1 files changed, 206 insertions, 54 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 613fb4066be7..dda9d7b9a840 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1554,6 +1554,23 @@ void dev_disable_lro(struct net_device *dev)
 }
 EXPORT_SYMBOL(dev_disable_lro);
 
+/**
+ *	dev_disable_gro_hw - disable HW Generic Receive Offload on a device
+ *	@dev: device
+ *
+ *	Disable HW Generic Receive Offload (GRO_HW) on a net device.  Must be
+ *	called under RTNL.  This is needed if Generic XDP is installed on
+ *	the device.
+ */
+static void dev_disable_gro_hw(struct net_device *dev)
+{
+	dev->wanted_features &= ~NETIF_F_GRO_HW;
+	netdev_update_features(dev);
+
+	if (unlikely(dev->features & NETIF_F_GRO_HW))
+		netdev_WARN(dev, "failed to disable GRO_HW!\n");
+}
+
 static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val,
 				   struct net_device *dev)
 {
@@ -1677,7 +1694,6 @@ EXPORT_SYMBOL(unregister_netdevice_notifier);
 /**
  *	call_netdevice_notifiers_info - call all network notifier blocks
  *	@val: value passed unmodified to notifier function
- *	@dev: net_device pointer passed unmodified to notifier function
  *	@info: notifier information data
  *
  *	Call all network notifier blocks.  Parameters and return value
@@ -2815,7 +2831,7 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 
 	segs = skb_mac_gso_segment(skb, features);
 
-	if (unlikely(skb_needs_check(skb, tx_path)))
+	if (unlikely(skb_needs_check(skb, tx_path) && !IS_ERR(segs)))
 		skb_warn_bad_offload(skb);
 
 	return segs;
@@ -3054,7 +3070,7 @@ int skb_csum_hwoffload_help(struct sk_buff *skb,
 }
 EXPORT_SYMBOL(skb_csum_hwoffload_help);
 
-static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev)
+static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev, bool *again)
 {
 	netdev_features_t features;
 
@@ -3078,9 +3094,6 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device
 		    __skb_linearize(skb))
 			goto out_kfree_skb;
 
-		if (validate_xmit_xfrm(skb, features))
-			goto out_kfree_skb;
-
 		/* If packet is not checksummed and device does not
 		 * support checksumming for this protocol, complete
 		 * checksumming here.
@@ -3097,6 +3110,8 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device
 		}
 	}
 
+	skb = validate_xmit_xfrm(skb, features, again);
+
 	return skb;
 
 out_kfree_skb:
@@ -3106,7 +3121,7 @@ out_null:
 	return NULL;
 }
 
-struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev)
+struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again)
 {
 	struct sk_buff *next, *head = NULL, *tail;
 
@@ -3117,7 +3132,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d
 		/* in case skb wont be segmented, point to itself */
 		skb->prev = skb;
 
-		skb = validate_xmit_skb(skb, dev);
+		skb = validate_xmit_skb(skb, dev, again);
 		if (!skb)
 			continue;
 
@@ -3185,6 +3200,21 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 	int rc;
 
 	qdisc_calculate_pkt_len(skb, q);
+
+	if (q->flags & TCQ_F_NOLOCK) {
+		if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
+			__qdisc_drop(skb, &to_free);
+			rc = NET_XMIT_DROP;
+		} else {
+			rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+			__qdisc_run(q);
+		}
+
+		if (unlikely(to_free))
+			kfree_skb_list(to_free);
+		return rc;
+	}
+
 	/*
 	 * Heuristic to force contended enqueues to serialize on a
 	 * separate lock before trying to get qdisc main lock.
@@ -3215,9 +3245,9 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 				contended = false;
 			}
 			__qdisc_run(q);
-		} else
-			qdisc_run_end(q);
+		}
 
+		qdisc_run_end(q);
 		rc = NET_XMIT_SUCCESS;
 	} else {
 		rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
@@ -3227,6 +3257,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 				contended = false;
 			}
 			__qdisc_run(q);
+			qdisc_run_end(q);
 		}
 	}
 	spin_unlock(root_lock);
@@ -3399,8 +3430,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 		else
 			queue_index = __netdev_pick_tx(dev, skb);
 
-		if (!accel_priv)
-			queue_index = netdev_cap_txqueue(dev, queue_index);
+		queue_index = netdev_cap_txqueue(dev, queue_index);
 	}
 
 	skb_set_queue_mapping(skb, queue_index);
@@ -3439,6 +3469,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
 	struct netdev_queue *txq;
 	struct Qdisc *q;
 	int rc = -ENOMEM;
+	bool again = false;
 
 	skb_reset_mac_header(skb);
 
@@ -3500,7 +3531,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
 				     XMIT_RECURSION_LIMIT))
 				goto recursion_alert;
 
