6.18.55-rc1 review

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bernardo Soares <[email protected]>

[ Upstream commit 35e6f970f553954d92ba20afa885139a8e7dd0d7 ]

mlx5 registers the bridge offload switchdev notifiers once per eswitch instance, but the notifier chains are global, so every instance sees every event and must filter out the ones that aren't its own. The existing filter, mlx5_esw_bridge_dev_same_hw(), only checks that the event netdevice sits on the same HCA - intentional for merged eswitch, where one bridge can span representors of several eswitches on one HCA - but same-HCA doesn't mean the instance actually has that port:
peer ports are only created reactively from NETDEV_CHANGEUPPER, so an instance brought up after a sibling PF's port was already enslaved has none. The port object and attribute handlers claim the event anyway once same-HW passes, then fail the port lookup and return -EINVAL, which gets reported to user space even though the owning instance already handled it (e.g. "bridge vlan add ... RTNETLINK answers:
Invalid argument"). Fix by filtering on the tracked port instead.

The same gap exists in the generic recursive lower-device walk used by attribute changes on a bridge with more than one representor enslaved
directly: mlx5_esw_bridge_lower_rep_vport_num_vhca_id_get() is entered with the bridge master netdevice, falls through to its generic netdev_for_each_lower_dev() loop, and returns as soon as the recursion into any one lower device yields a non-NULL rep - the underlying base case, mlx5_esw_bridge_rep_vport_num_vhca_id_get(), only checks mlx5_esw_bridge_dev_same_hw(), not ownership by the calling instance's br_offloads. mlx5_esw_bridge_lag_rep_get(), used for the LAG-master case, already filters on mlx5_esw_bridge_dev_same_esw() per candidate and so cannot select a sibling's rep; it is not the source of this bug. On a merged-eswitch HCA with a bridge spanning representors of more than one eswitch instance directly, the walk can return a sibling's rep instead of continuing to the one the calling instance actually owns, so the attribute change fails the same way as above. Fix by checking mlx5_esw_bridge_port_exists() at the point each rep is picked, same as the previous fix did for the notifier filter.

---
 .../mellanox/mlx5/core/en/rep/bridge.c        | 45 +++++++++++++++----
 .../ethernet/mellanox/mlx5/core/esw/bridge.c  |  6 +++
 .../ethernet/mellanox/mlx5/core/esw/bridge.h  |  2 +
 3 files changed, 44 insertions(+), 9 deletions(-)

index 9d1c677814e06..5eadc66037c4f 100644
@@ -89,9 +89,16 @@ mlx5_esw_bridge_lower_rep_vport_num_vhca_id_get(struct net_device *dev, struct m
 	struct net_device *lower_dev;
 	struct list_head *iter;
 
-	if (netif_is_lag_master(dev) || mlx5e_eswitch_rep(dev))
-		return mlx5_esw_bridge_rep_vport_num_vhca_id_get(dev, esw, vport_num,
-								 esw_owner_vhca_id);
+	if (netif_is_lag_master(dev) || mlx5e_eswitch_rep(dev)) {
+		struct net_device *rep;
+
+		rep = mlx5_esw_bridge_rep_vport_num_vhca_id_get(dev, esw, vport_num,
+								esw_owner_vhca_id);
+		if (rep && !mlx5_esw_bridge_port_exists(*vport_num, *esw_owner_vhca_id,
+							esw->br_offloads))
+			return NULL;
+		return rep;
+	}
 
 	netdev_for_each_lower_dev(dev, lower_dev, iter) {
 		struct net_device *rep;

@@ -108,6 +115,28 @@ mlx5_esw_bridge_lower_rep_vport_num_vhca_id_get(struct net_device *dev, struct m
 	return NULL;
 }
 
+static bool mlx5_esw_bridge_rep_port_lookup(struct net_device *dev,
+					    struct mlx5_esw_bridge_offloads *br_offloads,
+					    u16 *vport_num, u16 *esw_owner_vhca_id)
+{
+	if (!mlx5_esw_bridge_rep_vport_num_vhca_id_get(dev, br_offloads->esw, vport_num,
+						       esw_owner_vhca_id))
+		return false;
+
+	return mlx5_esw_bridge_port_exists(*vport_num, *esw_owner_vhca_id, br_offloads);
+}
+
+static bool mlx5_esw_bridge_lower_rep_port_lookup(struct net_device *dev,
+						  struct mlx5_esw_bridge_offloads *br_offloads,
+						  u16 *vport_num, u16 *esw_owner_vhca_id)
+{
+	if (!mlx5_esw_bridge_lower_rep_vport_num_vhca_id_get(dev, br_offloads->esw, vport_num,
+							     esw_owner_vhca_id))
+		return false;
+
+	return mlx5_esw_bridge_port_exists(*vport_num, *esw_owner_vhca_id, br_offloads);
+}
+
 static bool mlx5_esw_bridge_is_local(struct net_device *dev, struct net_device *rep,
 				     struct mlx5_eswitch *esw)
 {

@@ -222,8 +251,7 @@ mlx5_esw_bridge_port_obj_add(struct net_device *dev,
 	u16 vport_num, esw_owner_vhca_id;
 	int err;
 
-	if (!mlx5_esw_bridge_rep_vport_num_vhca_id_get(dev, br_offloads->esw, &vport_num,
-						       &esw_owner_vhca_id))
+	if (!mlx5_esw_bridge_rep_port_lookup(dev, br_offloads, &vport_num, &esw_owner_vhca_id))
 		return 0;
 
 	port_obj_info->handled = true;

@@ -255,8 +283,7 @@ mlx5_esw_bridge_port_obj_del(struct net_device *dev,
 	const struct switchdev_obj_port_mdb *mdb;
 	u16 vport_num, esw_owner_vhca_id;
 
-	if (!mlx5_esw_bridge_rep_vport_num_vhca_id_get(dev, br_offloads->esw, &vport_num,
-						       &esw_owner_vhca_id))
+	if (!mlx5_esw_bridge_rep_port_lookup(dev, br_offloads, &vport_num, &esw_owner_vhca_id))
 		return 0;
 
 	port_obj_info->handled = true;

@@ -287,8 +314,8 @@ mlx5_esw_bridge_port_obj_attr_set(struct net_device *dev,
 	u16 vport_num, esw_owner_vhca_id;
 	int err = 0;
 
-	if (!mlx5_esw_bridge_lower_rep_vport_num_vhca_id_get(dev, br_offloads->esw, &vport_num,
-							     &esw_owner_vhca_id))
+	if (!mlx5_esw_bridge_lower_rep_port_lookup(dev, br_offloads, &vport_num,
+						   &esw_owner_vhca_id))
 		return 0;
 
 	port_attr_info->handled = true;

index 60e10047770fa..695456c395039 100644
@@ -1686,6 +1686,12 @@ int mlx5_esw_bridge_vport_peer_unlink(struct net_device *br_netdev, u16 vport_nu
 					    extack);
 }
 
+bool mlx5_esw_bridge_port_exists(u16 vport_num, u16 esw_owner_vhca_id,
+				 struct mlx5_esw_bridge_offloads *br_offloads)
+{
+	return mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
+}
+
 int mlx5_esw_bridge_port_vlan_add(u16 vport_num, u16 esw_owner_vhca_id, u16 vid, u16 flags,
 				  struct mlx5_esw_bridge_offloads *br_offloads,
 				  struct netlink_ext_ack *extack)

index d6f5391619930..a4e59cc210894 100644
@@ -80,6 +80,8 @@ int mlx5_esw_bridge_vlan_proto_set(u16 vport_num, u16 esw_owner_vhca_id, u16 pro
 				   struct mlx5_esw_bridge_offloads *br_offloads);
 int mlx5_esw_bridge_mcast_set(u16 vport_num, u16 esw_owner_vhca_id, bool enable,
 			      struct mlx5_esw_bridge_offloads *br_offloads);
+bool mlx5_esw_bridge_port_exists(u16 vport_num, u16 esw_owner_vhca_id,
+				 struct mlx5_esw_bridge_offloads *br_offloads);
 int mlx5_esw_bridge_port_vlan_add(u16 vport_num, u16 esw_owner_vhca_id, u16 vid, u16 flags,
 				  struct mlx5_esw_bridge_offloads *br_offloads,
 				  struct netlink_ext_ack *extack);

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bernardo Soares <[email protected]>

[ Upstream commit 2e51097c982b7b22382fda3202ba29f0ea33e8c0 ]

mlx5_esw_bridge_vport_unlink() returns -EINVAL when the port isn't tracked by this instance's br_offloads. This is reachable on a sibling instance that registered its notifier after the port was already
enslaved: it never saw the NETDEV_CHANGEUPPER link event, so peer_link() never created a peer port for it, but it does see the later unlink event and fails. Return 0 instead, and give mlx5_esw_bridge_vport_peer_unlink() the same merged_eswitch capability guard peer_link() already has, since without it peer_link() likewise never creates a port to unlink.

This also matters beyond the -EINVAL itself:
mlx5_esw_bridge_switchdev_port_event() runs on the per-netns netdev_chain, and notifier_from_errno(-EINVAL) sets NOTIFY_STOP_MASK, which call_netdevice_notifiers_info() checks to stop calling further listeners on that chain - so the old -EINVAL silently dropped the event for any listener registered later on the same chain, even though none of it was visible to user space since __netdev_upper_dev_unlink() discards the return value.

---
 drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

index 695456c395039..88487e1a58878 100644
@@ -1649,10 +1649,8 @@ int mlx5_esw_bridge_vport_unlink(struct net_device *br_netdev, u16 vport_num,
 	int err;
 
 	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
-	if (!port) {
-		NL_SET_ERR_MSG_MOD(extack, "Port is not attached to any bridge");
-		return -EINVAL;
-	}
+	if (!port)
+		return 0;
 	if (port->bridge->ifindex != br_netdev->ifindex) {
 		NL_SET_ERR_MSG_MOD(extack, "Port is attached to another bridge");
 		return -EINVAL;

@@ -1682,6 +1680,9 @@ int mlx5_esw_bridge_vport_peer_unlink(struct net_device *br_netdev, u16 vport_nu
 				      struct mlx5_esw_bridge_offloads *br_offloads,
 				      struct netlink_ext_ack *extack)
 {
+	if (!MLX5_CAP_ESW(br_offloads->esw->dev, merged_eswitch))
+		return 0;
+
 	return mlx5_esw_bridge_vport_unlink(br_netdev, vport_num, esw_owner_vhca_id, br_offloads,
 					    extack);
 }

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xin Long <[email protected]>

[ Upstream commit cae23ae3f7887a1cf8a75da38edcebeef695040f ]

Take the association or transport reference before rearming a timer in the timer handlers.

The existing code calls mod_timer() before taking the reference needed by the rearmed timer without holding the sock lock. This creates a race with timer cleanup: if the timer is deleted after mod_timer() returns but before the reference is taken, the cleanup path can drop the timer's reference and destroy the transport or association. The timer handler then takes a reference on the already freed object and eventually drops it, causing a refcount underflow.

Hold the object before mod_timer() and drop the reference if mod_timer() reports that the timer was already pending in timer handlers. Apply the same ordering to the proto-unreachable path, which can rearm a transport timer outside the timer handlers without holding the sock lock.

---
 net/sctp/input.c         |  7 ++++---
 net/sctp/sm_sideeffect.c | 37 ++++++++++++++++++++++---------------
 2 files changed, 26 insertions(+), 18 deletions(-)

index 864741fae4187..9494cfa51106c 100644
@@ -436,9 +436,10 @@ void sctp_icmp_proto_unreachable(struct sock *sk,
 		if (timer_pending(&t->proto_unreach_timer))
 			return;
 		else {
-			if (!mod_timer(&t->proto_unreach_timer,
-						jiffies + (HZ/20)))
-				sctp_transport_hold(t);
+			sctp_transport_hold(t);
+			if (mod_timer(&t->proto_unreach_timer,
+				      jiffies + (HZ / 20)))
+				sctp_transport_put(t);
 		}
 	} else {
 		struct net *net = sock_net(sk);

index 0d99b7e8c082f..35f540fb15fc1 100644
@@ -244,8 +244,9 @@ void sctp_generate_t3_rtx_event(struct timer_list *t)
 		pr_debug("%s: sock is busy\n", __func__);
 
 		/* Try again later.  */
-		if (!mod_timer(&transport->T3_rtx_timer, jiffies + (HZ/20)))
-			sctp_transport_hold(transport);
+		sctp_transport_hold(transport);
+		if (mod_timer(&transport->T3_rtx_timer, jiffies + (HZ / 20)))
+			sctp_transport_put(transport);
 		goto out_unlock;
 	}
 

@@ -280,8 +281,9 @@ static void sctp_generate_timeout_event(struct sctp_association *asoc,
 			 timeout_type);
 
 		/* Try again later.  */
-		if (!mod_timer(&asoc->timers[timeout_type], jiffies + (HZ/20)))
-			sctp_association_hold(asoc);
+		sctp_association_hold(asoc);
+		if (mod_timer(&asoc->timers[timeout_type], jiffies + (HZ / 20)))
+			sctp_association_put(asoc);
 		goto out_unlock;
 	}
 

@@ -378,8 +380,9 @@ void sctp_generate_heartbeat_event(struct timer_list *t)
 		pr_debug("%s: sock is busy\n", __func__);
 
 		/* Try again later.  */
-		if (!mod_timer(&transport->hb_timer, jiffies + (HZ/20)))
-			sctp_transport_hold(transport);
+		sctp_transport_hold(transport);
+		if (mod_timer(&transport->hb_timer, jiffies + (HZ / 20)))
+			sctp_transport_put(transport);
 		goto out_unlock;
 	}
 

@@ -388,8 +391,9 @@ void sctp_generate_heartbeat_event(struct timer_list *t)
 	timeout = sctp_transport_timeout(transport);
 	if (elapsed < timeout) {
 		elapsed = timeout - elapsed;
-		if (!mod_timer(&transport->hb_timer, jiffies + elapsed))
-			sctp_transport_hold(transport);
+		sctp_transport_hold(transport);
+		if (mod_timer(&transport->hb_timer, jiffies + elapsed))
+			sctp_transport_put(transport);
 		goto out_unlock;
 	}
 

@@ -422,9 +426,10 @@ void sctp_generate_proto_unreach_event(struct timer_list *t)
 		pr_debug("%s: sock is busy\n", __func__);
 
 		/* Try again later.  */
-		if (!mod_timer(&transport->proto_unreach_timer,
-				jiffies + (HZ/20)))
-			sctp_transport_hold(transport);
+		sctp_transport_hold(transport);
+		if (mod_timer(&transport->proto_unreach_timer,
+			      jiffies + (HZ / 20)))
+			sctp_transport_put(transport);
 		goto out_unlock;
 	}
 

@@ -458,8 +463,9 @@ void sctp_generate_reconf_event(struct timer_list *t)
 		pr_debug("%s: sock is busy\n", __func__);
 
 		/* Try again later.  */
-		if (!mod_timer(&transport->reconf_timer, jiffies + (HZ / 20)))
-			sctp_transport_hold(transport);
+		sctp_transport_hold(transport);
+		if (mod_timer(&transport->reconf_timer, jiffies + (HZ / 20)))
+			sctp_transport_put(transport);
 		goto out_unlock;
 	}
 

@@ -495,8 +501,9 @@ void sctp_generate_probe_event(struct timer_list *t)
 		pr_debug("%s: sock is busy\n", __func__);
 
 		/* Try again later.  */
-		if (!mod_timer(&transport->probe_timer, jiffies + (HZ / 20)))
-			sctp_transport_hold(transport);
+		sctp_transport_hold(transport);
+		if (mod_timer(&transport->probe_timer, jiffies + (HZ / 20)))
+			sctp_transport_put(transport);
 		goto out_unlock;
 	}
 

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Maxime Chevallier <[email protected]>

[ Upstream commit d68acbf93531abdb5b02b21994cd4c15a3c95b42 ]

Most stmmac selftests rely on dev_add_pack() to add custom handlers, that validate the packets sent to ourselves through MAC loopback.

However, when the stmmac-driven interface is a DSA CPU conduit, all frames that are received have ETH_P_XDSA as a protocol, even though they don't actually contain any tag as they come from the loopback and not the switch.

This will prevent any incoming packet to match our packet handlers.

Let's register a ETH_P_ALL packet handler when we detect that we're a DSA conduit, and use a proxy packet handler to filter the h_proto.

As this allows external frames to be received through our .func(), the packet handler is added after the dev->addr field is populated in our selftest attributes.

Note that we may still receive incoming packets from the switch, but these frames shouldn't interfere with the very specific frames used for selftests, and stmmac selftests in general aren't safe against external traffic interferences.

This was validated on a WPQ864 devkit for IPQ8064, that has the SoC connected to a QCA8k switch.

The ARP offload's packet handler is left alone, this feature is just not implemented in stmmac and due for removal.

---
 .../stmicro/stmmac/stmmac_selftests.c         | 89 +++++++++++++++----
 1 file changed, 71 insertions(+), 18 deletions(-)

index 3f215ef3c89b7..1d46d5004c9f4 100644
@@ -13,6 +13,7 @@
 #include <linux/ip.h>
 #include <linux/phy.h>
 #include <linux/udp.h>
+#include <net/dsa.h>
 #include <net/pkt_cls.h>
 #include <net/pkt_sched.h>
 #include <net/tcp.h>

@@ -238,6 +239,9 @@ struct stmmac_test_priv {
 	struct stmmac_packet_attrs *packet;
 	struct packet_type pt;
 	struct completion comp;
+	__be16 packet_type;
+	int (*func)(struct sk_buff *skb, struct net_device *ndev,
+		    struct packet_type *pt, struct net_device *orig_ndev);
 	int double_vlan;
 	int vlan_id;
 	int ok;

@@ -317,6 +321,50 @@ static int stmmac_test_loopback_validate(struct sk_buff *skb,
 	return 0;
 }
 
+static int stmmac_sft_filter(struct sk_buff *skb, struct net_device *ndev,
+			     struct packet_type *pt,
+			     struct net_device *orig_ndev)
+{
+	struct stmmac_test_priv *tpriv = pt->af_packet_priv;
+	struct ethhdr *hdr = eth_hdr(skb);
+	int ret = 0;
+
+	if (hdr->h_proto == tpriv->packet_type) {
+		struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+
+		if (nskb)
+			ret = tpriv->func(nskb, ndev, pt, orig_ndev);
+	}
+
+	kfree_skb(skb);
+	return ret;
+}
+
+static void stmmac_sft_add_pack(struct packet_type *pt)
+{
+	struct stmmac_test_priv *tpriv = pt->af_packet_priv;
+
+	if (netdev_uses_dsa(tpriv->pt.dev)) {
+		tpriv->packet_type = tpriv->pt.type;
+		tpriv->func = tpriv->pt.func;
+
+		/* DSA conduit will report ETH_P_XDSA, so our packet handler
+		 * won't match. Let's register a ETH_P_ALL match and filter
+		 * manually in stmmac_sft_filter.
+		 */
+		tpriv->pt.type = htons(ETH_P_ALL);
+		tpriv->pt.func = stmmac_sft_filter;
+		tpriv->pt.ignore_outgoing = true;
+	}
+
+	dev_add_pack(pt);
+}
+
+static void stmmac_sft_remove_pack(struct packet_type *pt)
+{
+	dev_remove_pack(pt);
+}
+
 static int __stmmac_test_loopback(struct stmmac_priv *priv,
 				  struct stmmac_packet_attrs *attr)
 {

@@ -338,7 +386,7 @@ static int __stmmac_test_loopback(struct stmmac_priv *priv,
 	tpriv->packet = attr;
 
 	if (!attr->dont_wait)
-		dev_add_pack(&tpriv->pt);
+		stmmac_sft_add_pack(&tpriv->pt);
 
 	skb = stmmac_test_get_udp_skb(priv, attr);
 	if (!skb) {

@@ -361,7 +409,7 @@ static int __stmmac_test_loopback(struct stmmac_priv *priv,
 
 cleanup:
 	if (!attr->dont_wait)
-		dev_remove_pack(&tpriv->pt);
+		stmmac_sft_remove_pack(&tpriv->pt);
 	kfree(tpriv);
 	return ret;
 }

@@ -775,7 +823,7 @@ static int stmmac_test_flowctrl(struct stmmac_priv *priv)
 	tpriv->pt.func = stmmac_test_flowctrl_validate;
 	tpriv->pt.dev = priv->dev;
 	tpriv->pt.af_packet_priv = tpriv;
-	dev_add_pack(&tpriv->pt);
+	stmmac_sft_add_pack(&tpriv->pt);
 
 	/* Compute minimum number of packets to make FIFO full */
 	pkt_count = priv->plat->rx_fifo_size;

@@ -833,7 +881,7 @@ static int stmmac_test_flowctrl(struct stmmac_priv *priv)
 cleanup:
 	dev_mc_del(priv->dev, paddr);
 	dev_set_promiscuity(priv->dev, -1);
-	dev_remove_pack(&tpriv->pt);
+	stmmac_sft_remove_pack(&tpriv->pt);
 	kfree(tpriv);
 	return ret;
 }

@@ -938,18 +986,20 @@ static int __stmmac_test_vlanfilt(struct stmmac_priv *priv)
 	 * HASH values.
 	 */
 	tpriv->vlan_id = 0x123;
-	dev_add_pack(&tpriv->pt);
 
 	ret = vlan_vid_add(priv->dev, htons(ETH_P_8021Q), tpriv->vlan_id);
 	if (ret)
 		goto cleanup;
 
+	attr.vlan = 1;
+	attr.dst = priv->dev->dev_addr;
+	attr.sport = 9;
+	attr.dport = 9;
+
+	stmmac_sft_add_pack(&tpriv->pt);
+
 	for (i = 0; i < 4; i++) {
-		attr.vlan = 1;
 		attr.vlan_id_out = tpriv->vlan_id + i;
-		attr.dst = priv->dev->dev_addr;
-		attr.sport = 9;
-		attr.dport = 9;
 
 		skb = stmmac_test_get_udp_skb(priv, &attr);
 		if (!skb) {

@@ -976,9 +1026,9 @@ static int __stmmac_test_vlanfilt(struct stmmac_priv *priv)
 	}
 
 vlan_del:
+	stmmac_sft_remove_pack(&tpriv->pt);
 	vlan_vid_del(priv->dev, htons(ETH_P_8021Q), tpriv->vlan_id);
 cleanup:
-	dev_remove_pack(&tpriv->pt);
 	kfree(tpriv);
 	return ret;
 }

@@ -1032,18 +1082,20 @@ static int __stmmac_test_dvlanfilt(struct stmmac_priv *priv)
 	 * HASH values.
 	 */
 	tpriv->vlan_id = 0x123;
-	dev_add_pack(&tpriv->pt);
 
 	ret = vlan_vid_add(priv->dev, htons(ETH_P_8021AD), tpriv->vlan_id);
 	if (ret)
 		goto cleanup;
 
+	attr.vlan = 2;
+	attr.dst = priv->dev->dev_addr;
+	attr.sport = 9;
+	attr.dport = 9;
+
+	stmmac_sft_add_pack(&tpriv->pt);
+
 	for (i = 0; i < 4; i++) {
-		attr.vlan = 2;
 		attr.vlan_id_out = tpriv->vlan_id + i;
-		attr.dst = priv->dev->dev_addr;
-		attr.sport = 9;
-		attr.dport = 9;
 
 		skb = stmmac_test_get_udp_skb(priv, &attr);
 		if (!skb) {

@@ -1070,9 +1122,9 @@ static int __stmmac_test_dvlanfilt(struct stmmac_priv *priv)
 	}
 
 vlan_del:
+	stmmac_sft_remove_pack(&tpriv->pt);
 	vlan_vid_del(priv->dev, htons(ETH_P_8021AD), tpriv->vlan_id);
 cleanup:
-	dev_remove_pack(&tpriv->pt);
 	kfree(tpriv);
 	return ret;
 }

@@ -1303,7 +1355,6 @@ static int stmmac_test_vlanoff_common(struct stmmac_priv *priv, bool svlan)
 	tpriv->pt.af_packet_priv = tpriv;
 	tpriv->packet = &attr;
 	tpriv->vlan_id = 0x123;
-	dev_add_pack(&tpriv->pt);
 
 	ret = vlan_vid_add(priv->dev, htons(proto), tpriv->vlan_id);
 	if (ret)

@@ -1311,6 +1362,8 @@ static int stmmac_test_vlanoff_common(struct stmmac_priv *priv, bool svlan)
 
 	attr.dst = priv->dev->dev_addr;
 
+	stmmac_sft_add_pack(&tpriv->pt);
+
 	skb = stmmac_test_get_udp_skb(priv, &attr);
 	if (!skb) {
 		ret = -ENOMEM;

@@ -1328,9 +1381,9 @@ static int stmmac_test_vlanoff_common(struct stmmac_priv *priv, bool svlan)
 	ret = tpriv->ok ? 0 : -ETIMEDOUT;
 
 vlan_del:
+	stmmac_sft_remove_pack(&tpriv->pt);
 	vlan_vid_del(priv->dev, htons(proto), tpriv->vlan_id);
 cleanup:
-	dev_remove_pack(&tpriv->pt);
 	kfree(tpriv);
 	return ret;
 }

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Maxime Chevallier <[email protected]>

[ Upstream commit ba804b23d76d278ee475b8427fa7c5623ce5e270 ]

The S-TAG offload insertion incorrectly checks the dvlan (double vlan) DMA cap, which is different than S-TAG support. Use NETIF_F_HW_VLAN_STAG_TX to check if the feature is supported instead.

Note that this flag isn't set in stmmac yet, but contrary to ARP offload, this is a feature that has a chance to get there eventually so let's leave the selftest here for now. It'll report -EOPNOTSUPP in the meantime.

---
 drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 1d46d5004c9f4..71455457b0f3c 100644
@@ -1395,7 +1395,7 @@ static int stmmac_test_vlanoff(struct stmmac_priv *priv)
 
 static int stmmac_test_svlanoff(struct stmmac_priv *priv)
 {
-	if (!priv->dma_cap.dvlan)
+	if (!(priv->dev->features & NETIF_F_HW_VLAN_STAG_TX))
 		return -EOPNOTSUPP;
 	return stmmac_test_vlanoff_common(priv, true);
 }

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Maxime Chevallier <[email protected]>

[ Upstream commit 960db6f65788c21249ea04a947d5c01e38d19294 ]

While we use vlan_vid_add to trigger the tag filtering machinery in the driver, there's no netdev associated to the VLAN. This causes the skb to arrive with empty skb->vlan_tci fields, as the packet is marked OTHERHOST in __netif_receive_skb_core(), and we fail our validation.

Let's use the proxy mechanism introduced for DSA, that registers a ETH_P_ALL packet handler that runs earlier, before the vlan netdev lookup, then filters for the correct ethertype before passing an skb clone to our validation function.

As we may receive external frames with the right tag from the outside, let's move the address check in the vlan validation function earlier.

---
 .../stmicro/stmmac/stmmac_selftests.c         | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

index 71455457b0f3c..bd92d5b051953 100644
@@ -242,6 +242,7 @@ struct stmmac_test_priv {
 	__be16 packet_type;
 	int (*func)(struct sk_buff *skb, struct net_device *ndev,
 		    struct packet_type *pt, struct net_device *orig_ndev);
+	bool capture_all;
 	int double_vlan;
 	int vlan_id;
 	int ok;

@@ -344,13 +345,15 @@ static void stmmac_sft_add_pack(struct packet_type *pt)
 {
 	struct stmmac_test_priv *tpriv = pt->af_packet_priv;
 
-	if (netdev_uses_dsa(tpriv->pt.dev)) {
+	if (netdev_uses_dsa(tpriv->pt.dev) || tpriv->capture_all) {
 		tpriv->packet_type = tpriv->pt.type;
 		tpriv->func = tpriv->pt.func;
 
 		/* DSA conduit will report ETH_P_XDSA, so our packet handler
 		 * won't match. Let's register a ETH_P_ALL match and filter
-		 * manually in stmmac_sft_filter.
+		 * manually in stmmac_sft_filter. This is also useful for
+		 * VLAN tests, to capture packets otherwise marked as
+		 * OTHERHOST.
 		 */
 		tpriv->pt.type = htons(ETH_P_ALL);
 		tpriv->pt.func = stmmac_sft_filter;

@@ -923,6 +926,11 @@ static int stmmac_test_vlan_validate(struct sk_buff *skb,
 		goto out;
 	if (skb_headlen(skb) < (STMMAC_TEST_PKT_SIZE - ETH_HLEN))
 		goto out;
+
+	ehdr = (struct ethhdr *)skb_mac_header(skb);
+	if (!ether_addr_equal_unaligned(ehdr->h_dest, tpriv->packet->dst))
+		goto out;
+
 	if (tpriv->vlan_id) {
 		if (skb->vlan_proto != htons(proto))
 			goto out;

@@ -934,10 +942,6 @@ static int stmmac_test_vlan_validate(struct sk_buff *skb,
 		}
 	}
 
-	ehdr = (struct ethhdr *)skb_mac_header(skb);
-	if (!ether_addr_equal_unaligned(ehdr->h_dest, tpriv->packet->dst))
-		goto out;
-
 	ihdr = ip_hdr(skb);
 	if (tpriv->double_vlan)
 		ihdr = (struct iphdr *)(skb_network_header(skb) + 4);

@@ -979,6 +983,7 @@ static int __stmmac_test_vlanfilt(struct stmmac_priv *priv)
 	tpriv->pt.dev = priv->dev;
 	tpriv->pt.af_packet_priv = tpriv;
 	tpriv->packet = &attr;
+	tpriv->capture_all = true;
 
 	/*
 	 * As we use HASH filtering, false positives may appear. This is a

@@ -1075,6 +1080,7 @@ static int __stmmac_test_dvlanfilt(struct stmmac_priv *priv)
 	tpriv->pt.dev = priv->dev;
 	tpriv->pt.af_packet_priv = tpriv;
 	tpriv->packet = &attr;
+	tpriv->capture_all = true;
 
 	/*
 	 * As we use HASH filtering, false positives may appear. This is a

@@ -1355,6 +1361,7 @@ static int stmmac_test_vlanoff_common(struct stmmac_priv *priv, bool svlan)
 	tpriv->pt.af_packet_priv = tpriv;
 	tpriv->packet = &attr;
 	tpriv->vlan_id = 0x123;
+	tpriv->capture_all = true;
 
 	ret = vlan_vid_add(priv->dev, htons(proto), tpriv->vlan_id);
 	if (ret)

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Maxime Chevallier <[email protected]>

[ Upstream commit b42e7012773a0e81e97a2dda6ef907f5147a6658 ]

DMA bufsize selection isn't made on the MTU but the actual frame length, so including the L2 header. On DWMAC4, if the len is exactly BUF_SIZE_8KiB, the next larger size is incorrectly selected.

Lets fix the comparison and while at it, rename the parameter from len to mtu.

