[MPTCP][PATCH v5 mptcp-next 0/5] add MP_CAPABLE 'C' flag

[MPTCP][PATCH v5 mptcp-next 0/5] add MP_CAPABLE 'C' flag

[Geliang Tang]

v5:
 - add a new patch "mptcp: add add_list in mptcp_pm_data"
 - fix !CONFIG_SYSCTL case
 - tag: export/20210507T174457

v4:
 - rename mptcp_is_allow_join_id0 to mptcp_allow_join_id0
 - rename deny_join_id0 in mptcp_pm_data to remote_deny_join_id0
 - add comments for self test cases
 - apply: export/20210504T064955 +
          "data checksum support" +
          "data checksum support cleanups"

v3:
 - use 'u8 allow_join_initial_addr_port'
 - drop the spinlock in patch 3

v2:
 - rename join_denied to allow_join_id0 in mptcp_out_options
 - rename join_denied to deny_join_id0 in mptcp_options_received
 - add a new function mptcp_pm_deny_join_id0_received
 - move deny_join_id0 flag from mptcp_sock to mptcp_pm_data
 - check deny_join_id0 flag in mptcp_pm_create_subflow_or_signal_addr
instead of in mptcp_syn_options.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/183

Geliang Tang (5):
  mptcp: add sysctl allow_join_initial_addr_port
  mptcp: add allow_join_id0 in mptcp_out_options
  mptcp: add add_list in mptcp_pm_data
  mptcp: add deny_join_id0 in mptcp_options_received
  selftests: mptcp: add deny_join_id0 testcases

 Documentation/networking/mptcp-sysctl.rst     | 13 +++
 include/net/mptcp.h                           |  3 +-
 net/mptcp/ctrl.c                              | 16 ++++
 net/mptcp/options.c                           | 12 +++
 net/mptcp/pm.c                                |  2 +
 net/mptcp/pm_netlink.c                        | 86 ++++++++++++++++++-
 net/mptcp/protocol.c                          |  1 +
 net/mptcp/protocol.h                          | 13 ++-
 net/mptcp/subflow.c                           |  3 +
 .../testing/selftests/net/mptcp/mptcp_join.sh | 56 +++++++++++-
 10 files changed, 199 insertions(+), 6 deletions(-)

-- 
2.31.1

[MPTCP][PATCH v5 mptcp-next 1/5] mptcp: add sysctl allow_join_initial_addr_port

[Geliang Tang]

This patch added a new sysctl, named allow_join_initial_addr_port, to
control whether allow peers to send join requests to the IP address and
port number used by the initial subflow.

Suggested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Geliang Tang <geliangtang@gmail.com>
---
 Documentation/networking/mptcp-sysctl.rst | 13 +++++++++++++
 net/mptcp/ctrl.c                          | 16 ++++++++++++++++
 net/mptcp/protocol.h                      |  1 +
 3 files changed, 30 insertions(+)

diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index ee06fd782465..76d939e688b8 100644
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -32,3 +32,16 @@ checksum_enabled - BOOLEAN
 	per-namespace sysctl.
 
 	Default: 0
+
+allow_join_initial_addr_port - BOOLEAN
+	Allow peers to send join requests to the IP address and port number used
+	by the initial subflow if the value is 1. This controls a flag that is
+	sent to the peer at connection time, and whether such join requests are
+	accepted or denied.
+
+	Joins to addresses advertised with ADD_ADDR are not affected by this
+	value.
+
+	This is a per-namespace sysctl.
+
+	Default: 1
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index 6c2639bb9c19..7d738bd06f2c 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -24,6 +24,7 @@ struct mptcp_pernet {
 	u8 mptcp_enabled;
 	unsigned int add_addr_timeout;
 	u8 checksum_enabled;
+	u8 allow_join_initial_addr_port;
 };
 
 static struct mptcp_pernet *mptcp_get_pernet(struct net *net)
@@ -46,11 +47,17 @@ int mptcp_is_checksum_enabled(struct net *net)
 	return mptcp_get_pernet(net)->checksum_enabled;
 }
 
