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, 43 insertions, 68 deletions

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 5129647d420c..c5584c2d440e 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -35,6 +35,7 @@
 #include <linux/slab.h>
 #include <linux/rtnetlink.h>
 #include <linux/netpoll.h>
+#include <linux/reciprocal_div.h>
 
 #include <net/arp.h>
 #include <net/route.h>
@@ -46,17 +47,15 @@
 #include "hyperv_net.h"
 
 #define RING_SIZE_MIN		64
-#define NETVSC_MIN_TX_SECTIONS	10
-#define NETVSC_DEFAULT_TX	192	/* ~1M */
-#define NETVSC_MIN_RX_SECTIONS	10	/* ~64K */
-#define NETVSC_DEFAULT_RX	10485   /* Max ~16M */
 
 #define LINKCHANGE_INT (2 * HZ)
 #define VF_TAKEOVER_INT (HZ / 10)
 
-static int ring_size = 128;
-module_param(ring_size, int, S_IRUGO);
+static unsigned int ring_size __ro_after_init = 128;
+module_param(ring_size, uint, S_IRUGO);
 MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)");
+unsigned int netvsc_ring_bytes __ro_after_init;
+struct reciprocal_value netvsc_ring_reciprocal __ro_after_init;
 
 static const u32 default_msg = NETIF_MSG_DRV | NETIF_MSG_PROBE |
 				NETIF_MSG_LINK | NETIF_MSG_IFUP |
@@ -174,17 +173,15 @@ out:
 	return ret;
 }
 
-static void *init_ppi_data(struct rndis_message *msg, u32 ppi_size,
-			   int pkt_type)
+static inline void *init_ppi_data(struct rndis_message *msg,
+				  u32 ppi_size, u32 pkt_type)
 {
-	struct rndis_packet *rndis_pkt;
+	struct rndis_packet *rndis_pkt = &msg->msg.pkt;
 	struct rndis_per_packet_info *ppi;
 
-	rndis_pkt = &msg->msg.pkt;
 	rndis_pkt->data_offset += ppi_size;
-
-	ppi = (struct rndis_per_packet_info *)((void *)rndis_pkt +
-		rndis_pkt->per_pkt_info_offset + rndis_pkt->per_pkt_info_len);
+	ppi = (void *)rndis_pkt + rndis_pkt->per_pkt_info_offset
+		+ rndis_pkt->per_pkt_info_len;
 
 	ppi->size = ppi_size;
 	ppi->type = pkt_type;
@@ -192,7 +189,7 @@ static void *init_ppi_data(struct rndis_message *msg, u32 ppi_size,
 
 	rndis_pkt->per_pkt_info_len += ppi_size;
 
-	return ppi;
+	return ppi + 1;
 }
 
 /* Azure hosts don't support non-TCP port numbers in hashing for fragmented
@@ -469,10 +466,8 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	int ret;
 	unsigned int num_data_pgs;
 	struct rndis_message *rndis_msg;
-	struct rndis_packet *rndis_pkt;
 	struct net_device *vf_netdev;
 	u32 rndis_msg_size;
-	struct rndis_per_packet_info *ppi;
 	u32 hash;
 	struct hv_page_buffer pb[MAX_PAGE_BUFFER_COUNT];
 
@@ -527,34 +522,36 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 
 	rndis_msg = (struct rndis_message *)skb->head;
 
-	memset(rndis_msg, 0, RNDIS_AND_PPI_SIZE);
-
 	/* Add the rndis header */
 	rndis_msg->ndis_msg_type = RNDIS_MSG_PACKET;
 	rndis_msg->msg_len = packet->total_data_buflen;
-	rndis_pkt = &rndis_msg->msg.pkt;
-	rndis_pkt->data_offset = sizeof(struct rndis_packet);
-	rndis_pkt->data_len = packet->total_data_buflen;
-	rndis_pkt->per_pkt_info_offset = sizeof(struct rndis_packet);
+
+	rndis_msg->msg.pkt = (struct rndis_packet) {
+		.data_offset = sizeof(struct rndis_packet),
+		.data_len = packet->total_data_buflen,
+		.per_pkt_info_offset = sizeof(struct rndis_packet),
+	};
 
 	rndis_msg_size = RNDIS_MESSAGE_SIZE(struct rndis_packet);
 
 	hash = skb_get_hash_raw(skb);
 	if (hash != 0 && net->real_num_tx_queues > 1) {
+		u32 *hash_info;
+
 		rndis_msg_size += NDIS_HASH_PPI_SIZE;
-		ppi = init_ppi_data(rndis_msg, NDIS_HASH_PPI_SIZE,
-				    NBL_HASH_VALUE);
-		*(u32 *)((void *)ppi + ppi->ppi_offset) = hash;
+		hash_info = init_ppi_data(rndis_msg, NDIS_HASH_PPI_SIZE,
+					  NBL_HASH_VALUE);
+		*hash_info = hash;
 	}
 
