Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Trivial conflict in net/netfilter/nf_tables_api.c.

Duplicate fix in tools/testing/selftests/net/devlink_port_split.py
- take the net-next version.

skmsg, and L4 bpf - keep the bpf code but remove the flags
and err params.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

10 files changed, 50 insertions, 20 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index be1dcceda5e4..eaf5bb008aa9 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4114,7 +4114,7 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev,
 		return NET_RX_DROP;
 	}
 
-	skb_scrub_packet(skb, true);
+	skb_scrub_packet(skb, !net_eq(dev_net(dev), dev_net(skb->dev)));
 	skb->priority = 0;
 	return 0;
 }
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 31866031e370..96f319099744 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -126,7 +126,6 @@ int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
 			      struct sk_msg *msg, u32 bytes);
 int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
 			     struct sk_msg *msg, u32 bytes);
-int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, long timeo);
 int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 		   int len, int flags);
 
diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index dc5c1e69cd9f..69c9eabf8325 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -319,12 +319,14 @@ flow_action_mixed_hw_stats_check(const struct flow_action *action,
 	if (flow_offload_has_one_action(action))
 		return true;
 
-	flow_action_for_each(i, action_entry, action) {
-		if (i && action_entry->hw_stats != last_hw_stats) {
-			NL_SET_ERR_MSG_MOD(extack, "Mixing HW stats types for actions is not supported");
-			return false;
+	if (action) {
+		flow_action_for_each(i, action_entry, action) {
+			if (i && action_entry->hw_stats != last_hw_stats) {
+				NL_SET_ERR_MSG_MOD(extack, "Mixing HW stats types for actions is not supported");
+				return false;
+			}
+			last_hw_stats = action_entry->hw_stats;
 		}
-		last_hw_stats = action_entry->hw_stats;
 	}
 	return true;
 }
diff --git a/include/net/ip.h b/include/net/ip.h
index e20874059f82..d9683bef8684 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -31,6 +31,7 @@
 #include <net/flow.h>
 #include <net/flow_dissector.h>
 #include <net/netns/hash.h>
+#include <net/lwtunnel.h>
 
 #define IPV4_MAX_PMTU		65535U		/* RFC 2675, Section 5.1 */
 #define IPV4_MIN_MTU		68			/* RFC 791 */
@@ -445,22 +446,25 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 
 	/* 'forwarding = true' case should always honour route mtu */
 	mtu = dst_metric_raw(dst, RTAX_MTU);
-	if (mtu)
-		return mtu;
+	if (!mtu)
+		mtu = min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU);
 
-	return min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU);
+	return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
 }
 
 static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
 					  const struct sk_buff *skb)
 {
+	unsigned int mtu;
+
 	if (!sk || !sk_fullsock(sk) || ip_sk_use_pmtu(sk)) {
 		bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED;
 
 		return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding);
 	}
 
-	return min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU);
+	mtu = min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU);
+	return mtu - lwtunnel_headroom(skb_dst(skb)->lwtstate, mtu);
 }
 
 struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx,
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index f51a118bfce8..f14149df5a65 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -265,11 +265,18 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 
 static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
 {
+	int mtu;
+
 	struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ?
 				inet6_sk(skb->sk) : NULL;
 
-	return (np && np->pmtudisc >= IPV6_PMTUDISC_PROBE) ?
-	       skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb));
+	if (np && np->pmtudisc >= IPV6_PMTUDISC_PROBE) {
+		mtu = READ_ONCE(skb_dst(skb)->dev->mtu);
+		mtu -= lwtunnel_headroom(skb_dst(skb)->lwtstate, mtu);
+	} else
+		mtu = dst_mtu(skb_dst(skb));
+
+	return mtu;
 }
 
 static inline bool ip6_sk_accept_pmtu(const struct sock *sk)
@@ -317,7 +324,7 @@ static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
 	if (dst_metric_locked(dst, RTAX_MTU)) {
 		mtu = dst_metric_raw(dst, RTAX_MTU);
 		if (mtu)
-			return mtu;
+			goto out;
 	}
 
 	mtu = IPV6_MIN_MTU;
@@ -327,7 +334,8 @@ static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
 		mtu = idev->cnf.mtu6;
 	rcu_read_unlock();
 
