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

Cross-merge networking fixes after downstream PR (net-6.13-rc6).

No conflicts.

Adjacent changes:

include/linux/if_vlan.h
  f91a5b808938 ("af_packet: fix vlan_get_protocol_dgram() vs MSG_PEEK")
  3f330db30638 ("net: reformat kdoc return statements")

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

16 files changed, 95 insertions, 60 deletions

diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 9b1168eb77ab..b24afec24138 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1173,6 +1173,8 @@ EXPORT_SYMBOL(ceph_osdc_new_request);
 
 int __ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt)
 {
+	WARN_ON(op->op != CEPH_OSD_OP_SPARSE_READ);
+
 	op->extent.sparse_ext_cnt = cnt;
 	op->extent.sparse_ext = kmalloc_array(cnt,
 					      sizeof(*op->extent.sparse_ext),
diff --git a/net/core/dev.c b/net/core/dev.c
index c7f3dea3e0eb..e7223972b9aa 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3642,8 +3642,10 @@ int skb_csum_hwoffload_help(struct sk_buff *skb,
 
 	if (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) {
 		if (vlan_get_protocol(skb) == htons(ETH_P_IPV6) &&
-		    skb_network_header_len(skb) != sizeof(struct ipv6hdr))
+		    skb_network_header_len(skb) != sizeof(struct ipv6hdr) &&
+		    !ipv6_has_hopopt_jumbo(skb))
 			goto sw_checksum;
+
 		switch (skb->csum_offset) {
 		case offsetof(struct tcphdr, check):
 		case offsetof(struct udphdr, check):
diff --git a/net/core/filter.c b/net/core/filter.c
index 56fe194a76af..b957cf57299e 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3734,13 +3734,22 @@ static const struct bpf_func_proto bpf_skb_adjust_room_proto = {
 
 static u32 __bpf_skb_min_len(const struct sk_buff *skb)
 {
-	u32 min_len = skb_network_offset(skb);
+	int offset = skb_network_offset(skb);
+	u32 min_len = 0;
 
-	if (skb_transport_header_was_set(skb))
-		min_len = skb_transport_offset(skb);
-	if (skb->ip_summed == CHECKSUM_PARTIAL)
-		min_len = skb_checksum_start_offset(skb) +
-			  skb->csum_offset + sizeof(__sum16);
+	if (offset > 0)
+		min_len = offset;
+	if (skb_transport_header_was_set(skb)) {
+		offset = skb_transport_offset(skb);
+		if (offset > 0)
+			min_len = offset;
+	}
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		offset = skb_checksum_start_offset(skb) +
+			 skb->csum_offset + sizeof(__sum16);
+		if (offset > 0)
+			min_len = offset;
+	}
 	return min_len;
 }
 
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 2d3ae0cd3ad2..b0772d135efb 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -246,8 +246,12 @@ int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info)
 	rcu_read_unlock();
 	rtnl_unlock();
 
-	if (err)
+	if (err) {
+		goto err_free_msg;
+	} else if (!rsp->len) {
+		err = -ENOENT;
 		goto err_free_msg;
+	}
 
 	return genlmsg_reply(rsp, info);
 
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index e90fbab703b2..61f3f3d4e528 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -369,8 +369,8 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
 			     struct sk_msg *msg, u32 bytes)
 {
 	int ret = -ENOSPC, i = msg->sg.curr;
+	u32 copy, buf_size, copied = 0;
 	struct scatterlist *sge;
-	u32 copy, buf_size;
 	void *to;
 
 	do {
@@ -397,6 +397,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
 			goto out;
 		}
 		bytes -= copy;
+		copied += copy;
 		if (!bytes)
 			break;
 		msg->sg.copybreak = 0;
@@ -404,7 +405,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
 	} while (i != msg->sg.end);
 out:
 	msg->sg.curr = i;
-	return ret;
+	return (ret < 0) ? ret : copied;
 }
 EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter);
 
