Merge tag 'net-next-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - support "prefer busy polling" NAPI operation mode, where we defer
     softirq for some time expecting applications to periodically busy
     poll

   - AF_XDP: improve efficiency by more batching and hindering the
     adjacency cache prefetcher

   - af_packet: make packet_fanout.arr size configurable up to 64K

   - tcp: optimize TCP zero copy receive in presence of partial or
     unaligned reads making zero copy a performance win for much smaller
     messages

   - XDP: add bulk APIs for returning / freeing frames

   - sched: support fragmenting IP packets as they come out of conntrack

   - net: allow virtual netdevs to forward UDP L4 and fraglist GSO skbs

  BPF:

   - BPF switch from crude rlimit-based to memcg-based memory accounting

   - BPF type format information for kernel modules and related tracing
     enhancements

   - BPF implement task local storage for BPF LSM

   - allow the FENTRY/FEXIT/RAW_TP tracing programs to use
     bpf_sk_storage

  Protocols:

   - mptcp: improve multiple xmit streams support, memory accounting and
     many smaller improvements

   - TLS: support CHACHA20-POLY1305 cipher

   - seg6: add support for SRv6 End.DT4/DT6 behavior

   - sctp: Implement RFC 6951: UDP Encapsulation of SCTP

   - ppp_generic: add ability to bridge channels directly

   - bridge: Connectivity Fault Management (CFM) support as is defined
     in IEEE 802.1Q section 12.14.

  Drivers:

   - mlx5: make use of the new auxiliary bus to organize the driver
     internals

   - mlx5: more accurate port TX timestamping support

   - mlxsw:
      - improve the efficiency of offloaded next hop updates by using
        the new nexthop object API
      - support blackhole nexthops
      - support IEEE 802.1ad (Q-in-Q) bridging

   - rtw88: major bluetooth co-existance improvements

   - iwlwifi: support new 6 GHz frequency band

   - ath11k: Fast Initial Link Setup (FILS)

   - mt7915: dual band concurrent (DBDC) support

   - net: ipa: add basic support for IPA v4.5

  Refactor:

   - a few pieces of in_interrupt() cleanup work from Sebastian Andrzej
     Siewior

   - phy: add support for shared interrupts; get rid of multiple driver
     APIs and have the drivers write a full IRQ handler, slight growth
     of driver code should be compensated by the simpler API which also
     allows shared IRQs

   - add common code for handling netdev per-cpu counters

   - move TX packet re-allocation from Ethernet switch tag drivers to a
     central place

   - improve efficiency and rename nla_strlcpy

   - number of W=1 warning cleanups as we now catch those in a patchwork
     build bot

  Old code removal:

   - wan: delete the DLCI / SDLA drivers

   - wimax: move to staging

   - wifi: remove old WDS wifi bridging support"

* tag 'net-next-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1922 commits)
  net: hns3: fix expression that is currently always true
  net: fix proc_fs init handling in af_packet and tls
  nfc: pn533: convert comma to semicolon
  af_vsock: Assign the vsock transport considering the vsock address flags
  af_vsock: Set VMADDR_FLAG_TO_HOST flag on the receive path
  vsock_addr: Check for supported flag values
  vm_sockets: Add VMADDR_FLAG_TO_HOST vsock flag
  vm_sockets: Add flags field in the vsock address data structure
  net: Disable NETIF_F_HW_TLS_TX when HW_CSUM is disabled
  tcp: Add logic to check for SYN w/ data in tcp_simple_retransmit
  net: mscc: ocelot: install MAC addresses in .ndo_set_rx_mode from process context
  nfc: s3fwrn5: Release the nfc firmware
  net: vxget: clean up sparse warnings
  mlxsw: spectrum_router: Use eXtended mezzanine to offload IPv4 router
  mlxsw: spectrum: Set KVH XLT cache mode for Spectrum2/3
  mlxsw: spectrum_router_xm: Introduce basic XM cache flushing
  mlxsw: reg: Add Router LPM Cache Enable Register
  mlxsw: reg: Add Router LPM Cache ML Delete Register
  mlxsw: spectrum_router_xm: Implement L-value tracking for M-index
  mlxsw: reg: Add XM Router M Table Register
  ...

