> Will the changes you are proposing allow me to determine the set of all
> ptes (in all tasks) which reference a page in memory?
>
> I am working on something like distributed shared memory where a page
> shared by many processes may be invalidated without a local process writing
> to it. To keep everything up-to-date I have to invalidate all local ptes
> which point to such a page. It sure would be nice if your changes made
> this possible.
Ummm, take a look at the code I posted last month which walks the list of
vmas on an inode - the technique is applicable to 2.0.33 as well. The
message is at:
http://www.linuxhq.com/lnxlists/linux-kernel/lk_9801_01/0593.html
-ben
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu