From 7f5d5af0b2f859f09b3dcb16a00b800fa48d9288 Mon Sep 17 00:00:00 2001
From: Haiyang Zhang <haiyangz@microsoft.com>
Date: Thu, 4 Aug 2016 10:42:15 -0700
Subject: hv_netvsc: Add handler for physical link speed change

On Hyper-V host 2016 and later, VMs gets an event message of the physical
link speed when vSwitch is changed. This patch handles this message, so
the updated link speed can be reported by ethtool.

Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/hyperv_net.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/net/hyperv/hyperv_net.h')

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 467fb8b4d083..c1403fda874c 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -490,6 +490,7 @@ struct nvsp_2_vsc_capability {
 			u64 sriov:1;
 			u64 ieee8021q:1;
 			u64 correlation_id:1;
+			u64 teaming:1;
 		};
 	};
 } __packed;
-- 
cgit v1.2.3-70-g09d2


From c0b558e5a393b77d2fe53335b5e07ca0e77178f8 Mon Sep 17 00:00:00 2001
From: Haiyang Zhang <haiyangz@microsoft.com>
Date: Fri, 19 Aug 2016 14:47:09 -0700
Subject: hv_netvsc: Implement batching of receive completions

The existing code uses busy retry when unable to send out receive
completions due to full ring buffer. It also gives up retrying after limit
is reached, and causes receive buffer slots not being recycled.
This patch implements batching of receive completions. It also prevents
dropping receive completions due to full ring buffer.

Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/hyperv_net.h   |  17 ++++
 drivers/net/hyperv/netvsc.c       | 170 +++++++++++++++++++++++++++++++-------
 drivers/net/hyperv/rndis_filter.c |   6 +-
 3 files changed, 160 insertions(+), 33 deletions(-)

(limited to 'drivers/net/hyperv/hyperv_net.h')

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index fa7b1e42508b..ce45d6835e88 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -634,6 +634,20 @@ struct multi_send_data {
 	u32 count; /* counter of batched packets */
 };
 
+struct recv_comp_data {
+	u64 tid; /* transaction id */
+	u32 status;
+};
+
+/* Netvsc Receive Slots Max */
+#define NETVSC_RECVSLOT_MAX (NETVSC_RECEIVE_BUFFER_SIZE / ETH_DATA_LEN + 1)
+
+struct multi_recv_comp {
+	void *buf; /* queued receive completions */
+	u32 first; /* first data entry */
+	u32 next; /* next entry for writing */
+};
+
 struct netvsc_stats {
 	u64 packets;
 	u64 bytes;
@@ -736,6 +750,9 @@ struct netvsc_device {
 	u32 max_pkt; /* max number of pkt in one send, e.g. 8 */
 	u32 pkt_align; /* alignment bytes, e.g. 8 */
 
+	struct multi_recv_comp mrc[VRSS_CHANNEL_MAX];
+	atomic_t num_outstanding_recvs;
+
 	atomic_t open_cnt;
 };
 
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 8078bc209cac..b15edfc37a59 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -74,6 +74,9 @@ static struct netvsc_device *alloc_net_device(void)
 		return NULL;
 	}
 
+	net_device->mrc[0].buf = vzalloc(NETVSC_RECVSLOT_MAX *
+					 sizeof(struct recv_comp_data));
+
 	init_waitqueue_head(&net_device->wait_drain);
 	net_device->destroy = false;
 	atomic_set(&net_device->open_cnt, 0);
@@ -85,6 +88,11 @@ static struct netvsc_device *alloc_net_device(void)
 
 static void free_netvsc_device(struct netvsc_device *nvdev)
 {
+	int i;
+
+	for (i = 0; i < VRSS_CHANNEL_MAX; i++)
+		vfree(nvdev->mrc[i].buf);
+
 	kfree(nvdev->cb_buffer);
 	kfree(nvdev);
 }
@@ -107,7 +115,8 @@ static struct netvsc_device *get_inbound_net_device(struct hv_device *device)
 		goto get_in_err;
 
 	if (net_device->destroy &&
-		atomic_read(&net_device->num_outstanding_sends) == 0)
+	    atomic_read(&net_device->num_outstanding_sends) == 0 &&
+	    atomic_read(&net_device->num_outstanding_recvs) == 0)
 		net_device = NULL;
 
 get_in_err:
@@ -972,49 +981,121 @@ send_now:
 	return ret;
 }
 
-static void netvsc_send_recv_completion(struct hv_device *device,
-					struct vmbus_channel *channel,
-					struct netvsc_device *net_device,
-					u64 transaction_id, u32 status)
+static int netvsc_send_recv_completion(struct vmbus_channel *channel,
+				       u64 transaction_id, u32 status)
 {
 	struct nvsp_message recvcompMessage;
-	int retries = 0;
 	int ret;
-	struct net_device *ndev = hv_get_drvdata(device);
 
 	recvcompMessage.hdr.msg_type =
 				NVSP_MSG1_TYPE_SEND_RNDIS_PKT_COMPLETE;
 
 	recvcompMessage.msg.v1_msg.send_rndis_pkt_complete.status = status;
 
