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

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 181 insertions, 54 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 559b215..626c273 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -31,6 +31,7 @@
 #include <linux/average.h>
 #include <linux/filter.h>
 #include <net/route.h>
+#include <net/xdp.h>
 
 static int napi_weight = NAPI_POLL_WEIGHT;
 module_param(napi_weight, int, 0444);
@@ -65,16 +66,39 @@ static const unsigned long guest_offloads[] = {
 	VIRTIO_NET_F_GUEST_UFO
 };
 
-struct virtnet_stats {
-	struct u64_stats_sync tx_syncp;
-	struct u64_stats_sync rx_syncp;
-	u64 tx_bytes;
-	u64 tx_packets;
+struct virtnet_stat_desc {
+	char desc[ETH_GSTRING_LEN];
+	size_t offset;
+};
+
+struct virtnet_sq_stats {
+	struct u64_stats_sync syncp;
+	u64 packets;
+	u64 bytes;
+};
+
+struct virtnet_rq_stats {
+	struct u64_stats_sync syncp;
+	u64 packets;
+	u64 bytes;
+};
 
-	u64 rx_bytes;
-	u64 rx_packets;
+#define VIRTNET_SQ_STAT(m)	offsetof(struct virtnet_sq_stats, m)
+#define VIRTNET_RQ_STAT(m)	offsetof(struct virtnet_rq_stats, m)
+
+static const struct virtnet_stat_desc virtnet_sq_stats_desc[] = {
+	{ "packets",	VIRTNET_SQ_STAT(packets) },
+	{ "bytes",	VIRTNET_SQ_STAT(bytes) },
+};
+
+static const struct virtnet_stat_desc virtnet_rq_stats_desc[] = {
+	{ "packets",	VIRTNET_RQ_STAT(packets) },
+	{ "bytes",	VIRTNET_RQ_STAT(bytes) },
 };
 
+#define VIRTNET_SQ_STATS_LEN	ARRAY_SIZE(virtnet_sq_stats_desc)
+#define VIRTNET_RQ_STATS_LEN	ARRAY_SIZE(virtnet_rq_stats_desc)
+
 /* Internal representation of a send virtqueue */
 struct send_queue {
 	/* Virtqueue associated with this send _queue */
@@ -86,6 +110,8 @@ struct send_queue {
 	/* Name of the send queue: output.$index */
 	char name[40];
 
+	struct virtnet_sq_stats stats;
+
 	struct napi_struct napi;
 };
 
@@ -98,6 +124,8 @@ struct receive_queue {
 
 	struct bpf_prog __rcu *xdp_prog;
 
+	struct virtnet_rq_stats stats;
+
 	/* Chain pages by the private ptr. */
 	struct page *pages;
 
@@ -115,6 +143,8 @@ struct receive_queue {
 
 	/* Name of this receive queue: input.$index */
 	char name[40];
+
+	struct xdp_rxq_info xdp_rxq;
 };
 
 struct virtnet_info {
@@ -149,9 +179,6 @@ struct virtnet_info {
 	/* Packet virtio header size */
 	u8 hdr_len;
 
-	/* Active statistics */
-	struct virtnet_stats __percpu *stats;
-
 	/* Work struct for refilling if we run low on memory. */
 	struct delayed_work refill;
 
@@ -261,9 +288,12 @@ static void virtqueue_napi_complete(struct napi_struct *napi,
 	int opaque;
 
 	opaque = virtqueue_enable_cb_prepare(vq);
-	if (napi_complete_done(napi, processed) &&
-	    unlikely(virtqueue_poll(vq, opaque)))
-		virtqueue_napi_schedule(napi, vq);
+	if (napi_complete_done(napi, processed)) {
+		if (unlikely(virtqueue_poll(vq, opaque)))
+			virtqueue_napi_schedule(napi, vq);
+	} else {
+		virtqueue_disable_cb(vq);
+	}
 }
 
 static void skb_xmit_done(struct virtqueue *vq)
@@ -556,6 +586,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 		xdp.data = xdp.data_hard_start + xdp_headroom;
 		xdp_set_data_meta_invalid(&xdp);
 		xdp.data_end = xdp.data + len;
+		xdp.rxq = &rq->xdp_rxq;
 		orig_data = xdp.data;
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
 
