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

Pull networking updates from David Miller:
 "Highlights:

   - Gustavo A. R. Silva keeps working on the implicit switch fallthru
     changes.

   - Support 802.11ax High-Efficiency wireless in cfg80211 et al, From
     Luca Coelho.

   - Re-enable ASPM in r8169, from Kai-Heng Feng.

   - Add virtual XFRM interfaces, which avoids all of the limitations of
     existing IPSEC tunnels. From Steffen Klassert.

   - Convert GRO over to use a hash table, so that when we have many
     flows active we don't traverse a long list during accumluation.

   - Many new self tests for routing, TC, tunnels, etc. Too many
     contributors to mention them all, but I'm really happy to keep
     seeing this stuff.

   - Hardware timestamping support for dpaa_eth/fsl-fman from Yangbo Lu.

   - Lots of cleanups and fixes in L2TP code from Guillaume Nault.

   - Add IPSEC offload support to netdevsim, from Shannon Nelson.

   - Add support for slotting with non-uniform distribution to netem
     packet scheduler, from Yousuk Seung.

   - Add UDP GSO support to mlx5e, from Boris Pismenny.

   - Support offloading of Team LAG in NFP, from John Hurley.

   - Allow to configure TX queue selection based upon RX queue, from
     Amritha Nambiar.

   - Support ethtool ring size configuration in aquantia, from Anton
     Mikaev.

   - Support DSCP and flowlabel per-transport in SCTP, from Xin Long.

   - Support list based batching and stack traversal of SKBs, this is
     very exciting work. From Edward Cree.

   - Busyloop optimizations in vhost_net, from Toshiaki Makita.

   - Introduce the ETF qdisc, which allows time based transmissions. IGB
     can offload this in hardware. From Vinicius Costa Gomes.

   - Add parameter support to devlink, from Moshe Shemesh.

   - Several multiplication and division optimizations for BPF JIT in
     nfp driver, from Jiong Wang.

   - Lots of prepatory work to make more of the packet scheduler layer
     lockless, when possible, from Vlad Buslov.

   - Add ACK filter and NAT awareness to sch_cake packet scheduler, from
     Toke Høiland-Jørgensen.

   - Support regions and region snapshots in devlink, from Alex Vesker.

   - Allow to attach XDP programs to both HW and SW at the same time on
     a given device, with initial support in nfp. From Jakub Kicinski.

   - Add TLS RX offload and support in mlx5, from Ilya Lesokhin.

   - Use PHYLIB in r8169 driver, from Heiner Kallweit.

   - All sorts of changes to support Spectrum 2 in mlxsw driver, from
     Ido Schimmel.

   - PTP support in mv88e6xxx DSA driver, from Andrew Lunn.

   - Make TCP_USER_TIMEOUT socket option more accurate, from Jon
     Maxwell.

   - Support for templates in packet scheduler classifier, from Jiri
     Pirko.

   - IPV6 support in RDS, from Ka-Cheong Poon.

   - Native tproxy support in nf_tables, from Máté Eckl.

   - Maintain IP fragment queue in an rbtree, but optimize properly for
     in-order frags. From Peter Oskolkov.

   - Improvde handling of ACKs on hole repairs, from Yuchung Cheng"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1996 commits)
  bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT"
  hv/netvsc: Fix NULL dereference at single queue mode fallback
  net: filter: mark expected switch fall-through
  xen-netfront: fix warn message as irq device name has '/'
  cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0
  net: dsa: mv88e6xxx: missing unlock on error path
  rds: fix building with IPV6=m
  inet/connection_sock: prefer _THIS_IP_ to current_text_addr
  net: dsa: mv88e6xxx: bitwise vs logical bug
  net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd()
  ieee802154: hwsim: using right kind of iteration
  net: hns3: Add vlan filter setting by ethtool command -K
  net: hns3: Set tx ring' tc info when netdev is up
  net: hns3: Remove tx ring BD len register in hns3_enet
  net: hns3: Fix desc num set to default when setting channel
  net: hns3: Fix for phy link issue when using marvell phy driver
  net: hns3: Fix for information of phydev lost problem when down/up
  net: hns3: Fix for command format parsing error in hclge_is_all_function_id_zero
  net: hns3: Add support for serdes loopback selftest
  bnxt_en: take coredump_record structure off stack
  ...

