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

drivers/net/ethernet/mellanox/mlx5/core/main.c
  b33886971dbc ("net/mlx5: Initialize flow steering during driver probe")
  40379a0084c2 ("net/mlx5_fpga: Drop INNOVA TLS support")
  f2b41b32cde8 ("net/mlx5: Remove ipsec_ops function table")
https://lore.kernel.org/all/20220519040345.6yrjromcdistu7vh@sx1/
  16d42d313350 ("net/mlx5: Drain fw_reset when removing device")
  8324a02c342a ("net/mlx5: Add exit route when waiting for FW")
https://lore.kernel.org/all/20220519114119.060ce014@canb.auug.org.au/

tools/testing/selftests/net/mptcp/mptcp_join.sh
  e274f7154008 ("selftests: mptcp: add subflow limits test-cases")
  b6e074e171bc ("selftests: mptcp: add infinite map testcase")
  5ac1d2d63451 ("selftests: mptcp: Add tests for userspace PM type")
https://lore.kernel.org/all/20220516111918.366d747f@canb.auug.org.au/

net/mptcp/options.c
  ba2c89e0ea74 ("mptcp: fix checksum byte order")
  1e39e5a32ad7 ("mptcp: infinite mapping sending")
  ea66758c1795 ("tcp: allow MPTCP to update the announced window")
https://lore.kernel.org/all/20220519115146.751c3a37@canb.auug.org.au/

net/mptcp/pm.c
  95d686517884 ("mptcp: fix subflow accounting on close")
  4d25247d3ae4 ("mptcp: bypass in-kernel PM restrictions for non-kernel PMs")
https://lore.kernel.org/all/20220516111435.72f35dca@canb.auug.org.au/

net/mptcp/subflow.c
  ae66fb2ba6c3 ("mptcp: Do TCP fallback on early DSS checksum failure")
  0348c690ed37 ("mptcp: add the fallback check")
  f8d4bcacff3b ("mptcp: infinite mapping receiving")
https://lore.kernel.org/all/20220519115837.380bb8d4@canb.auug.org.au/

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

4 files changed, 71 insertions, 25 deletions

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index ac3b7b8a02f6..be3b918a6d15 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -107,7 +107,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 			ptr += 2;
 		}
 		if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM) {
-			mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr);
+			mp_opt->csum = get_unaligned((__force __sum16 *)ptr);
 			mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD;
 			ptr += 2;
 		}
@@ -221,7 +221,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 
 			if (opsize == expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) {
 				mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD;
-				mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr);
+				mp_opt->csum = get_unaligned((__force __sum16 *)ptr);
 				ptr += 2;
 			}
 
@@ -1282,7 +1282,7 @@ raise_win:
 	}
 }
 
-u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum)
+__sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum)
 {
 	struct csum_pseudo_header header;
 	__wsum csum;
@@ -1298,15 +1298,25 @@ u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum)
 	header.csum = 0;
 
 	csum = csum_partial(&header, sizeof(header), sum);
-	return (__force u16)csum_fold(csum);
+	return csum_fold(csum);
 }
 
-static u16 mptcp_make_csum(const struct mptcp_ext *mpext)
+static __sum16 mptcp_make_csum(const struct mptcp_ext *mpext)
 {
 	return __mptcp_make_csum(mpext->data_seq, mpext->subflow_seq, mpext->data_len,
 				 ~csum_unfold(mpext->csum));
 }
 
+static void put_len_csum(u16 len, __sum16 csum, void *data)
+{
+	__sum16 *sumptr = data + 2;
+	__be16 *ptr = data;
+
+	put_unaligned_be16(len, ptr);
+
+	put_unaligned(csum, sumptr);
+}
+
 void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp,
 			 struct mptcp_out_options *opts)
 {
@@ -1385,9 +1395,9 @@ void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp,
 				/* data_len == 0 is reserved for the infinite mapping,
 				 * the checksum will also be set to 0.
 				 */
-				put_unaligned_be32(mpext->data_len << 16 |
-						   (mpext->data_len ? mptcp_make_csum(mpext) : 0),
-						   ptr);
+				put_len_csum(mpext->data_len,
+					     (mpext->data_len ? mptcp_make_csum(mpext) : 0),
+					     ptr);
 			} else {
 				put_unaligned_be32(mpext->data_len << 16 |
 						   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
@@ -1438,11 +1448,12 @@ void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp,
 			goto mp_capable_done;
 
 		if (opts->csum_reqd) {
-			put_unaligned_be32(opts->data_len << 16 |
-					   __mptcp_make_csum(opts->data_seq,
-							     opts->subflow_seq,
-							     opts->data_len,
-							     ~csum_unfold(opts->csum)), ptr);
+			put_len_csum(opts->data_len,
+				     __mptcp_make_csum(opts->data_seq,
+						       opts->subflow_seq,
+						       opts->data_len,
+						       ~csum_unfold(opts->csum)),
+				     ptr);
 		} else {
 			put_unaligned_be32(opts->data_len << 16 |
 					   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index cdc2d79071f8..59fdab2d0c27 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -181,15 +181,14 @@ void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk,
 	struct mptcp_pm_data *pm = &msk->pm;
 	bool update_subflows;
 
