Skip to contentSkip to conversation

mptcp: improve subflow creation on errors

PATCH Superseded Paolo Abeni 2 participants 10 messages Nov 26, 2021 – Nov 29, 2021

Subsystems (3)

v2 of 6 Superseded Latest is v6 →

lore
Share & tools
lore

Paolo Abeni

author maintainer
#0 lore raw

v2 cover mptcp: improve subflow creation on errors

This iteration just addresses a compile warning spotted by the CI.

Currently when a subflow connection fails - either the TCP connection is reset by the peer, or the MPJ handshake never completes - the in kernel PM don't perform any further action. Notably no additional subflow creation is attempted.

This series is aimed at improving the in-kernel path manager behavior in the above scenario:
- each endpoint is used only once per connection (patch 2/4)
- on failure we try to move to the next subflow, if any (patch 3/4)

The first patch is minor cleanup, and the last patch adds specific self-tests.

This should address/close:
https://github.com/multipath-tcp/mptcp_net-next/issues/235
https://github.com/multipath-tcp/mptcp_net-next/issues/242

Paolo Abeni (4):
mptcp: clean-up MPJ option writing.
mptcp: keep track of used local endpoint
mptcp: do not block subflows creation on errors
selftests: mptcp: add tests for subflow creation failure

 net/mptcp/options.c                           | 65 ++++++++++++-------
 net/mptcp/pm.c                                | 28 +++++++-
 net/mptcp/pm_netlink.c                        |  8 ++-
 net/mptcp/protocol.c                          |  6 ++
 net/mptcp/protocol.h                          |  5 +-
 net/mptcp/subflow.c                           |  5 +-
 tools/testing/selftests/net/mptcp/config      |  1 +
 .../testing/selftests/net/mptcp/mptcp_join.sh | 65 ++++++++++++++++++-
 8 files changed, 153 insertions(+), 30 deletions(-)
Signature · 1 line
2.33.1
author maintainer
#1 lore raw

PATCH v2 1/4 mptcp: clean-up MPJ option writing.

Check for all MPJ variant at once, this reduces the number of conditionals traversed on average and will simplify the next patch.

No functional change intended.

---
 net/mptcp/options.c | 44 +++++++++++++++++++++++---------------------
 1 file changed, 23 insertions(+), 21 deletions(-)
net/mptcp/options.c +23 -21
index 8a1020e4285c..7a6a39b71633 100644
@@ -1381,27 +1381,29 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 
 		/* MPC is additionally mutually exclusive with MP_PRIO */
 		goto mp_capable_done;
-	} else if (OPTION_MPTCP_MPJ_SYN & opts->suboptions) {
-		*ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
-				      TCPOLEN_MPTCP_MPJ_SYN,
-				      opts->backup, opts->join_id);
-		put_unaligned_be32(opts->token, ptr);
-		ptr += 1;
-		put_unaligned_be32(opts->nonce, ptr);
-		ptr += 1;
-	} else if (OPTION_MPTCP_MPJ_SYNACK & opts->suboptions) {
-		*ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
-				      TCPOLEN_MPTCP_MPJ_SYNACK,
-				      opts->backup, opts->join_id);
-		put_unaligned_be64(opts->thmac, ptr);
-		ptr += 2;
-		put_unaligned_be32(opts->nonce, ptr);
-		ptr += 1;
-	} else if (OPTION_MPTCP_MPJ_ACK & opts->suboptions) {
-		*ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
-				      TCPOLEN_MPTCP_MPJ_ACK, 0, 0);
-		memcpy(ptr, opts->hmac, MPTCPOPT_HMAC_LEN);
-		ptr += 5;
+	} else if (OPTIONS_MPTCP_MPJ & opts->suboptions) {
+		if (OPTION_MPTCP_MPJ_SYN & opts->suboptions) {
+			*ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
+					      TCPOLEN_MPTCP_MPJ_SYN,
+					      opts->backup, opts->join_id);
+			put_unaligned_be32(opts->token, ptr);
+			ptr += 1;
+			put_unaligned_be32(opts->nonce, ptr);
+			ptr += 1;
+		} else if (OPTION_MPTCP_MPJ_SYNACK & opts->suboptions) {
+			*ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
+					      TCPOLEN_MPTCP_MPJ_SYNACK,
+					      opts->backup, opts->join_id);
+			put_unaligned_be64(opts->thmac, ptr);
+			ptr += 2;
+			put_unaligned_be32(opts->nonce, ptr);
+			ptr += 1;
+		} else {
+			*ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
+					      TCPOLEN_MPTCP_MPJ_ACK, 0, 0);
+			memcpy(ptr, opts->hmac, MPTCPOPT_HMAC_LEN);
+			ptr += 5;
+		}
 	} else if (OPTION_MPTCP_ADD_ADDR & opts->suboptions) {
 		u8 len = TCPOLEN_MPTCP_ADD_ADDR_BASE;
 		u8 echo = MPTCP_ADDR_ECHO;
Signature · 1 line
2.33.1
author maintainer
#2 lore raw