---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c | 4 ++--
 drivers/net/ethernet/stmicro/stmmac/hwif.h         | 2 +-
 drivers/net/ethernet/stmicro/stmmac/ring_mode.c    | 4 ++--
 3 files changed, 5 insertions(+), 5 deletions(-)

index aac68dc28dc19..2c63229bfb1a8 100644
@@ -496,11 +496,11 @@ static void dwmac4_set_sarc(struct dma_desc *p, u32 sarc_type)
 	p->des3 |= cpu_to_le32(sarc_type & TDES3_SA_INSERT_CTRL_MASK);
 }
 
-static int set_16kib_bfsize(int mtu)
+static int set_16kib_bfsize(int len)
 {
 	int ret = 0;
 
-	if (unlikely(mtu >= BUF_SIZE_8KiB))
+	if (unlikely(len > BUF_SIZE_8KiB))
 		ret = BUF_SIZE_16KiB;
 	return ret;
 }

index 75e915e86c789..ba36f1aa8c8a4 100644
@@ -536,7 +536,7 @@ struct stmmac_mode_ops {
 	unsigned int (*is_jumbo_frm) (int len, int ehn_desc);
 	int (*jumbo_frm)(struct stmmac_tx_queue *tx_q, struct sk_buff *skb,
 			 int csum);
-	int (*set_16kib_bfsize)(int mtu);
+	int (*set_16kib_bfsize)(int len);
 	void (*init_desc3)(struct dma_desc *p);
 	void (*refill_desc3)(struct stmmac_rx_queue *rx_q, struct dma_desc *p);
 	void (*clean_desc3)(struct stmmac_tx_queue *tx_q, struct dma_desc *p);

index 45c14c1bb0eaa..88a8d22812f5d 100644
@@ -128,10 +128,10 @@ static void clean_desc3(struct stmmac_tx_queue *tx_q, struct dma_desc *p)
 		p->des3 = 0;
 }
 
-static int set_16kib_bfsize(int mtu)
+static int set_16kib_bfsize(int len)
 {
 	int ret = 0;
-	if (unlikely(mtu > BUF_SIZE_8KiB))
+	if (unlikely(len > BUF_SIZE_8KiB))
 		ret = BUF_SIZE_16KiB;
 	return ret;
 }

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Maxime Chevallier <[email protected]>

[ Upstream commit c4ac6e94eb9423126bda907a7f2933284f7450ff ]

On dwmac1000, we currently only support single-descriptor frames. The Jumbo test started failing when NET_IP_ALIGN was added to align the IP header, as this tests tries to send the biggest possible frame.

On dwmac1000 the DMA transfer is aligned on 4-bytes, so adding a 2-byte shift at the start-of-buffer address means it takes a whole extra 4-byte DMA burst to receive the Jumbo packet, causing it to spill over the next descriptor.

This doesn't seem to happen on dwmac4 and xgmac that appear to correctly handle unaligned xfers (only tested on dwmac4)

Let's account for that in the Jumbo test, reduce the size of our big packet by the align size.

---
 drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c | 3 +++
 1 file changed, 3 insertions(+)

index bd92d5b051953..a2f99e2cb43b5 100644
@@ -1769,6 +1769,9 @@ static int __stmmac_test_jumbo(struct stmmac_priv *priv, u16 queue)
 	struct stmmac_packet_attrs attr = { };
 	int size = priv->dma_conf.dma_buf_sz;
 
+	if (!dwmac_is_xmac(priv->plat->core_type))
+		size -= NET_IP_ALIGN;
+
 	attr.dst = priv->dev->dev_addr;
 	attr.max_size = size - ETH_FCS_LEN;
 	attr.queue_mapping = queue;

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Björn Töpel <[email protected]>

[ Upstream commit 0160953d8eec75c3c55562158c46442ff1fd410b ]

roundup_pow_of_two() is undefined for zero. ethtool permits a zero ring size to reach the driver, where the minimum-size check should reject it.

Leave zero unchanged while rounding nonzero ring sizes. The minimum-size check then rejects zero deterministically without changing the established behavior for other values.

---
 drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

index 08aed4103323e..d67be9f1a575f 100644
@@ -299,6 +299,11 @@ fbnic_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
 	kernel_ring->hds_thresh = fbn->hds_thresh;
 }
 
+static u32 fbnic_ring_size_pow2(u32 size)
+{
+	return size ? roundup_pow_of_two(size) : 0;
+}
+
 static void fbnic_set_rings(struct fbnic_net *fbn,
 			    struct ethtool_ringparam *ring,
 			    struct kernel_ethtool_ringparam *kernel_ring)

@@ -320,10 +325,10 @@ fbnic_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
 	struct fbnic_net *clone;
 	int err;
 
-	ring->rx_pending	= roundup_pow_of_two(ring->rx_pending);
-	ring->rx_mini_pending	= roundup_pow_of_two(ring->rx_mini_pending);
-	ring->rx_jumbo_pending	= roundup_pow_of_two(ring->rx_jumbo_pending);
-	ring->tx_pending	= roundup_pow_of_two(ring->tx_pending);
+	ring->rx_pending	= fbnic_ring_size_pow2(ring->rx_pending);
+	ring->rx_mini_pending	= fbnic_ring_size_pow2(ring->rx_mini_pending);
+	ring->rx_jumbo_pending	= fbnic_ring_size_pow2(ring->rx_jumbo_pending);
+	ring->tx_pending	= fbnic_ring_size_pow2(ring->tx_pending);
 
 	/* These are absolute minimums allowing the device and driver to operate
 	 * but not necessarily guarantee reasonable performance. Settings below

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bernard Ladenthin <[email protected]>

[ Upstream commit 9c572a83037a7dcd653ba3a9cc468c16b857d0c9 ]

em_text_dump() allocates struct tcf_em_text on the stack without zeroing it. strscpy() writes the algorithm name and a NUL terminator into conf.algo[], leaving the remaining bytes uninitialised. nla_put_nohdr() then copies the full struct to the netlink response.

KMSAN on Linux 7.2-rc6 reports two kernel-infoleak splats from this path, one triggered via "tc filter show" and one via a raw RTM_GETTFILTER dump:

  BUG: KMSAN: kernel-infoleak in _copy_to_iter+0x1c9/0x2620
    nla_put_nohdr+0x83/0x130
    em_text_dump+0x291/0x550
  Local variable conf created at: em_text_dump+0x5d/0x550
  Bytes 168-179 of 199 are uninitialized

I am not certain whether this constitutes a real security problem in
practice: the test was conducted in a controlled KMSAN environment and the leaked stack bytes may or may not carry sensitive data on actual production kernels. I am reporting it because KMSAN flagged it as a kernel-infoleak and the fix is straightforward. I can provide a userspace reproducer on request.

The original code used strncpy() which zero-pads to the destination size. Commit b04202d6065c ("net/sched: replace strncpy with strscpy") replaced it with strscpy(), which does not pad, creating this condition. Zero-initialising the struct closes it.

---
 net/sched/em_text.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 692e2be1793e9..8052c55b2f4d0 100644
@@ -113,7 +113,7 @@ static void em_text_destroy(struct tcf_ematch *m)
 static int em_text_dump(struct sk_buff *skb, struct tcf_ematch *m)
 {
 	struct text_match *tm = EM_TEXT_PRIV(m);
-	struct tcf_em_text conf;
+	struct tcf_em_text conf = {};
 
 	strscpy(conf.algo, tm->config->ops->name);
 	conf.from_offset = tm->from_offset;

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Weiming Shi <[email protected]>

[ Upstream commit 6db1ce73e9853f533eb7f413f14ba00f8ec6f80d ]

__bpf_offload_dev_match() falls back to comparing offdev pointers after an exact netdev mismatch. Bound-only programs normally have NULL offdevs, so unrelated netdevs compare equal. A bound-only program on an offload-registered netdev can instead inherit a real offdev and match a sibling port. With CAP_BPF and CAP_NET_ADMIN, a caller can use bpf(BPF_LINK_CREATE) with a different target ifindex to run metadata kfuncs specialized for the bound driver on the target driver's xdp_buff. Running a veth-bound program on tun reads beyond tun's bare stack xdp_buff as a veth_xdp_buff.

  Oops: general protection fault, probably for non-canonical address
  KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017]
  RIP: 0010:veth_xdp_rx_timestamp (drivers/net/veth.c:1673)
  Call Trace:
   ...
   tun_build_skb (drivers/net/tun.c:1739)
   tun_get_user (drivers/net/tun.c:1856)
   tun_chr_write_iter (drivers/net/tun.c:2091)
   vfs_write (fs/read_write.c:595 fs/read_write.c:687)
   ksys_write (fs/read_write.c:739)
   do_syscall_64 (arch/x86/entry/syscall_64.c:84)
   entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:121)
  Kernel panic - not syncing: Fatal exception in interrupt

Restrict non-offloaded programs to exact netdev matches and retain the shared-offdev fallback only for genuinely offloaded multi-port programs.

---
 kernel/bpf/offload.c | 2 ++
 1 file changed, 2 insertions(+)

index a9a036547c960..884f1eeaba2ef 100644
@@ -708,6 +708,8 @@ static bool __bpf_offload_dev_match(struct bpf_prog *prog,
 		return false;
 	if (offload->netdev == netdev)
 		return true;
+	if (!bpf_prog_is_offloaded(prog->aux))
+		return false;
 
 	ondev1 = bpf_offload_find_netdev(offload->netdev);
 	ondev2 = bpf_offload_find_netdev(netdev);

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pengpeng Hou <[email protected]>

[ Upstream commit 686f942332b1667f13f3b8d6a2f50bcfbf42e277 ]

The firmware download receive path removes the NCI data header and reads the helper command before validating the remaining packet length. A short frame can therefore reach the data access before the malformed packet is rejected.

Validate the complete helper command length before stripping the NCI data header.

---
 drivers/nfc/nfcmrvl/fw_dnld.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

index a9b03dcc41006..2b734c1c1d1f9 100644
@@ -263,9 +263,14 @@ static int process_state_fw_dnld(struct nfcmrvl_private *priv,
 		 * B8..N: payload
 		 */
 
-		/* Remove NCI HDR */
-		skb_pull(skb, 3);
-		if (skb->data[0] != HELPER_CMD_PACKET_FORMAT || skb->len != 5) {
+		if (skb->len != NCI_DATA_HDR_SIZE + 5) {
+			nfc_err(priv->dev, "bad command");
+			return -EINVAL;
+		}
+
+		/* Remove NCI header */
+		skb_pull(skb, NCI_DATA_HDR_SIZE);
+		if (skb->data[0] != HELPER_CMD_PACKET_FORMAT) {
 			nfc_err(priv->dev, "bad command");
 			return -EINVAL;
 		}

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pengpeng Hou <[email protected]>

[ Upstream commit a653c01ce447f10c36b901646888c0330363af4f ]

st21nfca_hci_i2c_repack() trims a received frame at its EOF marker before removing byte stuffing. It then assumes the truncated frame contains the LLC header and two CRC bytes, and it unconditionally reads the byte after an escape marker.

A malformed frame can place EOF immediately after the start marker or can end its data portion with an escape marker. The former leaves too few bytes for check_crc(), while the latter makes the unstuffing loop read past the current skb length.

Require the minimum framing bytes both before and after unstuffing. Use separate input and output cursors while removing byte stuffing, and reject an escape marker without its encoded byte. This keeps malformed frames within the received frame boundary before CRC processing.

---
 drivers/nfc/st21nfca/i2c.c | 29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

index 6d78613838068..58f07725cc5f9 100644
@@ -289,27 +289,36 @@ static int check_crc(u8 *buf, int buflen)
  */
 static int st21nfca_hci_i2c_repack(struct sk_buff *skb)
 {
-	int i, j, r, size;
+	int read, write, r, size;
 
-	if (skb->len < 1 || (skb->len > 1 && skb->data[1] != 0))
+	if (skb->len < ST21NFCA_FRAME_HEADROOM ||
+	    !IS_START_OF_FRAME(skb->data))
 		return -EBADMSG;
 
 	size = get_frame_size(skb->data, skb->len);
 	if (size > 0) {
+		if (size < ST21NFCA_FRAME_HEADROOM + 2)
+			return -EBADMSG;
+
 		skb_trim(skb, size);
 		/* remove ST21NFCA byte stuffing for upper layer */
-		for (i = 1, j = 0; i < skb->len; i++) {
-			if (skb->data[i + j] ==
+		for (read = 1, write = 1; read < skb->len;) {
+			if (skb->data[read] ==
 					(u8) ST21NFCA_ESCAPE_BYTE_STUFFING) {
-				skb->data[i] = skb->data[i + j + 1]
-						| ST21NFCA_BYTE_STUFFING_MASK;
-				i++;
-				j++;
+				if (read + 1 == skb->len)
+					return -EBADMSG;
+
+				skb->data[write++] = skb->data[read + 1]
+						     | ST21NFCA_BYTE_STUFFING_MASK;
+				read += 2;
+			} else {
+				skb->data[write++] = skb->data[read++];
 			}
-			skb->data[i] = skb->data[i + j];
 		}
 		/* remove byte stuffing useless byte */
-		skb_trim(skb, i - j);
+		skb_trim(skb, write);
+		if (skb->len < ST21NFCA_FRAME_HEADROOM + 2)
+			return -EBADMSG;
 		/* remove ST21NFCA_SOF_EOF from head */
 		skb_pull(skb, 1);
 

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Aldo Ariel Panzardo <[email protected]>

[ Upstream commit bf1460acdf8cf5a07c819f59785d40f20d113099 ]

nfc_llcp_recv_dm() handles DM(NOBOUND)/DM(REJ) for a socket that is still linked on local->connecting_sockets: it looks the socket up with nfc_llcp_connecting_sock_get(), sets sk->sk_state = LLCP_CLOSED and returns, without taking the socket lock and without unlinking the socket from the connecting_sockets list.

llcp_sock_release() selects the list to unlink from by sk_state: a socket in LLCP_CONNECTING is unlinked from connecting_sockets, otherwise from the sockets list. Because recv_dm left the socket physically on connecting_sockets but in the LLCP_CLOSED state, release() takes the else branch and calls nfc_llcp_sock_unlink(&local->sockets, sk). That runs sk_del_node_init() while holding sockets.lock, i.e. it removes the socket from the connecting_sockets hlist under the wrong lock. A concurrent connect() linking another socket onto connecting_sockets under connecting_sockets.lock then mutates the same hlist unserialized, which corrupts the list and desyncs the sk_add_node()/sk_del_node_init() sock_hold()/__sock_put() pairing. An unprivileged local process holding LLCP sockets, with the DM supplied by the remote peer over an established LLCP link, can drive this to leak kernel sockets without bound (the mis-decrement goes through the non-freeing __sock_put() path, so the object is never released), leading to memory exhaustion / DoS.

This is the same class of bug that was fixed in the sibling handler nfc_llcp_recv_cc() by commit b493ea2765cc ("nfc: llcp: Fix use-after-free race in nfc_llcp_recv_cc()"); recv_dm did not receive the equivalent fix.

Fix it the same way: take lock_sock(), re-check that the socket is still hashed (release() may have won the race), and for the NOBOUND/REJ case unlink it from connecting_sockets before moving it to LLCP_CLOSED. The unlink drops the connecting_sockets membership reference via sk_del_node_init(), leaving the socket unhashed, so the later nfc_llcp_sock_unlink() in llcp_sock_release() becomes a no-op and no double put occurs.

---
 net/nfc/llcp_core.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

index 41f8e2f7875a0..dbba2e3ee7443 100644
@@ -1251,6 +1251,7 @@ static void nfc_llcp_recv_dm(struct nfc_llcp_local *local,
 	struct nfc_llcp_sock *llcp_sock;
 	struct sock *sk;
 	u8 dsap, ssap, reason;
+	bool connecting = false;
 
 	dsap = nfc_llcp_dsap(skb);
 	ssap = nfc_llcp_ssap(skb);

@@ -1262,6 +1263,7 @@ static void nfc_llcp_recv_dm(struct nfc_llcp_local *local,
 	case LLCP_DM_NOBOUND:
 	case LLCP_DM_REJ:
 		llcp_sock = nfc_llcp_connecting_sock_get(local, dsap);
+		connecting = true;
 		break;
 
 	default:

@@ -1276,10 +1278,33 @@ static void nfc_llcp_recv_dm(struct nfc_llcp_local *local,
 
 	sk = &llcp_sock->sk;
 
+	lock_sock(sk);
+
+	/* Check if socket was destroyed whilst waiting for the lock */
+	if (!sk_hashed(sk)) {
+		release_sock(sk);
+		nfc_llcp_sock_put(llcp_sock);
+		return;
+	}
+
+	/*
+	 * For DM(NOBOUND)/DM(REJ) the socket is still linked on the
+	 * connecting_sockets list.  Unlink it here, under the socket lock,
+	 * before moving it to LLCP_CLOSED: llcp_sock_release() selects the
+	 * list to unlink from by sk_state, so leaving a connecting socket
+	 * in the CLOSED state would make it unlink from the wrong list and
+	 * corrupt the connecting_sockets list / desync the socket refcount.
+	 * This mirrors nfc_llcp_recv_cc().
+	 */
+	if (connecting)
+		nfc_llcp_sock_unlink(&local->connecting_sockets, sk);
+
 	sk->sk_err = ENXIO;
 	sk->sk_state = LLCP_CLOSED;
 	sk->sk_state_change(sk);
 
+	release_sock(sk);
+
 	nfc_llcp_sock_put(llcp_sock);
 }
 

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Lei Zhu <[email protected]>

[ Upstream commit 3d8afc5243ea2ee803d98e69eb4a01748167ac1b ]

The pthread_create() functions returns 0 on success and a positive value on failure. Modify the return value check to correctly detect failure cases.