-	return mtu;
+out:
+	return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
 }
 
 u32 ip6_mtu_from_fib6(const struct fib6_result *res,
diff --git a/include/net/macsec.h b/include/net/macsec.h
index 52874cdfe226..d6fa6b97f6ef 100644
--- a/include/net/macsec.h
+++ b/include/net/macsec.h
@@ -241,7 +241,7 @@ struct macsec_context {
 	struct macsec_rx_sc *rx_sc;
 	struct {
 		unsigned char assoc_num;
-		u8 key[MACSEC_KEYID_LEN];
+		u8 key[MACSEC_MAX_KEY_LEN];
 		union {
 			struct macsec_rx_sa *rx_sa;
 			struct macsec_tx_sa *tx_sa;
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index c99ffe9cc88f..9ed33e6840bd 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -173,6 +173,12 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 		if (spin_trylock(&qdisc->seqlock))
 			return true;
 
+		/* Paired with smp_mb__after_atomic() to make sure
+		 * STATE_MISSED checking is synchronized with clearing
+		 * in pfifo_fast_dequeue().
+		 */
+		smp_mb__before_atomic();
+
 		/* If the MISSED flag is set, it means other thread has
 		 * set the MISSED flag before second spin_trylock(), so
 		 * we can return false here to avoid multi cpus doing
@@ -190,6 +196,12 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 		 */
 		set_bit(__QDISC_STATE_MISSED, &qdisc->state);
 
+		/* spin_trylock() only has load-acquire semantic, so use
+		 * smp_mb__after_atomic() to ensure STATE_MISSED is set
+		 * before doing the second spin_trylock().
+		 */
+		smp_mb__after_atomic();
+
 		/* Retry again in case other CPU may not see the new flag
 		 * after it releases the lock at the end of qdisc_run_end().
 		 */
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index c4a4c1754be8..32fc4a309df5 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -463,7 +463,7 @@ struct sctp_af {
 					 int saddr);
 	void		(*from_sk)	(union sctp_addr *,
 					 struct sock *sk);
-	void		(*from_addr_param) (union sctp_addr *,
+	bool		(*from_addr_param) (union sctp_addr *,
 					    union sctp_addr_param *,
 					    __be16 port, int iif);
 	int		(*to_addr_param) (const union sctp_addr *,
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index b7e65aec4b2d..cbff7c2a9724 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1538,6 +1538,7 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si);
 void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si);
 u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq);
 int xfrm_init_replay(struct xfrm_state *x);
+u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu);
 u32 xfrm_state_mtu(struct xfrm_state *x, int mtu);
 int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload);
 int xfrm_init_state(struct xfrm_state *x);
@@ -1562,7 +1563,6 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
 		    int encap_type);
 int xfrm4_transport_finish(struct sk_buff *skb, int async);
 int xfrm4_rcv(struct sk_buff *skb);
-int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq);
 
 static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi)
 {
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index eaa8386dbc63..7a9a23e7a604 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -147,11 +147,16 @@ static inline bool xp_desc_crosses_non_contig_pg(struct xsk_buff_pool *pool,
 {
 	bool cross_pg = (addr & (PAGE_SIZE - 1)) + len > PAGE_SIZE;
 
-	if (pool->dma_pages_cnt && cross_pg) {
+	if (likely(!cross_pg))
+		return false;
+
+	if (pool->dma_pages_cnt) {
 		return !(pool->dma_pages[addr >> PAGE_SHIFT] &
 			 XSK_NEXT_PG_CONTIG_MASK);
 	}
-	return false;
+
+	/* skb path */
+	return addr + len > pool->addrs_cnt;
 }
 
 static inline u64 xp_aligned_extract_addr(struct xsk_buff_pool *pool, u64 addr)