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

[Andy Lutomirski]

On Fri, Dec 2, 2016 at 1:10 PM, Linus Torvalds
<torvalds@xxxxxxxxxxxxxxxxxxxx> wrote:
> 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.
>

I'm not sure I follow.  If a user program gets migrated, it might end
up doing cross-modification when it expects self-modification.  If
that trips the program up, is that a user bug or a kernel bug?

Admittedly, I'd be very surprised if this happened in practice.
Migration is *slow*, caches tend to get blown away, lots of code gets
executed, etc.  Presumably any prefetched / trace cached / decoded /
i-cached user code is long gone when we migrate.