---
 tools/testing/selftests/nci/nci_dev.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

index 6dec59d64083d..8e09623d96a76 100644
@@ -438,7 +438,7 @@ FIXTURE_SETUP(NCI)
 	else
 		rc = pthread_create(&thread_t, NULL, virtual_dev_open,
 				    (void *)&self->virtual_nci_fd);
-	ASSERT_GT(rc, -1);
+	ASSERT_EQ(rc, 0);
 
 	rc = send_cmd_with_idx(self->sd, self->fid, self->pid,
 			       NFC_CMD_DEV_UP, self->dev_idex);

@@ -509,7 +509,7 @@ FIXTURE_TEARDOWN(NCI)
 			rc = pthread_create(&thread_t, NULL, virtual_deinit,
 					    (void *)&self->virtual_nci_fd);
 
-		ASSERT_GT(rc, -1);
+		ASSERT_EQ(rc, 0);
 		rc = send_cmd_with_idx(self->sd, self->fid, self->pid,
 				       NFC_CMD_DEV_DOWN, self->dev_idex);
 		EXPECT_EQ(rc, 0);

@@ -590,7 +590,7 @@ int start_polling(int dev_idx, int proto, int virtual_fd, int sd, int fid, int p
 
 	rc = pthread_create(&thread_t, NULL, virtual_poll_start,
 			    (void *)&virtual_fd);
-	if (rc < 0)
+	if (rc)
 		return rc;
 
 	rc = send_cmd_mt_nla(sd, fid, pid, NFC_CMD_START_POLL, 2, nla_start_poll_type,

@@ -610,7 +610,7 @@ int stop_polling(int dev_idx, int virtual_fd, int sd, int fid, int pid)
 
 	rc = pthread_create(&thread_t, NULL, virtual_poll_stop,
 			    (void *)&virtual_fd);
-	if (rc < 0)
+	if (rc)
 		return rc;
 
 	rc = send_cmd_with_idx(sd, fid, pid,

@@ -830,6 +830,8 @@ int disconnect_tag(int nfc_sock, int virtual_fd)
 
 	status = pthread_create(&thread_t, NULL, virtual_deactivate_proc,
 				(void *)&virtual_fd);
+	if (status)
+		return status;
 
 	close(nfc_sock);
 	pthread_join(thread_t, (void **)&status);

@@ -874,7 +876,7 @@ TEST_F(NCI, deinit)
 	else
 		rc = pthread_create(&thread_t, NULL, virtual_deinit,
 				    (void *)&self->virtual_nci_fd);
-	ASSERT_GT(rc, -1);
+	ASSERT_EQ(rc, 0);
 
 	rc = send_cmd_with_idx(self->sd, self->fid, self->pid,
 			       NFC_CMD_DEV_DOWN, self->dev_idex);

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Lee Jones <[email protected]>

[ Upstream commit c3eef2f988a3db9690369d7cef9a3344dd9788d3 ]

In nfc_llcp_socket_release(), sockets and listener accept queues are walked under the local sockets rwlock and bh_lock_sock(). However, bh_lock_sock() does not synchronise against process-context lock_sock() held by nfc_llcp_accept_dequeue() during accept(). Because socket_release() does not check sock_owned_by_user(), both paths can concurrently unlink and release the same child socket, resulting in use-after-free or a NULL pointer dereference of child->parent in nfc_llcp_accept_unlink().

Fix this synchronisation race by having nfc_llcp_socket_release() use process-context lock_sock() instead of bh_lock_sock():

1. Pop sockets from the local sockets list under the write lock using nfc_llcp_sock_list_pop() so lock_sock() can be acquired without holding the rwlock.

2. Because lock_sock() can sleep, defer the final release of the nfc_llcp_local structure to a workqueue (release_work). This avoids a sleeping-in-atomic bug when the last local reference is dropped from softirq context. Additionally, hold a single device reference on local from registration until final destruction.

3. In nfc_llcp_local_get(), use kref_get_unless_zero() to prevent resurrecting a local object whose teardown has been scheduled.

4. In llcp_sock_accept(), verify that the listener socket state is still LLCP_LISTEN after waking from schedule_timeout() to prevent hangs if the listener is closed concurrently.

5. When unlinking unaccepted child sockets during listener release, unlink them from local->sockets, call sock_orphan(), and drop their initial sk_alloc creation reference via sock_put().

6. Make nfc_llcp_accept_unlink() idempotent by guarding parent access with a NULL check.

---
 net/nfc/llcp.h      |   1 +
 net/nfc/llcp_core.c | 125 +++++++++++++++++++++++++++-----------------
 net/nfc/llcp_sock.c |  49 ++++++++++++-----
 3 files changed, 116 insertions(+), 59 deletions(-)

index d8345ed57c954..23ae7a0112d37 100644
@@ -91,6 +91,7 @@ struct nfc_llcp_local {
 	struct hlist_head pending_sdreqs;
 	struct timer_list sdreq_timer;
 	struct work_struct sdreq_timeout_work;
+	struct work_struct release_work;
 	u8 sdreq_next_tid;
 
 	/* sockets array */

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chaithanya Lagisetty <[email protected]>

[ Upstream commit eda518d2cdb6074a0bcdfa06af291616bcb5c421 ]

get_family_id() walks the generic netlink CTRL_CMD_GETFAMILY reply looking for the CTRL_ATTR_FAMILY_ID attribute and returns the parsed value in the local variable "id". If the reply does not carry that attribute, the parsing loop never assigns "id" and the function returns an indeterminate stack value, which the caller stores in self->fid and uses for subsequent netlink requests.

Initialize "id" to 0 so a missing attribute yields a deterministic (invalid) family ID instead of a garbage value.

---
 tools/testing/selftests/nci/nci_dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 8e09623d96a76..cc0732d439e02 100644
@@ -182,7 +182,7 @@ static int get_family_id(int sd, __u32 pid, __u32 *event_group)
 	} ans;
 	struct nlattr *na;
 	int resp_len;
-	__u16 id;
+	__u16 id = 0;
 	int len;
 	int rc;
 

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chris Gellermann <[email protected]>

[ Upstream commit 6be581aeffc215bfc77939cd59902b0dbc4af23e ]

The NCI test collects the exit status of its helper threads by passing the address of an int to pthread_join():

	int status;
	...
	pthread_join(thread_t, (void **) &status);

pthread_join() stores a void pointer to the memory location. On 64-bit systems, a void pointer is wider than an int, so the store overruns the 4 bytes of space allocated on the stack for the integer and corrupts the adjacent stack. On our CHERI system, this caused a fault due to a capability bounds violation.

Fix this by introducing a helper that joins a thread through a void pointer and converts the result back to an integer, which is what the helper threads return.

While here, also fix the logic in disconnect_tag() if the helper thread creation failed. Previously, it would have joined a thread that was never created when pthread_create() failed.

---
 tools/testing/selftests/nci/nci_dev.c | 31 +++++++++++++++++----------
 1 file changed, 20 insertions(+), 11 deletions(-)

index cc0732d439e02..ae9c2216860b0 100644
@@ -8,6 +8,7 @@
 
 #include <stdlib.h>
 #include <errno.h>
+#include <stdint.h>
 #include <string.h>
 #include <sys/ioctl.h>
 #include <fcntl.h>

@@ -87,6 +88,16 @@ struct msgtemplate {
 	char buf[MAX_MSG_SIZE];
 };
 
+static int join_thread_status(pthread_t thread)
+{
+	void *thread_ret = NULL;
+
+	if (pthread_join(thread, &thread_ret))
+		return -1;
+
+	return (int)(intptr_t)thread_ret;
+}
+
 static int create_nl_socket(void)
 {
 	int fd;

@@ -444,7 +455,7 @@ FIXTURE_SETUP(NCI)
 			       NFC_CMD_DEV_UP, self->dev_idex);
 	EXPECT_EQ(rc, 0);
 
-	pthread_join(thread_t, (void **)&status);
+	status = join_thread_status(thread_t);
 	ASSERT_EQ(status, 0);
 	self->open_state = true;
 }

@@ -514,7 +525,7 @@ FIXTURE_TEARDOWN(NCI)
 				       NFC_CMD_DEV_DOWN, self->dev_idex);
 		EXPECT_EQ(rc, 0);
 
-		pthread_join(thread_t, (void **)&status);
+		status = join_thread_status(thread_t);
 		ASSERT_EQ(status, 0);
 	}
 

@@ -585,7 +596,6 @@ int start_polling(int dev_idx, int proto, int virtual_fd, int sd, int fid, int p
 	void *nla_start_poll_data[2] = {&dev_idx, &proto};
 	int nla_start_poll_len[2] = {4, 4};
 	pthread_t thread_t;
-	int status;
 	int rc;
 
 	rc = pthread_create(&thread_t, NULL, virtual_poll_start,

@@ -598,14 +608,12 @@ int start_polling(int dev_idx, int proto, int virtual_fd, int sd, int fid, int p
 	if (rc != 0)
 		return rc;
 
-	pthread_join(thread_t, (void **)&status);
-	return status;
+	return join_thread_status(thread_t);
 }
 
 int stop_polling(int dev_idx, int virtual_fd, int sd, int fid, int pid)
 {
 	pthread_t thread_t;
-	int status;
 	int rc;
 
 	rc = pthread_create(&thread_t, NULL, virtual_poll_stop,

@@ -618,8 +626,7 @@ int stop_polling(int dev_idx, int virtual_fd, int sd, int fid, int pid)
 	if (rc != 0)
 		return rc;
 
-	pthread_join(thread_t, (void **)&status);
-	return status;
+	return join_thread_status(thread_t);
 }
 
 TEST_F(NCI, start_poll)

@@ -834,8 +841,10 @@ int disconnect_tag(int nfc_sock, int virtual_fd)
 		return status;
 
 	close(nfc_sock);
-	pthread_join(thread_t, (void **)&status);
-	return status;
+	if (status)
+		return -1;
+
+	return join_thread_status(thread_t);
 }
 
 TEST_F(NCI, t4t_tag_read)

@@ -882,7 +891,7 @@ TEST_F(NCI, deinit)
 			       NFC_CMD_DEV_DOWN, self->dev_idex);
 	EXPECT_EQ(rc, 0);
 
-	pthread_join(thread_t, (void **)&status);
+	status = join_thread_status(thread_t);
 	self->open_state = 0;
 	ASSERT_EQ(status, 0);
 

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chris Gellermann <[email protected]>

[ Upstream commit 51814683e28fc64eceb415962376956c3cfc75a7 ]

The compat handler for ioctls to the virtual nci device is missing. So, nci-specific ioctls of a compat task return with -1 and errno set to ENOTTY. Add a handler.

The handling of an ioctl() call of a compat task to get the index of virtual nci device (IOCTL_GET_NCIDEV_IDX) lands in the default case of the ioctl compat handler (see fs/ioctl.c):

COMPAT_SYSCALL_DEFINE3(ioctl, ...)

{
	...
	default:
       		error = do_vfs_ioctl(fd_file(f), fd, cmd, ...);
		if (error != -ENOIOCTLCMD)
			break;

		if (fd_file(f)->f_op->compat_ioctl)
			error = fd_file(f)->f_op->compat_ioctl(fd_file(f), cmd, arg);
		if (error == -ENOIOCTLCMD)
			error = -ENOTTY;
	...
}

There, do_vfs_ioctl() returns -ENOIOCTLCMD and compat_ioctl is not set for virtual_ncidev_fops, i.e. f_op->compat_ioctl == NULL. So, the ioctl() syscall returns with -1 and errno set to ENOTTY to the compat task.

To fix this, use the compat_ptr_ioctl helper for compat handling here. It shall be used for ioctls that "either ignore the argument or pass a pointer to a compatible data type". The driver's sole ioctl takes a user void pointer and copies nfc_dev->idx to it, a 4-byte integer across all ABIs.

This issue has been found by running the nci_dev kernel selftest as rv64 binary on top of a CHERI kernel, where the ioctl() ends up in the ioctl compat handler, similar to a 32-bit application on top of a 64-bit kernel.

---
 drivers/nfc/virtual_ncidev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index b957fce83b7c8..3eaa63bfee27b 100644
@@ -195,7 +195,8 @@ static const struct file_operations virtual_ncidev_fops = {
 	.write = virtual_ncidev_write,
 	.open = virtual_ncidev_open,
 	.release = virtual_ncidev_close,
-	.unlocked_ioctl = virtual_ncidev_ioctl
+	.unlocked_ioctl = virtual_ncidev_ioctl,
+	.compat_ioctl = compat_ptr_ioctl,
 };
 
 static struct miscdevice miscdev = {

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Cong Nguyen <[email protected]>

[ Upstream commit 66f4300206b82b0b143ef0d9be90cd8d29f23a47 ]

nfc_genl_llc_sdreq() builds a list of TLV nodes while walking nested netlink attrs, but 3 error paths (nested-attr parse failure, TLV alloc ENOMEM, nfc_llcp_send_snl_sdreq() failure) all skip freeing what was already queued.

Route them through a new free_list label, mirroring the SDRES path in the same file which already does this. Harmless on the success path too -- send_snl_sdreq() drains the list as it moves nodes, so it's already empty by the time free_list runs.

---
 net/nfc/netlink.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

index a18e2c503da61..3c599435c99e9 100644
@@ -1181,7 +1181,7 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info)
 
 		if (rc != 0) {
 			rc = -EINVAL;
-			goto put_local;
+			goto free_list;
 		}
 
 		if (!sdp_attrs[NFC_SDP_ATTR_URI])

@@ -1200,7 +1200,7 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info)
 		sdreq = nfc_llcp_build_sdreq_tlv(tid, uri, uri_len);
 		if (sdreq == NULL) {
 			rc = -ENOMEM;
-			goto put_local;
+			goto free_list;
 		}
 
 		tlvs_len += sdreq->tlv_len;

@@ -1215,6 +1215,9 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info)
 
 	rc = nfc_llcp_send_snl_sdreq(local, &sdreq_list, tlvs_len);
 
+free_list:
+	nfc_llcp_free_sdp_tlv_list(&sdreq_list);
+
 put_local:
 	nfc_llcp_local_put(local);
 

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pengpeng Hou <[email protected]>

[ Upstream commit 7f2ea5ed588c03d481f0301e6c3d4240132383fb ]

The ISO15693 inventory helper removes a two-byte prefix without checking that it exists, then accepts a one-byte remainder before reading data[1] as the DSFID.

Require the prefix and at least two remaining bytes before copying the UID data and reading the DSFID.