+int mptcp_allow_join_id0(struct net *net)
+{
+	return mptcp_get_pernet(net)->allow_join_initial_addr_port;
+}
+
 static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
 {
 	pernet->mptcp_enabled = 1;
 	pernet->add_addr_timeout = TCP_RTO_MAX;
 	pernet->checksum_enabled = 0;
+	pernet->allow_join_initial_addr_port = 1;
 }
 
 #ifdef CONFIG_SYSCTL
@@ -80,6 +87,14 @@ static struct ctl_table mptcp_sysctl_table[] = {
 		.extra1       = SYSCTL_ZERO,
 		.extra2       = SYSCTL_ONE
 	},
+	{
+		.procname = "allow_join_initial_addr_port",
+		.maxlen = sizeof(u8),
+		.mode = 0644,
+		.proc_handler = proc_dou8vec_minmax,
+		.extra1       = SYSCTL_ZERO,
+		.extra2       = SYSCTL_ONE
+	},
 	{}
 };
 
@@ -98,6 +113,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
 	table[0].data = &pernet->mptcp_enabled;
 	table[1].data = &pernet->add_addr_timeout;
 	table[2].data = &pernet->checksum_enabled;
+	table[3].data = &pernet->allow_join_initial_addr_port;
 
 	hdr = register_net_sysctl(net, MPTCP_SYSCTL_PATH, table);
 	if (!hdr)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 868e878af526..3d6bbdf00bfb 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -543,6 +543,7 @@ static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *su
 int mptcp_is_enabled(struct net *net);
 unsigned int mptcp_get_add_addr_timeout(struct net *net);
 int mptcp_is_checksum_enabled(struct net *net);
+int mptcp_allow_join_id0(struct net *net);
 void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
 				     struct mptcp_options_received *mp_opt);
 bool mptcp_subflow_data_available(struct sock *sk);
-- 
2.31.1

[MPTCP][PATCH v5 mptcp-next 2/5] mptcp: add allow_join_id0 in mptcp_out_options

[Geliang Tang]

This patch defined a new flag MPTCP_CAP_DENY_JOIN_ID0 for the third bit,
labeled "C" of the MP_CAPABLE option.

Add a new flag allow_join_id0 in struct mptcp_out_options. If this flag is
set, send out the MP_CAPABLE option with the flag MPTCP_CAP_DENY_JOIN_ID0.

Signed-off-by: Geliang Tang <geliangtang@gmail.com>
---
 include/net/mptcp.h  | 3 ++-
 net/mptcp/options.c  | 6 ++++++
 net/mptcp/protocol.h | 6 ++++--
 net/mptcp/subflow.c  | 1 +
 4 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index d61bbbf11979..cb580b06152f 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -67,7 +67,8 @@ struct mptcp_out_options {
 	u8 backup;
 	u8 reset_reason:4,
 	   reset_transient:1,
-	   csum_reqd:1;
+	   csum_reqd:1,
+	   allow_join_id0:1;
 	u32 nonce;
 	u64 thmac;
 	u32 token;
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 3428c163299b..441ec25e117d 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -403,6 +403,7 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
 	if (subflow->request_mptcp) {
 		opts->suboptions = OPTION_MPTCP_MPC_SYN;
 		opts->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk));
+		opts->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk));
 		*size = TCPOLEN_MPTCP_MPC_SYN;
 		return true;
 	} else if (subflow->request_join) {
@@ -491,6 +492,7 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
 		opts->sndr_key = subflow->local_key;
 		opts->rcvr_key = subflow->remote_key;
 		opts->csum_reqd = READ_ONCE(msk->csum_enabled);
+		opts->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk));
 
