Re: [PATCH] bpf: Call cond_resched() to avoid soft lockup in trie_free()

[Alexei Starovoitov]

On Wed, Jun 18, 2025 at 7:27 AM Ignat Korchagin <ignat@xxxxxxxxxxxxxx> wrote:
>
> On Wed, Jun 18, 2025 at 3:01 PM Alexei Starovoitov
> <alexei.starovoitov@xxxxxxxxx> wrote:
> >
> > On Wed, Jun 18, 2025 at 5:29 AM Matt Fleming <matt@xxxxxxxxxxxxxxxx> wrote:
> > >
> > > On Tue, Jun 17, 2025 at 4:55 PM Alexei Starovoitov
> > > <alexei.starovoitov@xxxxxxxxx> wrote:
> > > >
> > > > On Tue, Jun 17, 2025 at 2:43 AM Matt Fleming <matt@xxxxxxxxxxxxxxxx> wrote:
> > > > >
> > > >
> > > > > soft lockup - CPU#41 stuck for 76s
> > > >
> > > > How many elements are in the trie that it takes 76 seconds??
> > >
> > > We run our maps with potentially millions of entries, so it's the size
> > > of the map plus the fact that kfree() does more work with KASAN that
> > > triggers this for us.
> > >
> > > > I feel the issue is different.
> > > > It seems the trie_free() algorithm doesn't scale.
> > > > Pls share a full reproducer.
> > >
> > > Yes, the scalability of the algorithm is also an issue. Jesper (CC'd)
> > > had some thoughts on this.
> > >
> > > But regardless, it seems like a bad idea to have an unbounded loop
> > > inside the kernel that processes user-controlled data.
> >
> > 1M kfree should still be very fast even with kasan, lockdep, etc.
> > 76 seconds is an algorithm problem. Address the root cause.
>
> What if later we have 1G? 100G? Apart from the root cause we still
> have "scalability concerns" unless we can somehow reimplement this as
> O(1)

Do your homework pls.
Set max_entries to 100G and report back.
Then set max_entries to 1G _with_ cond_rescehd() hack and report back.