Merge tag 'net-6.11-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from netfilter.

  There is a recently notified BT regression with no fix yet. I do not
  think a fix will land in the next week.

  Current release - regressions:

   - core: tighten bad gso csum offset check in virtio_net_hdr

   - netfilter: move nf flowtable bpf initialization in
     nf_flow_table_module_init()

   - eth: ice: stop calling pci_disable_device() as we use pcim

   - eth: fou: fix null-ptr-deref in GRO.

  Current release - new code bugs:

   - hsr: prevent NULL pointer dereference in hsr_proxy_announce()

  Previous releases - regressions:

   - hsr: remove seqnr_lock

   - netfilter: nft_socket: fix sk refcount leaks

   - mptcp: pm: fix uaf in __timer_delete_sync

   - phy: dp83822: fix NULL pointer dereference on DP83825 devices

   - eth: revert "virtio_net: rx enable premapped mode by default"

   - eth: octeontx2-af: Modify SMQ flush sequence to drop packets

  Previous releases - always broken:

   - eth: mlx5: fix bridge mode operations when there are no VFs

   - eth: igb: Always call igb_xdp_ring_update_tail() under Tx lock"

* tag 'net-6.11-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (36 commits)
  net: netfilter: move nf flowtable bpf initialization in nf_flow_table_module_init()
  net: tighten bad gso csum offset check in virtio_net_hdr
  netlink: specs: mptcp: fix port endianness
  net: dpaa: Pad packets to ETH_ZLEN
  mptcp: pm: Fix uaf in __timer_delete_sync
  net: libwx: fix number of Rx and Tx descriptors
  net: dsa: felix: ignore pending status of TAS module when it's disabled
  net: hsr: prevent NULL pointer dereference in hsr_proxy_announce()
  selftests: mptcp: include net_helper.sh file
  selftests: mptcp: include lib.sh file
  selftests: mptcp: join: restrict fullmesh endp on 1st sf
  netfilter: nft_socket: make cgroupsv2 matching work with namespaces
  netfilter: nft_socket: fix sk refcount leaks
  MAINTAINERS: Add ethtool pse-pd to PSE NETWORK DRIVER
  dt-bindings: net: tja11xx: fix the broken binding
  selftests: net: csum: Fix checksums for packets with non-zero padding
  net: phy: dp83822: Fix NULL pointer dereference on DP83825 devices
  virtio_net: disable premapped mode by default
  Revert "virtio_net: big mode skip the unmap check"
  Revert "virtio_net: rx remove premapped failover code"
  ...

9 files changed, 78 insertions, 46 deletions

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index e4cc6b78dcfc..049e22bdaafb 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -231,9 +231,7 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 		skb->dev = master->dev;
 		skb_reset_mac_header(skb);
 		skb_reset_mac_len(skb);
-		spin_lock_bh(&hsr->seqnr_lock);
 		hsr_forward_skb(skb, master);
-		spin_unlock_bh(&hsr->seqnr_lock);
 	} else {
 		dev_core_stats_tx_dropped_inc(dev);
 		dev_kfree_skb_any(skb);
@@ -314,14 +312,10 @@ static void send_hsr_supervision_frame(struct hsr_port *port,
 	set_hsr_stag_HSR_ver(hsr_stag, hsr->prot_version);
 
 	/* From HSRv1 on we have separate supervision sequence numbers. */
-	spin_lock_bh(&hsr->seqnr_lock);
-	if (hsr->prot_version > 0) {
-		hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr);
-		hsr->sup_sequence_nr++;
-	} else {
-		hsr_stag->sequence_nr = htons(hsr->sequence_nr);
-		hsr->sequence_nr++;
-	}
+	if (hsr->prot_version > 0)
+		hsr_stag->sequence_nr = htons(atomic_inc_return(&hsr->sup_sequence_nr));
+	else
+		hsr_stag->sequence_nr = htons(atomic_inc_return(&hsr->sequence_nr));
 
 	hsr_stag->tlv.HSR_TLV_type = type;
 	/* TODO: Why 12 in HSRv0? */
@@ -343,13 +337,11 @@ static void send_hsr_supervision_frame(struct hsr_port *port,
 		ether_addr_copy(hsr_sp->macaddress_A, hsr->macaddress_redbox);
 	}
 
