1 files changed, 146 insertions, 36 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 68dc47d7e700..a64cef2c537e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3768,8 +3768,14 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb,
 	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL))
 		features &= ~dev->gso_partial_features;
 
-	/* Make sure to clear the IPv4 ID mangling feature if the
-	 * IPv4 header has the potential to be fragmented.
+	/* Make sure to clear the IPv4 ID mangling feature if the IPv4 header
+	 * has the potential to be fragmented so that TSO does not generate
+	 * segments with the same ID. For encapsulated packets, the ID mangling
+	 * feature is guaranteed not to use the same ID for the outer IPv4
+	 * headers of the generated segments if the headers have the potential
+	 * to be fragmented, so there is no need to clear the IPv4 ID mangling
+	 * feature (see the section about NETIF_F_TSO_MANGLEID in
+	 * segmentation-offloads.rst).
 	 */
 	if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) {
 		struct iphdr *iph = skb->encapsulation ?
@@ -3779,6 +3785,18 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb,
 			features &= ~NETIF_F_TSO_MANGLEID;
 	}
 
+	/* NETIF_F_IPV6_CSUM does not support IPv6 extension headers,
+	 * so neither does TSO that depends on it.
+	 */
+	if (features & NETIF_F_IPV6_CSUM &&
+	    (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6 ||
+	     (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 &&
+	      vlan_get_protocol(skb) == htons(ETH_P_IPV6))) &&
+	    skb_transport_header_was_set(skb) &&
+	    skb_network_header_len(skb) != sizeof(struct ipv6hdr) &&
+	    !ipv6_has_hopopt_jumbo(skb))
+		features &= ~(NETIF_F_IPV6_CSUM | NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4);
+
 	return features;
 }
 
@@ -3895,6 +3913,38 @@ sw_checksum:
 }
 EXPORT_SYMBOL(skb_csum_hwoffload_help);
 
+/* Checks if this SKB belongs to an HW offloaded socket
+ * and whether any SW fallbacks are required based on dev.
+ * Check decrypted mark in case skb_orphan() cleared socket.
+ */
+static struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb,
+					    struct net_device *dev)
+{
+#ifdef CONFIG_SOCK_VALIDATE_XMIT
+	struct sk_buff *(*sk_validate)(struct sock *sk, struct net_device *dev,
+				       struct sk_buff *skb);
+	struct sock *sk = skb->sk;
+
+	sk_validate = NULL;
+	if (sk) {
+		if (sk_fullsock(sk))
+			sk_validate = sk->sk_validate_xmit_skb;
+		else if (sk_is_inet(sk) && sk->sk_state == TCP_TIME_WAIT)
+			sk_validate = inet_twsk(sk)->tw_validate_xmit_skb;
+	}
+
+	if (sk_validate) {
+		skb = sk_validate(sk, dev, skb);
+	} else if (unlikely(skb_is_decrypted(skb))) {
+		pr_warn_ratelimited("unencrypted skb with no associated socket - dropping\n");
+		kfree_skb(skb);
+		skb = NULL;
+	}
+#endif
+
+	return skb;
+}
+
 static struct sk_buff *validate_xmit_unreadable_skb(struct sk_buff *skb,
 						    struct net_device *dev)
 {
@@ -4837,9 +4887,40 @@ static u32 rfs_slot(u32 hash, const struct rps_dev_flow_table *flow_table)
 	return hash_32(hash, flow_table->log);
 }
 
+#ifdef CONFIG_RFS_ACCEL
+/**
+ * rps_flow_is_active - check whether the flow is recently active.
+ * @rflow: Specific flow to check activity.
+ * @flow_table: per-queue flowtable that @rflow belongs to.
+ * @cpu: CPU saved in @rflow.
+ *
+ * If the CPU has processed many packets since the flow's last activity
+ * (beyond 10 times the table size), the flow is considered stale.
+ *
+ * Return: true if flow was recently active.
+ */
+static bool rps_flow_is_active(struct rps_dev_flow *rflow,
+			       struct rps_dev_flow_table *flow_table,
+			       unsigned int cpu)
+{
+	unsigned int flow_last_active;
+	unsigned int sd_input_head;
+
+	if (cpu >= nr_cpu_ids)
+		return false;
+
+	sd_input_head = READ_ONCE(per_cpu(softnet_data, cpu).input_queue_head);
+	flow_last_active = READ_ONCE(rflow->last_qtail);
+
+	return (int)(sd_input_head - flow_last_active) <
+		(int)(10 << flow_table->log);
+}
+#endif
+
 static struct rps_dev_flow *
 set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
-	    struct rps_dev_flow *rflow, u16 next_cpu)
+	    struct rps_dev_flow *rflow, u16 next_cpu, u32 hash,
+	    u32 flow_id)
 {
 	if (next_cpu < nr_cpu_ids) {
 		u32 head;
@@ -4847,8 +4928,9 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		struct netdev_rx_queue *rxqueue;
 		struct rps_dev_flow_table *flow_table;
 		struct rps_dev_flow *old_rflow;
+		struct rps_dev_flow *tmp_rflow;
+		unsigned int tmp_cpu;
 		u16 rxq_index;
-		u32 flow_id;
 		int rc;
 
 		/* Should we steer this flow to a different hardware queue? */
@@ -4863,14 +4945,29 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		flow_table = rcu_dereference(rxqueue->rps_flow_table);
 		if (!flow_table)
 			goto out;
-		flow_id = rfs_slot(skb_get_hash(skb), flow_table);
+
+		tmp_rflow = &flow_table->flows[flow_id];
+		tmp_cpu = READ_ONCE(tmp_rflow->cpu);
+
+		if (READ_ONCE(tmp_rflow->filter) != RPS_NO_FILTER) {
+			if (rps_flow_is_active(tmp_rflow, flow_table,
+					       tmp_cpu)) {
+				if (hash != READ_ONCE(tmp_rflow->hash) ||
+				    next_cpu == tmp_cpu)
+					goto out;
+			}
+		}
+
 		rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb,
 							rxq_index, flow_id);
 		if (rc < 0)
 			goto out;
+
 		old_rflow = rflow;
-		rflow = &flow_table->flows[flow_id];
+		rflow = tmp_rflow;
 		WRITE_ONCE(rflow->filter, rc);
+		WRITE_ONCE(rflow->hash, hash);
+
 		if (old_rflow->filter == rc)
 			WRITE_ONCE(old_rflow->filter, RPS_NO_FILTER);
 	out:
@@ -4896,6 +4993,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	struct rps_dev_flow_table *flow_table;
 	struct rps_map *map;
 	int cpu = -1;
+	u32 flow_id;
 	u32 tcpu;
 	u32 hash;
 
@@ -4942,7 +5040,8 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		/* OK, now we know there is a match,
 		 * we can look at the local (per receive queue) flow table
 		 */
-		rflow = &flow_table->flows[rfs_slot(hash, flow_table)];
+		flow_id = rfs_slot(hash, flow_table);
+		rflow = &flow_table->flows[flow_id];
 		tcpu = rflow->cpu;
 
 		/*
@@ -4961,7 +5060,8 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		     ((int)(READ_ONCE(per_cpu(softnet_data, tcpu).input_queue_head) -
 		      rflow->last_qtail)) >= 0)) {
 			tcpu = next_cpu;
-			rflow = set_rps_cpu(dev, skb, rflow, next_cpu);
+			rflow = set_rps_cpu(dev, skb, rflow, next_cpu, hash,
+					    flow_id);
 		}
 
 		if (tcpu < nr_cpu_ids && cpu_online(tcpu)) {
@@ -5005,17 +5105,16 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index,
 	struct rps_dev_flow_table *flow_table;
 	struct rps_dev_flow *rflow;
 	bool expire = true;
-	unsigned int cpu;
 
 	rcu_read_lock();
 	flow_table = rcu_dereference(rxqueue->rps_flow_table);
 	if (flow_table && flow_id < (1UL << flow_table->log)) {
+		unsigned int cpu;
+
 		rflow = &flow_table->flows[flow_id];
 		cpu = READ_ONCE(rflow->cpu);
-		if (READ_ONCE(rflow->filter) == filter_id && cpu < nr_cpu_ids &&
-		    ((int)(READ_ONCE(per_cpu(softnet_data, cpu).input_queue_head) -
-			   READ_ONCE(rflow->last_qtail)) <
-		     (int)(10 << flow_table->log)))
+		if (READ_ONCE(rflow->filter) == filter_id &&
+		    rps_flow_is_active(rflow, flow_table, cpu))
 			expire = false;
 	}
 	rcu_read_unlock();
@@ -5081,8 +5180,9 @@ static void napi_schedule_rps(struct softnet_data *sd)
 	__napi_schedule_irqoff(&mysd->backlog);
 }
 
-void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu)
+void kick_defer_list_purge(unsigned int cpu)
 {
+	struct softnet_data *sd = &per_cpu(softnet_data, cpu);
 	unsigned long flags;
 
 	if (use_backlog_threads()) {
@@ -5187,7 +5287,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
 	backlog_unlock_irq_restore(sd, &flags);
 
 cpu_backlog_drop:
-	atomic_inc(&sd->dropped);
+	numa_drop_add(&sd->drop_counters, 1);
 bad_dev:
 	dev_core_stats_rx_dropped_inc(skb->dev);
 	kfree_skb_reason(skb, reason);
@@ -6616,24 +6716,24 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 }
 EXPORT_SYMBOL(napi_complete_done);
 
-static void skb_defer_free_flush(struct softnet_data *sd)
+static void skb_defer_free_flush(void)
 {
+	struct llist_node *free_list;
 	struct sk_buff *skb, *next;
+	struct skb_defer_node *sdn;
+	int node;
 
-	/* Paired with WRITE_ONCE() in skb_attempt_defer_free() */
-	if (!READ_ONCE(sd->defer_list))
-		return;
+	for_each_node(node) {
+		sdn = this_cpu_ptr(net_hotdata.skb_defer_nodes) + node;
 
-	spin_lock(&sd->defer_lock);
-	skb = sd->defer_list;
-	sd->defer_list = NULL;
-	sd->defer_count = 0;
-	spin_unlock(&sd->defer_lock);
+		if (llist_empty(&sdn->defer_list))
+			continue;
+		atomic_long_set(&sdn->defer_count, 0);
+		free_list = llist_del_all(&sdn->defer_list);
 
-	while (skb != NULL) {
-		next = skb->next;
-		napi_consume_skb(skb, 1);
-		skb = next;
+		llist_for_each_entry_safe(skb, next, free_list, ll_node) {
+			napi_consume_skb(skb, 1);
+		}
 	}
 }
 
@@ -6761,7 +6861,7 @@ count:
 		if (work > 0)
 			__NET_ADD_STATS(dev_net(napi->dev),
 					LINUX_MIB_BUSYPOLLRXPACKETS, work);
-		skb_defer_free_flush(this_cpu_ptr(&softnet_data));
+		skb_defer_free_flush();
 		bpf_net_ctx_clear(bpf_net_ctx);
 		local_bh_enable();
 
@@ -6953,7 +7053,7 @@ static void napi_stop_kthread(struct napi_struct *napi)
 	 * the kthread.
 	 */
 	while (true) {
-		if (!test_bit(NAPIF_STATE_SCHED_THREADED, &napi->state))
+		if (!test_bit(NAPI_STATE_SCHED_THREADED, &napi->state))
 			break;
 
 		msleep(20);
@@ -6999,7 +7099,7 @@ int netif_set_threaded(struct net_device *dev,
 		       enum netdev_napi_threaded threaded)
 {
 	struct napi_struct *napi;
-	int err = 0;
+	int i, err = 0;
 
 	netdev_assert_locked_or_invisible(dev);
 
@@ -7021,6 +7121,10 @@ int netif_set_threaded(struct net_device *dev,
 	list_for_each_entry(napi, &dev->napi_list, dev_list)
 		WARN_ON_ONCE(napi_set_threaded(napi, threaded));
 
+	/* Override the config for all NAPIs even if currently not listed */
+	for (i = 0; i < dev->num_napi_configs; i++)
+		dev->napi_config[i].threaded = threaded;
+
 	return err;
 }
 
@@ -7353,8 +7457,9 @@ void netif_napi_add_weight_locked(struct net_device *dev,
 	 * Clear dev->threaded if kthread creation failed so that
 	 * threaded mode will not be enabled in napi_enable().
 	 */
-	if (dev->threaded && napi_kthread_create(napi))
-		dev->threaded = NETDEV_NAPI_THREADED_DISABLED;
+	if (napi_get_threaded_config(dev, napi))
+		if (napi_kthread_create(napi))
+			dev->threaded = NETDEV_NAPI_THREADED_DISABLED;
 	netif_napi_set_irq_locked(napi, -1);
 }
 EXPORT_SYMBOL(netif_napi_add_weight_locked);
@@ -7615,7 +7720,7 @@ static void napi_threaded_poll_loop(struct napi_struct *napi)
 			local_irq_disable();
 			net_rps_action_and_irq_enable(sd);
 		}
-		skb_defer_free_flush(sd);
+		skb_defer_free_flush();
 		bpf_net_ctx_clear(bpf_net_ctx);
 		local_bh_enable();
 
@@ -7657,7 +7762,7 @@ start:
 	for (;;) {
 		struct napi_struct *n;
 
-		skb_defer_free_flush(sd);
+		skb_defer_free_flush();
 
 		if (list_empty(&list)) {
 			if (list_empty(&repoll)) {
@@ -11873,6 +11978,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 		goto free_all;
 	dev->cfg_pending = dev->cfg;
 
+	dev->num_napi_configs = maxqs;
 	napi_config_sz = array_size(maxqs, sizeof(*dev->napi_config));
 	dev->napi_config = kvzalloc(napi_config_sz, GFP_KERNEL_ACCOUNT);
 	if (!dev->napi_config)
@@ -12890,7 +12996,6 @@ static int __init net_dev_init(void)
 		sd->cpu = i;
 #endif
 		INIT_CSD(&sd->defer_csd, trigger_rx_softirq, sd);
-		spin_lock_init(&sd->defer_lock);
 
 		gro_init(&sd->backlog.gro);
 		sd->backlog.poll = process_backlog;
@@ -12900,6 +13005,11 @@ static int __init net_dev_init(void)
 		if (net_page_pool_create(i))
 			goto out;
 	}
+	net_hotdata.skb_defer_nodes =
+		 __alloc_percpu(sizeof(struct skb_defer_node) * nr_node_ids,
+				__alignof__(struct skb_defer_node));
+	if (!net_hotdata.skb_defer_nodes)
+		goto out;
 	if (use_backlog_threads())
 		smpboot_register_percpu_thread(&backlog_threads);