Merging upstream version 6.9.8.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

16 files changed, 175 insertions, 51 deletions

diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index ac74f6ead6..8f6dd2c6ee 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -12,6 +12,7 @@
 #include <linux/errno.h>
 #include <linux/etherdevice.h>
 #include <linux/gfp.h>
+#include <linux/if_vlan.h>
 #include <linux/jiffies.h>
 #include <linux/kref.h>
 #include <linux/list.h>
@@ -132,6 +133,29 @@ batadv_orig_node_vlan_get(struct batadv_orig_node *orig_node,
 }
 
 /**
+ * batadv_vlan_id_valid() - check if vlan id is in valid batman-adv encoding
+ * @vid: the VLAN identifier
+ *
+ * Return: true when either no vlan is set or if VLAN is in correct range,
+ *  false otherwise
+ */
+static bool batadv_vlan_id_valid(unsigned short vid)
+{
+	unsigned short non_vlan = vid & ~(BATADV_VLAN_HAS_TAG | VLAN_VID_MASK);
+
+	if (vid == 0)
+		return true;
+
+	if (!(vid & BATADV_VLAN_HAS_TAG))
+		return false;
+
+	if (non_vlan)
+		return false;
+
+	return true;
+}
+
+/**
  * batadv_orig_node_vlan_new() - search and possibly create an orig_node_vlan
  *  object
  * @orig_node: the originator serving the VLAN
@@ -149,6 +173,9 @@ batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node,
 {
 	struct batadv_orig_node_vlan *vlan;
 
+	if (!batadv_vlan_id_valid(vid))
+		return NULL;
+
 	spin_lock_bh(&orig_node->vlan_list_lock);
 
 	/* first look if an object for this vid already exists */
diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c
index a6fb89fa62..7e8a20f2fc 100644
--- a/net/can/j1939/main.c
+++ b/net/can/j1939/main.c
@@ -30,10 +30,6 @@ MODULE_ALIAS("can-proto-" __stringify(CAN_J1939));
 /* CAN_HDR: #bytes before can_frame data part */
 #define J1939_CAN_HDR (offsetof(struct can_frame, data))
 
-/* CAN_FTR: #bytes beyond data part */
-#define J1939_CAN_FTR (sizeof(struct can_frame) - J1939_CAN_HDR - \
-		 sizeof(((struct can_frame *)0)->data))
-
 /* lowest layer */
 static void j1939_can_recv(struct sk_buff *iskb, void *data)
 {
@@ -342,7 +338,7 @@ int j1939_send_one(struct j1939_priv *priv, struct sk_buff *skb)
 	memset(cf, 0, J1939_CAN_HDR);
 
 	/* make it a full can frame again */
-	skb_put(skb, J1939_CAN_FTR + (8 - dlc));
+	skb_put_zero(skb, 8 - dlc);
 
 	canid = CAN_EFF_FLAG |
 		(skcb->priority << 26) |
diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index fe3df23a25..4be73de503 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -1593,8 +1593,8 @@ j1939_session *j1939_xtp_rx_rts_session_new(struct j1939_priv *priv,
 	struct j1939_sk_buff_cb skcb = *j1939_skb_to_cb(skb);
 	struct j1939_session *session;
 	const u8 *dat;
+	int len, ret;
 	pgn_t pgn;
-	int len;
 
 	netdev_dbg(priv->ndev, "%s\n", __func__);
 
@@ -1653,7 +1653,22 @@ j1939_session *j1939_xtp_rx_rts_session_new(struct j1939_priv *priv,
 	session->tskey = priv->rx_tskey++;
 	j1939_sk_errqueue(session, J1939_ERRQUEUE_RX_RTS);
 
-	WARN_ON_ONCE(j1939_session_activate(session));
+	ret = j1939_session_activate(session);
+	if (ret) {
+		/* Entering this scope indicates an issue with the J1939 bus.
+		 * Possible scenarios include:
+		 * - A time lapse occurred, and a new session was initiated
+		 *   due to another packet being sent correctly. This could
+		 *   have been caused by too long interrupt, debugger, or being
+		 *   out-scheduled by another task.
+		 * - The bus is receiving numerous erroneous packets, either
+		 *   from a malfunctioning device or during a test scenario.
+		 */
+		netdev_alert(priv->ndev, "%s: 0x%p: concurrent session with same addr (%02x %02x) is already active.\n",
+			     __func__, session, skcb.addr.sa, skcb.addr.da);
+		j1939_session_put(session);
+		return NULL;
+	}
 
 	return session;
 }
@@ -1681,6 +1696,8 @@ static int j1939_xtp_rx_rts_session_active(struct j1939_session *session,
 
 		j1939_session_timers_cancel(session);
 		j1939_session_cancel(session, J1939_XTP_ABORT_BUSY);
+		if (session->transmission)
+			j1939_session_deactivate_activate_next(session);
 
 		return -EBUSY;
 	}
diff --git a/net/core/filter.c b/net/core/filter.c
index ce255e0a2f..15d850ea7d 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -87,6 +87,9 @@
 
