Re: [PATCH net-next 1/9] netmem: introduce struct netmem_desc mirroring struct page

[Harry Yoo <harry.yoo@oracle.com>]

On Mon, Jun 09, 2025 at 01:32:17PM +0900, Byungchul Park wrote:
> To simplify struct page, the page pool members of struct page should be
> moved to other, allowing these members to be removed from struct page.
> 
> Introduce a network memory descriptor to store the members, struct
> netmem_desc, and make it union'ed with the existing fields in struct
> net_iov, allowing to organize the fields of struct net_iov.
> 
> Signed-off-by: Byungchul Park <byungchul@sk.com>
> Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
> Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
> Reviewed-by: Mina Almasry <almasrymina@google.com>
> ---

I think one point of confusion here is that net_iov mirrors some fields
in netmem_desc, even though net_iov itself does not overlay struct page.

Presumably the reason is because net_iovs may not be associated with
specific pages, but only with DMA addresses?

The only reason why it mirrors netmem_desc fields seems to be
"page_pool doesn't want to care if netmem_ref is netmem_desc or net_iov
 when doing something with netmem_ref".

Maybe it's worth clearly documenting that net_iov does not
overlay (I mean, does not share storage with) struct page, and
why it won't be a memdesc type in the memdesc world.

Other than that, it looks good to me:
Acked-by: Harry Yoo <harry.yoo@oracle.com>

>  include/net/netmem.h | 94 ++++++++++++++++++++++++++++++++++----------
>  1 file changed, 73 insertions(+), 21 deletions(-)
> 
> diff --git a/include/net/netmem.h b/include/net/netmem.h
> index 386164fb9c18..2687c8051ca5 100644
> --- a/include/net/netmem.h
> +++ b/include/net/netmem.h
> @@ -12,6 +12,50 @@
>  #include <linux/mm.h>
>  #include <net/net_debug.h>
>  
> +/* These fields in struct page are used by the page_pool and net stack:
> + *
> + *        struct {
> + *                unsigned long pp_magic;
> + *                struct page_pool *pp;
> + *                unsigned long _pp_mapping_pad;
> + *                unsigned long dma_addr;
> + *                atomic_long_t pp_ref_count;
> + *        };
> + *
> + * We mirror the page_pool fields here so the page_pool can access these
> + * fields without worrying whether the underlying fields belong to a
> + * page or netmem_desc.
> + *
> + * CAUTION: Do not update the fields in netmem_desc without also
> + * updating the anonymous aliasing union in struct net_iov.
> + */
> +struct netmem_desc {
> +	unsigned long _flags;
> +	unsigned long pp_magic;
> +	struct page_pool *pp;
> +	unsigned long _pp_mapping_pad;
> +	unsigned long dma_addr;
> +	atomic_long_t pp_ref_count;
> +};
> +
> +#define NETMEM_DESC_ASSERT_OFFSET(pg, desc)        \
> +	static_assert(offsetof(struct page, pg) == \
> +		      offsetof(struct netmem_desc, desc))
> +NETMEM_DESC_ASSERT_OFFSET(flags, _flags);
> +NETMEM_DESC_ASSERT_OFFSET(pp_magic, pp_magic);
> +NETMEM_DESC_ASSERT_OFFSET(pp, pp);
> +NETMEM_DESC_ASSERT_OFFSET(_pp_mapping_pad, _pp_mapping_pad);
> +NETMEM_DESC_ASSERT_OFFSET(dma_addr, dma_addr);
> +NETMEM_DESC_ASSERT_OFFSET(pp_ref_count, pp_ref_count);
> +#undef NETMEM_DESC_ASSERT_OFFSET
> +
> +/*
> + * Since struct netmem_desc uses the space in struct page, the size
> + * should be checked, until struct netmem_desc has its own instance from
> + * slab, to avoid conflicting with other members within struct page.
> + */
> +static_assert(sizeof(struct netmem_desc) <= offsetof(struct page, _refcount));
> +
>  /* net_iov */
>  
>  DECLARE_STATIC_KEY_FALSE(page_pool_mem_providers);
> @@ -31,12 +75,25 @@ enum net_iov_type {
>  };
>  
>  struct net_iov {
> -	enum net_iov_type type;
> -	unsigned long pp_magic;
> -	struct page_pool *pp;
> +	union {
> +		struct netmem_desc desc;
> +
> +		/* XXX: The following part should be removed once all
> +		 * the references to them are converted so as to be
> +		 * accessed via netmem_desc e.g. niov->desc.pp instead
> +		 * of niov->pp.
> +		 */
> +		struct {
> +			unsigned long _flags;
> +			unsigned long pp_magic;
> +			struct page_pool *pp;
> +			unsigned long _pp_mapping_pad;
> +			unsigned long dma_addr;
> +			atomic_long_t pp_ref_count;
> +		};
> +	};
>  	struct net_iov_area *owner;
> -	unsigned long dma_addr;
> -	atomic_long_t pp_ref_count;
> +	enum net_iov_type type;
>  };
>  
>  struct net_iov_area {
> @@ -48,27 +105,22 @@ struct net_iov_area {
>  	unsigned long base_virtual;
>  };
>  
> -/* These fields in struct page are used by the page_pool and net stack:
> +/* net_iov is union'ed with struct netmem_desc mirroring struct page, so
> + * the page_pool can access these fields without worrying whether the
> + * underlying fields are accessed via netmem_desc or directly via
> + * net_iov, until all the references to them are converted so as to be
> + * accessed via netmem_desc e.g. niov->desc.pp instead of niov->pp.
>   *
> - *        struct {
> - *                unsigned long pp_magic;
> - *                struct page_pool *pp;
> - *                unsigned long _pp_mapping_pad;
> - *                unsigned long dma_addr;
> - *                atomic_long_t pp_ref_count;
> - *        };
> - *
> - * We mirror the page_pool fields here so the page_pool can access these fields
> - * without worrying whether the underlying fields belong to a page or net_iov.
> - *
> - * The non-net stack fields of struct page are private to the mm stack and must
> - * never be mirrored to net_iov.
> + * The non-net stack fields of struct page are private to the mm stack
> + * and must never be mirrored to net_iov.
>   */
> -#define NET_IOV_ASSERT_OFFSET(pg, iov)             \
> -	static_assert(offsetof(struct page, pg) == \
> +#define NET_IOV_ASSERT_OFFSET(desc, iov)                    \
> +	static_assert(offsetof(struct netmem_desc, desc) == \
>  		      offsetof(struct net_iov, iov))
> +NET_IOV_ASSERT_OFFSET(_flags, _flags);
>  NET_IOV_ASSERT_OFFSET(pp_magic, pp_magic);
>  NET_IOV_ASSERT_OFFSET(pp, pp);
> +NET_IOV_ASSERT_OFFSET(_pp_mapping_pad, _pp_mapping_pad);
>  NET_IOV_ASSERT_OFFSET(dma_addr, dma_addr);
>  NET_IOV_ASSERT_OFFSET(pp_ref_count, pp_ref_count);
>  #undef NET_IOV_ASSERT_OFFSET
> -- 
> 2.17.1
>