PATCH v2 2/4 mptcp: keep track of used local endpoint

In reply to Paolo Abeni

So that we can skip already used endpoint at local address selection time.
This allows for fair local endpoints usage in case of subflow failure.

As a side effect, this patch also enforces that each endpoint is used at most once for each mptcp connection.

---
 net/mptcp/pm.c         | 1 +
 net/mptcp/pm_netlink.c | 8 +++++++-
 net/mptcp/protocol.h   | 1 +
 3 files changed, 9 insertions(+), 1 deletion(-)
net/mptcp/pm.c +1 -0
index 761995a34124..1ff856dd92c4 100644
@@ -376,6 +376,7 @@ void mptcp_pm_data_reset(struct mptcp_sock *msk)
 	WRITE_ONCE(msk->pm.accept_subflow, false);
 	WRITE_ONCE(msk->pm.remote_deny_join_id0, false);
 	msk->pm.status = 0;
+	bitmap_zero(msk->pm.endpoint_usage_mask, 256);
 
 	mptcp_pm_nl_data_init(msk);
 }
net/mptcp/pm_netlink.c +7 -1
index 3186d33b5208..78b68a8216b6 100644
@@ -173,6 +173,9 @@ select_local_address(const struct pm_nl_pernet *pernet,
 		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW))
 			continue;
 
+		if (test_bit(entry->addr.id, msk->pm.endpoint_usage_mask))
+			continue;
+
 		if (entry->addr.family != sk->sk_family) {
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 			if ((entry->addr.family == AF_INET &&
@@ -512,8 +515,10 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 			check_work_pending(msk);
 			nr = fill_remote_addresses_vec(msk, fullmesh, addrs);
 			spin_unlock_bh(&msk->pm.lock);
-			for (i = 0; i < nr; i++)
+			for (i = 0; i < nr; i++) {
+				set_bit(local->addr.id, msk->pm.endpoint_usage_mask);
 				__mptcp_subflow_connect(sk, &local->addr, &addrs[i]);
+			}
 			spin_lock_bh(&msk->pm.lock);
 			return;
 		}
@@ -1282,6 +1287,7 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
 		mptcp_pm_remove_anno_addr(msk, addr, remove_subflow);
 		if (remove_subflow)
 			mptcp_pm_remove_subflow(msk, &list);
+		clear_bit(addr->id, msk->pm.endpoint_usage_mask);
 		release_sock(sk);
 
 next:
net/mptcp/protocol.h +1 -0
index a6a4bd7de5b4..d384f285b6c1 100644
@@ -190,6 +190,7 @@ struct mptcp_pm_data {
 
 	spinlock_t	lock;		/*protects the whole PM data */
 
+	DECLARE_BITMAP(endpoint_usage_mask, 256);
 	u8		addr_signal;
 	bool		server_side;
 	bool		work_pending;
Signature · 1 line
2.33.1
Reviewed-by on v2 2/4
#3 lore raw

Re: [PATCH v2 mptcp-next 2/4] mptcp: keep track of used local endpoint

Hi Paolo,

Quoted 9 lines · Paolo Abeni

So that we can skip already used endpoint at local address selection time.
This allows for fair local endpoints usage in case of subflow failure.

As a side effect, this patch also enforces that each endpoint is used at most once for each mptcp connection.

Good idea!

