smc: socket closing and linkgroup cleanup

smc_shutdown() and smc_release() handling
delayed linkgroup cleanup for linkgroups without connections

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

Author: Ursula Braun

net/smc/Makefile

@@ -1,3 +1,3 @@
 obj-$(CONFIG_SMC)	+= smc.o
 smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o
-smc-y += smc_cdc.o smc_tx.o smc_rx.o
+smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o

net/smc/af_smc.c

@@ -39,6 +39,7 @@
 #include "smc_pnet.h"
 #include "smc_tx.h"
 #include "smc_rx.h"
+#include "smc_close.h"
 
 static DEFINE_MUTEX(smc_create_lgr_pending);	/* serialize link group
 						 * creation
@@ -70,14 +71,29 @@ static int smc_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 	struct smc_sock *smc;
+	int rc = 0;
 
 	if (!sk)
 		goto out;
 
 	smc = smc_sk(sk);
-	lock_sock(sk);
+	sock_hold(sk);
+	if (sk->sk_state == SMC_LISTEN)
+		/* smc_close_non_accepted() is called and acquires
+		 * sock lock for child sockets again
+		 */
+		lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
+	else
+		lock_sock(sk);
 
-	sk->sk_state = SMC_CLOSED;
+	if (smc->use_fallback) {
+		sk->sk_state = SMC_CLOSED;
+		sk->sk_state_change(sk);
+	} else {
+		rc = smc_close_active(smc);
+		sock_set_flag(sk, SOCK_DEAD);
+		sk->sk_shutdown |= SHUTDOWN_MASK;
+	}
 	if (smc->clcsock) {
 		sock_release(smc->clcsock);
 		smc->clcsock = NULL;
@@ -86,11 +102,18 @@ static int smc_release(struct socket *sock)
 	/* detach socket */
 	sock_orphan(sk);
 	sock->sk = NULL;
+	if (smc->use_fallback) {
+		schedule_delayed_work(&smc->sock_put_work, TCP_TIMEWAIT_LEN);
+	} else if (sk->sk_state == SMC_CLOSED) {
+		smc_conn_free(&smc->conn);
+		schedule_delayed_work(&smc->sock_put_work,
+				      SMC_CLOSE_SOCK_PUT_DELAY);
+	}
 	release_sock(sk);
 
 	sock_put(sk);
 out:
-	return 0;
+	return rc;
 }
 
 static void smc_destruct(struct sock *sk)
@@ -120,6 +143,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock)
 	INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work);
 	INIT_LIST_HEAD(&smc->accept_q);
 	spin_lock_init(&smc->accept_q_lock);
+	INIT_DELAYED_WORK(&smc->sock_put_work, smc_close_sock_put_work);
 	sk_refcnt_debug_inc(sk);
 
 	return sk;
@@ -417,7 +441,8 @@ static int smc_connect_rdma(struct smc_sock *smc)
 
 out_connected:
 	smc_copy_sock_settings_to_clc(smc);
-	smc->sk.sk_state = SMC_ACTIVE;
+	if (smc->sk.sk_state == SMC_INIT)
+		smc->sk.sk_state = SMC_ACTIVE;
 
 	return rc ? rc : local_contact;
 
@@ -559,8 +584,8 @@ static void smc_accept_unlink(struct sock *sk)
 /* remove a sock from the accept queue to bind it to a new socket created
  * for a socket accept call from user space
  */
-static struct sock *smc_accept_dequeue(struct sock *parent,
-				       struct socket *new_sock)
+struct sock *smc_accept_dequeue(struct sock *parent,
+				struct socket *new_sock)
 {
 	struct smc_sock *isk, *n;
 	struct sock *new_sk;
@@ -581,19 +606,34 @@ static struct sock *smc_accept_dequeue(struct sock *parent,
 }
 
 /* clean up for a created but never accepted sock */
-static void smc_close_non_accepted(struct sock *sk)
+void smc_close_non_accepted(struct sock *sk)
 {
 	struct smc_sock *smc = smc_sk(sk);
 
 	sock_hold(sk);
+	lock_sock(sk);
+	if (!sk->sk_lingertime)
+		/* wait for peer closing */
+		sk->sk_lingertime = SMC_MAX_STREAM_WAIT_TIMEOUT;
+	if (!smc->use_fallback)
+		smc_close_active(smc);
 	if (smc->clcsock) {
 		struct socket *tcp;
 
 		tcp = smc->clcsock;
 		smc->clcsock = NULL;
 		sock_release(tcp);
 	}
-	/* more closing stuff to be added with socket closing patch */
+	sock_set_flag(sk, SOCK_DEAD);
+	sk->sk_shutdown |= SHUTDOWN_MASK;
+	if (smc->use_fallback) {
+		schedule_delayed_work(&smc->sock_put_work, TCP_TIMEWAIT_LEN);
+	} else {
+		smc_conn_free(&smc->conn);
+		schedule_delayed_work(&smc->sock_put_work,
+				      SMC_CLOSE_SOCK_PUT_DELAY);
+	}
+	release_sock(sk);
 	sock_put(sk);
 }
 
@@ -761,11 +801,12 @@ static void smc_listen_work(struct work_struct *work)
 
 out_connected:
 	sk_refcnt_debug_inc(newsmcsk);
-	newsmcsk->sk_state = SMC_ACTIVE;
+	if (newsmcsk->sk_state == SMC_INIT)
+		newsmcsk->sk_state = SMC_ACTIVE;
 enqueue:
 	if (local_contact == SMC_FIRST_CONTACT)
 		mutex_unlock(&smc_create_lgr_pending);
-	lock_sock(&lsmc->sk);
+	lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
 	if (lsmc->sk.sk_state == SMC_LISTEN) {
 		smc_accept_enqueue(&lsmc->sk, newsmcsk);
 	} else { /* no longer listening */
@@ -791,6 +832,7 @@ static void smc_listen_work(struct work_struct *work)
 
 out_err:
 	newsmcsk->sk_state = SMC_CLOSED;
+	smc_conn_free(&new_smc->conn);
 	goto enqueue; /* queue new sock with sk_err set */
 }
 
