1 files changed, 388 insertions, 22 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7276d5a95bd0..08327e005ccc 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -22,6 +22,7 @@
 #include <linux/module.h>
 #include <linux/virtio.h>
 #include <linux/virtio_net.h>
+#include <linux/bpf.h>
 #include <linux/scatterlist.h>
 #include <linux/if_vlan.h>
 #include <linux/slab.h>
@@ -81,6 +82,8 @@ struct receive_queue {
 
 	struct napi_struct napi;
 
+	struct bpf_prog __rcu *xdp_prog;
+
 	/* Chain pages by the private ptr. */
 	struct page *pages;
 
@@ -111,6 +114,9 @@ struct virtnet_info {
 	/* # of queue pairs currently used by the driver */
 	u16 curr_queue_pairs;
 
+	/* # of XDP queue pairs currently used by the driver */
+	u16 xdp_queue_pairs;
+
 	/* I like... big packets and I cannot lie! */
 	bool big_packets;
 
@@ -324,6 +330,90 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	return skb;
 }
 
+static void virtnet_xdp_xmit(struct virtnet_info *vi,
+			     struct receive_queue *rq,
+			     struct send_queue *sq,
+			     struct xdp_buff *xdp)
+{
+	struct page *page = virt_to_head_page(xdp->data);
+	struct virtio_net_hdr_mrg_rxbuf *hdr;
+	unsigned int num_sg, len;
+	void *xdp_sent;
+	int err;
+
+	/* Free up any pending old buffers before queueing new ones. */
+	while ((xdp_sent = virtqueue_get_buf(sq->vq, &len)) != NULL) {
+		struct page *sent_page = virt_to_head_page(xdp_sent);
+
+		if (vi->mergeable_rx_bufs)
+			put_page(sent_page);
+		else
+			give_pages(rq, sent_page);
+	}
+
+	/* Zero header and leave csum up to XDP layers */
+	hdr = xdp->data;
+	memset(hdr, 0, vi->hdr_len);
+
+	num_sg = 1;
+	sg_init_one(sq->sg, xdp->data, xdp->data_end - xdp->data);
+	err = virtqueue_add_outbuf(sq->vq, sq->sg, num_sg,
+				   xdp->data, GFP_ATOMIC);
+	if (unlikely(err)) {
+		if (vi->mergeable_rx_bufs)
+			put_page(page);
+		else
+			give_pages(rq, page);
+		return; // On error abort to avoid unnecessary kick
+	} else if (!vi->mergeable_rx_bufs) {
+		/* If not mergeable bufs must be big packets so cleanup pages */
+		give_pages(rq, (struct page *)page->private);
+		page->private = 0;
+	}
+
+	virtqueue_kick(sq->vq);
+}
+
+static u32 do_xdp_prog(struct virtnet_info *vi,
+		       struct receive_queue *rq,
+		       struct bpf_prog *xdp_prog,
+		       struct page *page, int offset, int len)
+{
+	int hdr_padded_len;
+	struct xdp_buff xdp;
+	unsigned int qp;
+	u32 act;
+	u8 *buf;
+
+	buf = page_address(page) + offset;
+
+	if (vi->mergeable_rx_bufs)
+		hdr_padded_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
+	else
+		hdr_padded_len = sizeof(struct padded_vnet_hdr);
+
+	xdp.data = buf + hdr_padded_len;
+	xdp.data_end = xdp.data + (len - vi->hdr_len);
+
+	act = bpf_prog_run_xdp(xdp_prog, &xdp);
+	switch (act) {
+	case XDP_PASS:
+		return XDP_PASS;
+	case XDP_TX:
+		qp = vi->curr_queue_pairs -
+			vi->xdp_queue_pairs +
+			smp_processor_id();
+		xdp.data = buf + (vi->mergeable_rx_bufs ? 0 : 4);
+		virtnet_xdp_xmit(vi, rq, &vi->sq[qp], &xdp);
+		return XDP_TX;
+	default:
+		bpf_warn_invalid_xdp_action(act);
+	case XDP_ABORTED:
+	case XDP_DROP:
+		return XDP_DROP;
+	}
+}
+
 static struct sk_buff *receive_small(struct virtnet_info *vi, void *buf, unsigned int len)
 {
 	struct sk_buff * skb = buf;
@@ -340,17 +430,102 @@ static struct sk_buff *receive_big(struct net_device *dev,
 				   void *buf,
 				   unsigned int len)
 {
+	struct bpf_prog *xdp_prog;
 	struct page *page = buf;
-	struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE);
+	struct sk_buff *skb;
 