@@ -689,6 +720,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		xdp.data = data + vi->hdr_len;
 		xdp_set_data_meta_invalid(&xdp);
 		xdp.data_end = xdp.data + (len - vi->hdr_len);
+		xdp.rxq = &rq->xdp_rxq;
+
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
 
 		if (act != XDP_PASS)
@@ -1118,7 +1151,6 @@ 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;
 	void *buf;
-	struct virtnet_stats *stats = this_cpu_ptr(vi->stats);
 
 	if (!vi->big_packets || vi->mergeable_rx_bufs) {
 		void *ctx;
@@ -1141,10 +1173,10 @@ static int virtnet_receive(struct receive_queue *rq, int budget, bool *xdp_xmit)
 			schedule_delayed_work(&vi->refill, 0);
 	}
 
-	u64_stats_update_begin(&stats->rx_syncp);
-	stats->rx_bytes += bytes;
-	stats->rx_packets += received;
-	u64_stats_update_end(&stats->rx_syncp);
+	u64_stats_update_begin(&rq->stats.syncp);
+	rq->stats.bytes += bytes;
+	rq->stats.packets += received;
+	u64_stats_update_end(&rq->stats.syncp);
 
 	return received;
 }
@@ -1153,8 +1185,6 @@ static void free_old_xmit_skbs(struct send_queue *sq)
 {
 	struct sk_buff *skb;
 	unsigned int len;
-	struct virtnet_info *vi = sq->vq->vdev->priv;
-	struct virtnet_stats *stats = this_cpu_ptr(vi->stats);
 	unsigned int packets = 0;
 	unsigned int bytes = 0;
 
@@ -1173,10 +1203,10 @@ static void free_old_xmit_skbs(struct send_queue *sq)
 	if (!packets)
 		return;
 
-	u64_stats_update_begin(&stats->tx_syncp);
-	stats->tx_bytes += bytes;
-	stats->tx_packets += packets;
-	u64_stats_update_end(&stats->tx_syncp);
+	u64_stats_update_begin(&sq->stats.syncp);
+	sq->stats.bytes += bytes;
+	sq->stats.packets += packets;
+	u64_stats_update_end(&sq->stats.syncp);
 }
 
 static void virtnet_poll_cleantx(struct receive_queue *rq)
@@ -1222,13 +1252,18 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 static int virtnet_open(struct net_device *dev)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
-	int i;
+	int i, err;
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		if (i < vi->curr_queue_pairs)
 			/* Make sure we have some buffers: if oom use wq. */
 			if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
 				schedule_delayed_work(&vi->refill, 0);
+
+		err = xdp_rxq_info_reg(&vi->rq[i].xdp_rxq, dev, i);
+		if (err < 0)
+			return err;
+
 		virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
 		virtnet_napi_tx_enable(vi, vi->sq[i].vq, &vi->sq[i].napi);
 	}
@@ -1460,24 +1495,25 @@ static void virtnet_stats(struct net_device *dev,
 			  struct rtnl_link_stats64 *tot)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
-	int cpu;
 	unsigned int start;
+	int i;
 
-	for_each_possible_cpu(cpu) {
-		struct virtnet_stats *stats = per_cpu_ptr(vi->stats, cpu);
+	for (i = 0; i < vi->max_queue_pairs; i++) {
 		u64 tpackets, tbytes, rpackets, rbytes;
+		struct receive_queue *rq = &vi->rq[i];
+		struct send_queue *sq = &vi->sq[i];
 
 		do {
-			start = u64_stats_fetch_begin_irq(&stats->tx_syncp);
-			tpackets = stats->tx_packets;
-			tbytes   = stats->tx_bytes;
-		} while (u64_stats_fetch_retry_irq(&stats->tx_syncp, start));
+			start = u64_stats_fetch_begin_irq(&sq->stats.syncp);
+			tpackets = sq->stats.packets;
+			tbytes   = sq->stats.bytes;
+		} while (u64_stats_fetch_retry_irq(&sq->stats.syncp, start));
 
 		do {
-			start = u64_stats_fetch_begin_irq(&stats->rx_syncp);
-			rpackets = stats->rx_packets;
-			rbytes   = stats->rx_bytes;
-		} while (u64_stats_fetch_retry_irq(&stats->rx_syncp, start));
+			start = u64_stats_fetch_begin_irq(&rq->stats.syncp);
+			rpackets = rq->stats.packets;
+			rbytes   = rq->stats.bytes;
+		} while (u64_stats_fetch_retry_irq(&rq->stats.syncp, start));
 