-			skb = validate_xmit_skb(skb, dev);
+			skb = validate_xmit_skb(skb, dev, &again);
 			if (!skb)
 				goto out;
 
@@ -3896,9 +3927,33 @@ drop:
 	return NET_RX_DROP;
 }
 
+static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb)
+{
+	struct net_device *dev = skb->dev;
+	struct netdev_rx_queue *rxqueue;
+
+	rxqueue = dev->_rx;
+
+	if (skb_rx_queue_recorded(skb)) {
+		u16 index = skb_get_rx_queue(skb);
+
+		if (unlikely(index >= dev->real_num_rx_queues)) {
+			WARN_ONCE(dev->real_num_rx_queues > 1,
+				  "%s received packet on queue %u, but number "
+				  "of RX queues is %u\n",
+				  dev->name, index, dev->real_num_rx_queues);
+
+			return rxqueue; /* Return first rxqueue */
+		}
+		rxqueue += index;
+	}
+	return rxqueue;
+}
+
 static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 				     struct bpf_prog *xdp_prog)
 {
+	struct netdev_rx_queue *rxqueue;
 	u32 metalen, act = XDP_DROP;
 	struct xdp_buff xdp;
 	void *orig_data;
@@ -3942,6 +3997,9 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	xdp.data_hard_start = skb->data - skb_headroom(skb);
 	orig_data = xdp.data;
 
+	rxqueue = netif_get_rxqueue(skb);
+	xdp.rxq = &rxqueue->xdp_rxq;
+
 	act = bpf_prog_run_xdp(xdp_prog, &xdp);
 
 	off = xdp.data - orig_data;
@@ -4166,21 +4224,26 @@ static __latent_entropy void net_tx_action(struct softirq_action *h)
 
 		while (head) {
 			struct Qdisc *q = head;
-			spinlock_t *root_lock;
+			spinlock_t *root_lock = NULL;
 
 			head = head->next_sched;
 
-			root_lock = qdisc_lock(q);
-			spin_lock(root_lock);
+			if (!(q->flags & TCQ_F_NOLOCK)) {
+				root_lock = qdisc_lock(q);
+				spin_lock(root_lock);
+			}
 			/* We need to make sure head->next_sched is read
 			 * before clearing __QDISC_STATE_SCHED
 			 */
 			smp_mb__before_atomic();
 			clear_bit(__QDISC_STATE_SCHED, &q->state);
 			qdisc_run(q);
-			spin_unlock(root_lock);
+			if (root_lock)
+				spin_unlock(root_lock);
 		}
 	}
+
+	xfrm_dev_backlog(sd);
 }
 
 #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_ATM_LANE)
@@ -4568,6 +4631,7 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 		} else if (new && !old) {
 			static_key_slow_inc(&generic_xdp_needed);
 			dev_disable_lro(dev);
+			dev_disable_gro_hw(dev);
 		}
 		break;
 
@@ -6371,6 +6435,7 @@ rollback:
  * netdev_upper_dev_link - Add a link to the upper device
  * @dev: device
  * @upper_dev: new upper device
+ * @extack: netlink extended ack
  *
  * Adds a link to device which is upper to this one. The caller must hold
  * the RTNL lock. On a failure a negative errno code is returned.
@@ -6392,6 +6457,7 @@ EXPORT_SYMBOL(netdev_upper_dev_link);
  * @upper_dev: new upper device
  * @upper_priv: upper device private
  * @upper_info: upper info to be passed down via notifier
+ * @extack: netlink extended ack
  *
  * Adds a link to device which is upper to this one. In this case, only
  * one master upper device can be linked, although other non-master devices
@@ -6982,6 +7048,35 @@ int dev_set_mtu(struct net_device *dev, int new_mtu)
 EXPORT_SYMBOL(dev_set_mtu);
 
 /**
+ *	dev_change_tx_queue_len - Change TX queue length of a netdevice
+ *	@dev: device
+ *	@new_len: new tx queue length
+ */
+int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len)
+{
+	unsigned int orig_len = dev->tx_queue_len;
+	int res;
+
+	if (new_len != (unsigned int)new_len)
+		return -ERANGE;
+
+	if (new_len != orig_len) {
+		dev->tx_queue_len = new_len;
+		res = call_netdevice_notifiers(NETDEV_CHANGE_TX_QUEUE_LEN, dev);
+		res = notifier_to_errno(res);
+		if (res) {
+			netdev_err(dev,
+				   "refused to change device tx_queue_len\n");
+			dev->tx_queue_len = orig_len;
+			return res;
+		}
+		return dev_qdisc_change_tx_queue_len(dev);
+	}
+
+	return 0;
+}
+
+/**
  *	dev_set_group - Change group this device belongs to
  *	@dev: device
  *	@new_group: group this device should belong to
@@ -7096,17 +7191,21 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down)
 }
 EXPORT_SYMBOL(dev_change_proto_down);
 
