Merging upstream version 5.10.216.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

4 files changed, 146 insertions, 35 deletions

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 367878493..15652d795 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -847,6 +847,19 @@ struct nvsp_message {
 
 #define NETVSC_XDP_HDRM 256
 
+#define NETVSC_MIN_OUT_MSG_SIZE (sizeof(struct vmpacket_descriptor) + \
+				 sizeof(struct nvsp_message))
+#define NETVSC_MIN_IN_MSG_SIZE sizeof(struct vmpacket_descriptor)
+
+/* Estimated requestor size:
+ * out_ring_size/min_out_msg_size + in_ring_size/min_in_msg_size
+ */
+static inline u32 netvsc_rqstor_size(unsigned long ringbytes)
+{
+	return ringbytes / NETVSC_MIN_OUT_MSG_SIZE +
+		ringbytes / NETVSC_MIN_IN_MSG_SIZE;
+}
+
 #define NETVSC_XFER_HEADER_SIZE(rng_cnt) \
 		(offsetof(struct vmtransfer_page_packet_header, ranges) + \
 		(rng_cnt) * sizeof(struct vmtransfer_page_range))
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index d15da8287..03333a413 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -37,6 +37,10 @@ void netvsc_switch_datapath(struct net_device *ndev, bool vf)
 	struct netvsc_device *nv_dev = rtnl_dereference(net_device_ctx->nvdev);
 	struct nvsp_message *init_pkt = &nv_dev->channel_init_pkt;
 
+	/* Block sending traffic to VF if it's about to be gone */
+	if (!vf)
+		net_device_ctx->data_path_is_vf = vf;
+
 	memset(init_pkt, 0, sizeof(struct nvsp_message));
 	init_pkt->hdr.msg_type = NVSP_MSG4_TYPE_SWITCH_DATA_PATH;
 	if (vf)
@@ -51,7 +55,10 @@ void netvsc_switch_datapath(struct net_device *ndev, bool vf)
 	vmbus_sendpacket(dev->channel, init_pkt,
 			       sizeof(struct nvsp_message),
 			       (unsigned long)init_pkt,
-			       VM_PKT_DATA_INBAND, 0);
+			       VM_PKT_DATA_INBAND,
+			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+	wait_for_completion(&nv_dev->channel_init_wait);
+	net_device_ctx->data_path_is_vf = vf;
 }
 
 /* Worker to setup sub channels on initial setup
@@ -163,7 +170,7 @@ static void netvsc_revoke_recv_buf(struct hv_device *device,
 		ret = vmbus_sendpacket(device->channel,
 				       revoke_packet,
 				       sizeof(struct nvsp_message),
-				       (unsigned long)revoke_packet,
+				       VMBUS_RQST_ID_NO_RESPONSE,
 				       VM_PKT_DATA_INBAND, 0);
 		/* If the failure is because the channel is rescinded;
 		 * ignore the failure since we cannot send on a rescinded
@@ -213,7 +220,7 @@ static void netvsc_revoke_send_buf(struct hv_device *device,
 		ret = vmbus_sendpacket(device->channel,
 				       revoke_packet,
 				       sizeof(struct nvsp_message),
-				       (unsigned long)revoke_packet,
+				       VMBUS_RQST_ID_NO_RESPONSE,
 				       VM_PKT_DATA_INBAND, 0);
 
 		/* If the failure is because the channel is rescinded;
@@ -557,7 +564,7 @@ static int negotiate_nvsp_ver(struct hv_device *device,
 
 	ret = vmbus_sendpacket(device->channel, init_packet,
 				sizeof(struct nvsp_message),
-				(unsigned long)init_packet,
+				VMBUS_RQST_ID_NO_RESPONSE,
 				VM_PKT_DATA_INBAND, 0);
 