 		/* Section 3.1.
 		 * The MP_CAPABLE option is carried on the SYN, SYN/ACK, and ACK
@@ -833,6 +835,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
 		opts->suboptions = OPTION_MPTCP_MPC_SYNACK;
 		opts->sndr_key = subflow_req->local_key;
 		opts->csum_reqd = subflow_req->csum_reqd;
+		opts->allow_join_id0 = subflow_req->allow_join_id0;
 		*size = TCPOLEN_MPTCP_MPC_SYNACK;
 		pr_debug("subflow_req=%p, local_key=%llu",
 			 subflow_req, subflow_req->local_key);
@@ -1207,6 +1210,9 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 		if (opts->csum_reqd)
 			flag |= MPTCP_CAP_CHECKSUM_REQD;
 
+		if (!opts->allow_join_id0)
+			flag |= MPTCP_CAP_DENY_JOIN_ID0;
+
 		*ptr++ = mptcp_option(MPTCPOPT_MP_CAPABLE, len,
 				      MPTCP_SUPPORTED_VERSION,
 				      flag);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 3d6bbdf00bfb..fd7ff2d28cb3 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -79,8 +79,9 @@
 #define MPTCP_VERSION_MASK	(0x0F)
 #define MPTCP_CAP_CHECKSUM_REQD	BIT(7)
 #define MPTCP_CAP_EXTENSIBILITY	BIT(6)
+#define MPTCP_CAP_DENY_JOIN_ID0	BIT(5)
 #define MPTCP_CAP_HMAC_SHA256	BIT(0)
-#define MPTCP_CAP_FLAG_MASK	(0x3F)
+#define MPTCP_CAP_FLAG_MASK	(0x1F)
 
 /* MPTCP DSS flags */
 #define MPTCP_DSS_DATA_FIN	BIT(4)
@@ -352,7 +353,8 @@ struct mptcp_subflow_request_sock {
 	u16	mp_capable : 1,
 		mp_join : 1,
 		backup : 1,
-		csum_reqd : 1;
+		csum_reqd : 1,
+		allow_join_id0 : 1;
 	u8	local_id;
 	u8	remote_id;
 	u64	local_key;
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index c8968038174f..249a66ad54dc 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -109,6 +109,7 @@ 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);
 }
-- 
2.31.1

[MPTCP][PATCH v5 mptcp-next 3/5] mptcp: add add_list in mptcp_pm_data

[Geliang Tang]

Like the anno_list member in struct mptcp_pm_data, this patch added a
new member named add_list in it, to save all the received ADD_ADDRs in
this add_list.

Signed-off-by: Geliang Tang <geliangtang@gmail.com>
---
 net/mptcp/pm.c         |  1 +
 net/mptcp/pm_netlink.c | 74 ++++++++++++++++++++++++++++++++++++++++++
 net/mptcp/protocol.c   |  1 +
 net/mptcp/protocol.h   |  2 ++
 4 files changed, 78 insertions(+)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 9d00fa6d22e9..9456fe17b6a3 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -324,6 +324,7 @@ void mptcp_pm_data_init(struct mptcp_sock *msk)
 
 	spin_lock_init(&msk->pm.lock);
 	INIT_LIST_HEAD(&msk->pm.anno_list);
+	INIT_LIST_HEAD(&msk->pm.add_list);
 
 	mptcp_pm_nl_data_init(msk);
 }
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index d094588afad8..47a515af2b0a 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -483,6 +483,72 @@ static void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk)
 	mptcp_pm_create_subflow_or_signal_addr(msk);
 }
 