-retry_send_cmplt:
 	/* Send the completion */
 	ret = vmbus_sendpacket(channel, &recvcompMessage,
-			       sizeof(struct nvsp_message), transaction_id,
-			       VM_PKT_COMP, 0);
-	if (ret == 0) {
-		/* success */
-		/* no-op */
-	} else if (ret == -EAGAIN) {
-		/* no more room...wait a bit and attempt to retry 3 times */
-		retries++;
-		netdev_err(ndev, "unable to send receive completion pkt"
-			" (tid %llx)...retrying %d\n", transaction_id, retries);
-
-		if (retries < 4) {
-			udelay(100);
-			goto retry_send_cmplt;
-		} else {
-			netdev_err(ndev, "unable to send receive "
-				"completion pkt (tid %llx)...give up retrying\n",
-				transaction_id);
-		}
-	} else {
-		netdev_err(ndev, "unable to send receive "
-			"completion pkt - %llx\n", transaction_id);
+			       sizeof(struct nvsp_message_header) + sizeof(u32),
+			       transaction_id, VM_PKT_COMP, 0);
+
+	return ret;
+}
+
+static inline void count_recv_comp_slot(struct netvsc_device *nvdev, u16 q_idx,
+					u32 *filled, u32 *avail)
+{
+	u32 first = nvdev->mrc[q_idx].first;
+	u32 next = nvdev->mrc[q_idx].next;
+
+	*filled = (first > next) ? NETVSC_RECVSLOT_MAX - first + next :
+		  next - first;
+
+	*avail = NETVSC_RECVSLOT_MAX - *filled - 1;
+}
+
+/* Read the first filled slot, no change to index */
+static inline struct recv_comp_data *read_recv_comp_slot(struct netvsc_device
+							 *nvdev, u16 q_idx)
+{
+	u32 filled, avail;
+
+	if (!nvdev->mrc[q_idx].buf)
+		return NULL;
+
+	count_recv_comp_slot(nvdev, q_idx, &filled, &avail);
+	if (!filled)
+		return NULL;
+
+	return nvdev->mrc[q_idx].buf + nvdev->mrc[q_idx].first *
+	       sizeof(struct recv_comp_data);
+}
+
+/* Put the first filled slot back to available pool */
+static inline void put_recv_comp_slot(struct netvsc_device *nvdev, u16 q_idx)
+{
+	int num_recv;
+
+	nvdev->mrc[q_idx].first = (nvdev->mrc[q_idx].first + 1) %
+				  NETVSC_RECVSLOT_MAX;
+
+	num_recv = atomic_dec_return(&nvdev->num_outstanding_recvs);
+
+	if (nvdev->destroy && num_recv == 0)
+		wake_up(&nvdev->wait_drain);
+}
+
+/* Check and send pending recv completions */
+static void netvsc_chk_recv_comp(struct netvsc_device *nvdev,
+				 struct vmbus_channel *channel, u16 q_idx)
+{
+	struct recv_comp_data *rcd;
+	int ret;
+
+	while (true) {
+		rcd = read_recv_comp_slot(nvdev, q_idx);
+		if (!rcd)
+			break;
+
+		ret = netvsc_send_recv_completion(channel, rcd->tid,
+						  rcd->status);
+		if (ret)
+			break;
+
+		put_recv_comp_slot(nvdev, q_idx);
 	}
 }
 
+#define NETVSC_RCD_WATERMARK 80
+
+/* Get next available slot */
+static inline struct recv_comp_data *get_recv_comp_slot(
+	struct netvsc_device *nvdev, struct vmbus_channel *channel, u16 q_idx)
+{
+	u32 filled, avail, next;
+	struct recv_comp_data *rcd;
+
+	if (!nvdev->recv_section)
+		return NULL;
+
+	if (!nvdev->mrc[q_idx].buf)
+		return NULL;
+
+	if (atomic_read(&nvdev->num_outstanding_recvs) >
+	    nvdev->recv_section->num_sub_allocs * NETVSC_RCD_WATERMARK / 100)
+		netvsc_chk_recv_comp(nvdev, channel, q_idx);
+
+	count_recv_comp_slot(nvdev, q_idx, &filled, &avail);
+	if (!avail)
+		return NULL;
+
+	next = nvdev->mrc[q_idx].next;
+	rcd = nvdev->mrc[q_idx].buf + next * sizeof(struct recv_comp_data);
+	nvdev->mrc[q_idx].next = (next + 1) % NETVSC_RECVSLOT_MAX;
+
+	atomic_inc(&nvdev->num_outstanding_recvs);
+
+	return rcd;
+}
+
 static void netvsc_receive(struct netvsc_device *net_device,
 			struct vmbus_channel *channel,
 			struct hv_device *device,
@@ -1029,6 +1110,9 @@ static void netvsc_receive(struct netvsc_device *net_device,
 	int count = 0;
 	struct net_device *ndev = hv_get_drvdata(device);
 	void *data;
+	int ret;
+	struct recv_comp_data *rcd;
+	u16 q_idx = channel->offermsg.offer.sub_channel_index;
 