1 files changed, 163 insertions, 55 deletions

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 90cd52df99a6..c5328f407aab 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -242,7 +242,6 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 
 		mp_opt->add_addr = 1;
 		mp_opt->addr_id = *ptr++;
-		pr_debug("ADD_ADDR: id=%d, echo=%d", mp_opt->addr_id, mp_opt->echo);
 		if (mp_opt->family == MPTCP_ADDR_IPVERSION_4) {
 			memcpy((u8 *)&mp_opt->addr.s_addr, (u8 *)ptr, 4);
 			ptr += 4;
@@ -267,6 +266,9 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 			mp_opt->ahmac = get_unaligned_be64(ptr);
 			ptr += 8;
 		}
+		pr_debug("ADD_ADDR%s: id=%d, ahmac=%llu, echo=%d, port=%d",
+			 (mp_opt->family == MPTCP_ADDR_IPVERSION_6) ? "6" : "",
+			 mp_opt->addr_id, mp_opt->ahmac, mp_opt->echo, mp_opt->port);
 		break;
 
 	case MPTCPOPT_RM_ADDR:
@@ -280,6 +282,16 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		pr_debug("RM_ADDR: id=%d", mp_opt->rm_id);
 		break;
 
+	case MPTCPOPT_MP_FASTCLOSE:
+		if (opsize != TCPOLEN_MPTCP_FASTCLOSE)
+			break;
+
+		ptr += 2;
+		mp_opt->rcvr_key = get_unaligned_be64(ptr);
+		ptr += 8;
+		mp_opt->fastclose = 1;
+		break;
+
 	default:
 		break;
 	}
@@ -297,6 +309,7 @@ void mptcp_get_options(const struct sk_buff *skb,
 	mp_opt->mp_join = 0;
 	mp_opt->add_addr = 0;
 	mp_opt->ahmac = 0;
+	mp_opt->fastclose = 0;
 	mp_opt->port = 0;
 	mp_opt->rm_addr = 0;
 	mp_opt->dss = 0;
@@ -492,7 +505,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 	bool ret = false;
 
 	mpext = skb ? mptcp_get_ext(skb) : NULL;
-	snd_data_fin_enable = READ_ONCE(msk->snd_data_fin_enable);
+	snd_data_fin_enable = mptcp_data_fin_enabled(msk);
 
 	if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) {
 		unsigned int map_size;
@@ -528,6 +541,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 		opts->ext_copy.ack64 = 0;
 	}
 	opts->ext_copy.use_ack = 1;
+	WRITE_ONCE(msk->old_wspace, __mptcp_space((struct sock *)msk));
 
 	/* Add kind/length/subtype/flag overhead if mapping is not populated */
 	if (dss_size == 0)
@@ -573,27 +587,43 @@ static u64 add_addr6_generate_hmac(u64 key1, u64 key2, u8 addr_id,
 }
 #endif
 
-static bool mptcp_established_options_add_addr(struct sock *sk,
+static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *skb,
 					       unsigned int *size,
 					       unsigned int remaining,
 					       struct mptcp_out_options *opts)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+	bool drop_other_suboptions = false;
+	unsigned int opt_size = *size;
 	struct mptcp_addr_info saddr;
 	bool echo;
+	bool port;
 	int len;
 
+	if ((mptcp_pm_should_add_signal_ipv6(msk) ||
+	     mptcp_pm_should_add_signal_port(msk)) &&
+	    skb && skb_is_tcp_pure_ack(skb)) {
+		pr_debug("drop other suboptions");
+		opts->suboptions = 0;
+		remaining += opt_size;
+		drop_other_suboptions = true;
+	}
+
 	if (!mptcp_pm_should_add_signal(msk) ||
-	    !(mptcp_pm_add_addr_signal(msk, remaining, &saddr, &echo)))
+	    !(mptcp_pm_add_addr_signal(msk, remaining, &saddr, &echo, &port)))
 		return false;
 
-	len = mptcp_add_addr_len(saddr.family, echo);
+	len = mptcp_add_addr_len(saddr.family, echo, port);
 	if (remaining < len)
 		return false;
 
 	*size = len;
+	if (drop_other_suboptions)
+		*size -= opt_size;
 	opts->addr_id = saddr.id;
+	if (port)
+		opts->port = ntohs(saddr.port);
 	if (saddr.family == AF_INET) {
 		opts->suboptions |= OPTION_MPTCP_ADD_ADDR;
 		opts->addr = saddr.addr;
@@ -616,7 +646,8 @@ static bool mptcp_established_options_add_addr(struct sock *sk,
 		}
 	}
 #endif
-	pr_debug("addr_id=%d, ahmac=%llu, echo=%d", opts->addr_id, opts->ahmac, echo);
+	pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d",
+		 opts->addr_id, opts->ahmac, echo, opts->port);
 
 	return true;
 }
@@ -678,7 +709,7 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
 
 	*size += opt_size;
 	remaining -= opt_size;
-	if (mptcp_established_options_add_addr(sk, &opt_size, remaining, opts)) {
+	if (mptcp_established_options_add_addr(sk, skb, &opt_size, remaining, opts)) {
 		*size += opt_size;
 		remaining -= opt_size;
 		ret = true;
@@ -759,6 +790,11 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 		goto fully_established;
 	}
 
