Re: [PATCH net-next v3 RFC] skb_expand_head() adjust skb->truesize incorrectly

[Eric Dumazet]

On 8/31/21 7:34 AM, Vasily Averin wrote:
> RFC because it have an extra changes:
> new is_skb_wmem() helper can be called
>  - either before pskb_expand_head(), to create skb clones 
>     for skb with destructors that does not change sk->sk_wmem_alloc
>  - or after pskb_expand_head(), to change owner in skb_set_owner_w()
> 
> In current patch I've added both these ways,
> we need to keep one of them.
> ---
> Christoph Paasch reports [1] about incorrect skb->truesize
> after skb_expand_head() call in ip6_xmit.
> This may happen because of two reasons:
> - skb_set_owner_w() for newly cloned skb is called too early,
> before pskb_expand_head() where truesize is adjusted for (!skb-sk) case.
> - pskb_expand_head() does not adjust truesize in (skb->sk) case.
> In this case sk->sk_wmem_alloc should be adjusted too.
> 
> [1] https://lkml.org/lkml/2021/8/20/1082
> 
> Reported-by: Christoph Paasch <christoph.paasch@xxxxxxxxx>
> Signed-off-by: Vasily Averin <vvs@xxxxxxxxxxxxx>
> ---
> v3: removed __pskb_expand_head(),
>     added is_skb_wmem() helper for skb with wmem-compatible destructors
>     there are 2 ways to use it:
>      - before pskb_expand_head(), to create skb clones
>      - after pskb_expand_head(), to change owner on extended skb.
> v2: based on patch version from Eric Dumazet,
>     added __pskb_expand_head() function, which can be forced
>     to adjust skb->truesize and sk->sk_wmem_alloc.
> ---
>  include/net/sock.h |  1 +
>  net/core/skbuff.c  | 39 ++++++++++++++++++++++++++++-----------
>  net/core/sock.c    |  8 ++++++++
>  3 files changed, 37 insertions(+), 11 deletions(-)
> 
> diff --git a/include/net/sock.h b/include/net/sock.h
> index 95b2577..173d58c 100644
> --- a/include/net/sock.h
> +++ b/include/net/sock.h
> @@ -1695,6 +1695,7 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
>  			     gfp_t priority);
>  void __sock_wfree(struct sk_buff *skb);
>  void sock_wfree(struct sk_buff *skb);
> +bool is_skb_wmem(const struct sk_buff *skb);
>  struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
>  			     gfp_t priority);
>  void skb_orphan_partial(struct sk_buff *skb);
> diff --git a/net/core/skbuff.c b/net/core/skbuff.c
> index f931176..3ce33f2 100644
> --- a/net/core/skbuff.c
> +++ b/net/core/skbuff.c
> @@ -1804,30 +1804,47 @@ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom)
>  struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom)
>  {
>  	int delta = headroom - skb_headroom(skb);
> +	int osize = skb_end_offset(skb);
> +	struct sk_buff *oskb = NULL;
> +	struct sock *sk = skb->sk;
>  
>  	if (WARN_ONCE(delta <= 0,
>  		      "%s is expecting an increase in the headroom", __func__))
>  		return skb;
>  
> -	/* pskb_expand_head() might crash, if skb is shared */
> -	if (skb_shared(skb)) {
> +	delta = SKB_DATA_ALIGN(delta);
> +	/* pskb_expand_head() might crash, if skb is shared.
> +	 * Also we should clone skb if its destructor does
> +	 * not adjust skb->truesize and sk->sk_wmem_alloc
> + 	 */
> +	if (skb_shared(skb) ||
> +	    (sk && (!sk_fullsock(sk) || !is_skb_wmem(skb)))) {

is_skb_wmem() is only possibly true for full sockets by definition.

So the (sk_fullsock(sk) && is_skb_wmem(skb)) can be reduced to is_skb_wmem(skb)

>  		struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
>  
> -		if (likely(nskb)) {
> -			if (skb->sk)
> -				skb_set_owner_w(nskb, skb->sk);
> -			consume_skb(skb);
> -		} else {
> +		if (unlikely(!nskb)) {
>  			kfree_skb(skb);
> +			return NULL;
>  		}
> +		oskb = skb;
>  		skb = nskb;
>  	}
> -	if (skb &&
> -	    pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) {
> +	if (pskb_expand_head(skb, delta, 0, GFP_ATOMIC)) {
>  		kfree_skb(skb);
> -		skb = NULL;
> +		kfree_skb(oskb);
> +		return NULL;
>  	}
> -	return skb;
> +	if (oskb) {
> +		if (sk)
> +			skb_set_owner_w(skb, sk);

Broken for non full sockets.
Calling skb_set_owner_w(skb, sk) for them is a bug.
> +		consume_skb(oskb);
> +	} else if (sk) {
> +		delta = osize - skb_end_offset(skb);
> +		if (!is_skb_wmem(skb))
> +			skb_set_owner_w(skb, sk);

This would be broken for non full sockets.
Calling skb_set_owner_w(skb, sk) for them is a bug.

> +		skb->truesize += delta;
> +		if (sk_fullsock(sk))
> +			refcount_add(delta, &sk->sk_wmem_alloc);


> +	}	return skb;
>  }
>  EXPORT_SYMBOL(skb_expand_head);
>  
> diff --git a/net/core/sock.c b/net/core/sock.c
> index 950f1e7..0315dcb 100644
> --- a/net/core/sock.c
> +++ b/net/core/sock.c
> @@ -2227,6 +2227,14 @@ void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
>  }
>  EXPORT_SYMBOL(skb_set_owner_w);
>  
> +bool is_skb_wmem(const struct sk_buff *skb)
> +{
> +	return (skb->destructor == sock_wfree ||
> +		skb->destructor == __sock_wfree ||
> +		(IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree));

No need for return (EXPRESSION);

You can simply : return EXPRESSION;

ie
   return skb->destructor == sock_wfree ||
          skb->destructor == __sock_wfree ||
          (IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree);


> +}
> +EXPORT_SYMBOL(is_skb_wmem);
> +
>  static bool can_skb_orphan_partial(const struct sk_buff *skb)
>  {
>  #ifdef CONFIG_TLS_DEVICE
>