Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...

1 files changed, 69 insertions, 21 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 511f8339fa96..edf984406ba0 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -29,6 +29,7 @@
 #include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/average.h>
+#include <linux/filter.h>
 #include <net/route.h>
 
 static int napi_weight = NAPI_POLL_WEIGHT;
@@ -372,9 +373,20 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	return skb;
 }
 
-static bool virtnet_xdp_xmit(struct virtnet_info *vi,
-			     struct receive_queue *rq,
-			     struct xdp_buff *xdp)
+static void virtnet_xdp_flush(struct net_device *dev)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	struct send_queue *sq;
+	unsigned int qp;
+
+	qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id();
+	sq = &vi->sq[qp];
+
+	virtqueue_kick(sq->vq);
+}
+
+static bool __virtnet_xdp_xmit(struct virtnet_info *vi,
+			       struct xdp_buff *xdp)
 {
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
 	unsigned int len;
@@ -408,10 +420,19 @@ static bool virtnet_xdp_xmit(struct virtnet_info *vi,
 		return false;
 	}
 
-	virtqueue_kick(sq->vq);
 	return true;
 }
 
+static int virtnet_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	bool sent = __virtnet_xdp_xmit(vi, xdp);
+
+	if (!sent)
+		return -ENOSPC;
+	return 0;
+}
+
 static unsigned int virtnet_get_headroom(struct virtnet_info *vi)
 {
 	return vi->xdp_queue_pairs ? VIRTIO_XDP_HEADROOM : 0;
@@ -484,7 +505,8 @@ static struct sk_buff *receive_small(struct net_device *dev,
 				     struct virtnet_info *vi,
 				     struct receive_queue *rq,
 				     void *buf, void *ctx,
-				     unsigned int len)
+				     unsigned int len,
+				     bool *xdp_xmit)
 {
 	struct sk_buff *skb;
 	struct bpf_prog *xdp_prog;
@@ -494,7 +516,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 	unsigned int buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) +
 			      SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 	struct page *page = virt_to_head_page(buf);
-	unsigned int delta = 0;
+	unsigned int delta = 0, err;
 	struct page *xdp_page;
 	len -= vi->hdr_len;
 
@@ -532,6 +554,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 
 		xdp.data_hard_start = buf + VIRTNET_RX_PAD + vi->hdr_len;
 		xdp.data = xdp.data_hard_start + xdp_headroom;
+		xdp_set_data_meta_invalid(&xdp);
 		xdp.data_end = xdp.data + len;
 		orig_data = xdp.data;
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
@@ -542,8 +565,16 @@ static struct sk_buff *receive_small(struct net_device *dev,
 			delta = orig_data - xdp.data;
 			break;
 		case XDP_TX:
-			if (unlikely(!virtnet_xdp_xmit(vi, rq, &xdp)))
+			if (unlikely(!__virtnet_xdp_xmit(vi, &xdp)))
 				trace_xdp_exception(vi->dev, xdp_prog, act);
+			else
+				*xdp_xmit = true;
+			rcu_read_unlock();
+			goto xdp_xmit;
+		case XDP_REDIRECT:
+			err = xdp_do_redirect(dev, &xdp, xdp_prog);
+			if (!err)
+				*xdp_xmit = true;
 			rcu_read_unlock();
 			goto xdp_xmit;
 		default:
@@ -604,7 +635,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 					 struct receive_queue *rq,
 					 void *buf,
 					 void *ctx,
-					 unsigned int len)
+					 unsigned int len,
+					 bool *xdp_xmit)
 {
 	struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
 	u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
@@ -614,6 +646,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	struct bpf_prog *xdp_prog;
 	unsigned int truesize;
 	unsigned int headroom = mergeable_ctx_to_headroom(ctx);
+	int err;
 
 	head_skb = NULL;
 
@@ -654,9 +687,13 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		data = page_address(xdp_page) + offset;
 		xdp.data_hard_start = data - VIRTIO_XDP_HEADROOM + vi->hdr_len;
 		xdp.data = data + vi->hdr_len;
+		xdp_set_data_meta_invalid(&xdp);
 		xdp.data_end = xdp.data + (len - vi->hdr_len);
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
 
