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

No conflicts.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

19 files changed, 120 insertions, 70 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 8958c4227b67..978ed0622d8f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -397,16 +397,18 @@ static void list_netdevice(struct net_device *dev)
 /* Device list removal
  * caller must respect a RCU grace period before freeing/reusing dev
  */
-static void unlist_netdevice(struct net_device *dev)
+static void unlist_netdevice(struct net_device *dev, bool lock)
 {
 	ASSERT_RTNL();
 
 	/* Unlink dev from the device chain */
-	write_lock(&dev_base_lock);
+	if (lock)
+		write_lock(&dev_base_lock);
 	list_del_rcu(&dev->dev_list);
 	netdev_name_node_del(dev->name_node);
 	hlist_del_rcu(&dev->index_hlist);
-	write_unlock(&dev_base_lock);
+	if (lock)
+		write_unlock(&dev_base_lock);
 
 	dev_base_seq_inc(dev_net(dev));
 }
@@ -10061,11 +10063,11 @@ int register_netdevice(struct net_device *dev)
 		goto err_uninit;
 
 	ret = netdev_register_kobject(dev);
-	if (ret) {
-		dev->reg_state = NETREG_UNREGISTERED;
+	write_lock(&dev_base_lock);
+	dev->reg_state = ret ? NETREG_UNREGISTERED : NETREG_REGISTERED;
+	write_unlock(&dev_base_lock);
+	if (ret)
 		goto err_uninit;
-	}
-	dev->reg_state = NETREG_REGISTERED;
 
 	__netdev_update_features(dev);
 
@@ -10347,7 +10349,9 @@ void netdev_run_todo(void)
 			continue;
 		}
 
+		write_lock(&dev_base_lock);
 		dev->reg_state = NETREG_UNREGISTERED;
+		write_unlock(&dev_base_lock);
 		linkwatch_forget_dev(dev);
 	}
 
@@ -10828,9 +10832,10 @@ void unregister_netdevice_many(struct list_head *head)
 
 	list_for_each_entry(dev, head, unreg_list) {
 		/* And unlink it from device chain. */
-		unlist_netdevice(dev);
-
+		write_lock(&dev_base_lock);
+		unlist_netdevice(dev, false);
 		dev->reg_state = NETREG_UNREGISTERING;
+		write_unlock(&dev_base_lock);
 	}
 	flush_all_backlogs();
 
@@ -10977,7 +10982,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
 	dev_close(dev);
 
 	/* And unlink it from device chain */
-	unlist_netdevice(dev);
+	unlist_netdevice(dev, true);
 
 	synchronize_net();
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 151aa4756bd6..994d91680b12 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6514,10 +6514,21 @@ __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 					   ifindex, proto, netns_id, flags);
 
 	if (sk) {
-		sk = sk_to_full_sk(sk);
-		if (!sk_fullsock(sk)) {
+		struct sock *sk2 = sk_to_full_sk(sk);
+
+		/* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk
+		 * sock refcnt is decremented to prevent a request_sock leak.
+		 */
+		if (!sk_fullsock(sk2))
+			sk2 = NULL;
+		if (sk2 != sk) {
 			sock_gen_put(sk);
-			return NULL;
+			/* Ensure there is no need to bump sk2 refcnt */
+			if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) {
+				WARN_ONCE(1, "Found non-RCU, unreferenced socket!");
+				return NULL;
+			}
+			sk = sk2;
 		}
 	}
 
@@ -6551,10 +6562,21 @@ bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 					 flags);
 
 	if (sk) {
-		sk = sk_to_full_sk(sk);
-		if (!sk_fullsock(sk)) {
+		struct sock *sk2 = sk_to_full_sk(sk);
+
+		/* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk
+		 * sock refcnt is decremented to prevent a request_sock leak.
+		 */
+		if (!sk_fullsock(sk2))
+			sk2 = NULL;
+		if (sk2 != sk) {
 			sock_gen_put(sk);
-			return NULL;
+			/* Ensure there is no need to bump sk2 refcnt */
+			if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) {
+				WARN_ONCE(1, "Found non-RCU, unreferenced socket!");
+				return NULL;
+			}
+			sk = sk2;
 		}
 	}
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index d49fc974e630..d61afd21aab5 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -33,6 +33,7 @@ static const char fmt_dec[] = "%d\n";
 static const char fmt_ulong[] = "%lu\n";
 static const char fmt_u64[] = "%llu\n";
 
+/* Caller holds RTNL or dev_base_lock */
 static inline int dev_isalive(const struct net_device *dev)
 {
 	return dev->reg_state <= NETREG_REGISTERED;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 7e03f96e441b..fc69154bbc88 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -699,6 +699,11 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node)
 
 	write_lock_bh(&sk->sk_callback_lock);
 
