1 files changed, 175 insertions, 137 deletions

diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 3c2e166b5d22..10219f55aad1 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  Shared Memory Communications over RDMA (SMC-R) and RoCE
  *
@@ -12,13 +13,28 @@
 #include <linux/sched/signal.h>
 
 #include <net/sock.h>
+#include <net/tcp.h>
 
 #include "smc.h"
 #include "smc_tx.h"
 #include "smc_cdc.h"
 #include "smc_close.h"
 
-#define SMC_CLOSE_WAIT_TX_PENDS_TIME		(5 * HZ)
+/* release the clcsock that is assigned to the smc_sock */
+void smc_clcsock_release(struct smc_sock *smc)
+{
+	struct socket *tcp;
+
+	if (smc->listen_smc && current_work() != &smc->smc_listen_work)
+		cancel_work_sync(&smc->smc_listen_work);
+	mutex_lock(&smc->clcsock_release_lock);
+	if (smc->clcsock) {
+		tcp = smc->clcsock;
+		smc->clcsock = NULL;
+		sock_release(tcp);
+	}
+	mutex_unlock(&smc->clcsock_release_lock);
+}
 
 static void smc_close_cleanup_listen(struct sock *parent)
 {
@@ -29,26 +45,6 @@ static void smc_close_cleanup_listen(struct sock *parent)
 		smc_close_non_accepted(sk);
 }
 
-static void smc_close_wait_tx_pends(struct smc_sock *smc)
-{
-	DEFINE_WAIT_FUNC(wait, woken_wake_function);
-	struct sock *sk = &smc->sk;
-	signed long timeout;
-
-	timeout = SMC_CLOSE_WAIT_TX_PENDS_TIME;
-	add_wait_queue(sk_sleep(sk), &wait);
-	while (!signal_pending(current) && timeout) {
-		int rc;
-
-		rc = sk_wait_event(sk, &timeout,
-				   !smc_cdc_tx_has_pending(&smc->conn),
-				   &wait);
-		if (rc)
-			break;
-	}
-	remove_wait_queue(sk_sleep(sk), &wait);
-}
-
 /* wait for sndbuf data being transmitted */
 static void smc_close_stream_wait(struct smc_sock *smc, long timeout)
 {
@@ -61,6 +57,9 @@ static void smc_close_stream_wait(struct smc_sock *smc, long timeout)
 	if (!smc_tx_prepared_sends(&smc->conn))
 		return;
 
+	/* Send out corked data remaining in sndbuf */
+	smc_tx_pending(&smc->conn);
+
 	smc->wait_close_tx_prepared = 1;
 	add_wait_queue(sk_sleep(sk), &wait);
 	while (!signal_pending(current) && timeout) {
@@ -68,8 +67,9 @@ static void smc_close_stream_wait(struct smc_sock *smc, long timeout)
 
 		rc = sk_wait_event(sk, &timeout,
 				   !smc_tx_prepared_sends(&smc->conn) ||
-				   (sk->sk_err == ECONNABORTED) ||
-				   (sk->sk_err == ECONNRESET),
+				   READ_ONCE(sk->sk_err) == ECONNABORTED ||
+				   READ_ONCE(sk->sk_err) == ECONNRESET ||
+				   smc->conn.killed,
 				   &wait);
 		if (rc)
 			break;
@@ -98,70 +98,90 @@ static int smc_close_final(struct smc_connection *conn)
 		conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1;
 	else
 		conn->local_tx_ctrl.conn_state_flags.peer_conn_closed = 1;
+	if (conn->killed)
+		return -EPIPE;
 
 	return smc_cdc_get_slot_and_msg_send(conn);
 }
 
-static int smc_close_abort(struct smc_connection *conn)
+int smc_close_abort(struct smc_connection *conn)
 {
 	conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1;
 
 	return smc_cdc_get_slot_and_msg_send(conn);
 }
 
+static void smc_close_cancel_work(struct smc_sock *smc)
+{
+	struct sock *sk = &smc->sk;
+
+	release_sock(sk);
+	if (cancel_work_sync(&smc->conn.close_work))
+		sock_put(sk);
+	cancel_delayed_work_sync(&smc->conn.tx_work);
+	lock_sock(sk);
+}
+
 /* terminate smc socket abnormally - active abort
- * RDMA communication no longer possible
+ * link group is terminated, i.e. RDMA communication no longer possible
  */
 void smc_close_active_abort(struct smc_sock *smc)
 {
-	struct smc_cdc_conn_state_flags *txflags =
-		&smc->conn.local_tx_ctrl.conn_state_flags;
+	struct sock *sk = &smc->sk;
+	bool release_clcsock = false;
 