---
 drivers/nfc/st21nfca/core.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

index bec6f607c32c9..f0a451fe525a5 100644
@@ -577,9 +577,7 @@ static int st21nfca_get_iso15693_inventory(struct nfc_hci_dev *hdev,
 	if (r < 0)
 		goto exit;
 
-	skb_pull(inventory_skb, 2);
-
-	if (inventory_skb->len == 0 ||
+	if (!skb_pull(inventory_skb, 2) || inventory_skb->len < 2 ||
 	    inventory_skb->len > NFC_ISO15693_UID_MAXSIZE) {
 		r = -EPROTO;
 		goto exit;

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ömer Mete Kaya <[email protected]>

[ Upstream commit c04981e42d94f39c1dba965cc462a046e946a6c5 ]

When service_name_len is 0, kmemdup() returns ZERO_SIZE_PTR which passes the NULL check, causing nfc_llcp_send_connect() to attempt building a zero-length service name TLV and fail with -ENOMEM.

Fix by setting service_name to NULL directly when service_name_len is 0.

---
 net/nfc/llcp_sock.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

index f9d35711eb9a7..0601ddb4304aa 100644
@@ -759,12 +759,16 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr,
 	llcp_sock->service_name_len = min_t(unsigned int,
 					    addr->service_name_len,
 					    NFC_LLCP_MAX_SERVICE_NAME);
-	llcp_sock->service_name = kmemdup(addr->service_name,
-					  llcp_sock->service_name_len,
-					  GFP_KERNEL);
-	if (!llcp_sock->service_name) {
-		ret = -ENOMEM;
-		goto sock_llcp_release;
+	if (llcp_sock->service_name_len == 0) {
+		llcp_sock->service_name = NULL;
+	} else {
+		llcp_sock->service_name = kmemdup(addr->service_name,
+						  llcp_sock->service_name_len,
+						  GFP_KERNEL);
+		if (!llcp_sock->service_name) {
+			ret = -ENOMEM;
+			goto sock_llcp_release;
+		}
 	}
 
 	nfc_llcp_sock_link(&local->connecting_sockets, sk);

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ömer Mete Kaya <[email protected]>

[ Upstream commit 408cff6bd60636df201274d320edfdfde9ed41db ]

nfc_llcp_wks_sap() compares only service_name_len bytes, so a short service_name like "u" matches longer WKS strings like "urn:nfc:sn:snep". Fix by requiring exact length match before strncmp().

---
 net/nfc/llcp_core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index 856b3d1710020..db729dc9def5a 100644
@@ -369,7 +369,8 @@ static int nfc_llcp_wks_sap(const char *service_name, size_t service_name_len)
 		if (wks[sap] == NULL)
 			continue;
 
-		if (strncmp(wks[sap], service_name, service_name_len) == 0)
+		if (strlen(wks[sap]) == service_name_len &&
+		    !strncmp(wks[sap], service_name, service_name_len))
 			return sap;
 	}
 

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ömer Mete Kaya <[email protected]>

[ Upstream commit 7dcf371a35632f035baf77bcf2c129165f772ce4 ]

nfc_llcp_wks_sap() and nfc_llcp_build_sdreq_tlv() pass non-null- terminated strings to pr_debug() using the %s format specifier. The buffers are allocated via kmemdup() or come from netlink attributes and are not guaranteed to be null-terminated, causing __dynamic_pr_debug() to read beyond the allocated region:

  KASAN: slab-out-of-bounds Read in __dynamic_pr_debug

Fix both call sites by using %.*s with the explicit length to limit the output to the actual length of the string.

---
 net/nfc/llcp_commands.c | 2 +-
 net/nfc/llcp_core.c     | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

index a93bf0b43d504..2d9e0925b1cc7 100644
@@ -135,7 +135,7 @@ struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, const char *uri,
 {
 	struct nfc_llcp_sdp_tlv *sdreq;
 
-	pr_debug("uri: %s, len: %zu\n", uri, uri_len);
+	pr_debug("uri: %.*s, len: %zu\n", (int)uri_len, uri, uri_len);
 
 	/* sdreq->tlv_len is u8, takes uri_len, + 3 for header, + 1 for NULL */
 	if (WARN_ON_ONCE(uri_len > U8_MAX - 4))

index db729dc9def5a..876756a376ee8 100644
@@ -358,7 +358,7 @@ static int nfc_llcp_wks_sap(const char *service_name, size_t service_name_len)
 {
 	int sap, num_wks;
 
-	pr_debug("%s\n", service_name);
+	pr_debug("%.*s\n", (int)service_name_len, service_name);
 
 	if (service_name == NULL)
 		return -EINVAL;

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Deepanshu Kartikey <[email protected]>

[ Upstream commit b61732f47316d45f27706db7812950145d3327b5 ]

frame->ccid.datalen is read directly from the USB response frame and used, unchecked, as an index into frame->data[]. A malicious or malfunctioning device can set this field to an arbitrary value, causing the driver to read far outside the received buffer.

Bound ccid.datalen against the maximum possible ACR122 frame size before using it. This replaces the existing datalen == 0 check, since datalen < 2 already covers that case and additionally rejects datalen == 1, which would still underflow the "datalen - 2" offset used below.

---
 drivers/nfc/pn533/usb.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index 0f12f86ebb023..35f3350cad324 100644
@@ -319,7 +319,9 @@ static bool pn533_acr122_is_rx_frame_valid(void *_frame, struct pn533 *dev)
 	if (frame->ccid.type != 0x83)
 		return false;
 
-	if (!frame->ccid.datalen)
+	if (frame->ccid.datalen < 2 ||
+	    frame->ccid.datalen > PN533_ACR122_FRAME_MAX_PAYLOAD_LEN +
+	    PN533_ACR122_RX_FRAME_TAIL_LEN)
 		return false;
 
 	if (frame->data[frame->ccid.datalen - 2] == 0x63)

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Victor Nogueira <[email protected]>

[ Upstream commit cfa165cbfbed9d0f4bbc22fef4309f595a3ab187 ]

tcf_gate_get_fill_size returns only the TCA_GATE_PARMS size, but tcf_gate_dump also emits three 64-bit timestamps, the clock id, flags, priority and the variable-length TCA_GATE_ENTRY_LIST nest. The per-entry nest is unbounded: parse_gate_list places no cap on the number of sched-entries, so a gate with many entries can push the real dump well past the skb that tca_get_fill allocates from this size.

RTM_NEWACTION then fails the add-notify with -EINVAL while the action is already committed to the IDR, and a subsequent RTM_GETACTION on the installed gate also returns -EINVAL because its dump no longer fits.

Fix this by accounting for the missing fields in tcf_gate_get_fill_size along with all elements in the entries list.

Note that sizing the reply from the action lets an oversized gate install cleanly for the first time: with the input unbounded by parse_gate_list, the sized skb can now grow well above NLMSG_GOODSIZE per netlink request (a transient GFP_KERNEL allocation reachable only with namespace-local CAP_NET_ADMIN). Overload from a malicious netns admin is hardening material, not net, per the discussion at
https://lore.kernel.org/netdev/[email protected]/;
a follow-up patch for net-next will cap the sched-entry count.

---
 net/sched/act_gate.c | 30 +++++++++++++++++++++++++++++-
 1 file changed, 29 insertions(+), 1 deletion(-)

index d09013ae1892a..e21f72c0fc45c 100644
@@ -681,7 +681,35 @@ static void tcf_gate_stats_update(struct tc_action *a, u64 bytes, u64 packets,
 
 static size_t tcf_gate_get_fill_size(const struct tc_action *act)
 {
-	return nla_total_size(sizeof(struct tc_gate));
+	struct tcf_gate *gact = to_gate(act);
+	const struct tcf_gate_params *p;
+	struct tcfg_gate_entry *entry;
+	size_t size = nla_total_size(sizeof(struct tc_gate)) /* TCA_GATE_PARMS */
+		+ 3 * nla_total_size_64bit(sizeof(u64)) /* TCA_GATE_BASE_TIME
+							 * TCA_GATE_CYCLE_TIME
+							 * TCA_GATE_CYCLE_TIME_EXT
+							 */
+		+ nla_total_size(sizeof(s32)) /* TCA_GATE_CLOCKID */
+		+ nla_total_size(sizeof(u32)) /* TCA_GATE_FLAGS */
+		+ nla_total_size(sizeof(s32)) /* TCA_GATE_PRIORITY */
+		+ nla_total_size(0); /* TCA_GATE_ENTRY_LIST */
+	/* TCA_GATE_TM is budgeted by tcf_action_shared_attrs_size() */
+
+	rcu_read_lock();
+	p = rcu_dereference(gact->param);
+	if (p) {
+		list_for_each_entry_rcu(entry, &p->entries, list)
+			/* TCA_GATE_ONE_ENTRY nest and its attributes */
+			size += nla_total_size(0)
+				+ nla_total_size(sizeof(u32)) /* TCA_GATE_ENTRY_INDEX */
+				+ nla_total_size(0) /* TCA_GATE_ENTRY_GATE */
+				+ nla_total_size(sizeof(u32)) /* TCA_GATE_ENTRY_INTERVAL */
+				+ nla_total_size(sizeof(s32)) /* TCA_GATE_ENTRY_MAX_OCTETS */
+				+ nla_total_size(sizeof(s32)); /* TCA_GATE_ENTRY_IPV */
+	}
+	rcu_read_unlock();
+
+	return size;
 }
 
 static void tcf_gate_entry_destructor(void *priv)

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nicolai Buchwitz <[email protected]>

[ Upstream commit 7e87508b5c4d81210d0a736ed01962e52f5c4c56 ]

bcmgenet_netif_stop() and the Wake-on-LAN branch of bcmgenet_suspend() both disable the Tx queues first and stop Tx NAPI several steps later. A completion in flight calls netif_tx_wake_queue() in between, and nothing stops the queue again, so a transmit can reach the rings after they have been freed.

Close is safe because dev_deactivate_many() stops the qdisc first. bcmgenet_suspend() does not, so stop Tx NAPI before the queues on both paths.

KASAN on a Raspberry Pi CM4, driven from an MTU change because suspend freezes user space before the callback runs:

  BUG: KASAN: use-after-free in bcmgenet_xmit+0x17f8/0x2258
  Write of size 8 at addr ffffff8055844a68 by task ksoftirqd/0/14
   bcmgenet_xmit+0x17f8/0x2258
   dev_hard_start_xmit+0x13c/0x588
   sch_direct_xmit+0x108/0x340
   __dev_queue_xmit+0x1190/0x3848

---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

index 41539f9f8061c..c9a8018148483 100644
@@ -3439,6 +3439,8 @@ static void bcmgenet_netif_stop(struct net_device *dev, bool stop_phy)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 
+	/* Stop completion polling before it can wake a stopped queue */
+	bcmgenet_disable_tx_napi(priv);
 	netif_tx_disable(dev);
 
 	/* Disable MAC receive */

@@ -3453,7 +3455,6 @@ static void bcmgenet_netif_stop(struct net_device *dev, bool stop_phy)
 	/* Disable MAC transmit. TX DMA disabled must be done before this */
 	umac_enable_set(priv, CMD_TX_EN, false);
 
-	bcmgenet_disable_tx_napi(priv);
 	bcmgenet_disable_rx_napi(priv);
 	bcmgenet_intr_disable(priv);
 

@@ -4325,6 +4326,8 @@ static int bcmgenet_suspend(struct device *d)
 	netif_device_detach(dev);
 
 	if (device_may_wakeup(d) && priv->wolopts) {
+		/* Stop completion polling before it can wake a stopped queue */
+		bcmgenet_disable_tx_napi(priv);
 		netif_tx_disable(dev);
 
 		/* Suspend non-wake Rx data flows */

@@ -4353,7 +4356,6 @@ static int bcmgenet_suspend(struct device *d)
 			netdev_warn(priv->dev,
 				    "Timed out while disabling TX DMA\n");
 
-		bcmgenet_disable_tx_napi(priv);
 		bcmgenet_disable_rx_napi(priv);
 		disable_irq(priv->irq1);
 		bcmgenet_tx_reclaim_all(dev);

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jakub Kicinski <[email protected]>

[ Upstream commit 7104a370714346b667712913dc16abf14bbc97ed ]

veth_set_channels() tears down XDP resources for removed RX queues without clearing rq->xdp_prog. If the program is then detached or replaced, those queues keep the old pointer after bpf_prog_put(). A later channel increase can re-enable NAPI and run the freed program.

  BUG: unable to handle page fault for address: ffffc90000256048
  Oops: Oops: 0000 [#1] SMP KASAN NOPTI
  RIP: veth_xdp_rcv_skb (include/linux/filter.h:779
                         include/net/xdp.h:696 drivers/net/veth.c:820)
  Call Trace:
   veth_xdp_rcv (drivers/net/veth.c:941)
   veth_poll (drivers/net/veth.c:986)
   __napi_poll (net/core/dev.c:7787)
   net_rx_action (net/core/dev.c:7850 net/core/dev.c:8007)
   handle_softirqs (kernel/softirq.c:645)
  Kernel panic - not syncing: Fatal exception in interrupt

---
 drivers/net/veth.c | 2 ++
 1 file changed, 2 insertions(+)

index 56519b646cacd..fea031d491b34 100644
@@ -1053,6 +1053,7 @@ static int __veth_napi_enable_range(struct net_device *dev, int start, int end)
 	for (i = start; i < end; i++) {
 		struct veth_rq *rq = &priv->rq[i];
 
+		rcu_assign_pointer(rq->xdp_prog, priv->_xdp_prog);
 		napi_enable(&rq->xdp_napi);
 		rcu_assign_pointer(priv->rq[i].napi, &priv->rq[i].xdp_napi);
 	}

@@ -1087,6 +1088,7 @@ static void veth_napi_del_range(struct net_device *dev, int start, int end)
 
 		rcu_assign_pointer(priv->rq[i].napi, NULL);
 		napi_disable(&rq->xdp_napi);
+		rcu_assign_pointer(rq->xdp_prog, NULL);
 		__netif_napi_del(&rq->xdp_napi);
 	}
 	synchronize_net();

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shihuang Liu <[email protected]>

[ Upstream commit 3b4e0b0c008a8c1b474730248cd5b873026c74bd ]

skb_maybe_pull_tail() subtracts skb_headlen(skb) from the unsigned max argument and passes the result to __pskb_pull_tail() as a signed int. The function does not ensure that max is at least skb_headlen(skb).

This can happen while parsing IPv6 extension headers when an skb already has a linear area larger than MAX_IPV6_HDR_LEN. Once the parser needs data beyond the linear area, max - skb_headlen(skb) wraps and is converted to a negative delta. __pskb_pull_tail() then passes that negative length to skb_copy_bits(), where it can become a very large copy length.

Pass the requested length itself as the pull bound at the three extension-header call sites, so the delta can no longer go negative.

---
 net/core/skbuff.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

index 594764eab40dc..9ef8b31dbc870 100644
@@ -5911,7 +5911,8 @@ static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate)
 			err = skb_maybe_pull_tail(skb,
 						  off +
 						  sizeof(struct ipv6_opt_hdr),
-						  MAX_IPV6_HDR_LEN);
+						  off +
+						  sizeof(struct ipv6_opt_hdr));
 			if (err < 0)
 				goto out;
 

@@ -5926,7 +5927,8 @@ static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate)
 			err = skb_maybe_pull_tail(skb,
 						  off +
 						  sizeof(struct ip_auth_hdr),
-						  MAX_IPV6_HDR_LEN);
+						  off +
+						  sizeof(struct ip_auth_hdr));
 			if (err < 0)
 				goto out;
 

@@ -5941,7 +5943,8 @@ static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate)
 			err = skb_maybe_pull_tail(skb,
 						  off +
 						  sizeof(struct frag_hdr),
-						  MAX_IPV6_HDR_LEN);
+						  off +
+						  sizeof(struct frag_hdr));
 			if (err < 0)
 				goto out;
 

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ido Schimmel <[email protected]>

[ Upstream commit ab7aa05c06ae340e5c7530bb78fa8d23794e460b ]

The VRF device is an Ethernet device but it can have non-Ethernet ports such as IP tunnels. Before the cited commit, capturing packets from such ports on the VRF device resulted in these packets being detected as malformed since they lack an Ethernet header.