3 files changed, 118 insertions, 7 deletions

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 4b6e308199d2..a32ded5b4f41 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -873,6 +873,17 @@ struct netvsc_ethtool_stats {
 	unsigned long wake_queue;
 };
 
+struct netvsc_ethtool_pcpu_stats {
+	u64     rx_packets;
+	u64     rx_bytes;
+	u64     tx_packets;
+	u64     tx_bytes;
+	u64     vf_rx_packets;
+	u64     vf_rx_bytes;
+	u64     vf_tx_packets;
+	u64     vf_tx_bytes;
+};
+
 struct netvsc_vf_pcpu_stats {
 	u64     rx_packets;
 	u64     rx_bytes;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index dd1d6e115145..20275d1e6f9a 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -329,7 +329,7 @@ static u16 netvsc_pick_tx(struct net_device *ndev, struct sk_buff *skb)
 }
 
 static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
-			       void *accel_priv,
+			       struct net_device *sb_dev,
 			       select_queue_fallback_t fallback)
 {
 	struct net_device_context *ndc = netdev_priv(ndev);
@@ -343,9 +343,9 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 
 		if (vf_ops->ndo_select_queue)
 			txq = vf_ops->ndo_select_queue(vf_netdev, skb,
-						       accel_priv, fallback);
+						       sb_dev, fallback);
 		else
-			txq = fallback(vf_netdev, skb);
+			txq = fallback(vf_netdev, skb, NULL);
 
 		/* Record the queue selected by VF so that it can be
 		 * used for common case where VF has more queues than
@@ -1118,6 +1118,64 @@ static void netvsc_get_vf_stats(struct net_device *net,
 	}
 }
 
+static void netvsc_get_pcpu_stats(struct net_device *net,
+				  struct netvsc_ethtool_pcpu_stats *pcpu_tot)
+{
+	struct net_device_context *ndev_ctx = netdev_priv(net);
+	struct netvsc_device *nvdev = rcu_dereference_rtnl(ndev_ctx->nvdev);
+	int i;
+
+	/* fetch percpu stats of vf */
+	for_each_possible_cpu(i) {
+		const struct netvsc_vf_pcpu_stats *stats =
+			per_cpu_ptr(ndev_ctx->vf_stats, i);
+		struct netvsc_ethtool_pcpu_stats *this_tot = &pcpu_tot[i];
+		unsigned int start;
+
+		do {
+			start = u64_stats_fetch_begin_irq(&stats->syncp);
+			this_tot->vf_rx_packets = stats->rx_packets;
+			this_tot->vf_tx_packets = stats->tx_packets;
+			this_tot->vf_rx_bytes = stats->rx_bytes;
+			this_tot->vf_tx_bytes = stats->tx_bytes;
+		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+		this_tot->rx_packets = this_tot->vf_rx_packets;
+		this_tot->tx_packets = this_tot->vf_tx_packets;
+		this_tot->rx_bytes   = this_tot->vf_rx_bytes;
+		this_tot->tx_bytes   = this_tot->vf_tx_bytes;
+	}
+
+	/* fetch percpu stats of netvsc */
+	for (i = 0; i < nvdev->num_chn; i++) {
+		const struct netvsc_channel *nvchan = &nvdev->chan_table[i];
+		const struct netvsc_stats *stats;
+		struct netvsc_ethtool_pcpu_stats *this_tot =
+			&pcpu_tot[nvchan->channel->target_cpu];
+		u64 packets, bytes;
+		unsigned int start;
+
+		stats = &nvchan->tx_stats;
+		do {
+			start = u64_stats_fetch_begin_irq(&stats->syncp);
+			packets = stats->packets;
+			bytes = stats->bytes;
+		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+
+		this_tot->tx_bytes	+= bytes;
+		this_tot->tx_packets	+= packets;
+
+		stats = &nvchan->rx_stats;
+		do {
+			start = u64_stats_fetch_begin_irq(&stats->syncp);
+			packets = stats->packets;
+			bytes = stats->bytes;
+		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+
+		this_tot->rx_bytes	+= bytes;
+		this_tot->rx_packets	+= packets;
+	}
+}
+
 static void netvsc_get_stats64(struct net_device *net,
 			       struct rtnl_link_stats64 *t)
 {
@@ -1215,6 +1273,23 @@ static const struct {
 	{ "rx_no_memory", offsetof(struct netvsc_ethtool_stats, rx_no_memory) },
 	{ "stop_queue", offsetof(struct netvsc_ethtool_stats, stop_queue) },
 	{ "wake_queue", offsetof(struct netvsc_ethtool_stats, wake_queue) },
+}, pcpu_stats[] = {
+	{ "cpu%u_rx_packets",
+		offsetof(struct netvsc_ethtool_pcpu_stats, rx_packets) },
+	{ "cpu%u_rx_bytes",
+		offsetof(struct netvsc_ethtool_pcpu_stats, rx_bytes) },
+	{ "cpu%u_tx_packets",
+		offsetof(struct netvsc_ethtool_pcpu_stats, tx_packets) },
+	{ "cpu%u_tx_bytes",
+		offsetof(struct netvsc_ethtool_pcpu_stats, tx_bytes) },
+	{ "cpu%u_vf_rx_packets",
+		offsetof(struct netvsc_ethtool_pcpu_stats, vf_rx_packets) },
+	{ "cpu%u_vf_rx_bytes",
+		offsetof(struct netvsc_ethtool_pcpu_stats, vf_rx_bytes) },
+	{ "cpu%u_vf_tx_packets",
+		offsetof(struct netvsc_ethtool_pcpu_stats, vf_tx_packets) },
+	{ "cpu%u_vf_tx_bytes",
+		offsetof(struct netvsc_ethtool_pcpu_stats, vf_tx_bytes) },
 }, vf_stats[] = {
 	{ "vf_rx_packets", offsetof(struct netvsc_vf_pcpu_stats, rx_packets) },
 	{ "vf_rx_bytes",   offsetof(struct netvsc_vf_pcpu_stats, rx_bytes) },
@@ -1226,6 +1301,9 @@ static const struct {
 #define NETVSC_GLOBAL_STATS_LEN	ARRAY_SIZE(netvsc_stats)
 #define NETVSC_VF_STATS_LEN	ARRAY_SIZE(vf_stats)
 