 	return ret;
@@ -614,7 +621,7 @@ static int netvsc_connect_vsp(struct hv_device *device,
 	/* Send the init request */
 	ret = vmbus_sendpacket(device->channel, init_packet,
 				sizeof(struct nvsp_message),
-				(unsigned long)init_packet,
+				VMBUS_RQST_ID_NO_RESPONSE,
 				VM_PKT_DATA_INBAND, 0);
 	if (ret != 0)
 		goto cleanup;
@@ -654,7 +661,10 @@ void netvsc_device_remove(struct hv_device *device)
 	/* Disable NAPI and disassociate its context from the device. */
 	for (i = 0; i < net_device->num_chn; i++) {
 		/* See also vmbus_reset_channel_cb(). */
-		napi_disable(&net_device->chan_table[i].napi);
+		/* only disable enabled NAPI channel */
+		if (i < ndev->real_num_rx_queues)
+			napi_disable(&net_device->chan_table[i].napi);
+
 		netif_napi_del(&net_device->chan_table[i].napi);
 	}
 
@@ -695,10 +705,19 @@ static void netvsc_send_tx_complete(struct net_device *ndev,
 				    const struct vmpacket_descriptor *desc,
 				    int budget)
 {
-	struct sk_buff *skb = (struct sk_buff *)(unsigned long)desc->trans_id;
 	struct net_device_context *ndev_ctx = netdev_priv(ndev);
+	struct sk_buff *skb;
 	u16 q_idx = 0;
 	int queue_sends;
+	u64 cmd_rqst;
+
+	cmd_rqst = vmbus_request_addr(&channel->requestor, (u64)desc->trans_id);
+	if (cmd_rqst == VMBUS_RQST_ERROR) {
+		netdev_err(ndev, "Incorrect transaction id\n");
+		return;
+	}
+
+	skb = (struct sk_buff *)(unsigned long)cmd_rqst;
 
 	/* Notify the layer above us */
 	if (likely(skb)) {
@@ -745,8 +764,31 @@ static void netvsc_send_completion(struct net_device *ndev,
 				   const struct vmpacket_descriptor *desc,
 				   int budget)
 {
-	const struct nvsp_message *nvsp_packet = hv_pkt_data(desc);
+	const struct nvsp_message *nvsp_packet;
 	u32 msglen = hv_pkt_datalen(desc);
+	struct nvsp_message *pkt_rqst;
+	u64 cmd_rqst;
+
+	/* First check if this is a VMBUS completion without data payload */
+	if (!msglen) {
+		cmd_rqst = vmbus_request_addr(&incoming_channel->requestor,
+					      (u64)desc->trans_id);
+		if (cmd_rqst == VMBUS_RQST_ERROR) {
+			netdev_err(ndev, "Invalid transaction id\n");
+			return;
+		}
+
+		pkt_rqst = (struct nvsp_message *)(uintptr_t)cmd_rqst;
+		switch (pkt_rqst->hdr.msg_type) {
+		case NVSP_MSG4_TYPE_SWITCH_DATA_PATH:
+			complete(&net_device->channel_init_wait);
+			break;
+
+		default:
+			netdev_err(ndev, "Unexpected VMBUS completion!!\n");
+		}
+		return;
+	}
 
 	/* Ensure packet is big enough to read header fields */
 	if (msglen < sizeof(struct nvsp_message_header)) {
@@ -754,6 +796,7 @@ static void netvsc_send_completion(struct net_device *ndev,
 		return;
 	}
 
+	nvsp_packet = hv_pkt_data(desc);
 	switch (nvsp_packet->hdr.msg_type) {
 	case NVSP_MSG_TYPE_INIT_COMPLETE:
 		if (msglen < sizeof(struct nvsp_message_header) +
@@ -1527,6 +1570,7 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 		       netvsc_poll, NAPI_POLL_WEIGHT);
 
 	/* Open the channel */
+	device->channel->rqstor_size = netvsc_rqstor_size(netvsc_ring_bytes);
 	ret = vmbus_open(device->channel, netvsc_ring_bytes,
 			 netvsc_ring_bytes,  NULL, 0,
 			 netvsc_channel_cb, net_device->chan_table);
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 790bf7502..0fc0f9cb3 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -44,6 +44,10 @@
 #define LINKCHANGE_INT (2 * HZ)
 #define VF_TAKEOVER_INT (HZ / 10)
 
