Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Add Maglev hashing scheduler to IPVS, from Inju Song.

 2) Lots of new TC subsystem tests from Roman Mashak.

 3) Add TCP zero copy receive and fix delayed acks and autotuning with
    SO_RCVLOWAT, from Eric Dumazet.

 4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
    Brouer.

 5) Add ttl inherit support to vxlan, from Hangbin Liu.

 6) Properly separate ipv6 routes into their logically independant
    components. fib6_info for the routing table, and fib6_nh for sets of
    nexthops, which thus can be shared. From David Ahern.

 7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
    messages from XDP programs. From Nikita V. Shirokov.

 8) Lots of long overdue cleanups to the r8169 driver, from Heiner
    Kallweit.

 9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.

10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.

11) Plumb extack down into fib_rules, from Roopa Prabhu.

12) Add Flower classifier offload support to igb, from Vinicius Costa
    Gomes.

13) Add UDP GSO support, from Willem de Bruijn.

14) Add documentation for eBPF helpers, from Quentin Monnet.

15) Add TLS tx offload to mlx5, from Ilya Lesokhin.

16) Allow applications to be given the number of bytes available to read
    on a socket via a control message returned from recvmsg(), from
    Soheil Hassas Yeganeh.

17) Add x86_32 eBPF JIT compiler, from Wang YanQing.

18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
    From Björn Töpel.

19) Remove indirect load support from all of the BPF JITs and handle
    these operations in the verifier by translating them into native BPF
    instead. From Daniel Borkmann.

20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.

21) Allow XDP programs to do lookups in the main kernel routing tables
    for forwarding. From David Ahern.

22) Allow drivers to store hardware state into an ELF section of kernel
    dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.

23) Various RACK and loss detection improvements in TCP, from Yuchung
    Cheng.

24) Add TCP SACK compression, from Eric Dumazet.

25) Add User Mode Helper support and basic bpfilter infrastructure, from
    Alexei Starovoitov.

26) Support ports and protocol values in RTM_GETROUTE, from Roopa
    Prabhu.

27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
    Brouer.

28) Add lots of forwarding selftests, from Petr Machata.

29) Add generic network device failover driver, from Sridhar Samudrala.

* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
  strparser: Add __strp_unpause and use it in ktls.
  rxrpc: Fix terminal retransmission connection ID to include the channel
  net: hns3: Optimize PF CMDQ interrupt switching process
  net: hns3: Fix for VF mailbox receiving unknown message
  net: hns3: Fix for VF mailbox cannot receiving PF response
  bnx2x: use the right constant
  Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
  net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
  enic: fix UDP rss bits
  netdev-FAQ: clarify DaveM's position for stable backports
  rtnetlink: validate attributes in do_setlink()
  mlxsw: Add extack messages for port_{un, }split failures
  netdevsim: Add extack error message for devlink reload
  devlink: Add extack to reload and port_{un, }split operations
  net: metrics: add proper netlink validation
  ipmr: fix error path when ipmr_new_table fails
  ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
  net: hns3: remove unused hclgevf_cfg_func_mta_filter
  netfilter: provide udp*_lib_lookup for nf_tproxy
  qed*: Utilize FW 8.37.2.0
  ...

lib/kobject_uevent.c

@@ -22,6 +22,7 @@
 #include <linux/socket.h>
 #include <linux/skbuff.h>
 #include <linux/netlink.h>
+#include <linux/uidgid.h>
 #include <linux/uuid.h>
 #include <linux/ctype.h>
 #include <net/sock.h>
@@ -231,30 +232,6 @@ out:
 	return r;
 }
 
-#ifdef CONFIG_NET
-static int kobj_bcast_filter(struct sock *dsk, struct sk_buff *skb, void *data)
-{
-	struct kobject *kobj = data, *ksobj;
-	const struct kobj_ns_type_operations *ops;
-
-	ops = kobj_ns_ops(kobj);
-	if (!ops && kobj->kset) {
-		ksobj = &kobj->kset->kobj;
-		if (ksobj->parent != NULL)
-			ops = kobj_ns_ops(ksobj->parent);
-	}
-
-	if (ops && ops->netlink_ns && kobj->ktype->namespace) {
-		const void *sock_ns, *ns;
-		ns = kobj->ktype->namespace(kobj);
-		sock_ns = ops->netlink_ns(dsk);
-		return sock_ns != ns;
-	}
-
-	return 0;
-}
-#endif
-
 #ifdef CONFIG_UEVENT_HELPER
 static int kobj_usermode_filter(struct kobject *kobj)
 {
@@ -296,15 +273,44 @@ static void cleanup_uevent_env(struct subprocess_info *info)
 }
 #endif
 