 	/*
 	 * All inbound packets other than send completion should be xfer page
@@ -1076,8 +1160,26 @@ static void netvsc_receive(struct netvsc_device *net_device,
 
 	}
 
-	netvsc_send_recv_completion(device, channel, net_device,
-				    vmxferpage_packet->d.trans_id, status);
+	if (!net_device->mrc[q_idx].buf) {
+		ret = netvsc_send_recv_completion(channel,
+						  vmxferpage_packet->d.trans_id,
+						  status);
+		if (ret)
+			netdev_err(ndev, "Recv_comp q:%hd, tid:%llx, err:%d\n",
+				   q_idx, vmxferpage_packet->d.trans_id, ret);
+		return;
+	}
+
+	rcd = get_recv_comp_slot(net_device, channel, q_idx);
+
+	if (!rcd) {
+		netdev_err(ndev, "Recv_comp full buf q:%hd, tid:%llx\n",
+			   q_idx, vmxferpage_packet->d.trans_id);
+		return;
+	}
+
+	rcd->tid = vmxferpage_packet->d.trans_id;
+	rcd->status = status;
 }
 
 
@@ -1166,6 +1268,7 @@ void netvsc_channel_cb(void *context)
 {
 	int ret;
 	struct vmbus_channel *channel = (struct vmbus_channel *)context;
+	u16 q_idx = channel->offermsg.offer.sub_channel_index;
 	struct hv_device *device;
 	struct netvsc_device *net_device;
 	u32 bytes_recvd;
@@ -1245,6 +1348,9 @@ void netvsc_channel_cb(void *context)
 
 	if (bufferlen > NETVSC_PACKET_SIZE)
 		kfree(buffer);
+
+	netvsc_chk_recv_comp(net_device, channel, q_idx);
+
 	return;
 }
 
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index dd3b3352a950..3ecb2d05cf3f 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -897,7 +897,8 @@ cleanup:
 
 	/* Wait for all send completions */
 	wait_event(nvdev->wait_drain,
-		atomic_read(&nvdev->num_outstanding_sends) == 0);
+		   atomic_read(&nvdev->num_outstanding_sends) == 0 &&
+		   atomic_read(&nvdev->num_outstanding_recvs) == 0);
 
 	if (request)
 		put_rndis_request(dev, request);
@@ -953,6 +954,9 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
 	set_per_channel_state(new_sc, nvscdev->sub_cb_buf + (chn_index - 1) *
 			      NETVSC_PACKET_SIZE);
 
+	nvscdev->mrc[chn_index].buf = vzalloc(NETVSC_RECVSLOT_MAX *
+					      sizeof(struct recv_comp_data));
+
 	ret = vmbus_open(new_sc, nvscdev->ring_size * PAGE_SIZE,
 			 nvscdev->ring_size * PAGE_SIZE, NULL, 0,
 			 netvsc_channel_cb, new_sc);
-- 
cgit v1.2.3-70-g09d2


From 9477386687354f2aa8f4843170b7093c6dd1eb37 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <sthemmin@microsoft.com>
Date: Tue, 23 Aug 2016 12:17:45 -0700
Subject: hv_netvsc: make RSS hash key static

Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/hyperv_net.h   | 2 --
 drivers/net/hyperv/rndis_filter.c | 3 ++-
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'drivers/net/hyperv/hyperv_net.h')

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index ce45d6835e88..b58e5592a5d5 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -84,8 +84,6 @@ struct ndis_recv_scale_cap { /* NDIS_RECEIVE_SCALE_CAPABILITIES */
 #define NDIS_RSS_HASH_SECRET_KEY_MAX_SIZE_REVISION_2   40
 
 #define ITAB_NUM 128
-#define HASH_KEYLEN NDIS_RSS_HASH_SECRET_KEY_MAX_SIZE_REVISION_2
-extern u8 netvsc_hash_key[];
 
 struct ndis_recv_scale_param { /* NDIS_RECEIVE_SCALE_PARAMETERS */
 	struct ndis_obj_header hdr;
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 3ecb2d05cf3f..a100380ba6b9 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -663,13 +663,14 @@ cleanup:
 	return ret;
 }
 
-u8 netvsc_hash_key[HASH_KEYLEN] = {
+static const u8 netvsc_hash_key[] = {
 	0x6d, 0x5a, 0x56, 0xda, 0x25, 0x5b, 0x0e, 0xc2,
 	0x41, 0x67, 0x25, 0x3d, 0x43, 0xa3, 0x8f, 0xb0,
 	0xd0, 0xca, 0x2b, 0xcb, 0xae, 0x7b, 0x30, 0xb4,
 	0x77, 0xcb, 0x2d, 0xa3, 0x80, 0x30, 0xf2, 0x0c,
 	0x6a, 0x42, 0xb7, 0x3b, 0xbe, 0xac, 0x01, 0xfa
 };
+#define HASH_KEYLEN ARRAY_SIZE(netvsc_hash_key)
 
 static int rndis_filter_set_rss_param(struct rndis_device *rdev, int num_queue)
 {
-- 
cgit v1.2.3-70-g09d2


From e08f3ea586d4145e36c77f0dd1602374b5d7e928 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <sthemmin@microsoft.com>
Date: Tue, 23 Aug 2016 12:17:50 -0700
Subject: hv_netvsc: make device_remove void

Always returns 0 and no callers check.

Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/hyperv_net.h | 2 +-
 drivers/net/hyperv/netvsc.c     | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'drivers/net/hyperv/hyperv_net.h')

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index b58e5592a5d5..8031deeb0a40 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -173,7 +173,7 @@ struct rndis_device {
 struct rndis_message;
 struct netvsc_device;
 int netvsc_device_add(struct hv_device *device, void *additional_info);
-int netvsc_device_remove(struct hv_device *device);
+void netvsc_device_remove(struct hv_device *device);
 int netvsc_send(struct hv_device *device,
 		struct hv_netvsc_packet *packet,
 		struct rndis_message *rndis_msg,
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 110bbb8a0baa..2ece27ad8429 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -648,7 +648,7 @@ static void netvsc_disconnect_vsp(struct hv_device *device)
 /*
  * netvsc_device_remove - Callback when the root bus device is removed
  */
-int netvsc_device_remove(struct hv_device *device)
+void netvsc_device_remove(struct hv_device *device)
 {
 	struct net_device *ndev = hv_get_drvdata(device);
 	struct net_device_context *net_device_ctx = netdev_priv(ndev);
@@ -670,7 +670,6 @@ int netvsc_device_remove(struct hv_device *device)
 	/* Release all resources */
 	vfree(net_device->sub_cb_buf);
 	free_netvsc_device(net_device);
-	return 0;
 }
 
 #define RING_AVAIL_PERCENT_HIWATER 20
-- 
cgit v1.2.3-70-g09d2


From 4323b47cf8edfe95bd58e20965667e71121c866e Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <sthemmin@microsoft.com>
Date: Tue, 23 Aug 2016 12:17:57 -0700
Subject: hv_netvsc: add ethtool statistics for tx packet issues

Printing console messages is not helpful when system is out of memory;
and can be disastrous with netconsole. Instead keep statistics
of these anomalous conditions.

Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/hyperv_net.h |  9 +++++
 drivers/net/hyperv/netvsc_drv.c | 86 +++++++++++++++++++++++++++++++++--------
 2 files changed, 79 insertions(+), 16 deletions(-)

(limited to 'drivers/net/hyperv/hyperv_net.h')

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 8031deeb0a40..284b97b6b258 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -652,6 +652,14 @@ struct netvsc_stats {
 	struct u64_stats_sync syncp;
 };
 
+struct netvsc_ethtool_stats {
+	unsigned long tx_scattered;
+	unsigned long tx_no_memory;
+	unsigned long tx_no_space;
+	unsigned long tx_too_big;
+	unsigned long tx_busy;
+};
+
 struct netvsc_reconfig {
 	struct list_head list;
 	u32 event;
@@ -681,6 +689,7 @@ struct net_device_context {
 	/* Ethtool settings */
 	u8 duplex;
 	u32 speed;
+	struct netvsc_ethtool_stats eth_stats;
 
 	/* the device is going away */
 	bool start_remove;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index b874ab1317c6..2360e704e271 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -365,7 +365,6 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	u32 skb_length;
 	struct hv_page_buffer page_buf[MAX_PAGE_BUFFER_COUNT];
 	struct hv_page_buffer *pb = page_buf;
-	struct netvsc_stats *tx_stats = this_cpu_ptr(net_device_ctx->tx_stats);
 
 	/* We will atmost need two pages to describe the rndis
 	 * header. We can only transmit MAX_PAGE_BUFFER_COUNT number
@@ -377,17 +376,14 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	num_data_pgs = netvsc_get_slots(skb) + 2;
 
 	if (unlikely(num_data_pgs > MAX_PAGE_BUFFER_COUNT)) {
-		if (skb_linearize(skb)) {
-			net_alert_ratelimited("failed to linearize skb\n");
-			ret = -ENOMEM;
-			goto drop;
-		}
+		++net_device_ctx->eth_stats.tx_scattered;
+
+		if (skb_linearize(skb))
+			goto no_memory;
 
 		num_data_pgs = netvsc_get_slots(skb) + 2;
 		if (num_data_pgs > MAX_PAGE_BUFFER_COUNT) {
-			net_alert_ratelimited("packet too big: %u pages (%u bytes)\n",
-					      num_data_pgs, skb->len);
-			ret = -EFAULT;
+			++net_device_ctx->eth_stats.tx_too_big;
 			goto drop;
 		}
 	}
@@ -398,11 +394,9 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	 * structure.
 	 */
 	ret = skb_cow_head(skb, RNDIS_AND_PPI_SIZE);
-	if (ret) {
-		netdev_err(net, "unable to alloc hv_netvsc_packet\n");
-		ret = -ENOMEM;
-		goto drop;
-	}
+	if (ret)
+		goto no_memory;
+
 	/* Use the skb control buffer for building up the packet */
 	BUILD_BUG_ON(sizeof(struct hv_netvsc_packet) >
 			FIELD_SIZEOF(struct sk_buff, cb));
@@ -518,7 +512,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 
 		ret = skb_cow_head(skb, 0);
 		if (ret)
-			goto drop;
+			goto no_memory;
 
