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

Pull networking fixes from David Miller:

 1) Fix sk_psock reference count leak on receive, from Xiyu Yang.

 2) CONFIG_HNS should be invisible, from Geert Uytterhoeven.

 3) Don't allow locking route MTUs in ipv6, RFCs actually forbid this,
    from Maciej Żenczykowski.

 4) ipv4 route redirect backoff wasn't actually enforced, from Paolo
    Abeni.

 5) Fix netprio cgroup v2 leak, from Zefan Li.

 6) Fix infinite loop on rmmod in conntrack, from Florian Westphal.

 7) Fix tcp SO_RCVLOWAT hangs, from Eric Dumazet.

 8) Various bpf probe handling fixes, from Daniel Borkmann.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (68 commits)
  selftests: mptcp: pm: rm the right tmp file
  dpaa2-eth: properly handle buffer size restrictions
  bpf: Restrict bpf_trace_printk()'s %s usage and add %pks, %pus specifier
  bpf: Add bpf_probe_read_{user, kernel}_str() to do_refine_retval_range
  bpf: Restrict bpf_probe_read{, str}() only to archs where they work
  MAINTAINERS: Mark networking drivers as Maintained.
  ipmr: Add lockdep expression to ipmr_for_each_table macro
  ipmr: Fix RCU list debugging warning
  drivers: net: hamradio: Fix suspicious RCU usage warning in bpqether.c
  net: phy: broadcom: fix BCM54XX_SHD_SCR3_TRDDAPD value for BCM54810
  tcp: fix error recovery in tcp_zerocopy_receive()
  MAINTAINERS: Add Jakub to networking drivers.
  MAINTAINERS: another add of Karsten Graul for S390 networking
  drivers: ipa: fix typos for ipa_smp2p structure doc
  pppoe: only process PADT targeted at local interfaces
  selftests/bpf: Enforce returning 0 for fentry/fexit programs
  bpf: Enforce returning 0 for fentry/fexit progs
  net: stmmac: fix num_por initialization
  security: Fix the default value of secid_to_secctx hook
  libbpf: Fix register naming in PT_REGS s390 macros
  ...

6 files changed, 36 insertions, 18 deletions

diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 0bd10a1f477f..a23094b050f8 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1258,7 +1258,8 @@ static int cipso_v4_parsetag_rbm(const struct cipso_v4_doi *doi_def,
 			return ret_val;
 		}
 
-		secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+		if (secattr->attr.mls.cat)
+			secattr->flags |= NETLBL_SECATTR_MLS_CAT;
 	}
 
 	return 0;
@@ -1439,7 +1440,8 @@ static int cipso_v4_parsetag_rng(const struct cipso_v4_doi *doi_def,
 			return ret_val;
 		}
 
-		secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+		if (secattr->attr.mls.cat)
+			secattr->flags |= NETLBL_SECATTR_MLS_CAT;
 	}
 
 	return 0;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 9cf83cc85e4a..5c218db2dede 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -109,8 +109,10 @@ static void mroute_clean_tables(struct mr_table *mrt, int flags);
 static void ipmr_expire_process(struct timer_list *t);
 
 #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
-#define ipmr_for_each_table(mrt, net) \
-	list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list)
+#define ipmr_for_each_table(mrt, net)					\
+	list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list,	\
+				lockdep_rtnl_is_held() ||		\
+				list_empty(&net->ipv4.mr_tables))
 
 static struct mr_table *ipmr_mr_table_iter(struct net *net,
 					   struct mr_table *mrt)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 788c69d9bfe0..fa829f31a3f5 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -915,7 +915,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 	/* Check for load limit; set rate_last to the latest sent
 	 * redirect.
 	 */
-	if (peer->rate_tokens == 0 ||
+	if (peer->n_redirects == 0 ||
 	    time_after(jiffies,
 		       (peer->rate_last +
 			(ip_rt_redirect_load << peer->n_redirects)))) {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 6d87de434377..dd401757eea1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -476,9 +476,17 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
 static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
 					  int target, struct sock *sk)
 {
-	return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) ||
-		(sk->sk_prot->stream_memory_read ?
-		sk->sk_prot->stream_memory_read(sk) : false);
+	int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq);
+
+	if (avail > 0) {
+		if (avail >= target)
+			return true;
+		if (tcp_rmem_pressure(sk))
+			return true;
+	}
+	if (sk->sk_prot->stream_memory_read)
+		return sk->sk_prot->stream_memory_read(sk);
+	return false;
 }
 
 /*
@@ -1756,10 +1764,11 @@ static int tcp_zerocopy_receive(struct sock *sk,
 
 	down_read(&current->mm->mmap_sem);
 
-	ret = -EINVAL;
 	vma = find_vma(current->mm, address);
-	if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops)
-		goto out;
+	if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) {
+		up_read(&current->mm->mmap_sem);
+		return -EINVAL;
+	}
 	zc->length = min_t(unsigned long, zc->length, vma->vm_end - address);
 
 	tp = tcp_sk(sk);
@@ -2154,13 +2163,15 @@ skip_copy:
 			tp->urg_data = 0;
 			tcp_fast_path_check(sk);
 		}
-		if (used + offset < skb->len)
-			continue;
 
 		if (TCP_SKB_CB(skb)->has_rxtstamp) {
 			tcp_update_recv_tstamps(skb, &tss);
 			cmsg_flags |= 2;
 		}
+
+		if (used + offset < skb->len)
+			continue;
+
 		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 			goto found_fin_ok;
 		if (!(flags & MSG_PEEK))
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 5a05327f97c1..629aaa9a1eb9 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -125,7 +125,6 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
 
 	if (!ret) {
 		msg->sg.start = i;
-		msg->sg.size -= apply_bytes;
 		sk_psock_queue_msg(psock, tmp);
 		sk_psock_data_ready(sk, psock);
 	} else {
@@ -262,14 +261,17 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	struct sk_psock *psock;
 	int copied, ret;
 
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return inet_recv_error(sk, msg, len, addr_len);
+
 	psock = sk_psock_get(sk);
 	if (unlikely(!psock))
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
-	if (unlikely(flags & MSG_ERRQUEUE))
-		return inet_recv_error(sk, msg, len, addr_len);
 	if (!skb_queue_empty(&sk->sk_receive_queue) &&
-	    sk_psock_queue_empty(psock))
+	    sk_psock_queue_empty(psock)) {
+		sk_psock_put(sk, psock);
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+	}
 	lock_sock(sk);
 msg_bytes_ready:
 	copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b996dc1069c5..29c6fc8c7716 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4757,7 +4757,8 @@ void tcp_data_ready(struct sock *sk)
 	const struct tcp_sock *tp = tcp_sk(sk);
 	int avail = tp->rcv_nxt - tp->copied_seq;
 
-	if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE))
+	if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) &&
+	    !sock_flag(sk, SOCK_DONE))
 		return;
 
 	sk->sk_data_ready(sk);