Re: [PATCH net-next v6 7/10] xen-netback: Handle guests with too many frags

[Wei Liu <wei.liu2@citrix.com>]

On Tue, Mar 04, 2014 at 10:32:18PM +0000, Zoltan Kiss wrote:
> Xen network protocol had implicit dependency on MAX_SKB_FRAGS. Netback has to
> handle guests sending up to XEN_NETBK_LEGACY_SLOTS_MAX slots. To achieve that:
> - create a new skb
> - map the leftover slots to its frags (no linear buffer here!)
> - chain it to the previous through skb_shinfo(skb)->frag_list
> - map them
> - copy and coalesce the frags into a brand new one and send it to the stack
> - unmap the 2 old skb's pages
> 

IIRC you once said there's problem with some NICs sending out SKBs with
large linear area. Is that solved?

> NOTE: if bisect brought you here, you should apply the series up until #9,
> otherwise malicious guests can block other guests by not releasing their sent
> packets.
> 
> Signed-off-by: Zoltan Kiss <zoltan.kiss@citrix.com>
> ---
[...]
> v6:
> - move out handling from tx_submit into a new funciont, as it became quite long
> - skb_copy[_expand] allocate a new skb with a huge linear buffer, which is bad
>   in times of memory pressure. Just make a new frags array and do the copy and
>   coalesce with skb_copy_bits
> 

And with this change, the above issue is solved?

>  drivers/net/xen-netback/netback.c |  172 ++++++++++++++++++++++++++++++++++---
>  1 file changed, 162 insertions(+), 10 deletions(-)
> 
> diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
> index 447d58a..b284851 100644
> --- a/drivers/net/xen-netback/netback.c
> +++ b/drivers/net/xen-netback/netback.c
> @@ -37,6 +37,7 @@
>  #include <linux/kthread.h>
>  #include <linux/if_vlan.h>
>  #include <linux/udp.h>
> +#include <linux/highmem.h>
>  
>  #include <net/tcp.h>
>  
> @@ -792,6 +793,23 @@ static inline void xenvif_tx_create_gop(struct xenvif *vif,
>  	       sizeof(*txp));
>  }
>  
> +static inline struct sk_buff *xenvif_alloc_skb(unsigned int size)
> +{
> +	struct sk_buff *skb =
> +		alloc_skb(size + NET_SKB_PAD + NET_IP_ALIGN,
> +			  GFP_ATOMIC | __GFP_NOWARN);
> +	if (unlikely(skb == NULL))
> +		return NULL;
> +
> +	/* Packets passed to netif_rx() must have some headroom. */
> +	skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
> +
> +	/* Initialize it here to avoid later surprises */
> +	skb_shinfo(skb)->destructor_arg = NULL;
> +
> +	return skb;
> +}

This hunk can probably be moved to previous where you introduce mapping
mechanism.

> +
>  static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif,
>  							struct sk_buff *skb,
>  							struct xen_netif_tx_request *txp,
> @@ -802,11 +820,16 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif,
>  	u16 pending_idx = *((u16 *)skb->cb);
>  	int start;
>  	pending_ring_idx_t index;
> -	unsigned int nr_slots;
> +	unsigned int nr_slots, frag_overflow = 0;
>  
>  	/* At this point shinfo->nr_frags is in fact the number of
>  	 * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX.
>  	 */
> +	if (shinfo->nr_frags > MAX_SKB_FRAGS) {
> +		frag_overflow = shinfo->nr_frags - MAX_SKB_FRAGS;
> +		BUG_ON(frag_overflow > MAX_SKB_FRAGS);
> +		shinfo->nr_frags = MAX_SKB_FRAGS;
> +	}
>  	nr_slots = shinfo->nr_frags;
>  
>  	/* Skip first skb fragment if it is on same page as header fragment. */
> @@ -822,6 +845,30 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif,
>  
>  	BUG_ON(shinfo->nr_frags > MAX_SKB_FRAGS);
>  

This BUG_ON is pointless as shinfo->nr_frags is guaranteed to be not
larger than MAX_SKB_FRAGS a few lines above.

