1 files changed, 93 insertions, 54 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 253584777101..735096d42c1d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -160,8 +160,6 @@ struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
 struct list_head ptype_all __read_mostly;	/* Taps */
 
 static int netif_rx_internal(struct sk_buff *skb);
-static int call_netdevice_notifiers_info(unsigned long val,
-					 struct netdev_notifier_info *info);
 static int call_netdevice_notifiers_extack(unsigned long val,
 					   struct net_device *dev,
 					   struct netlink_ext_ack *extack);
@@ -1919,8 +1917,8 @@ static void move_netdevice_notifiers_dev_net(struct net_device *dev,
  *	are as for raw_notifier_call_chain().
  */
 
-static int call_netdevice_notifiers_info(unsigned long val,
-					 struct netdev_notifier_info *info)
+int call_netdevice_notifiers_info(unsigned long val,
+				  struct netdev_notifier_info *info)
 {
 	struct net *net = dev_net(info->dev);
 	int ret;
@@ -2535,6 +2533,8 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
 	struct xps_map *map, *new_map;
 	unsigned int nr_ids;
 
+	WARN_ON_ONCE(index >= dev->num_tx_queues);
+
 	if (dev->num_tc) {
 		/* Do not allow XPS on subordinate device directly */
 		num_tc = dev->num_tc;
@@ -3075,7 +3075,7 @@ void __netif_schedule(struct Qdisc *q)
 EXPORT_SYMBOL(__netif_schedule);
 
 struct dev_kfree_skb_cb {
-	enum skb_free_reason reason;
+	enum skb_drop_reason reason;
 };
 
 static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb)
@@ -3108,7 +3108,7 @@ void netif_tx_wake_queue(struct netdev_queue *dev_queue)
 }
 EXPORT_SYMBOL(netif_tx_wake_queue);
 
-void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason)
+void dev_kfree_skb_irq_reason(struct sk_buff *skb, enum skb_drop_reason reason)
 {
 	unsigned long flags;
 
@@ -3128,18 +3128,16 @@ void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason)
 	raise_softirq_irqoff(NET_TX_SOFTIRQ);
 	local_irq_restore(flags);
 }
-EXPORT_SYMBOL(__dev_kfree_skb_irq);
+EXPORT_SYMBOL(dev_kfree_skb_irq_reason);
 
-void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason)
+void dev_kfree_skb_any_reason(struct sk_buff *skb, enum skb_drop_reason reason)
 {
 	if (in_hardirq() || irqs_disabled())
-		__dev_kfree_skb_irq(skb, reason);
-	else if (unlikely(reason == SKB_REASON_DROPPED))
-		kfree_skb(skb);
+		dev_kfree_skb_irq_reason(skb, reason);
 	else
-		consume_skb(skb);
+		kfree_skb_reason(skb, reason);
 }
-EXPORT_SYMBOL(__dev_kfree_skb_any);
+EXPORT_SYMBOL(dev_kfree_skb_any_reason);
 
 
 /**
@@ -3199,6 +3197,7 @@ static u16 skb_tx_hash(const struct net_device *dev,
 	}
 
 	if (skb_rx_queue_recorded(skb)) {
+		DEBUG_NET_WARN_ON_ONCE(qcount == 0);
 		hash = skb_get_rx_queue(skb);
 		if (hash >= qoffset)
 			hash -= qoffset;
@@ -3316,8 +3315,7 @@ int skb_crc32c_csum_help(struct sk_buff *skb)
 						  skb->len - start, ~(__u32)0,
 						  crc32c_csum_stub));
 	*(__le32 *)(skb->data + offset) = crc32c_csum;
-	skb->ip_summed = CHECKSUM_NONE;
-	skb->csum_not_inet = 0;
+	skb_reset_csum_not_inet(skb);
 out:
 	return ret;
 }
@@ -3735,25 +3733,25 @@ static void qdisc_pkt_len_init(struct sk_buff *skb)
 	 * we add to pkt_len the headers size of all segments
 	 */
 	if (shinfo->gso_size && skb_transport_header_was_set(skb)) {
-		unsigned int hdr_len;
 		u16 gso_segs = shinfo->gso_segs;
+		unsigned int hdr_len;
 
 		/* mac layer + network layer */
-		hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
+		hdr_len = skb_transport_offset(skb);
 
 		/* + transport layer */
 		if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) {
 			const struct tcphdr *th;
 			struct tcphdr _tcphdr;
 
-			th = skb_header_pointer(skb, skb_transport_offset(skb),
+			th = skb_header_pointer(skb, hdr_len,
 						sizeof(_tcphdr), &_tcphdr);
 			if (likely(th))
 				hdr_len += __tcp_hdrlen(th);
 		} else {
 			struct udphdr _udphdr;
 
-			if (skb_header_pointer(skb, skb_transport_offset(skb),
+			if (skb_header_pointer(skb, hdr_len,
 					       sizeof(_udphdr), &_udphdr))
 				hdr_len += sizeof(struct udphdr);
 		}
@@ -4360,7 +4358,12 @@ static inline void ____napi_schedule(struct softnet_data *sd,
 	}
 
 	list_add_tail(&napi->poll_list, &sd->poll_list);
-	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
+	WRITE_ONCE(napi->list_owner, smp_processor_id());
+	/* If not called from net_rx_action()
+	 * we have to raise NET_RX_SOFTIRQ.
+	 */
+	if (!sd->in_net_rx_action)
+		__raise_softirq_irqoff(NET_RX_SOFTIRQ);
 }
 
 #ifdef CONFIG_RPS
@@ -4582,11 +4585,16 @@ static void trigger_rx_softirq(void *data)
 }
 
 /*
- * Check if this softnet_data structure is another cpu one
- * If yes, queue it to our IPI list and return 1
- * If no, return 0
+ * After we queued a packet into sd->input_pkt_queue,
+ * we need to make sure this queue is serviced soon.
+ *
+ * - If this is another cpu queue, link it to our rps_ipi_list,
+ *   and make sure we will process rps_ipi_list from net_rx_action().
+ *
+ * - If this is our own queue, NAPI schedule our backlog.
+ *   Note that this also raises NET_RX_SOFTIRQ.
  */
-static int napi_schedule_rps(struct softnet_data *sd)
+static void napi_schedule_rps(struct softnet_data *sd)
 {
 	struct softnet_data *mysd = this_cpu_ptr(&softnet_data);
 
@@ -4595,12 +4603,15 @@ static int napi_schedule_rps(struct softnet_data *sd)
 		sd->rps_ipi_next = mysd->rps_ipi_list;
 		mysd->rps_ipi_list = sd;
 
-		__raise_softirq_irqoff(NET_RX_SOFTIRQ);
-		return 1;
+		/* If not called from net_rx_action() or napi_threaded_poll()
+		 * we have to raise NET_RX_SOFTIRQ.
+		 */
+		if (!mysd->in_net_rx_action && !mysd->in_napi_threaded_poll)
+			__raise_softirq_irqoff(NET_RX_SOFTIRQ);
+		return;
 	}
 #endif /* CONFIG_RPS */
 	__napi_schedule_irqoff(&mysd->backlog);
-	return 0;
 }
 
 #ifdef CONFIG_NET_FLOW_LIMIT
@@ -5020,16 +5031,17 @@ static __latent_entropy void net_tx_action(struct softirq_action *h)
 			clist = clist->next;
 
 			WARN_ON(refcount_read(&skb->users));
-			if (likely(get_kfree_skb_cb(skb)->reason == SKB_REASON_CONSUMED))
+			if (likely(get_kfree_skb_cb(skb)->reason == SKB_CONSUMED))
 				trace_consume_skb(skb, net_tx_action);
 			else
 				trace_kfree_skb(skb, net_tx_action,
-						SKB_DROP_REASON_NOT_SPECIFIED);
+						get_kfree_skb_cb(skb)->reason);
 
 			if (skb->fclone != SKB_FCLONE_UNAVAILABLE)
 				__kfree_skb(skb);
 			else
-				__kfree_skb_defer(skb);
+				__napi_kfree_skb(skb,
+						 get_kfree_skb_cb(skb)->reason);
 		}
 	}
 
@@ -6058,6 +6070,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 		list_del_init(&n->poll_list);
 		local_irq_restore(flags);
 	}
+	WRITE_ONCE(n->list_owner, -1);
 
 	val = READ_ONCE(n->state);
 	do {
@@ -6373,6 +6386,7 @@ void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
 #ifdef CONFIG_NETPOLL
 	napi->poll_owner = -1;
 #endif
+	napi->list_owner = -1;
 	set_bit(NAPI_STATE_SCHED, &napi->state);
 	set_bit(NAPI_STATE_NPSVC, &napi->state);
 	list_add_rcu(&napi->dev_list, &dev->napi_list);
@@ -6584,9 +6598,31 @@ static int napi_thread_wait(struct napi_struct *napi)
 	return -1;
 }
 