Cheers,
Matt

Signature · 2 lines
Tessares | Belgium | Hybrid Access Solutions
www.tessares.net
author maintainer
#4 lore raw

PATCH v2 3/4 mptcp: do not block subflows creation on errors

In reply to Paolo Abeni

If the MPTCP configuration allows for multiple subflows creation, and the first additional subflows never reach the fully established status - e.g. due to packets drop or reset - the in kernel path manager do not move to the next subflow.

This patch introduces a new PM helper to cope with MPJ subflow creation failure and delay and hook it where appropriate.

Such helper triggers additional subflow creation, as needed and updates the PM subflow counter, if the current one is closing.

Note that we don't need an additional timer to catch timeout and/or long delay in connection completion: we just need to measure the time elapsed since the subflow creation every time we emit an MPJ sub-option.

---
v2 -> v3:
- fix compile warning (CI)

v1 -> v2:
- explicitly hook on subflow close instead of error notification
- fix checkpatch issue (Mat)
- introduce and use a new pm helper to cope with subflow close
- update pm subflow counters on close

---
 net/mptcp/options.c  | 21 ++++++++++++++++++---
 net/mptcp/pm.c       | 27 +++++++++++++++++++++++++--
 net/mptcp/protocol.c |  6 ++++++
 net/mptcp/protocol.h |  4 +++-
 net/mptcp/subflow.c  |  5 ++++-
 5 files changed, 56 insertions(+), 7 deletions(-)
net/mptcp/options.c +18 -3
index 7a6a39b71633..00a8697addcd 100644
@@ -1257,10 +1257,10 @@ static u16 mptcp_make_csum(const struct mptcp_ext *mpext)
 void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 			 struct mptcp_out_options *opts)
 {
-	if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions)) {
-		const struct sock *ssk = (const struct sock *)tp;
-		struct mptcp_subflow_context *subflow;
+	const struct sock *ssk = (const struct sock *)tp;
+	struct mptcp_subflow_context *subflow;
 
+	if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions)) {
 		subflow = mptcp_subflow_ctx(ssk);
 		subflow->send_mp_fail = 0;
 
@@ -1382,6 +1382,21 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 		/* MPC is additionally mutually exclusive with MP_PRIO */
 		goto mp_capable_done;
 	} else if (OPTIONS_MPTCP_MPJ & opts->suboptions) {
+		if (ssk) {
+			/* we are still in the MPJ handshake and "a lot" of time passed
+			 * e.g. due to syn retranmissions. We can attempt next
+			 * subflow creation
+			 */
+			subflow = mptcp_subflow_ctx(ssk);
+			if (subflow->start_stamp &&
+			    unlikely(after(tcp_jiffies32, subflow->start_stamp + HZ / 10))) {
+				mptcp_pm_subflow_check_next(mptcp_sk(subflow->conn), ssk, subflow);
+
+				/* avoid triggering the PM multiple times due to timeout */
+				subflow->start_stamp = 0;
+			}
+		}
+
 		if (OPTION_MPTCP_MPJ_SYN & opts->suboptions) {
 			*ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
 					      TCPOLEN_MPTCP_MPJ_SYN,
net/mptcp/pm.c +25 -2
index 1ff856dd92c4..df8a596cd3ff 100644
@@ -172,9 +172,32 @@ void mptcp_pm_subflow_established(struct mptcp_sock *msk)
 	spin_unlock_bh(&pm->lock);
 }
 
-void mptcp_pm_subflow_closed(struct mptcp_sock *msk, u8 id)
+void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk,
+				 const struct mptcp_subflow_context *subflow)
 {
-	pr_debug("msk=%p", msk);
+	struct mptcp_pm_data *pm = &msk->pm;
+	bool closed;
+
+	closed = ssk->sk_state == TCP_CLOSE;
+	if (subflow->fully_established && !closed)
+		return;
+
+	spin_lock_bh(&pm->lock);
+	if (closed) {
+		pm->local_addr_used--;
+		pm->subflows--;
+		/* do not enable the pm worker: we don't want to pick again
+		 * the just closed subflow
+		 */
+	}
+
+	/* Even if this subflow is not really established, tell the PM to try
+	 * to pick the next one, if possible.
+	 */
+	if (pm->work_pending)
+		mptcp_pm_schedule_work(msk, MPTCP_PM_SUBFLOW_ESTABLISHED);
+
+	spin_unlock_bh(&pm->lock);
 }
 
