Re: [Qemu-devel] [RFC PATCH] target-arm: protect cpu_exclusive_*.

[Peter Maydell]

On 17 December 2014 at 11:12, Mark Burton <address@hidden> wrote:
> We were not (yet) trying to fix that, we were simply asking the
> question, if we add these mutex’s - do we have any detrimental impact
> on anything.
> Seems like the answer is that adding the mutex’s is fine - it doesn’t
> seem to have a performance impact or anything. Good.

Personally I dislike the mutex approach because it means that every
target ends up with its own ad-hoc implementation of something that
would be better implemented in the QEMU core support (even if that
core support is simply taking mutexes in the end).

I also note that the linux-user code for handling exclusives does it
by having a region (effectively) where all other CPUs stop executing
*anything*. Do we need that?

PS: you'll find that we already have some ancient and half-broken
support code for the mutex approach (search for 'spinlock_t')...

-- PMM