@@ -445,8 +446,10 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 			if (likely(!peek)) {
 				sge->offset += copy;
 				sge->length -= copy;
-				if (!msg_rx->skb)
+				if (!msg_rx->skb) {
 					sk_mem_uncharge(sk, copy);
+					atomic_sub(copy, &sk->sk_rmem_alloc);
+				}
 				msg_rx->sg.size -= copy;
 
 				if (!sge->length) {
@@ -772,6 +775,8 @@ static void __sk_psock_purge_ingress_msg(struct sk_psock *psock)
 
 	list_for_each_entry_safe(msg, tmp, &psock->ingress_msg, list) {
 		list_del(&msg->list);
+		if (!msg->skb)
+			atomic_sub(msg->sg.size, &psock->sk->sk_rmem_alloc);
 		sk_msg_free(psock->sk, msg);
 		kfree(msg);
 	}
diff --git a/net/core/sock.c b/net/core/sock.c
index e7bcc8952248..eae2ae70a2e0 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1300,7 +1300,10 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 		sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE);
 		break;
 	case SO_REUSEPORT:
-		sk->sk_reuseport = valbool;
+		if (valbool && !sk_is_inet(sk))
+			ret = -EOPNOTSUPP;
+		else
+			sk->sk_reuseport = valbool;
 		break;
 	case SO_DONTROUTE:
 		sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool);
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 25505f9b724c..09b73acf037a 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -294,7 +294,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 
 		ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr,
 				    iph->saddr, tunnel->parms.o_key,
-				    iph->tos & INET_DSCP_MASK, dev_net(dev),
+				    iph->tos & INET_DSCP_MASK, tunnel->net,
 				    tunnel->parms.link, tunnel->fwmark, 0, 0);
 		rt = ip_route_output_key(tunnel->net, &fl4);
 
@@ -611,7 +611,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 	ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src,
 			    tunnel_id_to_key32(key->tun_id),
-			    tos & INET_DSCP_MASK, dev_net(dev), 0, skb->mark,
+			    tos & INET_DSCP_MASK, tunnel->net, 0, skb->mark,
 			    skb_get_hash(skb), key->flow_flags);
 
 	if (!tunnel_hlen)
@@ -774,7 +774,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr,
 			    tunnel->parms.o_key, tos & INET_DSCP_MASK,
-			    dev_net(dev), READ_ONCE(tunnel->parms.link),
+			    tunnel->net, READ_ONCE(tunnel->parms.link),
 			    tunnel->fwmark, skb_get_hash(skb), 0);
 
 	if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0)
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 99cef92e6290..47f65b1b70ca 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -49,13 +49,14 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
 		sge = sk_msg_elem(msg, i);
 		size = (apply && apply_bytes < sge->length) ?
 			apply_bytes : sge->length;
-		if (!sk_wmem_schedule(sk, size)) {
+		if (!__sk_rmem_schedule(sk, size, false)) {
 			if (!copied)
 				ret = -ENOMEM;
 			break;
 		}
 
 		sk_mem_charge(sk, size);
+		atomic_add(size, &sk->sk_rmem_alloc);
 		sk_msg_xfer(tmp, msg, i, size);
 		copied += size;
 		if (sge->length)
@@ -74,7 +75,8 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
 
 	if (!ret) {
 		msg->sg.start = i;
-		sk_psock_queue_msg(psock, tmp);
+		if (!sk_psock_queue_msg(psock, tmp))
+			atomic_sub(copied, &sk->sk_rmem_alloc);
 		sk_psock_data_ready(sk, psock);
 	} else {
 		sk_msg_free(sk, tmp);
@@ -493,7 +495,7 @@ more_data:
 static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	struct sk_msg tmp, *msg_tx = NULL;
-	int copied = 0, err = 0;
+	int copied = 0, err = 0, ret = 0;
 	struct sk_psock *psock;
 	long timeo;
 	int flags;
@@ -536,14 +538,14 @@ static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 			copy = msg_tx->sg.size - osize;
 		}
 
-		err = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_tx,
+		ret = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_tx,
 					       copy);
-		if (err < 0) {
+		if (ret < 0) {
 			sk_msg_trim(sk, msg_tx, osize);
 			goto out_err;
 		}
 
-		copied += copy;
+		copied += ret;
 		if (psock->cork_bytes) {
 			if (size > psock->cork_bytes)
 				psock->cork_bytes = 0;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5bdf13ac26ef..4811727b8a02 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -7328,6 +7328,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 			if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req,
 								    req->timeout))) {
 				reqsk_free(req);
+				dst_release(dst);
 				return 0;
 			}
 
diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index 7646e401c630..1d41b2ab4884 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -195,6 +195,8 @@ static const struct nf_hook_ops ila_nf_hook_ops[] = {
 	},
 };
 
+static DEFINE_MUTEX(ila_mutex);
+
 static int ila_add_mapping(struct net *net, struct ila_xlat_params *xp)
 {
 	struct ila_net *ilan = net_generic(net, ila_net_id);
@@ -202,16 +204,20 @@ static int ila_add_mapping(struct net *net, struct ila_xlat_params *xp)
 	spinlock_t *lock = ila_get_lock(ilan, xp->ip.locator_match);
 	int err = 0, order;
 
