On 22/09/2023 10:04, Johannes Berg wrote:
On Fri, 2023-09-22 at 10:43 +0200, Johannes Berg wrote:
I think this has pretty much always been wrong, just now we actually
notice it?
Basically, when we create a new thread (really just mm I think), we say
the first thing that has to run there is fork_handler(), which
initialises things the first time around. This calls force_flush_all()
So I thought we could perhaps just force_flush_all() the new mm in
init_new_context(), but that segfaults userspace immediately.
Been there done that.
So I need to fully understand first (again?) why we even need
force_flush_all() at this spot, but probably not today.
No idea, but it does not seem to work without it. This is actually
the biggest performance bugbear in UML. If this is fixed, the
performance will go reasonably close to native.
johannes
_______________________________________________
linux-um mailing list
linux-um@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-um
--
Anton R. Ivanov
Cambridgegreys Limited. Registered in England. Company Number 10273661
https://www.cambridgegreys.com/
_______________________________________________
linux-um mailing list
linux-um@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-um
