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>

4 files changed, 53 insertions, 41 deletions

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index a05270996613..b5850afea343 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -942,19 +942,20 @@ reset:
 	return false;
 }
 
-static u64 expand_ack(u64 old_ack, u64 cur_ack, bool use_64bit)
+u64 __mptcp_expand_seq(u64 old_seq, u64 cur_seq)
 {
-	u32 old_ack32, cur_ack32;
-
-	if (use_64bit)
-		return cur_ack;
-
-	old_ack32 = (u32)old_ack;
-	cur_ack32 = (u32)cur_ack;
-	cur_ack = (old_ack & GENMASK_ULL(63, 32)) + cur_ack32;
-	if (unlikely(before(cur_ack32, old_ack32)))
-		return cur_ack + (1LL << 32);
-	return cur_ack;
+	u32 old_seq32, cur_seq32;
+
+	old_seq32 = (u32)old_seq;
+	cur_seq32 = (u32)cur_seq;
+	cur_seq = (old_seq & GENMASK_ULL(63, 32)) + cur_seq32;
+	if (unlikely(cur_seq32 < old_seq32 && before(old_seq32, cur_seq32)))
+		return cur_seq + (1LL << 32);
+
+	/* reverse wrap could happen, too */
+	if (unlikely(cur_seq32 > old_seq32 && after(old_seq32, cur_seq32)))
+		return cur_seq - (1LL << 32);
+	return cur_seq;
 }
 
 static void ack_update_msk(struct mptcp_sock *msk,
@@ -972,7 +973,7 @@ static void ack_update_msk(struct mptcp_sock *msk,
 	 * more dangerous than missing an ack
 	 */
 	old_snd_una = msk->snd_una;
-	new_snd_una = expand_ack(old_snd_una, mp_opt->data_ack, mp_opt->ack64);
+	new_snd_una = mptcp_expand_seq(old_snd_una, mp_opt->data_ack, mp_opt->ack64);
 
 	/* ACK for data not even sent yet? Ignore. */
 	if (after64(new_snd_una, snd_nxt))
@@ -1009,7 +1010,7 @@ bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool us
 		return false;
 
 	WRITE_ONCE(msk->rcv_data_fin_seq,
-		   expand_ack(READ_ONCE(msk->ack_seq), data_fin_seq, use_64bit));
+		   mptcp_expand_seq(READ_ONCE(msk->ack_seq), data_fin_seq, use_64bit));
 	WRITE_ONCE(msk->rcv_data_fin, 1);
 
 	return true;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 7bb82424e551..7a5afa8c6866 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2896,6 +2896,11 @@ static void mptcp_release_cb(struct sock *sk)
 		spin_lock_bh(&sk->sk_lock.slock);
 	}
 
+	/* be sure to set the current sk state before tacking actions
+	 * depending on sk_state
+	 */
+	if (test_and_clear_bit(MPTCP_CONNECTED, &mptcp_sk(sk)->flags))
+		__mptcp_set_connected(sk);
 	if (test_and_clear_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags))
 		__mptcp_clean_una_wakeup(sk);
 	if (test_and_clear_bit(MPTCP_ERROR_REPORT, &mptcp_sk(sk)->flags))
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index d8ad3270dfab..426ed80fe72f 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -112,6 +112,7 @@
 #define MPTCP_ERROR_REPORT	8
 #define MPTCP_RETRANSMIT	9
 #define MPTCP_WORK_SYNC_SETSOCKOPT 10
+#define MPTCP_CONNECTED		11
 
 static inline bool before64(__u64 seq1, __u64 seq2)
 {
@@ -600,6 +601,7 @@ void mptcp_get_options(const struct sock *sk,
 		       struct mptcp_options_received *mp_opt);
 
 void mptcp_finish_connect(struct sock *sk);
+void __mptcp_set_connected(struct sock *sk);
 static inline bool mptcp_is_fully_established(struct sock *sk)
 {
 	return inet_sk_state_load(sk) == TCP_ESTABLISHED &&
@@ -614,6 +616,14 @@ int mptcp_setsockopt(struct sock *sk, int level, int optname,
 int mptcp_getsockopt(struct sock *sk, int level, int optname,
 		     char __user *optval, int __user *option);
 
