Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - BPF:
      - add syscall program type and libbpf support for generating
        instructions and bindings for in-kernel BPF loaders (BPF loaders
        for BPF), this is a stepping stone for signed BPF programs
      - infrastructure to migrate TCP child sockets from one listener to
        another in the same reuseport group/map to improve flexibility
        of service hand-off/restart
      - add broadcast support to XDP redirect

   - allow bypass of the lockless qdisc to improving performance (for
     pktgen: +23% with one thread, +44% with 2 threads)

   - add a simpler version of "DO_ONCE()" which does not require jump
     labels, intended for slow-path usage

   - virtio/vsock: introduce SOCK_SEQPACKET support

   - add getsocketopt to retrieve netns cookie

   - ip: treat lowest address of a IPv4 subnet as ordinary unicast
     address allowing reclaiming of precious IPv4 addresses

   - ipv6: use prandom_u32() for ID generation

   - ip: add support for more flexible field selection for hashing
     across multi-path routes (w/ offload to mlxsw)

   - icmp: add support for extended RFC 8335 PROBE (ping)

   - seg6: add support for SRv6 End.DT46 behavior

   - mptcp:
      - DSS checksum support (RFC 8684) to detect middlebox meddling
      - support Connection-time 'C' flag
      - time stamping support

   - sctp: packetization Layer Path MTU Discovery (RFC 8899)

   - xfrm: speed up state addition with seq set

   - WiFi:
      - hidden AP discovery on 6 GHz and other HE 6 GHz improvements
      - aggregation handling improvements for some drivers
      - minstrel improvements for no-ack frames
      - deferred rate control for TXQs to improve reaction times
      - switch from round robin to virtual time-based airtime scheduler

   - add trace points:
      - tcp checksum errors
      - openvswitch - action execution, upcalls
      - socket errors via sk_error_report

  Device APIs:

   - devlink: add rate API for hierarchical control of max egress rate
     of virtual devices (VFs, SFs etc.)

   - don't require RCU read lock to be held around BPF hooks in NAPI
     context

   - page_pool: generic buffer recycling

  New hardware/drivers:

   - mobile:
      - iosm: PCIe Driver for Intel M.2 Modem
      - support for Qualcomm MSM8998 (ipa)

   - WiFi: Qualcomm QCN9074 and WCN6855 PCI devices

   - sparx5: Microchip SparX-5 family of Enterprise Ethernet switches

   - Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)

   - NXP SJA1110 Automotive Ethernet 10-port switch

   - Qualcomm QCA8327 switch support (qca8k)

   - Mikrotik 10/25G NIC (atl1c)

  Driver changes:

   - ACPI support for some MDIO, MAC and PHY devices from Marvell and
     NXP (our first foray into MAC/PHY description via ACPI)

   - HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx

   - Mellanox/Nvidia NIC (mlx5)
      - NIC VF offload of L2 bridging
      - support IRQ distribution to Sub-functions

   - Marvell (prestera):
      - add flower and match all
      - devlink trap
      - link aggregation

   - Netronome (nfp): connection tracking offload

   - Intel 1GE (igc): add AF_XDP support

   - Marvell DPU (octeontx2): ingress ratelimit offload

   - Google vNIC (gve): new ring/descriptor format support

   - Qualcomm mobile (rmnet & ipa): inline checksum offload support

   - MediaTek WiFi (mt76)
      - mt7915 MSI support
      - mt7915 Tx status reporting
      - mt7915 thermal sensors support
      - mt7921 decapsulation offload
      - mt7921 enable runtime pm and deep sleep

   - Realtek WiFi (rtw88)
      - beacon filter support
      - Tx antenna path diversity support
      - firmware crash information via devcoredump

   - Qualcomm WiFi (wcn36xx)
      - Wake-on-WLAN support with magic packets and GTK rekeying

   - Micrel PHY (ksz886x/ksz8081): add cable test support"

* tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits)
  tcp: change ICSK_CA_PRIV_SIZE definition
  tcp_yeah: check struct yeah size at compile time
  gve: DQO: Fix off by one in gve_rx_dqo()
  stmmac: intel: set PCI_D3hot in suspend
  stmmac: intel: Enable PHY WOL option in EHL
  net: stmmac: option to enable PHY WOL with PMT enabled
  net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del}
  net: use netdev_info in ndo_dflt_fdb_{add,del}
  ptp: Set lookup cookie when creating a PTP PPS source.
  net: sock: add trace for socket errors
  net: sock: introduce sk_error_report
  net: dsa: replay the local bridge FDB entries pointing to the bridge dev too
  net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev
  net: dsa: include fdb entries pointing to bridge in the host fdb list
  net: dsa: include bridge addresses which are local in the host fdb list
  net: dsa: sync static FDB entries on foreign interfaces to hardware
  net: dsa: install the host MDB and FDB entries in the master's RX filter
  net: dsa: reference count the FDB addresses at the cross-chip notifier level
  net: dsa: introduce a separate cross-chip notifier type for host FDBs
  net: dsa: reference count the MDB entries at the cross-chip notifier level
  ...

