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, 37 insertions, 36 deletions

diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index bfc7969..17e529a 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -31,6 +31,7 @@
 #include <linux/vmalloc.h>
 #include <linux/rtnetlink.h>
 #include <linux/prefetch.h>
+#include <linux/reciprocal_div.h>
 
 #include <asm/sync_bitops.h>
 
@@ -72,7 +73,7 @@ static struct netvsc_device *alloc_net_device(void)
 
 	init_waitqueue_head(&net_device->wait_drain);
 	net_device->destroy = false;
-	atomic_set(&net_device->open_cnt, 0);
+
 	net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT;
 	net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT;
 
@@ -267,6 +268,11 @@ static int netvsc_init_buf(struct hv_device *device,
 	buf_size = device_info->recv_sections * device_info->recv_section_size;
 	buf_size = roundup(buf_size, PAGE_SIZE);
 
+	/* Legacy hosts only allow smaller receive buffer */
+	if (net_device->nvsp_version <= NVSP_PROTOCOL_VERSION_2)
+		buf_size = min_t(unsigned int, buf_size,
+				 NETVSC_RECEIVE_BUFFER_SIZE_LEGACY);
+
 	net_device->recv_buf = vzalloc(buf_size);
 	if (!net_device->recv_buf) {
 		netdev_err(ndev,
@@ -588,14 +594,11 @@ void netvsc_device_remove(struct hv_device *device)
  * Get the percentage of available bytes to write in the ring.
  * The return value is in range from 0 to 100.
  */
-static inline u32 hv_ringbuf_avail_percent(
-		struct hv_ring_buffer_info *ring_info)
+static u32 hv_ringbuf_avail_percent(const struct hv_ring_buffer_info *ring_info)
 {
-	u32 avail_read, avail_write;
-
-	hv_get_ringbuffer_availbytes(ring_info, &avail_read, &avail_write);
+	u32 avail_write = hv_get_bytes_to_write(ring_info);
 
-	return avail_write * 100 / ring_info->ring_datasize;
+	return reciprocal_divide(avail_write  * 100, netvsc_ring_reciprocal);
 }
 
 static inline void netvsc_free_send_slot(struct netvsc_device *net_device,
@@ -698,26 +701,26 @@ static u32 netvsc_get_next_send_section(struct netvsc_device *net_device)
 	return NETVSC_INVALID_INDEX;
 }
 
-static u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device,
-				   unsigned int section_index,
-				   u32 pend_size,
-				   struct hv_netvsc_packet *packet,
-				   struct rndis_message *rndis_msg,
-				   struct hv_page_buffer *pb,
-				   struct sk_buff *skb)
+static void netvsc_copy_to_send_buf(struct netvsc_device *net_device,
+				    unsigned int section_index,
+				    u32 pend_size,
+				    struct hv_netvsc_packet *packet,
+				    struct rndis_message *rndis_msg,
+				    struct hv_page_buffer *pb,
+				    bool xmit_more)
 {
 	char *start = net_device->send_buf;
 	char *dest = start + (section_index * net_device->send_section_size)
 		     + pend_size;
 	int i;
-	u32 msg_size = 0;
 	u32 padding = 0;
-	u32 remain = packet->total_data_buflen % net_device->pkt_align;
 	u32 page_count = packet->cp_partial ? packet->rmsg_pgcnt :
 		packet->page_buf_cnt;
+	u32 remain;
 
 	/* Add padding */
-	if (skb->xmit_more && remain && !packet->cp_partial) {
+	remain = packet->total_data_buflen & (net_device->pkt_align - 1);
+	if (xmit_more && remain) {
 		padding = net_device->pkt_align - remain;
 		rndis_msg->msg_len += padding;
 		packet->total_data_buflen += padding;
@@ -729,16 +732,11 @@ static u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device,
 		u32 len = pb[i].len;
 
 		memcpy(dest, (src + offset), len);
-		msg_size += len;
 		dest += len;
 	}
 
-	if (padding) {
+	if (padding)
 		memset(dest, 0, padding);
-		msg_size += padding;
-	}
-
-	return msg_size;
 }
 
 static inline int netvsc_send_pkt(
@@ -831,12 +829,13 @@ static inline void move_pkt_msd(struct hv_netvsc_packet **msd_send,
 }
 
