From a78d163978567adc2733465289293dad479d842a Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Fri, 24 Apr 2020 17:08:30 +0200
Subject: vsock/virtio: fix multiple packet delivery to monitoring devices

In virtio_transport.c, if the virtqueue is full, the transmitting
packet is queued up and it will be sent in the next iteration.
This causes the same packet to be delivered multiple times to
monitoring devices.

We want to continue to deliver packets to monitoring devices before
it is put in the virtqueue, to avoid that replies can appear in the
packet capture before the transmitted packet.

This patch fixes the issue, adding a new flag (tap_delivered) in
struct virtio_vsock_pkt, to check if the packet is already delivered
to monitoring devices.

In vhost/vsock.c, we are splitting packets, so we must set
'tap_delivered' to false when we queue up the same virtio_vsock_pkt
to handle the remaining bytes.

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/virtio_vsock.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 71c81e0dc8f2..dc636b727179 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -48,6 +48,7 @@ struct virtio_vsock_pkt {
 	u32 len;
 	u32 off;
 	bool reply;
+	bool tap_delivered;
 };
 
 struct virtio_vsock_pkt_info {
-- 
cgit v1.2.3


From 263e1201a2c324b60b15ecda5de9ebf1e7293e31 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 30 Apr 2020 15:01:51 +0200
Subject: mptcp: consolidate synack processing.

Currently the MPTCP code uses 2 hooks to process syn-ack
packets, mptcp_rcv_synsent() and the sk_rx_dst_set()
callback.

We can drop the first, moving the relevant code into the
latter, reducing the hooking into the TCP code. This is
also needed by the next patch.

v1 -> v2:
 - use local tcp sock ptr instead of casting the sk variable
   several times - DaveM

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/mptcp.h  |  1 -
 net/ipv4/tcp_input.c |  3 ---
 net/mptcp/options.c  | 22 ----------------------
 net/mptcp/subflow.c  | 27 ++++++++++++++++++++++++---
 4 files changed, 24 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 0e7c5471010b..4ecfa7d5e0c7 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -72,7 +72,6 @@ void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr,
 			int opsize, struct tcp_options_received *opt_rx);
 bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
 		       unsigned int *size, struct mptcp_out_options *opts);
-void mptcp_rcv_synsent(struct sock *sk);
 bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
 			  struct mptcp_out_options *opts);
 bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index bf4ced9273e8..81425542da44 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5990,9 +5990,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		tcp_initialize_rcv_mss(sk);
 
-		if (sk_is_mptcp(sk))
-			mptcp_rcv_synsent(sk);
-
 		/* Remember, tcp_poll() does not lock socket!
 		 * Change state from SYN-SENT only after copied_seq
 		 * is initialized. */
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 4a7c467b99db..8fea686a5562 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -344,28 +344,6 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
 	return false;
 }
 
-void mptcp_rcv_synsent(struct sock *sk)
-{
-	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	if (subflow->request_mptcp && tp->rx_opt.mptcp.mp_capable) {
-		subflow->mp_capable = 1;
-		subflow->can_ack = 1;
-		subflow->remote_key = tp->rx_opt.mptcp.sndr_key;
-		pr_debug("subflow=%p, remote_key=%llu", subflow,
-			 subflow->remote_key);
-	} else if (subflow->request_join && tp->rx_opt.mptcp.mp_join) {
-		subflow->mp_join = 1;
-		subflow->thmac = tp->rx_opt.mptcp.thmac;
-		subflow->remote_nonce = tp->rx_opt.mptcp.nonce;
-		pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u", subflow,
-			 subflow->thmac, subflow->remote_nonce);
-	} else if (subflow->request_mptcp) {
-		tcp_sk(sk)->is_mptcp = 0;
-	}
-}
-
 /* MP_JOIN client subflow must wait for 4th ack before sending any data:
  * TCP can't schedule delack timer before the subflow is fully established.
  * MPTCP uses the delack timer to do 3rd ack retransmissions
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 71256f03707f..84f6408594c9 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -222,6 +222,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct sock *parent = subflow->conn;
+	struct tcp_sock *tp = tcp_sk(sk);
 
 	subflow->icsk_af_ops->sk_rx_dst_set(sk, skb);
 
@@ -230,14 +231,35 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		parent->sk_state_change(parent);
 	}
 
-	if (subflow->conn_finished || !tcp_sk(sk)->is_mptcp)
+	/* be sure no special action on any packet other than syn-ack */
+	if (subflow->conn_finished)
+		return;
+
+	subflow->conn_finished = 1;
+
+	if (subflow->request_mptcp && tp->rx_opt.mptcp.mp_capable) {
+		subflow->mp_capable = 1;
+		subflow->can_ack = 1;
+		subflow->remote_key = tp->rx_opt.mptcp.sndr_key;
+		pr_debug("subflow=%p, remote_key=%llu", subflow,
+			 subflow->remote_key);
+	} else if (subflow->request_join && tp->rx_opt.mptcp.mp_join) {
+		subflow->mp_join = 1;
+		subflow->thmac = tp->rx_opt.mptcp.thmac;
+		subflow->remote_nonce = tp->rx_opt.mptcp.nonce;
+		pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u", subflow,
+			 subflow->thmac, subflow->remote_nonce);
+	} else if (subflow->request_mptcp) {
+		tp->is_mptcp = 0;
+	}
+
+	if (!tp->is_mptcp)
 		return;
 
 	if (subflow->mp_capable) {
 		pr_debug("subflow=%p, remote_key=%llu", mptcp_subflow_ctx(sk),
 			 subflow->remote_key);
 		mptcp_finish_connect(sk);
-		subflow->conn_finished = 1;
 
 		if (skb) {
 			pr_debug("synack seq=%u", TCP_SKB_CB(skb)->seq);
@@ -264,7 +286,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		if (!mptcp_finish_join(sk))
 			goto do_reset;
 
-		subflow->conn_finished = 1;
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX);
 	} else {
 do_reset:
-- 
cgit v1.2.3


From cfde141ea3faa30e362bbdb5c28001bbbdb0b8e0 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 30 Apr 2020 15:01:52 +0200
Subject: mptcp: move option parsing into mptcp_incoming_options()

The mptcp_options_received structure carries several per
packet flags (mp_capable, mp_join, etc.). Such fields must
be cleared on each packet, even on dropped ones or packet
not carrying any MPTCP options, but the current mptcp
code clears them only on TCP option reset.