 void mptcp_pm_add_addr_received(struct mptcp_sock *msk,
net/mptcp/protocol.c +6 -0
index ef2125798e64..2ee2fe97c553 100644
@@ -2351,6 +2351,12 @@ void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 {
 	if (sk->sk_state == TCP_ESTABLISHED)
 		mptcp_event(MPTCP_EVENT_SUB_CLOSED, mptcp_sk(sk), ssk, GFP_KERNEL);
+
+	/* subflow aborted before reaching the fully_established status
+	 * attempt the creation of the next subflow
+	 */
+	mptcp_pm_subflow_check_next(mptcp_sk(sk), ssk, subflow);
+
 	__mptcp_close_ssk(sk, ssk, subflow, MPTCP_CF_PUSH);
 }
 
net/mptcp/protocol.h +3 -1
index d384f285b6c1..4da1ef964b88 100644
@@ -433,6 +433,7 @@ struct mptcp_subflow_context {
 		stale : 1;	    /* unable to snd/rcv data, do not use for xmit */
 	enum mptcp_data_avail data_avail;
 	u32	remote_nonce;
+	u32	start_stamp;
 	u64	thmac;
 	u32	local_nonce;
 	u32	remote_token;
@@ -733,7 +734,8 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk,
 bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk);
 void mptcp_pm_connection_closed(struct mptcp_sock *msk);
 void mptcp_pm_subflow_established(struct mptcp_sock *msk);
-void mptcp_pm_subflow_closed(struct mptcp_sock *msk, u8 id);
+void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk,
+				 const struct mptcp_subflow_context *subflow);
 void mptcp_pm_add_addr_received(struct mptcp_sock *msk,
 				const struct mptcp_addr_info *addr);
 void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk,
net/mptcp/subflow.c +4 -1
index 0f90bd61de01..76556743e952 100644
@@ -1273,7 +1273,8 @@ void __mptcp_error_report(struct sock *sk)
 
 static void subflow_error_report(struct sock *ssk)
 {
-	struct sock *sk = mptcp_subflow_ctx(ssk)->conn;
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+	struct sock *sk = subflow->conn;
 
 	mptcp_data_lock(sk);
 	if (!sock_owned_by_user(sk))
@@ -1444,6 +1445,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 	subflow->remote_id = remote_id;
 	subflow->request_join = 1;
 	subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+	subflow->start_stamp = tcp_jiffies32;
 	mptcp_info2sockaddr(remote, &addr, ssk->sk_family);
 
 	mptcp_add_pending_subflow(msk, subflow);
@@ -1461,6 +1463,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 	spin_lock_bh(&msk->join_list_lock);
 	list_del(&subflow->node);
 	spin_unlock_bh(&msk->join_list_lock);
+	mptcp_pm_subflow_check_next(msk, ssk, subflow);
 	sock_put(mptcp_subflow_tcp_sock(subflow));
 
 failed:
Signature · 1 line
2.33.1
#5 lore raw

Re: [PATCH v2 mptcp-next 3/4] mptcp: do not block subflows creation on errors

Hi Paolo,

Quoted 18 lines · Paolo Abeni

If the MPTCP configuration allows for multiple subflows creation, and the first additional subflows never reach the fully established status - e.g. due to packets drop or reset - the in kernel path manager do not move to the next subflow.

This patch introduces a new PM helper to cope with MPJ subflow creation failure and delay and hook it where appropriate.

Such helper triggers additional subflow creation, as needed and updates the PM subflow counter, if the current one is closing.

Note that we don't need an additional timer to catch timeout and/or long delay in connection completion: we just need to measure the time elapsed since the subflow creation every time we emit an MPJ sub-option.

Quoted 8 lines

---
v2 -> v3:
- fix compile warning (CI)

v1 -> v2:
- explicitly hook on subflow close instead of error notification
- fix checkpatch issue (Mat)

(+t :-P )

Quoted 2 lines

- introduce and use a new pm helper to cope with subflow close
- update pm subflow counters on close

Thank you for the new version!