+	if (sk_is_inet(sk) && inet_csk_has_ulp(sk)) {
+		psock = ERR_PTR(-EINVAL);
+		goto out;
+	}
+
 	if (sk->sk_user_data) {
 		psock = ERR_PTR(-EBUSY);
 		goto out;
diff --git a/net/ethtool/eeprom.c b/net/ethtool/eeprom.c
index 7e6b37a54add..1c94bb8ea03f 100644
--- a/net/ethtool/eeprom.c
+++ b/net/ethtool/eeprom.c
@@ -36,7 +36,7 @@ static int fallback_set_params(struct eeprom_req_info *request,
 	if (request->page)
 		offset = request->page * ETH_MODULE_EEPROM_PAGE_LEN + offset;
 
-	if (modinfo->type == ETH_MODULE_SFF_8079 &&
+	if (modinfo->type == ETH_MODULE_SFF_8472 &&
 	    request->i2c_address == 0x51)
 		offset += ETH_MODULE_EEPROM_PAGE_LEN * 2;
 
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 3b9cd487075a..5c58e21f724e 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -524,7 +524,6 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev)
 	int tunnel_hlen;
 	int version;
 	int nhoff;
-	int thoff;
 
 	tun_info = skb_tunnel_info(skb);
 	if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
@@ -558,10 +557,16 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev)
 	    (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff))
 		truncate = true;
 
-	thoff = skb_transport_header(skb) - skb_mac_header(skb);
-	if (skb->protocol == htons(ETH_P_IPV6) &&
-	    (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff))
-		truncate = true;
+	if (skb->protocol == htons(ETH_P_IPV6)) {
+		int thoff;
+
+		if (skb_transport_header_was_set(skb))
+			thoff = skb_transport_header(skb) - skb_mac_header(skb);
+		else
+			thoff = nhoff + sizeof(struct ipv6hdr);
+		if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff)
+			truncate = true;
+	}
 
 	if (version == 1) {
 		erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)),
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 3d6fc6d841b8..b83c2bd9d722 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -316,12 +316,16 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
 		pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n",
 			 sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port));
 
+		if (addr->sin_addr.s_addr == htonl(INADDR_ANY))
+			return 0;
+
 		tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id;
 		chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id);
 
-		if (!inet_addr_valid_or_nonlocal(net, inet_sk(sk),
-					         addr->sin_addr.s_addr,
-	                                         chk_addr_ret))
+		if (chk_addr_ret == RTN_MULTICAST ||
+		    chk_addr_ret == RTN_BROADCAST ||
+		    (chk_addr_ret != RTN_LOCAL &&
+		     !inet_can_nonlocal_bind(net, isk)))
 			return -EADDRNOTAVAIL;
 
 #if IS_ENABLED(CONFIG_IPV6)
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 38550bb1b90b..a1626afe87a1 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -612,9 +612,6 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 		return 0;
 	}
 
-	if (inet_csk_has_ulp(sk))
-		return -EINVAL;
-
 	if (sk->sk_family == AF_INET6) {
 		if (tcp_bpf_assert_proto_ops(psock->sk_proto))
 			return -EINVAL;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 3e22cbe5966a..1bd10ae332e8 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -939,7 +939,6 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 	__be16 proto;
 	__u32 mtu;
 	int nhoff;
-	int thoff;
 
 	if (!pskb_inet_may_pull(skb))
 		goto tx_err;
@@ -960,10 +959,16 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 	    (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff))
 		truncate = true;
 
-	thoff = skb_transport_header(skb) - skb_mac_header(skb);
-	if (skb->protocol == htons(ETH_P_IPV6) &&
-	    (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff))
-		truncate = true;
+	if (skb->protocol == htons(ETH_P_IPV6)) {
+		int thoff;
+
+		if (skb_transport_header_was_set(skb))
+			thoff = skb_transport_header(skb) - skb_mac_header(skb);
+		else
+			thoff = nhoff + sizeof(struct ipv6hdr);
+		if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff)
+			truncate = true;
+	}
 
 	if (skb_cow_head(skb, dev->needed_headroom ?: t->hlen))
 		goto tx_err;
diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c
index 7873bd1389c3..a8e2425e43b0 100644
--- a/net/netfilter/nf_dup_netdev.c
+++ b/net/netfilter/nf_dup_netdev.c
@@ -13,14 +13,31 @@
 #include <net/netfilter/nf_tables_offload.h>
 #include <net/netfilter/nf_dup_netdev.h>
 
