Re: [PATCH v4 2/3] mm/swap: use swap_ops to register swap device's methods

[Chris Li]

On Thu, Apr 16, 2026 at 8:40 PM Baoquan He <baoquan.he@xxxxxxxxx> wrote:
>
> This simplifies codes and makes logic clearer. And also makes later any
> new swap device type being added easier to handle.
>
> Currently there are three types of swap devices: bdev_fs, bdev_sync
> and bdev_async, and only operations read_folio and write_folio are
> included. In the future, there could be more swap device types added
> and more appropriate operations adapted into swap_ops.
>
> Suggested-by: Chris Li <chrisl@xxxxxxxxxx>
> Co-developed-by: Barry Song <baohua@xxxxxxxxxx>
> Signed-off-by: Barry Song <baohua@xxxxxxxxxx>
> Signed-off-by: Baoquan He <baoquan.he@xxxxxxxxx>

Overall looks good, I have some nitpick follows.

Acked-by: Chris Li <chrisl@xxxxxxxxxx>


> ---
>  include/linux/swap.h |   2 +
>  mm/swap.h            |  10 ++++-
>  mm/swap_io.c         | 102 +++++++++++++++++++++++++------------------
>  mm/swapfile.c        |   5 +++
>  mm/zswap.c           |   2 +-
>  5 files changed, 76 insertions(+), 45 deletions(-)
>
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 4b1f13b5bbad..5fdda26f5c1d 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -242,6 +242,7 @@ struct swap_sequential_cluster {
>         unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
>  };
>
> +struct swap_ops;
>  /*
>   * The in-memory structure used to track swap areas.
>   */
> @@ -282,6 +283,7 @@ struct swap_info_struct {
>         struct work_struct reclaim_work; /* reclaim worker */
>         struct list_head discard_clusters; /* discard clusters list */
>         struct plist_node avail_list;   /* entry in swap_avail_head */
> +       const struct swap_ops *ops;
>  };
>
>  static inline swp_entry_t page_swap_entry(struct page *page)
> diff --git a/mm/swap.h b/mm/swap.h
> index 161185057993..29bdc679fa98 100644
> --- a/mm/swap.h
> +++ b/mm/swap.h
> @@ -217,6 +217,15 @@ extern void __swap_cluster_free_entries(struct swap_info_struct *si,
>  /* linux/mm/swap_io.c */
>  int sio_pool_init(void);
>  struct swap_iocb;
> +struct swap_ops {
> +       void (*read_folio)(struct swap_info_struct *sis,
> +                       struct folio *folio,
> +                       struct swap_iocb **plug);
> +       void (*write_folio)(struct swap_info_struct *sis,
> +                       struct folio *folio,
> +                       struct swap_iocb **plug);
> +};
> +int init_swap_ops(struct swap_info_struct *sis);
>  void swap_read_folio(struct folio *folio, struct swap_iocb **plug);
>  void __swap_read_unplug(struct swap_iocb *plug);
>  static inline void swap_read_unplug(struct swap_iocb *plug)
> @@ -226,7 +235,6 @@ static inline void swap_read_unplug(struct swap_iocb *plug)
>  }
>  void swap_write_unplug(struct swap_iocb *sio);
>  int swap_writeout(struct folio *folio, struct swap_iocb **swap_plug);
> -void __swap_writepage(struct folio *folio, struct swap_iocb **swap_plug);
>
>  /* linux/mm/swap_state.c */
>  extern struct address_space swap_space __read_mostly;
> diff --git a/mm/swap_io.c b/mm/swap_io.c
> index a62c02ab0551..1b054a122f53 100644
> --- a/mm/swap_io.c
> +++ b/mm/swap_io.c