-	if (skb_put_padto(skb, ETH_ZLEN)) {
-		spin_unlock_bh(&hsr->seqnr_lock);
+	if (skb_put_padto(skb, ETH_ZLEN))
 		return;
-	}
 
 	hsr_forward_skb(skb, port);
-	spin_unlock_bh(&hsr->seqnr_lock);
+
 	return;
 }
 
@@ -374,9 +366,7 @@ static void send_prp_supervision_frame(struct hsr_port *master,
 	set_hsr_stag_HSR_ver(hsr_stag, (hsr->prot_version ? 1 : 0));
 
 	/* From HSRv1 on we have separate supervision sequence numbers. */
-	spin_lock_bh(&hsr->seqnr_lock);
-	hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr);
-	hsr->sup_sequence_nr++;
+	hsr_stag->sequence_nr = htons(atomic_inc_return(&hsr->sup_sequence_nr));
 	hsr_stag->tlv.HSR_TLV_type = PRP_TLV_LIFE_CHECK_DD;
 	hsr_stag->tlv.HSR_TLV_length = sizeof(struct hsr_sup_payload);
 
@@ -384,13 +374,10 @@ static void send_prp_supervision_frame(struct hsr_port *master,
 	hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload));
 	ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr);
 
-	if (skb_put_padto(skb, ETH_ZLEN)) {
-		spin_unlock_bh(&hsr->seqnr_lock);
+	if (skb_put_padto(skb, ETH_ZLEN))
 		return;
-	}
 
 	hsr_forward_skb(skb, master);
-	spin_unlock_bh(&hsr->seqnr_lock);
 }
 
 /* Announce (supervision frame) timer function
@@ -427,6 +414,9 @@ static void hsr_proxy_announce(struct timer_list *t)
 	 * of SAN nodes stored in ProxyNodeTable.
 	 */
 	interlink = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK);
+	if (!interlink)
+		goto done;
+
 	list_for_each_entry_rcu(node, &hsr->proxy_node_db, mac_list) {
 		if (hsr_addr_is_redbox(hsr, node->macaddress_A))
 			continue;
@@ -441,6 +431,7 @@ static void hsr_proxy_announce(struct timer_list *t)
 		mod_timer(&hsr->announce_proxy_timer, jiffies + interval);
 	}
 
+done:
 	rcu_read_unlock();
 }
 
@@ -621,11 +612,9 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
 	if (res < 0)
 		return res;
 
-	spin_lock_init(&hsr->seqnr_lock);
 	/* Overflow soon to find bugs easier: */
-	hsr->sequence_nr = HSR_SEQNR_START;
-	hsr->sup_sequence_nr = HSR_SUP_SEQNR_START;
-	hsr->interlink_sequence_nr = HSR_SEQNR_START;
+	atomic_set(&hsr->sequence_nr, HSR_SEQNR_START);
+	atomic_set(&hsr->sup_sequence_nr, HSR_SUP_SEQNR_START);
 
 	timer_setup(&hsr->announce_timer, hsr_announce, 0);
 	timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0);
diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c
index b38060246e62..6f63c8a775c4 100644
--- a/net/hsr/hsr_forward.c
+++ b/net/hsr/hsr_forward.c
@@ -599,9 +599,7 @@ static void handle_std_frame(struct sk_buff *skb,
 	if (port->type == HSR_PT_MASTER ||
 	    port->type == HSR_PT_INTERLINK) {
 		/* Sequence nr for the master/interlink node */
-		lockdep_assert_held(&hsr->seqnr_lock);
-		frame->sequence_nr = hsr->sequence_nr;
-		hsr->sequence_nr++;
+		frame->sequence_nr = atomic_inc_return(&hsr->sequence_nr);
 	}
 }
 
diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h
index ab1f8d35d9dc..6f7bbf01f3e4 100644
--- a/net/hsr/hsr_main.h
+++ b/net/hsr/hsr_main.h
@@ -202,11 +202,9 @@ struct hsr_priv {
 	struct timer_list	prune_timer;
 	struct timer_list	prune_proxy_timer;
 	int announce_count;
-	u16 sequence_nr;
-	u16 interlink_sequence_nr; /* Interlink port seq_nr */
-	u16 sup_sequence_nr;	/* For HSRv1 separate seq_nr for supervision */
+	atomic_t sequence_nr;
+	atomic_t sup_sequence_nr;	/* For HSRv1 separate seq_nr for supervision */
 	enum hsr_version prot_version;	/* Indicate if HSRv0, HSRv1 or PRPv1 */
-	spinlock_t seqnr_lock;	/* locking for sequence_nr */
 	spinlock_t list_lock;	/* locking for node list */
 	struct hsr_proto_ops	*proto_ops;
 #define PRP_LAN_ID	0x5     /* 0x1010 for A and 0x1011 for B. Bit 0 is set
diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index f6ff0b61e08a..8aea4ff5f49e 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -163,7 +163,7 @@ static int hsr_fill_info(struct sk_buff *skb, const struct net_device *dev)
 
 	if (nla_put(skb, IFLA_HSR_SUPERVISION_ADDR, ETH_ALEN,
 		    hsr->sup_multicast_addr) ||
-	    nla_put_u16(skb, IFLA_HSR_SEQ_NR, hsr->sequence_nr))
+	    nla_put_u16(skb, IFLA_HSR_SEQ_NR, atomic_read(&hsr->sequence_nr)))
 		goto nla_put_failure;
 	if (hsr->prot_version == PRP_V1)
 		proto = HSR_PROTOCOL_PRP;
diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c
index 78b869b31492..3e30745e2c09 100644
--- a/net/ipv4/fou_core.c
+++ b/net/ipv4/fou_core.c
@@ -336,11 +336,11 @@ static struct sk_buff *gue_gro_receive(struct sock *sk,
 	struct gro_remcsum grc;
 	u8 proto;
 
+	skb_gro_remcsum_init(&grc);
+
 	if (!fou)
 		goto out;
 
-	skb_gro_remcsum_init(&grc);
-
 	off = skb_gro_offset(skb);
 	len = off + sizeof(*guehdr);
 
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index f891bc714668..ad935d34c973 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -334,15 +334,21 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk,
 {
 	struct mptcp_pm_add_entry *entry;
 	struct sock *sk = (struct sock *)msk;
+	struct timer_list *add_timer = NULL;
 
 	spin_lock_bh(&msk->pm.lock);
 	entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
-	if (entry && (!check_id || entry->addr.id == addr->id))
+	if (entry && (!check_id || entry->addr.id == addr->id)) {
 		entry->retrans_times = ADD_ADDR_RETRANS_MAX;
+		add_timer = &entry->add_timer;
+	}
+	if (!check_id && entry)
+		list_del(&entry->list);
 	spin_unlock_bh(&msk->pm.lock);
 
-	if (entry && (!check_id || entry->addr.id == addr->id))
-		sk_stop_timer_sync(sk, &entry->add_timer);
+	/* no lock, because sk_stop_timer_sync() is calling del_timer_sync() */
+	if (add_timer)
+		sk_stop_timer_sync(sk, add_timer);
 
 	return entry;
 }
@@ -1462,7 +1468,6 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk,
 
 	entry = mptcp_pm_del_add_timer(msk, addr, false);
 	if (entry) {
-		list_del(&entry->list);
 		kfree(entry);
 		return true;
 	}
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 5c1ff07eaee0..df72b0376970 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -670,8 +670,14 @@ static int __init nf_flow_table_module_init(void)
 	if (ret)
 		goto out_offload;
 
+	ret = nf_flow_register_bpf();
+	if (ret)
+		goto out_bpf;
+
 	return 0;
 
+out_bpf:
+	nf_flow_table_offload_exit();
 out_offload:
 	unregister_pernet_subsys(&nf_flow_table_net_ops);
 	return ret;
diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c
index 8b541a080342..b0f199171932 100644
--- a/net/netfilter/nf_flow_table_inet.c
+++ b/net/netfilter/nf_flow_table_inet.c
@@ -101,7 +101,7 @@ static int __init nf_flow_inet_module_init(void)
 	nft_register_flowtable_type(&flowtable_ipv6);
 	nft_register_flowtable_type(&flowtable_inet);
 