-static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev)
+#define NF_RECURSION_LIMIT	2
+
+static DEFINE_PER_CPU(u8, nf_dup_skb_recursion);
+
+static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev,
+				enum nf_dev_hooks hook)
 {
-	if (skb_mac_header_was_set(skb))
+	if (__this_cpu_read(nf_dup_skb_recursion) > NF_RECURSION_LIMIT)
+		goto err;
+
+	if (hook == NF_NETDEV_INGRESS && skb_mac_header_was_set(skb)) {
+		if (skb_cow_head(skb, skb->mac_len))
+			goto err;
+
 		skb_push(skb, skb->mac_len);
+	}
 
 	skb->dev = dev;
 	skb_clear_tstamp(skb);
+	__this_cpu_inc(nf_dup_skb_recursion);
 	dev_queue_xmit(skb);
+	__this_cpu_dec(nf_dup_skb_recursion);
+	return;
+err:
+	kfree_skb(skb);
 }
 
 void nf_fwd_netdev_egress(const struct nft_pktinfo *pkt, int oif)
@@ -33,7 +50,7 @@ void nf_fwd_netdev_egress(const struct nft_pktinfo *pkt, int oif)
 		return;
 	}
 
-	nf_do_netdev_egress(pkt->skb, dev);
+	nf_do_netdev_egress(pkt->skb, dev, nft_hook(pkt));
 }
 EXPORT_SYMBOL_GPL(nf_fwd_netdev_egress);
 
@@ -48,7 +65,7 @@ void nf_dup_netdev_egress(const struct nft_pktinfo *pkt, int oif)
 
 	skb = skb_clone(pkt->skb, GFP_ATOMIC);
 	if (skb)
-		nf_do_netdev_egress(skb, dev);
+		nf_do_netdev_egress(skb, dev, nft_hook(pkt));
 }
 EXPORT_SYMBOL_GPL(nf_dup_netdev_egress);
 
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index af15102bc696..f466af4f8531 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -614,7 +614,7 @@ static void __net_exit cttimeout_net_exit(struct net *net)
 
 	nf_ct_untimeout(net, NULL);
 
-	list_for_each_entry_safe(cur, tmp, &pernet->nfct_timeout_freelist, head) {
+	list_for_each_entry_safe(cur, tmp, &pernet->nfct_timeout_freelist, free_head) {
 		list_del(&cur->free_head);
 
 		if (refcount_dec_and_test(&cur->refcnt))
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index ac4859241e17..55d2d49c3425 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -14,6 +14,7 @@
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/random.h>
 #include <linux/smp.h>
 #include <linux/static_key.h>
 #include <net/dst.h>
@@ -32,8 +33,6 @@
 #define NFT_META_SECS_PER_DAY		86400
 #define NFT_META_DAYS_PER_WEEK		7
 
-static DEFINE_PER_CPU(struct rnd_state, nft_prandom_state);
-
 static u8 nft_meta_weekday(void)
 {
 	time64_t secs = ktime_get_real_seconds();
@@ -271,13 +270,6 @@ static bool nft_meta_get_eval_ifname(enum nft_meta_keys key, u32 *dest,
 	return true;
 }
 
-static noinline u32 nft_prandom_u32(void)
-{
-	struct rnd_state *state = this_cpu_ptr(&nft_prandom_state);
-
-	return prandom_u32_state(state);
-}
-
 #ifdef CONFIG_IP_ROUTE_CLASSID
 static noinline bool
 nft_meta_get_eval_rtclassid(const struct sk_buff *skb, u32 *dest)
@@ -389,7 +381,7 @@ void nft_meta_get_eval(const struct nft_expr *expr,
 		break;
 #endif
 	case NFT_META_PRANDOM:
-		*dest = nft_prandom_u32();
+		*dest = get_random_u32();
 		break;
 #ifdef CONFIG_XFRM
 	case NFT_META_SECPATH:
@@ -518,7 +510,6 @@ int nft_meta_get_init(const struct nft_ctx *ctx,
 		len = IFNAMSIZ;
 		break;
 	case NFT_META_PRANDOM:
-		prandom_init_once(&nft_prandom_state);
 		len = sizeof(u32);
 		break;
 #ifdef CONFIG_XFRM
diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c
index 81b40c663d86..45d3dc9e96f2 100644
--- a/net/netfilter/nft_numgen.c
+++ b/net/netfilter/nft_numgen.c
@@ -9,12 +9,11 @@
 #include <linux/netlink.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
+#include <linux/random.h>
 #include <linux/static_key.h>
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables_core.h>
 
-static DEFINE_PER_CPU(struct rnd_state, nft_numgen_prandom_state);
-
 struct nft_ng_inc {
 	u8			dreg;
 	u32			modulus;
@@ -135,12 +134,9 @@ struct nft_ng_random {
 	u32			offset;
 };
 
