net: copy userspace buffers on device forwarding

dev_forward_skb loops an skb back into host networking
stack which might hang on the memory indefinitely.
In particular, this can happen in macvtap in bridged mode.
Copy the userspace fragments to avoid blocking the
sender in that case.

As this patch makes skb_copy_ubufs extern now,
I also added some documentation and made it clear
the SKBTX_DEV_ZEROCOPY flag automatically instead
of doing it in all callers. This can be made into a separate
patch if people feel it's worth it.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Michael S. Tsirkin 2011-08-31 08:03:29 +00:00 committed by David S. Miller
parent 0542b69e2c
commit 48c830120f
3 changed files with 26 additions and 5 deletions

View File

@ -524,6 +524,7 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
extern bool skb_recycle_check(struct sk_buff *skb, int skb_size);
extern struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src);
extern int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask);
extern struct sk_buff *skb_clone(struct sk_buff *skb,
gfp_t priority);
extern struct sk_buff *skb_copy(const struct sk_buff *skb,

View File

@ -1515,6 +1515,14 @@ static inline bool is_skb_forwardable(struct net_device *dev,
*/
int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
{
if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
if (skb_copy_ubufs(skb, GFP_ATOMIC)) {
atomic_long_inc(&dev->rx_dropped);
kfree_skb(skb);
return NET_RX_DROP;
}
}
skb_orphan(skb);
nf_reset(skb);

View File

@ -611,8 +611,21 @@ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src)
}
EXPORT_SYMBOL_GPL(skb_morph);
/* skb frags copy userspace buffers to kernel */
static int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
/* skb_copy_ubufs - copy userspace skb frags buffers to kernel
* @skb: the skb to modify
* @gfp_mask: allocation priority
*
* This must be called on SKBTX_DEV_ZEROCOPY skb.
* It will copy all frags into kernel and drop the reference
* to userspace pages.
*
* If this function is called from an interrupt gfp_mask() must be
* %GFP_ATOMIC.
*
* Returns 0 on success or a negative error code on failure
* to allocate kernel memory to copy to.
*/
int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
{
int i;
int num_frags = skb_shinfo(skb)->nr_frags;
@ -652,6 +665,8 @@ static int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
skb_shinfo(skb)->frags[i - 1].page = head;
head = (struct page *)head->private;
}
skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY;
return 0;
}
@ -677,7 +692,6 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
if (skb_copy_ubufs(skb, gfp_mask))
return NULL;
skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY;
}
n = skb + 1;
@ -803,7 +817,6 @@ struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask)
n = NULL;
goto out;
}
skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY;
}
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i];
@ -896,7 +909,6 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
if (skb_copy_ubufs(skb, gfp_mask))
goto nofrags;
skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY;
}
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
get_page(skb_shinfo(skb)->frags[i].page);