+	rcu_read_lock();
+	xdp_prog = rcu_dereference(rq->xdp_prog);
+	if (xdp_prog) {
+		struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
+		u32 act;
+
+		if (unlikely(hdr->hdr.gso_type || hdr->hdr.flags))
+			goto err_xdp;
+		act = do_xdp_prog(vi, rq, xdp_prog, page, 0, len);
+		switch (act) {
+		case XDP_PASS:
+			break;
+		case XDP_TX:
+			rcu_read_unlock();
+			goto xdp_xmit;
+		case XDP_DROP:
+		default:
+			goto err_xdp;
+		}
+	}
+	rcu_read_unlock();
+
+	skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE);
 	if (unlikely(!skb))
 		goto err;
 
 	return skb;
 
+err_xdp:
+	rcu_read_unlock();
 err:
 	dev->stats.rx_dropped++;
 	give_pages(rq, page);
+xdp_xmit:
+	return NULL;
+}
+
+/* The conditions to enable XDP should preclude the underlying device from
+ * sending packets across multiple buffers (num_buf > 1). However per spec
+ * it does not appear to be illegal to do so but rather just against convention.
+ * So in order to avoid making a system unresponsive the packets are pushed
+ * into a page and the XDP program is run. This will be extremely slow and we
+ * push a warning to the user to fix this as soon as possible. Fixing this may
+ * require resolving the underlying hardware to determine why multiple buffers
+ * are being received or simply loading the XDP program in the ingress stack
+ * after the skb is built because there is no advantage to running it here
+ * anymore.
+ */
+static struct page *xdp_linearize_page(struct receive_queue *rq,
+				       u16 num_buf,
+				       struct page *p,
+				       int offset,
+				       unsigned int *len)
+{
+	struct page *page = alloc_page(GFP_ATOMIC);
+	unsigned int page_off = 0;
+
+	if (!page)
+		return NULL;
+
+	memcpy(page_address(page) + page_off, page_address(p) + offset, *len);
+	page_off += *len;
+
+	while (--num_buf) {
+		unsigned int buflen;
+		unsigned long ctx;
+		void *buf;
+		int off;
+
+		ctx = (unsigned long)virtqueue_get_buf(rq->vq, &buflen);
+		if (unlikely(!ctx))
+			goto err_buf;
+
+		/* guard against a misconfigured or uncooperative backend that
+		 * is sending packet larger than the MTU.
+		 */
+		if ((page_off + buflen) > PAGE_SIZE)
+			goto err_buf;
+
+		buf = mergeable_ctx_to_buf_address(ctx);
+		p = virt_to_head_page(buf);
+		off = buf - page_address(p);
+
+		memcpy(page_address(page) + page_off,
+		       page_address(p) + off, buflen);
+		page_off += buflen;
+	}
+
+	*len = page_off;
+	return page;
+err_buf:
+	__free_pages(page, 0);
 	return NULL;
 }
 
@@ -365,11 +540,67 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
 	struct page *page = virt_to_head_page(buf);
 	int offset = buf - page_address(page);
-	unsigned int truesize = max(len, mergeable_ctx_to_buf_truesize(ctx));
+	struct sk_buff *head_skb, *curr_skb;
+	struct bpf_prog *xdp_prog;
+	unsigned int truesize;
+
+	head_skb = NULL;
+
+	rcu_read_lock();
+	xdp_prog = rcu_dereference(rq->xdp_prog);
+	if (xdp_prog) {
+		struct page *xdp_page;
+		u32 act;
+
+		/* No known backend devices should send packets with
+		 * more than a single buffer when XDP conditions are
+		 * met. However it is not strictly illegal so the case
+		 * is handled as an exception and a warning is thrown.
+		 */
+		if (unlikely(num_buf > 1)) {
+			bpf_warn_invalid_xdp_buffer();
+
+			/* linearize data for XDP */
+			xdp_page = xdp_linearize_page(rq, num_buf,
+						      page, offset, &len);
+			if (!xdp_page)
+				goto err_xdp;
+			offset = 0;
+		} else {
+			xdp_page = page;
+		}
 