-	if (!ilan->xlat.hooks_registered) {
+	if (!READ_ONCE(ilan->xlat.hooks_registered)) {
 		/* We defer registering net hooks in the namespace until the
 		 * first mapping is added.
 		 */
-		err = nf_register_net_hooks(net, ila_nf_hook_ops,
-					    ARRAY_SIZE(ila_nf_hook_ops));
+		mutex_lock(&ila_mutex);
+		if (!ilan->xlat.hooks_registered) {
+			err = nf_register_net_hooks(net, ila_nf_hook_ops,
+						ARRAY_SIZE(ila_nf_hook_ops));
+			if (!err)
+				WRITE_ONCE(ilan->xlat.hooks_registered, true);
+		}
+		mutex_unlock(&ila_mutex);
 		if (err)
 			return err;
-
-		ilan->xlat.hooks_registered = true;
 	}
 
 	ila = kzalloc(sizeof(*ila), GFP_KERNEL);
diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c
index 51bccfb00a9c..61b0159b2fbe 100644
--- a/net/llc/llc_input.c
+++ b/net/llc/llc_input.c
@@ -124,8 +124,8 @@ static inline int llc_fixup_skb(struct sk_buff *skb)
 	if (unlikely(!pskb_may_pull(skb, llc_len)))
 		return 0;
 
-	skb->transport_header += llc_len;
 	skb_pull(skb, llc_len);
+	skb_reset_transport_header(skb);
 	if (skb->protocol == htons(ETH_P_802_2)) {
 		__be16 pdulen;
 		s32 data_size;
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 1603b3702e22..a62bc874bf1e 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -667,8 +667,15 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
 		    &echo, &drop_other_suboptions))
 		return false;
 
+	/*
+	 * Later on, mptcp_write_options() will enforce mutually exclusion with
+	 * DSS, bail out if such option is set and we can't drop it.
+	 */
 	if (drop_other_suboptions)
 		remaining += opt_size;
+	else if (opts->suboptions & OPTION_MPTCP_DSS)
+		return false;
+
 	len = mptcp_add_addr_len(opts->addr.family, echo, !!opts->addr.port);
 	if (remaining < len)
 		return false;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 08a72242428c..1b2e7cbb577f 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -136,6 +136,7 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
 	int delta;
 
 	if (MPTCP_SKB_CB(from)->offset ||
+	    ((to->len + from->len) > (sk->sk_rcvbuf >> 3)) ||
 	    !skb_try_coalesce(to, from, &fragstolen, &delta))
 		return false;
 
@@ -528,13 +529,13 @@ static void mptcp_send_ack(struct mptcp_sock *msk)
 		mptcp_subflow_send_ack(mptcp_subflow_tcp_sock(subflow));
 }
 
-static void mptcp_subflow_cleanup_rbuf(struct sock *ssk)
+static void mptcp_subflow_cleanup_rbuf(struct sock *ssk, int copied)
 {
 	bool slow;
 
 	slow = lock_sock_fast(ssk);
 	if (tcp_can_send_ack(ssk))
-		tcp_cleanup_rbuf(ssk, 1);
+		tcp_cleanup_rbuf(ssk, copied);
 	unlock_sock_fast(ssk, slow);
 }
 
@@ -551,7 +552,7 @@ static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty)
 			      (ICSK_ACK_PUSHED2 | ICSK_ACK_PUSHED)));
 }
 
-static void mptcp_cleanup_rbuf(struct mptcp_sock *msk)
+static void mptcp_cleanup_rbuf(struct mptcp_sock *msk, int copied)
 {
 	int old_space = READ_ONCE(msk->old_wspace);
 	struct mptcp_subflow_context *subflow;
@@ -559,14 +560,14 @@ static void mptcp_cleanup_rbuf(struct mptcp_sock *msk)
 	int space =  __mptcp_space(sk);
 	bool cleanup, rx_empty;
 
-	cleanup = (space > 0) && (space >= (old_space << 1));
-	rx_empty = !__mptcp_rmem(sk);
+	cleanup = (space > 0) && (space >= (old_space << 1)) && copied;
+	rx_empty = !__mptcp_rmem(sk) && copied;
 
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
 		if (cleanup || mptcp_subflow_could_cleanup(ssk, rx_empty))
-			mptcp_subflow_cleanup_rbuf(ssk);
+			mptcp_subflow_cleanup_rbuf(ssk, copied);
 	}
 }
 