> @@ -238,6 +238,7 @@ static void swap_zeromap_folio_clear(struct folio *folio)
>  int swap_writeout(struct folio *folio, struct swap_iocb **swap_plug)
>  {
>         int ret = 0;
> +       struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
>
>         if (folio_free_swap(folio))
>                 goto out_unlock;
> @@ -279,7 +280,7 @@ int swap_writeout(struct folio *folio, struct swap_iocb **swap_plug)
>                 return AOP_WRITEPAGE_ACTIVATE;
>         }
>
> -       __swap_writepage(folio, swap_plug);
> +       sis->ops->write_folio(sis, folio, swap_plug);
>         return 0;
>  out_unlock:
>         folio_unlock(folio);
> @@ -369,10 +370,11 @@ static void sio_write_complete(struct kiocb *iocb, long ret)
>         mempool_free(sio, sio_pool);
>  }
>
> -static void swap_writepage_fs(struct folio *folio, struct swap_iocb **swap_plug)
> +static void swap_writepage_fs(struct swap_info_struct *sis,
> +                             struct folio *folio,
> +                             struct swap_iocb **swap_plug)
>  {
>         struct swap_iocb *sio = swap_plug ? *swap_plug : NULL;
> -       struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
>         struct file *swap_file = sis->swap_file;
>         loff_t pos = swap_dev_pos(folio->swap);
>
> @@ -405,8 +407,9 @@ static void swap_writepage_fs(struct folio *folio, struct swap_iocb **swap_plug)
>                 *swap_plug = sio;
>  }
>
> -static void swap_writepage_bdev_sync(struct folio *folio,
> -               struct swap_info_struct *sis)
> +static void swap_writepage_bdev_sync(struct swap_info_struct *sis,
> +                                    struct folio *folio,
> +                                    struct swap_iocb **plug)
>  {
>         struct bio_vec bv;
>         struct bio bio;
> @@ -425,8 +428,9 @@ static void swap_writepage_bdev_sync(struct folio *folio,
>         __end_swap_bio_write(&bio);
>  }
>
> -static void swap_writepage_bdev_async(struct folio *folio,
> -               struct swap_info_struct *sis)
> +static void swap_writepage_bdev_async(struct swap_info_struct *sis,
> +                                     struct folio *folio,
> +                                     struct swap_iocb **plug)
>  {
>         struct bio *bio;
>
> @@ -442,29 +446,6 @@ static void swap_writepage_bdev_async(struct folio *folio,
>         submit_bio(bio);
>  }
>
> -void __swap_writepage(struct folio *folio, struct swap_iocb **swap_plug)
> -{
> -       struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
> -
> -       VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio);
> -       /*
> -        * ->flags can be updated non-atomically,
> -        * but that will never affect SWP_FS_OPS, so the data_race
> -        * is safe.
> -        */
> -       if (data_race(sis->flags & SWP_FS_OPS))
> -               swap_writepage_fs(folio, swap_plug);
> -       /*
> -        * ->flags can be updated non-atomically,
> -        * but that will never affect SWP_SYNCHRONOUS_IO, so the data_race
> -        * is safe.
> -        */
> -       else if (data_race(sis->flags & SWP_SYNCHRONOUS_IO))
> -               swap_writepage_bdev_sync(folio, sis);
> -       else
> -               swap_writepage_bdev_async(folio, sis);
> -}
> -