-	update_subflows = (ssk->sk_state == TCP_CLOSE) &&
-			  (subflow->request_join || subflow->mp_join) &&
+	update_subflows = (subflow->request_join || subflow->mp_join) &&
 			  mptcp_pm_is_kernel(msk);
 	if (!READ_ONCE(pm->work_pending) && !update_subflows)
 		return;
 
 	spin_lock_bh(&pm->lock);
 	if (update_subflows)
-		pm->subflows--;
+		__mptcp_pm_close_subflow(msk);
 
 	/* Even if this subflow is not really established, tell the PM to try
 	 * to pick the next ones, if possible.
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 4672901d0dfe..08b8015cb69f 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -466,7 +466,8 @@ struct mptcp_subflow_context {
 		can_ack : 1,        /* only after processing the remote a key */
 		disposable : 1,	    /* ctx can be free at ulp release time */
 		stale : 1,	    /* unable to snd/rcv data, do not use for xmit */
-		local_id_valid : 1; /* local_id is correctly initialized */
+		local_id_valid : 1, /* local_id is correctly initialized */
+		valid_csum_seen : 1;        /* at least one csum validated */
 	enum mptcp_data_avail data_avail;
 	bool	mp_fail_response_expect;
 	u32	remote_nonce;
@@ -751,7 +752,7 @@ void mptcp_token_destroy(struct mptcp_sock *msk);
 void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn);
 
 void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac);
-u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum);
+__sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum);
 
 void __init mptcp_pm_init(void);
 void mptcp_pm_data_init(struct mptcp_sock *msk);
@@ -893,6 +894,20 @@ unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk);
 unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk);
 unsigned int mptcp_pm_get_local_addr_max(const struct mptcp_sock *msk);
 
+/* called under PM lock */
+static inline void __mptcp_pm_close_subflow(struct mptcp_sock *msk)
+{
+	if (--msk->pm.subflows < mptcp_pm_get_subflows_max(msk))
+		WRITE_ONCE(msk->pm.accept_subflow, true);
+}
+
+static inline void mptcp_pm_close_subflow(struct mptcp_sock *msk)
+{
+	spin_lock_bh(&msk->pm.lock);
+	__mptcp_pm_close_subflow(msk);
+	spin_unlock_bh(&msk->pm.lock);
+}
+
 void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk);
 void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk);
 
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 6d59336a8e1e..aecd98ac5dfe 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -891,7 +891,7 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff *
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	u32 offset, seq, delta;
-	u16 csum;
+	__sum16 csum;
 	int len;
 
 	if (!csum_reqd)
@@ -958,11 +958,14 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff *
 				 subflow->map_data_csum);
 	if (unlikely(csum)) {
 		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR);
-		subflow->send_mp_fail = 1;
-		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX);
+		if (subflow->mp_join || subflow->valid_csum_seen) {
+			subflow->send_mp_fail = 1;
+			MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX);
+		}
 		return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY;
 	}
 
+	subflow->valid_csum_seen = 1;
 	return MAPPING_OK;
 }
 
@@ -1153,6 +1156,18 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss
 	}
 }
 
+static bool subflow_can_fallback(struct mptcp_subflow_context *subflow)
+{
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+
+	if (subflow->mp_join)
+		return false;
+	else if (READ_ONCE(msk->csum_enabled))
+		return !subflow->valid_csum_seen;
+	else
+		return !subflow->fully_established;
+}
+
 static bool subflow_check_data_avail(struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
@@ -1238,7 +1253,7 @@ fallback:
 			return true;
 		}
 
-		if ((subflow->mp_join || subflow->fully_established) && subflow->map_data_len) {
+		if (!subflow_can_fallback(subflow) && subflow->map_data_len) {
 			/* fatal protocol error, close the socket.
 			 * subflow_error_report() will introduce the appropriate barriers
 			 */
@@ -1444,20 +1459,20 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 	struct sockaddr_storage addr;
 	int remote_id = remote->id;
 	int local_id = loc->id;
+	int err = -ENOTCONN;
 	struct socket *sf;
 	struct sock *ssk;
 	u32 remote_token;
 	int addrlen;
 	int ifindex;
 	u8 flags;
-	int err;
 
 	if (!mptcp_is_fully_established(sk))
-		return -ENOTCONN;
+		goto err_out;
 
 	err = mptcp_subflow_create_socket(sk, &sf);
 	if (err)
-		return err;
+		goto err_out;
 
 	ssk = sf->sk;
 	subflow = mptcp_subflow_ctx(ssk);
@@ -1515,6 +1530,12 @@ failed_unlink:
 failed:
 	subflow->disposable = 1;
 	sock_release(sf);
+
+err_out:
+	/* we account subflows before the creation, and this failures will not
+	 * be caught by sk_state_change()
+	 */
+	mptcp_pm_close_subflow(msk);
 	return err;
 }