-	smc->sk.sk_err = ECONNABORTED;
-	if (smc->clcsock && smc->clcsock->sk) {
-		smc->clcsock->sk->sk_err = ECONNABORTED;
-		smc->clcsock->sk->sk_state_change(smc->clcsock->sk);
+	if (sk->sk_state != SMC_INIT && smc->clcsock && smc->clcsock->sk) {
+		sk->sk_err = ECONNABORTED;
+		if (smc->clcsock && smc->clcsock->sk)
+			tcp_abort(smc->clcsock->sk, ECONNABORTED);
 	}
-	switch (smc->sk.sk_state) {
-	case SMC_INIT:
+	switch (sk->sk_state) {
 	case SMC_ACTIVE:
-		smc->sk.sk_state = SMC_PEERABORTWAIT;
-		break;
 	case SMC_APPCLOSEWAIT1:
 	case SMC_APPCLOSEWAIT2:
-		txflags->peer_conn_abort = 1;
-		sock_release(smc->clcsock);
-		if (!smc_cdc_rxed_any_close(&smc->conn))
-			smc->sk.sk_state = SMC_PEERABORTWAIT;
-		else
-			smc->sk.sk_state = SMC_CLOSED;
+		sk->sk_state = SMC_PEERABORTWAIT;
+		smc_close_cancel_work(smc);
+		if (sk->sk_state != SMC_PEERABORTWAIT)
+			break;
+		sk->sk_state = SMC_CLOSED;
+		sock_put(sk); /* (postponed) passive closing */
 		break;
 	case SMC_PEERCLOSEWAIT1:
 	case SMC_PEERCLOSEWAIT2:
-		if (!txflags->peer_conn_closed) {
-			smc->sk.sk_state = SMC_PEERABORTWAIT;
-			txflags->peer_conn_abort = 1;
-			sock_release(smc->clcsock);
-		} else {
-			smc->sk.sk_state = SMC_CLOSED;
-		}
+	case SMC_PEERFINCLOSEWAIT:
+		sk->sk_state = SMC_PEERABORTWAIT;
+		smc_close_cancel_work(smc);
+		if (sk->sk_state != SMC_PEERABORTWAIT)
+			break;
+		sk->sk_state = SMC_CLOSED;
+		smc_conn_free(&smc->conn);
+		release_clcsock = true;
+		sock_put(sk); /* passive closing */
 		break;
 	case SMC_PROCESSABORT:
 	case SMC_APPFINCLOSEWAIT:
-		if (!txflags->peer_conn_closed) {
-			txflags->peer_conn_abort = 1;
-			sock_release(smc->clcsock);
-		}
-		smc->sk.sk_state = SMC_CLOSED;
+		sk->sk_state = SMC_PEERABORTWAIT;
+		smc_close_cancel_work(smc);
+		if (sk->sk_state != SMC_PEERABORTWAIT)
+			break;
+		sk->sk_state = SMC_CLOSED;
+		smc_conn_free(&smc->conn);
+		release_clcsock = true;
 		break;
-	case SMC_PEERFINCLOSEWAIT:
+	case SMC_INIT:
 	case SMC_PEERABORTWAIT:
 	case SMC_CLOSED:
 		break;
 	}
 
-	sock_set_flag(&smc->sk, SOCK_DEAD);
-	smc->sk.sk_state_change(&smc->sk);
+	smc_sock_set_flag(sk, SOCK_DEAD);
+	sk->sk_state_change(sk);
+
+	if (release_clcsock) {
+		release_sock(sk);
+		smc_clcsock_release(smc);
+		lock_sock(sk);
+	}
 }
 
 static inline bool smc_close_sent_any_close(struct smc_connection *conn)
@@ -174,46 +194,57 @@ int smc_close_active(struct smc_sock *smc)
 {
 	struct smc_cdc_conn_state_flags *txflags =
 		&smc->conn.local_tx_ctrl.conn_state_flags;
-	long timeout = SMC_MAX_STREAM_WAIT_TIMEOUT;
 	struct smc_connection *conn = &smc->conn;
 	struct sock *sk = &smc->sk;
 	int old_state;
+	long timeout;
 	int rc = 0;
+	int rc1 = 0;
 