+static void skb_defer_free_flush(struct softnet_data *sd)
+{
+	struct sk_buff *skb, *next;
+
+	/* Paired with WRITE_ONCE() in skb_attempt_defer_free() */
+	if (!READ_ONCE(sd->defer_list))
+		return;
+
+	spin_lock(&sd->defer_lock);
+	skb = sd->defer_list;
+	sd->defer_list = NULL;
+	sd->defer_count = 0;
+	spin_unlock(&sd->defer_lock);
+
+	while (skb != NULL) {
+		next = skb->next;
+		napi_consume_skb(skb, 1);
+		skb = next;
+	}
+}
+
 static int napi_threaded_poll(void *data)
 {
 	struct napi_struct *napi = data;
+	struct softnet_data *sd;
 	void *have;
 
 	while (!napi_thread_wait(napi)) {
@@ -6594,11 +6630,21 @@ static int napi_threaded_poll(void *data)
 			bool repoll = false;
 
 			local_bh_disable();
+			sd = this_cpu_ptr(&softnet_data);
+			sd->in_napi_threaded_poll = true;
 
 			have = netpoll_poll_lock(napi);
 			__napi_poll(napi, &repoll);
 			netpoll_poll_unlock(have);
 
+			sd->in_napi_threaded_poll = false;
+			barrier();
+
+			if (sd_has_rps_ipi_waiting(sd)) {
+				local_irq_disable();
+				net_rps_action_and_irq_enable(sd);
+			}
+			skb_defer_free_flush(sd);
 			local_bh_enable();
 
 			if (!repoll)
@@ -6610,27 +6656,6 @@ static int napi_threaded_poll(void *data)
 	return 0;
 }
 
-static void skb_defer_free_flush(struct softnet_data *sd)
-{
-	struct sk_buff *skb, *next;
-
-	/* Paired with WRITE_ONCE() in skb_attempt_defer_free() */
-	if (!READ_ONCE(sd->defer_list))
-		return;
-
-	spin_lock_irq(&sd->defer_lock);
-	skb = sd->defer_list;
-	sd->defer_list = NULL;
-	sd->defer_count = 0;
-	spin_unlock_irq(&sd->defer_lock);
-
-	while (skb != NULL) {
-		next = skb->next;
-		napi_consume_skb(skb, 1);
-		skb = next;
-	}
-}
-
 static __latent_entropy void net_rx_action(struct softirq_action *h)
 {
 	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
@@ -6640,6 +6665,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
 	LIST_HEAD(list);
 	LIST_HEAD(repoll);
 
+start:
+	sd->in_net_rx_action = true;
 	local_irq_disable();
 	list_splice_init(&sd->poll_list, &list);
 	local_irq_enable();
@@ -6650,8 +6677,18 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
 		skb_defer_free_flush(sd);
 
 		if (list_empty(&list)) {
-			if (!sd_has_rps_ipi_waiting(sd) && list_empty(&repoll))
-				goto end;
+			if (list_empty(&repoll)) {
+				sd->in_net_rx_action = false;
+				barrier();
+				/* We need to check if ____napi_schedule()
+				 * had refilled poll_list while
+				 * sd->in_net_rx_action was true.
+				 */
+				if (!list_empty(&sd->poll_list))
+					goto start;
+				if (!sd_has_rps_ipi_waiting(sd))
+					goto end;
+			}
 			break;
 		}
 
@@ -6676,6 +6713,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
 	list_splice(&list, &sd->poll_list);
 	if (!list_empty(&sd->poll_list))
 		__raise_softirq_irqoff(NET_RX_SOFTIRQ);
+	else
+		sd->in_net_rx_action = false;
 
 	net_rps_action_and_irq_enable(sd);
 end:;
@@ -10846,7 +10885,7 @@ void unregister_netdevice_many_notify(struct list_head *head,
 		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
 			skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0,
 						     GFP_KERNEL, NULL, 0,
-						     portid, nlmsg_seq(nlh));
+						     portid, nlh);
 
 		/*
 		 *	Flush the unicast and multicast chains