 		uh = udp_hdr(skb);
 		udp_len = ntohs(uh->len);
@@ -545,20 +539,32 @@ do_send:
 	ret = netvsc_send(net_device_ctx->device_ctx, packet,
 			  rndis_msg, &pb, skb);
 	if (likely(ret == 0)) {
+		struct netvsc_stats *tx_stats = this_cpu_ptr(net_device_ctx->tx_stats);
+
 		u64_stats_update_begin(&tx_stats->syncp);
 		tx_stats->packets++;
 		tx_stats->bytes += skb_length;
 		u64_stats_update_end(&tx_stats->syncp);
 		return NETDEV_TX_OK;
 	}
-	if (ret == -EAGAIN)
+
+	if (ret == -EAGAIN) {
+		++net_device_ctx->eth_stats.tx_busy;
 		return NETDEV_TX_BUSY;
+	}
+
+	if (ret == -ENOSPC)
+		++net_device_ctx->eth_stats.tx_no_space;
 
 drop:
 	dev_kfree_skb_any(skb);
 	net->stats.tx_dropped++;
 
 	return NETDEV_TX_OK;
+
+no_memory:
+	++net_device_ctx->eth_stats.tx_no_memory;
+	goto drop;
 }
 
 /*
@@ -1015,6 +1021,51 @@ static int netvsc_set_mac_addr(struct net_device *ndev, void *p)
 	return err;
 }
 
+static const struct {
+	char name[ETH_GSTRING_LEN];
+	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_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) },
+};
+
+static int netvsc_get_sset_count(struct net_device *dev, int string_set)
+{
+	switch (string_set) {
+	case ETH_SS_STATS:
+		return ARRAY_SIZE(netvsc_stats);
+	default:
+		return -EINVAL;
+	}
+}
+
+static void netvsc_get_ethtool_stats(struct net_device *dev,
+				     struct ethtool_stats *stats, u64 *data)
+{
+	struct net_device_context *ndc = netdev_priv(dev);
+	const void *nds = &ndc->eth_stats;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(netvsc_stats); i++)
+		data[i] = *(unsigned long *)(nds + netvsc_stats[i].offset);
+}
+
+static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
+{
+	int i;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < ARRAY_SIZE(netvsc_stats); i++)
+			memcpy(data + i * ETH_GSTRING_LEN,
+			       netvsc_stats[i].name, ETH_GSTRING_LEN);
+		break;
+	}
+}
+
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static void netvsc_poll_controller(struct net_device *net)
 {
@@ -1027,6 +1078,9 @@ static void netvsc_poll_controller(struct net_device *net)
 static const struct ethtool_ops ethtool_ops = {
 	.get_drvinfo	= netvsc_get_drvinfo,
 	.get_link	= ethtool_op_get_link,
+	.get_ethtool_stats = netvsc_get_ethtool_stats,
+	.get_sset_count = netvsc_get_sset_count,
+	.get_strings	= netvsc_get_strings,
 	.get_channels   = netvsc_get_channels,
 	.set_channels   = netvsc_set_channels,
 	.get_ts_info	= ethtool_op_get_ts_info,
-- 
cgit v1.2.3-70-g09d2


From f207c10d982388fa42710922ad1c0c9d3ba9a87b Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <sthemmin@microsoft.com>
Date: Thu, 22 Sep 2016 16:56:33 -0700
Subject: hv_netvsc: use RCU to protect vf_netdev

The vf_netdev pointer in the netvsc device context can simply be protected
by RCU because network device destruction is already RCU synchronized.

Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/hyperv_net.h |  2 +-
 drivers/net/hyperv/netvsc_drv.c | 29 +++++++++++++++--------------
 2 files changed, 16 insertions(+), 15 deletions(-)

(limited to 'drivers/net/hyperv/hyperv_net.h')

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 284b97b6b258..6b7948764443 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -695,7 +695,7 @@ struct net_device_context {
 	bool start_remove;
 
 	/* State to manage the associated VF interface. */
-	struct net_device *vf_netdev;
+	struct net_device __rcu *vf_netdev;
 	bool vf_inject;
 	atomic_t vf_use_cnt;
 	/* 1: allocated, serial number is valid. 0: not allocated */
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 87682198ff73..dde17c0faf9f 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -667,8 +667,8 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 {
 	struct net_device *net = hv_get_drvdata(device_obj);
 	struct net_device_context *net_device_ctx = netdev_priv(net);
+	struct net_device *vf_netdev;
 	struct sk_buff *skb;
-	struct sk_buff *vf_skb;
 	struct netvsc_stats *rx_stats;
 	u32 bytes_recvd = packet->total_data_buflen;
 	int ret = 0;
@@ -676,9 +676,12 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 	if (!net || net->reg_state != NETREG_REGISTERED)
 		return NVSP_STAT_FAIL;
 