-	if (sock_flag(sk, SOCK_LINGER) &&
-	    !(current->flags & PF_EXITING))
-		timeout = sk->sk_lingertime;
+	timeout = current->flags & PF_EXITING ?
+		  0 : sock_flag(sk, SOCK_LINGER) ?
+		      sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT;
 
-again:
 	old_state = sk->sk_state;
-	switch (old_state) {
+again:
+	switch (sk->sk_state) {
 	case SMC_INIT:
 		sk->sk_state = SMC_CLOSED;
-		if (smc->smc_listen_work.func)
-			cancel_work_sync(&smc->smc_listen_work);
 		break;
 	case SMC_LISTEN:
 		sk->sk_state = SMC_CLOSED;
 		sk->sk_state_change(sk); /* wake up accept */
 		if (smc->clcsock && smc->clcsock->sk) {
+			write_lock_bh(&smc->clcsock->sk->sk_callback_lock);
+			smc_clcsock_restore_cb(&smc->clcsock->sk->sk_data_ready,
+					       &smc->clcsk_data_ready);
+			smc->clcsock->sk->sk_user_data = NULL;
+			write_unlock_bh(&smc->clcsock->sk->sk_callback_lock);
 			rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR);
-			/* wake up kernel_accept of smc_tcp_listen_worker */
-			smc->clcsock->sk->sk_data_ready(smc->clcsock->sk);
 		}
-		release_sock(sk);
 		smc_close_cleanup_listen(sk);
-		cancel_work_sync(&smc->smc_listen_work);
+		release_sock(sk);
+		flush_work(&smc->tcp_listen_work);
 		lock_sock(sk);
 		break;
 	case SMC_ACTIVE:
 		smc_close_stream_wait(smc, timeout);
 		release_sock(sk);
-		cancel_work_sync(&conn->tx_work);
+		cancel_delayed_work_sync(&conn->tx_work);
 		lock_sock(sk);
 		if (sk->sk_state == SMC_ACTIVE) {
 			/* send close request */
 			rc = smc_close_final(conn);
 			sk->sk_state = SMC_PEERCLOSEWAIT1;
+
+			/* actively shutdown clcsock before peer close it,
+			 * prevent peer from entering TIME_WAIT state.
+			 */
+			if (smc->clcsock && smc->clcsock->sk) {
+				rc1 = kernel_sock_shutdown(smc->clcsock,
+							   SHUT_RDWR);
+				rc = rc ? rc : rc1;
+			}
 		} else {
 			/* peer event has changed the state */
 			goto again;
@@ -227,28 +258,27 @@ again:
 			rc = smc_close_final(conn);
 		}
 		sk->sk_state = SMC_CLOSED;
-		smc_close_wait_tx_pends(smc);
 		break;
 	case SMC_APPCLOSEWAIT1:
 	case SMC_APPCLOSEWAIT2:
 		if (!smc_cdc_rxed_any_close(conn))
 			smc_close_stream_wait(smc, timeout);
 		release_sock(sk);
-		cancel_work_sync(&conn->tx_work);
+		cancel_delayed_work_sync(&conn->tx_work);
 		lock_sock(sk);
-		if (sk->sk_err != ECONNABORTED) {
-			/* confirm close from peer */
-			rc = smc_close_final(conn);
-			if (rc)
-				break;
-		}
-		if (smc_cdc_rxed_any_close(conn))
+		if (sk->sk_state != SMC_APPCLOSEWAIT1 &&
+		    sk->sk_state != SMC_APPCLOSEWAIT2)
+			goto again;
+		/* confirm close from peer */
+		rc = smc_close_final(conn);
+		if (smc_cdc_rxed_any_close(conn)) {
 			/* peer has closed the socket already */
 			sk->sk_state = SMC_CLOSED;
-		else
+			sock_put(sk); /* postponed passive closing */
+		} else {
 			/* peer has just issued a shutdown write */
 			sk->sk_state = SMC_PEERFINCLOSEWAIT;
-		smc_close_wait_tx_pends(smc);
+		}
 		break;
 	case SMC_PEERCLOSEWAIT1:
 	case SMC_PEERCLOSEWAIT2:
@@ -263,19 +293,19 @@ again:
 		/* peer sending PeerConnectionClosed will cause transition */
 		break;
 	case SMC_PROCESSABORT:
-		cancel_work_sync(&conn->tx_work);
-		smc_close_abort(conn);
+		rc = smc_close_abort(conn);
 		sk->sk_state = SMC_CLOSED;
-		smc_close_wait_tx_pends(smc);
 		break;
 	case SMC_PEERABORTWAIT:
+		sk->sk_state = SMC_CLOSED;
+		break;
 	case SMC_CLOSED:
 		/* nothing to do, add tracing in future patch */
 		break;
 	}
 
 	if (old_state != sk->sk_state)
-		sk->sk_state_change(&smc->sk);
+		sk->sk_state_change(sk);
 	return rc;
 }
 