+struct mptcp_pm_add_entry *
+mptcp_lookup_add_list_by_id(struct mptcp_sock *msk, u8 id)
+{
+	struct mptcp_pm_add_entry *entry;
+
+	lockdep_assert_held(&msk->pm.lock);
+
+	list_for_each_entry(entry, &msk->pm.add_list, list) {
+		if (entry->addr.id == id)
+			return entry;
+	}
+
+	return NULL;
+}
+
+struct mptcp_pm_add_entry *
+mptcp_lookup_add_list_by_saddr(struct mptcp_sock *msk,
+			       struct mptcp_addr_info *addr)
+{
+	struct mptcp_pm_add_entry *entry;
+
+	lockdep_assert_held(&msk->pm.lock);
+
+	list_for_each_entry(entry, &msk->pm.add_list, list) {
+		if (addresses_equal(&entry->addr, addr, true))
+			return entry;
+	}
+
+	return NULL;
+}
+
+static bool mptcp_pm_alloc_add_list(struct mptcp_sock *msk,
+				    struct mptcp_addr_info *addr)
+{
+	struct mptcp_pm_add_entry *add_entry = NULL;
+
+	lockdep_assert_held(&msk->pm.lock);
+
+	if (mptcp_lookup_add_list_by_saddr(msk, addr))
+		return false;
+
+	add_entry = kmalloc(sizeof(*add_entry), GFP_ATOMIC);
+	if (!add_entry)
+		return false;
+
+	list_add(&add_entry->list, &msk->pm.add_list);
+	add_entry->addr = *addr;
+
+	return true;
+}
+
+void mptcp_pm_free_add_list(struct mptcp_sock *msk)
+{
+	struct mptcp_pm_add_entry *entry, *tmp;
+	LIST_HEAD(free_list);
+
+	pr_debug("msk=%p", msk);
+
+	spin_lock_bh(&msk->pm.lock);
+	list_splice_init(&msk->pm.add_list, &free_list);
+	spin_unlock_bh(&msk->pm.lock);
+
+	list_for_each_entry_safe(entry, tmp, &free_list, list)
+		kfree(entry);
+}
+
 static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 {
 	struct sock *sk = (struct sock *)msk;
@@ -513,6 +579,8 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 	remote = msk->pm.remote;
 	if (!remote.port)
 		remote.port = sk->sk_dport;
+	if (!mptcp_pm_alloc_add_list(msk, &remote))
+		return;
 	memset(&local, 0, sizeof(local));
 	local.family = remote.family;
 
@@ -612,6 +680,7 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 		list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
 			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 			int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
+			struct mptcp_pm_add_entry *entry;
 			u8 id = subflow->local_id;
 
 			if (rm_type == MPTCP_MIB_RMADDR)
@@ -631,6 +700,11 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 			if (rm_type == MPTCP_MIB_RMADDR) {
 				msk->pm.add_addr_accepted--;
 				WRITE_ONCE(msk->pm.accept_addr, true);
+				entry = mptcp_lookup_add_list_by_id(msk, id);
+				if (entry) {
+					list_del(&entry->list);
+					kfree(entry);
+				}
 			} else if (rm_type == MPTCP_MIB_RMSUBFLOW) {
 				msk->pm.local_addr_used--;
 			}
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 652e55a0c6e8..446076388637 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2882,6 +2882,7 @@ void mptcp_destroy_common(struct mptcp_sock *msk)
 	skb_rbtree_purge(&msk->out_of_order_queue);
 	mptcp_token_destroy(msk);
 	mptcp_pm_free_anno_list(msk);
+	mptcp_pm_free_add_list(msk);
 }
 
 static void mptcp_destroy(struct sock *sk)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index fd7ff2d28cb3..d19deee01896 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -185,6 +185,7 @@ struct mptcp_pm_data {
 	struct mptcp_addr_info local;
 	struct mptcp_addr_info remote;
 	struct list_head anno_list;
+	struct list_head add_list;
 
 	spinlock_t	lock;		/*protects the whole PM data */
 
@@ -693,6 +694,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
 				 struct mptcp_addr_info *addr,
 				 u8 bkup);
 void mptcp_pm_free_anno_list(struct mptcp_sock *msk);
+void mptcp_pm_free_add_list(struct mptcp_sock *msk);
 bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk);
 struct mptcp_pm_add_entry *
 mptcp_pm_del_add_timer(struct mptcp_sock *msk,
-- 
2.31.1

[MPTCP][PATCH v5 mptcp-next 4/5] mptcp: add deny_join_id0 in mptcp_options_received

[Geliang Tang]

This patch added a new flag named deny_join_id0 in struct
mptcp_options_received. Set it when MP_CAPABLE with the flag
MPTCP_CAP_DENYJOIN_ID0 is received.