-	struct sk_buff *head_skb = page_to_skb(vi, rq, page, offset, len,
-					       truesize);
-	struct sk_buff *curr_skb = head_skb;
+		/* Transient failure which in theory could occur if
+		 * in-flight packets from before XDP was enabled reach
+		 * the receive path after XDP is loaded. In practice I
+		 * was not able to create this condition.
+		 */
+		if (unlikely(hdr->hdr.gso_type || hdr->hdr.flags))
+			goto err_xdp;
+
+		act = do_xdp_prog(vi, rq, xdp_prog, page, offset, len);
+		switch (act) {
+		case XDP_PASS:
+			if (unlikely(xdp_page != page))
+				__free_pages(xdp_page, 0);
+			break;
+		case XDP_TX:
+			if (unlikely(xdp_page != page))
+				goto err_xdp;
+			rcu_read_unlock();
+			goto xdp_xmit;
+		case XDP_DROP:
+		default:
+			if (unlikely(xdp_page != page))
+				__free_pages(xdp_page, 0);
+			goto err_xdp;
+		}
+	}
+	rcu_read_unlock();
+
+	truesize = max(len, mergeable_ctx_to_buf_truesize(ctx));
+	head_skb = page_to_skb(vi, rq, page, offset, len, truesize);
+	curr_skb = head_skb;
 
 	if (unlikely(!curr_skb))
 		goto err_skb;
@@ -423,6 +654,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	ewma_pkt_len_add(&rq->mrg_avg_pkt_len, head_skb->len);
 	return head_skb;
 
+err_xdp:
+	rcu_read_unlock();
 err_skb:
 	put_page(page);
 	while (--num_buf) {
@@ -439,6 +672,7 @@ err_skb:
 err_buf:
 	dev->stats.rx_dropped++;
 	dev_kfree_skb(head_skb);
+xdp_xmit:
 	return NULL;
 }
 
@@ -969,12 +1203,17 @@ static int virtnet_set_mac_address(struct net_device *dev, void *p)
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct virtio_device *vdev = vi->vdev;
 	int ret;
-	struct sockaddr *addr = p;
+	struct sockaddr *addr;
 	struct scatterlist sg;
 
-	ret = eth_prepare_mac_addr_change(dev, p);
+	addr = kmalloc(sizeof(*addr), GFP_KERNEL);
+	if (!addr)
+		return -ENOMEM;
+	memcpy(addr, p, sizeof(*addr));
+
+	ret = eth_prepare_mac_addr_change(dev, addr);
 	if (ret)
-		return ret;
+		goto out;
 
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR)) {
 		sg_init_one(&sg, addr->sa_data, dev->addr_len);
@@ -982,7 +1221,8 @@ static int virtnet_set_mac_address(struct net_device *dev, void *p)
 					  VIRTIO_NET_CTRL_MAC_ADDR_SET, &sg)) {
 			dev_warn(&vdev->dev,
 				 "Failed to set mac address by vq command.\n");
-			return -EINVAL;
+			ret = -EINVAL;
+			goto out;
 		}
 	} else if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC) &&
 		   !virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) {
@@ -996,8 +1236,11 @@ static int virtnet_set_mac_address(struct net_device *dev, void *p)
 	}
 
 	eth_commit_mac_addr_change(dev, p);
+	ret = 0;
 
-	return 0;
+out:
+	kfree(addr);
+	return ret;
 }
 
 static struct rtnl_link_stats64 *virtnet_stats(struct net_device *dev,
@@ -1328,6 +1571,13 @@ static int virtnet_set_channels(struct net_device *dev,
 	if (queue_pairs > vi->max_queue_pairs || queue_pairs == 0)
 		return -EINVAL;
 
