Re: 2.6.29 pat issue

[ebiederm@xmission.com (Eric W. Biederman)]

Thomas Hellstrom <thellstrom@vmware.com> writes:


> Indeed, it's crucial to keep the mappings consistent, but failure to do so is a
> kernel driver bug, it should never be the result of invalid user data.

It easily can be.  Think of an X server mmaping frame buffers. Or other
device bars.

> There are other more common kernel bugs that can be even worse and hang / crash
> the system. For example using uninitialized spinlocks, writing to kfreed memory
> etc. There is code in the kernel to detect these as well, but this code is
> behind debug defines.

There are cpu errata on almost every cpu in existence that come into play
if you have the cacheabilty attributes wrong on a page.  CPUs have been known
to do very weird things when you hit those errata.  At the best of it you
are no longer running on a deterministic machine, at the worst of it you
crash the cpu.

> IMHO checking each vm_insert_pfn() for caching attribute correctness is not
> something that should be enabled by default, due to the CPU overhead. Production
> drivers should never violate this.

If it is a problem the implementation should become more efficient.  Userspace
as well as drivers can generate these mappings so even with a perfect driver
you cannot guarantee that someone else does not have that area of memory
mapped differently.

Eric