[PATCH v8 8/8] Linux: Use rseq to accelerate getcpu

[DJ Delorie]

Michael Jeanson <mjeanson@efficios.com> writes:
> diff --git a/sysdeps/unix/sysv/linux/getcpu.c b/sysdeps/unix/sysv/linux/getcpu.c
> index 0e7c3238c9..7e34d6d1eb 100644
> --- a/sysdeps/unix/sysv/linux/getcpu.c
> +++ b/sysdeps/unix/sysv/linux/getcpu.c
> @@ -19,9 +19,10 @@
>  #include <sched.h>
>  #include <sysdep.h>
>  #include <sysdep-vdso.h>
> +#include <rseq-internal.h>
>  
> -int
> -__getcpu (unsigned int *cpu, unsigned int *node)
> +static int
> +vsyscall_getcpu (unsigned int *cpu, unsigned int *node)

Ok; this is the original function.  Any reason (other than "cleaner
diffs") to have this separate, and not just make it the #else clause
below?

Ah, it's called twice below.  Got it.  Ok.  Do we want to tag this as
always inline for the better CPU performance?

> @@ -29,5 +30,32 @@ __getcpu (unsigned int *cpu, unsigned int *node)

> +#if defined (RSEQ_SIG) && defined (RSEQ_HAS_LOAD32_LOAD32_RELAXED)
> +int
> +__getcpu (unsigned int *cpu, unsigned int *node)
> +{
> +  /* Check if rseq is registered and the node_id feature is available.  */
> +  if (__glibc_likely (rseq_node_id_available()))
> +  {
> +    struct rseq_area *rseq_area = rseq_get_area();
> +
> +    if (rseq_load32_load32_relaxed(cpu, &rseq_area->cpu_id,
> +                                   node, &rseq_area->node_id) == 0)
> +    {
> +      /* The critical section was not aborted, return 0.  */
> +      return 0;
> +    }
> +  }
> +
> +  return vsyscall_getcpu (cpu, node);
> +}
> +#else
> +int
> +__getcpu (unsigned int *cpu, unsigned int *node)
> +{
> +  return vsyscall_getcpu (cpu, node);
> +}
> +#endif
>  weak_alias (__getcpu, getcpu)
>  libc_hidden_def (__getcpu)

Ok.