Also add a new flag remote_deny_join_id0 in struct mptcp_pm_data. When the
flag deny_join_id0 is set, set this remote_deny_join_id0 flag.

In mptcp_pm_create_subflow_or_signal_addr, if the remote_deny_join_id0 flag
is set, use the first received ADD_ADDR address as the remote address to
connect.

Suggested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Geliang Tang <geliangtang@gmail.com>
---
 net/mptcp/options.c    |  6 ++++++
 net/mptcp/pm.c         |  1 +
 net/mptcp/pm_netlink.c | 12 +++++++++++-
 net/mptcp/protocol.h   |  4 +++-
 net/mptcp/subflow.c    |  2 ++
 5 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 441ec25e117d..b9188c53e58f 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -87,6 +87,9 @@ static void mptcp_parse_option(const struct sock *sk,
 		if (flags & MPTCP_CAP_CHECKSUM_REQD)
 			mp_opt->csum_reqd = 1;
 
+		if (flags & MPTCP_CAP_DENY_JOIN_ID0)
+			mp_opt->deny_join_id0 = 1;
+
 		mp_opt->mp_capable = 1;
 		if (opsize >= TCPOLEN_MPTCP_MPC_SYNACK) {
 			mp_opt->sndr_key = get_unaligned_be64(ptr);
@@ -363,6 +366,7 @@ void mptcp_get_options(const struct sock *sk,
 	mp_opt->mp_prio = 0;
 	mp_opt->reset = 0;
 	mp_opt->csum_reqd = 0;
+	mp_opt->deny_join_id0 = 0;
 
 	length = (th->doff * 4) - sizeof(struct tcphdr);
 	ptr = (const unsigned char *)(th + 1);
@@ -1055,6 +1059,8 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 	}
 
 	mptcp_get_options(sk, skb, &mp_opt);
+	if (mp_opt.deny_join_id0)
+		WRITE_ONCE(msk->pm.remote_deny_join_id0, true);
 	if (!check_fully_established(msk, sk, subflow, skb, &mp_opt))
 		return;
 
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 9456fe17b6a3..23a309f641aa 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -320,6 +320,7 @@ void mptcp_pm_data_init(struct mptcp_sock *msk)
 	WRITE_ONCE(msk->pm.addr_signal, 0);
 	WRITE_ONCE(msk->pm.accept_addr, false);
 	WRITE_ONCE(msk->pm.accept_subflow, false);
+	WRITE_ONCE(msk->pm.remote_deny_join_id0, false);
 	msk->pm.status = 0;
 
 	spin_lock_init(&msk->pm.lock);
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 47a515af2b0a..dddd7c5613fa 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -456,10 +456,20 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 		if (local) {
 			struct mptcp_addr_info remote = { 0 };
 
+			remote_address((struct sock_common *)sk, &remote);
+			if (READ_ONCE(msk->pm.remote_deny_join_id0)) {
+				struct mptcp_pm_add_entry *entry;
+
+				entry = list_first_entry_or_null(&msk->pm.add_list,
+								 typeof(*entry), list);
+				if (!entry)
+					return;
+
+				remote = entry->addr;
+			}
 			msk->pm.local_addr_used++;
 			msk->pm.subflows++;
 			check_work_pending(msk);
-			remote_address((struct sock_common *)sk, &remote);
 			spin_unlock_bh(&msk->pm.lock);
 			__mptcp_subflow_connect(sk, &local->addr, &remote,
 						local->flags, local->ifindex);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index d19deee01896..5b2e72cf8e06 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -138,7 +138,8 @@ struct mptcp_options_received {
 		mp_prio : 1,
 		echo : 1,
 		csum_reqd : 1,
-		backup : 1;
+		backup : 1,
+		deny_join_id0 : 1;
 	u32	token;
 	u32	nonce;
 	u64	thmac;
@@ -194,6 +195,7 @@ struct mptcp_pm_data {
 	bool		work_pending;
 	bool		accept_addr;
 	bool		accept_subflow;
+	bool		remote_deny_join_id0;
 	u8		add_addr_signaled;
 	u8		add_addr_accepted;
 	u8		local_addr_used;
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 249a66ad54dc..bb4bf31e73cf 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -408,6 +408,8 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 
 		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;
-- 
2.31.1