-	if (READ_ONCE(net_device_ctx->vf_inject)) {
+	vf_netdev = rcu_dereference(net_device_ctx->vf_netdev);
+	if (vf_netdev) {
+		struct sk_buff *vf_skb;
+
 		atomic_inc(&net_device_ctx->vf_use_cnt);
-		if (!READ_ONCE(net_device_ctx->vf_inject)) {
+		if (!net_device_ctx->vf_inject) {
 			/*
 			 * We raced; just move on.
 			 */
@@ -694,13 +697,12 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 		 * the host). Deliver these via the VF interface
 		 * in the guest.
 		 */
-		vf_skb = netvsc_alloc_recv_skb(net_device_ctx->vf_netdev,
+		vf_skb = netvsc_alloc_recv_skb(vf_netdev,
 					       packet, csum_info, *data,
 					       vlan_tci);
 		if (vf_skb != NULL) {
-			++net_device_ctx->vf_netdev->stats.rx_packets;
-			net_device_ctx->vf_netdev->stats.rx_bytes +=
-				bytes_recvd;
+			++vf_netdev->stats.rx_packets;
+			vf_netdev->stats.rx_bytes += bytes_recvd;
 			netif_receive_skb(vf_skb);
 		} else {
 			++net->stats.rx_dropped;
@@ -1232,7 +1234,7 @@ static struct net_device *get_netvsc_bymac(const u8 *mac)
 	return NULL;
 }
 
-static struct net_device *get_netvsc_byref(const struct net_device *vf_netdev)
+static struct net_device *get_netvsc_byref(struct net_device *vf_netdev)
 {
 	struct net_device *dev;
 
@@ -1248,7 +1250,7 @@ static struct net_device *get_netvsc_byref(const struct net_device *vf_netdev)
 		if (net_device_ctx->nvdev == NULL)
 			continue;	/* device is removed */
 
-		if (net_device_ctx->vf_netdev == vf_netdev)
+		if (rtnl_dereference(net_device_ctx->vf_netdev) == vf_netdev)
 			return dev;	/* a match */
 	}
 
@@ -1275,7 +1277,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
 
 	net_device_ctx = netdev_priv(ndev);
 	netvsc_dev = net_device_ctx->nvdev;
-	if (!netvsc_dev || net_device_ctx->vf_netdev)
+	if (!netvsc_dev || rtnl_dereference(net_device_ctx->vf_netdev))
 		return NOTIFY_DONE;
 
 	netdev_info(ndev, "VF registering: %s\n", vf_netdev->name);
@@ -1285,7 +1287,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
 	try_module_get(THIS_MODULE);
 
 	dev_hold(vf_netdev);
-	net_device_ctx->vf_netdev = vf_netdev;
+	rcu_assign_pointer(net_device_ctx->vf_netdev, vf_netdev);
 	return NOTIFY_OK;
 }
 
@@ -1379,7 +1381,8 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev)
 
 	netdev_info(ndev, "VF unregistering: %s\n", vf_netdev->name);
 	netvsc_inject_disable(net_device_ctx);
-	net_device_ctx->vf_netdev = NULL;
+
+	RCU_INIT_POINTER(net_device_ctx->vf_netdev, NULL);
 	dev_put(vf_netdev);
 	module_put(THIS_MODULE);
 	return NOTIFY_OK;
@@ -1433,8 +1436,6 @@ static int netvsc_probe(struct hv_device *dev,
 	INIT_LIST_HEAD(&net_device_ctx->reconfig_events);
 
 	atomic_set(&net_device_ctx->vf_use_cnt, 0);
-	net_device_ctx->vf_netdev = NULL;
-	net_device_ctx->vf_inject = false;
 
 	net->netdev_ops = &device_ops;
 
-- 
cgit v1.2.3-70-g09d2


From 9cbcc4280645f0e7e19e6a0da443ec7e69cecf40 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <sthemmin@microsoft.com>
Date: Thu, 22 Sep 2016 16:56:34 -0700
Subject: hv_netvsc: remove VF in flight counters

Since VF reference is now protected by RCU, no longer need the VF usage
counter and can use device flags to see whether to inject or not.

Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/hyperv_net.h |  3 +-
 drivers/net/hyperv/netvsc_drv.c | 81 ++++++++++-------------------------------
 2 files changed, 21 insertions(+), 63 deletions(-)

(limited to 'drivers/net/hyperv/hyperv_net.h')

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 6b7948764443..1d4974026eff 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -696,8 +696,7 @@ struct net_device_context {
 
 	/* State to manage the associated VF interface. */
 	struct net_device __rcu *vf_netdev;
-	bool vf_inject;
-	atomic_t vf_use_cnt;
+
 	/* 1: allocated, serial number is valid. 0: not allocated */
 	u32 vf_alloc;
 	/* Serial number of the VF to team with */
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index dde17c0faf9f..9375d82702ce 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -670,50 +670,20 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 	struct net_device *vf_netdev;
 	struct sk_buff *skb;
 	struct netvsc_stats *rx_stats;
-	u32 bytes_recvd = packet->total_data_buflen;
-	int ret = 0;
 
