Merge branch 'mptcp-next'

Mat Martineau says:

====================
mptcp: New features and cleanup

These patches have been tested in the MPTCP tree for a longer than usual
time (thanks to holiday schedules), and are ready for the net-next
branch. Changes include feature updates, small fixes, refactoring, and
some selftest changes.

Patch 1 fixes an OUTQ ioctl issue with TCP fallback sockets.

Patches 2, 3, and 6 add support of the MPTCP fastclose option (quick
shutdown of the full MPTCP connection, similar to TCP RST in regular
TCP), and a related self test.

Patch 4 cleans up some accept and poll code that is no longer needed
after the fastclose changes.

Patch 5 add userspace disconnect using AF_UNSPEC, which is used when
testing fastclose and makes the MPTCP socket's handling of AF_UNSPEC in
connect() more TCP-like.

Patches 7-11 refactor subflow creation to make better use of multiple
local endpoints and to better handle individual connection failures when
creating multiple subflows. Includes self test updates.

Patch 12 cleans up the way subflows are added to the MPTCP connection
list, eliminating the need for calls throughout the MPTCP code that had
to check the intermediate "join list" for entries to shift over to the
main "connection list".

Patch 13 refactors the MPTCP release_cb flags to use separate storage
for values only accessed with the socket lock held (no atomic ops
needed), and for values that need atomic operations.
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

net/mptcp/options.c

@@ -768,6 +768,28 @@ static noinline bool mptcp_established_options_rst(struct sock *sk, struct sk_bu
 	return true;
 }
 
+static bool mptcp_established_options_fastclose(struct sock *sk,
+						unsigned int *size,
+						unsigned int remaining,
+						struct mptcp_out_options *opts)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+
+	if (likely(!subflow->send_fastclose))
+		return false;
+
+	if (remaining < TCPOLEN_MPTCP_FASTCLOSE)
+		return false;
+
+	*size = TCPOLEN_MPTCP_FASTCLOSE;
+	opts->suboptions |= OPTION_MPTCP_FASTCLOSE;
+	opts->rcvr_key = msk->remote_key;
+
+	pr_debug("FASTCLOSE key=%llu", opts->rcvr_key);
+	return true;
+}
+
 static bool mptcp_established_options_mp_fail(struct sock *sk,
 					      unsigned int *size,
 					      unsigned int remaining,
@@ -806,10 +828,12 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
 		return false;
 
 	if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) {
-		if (mptcp_established_options_mp_fail(sk, &opt_size, remaining, opts)) {
+		if (mptcp_established_options_fastclose(sk, &opt_size, remaining, opts) ||
+		    mptcp_established_options_mp_fail(sk, &opt_size, remaining, opts)) {
 			*size += opt_size;
 			remaining -= opt_size;
 		}
+		/* MP_RST can be used with MP_FASTCLOSE and MP_FAIL if there is room */
 		if (mptcp_established_options_rst(sk, skb, &opt_size, remaining, opts)) {
 			*size += opt_size;
 			remaining -= opt_size;
@@ -1251,17 +1275,8 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 		ptr += 2;
 	}
 
-	/* RST is mutually exclusive with everything else */
-	if (unlikely(OPTION_MPTCP_RST & opts->suboptions)) {
-		*ptr++ = mptcp_option(MPTCPOPT_RST,
-				      TCPOLEN_MPTCP_RST,
-				      opts->reset_transient,
-				      opts->reset_reason);
-		return;
-	}
-
-	/* DSS, MPC, MPJ and ADD_ADDR are mutually exclusive, see
-	 * mptcp_established_options*()
+	/* DSS, MPC, MPJ, ADD_ADDR, FASTCLOSE and RST are mutually exclusive,
+	 * see mptcp_established_options*()
 	 */
 	if (likely(OPTION_MPTCP_DSS & opts->suboptions)) {
 		struct mptcp_ext *mpext = &opts->ext_copy;
@@ -1370,27 +1385,29 @@ 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;
@@ -1447,6 +1464,24 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 				ptr += 1;
 			}
 		}
+	} else if (unlikely(OPTION_MPTCP_FASTCLOSE & opts->suboptions)) {
+		/* FASTCLOSE is mutually exclusive with others except RST */
+		*ptr++ = mptcp_option(MPTCPOPT_MP_FASTCLOSE,
+				      TCPOLEN_MPTCP_FASTCLOSE,
+				      0, 0);
+		put_unaligned_be64(opts->rcvr_key, ptr);
+		ptr += 2;
+
+		if (OPTION_MPTCP_RST & opts->suboptions)
+			goto mp_rst;
+		return;
+	} else if (unlikely(OPTION_MPTCP_RST & opts->suboptions)) {
+mp_rst:
+		*ptr++ = mptcp_option(MPTCPOPT_RST,
+				      TCPOLEN_MPTCP_RST,
+				      opts->reset_transient,
+				      opts->reset_reason);
+		return;
 	}
 
 	if (OPTION_MPTCP_PRIO & opts->suboptions) {

net/mptcp/pm.c

@@ -172,9 +172,28 @@ 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 update_subflows;
+
+	update_subflows = (ssk->sk_state == TCP_CLOSE) &&
+			  (subflow->request_join || subflow->mp_join);
+	if (!READ_ONCE(pm->work_pending) && !update_subflows)
+		return;
+
+	spin_lock_bh(&pm->lock);
+	if (update_subflows)
+		pm->subflows--;
+
+	/* Even if this subflow is not really established, tell the PM to try
+	 * to pick the next ones, if possible.
+	 */
+	if (mptcp_pm_nl_check_work_pending(msk))
+		mptcp_pm_schedule_work(msk, MPTCP_PM_SUBFLOW_ESTABLISHED);
+
+	spin_unlock_bh(&pm->lock);
 }
 
 void mptcp_pm_add_addr_received(struct mptcp_sock *msk,
@@ -356,7 +375,7 @@ void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
 	}
 }
 
-void mptcp_pm_data_init(struct mptcp_sock *msk)
+void mptcp_pm_data_reset(struct mptcp_sock *msk)
 {
 	msk->pm.add_addr_signaled = 0;
 	msk->pm.add_addr_accepted = 0;
@@ -370,11 +389,16 @@ void mptcp_pm_data_init(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_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
+
+	mptcp_pm_nl_data_init(msk);
+}
 
+void mptcp_pm_data_init(struct mptcp_sock *msk)
+{
 	spin_lock_init(&msk->pm.lock);
 	INIT_LIST_HEAD(&msk->pm.anno_list);
-
-	mptcp_pm_nl_data_init(msk);
+	mptcp_pm_data_reset(msk);
 }
 
 void __init mptcp_pm_init(void)