Re: [RFC PATCH v2 22/27] x86/cet/ibt: User-mode indirect branch tracking support

On 07/13/2018 10:56 AM, Yu-cheng Yu wrote:

quoted

quoted

GLIBC does the bitmap setup.  It sets bits in there.
I thought you wanted a smaller bitmap?  One way is forcing legacy libs
to low address, or not having the bitmap at all, i.e. turn IBT off.

I'm concerned with two things:
1. the virtual address space consumption, especially the *default* case
   which will be apps using 4-level address space amounts, but having
   5-level-sized tables.
2. the driving a truck-sized hole in the address space limits

You can force legacy libs to low addresses, but you can't stop anyone
from putting code into a high address *later*, at least with the code we
have today.

So we will always reserve a big space for all CET tasks?

Yes.  You either hard-restrict the address space (which we can't do
currently) or you reserve a big space.

Currently if an application does dlopen() a legacy lib, it will have only
partial IBT protection and no SHSTK.  Do we want to consider simply turning
off IBT in that case?

I don't know.  I honestly don't understand the threat model enough to
give you a good answer.  Is there background on this in the docs?