-	if (!net || net->reg_state != NETREG_REGISTERED)
+	if (net->reg_state != NETREG_REGISTERED)
 		return NVSP_STAT_FAIL;
 
+	/*
+	 * If necessary, inject this packet into the VF interface.
+	 * On Hyper-V, multicast and brodcast packets are only delivered
+	 * to the synthetic interface (after subjecting these to
+	 * policy filters on the host). Deliver these via the VF
+	 * interface in the guest.
+	 */
 	vf_netdev = rcu_dereference(net_device_ctx->vf_netdev);
-	if (vf_netdev) {
-		struct sk_buff *vf_skb;
-
-		atomic_inc(&net_device_ctx->vf_use_cnt);
-		if (!net_device_ctx->vf_inject) {
-			/*
-			 * We raced; just move on.
-			 */
-			atomic_dec(&net_device_ctx->vf_use_cnt);
-			goto vf_injection_done;
-		}
-
-		/*
-		 * Inject this packet into the VF inerface.
-		 * On Hyper-V, multicast and brodcast packets
-		 * are only delivered on the synthetic interface
-		 * (after subjecting these to policy filters on
-		 * the host). Deliver these via the VF interface
-		 * in the guest.
-		 */
-		vf_skb = netvsc_alloc_recv_skb(vf_netdev,
-					       packet, csum_info, *data,
-					       vlan_tci);
-		if (vf_skb != NULL) {
-			++vf_netdev->stats.rx_packets;
-			vf_netdev->stats.rx_bytes += bytes_recvd;
-			netif_receive_skb(vf_skb);
-		} else {
-			++net->stats.rx_dropped;
-			ret = NVSP_STAT_FAIL;
-		}
-		atomic_dec(&net_device_ctx->vf_use_cnt);
-		return ret;
-	}
-
-vf_injection_done:
-	rx_stats = this_cpu_ptr(net_device_ctx->rx_stats);
+	if (vf_netdev && (vf_netdev->flags & IFF_UP))
+		net = vf_netdev;
 
 	/* Allocate a skb - TODO direct I/O to pages? */
 	skb = netvsc_alloc_recv_skb(net, packet, csum_info, *data, vlan_tci);
@@ -721,9 +691,17 @@ vf_injection_done:
 		++net->stats.rx_dropped;
 		return NVSP_STAT_FAIL;
 	}
-	skb_record_rx_queue(skb, channel->
-			    offermsg.offer.sub_channel_index);
 
+	if (net != vf_netdev)
+		skb_record_rx_queue(skb,
+				    channel->offermsg.offer.sub_channel_index);
+
+	/*
+	 * Even if injecting the packet, record the statistics
+	 * on the synthetic device because modifying the VF device
+	 * statistics will not work correctly.
+	 */
+	rx_stats = this_cpu_ptr(net_device_ctx->rx_stats);
 	u64_stats_update_begin(&rx_stats->syncp);
 	rx_stats->packets++;
 	rx_stats->bytes += packet->total_data_buflen;
@@ -1291,20 +1269,6 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
 	return NOTIFY_OK;
 }
 
-static void netvsc_inject_enable(struct net_device_context *net_device_ctx)
-{
-	net_device_ctx->vf_inject = true;
-}
-
-static void netvsc_inject_disable(struct net_device_context *net_device_ctx)
-{
-	net_device_ctx->vf_inject = false;
-
-	/* Wait for currently active users to drain out. */
-	while (atomic_read(&net_device_ctx->vf_use_cnt) != 0)
-		udelay(50);
-}
-
 static int netvsc_vf_up(struct net_device *vf_netdev)
 {
 	struct net_device *ndev;
@@ -1319,7 +1283,6 @@ static int netvsc_vf_up(struct net_device *vf_netdev)
 	netvsc_dev = net_device_ctx->nvdev;
 
 	netdev_info(ndev, "VF up: %s\n", vf_netdev->name);
-	netvsc_inject_enable(net_device_ctx);
 
 	/*
 	 * Open the device before switching data path.
@@ -1354,7 +1317,6 @@ static int netvsc_vf_down(struct net_device *vf_netdev)
 	netvsc_dev = net_device_ctx->nvdev;
 
 	netdev_info(ndev, "VF down: %s\n", vf_netdev->name);
-	netvsc_inject_disable(net_device_ctx);
 	netvsc_switch_datapath(ndev, false);
 	netdev_info(ndev, "Data path switched from VF: %s\n", vf_netdev->name);
 	rndis_filter_close(netvsc_dev);
@@ -1380,7 +1342,6 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev)
 	netvsc_dev = net_device_ctx->nvdev;
 
 	netdev_info(ndev, "VF unregistering: %s\n", vf_netdev->name);
-	netvsc_inject_disable(net_device_ctx);
 
