On Tue, May 20, 2014 at 04:47:07PM +0200, Andreas Herrmann wrote:
> +static inline void r4k_blast_dcache_page_dc128(unsigned long addr)
> +{
> + R4600_HIT_CACHEOP_WAR_IMPL;
The R4600 has 32 byte cache lines that is this line will never be
executed on an R4600 thus can be dropped.
> + blast_dcache128_page(addr);
> +}
> +
> static void r4k_blast_dcache_page_setup(void)
> {
> unsigned long dc_lsize = cpu_dcache_line_size();
> @@ -121,6 +127,8 @@ static void r4k_blast_dcache_page_setup(void)
> r4k_blast_dcache_page = r4k_blast_dcache_page_dc32;
> else if (dc_lsize == 64)
> r4k_blast_dcache_page = r4k_blast_dcache_page_dc64;
> + else if (dc_lsize == 128)
> + r4k_blast_dcache_page = r4k_blast_dcache_page_dc128;
For another patch - let's see if this can be turned into a switch
construct which hopefully is more readable and produces just as
afficient code with reasonable vintage of gcc.
Ralf
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
