Re: [PATCH 09/10] x86-32: use SSE for atomic64_read/set if available

[Peter Zijlstra <peterz@infradead.org>]

On Wed, 2010-02-17 at 12:42 +0100, Luca Barbieri wrote:
> +DEFINE_PER_CPU_ALIGNED(struct sse_atomic64_percpu, sse_atomic64_percpu);
> +
> +/* using the fpu/mmx looks infeasible due to the need to save the FPU environment, which is very slow
> + * SSE2 is slightly slower on Core 2 and less compatible, so avoid it for now
> + */
> +long long sse_atomic64_read_cx8call(long long dummy, const atomic64_t *v)
> +{
> +       long long res;
> +       unsigned long cr0 = 0;
> +       struct thread_info *me = current_thread_info();
> +       preempt_disable();
> +       if (!(me->status & TS_USEDFPU)) {
> +               cr0 = read_cr0();
> +               if (cr0 & X86_CR0_TS)
> +                       clts();
> +       }
> +       asm volatile(
> +                       "movlps %%xmm0, " __percpu_arg(0) "\n\t"
> +                       "movlps %3, %%xmm0\n\t"
> +                       "movlps %%xmm0, " __percpu_arg(1) "\n\t"
> +                       "movlps " __percpu_arg(0) ", %%xmm0\n\t"
> +                           : "+m" (per_cpu__sse_atomic64_percpu.xmm0_low), "=m" (per_cpu__sse_atomic64_percpu.low), "=m" (per_cpu__sse_atomic64_percpu.high)
> +                           : "m" (v->counter));
> +       if (cr0 & X86_CR0_TS)
> +               write_cr0(cr0);
> +       res = (long long)(unsigned)percpu_read(sse_atomic64_percpu.low) | ((long long)(unsigned)percpu_read(sse_atomic64_percpu.high) << 32);
> +       preempt_enable();
> +       return res;
> +}
> +EXPORT_SYMBOL(sse_atomic64_read_cx8call); 

Care to explain how this is IRQ and NMI safe?