 		tot->rx_packets += rpackets;
 		tot->tx_packets += tpackets;
@@ -1557,6 +1593,7 @@ static int virtnet_close(struct net_device *dev)
 	cancel_delayed_work_sync(&vi->refill);
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
+		xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq);
 		napi_disable(&vi->rq[i].napi);
 		virtnet_napi_tx_disable(&vi->sq[i].napi);
 	}
@@ -1814,6 +1851,83 @@ static int virtnet_set_channels(struct net_device *dev,
 	return err;
 }
 
+static void virtnet_get_strings(struct net_device *dev, u32 stringset, u8 *data)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	char *p = (char *)data;
+	unsigned int i, j;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < vi->curr_queue_pairs; i++) {
+			for (j = 0; j < VIRTNET_RQ_STATS_LEN; j++) {
+				snprintf(p, ETH_GSTRING_LEN, "rx_queue_%u_%s",
+					 i, virtnet_rq_stats_desc[j].desc);
+				p += ETH_GSTRING_LEN;
+			}
+		}
+
+		for (i = 0; i < vi->curr_queue_pairs; i++) {
+			for (j = 0; j < VIRTNET_SQ_STATS_LEN; j++) {
+				snprintf(p, ETH_GSTRING_LEN, "tx_queue_%u_%s",
+					 i, virtnet_sq_stats_desc[j].desc);
+				p += ETH_GSTRING_LEN;
+			}
+		}
+		break;
+	}
+}
+
+static int virtnet_get_sset_count(struct net_device *dev, int sset)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+
+	switch (sset) {
+	case ETH_SS_STATS:
+		return vi->curr_queue_pairs * (VIRTNET_RQ_STATS_LEN +
+					       VIRTNET_SQ_STATS_LEN);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void virtnet_get_ethtool_stats(struct net_device *dev,
+				      struct ethtool_stats *stats, u64 *data)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	unsigned int idx = 0, start, i, j;
+	const u8 *stats_base;
+	size_t offset;
+
+	for (i = 0; i < vi->curr_queue_pairs; i++) {
+		struct receive_queue *rq = &vi->rq[i];
+
+		stats_base = (u8 *)&rq->stats;
+		do {
+			start = u64_stats_fetch_begin_irq(&rq->stats.syncp);
+			for (j = 0; j < VIRTNET_RQ_STATS_LEN; j++) {
+				offset = virtnet_rq_stats_desc[j].offset;
+				data[idx + j] = *(u64 *)(stats_base + offset);
+			}
+		} while (u64_stats_fetch_retry_irq(&rq->stats.syncp, start));
+		idx += VIRTNET_RQ_STATS_LEN;
+	}
+
+	for (i = 0; i < vi->curr_queue_pairs; i++) {
+		struct send_queue *sq = &vi->sq[i];
+
+		stats_base = (u8 *)&sq->stats;
+		do {
+			start = u64_stats_fetch_begin_irq(&sq->stats.syncp);
+			for (j = 0; j < VIRTNET_SQ_STATS_LEN; j++) {
+				offset = virtnet_sq_stats_desc[j].offset;
+				data[idx + j] = *(u64 *)(stats_base + offset);
+			}
+		} while (u64_stats_fetch_retry_irq(&sq->stats.syncp, start));
+		idx += VIRTNET_SQ_STATS_LEN;
+	}
+}
+
 static void virtnet_get_channels(struct net_device *dev,
 				 struct ethtool_channels *channels)
 {
@@ -1891,10 +2005,31 @@ static void virtnet_init_settings(struct net_device *dev)
 	vi->duplex = DUPLEX_UNKNOWN;
 }
 