-static int kobject_uevent_net_broadcast(struct kobject *kobj,
-					struct kobj_uevent_env *env,
+#ifdef CONFIG_NET
+static struct sk_buff *alloc_uevent_skb(struct kobj_uevent_env *env,
 					const char *action_string,
 					const char *devpath)
 {
-	int retval = 0;
-#if defined(CONFIG_NET)
+	struct netlink_skb_parms *parms;
+	struct sk_buff *skb = NULL;
+	char *scratch;
+	size_t len;
+
+	/* allocate message with maximum possible size */
+	len = strlen(action_string) + strlen(devpath) + 2;
+	skb = alloc_skb(len + env->buflen, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	/* add header */
+	scratch = skb_put(skb, len);
+	sprintf(scratch, "%s@%s", action_string, devpath);
+
+	skb_put_data(skb, env->buf, env->buflen);
+
+	parms = &NETLINK_CB(skb);
+	parms->creds.uid = GLOBAL_ROOT_UID;
+	parms->creds.gid = GLOBAL_ROOT_GID;
+	parms->dst_group = 1;
+	parms->portid = 0;
+
+	return skb;
+}
+
+static int uevent_net_broadcast_untagged(struct kobj_uevent_env *env,
+					 const char *action_string,
+					 const char *devpath)
+{
 	struct sk_buff *skb = NULL;
 	struct uevent_sock *ue_sk;
+	int retval = 0;
 
 	/* send netlink message */
 	list_for_each_entry(ue_sk, &uevent_sock_list, list) {
@@ -314,37 +320,99 @@ static int kobject_uevent_net_broadcast(struct kobject *kobj,
 			continue;
 
 		if (!skb) {
-			/* allocate message with the maximum possible size */
-			size_t len = strlen(action_string) + strlen(devpath) + 2;
-			char *scratch;
-
 			retval = -ENOMEM;
-			skb = alloc_skb(len + env->buflen, GFP_KERNEL);
+			skb = alloc_uevent_skb(env, action_string, devpath);
 			if (!skb)
 				continue;
-
-			/* add header */
-			scratch = skb_put(skb, len);
-			sprintf(scratch, "%s@%s", action_string, devpath);
-
-			skb_put_data(skb, env->buf, env->buflen);
-
-			NETLINK_CB(skb).dst_group = 1;
 		}
 
-		retval = netlink_broadcast_filtered(uevent_sock, skb_get(skb),
-						    0, 1, GFP_KERNEL,
-						    kobj_bcast_filter,
-						    kobj);
+		retval = netlink_broadcast(uevent_sock, skb_get(skb), 0, 1,
+					   GFP_KERNEL);
 		/* ENOBUFS should be handled in userspace */
 		if (retval == -ENOBUFS || retval == -ESRCH)
 			retval = 0;
 	}
 	consume_skb(skb);
-#endif
+
 	return retval;
 }
 
+static int uevent_net_broadcast_tagged(struct sock *usk,
+				       struct kobj_uevent_env *env,
+				       const char *action_string,
+				       const char *devpath)
+{
+	struct user_namespace *owning_user_ns = sock_net(usk)->user_ns;
+	struct sk_buff *skb = NULL;
+	int ret = 0;
+
+	skb = alloc_uevent_skb(env, action_string, devpath);
+	if (!skb)
+		return -ENOMEM;
+
+	/* fix credentials */
+	if (owning_user_ns != &init_user_ns) {
+		struct netlink_skb_parms *parms = &NETLINK_CB(skb);
+		kuid_t root_uid;
+		kgid_t root_gid;
+
+		/* fix uid */
+		root_uid = make_kuid(owning_user_ns, 0);
+		if (uid_valid(root_uid))
+			parms->creds.uid = root_uid;
+
+		/* fix gid */
+		root_gid = make_kgid(owning_user_ns, 0);
+		if (gid_valid(root_gid))
+			parms->creds.gid = root_gid;
+	}
+
+	ret = netlink_broadcast(usk, skb, 0, 1, GFP_KERNEL);
+	/* ENOBUFS should be handled in userspace */
+	if (ret == -ENOBUFS || ret == -ESRCH)
+		ret = 0;
+
+	return ret;
+}
+#endif
+
+static int kobject_uevent_net_broadcast(struct kobject *kobj,
+					struct kobj_uevent_env *env,
+					const char *action_string,
+					const char *devpath)
+{
+	int ret = 0;
+
+#ifdef CONFIG_NET
+	const struct kobj_ns_type_operations *ops;
+	const struct net *net = NULL;
+
+	ops = kobj_ns_ops(kobj);
+	if (!ops && kobj->kset) {
+		struct kobject *ksobj = &kobj->kset->kobj;
+		if (ksobj->parent != NULL)
+			ops = kobj_ns_ops(ksobj->parent);
+	}
+
+	/* kobjects currently only carry network namespace tags and they
+	 * are the only tag relevant here since we want to decide which
+	 * network namespaces to broadcast the uevent into.
+	 */
+	if (ops && ops->netlink_ns && kobj->ktype->namespace)
+		if (ops->type == KOBJ_NS_TYPE_NET)
+			net = kobj->ktype->namespace(kobj);
+
+	if (!net)
+		ret = uevent_net_broadcast_untagged(env, action_string,
+						    devpath);
+	else
+		ret = uevent_net_broadcast_tagged(net->uevent_sock->sk, env,
+						  action_string, devpath);
+#endif
+
+	return ret;
+}
+
 static void zap_modalias_env(struct kobj_uevent_env *env)
 {
 	static const char modalias_prefix[] = "MODALIAS=";
@@ -703,9 +771,13 @@ static int uevent_net_init(struct net *net)
 