+u64 __mptcp_expand_seq(u64 old_seq, u64 cur_seq);
+static inline u64 mptcp_expand_seq(u64 old_seq, u64 cur_seq, bool use_64bit)
+{
+	if (use_64bit)
+		return cur_seq;
+
+	return __mptcp_expand_seq(old_seq, cur_seq);
+}
 void __mptcp_check_push(struct sock *sk, struct sock *ssk);
 void __mptcp_data_acked(struct sock *sk);
 void __mptcp_error_report(struct sock *sk);
@@ -775,9 +785,6 @@ unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk);
 unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk);
 unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk);
 
-int mptcp_setsockopt(struct sock *sk, int level, int optname,
-		     sockptr_t optval, unsigned int optlen);
-
 void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk);
 void mptcp_sockopt_sync_all(struct mptcp_sock *msk);
 
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 706a26a1b0fe..66d0b1893d26 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -373,6 +373,24 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc
 	return inet_sk(sk)->inet_dport != inet_sk((struct sock *)msk)->inet_dport;
 }
 
+void __mptcp_set_connected(struct sock *sk)
+{
+	if (sk->sk_state == TCP_SYN_SENT) {
+		inet_sk_state_store(sk, TCP_ESTABLISHED);
+		sk->sk_state_change(sk);
+	}
+}
+
+static void mptcp_set_connected(struct sock *sk)
+{
+	mptcp_data_lock(sk);
+	if (!sock_owned_by_user(sk))
+		__mptcp_set_connected(sk);
+	else
+		set_bit(MPTCP_CONNECTED, &mptcp_sk(sk)->flags);
+	mptcp_data_unlock(sk);
+}
+
 static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
@@ -381,10 +399,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 
 	subflow->icsk_af_ops->sk_rx_dst_set(sk, skb);
 
-	if (inet_sk_state_load(parent) == TCP_SYN_SENT) {
-		inet_sk_state_store(parent, TCP_ESTABLISHED);
-		parent->sk_state_change(parent);
-	}
 
 	/* be sure no special action on any packet other than syn-ack */
 	if (subflow->conn_finished)
@@ -417,6 +431,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 			 subflow->remote_key);
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK);
 		mptcp_finish_connect(sk);
+		mptcp_set_connected(parent);
 	} else if (subflow->request_join) {
 		u8 hmac[SHA256_DIGEST_SIZE];
 
@@ -457,6 +472,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 	} else if (mptcp_check_fallback(sk)) {
 fallback:
 		mptcp_rcv_space_init(mptcp_sk(parent), sk);
+		mptcp_set_connected(parent);
 	}
 	return;
 
@@ -564,6 +580,7 @@ static void mptcp_sock_destruct(struct sock *sk)
 
 static void mptcp_force_close(struct sock *sk)
 {
+	/* the msk is not yet exposed to user-space */
 	inet_sk_state_store(sk, TCP_CLOSE);
 	sk_common_release(sk);
 }
@@ -781,15 +798,6 @@ enum mapping_status {
 	MAPPING_DUMMY
 };
 
-static u64 expand_seq(u64 old_seq, u16 old_data_len, u64 seq)
-{
-	if ((u32)seq == (u32)old_seq)
-		return old_seq;
-
-	/* Assume map covers data not mapped yet. */
-	return seq | ((old_seq + old_data_len + 1) & GENMASK_ULL(63, 32));
-}
-
 static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn)
 {
 	pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d",
@@ -995,13 +1003,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 		data_len--;
 	}
 
-	if (!mpext->dsn64) {
-		map_seq = expand_seq(subflow->map_seq, subflow->map_data_len,
-				     mpext->data_seq);
-		pr_debug("expanded seq=%llu", subflow->map_seq);
-	} else {
-		map_seq = mpext->data_seq;
-	}
+	map_seq = mptcp_expand_seq(READ_ONCE(msk->ack_seq), mpext->data_seq, mpext->dsn64);
 	WRITE_ONCE(mptcp_sk(subflow->conn)->use_64bit_ack, !!mpext->dsn64);
 
 	if (subflow->map_valid) {
@@ -1592,10 +1594,7 @@ static void subflow_state_change(struct sock *sk)
 		mptcp_rcv_space_init(mptcp_sk(parent), sk);
 		pr_fallback(mptcp_sk(parent));
 		subflow->conn_finished = 1;
-		if (inet_sk_state_load(parent) == TCP_SYN_SENT) {
-			inet_sk_state_store(parent, TCP_ESTABLISHED);
-			parent->sk_state_change(parent);
-		}
+		mptcp_set_connected(parent);
 	}
 
 	/* as recvmsg() does not acquire the subflow socket for ssk selection