[MPTCP][PATCH v5 mptcp-next 5/5] selftests: mptcp: add deny_join_id0 testcases

[Geliang Tang]

This patch added a new argument '-d' for mptcp_join.sh script, to invoke
the testcases for the MP_CAPABLE 'C' flag.

Signed-off-by: Geliang Tang <geliangtang@gmail.com>
---
 .../testing/selftests/net/mptcp/mptcp_join.sh | 56 ++++++++++++++++++-
 1 file changed, 55 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 523c7797f30a..17b385f011d2 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -139,6 +139,17 @@ reset_with_checksum()
 	ip netns exec $ns2 sysctl -q net.mptcp.checksum_enabled=$ns2_enable
 }
 
+reset_with_allow_join_id0()
+{
+	local ns1_enable=$1
+	local ns2_enable=$2
+
+	reset
+
+	ip netns exec $ns1 sysctl -q net.mptcp.allow_join_initial_addr_port=$ns1_enable
+	ip netns exec $ns2 sysctl -q net.mptcp.allow_join_initial_addr_port=$ns2_enable
+}
+
 ip -Version > /dev/null 2>&1
 if [ $? -ne 0 ];then
 	echo "SKIP: Could not run test without ip tool"
@@ -1462,6 +1473,44 @@ checksum_tests()
 	chk_csum_nr "checksum test 1 0"
 }
 
+deny_join_id0_tests()
+{
+	# subflow allow join id0 ns1
+	reset_with_allow_join_id0 1 0
+	ip netns exec $ns1 ./pm_nl_ctl limits 1 1
+	ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+	ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+	run_tests $ns1 $ns2 10.0.1.1
+	chk_join_nr "single subflow allow join id0 ns1" 1 1 1
+
+	# subflow allow join id0 ns2
+	reset_with_allow_join_id0 0 1
+	ip netns exec $ns1 ./pm_nl_ctl limits 1 1
+	ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+	ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+	run_tests $ns1 $ns2 10.0.1.1
+	chk_join_nr "single subflow allow join id0 ns2" 0 0 0
+
+	# subflow and address allow join id0
+	reset_with_allow_join_id0 0 1
+	ip netns exec $ns1 ./pm_nl_ctl limits 2 2
+	ip netns exec $ns2 ./pm_nl_ctl limits 2 2
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+	ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+	run_tests $ns1 $ns2 10.0.1.1
+	chk_join_nr "subflow and address allow join id0" 2 2 2
+
+	# signal address allow join id0
+	# ADD_ADDRs are not affected by allow_join_id0 value.
+	reset_with_allow_join_id0 0 0
+	ip netns exec $ns1 ./pm_nl_ctl limits 1 1
+	ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+	ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+	run_tests $ns1 $ns2 10.0.1.1
+	chk_join_nr "signal address allow join id0" 1 1 1
+	chk_add_nr 1 1
+}
+
 all_tests()
 {
 	subflows_tests
@@ -1476,6 +1525,7 @@ all_tests()
 	add_addr_ports_tests
 	syncookies_tests
 	checksum_tests
+	deny_join_id0_tests
 }
 
 usage()
@@ -1493,6 +1543,7 @@ usage()
 	echo "  -p add_addr_ports_tests"
 	echo "  -k syncookies_tests"
 	echo "  -S checksum_tests"
+	echo "  -d deny_join_id0_tests"
 	echo "  -c capture pcap files"
 	echo "  -C enable data checksum"
 	echo "  -h help"
@@ -1528,7 +1579,7 @@ if [ $do_all_tests -eq 1 ]; then
 	exit $ret
 fi
 