On several races/corner cases we end-up with stray bits in
incoming options, leading to WARN_ON splats. e.g.:

[  171.164906] Bad mapping: ssn=32714 map_seq=1 map_data_len=32713
[  171.165006] WARNING: CPU: 1 PID: 5026 at net/mptcp/subflow.c:533 warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531)
[  171.167632] Modules linked in: ip6_vti ip_vti ip_gre ipip sit tunnel4 ip_tunnel geneve ip6_udp_tunnel udp_tunnel macsec macvtap tap ipvlan macvlan 8021q garp mrp xfrm_interface veth netdevsim nlmon dummy team bonding vcan bridge stp llc ip6_gre gre ip6_tunnel tunnel6 tun binfmt_misc intel_rapl_msr intel_rapl_common rfkill kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel joydev virtio_balloon pcspkr i2c_piix4 sunrpc ip_tables xfs libcrc32c crc32c_intel serio_raw virtio_console ata_generic virtio_blk virtio_net net_failover failover ata_piix libata
[  171.199464] CPU: 1 PID: 5026 Comm: repro Not tainted 5.7.0-rc1.mptcp_f227fdf5d388+ #95
[  171.200886] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014
[  171.202546] RIP: 0010:warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531)
[  171.206537] Code: c1 ea 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 04 84 d2 75 1d 8b 55 3c 44 89 e6 48 c7 c7 20 51 13 95 e8 37 8b 22 fe <0f> 0b 48 83 c4 08 5b 5d 41 5c c3 89 4c 24 04 e8 db d6 94 fe 8b 4c
[  171.220473] RSP: 0018:ffffc90000150560 EFLAGS: 00010282
[  171.221639] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
[  171.223108] RDX: 0000000000000000 RSI: 0000000000000008 RDI: fffff5200002a09e
[  171.224388] RBP: ffff8880aa6e3c00 R08: 0000000000000001 R09: fffffbfff2ec9955
[  171.225706] R10: ffffffff9764caa7 R11: fffffbfff2ec9954 R12: 0000000000007fca
[  171.227211] R13: ffff8881066f4a7f R14: ffff8880aa6e3c00 R15: 0000000000000020
[  171.228460] FS:  00007f8623719740(0000) GS:ffff88810be00000(0000) knlGS:0000000000000000
[  171.230065] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  171.231303] CR2: 00007ffdab190a50 CR3: 00000001038ea006 CR4: 0000000000160ee0
[  171.232586] Call Trace:
[  171.233109]  <IRQ>
[  171.233531] get_mapping_status (linux-mptcp/net/mptcp/subflow.c:691)
[  171.234371] mptcp_subflow_data_available (linux-mptcp/net/mptcp/subflow.c:736 linux-mptcp/net/mptcp/subflow.c:832)
[  171.238181] subflow_state_change (linux-mptcp/net/mptcp/subflow.c:1085 (discriminator 1))
[  171.239066] tcp_fin (linux-mptcp/net/ipv4/tcp_input.c:4217)
[  171.240123] tcp_data_queue (linux-mptcp/./include/linux/compiler.h:199 linux-mptcp/net/ipv4/tcp_input.c:4822)
[  171.245083] tcp_rcv_established (linux-mptcp/./include/linux/skbuff.h:1785 linux-mptcp/./include/net/tcp.h:1774 linux-mptcp/./include/net/tcp.h:1847 linux-mptcp/net/ipv4/tcp_input.c:5238 linux-mptcp/net/ipv4/tcp_input.c:5730)
[  171.254089] tcp_v4_rcv (linux-mptcp/./include/linux/spinlock.h:393 linux-mptcp/net/ipv4/tcp_ipv4.c:2009)
[  171.258969] ip_protocol_deliver_rcu (linux-mptcp/net/ipv4/ip_input.c:204 (discriminator 1))
[  171.260214] ip_local_deliver_finish (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/ipv4/ip_input.c:232)
[  171.261389] ip_local_deliver (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:252)
[  171.265884] ip_rcv (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:539)
[  171.273666] process_backlog (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/core/dev.c:6135)
[  171.275328] net_rx_action (linux-mptcp/net/core/dev.c:6572 linux-mptcp/net/core/dev.c:6640)
[  171.280472] __do_softirq (linux-mptcp/./arch/x86/include/asm/jump_label.h:25 linux-mptcp/./include/linux/jump_label.h:200 linux-mptcp/./include/trace/events/irq.h:142 linux-mptcp/kernel/softirq.c:293)
[  171.281379] do_softirq_own_stack (linux-mptcp/arch/x86/entry/entry_64.S:1083)
[  171.282358]  </IRQ>

We could address the issue clearing explicitly the relevant fields
in several places - tcp_parse_option, tcp_fast_parse_options,
possibly others.

Instead we move the MPTCP option parsing into the already existing
mptcp ingress hook, so that we need to clear the fields in a single
place.

This allows us dropping an MPTCP hook from the TCP code and
removing the quite large mptcp_options_received from the tcp_sock
struct. On the flip side, the MPTCP sockets will traverse the
option space twice (in tcp_parse_option() and in
mptcp_incoming_options(). That looks acceptable: we already
do that for syn and 3rd ack packets, plain TCP socket will
benefit from it, and even MPTCP sockets will experience better
code locality, reducing the jumps between TCP and MPTCP code.

v1 -> v2:
 - rebased on current '-net' tree

Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h  | 51 ----------------------------------------
 include/net/mptcp.h  |  2 --
 net/ipv4/tcp_input.c |  4 ----
 net/mptcp/options.c  | 66 +++++++++++++++++++++++++++++-----------------------
 net/mptcp/protocol.c |  6 ++---
 net/mptcp/protocol.h | 43 ++++++++++++++++++++++++++++++++--
 net/mptcp/subflow.c  | 65 +++++++++++++++++++++++++++------------------------
 7 files changed, 115 insertions(+), 122 deletions(-)

(limited to 'include')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 421c99c12291..4f8159e90ce1 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -78,47 +78,6 @@ struct tcp_sack_block {
 #define TCP_SACK_SEEN     (1 << 0)   /*1 = peer is SACK capable, */
 #define TCP_DSACK_SEEN    (1 << 2)   /*1 = DSACK was received from peer*/
 
-#if IS_ENABLED(CONFIG_MPTCP)
-struct mptcp_options_received {
-	u64	sndr_key;
-	u64	rcvr_key;
-	u64	data_ack;
-	u64	data_seq;
-	u32	subflow_seq;
-	u16	data_len;
-	u16	mp_capable : 1,
-		mp_join : 1,
-		dss : 1,
-		add_addr : 1,
-		rm_addr : 1,
-		family : 4,
-		echo : 1,
-		backup : 1;
-	u32	token;
-	u32	nonce;
-	u64	thmac;
-	u8	hmac[20];
-	u8	join_id;
-	u8	use_map:1,
-		dsn64:1,
-		data_fin:1,
-		use_ack:1,
-		ack64:1,
-		mpc_map:1,
-		__unused:2;
-	u8	addr_id;
-	u8	rm_id;
-	union {
-		struct in_addr	addr;
-#if IS_ENABLED(CONFIG_MPTCP_IPV6)
-		struct in6_addr	addr6;
-#endif
-	};
-	u64	ahmac;
-	u16	port;
-};
-#endif
-
 struct tcp_options_received {
 /*	PAWS/RTTM data	*/
 	int	ts_recent_stamp;/* Time we stored ts_recent (for aging) */
@@ -136,9 +95,6 @@ struct tcp_options_received {
 	u8	num_sacks;	/* Number of SACK blocks		*/
 	u16	user_mss;	/* mss requested by user in ioctl	*/
 	u16	mss_clamp;	/* Maximal mss, negotiated at connection setup */
-#if IS_ENABLED(CONFIG_MPTCP)
-	struct mptcp_options_received	mptcp;
-#endif
 };
 
 static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
@@ -148,13 +104,6 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
 #if IS_ENABLED(CONFIG_SMC)
 	rx_opt->smc_ok = 0;
 #endif
-#if IS_ENABLED(CONFIG_MPTCP)
-	rx_opt->mptcp.mp_capable = 0;
-	rx_opt->mptcp.mp_join = 0;
-	rx_opt->mptcp.add_addr = 0;
-	rx_opt->mptcp.rm_addr = 0;
-	rx_opt->mptcp.dss = 0;
-#endif
 }
 
