Merge tag 'net-6.1-rc3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from bpf.

  The net-memcg fix stands out, the rest is very run-off-the-mill. Maybe
  I'm biased.

  Current release - regressions:

   - eth: fman: re-expose location of the MAC address to userspace,
     apparently some udev scripts depended on the exact value

  Current release - new code bugs:

   - bpf:
       - wait for busy refill_work when destroying bpf memory allocator
       - allow bpf_user_ringbuf_drain() callbacks to return 1
       - fix dispatcher patchable function entry to 5 bytes nop

  Previous releases - regressions:

   - net-memcg: avoid stalls when under memory pressure

   - tcp: fix indefinite deferral of RTO with SACK reneging

   - tipc: fix a null-ptr-deref in tipc_topsrv_accept

   - eth: macb: specify PHY PM management done by MAC

   - tcp: fix a signed-integer-overflow bug in tcp_add_backlog()

  Previous releases - always broken:

   - eth: amd-xgbe: SFP fixes and compatibility improvements

  Misc:

   - docs: netdev: offer performance feedback to contributors"

* tag 'net-6.1-rc3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (37 commits)
  net-memcg: avoid stalls when under memory pressure
  tcp: fix indefinite deferral of RTO with SACK reneging
  tcp: fix a signed-integer-overflow bug in tcp_add_backlog()
  net: lantiq_etop: don't free skb when returning NETDEV_TX_BUSY
  net: fix UAF issue in nfqnl_nf_hook_drop() when ops_init() failed
  docs: netdev: offer performance feedback to contributors
  kcm: annotate data-races around kcm->rx_wait
  kcm: annotate data-races around kcm->rx_psock
  net: fman: Use physical address for userspace interfaces
  net/mlx5e: Cleanup MACsec uninitialization routine
  atlantic: fix deadlock at aq_nic_stop
  nfp: only clean `sp_indiff` when application firmware is unloaded
  amd-xgbe: add the bit rate quirk for Molex cables
  amd-xgbe: fix the SFP compliance codes check for DAC cables
  amd-xgbe: enable PLL_CTL for fixed PHY modes only
  amd-xgbe: use enums for mailbox cmd and sub_cmds
  amd-xgbe: Yellow carp devices do not need rrc
  bpf: Use __llist_del_all() whenever possbile during memory draining
  bpf: Wait for busy refill_work when destroying bpf memory allocator
  MAINTAINERS: add keyword match on PTP
  ...

6 files changed, 40 insertions, 15 deletions

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 0ec2f5906a27..f64654df71a2 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -117,6 +117,7 @@ static int net_assign_generic(struct net *net, unsigned int id, void *data)
 
 static int ops_init(const struct pernet_operations *ops, struct net *net)
 {
+	struct net_generic *ng;
 	int err = -ENOMEM;
 	void *data = NULL;
 
@@ -135,7 +136,13 @@ static int ops_init(const struct pernet_operations *ops, struct net *net)
 	if (!err)
 		return 0;
 
+	if (ops->id && ops->size) {
 cleanup:
+		ng = rcu_dereference_protected(net->gen,
+					       lockdep_is_held(&pernet_ops_rwsem));
+		ng->ptr[*ops->id] = NULL;
+	}
+
 	kfree(data);
 
 out:
diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c
index 5a471e115b66..e8683e485dc9 100644
--- a/net/ethtool/pse-pd.c
+++ b/net/ethtool/pse-pd.c
@@ -64,7 +64,7 @@ static int pse_prepare_data(const struct ethnl_req_info *req_base,
 	if (ret < 0)
 		return ret;
 
-	ret = pse_get_pse_attributes(dev, info->extack, data);
+	ret = pse_get_pse_attributes(dev, info ? info->extack : NULL, data);
 
 	ethnl_ops_complete(dev);
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index bc2ea12221f9..0640453fce54 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2192,7 +2192,8 @@ void tcp_enter_loss(struct sock *sk)
  */
 static bool tcp_check_sack_reneging(struct sock *sk, int flag)
 {
-	if (flag & FLAG_SACK_RENEGING) {
+	if (flag & FLAG_SACK_RENEGING &&
+	    flag & FLAG_SND_UNA_ADVANCED) {
 		struct tcp_sock *tp = tcp_sk(sk);
 		unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4),
 					  msecs_to_jiffies(10));
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7a250ef9d1b7..87d440f47a70 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1874,11 +1874,13 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
 	__skb_push(skb, hdrlen);
 
 no_coalesce:
+	limit = (u32)READ_ONCE(sk->sk_rcvbuf) + (u32)(READ_ONCE(sk->sk_sndbuf) >> 1);
+
 	/* Only socket owner can try to collapse/prune rx queues
 	 * to reduce memory overhead, so add a little headroom here.
 	 * Few sockets backlog are possibly concurrently non empty.
 	 */
-	limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf) + 64*1024;
+	limit += 64 * 1024;
 
 	if (unlikely(sk_add_backlog(sk, skb, limit))) {
 		bh_unlock_sock(sk);
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 27725464ec08..63e32f181f43 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -162,7 +162,8 @@ static void kcm_rcv_ready(struct kcm_sock *kcm)
 	/* Buffer limit is okay now, add to ready list */
 	list_add_tail(&kcm->wait_rx_list,
 		      &kcm->mux->kcm_rx_waiters);
-	kcm->rx_wait = true;
+	/* paired with lockless reads in kcm_rfree() */
+	WRITE_ONCE(kcm->rx_wait, true);
 }
 
 static void kcm_rfree(struct sk_buff *skb)
@@ -178,7 +179,7 @@ static void kcm_rfree(struct sk_buff *skb)
 	/* For reading rx_wait and rx_psock without holding lock */
 	smp_mb__after_atomic();
 