-while getopts 'fsltra64bpkchCS' opt; do
+while getopts 'fsltra64bpkdchCS' opt; do
 	case $opt in
 		f)
 			subflows_tests
@@ -1566,6 +1617,9 @@ while getopts 'fsltra64bpkchCS' opt; do
 		S)
 			checksum_tests
 			;;
+		d)
+			deny_join_id0_tests
+			;;
 		c)
 			;;
 		C)
-- 
2.31.1

Re: [MPTCP][PATCH v5 mptcp-next 3/5] mptcp: add add_list in mptcp_pm_data

[Mat Martineau]

On Sat, 8 May 2021, Geliang Tang wrote:

> Like the anno_list member in struct mptcp_pm_data, this patch added a
> new member named add_list in it, to save all the received ADD_ADDRs in
> this add_list.
>
> Signed-off-by: Geliang Tang <geliangtang@gmail.com>
> ---
> net/mptcp/pm.c         |  1 +
> net/mptcp/pm_netlink.c | 74 ++++++++++++++++++++++++++++++++++++++++++
> net/mptcp/protocol.c   |  1 +
> net/mptcp/protocol.h   |  2 ++
> 4 files changed, 78 insertions(+)
>
> diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
> index 9d00fa6d22e9..9456fe17b6a3 100644
> --- a/net/mptcp/pm.c
> +++ b/net/mptcp/pm.c
> @@ -324,6 +324,7 @@ void mptcp_pm_data_init(struct mptcp_sock *msk)
>
> 	spin_lock_init(&msk->pm.lock);
> 	INIT_LIST_HEAD(&msk->pm.anno_list);
> +	INIT_LIST_HEAD(&msk->pm.add_list);
>
> 	mptcp_pm_nl_data_init(msk);
> }
> diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
> index d094588afad8..47a515af2b0a 100644
> --- a/net/mptcp/pm_netlink.c
> +++ b/net/mptcp/pm_netlink.c
> @@ -483,6 +483,72 @@ static void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk)
> 	mptcp_pm_create_subflow_or_signal_addr(msk);
> }
>
> +struct mptcp_pm_add_entry *
> +mptcp_lookup_add_list_by_id(struct mptcp_sock *msk, u8 id)
> +{
> +	struct mptcp_pm_add_entry *entry;
> +
> +	lockdep_assert_held(&msk->pm.lock);
> +
> +	list_for_each_entry(entry, &msk->pm.add_list, list) {
> +		if (entry->addr.id == id)
> +			return entry;
> +	}
> +
> +	return NULL;
> +}
> +
> +struct mptcp_pm_add_entry *
> +mptcp_lookup_add_list_by_saddr(struct mptcp_sock *msk,
> +			       struct mptcp_addr_info *addr)
> +{
> +	struct mptcp_pm_add_entry *entry;
> +
> +	lockdep_assert_held(&msk->pm.lock);
> +
> +	list_for_each_entry(entry, &msk->pm.add_list, list) {
> +		if (addresses_equal(&entry->addr, addr, true))
> +			return entry;
> +	}
> +
> +	return NULL;
> +}
> +
> +static bool mptcp_pm_alloc_add_list(struct mptcp_sock *msk,
> +				    struct mptcp_addr_info *addr)
> +{
> +	struct mptcp_pm_add_entry *add_entry = NULL;
> +
> +	lockdep_assert_held(&msk->pm.lock);
> +
> +	if (mptcp_lookup_add_list_by_saddr(msk, addr))
> +		return false;
> +
> +	add_entry = kmalloc(sizeof(*add_entry), GFP_ATOMIC);

Hi Geliang -

Thanks for adding the list to track addresses announced by the peer. It 
will also be helpful for future in-kernel path manager functionality.