 /* This is the max number of SACKS that we'll generate and process. It's safe
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 4ecfa7d5e0c7..3bce2019e4da 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -68,8 +68,6 @@ static inline bool rsk_is_mptcp(const struct request_sock *req)
 	return tcp_rsk(req)->is_mptcp;
 }
 
-void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr,
-			int opsize, struct tcp_options_received *opt_rx);
 bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
 		       unsigned int *size, struct mptcp_out_options *opts);
 bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 81425542da44..b996dc1069c5 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3926,10 +3926,6 @@ void tcp_parse_options(const struct net *net,
 				 */
 				break;
 #endif
-			case TCPOPT_MPTCP:
-				mptcp_parse_option(skb, ptr, opsize, opt_rx);
-				break;
-
 			case TCPOPT_FASTOPEN:
 				tcp_parse_fastopen_option(
 					opsize - TCPOLEN_FASTOPEN_BASE,
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 8fea686a5562..eadbd59586e4 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -16,10 +16,10 @@ static bool mptcp_cap_flag_sha256(u8 flags)
 	return (flags & MPTCP_CAP_FLAG_MASK) == MPTCP_CAP_HMAC_SHA256;
 }
 
-void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr,
-			int opsize, struct tcp_options_received *opt_rx)
+static void mptcp_parse_option(const struct sk_buff *skb,
+			       const unsigned char *ptr, int opsize,
+			       struct mptcp_options_received *mp_opt)
 {
-	struct mptcp_options_received *mp_opt = &opt_rx->mptcp;
 	u8 subtype = *ptr >> 4;
 	int expected_opsize;
 	u8 version;
@@ -283,12 +283,20 @@ void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr,
 }
 
 void mptcp_get_options(const struct sk_buff *skb,
-		       struct tcp_options_received *opt_rx)
+		       struct mptcp_options_received *mp_opt)
 {
-	const unsigned char *ptr;
 	const struct tcphdr *th = tcp_hdr(skb);
-	int length = (th->doff * 4) - sizeof(struct tcphdr);
+	const unsigned char *ptr;
+	int length;
 
+	/* initialize option status */
+	mp_opt->mp_capable = 0;
+	mp_opt->mp_join = 0;
+	mp_opt->add_addr = 0;
+	mp_opt->rm_addr = 0;
+	mp_opt->dss = 0;
+
+	length = (th->doff * 4) - sizeof(struct tcphdr);
 	ptr = (const unsigned char *)(th + 1);
 
 	while (length > 0) {
@@ -308,7 +316,7 @@ void mptcp_get_options(const struct sk_buff *skb,
 			if (opsize > length)
 				return;	/* don't parse partial options */
 			if (opcode == TCPOPT_MPTCP)
-				mptcp_parse_option(skb, ptr, opsize, opt_rx);
+				mptcp_parse_option(skb, ptr, opsize, mp_opt);
 			ptr += opsize - 2;
 			length -= opsize;
 		}
@@ -797,41 +805,41 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
-	struct mptcp_options_received *mp_opt;
+	struct mptcp_options_received mp_opt;
 	struct mptcp_ext *mpext;
 
-	mp_opt = &opt_rx->mptcp;
-	if (!check_fully_established(msk, sk, subflow, skb, mp_opt))
+	mptcp_get_options(skb, &mp_opt);
+	if (!check_fully_established(msk, sk, subflow, skb, &mp_opt))
 		return;
 
-	if (mp_opt->add_addr && add_addr_hmac_valid(msk, mp_opt)) {
+	if (mp_opt.add_addr && add_addr_hmac_valid(msk, &mp_opt)) {
 		struct mptcp_addr_info addr;
 
-		addr.port = htons(mp_opt->port);
-		addr.id = mp_opt->addr_id;
-		if (mp_opt->family == MPTCP_ADDR_IPVERSION_4) {
+		addr.port = htons(mp_opt.port);
+		addr.id = mp_opt.addr_id;
+		if (mp_opt.family == MPTCP_ADDR_IPVERSION_4) {
 			addr.family = AF_INET;
-			addr.addr = mp_opt->addr;
+			addr.addr = mp_opt.addr;
 		}
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
-		else if (mp_opt->family == MPTCP_ADDR_IPVERSION_6) {
+		else if (mp_opt.family == MPTCP_ADDR_IPVERSION_6) {
 			addr.family = AF_INET6;
-			addr.addr6 = mp_opt->addr6;
+			addr.addr6 = mp_opt.addr6;
 		}
 #endif
-		if (!mp_opt->echo)
+		if (!mp_opt.echo)
 			mptcp_pm_add_addr_received(msk, &addr);
-		mp_opt->add_addr = 0;
+		mp_opt.add_addr = 0;
 	}
 
-	if (!mp_opt->dss)
+	if (!mp_opt.dss)
 		return;
 
 	/* we can't wait for recvmsg() to update the ack_seq, otherwise
 	 * monodirectional flows will stuck
 	 */
-	if (mp_opt->use_ack)
-		update_una(msk, mp_opt);
+	if (mp_opt.use_ack)
+		update_una(msk, &mp_opt);
 
 	mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
 	if (!mpext)
@@ -839,8 +847,8 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
 
 	memset(mpext, 0, sizeof(*mpext));
 
-	if (mp_opt->use_map) {
-		if (mp_opt->mpc_map) {
+	if (mp_opt.use_map) {
+		if (mp_opt.mpc_map) {
 			/* this is an MP_CAPABLE carrying MPTCP data
 			 * we know this map the first chunk of data
 			 */
@@ -851,12 +859,12 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
 			mpext->dsn64 = 1;
 			mpext->mpc_map = 1;
 		} else {
-			mpext->data_seq = mp_opt->data_seq;
-			mpext->subflow_seq = mp_opt->subflow_seq;
-			mpext->dsn64 = mp_opt->dsn64;
-			mpext->data_fin = mp_opt->data_fin;
+			mpext->data_seq = mp_opt.data_seq;
+			mpext->subflow_seq = mp_opt.subflow_seq;
+			mpext->dsn64 = mp_opt.dsn64;
+			mpext->data_fin = mp_opt.data_fin;
 		}
-		mpext->data_len = mp_opt->data_len;
+		mpext->data_len = mp_opt.data_len;
 		mpext->use_map = 1;
 	}
 }
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 6e0188f5d3f3..e1f23016ed3f 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1334,7 +1334,7 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk)
 #endif
 
 struct sock *mptcp_sk_clone(const struct sock *sk,
-			    const struct tcp_options_received *opt_rx,
+			    const struct mptcp_options_received *mp_opt,
 			    struct request_sock *req)
 {
 	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
@@ -1373,9 +1373,9 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
 
 	msk->write_seq = subflow_req->idsn + 1;
 	atomic64_set(&msk->snd_una, msk->write_seq);
-	if (opt_rx->mptcp.mp_capable) {
+	if (mp_opt->mp_capable) {
 		msk->can_ack = true;
-		msk->remote_key = opt_rx->mptcp.sndr_key;
+		msk->remote_key = mp_opt->sndr_key;
 		mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq);
 		ack_seq++;
 		msk->ack_seq = ack_seq;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index a2b3048037d0..e4ca6320ce76 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -91,6 +91,45 @@
 #define MPTCP_WORK_RTX		2
 #define MPTCP_WORK_EOF		3
 
