net, xsk: Avoid taking multiple skbuff references

Commit 642e450b6b59 ("xsk: Do not discard packet when NETDEV_TX_BUSY")
addressed the problem that packets were discarded from the Tx AF_XDP
ring, when the driver returned NETDEV_TX_BUSY. Part of the fix was
bumping the skbuff reference count, so that the buffer would not be
freed by dev_direct_xmit(). A reference count larger than one means
that the skbuff is "shared", which is not the case.

If the "shared" skbuff is sent to the generic XDP receive path,
netif_receive_generic_xdp(), and pskb_expand_head() is entered the
BUG_ON(skb_shared(skb)) will trigger.

This patch adds a variant to dev_direct_xmit(), __dev_direct_xmit(),
where a user can select the skbuff free policy. This allows AF_XDP to
avoid bumping the reference count, but still keep the NETDEV_TX_BUSY
behavior.

Fixes: 642e450b6b59 ("xsk: Do not discard packet when NETDEV_TX_BUSY")
Reported-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20201123175600.146255-1-bjorn.topel@gmail.com

3 files changed, 16 insertions, 14 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 964b494b0e8d..76775abf259d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2813,9 +2813,21 @@ u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
 		     struct net_device *sb_dev);
 u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
 		       struct net_device *sb_dev);
+
 int dev_queue_xmit(struct sk_buff *skb);
 int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev);
-int dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
+int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
+
+static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
+{
+	int ret;
+
+	ret = __dev_direct_xmit(skb, queue_id);
+	if (!dev_xmit_complete(ret))
+		kfree_skb(skb);
+	return ret;
+}
+
 int register_netdevice(struct net_device *dev);
 void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
 void unregister_netdevice_many(struct list_head *head);
diff --git a/net/core/dev.c b/net/core/dev.c
index 82dc6b48e45f..8588ade790cb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4180,7 +4180,7 @@ int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev)
 }
 EXPORT_SYMBOL(dev_queue_xmit_accel);
 
-int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
+int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 {
 	struct net_device *dev = skb->dev;
 	struct sk_buff *orig_skb = skb;
@@ -4210,17 +4210,13 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 	dev_xmit_recursion_dec();
 
 	local_bh_enable();
-
-	if (!dev_xmit_complete(ret))
-		kfree_skb(skb);
-
 	return ret;
 drop:
 	atomic_long_inc(&dev->tx_dropped);
 	kfree_skb_list(skb);
 	return NET_XMIT_DROP;
 }
-EXPORT_SYMBOL(dev_direct_xmit);
+EXPORT_SYMBOL(__dev_direct_xmit);
 
 /*************************************************************************
  *			Receiver routines
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 5a6cdf7b320d..b7b039bd9d03 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -411,11 +411,7 @@ static int xsk_generic_xmit(struct sock *sk)
 		skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr;
 		skb->destructor = xsk_destruct_skb;
 
-		/* Hinder dev_direct_xmit from freeing the packet and
-		 * therefore completing it in the destructor
-		 */
-		refcount_inc(&skb->users);
-		err = dev_direct_xmit(skb, xs->queue_id);
+		err = __dev_direct_xmit(skb, xs->queue_id);
 		if  (err == NETDEV_TX_BUSY) {
 			/* Tell user-space to retry the send */
 			skb->destructor = sock_wfree;
@@ -429,12 +425,10 @@ static int xsk_generic_xmit(struct sock *sk)
 		/* Ignore NET_XMIT_CN as packet might have been sent */
 		if (err == NET_XMIT_DROP) {
 			/* SKB completed but not sent */
-			kfree_skb(skb);
 			err = -EBUSY;
 			goto out;
 		}
 
-		consume_skb(skb);
 		sent_frame = true;
 	}