@@ -286,37 +316,42 @@ static void smc_close_passive_abort_received(struct smc_sock *smc)
 	struct sock *sk = &smc->sk;
 
 	switch (sk->sk_state) {
+	case SMC_INIT:
 	case SMC_ACTIVE:
-	case SMC_APPFINCLOSEWAIT:
 	case SMC_APPCLOSEWAIT1:
-	case SMC_APPCLOSEWAIT2:
-		smc_close_abort(&smc->conn);
+		sk->sk_state = SMC_PROCESSABORT;
+		sock_put(sk); /* passive closing */
+		break;
+	case SMC_APPFINCLOSEWAIT:
 		sk->sk_state = SMC_PROCESSABORT;
 		break;
 	case SMC_PEERCLOSEWAIT1:
 	case SMC_PEERCLOSEWAIT2:
 		if (txflags->peer_done_writing &&
-		    !smc_close_sent_any_close(&smc->conn)) {
+		    !smc_close_sent_any_close(&smc->conn))
 			/* just shutdown, but not yet closed locally */
-			smc_close_abort(&smc->conn);
 			sk->sk_state = SMC_PROCESSABORT;
-		} else {
+		else
 			sk->sk_state = SMC_CLOSED;
-		}
+		sock_put(sk); /* passive closing */
 		break;
+	case SMC_APPCLOSEWAIT2:
 	case SMC_PEERFINCLOSEWAIT:
+		sk->sk_state = SMC_CLOSED;
+		sock_put(sk); /* passive closing */
+		break;
 	case SMC_PEERABORTWAIT:
 		sk->sk_state = SMC_CLOSED;
 		break;
-	case SMC_INIT:
 	case SMC_PROCESSABORT:
 	/* nothing to do, add tracing in future patch */
 		break;
 	}
 }
 
-/* Some kind of closing has been received: peer_conn_closed, peer_conn_abort,
- * or peer_done_writing.
+/* Either some kind of closing has been received: peer_conn_closed,
+ * peer_conn_abort, or peer_done_writing
+ * or the link group of the connection terminates abnormally.
  */
 static void smc_close_passive_work(struct work_struct *work)
 {
@@ -325,43 +360,40 @@ static void smc_close_passive_work(struct work_struct *work)
 						   close_work);
 	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
 	struct smc_cdc_conn_state_flags *rxflags;
+	bool release_clcsock = false;
 	struct sock *sk = &smc->sk;
 	int old_state;
 
-	lock_sock(&smc->sk);
+	lock_sock(sk);
 	old_state = sk->sk_state;
 
-	if (!conn->alert_token_local) {
-		/* abnormal termination */
-		smc_close_active_abort(smc);
-		goto wakeup;
-	}
-
-	rxflags = &smc->conn.local_rx_ctrl.conn_state_flags;
+	rxflags = &conn->local_rx_ctrl.conn_state_flags;
 	if (rxflags->peer_conn_abort) {
+		/* peer has not received all data */
 		smc_close_passive_abort_received(smc);
+		release_sock(sk);
+		cancel_delayed_work_sync(&conn->tx_work);
+		lock_sock(sk);
 		goto wakeup;
 	}
 