Quoted 6 lines
net/mptcp/options.c +0 -0
index 7a6a39b71633..00a8697addcd 100644
@@ -1382,6 +1382,21 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 		/* MPC is additionally mutually exclusive with MP_PRIO */

net/mptcp/options.c void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, · line 1392

Quoted 10 lines
net/mptcp/options.c +8 -0
 		goto mp_capable_done;
 	} else if (OPTIONS_MPTCP_MPJ & opts->suboptions) {
+		if (ssk) {
+			/* we are still in the MPJ handshake and "a lot" of time passed
+			 * e.g. due to syn retranmissions. We can attempt next
+			 * subflow creation
+			 */
+			subflow = mptcp_subflow_ctx(ssk);
+			if (subflow->start_stamp &&
+			    unlikely(after(tcp_jiffies32, subflow->start_stamp + HZ / 10))) {

As discussed at the last meeting, we will reach this code path when retransmitting the SYN, one second after having sent the initial one. In this case, we might not need to keep 'start_stamp'.

But we can improve that in a new version after.

Quoted 15 lines
net/mptcp/options.c +7 -0
+				mptcp_pm_subflow_check_next(mptcp_sk(subflow->conn), ssk, subflow);
+
+				/* avoid triggering the PM multiple times due to timeout */
+				subflow->start_stamp = 0;
+			}
+		}
+
 		if (OPTION_MPTCP_MPJ_SYN & opts->suboptions) {
 			*ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
 					      TCPOLEN_MPTCP_MPJ_SYN,
net/mptcp/pm.c +0 -0
index 1ff856dd92c4..df8a596cd3ff 100644

net/mptcp/pm.c void mptcp_pm_subflow_established(struct mptcp_sock *msk) · line 176

Quoted 6 lines
net/mptcp/pm.c +2 -1
@@ -172,9 +172,32 @@ void mptcp_pm_subflow_established(struct mptcp_sock *msk)
 	spin_unlock_bh(&pm->lock);
 }
 
-void mptcp_pm_subflow_closed(struct mptcp_sock *msk, u8 id)
+void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk,
+				 const struct mptcp_subflow_context *subflow)

Detail: do we need to pass the 'msk'? Can we not get it from 'subflow'?

Quoted 12 lines
net/mptcp/pm.c +10 -1
 {
-	pr_debug("msk=%p", msk);
+	struct mptcp_pm_data *pm = &msk->pm;
+	bool closed;
+
+	closed = ssk->sk_state == TCP_CLOSE;
+	if (subflow->fully_established && !closed)
+		return;
+
+	spin_lock_bh(&pm->lock);
+	if (closed) {
+		pm->local_addr_used--;

net/mptcp/pm.c void mptcp_pm_subflow_established(struct mptcp_sock *msk) · line 197

Quoted 10 lines
net/mptcp/pm.c +10 -0
+		pm->subflows--;
+		/* do not enable the pm worker: we don't want to pick again
+		 * the just closed subflow
+		 */
+	}
+
+	/* Even if this subflow is not really established, tell the PM to try
+	 * to pick the next one, if possible.
+	 */
+	if (pm->work_pending)

Does it not need to be "protected" with a READ_ONCE?

net/mptcp/pm.c void mptcp_pm_subflow_established(struct mptcp_sock *msk) · line 203

Quoted 6 lines
net/mptcp/pm.c +3 -0
+		mptcp_pm_schedule_work(msk, MPTCP_PM_SUBFLOW_ESTABLISHED);
+
+	spin_unlock_bh(&pm->lock);
 }
 
 void mptcp_pm_add_addr_received(struct mptcp_sock *msk,

(not related to this line)

Did you see that the "fastclose" packetdrill tests are failing? Is it due to these modifications?

Cheers,
Matt

Signature · 2 lines
Tessares | Belgium | Hybrid Access Solutions
www.tessares.net
author maintainer
#6 lore raw

Re: [PATCH v2 mptcp-next 3/4] mptcp: do not block subflows creation on errors

Quoted 78 lines · Matthieu Baerts

Hi Paolo,

Quoted 18 lines · Paolo Abeni

If the MPTCP configuration allows for multiple subflows creation, and the first additional subflows never reach the fully established status - e.g. due to packets drop or reset - the in kernel path manager do not move to the next subflow.