The cited commit fixed it by pushing a dummy Ethernet header to such packets before the capture and pulling it afterwards. In the case of CHECKSUM_COMPLETE packets it also updated skb->csum with the checksum of the dummy Ethernet header. This is wrong as skb->csum should not include the checksum of the Ethernet header ("checksum of the _whole_ packet as seen by netif_rx()").

This also means that L4 protocols receive a corrupted skb->csum and potentially drop the packet, as is the case with UDP packets whose checksum was completed by software.

Fix by removing the unnecessary call to skb_postpush_rcsum().

---
 drivers/net/vrf.c | 2 --
 1 file changed, 2 deletions(-)

index 4b62b167650ea..7ac320da3ba20 100644
@@ -1225,8 +1225,6 @@ static int vrf_prepare_mac_header(struct sk_buff *skb,
 	skb->protocol = eth->h_proto;
 	skb->pkt_type = PACKET_HOST;
 
-	skb_postpush_rcsum(skb, skb->data, ETH_HLEN);
-
 	skb_pull_inline(skb, ETH_HLEN);
 
 	return 0;

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Johan Almbladh <[email protected]>

[ Upstream commit db762fd96be225bd06161c9631160c755d891693 ]

An addu instruction was emitted instead of addiu, causing the immediate value 1 to be interpreted as register $at. This made the comparison result invalid when the immediate operand was negative. Note that $at is mapped to BPF_REG_AX, which is used for constant blinding.

Fix the instruction to use the immediate form.

Found with test_bpf on MIPS32r1 emulated by QEMU.

---
 arch/mips/net/bpf_jit_comp32.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 40a878b672f5d..15a2a153dc873 100644
@@ -1111,7 +1111,7 @@ static void emit_jmp_i64(struct jit_context *ctx,
 			emit(ctx, xor, tmp, lo(dst), tmp);
 		}
 		if (imm < 0) { /* Compare sign extension */
-			emit(ctx, addu, MIPS_R_T9, hi(dst), 1);
+			emit(ctx, addiu, MIPS_R_T9, hi(dst), 1);
 			emit(ctx, or, tmp, tmp, MIPS_R_T9);
 		} else {       /* Compare zero extension */
 			emit(ctx, or, tmp, tmp, hi(dst));

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Johan Almbladh <[email protected]>

[ Upstream commit 8110ba09777873443db286b3cbb89b0e6311c554 ]

The 16/32-bit byteswap implementations for MIPS64r1 and earlier do not have an explicit zero extension afterwards. The input is first sign-extended to 64 bits, and the byteswap sequence can then leave the result sign-extended depending on the value of the low bits.

Add the missing zero-extension.

Found with test_bpf on MIPS64r1 emulated by QEMU.

---
 arch/mips/net/bpf_jit_comp64.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

index fa7e9aa37f498..6681ccac9dd9e 100644
@@ -305,8 +305,7 @@ static void emit_bswap_r64(struct jit_context *ctx, u8 dst, u32 width)
 	case 16:
 		emit_sext(ctx, dst, dst);
 		emit_bswap_r(ctx, dst, width);
-		if (cpu_has_mips64r2 || cpu_has_mips64r6)
-			emit_zext(ctx, dst);
+		emit_zext(ctx, dst);
 		break;
 	}
 	clobber_reg(ctx, dst);

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ivan Delalande <[email protected]>

[ Upstream commit 4eb3f195ef08c5acaed87958297e41cc49588dde ]

Some of the tg3 NICs we use (BCM57762) reset the SRAM MAC address to the placeholder address on link flaps, tg3_chip_reset, etc. We've typically fixed it from userspace, but since e4c00ba7274b ("tg3: replace placeholder MAC address with device property") was merged, tg3 just fails probe as we don't have a way to get it through the generic device_get_mac_address infrastructure as fallback on our systems.

Make the driver assign a random address in this condition instead of being fatal for probe. Set deferred_probe_reason through dev_warn_probe if the address isn't yet available from the provider.

---
 drivers/net/ethernet/broadcom/tg3.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

index e212afe53e0b7..50eb40de7b220 100644
@@ -17928,11 +17928,14 @@ static int tg3_init_one(struct pci_dev *pdev,
 
 	err = tg3_get_device_address(tp, addr);
 	if (err) {
-		dev_err(&pdev->dev,
-			"Could not obtain valid ethernet address, aborting\n");
-		goto err_out_apeunmap;
+		dev_warn_probe(&pdev->dev, err,
+			       "Could not obtain a valid ethernet address\n");
+		if (err == -EPROBE_DEFER)
+			goto err_out_apeunmap;
+		eth_hw_addr_random(dev);
+	} else {
+		eth_hw_addr_set(dev, addr);
 	}
-	eth_hw_addr_set(dev, addr);
 
 	intmbx = MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW;
 	rcvmbx = MAILBOX_RCVRET_CON_IDX_0 + TG3_64BIT_REG_LOW;

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Lorenzo Bianconi <[email protected]>

[ Upstream commit 0a7822e34a0bfde31b194ac3da3253e5032b44cc ]

In stmmac_rx(), when napi_build_skb() fails the descriptor page is recycled back to the page pool with page_pool_recycle_direct(), but buf->page is left pointing at the recycled page, unlike every other consumption site in the function which clears the pointer after handing the page away.

With the stale pointer stmmac_rx_refill() skips the replacement allocation and programs the already-recycled page back into the RX descriptor.

Clear buf->page on the napi_build_skb() failure path to keep the buffer lifecycle consistent with the other consumption sites.

---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 +
 1 file changed, 1 insertion(+)

index 6a6cac88f7ecd..b9d4c2afc9a80 100644
@@ -5672,6 +5672,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			if (!skb) {
 				page_pool_recycle_direct(rx_q->page_pool,
 							 buf->page);
+				buf->page = NULL;
 				rx_dropped++;
 				count++;
 				goto drain_data;

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Florian Fainelli <[email protected]>

[ Upstream commit 0e2bec77ea62895416600c90588f593516572bca ]

When bcmgenet was converted to 64-bit statistics, STAT_RTNL members were switched to point into struct rtnl_link_stats64, whose fields are 64-bit (__u64) regardless of architecture.

However, bcmgenet_get_ethtool_stats() retained a legacy check:
if (sizeof(unsigned long) != sizeof(u32) &&

      s->stat_sizeof == sizeof(unsigned long))

On 32-bit systems, sizeof(unsigned long) == sizeof(u32), causing this condition to evaluate to false. As a result, 64-bit RTNL stats fields were read via *(u32 *)p. On 32-bit Big-Endian systems (such as MIPS BE), this reads the high 32 bits and returns 0 until the counter exceeds 4GB; on 32-bit Little-Endian systems (such as 32-bit ARM), the value is truncated to 32 bits.

Fix this by checking if s->stat_sizeof == sizeof(u64) so 64-bit fields are always read as 64-bit values.

---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

index c9a8018148483..0e6c89988d1c1 100644
@@ -1347,9 +1347,8 @@ static void bcmgenet_get_ethtool_stats(struct net_device *dev,
 				p = (char *)&stats64;
 
 			p += s->stat_offset;
-			if (sizeof(unsigned long) != sizeof(u32) &&
-				s->stat_sizeof == sizeof(unsigned long))
-				data[i] = *(unsigned long *)p;
+			if (s->stat_sizeof == sizeof(u64))
+				data[i] = *(u64 *)p;
 			else
 				data[i] = *(u32 *)p;
 		}

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Florian Fainelli <[email protected]>

[ Upstream commit 3aeaa609fda19c09d5298c9fedaaa3b6229601b5 ]

bcmgenet_gstrings_stats statically defines ethtool statistics for queues 0 through GENET_MAX_MQ_CNT (4). However, bcmgenet_probe() only initialized the u64_stats_sync seq counter up to priv->hw_params->rx_queues and priv->hw_params->tx_queues.

Since priv->hw_params->rx_queues is 0 across all hardware versions (and priv->hw_params->tx_queues is 0 on GENET V1), rings 1..4 have uninitialized u64_stats_sync structures. When ethtool -S is run on 32-bit kernels, bcmgenet_get_ethtool_stats() reads stats from rx_rings[1..4], causing lockdep warnings due to the uninitialized sequence counters.

Initialize the sequence counters for all GENET_MAX_MQ_CNT + 1 queues.

---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 0e6c89988d1c1..5050712166aa9 100644
@@ -4140,10 +4140,10 @@ static int bcmgenet_probe(struct platform_device *pdev)
 		priv->rx_rings[i].rx_max_coalesced_frames = 1;
 
 	/* Initialize u64 stats seq counter for 32bit machines */
-	for (i = 0; i <= priv->hw_params->rx_queues; i++)
+	for (i = 0; i <= GENET_MAX_MQ_CNT; i++) {
 		u64_stats_init(&priv->rx_rings[i].stats64.syncp);
-	for (i = 0; i <= priv->hw_params->tx_queues; i++)
 		u64_stats_init(&priv->tx_rings[i].stats64.syncp);
+	}
 
 	/* libphy will determine the link state */
 	netif_carrier_off(dev);

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Florian Fainelli <[email protected]>

[ Upstream commit cbbc1aee7776c7fa1d89e6cb963a23e58c495dca ]

bcmgenet_power_up() had an early check for bcmgenet_has_ext(priv) before dispatching by power mode. GENET V1 does not have the EXT block (unlike GENET V2+), which causes bcmgenet_power_up() to immediately return 0.

As a consequence, when waking up from GENET_POWER_WOL_MAGIC on GENET V1, bcmgenet_wol_power_up_cfg() is never invoked to disable the WoL clock, clear wake event masks, and restore normal PHY and MAC operations.

Move the bcmgenet_has_ext() checks to the GENET_POWER_PASSIVE and GENET_POWER_CABLE_SENSE cases where the EXT registers are actually accessed, allowing GENET_POWER_WOL_MAGIC cleanup to execute on all hardware versions.

---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

index 5050712166aa9..96308c85899f7 100644
@@ -1758,13 +1758,12 @@ static int bcmgenet_power_up(struct bcmgenet_priv *priv,
 	int ret = 0;
 	u32 reg;
 
-	if (!bcmgenet_has_ext(priv))
-		return ret;
-
-	reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
-
 	switch (mode) {
 	case GENET_POWER_PASSIVE:
+		if (!bcmgenet_has_ext(priv))
+			break;
+
+		reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
 		reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS |
 			 EXT_ENERGY_DET_MASK);
 		if (GENET_IS_V5(priv) && !bcmgenet_has_ephy_16nm(priv)) {

@@ -1788,8 +1787,12 @@ static int bcmgenet_power_up(struct bcmgenet_priv *priv,
 		break;
 
 	case GENET_POWER_CABLE_SENSE:
+		if (!bcmgenet_has_ext(priv))
+			break;
+
 		/* enable APD */
 		if (!GENET_IS_V5(priv)) {
+			reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
 			reg |= EXT_PWR_DN_EN_LD;
 			bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
 		}

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Florian Fainelli <[email protected]>

[ Upstream commit 273941c85fc2632cd3e56ddff737b9245de7697d ]

bcmgenet_set_mac_addr() did not check whether the provided MAC address is a valid Ethernet address before applying it. Userspace could configure an invalid address (such as all zeroes or a multicast address) while the interface is down.

Add a call to is_valid_ether_addr() and return -EADDRNOTAVAIL if the MAC address is not valid.

---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 3 +++
 1 file changed, 3 insertions(+)

index 96308c85899f7..c18702f3dd766 100644
@@ -3633,6 +3633,9 @@ static int bcmgenet_set_mac_addr(struct net_device *dev, void *p)
 	if (netif_running(dev))
 		return -EBUSY;
 
+	if (!is_valid_ether_addr(addr->sa_data))
+		return -EADDRNOTAVAIL;
+
 	eth_hw_addr_set(dev, addr->sa_data);
 
 	return 0;

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Florian Fainelli <[email protected]>

[ Upstream commit d64e277b955be4506931802837499b62c8f3968a ]

bcmgenet_get_coalesce() reads DMA_RING0_TIMEOUT to calculate rx_coalesce_usecs without masking out bits outside DMA_TIMEOUT_MASK (16 bits). If upper bits are non-zero or contain status/flags, the computed value of rx_coalesce_usecs returned to userspace via ethtool becomes corrupted.

Mask the register read with DMA_TIMEOUT_MASK before computing the timeout in microseconds.

---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index c18702f3dd766..a72e136fd9c38 100644
@@ -853,7 +853,8 @@ static int bcmgenet_get_coalesce(struct net_device *dev,
 	ec->rx_max_coalesced_frames =
 		bcmgenet_rdma_ring_readl(priv, 0, DMA_MBUF_DONE_THRESH);
 	ec->rx_coalesce_usecs =
-		bcmgenet_rdma_readl(priv, DMA_RING0_TIMEOUT) * 8192 / 1000;
+		(bcmgenet_rdma_readl(priv, DMA_RING0_TIMEOUT) &
+		 DMA_TIMEOUT_MASK) * 8192 / 1000;
 
 	for (i = 0; i <= priv->hw_params->rx_queues; i++) {
 		ring = &priv->rx_rings[i];

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xuanqiang Luo <[email protected]>

[ Upstream commit a3f315be9d30eeb6938d11fa17fd4b32d52f7c42 ]

ipgre_netlink_parms() can enable collect_md on an existing GRE, GRETAP or ERSPAN device. Unlike newlink, changelink does not enforce metadata tunnel uniqueness. Converting a non-metadata device can therefore replace the metadata receive entry for another device of the same type in the same netns. Deleting either device then clears the shared entry, breaking metadata receive lookup for the surviving device.

If parameter validation fails after collect_md is set, deleting the modified device can also clear an entry it never owned.

Reject enabling metadata mode in both changelink callbacks before any encapsulation or tunnel parameters are modified. Allow requests that repeat the metadata attribute on an existing metadata device.

---
 net/ipv4/ip_gre.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

index 300b802125db2..b15cc4ee0d920 100644
@@ -1459,6 +1459,12 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
 	if (!rtnl_dev_link_net_capable(dev, t->net))
 		return -EPERM;
 
+	if (data && data[IFLA_GRE_COLLECT_METADATA] && !t->collect_md) {
+		NL_SET_ERR_MSG(extack,
+			       "Enabling collect_md on an existing device is not supported");
+		return -EOPNOTSUPP;
+	}
+
 	err = ipgre_newlink_encap_setup(dev, data);
 	if (err)
 		return err;

@@ -1491,6 +1497,12 @@ static int erspan_changelink(struct net_device *dev, struct nlattr *tb[],
 	if (!rtnl_dev_link_net_capable(dev, t->net))
 		return -EPERM;
 
+	if (data && data[IFLA_GRE_COLLECT_METADATA] && !t->collect_md) {
+		NL_SET_ERR_MSG(extack,
+			       "Enabling collect_md on an existing device is not supported");
+		return -EOPNOTSUPP;
+	}
+
 	err = ipgre_newlink_encap_setup(dev, data);
 	if (err)
 		return err;

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sanghyun Park <[email protected]>

[ Upstream commit 481506a756dcd828ef42391cb08f38d8d96d38fc ]

vxlan_na_create() samples LL_RESERVED_SPACE() to size the reply skb and then samples it again to reserve headroom. A concurrent vxlan_changelink() can update needed_headroom between the two reads, creating a TOCTOU race. The second value can exceed the allocation and make the Ethernet header write out of bounds.

The race is reproducible on the unpatched kernel. It occurred when vxlan_na_create() generated a neighbour reply while vxlan_changelink() changed the link headroom. KASAN caught a four-byte write two bytes beyond a 704-byte skbuff_small_head allocation.

Snapshot the headroom once and use that value for both allocation and reservation.