-static u32 nft_ng_random_gen(struct nft_ng_random *priv)
+static u32 nft_ng_random_gen(const struct nft_ng_random *priv)
 {
-	struct rnd_state *state = this_cpu_ptr(&nft_numgen_prandom_state);
-
-	return reciprocal_scale(prandom_u32_state(state), priv->modulus) +
-	       priv->offset;
+	return reciprocal_scale(get_random_u32(), priv->modulus) + priv->offset;
 }
 
 static void nft_ng_random_eval(const struct nft_expr *expr,
@@ -168,8 +164,6 @@ static int nft_ng_random_init(const struct nft_ctx *ctx,
 	if (priv->offset + priv->modulus - 1 < priv->offset)
 		return -EOVERFLOW;
 
-	prandom_init_once(&nft_numgen_prandom_state);
-
 	return nft_parse_register_store(ctx, tb[NFTA_NG_DREG], &priv->dreg,
 					NULL, NFT_DATA_VALUE, sizeof(u32));
 }
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 372bf54a0ca9..e20d1a973417 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -407,7 +407,7 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
 	if (flags & IP6_FH_F_FRAG) {
 		if (frag_off) {
 			key->ip.frag = OVS_FRAG_TYPE_LATER;
-			key->ip.proto = nexthdr;
+			key->ip.proto = NEXTHDR_FRAGMENT;
 			return 0;
 		}
 		key->ip.frag = OVS_FRAG_TYPE_FIRST;
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index ed4ccef5d6a8..5449ed114e40 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -1146,9 +1146,9 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct tc_netem_rate rate;
 	struct tc_netem_slot slot;
 
-	qopt.latency = min_t(psched_tdiff_t, PSCHED_NS2TICKS(q->latency),
+	qopt.latency = min_t(psched_time_t, PSCHED_NS2TICKS(q->latency),
 			     UINT_MAX);
-	qopt.jitter = min_t(psched_tdiff_t, PSCHED_NS2TICKS(q->jitter),
+	qopt.jitter = min_t(psched_time_t, PSCHED_NS2TICKS(q->jitter),
 			    UINT_MAX);
 	qopt.limit = q->limit;
 	qopt.loss = q->loss;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index e2c6eca0271b..b6781ada3aa8 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -651,6 +651,7 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args,
 	new->cl_discrtry = clnt->cl_discrtry;
 	new->cl_chatty = clnt->cl_chatty;
 	new->cl_principal = clnt->cl_principal;
+	new->cl_max_connect = clnt->cl_max_connect;
 	return new;
 
 out_err:
diff --git a/net/tipc/core.c b/net/tipc/core.c
index 3f4542e0f065..434e70eabe08 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -109,10 +109,9 @@ static void __net_exit tipc_exit_net(struct net *net)
 	struct tipc_net *tn = tipc_net(net);
 
 	tipc_detach_loopback(net);
+	tipc_net_stop(net);
 	/* Make sure the tipc_net_finalize_work() finished */
 	cancel_work_sync(&tn->work);
-	tipc_net_stop(net);
-
 	tipc_bcast_stop(net);
 	tipc_nametbl_stop(net);
 	tipc_sk_rht_destroy(net);
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index da176411c1b5..2ffede463e4a 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -921,6 +921,8 @@ static void tls_update(struct sock *sk, struct proto *p,
 {
 	struct tls_context *ctx;
 
+	WARN_ON_ONCE(sk->sk_prot == p);
+
 	ctx = tls_get_ctx(sk);
 	if (likely(ctx)) {
 		ctx->sk_write_space = write_space;
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 19ac872a6624..09002387987e 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -538,12 +538,6 @@ static int xsk_generic_xmit(struct sock *sk)
 			goto out;
 		}
 
-		skb = xsk_build_skb(xs, &desc);
-		if (IS_ERR(skb)) {
-			err = PTR_ERR(skb);
-			goto out;
-		}
-
 		/* This is the backpressure mechanism for the Tx path.
 		 * Reserve space in the completion queue and only proceed
 		 * if there is space in it. This avoids having to implement
@@ -552,11 +546,19 @@ static int xsk_generic_xmit(struct sock *sk)
 		spin_lock_irqsave(&xs->pool->cq_lock, flags);
 		if (xskq_prod_reserve(xs->pool->cq)) {
 			spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
-			kfree_skb(skb);
 			goto out;
 		}
 		spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
 
+		skb = xsk_build_skb(xs, &desc);
+		if (IS_ERR(skb)) {
+			err = PTR_ERR(skb);
+			spin_lock_irqsave(&xs->pool->cq_lock, flags);
+			xskq_prod_cancel(xs->pool->cq);
+			spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
+			goto out;
+		}
+
 		err = __dev_direct_xmit(skb, xs->queue_id);
 		if  (err == NETDEV_TX_BUSY) {
 			/* Tell user-space to retry the send */