+	if (mp_opt->add_addr) {
+		WRITE_ONCE(msk->fully_established, true);
+		return true;
+	}
+
 	/* If the first established packet does not contain MP_CAPABLE + data
 	 * then fallback to TCP. Fallback scenarios requires a reset for
 	 * MP_JOIN subflows.
@@ -777,7 +813,12 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 	mptcp_subflow_fully_established(subflow, mp_opt);
 
 fully_established:
-	if (likely(subflow->pm_notified))
+	/* if the subflow is not already linked into the conn_list, we can't
+	 * notify the PM: this subflow is still on the listener queue
+	 * and the PM possibly acquiring the subflow lock could race with
+	 * the listener close
+	 */
+	if (likely(subflow->pm_notified) || list_empty(&subflow->node))
 		return true;
 
 	subflow->pm_notified = 1;
@@ -809,31 +850,39 @@ static u64 expand_ack(u64 old_ack, u64 cur_ack, bool use_64bit)
 	return cur_ack;
 }
 
-static void update_una(struct mptcp_sock *msk,
-		       struct mptcp_options_received *mp_opt)
+static void ack_update_msk(struct mptcp_sock *msk,
+			   struct sock *ssk,
+			   struct mptcp_options_received *mp_opt)
 {
-	u64 new_snd_una, snd_una, old_snd_una = atomic64_read(&msk->snd_una);
-	u64 write_seq = READ_ONCE(msk->write_seq);
+	u64 new_wnd_end, new_snd_una, snd_nxt = READ_ONCE(msk->snd_nxt);
+	struct sock *sk = (struct sock *)msk;
+	u64 old_snd_una;
+
+	mptcp_data_lock(sk);
 
 	/* avoid ack expansion on update conflict, to reduce the risk of
 	 * wrongly expanding to a future ack sequence number, which is way
 	 * 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);
 
 	/* ACK for data not even sent yet? Ignore. */
-	if (after64(new_snd_una, write_seq))
+	if (after64(new_snd_una, snd_nxt))
 		new_snd_una = old_snd_una;
 
-	while (after64(new_snd_una, old_snd_una)) {
-		snd_una = old_snd_una;
-		old_snd_una = atomic64_cmpxchg(&msk->snd_una, snd_una,
-					       new_snd_una);
-		if (old_snd_una == snd_una) {
-			mptcp_data_acked((struct sock *)msk);
-			break;
-		}
+	new_wnd_end = new_snd_una + tcp_sk(ssk)->snd_wnd;
+
+	if (after64(new_wnd_end, msk->wnd_end)) {
+		msk->wnd_end = new_wnd_end;
+		__mptcp_wnd_updated(sk, ssk);
+	}
+
+	if (after64(new_snd_una, old_snd_una)) {
+		msk->snd_una = new_snd_una;
+		__mptcp_data_acked(sk);
 	}
+	mptcp_data_unlock(sk);
 }
 
 bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit)
@@ -886,13 +935,30 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 	struct mptcp_options_received mp_opt;
 	struct mptcp_ext *mpext;
 
-	if (__mptcp_check_fallback(msk))
+	if (__mptcp_check_fallback(msk)) {
+		/* Keep it simple and unconditionally trigger send data cleanup and
+		 * pending queue spooling. We will need to acquire the data lock
+		 * for more accurate checks, and once the lock is acquired, such
+		 * helpers are cheap.
+		 */
+		mptcp_data_lock(subflow->conn);
+		if (mptcp_send_head(subflow->conn))
+			__mptcp_wnd_updated(subflow->conn, sk);
+		__mptcp_data_acked(subflow->conn);
+		mptcp_data_unlock(subflow->conn);
 		return;
+	}
 
 	mptcp_get_options(skb, &mp_opt);
 	if (!check_fully_established(msk, sk, subflow, skb, &mp_opt))
 		return;
 
+	if (mp_opt.fastclose &&
+	    msk->local_key == mp_opt.rcvr_key) {
+		WRITE_ONCE(msk->rcv_fastclose, true);
+		mptcp_schedule_work((struct sock *)msk);
+	}
+
 	if (mp_opt.add_addr && add_addr_hmac_valid(msk, &mp_opt)) {
 		struct mptcp_addr_info addr;
 
@@ -930,7 +996,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 	 * monodirectional flows will stuck
 	 */
 	if (mp_opt.use_ack)
-		update_una(msk, &mp_opt);
+		ack_update_msk(msk, sk, &mp_opt);
 
 	/* Zero-data-length packets are dropped by the caller and not
 	 * propagated to the MPTCP layer, so the skb extension does not
@@ -975,7 +1041,24 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 	}
 }
 