Nice

>  void swap_write_unplug(struct swap_iocb *sio)
>  {
>         struct iov_iter from;
> @@ -533,9 +514,10 @@ static bool swap_read_folio_zeromap(struct folio *folio)
>         return true;
>  }
>
> -static void swap_read_folio_fs(struct folio *folio, struct swap_iocb **plug)
> +static void swap_read_folio_fs(struct swap_info_struct *sis,
> +                              struct folio *folio,
> +                              struct swap_iocb **plug)
>  {
> -       struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
>         struct swap_iocb *sio = NULL;
>         loff_t pos = swap_dev_pos(folio->swap);
>
> @@ -567,8 +549,9 @@ static void swap_read_folio_fs(struct folio *folio, struct swap_iocb **plug)
>                 *plug = sio;
>  }
>
> -static void swap_read_folio_bdev_sync(struct folio *folio,
> -               struct swap_info_struct *sis)
> +static void swap_read_folio_bdev_sync(struct swap_info_struct *sis,
> +                                     struct folio *folio,
> +                                     struct swap_iocb **plug)
>  {
>         struct bio_vec bv;
>         struct bio bio;
> @@ -589,8 +572,9 @@ static void swap_read_folio_bdev_sync(struct folio *folio,
>         put_task_struct(current);
>  }
>
> -static void swap_read_folio_bdev_async(struct folio *folio,
> -               struct swap_info_struct *sis)
> +static void swap_read_folio_bdev_async(struct swap_info_struct *sis,
> +                                      struct folio *folio,
> +                                      struct swap_iocb **plug)
>  {
>         struct bio *bio;
>
> @@ -604,6 +588,44 @@ static void swap_read_folio_bdev_async(struct folio *folio,
>         submit_bio(bio);
>  }
>
> +static const struct swap_ops bdev_fs_swap_ops = {
> +       .read_folio = swap_read_folio_fs,
> +       .write_folio = swap_writepage_fs,
> +};
> +
> +static const struct swap_ops bdev_sync_swap_ops = {
> +       .read_folio = swap_read_folio_bdev_sync,
> +       .write_folio = swap_writepage_bdev_sync,
> +};
> +
> +static const struct swap_ops bdev_async_swap_ops = {
> +       .read_folio = swap_read_folio_bdev_async,
> +       .write_folio = swap_writepage_bdev_async,
> +};
> +
> +int init_swap_ops(struct swap_info_struct *sis)
> +{
> +       /*
> +        * ->flags can be updated non-atomically, but that will
> +        * never affect SWP_FS_OPS, so the data_race is safe.
> +        */
> +       if (data_race(sis->flags & SWP_FS_OPS))
> +               sis->ops = &bdev_fs_swap_ops;
> +       /*
> +        * ->flags can be updated non-atomically, but that will
> +        * never affect SWP_SYNCHRONOUS_IO, so the data_race is safe.
> +        */
> +       else if (data_race(sis->flags & SWP_SYNCHRONOUS_IO))
> +               sis->ops = &bdev_sync_swap_ops;
> +       else
> +               sis->ops = &bdev_async_swap_ops;
> +
> +       if (!sis->ops || !sis->ops->read_folio || !sis->ops->write_folio)
> +               return -1;
Nitpick:

For int type error return, you should use  -EINVAL or some thing with
error code. If you don't care about error code, change the return type
to bool instead.

> +
> +       return 0;
> +}
> +
>  void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
>  {
>         struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
> @@ -638,13 +660,7 @@ void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
>         /* We have to read from slower devices. Increase zswap protection. */
>         zswap_folio_swapin(folio);
>
> -       if (data_race(sis->flags & SWP_FS_OPS)) {
> -               swap_read_folio_fs(folio, plug);
> -       } else if (synchronous) {
> -               swap_read_folio_bdev_sync(folio, sis);
> -       } else {
> -               swap_read_folio_bdev_async(folio, sis);
> -       }
> +       sis->ops->read_folio(sis, folio, plug);

Nice.

>
>  finish:
>         if (workingset) {
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index 9174f1eeffb0..af81fa212f1e 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -3518,6 +3518,11 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
>                 goto bad_swap_unlock_inode;
>         }
>

> +       if (init_swap_ops(si)) {
> +               error = -EINVAL;
> +               goto bad_swap_unlock_inode;
> +       }

Assume you return the error code above. Here can be
error = init_swap_ops(si)
if (error)
     goto ...;


Chris

> +
>         si->max = maxpages;
>         si->pages = maxpages - 1;
>         nr_extents = setup_swap_extents(si, swap_file, &span);
> diff --git a/mm/zswap.c b/mm/zswap.c
> index 0823cadd02b6..b699413a2526 100644
> --- a/mm/zswap.c
> +++ b/mm/zswap.c
> @@ -1061,7 +1061,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
>         folio_set_reclaim(folio);
>
>         /* start writeback */
> -       __swap_writepage(folio, NULL);
> +       si->ops->write_folio(si, folio, NULL);
>
>  out:
>         if (ret && ret != -EEXIST) {
> --
> 2.52.0
>
>