Dear Ralf and Sergei,
If we have L2 cache, then we need to invalidate them also ?
our system have L2 cache(write back).
Regards
On Mon, Jun 20, 2011 at 3:26 PM, Ralf Baechle <ralf@xxxxxxxxxxxxxx> wrote:
> On Sat, Jun 18, 2011 at 05:06:37PM +0400, Sergei Shtylyov wrote:
>
>> >+static inline void flush_kernel_vmap_range(void *vaddr, int size)
>> >+{
>> >+ if (cpu_has_dc_aliases)
>> >+ __flush_kernel_vmap_range((unsigned long) vaddr, size);
>> >+}
>> >+
>> >+static inline void invalidate_kernel_vmap_range(void *vaddr, int size)
>> >+{
>> >+ if (cpu_has_dc_aliases)
>> >+ __flush_kernel_vmap_range((unsigned long) vaddr, size);
>>
>> Not __invalidate_kernel_vmap_range()?
>
> No, for the moment both just do a writeback + invalidate. I may change
> that for something more efficient later once I understand the consequences
> of this.
>
> Ralf
>
