Re: [PATCH V3 3/8] Add userspace buffers support in skb

["Michael S. Tsirkin" <mst@redhat.com>]

On Wed, Apr 20, 2011 at 12:47:57PM -0700, Shirley Ma wrote:
> This patch adds userspace buffers support in skb. A new struct
> skb_ubuf_info is needed to maintain the userspace buffers argument
> and index, a callback is used to notify userspace to release the
> buffers once lower device has done DMA (Last reference to that skb
> has gone).
> 
> Signed-off-by: Shirley Ma <xma@us.ibm.com>
> ---
> 
>  include/linux/skbuff.h |   14 ++++++++++++++
>  net/core/skbuff.c      |   15 ++++++++++++++-
>  2 files changed, 28 insertions(+), 1 deletions(-)
> 
> diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
> index d0ae90a..47a187b 100644
> --- a/include/linux/skbuff.h
> +++ b/include/linux/skbuff.h
> @@ -189,6 +189,16 @@ enum {
>  	SKBTX_DRV_NEEDS_SK_REF = 1 << 3,
>  };
>  
> +/* The callback notifies userspace to release buffers when skb DMA is done in
> + * lower device, the desc is used to track userspace buffer index.
> + */
> +struct skb_ubuf_info {
> +	/* support buffers allocation from userspace */
> +	void		(*callback)(struct sk_buff *);
> +	void		*arg;
> +	size_t		desc;
> +};
> +
>  /* This data is invariant across clones and lives at
>   * the end of the header data, ie. at skb->end.
>   */
> @@ -211,6 +221,10 @@ struct skb_shared_info {
>  	/* Intermediate layers must ensure that destructor_arg
>  	 * remains valid until skb destructor */
>  	void *		destructor_arg;
> +
> +	/* DMA mapping from/to userspace buffers */
> +	struct skb_ubuf_info ubuf;
> +
>  	/* must be last field, see pskb_expand_head() */
>  	skb_frag_t	frags[MAX_SKB_FRAGS];
>  };
> diff --git a/net/core/skbuff.c b/net/core/skbuff.c
> index 7ebeed0..822c07d 100644
> --- a/net/core/skbuff.c
> +++ b/net/core/skbuff.c
> @@ -210,6 +210,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
>  	shinfo = skb_shinfo(skb);
>  	memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
>  	atomic_set(&shinfo->dataref, 1);
> +	shinfo->ubuf.callback = NULL;
> +	shinfo->ubuf.arg = NULL;
>  	kmemcheck_annotate_variable(shinfo->destructor_arg);
>  
>  	if (fclone) {
> @@ -327,7 +329,15 @@ static void skb_release_data(struct sk_buff *skb)
>  			for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
>  				put_page(skb_shinfo(skb)->frags[i].page);
>  		}
> -
> +		/*
> +		 * if skb buf is from userspace, we need to notify the caller
> +		 * the lower device DMA has done;
> +		 */
> +		if (skb_shinfo(skb)->ubuf.callback) {
> +			skb_shinfo(skb)->ubuf.callback(skb);
> +			skb_shinfo(skb)->ubuf.callback = NULL;
> +			skb_shinfo(skb)->ubuf.arg = NULL;
> +		}
>  		if (skb_has_frag_list(skb))
>  			skb_drop_fraglist(skb);
>  

We probably don't need to touch arg if callback is NULL?

> @@ -480,6 +490,9 @@ bool skb_recycle_check(struct sk_buff *skb, int skb_size)
>  	if (irqs_disabled())
>  		return false;
>  
> +	if (shinfo->ubuf.callback)
> +		return false;
> +
>  	if (skb_is_nonlinear(skb) || skb->fclone != SKB_FCLONE_UNAVAILABLE)
>  		return false;

This is not the only API unsupported for these skbs, is it?
Probably need to check and fail there as well.

> 
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html