---
 drivers/net/vxlan/vxlan_core.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

index 1e411a57d1fe7..02cc791699458 100644
@@ -1956,13 +1956,15 @@ static struct sk_buff *vxlan_na_create(struct sk_buff *request,
 	struct ipv6hdr *pip6;
 	u8 *daddr;
 	int na_olen = 8; /* opt hdr + ETH_ALEN for target */
+	int headroom;
 	int ns_olen;
 	int i, len;
 
 	if (dev == NULL || !pskb_may_pull(request, request->len))
 		return NULL;
 
-	len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) +
+	headroom = LL_RESERVED_SPACE(dev);
+	len = headroom + sizeof(struct ipv6hdr) +
 		sizeof(*na) + na_olen + dev->needed_tailroom;
 	reply = alloc_skb(len, GFP_ATOMIC);
 	if (reply == NULL)

@@ -1970,7 +1972,7 @@ static struct sk_buff *vxlan_na_create(struct sk_buff *request,
 
 	reply->protocol = htons(ETH_P_IPV6);
 	reply->dev = dev;
-	skb_reserve(reply, LL_RESERVED_SPACE(request->dev));
+	skb_reserve(reply, headroom);
 	skb_push(reply, sizeof(struct ethhdr));
 	skb_reset_mac_header(reply);
 

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Norbert Szetei <[email protected]>

[ Upstream commit 4da3b7b8b50f3e2fde54a4c18a82a8e3f6223910 ]

Only the entries below dev->num_tc are valid in dev->tc_to_txq[], and dev->prio_tc_map[] may only name classes below it. netdev_set_num_tc() lowers dev->num_tc without touching either array.

netdev_txq_to_tc() walks all TC_MAX_QUEUE slots and netdev_get_prio_tc_map() returns the entry as it stands, so a leftover entry is handed out as a traffic class >= dev->num_tc. Taking that class from netdev_txq_to_tc(), __netif_set_xps_queue() rejects only a negative one and indexes an XPS map sized for dev->num_tc classes:

	tci = j * num_tc + tc;
	RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);

attr_map[] holds nr_ids * num_tc entries and j runs over the ids named in the mask, so a class that is not below num_tc pushes tci past the end of the map for the last ids and the store overruns it.

Any caller that lowers num_tc leaves such entries behind, and mqprio_destroy() tears down with netdev_set_num_tc(dev, 0) rather than netdev_reset_tc(). After mqprio with 8 classes then 1, tc_to_txq[1..7] still describe txq 1..7. The splat is from an XPS write to txq 2 on a veth with 8 rx queues: attr_map[] has 8 * 1 entries, tci = j + 2, and j == 6 stores one past the end of the 88-byte map:

  BUG: KASAN: slab-out-of-bounds in __netif_set_xps_queue (net/core/dev.c:2954)
  Write of size 8 at addr ffff88813016bc58 by task xps_oob/634
   __netif_set_xps_queue (net/core/dev.c:2954)
   xps_rxqs_store (net/core/net-sysfs.c:1880)
   netdev_queue_attr_store (net/core/net-sysfs.c:1390)
  Allocated by task 634:
   __kmalloc_noprof (mm/slub.c:5439)
   __netif_set_xps_queue (net/core/dev.c:2937)
  The buggy address is located 0 bytes to the right of
   allocated 88-byte region [ffff88813016bc00, ffff88813016bc58)

Reject a class the map has no room for.

---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 48983bac5b539..6569605cc666a 100644
@@ -2863,7 +2863,7 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
 		dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
 
 		tc = netdev_txq_to_tc(dev, index);
-		if (tc < 0)
+		if (tc < 0 || tc >= num_tc)
 			return -EINVAL;
 	}
 

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pengpeng Hou <[email protected]>

[ Upstream commit 45585c3aa285854face65293acc95eff73063d6d ]

The firmware reconstruction count controls accesses to the request's fixed freelist ID array and the copy into the fixed response array. Neither access currently bounds the count to those protocol arrays.

Clamp the count to the request capacity, which is shared by the response layout, and use that count consistently for reconstruction and response publication. Keep the firmware recovery exchange instead of dropping an oversized request without a response, as discussed with the firmware maintainer.

The issue was found by our static-analysis tool.

---
 drivers/gpu/drm/imagination/pvr_free_list.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

index 5228e214491c6..2ced452e9ce34 100644
@@ -8,6 +8,7 @@
 #include "pvr_vm.h"
 
 #include <drm/drm_gem.h>
+#include <drm/drm_print.h>
 #include <linux/slab.h>
 #include <linux/xarray.h>
 #include <uapi/drm/pvr_drm.h>

@@ -612,13 +613,21 @@ pvr_free_list_process_reconstruct_req(struct pvr_device *pvr_dev,
 	};
 	struct rogue_fwif_freelists_reconstruction_data *resp =
 		&resp_cmd.cmd_data.free_lists_reconstruction_data;
+	u32 count = min_t(u32, req->freelist_count,
+			  ARRAY_SIZE(req->freelist_ids));
 
-	for (u32 i = 0; i < req->freelist_count; i++)
+	if (count != req->freelist_count) {
+		drm_warn_once(from_pvr_device(pvr_dev),
+			      "Requested reconstruction of %u freelists, limiting to %u\n",
+			      req->freelist_count, count);
+	}
+
+	for (u32 i = 0; i < count; i++)
 		pvr_free_list_reconstruct(pvr_dev, req->freelist_ids[i]);
 
-	resp->freelist_count = req->freelist_count;
+	resp->freelist_count = count;
 	memcpy(resp->freelist_ids, req->freelist_ids,
-	       req->freelist_count * sizeof(resp->freelist_ids[0]));
+	       count * sizeof(resp->freelist_ids[0]));
 
 	WARN_ON(pvr_kccb_send_cmd(pvr_dev, &resp_cmd, NULL));
 }

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Dai <[email protected]>

[ Upstream commit 00efbbd40bd5fd92c67b7cf1aab8904fa59a96f6 ]

Create a bonding device (i.e. bond0) in active-backup mode, 2 slaves. Active slave: offload capable interface (i.e. eth1), primary interface. Backup slave: non-offload capable interface(i.e. eth2). Configure strongswan service swantl.conf child SA "hw_offload = crypto" Start strongswan service
IPSec Crytpo Offload is enabled on top of bond0. i.e.
ip xfrm state |grep offload
crypto offload parameters: dev bond0 dir out mode crypto crypto offload parameters: dev bond0 dir in mode crypto

Active slave eth1 takes adavantage of IPSec Crypto Offload capability.

If active slave eth1 is down for any reason (i.e. eth1 link down):
ip link set down dev eth1
non-offload capable interface eth2 failover to becomes active slave. The existing SAs can continue use software IPsec after failover. Traffic still keeps going properly.

However if eth1 link had not recovered yet, strongswan service does new child SA rekey, or uses swanctl command to do new child SA rekey, it will fail because active slave eth2 doesn't support crypto offload. In bond_ipsec_add_sa routine, it returns -EINVAL now, which is treated as fatal error by xfrm_dev_state_add routine in kernel xfrm.

To make the non-offload active slave survive the child SA rekey, need to make bond_ipsec_add_sa routine returns -EOPNOTSUPP instead when active slave doesn't support IPsec Crypto offload, the xfrm will gracefully fallback to create new SA using Software IPsec. Network traffic can keep going.

After offload capable interface eth1 link is up, becomes active slave, next time strongswan child SA rekey will create a new SA which enables crypto offload again.

---
 drivers/net/bonding/bond_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 6b9509e939289..e555c5ce4bdfa 100644
@@ -492,7 +492,7 @@ static int bond_ipsec_add_sa(struct net_device *bond_dev,
 	    !real_dev->xfrmdev_ops->xdo_dev_state_add ||
 	    netif_is_bond_master(real_dev)) {
 		NL_SET_ERR_MSG_MOD(extack, "Slave does not support ipsec offload");
-		err = -EINVAL;
+		err = -EOPNOTSUPP;
 		goto out;
 	}
 

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Haseeb Malik <[email protected]>

[ Upstream commit c2de369c5c5b8599ca10fd5ca8d11fcd845c1331 ]

Creating a MACsec device with MAC offload over an LRO-capable lower device triggers a warning in rtmsg_ifinfo_build_skb() when IPv4 forwarding is enabled by default.

register_netdevice() invokes inetdev_init(), which disables LRO and emits a NETDEV_FEAT_CHANGE notification. This reaches macsec_fill_info() before macsec_add_dev() initializes the SecY. key_len is still zero, so macsec_fill_info() returns -EMSGSIZE and trips the WARN_ON in rtmsg_ifinfo_build_skb(), even though the skb has enough space.

Even without the warning, notifications during registration can report uninitialized SecY attributes, including the SCI. This ordering has existed since the driver was introduced.

Initialize the SecY and apply the new-link attributes before registration. Move MAC address inheritance into macsec_newlink() so the SCI can also be initialized before registration-time notifications report it. Move the per-CPU statistics and metadata destination allocation into ndo_init(), and release partial allocations on failure.

---
 drivers/net/macsec.c | 84 +++++++++++++++++++++++---------------------
 1 file changed, 43 insertions(+), 41 deletions(-)

index e20538eda2001..ef1d65d98a34b 100644
@@ -3533,6 +3533,22 @@ static int macsec_dev_init(struct net_device *dev)
 	if (err)
 		return err;
 
+	err = -ENOMEM;
+	macsec->stats = netdev_alloc_pcpu_stats(struct pcpu_secy_stats);
+	if (!macsec->stats)
+		goto destroy_gro_cells;
+
+	macsec->secy.tx_sc.stats =
+		netdev_alloc_pcpu_stats(struct pcpu_tx_sc_stats);
+	if (!macsec->secy.tx_sc.stats)
+		goto free_secy_stats;
+
+	macsec->secy.tx_sc.md_dst = metadata_dst_alloc(0, METADATA_MACSEC,
+						       GFP_KERNEL);
+	if (!macsec->secy.tx_sc.md_dst)
+		goto free_tx_sc_stats;
+	macsec->secy.tx_sc.md_dst->u.macsec_info.sci = macsec->secy.sci;
+
 	macsec_inherit_tso_max(dev);
 
 	dev->hw_features = real_dev->hw_features & MACSEC_OFFLOAD_FEATURES;

@@ -3545,8 +3561,6 @@ static int macsec_dev_init(struct net_device *dev)
 
 	macsec_set_head_tail_room(dev);
 
-	if (is_zero_ether_addr(dev->dev_addr))
-		eth_hw_addr_inherit(dev, real_dev);
 	if (is_zero_ether_addr(dev->broadcast))
 		memcpy(dev->broadcast, real_dev->broadcast, dev->addr_len);
 

@@ -3554,6 +3568,14 @@ static int macsec_dev_init(struct net_device *dev)
 	netdev_hold(real_dev, &macsec->dev_tracker, GFP_KERNEL);
 
 	return 0;
+
+free_tx_sc_stats:
+	free_percpu(macsec->secy.tx_sc.stats);
+free_secy_stats:
+	free_percpu(macsec->stats);
+destroy_gro_cells:
+	gro_cells_destroy(&macsec->gro_cells);
+	return err;
 }
 
 static void macsec_dev_uninit(struct net_device *dev)

@@ -4108,26 +4130,11 @@ static sci_t dev_to_sci(struct net_device *dev, __be16 port)
 	return make_sci(dev->dev_addr, port);
 }
 
-static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len)
+static void macsec_init_secy(struct net_device *dev, sci_t sci, u8 icv_len)
 {
 	struct macsec_dev *macsec = macsec_priv(dev);
 	struct macsec_secy *secy = &macsec->secy;
 
-	macsec->stats = netdev_alloc_pcpu_stats(struct pcpu_secy_stats);
-	if (!macsec->stats)
-		return -ENOMEM;
-
-	secy->tx_sc.stats = netdev_alloc_pcpu_stats(struct pcpu_tx_sc_stats);
-	if (!secy->tx_sc.stats)
-		return -ENOMEM;
-
-	secy->tx_sc.md_dst = metadata_dst_alloc(0, METADATA_MACSEC, GFP_KERNEL);
-	if (!secy->tx_sc.md_dst)
-		/* macsec and secy percpu stats will be freed when unregistering
-		 * net_device in macsec_free_netdev()
-		 */
-		return -ENOMEM;
-
 	if (sci == MACSEC_UNDEF_SCI)
 		sci = dev_to_sci(dev, MACSEC_PORT_ES);
 

@@ -4141,15 +4148,12 @@ static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len)
 	secy->xpn = DEFAULT_XPN;
 
 	secy->sci = sci;
-	secy->tx_sc.md_dst->u.macsec_info.sci = sci;
 	secy->tx_sc.active = true;
 	secy->tx_sc.encoding_sa = DEFAULT_ENCODING_SA;
 	secy->tx_sc.encrypt = DEFAULT_ENCRYPT;
 	secy->tx_sc.send_sci = DEFAULT_SEND_SCI;
 	secy->tx_sc.end_station = false;
 	secy->tx_sc.scb = false;
-
-	return 0;
 }
 
 static struct lock_class_key macsec_netdev_addr_lock_key;

@@ -4212,6 +4216,24 @@ static int macsec_newlink(struct net_device *dev,
 	if (rx_handler && rx_handler != macsec_handle_frame)
 		return -EBUSY;
 
+	if (is_zero_ether_addr(dev->dev_addr))
+		eth_hw_addr_inherit(dev, real_dev);
+
+	if (data && data[IFLA_MACSEC_SCI])
+		sci = nla_get_sci(data[IFLA_MACSEC_SCI]);
+	else if (data && data[IFLA_MACSEC_PORT])
+		sci = dev_to_sci(dev, nla_get_be16(data[IFLA_MACSEC_PORT]));
+	else
+		sci = dev_to_sci(dev, MACSEC_PORT_ES);
+
+	/* Registration can notify listeners before returning. */
+	macsec_init_secy(dev, sci, icv_len);
+	if (data) {
+		err = macsec_changelink_common(dev, data);
+		if (err)
+			return err;
+	}
+
 	err = register_netdevice(dev);
 	if (err < 0)
 		return err;

@@ -4224,31 +4246,11 @@ static int macsec_newlink(struct net_device *dev,
 	if (err < 0)
 		goto unregister;
 
-	/* need to be already registered so that ->init has run and
-	 * the MAC addr is set
-	 */
-	if (data && data[IFLA_MACSEC_SCI])
-		sci = nla_get_sci(data[IFLA_MACSEC_SCI]);
-	else if (data && data[IFLA_MACSEC_PORT])
-		sci = dev_to_sci(dev, nla_get_be16(data[IFLA_MACSEC_PORT]));
-	else
-		sci = dev_to_sci(dev, MACSEC_PORT_ES);
-
 	if (rx_handler && sci_exists(real_dev, sci)) {
 		err = -EBUSY;
 		goto unlink;
 	}
 
-	err = macsec_add_dev(dev, sci, icv_len);
-	if (err)
-		goto unlink;
-
-	if (data) {
-		err = macsec_changelink_common(dev, data);
-		if (err)
-			goto del_dev;
-	}
-
 	/* If h/w offloading is available, propagate to the device */
 	if (macsec_is_offloaded(macsec)) {
 		const struct macsec_ops *ops;

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Aleksei Sviridkin <[email protected]>

[ Upstream commit c2cdef41e0b4d8ed23a5b41e6ad4e64594e055e4 ]

The core and io supplies are only requested for ID_MT7530: both the devm_regulator_get() in probe and the regulator_enable() in mt7530_setup() are guarded by the switch id, but mt7530_remove() disables them unconditionally. On an MT7621 or an MT7531 both pointers are still NULL from devm_kzalloc(), so rmmod or a sysfs unbind calls regulator_disable() on NULL.