+	/* For now we don't support modifying channels while XDP is loaded
+	 * also when XDP is loaded all RX queues have XDP programs so we only
+	 * need to check a single RX queue.
+	 */
+	if (vi->rq[0].xdp_prog)
+		return -EINVAL;
+
 	get_online_cpus();
 	err = virtnet_set_queues(vi, queue_pairs);
 	if (!err) {
@@ -1419,17 +1669,93 @@ static const struct ethtool_ops virtnet_ethtool_ops = {
 	.set_settings = virtnet_set_settings,
 };
 
-#define MIN_MTU 68
-#define MAX_MTU 65535
-
-static int virtnet_change_mtu(struct net_device *dev, int new_mtu)
+static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog)
 {
-	if (new_mtu < MIN_MTU || new_mtu > MAX_MTU)
+	unsigned long int max_sz = PAGE_SIZE - sizeof(struct padded_vnet_hdr);
+	struct virtnet_info *vi = netdev_priv(dev);
+	struct bpf_prog *old_prog;
+	u16 xdp_qp = 0, curr_qp;
+	int i, err;
+
+	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) ||
+	    virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6)) {
+		netdev_warn(dev, "can't set XDP while host is implementing LRO, disable LRO first\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (vi->mergeable_rx_bufs && !vi->any_header_sg) {
+		netdev_warn(dev, "XDP expects header/data in single page, any_header_sg required\n");
 		return -EINVAL;
-	dev->mtu = new_mtu;
+	}
+
+	if (dev->mtu > max_sz) {
+		netdev_warn(dev, "XDP requires MTU less than %lu\n", max_sz);
+		return -EINVAL;
+	}
+
+	curr_qp = vi->curr_queue_pairs - vi->xdp_queue_pairs;
+	if (prog)
+		xdp_qp = nr_cpu_ids;
+
+	/* XDP requires extra queues for XDP_TX */
+	if (curr_qp + xdp_qp > vi->max_queue_pairs) {
+		netdev_warn(dev, "request %i queues but max is %i\n",
+			    curr_qp + xdp_qp, vi->max_queue_pairs);
+		return -ENOMEM;
+	}
+
+	err = virtnet_set_queues(vi, curr_qp + xdp_qp);
+	if (err) {
+		dev_warn(&dev->dev, "XDP Device queue allocation failure.\n");
+		return err;
+	}
+
+	if (prog) {
+		prog = bpf_prog_add(prog, vi->max_queue_pairs - 1);
+		if (IS_ERR(prog)) {
+			virtnet_set_queues(vi, curr_qp);
+			return PTR_ERR(prog);
+		}
+	}
+
+	vi->xdp_queue_pairs = xdp_qp;
+	netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp);
+
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		old_prog = rtnl_dereference(vi->rq[i].xdp_prog);
+		rcu_assign_pointer(vi->rq[i].xdp_prog, prog);
+		if (old_prog)
+			bpf_prog_put(old_prog);
+	}
+
 	return 0;
 }
 
+static bool virtnet_xdp_query(struct net_device *dev)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	int i;
+
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		if (vi->rq[i].xdp_prog)
+			return true;
+	}
+	return false;
+}
+
+static int virtnet_xdp(struct net_device *dev, struct netdev_xdp *xdp)
+{
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return virtnet_xdp_set(dev, xdp->prog);
+	case XDP_QUERY_PROG:
+		xdp->prog_attached = virtnet_xdp_query(dev);
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
 static const struct net_device_ops virtnet_netdev = {
 	.ndo_open            = virtnet_open,
 	.ndo_stop   	     = virtnet_close,
@@ -1437,7 +1763,6 @@ static const struct net_device_ops virtnet_netdev = {
 	.ndo_validate_addr   = eth_validate_addr,
 	.ndo_set_mac_address = virtnet_set_mac_address,
 	.ndo_set_rx_mode     = virtnet_set_rx_mode,
-	.ndo_change_mtu	     = virtnet_change_mtu,
 	.ndo_get_stats64     = virtnet_stats,
 	.ndo_vlan_rx_add_vid = virtnet_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid = virtnet_vlan_rx_kill_vid,
@@ -1447,6 +1772,7 @@ static const struct net_device_ops virtnet_netdev = {
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	.ndo_busy_poll		= virtnet_busy_poll,
 #endif
+	.ndo_xdp		= virtnet_xdp,
 };
 
 static void virtnet_config_changed_work(struct work_struct *work)
@@ -1508,12 +1834,20 @@ static void virtnet_free_queues(struct virtnet_info *vi)
 
 static void free_receive_bufs(struct virtnet_info *vi)
 {
+	struct bpf_prog *old_prog;
 	int i;
 