+struct mptcp_options_received {
+	u64	sndr_key;
+	u64	rcvr_key;
+	u64	data_ack;
+	u64	data_seq;
+	u32	subflow_seq;
+	u16	data_len;
+	u16	mp_capable : 1,
+		mp_join : 1,
+		dss : 1,
+		add_addr : 1,
+		rm_addr : 1,
+		family : 4,
+		echo : 1,
+		backup : 1;
+	u32	token;
+	u32	nonce;
+	u64	thmac;
+	u8	hmac[20];
+	u8	join_id;
+	u8	use_map:1,
+		dsn64:1,
+		data_fin:1,
+		use_ack:1,
+		ack64:1,
+		mpc_map:1,
+		__unused:2;
+	u8	addr_id;
+	u8	rm_id;
+	union {
+		struct in_addr	addr;
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+		struct in6_addr	addr6;
+#endif
+	};
+	u64	ahmac;
+	u16	port;
+};
+
 static inline __be32 mptcp_option(u8 subopt, u8 len, u8 nib, u8 field)
 {
 	return htonl((TCPOPT_MPTCP << 24) | (len << 16) | (subopt << 12) |
@@ -331,10 +370,10 @@ int mptcp_proto_v6_init(void);
 #endif
 
 struct sock *mptcp_sk_clone(const struct sock *sk,
-			    const struct tcp_options_received *opt_rx,
+			    const struct mptcp_options_received *mp_opt,
 			    struct request_sock *req);
 void mptcp_get_options(const struct sk_buff *skb,
-		       struct tcp_options_received *opt_rx);
+		       struct mptcp_options_received *mp_opt);
 
 void mptcp_finish_connect(struct sock *sk);
 void mptcp_data_ready(struct sock *sk, struct sock *ssk);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 84f6408594c9..bad998529767 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -124,12 +124,11 @@ static void subflow_init_req(struct request_sock *req,
 {
 	struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener);
 	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
-	struct tcp_options_received rx_opt;
+	struct mptcp_options_received mp_opt;
 
 	pr_debug("subflow_req=%p, listener=%p", subflow_req, listener);
 
-	memset(&rx_opt.mptcp, 0, sizeof(rx_opt.mptcp));
-	mptcp_get_options(skb, &rx_opt);
+	mptcp_get_options(skb, &mp_opt);
 
 	subflow_req->mp_capable = 0;
 	subflow_req->mp_join = 0;
@@ -142,16 +141,16 @@ static void subflow_init_req(struct request_sock *req,
 		return;
 #endif
 
-	if (rx_opt.mptcp.mp_capable) {
+	if (mp_opt.mp_capable) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
 
-		if (rx_opt.mptcp.mp_join)
+		if (mp_opt.mp_join)
 			return;
-	} else if (rx_opt.mptcp.mp_join) {
+	} else if (mp_opt.mp_join) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX);
 	}
 
-	if (rx_opt.mptcp.mp_capable && listener->request_mptcp) {
+	if (mp_opt.mp_capable && listener->request_mptcp) {
 		int err;
 
 		err = mptcp_token_new_request(req);
@@ -159,13 +158,13 @@ static void subflow_init_req(struct request_sock *req,
 			subflow_req->mp_capable = 1;
 
 		subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
-	} else if (rx_opt.mptcp.mp_join && listener->request_mptcp) {
+	} else if (mp_opt.mp_join && listener->request_mptcp) {
 		subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
 		subflow_req->mp_join = 1;
-		subflow_req->backup = rx_opt.mptcp.backup;
-		subflow_req->remote_id = rx_opt.mptcp.join_id;
-		subflow_req->token = rx_opt.mptcp.token;
-		subflow_req->remote_nonce = rx_opt.mptcp.nonce;
+		subflow_req->backup = mp_opt.backup;
+		subflow_req->remote_id = mp_opt.join_id;
+		subflow_req->token = mp_opt.token;
+		subflow_req->remote_nonce = mp_opt.nonce;
 		pr_debug("token=%u, remote_nonce=%u", subflow_req->token,
 			 subflow_req->remote_nonce);
 		if (!subflow_token_join_request(req, skb)) {
@@ -221,6 +220,7 @@ static bool subflow_thmac_valid(struct mptcp_subflow_context *subflow)
 static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct mptcp_options_received mp_opt;
 	struct sock *parent = subflow->conn;
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -237,16 +237,17 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 
 	subflow->conn_finished = 1;
 
-	if (subflow->request_mptcp && tp->rx_opt.mptcp.mp_capable) {
+	mptcp_get_options(skb, &mp_opt);
+	if (subflow->request_mptcp && mp_opt.mp_capable) {
 		subflow->mp_capable = 1;
 		subflow->can_ack = 1;
-		subflow->remote_key = tp->rx_opt.mptcp.sndr_key;
+		subflow->remote_key = mp_opt.sndr_key;
 		pr_debug("subflow=%p, remote_key=%llu", subflow,
 			 subflow->remote_key);
-	} else if (subflow->request_join && tp->rx_opt.mptcp.mp_join) {
+	} else if (subflow->request_join && mp_opt.mp_join) {
 		subflow->mp_join = 1;
-		subflow->thmac = tp->rx_opt.mptcp.thmac;
-		subflow->remote_nonce = tp->rx_opt.mptcp.nonce;
+		subflow->thmac = mp_opt.thmac;
+		subflow->remote_nonce = mp_opt.nonce;
 		pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u", subflow,
 			 subflow->thmac, subflow->remote_nonce);
 	} else if (subflow->request_mptcp) {
@@ -343,7 +344,7 @@ drop:
 
 /* validate hmac received in third ACK */
 static bool subflow_hmac_valid(const struct request_sock *req,
-			       const struct tcp_options_received *rx_opt)
+			       const struct mptcp_options_received *mp_opt)
 {
 	const struct mptcp_subflow_request_sock *subflow_req;
 	u8 hmac[MPTCPOPT_HMAC_LEN];
@@ -360,7 +361,7 @@ static bool subflow_hmac_valid(const struct request_sock *req,
 			      subflow_req->local_nonce, hmac);
 
 	ret = true;
-	if (crypto_memneq(hmac, rx_opt->mptcp.hmac, sizeof(hmac)))
+	if (crypto_memneq(hmac, mp_opt->hmac, sizeof(hmac)))
 		ret = false;
 
 	sock_put((struct sock *)msk);
@@ -416,7 +417,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 {
 	struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk);
 	struct mptcp_subflow_request_sock *subflow_req;
-	struct tcp_options_received opt_rx;
+	struct mptcp_options_received mp_opt;
 	bool fallback_is_fatal = false;
 	struct sock *new_msk = NULL;
 	bool fallback = false;
@@ -424,7 +425,10 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 
 	pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn);
 