 	RCU_INIT_POINTER(net_device_ctx->vf_netdev, NULL);
 	dev_put(vf_netdev);
@@ -1435,8 +1396,6 @@ static int netvsc_probe(struct hv_device *dev,
 	spin_lock_init(&net_device_ctx->lock);
 	INIT_LIST_HEAD(&net_device_ctx->reconfig_events);
 
-	atomic_set(&net_device_ctx->vf_use_cnt, 0);
-
 	net->netdev_ops = &device_ops;
 
 	net->hw_features = NETVSC_HW_FEATURES;
-- 
cgit v1.2.3-70-g09d2


From f7ad75b753f386454f50044fd69edad767b69ce8 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <sthemmin@microsoft.com>
Date: Thu, 22 Sep 2016 16:56:35 -0700
Subject: hv_netvsc: count multicast packets received

Useful for debugging issues with multicast and SR-IOV to keep track
of number of received multicast packets.

Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/hyperv_net.h | 2 ++
 drivers/net/hyperv/netvsc_drv.c | 9 ++++++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'drivers/net/hyperv/hyperv_net.h')

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 1d4974026eff..7130bf910f52 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -649,6 +649,8 @@ struct multi_recv_comp {
 struct netvsc_stats {
 	u64 packets;
 	u64 bytes;
+	u64 broadcast;
+	u64 multicast;
 	struct u64_stats_sync syncp;
 };
 
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 9375d82702ce..52eeb2f67276 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -705,6 +705,11 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 	u64_stats_update_begin(&rx_stats->syncp);
 	rx_stats->packets++;
 	rx_stats->bytes += packet->total_data_buflen;
+
+	if (skb->pkt_type == PACKET_BROADCAST)
+		++rx_stats->broadcast;
+	else if (skb->pkt_type == PACKET_MULTICAST)
+		++rx_stats->multicast;
 	u64_stats_update_end(&rx_stats->syncp);
 
 	/*
@@ -947,7 +952,7 @@ static struct rtnl_link_stats64 *netvsc_get_stats64(struct net_device *net,
 							    cpu);
 		struct netvsc_stats *rx_stats = per_cpu_ptr(ndev_ctx->rx_stats,
 							    cpu);
-		u64 tx_packets, tx_bytes, rx_packets, rx_bytes;
+		u64 tx_packets, tx_bytes, rx_packets, rx_bytes, rx_multicast;
 		unsigned int start;
 
 		do {
@@ -960,12 +965,14 @@ static struct rtnl_link_stats64 *netvsc_get_stats64(struct net_device *net,
 			start = u64_stats_fetch_begin_irq(&rx_stats->syncp);
 			rx_packets = rx_stats->packets;
 			rx_bytes = rx_stats->bytes;
+			rx_multicast = rx_stats->multicast + rx_stats->broadcast;
 		} while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start));
 
 		t->tx_bytes	+= tx_bytes;
 		t->tx_packets	+= tx_packets;
 		t->rx_bytes	+= rx_bytes;
 		t->rx_packets	+= rx_packets;
+		t->multicast	+= rx_multicast;
 	}
 
 	t->tx_dropped	= net->stats.tx_dropped;
-- 
cgit v1.2.3-70-g09d2


From c6a77ff82fb849534748719f37f3f9086d78ed39 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <sthemmin@microsoft.com>
Date: Fri, 23 Sep 2016 17:08:17 -0700
Subject: hv_netvsc: fix comments

Typo's and spelling errors. Also remove old comment from staging era.

Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/hyperv_net.h | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

(limited to 'drivers/net/hyperv/hyperv_net.h')

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 7130bf910f52..f4fbcb5aa24a 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -433,7 +433,7 @@ struct nvsp_1_message_revoke_send_buffer {
  */
 struct nvsp_1_message_send_rndis_packet {
 	/*
-	 * This field is specified by RNIDS. They assume there's two different
+	 * This field is specified by RNDIS. They assume there's two different
 	 * channels of communication. However, the Network VSP only has one.
 	 * Therefore, the channel travels with the RNDIS packet.
 	 */
@@ -578,7 +578,7 @@ struct nvsp_5_send_indirect_table {
 	/* The number of entries in the send indirection table */
 	u32 count;
 
-	/* The offset of the send indireciton table from top of this struct.
+	/* The offset of the send indirection table from top of this struct.
 	 * The send indirection table tells which channel to put the send
 	 * traffic on. Each entry is a channel number.
 	 */
@@ -734,7 +734,6 @@ struct netvsc_device {
 	struct nvsp_message channel_init_pkt;
 
 	struct nvsp_message revoke_packet;
-	/* unsigned char HwMacAddr[HW_MACADDR_LEN]; */
 
 	struct vmbus_channel *chn_table[VRSS_CHANNEL_MAX];
 	u32 send_table[VRSS_SEND_TAB_SIZE];
@@ -1239,7 +1238,7 @@ struct rndis_message {
 	u32 ndis_msg_type;
 
 	/* Total length of this message, from the beginning */
-	/* of the sruct rndis_message, in bytes. */
+	/* of the struct rndis_message, in bytes. */
 	u32 msg_len;
 
 	/* Actual message */
-- 
cgit v1.2.3-70-g09d2