Merging upstream version 6.1.90.

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

8 files changed, 91 insertions, 20 deletions

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 86eb2aba1..5bcc63ead 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -437,6 +437,10 @@ static inline void in6_ifa_hold(struct inet6_ifaddr *ifp)
 	refcount_inc(&ifp->refcnt);
 }
 
+static inline bool in6_ifa_hold_safe(struct inet6_ifaddr *ifp)
+{
+	return refcount_inc_not_zero(&ifp->refcnt);
+}
 
 /*
  *	compute link-local solicited-node multicast address
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 0920b669b..e7d71a516 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -54,7 +54,7 @@ struct unix_sock {
 	struct mutex		iolock, bindlock;
 	struct sock		*peer;
 	struct list_head	link;
-	atomic_long_t		inflight;
+	unsigned long		inflight;
 	spinlock_t		lock;
 	unsigned long		gc_flags;
 #define UNIX_GC_CANDIDATE	0
@@ -79,6 +79,9 @@ enum unix_socket_lock_class {
 	U_LOCK_NORMAL,
 	U_LOCK_SECOND,	/* for double locking, see unix_state_double_lock(). */
 	U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */
+	U_LOCK_GC_LISTENER, /* used for listening socket while determining gc
+			     * candidates to close a small race window.
+			     */
 };
 
 static inline void unix_state_lock_nested(struct sock *sk,
diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index bcc5a4cd2..5aaf7d7f3 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -565,6 +565,15 @@ static inline struct sk_buff *bt_skb_sendmmsg(struct sock *sk,
 	return skb;
 }
 
+static inline int bt_copy_from_sockptr(void *dst, size_t dst_size,
+				       sockptr_t src, size_t src_size)
+{
+	if (dst_size > src_size)
+		return -EINVAL;
+
+	return copy_from_sockptr(dst, src, dst_size);
+}
+
 int bt_to_errno(u16 code);
 __u8 bt_status(int err);
 
diff --git a/include/net/dsa.h b/include/net/dsa.h
index ee369670e..f96b61d97 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -969,6 +969,14 @@ struct dsa_switch_ops {
 	void	(*port_disable)(struct dsa_switch *ds, int port);
 
 	/*
+	 * Compatibility between device trees defining multiple CPU ports and
+	 * drivers which are not OK to use by default the numerically smallest
+	 * CPU port of a switch for its local ports. This can return NULL,
+	 * meaning "don't know/don't care".
+	 */
+	struct dsa_port *(*preferred_default_local_cpu_port)(struct dsa_switch *ds);
+
+	/*
 	 * Port's MAC EEE settings
 	 */
 	int	(*set_mac_eee)(struct dsa_switch *ds, int port,
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index bca80522f..f9906b73e 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -351,6 +351,39 @@ static inline bool pskb_inet_may_pull(struct sk_buff *skb)
 	return pskb_network_may_pull(skb, nhlen);
 }
 
+/* Variant of pskb_inet_may_pull().
+ */
+static inline bool skb_vlan_inet_prepare(struct sk_buff *skb)
+{
+	int nhlen = 0, maclen = ETH_HLEN;
+	__be16 type = skb->protocol;
+
+	/* Essentially this is skb_protocol(skb, true)
+	 * And we get MAC len.
+	 */
+	if (eth_type_vlan(type))
+		type = __vlan_get_protocol(skb, type, &maclen);
+
+	switch (type) {
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		nhlen = sizeof(struct ipv6hdr);
+		break;
+#endif
+	case htons(ETH_P_IP):
+		nhlen = sizeof(struct iphdr);
+		break;
+	}
+	/* For ETH_P_IPV6/ETH_P_IP we make sure to pull
+	 * a base network header in skb->head.
+	 */
+	if (!pskb_may_pull(skb, maclen + nhlen))
+		return false;
+
+	skb_set_network_header(skb, maclen);
+	return true;
+}
+
 static inline int ip_encap_hlen(struct ip_tunnel_encap *e)
 {
 	const struct ip_tunnel_encap_ops *ops;
diff --git a/include/net/macsec.h b/include/net/macsec.h
index 65c93959c..dd578d193 100644
--- a/include/net/macsec.h
+++ b/include/net/macsec.h
@@ -302,6 +302,7 @@ struct macsec_ops {
 	int (*mdo_get_tx_sa_stats)(struct macsec_context *ctx);
 	int (*mdo_get_rx_sc_stats)(struct macsec_context *ctx);
 	int (*mdo_get_rx_sa_stats)(struct macsec_context *ctx);
+	bool rx_uses_md_dst;
 };
 