-	return nf_flow_register_bpf();
+	return 0;
 }
 
 static void __exit nf_flow_inet_module_exit(void)
diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
index f30163e2ca62..12cdff640492 100644
--- a/net/netfilter/nft_socket.c
+++ b/net/netfilter/nft_socket.c
@@ -9,7 +9,8 @@
 
 struct nft_socket {
 	enum nft_socket_keys		key:8;
-	u8				level;
+	u8				level;		/* cgroupv2 level to extract */
+	u8				level_user;	/* cgroupv2 level provided by userspace */
 	u8				len;
 	union {
 		u8			dreg;
@@ -53,6 +54,28 @@ nft_sock_get_eval_cgroupv2(u32 *dest, struct sock *sk, const struct nft_pktinfo
 	memcpy(dest, &cgid, sizeof(u64));
 	return true;
 }
+
+/* process context only, uses current->nsproxy. */
+static noinline int nft_socket_cgroup_subtree_level(void)
+{
+	struct cgroup *cgrp = cgroup_get_from_path("/");
+	int level;
+
+	if (!cgrp)
+		return -ENOENT;
+
+	level = cgrp->level;
+
+	cgroup_put(cgrp);
+
+	if (WARN_ON_ONCE(level > 255))
+		return -ERANGE;
+
+	if (WARN_ON_ONCE(level < 0))
+		return -EINVAL;
+
+	return level;
+}
 #endif
 
 static struct sock *nft_socket_do_lookup(const struct nft_pktinfo *pkt)
@@ -110,13 +133,13 @@ static void nft_socket_eval(const struct nft_expr *expr,
 			*dest = READ_ONCE(sk->sk_mark);
 		} else {
 			regs->verdict.code = NFT_BREAK;
-			return;
+			goto out_put_sk;
 		}
 		break;
 	case NFT_SOCKET_WILDCARD:
 		if (!sk_fullsock(sk)) {
 			regs->verdict.code = NFT_BREAK;
-			return;
+			goto out_put_sk;
 		}
 		nft_socket_wildcard(pkt, regs, sk, dest);
 		break;
@@ -124,7 +147,7 @@ static void nft_socket_eval(const struct nft_expr *expr,
 	case NFT_SOCKET_CGROUPV2:
 		if (!nft_sock_get_eval_cgroupv2(dest, sk, pkt, priv->level)) {
 			regs->verdict.code = NFT_BREAK;
-			return;
+			goto out_put_sk;
 		}
 		break;
 #endif
@@ -133,6 +156,7 @@ static void nft_socket_eval(const struct nft_expr *expr,
 		regs->verdict.code = NFT_BREAK;
 	}
 
+out_put_sk:
 	if (sk != skb->sk)
 		sock_gen_put(sk);
 }
@@ -173,9 +197,10 @@ static int nft_socket_init(const struct nft_ctx *ctx,
 	case NFT_SOCKET_MARK:
 		len = sizeof(u32);
 		break;
-#ifdef CONFIG_CGROUPS
+#ifdef CONFIG_SOCK_CGROUP_DATA
 	case NFT_SOCKET_CGROUPV2: {
 		unsigned int level;
+		int err;
 
 		if (!tb[NFTA_SOCKET_LEVEL])
 			return -EINVAL;
@@ -184,6 +209,17 @@ static int nft_socket_init(const struct nft_ctx *ctx,
 		if (level > 255)
 			return -EOPNOTSUPP;
 
+		err = nft_socket_cgroup_subtree_level();
+		if (err < 0)
+			return err;
+
+		priv->level_user = level;
+
+		level += err;
+		/* Implies a giant cgroup tree */
+		if (WARN_ON_ONCE(level > 255))
+			return -EOPNOTSUPP;
+
 		priv->level = level;
 		len = sizeof(u64);
 		break;
@@ -208,7 +244,7 @@ static int nft_socket_dump(struct sk_buff *skb,
 	if (nft_dump_register(skb, NFTA_SOCKET_DREG, priv->dreg))
 		return -1;
 	if (priv->key == NFT_SOCKET_CGROUPV2 &&
-	    nla_put_be32(skb, NFTA_SOCKET_LEVEL, htonl(priv->level)))
+	    nla_put_be32(skb, NFTA_SOCKET_LEVEL, htonl(priv->level_user)))
 		return -1;
 	return 0;
 }