 #include "dev.h"
 
+/* Keep the struct bpf_fib_lookup small so that it fits into a cacheline */
+static_assert(sizeof(struct bpf_fib_lookup) == 64, "struct bpf_fib_lookup size check");
+
 static const struct bpf_func_proto *
 bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog);
 
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 41693154e4..022c12059c 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -295,10 +295,8 @@ static struct xdp_mem_allocator *__xdp_reg_mem_model(struct xdp_mem_info *mem,
 		mutex_lock(&mem_id_lock);
 		ret = __mem_id_init_hash_table();
 		mutex_unlock(&mem_id_lock);
-		if (ret < 0) {
-			WARN_ON(1);
+		if (ret < 0)
 			return ERR_PTR(ret);
-		}
 	}
 
 	xdp_alloc = kzalloc(sizeof(*xdp_alloc), gfp);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 44b033fe1e..f94d30b171 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -655,8 +655,11 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	if (dccp_v4_send_response(sk, req))
 		goto drop_and_free;
 
-	inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
-	reqsk_put(req);
+	if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT)))
+		reqsk_free(req);
+	else
+		reqsk_put(req);
+
 	return 0;
 
 drop_and_free:
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index ded07e09f8..ddbd490b35 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -398,8 +398,11 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	if (dccp_v6_send_response(sk, req))
 		goto drop_and_free;
 
-	inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
-	reqsk_put(req);
+	if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT)))
+		reqsk_free(req);
+	else
+		reqsk_put(req);
+
 	return 0;
 
 drop_and_free:
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 3b38610958..39e9070fe3 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1121,25 +1121,34 @@ drop:
 	inet_csk_reqsk_queue_drop_and_put(oreq->rsk_listener, oreq);
 }
 
-static void reqsk_queue_hash_req(struct request_sock *req,
+static bool reqsk_queue_hash_req(struct request_sock *req,
 				 unsigned long timeout)
 {
+	bool found_dup_sk = false;
+
+	if (!inet_ehash_insert(req_to_sk(req), NULL, &found_dup_sk))
+		return false;
+
+	/* The timer needs to be setup after a successful insertion. */
 	timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED);
 	mod_timer(&req->rsk_timer, jiffies + timeout);
 
-	inet_ehash_insert(req_to_sk(req), NULL, NULL);
 	/* before letting lookups find us, make sure all req fields
 	 * are committed to memory and refcnt initialized.
 	 */
 	smp_wmb();
 	refcount_set(&req->rsk_refcnt, 2 + 1);
+	return true;
 }
 
-void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
+bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
 				   unsigned long timeout)
 {
-	reqsk_queue_hash_req(req, timeout);
+	if (!reqsk_queue_hash_req(req, timeout))
+		return false;
+
 	inet_csk_reqsk_queue_added(sk);
+	return true;
 }
 EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 1054a44033..0953c915bb 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2779,13 +2779,37 @@ static void tcp_mtup_probe_success(struct sock *sk)
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMTUPSUCCESS);
 }
 
+/* Sometimes we deduce that packets have been dropped due to reasons other than
+ * congestion, like path MTU reductions or failed client TFO attempts. In these
+ * cases we call this function to retransmit as many packets as cwnd allows,
+ * without reducing cwnd. Given that retransmits will set retrans_stamp to a
+ * non-zero value (and may do so in a later calling context due to TSQ), we
+ * also enter CA_Loss so that we track when all retransmitted packets are ACKed
+ * and clear retrans_stamp when that happens (to ensure later recurring RTOs
+ * are using the correct retrans_stamp and don't declare ETIMEDOUT
+ * prematurely).
+ */
+static void tcp_non_congestion_loss_retransmit(struct sock *sk)
+{
+	const struct inet_connection_sock *icsk = inet_csk(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (icsk->icsk_ca_state != TCP_CA_Loss) {
+		tp->high_seq = tp->snd_nxt;
+		tp->snd_ssthresh = tcp_current_ssthresh(sk);
+		tp->prior_ssthresh = 0;
+		tp->undo_marker = 0;
+		tcp_set_ca_state(sk, TCP_CA_Loss);
+	}
+	tcp_xmit_retransmit_queue(sk);
+}
+
 /* Do a simple retransmit without using the backoff mechanisms in
  * tcp_timer. This is used for path mtu discovery.
  * The socket is already locked here.
  */
 void tcp_simple_retransmit(struct sock *sk)
 {
-	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
 	int mss;
@@ -2825,14 +2849,7 @@ void tcp_simple_retransmit(struct sock *sk)
 	 * in network, but units changed and effective
 	 * cwnd/ssthresh really reduced now.
 	 */
-	if (icsk->icsk_ca_state != TCP_CA_Loss) {
-		tp->high_seq = tp->snd_nxt;
-		tp->snd_ssthresh = tcp_current_ssthresh(sk);
-		tp->prior_ssthresh = 0;
-		tp->undo_marker = 0;
-		tcp_set_ca_state(sk, TCP_CA_Loss);
-	}
-	tcp_xmit_retransmit_queue(sk);
+	tcp_non_congestion_loss_retransmit(sk);
 }
 EXPORT_SYMBOL(tcp_simple_retransmit);
 