 	if (skb_vlan_tag_present(skb)) {
 		struct ndis_pkt_8021q_info *vlan;
 
 		rndis_msg_size += NDIS_VLAN_PPI_SIZE;
-		ppi = init_ppi_data(rndis_msg, NDIS_VLAN_PPI_SIZE,
-				    IEEE_8021Q_INFO);
+		vlan = init_ppi_data(rndis_msg, NDIS_VLAN_PPI_SIZE,
+				     IEEE_8021Q_INFO);
 
-		vlan = (void *)ppi + ppi->ppi_offset;
+		vlan->value = 0;
 		vlan->vlanid = skb->vlan_tci & VLAN_VID_MASK;
 		vlan->pri = (skb->vlan_tci & VLAN_PRIO_MASK) >>
 				VLAN_PRIO_SHIFT;
@@ -564,11 +561,10 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 		struct ndis_tcp_lso_info *lso_info;
 
 		rndis_msg_size += NDIS_LSO_PPI_SIZE;
-		ppi = init_ppi_data(rndis_msg, NDIS_LSO_PPI_SIZE,
-				    TCP_LARGESEND_PKTINFO);
-
-		lso_info = (void *)ppi + ppi->ppi_offset;
+		lso_info = init_ppi_data(rndis_msg, NDIS_LSO_PPI_SIZE,
+					 TCP_LARGESEND_PKTINFO);
 
+		lso_info->value = 0;
 		lso_info->lso_v2_transmit.type = NDIS_TCP_LARGE_SEND_OFFLOAD_V2_TYPE;
 		if (skb->protocol == htons(ETH_P_IP)) {
 			lso_info->lso_v2_transmit.ip_version =
@@ -593,12 +589,10 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 			struct ndis_tcp_ip_checksum_info *csum_info;
 
 			rndis_msg_size += NDIS_CSUM_PPI_SIZE;
-			ppi = init_ppi_data(rndis_msg, NDIS_CSUM_PPI_SIZE,
-					    TCPIP_CHKSUM_PKTINFO);
-
-			csum_info = (struct ndis_tcp_ip_checksum_info *)((void *)ppi +
-									 ppi->ppi_offset);
+			csum_info = init_ppi_data(rndis_msg, NDIS_CSUM_PPI_SIZE,
+						  TCPIP_CHKSUM_PKTINFO);
 
+			csum_info->value = 0;
 			csum_info->transmit.tcp_header_offset = skb_transport_offset(skb);
 
 			if (skb->protocol == htons(ETH_P_IP)) {
@@ -632,7 +626,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	/* timestamp packet in software */
 	skb_tx_timestamp(skb);
 
-	ret = netvsc_send(net_device_ctx, packet, rndis_msg, pb, skb);
+	ret = netvsc_send(net, packet, rndis_msg, pb, skb);
 	if (likely(ret == 0))
 		return NETDEV_TX_OK;
 
@@ -658,22 +652,14 @@ no_memory:
 /*
  * netvsc_linkstatus_callback - Link up/down notification
  */
-void netvsc_linkstatus_callback(struct hv_device *device_obj,
+void netvsc_linkstatus_callback(struct net_device *net,
 				struct rndis_message *resp)
 {
 	struct rndis_indicate_status *indicate = &resp->msg.indicate_status;
-	struct net_device *net;
-	struct net_device_context *ndev_ctx;
+	struct net_device_context *ndev_ctx = netdev_priv(net);
 	struct netvsc_reconfig *event;
 	unsigned long flags;
 
-	net = hv_get_drvdata(device_obj);
-
-	if (!net)
-		return;
-
-	ndev_ctx = netdev_priv(net);
-
 	/* Update the physical link speed when changing to another vSwitch */
 	if (indicate->status == RNDIS_STATUS_LINK_SPEED_CHANGE) {
 		u32 speed;
@@ -753,34 +739,26 @@ static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net,
  * "wire" on the specified device.
  */
 int netvsc_recv_callback(struct net_device *net,
+			 struct netvsc_device *net_device,
 			 struct vmbus_channel *channel,
 			 void  *data, u32 len,
 			 const struct ndis_tcp_ip_checksum_info *csum_info,
 			 const struct ndis_pkt_8021q_info *vlan)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(net);
-	struct netvsc_device *net_device;
 	u16 q_idx = channel->offermsg.offer.sub_channel_index;
-	struct netvsc_channel *nvchan;
+	struct netvsc_channel *nvchan = &net_device->chan_table[q_idx];
 	struct sk_buff *skb;
 	struct netvsc_stats *rx_stats;
 
 	if (net->reg_state != NETREG_REGISTERED)
 		return NVSP_STAT_FAIL;
 