-	opt_rx.mptcp.mp_capable = 0;
+	/* we need later a valid 'mp_capable' value even when options are not
+	 * parsed
+	 */
+	mp_opt.mp_capable = 0;
 	if (tcp_rsk(req)->is_mptcp == 0)
 		goto create_child;
 
@@ -439,22 +443,21 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 			goto create_msk;
 		}
 
-		mptcp_get_options(skb, &opt_rx);
-		if (!opt_rx.mptcp.mp_capable) {
+		mptcp_get_options(skb, &mp_opt);
+		if (!mp_opt.mp_capable) {
 			fallback = true;
 			goto create_child;
 		}
 
 create_msk:
-		new_msk = mptcp_sk_clone(listener->conn, &opt_rx, req);
+		new_msk = mptcp_sk_clone(listener->conn, &mp_opt, req);
 		if (!new_msk)
 			fallback = true;
 	} else if (subflow_req->mp_join) {
 		fallback_is_fatal = true;
-		opt_rx.mptcp.mp_join = 0;
-		mptcp_get_options(skb, &opt_rx);
-		if (!opt_rx.mptcp.mp_join ||
-		    !subflow_hmac_valid(req, &opt_rx)) {
+		mptcp_get_options(skb, &mp_opt);
+		if (!mp_opt.mp_join ||
+		    !subflow_hmac_valid(req, &mp_opt)) {
 			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
 			return NULL;
 		}
@@ -494,9 +497,9 @@ create_child:
 			/* with OoO packets we can reach here without ingress
 			 * mpc option
 			 */
-			ctx->remote_key = opt_rx.mptcp.sndr_key;
-			ctx->fully_established = opt_rx.mptcp.mp_capable;
-			ctx->can_ack = opt_rx.mptcp.mp_capable;
+			ctx->remote_key = mp_opt.sndr_key;
+			ctx->fully_established = mp_opt.mp_capable;
+			ctx->can_ack = mp_opt.mp_capable;
 		} else if (ctx->mp_join) {
 			struct mptcp_sock *owner;
 
-- 
cgit v1.2.3


From b723748750ece7d844cdf2f52c01d37f83387208 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Mon, 27 Apr 2020 16:11:05 +0200
Subject: tunnel: Propagate ECT(1) when decapsulating as recommended by RFC6040
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

RFC 6040 recommends propagating an ECT(1) mark from an outer tunnel header
to the inner header if that inner header is already marked as ECT(0). When
RFC 6040 decapsulation was implemented, this case of propagation was not
added. This simply appears to be an oversight, so let's fix that.

Fixes: eccc1bb8d4b4 ("tunnel: drop packet if ECN present with not-ECT")
Reported-by: Bob Briscoe <ietf@bobbriscoe.net>
Reported-by: Olivier Tilmans <olivier.tilmans@nokia-bell-labs.com>
Cc: Dave Taht <dave.taht@gmail.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_ecn.h | 57 ++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 55 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h
index c8e2bebd8d93..0f0d1efe06dd 100644
--- a/include/net/inet_ecn.h
+++ b/include/net/inet_ecn.h
@@ -99,6 +99,20 @@ static inline int IP_ECN_set_ce(struct iphdr *iph)
 	return 1;
 }
 
+static inline int IP_ECN_set_ect1(struct iphdr *iph)
+{
+	u32 check = (__force u32)iph->check;
+
+	if ((iph->tos & INET_ECN_MASK) != INET_ECN_ECT_0)
+		return 0;
+
+	check += (__force u16)htons(0x100);
+
+	iph->check = (__force __sum16)(check + (check>=0xFFFF));
+	iph->tos ^= INET_ECN_MASK;
+	return 1;
+}
+
 static inline void IP_ECN_clear(struct iphdr *iph)
 {
 	iph->tos &= ~INET_ECN_MASK;
@@ -134,6 +148,22 @@ static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph)
 	return 1;
 }
 
+static inline int IP6_ECN_set_ect1(struct sk_buff *skb, struct ipv6hdr *iph)
+{
+	__be32 from, to;
+
+	if ((ipv6_get_dsfield(iph) & INET_ECN_MASK) != INET_ECN_ECT_0)
+		return 0;
+
+	from = *(__be32 *)iph;
+	to = from ^ htonl(INET_ECN_MASK << 20);
+	*(__be32 *)iph = to;
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_add(csum_sub(skb->csum, (__force __wsum)from),
+				     (__force __wsum)to);
+	return 1;
+}
+
 static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner)
 {
 	dscp &= ~INET_ECN_MASK;
@@ -159,6 +189,25 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb)
 	return 0;
 }
 
+static inline int INET_ECN_set_ect1(struct sk_buff *skb)
+{
+	switch (skb->protocol) {
+	case cpu_to_be16(ETH_P_IP):
+		if (skb_network_header(skb) + sizeof(struct iphdr) <=
+		    skb_tail_pointer(skb))
+			return IP_ECN_set_ect1(ip_hdr(skb));
+		break;
+
+	case cpu_to_be16(ETH_P_IPV6):
+		if (skb_network_header(skb) + sizeof(struct ipv6hdr) <=
+		    skb_tail_pointer(skb))
+			return IP6_ECN_set_ect1(skb, ipv6_hdr(skb));
+		break;
+	}
+
+	return 0;
+}
+
 /*
  * RFC 6040 4.2
  *  To decapsulate the inner header at the tunnel egress, a compliant
@@ -208,8 +257,12 @@ static inline int INET_ECN_decapsulate(struct sk_buff *skb,
 	int rc;
 
 	rc = __INET_ECN_decapsulate(outer, inner, &set_ce);
-	if (!rc && set_ce)
-		INET_ECN_set_ce(skb);
+	if (!rc) {
+		if (set_ce)
+			INET_ECN_set_ce(skb);
+		else if ((outer & INET_ECN_MASK) == INET_ECN_ECT_1)
+			INET_ECN_set_ect1(skb);
+	}
 
 	return rc;
 }
-- 
cgit v1.2.3


From 8f34e53b60b337e559f1ea19e2780ff95ab2fa65 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@kernel.org>
Date: Fri, 1 May 2020 08:53:08 -0600
Subject: ipv6: Use global sernum for dst validation with nexthop objects

Nik reported a bug with pcpu dst cache when nexthop objects are
used illustrated by the following:
    $ ip netns add foo
    $ ip -netns foo li set lo up
    $ ip -netns foo addr add 2001:db8:11::1/128 dev lo
    $ ip netns exec foo sysctl net.ipv6.conf.all.forwarding=1
    $ ip li add veth1 type veth peer name veth2
    $ ip li set veth1 up
    $ ip addr add 2001:db8:10::1/64 dev veth1
    $ ip li set dev veth2 netns foo
    $ ip -netns foo li set veth2 up
    $ ip -netns foo addr add 2001:db8:10::2/64 dev veth2
    $ ip -6 nexthop add id 100 via 2001:db8:10::2 dev veth1
    $ ip -6 route add 2001:db8:11::1/128 nhid 100

    Create a pcpu entry on cpu 0:
    $ taskset -a -c 0 ip -6 route get 2001:db8:11::1

    Re-add the route entry:
    $ ip -6 ro del 2001:db8:11::1
    $ ip -6 route add 2001:db8:11::1/128 nhid 100

    Route get on cpu 0 returns the stale pcpu:
    $ taskset -a -c 0 ip -6 route get 2001:db8:11::1
    RTNETLINK answers: Network is unreachable

    While cpu 1 works:
    $ taskset -a -c 1 ip -6 route get 2001:db8:11::1
    2001:db8:11::1 from :: via 2001:db8:10::2 dev veth1 src 2001:db8:10::1 metric 1024 pref medium

Conversion of FIB entries to work with external nexthop objects
missed an important difference between IPv4 and IPv6 - how dst
entries are invalidated when the FIB changes. IPv4 has a per-network
namespace generation id (rt_genid) that is bumped on changes to the FIB.
Checking if a dst_entry is still valid means comparing rt_genid in the
rtable to the current value of rt_genid for the namespace.