+/* statistics per queue (rx/tx packets/bytes) */
+#define NETVSC_PCPU_STATS_LEN (num_present_cpus() * ARRAY_SIZE(pcpu_stats))
+
 /* 4 statistics per queue (rx/tx packets/bytes) */
 #define NETVSC_QUEUE_STATS_LEN(dev) ((dev)->num_chn * 4)
 
@@ -1241,7 +1319,8 @@ static int netvsc_get_sset_count(struct net_device *dev, int string_set)
 	case ETH_SS_STATS:
 		return NETVSC_GLOBAL_STATS_LEN
 			+ NETVSC_VF_STATS_LEN
-			+ NETVSC_QUEUE_STATS_LEN(nvdev);
+			+ NETVSC_QUEUE_STATS_LEN(nvdev)
+			+ NETVSC_PCPU_STATS_LEN;
 	default:
 		return -EINVAL;
 	}
@@ -1255,9 +1334,10 @@ static void netvsc_get_ethtool_stats(struct net_device *dev,
 	const void *nds = &ndc->eth_stats;
 	const struct netvsc_stats *qstats;
 	struct netvsc_vf_pcpu_stats sum;
+	struct netvsc_ethtool_pcpu_stats *pcpu_sum;
 	unsigned int start;
 	u64 packets, bytes;
-	int i, j;
+	int i, j, cpu;
 
 	if (!nvdev)
 		return;
@@ -1289,6 +1369,19 @@ static void netvsc_get_ethtool_stats(struct net_device *dev,
 		data[i++] = packets;
 		data[i++] = bytes;
 	}
+
+	pcpu_sum = kvmalloc_array(num_possible_cpus(),
+				  sizeof(struct netvsc_ethtool_pcpu_stats),
+				  GFP_KERNEL);
+	netvsc_get_pcpu_stats(dev, pcpu_sum);
+	for_each_present_cpu(cpu) {
+		struct netvsc_ethtool_pcpu_stats *this_sum = &pcpu_sum[cpu];
+
+		for (j = 0; j < ARRAY_SIZE(pcpu_stats); j++)
+			data[i++] = *(u64 *)((void *)this_sum
+					     + pcpu_stats[j].offset);
+	}
+	kvfree(pcpu_sum);
 }
 
 static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
@@ -1296,7 +1389,7 @@ static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 	struct net_device_context *ndc = netdev_priv(dev);
 	struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev);
 	u8 *p = data;
-	int i;
+	int i, cpu;
 
 	if (!nvdev)
 		return;
@@ -1324,6 +1417,13 @@ static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 			p += ETH_GSTRING_LEN;
 		}
 
+		for_each_present_cpu(cpu) {
+			for (i = 0; i < ARRAY_SIZE(pcpu_stats); i++) {
+				sprintf(p, pcpu_stats[i].name, cpu);
+				p += ETH_GSTRING_LEN;
+			}
+		}
+
 		break;
 	}
 }
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 408ece27131c..2a5209f23f29 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1338,7 +1338,7 @@ out:
 	/* setting up multiple channels failed */
 	net_device->max_chn = 1;
 	net_device->num_chn = 1;
-	return 0;
+	return net_device;
 
 err_dev_remv:
 	rndis_filter_device_remove(dev, net_device);