Re: [PATCH] mm: make __GFP_SKIP_ZERO visible to skip zero operation

[Michal Hocko]

On Fri 01-09-23 14:55:17, Alexander Potapenko wrote:
> On Fri, Sep 1, 2023 at 12:29 PM Zhaoyang Huang <huangzhaoyang@xxxxxxxxx> wrote:
> >
> > loop alex
> 
> (adding more people who took part in the previous discussions)
> 
> >
> > On Thu, Aug 31, 2023 at 8:16 PM Matthew Wilcox <willy@xxxxxxxxxxxxx> wrote:
> > >
> > > On Thu, Aug 31, 2023 at 06:52:52PM +0800, zhaoyang.huang wrote:
> > > > From: Zhaoyang Huang <zhaoyang.huang@xxxxxxxxxx>
> > > >
> > > > There is no explicit gfp flags to let the allocation skip zero
> > > > operation when CONFIG_INIT_ON_ALLOC_DEFAULT_ON=y. I would like to make
> > > > __GFP_SKIP_ZERO be visible even if kasan is not configured.
> 
> Hi all,
> 
> This is a recurring question, as people keep encountering performance
> problems on systems with init_on_alloc=1
> (https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1862822 being
> one of the examples).
> 
> Brad Spengler has also pointed out
> (https://twitter.com/spendergrsec/status/1296461651659694082) that
> there are cases where there is no security vs. performance tradeoff
> (e.g. kmemdup() and kstrdup()).
> 
> An opt-out flag was included in the initial init_on_alloc series, but
> back then Michal Hocko has noted that it might easily get out of
> control: https://patchwork.kernel.org/project/linux-hardening/patch/20190418154208.131118-2-glider@xxxxxxxxxx/#22600229.

I still maintain my opinion. I really do not like the idea of mixing
concepts of init_on_alloc (which is pretty much security oriented) and
an opt out flag which bypasses it. Sooner or later this will become an
unreviewable mess so the value of init_on_alloc will become very
dubious.

> Now that init_on_alloc is actually being used by people which may have
> different preferences wrt. security and performance (in the cases
> where this tradeoff exists), we must be very careful with the opt-out
> GFP flag. Not initializing a particular allocation site in the
> upstream kernel will affect every downstream user, and some may
> consider this a security regression.

Fully agreed!

> Another problematic case is an OS vendor mandating init_on_alloc
> everywhere, but a third party driver vendor doing kmalloc(...,
> __GFP_SKIP_ZERO) for their allocations.

Exactly. This allows to sniff into driver unrelated proper and allow a
whole class of isssues.

> So I think a working opt-out scheme for the heap initialization should
> be two-step:
> 1. The code owner may decide that a particular allocation site needs
> an opt-out, and make the upstream code change;
> 2. The OS vendor has the ability to override that decision for the
> kernel they ship without the need to patch the source.

Practically speaking this would require a new mode
init_on_alloc_but_potentially_unsafe

Another option would be to provide a simple page allocator wrapper that
would allow to recycle pages for a particular user or providing a slab
cache that would achieve the same thing. This would be still a bit
quetiongable because the user could be seeing stale data but less of a
problem than crossing propers and potentially security domains.
-- 
Michal Hocko
SUSE Labs