-	if (!kcm->rx_wait && !kcm->rx_psock &&
+	if (!READ_ONCE(kcm->rx_wait) && !READ_ONCE(kcm->rx_psock) &&
 	    sk_rmem_alloc_get(sk) < sk->sk_rcvlowat) {
 		spin_lock_bh(&mux->rx_lock);
 		kcm_rcv_ready(kcm);
@@ -237,7 +238,8 @@ try_again:
 		if (kcm_queue_rcv_skb(&kcm->sk, skb)) {
 			/* Should mean socket buffer full */
 			list_del(&kcm->wait_rx_list);
-			kcm->rx_wait = false;
+			/* paired with lockless reads in kcm_rfree() */
+			WRITE_ONCE(kcm->rx_wait, false);
 
 			/* Commit rx_wait to read in kcm_free */
 			smp_wmb();
@@ -280,10 +282,12 @@ static struct kcm_sock *reserve_rx_kcm(struct kcm_psock *psock,
 	kcm = list_first_entry(&mux->kcm_rx_waiters,
 			       struct kcm_sock, wait_rx_list);
 	list_del(&kcm->wait_rx_list);
-	kcm->rx_wait = false;
+	/* paired with lockless reads in kcm_rfree() */
+	WRITE_ONCE(kcm->rx_wait, false);
 
 	psock->rx_kcm = kcm;
-	kcm->rx_psock = psock;
+	/* paired with lockless reads in kcm_rfree() */
+	WRITE_ONCE(kcm->rx_psock, psock);
 
 	spin_unlock_bh(&mux->rx_lock);
 
@@ -310,7 +314,8 @@ static void unreserve_rx_kcm(struct kcm_psock *psock,
 	spin_lock_bh(&mux->rx_lock);
 
 	psock->rx_kcm = NULL;
-	kcm->rx_psock = NULL;
+	/* paired with lockless reads in kcm_rfree() */
+	WRITE_ONCE(kcm->rx_psock, NULL);
 
 	/* Commit kcm->rx_psock before sk_rmem_alloc_get to sync with
 	 * kcm_rfree
@@ -1240,7 +1245,8 @@ static void kcm_recv_disable(struct kcm_sock *kcm)
 	if (!kcm->rx_psock) {
 		if (kcm->rx_wait) {
 			list_del(&kcm->wait_rx_list);
-			kcm->rx_wait = false;
+			/* paired with lockless reads in kcm_rfree() */
+			WRITE_ONCE(kcm->rx_wait, false);
 		}
 
 		requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue);
@@ -1793,7 +1799,8 @@ static void kcm_done(struct kcm_sock *kcm)
 
 	if (kcm->rx_wait) {
 		list_del(&kcm->wait_rx_list);
-		kcm->rx_wait = false;
+		/* paired with lockless reads in kcm_rfree() */
+		WRITE_ONCE(kcm->rx_wait, false);
 	}
 	/* Move any pending receive messages to other kcm sockets */
 	requeue_rx_msgs(mux, &sk->sk_receive_queue);
diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index 14fd05fd6107..d92ec92f0b71 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -450,12 +450,19 @@ static void tipc_conn_data_ready(struct sock *sk)
 static void tipc_topsrv_accept(struct work_struct *work)
 {
 	struct tipc_topsrv *srv = container_of(work, struct tipc_topsrv, awork);
-	struct socket *lsock = srv->listener;
-	struct socket *newsock;
+	struct socket *newsock, *lsock;
 	struct tipc_conn *con;
 	struct sock *newsk;
 	int ret;
 
+	spin_lock_bh(&srv->idr_lock);
+	if (!srv->listener) {
+		spin_unlock_bh(&srv->idr_lock);
+		return;
+	}
+	lsock = srv->listener;
+	spin_unlock_bh(&srv->idr_lock);
+
 	while (1) {
 		ret = kernel_accept(lsock, &newsock, O_NONBLOCK);
 		if (ret < 0)
@@ -489,7 +496,7 @@ static void tipc_topsrv_listener_data_ready(struct sock *sk)
 
 	read_lock_bh(&sk->sk_callback_lock);
 	srv = sk->sk_user_data;
-	if (srv->listener)
+	if (srv)
 		queue_work(srv->rcv_wq, &srv->awork);
 	read_unlock_bh(&sk->sk_callback_lock);
 }
@@ -699,8 +706,9 @@ static void tipc_topsrv_stop(struct net *net)
 	__module_get(lsock->sk->sk_prot_creator->owner);
 	srv->listener = NULL;
 	spin_unlock_bh(&srv->idr_lock);
-	sock_release(lsock);
+
 	tipc_topsrv_work_stop(srv);
+	sock_release(lsock);
 	idr_destroy(&srv->conn_idr);
 	kfree(srv);
 }