Re: [PATCH net-next v3 3/6] net: skbuff: replace skb_page_unref() and __skb_frag_unref() with skb_netmem_unref()

[Stanislav Fomichev <sdf.kernel@gmail.com>]

On 10/14, Mina Almasry wrote:
> Unreferencing a page_pool fragment with recycle=false decrements the
> non-pp backing refcount instead of pp_ref_count, underflowing the page
> refcount when the fragment was owned via page_pool (as on mlx4's RX
> error path). Having both skb_page_unref() and __skb_frag_unref(frag,
> recycle) made it easy for callers to pass hardcoded recycle=false on
> SKB-owned fragments.
> 
> Replace skb_page_unref() and __skb_frag_unref() with
> skb_netmem_unref(netmem, recycle), which dispatches to
> napi_pp_put_page() when recycle is true and put_netmem() otherwise:
> 
> - Use skb_frag_unref(skb, ...) on SKB-owned fragments in mlx4, sky2,
>   tls_strp, and skb_shift() so unrefs always match skb->pp_recycle.
> - Use put_netmem() directly in tls_device's destroy_record(), which
>   releases raw non-pp page references outside an SKB.
> 
> Found by code inspection and confirmed with the KUnit tests added later
> in this series; not observed in production. The mlx4, sky2, and TLS
> call-site changes are compile-tested only.
> 
> Assisted-by: LLM
> Signed-off-by: Mina Almasry <almasrymina@google.com>
> ---
> v2:
> - Note how the issue was found and how the change was tested.
> - Link to v1: https://lore.kernel.org/netdev/20261010083935.3274178-4-almasrymina@google.com/
> ---
>  drivers/net/ethernet/marvell/sky2.c        |  2 +-
>  drivers/net/ethernet/mellanox/mlx4/en_rx.c |  2 +-
>  include/linux/skbuff_ref.h                 | 34 +++++++++++-----------
>  net/core/skbuff.c                          |  7 +++--
>  net/ipv4/esp4.c                            |  4 +--
>  net/ipv6/esp6.c                            |  4 +--
>  net/tls/tls_device.c                       |  2 +-
>  net/tls/tls_strp.c                         |  2 +-
>  8 files changed, 29 insertions(+), 28 deletions(-)
> 
> diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
> index 30facdece3e29..1d42a82db8f2b 100644

[..]

> --- a/drivers/net/ethernet/marvell/sky2.c
> +++ b/drivers/net/ethernet/marvell/sky2.c
> @@ -2501,7 +2501,7 @@ static void skb_put_frags(struct sk_buff *skb, unsigned int hdr_space,
>  
>  		if (length == 0) {
>  			/* don't need this page */
> -			__skb_frag_unref(frag, false);
> +			skb_frag_unref(skb, i);
>  			--skb_shinfo(skb)->nr_frags;
>  		} else {
>  			size = min(length, (unsigned) PAGE_SIZE);
> diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
> index 96f97fa0f5489..fe18606c2ab55 100644
> --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
> +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
> @@ -497,7 +497,7 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
>  fail:
>  	while (nr > 0) {
>  		nr--;
> -		__skb_frag_unref(skb_shinfo(skb)->frags + nr, false);
> +		skb_frag_unref(skb, nr);
>  	}
>  	return 0;
>  }

These do not support qops and don't advertise devmem tx, so they are not
going to deal with netmems anytime soon, why touch these?

