Re: [Xen-devel] [PATCH] x86: slightly reduce Meltdown band-aid overhead

[Andrew Cooper <andrew.cooper3@xxxxxxxxxx>]

On 29/01/18 18:55, Andrew Cooper wrote:
> On 18/01/18 15:39, Jan Beulich wrote:
>> Along those lines the "sync" IPI after L4 entry updates now needs to become a
>> real (and global) flush IPI, so that inside Xen we'll also pick up such
>> changes.
> The entry paths don't tick the TLB clock, so we are in no worse of a
> position than before.  IOW, I don't see why this needs to change to
> being a FLUSH_GLOBAL.

Actually, I've just worked out why.  Guest user mappings are still
global, and we do need to flush those.  I think it would be worth
identifying this in the comment.

~Andrew

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel