Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 135 insertions, 38 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 4bb6dcdbed8b..48b529d59157 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1230,6 +1230,18 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf)
 			return -ENOMEM;
 
 		for_each_netdev(net, d) {
+			struct netdev_name_node *name_node;
+			list_for_each_entry(name_node, &d->name_node->list, list) {
+				if (!sscanf(name_node->name, name, &i))
+					continue;
+				if (i < 0 || i >= max_netdevices)
+					continue;
+
+				/*  avoid cases where sscanf is not exact inverse of printf */
+				snprintf(buf, IFNAMSIZ, name, i);
+				if (!strncmp(buf, name_node->name, IFNAMSIZ))
+					set_bit(i, inuse);
+			}
 			if (!sscanf(d->name, name, &i))
 				continue;
 			if (i < 0 || i >= max_netdevices)
@@ -4345,6 +4357,13 @@ static inline void ____napi_schedule(struct softnet_data *sd,
 		 */
 		thread = READ_ONCE(napi->thread);
 		if (thread) {
+			/* Avoid doing set_bit() if the thread is in
+			 * INTERRUPTIBLE state, cause napi_thread_wait()
+			 * makes sure to proceed with napi polling
+			 * if the thread is explicitly woken from here.
+			 */
+			if (READ_ONCE(thread->state) != TASK_INTERRUPTIBLE)
+				set_bit(NAPI_STATE_SCHED_THREADED, &napi->state);
 			wake_up_process(thread);
 			return;
 		}
@@ -6534,6 +6553,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 		WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED));
 
 		new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED |
+			      NAPIF_STATE_SCHED_THREADED |
 			      NAPIF_STATE_PREFER_BUSY_POLL);
 
 		/* If STATE_MISSED was set, leave STATE_SCHED set,
@@ -7017,16 +7037,25 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 
 static int napi_thread_wait(struct napi_struct *napi)
 {
+	bool woken = false;
+
 	set_current_state(TASK_INTERRUPTIBLE);
 
 	while (!kthread_should_stop() && !napi_disable_pending(napi)) {
-		if (test_bit(NAPI_STATE_SCHED, &napi->state)) {
+		/* Testing SCHED_THREADED bit here to make sure the current
+		 * kthread owns this napi and could poll on this napi.
+		 * Testing SCHED bit is not enough because SCHED bit might be
+		 * set by some other busy poll thread or by napi_disable().
+		 */
+		if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state) || woken) {
 			WARN_ON(!list_empty(&napi->poll_list));
 			__set_current_state(TASK_RUNNING);
 			return 0;
 		}
 
 		schedule();
+		/* woken being true indicates this thread owns this napi. */
+		woken = true;
 		set_current_state(TASK_INTERRUPTIBLE);
 	}
 	__set_current_state(TASK_RUNNING);
@@ -11412,7 +11441,7 @@ static void __net_exit default_device_exit(struct net *net)
 			continue;
 
 		/* Leave virtual devices for the generic cleanup */
-		if (dev->rtnl_link_ops)
+		if (dev->rtnl_link_ops && !dev->rtnl_link_ops->netns_refund)
 			continue;
 
 		/* Push remaining network devices to init_net */
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 1eb02c2236f2..ead2a8aa57b4 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -1053,6 +1053,20 @@ static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack)
 	return 0;
 
 err_module_put:
+	for_each_possible_cpu(cpu) {
+		struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu);
+		struct sk_buff *skb;
+
+		del_timer_sync(&hw_data->send_timer);
+		cancel_work_sync(&hw_data->dm_alert_work);
+		while ((skb = __skb_dequeue(&hw_data->drop_queue))) {
+			struct devlink_trap_metadata *hw_metadata;
+
+			hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata;
+			net_dm_hw_metadata_free(hw_metadata);
+			consume_skb(skb);
+		}
+	}
 	module_put(THIS_MODULE);
 	return rc;
 }
@@ -1134,6 +1148,15 @@ static int net_dm_trace_on_set(struct netlink_ext_ack *extack)
 err_unregister_trace:
 	unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL);
 err_module_put:
+	for_each_possible_cpu(cpu) {
+		struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu);
+		struct sk_buff *skb;
+
+		del_timer_sync(&data->send_timer);
+		cancel_work_sync(&data->dm_alert_work);
+		while ((skb = __skb_dequeue(&data->drop_queue)))
+			consume_skb(skb);
+	}
 	module_put(THIS_MODULE);
 	return rc;
 }
diff --git a/net/core/dst.c b/net/core/dst.c
index 0c01bd8d9d81..fb3bcba87744 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -237,37 +237,62 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
 }
 EXPORT_SYMBOL(__dst_destroy_metrics_generic);
 
-static struct dst_ops md_dst_ops = {
-	.family =		AF_UNSPEC,
-};
+struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie)
+{
+	return NULL;
+}
 
-static int dst_md_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
+u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old)
 {
-	WARN_ONCE(1, "Attempting to call output on metadata dst\n");
-	kfree_skb(skb);
-	return 0;
+	return NULL;
 }
 
-static int dst_md_discard(struct sk_buff *skb)
+struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst,
+					     struct sk_buff *skb,
+					     const void *daddr)
 {
-	WARN_ONCE(1, "Attempting to call input on metadata dst\n");
-	kfree_skb(skb);
-	return 0;
+	return NULL;
+}
+
+void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
+			       struct sk_buff *skb, u32 mtu,
+			       bool confirm_neigh)
+{
+}
+EXPORT_SYMBOL_GPL(dst_blackhole_update_pmtu);
+
+void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
+			    struct sk_buff *skb)
+{
+}
+EXPORT_SYMBOL_GPL(dst_blackhole_redirect);
+
+unsigned int dst_blackhole_mtu(const struct dst_entry *dst)
+{
+	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+	return mtu ? : dst->dev->mtu;
 }
+EXPORT_SYMBOL_GPL(dst_blackhole_mtu);
+
+static struct dst_ops dst_blackhole_ops = {
+	.family		= AF_UNSPEC,
+	.neigh_lookup	= dst_blackhole_neigh_lookup,
+	.check		= dst_blackhole_check,
+	.cow_metrics	= dst_blackhole_cow_metrics,
+	.update_pmtu	= dst_blackhole_update_pmtu,
+	.redirect	= dst_blackhole_redirect,
+	.mtu		= dst_blackhole_mtu,
+};
 
 static void __metadata_dst_init(struct metadata_dst *md_dst,
 				enum metadata_type type, u8 optslen)
-
 {
 	struct dst_entry *dst;
 
 	dst = &md_dst->dst;
-	dst_init(dst, &md_dst_ops, NULL, 1, DST_OBSOLETE_NONE,
+	dst_init(dst, &dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE,
 		 DST_METADATA | DST_NOCOUNT);
-
-	dst->input = dst_md_discard;
-	dst->output = dst_md_discard_out;
-
 	memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst));
 	md_dst->type = type;
 }
diff --git a/net/core/filter.c b/net/core/filter.c
index b6732000d8a2..f5eeebf6a16f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5600,7 +5600,7 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
 	if (unlikely(flags & ~(BPF_MTU_CHK_SEGS)))
 		return -EINVAL;
 
-	if (unlikely(flags & BPF_MTU_CHK_SEGS && len_diff))
+	if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len)))
 		return -EINVAL;
 
 	dev = __dev_via_ifindex(dev, ifindex);
@@ -5610,7 +5610,11 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
 	mtu = READ_ONCE(dev->mtu);
 
 	dev_len = mtu + dev->hard_header_len;
-	skb_len = skb->len + len_diff; /* minus result pass check */
+
+	/* If set use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
+	skb_len = *mtu_len ? *mtu_len + dev->hard_header_len : skb->len;
+
+	skb_len += len_diff; /* minus result pass check */
 	if (skb_len <= dev_len) {
 		ret = BPF_MTU_CHK_RET_SUCCESS;
 		goto out;
@@ -5655,6 +5659,10 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp,
 	/* Add L2-header as dev MTU is L3 size */
 	dev_len = mtu + dev->hard_header_len;
 
+	/* Use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
+	if (*mtu_len)
+		xdp_len = *mtu_len + dev->hard_header_len;
+
 	xdp_len += len_diff; /* minus result pass check */
 	if (xdp_len > dev_len)
 		ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 2ed380d096ce..5985029e43d4 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -176,7 +176,7 @@ void skb_flow_get_icmp_tci(const struct sk_buff *skb,
 	 * avoid confusion with packets without such field
 	 */
 	if (icmp_has_id(ih->type))
-		key_icmp->id = ih->un.echo.id ? : 1;
+		key_icmp->id = ih->un.echo.id ? ntohs(ih->un.echo.id) : 1;
 	else
 		key_icmp->id = 0;
 }
diff --git a/net/core/sock.c b/net/core/sock.c
index 0ed98f20448a..cc31b601ae10 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3440,6 +3440,32 @@ static void tw_prot_cleanup(struct timewait_sock_ops *twsk_prot)
 	twsk_prot->twsk_slab = NULL;
 }
 
+static int tw_prot_init(const struct proto *prot)
+{
+	struct timewait_sock_ops *twsk_prot = prot->twsk_prot;
+
+	if (!twsk_prot)
+		return 0;
+
+	twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s",
+					      prot->name);
+	if (!twsk_prot->twsk_slab_name)
+		return -ENOMEM;
+
+	twsk_prot->twsk_slab =
+		kmem_cache_create(twsk_prot->twsk_slab_name,
+				  twsk_prot->twsk_obj_size, 0,
+				  SLAB_ACCOUNT | prot->slab_flags,
+				  NULL);
+	if (!twsk_prot->twsk_slab) {
+		pr_crit("%s: Can't create timewait sock SLAB cache!\n",
+			prot->name);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 static void req_prot_cleanup(struct request_sock_ops *rsk_prot)
 {
 	if (!rsk_prot)
@@ -3496,22 +3522,8 @@ int proto_register(struct proto *prot, int alloc_slab)
 		if (req_prot_init(prot))
 			goto out_free_request_sock_slab;
 
-		if (prot->twsk_prot != NULL) {
-			prot->twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name);
-
-			if (prot->twsk_prot->twsk_slab_name == NULL)
-				goto out_free_request_sock_slab;
-
-			prot->twsk_prot->twsk_slab =
-				kmem_cache_create(prot->twsk_prot->twsk_slab_name,
-						  prot->twsk_prot->twsk_obj_size,
-						  0,
-						  SLAB_ACCOUNT |
-						  prot->slab_flags,
-						  NULL);
-			if (prot->twsk_prot->twsk_slab == NULL)
-				goto out_free_timewait_sock_slab;
-		}
+		if (tw_prot_init(prot))
+			goto out_free_timewait_sock_slab;
 	}
 
 	mutex_lock(&proto_list_mutex);