-u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op, u32 *prog_id)
+void __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op,
+		     struct netdev_bpf *xdp)
 {
-	struct netdev_bpf xdp;
-
-	memset(&xdp, 0, sizeof(xdp));
-	xdp.command = XDP_QUERY_PROG;
+	memset(xdp, 0, sizeof(*xdp));
+	xdp->command = XDP_QUERY_PROG;
 
 	/* Query must always succeed. */
-	WARN_ON(bpf_op(dev, &xdp) < 0);
-	if (prog_id)
-		*prog_id = xdp.prog_id;
+	WARN_ON(bpf_op(dev, xdp) < 0);
+}
+
+static u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op)
+{
+	struct netdev_bpf xdp;
+
+	__dev_xdp_query(dev, bpf_op, &xdp);
 
 	return xdp.prog_attached;
 }
@@ -7129,6 +7228,27 @@ static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op,
 	return bpf_op(dev, &xdp);
 }
 
+static void dev_xdp_uninstall(struct net_device *dev)
+{
+	struct netdev_bpf xdp;
+	bpf_op_t ndo_bpf;
+
+	/* Remove generic XDP */
+	WARN_ON(dev_xdp_install(dev, generic_xdp_install, NULL, 0, NULL));
+
+	/* Remove from the driver */
+	ndo_bpf = dev->netdev_ops->ndo_bpf;
+	if (!ndo_bpf)
+		return;
+
+	__dev_xdp_query(dev, ndo_bpf, &xdp);
+	if (xdp.prog_attached == XDP_ATTACHED_NONE)
+		return;
+
+	/* Program removal should always succeed */
+	WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags, NULL));
+}
+
 /**
  *	dev_change_xdp_fd - set or clear a bpf program for a device rx path
  *	@dev: device
@@ -7157,10 +7277,10 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		bpf_chk = generic_xdp_install;
 
 	if (fd >= 0) {
-		if (bpf_chk && __dev_xdp_attached(dev, bpf_chk, NULL))
+		if (bpf_chk && __dev_xdp_attached(dev, bpf_chk))
 			return -EEXIST;
 		if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) &&
-		    __dev_xdp_attached(dev, bpf_op, NULL))
+		    __dev_xdp_attached(dev, bpf_op))
 			return -EBUSY;
 
 		prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP,
@@ -7259,6 +7379,7 @@ static void rollback_registered_many(struct list_head *head)
 		/* Shutdown queueing discipline. */
 		dev_shutdown(dev);
 
+		dev_xdp_uninstall(dev);
 
 		/* Notify protocols, that we are about to destroy
 		 * this device. They should clean all the things.
@@ -7268,7 +7389,7 @@ static void rollback_registered_many(struct list_head *head)
 		if (!dev->rtnl_link_ops ||
 		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
 			skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0,
-						     GFP_KERNEL, NULL);
+						     GFP_KERNEL, NULL, 0);
 
 		/*
 		 *	Flush the unicast and multicast chains
@@ -7402,6 +7523,18 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
 		features &= ~dev->gso_partial_features;
 	}
 
+	if (!(features & NETIF_F_RXCSUM)) {
+		/* NETIF_F_GRO_HW implies doing RXCSUM since every packet
+		 * successfully merged by hardware must also have the
+		 * checksum verified by hardware.  If the user does not
+		 * want to enable RXCSUM, logically, we should disable GRO_HW.
+		 */
+		if (features & NETIF_F_GRO_HW) {
+			netdev_dbg(dev, "Dropping NETIF_F_GRO_HW since no RXCSUM feature.\n");
+			features &= ~NETIF_F_GRO_HW;
+		}
+	}
+
 	return features;
 }
 
@@ -7535,12 +7668,12 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev,
 }
 EXPORT_SYMBOL(netif_stacked_transfer_operstate);
 
-#ifdef CONFIG_SYSFS
 static int netif_alloc_rx_queues(struct net_device *dev)
 {
 	unsigned int i, count = dev->num_rx_queues;
 	struct netdev_rx_queue *rx;
 	size_t sz = count * sizeof(*rx);
+	int err = 0;
 
 	BUG_ON(count < 1);
 
@@ -7550,11 +7683,38 @@ static int netif_alloc_rx_queues(struct net_device *dev)
 
 	dev->_rx = rx;
 