-	rcu_read_lock();
-	net_device = rcu_dereference(net_device_ctx->nvdev);
-	if (unlikely(!net_device))
-		goto drop;
-
-	nvchan = &net_device->chan_table[q_idx];
-
 	/* Allocate a skb - TODO direct I/O to pages? */
 	skb = netvsc_alloc_recv_skb(net, &nvchan->napi,
 				    csum_info, vlan, data, len);
 	if (unlikely(!skb)) {
-drop:
-		++net->stats.rx_dropped;
+		++net_device_ctx->eth_stats.rx_no_memory;
 		rcu_read_unlock();
 		return NVSP_STAT_FAIL;
 	}
@@ -804,8 +782,6 @@ drop:
 	u64_stats_update_end(&rx_stats->syncp);
 
 	napi_gro_receive(&nvchan->napi, skb);
-	rcu_read_unlock();
-
 	return 0;
 }
 
@@ -860,7 +836,6 @@ static int netvsc_set_channels(struct net_device *net,
 
 	memset(&device_info, 0, sizeof(device_info));
 	device_info.num_chn = count;
-	device_info.ring_size = ring_size;
 	device_info.send_sections = nvdev->send_section_cnt;
 	device_info.send_section_size = nvdev->send_section_size;
 	device_info.recv_sections = nvdev->recv_section_cnt;
@@ -975,7 +950,6 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 		rndis_filter_close(nvdev);
 
 	memset(&device_info, 0, sizeof(device_info));
-	device_info.ring_size = ring_size;
 	device_info.num_chn = nvdev->num_chn;
 	device_info.send_sections = nvdev->send_section_cnt;
 	device_info.send_section_size = nvdev->send_section_size;
@@ -1133,12 +1107,13 @@ static const struct {
 	u16 offset;
 } netvsc_stats[] = {
 	{ "tx_scattered", offsetof(struct netvsc_ethtool_stats, tx_scattered) },
-	{ "tx_no_memory",  offsetof(struct netvsc_ethtool_stats, tx_no_memory) },
+	{ "tx_no_memory", offsetof(struct netvsc_ethtool_stats, tx_no_memory) },
 	{ "tx_no_space",  offsetof(struct netvsc_ethtool_stats, tx_no_space) },
 	{ "tx_too_big",	  offsetof(struct netvsc_ethtool_stats, tx_too_big) },
 	{ "tx_busy",	  offsetof(struct netvsc_ethtool_stats, tx_busy) },
 	{ "tx_send_full", offsetof(struct netvsc_ethtool_stats, tx_send_full) },
 	{ "rx_comp_busy", offsetof(struct netvsc_ethtool_stats, rx_comp_busy) },
+	{ "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) },
 }, vf_stats[] = {
@@ -1539,7 +1514,6 @@ static int netvsc_set_ringparam(struct net_device *ndev,
 
 	memset(&device_info, 0, sizeof(device_info));
 	device_info.num_chn = nvdev->num_chn;
-	device_info.ring_size = ring_size;
 	device_info.send_sections = new_tx;
 	device_info.send_section_size = nvdev->send_section_size;
 	device_info.recv_sections = new_rx;
@@ -1995,7 +1969,6 @@ static int netvsc_probe(struct hv_device *dev,
 
 	/* Notify the netvsc driver of the new device */
 	memset(&device_info, 0, sizeof(device_info));
-	device_info.ring_size = ring_size;
 	device_info.num_chn = VRSS_CHANNEL_DEFAULT;
 	device_info.send_sections = NETVSC_DEFAULT_TX;
 	device_info.send_section_size = NETVSC_SEND_SECTION_SIZE;
@@ -2158,11 +2131,13 @@ static int __init netvsc_drv_init(void)
 
 	if (ring_size < RING_SIZE_MIN) {
 		ring_size = RING_SIZE_MIN;
-		pr_info("Increased ring_size to %d (min allowed)\n",
+		pr_info("Increased ring_size to %u (min allowed)\n",
 			ring_size);
 	}
-	ret = vmbus_driver_register(&netvsc_drv);
+	netvsc_ring_bytes = ring_size * PAGE_SIZE;
+	netvsc_ring_reciprocal = reciprocal_value(netvsc_ring_bytes);
 
+	ret = vmbus_driver_register(&netvsc_drv);
 	if (ret)
 		return ret;