 	net->uevent_sock = ue_sk;
 
-	mutex_lock(&uevent_sock_mutex);
-	list_add_tail(&ue_sk->list, &uevent_sock_list);
-	mutex_unlock(&uevent_sock_mutex);
+	/* Restrict uevents to initial user namespace. */
+	if (sock_net(ue_sk->sk)->user_ns == &init_user_ns) {
+		mutex_lock(&uevent_sock_mutex);
+		list_add_tail(&ue_sk->list, &uevent_sock_list);
+		mutex_unlock(&uevent_sock_mutex);
+	}
+
 	return 0;
 }
 
@@ -713,9 +785,11 @@ static void uevent_net_exit(struct net *net)
 {
 	struct uevent_sock *ue_sk = net->uevent_sock;
 
-	mutex_lock(&uevent_sock_mutex);
-	list_del(&ue_sk->list);
-	mutex_unlock(&uevent_sock_mutex);
+	if (sock_net(ue_sk->sk)->user_ns == &init_user_ns) {
+		mutex_lock(&uevent_sock_mutex);
+		list_del(&ue_sk->list);
+		mutex_unlock(&uevent_sock_mutex);
+	}
 
 	netlink_kernel_release(ue_sk->sk);
 	kfree(ue_sk);

lib/rhashtable.c

@@ -668,8 +668,9 @@ EXPORT_SYMBOL_GPL(rhashtable_insert_slow);
  * For a completely stable walk you should construct your own data
  * structure outside the hash table.
  *
- * This function may sleep so you must not call it from interrupt
- * context or with spin locks held.
+ * This function may be called from any process context, including
+ * non-preemptable context, but cannot be called from softirq or
+ * hardirq context.
  *
  * You must call rhashtable_walk_exit after this function returns.
  */
@@ -726,6 +727,7 @@ int rhashtable_walk_start_check(struct rhashtable_iter *iter)
 	__acquires(RCU)
 {
 	struct rhashtable *ht = iter->ht;
+	bool rhlist = ht->rhlist;
 
 	rcu_read_lock();
 
@@ -734,11 +736,52 @@ int rhashtable_walk_start_check(struct rhashtable_iter *iter)
 		list_del(&iter->walker.list);
 	spin_unlock(&ht->lock);
 
-	if (!iter->walker.tbl && !iter->end_of_table) {
+	if (iter->end_of_table)
+		return 0;
+	if (!iter->walker.tbl) {
 		iter->walker.tbl = rht_dereference_rcu(ht->tbl, ht);
+		iter->slot = 0;
+		iter->skip = 0;
 		return -EAGAIN;
 	}
 
+	if (iter->p && !rhlist) {
+		/*
+		 * We need to validate that 'p' is still in the table, and
+		 * if so, update 'skip'
+		 */
+		struct rhash_head *p;
+		int skip = 0;
+		rht_for_each_rcu(p, iter->walker.tbl, iter->slot) {
+			skip++;
+			if (p == iter->p) {
+				iter->skip = skip;
+				goto found;
+			}
+		}
+		iter->p = NULL;
+	} else if (iter->p && rhlist) {
+		/* Need to validate that 'list' is still in the table, and
+		 * if so, update 'skip' and 'p'.
+		 */
+		struct rhash_head *p;
+		struct rhlist_head *list;
+		int skip = 0;
+		rht_for_each_rcu(p, iter->walker.tbl, iter->slot) {
+			for (list = container_of(p, struct rhlist_head, rhead);
+			     list;
+			     list = rcu_dereference(list->next)) {
+				skip++;
+				if (list == iter->list) {
+					iter->p = p;
+					skip = skip;
+					goto found;
+				}
+			}
+		}
+		iter->p = NULL;
+	}
+found:
 	return 0;
 }
 EXPORT_SYMBOL_GPL(rhashtable_walk_start_check);
@@ -914,8 +957,6 @@ void rhashtable_walk_stop(struct rhashtable_iter *iter)
 		iter->walker.tbl = NULL;
 	spin_unlock(&ht->lock);
 
-	iter->p = NULL;
-
 out:
 	rcu_read_unlock();
 }