+static void virtnet_update_settings(struct virtnet_info *vi)
+{
+	u32 speed;
+	u8 duplex;
+
+	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_SPEED_DUPLEX))
+		return;
+
+	speed = virtio_cread32(vi->vdev, offsetof(struct virtio_net_config,
+						  speed));
+	if (ethtool_validate_speed(speed))
+		vi->speed = speed;
+	duplex = virtio_cread8(vi->vdev, offsetof(struct virtio_net_config,
+						  duplex));
+	if (ethtool_validate_duplex(duplex))
+		vi->duplex = duplex;
+}
+
 static const struct ethtool_ops virtnet_ethtool_ops = {
 	.get_drvinfo = virtnet_get_drvinfo,
 	.get_link = ethtool_op_get_link,
 	.get_ringparam = virtnet_get_ringparam,
+	.get_strings = virtnet_get_strings,
+	.get_sset_count = virtnet_get_sset_count,
+	.get_ethtool_stats = virtnet_get_ethtool_stats,
 	.set_channels = virtnet_set_channels,
 	.get_channels = virtnet_get_channels,
 	.get_ts_info = ethtool_op_get_ts_info,
@@ -2144,6 +2279,7 @@ static void virtnet_config_changed_work(struct work_struct *work)
 	vi->status = v;
 
 	if (vi->status & VIRTIO_NET_S_LINK_UP) {
+		virtnet_update_settings(vi);
 		netif_carrier_on(vi->dev);
 		netif_tx_wake_all_queues(vi->dev);
 	} else {
@@ -2386,6 +2522,9 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
 		sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg));
 		ewma_pkt_len_init(&vi->rq[i].mrg_avg_pkt_len);
 		sg_init_table(vi->sq[i].sg, ARRAY_SIZE(vi->sq[i].sg));
+
+		u64_stats_init(&vi->rq[i].stats.syncp);
+		u64_stats_init(&vi->sq[i].stats.syncp);
 	}
 
 	return 0;
@@ -2510,7 +2649,7 @@ static int virtnet_validate(struct virtio_device *vdev)
 
 static int virtnet_probe(struct virtio_device *vdev)
 {
-	int i, err;
+	int i, err = -ENOMEM;
 	struct net_device *dev;
 	struct virtnet_info *vi;
 	u16 max_queue_pairs;
@@ -2587,17 +2726,6 @@ static int virtnet_probe(struct virtio_device *vdev)
 	vi->dev = dev;
 	vi->vdev = vdev;
 	vdev->priv = vi;
-	vi->stats = alloc_percpu(struct virtnet_stats);
-	err = -ENOMEM;
-	if (vi->stats == NULL)
-		goto free;
-
-	for_each_possible_cpu(i) {
-		struct virtnet_stats *virtnet_stats;
-		virtnet_stats = per_cpu_ptr(vi->stats, i);
-		u64_stats_init(&virtnet_stats->tx_syncp);
-		u64_stats_init(&virtnet_stats->rx_syncp);
-	}
 
 	INIT_WORK(&vi->config_work, virtnet_config_changed_work);
 
@@ -2634,7 +2762,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 			 */
 			dev_err(&vdev->dev, "device MTU appears to have changed "
 				"it is now %d < %d", mtu, dev->min_mtu);
-			goto free_stats;
+			goto free;
 		}
 
 		dev->mtu = mtu;
@@ -2658,7 +2786,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 	/* Allocate/initialize the rx/tx queues, and invoke find_vqs */
 	err = init_vqs(vi);
 	if (err)
-		goto free_stats;
+		goto free;
 
 #ifdef CONFIG_SYSFS
 	if (vi->mergeable_rx_bufs)
@@ -2692,6 +2820,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 		schedule_work(&vi->config_work);
 	} else {
 		vi->status = VIRTIO_NET_S_LINK_UP;
+		virtnet_update_settings(vi);
 		netif_carrier_on(dev);
 	}
 
@@ -2712,8 +2841,6 @@ free_vqs:
 	cancel_delayed_work_sync(&vi->refill);
 	free_receive_page_frags(vi);
 	virtnet_del_vqs(vi);
-free_stats:
-	free_percpu(vi->stats);
 free:
 	free_netdev(dev);
 	return err;
@@ -2746,7 +2873,6 @@ static void virtnet_remove(struct virtio_device *vdev)
 
 	remove_vq_common(vi);
 
-	free_percpu(vi->stats);
 	free_netdev(vi->dev);
 }
 
@@ -2793,7 +2919,8 @@ static struct virtio_device_id id_table[] = {
 	VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN, \
 	VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, \
 	VIRTIO_NET_F_CTRL_MAC_ADDR, \
-	VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS
+	VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, \
+	VIRTIO_NET_F_SPEED_DUPLEX
 
 static unsigned int features[] = {
 	VIRTNET_FEATURES,