Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of running thread

From: H. Peter Anvin
Date: Mon Feb 29 2016 - 13:21:25 EST

On February 29, 2016 4:41:49 AM PST, Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx> wrote:
>Agreed that many architectures issue slower instructions when reading
>from packed structures, which is unwanted.

And detrimental to atomicity.

>Could we require that each field be naturally aligned and require that
>they are placed so _no_ padding whatsoever should ever be added by the
>compiler ? If that's possible, then we could remove the packed.

What people have been trying to tell you is that we *must* do this, and no compiler truck like packed will help.

Sent from my Android device with K-9 Mail. Please excuse brevity and formatting.