Re: [RFC 1/4] mm/zswap: skip swapcache for swapping in zswap pages

[Usama Arif <usamaarif642@gmail.com>]

On 21/10/2024 22:11, Yosry Ahmed wrote:
> On Fri, Oct 18, 2024 at 3:50 AM Usama Arif <usamaarif642@gmail.com> wrote:
>>
>> As mentioned in [1], there is a significant improvement in no
>> readahead swapin performance for super fast devices when skipping
>> swapcache.
>>
>> With large folio zswapin support added in later patches, this will also
>> mean this path will also act as "readahead" by swapping in multiple
>> pages into large folios. further improving performance.
>>
>> [1] https://lore.kernel.org/all/1505886205-9671-5-git-send-email-minchan@kernel.org/T/#m5a792a04dfea20eb7af4c355d00503efe1c86a93
>>
>> Signed-off-by: Usama Arif <usamaarif642@gmail.com>
>> ---
>>  include/linux/zswap.h |  6 ++++++
>>  mm/memory.c           |  3 ++-
>>  mm/page_io.c          |  1 -
>>  mm/zswap.c            | 46 +++++++++++++++++++++++++++++++++++++++++++
>>  4 files changed, 54 insertions(+), 2 deletions(-)
>>
>> diff --git a/include/linux/zswap.h b/include/linux/zswap.h
>> index d961ead91bf1..e418d75db738 100644
>> --- a/include/linux/zswap.h
>> +++ b/include/linux/zswap.h
>> @@ -27,6 +27,7 @@ struct zswap_lruvec_state {
>>  unsigned long zswap_total_pages(void);
>>  bool zswap_store(struct folio *folio);
>>  bool zswap_load(struct folio *folio);
>> +bool zswap_present_test(swp_entry_t swp, int nr_pages);
>>  void zswap_invalidate(swp_entry_t swp);
>>  int zswap_swapon(int type, unsigned long nr_pages);
>>  void zswap_swapoff(int type);
>> @@ -49,6 +50,11 @@ static inline bool zswap_load(struct folio *folio)
>>         return false;
>>  }
>>
>> +static inline bool zswap_present_test(swp_entry_t swp, int nr_pages)
>> +{
>> +       return false;
>> +}
>> +
>>  static inline void zswap_invalidate(swp_entry_t swp) {}
>>  static inline int zswap_swapon(int type, unsigned long nr_pages)
>>  {
>> diff --git a/mm/memory.c b/mm/memory.c
>> index 03e5452dd0c0..49d243131169 100644
>> --- a/mm/memory.c
>> +++ b/mm/memory.c
>> @@ -4289,7 +4289,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
>>         swapcache = folio;
>>
>>         if (!folio) {
>> -               if (data_race(si->flags & SWP_SYNCHRONOUS_IO) &&
>> +               if ((data_race(si->flags & SWP_SYNCHRONOUS_IO) ||
>> +                   zswap_present_test(entry, 1)) &&
>>                     __swap_count(entry) == 1) {
>>                         /* skip swapcache */
>>                         folio = alloc_swap_folio(vmf);
>> diff --git a/mm/page_io.c b/mm/page_io.c
>> index 4aa34862676f..2a15b197968a 100644
>> --- a/mm/page_io.c
>> +++ b/mm/page_io.c
>> @@ -602,7 +602,6 @@ void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
>>         unsigned long pflags;
>>         bool in_thrashing;
>>
>> -       VM_BUG_ON_FOLIO(!folio_test_swapcache(folio) && !synchronous, folio);
>>         VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
>>         VM_BUG_ON_FOLIO(folio_test_uptodate(folio), folio);
>>
>> diff --git a/mm/zswap.c b/mm/zswap.c
>> index 7f00cc918e7c..f4b03071b2fb 100644
>> --- a/mm/zswap.c
>> +++ b/mm/zswap.c
>> @@ -1576,6 +1576,52 @@ bool zswap_store(struct folio *folio)
>>         return ret;
>>  }
>>
>> +static bool swp_offset_in_zswap(unsigned int type, pgoff_t offset)
>> +{
>> +       return (offset >> SWAP_ADDRESS_SPACE_SHIFT) <  nr_zswap_trees[type];
>> +}
>> +
>> +/* Returns true if the entire folio is in zswap */
>> +bool zswap_present_test(swp_entry_t swp, int nr_pages)
> 
> Also, did you check how the performance changes if we bring back the
> bitmap of present entries (i.e. what used to be frontswap's bitmap)
> instead of the tree lookups here?
> 

I think the cost of tree lookup is not much and compared to zswap_decompress
can probably be ignored. zswap_present_test is essentially just xa_load for
the first entry, and then xas_next_entry for subsequent entries which is even
cheaper than xa_load.