1 files changed, 132 insertions, 77 deletions

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 4406427d4617..c41a025c66f0 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -29,6 +29,7 @@
 #include <linux/bpf.h>
 
 #include <net/arp.h>
+#include <net/netdev_lock.h>
 #include <net/route.h>
 #include <net/sock.h>
 #include <net/pkt_sched.h>
@@ -42,9 +43,13 @@
 #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)");
+MODULE_PARM_DESC(ring_size, "Ring buffer size (# of 4K pages)");
 unsigned int netvsc_ring_bytes __ro_after_init;
 
 static const u32 default_msg = NETIF_MSG_DRV | NETIF_MSG_PROBE |
@@ -321,43 +326,10 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 	return txq;
 }
 
-static u32 fill_pg_buf(unsigned long hvpfn, u32 offset, u32 len,
-		       struct hv_page_buffer *pb)
-{
-	int j = 0;
-
-	hvpfn += offset >> HV_HYP_PAGE_SHIFT;
-	offset = offset & ~HV_HYP_PAGE_MASK;
-
-	while (len > 0) {
-		unsigned long bytes;
-
-		bytes = HV_HYP_PAGE_SIZE - offset;
-		if (bytes > len)
-			bytes = len;
-		pb[j].pfn = hvpfn;
-		pb[j].offset = offset;
-		pb[j].len = bytes;
-
-		offset += bytes;
-		len -= bytes;
-
-		if (offset == HV_HYP_PAGE_SIZE && len) {
-			hvpfn++;
-			offset = 0;
-			j++;
-		}
-	}
-
-	return j + 1;
-}
-
 static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb,
 			   struct hv_netvsc_packet *packet,
 			   struct hv_page_buffer *pb)
 {
-	u32 slots_used = 0;
-	char *data = skb->data;
 	int frags = skb_shinfo(skb)->nr_frags;
 	int i;
 
@@ -366,28 +338,27 @@ static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb,
 	 * 2. skb linear data
 	 * 3. skb fragment data
 	 */
-	slots_used += fill_pg_buf(virt_to_hvpfn(hdr),
-				  offset_in_hvpage(hdr),
-				  len,
-				  &pb[slots_used]);
 
+	pb[0].offset = offset_in_hvpage(hdr);
+	pb[0].len = len;
+	pb[0].pfn = virt_to_hvpfn(hdr);
 	packet->rmsg_size = len;
-	packet->rmsg_pgcnt = slots_used;
 
-	slots_used += fill_pg_buf(virt_to_hvpfn(data),
-				  offset_in_hvpage(data),
-				  skb_headlen(skb),
-				  &pb[slots_used]);
+	pb[1].offset = offset_in_hvpage(skb->data);
+	pb[1].len = skb_headlen(skb);
+	pb[1].pfn = virt_to_hvpfn(skb->data);
 
 	for (i = 0; i < frags; i++) {
 		skb_frag_t *frag = skb_shinfo(skb)->frags + i;
+		struct hv_page_buffer *cur_pb = &pb[i + 2];
+		u64 pfn = page_to_hvpfn(skb_frag_page(frag));
+		u32 offset = skb_frag_off(frag);
 
-		slots_used += fill_pg_buf(page_to_hvpfn(skb_frag_page(frag)),
-					  skb_frag_off(frag),
-					  skb_frag_size(frag),
-					  &pb[slots_used]);
+		cur_pb->offset = offset_in_hvpage(offset);
+		cur_pb->len = skb_frag_size(frag);
+		cur_pb->pfn = pfn + (offset >> HV_HYP_PAGE_SHIFT);
 	}
-	return slots_used;
+	return frags + 2;
 }
 
 static int count_skb_frag_slots(struct sk_buff *skb)
@@ -478,7 +449,7 @@ static int netvsc_xmit(struct sk_buff *skb, struct net_device *net, bool xdp_tx)
 	struct net_device *vf_netdev;
 	u32 rndis_msg_size;
 	u32 hash;
-	struct hv_page_buffer pb[MAX_PAGE_BUFFER_COUNT];
+	struct hv_page_buffer pb[MAX_DATA_RANGES];
 
 	/* If VF is present and up then redirect packets to it.
 	 * Skip the VF if it is marked down or has no carrier.
@@ -983,7 +954,8 @@ struct netvsc_device_info *netvsc_devinfo_get(struct netvsc_device *nvdev)
 			dev_info->bprog = prog;
 		}
 	} else {
-		dev_info->num_chn = VRSS_CHANNEL_DEFAULT;
+		dev_info->num_chn = max(VRSS_CHANNEL_DEFAULT,
+					netif_get_num_default_rss_queues());
 		dev_info->send_sections = NETVSC_DEFAULT_TX;
 		dev_info->send_section_size = NETVSC_SEND_SECTION_SIZE;
 		dev_info->recv_sections = NETVSC_DEFAULT_RX;
@@ -1229,14 +1201,14 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 	if (ret)
 		goto rollback_vf;
 
-	ndev->mtu = mtu;
+	WRITE_ONCE(ndev->mtu, mtu);
 
 	ret = netvsc_attach(ndev, device_info);
 	if (!ret)
 		goto out;
 
