENMASK_ULL(nbits, 0);
> +}
> +EXPORT_SYMBOL(bitmap_to_arr64);
>  #endif
> --
> 2.32.0

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)
Yury Norov April 21, 2022, 4:31 p.m. UTC | #2
On Thu, Apr 21, 2022 at 07:40:25AM +0000, David Laight wrote:
> From: Yury Norov
> > Sent: 20 April 2022 23:25
> > 
> > Manipulating 64-bit arrays with bitmap functions is potentially dangerous
> > because on 32-bit BE machines the order of halfwords doesn't match. Another
> > issue is that compiler may throw a warning about out-of-boundary access.
> > 
> > This patch adds bitmap_{from,to}_arr64 functions in addition to existing
> > bitmap_{from,to}_arr32.
> > 
> > Signed-off-by: Yury Norov <yury.norov@gmail.com>
> > ---
> >  include/linux/bitmap.h | 23 +++++++++++++++++----
> >  lib/bitmap.c           | 47 ++++++++++++++++++++++++++++++++++++++++++
> >  2 files changed, 66 insertions(+), 4 deletions(-)
> > 
> > diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
> > index 10d805c2893c..f78c534fb814 100644
> > --- a/include/linux/bitmap.h
> > +++ b/include/linux/bitmap.h
> > @@ -292,6 +292,24 @@ void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap,
> >  			(const unsigned long *) (bitmap), (nbits))
> >  #endif
> > 
> > +/*
> > + * On 64-bit systems bitmaps are represented as u64 arrays internally. On LE32
> > + * machines the order of hi and lo parts of nubmers match the bitmap structure.
> > + * In both cases conversion is not needed when copying data from/to arrays of
> > + * u64.
> > + */
> > +#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN)
> 
> I think I'd change the condition to (inverting it):
> #if (BITS_PER_LONG == 64) || defined(__LITTLE_ENDIAN)
> since that is the condition when the layout matches.

Sorry, I don't understand about 'layout matches'. Why this way is
better than another?
 
> > +void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits);
> > +void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits);
> > +#else
> > +#define bitmap_from_arr64(bitmap, buf, nbits)			\
> > +	bitmap_copy_clear_tail((unsigned long *) (bitmap),	\
> > +			(const unsigned long *) (buf), (nbits))
> > +#define bitmap_to_arr64(buf, bitmap, nbits)			\
> > +	bitmap_copy_clear_tail((unsigned long *) (buf),		\
> > +			(const unsigned long *) (bitmap), (nbits))
> > +#endif
> > +
> >  static inline int bitmap_and(unsigned long *dst, const unsigned long *src1,
> >  			const unsigned long *src2, unsigned int nbits)
> >  {
> > @@ -596,10 +614,7 @@ static inline void bitmap_next_set_region(unsigned long *bitmap,
> >   */
> >  static inline void bitmap_from_u64(unsigned long *dst, u64 mask)
> >  {
> > -	dst[0] = mask & ULONG_MAX;
> > -
> > -	if (sizeof(mask) > sizeof(unsigned long))
> > -		dst[1] = mask >> 32;
> > +	bitmap_from_arr64(dst, &mask, 64);
> >  }
> 
> I'd leave this alone.
 
I'd change it in sake of consistency. Let's see what others say.

> >  /**
> > diff --git a/lib/bitmap.c b/lib/bitmap.c
> > index d9a4480af5b9..aea9493f4216 100644
> > --- a/lib/bitmap.c
> > +++ b/lib/bitmap.c
> > @@ -1533,5 +1533,52 @@ void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, unsigned int nbits)
> >  		buf[halfwords - 1] &= (u32) (UINT_MAX >> ((-nbits) & 31));
> >  }
> >  EXPORT_SYMBOL(bitmap_to_arr32);
> > +#endif
> > +
> > +#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN)
> > +/**
> > + * bitmap_from_arr64 - copy the contents of u64 array of bits to bitmap
> > + *	@bitmap: array of unsigned longs, the destination bitmap
> > + *	@buf: array of u64 (in host byte order), the source bitmap
> > + *	@nbits: number of bits in @bitmap
> > + */
> > +void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits)
> > +{
> > +	while (nbits > 0) {
> 
> This looks like a for look to me...

Can you explain why for() is better then while() here? Is generated
code better, or something else?

> > +		u64 val = *buf++;
> > +
> > +		*bitmap++ = (unsigned long)val;
> > +		if (nbits > 32)
> > +			*bitmap++ = (unsigned long)(val >> 32);
> 
> No need for either cast.

Yep, thanks.

> > +		nbits -= 64;
> > +	}
> > 
> > +	/* Clear tail bits in last word beyond nbits. */
> > +	if (nbits % BITS_PER_LONG)
> > +		bitmap[-1] &= BITMAP_LAST_WORD_MASK(nbits);
> > +}
> > +EXPORT_SYMBOL(bitmap_from_arr64);
> > +
> > +/**
> > + * bitmap_to_arr64 - copy the contents of bitmap to a u64 array of bits
> > + *	@buf: array of u64 (in host byte order), the dest bitmap
> > + *	@bitmap: array of unsigned longs, the source bitmap
> > + *	@nbits: number of bits in @bitmap
> > + */
> > +void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits)
> > +{
> > +	unsigned long *end = bitmap + BITS_TO_LONGS(nbits);

This should be const unsigned long.