---
 drivers/net/dsa/mt7530-mdio.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

index 6cc2c8975af66..119fdbea57160 100644
@@ -227,15 +227,17 @@ mt7530_remove(struct mdio_device *mdiodev)
 	if (!priv)
 		return;
 
-	ret = regulator_disable(priv->core_pwr);
-	if (ret < 0)
-		dev_err(priv->dev,
-			"Failed to disable core power: %d\n", ret);
-
-	ret = regulator_disable(priv->io_pwr);
-	if (ret < 0)
-		dev_err(priv->dev, "Failed to disable io pwr: %d\n",
-			ret);
+	if (priv->id == ID_MT7530) {
+		ret = regulator_disable(priv->core_pwr);
+		if (ret < 0)
+			dev_err(priv->dev,
+				"Failed to disable core power: %d\n", ret);
+
+		ret = regulator_disable(priv->io_pwr);
+		if (ret < 0)
+			dev_err(priv->dev, "Failed to disable io pwr: %d\n",
+				ret);
+	}
 
 	mt7530_remove_common(priv);
 

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Aleksei Sviridkin <[email protected]>

[ Upstream commit 0d80ba0a204c6a16bd7778b50de578dff107c0fe ]

mt7530_remove_common() disposes the per-PHY interrupt mappings from .remove, but the regmap-irq chip that owns the domain is devm-registered, so its parent interrupt is only freed once .remove has returned. The switch's own regmap-irq thread can therefore still dispatch on a mapping that is already gone: irq_find_mapping() returns 0, irq_to_desc() returns NULL and handle_nested_irq() locks desc->lock without checking it. The attached PHYs have not given those interrupts back yet either, which the kernel warns about a moment before the fault.

regmap_del_irq_chip() disposes the same mappings itself, after freeing the parent interrupt and before removing the domain, so there is nothing left for the driver to do here. Until it runs the descriptors stay alive, and a late dispatch on one of them is harmless: dsa_unregister_switch() has freed the PHY handlers by then, so handle_nested_irq() finds no action and returns.

---
 drivers/net/dsa/mt7530.c | 3 ---
 1 file changed, 3 deletions(-)

index d7ebb7b8ee72c..4001779a91591 100644
@@ -3446,9 +3446,6 @@ EXPORT_SYMBOL_GPL(mt7530_probe_common);
 void
 mt7530_remove_common(struct mt7530_priv *priv)
 {
-	if (priv->irq_domain)
-		mt7530_free_mdio_irq(priv);
-
 	dsa_unregister_switch(priv->ds);
 
 	mutex_destroy(&priv->reg_mutex);

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yilin Zhang <[email protected]>

[ Upstream commit fe99bbeee5c5dbd3abc30721a8079ced59649d97 ]

When tcp_send_synack() replaces the cloned SYN skb at the head of the retransmit queue with a copy, it frees the original with tcp_rtx_queue_unlink_and_free() and only repairs tp->highest_sack. tp->retransmit_skb_hint keeps pointing at the freed skbuff_fclone_cache object.

The dangling hint is read in tcp_verify_retransmit_hint() and used as the root of the rbtree walk in tcp_xmit_retransmit_queue(). An unprivileged TFO client (sendmsg(MSG_FASTOPEN)) can arm the hint with an attacker-supplied ICMP fragmentation-needed message, after which a simultaneous open frees the armed SYN skb:

  BUG: KASAN: slab-use-after-free in tcp_mark_skb_lost (net/ipv4/tcp_input.c:1316)
  Read of size 4 at addr ffff88800604d928 by task swapper/1/0
  Call Trace:
   tcp_mark_skb_lost (net/ipv4/tcp_input.c:1316)
   tcp_simple_retransmit (net/ipv4/tcp_input.c:3158)
   tcp_v4_err (net/ipv4/tcp_ipv4.c:587)

Sync the hint to the copy.

---
 net/ipv4/tcp_output.c | 3 +++
 1 file changed, 3 insertions(+)

index 0cd46896e7983..3f9e11a43f35f 100644
@@ -3821,6 +3821,7 @@ void tcp_send_active_reset(struct sock *sk, enum sk_rst_reason reason)
  */
 int tcp_send_synack(struct sock *sk)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
 
 	skb = tcp_rtx_queue_head(sk);

@@ -3838,6 +3839,8 @@ int tcp_send_synack(struct sock *sk)
 			if (!nskb)
 				return -ENOMEM;
 			INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor);
+			if (skb == tp->retransmit_skb_hint)
+				tp->retransmit_skb_hint = nskb;
 			tcp_highest_sack_replace(sk, skb, nskb);
 			tcp_rtx_queue_unlink_and_free(skb, sk);
 			__skb_header_release(nskb);

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Aleksei Sviridkin <[email protected]>

[ Upstream commit a940003f44e7e441c228151dd212642152700ec8 ]

phylink_bringup_phy() stores the PHY in pl->phydev before its last fallible step: on a MAC whose phylink ops implement LPI, phy_eee_rx_clock_stop() can fail with a real MDIO error. The callers unwind with phy_detach(), which knows nothing about pl->phydev, so a pointer to a PHY that is no longer attached outlives the failed connect.

What that costs depends on how the caller got here. phylink_connect_phy() goes through phylink_attach_phy(), which refuses to attach while pl->phydev is set, turning a transient MDIO error into a permanent -EBUSY. The SFP path is worse than that: sfp_sm_probe_phy() answers the failure with phy_device_remove() and phy_device_free(), and it assigns sfp->mod_phy only past that error return, so nothing clears pl->phydev and it is left pointing at a freed phy_device that phylink_resolve() and the ethtool helpers go on reading. phylink_fwnode_phy_connect() has no such check, so a later connect overwrites the stale pointer and hides the problem. A disconnect does
not: phylink_disconnect_phy() hands that pointer to phy_disconnect(), and the second phy_detach() on the same PHY drops references the first one already released.

Found while making a DSA port survive a PHY whose driver arrives after the switch probes: keeping the port across a failed connect and retrying is what makes this window reachable.

Publish the pointer after the last call that can fail instead of unwinding it afterwards. Nothing between the two points reads pl->phydev, and the registration that follows cannot fail:
phy_request_interrupt() falls back to polling on its own. The PHY-side state keeps the order it had, so no MDIO operation moves relative to another.

---
 drivers/net/phy/phylink.c | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

index 848b6ec9bd85b..0b618842d41d7 100644
@@ -2115,7 +2115,6 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy,
 	mutex_lock(&pl->phydev_mutex);
 	mutex_lock(&phy->lock);
 	mutex_lock(&pl->state_mutex);
-	pl->phydev = phy;
 	pl->phy_state.interface = interface;
 	pl->phy_state.pause = MLO_PAUSE_NONE;
 	pl->phy_state.speed = SPEED_UNKNOWN;

@@ -2182,10 +2181,25 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy,
 			ret = 0;
 	}
 
-	if (ret == 0 && phy_interrupt_is_valid(phy))
+	if (ret)
+		return ret;
+
+	/* Nothing below can fail, so the PHY can be recorded now. Doing it
+	 * here rather than above keeps a failed bringup from leaving
+	 * pl->phydev pointing at a PHY the caller is about to detach.
+	 */
+	mutex_lock(&pl->phydev_mutex);
+	mutex_lock(&phy->lock);
+	mutex_lock(&pl->state_mutex);
+	pl->phydev = phy;
+	mutex_unlock(&pl->state_mutex);
+	mutex_unlock(&phy->lock);
+	mutex_unlock(&pl->phydev_mutex);
+
+	if (phy_interrupt_is_valid(phy))
 		phy_request_interrupt(phy);
 
-	return ret;
+	return 0;
 }
 
 static int phylink_attach_phy(struct phylink *pl, struct phy_device *phy,

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sang-Hoon Choi <[email protected]>

[ Upstream commit 1a983a4e14c635c40354be110cd9a1a5c94e01e6 ]

nfp_net_ipsec_rx() drops the XArray lock before taking a reference to the xfrm_state it found. The delete path can erase the entry and drop the last state reference in that interval. RX can then try to increment a zero refcount after the state has been queued for destruction.

The driver queues firmware invalidation asynchronously; the delete path does not wait for the command to complete or drain pending RX processing.

The XFRM garbage collector waits for an RCU grace period before freeing the state. That delays reclamation but does not make acquiring a reference from zero valid.

Take the xfrm_state reference before releasing the XArray lock so xa_erase() cannot run between lookup and reference acquisition.

---
 drivers/net/ethernet/netronome/nfp/crypto/ipsec.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index 9e7c285eaa6bc..960d7513aa8dd 100644
@@ -625,11 +625,12 @@ int nfp_net_ipsec_rx(struct nfp_meta_parsed *meta, struct sk_buff *skb)
 
 	xa_lock(&nn->xa_ipsec);
 	x = xa_load(&nn->xa_ipsec, saidx);
+	if (x)
+		xfrm_state_hold(x);
 	xa_unlock(&nn->xa_ipsec);
 	if (!x)
 		return -EINVAL;
 
-	xfrm_state_hold(x);
 	sp->xvec[sp->len++] = x;
 	sp->olen++;
 	xo = xfrm_offload(skb);

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sidraya Jayagond <[email protected]>

[ Upstream commit 61cb282fe97b3b0ba32ca09417a693162bf4ae3f ]

smcr_port_err() traverses smc_lgr_list.list without holding smc_lgr_list.lock, allowing a concurrent smc_lgr_terminate_sched() to free an lgr while it is still being dereferenced.

Hold smc_lgr_list.lock across the traversal. Update smc_ib_gid_check() to call smcr_port_err() after releasing the lock.

---
 net/smc/smc_core.c |  2 ++
 net/smc/smc_ib.c   | 10 ++++++++--
 2 files changed, 10 insertions(+), 2 deletions(-)

index 34fa809e95047..fff84df00cab3 100644
@@ -1835,6 +1835,7 @@ void smcr_port_err(struct smc_ib_device *smcibdev, u8 ibport)
 	struct smc_link_group *lgr, *n;
 	int i;
 
+	spin_lock_bh(&smc_lgr_list.lock);
 	list_for_each_entry_safe(lgr, n, &smc_lgr_list.list, list) {
 		if (strncmp(smcibdev->pnetid[ibport - 1], lgr->pnet_id,
 			    SMC_MAX_PNETID_LEN))

@@ -1849,6 +1850,7 @@ void smcr_port_err(struct smc_ib_device *smcibdev, u8 ibport)
 				smcr_link_down_cond_sched(lnk);
 		}
 	}
+	spin_unlock_bh(&smc_lgr_list.lock);
 }
 
 static void smc_link_down_work(struct work_struct *work)

index 0052f02756ebb..845f15ed06bf1 100644
@@ -333,6 +333,7 @@ static bool smc_ib_check_link_gid(u8 gid[SMC_GID_SIZE], bool smcrv2,
 static void smc_ib_gid_check(struct smc_ib_device *smcibdev, u8 ibport)
 {
 	struct smc_link_group *lgr;
+	bool stale_gid = false;
 	int i;
 
 	spin_lock_bh(&smc_lgr_list.lock);

@@ -348,11 +349,16 @@ static void smc_ib_gid_check(struct smc_ib_device *smcibdev, u8 ibport)
 				continue;
 			if (!smc_ib_check_link_gid(lgr->lnk[i].gid,
 						   lgr->smc_version == SMC_V2,
-						   smcibdev, ibport))
-				smcr_port_err(smcibdev, ibport);
+						   smcibdev, ibport)) {
+				stale_gid = true;
+				goto out;
+			}
 		}
 	}
+out:
 	spin_unlock_bh(&smc_lgr_list.lock);
+	if (stale_gid)
+		smcr_port_err(smcibdev, ibport);
 }
 
 static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport)

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ginger Li <[email protected]>

[ Upstream commit 8e1937fed6738460554ec123c64839e2445e7d53 ]

mon_timeout() evaluates dom_size(mon->peer_cnt) before it takes mon->lock, while mon->peer_cnt is updated under that lock by tipc_mon_add_peer() and tipc_mon_remove_peer(). The value can therefore be stale, and the decision whether the local domain has to be recomputed can be based on an outdated member count.

Read mon->peer_cnt inside the write_lock_bh(&mon->lock) protected region.

---
 net/tipc/monitor.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index 572b79bf76ce1..f47d0dba5e8fe 100644
@@ -632,9 +632,10 @@ static void mon_timeout(struct timer_list *t)
 {
 	struct tipc_monitor *mon = timer_container_of(mon, t, timer);
 	struct tipc_peer *self;
-	int best_member_cnt = dom_size(mon->peer_cnt) - 1;
+	int best_member_cnt;
 
 	write_lock_bh(&mon->lock);
+	best_member_cnt = dom_size(mon->peer_cnt) - 1;
 	self = mon->self;
 	if (self && (best_member_cnt != self->applied)) {
 		mon_update_local_domain(mon);

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Coia Prant <[email protected]>

[ Upstream commit 8db67bb6a1fffa4df68fbbc22e39943aeeff9178 ]

gmac_clk_enable() enables the bulk clocks first and then the optional PHY clock. If clk_prepare_enable() on the PHY clock fails, the function returns without rolling back the bulk clocks, and bsp_priv->clk_enabled stays false, so the later gmac_clk_enable(bsp_priv, false) becomes a no-op and the bulk clock references are leaked.

Add the missing clk_bulk_disable_unprepare() on that failure path.

---
 drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

index 643578266dfca..8580175a5f926 100644
@@ -1434,8 +1434,11 @@ static int gmac_clk_enable(struct rk_priv_data *bsp_priv, bool enable)
 				return ret;
 
 			ret = clk_prepare_enable(bsp_priv->clk_phy);
-			if (ret)
+			if (ret) {
+				clk_bulk_disable_unprepare(bsp_priv->num_clks,
+							   bsp_priv->clks);
 				return ret;
+			}
 
 			if (bsp_priv->ops && bsp_priv->ops->set_clock_selection)
 				bsp_priv->ops->set_clock_selection(bsp_priv,

2.53.0

6.18-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ankit Garg <[email protected]>

[ Upstream commit c30fd916c4d7760ccf654e52370b0a31be885789 ]

Refactor the ethtool ring parameter configuration logic to address two
issues: unnecessary queue resets and lost configuration changes when the interface is down.

Previously, gve_set_ringparam could trigger multiple queue destructions and recreations for a single command, as different settings (e.g., header split, ring sizes) were applied one by one. Furthermore, if the interface was down, any changes made via ethtool were discarded instead of being saved for the next time the interface was brought up.

This patch centralizes the configuration logic. Individual functions like gve_set_hsplit_config are modified to only validate and stage changes in a temporary config struct.

The main gve_set_ringparam function now gathers all staged changes and applies them as a single, combined configuration:
1. If the interface is up, it calls gve_adjust_config once.
2. If the interface is down, it saves the settings directly to the driver's private struct, ensuring they persist and are used when the interface is brought back up.

Stable-dep-of: 3b430ea62340 ("gve: fix TX drop when GSO MSS is too small for hw")

---
 drivers/net/ethernet/google/gve/gve.h         |  3 +-
 drivers/net/ethernet/google/gve/gve_ethtool.c | 86 +++++++++----------
 drivers/net/ethernet/google/gve/gve_main.c    | 17 ++--
 3 files changed, 51 insertions(+), 55 deletions(-)

index 9e7d6860b83fa..64075bdc6789b 100644
@@ -1254,7 +1254,8 @@ void gve_rx_start_ring_gqi(struct gve_priv *priv, int idx);
 void gve_rx_stop_ring_gqi(struct gve_priv *priv, int idx);
 u16 gve_get_pkt_buf_size(const struct gve_priv *priv, bool enable_hplit);
 bool gve_header_split_supported(const struct gve_priv *priv);
-int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split);
+int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split,
+			  struct gve_rx_alloc_rings_cfg *rx_alloc_cfg);
 /* rx buffer handling */
 int gve_buf_ref_cnt(struct gve_rx_buf_state_dqo *bs);
 void gve_free_page_dqo(struct gve_priv *priv, struct gve_rx_buf_state_dqo *bs,

index 9751049849432..78e72a1e71824 100644
@@ -2058,12 +2058,10 @@ bool gve_header_split_supported(const struct gve_priv *priv)
 		priv->queue_format == GVE_DQO_RDA_FORMAT && !priv->xdp_prog;
 }
 
-int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split)
+int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split,
+			  struct gve_rx_alloc_rings_cfg *rx_alloc_cfg)
 {
-	struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0};
-	struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0};
 	bool enable_hdr_split;
-	int err = 0;
 
 	if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_UNKNOWN)
 		return 0;