Re: [PATCH linux-next v3] mm, page_pool: introduce a new page type for page pool in page type

[Zi Yan <ziy@nvidia.com>]

On 29 Jul 2025, at 7:02, Byungchul Park wrote:

> Changes from v2:
> 	1. Rebase on linux-next as of Jul 29.
> 	2. Skip 'niov->pp = NULL' when it's allocated using __GFP_ZERO.
> 	3. Change trivial coding style. (feedbacked by Mina)
> 	4. Add Co-developed-by, Acked-by, and Reviewed-by properly.
> 	   Thanks to all.
>
> Changes from v1:
> 	1. Rebase on linux-next.
> 	2. Initialize net_iov->pp = NULL when allocating net_iov in
> 	   net_devmem_bind_dmabuf() and io_zcrx_create_area().
> 	3. Use ->pp for net_iov to identify if it's pp rather than
> 	   always consider net_iov as pp.
> 	4. Add Suggested-by: David Hildenbrand <david@redhat.com>.
>
> ---8<---
> From 88bcb9907a0cef65a9c0adf35e144f9eb67e0542 Mon Sep 17 00:00:00 2001
> From: Byungchul Park <byungchul@sk.com>
> Date: Tue, 29 Jul 2025 19:49:44 +0900
> Subject: [PATCH linux-next v3] mm, page_pool: introduce a new page type for page pool in page type
>
> ->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().
>
> For net_iov, use ->pp to identify if it's pp, with making sure that ->pp
> is NULL for non-pp net_iov.
>
> 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>
> Reviewed-by: Mina Almasry <almasrymina@google.com>
> ---
>  .../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 +-
>  io_uring/zcrx.c                               |  4 +++
>  mm/page_alloc.c                               |  7 +++--
>  net/core/devmem.c                             |  1 +
>  net/core/netmem_priv.h                        | 23 +++++++---------
>  net/core/page_pool.c                          | 10 +++++--
>  9 files changed, 37 insertions(+), 45 deletions(-)
>

<snip>

> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 0d4ee569aa6b..d01b296e7184 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -4171,10 +4171,9 @@ 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.
>   *
> @@ -4205,26 +4204,6 @@ 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 8d3fa3a91ce4..84247e39e9e7 100644
> --- a/include/linux/page-flags.h
> +++ b/include/linux/page-flags.h
> @@ -933,6 +933,7 @@ enum pagetype {
>  	PGTY_zsmalloc		= 0xf6,
>  	PGTY_unaccepted		= 0xf7,
>  	PGTY_large_kmalloc	= 0xf8,
> +	PGTY_netpp		= 0xf9,
>
>  	PGTY_mapcount_underflow = 0xff
>  };
> @@ -1077,6 +1078,11 @@ 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.

<snip>

> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index d1d037f97c5f..2f6a55fab942 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) |
>  			(page->flags & check_flags)))
>  		return false;
>
> @@ -1069,8 +1068,6 @@ static const char *page_bad_reason(struct page *page, unsigned long flags)
>  	if (unlikely(page->memcg_data))
>  		bad_reason = "page still charged to cgroup";
>  #endif
> -	if (unlikely(page_pool_page_is_pp(page)))
> -		bad_reason = "page_pool leak";
>  	return bad_reason;
>  }
>
> @@ -1379,9 +1376,11 @@ __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))) {
> +		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))

The mm part looks good to me.

Acked-by: Zi Yan <ziy@nvidia.com>

Best Regards,
Yan, Zi