Re: [PATCH 02/17] bitops: Add generic parity calculation for u64

Hi Yury,

On Mon, Feb 24, 2025 at 02:27:03PM -0500, Yury Norov wrote:
> On Mon, Feb 24, 2025 at 12:42:02AM +0800, Kuan-Wei Chiu wrote:
> > Several parts of the kernel open-code parity calculations using
> > different methods. Add a generic parity64() helper implemented with the
> > same efficient approach as parity8().
> 
> No reason to add parity32() and parity64() in separate patches

Ack.

>  
> > Co-developed-by: Yu-Chun Lin <[email protected]>
> > Signed-off-by: Yu-Chun Lin <[email protected]>
> > Signed-off-by: Kuan-Wei Chiu <[email protected]>
> > ---
> >  include/linux/bitops.h | 22 ++++++++++++++++++++++
> >  1 file changed, 22 insertions(+)
> > 
> > diff --git a/include/linux/bitops.h b/include/linux/bitops.h
> > index fb13dedad7aa..67677057f5e2 100644
> > --- a/include/linux/bitops.h
> > +++ b/include/linux/bitops.h
> > @@ -281,6 +281,28 @@ static inline int parity32(u32 val)
> >  	return (0x6996 >> (val & 0xf)) & 1;
> >  }
> >  
> > +/**
> > + * parity64 - get the parity of an u64 value
> > + * @value: the value to be examined
> > + *
> > + * Determine the parity of the u64 argument.
> > + *
> > + * Returns:
> > + * 0 for even parity, 1 for odd parity
> > + */
> > +static inline int parity64(u64 val)
> > +{
> > +	/*
> > +	 * One explanation of this algorithm:
> > +	 * https://funloop.org/codex/problem/parity/README.html
> 
> This is already referenced in sources. No need to spread it for more.

Ack.

> 
> > +	 */
> > +	val ^= val >> 32;
> > +	val ^= val >> 16;
> > +	val ^= val >> 8;
> > +	val ^= val >> 4;
> > +	return (0x6996 >> (val & 0xf)) & 1;
> 
> It's better to avoid duplicating the same logic again and again.

Ack.

> 
> > +}
> > +
> 
> So maybe make it a macro?
> 
> 
> From f17a28ae3429f49825d65ebc0f7717c6a191a3e2 Mon Sep 17 00:00:00 2001
> From: Yury Norov <[email protected]>
> Date: Mon, 24 Feb 2025 14:14:27 -0500
> Subject: [PATCH] bitops: generalize parity8()
> 
> The generic parity calculation approach may be easily generalized for
> other standard types. Do that and drop sub-optimal implementation of
> parity calculation in x86 code.
> 
> Signed-off-by: Yury Norov [NVIDIA] <[email protected]>
> ---
>  arch/x86/kernel/bootflag.c | 14 +-----------
>  include/linux/bitops.h     | 47 +++++++++++++++++++++++++++-----------
>  2 files changed, 35 insertions(+), 26 deletions(-)
> 
> diff --git a/arch/x86/kernel/bootflag.c b/arch/x86/kernel/bootflag.c
> index 3fed7ae58b60..4a85c69a28f8 100644
> --- a/arch/x86/kernel/bootflag.c
> +++ b/arch/x86/kernel/bootflag.c
> @@ -2,6 +2,7 @@
>  /*
>   *	Implement 'Simple Boot Flag Specification 2.0'
>   */
> +#include <linux/bitops.h>
>  #include <linux/types.h>
>  #include <linux/kernel.h>
>  #include <linux/init.h>
> @@ -20,19 +21,6 @@
>  
>  int sbf_port __initdata = -1;	/* set via acpi_boot_init() */
>  
> -static int __init parity(u8 v)
> -{
> -	int x = 0;
> -	int i;
> -
> -	for (i = 0; i < 8; i++) {
> -		x ^= (v & 1);
> -		v >>= 1;
> -	}
> -
> -	return x;
> -}
> -
>  static void __init sbf_write(u8 v)
>  {
>  	unsigned long flags;
> diff --git a/include/linux/bitops.h b/include/linux/bitops.h
> index c1cb53cf2f0f..29601434f5f4 100644
> --- a/include/linux/bitops.h
> +++ b/include/linux/bitops.h
> @@ -230,10 +230,10 @@ static inline int get_count_order_long(unsigned long l)
>  }
>  
>  /**
> - * parity8 - get the parity of an u8 value
> + * parity - get the parity of a value
>   * @value: the value to be examined
>   *
> - * Determine the parity of the u8 argument.
> + * Determine parity of the argument.
>   *
>   * Returns:
>   * 0 for even parity, 1 for odd parity
> @@ -241,24 +241,45 @@ static inline int get_count_order_long(unsigned long l)
>   * Note: This function informs you about the current parity. Example to bail
>   * out when parity is odd:
>   *
> - *	if (parity8(val) == 1)
> + *	if (parity(val) == 1)
>   *		return -EBADMSG;
>   *
>   * If you need to calculate a parity bit, you need to draw the conclusion from
>   * this result yourself. Example to enforce odd parity, parity bit is bit 7:
>   *
> - *	if (parity8(val) == 0)
> + *	if (parity(val) == 0)
>   *		val ^= BIT(7);
> + *
> + * One explanation of this algorithm:
> + * https://funloop.org/codex/problem/parity/README.html
>   */
> -static inline int parity8(u8 val)
> -{
> -	/*
> -	 * One explanation of this algorithm:
> -	 * https://funloop.org/codex/problem/parity/README.html
> -	 */
> -	val ^= val >> 4;
> -	return (0x6996 >> (val & 0xf)) & 1;
> -}
> +#define parity(val)					\
> +({							\
> +	u64 __v = (val);				\
> +	int __ret;					\
> +	switch (BITS_PER_TYPE(val)) {			\
> +	case 64:					\
> +		__v ^= __v >> 32;			\
> +		fallthrough;				\
> +	case 32:					\
> +		__v ^= __v >> 16;			\
> +		fallthrough;				\
> +	case 16:					\
> +		__v ^= __v >> 8;			\
> +		fallthrough;				\
> +	case 8:						\
> +		__v ^= __v >> 4;			\
> +		__ret =  (0x6996 >> (__v & 0xf)) & 1;	\
> +		break;					\
> +	default:					\
> +		BUILD_BUG();				\
> +	}						\
> +	__ret;						\
> +})
> +
> +#define parity8(val)	parity((u8)(val))
> +#define parity32(val)	parity((u32)(val))
> +#define parity64(val)	parity((u64)(val))
>  
What do you think about using these inline functions instead of macros?
Except for parity8(), each function is a single line and follows the
same logic. I find inline functions more readable, and coding-style.rst
also recommends them over macros.

Regards,
Kuan-Wei

diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index c1cb53cf2f0f..d518a382f1fe 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -260,6 +260,26 @@ static inline int parity8(u8 val)
 	return (0x6996 >> (val & 0xf)) & 1;
 }
 
+static inline parity16(u16 val)
+{
+	return parity8(val ^ (val >> 8));
+}
+
+static inline parity16(u16 val)
+{
+	return parity8(val ^ (val >> 8));
+}
+
+static inline parity32(u32)
+{
+	return parity16(val ^ (val >> 16));
+}
+
+static inline parity64(u64)
+{
+	return parity32(val ^ (val >> 32));
+}
+
 /**
  * __ffs64 - find first set bit in a 64 bit word
  * @word: The 64 bit word


>  /**
>   * __ffs64 - find first set bit in a 64 bit word
> -- 
> 2.43.0
>