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>

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 7b996ed86d5b823d1b92a0df82da033cafa4d6c3..8bd383caa363ad31bd965b2f2316298042da8af5 100644 (file)
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -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,

diff --git a/net/core/dev.c b/net/core/dev.c
index 17d67b579beb0c3f6f97bfd8add5d7027741854a..b10ff0a71855207ecf56fc815d2b08b4239693cd 100644 (file)
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -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);
 

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 27002dffe7ed3ea4df4f9b8d77b4210615d668c2..387703f56fcef6784d0d449e38d4cd73cdf8ce3e 100644 (file)
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -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);