This patch introduces a new PM helper to cope with MPJ subflow creation failure and delay and hook it where appropriate.

Such helper triggers additional subflow creation, as needed and updates the PM subflow counter, if the current one is closing.

Note that we don't need an additional timer to catch timeout and/or long delay in connection completion: we just need to measure the time elapsed since the subflow creation every time we emit an MPJ sub-option.

Quoted 8 lines

---
v2 -> v3:
- fix compile warning (CI)

v1 -> v2:
- explicitly hook on subflow close instead of error notification
- fix checkpatch issue (Mat)

(+t :-P )

Quoted 2 lines

- introduce and use a new pm helper to cope with subflow close
- update pm subflow counters on close

Thank you for the new version!

Quoted 6 lines
net/mptcp/options.c +0 -0
index 7a6a39b71633..00a8697addcd 100644
@@ -1382,6 +1382,21 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 		/* MPC is additionally mutually exclusive with MP_PRIO */

net/mptcp/options.c void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, · line 1392

Quoted 10 lines
net/mptcp/options.c +8 -0
 		goto mp_capable_done;
 	} else if (OPTIONS_MPTCP_MPJ & opts->suboptions) {
+		if (ssk) {
+			/* we are still in the MPJ handshake and "a lot" of time passed
+			 * e.g. due to syn retranmissions. We can attempt next
+			 * subflow creation
+			 */
+			subflow = mptcp_subflow_ctx(ssk);
+			if (subflow->start_stamp &&
+			    unlikely(after(tcp_jiffies32, subflow->start_stamp + HZ / 10))) {

As discussed at the last meeting, we will reach this code path when retransmitting the SYN, one second after having sent the initial one. In this case, we might not need to keep 'start_stamp'.

But we can improve that in a new version after.

Quoted 18 lines
net/mptcp/options.c +7 -0
+				mptcp_pm_subflow_check_next(mptcp_sk(subflow->conn), ssk, subflow);
+
+				/* avoid triggering the PM multiple times due to timeout */
+				subflow->start_stamp = 0;
+			}
+		}
+
 		if (OPTION_MPTCP_MPJ_SYN & opts->suboptions) {
 			*ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
 					      TCPOLEN_MPTCP_MPJ_SYN,
net/mptcp/pm.c +0 -0
index 1ff856dd92c4..df8a596cd3ff 100644
@@ -172,9 +172,32 @@ void mptcp_pm_subflow_established(struct mptcp_sock *msk)
 	spin_unlock_bh(&pm->lock);
 }
 
Quoted 5 lines

net/mptcp/pm.c void mptcp_pm_subflow_established(struct mptcp_sock *msk) · line 176

Quoted 3 lines
net/mptcp/pm.c +2 -1
-void mptcp_pm_subflow_closed(struct mptcp_sock *msk, u8 id)
+void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk,
+				 const struct mptcp_subflow_context *subflow)

Detail: do we need to pass the 'msk'? Can we not get it from 'subflow'?

The caler has the msk handy, passing it to the helper keeps the args list similar to other releated helpers and avoid some more dup code.

Quoted 16 lines
Quoted 16 lines
net/mptcp/pm.c +14 -1
 {
-	pr_debug("msk=%p", msk);
+	struct mptcp_pm_data *pm = &msk->pm;
+	bool closed;
+
+	closed = ssk->sk_state == TCP_CLOSE;
+	if (subflow->fully_established && !closed)
+		return;
+
+	spin_lock_bh(&pm->lock);
+	if (closed) {
+		pm->local_addr_used--;
+		pm->subflows--;
+		/* do not enable the pm worker: we don't want to pick again
+		 * the just closed subflow
+		 */
Quoted 8 lines

net/mptcp/pm.c void mptcp_pm_subflow_established(struct mptcp_sock *msk) · line 197

Quoted 6 lines
net/mptcp/pm.c +6 -0
+	}
+
+	/* Even if this subflow is not really established, tell the PM to try
+	 * to pick the next one, if possible.
+	 */
+	if (pm->work_pending)

Does it not need to be "protected" with a READ_ONCE?