 void macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa);
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 4a767b3d2..df7775afb 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -335,7 +335,7 @@ int nf_flow_rule_route_ipv6(struct net *net, struct flow_offload *flow,
 int nf_flow_table_offload_init(void);
 void nf_flow_table_offload_exit(void);
 
-static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb)
+static inline __be16 __nf_flow_pppoe_proto(const struct sk_buff *skb)
 {
 	__be16 proto;
 
@@ -351,6 +351,16 @@ static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb)
 	return 0;
 }
 
+static inline bool nf_flow_pppoe_proto(struct sk_buff *skb, __be16 *inner_proto)
+{
+	if (!pskb_may_pull(skb, PPPOE_SES_HLEN))
+		return false;
+
+	*inner_proto = __nf_flow_pppoe_proto(skb);
+
+	return true;
+}
+
 #define NF_FLOW_TABLE_STAT_INC(net, count) __this_cpu_inc((net)->ft.stat->count)
 #define NF_FLOW_TABLE_STAT_DEC(net, count) __this_cpu_dec((net)->ft.stat->count)
 #define NF_FLOW_TABLE_STAT_INC_ATOMIC(net, count)	\
diff --git a/include/net/sock.h b/include/net/sock.h
index 60577751e..77298c748 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1483,33 +1483,36 @@ sk_memory_allocated(const struct sock *sk)
 
 /* 1 MB per cpu, in page units */
 #define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT))
+extern int sysctl_mem_pcpu_rsv;
+
+static inline void proto_memory_pcpu_drain(struct proto *proto)
+{
+	int val = this_cpu_xchg(*proto->per_cpu_fw_alloc, 0);
+
+	if (val)
+		atomic_long_add(val, proto->memory_allocated);
+}
 
 static inline void
-sk_memory_allocated_add(struct sock *sk, int amt)
+sk_memory_allocated_add(const struct sock *sk, int val)
 {
-	int local_reserve;
+	struct proto *proto = sk->sk_prot;
 
-	preempt_disable();
-	local_reserve = __this_cpu_add_return(*sk->sk_prot->per_cpu_fw_alloc, amt);
-	if (local_reserve >= SK_MEMORY_PCPU_RESERVE) {
-		__this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve);
-		atomic_long_add(local_reserve, sk->sk_prot->memory_allocated);
-	}
-	preempt_enable();
+	val = this_cpu_add_return(*proto->per_cpu_fw_alloc, val);
+
+	if (unlikely(val >= READ_ONCE(sysctl_mem_pcpu_rsv)))
+		proto_memory_pcpu_drain(proto);
 }
 
 static inline void
-sk_memory_allocated_sub(struct sock *sk, int amt)
+sk_memory_allocated_sub(const struct sock *sk, int val)
 {
-	int local_reserve;
+	struct proto *proto = sk->sk_prot;
 
-	preempt_disable();
-	local_reserve = __this_cpu_sub_return(*sk->sk_prot->per_cpu_fw_alloc, amt);
-	if (local_reserve <= -SK_MEMORY_PCPU_RESERVE) {
-		__this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve);
-		atomic_long_add(local_reserve, sk->sk_prot->memory_allocated);
-	}
-	preempt_enable();
+	val = this_cpu_sub_return(*proto->per_cpu_fw_alloc, val);
+
+	if (unlikely(val <= -READ_ONCE(sysctl_mem_pcpu_rsv)))
+		proto_memory_pcpu_drain(proto);
 }
 
 #define SK_ALLOC_PERCPU_COUNTER_BATCH 16