 	/* Attempt rollback to original MTU */
-	ndev->mtu = orig_mtu;
+	WRITE_ONCE(ndev->mtu, orig_mtu);
 
 	if (netvsc_attach(ndev, device_info))
 		netdev_err(ndev, "restoring mtu failed\n");
@@ -1399,7 +1371,7 @@ static int netvsc_set_mac_addr(struct net_device *ndev, void *p)
 	struct net_device_context *ndc = netdev_priv(ndev);
 	struct net_device *vf_netdev = rtnl_dereference(ndc->vf_netdev);
 	struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev);
-	struct sockaddr *addr = p;
+	struct sockaddr_storage *addr = p;
 	int err;
 
 	err = eth_prepare_mac_addr_change(ndev, p);
@@ -1415,12 +1387,12 @@ static int netvsc_set_mac_addr(struct net_device *ndev, void *p)
 			return err;
 	}
 
-	err = rndis_filter_set_device_mac(nvdev, addr->sa_data);
+	err = rndis_filter_set_device_mac(nvdev, addr->__data);
 	if (!err) {
 		eth_commit_mac_addr_change(ndev, p);
 	} else if (vf_netdev) {
 		/* rollback change on VF */
-		memcpy(addr->sa_data, ndev->dev_addr, ETH_ALEN);
+		memcpy(addr->__data, ndev->dev_addr, ETH_ALEN);
 		dev_set_mac_address(vf_netdev, addr, NULL);
 	}
 
@@ -1552,7 +1524,7 @@ static void netvsc_get_ethtool_stats(struct net_device *dev,
 		data[i++] = xdp_tx;
 	}
 
-	pcpu_sum = kvmalloc_array(num_possible_cpus(),
+	pcpu_sum = kvmalloc_array(nr_cpu_ids,
 				  sizeof(struct netvsc_ethtool_pcpu_stats),
 				  GFP_KERNEL);
 	if (!pcpu_sum)
@@ -2185,7 +2157,7 @@ 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;
@@ -2208,7 +2180,11 @@ 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);
 
@@ -2346,7 +2322,7 @@ 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 +2362,7 @@ 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);
@@ -2452,6 +2428,21 @@ static int netvsc_vf_changed(struct net_device *vf_netdev, unsigned long event)
 	} else {
 		netdev_info(ndev, "Data path switched %s VF: %s\n",
 			    vf_is_up ? "to" : "from", vf_netdev->name);
+
+		/* In Azure, when accelerated networking in enabled, other NICs
+		 * like MANA, MLX, are configured as a bonded nic with
+		 * Netvsc(failover) NIC. For bonded NICs, the min of the max
+		 * pkt aggregate size of the members is propagated in the stack.
+		 * In order to allow these NICs (MANA/MLX) to use up to
+		 * GSO_MAX_SIZE gso packet size, we need to allow Netvsc NIC to
+		 * also support this in the guest.
+		 * This value is only increased for netvsc NIC when datapath is
+		 * switched over to the VF
+		 */
+		if (vf_is_up)
+			netif_set_tso_max_size(ndev, vf_netdev->tso_max_size);
+		else
+			netif_set_tso_max_size(ndev, netvsc_dev->netvsc_gso_max_size);
 	}
 
 	return NOTIFY_OK;
@@ -2471,8 +2462,6 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev)
 
 	netdev_info(ndev, "VF unregistering: %s\n", vf_netdev->name);
 
-	netvsc_vf_setxdp(vf_netdev, NULL);
-
 	reinit_completion(&net_device_ctx->vf_add);
 	netdev_rx_handler_unregister(vf_netdev);
 	netdev_upper_dev_unlink(vf_netdev, ndev);
@@ -2484,10 +2473,31 @@ 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;
@@ -2599,6 +2609,32 @@ 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);
+		netdev_lock_ops(vf_netdev);
+		netvsc_register_vf(vf_netdev, VF_REG_IN_PROBE);
+		netdev_unlock_ops(vf_netdev);
+		__netvsc_vf_setup(net, vf_netdev);
+		break;
+	}
 	rtnl_unlock();
 
 	netvsc_devinfo_put(device_info);
@@ -2744,6 +2780,31 @@ static struct  hv_driver netvsc_drv = {
 	},
 };
 
+/* Set VF's namespace same as the synthetic NIC */
+static void netvsc_event_set_vf_ns(struct net_device *ndev)
+{
+	struct net_device_context *ndev_ctx = netdev_priv(ndev);
+	struct net_device *vf_netdev;
+	int ret;
+
+	vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
+	if (!vf_netdev)
+		return;
+
+	if (!net_eq(dev_net(ndev), dev_net(vf_netdev))) {
+		ret = dev_change_net_namespace(vf_netdev, dev_net(ndev),
+					       "eth%d");
+		if (ret)
+			netdev_err(vf_netdev,
+				   "Cannot move to same namespace as %s: %d\n",
+				   ndev->name, ret);
+		else
+			netdev_info(vf_netdev,
+				    "Moved VF to namespace with: %s\n",
+				    ndev->name);
+	}
+}
+
 /*
  * On Hyper-V, every VF interface is matched with a corresponding
  * synthetic interface. The synthetic interface is presented first
@@ -2754,28 +2815,22 @@ 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))
+	if (event_dev->netdev_ops == &device_ops && event == NETDEV_REGISTER) {
+		netvsc_event_set_vf_ns(event_dev);
 		return NOTIFY_DONE;
+	}
 
-	/* Avoid Bonding master dev with same MAC registering as VF */
-	if (netif_is_bond_master(event_dev))
+	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:
@@ -2807,7 +2862,7 @@ static int __init netvsc_drv_init(void)
 		pr_info("Increased ring_size to %u (min allowed)\n",
 			ring_size);
 	}
-	netvsc_ring_bytes = ring_size * PAGE_SIZE;
+	netvsc_ring_bytes = VMBUS_RING_SIZE(ring_size * 4096);
 
 	register_netdevice_notifier(&netvsc_netdev_notifier);