@@ -6288,8 +6305,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 			tp->fastopen_client_fail = TFO_DATA_NOT_ACKED;
 		skb_rbtree_walk_from(data)
 			 tcp_mark_skb_lost(sk, data);
-		tcp_xmit_retransmit_queue(sk);
-		tp->retrans_stamp = 0;
+		tcp_non_congestion_loss_retransmit(sk);
 		NET_INC_STATS(sock_net(sk),
 				LINUX_MIB_TCPFASTOPENACTIVEFAIL);
 		return true;
@@ -7243,7 +7259,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		tcp_rsk(req)->tfo_listener = false;
 		if (!want_cookie) {
 			req->timeout = tcp_timeout_init((struct sock *)req);
-			inet_csk_reqsk_queue_hash_add(sk, req, req->timeout);
+			if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req,
+								    req->timeout))) {
+				reqsk_free(req);
+				return 0;
+			}
+
 		}
 		af_ops->send_synack(sk, dst, &fl, req, &foc,
 				    !want_cookie ? TCP_SYNACK_NORMAL :
diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index a4ab615ca3..5e37a8ceeb 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -520,7 +520,7 @@ static void iucv_setmask_mp(void)
  */
 static void iucv_setmask_up(void)
 {
-	cpumask_t cpumask;
+	static cpumask_t cpumask;
 	int cpu;
 
 	/* Disable all cpu but the first in cpu_irq_cpumask. */
@@ -628,23 +628,33 @@ static int iucv_cpu_online(unsigned int cpu)
 
 static int iucv_cpu_down_prep(unsigned int cpu)
 {
-	cpumask_t cpumask;
+	cpumask_var_t cpumask;
+	int ret = 0;
 
 	if (!iucv_path_table)
 		return 0;
 
-	cpumask_copy(&cpumask, &iucv_buffer_cpumask);
-	cpumask_clear_cpu(cpu, &cpumask);
-	if (cpumask_empty(&cpumask))
+	if (!alloc_cpumask_var(&cpumask, GFP_KERNEL))
+		return -ENOMEM;
+
+	cpumask_copy(cpumask, &iucv_buffer_cpumask);
+	cpumask_clear_cpu(cpu, cpumask);
+	if (cpumask_empty(cpumask)) {
 		/* Can't offline last IUCV enabled cpu. */
-		return -EINVAL;
+		ret = -EINVAL;
+		goto __free_cpumask;
+	}
 
 	iucv_retrieve_cpu(NULL);
 	if (!cpumask_empty(&iucv_irq_cpumask))
-		return 0;
+		goto __free_cpumask;
+
 	smp_call_function_single(cpumask_first(&iucv_buffer_cpumask),
 				 iucv_allow_cpu, NULL, 1);
-	return 0;
+
+__free_cpumask:
+	free_cpumask_var(cpumask);
+	return ret;
 }
 
 /**
diff --git a/net/netfilter/nf_hooks_lwtunnel.c b/net/netfilter/nf_hooks_lwtunnel.c
index 7cdb59bb44..d8ebebc977 100644
--- a/net/netfilter/nf_hooks_lwtunnel.c
+++ b/net/netfilter/nf_hooks_lwtunnel.c
@@ -117,4 +117,7 @@ void netfilter_lwtunnel_fini(void)
 {
 	unregister_pernet_subsys(&nf_lwtunnel_net_ops);
 }
+#else
+int __init netfilter_lwtunnel_init(void) { return 0; }
+void netfilter_lwtunnel_fini(void) {}
 #endif /* CONFIG_SYSCTL */
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 167074283e..faa77b031d 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5740,8 +5740,7 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
 
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) &&
 	    nft_data_dump(skb, NFTA_SET_ELEM_DATA, nft_set_ext_data(ext),
-			  set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE,
-			  set->dlen) < 0)
+			  nft_set_datatype(set), set->dlen) < 0)
 		goto nla_put_failure;
 