 	switch (sk->sk_state) {
 	case SMC_INIT:
-		if (atomic_read(&smc->conn.bytes_to_rcv) ||
-		    (rxflags->peer_done_writing &&
-		     !smc_cdc_rxed_any_close(conn)))
-			sk->sk_state = SMC_APPCLOSEWAIT1;
-		else
-			sk->sk_state = SMC_CLOSED;
+		sk->sk_state = SMC_APPCLOSEWAIT1;
 		break;
 	case SMC_ACTIVE:
 		sk->sk_state = SMC_APPCLOSEWAIT1;
+		/* postpone sock_put() for passive closing to cover
+		 * received SEND_SHUTDOWN as well
+		 */
 		break;
 	case SMC_PEERCLOSEWAIT1:
 		if (rxflags->peer_done_writing)
 			sk->sk_state = SMC_PEERCLOSEWAIT2;
-		/* fall through to check for closing */
+		fallthrough;
+		/* to check for closing */
 	case SMC_PEERCLOSEWAIT2:
-	case SMC_PEERFINCLOSEWAIT:
-		if (!smc_cdc_rxed_any_close(&smc->conn))
+		if (!smc_cdc_rxed_any_close(conn))
 			break;
 		if (sock_flag(sk, SOCK_DEAD) &&
 		    smc_close_sent_any_close(conn)) {
@@ -371,9 +403,20 @@ static void smc_close_passive_work(struct work_struct *work)
 			/* just shutdown, but not yet closed locally */
 			sk->sk_state = SMC_APPFINCLOSEWAIT;
 		}
+		sock_put(sk); /* passive closing */
+		break;
+	case SMC_PEERFINCLOSEWAIT:
+		if (smc_cdc_rxed_any_close(conn)) {
+			sk->sk_state = SMC_CLOSED;
+			sock_put(sk); /* passive closing */
+		}
 		break;
 	case SMC_APPCLOSEWAIT1:
 	case SMC_APPCLOSEWAIT2:
+		/* postpone sock_put() for passive closing to cover
+		 * received SEND_SHUTDOWN as well
+		 */
+		break;
 	case SMC_APPFINCLOSEWAIT:
 	case SMC_PEERABORTWAIT:
 	case SMC_PROCESSABORT:
@@ -390,57 +433,52 @@ wakeup:
 		sk->sk_state_change(sk);
 		if ((sk->sk_state == SMC_CLOSED) &&
 		    (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) {
-			smc_conn_free(&smc->conn);
-			schedule_delayed_work(&smc->sock_put_work,
-					      SMC_CLOSE_SOCK_PUT_DELAY);
+			smc_conn_free(conn);
+			if (smc->clcsock)
+				release_clcsock = true;
 		}
 	}
-	release_sock(&smc->sk);
-}
-
-void smc_close_sock_put_work(struct work_struct *work)
-{
-	struct smc_sock *smc = container_of(to_delayed_work(work),
-					    struct smc_sock,
-					    sock_put_work);
-
-	smc->sk.sk_prot->unhash(&smc->sk);
-	sock_put(&smc->sk);
+	release_sock(sk);
+	if (release_clcsock)
+		smc_clcsock_release(smc);
+	sock_put(sk); /* sock_hold done by schedulers of close_work */
 }
 
 int smc_close_shutdown_write(struct smc_sock *smc)
 {
 	struct smc_connection *conn = &smc->conn;
-	long timeout = SMC_MAX_STREAM_WAIT_TIMEOUT;
 	struct sock *sk = &smc->sk;
 	int old_state;
+	long timeout;
 	int rc = 0;
 
-	if (sock_flag(sk, SOCK_LINGER))
-		timeout = sk->sk_lingertime;
+	timeout = current->flags & PF_EXITING ?
+		  0 : sock_flag(sk, SOCK_LINGER) ?
+		      sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT;
 
-again:
 	old_state = sk->sk_state;
-	switch (old_state) {
+again:
+	switch (sk->sk_state) {
 	case SMC_ACTIVE:
 		smc_close_stream_wait(smc, timeout);
 		release_sock(sk);
-		cancel_work_sync(&conn->tx_work);
+		cancel_delayed_work_sync(&conn->tx_work);
 		lock_sock(sk);
+		if (sk->sk_state != SMC_ACTIVE)
+			goto again;
 		/* send close wr request */
 		rc = smc_close_wr(conn);
-		if (sk->sk_state == SMC_ACTIVE)
-			sk->sk_state = SMC_PEERCLOSEWAIT1;
-		else
-			goto again;
+		sk->sk_state = SMC_PEERCLOSEWAIT1;
 		break;
 	case SMC_APPCLOSEWAIT1:
 		/* passive close */
 		if (!smc_cdc_rxed_any_close(conn))
 			smc_close_stream_wait(smc, timeout);
 		release_sock(sk);
-		cancel_work_sync(&conn->tx_work);
+		cancel_delayed_work_sync(&conn->tx_work);
 		lock_sock(sk);
+		if (sk->sk_state != SMC_APPCLOSEWAIT1)
+			goto again;
 		/* confirm close from peer */
 		rc = smc_close_wr(conn);
 		sk->sk_state = SMC_APPCLOSEWAIT2;
@@ -457,7 +495,7 @@ again:
 	}
 
 	if (old_state != sk->sk_state)
-		sk->sk_state_change(&smc->sk);
+		sk->sk_state_change(sk);
 	return rc;
 }