Re: [PATCH v4 bpf-next 1/3] bpf: Add kmem_cache iterator

[Namhyung Kim <namhyung@kernel.org>]

Hi Song,

On Fri, Oct 04, 2024 at 01:33:19PM -0700, Song Liu wrote:
> On Wed, Oct 2, 2024 at 11:09 AM Namhyung Kim <namhyung@kernel.org> wrote:
> >
> [...]
> > +
> > +       mutex_lock(&slab_mutex);
> > +
> > +       /*
> > +        * Find an entry at the given position in the slab_caches list instead
> 
> Nit: style of multi-line comment: "/* Find ...".

Ok, will update.

> 
> > +        * of keeping a reference (of the last visited entry, if any) out of
> > +        * slab_mutex. It might miss something if one is deleted in the middle
> > +        * while it releases the lock.  But it should be rare and there's not
> > +        * much we can do about it.
> > +        */
> > +       list_for_each_entry(s, &slab_caches, list) {
> > +               if (cnt == *pos) {
> > +                       /*
> > +                        * Make sure this entry remains in the list by getting
> > +                        * a new reference count.  Note that boot_cache entries
> > +                        * have a negative refcount, so don't touch them.
> > +                        */
> > +                       if (s->refcount > 0)
> > +                               s->refcount++;
> > +                       found = true;
> > +                       break;
> > +               }
> > +               cnt++;
> > +       }
> > +       mutex_unlock(&slab_mutex);
> > +
> > +       if (!found)
> > +               return NULL;
> > +
> > +       ++*pos;
> > +       return s;
> > +}
> > +
> > +static void kmem_cache_iter_seq_stop(struct seq_file *seq, void *v)
> > +{
> > +       struct bpf_iter_meta meta;
> > +       struct bpf_iter__kmem_cache ctx = {
> > +               .meta = &meta,
> > +               .s = v,
> > +       };
> > +       struct bpf_prog *prog;
> > +       bool destroy = false;
> > +
> > +       meta.seq = seq;
> > +       prog = bpf_iter_get_info(&meta, true);
> > +       if (prog)
> > +               bpf_iter_run_prog(prog, &ctx);
> > +
> > +       if (ctx.s == NULL)
> > +               return;
> > +
> > +       mutex_lock(&slab_mutex);
> > +
> > +       /* Skip kmem_cache_destroy() for active entries */
> > +       if (ctx.s->refcount > 1)
> > +               ctx.s->refcount--;
> > +       else if (ctx.s->refcount == 1)
> > +               destroy = true;
> > +
> > +       mutex_unlock(&slab_mutex);
> > +
> > +       if (destroy)
> > +               kmem_cache_destroy(ctx.s);
> > +}
> > +
> > +static void *kmem_cache_iter_seq_next(struct seq_file *seq, void *v, loff_t *pos)
> > +{
> > +       struct kmem_cache *s = v;
> > +       struct kmem_cache *next = NULL;
> > +       bool destroy = false;
> > +
> > +       ++*pos;
> > +
> > +       mutex_lock(&slab_mutex);
> > +
> > +       if (list_last_entry(&slab_caches, struct kmem_cache, list) != s) {
> > +               next = list_next_entry(s, list);
> > +               if (next->refcount > 0)
> > +                       next->refcount++;
> 
> What if next->refcount <=0? Shall we find next of next?

The slab_mutex should protect refcount == 0 case so it won't see that.
The negative refcount means it's a boot_cache and we shouldn't touch the
refcount.

Thanks,
Namhyung

> 
> > +       }
> > +
> > +       /* Skip kmem_cache_destroy() for active entries */
> > +       if (s->refcount > 1)
> > +               s->refcount--;
> > +       else if (s->refcount == 1)
> > +               destroy = true;
> > +
> > +       mutex_unlock(&slab_mutex);
> > +
> > +       if (destroy)
> > +               kmem_cache_destroy(s);
> > +
> > +       return next;
> > +}
> [...]