> diff --git a/include/linux/skbuff_ref.h b/include/linux/skbuff_ref.h
> index 0441c220fdbdf..04114c64dad99 100644
> --- a/include/linux/skbuff_ref.h
> +++ b/include/linux/skbuff_ref.h
> @@ -36,7 +36,16 @@ static __always_inline void skb_frag_ref(struct sk_buff *skb, int f)
>  
>  bool napi_pp_put_page(netmem_ref netmem);
>  
> -static __always_inline void skb_page_unref(netmem_ref netmem, bool recycle)
> +/**
> + * skb_netmem_unref - release a fragment reference on a netmem
> + * @netmem: netmem to unreference
> + * @recycle: whether page_pool recycling is enabled (e.g. skb->pp_recycle)
> + *
> + * Drops pp_ref_count via napi_pp_put_page() if @recycle is true and @netmem
> + * belongs to a page_pool; otherwise drops a non-pp backing reference via
> + * put_netmem(). Counterpart to skb_netmem_ref().
> + */
> +static __always_inline void skb_netmem_unref(netmem_ref netmem, bool recycle)
>  {
>  #ifdef CONFIG_PAGE_POOL
>  	if (recycle && napi_pp_put_page(netmem))
> @@ -46,31 +55,22 @@ static __always_inline void skb_page_unref(netmem_ref netmem, bool recycle)
>  }
>  
>  /**
> - * __skb_frag_unref - release a reference on a paged fragment.
> - * @frag: the paged fragment
> - * @recycle: recycle the page if allocated via page_pool
> - *
> - * Releases a reference on the paged fragment @frag
> - * or recycles the page via the page_pool API.
> - */
> -static __always_inline void __skb_frag_unref(skb_frag_t *frag, bool recycle)
> -{
> -	skb_page_unref(skb_frag_netmem(frag), recycle);
> -}
> -
> -/**
> - * skb_frag_unref - release a reference on a paged fragment of an skb.
> + * skb_frag_unref - release a reference on a paged fragment of an skb
>   * @skb: the buffer
>   * @f: the fragment offset
>   *
> - * Releases a reference on the @f'th paged fragment of @skb.
> + * Drops a reference on the @f'th fragment of @skb via skb_netmem_unref()
> + * (pp_ref_count if skb->pp_recycle and page_pool-backed, else non-pp
> + * backing refcount), skipping managed zerocopy fragments. Counterpart to
> + * skb_frag_ref().
>   */
>  static __always_inline void skb_frag_unref(struct sk_buff *skb, int f)
>  {
>  	struct skb_shared_info *shinfo = skb_shinfo(skb);
>  
>  	if (!skb_zcopy_managed(skb))
> -		__skb_frag_unref(&shinfo->frags[f], skb->pp_recycle);
> +		skb_netmem_unref(skb_frag_netmem(&shinfo->frags[f]),
> +				 skb->pp_recycle);
>  }
>  
>  #endif	/* _LINUX_SKBUFF_REF_H */
> diff --git a/net/core/skbuff.c b/net/core/skbuff.c
> index 76a42c60508d9..980bbe9166393 100644
> --- a/net/core/skbuff.c
> +++ b/net/core/skbuff.c
> @@ -1144,7 +1144,8 @@ static void skb_release_data(struct sk_buff *skb, enum skb_drop_reason reason)
>  	}
>  
>  	for (i = 0; i < shinfo->nr_frags; i++)
> -		__skb_frag_unref(&shinfo->frags[i], skb->pp_recycle);
> +		skb_netmem_unref(skb_frag_netmem(&shinfo->frags[i]),
> +				 skb->pp_recycle);
>  
>  free_head:
>  	if (shinfo->frag_list)
> @@ -1154,7 +1155,7 @@ static void skb_release_data(struct sk_buff *skb, enum skb_drop_reason reason)
>  exit:
>  	/* When we clone an SKB we copy the reycling bit. The pp_recycle
>  	 * bit is only set on the head though, so in order to avoid races
> -	 * while trying to recycle fragments on __skb_frag_unref() we need
> +	 * while trying to recycle fragments on skb_netmem_unref() we need
>  	 * to make one SKB responsible for triggering the recycle path.
>  	 * So disable the recycling bit if an SKB is cloned and we have
>  	 * additional references to the fragmented part of the SKB.
> @@ -4412,7 +4413,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen)
>  		fragto = &skb_shinfo(tgt)->frags[merge];
>  
>  		skb_frag_size_add(fragto, skb_frag_size(fragfrom));
> -		__skb_frag_unref(fragfrom, skb->pp_recycle);
> +		skb_frag_unref(skb, 0);
>  	}

[..]

>  	/* Reposition in the original skb */
> diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
> index e76db5817e78e..ae701561d9f12 100644
> --- a/net/ipv4/esp4.c
> +++ b/net/ipv4/esp4.c
> @@ -117,8 +117,8 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb,
>  		struct scatterlist *src = already_unref ? esp_req_sg(aead, req) : req->src;
>  
>  		for (sg = sg_next(src); sg; sg = sg_next(sg))
> -			skb_page_unref(page_to_netmem(sg_page(sg)),
> -				       skb->pp_recycle);
> +			skb_netmem_unref(page_to_netmem(sg_page(sg)),
> +					 skb->pp_recycle);
>  	}
>  }
>  
> diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
> index b1c9b36f76dc4..d654f0f442388 100644
> --- a/net/ipv6/esp6.c
> +++ b/net/ipv6/esp6.c
> @@ -134,8 +134,8 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb,
>  		struct scatterlist *src = already_unref ? esp_req_sg(aead, req) : req->src;
>  
>  		for (sg = sg_next(src); sg; sg = sg_next(sg))
> -			skb_page_unref(page_to_netmem(sg_page(sg)),
> -				       skb->pp_recycle);
> +			skb_netmem_unref(page_to_netmem(sg_page(sg)),
> +					 skb->pp_recycle);
>  	}
>  }
>  
> diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
> index f11d0528fc431..b333a9a72cdae 100644
> --- a/net/tls/tls_device.c
> +++ b/net/tls/tls_device.c
> @@ -143,7 +143,7 @@ static void destroy_record(struct tls_record_info *record)
>  	int i;
>  
>  	for (i = 0; i < record->num_frags; i++)
> -		__skb_frag_unref(&record->frags[i], false);
> +		put_netmem(skb_frag_netmem(&record->frags[i]));
>  	kfree(record);
>  }
>  
> diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c
> index 6cc222008d95c..53d3256d0114a 100644
> --- a/net/tls/tls_strp.c
> +++ b/net/tls/tls_strp.c
> @@ -197,7 +197,7 @@ static void tls_strp_flush_anchor_copy(struct tls_strparser *strp)
>  	DEBUG_NET_WARN_ON_ONCE(atomic_read(&shinfo->dataref) != 1);
>  
>  	for (i = 0; i < shinfo->nr_frags; i++)
> -		__skb_frag_unref(&shinfo->frags[i], false);
> +		skb_frag_unref(strp->anchor, i);
>  	shinfo->nr_frags = 0;
>  	if (strp->copy_mode) {
>  		kfree_skb_list(shinfo->frag_list);

Idk this part, seems harmless.. But are you sure we can even reach xfrm
(supposedly that's how we get to esp4) with netmems?