AFAIK not needed: this is the only read issued on such field in this scope and and is done under the relevant lock (all write operation occours under the pm lock).

Quoted 11 lines

net/mptcp/pm.c void mptcp_pm_subflow_established(struct mptcp_sock *msk) · line 203

Quoted 6 lines
net/mptcp/pm.c +3 -0
+		mptcp_pm_schedule_work(msk, MPTCP_PM_SUBFLOW_ESTABLISHED);
+
+	spin_unlock_bh(&pm->lock);
 }
 
 void mptcp_pm_add_addr_received(struct mptcp_sock *msk,

(not related to this line)

Did you see that the "fastclose" packetdrill tests are failing? Is it due to these modifications?

uhm... I haven't check them. I'll have a look soon.

Thanks!

Paolo

author maintainer
#7 lore raw

PATCH v2 4/4 selftests: mptcp: add tests for subflow creation failure

In reply to Paolo Abeni

Verify that, when multiple endpoints are available, subflows creation proceed even when the first additional subflow creation fails - due to packet drop on the relevant link

---
v1 -> v2:
- add missing NF kconfig
- add more test-cases (drop, later subflow creation)

---
 tools/testing/selftests/net/mptcp/config      |  1 +
 .../testing/selftests/net/mptcp/mptcp_join.sh | 65 ++++++++++++++++++-
 2 files changed, 65 insertions(+), 1 deletion(-)
tools/testing/selftests/net/mptcp/config +1 -0
index 419e71560fd1..41e94e004bdc 100644
@@ -18,4 +18,5 @@ CONFIG_NFT_TPROXY=m
 CONFIG_NFT_SOCKET=m
 CONFIG_IP_ADVANCED_ROUTER=y
 CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_NF_TARGET_REJECT=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
tools/testing/selftests/net/mptcp/mptcp_join.sh +64 -1

99 lines not on this page · raw message

Signature · 1 line
2.33.1
#8 lore raw

Re: [PATCH v2 mptcp-next 4/4] selftests: mptcp: add tests for subflow creation failure

Hi Paolo,

Quoted 9 lines · Paolo Abeni

Verify that, when multiple endpoints are available, subflows creation proceed even when the first additional subflow creation fails - due to packet drop on the relevant link

---
v1 -> v2:
- add missing NF kconfig
- add more test-cases (drop, later subflow creation)

Thank you for the modifications!

Quoted 6 lines
tools/testing/selftests/net/mptcp/mptcp_join.sh +0 -0
index 2684ef9c0d42..6d342f9985b8 100755
@@ -975,6 +975,22 @@ chk_link_usage()
 	fi

tools/testing/selftests/net/mptcp/mptcp_join.sh chk_link_usage() · line 985

Quoted 10 lines
tools/testing/selftests/net/mptcp/mptcp_join.sh +8 -0
 }
 
+wait_for_tw()
+{
+	local timeout_ms=$((timeout_poll * 1000))
+	local time=0
+	local ns=$1
+
+	while [ $time -lt $timeout_ms ]; do
+		local cnt=`ip netns exec $ns ss -t state time-wait |wc -l`

(no need to change but it is often recommended to use $(...) instead of ... because it supports nested commands and is more "visible")

(...)

tools/testing/selftests/net/mptcp/mptcp_join.sh usage() · line 1921

Quoted 5 lines
tools/testing/selftests/net/mptcp/mptcp_join.sh +1 -0
@@ -1859,6 +1918,7 @@ usage()
 {
 	echo "mptcp_join usage:"
 	echo "  -f subflows_tests"
+	echo "  -f subflows_error_tests"

Detail: s/-f/-e/

I can fix it before applying if you didn't already plan to send a new v4 :)

Cheers,
Matt

PS: for the lagging a bit with the reviews!

Signature · 2 lines
Tessares | Belgium | Hybrid Access Solutions
www.tessares.net
author maintainer
#9 lore raw
In reply to Paolo Abeni
Quoted 2 lines · Paolo Abeni

This iteration just addresses a compile warning spotted by the CI.

I'm sorry for the confusion: this is really a v3, not v2. Hopefully patchwork is still happy?

I could not even say ENOCOFFEE because I just had one before posting.

Cheers,

Paolo