+		if (act != XDP_PASS)
+			ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
+
 		switch (act) {
 		case XDP_PASS:
 			/* recalculate offset to account for any header
@@ -672,18 +709,24 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 				put_page(page);
 				head_skb = page_to_skb(vi, rq, xdp_page,
 						       offset, len, PAGE_SIZE);
-				ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
 				return head_skb;
 			}
 			break;
 		case XDP_TX:
-			if (unlikely(!virtnet_xdp_xmit(vi, rq, &xdp)))
+			if (unlikely(!__virtnet_xdp_xmit(vi, &xdp)))
 				trace_xdp_exception(vi->dev, xdp_prog, act);
-			ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
+			else
+				*xdp_xmit = true;
 			if (unlikely(xdp_page != page))
 				goto err_xdp;
 			rcu_read_unlock();
 			goto xdp_xmit;
+		case XDP_REDIRECT:
+			err = xdp_do_redirect(dev, &xdp, xdp_prog);
+			if (!err)
+				*xdp_xmit = true;
+			rcu_read_unlock();
+			goto xdp_xmit;
 		default:
 			bpf_warn_invalid_xdp_action(act);
 		case XDP_ABORTED:
@@ -691,7 +734,6 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		case XDP_DROP:
 			if (unlikely(xdp_page != page))
 				__free_pages(xdp_page, 0);
-			ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
 			goto err_xdp;
 		}
 	}
@@ -789,7 +831,7 @@ xdp_xmit:
 }
 
 static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
-		       void *buf, unsigned int len, void **ctx)
+		       void *buf, unsigned int len, void **ctx, bool *xdp_xmit)
 {
 	struct net_device *dev = vi->dev;
 	struct sk_buff *skb;
@@ -810,11 +852,11 @@ static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 	}
 
 	if (vi->mergeable_rx_bufs)
-		skb = receive_mergeable(dev, vi, rq, buf, ctx, len);
+		skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit);
 	else if (vi->big_packets)
 		skb = receive_big(dev, vi, rq, buf, len);
 	else
-		skb = receive_small(dev, vi, rq, buf, ctx, len);
+		skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit);
 
 	if (unlikely(!skb))
 		return 0;
@@ -1072,7 +1114,7 @@ static void refill_work(struct work_struct *work)
 	}
 }
 
-static int virtnet_receive(struct receive_queue *rq, int budget)
+static int virtnet_receive(struct receive_queue *rq, int budget, bool *xdp_xmit)
 {
 	struct virtnet_info *vi = rq->vq->vdev->priv;
 	unsigned int len, received = 0, bytes = 0;
@@ -1084,13 +1126,13 @@ static int virtnet_receive(struct receive_queue *rq, int budget)
 
 		while (received < budget &&
 		       (buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) {
-			bytes += receive_buf(vi, rq, buf, len, ctx);
+			bytes += receive_buf(vi, rq, buf, len, ctx, xdp_xmit);
 			received++;
 		}
 	} else {
 		while (received < budget &&
 		       (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
-			bytes += receive_buf(vi, rq, buf, len, NULL);
+			bytes += receive_buf(vi, rq, buf, len, NULL, xdp_xmit);
 			received++;
 		}
 	}
@@ -1162,15 +1204,19 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 	struct receive_queue *rq =
 		container_of(napi, struct receive_queue, napi);
 	unsigned int received;
+	bool xdp_xmit = false;
 
 	virtnet_poll_cleantx(rq);
 
-	received = virtnet_receive(rq, budget);
+	received = virtnet_receive(rq, budget, &xdp_xmit);
 
 	/* Out of packets? */
 	if (received < budget)
 		virtqueue_napi_complete(napi, rq->vq, received);
 
+	if (xdp_xmit)
+		xdp_do_flush_map();
+
 	return received;
 }
 
@@ -2042,7 +2088,7 @@ static u32 virtnet_xdp_query(struct net_device *dev)
 	return 0;
 }
 
-static int virtnet_xdp(struct net_device *dev, struct netdev_xdp *xdp)
+static int virtnet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
@@ -2069,7 +2115,9 @@ static const struct net_device_ops virtnet_netdev = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = virtnet_netpoll,
 #endif
-	.ndo_xdp		= virtnet_xdp,
+	.ndo_bpf		= virtnet_xdp,
+	.ndo_xdp_xmit		= virtnet_xdp_xmit,
+	.ndo_xdp_flush		= virtnet_xdp_flush,
 	.ndo_features_check	= passthru_features_check,
 };