Re: x86_64 RIP-relative addressing bug

["Frank Ch. Eigler" <fche at redhat dot com>]

Hi, Roland -

roland wrote:

> I won't go into the gory details, but trying to play VM tricks is a
> royal can of worms.  [...]  In the general case, making a modified
> page table for one CPU to use momentarily involves copying that
> entire page table tree [...]

You're very likely right about the relative hassles, I'm certainly no
expert.  On this single point though, isn't it true that it would be
sufficient to copy & modify only the parent nodes of the specific page
table leaf node, and not the entire rest of the tree?  This would be
similar to filesystem "phase tree" algorithms that accomplish atomic
changes to metadata while preserving concurrent access to previous
versions.

- FChE

Attachment: pgp00000.pgp
Description: PGP signature