Re: [RFC mm v4 2/2] mm: introduce a new page type for page pool in page type

[Zi Yan <ziy@nvidia.com>]

On 27 Oct 2025, at 21:28, Mina Almasry wrote:

> On Thu, Oct 23, 2025 at 12:45 AM Byungchul Park <byungchul@sk.com> wrote:
>>
>> ->pp_magic field in struct page is current used to identify if a page
>> belongs to a page pool.  However, ->pp_magic will be removed and page
>> type bit in struct page e.i. PGTY_netpp can be used for that purpose.
>>
>> Introduce and use the page type APIs e.g. PageNetpp(), __SetPageNetpp(),
>> and __ClearPageNetpp() instead, and remove the existing APIs accessing
>> ->pp_magic e.g. page_pool_page_is_pp(), netmem_or_pp_magic(), and
>> netmem_clear_pp_magic().
>>
>> This work was inspired by the following link:
>>
>> [1] https://lore.kernel.org/all/582f41c0-2742-4400-9c81-0d46bf4e8314@gmail.com/
>>
>> While at it, move the sanity check for page pool to on free.
>>
>> Suggested-by: David Hildenbrand <david@redhat.com>
>> Co-developed-by: Pavel Begunkov <asml.silence@gmail.com>
>> Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
>> Signed-off-by: Byungchul Park <byungchul@sk.com>
>> Acked-by: David Hildenbrand <david@redhat.com>
>> Acked-by: Zi Yan <ziy@nvidia.com>
>> ---
>> Hi Mina,
>>
>> I dropped your Reviewed-by tag since there are updates on some comments
>> in network part.  Can I still keep your Reviewed-by?
>>
>>         Byungchul
>> ---
>>  .../net/ethernet/mellanox/mlx5/core/en/xdp.c  |  2 +-
>>  include/linux/mm.h                            | 27 +++----------------
>>  include/linux/page-flags.h                    |  6 +++++
>>  include/net/netmem.h                          |  2 +-
>>  mm/page_alloc.c                               |  8 +++---
>>  net/core/netmem_priv.h                        | 17 +++---------
>>  net/core/page_pool.c                          | 14 +++++-----
>>  7 files changed, 25 insertions(+), 51 deletions(-)
>>
>> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
>> index 5d51600935a6..def274f5c1ca 100644
>> --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
>> +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
>> @@ -707,7 +707,7 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
>>                                 xdpi = mlx5e_xdpi_fifo_pop(xdpi_fifo);
>>                                 page = xdpi.page.page;
>>
>> -                               /* No need to check page_pool_page_is_pp() as we
>> +                               /* No need to check PageNetpp() as we
>>                                  * know this is a page_pool page.
>>                                  */
>>                                 page_pool_recycle_direct(pp_page_to_nmdesc(page)->pp,
>> diff --git a/include/linux/mm.h b/include/linux/mm.h
>> index b6fdf3557807..f5155f1c75f5 100644
>> --- a/include/linux/mm.h
>> +++ b/include/linux/mm.h
>> @@ -4361,10 +4361,9 @@ int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status);
>>   * DMA mapping IDs for page_pool
>>   *
>>   * When DMA-mapping a page, page_pool allocates an ID (from an xarray) and
>> - * stashes it in the upper bits of page->pp_magic. We always want to be able to
>> - * unambiguously identify page pool pages (using page_pool_page_is_pp()). Non-PP
>> - * pages can have arbitrary kernel pointers stored in the same field as pp_magic
>> - * (since it overlaps with page->lru.next), so we must ensure that we cannot
>> + * stashes it in the upper bits of page->pp_magic. Non-PP pages can have
>> + * arbitrary kernel pointers stored in the same field as pp_magic (since
>> + * it overlaps with page->lru.next), so we must ensure that we cannot
>>   * mistake a valid kernel pointer with any of the values we write into this
>>   * field.
>>   *
