Re: [PATCH 2/2] The new jhash implementation

[Eric Dumazet]

Le jeudi 25 novembre 2010 Ã 15:41 +0100, Jozsef Kadlecsik a Ãcrit :

...

> +/* __jhash_mix -- mix 3 32-bit values reversibly. */
> +#define __jhash_mix(a, b, c)			\
> +{						\
> +	a -= c;  a ^= rol32(c, 4);  c += b;	\
> +	b -= a;  b ^= rol32(a, 6);  a += c;	\
> +	c -= b;  c ^= rol32(b, 8);  b += a;	\
> +	a -= c;  a ^= rol32(c, 16); c += b;	\
> +	b -= a;  b ^= rol32(a, 19); a += c;	\
> +	c -= b;  c ^= rol32(b, 4);  b += a;	\
> +}
> +
> +/* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */
> +#define __jhash_final(a, b, c)			\
> +{						\
> +	c ^= b; c -= rol32(b, 14);		\
> +	a ^= c; a -= rol32(c, 11);		\
> +	b ^= a; b -= rol32(a, 25);		\
> +	c ^= b; c -= rol32(b, 16);		\
> +	a ^= c; a -= rol32(c, 4);		\
> +	b ^= a; b -= rol32(a, 14);		\
> +	c ^= b; c -= rol32(b, 24);		\
> +}
> +

So we now have a special __jhash_final(a, b, c) thing for the last
values.



> +/* jhash_3words - hash exactly 3, 2 or 1 word(s) */
> +u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval)
> +{
> +	a += JHASH_INITVAL;
> +	b += JHASH_INITVAL;
> +	c += initval;
> +
> +	__jhash_mix(a, b, c);
> +
> +	return c;
> +}
> +EXPORT_SYMBOL(jhash_3words);


But you dont use it in jhash_3words().


I do think jhash_3words() should stay inlined, unless maybe
CONFIG_CC_OPTIMIZE_FOR_SIZE=y

We hit it several time per packet in network stack in RX path.

Once in skb_get_rxhash() (unless device fills skb->rxhash)
Once at least in conntrack (if used).
Once in UDP or TCP stack



--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/