+	rtnl_lock();
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		while (vi->rq[i].pages)
 			__free_pages(get_a_page(&vi->rq[i], GFP_KERNEL), 0);
+
+		old_prog = rtnl_dereference(vi->rq[i].xdp_prog);
+		RCU_INIT_POINTER(vi->rq[i].xdp_prog, NULL);
+		if (old_prog)
+			bpf_prog_put(old_prog);
 	}
+	rtnl_unlock();
 }
 
 static void free_receive_page_frags(struct virtnet_info *vi)
@@ -1524,6 +1858,16 @@ static void free_receive_page_frags(struct virtnet_info *vi)
 			put_page(vi->rq[i].alloc_frag.page);
 }
 
+static bool is_xdp_queue(struct virtnet_info *vi, int q)
+{
+	if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs))
+		return false;
+	else if (q < vi->curr_queue_pairs)
+		return true;
+	else
+		return false;
+}
+
 static void free_unused_bufs(struct virtnet_info *vi)
 {
 	void *buf;
@@ -1531,8 +1875,12 @@ static void free_unused_bufs(struct virtnet_info *vi)
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		struct virtqueue *vq = vi->sq[i].vq;
-		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
-			dev_kfree_skb(buf);
+		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
+			if (!is_xdp_queue(vi, i))
+				dev_kfree_skb(buf);
+			else
+				put_page(virt_to_head_page(buf));
+		}
 	}
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
@@ -1753,6 +2101,9 @@ static bool virtnet_validate_features(struct virtio_device *vdev)
 	return true;
 }
 
+#define MIN_MTU ETH_MIN_MTU
+#define MAX_MTU ETH_MAX_MTU
+
 static int virtnet_probe(struct virtio_device *vdev)
 {
 	int i, err;
@@ -1826,6 +2177,10 @@ static int virtnet_probe(struct virtio_device *vdev)
 
 	dev->vlan_features = dev->features;
 
+	/* MTU range: 68 - 65535 */
+	dev->min_mtu = MIN_MTU;
+	dev->max_mtu = MAX_MTU;
+
 	/* Configuration may specify what MAC to use.  Otherwise random. */
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC))
 		virtio_cread_bytes(vdev,
@@ -1880,15 +2235,22 @@ static int virtnet_probe(struct virtio_device *vdev)
 		mtu = virtio_cread16(vdev,
 				     offsetof(struct virtio_net_config,
 					      mtu));
-		if (virtnet_change_mtu(dev, mtu))
+		if (mtu < dev->min_mtu) {
 			__virtio_clear_bit(vdev, VIRTIO_NET_F_MTU);
+		} else {
+			dev->mtu = mtu;
+			dev->max_mtu = mtu;
+		}
 	}
 
 	if (vi->any_header_sg)
 		dev->needed_headroom = vi->hdr_len;
 
-	/* Use single tx/rx queue pair as default */
-	vi->curr_queue_pairs = 1;
+	/* Enable multiqueue by default */
+	if (num_online_cpus() >= max_queue_pairs)
+		vi->curr_queue_pairs = max_queue_pairs;
+	else
+		vi->curr_queue_pairs = num_online_cpus();
 	vi->max_queue_pairs = max_queue_pairs;
 
 	/* Allocate/initialize the rx/tx queues, and invoke find_vqs */
@@ -1919,6 +2281,10 @@ static int virtnet_probe(struct virtio_device *vdev)
 		goto free_unregister_netdev;
 	}
 
+	rtnl_lock();
+	virtnet_set_queues(vi, vi->curr_queue_pairs);
+	rtnl_unlock();
+
 	/* Assume link up if device can't report link status,
 	   otherwise get link status from config. */
 	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) {