+/* Macros to define the context of vf registration */
+#define VF_REG_IN_PROBE		1
+#define VF_REG_IN_NOTIFIER	2
+
 static unsigned int ring_size __ro_after_init = 128;
 module_param(ring_size, uint, 0444);
 MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)");
@@ -2194,7 +2198,7 @@ static rx_handler_result_t netvsc_vf_handle_frame(struct sk_buff **pskb)
 }
 
 static int netvsc_vf_join(struct net_device *vf_netdev,
-			  struct net_device *ndev)
+			  struct net_device *ndev, int context)
 {
 	struct net_device_context *ndev_ctx = netdev_priv(ndev);
 	int ret;
@@ -2217,7 +2221,11 @@ static int netvsc_vf_join(struct net_device *vf_netdev,
 		goto upper_link_failed;
 	}
 
-	schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
+	/* If this registration is called from probe context vf_takeover
+	 * is taken care of later in probe itself.
+	 */
+	if (context == VF_REG_IN_NOTIFIER)
+		schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT);
 
 	call_netdevice_notifiers(NETDEV_JOIN, vf_netdev);
 
@@ -2310,8 +2318,17 @@ static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev)
 		if (!ndev_ctx->vf_alloc)
 			continue;
 
-		if (ndev_ctx->vf_serial == serial)
-			return hv_get_drvdata(ndev_ctx->device_ctx);
+		if (ndev_ctx->vf_serial != serial)
+			continue;
+
+		ndev = hv_get_drvdata(ndev_ctx->device_ctx);
+		if (ndev->addr_len != vf_netdev->addr_len ||
+		    memcmp(ndev->perm_addr, vf_netdev->perm_addr,
+			   ndev->addr_len) != 0)
+			continue;
+
+		return ndev;
+
 	}
 
 	/* Fallback path to check synthetic vf with help of mac addr.
@@ -2346,7 +2363,7 @@ static int netvsc_prepare_bonding(struct net_device *vf_netdev)
 	return NOTIFY_DONE;
 }
 
-static int netvsc_register_vf(struct net_device *vf_netdev)
+static int netvsc_register_vf(struct net_device *vf_netdev, int context)
 {
 	struct net_device_context *net_device_ctx;
 	struct netvsc_device *netvsc_dev;
@@ -2386,7 +2403,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
 
 	netdev_info(ndev, "VF registering: %s\n", vf_netdev->name);
 
-	if (netvsc_vf_join(vf_netdev, ndev) != 0)
+	if (netvsc_vf_join(vf_netdev, ndev, context) != 0)
 		return NOTIFY_DONE;
 
 	dev_hold(vf_netdev);
@@ -2411,12 +2428,15 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
  * During hibernation, if a VF NIC driver (e.g. mlx5) preserves the network
  * interface, there is only the CHANGE event and no UP or DOWN event.
  */
-static int netvsc_vf_changed(struct net_device *vf_netdev)
+static int netvsc_vf_changed(struct net_device *vf_netdev, unsigned long event)
 {
 	struct net_device_context *net_device_ctx;
 	struct netvsc_device *netvsc_dev;
 	struct net_device *ndev;
-	bool vf_is_up = netif_running(vf_netdev);
+	bool vf_is_up = false;
+
+	if (event != NETDEV_GOING_DOWN)
+		vf_is_up = netif_running(vf_netdev);
 
 	ndev = get_netvsc_byref(vf_netdev);
 	if (!ndev)
@@ -2429,7 +2449,6 @@ static int netvsc_vf_changed(struct net_device *vf_netdev)
 
 	if (net_device_ctx->data_path_is_vf == vf_is_up)
 		return NOTIFY_OK;
-	net_device_ctx->data_path_is_vf = vf_is_up;
 
 	if (vf_is_up && !net_device_ctx->vf_alloc) {
 		netdev_info(ndev, "Waiting for the VF association from host\n");
@@ -2468,10 +2487,31 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev)
 	return NOTIFY_OK;
 }
 