1 files changed, 143 insertions, 41 deletions

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index be1de4084196..66d0b1893d26 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -108,6 +108,8 @@ static void subflow_init_req(struct request_sock *req, const struct sock *sk_lis
 
 	subflow_req->mp_capable = 0;
 	subflow_req->mp_join = 0;
+	subflow_req->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk_listener));
+	subflow_req->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk_listener));
 	subflow_req->msk = NULL;
 	mptcp_token_init_request(req);
 }
@@ -150,7 +152,7 @@ static int subflow_check_req(struct request_sock *req,
 		return -EINVAL;
 #endif
 
-	mptcp_get_options(skb, &mp_opt);
+	mptcp_get_options(sk_listener, skb, &mp_opt);
 
 	if (mp_opt.mp_capable) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
@@ -162,7 +164,7 @@ static int subflow_check_req(struct request_sock *req,
 	}
 
 	if (mp_opt.mp_capable && listener->request_mptcp) {
-		int err, retries = 4;
+		int err, retries = MPTCP_TOKEN_MAX_RETRIES;
 
 		subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
 again:
@@ -247,7 +249,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req,
 	int err;
 
 	subflow_init_req(req, sk_listener);
-	mptcp_get_options(skb, &mp_opt);
+	mptcp_get_options(sk_listener, skb, &mp_opt);
 
 	if (mp_opt.mp_capable && mp_opt.mp_join)
 		return -EINVAL;
@@ -371,6 +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);
@@ -379,10 +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)
@@ -394,7 +410,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 	subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
 	pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset);
 
-	mptcp_get_options(skb, &mp_opt);
+	mptcp_get_options(sk, skb, &mp_opt);
 	if (subflow->request_mptcp) {
 		if (!mp_opt.mp_capable) {
 			MPTCP_INC_STATS(sock_net(sk),
@@ -404,6 +420,10 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 			goto fallback;
 		}
 
+		if (mp_opt.csum_reqd)
+			WRITE_ONCE(mptcp_sk(parent)->csum_enabled, true);
+		if (mp_opt.deny_join_id0)
+			WRITE_ONCE(mptcp_sk(parent)->pm.remote_deny_join_id0, true);
 		subflow->mp_capable = 1;
 		subflow->can_ack = 1;
 		subflow->remote_key = mp_opt.sndr_key;
@@ -411,6 +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];
 
@@ -430,15 +451,15 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 			goto do_reset;
 		}
 
+		if (!mptcp_finish_join(sk))
+			goto do_reset;
+
 		subflow_generate_hmac(subflow->local_key, subflow->remote_key,
 				      subflow->local_nonce,
 				      subflow->remote_nonce,
 				      hmac);
 		memcpy(subflow->hmac, hmac, MPTCPOPT_HMAC_LEN);
 
-		if (!mptcp_finish_join(sk))
-			goto do_reset;
-
 		subflow->mp_join = 1;
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX);
 
@@ -451,6 +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;
 
@@ -558,6 +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);
 }
@@ -638,7 +661,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 		 * reordered MPC will cause fallback, but we don't have other
 		 * options.
 		 */
-		mptcp_get_options(skb, &mp_opt);
+		mptcp_get_options(sk, skb, &mp_opt);
 		if (!mp_opt.mp_capable) {
 			fallback = true;
 			goto create_child;
@@ -648,7 +671,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 		if (!new_msk)
 			fallback = true;
 	} else if (subflow_req->mp_join) {
-		mptcp_get_options(skb, &mp_opt);
+		mptcp_get_options(sk, skb, &mp_opt);
 		if (!mp_opt.mp_join || !subflow_hmac_valid(req, &mp_opt) ||
 		    !mptcp_can_accept_new_subflow(subflow_req->msk)) {
 			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
@@ -775,15 +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",
@@ -824,10 +838,92 @@ static bool validate_mapping(struct sock *ssk, struct sk_buff *skb)
 	return true;
 }
 