IPv6 also has a per network namespace counter, fib6_sernum, but the
count is saved per fib6_node. With the per-node counter only dst_entries
based on fib entries under the node are invalidated when changes are
made to the routes - limiting the scope of invalidations. IPv6 uses a
reference in the rt6_info, 'from', to track the corresponding fib entry
used to create the dst_entry. When validating a dst_entry, the 'from'
is used to backtrack to the fib6_node and check the sernum of it to the
cookie passed to the dst_check operation.

With the inline format (nexthop definition inline with the fib6_info),
dst_entries cached in the fib6_nh have a 1:1 correlation between fib
entries, nexthop data and dst_entries. With external nexthops, IPv6
looks more like IPv4 which means multiple fib entries across disparate
fib6_nodes can all reference the same fib6_nh. That means validation
of dst_entries based on external nexthops needs to use the IPv4 format
- the per-network namespace counter.

Add sernum to rt6_info and set it when creating a pcpu dst entry. Update
rt6_get_cookie to return sernum if it is set and update dst_check for
IPv6 to look for sernum set and based the check on it if so. Finally,
rt6_get_pcpu_route needs to validate the cached entry before returning
a pcpu entry (similar to the rt_cache_valid calls in __mkroute_input and
__mkroute_output for IPv4).

This problem only affects routes using the new, external nexthops.

Thanks to the kbuild test robot for catching the IS_ENABLED needed
around rt_genid_ipv6 before I sent this out.

Fixes: 5b98324ebe29 ("ipv6: Allow routes to use nexthop objects")
Reported-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Tested-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h       |  4 ++++
 include/net/net_namespace.h |  7 +++++++
 net/ipv6/route.c            | 25 +++++++++++++++++++++++++
 3 files changed, 36 insertions(+)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 80262d2980f5..1d98828c6649 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -203,6 +203,7 @@ struct fib6_info {
 struct rt6_info {
 	struct dst_entry		dst;
 	struct fib6_info __rcu		*from;
+	int				sernum;
 
 	struct rt6key			rt6i_dst;
 	struct rt6key			rt6i_src;
@@ -291,6 +292,9 @@ static inline u32 rt6_get_cookie(const struct rt6_info *rt)
 	struct fib6_info *from;
 	u32 cookie = 0;
 
+	if (rt->sernum)
+		return rt->sernum;
+
 	rcu_read_lock();
 
 	from = rcu_dereference(rt->from);
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index ab96fb59131c..8e001e049497 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -437,6 +437,13 @@ static inline int rt_genid_ipv4(const struct net *net)
 	return atomic_read(&net->ipv4.rt_genid);
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
+static inline int rt_genid_ipv6(const struct net *net)
+{
+	return atomic_read(&net->ipv6.fib6_sernum);
+}
+#endif
+
 static inline void rt_genid_bump_ipv4(struct net *net)
 {
 	atomic_inc(&net->ipv4.rt_genid);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 310cbddaa533..8d418038fe32 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1385,9 +1385,18 @@ static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res)
 	}
 	ip6_rt_copy_init(pcpu_rt, res);
 	pcpu_rt->rt6i_flags |= RTF_PCPU;
+
+	if (f6i->nh)
+		pcpu_rt->sernum = rt_genid_ipv6(dev_net(dev));
+
 	return pcpu_rt;
 }
 
+static bool rt6_is_valid(const struct rt6_info *rt6)
+{
+	return rt6->sernum == rt_genid_ipv6(dev_net(rt6->dst.dev));
+}
+
 /* It should be called with rcu_read_lock() acquired */
 static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
 {
@@ -1395,6 +1404,19 @@ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
 
 	pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu);
 
+	if (pcpu_rt && pcpu_rt->sernum && !rt6_is_valid(pcpu_rt)) {
+		struct rt6_info *prev, **p;
+
+		p = this_cpu_ptr(res->nh->rt6i_pcpu);
+		prev = xchg(p, NULL);
+		if (prev) {
+			dst_dev_put(&prev->dst);
+			dst_release(&prev->dst);
+		}
+
+		pcpu_rt = NULL;
+	}
+
 	return pcpu_rt;
 }
 
@@ -2593,6 +2615,9 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 
 	rt = container_of(dst, struct rt6_info, dst);
 
+	if (rt->sernum)
+		return rt6_is_valid(rt) ? dst : NULL;
+
 	rcu_read_lock();
 
 	/* All IPV6 dsts are created with ->obsolete set to the value
-- 
cgit v1.2.3


From a7df4870d79b00742da6cc93ca2f336a71db77f7 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 30 Apr 2020 20:53:49 -0700
Subject: net_sched: fix tcm_parent in tc filter dump

When we tell kernel to dump filters from root (ffff:ffff),
those filters on ingress (ffff:0000) are matched, but their
true parents must be dumped as they are. However, kernel
dumps just whatever we tell it, that is either ffff:ffff
or ffff:0000:

 $ nl-cls-list --dev=dummy0 --parent=root
 cls basic dev dummy0 id none parent root prio 49152 protocol ip match-all
 cls basic dev dummy0 id :1 parent root prio 49152 protocol ip match-all
 $ nl-cls-list --dev=dummy0 --parent=ffff:
 cls basic dev dummy0 id none parent ffff: prio 49152 protocol ip match-all
 cls basic dev dummy0 id :1 parent ffff: prio 49152 protocol ip match-all

This is confusing and misleading, more importantly this is
a regression since 4.15, so the old behavior must be restored.

And, when tc filters are installed on a tc class, the parent
should be the classid, rather than the qdisc handle. Commit
edf6711c9840 ("net: sched: remove classid and q fields from tcf_proto")
removed the classid we save for filters, we can just restore
this classid in tcf_block.

