Re: [Qemu-devel] [RFC PATCH V6 15/18] cpu: introduce tlb_flush*_all.

[Frederic Konrad]

On 26/06/2015 17:15, Paolo Bonzini wrote:
> On 26/06/2015 16:47, address@hidden wrote:
> > +    CPU_FOREACH(cpu) {
> > +        if (qemu_cpu_is_self(cpu)) {
> > +            /* async_run_on_cpu handle this case but this just avoid a malloc
> > +             * here.
> > +             */
> > +            tlb_flush(cpu, flush_global);
> > +        } else {
> > +            params = g_malloc(sizeof(struct TLBFlushParams));
> > +            params->cpu = cpu;
> > +            params->flush_global = flush_global;
> > +            async_run_on_cpu(cpu, tlb_flush_async_work, params);
> Shouldn't this be synchronous (which you cannot do straightforwardly
> because of deadlocks---hence the need to hook cpu_has_work as discussed
> earlier)?
>
> Paolo
I think it doesn't requires to be synchronous as each VCPUs only clear 
it's own
tlb here:

void tlb_flush(CPUState *cpu, int flush_global)
{
    CPUArchState *env = cpu->env_ptr;

#if defined(DEBUG_TLB)
    printf("tlb_flush:\n");
#endif
    /* must reset current TB so that interrupts cannot modify the
       links while we are modifying them */
    cpu->current_tb = NULL;

    memset(env->tlb_table, -1, sizeof(env->tlb_table));
    memset(env->tlb_v_table, -1, sizeof(env->tlb_v_table));
    memset(cpu->tb_jmp_cache, 0, sizeof(cpu->tb_jmp_cache));

    env->vtlb_index = 0;
    env->tlb_flush_addr = -1;
    env->tlb_flush_mask = 0;
    tlb_flush_count++;
}

So what happen is:
An arm instruction want to clear tlb of all VCPUs eg: IS version of TLBIALL.
The VCPU which execute the TLBIALL_IS can't flush tlb of other VCPU.
It will just ask all VCPU thread to exit and to do tlb_flush hence the 
async_work.

Maybe the big issue might be memory barrier instruction here which I didn't
checked.

Fred
> > +        }
> > +    }