>> @@ -4399,26 +4398,6 @@ int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status);
>>  #define PP_DMA_INDEX_MASK GENMASK(PP_DMA_INDEX_BITS + PP_DMA_INDEX_SHIFT - 1, \
>>                                   PP_DMA_INDEX_SHIFT)
>>
>> -/* Mask used for checking in page_pool_page_is_pp() below. page->pp_magic is
>> - * OR'ed with PP_SIGNATURE after the allocation in order to preserve bit 0 for
>> - * the head page of compound page and bit 1 for pfmemalloc page, as well as the
>> - * bits used for the DMA index. page_is_pfmemalloc() is checked in
>> - * __page_pool_put_page() to avoid recycling the pfmemalloc page.
>> - */
>> -#define PP_MAGIC_MASK ~(PP_DMA_INDEX_MASK | 0x3UL)
>> -
>> -#ifdef CONFIG_PAGE_POOL
>> -static inline bool page_pool_page_is_pp(const struct page *page)
>> -{
>> -       return (page->pp_magic & PP_MAGIC_MASK) == PP_SIGNATURE;
>> -}
>> -#else
>> -static inline bool page_pool_page_is_pp(const struct page *page)
>> -{
>> -       return false;
>> -}
>> -#endif
>> -
>>  #define PAGE_SNAPSHOT_FAITHFUL (1 << 0)
>>  #define PAGE_SNAPSHOT_PG_BUDDY (1 << 1)
>>  #define PAGE_SNAPSHOT_PG_IDLE  (1 << 2)
>> diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
>> index 0091ad1986bf..edf5418c91dd 100644
>> --- a/include/linux/page-flags.h
>> +++ b/include/linux/page-flags.h
>> @@ -934,6 +934,7 @@ enum pagetype {
>>         PGTY_zsmalloc           = 0xf6,
>>         PGTY_unaccepted         = 0xf7,
>>         PGTY_large_kmalloc      = 0xf8,
>> +       PGTY_netpp              = 0xf9,
>>
>>         PGTY_mapcount_underflow = 0xff
>>  };
>> @@ -1078,6 +1079,11 @@ PAGE_TYPE_OPS(Zsmalloc, zsmalloc, zsmalloc)
>>  PAGE_TYPE_OPS(Unaccepted, unaccepted, unaccepted)
>>  FOLIO_TYPE_OPS(large_kmalloc, large_kmalloc)
>>
>> +/*
>> + * Marks page_pool allocated pages.
>> + */
>> +PAGE_TYPE_OPS(Netpp, netpp, netpp)
>> +
>>  /**
>>   * PageHuge - Determine if the page belongs to hugetlbfs
>>   * @page: The page to test.
>> diff --git a/include/net/netmem.h b/include/net/netmem.h
>> index 651e2c62d1dd..0ec4c7561081 100644
>> --- a/include/net/netmem.h
>> +++ b/include/net/netmem.h
>> @@ -260,7 +260,7 @@ static inline unsigned long netmem_pfn_trace(netmem_ref netmem)
>>   */
>>  #define pp_page_to_nmdesc(p)                                           \
>>  ({                                                                     \
>> -       DEBUG_NET_WARN_ON_ONCE(!page_pool_page_is_pp(p));               \
>> +       DEBUG_NET_WARN_ON_ONCE(!PageNetpp(p));                          \
>>         __pp_page_to_nmdesc(p);                                         \
>>  })
>>
>> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
>> index fb91c566327c..c69ed3741bbc 100644
>> --- a/mm/page_alloc.c
>> +++ b/mm/page_alloc.c
>> @@ -1042,7 +1042,6 @@ static inline bool page_expected_state(struct page *page,
>>  #ifdef CONFIG_MEMCG
>>                         page->memcg_data |
>>  #endif
>> -                       page_pool_page_is_pp(page) |
>
> Shouldn't you replace the page_pool_page_is_pp check with a PageNetpp
> check in this call site and below? Or is that no longer necessary for
> some reason?

It is done in the hunk below this one:

@@ -1379,9 +1376,12 @@ __always_inline bool free_pages_prepare(struct page *page,
 		mod_mthp_stat(order, MTHP_STAT_NR_ANON, -1);
 		folio->mapping = NULL;
 	}
-	if (unlikely(page_has_type(page)))
+	if (unlikely(page_has_type(page))) {
+		/* networking expects to clear its page type before releasing */
+		WARN_ON_ONCE(PageNetpp(page));
 		/* Reset the page_type (which overlays _mapcount) */
 		page->page_type = UINT_MAX;
+	}

 	if (is_check_pages_enabled()) {
 		if (free_page_is_bad(page))

where
free_pages_prepare()
  -> free_page_is_bad()
    -> page_expected_state()

--
Best Regards,
Yan, Zi