> > +
> > +	while (bitmap < end) {
> 
> Another for loop...
> 
> > +		*buf = *bitmap++;
> > +		if (bitmap < end)
> > +			*buf |= *bitmap++ << 32;
> 
> That is UB.

It's -Wshift-count-overflow. Should be
        *buf |= (u64)(*bitmap++) << 32;

> Did you even compile this??

Yes. That's it, my BE32 platform is arm, and I had to disable CONFIG_WERROR
because arm breaks build with that, and forgot about it. :(

I boot-tested it on mips with the fix above with no issues.
 
> 	David
> 
> > +		buf++;
> > +	}
> > +
> > +	/* Clear tail bits in last element of array beyond nbits. */
> > +	if (nbits % 64)
> > +		buf[-1] &= GENMASK_ULL(nbits, 0);
> > +}
> > +EXPORT_SYMBOL(bitmap_to_arr64);
> >  #endif
> > --
> > 2.32.0
> 
> -
> Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
> Registration No: 1397386 (Wales)
diff mbox series

Patch

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 10d805c2893c..f78c534fb814 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -292,6 +292,24 @@  void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap,
 			(const unsigned long *) (bitmap), (nbits))
 #endif
 
+/*
+ * On 64-bit systems bitmaps are represented as u64 arrays internally. On LE32
+ * machines the order of hi and lo parts of nubmers match the bitmap structure.
+ * In both cases conversion is not needed when copying data from/to arrays of
+ * u64.
+ */
+#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN)
+void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits);
+void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits);
+#else
+#define bitmap_from_arr64(bitmap, buf, nbits)			\
+	bitmap_copy_clear_tail((unsigned long *) (bitmap),	\
+			(const unsigned long *) (buf), (nbits))
+#define bitmap_to_arr64(buf, bitmap, nbits)			\
+	bitmap_copy_clear_tail((unsigned long *) (buf),		\
+			(const unsigned long *) (bitmap), (nbits))
+#endif
+
 static inline int bitmap_and(unsigned long *dst, const unsigned long *src1,
 			const unsigned long *src2, unsigned int nbits)
 {
@@ -596,10 +614,7 @@  static inline void bitmap_next_set_region(unsigned long *bitmap,
  */
 static inline void bitmap_from_u64(unsigned long *dst, u64 mask)
 {
-	dst[0] = mask & ULONG_MAX;
-
-	if (sizeof(mask) > sizeof(unsigned long))
-		dst[1] = mask >> 32;
+	bitmap_from_arr64(dst, &mask, 64);
 }
 
 /**
diff --git a/lib/bitmap.c b/lib/bitmap.c
index d9a4480af5b9..aea9493f4216 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -1533,5 +1533,52 @@  void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, unsigned int nbits)
 		buf[halfwords - 1] &= (u32) (UINT_MAX >> ((-nbits) & 31));
 }
 EXPORT_SYMBOL(bitmap_to_arr32);
+#endif
+
+#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN)
+/**
+ * bitmap_from_arr64 - copy the contents of u64 array of bits to bitmap
+ *	@bitmap: array of unsigned longs, the destination bitmap
+ *	@buf: array of u64 (in host byte order), the source bitmap
+ *	@nbits: number of bits in @bitmap
+ */
+void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits)
+{
+	while (nbits > 0) {
+		u64 val = *buf++;
+
+		*bitmap++ = (unsigned long)val;
+		if (nbits > 32)
+			*bitmap++ = (unsigned long)(val >> 32);
+		nbits -= 64;
+	}
 
+	/* Clear tail bits in last word beyond nbits. */
+	if (nbits % BITS_PER_LONG)
+		bitmap[-1] &= BITMAP_LAST_WORD_MASK(nbits);
+}
+EXPORT_SYMBOL(bitmap_from_arr64);
+
+/**
+ * bitmap_to_arr64 - copy the contents of bitmap to a u64 array of bits
+ *	@buf: array of u64 (in host byte order), the dest bitmap
+ *	@bitmap: array of unsigned longs, the source bitmap
+ *	@nbits: number of bits in @bitmap
+ */
+void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits)
+{
+	unsigned long *end = bitmap + BITS_TO_LONGS(nbits);
+
+	while (bitmap < end) {
+		*buf = *bitmap++;
+		if (bitmap < end)
+			*buf |= *bitmap++ << 32;
+		buf++;
+	}
+
+	/* Clear tail bits in last element of array beyond nbits. */
+	if (nbits % 64)
+		buf[-1] &= GENMASK_ULL(nbits, 0);
+}
+EXPORT_SYMBOL(bitmap_to_arr64);
 #endif