On Mon, Mar 27, 2017 at 02:39:47PM +0200, Jesper Dangaard Brouer wrote:
>
> +static __always_inline int in_irq_or_nmi(void)
> +{
> + return in_irq() || in_nmi();
> +// XXX: hoping compiler will optimize this (todo verify) into:
> +// #define in_irq_or_nmi() (preempt_count() & (HARDIRQ_MASK | NMI_MASK))
> +
> + /* compiler was smart enough to only read __preempt_count once
> + * but added two branches
> +asm code:
> + │ mov __preempt_count,%eax
> + │ test $0xf0000,%eax // HARDIRQ_MASK: 0x000f0000
> + │ ┌──jne 2a
> + │ │ test $0x100000,%eax // NMI_MASK: 0x00100000
> + │ │↓ je 3f
> + │ 2a:└─→mov %rbx,%rdi
> +
> + */
> +}
To be fair, you told the compiler to do that with your use of fancy-pants ||
instead of optimisable |. Try this instead:
static __always_inline int in_irq_or_nmi(void)
{
return in_irq() | in_nmi();
}
0000000000001770 <test_fn>:
1770: 65 8b 05 00 00 00 00 mov %gs:0x0(%rip),%eax # 1777
<test_fn+0x7>
1773: R_X86_64_PC32 __preempt_count-0x4
#define in_nmi() (preempt_count() & NMI_MASK)
#define in_task() (!(preempt_count() & \
(NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))
static __always_inline int in_irq_or_nmi(void)
{
return in_irq() | in_nmi();
1777: 25 00 00 1f 00 and $0x1f0000,%eax
}
177c: c3 retq
177d: 0f 1f 00 nopl (%rax)
