Re: [PATCH v5 11/12] mm: zswap: Restructure & simplify zswap_store() to make it amenable for batching.

[Yosry Ahmed <yosryahmed@google.com>]

[..]
> > > diff --git a/mm/zswap.c b/mm/zswap.c
> > > index 99cd78891fd0..1be0f1807bfc 100644
> > > --- a/mm/zswap.c
> > > +++ b/mm/zswap.c
> > > @@ -1467,77 +1467,129 @@ static void shrink_worker(struct work_struct
> > *w)
> > >  * main API
> > >  **********************************/
> > >
> > > -static ssize_t zswap_store_page(struct page *page,
> > > -                               struct obj_cgroup *objcg,
> > > -                               struct zswap_pool *pool)
> > > +static bool zswap_compress_folio(struct folio *folio,
> > > +                                struct zswap_entry *entries[],
> > > +                                struct zswap_pool *pool)
> > >  {
> > > -       swp_entry_t page_swpentry = page_swap_entry(page);
> > > -       struct zswap_entry *entry, *old;
> > > +       long index, nr_pages = folio_nr_pages(folio);
> > >
> > > -       /* allocate entry */
> > > -       entry = zswap_entry_cache_alloc(GFP_KERNEL, page_to_nid(page));
> > > -       if (!entry) {
> > > -               zswap_reject_kmemcache_fail++;
> > > -               return -EINVAL;
> > > +       for (index = 0; index < nr_pages; ++index) {
> > > +               struct page *page = folio_page(folio, index);
> > > +
> > > +               if (!zswap_compress(page, entries[index], pool))
> > > +                       return false;
> > >         }
> > >
> > > -       if (!zswap_compress(page, entry, pool))
> > > -               goto compress_failed;
> > > +       return true;
> > > +}
> > >
> > > -       old = xa_store(swap_zswap_tree(page_swpentry),
> > > -                      swp_offset(page_swpentry),
> > > -                      entry, GFP_KERNEL);
> > > -       if (xa_is_err(old)) {
> > > -               int err = xa_err(old);
> > > +/*
> > > + * Store all pages in a folio.
> > > + *
> > > + * The error handling from all failure points is consolidated to the
> > > + * "store_folio_failed" label, based on the initialization of the zswap
> > entries'
> > > + * handles to ERR_PTR(-EINVAL) at allocation time, and the fact that the
> > > + * entry's handle is subsequently modified only upon a successful
> > zpool_malloc()
> > > + * after the page is compressed.
> > > + */
> > > +static ssize_t zswap_store_folio(struct folio *folio,
> > > +                                struct obj_cgroup *objcg,
> > > +                                struct zswap_pool *pool)
> > > +{
> > > +       long index, nr_pages = folio_nr_pages(folio);
> > > +       struct zswap_entry **entries = NULL;
> > > +       int node_id = folio_nid(folio);
> > > +       size_t compressed_bytes = 0;
> > >
> > > -               WARN_ONCE(err != -ENOMEM, "unexpected xarray error: %d\n",
> > err);
> > > -               zswap_reject_alloc_fail++;
> > > -               goto store_failed;
> > > +       entries = kmalloc(nr_pages * sizeof(*entries), GFP_KERNEL);
> >
> > We can probably use kcalloc() here.
>
> I am a little worried about the latency penalty of kcalloc() in the reclaim path,
> especially since I am not relying on zero-initialized memory for "entries"..

Hmm good point, for a 2M THP we could be allocating an entire page here.

[..]
> > > @@ -1549,8 +1601,8 @@ bool zswap_store(struct folio *folio)
> > >         struct mem_cgroup *memcg = NULL;
> > >         struct zswap_pool *pool;
> > >         size_t compressed_bytes = 0;
> > > +       ssize_t bytes;
> > >         bool ret = false;
> > > -       long index;
> > >
> > >         VM_WARN_ON_ONCE(!folio_test_locked(folio));
> > >         VM_WARN_ON_ONCE(!folio_test_swapcache(folio));
> > > @@ -1584,15 +1636,11 @@ bool zswap_store(struct folio *folio)
> > >                 mem_cgroup_put(memcg);
> > >         }
> > >
> > > -       for (index = 0; index < nr_pages; ++index) {
> > > -               struct page *page = folio_page(folio, index);
> > > -               ssize_t bytes;
> > > +       bytes = zswap_store_folio(folio, objcg, pool);
> > > +       if (bytes < 0)
> > > +               goto put_pool;
> > >
> > > -               bytes = zswap_store_page(page, objcg, pool);
> > > -               if (bytes < 0)
> > > -                       goto put_pool;
> > > -               compressed_bytes += bytes;
> > > -       }
> > > +       compressed_bytes = bytes;
> >
> > What's the point of having both compressed_bytes and bytes now?
>
> The main reason was to cleanly handle a negative error value returned in "bytes"
> (declared as ssize_t), as against a true total "compressed_bytes" (declared as size_t)
> for the folio to use for objcg charging. This is similar to the current mainline
> code where zswap_store() calls zswap_store_page(). I was hoping to avoid potential
> issues with overflow/underflow, and for maintainability. Let me know if this is Ok.

It makes sense in the current mainline because we store the return
value of each call to zswap_store_page() in 'bytes', then check if
it's an error value, then add it to 'compressed_bytes'. Now we have a
single call to zswap_store_folio() and a single return value. AFAICT,
there is currently no benefit to storing it in 'bytes', checking it,
then moving it to 'compressed_bytes'. The compiler will probably
optimize the variable away anyway, but it looks weird.