1 files changed, 65 insertions, 8 deletions

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index ae9f8cb611f6..1eadfac03cc4 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -167,8 +167,10 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 		contd = XDP_PKT_CONTD;
 
 	err = __xsk_rcv_zc(xs, xskb, len, contd);
-	if (err || likely(!frags))
-		goto out;
+	if (err)
+		goto err;
+	if (likely(!frags))
+		return 0;
 
 	xskb_list = &xskb->pool->xskb_list;
 	list_for_each_entry_safe(pos, tmp, xskb_list, xskb_list_node) {
@@ -177,11 +179,13 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 		len = pos->xdp.data_end - pos->xdp.data;
 		err = __xsk_rcv_zc(xs, pos, len, contd);
 		if (err)
-			return err;
+			goto err;
 		list_del(&pos->xskb_list_node);
 	}
 
-out:
+	return 0;
+err:
+	xsk_buff_free(xdp);
 	return err;
 }
 
@@ -571,6 +575,13 @@ static u32 xsk_get_num_desc(struct sk_buff *skb)
 
 static void xsk_destruct_skb(struct sk_buff *skb)
 {
+	struct xsk_tx_metadata_compl *compl = &skb_shinfo(skb)->xsk_meta;
+
+	if (compl->tx_timestamp) {
+		/* sw completion timestamp, not a real one */
+		*compl->tx_timestamp = ktime_get_tai_fast_ns();
+	}
+
 	xsk_cq_submit_locked(xdp_sk(skb->sk), xsk_get_num_desc(skb));
 	sock_wfree(skb);
 }
@@ -655,8 +666,10 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
 static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 				     struct xdp_desc *desc)
 {
+	struct xsk_tx_metadata *meta = NULL;
 	struct net_device *dev = xs->dev;
 	struct sk_buff *skb = xs->skb;
+	bool first_frag = false;
 	int err;
 
 	if (dev->priv_flags & IFF_TX_SKB_NO_LINEAR) {
@@ -687,6 +700,8 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 				kfree_skb(skb);
 				goto free_err;
 			}
+
+			first_frag = true;
 		} else {
 			int nr_frags = skb_shinfo(skb)->nr_frags;
 			struct page *page;
@@ -709,12 +724,45 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 
 			skb_add_rx_frag(skb, nr_frags, page, 0, len, 0);
 		}
+
+		if (first_frag && desc->options & XDP_TX_METADATA) {
+			if (unlikely(xs->pool->tx_metadata_len == 0)) {
+				err = -EINVAL;
+				goto free_err;
+			}
+
+			meta = buffer - xs->pool->tx_metadata_len;
+			if (unlikely(!xsk_buff_valid_tx_metadata(meta))) {
+				err = -EINVAL;
+				goto free_err;
+			}
+
+			if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) {
+				if (unlikely(meta->request.csum_start +
+					     meta->request.csum_offset +
+					     sizeof(__sum16) > len)) {
+					err = -EINVAL;
+					goto free_err;
+				}
+
+				skb->csum_start = hr + meta->request.csum_start;
+				skb->csum_offset = meta->request.csum_offset;
+				skb->ip_summed = CHECKSUM_PARTIAL;
+
+				if (unlikely(xs->pool->tx_sw_csum)) {
+					err = skb_checksum_help(skb);
+					if (err)
+						goto free_err;
+				}
+			}
+		}
 	}
 
 	skb->dev = dev;
 	skb->priority = READ_ONCE(xs->sk.sk_priority);
 	skb->mark = READ_ONCE(xs->sk.sk_mark);
 	skb->destructor = xsk_destruct_skb;
+	xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta);
 	xsk_set_destructor_arg(skb);
 
 	return skb;
@@ -947,7 +995,7 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock,
 
 	rcu_read_lock();
 	if (xsk_check_common(xs))
-		goto skip_tx;
+		goto out;
 
 	pool = xs->pool;
 
@@ -959,12 +1007,11 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock,
 			xsk_generic_xmit(sk);
 	}
 
-skip_tx:
 	if (xs->rx && !xskq_prod_is_empty(xs->rx))
 		mask |= EPOLLIN | EPOLLRDNORM;
 	if (xs->tx && xsk_tx_writeable(xs))
 		mask |= EPOLLOUT | EPOLLWRNORM;
-
+out:
 	rcu_read_unlock();
 	return mask;
 }
@@ -1283,6 +1330,14 @@ struct xdp_umem_reg_v1 {
 	__u32 headroom;
 };
 
+struct xdp_umem_reg_v2 {
+	__u64 addr; /* Start of packet data area */
+	__u64 len; /* Length of packet data area */
+	__u32 chunk_size;
+	__u32 headroom;
+	__u32 flags;
+};
+
 static int xsk_setsockopt(struct socket *sock, int level, int optname,
 			  sockptr_t optval, unsigned int optlen)
 {
@@ -1326,8 +1381,10 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 
 		if (optlen < sizeof(struct xdp_umem_reg_v1))
 			return -EINVAL;
-		else if (optlen < sizeof(mr))
+		else if (optlen < sizeof(struct xdp_umem_reg_v2))
 			mr_size = sizeof(struct xdp_umem_reg_v1);
+		else if (optlen < sizeof(mr))
+			mr_size = sizeof(struct xdp_umem_reg_v2);
 
 		if (copy_from_sockptr(&mr, optval, mr_size))
 			return -EFAULT;