+static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff *skb,
+					      bool csum_reqd)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+	struct csum_pseudo_header header;
+	u32 offset, seq, delta;
+	__wsum csum;
+	int len;
+
+	if (!csum_reqd)
+		return MAPPING_OK;
+
+	/* mapping already validated on previous traversal */
+	if (subflow->map_csum_len == subflow->map_data_len)
+		return MAPPING_OK;
+
+	/* traverse the receive queue, ensuring it contains a full
+	 * DSS mapping and accumulating the related csum.
+	 * Preserve the accoumlate csum across multiple calls, to compute
+	 * the csum only once
+	 */
+	delta = subflow->map_data_len - subflow->map_csum_len;
+	for (;;) {
+		seq = tcp_sk(ssk)->copied_seq + subflow->map_csum_len;
+		offset = seq - TCP_SKB_CB(skb)->seq;
+
+		/* if the current skb has not been accounted yet, csum its contents
+		 * up to the amount covered by the current DSS
+		 */
+		if (offset < skb->len) {
+			__wsum csum;
+
+			len = min(skb->len - offset, delta);
+			csum = skb_checksum(skb, offset, len, 0);
+			subflow->map_data_csum = csum_block_add(subflow->map_data_csum, csum,
+								subflow->map_csum_len);
+
+			delta -= len;
+			subflow->map_csum_len += len;
+		}
+		if (delta == 0)
+			break;
+
+		if (skb_queue_is_last(&ssk->sk_receive_queue, skb)) {
+			/* if this subflow is closed, the partial mapping
+			 * will be never completed; flush the pending skbs, so
+			 * that subflow_sched_work_if_closed() can kick in
+			 */
+			if (unlikely(ssk->sk_state == TCP_CLOSE))
+				while ((skb = skb_peek(&ssk->sk_receive_queue)))
+					sk_eat_skb(ssk, skb);
+
+			/* not enough data to validate the csum */
+			return MAPPING_EMPTY;
+		}
+
+		/* the DSS mapping for next skbs will be validated later,
+		 * when a get_mapping_status call will process such skb
+		 */
+		skb = skb->next;
+	}
+
+	/* note that 'map_data_len' accounts only for the carried data, does
+	 * not include the eventual seq increment due to the data fin,
+	 * while the pseudo header requires the original DSS data len,
+	 * including that
+	 */
+	header.data_seq = cpu_to_be64(subflow->map_seq);
+	header.subflow_seq = htonl(subflow->map_subflow_seq);
+	header.data_len = htons(subflow->map_data_len + subflow->map_data_fin);
+	header.csum = 0;
+
+	csum = csum_partial(&header, sizeof(header), subflow->map_data_csum);
+	if (unlikely(csum_fold(csum))) {
+		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR);
+		return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY;
+	}
+
+	return MAPPING_OK;
+}
+
 static enum mapping_status get_mapping_status(struct sock *ssk,
 					      struct mptcp_sock *msk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+	bool csum_reqd = READ_ONCE(msk->csum_enabled);
 	struct mptcp_ext *mpext;
 	struct sk_buff *skb;
 	u16 data_len;
@@ -907,22 +1003,17 @@ 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) {
 		/* Allow replacing only with an identical map */
 		if (subflow->map_seq == map_seq &&
 		    subflow->map_subflow_seq == mpext->subflow_seq &&
-		    subflow->map_data_len == data_len) {
+		    subflow->map_data_len == data_len &&
+		    subflow->map_csum_reqd == mpext->csum_reqd) {
 			skb_ext_del(skb, SKB_EXT_MPTCP);
-			return MAPPING_OK;
+			goto validate_csum;
 		}
 
 		/* If this skb data are fully covered by the current mapping,
@@ -934,27 +1025,41 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 		}
 
 		/* will validate the next map after consuming the current one */
-		return MAPPING_OK;
+		goto validate_csum;
 	}
 
 	subflow->map_seq = map_seq;
 	subflow->map_subflow_seq = mpext->subflow_seq;
 	subflow->map_data_len = data_len;
 	subflow->map_valid = 1;
+	subflow->map_data_fin = mpext->data_fin;
 	subflow->mpc_map = mpext->mpc_map;
-	pr_debug("new map seq=%llu subflow_seq=%u data_len=%u",
+	subflow->map_csum_reqd = mpext->csum_reqd;
+	subflow->map_csum_len = 0;
+	subflow->map_data_csum = csum_unfold(mpext->csum);
+
+	/* Cfr RFC 8684 Section 3.3.0 */
+	if (unlikely(subflow->map_csum_reqd != csum_reqd))
+		return MAPPING_INVALID;
+
+	pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u",
 		 subflow->map_seq, subflow->map_subflow_seq,
-		 subflow->map_data_len);
+		 subflow->map_data_len, subflow->map_csum_reqd,
+		 subflow->map_data_csum);
 
 validate_seq:
 	/* we revalidate valid mapping on new skb, because we must ensure
 	 * the current skb is completely covered by the available mapping
 	 */
-	if (!validate_mapping(ssk, skb))
+	if (!validate_mapping(ssk, skb)) {
+		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSTCPMISMATCH);
 		return MAPPING_INVALID;
+	}
 
 	skb_ext_del(skb, SKB_EXT_MPTCP);
-	return MAPPING_OK;
+
+validate_csum:
+	return validate_data_csum(ssk, skb, csum_reqd);
 }
 
 static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
@@ -1137,7 +1242,7 @@ void __mptcp_error_report(struct sock *sk)
 
 		/* This barrier is coupled with smp_rmb() in mptcp_poll() */
 		smp_wmb();
-		sk->sk_error_report(sk);
+		sk_error_report(sk);
 		break;
 	}
 }
@@ -1489,10 +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