@@ -1939,6 +1940,8 @@ do_error:
 	goto out;
 }
 
+static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied);
+
 static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
 				struct msghdr *msg,
 				size_t len, int flags,
@@ -1992,6 +1995,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
 			break;
 	}
 
+	mptcp_rcv_space_adjust(msk, copied);
 	return copied;
 }
 
@@ -2217,9 +2221,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 
 		copied += bytes_read;
 
-		/* be sure to advertise window change */
-		mptcp_cleanup_rbuf(msk);
-
 		if (skb_queue_empty(&msk->receive_queue) && __mptcp_move_skbs(msk))
 			continue;
 
@@ -2268,7 +2269,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		}
 
 		pr_debug("block timeout %ld\n", timeo);
-		mptcp_rcv_space_adjust(msk, copied);
+		mptcp_cleanup_rbuf(msk, copied);
 		err = sk_wait_data(sk, &timeo, NULL);
 		if (err < 0) {
 			err = copied ? : err;
@@ -2276,7 +2277,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		}
 	}
 
-	mptcp_rcv_space_adjust(msk, copied);
+	mptcp_cleanup_rbuf(msk, copied);
 
 out_err:
 	if (cmsg_flags && copied >= 0) {
diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c
index 2b5e246b8d9a..b94cb2ffbaf8 100644
--- a/net/netrom/nr_route.c
+++ b/net/netrom/nr_route.c
@@ -754,6 +754,12 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25)
 	int ret;
 	struct sk_buff *skbn;
 
+	/*
+	 * Reject malformed packets early. Check that it contains at least 2
+	 * addresses and 1 byte more for Time-To-Live
+	 */
+	if (skb->len < 2 * sizeof(ax25_address) + 1)
+		return 0;
 
 	nr_src  = (ax25_address *)(skb->data + 0);
 	nr_dest = (ax25_address *)(skb->data + 7);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index f8d87d622699..c131e5ceea37 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -538,10 +538,8 @@ static void *packet_current_frame(struct packet_sock *po,
 	return packet_lookup_frame(po, rb, rb->head, status);
 }
 
-static u16 vlan_get_tci(struct sk_buff *skb, struct net_device *dev)
+static u16 vlan_get_tci(const struct sk_buff *skb, struct net_device *dev)
 {
-	u8 *skb_orig_data = skb->data;
-	int skb_orig_len = skb->len;
 	struct vlan_hdr vhdr, *vh;
 	unsigned int header_len;
 
@@ -562,33 +560,21 @@ static u16 vlan_get_tci(struct sk_buff *skb, struct net_device *dev)
 	else
 		return 0;
 
-	skb_push(skb, skb->data - skb_mac_header(skb));
-	vh = skb_header_pointer(skb, header_len, sizeof(vhdr), &vhdr);
-	if (skb_orig_data != skb->data) {
-		skb->data = skb_orig_data;
-		skb->len = skb_orig_len;
-	}
+	vh = skb_header_pointer(skb, skb_mac_offset(skb) + header_len,
+				sizeof(vhdr), &vhdr);
 	if (unlikely(!vh))
 		return 0;
 
 	return ntohs(vh->h_vlan_TCI);
 }
 
-static __be16 vlan_get_protocol_dgram(struct sk_buff *skb)
+static __be16 vlan_get_protocol_dgram(const struct sk_buff *skb)
 {
 	__be16 proto = skb->protocol;
 
-	if (unlikely(eth_type_vlan(proto))) {
-		u8 *skb_orig_data = skb->data;
-		int skb_orig_len = skb->len;
-
-		skb_push(skb, skb->data - skb_mac_header(skb));
-		proto = __vlan_get_protocol(skb, proto, NULL);
-		if (skb_orig_data != skb->data) {
-			skb->data = skb_orig_data;
-			skb->len = skb_orig_len;
-		}
-	}
+	if (unlikely(eth_type_vlan(proto)))
+		proto = __vlan_get_protocol_offset(skb, proto,
+						   skb_mac_offset(skb), NULL);
 
 	return proto;
 }
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index c45c192b7878..0b0794f164cf 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -137,7 +137,8 @@ static struct sctp_association *sctp_association_init(
 		= 5 * asoc->rto_max;
 
 	asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay;
-	asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = sp->autoclose * HZ;
+	asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] =
+		(unsigned long)sp->autoclose * HZ;
 
 	/* Initializes the timers */
 	for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i)