-void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts)
+static void mptcp_set_rwin(const struct tcp_sock *tp)
+{
+	const struct sock *ssk = (const struct sock *)tp;
+	const struct mptcp_subflow_context *subflow;
+	struct mptcp_sock *msk;
+	u64 ack_seq;
+
+	subflow = mptcp_subflow_ctx(ssk);
+	msk = mptcp_sk(subflow->conn);
+
+	ack_seq = READ_ONCE(msk->ack_seq) + tp->rcv_wnd;
+
+	if (after64(ack_seq, READ_ONCE(msk->rcv_wnd_sent)))
+		WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
+}
+
+void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
+			 struct mptcp_out_options *opts)
 {
 	if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK |
 	     OPTION_MPTCP_MPC_ACK) & opts->suboptions) {
@@ -1014,44 +1097,66 @@ void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts)
 	}
 
 mp_capable_done:
-	if (OPTION_MPTCP_ADD_ADDR & opts->suboptions) {
-		if (opts->ahmac)
-			*ptr++ = mptcp_option(MPTCPOPT_ADD_ADDR,
-					      TCPOLEN_MPTCP_ADD_ADDR, 0,
-					      opts->addr_id);
-		else
-			*ptr++ = mptcp_option(MPTCPOPT_ADD_ADDR,
-					      TCPOLEN_MPTCP_ADD_ADDR_BASE,
-					      MPTCP_ADDR_ECHO,
-					      opts->addr_id);
-		memcpy((u8 *)ptr, (u8 *)&opts->addr.s_addr, 4);
-		ptr += 1;
+	if ((OPTION_MPTCP_ADD_ADDR
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	     | OPTION_MPTCP_ADD_ADDR6
+#endif
+	    ) & opts->suboptions) {
+		u8 len = TCPOLEN_MPTCP_ADD_ADDR_BASE;
+		u8 echo = MPTCP_ADDR_ECHO;
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+		if (OPTION_MPTCP_ADD_ADDR6 & opts->suboptions)
+			len = TCPOLEN_MPTCP_ADD_ADDR6_BASE;
+#endif
+
+		if (opts->port)
+			len += TCPOLEN_MPTCP_PORT_LEN;
+
 		if (opts->ahmac) {
-			put_unaligned_be64(opts->ahmac, ptr);
-			ptr += 2;
+			len += sizeof(opts->ahmac);
+			echo = 0;
 		}
-	}
 
+		*ptr++ = mptcp_option(MPTCPOPT_ADD_ADDR,
+				      len, echo, opts->addr_id);
+		if (OPTION_MPTCP_ADD_ADDR & opts->suboptions) {
+			memcpy((u8 *)ptr, (u8 *)&opts->addr.s_addr, 4);
+			ptr += 1;
+		}
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
-	if (OPTION_MPTCP_ADD_ADDR6 & opts->suboptions) {
-		if (opts->ahmac)
-			*ptr++ = mptcp_option(MPTCPOPT_ADD_ADDR,
-					      TCPOLEN_MPTCP_ADD_ADDR6, 0,
-					      opts->addr_id);
-		else
-			*ptr++ = mptcp_option(MPTCPOPT_ADD_ADDR,
-					      TCPOLEN_MPTCP_ADD_ADDR6_BASE,
-					      MPTCP_ADDR_ECHO,
-					      opts->addr_id);
-		memcpy((u8 *)ptr, opts->addr6.s6_addr, 16);
-		ptr += 4;
-		if (opts->ahmac) {
-			put_unaligned_be64(opts->ahmac, ptr);
-			ptr += 2;
+		else if (OPTION_MPTCP_ADD_ADDR6 & opts->suboptions) {
+			memcpy((u8 *)ptr, opts->addr6.s6_addr, 16);
+			ptr += 4;
 		}
-	}
 #endif
 
+		if (!opts->port) {
+			if (opts->ahmac) {
+				put_unaligned_be64(opts->ahmac, ptr);
+				ptr += 2;
+			}
+		} else {
+			if (opts->ahmac) {
+				u8 *bptr = (u8 *)ptr;
+
+				put_unaligned_be16(opts->port, bptr);
+				bptr += 2;
+				put_unaligned_be64(opts->ahmac, bptr);
+				bptr += 8;
+				put_unaligned_be16(TCPOPT_NOP << 8 |
+						   TCPOPT_NOP, bptr);
+
+				ptr += 3;
+			} else {
+				put_unaligned_be32(opts->port << 16 |
+						   TCPOPT_NOP << 8 |
+						   TCPOPT_NOP, ptr);
+				ptr += 1;
+			}
+		}
+	}
+
 	if (OPTION_MPTCP_RM_ADDR & opts->suboptions) {
 		*ptr++ = mptcp_option(MPTCPOPT_RM_ADDR,
 				      TCPOLEN_MPTCP_RM_ADDR_BASE,
@@ -1132,4 +1237,7 @@ mp_capable_done:
 					   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
 		}
 	}
+
+	if (tp)
+		mptcp_set_rwin(tp);
 }