I think it's worthwhile to add a separate struct for this list instead of 
reusing struct mptcp_pm_add_entry. The timer_list is a large number of 
bytes to allocate and not use:

// from pahole

struct mptcp_pm_add_entry {
         struct list_head           list;                 /*     0    16 */
         struct mptcp_addr_info     addr;                 /*    16    24 */
         struct timer_list          add_timer;            /*    40    80 */
         /* --- cacheline 1 boundary (64 bytes) was 56 bytes ago --- */
         struct mptcp_sock *        sock;                 /*   120     8 */
         /* --- cacheline 2 boundary (128 bytes) --- */
         u8                         retrans_times;        /*   128     1 */

         /* size: 136, cachelines: 3, members: 5 */
         /* padding: 7 */
         /* last cacheline: 8 bytes */
};


-Mat


> +	if (!add_entry)
> +		return false;
> +
> +	list_add(&add_entry->list, &msk->pm.add_list);
> +	add_entry->addr = *addr;
> +
> +	return true;
> +}
> +
> +void mptcp_pm_free_add_list(struct mptcp_sock *msk)
> +{
> +	struct mptcp_pm_add_entry *entry, *tmp;
> +	LIST_HEAD(free_list);
> +
> +	pr_debug("msk=%p", msk);
> +
> +	spin_lock_bh(&msk->pm.lock);
> +	list_splice_init(&msk->pm.add_list, &free_list);
> +	spin_unlock_bh(&msk->pm.lock);
> +
> +	list_for_each_entry_safe(entry, tmp, &free_list, list)
> +		kfree(entry);
> +}
> +
> static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
> {
> 	struct sock *sk = (struct sock *)msk;
> @@ -513,6 +579,8 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
> 	remote = msk->pm.remote;
> 	if (!remote.port)
> 		remote.port = sk->sk_dport;
> +	if (!mptcp_pm_alloc_add_list(msk, &remote))
> +		return;
> 	memset(&local, 0, sizeof(local));
> 	local.family = remote.family;
>
> @@ -612,6 +680,7 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
> 		list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
> 			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
> 			int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
> +			struct mptcp_pm_add_entry *entry;
> 			u8 id = subflow->local_id;
>
> 			if (rm_type == MPTCP_MIB_RMADDR)
> @@ -631,6 +700,11 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
> 			if (rm_type == MPTCP_MIB_RMADDR) {
> 				msk->pm.add_addr_accepted--;
> 				WRITE_ONCE(msk->pm.accept_addr, true);
> +				entry = mptcp_lookup_add_list_by_id(msk, id);
> +				if (entry) {
> +					list_del(&entry->list);
> +					kfree(entry);
> +				}
> 			} else if (rm_type == MPTCP_MIB_RMSUBFLOW) {
> 				msk->pm.local_addr_used--;
> 			}
> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
> index 652e55a0c6e8..446076388637 100644
> --- a/net/mptcp/protocol.c
> +++ b/net/mptcp/protocol.c
> @@ -2882,6 +2882,7 @@ void mptcp_destroy_common(struct mptcp_sock *msk)
> 	skb_rbtree_purge(&msk->out_of_order_queue);
> 	mptcp_token_destroy(msk);
> 	mptcp_pm_free_anno_list(msk);
> +	mptcp_pm_free_add_list(msk);
> }
>
> static void mptcp_destroy(struct sock *sk)
> diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
> index fd7ff2d28cb3..d19deee01896 100644
> --- a/net/mptcp/protocol.h
> +++ b/net/mptcp/protocol.h
> @@ -185,6 +185,7 @@ struct mptcp_pm_data {
> 	struct mptcp_addr_info local;
> 	struct mptcp_addr_info remote;
> 	struct list_head anno_list;
> +	struct list_head add_list;
>
> 	spinlock_t	lock;		/*protects the whole PM data */
>
> @@ -693,6 +694,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
> 				 struct mptcp_addr_info *addr,
> 				 u8 bkup);
> void mptcp_pm_free_anno_list(struct mptcp_sock *msk);
> +void mptcp_pm_free_add_list(struct mptcp_sock *msk);
> bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk);
> struct mptcp_pm_add_entry *
> mptcp_pm_del_add_timer(struct mptcp_sock *msk,
> -- 
> 2.31.1
>
>
>

--
Mat Martineau
Intel