+static int check_dev_is_matching_vf(struct net_device *event_ndev)
+{
+	/* Skip NetVSC interfaces */
+	if (event_ndev->netdev_ops == &device_ops)
+		return -ENODEV;
+
+	/* Avoid non-Ethernet type devices */
+	if (event_ndev->type != ARPHRD_ETHER)
+		return -ENODEV;
+
+	/* Avoid Vlan dev with same MAC registering as VF */
+	if (is_vlan_dev(event_ndev))
+		return -ENODEV;
+
+	/* Avoid Bonding master dev with same MAC registering as VF */
+	if (netif_is_bond_master(event_ndev))
+		return -ENODEV;
+
+	return 0;
+}
+
 static int netvsc_probe(struct hv_device *dev,
 			const struct hv_vmbus_device_id *dev_id)
 {
-	struct net_device *net = NULL;
+	struct net_device *net = NULL, *vf_netdev;
 	struct net_device_context *net_device_ctx;
 	struct netvsc_device_info *device_info = NULL;
 	struct netvsc_device *nvdev;
@@ -2579,6 +2619,30 @@ static int netvsc_probe(struct hv_device *dev,
 	}
 
 	list_add(&net_device_ctx->list, &netvsc_dev_list);
+
+	/* When the hv_netvsc driver is unloaded and reloaded, the
+	 * NET_DEVICE_REGISTER for the vf device is replayed before probe
+	 * is complete. This is because register_netdevice_notifier() gets
+	 * registered before vmbus_driver_register() so that callback func
+	 * is set before probe and we don't miss events like NETDEV_POST_INIT
+	 * So, in this section we try to register the matching vf device that
+	 * is present as a netdevice, knowing that its register call is not
+	 * processed in the netvsc_netdev_notifier(as probing is progress and
+	 * get_netvsc_byslot fails).
+	 */
+	for_each_netdev(dev_net(net), vf_netdev) {
+		ret = check_dev_is_matching_vf(vf_netdev);
+		if (ret != 0)
+			continue;
+
+		if (net != get_netvsc_byslot(vf_netdev))
+			continue;
+
+		netvsc_prepare_bonding(vf_netdev);
+		netvsc_register_vf(vf_netdev, VF_REG_IN_PROBE);
+		__netvsc_vf_setup(net, vf_netdev);
+		break;
+	}
 	rtnl_unlock();
 
 	netvsc_devinfo_put(device_info);
@@ -2735,35 +2799,24 @@ static int netvsc_netdev_event(struct notifier_block *this,
 			       unsigned long event, void *ptr)
 {
 	struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
+	int ret = 0;
 
-	/* Skip our own events */
-	if (event_dev->netdev_ops == &device_ops)
-		return NOTIFY_DONE;
-
-	/* Avoid non-Ethernet type devices */
-	if (event_dev->type != ARPHRD_ETHER)
-		return NOTIFY_DONE;
-
-	/* Avoid Vlan dev with same MAC registering as VF */
-	if (is_vlan_dev(event_dev))
-		return NOTIFY_DONE;
-
-	/* Avoid Bonding master dev with same MAC registering as VF */
-	if ((event_dev->priv_flags & IFF_BONDING) &&
-	    (event_dev->flags & IFF_MASTER))
+	ret = check_dev_is_matching_vf(event_dev);
+	if (ret != 0)
 		return NOTIFY_DONE;
 
 	switch (event) {
 	case NETDEV_POST_INIT:
 		return netvsc_prepare_bonding(event_dev);
 	case NETDEV_REGISTER:
-		return netvsc_register_vf(event_dev);
+		return netvsc_register_vf(event_dev, VF_REG_IN_NOTIFIER);
 	case NETDEV_UNREGISTER:
 		return netvsc_unregister_vf(event_dev);
 	case NETDEV_UP:
 	case NETDEV_DOWN:
 	case NETDEV_CHANGE:
-		return netvsc_vf_changed(event_dev);
+	case NETDEV_GOING_DOWN:
+		return netvsc_vf_changed(event_dev, event);
 	default:
 		return NOTIFY_DONE;
 	}
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 90bc0008f..13f62950e 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1170,6 +1170,7 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
 	/* Set the channel before opening.*/
 	nvchan->channel = new_sc;
 
+	new_sc->rqstor_size = netvsc_rqstor_size(netvsc_ring_bytes);
 	ret = vmbus_open(new_sc, netvsc_ring_bytes,
 			 netvsc_ring_bytes, NULL, 0,
 			 netvsc_channel_cb, nvchan);