 /* RCU already held by caller */
-int netvsc_send(struct net_device_context *ndev_ctx,
+int netvsc_send(struct net_device *ndev,
 		struct hv_netvsc_packet *packet,
 		struct rndis_message *rndis_msg,
 		struct hv_page_buffer *pb,
 		struct sk_buff *skb)
 {
+	struct net_device_context *ndev_ctx = netdev_priv(ndev);
 	struct netvsc_device *net_device
 		= rcu_dereference_bh(ndev_ctx->nvdev);
 	struct hv_device *device = ndev_ctx->device_ctx;
@@ -847,8 +846,7 @@ int netvsc_send(struct net_device_context *ndev_ctx,
 	struct multi_send_data *msdp;
 	struct hv_netvsc_packet *msd_send = NULL, *cur_send = NULL;
 	struct sk_buff *msd_skb = NULL;
-	bool try_batch;
-	bool xmit_more = (skb != NULL) ? skb->xmit_more : false;
+	bool try_batch, xmit_more;
 
 	/* If device is rescinded, return error and packet will get dropped. */
 	if (unlikely(!net_device || net_device->destroy))
@@ -899,10 +897,17 @@ int netvsc_send(struct net_device_context *ndev_ctx,
 		}
 	}
 
+	/* Keep aggregating only if stack says more data is coming
+	 * and not doing mixed modes send and not flow blocked
+	 */
+	xmit_more = skb->xmit_more &&
+		!packet->cp_partial &&
+		!netif_xmit_stopped(netdev_get_tx_queue(ndev, packet->q_idx));
+
 	if (section_index != NETVSC_INVALID_INDEX) {
 		netvsc_copy_to_send_buf(net_device,
 					section_index, msd_len,
-					packet, rndis_msg, pb, skb);
+					packet, rndis_msg, pb, xmit_more);
 
 		packet->send_buf_index = section_index;
 
@@ -922,7 +927,7 @@ int netvsc_send(struct net_device_context *ndev_ctx,
 		if (msdp->skb)
 			dev_consume_skb_any(msdp->skb);
 
-		if (xmit_more && !packet->cp_partial) {
+		if (xmit_more) {
 			msdp->skb = skb;
 			msdp->pkt = packet;
 			msdp->count++;
@@ -1085,7 +1090,7 @@ static int netvsc_receive(struct net_device *ndev,
 		u32 buflen = vmxferpage_packet->ranges[i].byte_count;
 
 		/* Pass it to the upper layer */
-		status = rndis_filter_receive(ndev, net_device, device,
+		status = rndis_filter_receive(ndev, net_device,
 					      channel, data, buflen);
 	}
 
@@ -1249,7 +1254,6 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 				const struct netvsc_device_info *device_info)
 {
 	int i, ret = 0;
-	int ring_size = device_info->ring_size;
 	struct netvsc_device *net_device;
 	struct net_device *ndev = hv_get_drvdata(device);
 	struct net_device_context *net_device_ctx = netdev_priv(ndev);
@@ -1261,8 +1265,6 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 	for (i = 0; i < VRSS_SEND_TAB_SIZE; i++)
 		net_device_ctx->tx_table[i] = 0;
 
-	net_device->ring_size = ring_size;
-
 	/* Because the device uses NAPI, all the interrupt batching and
 	 * control is done via Net softirq, not the channel handling
 	 */
@@ -1289,10 +1291,9 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 		       netvsc_poll, NAPI_POLL_WEIGHT);
 
 	/* Open the channel */
-	ret = vmbus_open(device->channel, ring_size * PAGE_SIZE,
-			 ring_size * PAGE_SIZE, NULL, 0,
-			 netvsc_channel_cb,
-			 net_device->chan_table);
+	ret = vmbus_open(device->channel, netvsc_ring_bytes,
+			 netvsc_ring_bytes,  NULL, 0,
+			 netvsc_channel_cb, net_device->chan_table);
 
 	if (ret != 0) {
 		netif_napi_del(&net_device->chan_table[0].napi);