Steps to reproduce this:
 ip li set dev dummy0 up
 tc qd add dev dummy0 ingress
 tc filter add dev dummy0 parent ffff: protocol arp basic action pass
 tc filter show dev dummy0 root

Before this patch:
 filter protocol arp pref 49152 basic
 filter protocol arp pref 49152 basic handle 0x1
	action order 1: gact action pass
	 random type none pass val 0
	 index 1 ref 1 bind 1

After this patch:
 filter parent ffff: protocol arp pref 49152 basic
 filter parent ffff: protocol arp pref 49152 basic handle 0x1
 	action order 1: gact action pass
 	 random type none pass val 0
	 index 1 ref 1 bind 1

Fixes: a10fa20101ae ("net: sched: propagate q and parent from caller down to tcf_fill_node")
Fixes: edf6711c9840 ("net: sched: remove classid and q fields from tcf_proto")
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 1 +
 net/sched/cls_api.c       | 8 ++++----
 2 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 25d2ec4c8f00..8428aa614265 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -407,6 +407,7 @@ struct tcf_block {
 	struct mutex lock;
 	struct list_head chain_list;
 	u32 index; /* block index for shared blocks */
+	u32 classid; /* which class this block belongs to */
 	refcount_t refcnt;
 	struct net *net;
 	struct Qdisc *q;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 55bd1429678f..c0e5b64b3caf 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2070,6 +2070,7 @@ replay:
 		err = PTR_ERR(block);
 		goto errout;
 	}
+	block->classid = parent;
 
 	chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
 	if (chain_index > TC_ACT_EXT_VAL_MASK) {
@@ -2612,12 +2613,10 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 			return skb->len;
 
 		parent = tcm->tcm_parent;
-		if (!parent) {
+		if (!parent)
 			q = dev->qdisc;
-			parent = q->handle;
-		} else {
+		else
 			q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
-		}
 		if (!q)
 			goto out;
 		cops = q->ops->cl_ops;
@@ -2633,6 +2632,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 		block = cops->tcf_block(q, cl, NULL);
 		if (!block)
 			goto out;
+		parent = block->classid;
 		if (tcf_block_shared(block))
 			q = NULL;
 	}
-- 
cgit v1.2.3


From 21ce7f3e16fbf89faaf149cfe0f730edfc553914 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 4 May 2020 01:20:26 +0300
Subject: net: dsa: ocelot: the MAC table on Felix is twice as large

When running 'bridge fdb dump' on Felix, sometimes learnt and static MAC
addresses would appear, sometimes they wouldn't.

Turns out, the MAC table has 4096 entries on VSC7514 (Ocelot) and 8192
entries on VSC9959 (Felix), so the existing code from the Ocelot common
library only dumped half of Felix's MAC table. They are both organized
as a 4-way set-associative TCAM, so we just need a single variable
indicating the correct number of rows.

Fixes: 56051948773e ("net: dsa: ocelot: add driver for Felix switch family")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix.c          | 1 +
 drivers/net/dsa/ocelot/felix.h          | 1 +
 drivers/net/dsa/ocelot/felix_vsc9959.c  | 1 +
 drivers/net/ethernet/mscc/ocelot.c      | 6 ++----
 drivers/net/ethernet/mscc/ocelot_regs.c | 1 +
 include/soc/mscc/ocelot.h               | 1 +
 6 files changed, 7 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index d0a3764ff0cf..e2c6bf0e430e 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -400,6 +400,7 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 	ocelot->stats_layout	= felix->info->stats_layout;
 	ocelot->num_stats	= felix->info->num_stats;
 	ocelot->shared_queue_sz	= felix->info->shared_queue_sz;
+	ocelot->num_mact_rows	= felix->info->num_mact_rows;
 	ocelot->vcap_is2_keys	= felix->info->vcap_is2_keys;
 	ocelot->vcap_is2_actions= felix->info->vcap_is2_actions;
 	ocelot->vcap		= felix->info->vcap;
diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h
index 82d46f260041..9af106513e53 100644
--- a/drivers/net/dsa/ocelot/felix.h
+++ b/drivers/net/dsa/ocelot/felix.h
@@ -15,6 +15,7 @@ struct felix_info {
 	const u32 *const		*map;
 	const struct ocelot_ops		*ops;
 	int				shared_queue_sz;
+	int				num_mact_rows;
 	const struct ocelot_stat_layout	*stats_layout;
 	unsigned int			num_stats;
 	int				num_ports;
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index b4078f3c5c38..8bf395f12b47 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -1220,6 +1220,7 @@ struct felix_info felix_info_vsc9959 = {
 	.vcap_is2_actions	= vsc9959_vcap_is2_actions,
 	.vcap			= vsc9959_vcap_props,
 	.shared_queue_sz	= 128 * 1024,
+	.num_mact_rows		= 2048,
 	.num_ports		= 6,
 	.switch_pci_bar		= 4,
 	.imdio_pci_bar		= 0,
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index a8c48a4a708f..887b3cc88354 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1031,10 +1031,8 @@ int ocelot_fdb_dump(struct ocelot *ocelot, int port,
 {
 	int i, j;
 
-	/* Loop through all the mac tables entries. There are 1024 rows of 4
-	 * entries.
-	 */
-	for (i = 0; i < 1024; i++) {
+	/* Loop through all the mac tables entries. */
+	for (i = 0; i < ocelot->num_mact_rows; i++) {
 		for (j = 0; j < 4; j++) {
 			struct ocelot_mact_entry entry;
 			bool is_static;
diff --git a/drivers/net/ethernet/mscc/ocelot_regs.c b/drivers/net/ethernet/mscc/ocelot_regs.c
index b88b5899b227..7d4fd1b6adda 100644
--- a/drivers/net/ethernet/mscc/ocelot_regs.c
+++ b/drivers/net/ethernet/mscc/ocelot_regs.c
@@ -431,6 +431,7 @@ int ocelot_chip_init(struct ocelot *ocelot, const struct ocelot_ops *ops)
 	ocelot->stats_layout = ocelot_stats_layout;
 	ocelot->num_stats = ARRAY_SIZE(ocelot_stats_layout);
 	ocelot->shared_queue_sz = 224 * 1024;
+	ocelot->num_mact_rows = 1024;
 	ocelot->ops = ops;
 
 	ret = ocelot_regfields_init(ocelot, ocelot_regfields);
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 6d6a3947c8b7..efc8b613d486 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -502,6 +502,7 @@ struct ocelot {
 	unsigned int			num_stats;
 
 	int				shared_queue_sz;
+	int				num_mact_rows;
 
 	struct net_device		*hw_bridge_dev;
 	u16				bridge_mask;
-- 
cgit v1.2.3


From 9274124f023b5c56dc4326637d4f787968b03607 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 4 May 2020 12:48:54 -0400
Subject: net: stricter validation of untrusted gso packets

Syzkaller again found a path to a kernel crash through bad gso input:
a packet with transport header extending beyond skb_headlen(skb).

Tighten validation at kernel entry:

- Verify that the transport header lies within the linear section.

    To avoid pulling linux/tcp.h, verify just sizeof tcphdr.
    tcp_gso_segment will call pskb_may_pull (th->doff * 4) before use.

- Match the gso_type against the ip_proto found by the flow dissector.