> +	if (frag_overflow) {
> +		struct sk_buff *nskb = xenvif_alloc_skb(0);
> +		if (unlikely(nskb == NULL)) {
> +			if (net_ratelimit())
> +				netdev_err(vif->dev,
> +					   "Can't allocate the frag_list skb.\n");
> +			return NULL;
> +		}
> +
> +		shinfo = skb_shinfo(nskb);
> +		frags = shinfo->frags;
> +
> +		for (shinfo->nr_frags = 0; shinfo->nr_frags < frag_overflow;
> +		     shinfo->nr_frags++, txp++, gop++) {
> +			index = pending_index(vif->pending_cons++);
> +			pending_idx = vif->pending_ring[index];
> +			xenvif_tx_create_gop(vif, pending_idx, txp, gop);
> +			frag_set_pending_idx(&frags[shinfo->nr_frags],
> +					     pending_idx);
> +		}
> +
> +		skb_shinfo(skb)->frag_list = nskb;
> +	}
> +
>  	return gop;
>  }
>  
[...]
> +	if (skb_has_frag_list(skb)) {
> +		first_skb = skb;
> +		skb = shinfo->frag_list;
> +		shinfo = skb_shinfo(skb);
> +		nr_frags = shinfo->nr_frags;
> +		start = 0;
> +
> +		goto check_frags;
> +	}
> +
> +	/* There was a mapping error in the frag_list skb. We have to unmap
> +	 * the first skb's frags
> +	 */
> +	if (first_skb && err) {
> +		int j;
> +		shinfo = skb_shinfo(first_skb);
> +		pending_idx = *((u16 *)first_skb->cb);
> +		start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx);
> +		for (j = start; j < shinfo->nr_frags; j++) {
> +			pending_idx = frag_get_pending_idx(&shinfo->frags[j]);
> +			xenvif_idx_unmap(vif, pending_idx);
> +			xenvif_idx_release(vif, pending_idx,
> +					   XEN_NETIF_RSP_OKAY);

_unmap and _release at the same time? IIRC _unmap calls _release.

> +		}
> +	}
> +
>  	*gopp = gop + 1;
>  	return err;
>  }
[...]
> +static int xenvif_handle_frag_list(struct xenvif *vif, struct sk_buff *skb)
> +{
> +	unsigned int offset = skb_headlen(skb);
> +	skb_frag_t frags[MAX_SKB_FRAGS];
> +	int i;
> +	struct ubuf_info *uarg;
> +	struct sk_buff *nskb = skb_shinfo(skb)->frag_list;
> +
> +	vif->tx_zerocopy_sent += 2;
> +	vif->tx_frag_overflow++;
> +
> +	xenvif_fill_frags(vif, nskb);
> +	/* Subtract frags size, we will correct it later */
> +	skb->truesize -= skb->data_len;
> +	skb->len += nskb->len;
> +	skb->data_len += nskb->len;
> +
> +	/* create a brand new frags array and coalesce there */
> +	for (i = 0; offset < skb->len; i++) {
> +		struct page *page;
> +		void *vaddr;
> +		unsigned int len;
> +
> +		BUG_ON(i >= MAX_SKB_FRAGS);
> +		page = alloc_page(GFP_ATOMIC|__GFP_COLD);
> +		if (!page) {
> +			int j;
> +			skb->truesize += skb->data_len;
> +			for (j = 0; j < i; j++)
> +				put_page(frags[j].page.p);
> +			return -ENOMEM;
> +		}
> +
> +		vaddr = kmap_atomic(page);

Why do you need this? The page is not allocated with __GFP_HIGHMEM.

> +		if (offset + PAGE_SIZE < skb->len)
> +			len = PAGE_SIZE;
> +		else
> +			len = skb->len - offset;
> +		if (skb_copy_bits(skb, offset, vaddr, len))
> +			BUG();
> +
> +		kunmap_atomic(vaddr);
> +		offset += len;
> +		frags[i].page.p = page;
> +		frags[i].page_offset = 0;
> +		skb_frag_size_set(&frags[i], len);
> +

Stray blank line.

> +	}
> +	/* swap out with old one */
> +	memcpy(skb_shinfo(skb)->frags,
> +	       frags,
> +	       i * sizeof(skb_frag_t));

The old frags array is over-written, when do you pages in old frags
array?

> +	skb_shinfo(skb)->nr_frags = i;
> +	skb->truesize += i * PAGE_SIZE;
> +
> +	/* remove traces of mapped pages and frag_list */
> +	skb_frag_list_init(skb);
> +	uarg = skb_shinfo(skb)->destructor_arg;
> +	uarg->callback(uarg, true);
> +	skb_shinfo(skb)->destructor_arg = NULL;
> +
> +	skb_shinfo(nskb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
> +	kfree_skb(nskb);
> +
> +	return 0;
> +}
>  
>  static int xenvif_tx_submit(struct xenvif *vif)
>  {
> @@ -1258,7 +1400,6 @@ static int xenvif_tx_submit(struct xenvif *vif)
>  				&vif->pending_tx_info[pending_idx].callback_struct;
>  		} else {
>  			/* Schedule a response immediately. */
> -			skb_shinfo(skb)->destructor_arg = NULL;

Why? You added this in previous patch but remove it here.

Wei.