Re: [PATCH v2 5/6] x86/xen: Add a Xen-specific sync_core() implementation

[Linus Torvalds]

On Fri, Dec 2, 2016 at 12:41 PM, Andy Lutomirski <luto@xxxxxxxxxxxxxx> wrote:
>
> Because, if so, we should maybe serialize whenever we migrate a
> process to a different CPU.

The intel docs are bad on this issue.

Technically what we do could fall under the "cross-modifying code"
case, where one CPU does the write, and then we run it on another CPU.

And no, we do *not* do a serializing instruction before returning to
user space. Sure, we might do an iret (which is serializing), but we
equally well might be doing a systret (which is not).

Honestly, I think Intel should clean up their documentation.

> (We *definitely* need to flush the store  buffer when migrating,

There is no such thing as flushing the store buffer.

But we do end up doing a memory barrier which gives you the required
semantics. That's not a problem. Those operations are fast. The
serializing instructions are not.

               Linus