Re: [PATCH bpf-next v4 1/4] bpf: Add a sleepable page allocator for map memory

On Mon 24-08-26 15:11:57, Kumar Kartikeya Dwivedi wrote:
> On Mon Aug 24, 2026 at 3:01 PM CEST, Michal Hocko wrote:
> > On Mon 24-08-26 20:44:18, Jiayuan Chen wrote:
> >>
> >> On 8/24/26 8:26 PM, Michal Hocko wrote:
> >> > On Fri 21-08-26 13:06:12, Jiayuan Chen wrote:
> >> > > bpf_map_alloc_pages() picks the allocator via can_alloc_pages(), a
> >> > > conservative guess for BPF program context that is always false under
> >> > > PREEMPT_RT. So even a caller that really is sleepable gets the
> >> > > non-blocking allocator, which never reclaims and never engages the OOM
> >> > > machinery.
> >> > I thought one of the main motivations was reentrancy. As you cannot
> >> > really assume the context bpf_map_alloc_pages is called from there is an
> >> > extra care needed so that this doesn't re-enter the allocator from bpf
> >> > program called from allocator path and deadlock.
> >>
> >>
> >> Agreed, bpf_map_alloc_pages() is designed to be safe to run in any context.
> >>
> >> The commit message should be precise.
> >
> > How do you achive any level of safety for the _sleepable version? Vast
> > majority of the kernel is sleepable but that doesn't mean this is safe
> > from the mm reentrancy POV.
> 
> I think it will only be invoked directly in the arena map fault handler, which
> runs in task context. If an interrupt occurs and tries to allocate pages,
> can_alloc_pages() will return false and it should pick the _nolock() variant
> which is safe against reentrancy.

So you rely on callers to know what they are doing. If that is the case
and generally acceptable by the BPF community (no real saying from me
in that matter) then make sure all that is properly documented. Because
sleepable context is not merely enough.

-- 
Michal Hocko
SUSE Labs