-	for (i = 0; i < count; i++)
+	for (i = 0; i < count; i++) {
 		rx[i].dev = dev;
+
+		/* XDP RX-queue setup */
+		err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i);
+		if (err < 0)
+			goto err_rxq_info;
+	}
 	return 0;
+
+err_rxq_info:
+	/* Rollback successful reg's and free other resources */
+	while (i--)
+		xdp_rxq_info_unreg(&rx[i].xdp_rxq);
+	kvfree(dev->_rx);
+	dev->_rx = NULL;
+	return err;
+}
+
+static void netif_free_rx_queues(struct net_device *dev)
+{
+	unsigned int i, count = dev->num_rx_queues;
+
+	/* netif_alloc_rx_queues alloc failed, resources have been unreg'ed */
+	if (!dev->_rx)
+		return;
+
+	for (i = 0; i < count; i++)
+		xdp_rxq_info_unreg(&dev->_rx[i].xdp_rxq);
+
+	kvfree(dev->_rx);
 }
-#endif
 
 static void netdev_init_one_queue(struct net_device *dev,
 				  struct netdev_queue *queue, void *_unused)
@@ -8115,12 +8275,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 		return NULL;
 	}
 
-#ifdef CONFIG_SYSFS
 	if (rxqs < 1) {
 		pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n");
 		return NULL;
 	}
-#endif
 
 	alloc_size = sizeof(struct net_device);
 	if (sizeof_priv) {
@@ -8177,12 +8335,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	if (netif_alloc_netdev_queues(dev))
 		goto free_all;
 
-#ifdef CONFIG_SYSFS
 	dev->num_rx_queues = rxqs;
 	dev->real_num_rx_queues = rxqs;
 	if (netif_alloc_rx_queues(dev))
 		goto free_all;
-#endif
 
 	strcpy(dev->name, name);
 	dev->name_assign_type = name_assign_type;
@@ -8218,13 +8374,10 @@ EXPORT_SYMBOL(alloc_netdev_mqs);
 void free_netdev(struct net_device *dev)
 {
 	struct napi_struct *p, *n;
-	struct bpf_prog *prog;
 
 	might_sleep();
 	netif_free_tx_queues(dev);
-#ifdef CONFIG_SYSFS
-	kvfree(dev->_rx);
-#endif
+	netif_free_rx_queues(dev);
 
 	kfree(rcu_dereference_protected(dev->ingress_queue, 1));
 
@@ -8237,12 +8390,6 @@ void free_netdev(struct net_device *dev)
 	free_percpu(dev->pcpu_refcnt);
 	dev->pcpu_refcnt = NULL;
 
-	prog = rcu_dereference_protected(dev->xdp_prog, 1);
-	if (prog) {
-		bpf_prog_put(prog);
-		static_key_slow_dec(&generic_xdp_needed);
-	}
-
 	/*  Compatibility with error handling in drivers */
 	if (dev->reg_state == NETREG_UNINITIALIZED) {
 		netdev_freemem(dev);
@@ -8355,7 +8502,7 @@ EXPORT_SYMBOL(unregister_netdev);
 
 int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat)
 {
-	int err, new_nsid;
+	int err, new_nsid, new_ifindex;
 
 	ASSERT_RTNL();
 
@@ -8411,11 +8558,16 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
 	call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
 	rcu_barrier();
 	call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev);
-	if (dev->rtnl_link_ops && dev->rtnl_link_ops->get_link_net)
-		new_nsid = peernet2id_alloc(dev_net(dev), net);
+
+	new_nsid = peernet2id_alloc(dev_net(dev), net);
+	/* If there is an ifindex conflict assign a new one */
+	if (__dev_get_by_index(net, dev->ifindex))
+		new_ifindex = dev_new_index(net);
 	else
-		new_nsid = peernet2id(dev_net(dev), net);
-	rtmsg_ifinfo_newnet(RTM_DELLINK, dev, ~0U, GFP_KERNEL, &new_nsid);
+		new_ifindex = dev->ifindex;
+
+	rtmsg_ifinfo_newnet(RTM_DELLINK, dev, ~0U, GFP_KERNEL, &new_nsid,
+			    new_ifindex);
 
 	/*
 	 *	Flush the unicast and multicast chains
@@ -8429,10 +8581,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
 
 	/* Actually switch the network namespace */
 	dev_net_set(dev, net);
-
-	/* If there is an ifindex conflict assign a new one */
-	if (__dev_get_by_index(net, dev->ifindex))
-		dev->ifindex = dev_new_index(net);
+	dev->ifindex = new_ifindex;
 
 	/* Send a netdev-add uevent to the new namespace */
 	kobject_uevent(&dev->dev.kobj, KOBJ_ADD);
@@ -8830,6 +8979,9 @@ static int __init net_dev_init(void)
 
 		skb_queue_head_init(&sd->input_pkt_queue);
 		skb_queue_head_init(&sd->process_queue);
+#ifdef CONFIG_XFRM_OFFLOAD
+		skb_queue_head_init(&sd->xfrm_backlog);
+#endif
 		INIT_LIST_HEAD(&sd->poll_list);
 		sd->output_queue_tailp = &sd->output_queue;
 #ifdef CONFIG_RPS