Fixes: bfd5f4a3d605 ("packet: Add GSO/csum offload support.")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/virtio_net.h | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 0d1fe9297ac6..6f6ade63b04c 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -3,6 +3,8 @@
 #define _LINUX_VIRTIO_NET_H
 
 #include <linux/if_vlan.h>
+#include <uapi/linux/tcp.h>
+#include <uapi/linux/udp.h>
 #include <uapi/linux/virtio_net.h>
 
 static inline int virtio_net_hdr_set_proto(struct sk_buff *skb,
@@ -28,17 +30,25 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 					bool little_endian)
 {
 	unsigned int gso_type = 0;
+	unsigned int thlen = 0;
+	unsigned int ip_proto;
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
 		case VIRTIO_NET_HDR_GSO_TCPV4:
 			gso_type = SKB_GSO_TCPV4;
+			ip_proto = IPPROTO_TCP;
+			thlen = sizeof(struct tcphdr);
 			break;
 		case VIRTIO_NET_HDR_GSO_TCPV6:
 			gso_type = SKB_GSO_TCPV6;
+			ip_proto = IPPROTO_TCP;
+			thlen = sizeof(struct tcphdr);
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
 			gso_type = SKB_GSO_UDP;
+			ip_proto = IPPROTO_UDP;
+			thlen = sizeof(struct udphdr);
 			break;
 		default:
 			return -EINVAL;
@@ -57,16 +67,22 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 
 		if (!skb_partial_csum_set(skb, start, off))
 			return -EINVAL;
+
+		if (skb_transport_offset(skb) + thlen > skb_headlen(skb))
+			return -EINVAL;
 	} else {
 		/* gso packets without NEEDS_CSUM do not set transport_offset.
 		 * probe and drop if does not match one of the above types.
 		 */
 		if (gso_type && skb->network_header) {
+			struct flow_keys_basic keys;
+
 			if (!skb->protocol)
 				virtio_net_hdr_set_proto(skb, hdr);
 retry:
-			skb_probe_transport_header(skb);
-			if (!skb_transport_header_was_set(skb)) {
+			if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys,
+							      NULL, 0, 0, 0,
+							      0)) {
 				/* UFO does not specify ipv4 or 6: try both */
 				if (gso_type & SKB_GSO_UDP &&
 				    skb->protocol == htons(ETH_P_IP)) {
@@ -75,6 +91,12 @@ retry:
 				}
 				return -EINVAL;
 			}
+
+			if (keys.control.thoff + thlen > skb_headlen(skb) ||
+			    keys.basic.ip_proto != ip_proto)
+				return -EINVAL;
+
+			skb_set_transport_header(skb, keys.control.thoff);
 		}
 	}
 
-- 
cgit v1.2.3


From 16f8036086a929694c3c62f577bb5925fe4fd607 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 6 May 2020 20:34:50 +0200
Subject: net: flow_offload: skip hw stats check for
 FLOW_ACTION_HW_STATS_DONT_CARE

This patch adds FLOW_ACTION_HW_STATS_DONT_CARE which tells the driver
that the frontend does not need counters, this hw stats type request
never fails. The FLOW_ACTION_HW_STATS_DISABLED type explicitly requests
the driver to disable the stats, however, if the driver cannot disable
counters, it bails out.

TCA_ACT_HW_STATS_* maintains the 1:1 mapping with FLOW_ACTION_HW_STATS_*
except by disabled which is mapped to FLOW_ACTION_HW_STATS_DISABLED
(this is 0 in tc). Add tc_act_hw_stats() to perform the mapping between
TCA_ACT_HW_STATS_* and FLOW_ACTION_HW_STATS_*.

Fixes: 319a1d19471e ("flow_offload: check for basic action hw stats type")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c |  3 ++-
 include/net/flow_offload.h                            |  9 ++++++++-
 net/sched/cls_api.c                                   | 14 ++++++++++++--
 3 files changed, 22 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 51117a5a6bbf..890b078851c9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -36,7 +36,8 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 		err = mlxsw_sp_acl_rulei_act_count(mlxsw_sp, rulei, extack);
 		if (err)
 			return err;
-	} else if (act->hw_stats != FLOW_ACTION_HW_STATS_DISABLED) {
+	} else if (act->hw_stats != FLOW_ACTION_HW_STATS_DISABLED &&
+		   act->hw_stats != FLOW_ACTION_HW_STATS_DONT_CARE) {
 		NL_SET_ERR_MSG_MOD(extack, "Unsupported action HW stats type");
 		return -EOPNOTSUPP;
 	}
diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index 3619c6acf60f..efc8350b42fb 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -166,15 +166,18 @@ enum flow_action_mangle_base {
 enum flow_action_hw_stats_bit {
 	FLOW_ACTION_HW_STATS_IMMEDIATE_BIT,
 	FLOW_ACTION_HW_STATS_DELAYED_BIT,
+	FLOW_ACTION_HW_STATS_DISABLED_BIT,
 };
 
 enum flow_action_hw_stats {
-	FLOW_ACTION_HW_STATS_DISABLED = 0,
+	FLOW_ACTION_HW_STATS_DONT_CARE = 0,
 	FLOW_ACTION_HW_STATS_IMMEDIATE =
 		BIT(FLOW_ACTION_HW_STATS_IMMEDIATE_BIT),
 	FLOW_ACTION_HW_STATS_DELAYED = BIT(FLOW_ACTION_HW_STATS_DELAYED_BIT),
 	FLOW_ACTION_HW_STATS_ANY = FLOW_ACTION_HW_STATS_IMMEDIATE |
 				   FLOW_ACTION_HW_STATS_DELAYED,
+	FLOW_ACTION_HW_STATS_DISABLED =
+		BIT(FLOW_ACTION_HW_STATS_DISABLED_BIT),
 };
 
 typedef void (*action_destr)(void *priv);
@@ -325,7 +328,11 @@ __flow_action_hw_stats_check(const struct flow_action *action,
 		return true;
 	if (!flow_action_mixed_hw_stats_check(action, extack))
 		return false;
+
 	action_entry = flow_action_first_entry_get(action);
+	if (action_entry->hw_stats == FLOW_ACTION_HW_STATS_DONT_CARE)
+		return true;
+
 	if (!check_allow_bit &&
 	    action_entry->hw_stats != FLOW_ACTION_HW_STATS_ANY) {
 		NL_SET_ERR_MSG_MOD(extack, "Driver supports only default HW stats type \"any\"");
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index c0e5b64b3caf..0a7ecc292bd3 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3523,6 +3523,16 @@ static void tcf_sample_get_group(struct flow_action_entry *entry,
 #endif
 }
 
+static enum flow_action_hw_stats tc_act_hw_stats(u8 hw_stats)
+{
+	if (WARN_ON_ONCE(hw_stats > TCA_ACT_HW_STATS_ANY))
+		return FLOW_ACTION_HW_STATS_DONT_CARE;
+	else if (!hw_stats)
+		return FLOW_ACTION_HW_STATS_DISABLED;
+
+	return hw_stats;
+}
+
 int tc_setup_flow_action(struct flow_action *flow_action,
 			 const struct tcf_exts *exts)
 {
@@ -3546,7 +3556,7 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 		if (err)
 			goto err_out_locked;
 
-		entry->hw_stats = act->hw_stats;
+		entry->hw_stats = tc_act_hw_stats(act->hw_stats);
 
 		if (is_tcf_gact_ok(act)) {
 			entry->id = FLOW_ACTION_ACCEPT;
@@ -3614,7 +3624,7 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 				entry->mangle.mask = tcf_pedit_mask(act, k);
 				entry->mangle.val = tcf_pedit_val(act, k);
 				entry->mangle.offset = tcf_pedit_offset(act, k);
-				entry->hw_stats = act->hw_stats;
+				entry->hw_stats = tc_act_hw_stats(act->hw_stats);
 				entry = &flow_action->entries[++j];
 			}
 		} else if (is_tcf_csum(act)) {
-- 
cgit v1.2.3