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS) &&
@@ -11069,6 +11068,9 @@ static int nft_validate_register_store(const struct nft_ctx *ctx,
 
 		return 0;
 	default:
+		if (type != NFT_DATA_VALUE)
+			return -EINVAL;
+
 		if (reg < NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE)
 			return -EINVAL;
 		if (len == 0)
@@ -11077,8 +11079,6 @@ static int nft_validate_register_store(const struct nft_ctx *ctx,
 		    sizeof_field(struct nft_regs, data))
 			return -ERANGE;
 
-		if (data != NULL && type != NFT_DATA_VALUE)
-			return -EINVAL;
 		return 0;
 	}
 }
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index b314ca728a..f3080fa1b2 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -132,7 +132,8 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
 			return -EINVAL;
 
 		err = nft_parse_register_store(ctx, tb[NFTA_LOOKUP_DREG],
-					       &priv->dreg, NULL, set->dtype,
+					       &priv->dreg, NULL,
+					       nft_set_datatype(set),
 					       set->dlen);
 		if (err < 0)
 			return err;
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 2928c142a2..3b980bf277 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -168,8 +168,13 @@ static u32 ovs_ct_get_mark(const struct nf_conn *ct)
 static void ovs_ct_get_labels(const struct nf_conn *ct,
 			      struct ovs_key_ct_labels *labels)
 {
-	struct nf_conn_labels *cl = ct ? nf_ct_labels_find(ct) : NULL;
+	struct nf_conn_labels *cl = NULL;
 
+	if (ct) {
+		if (ct->master && !nf_ct_is_confirmed(ct))
+			ct = ct->master;
+		cl = nf_ct_labels_find(ct);
+	}
 	if (cl)
 		memcpy(labels, cl->bits, OVS_CT_LABELS_LEN);
 	else
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 2b4b1276d4..d9cda1e53a 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1557,9 +1557,11 @@ out_drop:
  */
 void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp)
 {
+	struct rpc_timeout timeout = {
+		.to_increment		= 0,
+	};
 	struct rpc_task *task;
 	int proc_error;
-	struct rpc_timeout timeout;
 
 	/* Build the svc_rqst used by the common processing routine */
 	rqstp->rq_xid = req->rq_xid;
@@ -1612,6 +1614,7 @@ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp)
 		timeout.to_initval = req->rq_xprt->timeout->to_initval;
 		timeout.to_retries = req->rq_xprt->timeout->to_retries;
 	}
+	timeout.to_maxval = timeout.to_initval;
 	memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf));
 	task = rpc_run_bc_task(req, &timeout);
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 68a58bc07c..24286ce0ef 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2660,10 +2660,24 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 {
 	struct unix_sock *u = unix_sk(sk);
 
-	if (!unix_skb_len(skb) && !(flags & MSG_PEEK)) {
-		skb_unlink(skb, &sk->sk_receive_queue);
-		consume_skb(skb);
-		skb = NULL;
+	if (!unix_skb_len(skb)) {
+		struct sk_buff *unlinked_skb = NULL;
+
+		spin_lock(&sk->sk_receive_queue.lock);
+
+		if (copied && (!u->oob_skb || skb == u->oob_skb)) {
+			skb = NULL;
+		} else if (flags & MSG_PEEK) {
+			skb = skb_peek_next(skb, &sk->sk_receive_queue);
+		} else {
+			unlinked_skb = skb;
+			skb = skb_peek_next(skb, &sk->sk_receive_queue);
+			__skb_unlink(unlinked_skb, &sk->sk_receive_queue);
+		}
+
+		spin_unlock(&sk->sk_receive_queue.lock);
+
+		consume_skb(unlinked_skb);
 	} else {
 		struct sk_buff *unlinked_skb = NULL;
 
@@ -3140,12 +3154,23 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 #if IS_ENABLED(CONFIG_AF_UNIX_OOB)
 	case SIOCATMARK:
 		{
+			struct unix_sock *u = unix_sk(sk);
 			struct sk_buff *skb;
 			int answ = 0;
 
+			mutex_lock(&u->iolock);
+
 			skb = skb_peek(&sk->sk_receive_queue);
-			if (skb && skb == READ_ONCE(unix_sk(sk)->oob_skb))
-				answ = 1;
+			if (skb) {
+				struct sk_buff *oob_skb = READ_ONCE(u->oob_skb);
+
+				if (skb == oob_skb ||
+				    (!oob_skb && !unix_skb_len(skb)))
+					answ = 1;
+			}
+
+			mutex_unlock(&u->iolock);
+
 			err = put_user(answ, (int __user *)arg);
 		}
 		break;