@@ -911,7 +953,8 @@ static int smc_getname(struct socket *sock, struct sockaddr *addr,
 {
 	struct smc_sock *smc;
 
-	if (peer && (sock->sk->sk_state != SMC_ACTIVE))
+	if (peer && (sock->sk->sk_state != SMC_ACTIVE) &&
+	    (sock->sk->sk_state != SMC_APPCLOSEWAIT1))
 		return -ENOTCONN;
 
 	smc = smc_sk(sock->sk);
@@ -927,7 +970,9 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 
 	smc = smc_sk(sk);
 	lock_sock(sk);
-	if (sk->sk_state != SMC_ACTIVE)
+	if ((sk->sk_state != SMC_ACTIVE) &&
+	    (sk->sk_state != SMC_APPCLOSEWAIT1) &&
+	    (sk->sk_state != SMC_INIT))
 		goto out;
 	if (smc->use_fallback)
 		rc = smc->clcsock->ops->sendmsg(smc->clcsock, msg, len);
@@ -947,13 +992,21 @@ static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 	smc = smc_sk(sk);
 	lock_sock(sk);
-	if ((sk->sk_state != SMC_ACTIVE) && (sk->sk_state != SMC_CLOSED))
+	if ((sk->sk_state == SMC_INIT) ||
+	    (sk->sk_state == SMC_LISTEN) ||
+	    (sk->sk_state == SMC_CLOSED))
+		goto out;
+
+	if (sk->sk_state == SMC_PEERFINCLOSEWAIT) {
+		rc = 0;
 		goto out;
+	}
 
 	if (smc->use_fallback)
 		rc = smc->clcsock->ops->recvmsg(smc->clcsock, msg, len, flags);
 	else
 		rc = smc_rx_recvmsg(smc, msg, len, flags);
+
 out:
 	release_sock(sk);
 	return rc;
@@ -1013,15 +1066,23 @@ static unsigned int smc_poll(struct file *file, struct socket *sock,
 			mask |= smc_accept_poll(sk);
 		if (sk->sk_err)
 			mask |= POLLERR;
-		if (atomic_read(&smc->conn.sndbuf_space)) {
+		if (atomic_read(&smc->conn.sndbuf_space) ||
+		    (sk->sk_shutdown & SEND_SHUTDOWN)) {
 			mask |= POLLOUT | POLLWRNORM;
 		} else {
 			sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 			set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 		}
 		if (atomic_read(&smc->conn.bytes_to_rcv))
 			mask |= POLLIN | POLLRDNORM;
-		/* for now - to be enhanced in follow-on patch */
+		if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
+		    (sk->sk_state == SMC_CLOSED))
+			mask |= POLLHUP;
+		if (sk->sk_shutdown & RCV_SHUTDOWN)
+			mask |= POLLIN | POLLRDNORM | POLLRDHUP;
+		if (sk->sk_state == SMC_APPCLOSEWAIT1)
+			mask |= POLLIN;
+
 	}
 
 	return mask;
@@ -1032,31 +1093,53 @@ static int smc_shutdown(struct socket *sock, int how)
 	struct sock *sk = sock->sk;
 	struct smc_sock *smc;
 	int rc = -EINVAL;
+	int rc1 = 0;
 
 	smc = smc_sk(sk);
 
 	if ((how < SHUT_RD) || (how > SHUT_RDWR))
-		goto out_err;
+		return rc;
 
 	lock_sock(sk);
 
 	rc = -ENOTCONN;
-	if (sk->sk_state == SMC_CLOSED)
+	if ((sk->sk_state != SMC_LISTEN) &&
+	    (sk->sk_state != SMC_ACTIVE) &&
+	    (sk->sk_state != SMC_PEERCLOSEWAIT1) &&
+	    (sk->sk_state != SMC_PEERCLOSEWAIT2) &&
+	    (sk->sk_state != SMC_APPCLOSEWAIT1) &&
+	    (sk->sk_state != SMC_APPCLOSEWAIT2) &&
+	    (sk->sk_state != SMC_APPFINCLOSEWAIT))
 		goto out;
 	if (smc->use_fallback) {
 		rc = kernel_sock_shutdown(smc->clcsock, how);
 		sk->sk_shutdown = smc->clcsock->sk->sk_shutdown;
 		if (sk->sk_shutdown == SHUTDOWN_MASK)
 			sk->sk_state = SMC_CLOSED;
-	} else {
-		rc = sock_no_shutdown(sock, how);
+		goto out;
+	}
+	switch (how) {
+	case SHUT_RDWR:		/* shutdown in both directions */
+		rc = smc_close_active(smc);
+		break;
+	case SHUT_WR:
+		rc = smc_close_shutdown_write(smc);
+		break;
+	case SHUT_RD:
+		if (sk->sk_state == SMC_LISTEN)
+			rc = smc_close_active(smc);
+		else
+			rc = 0;
+			/* nothing more to do because peer is not involved */
+		break;
 	}
+	rc1 = kernel_sock_shutdown(smc->clcsock, how);
+	/* map sock_shutdown_cmd constants to sk_shutdown value range */
+	sk->sk_shutdown |= how + 1;
 
 out:
 	release_sock(sk);
-
-out_err:
-	return rc;
+	return rc ? rc : rc1;
 }
 
 static int smc_setsockopt(struct socket *sock, int level, int optname,

net/smc/smc.h

@@ -30,6 +30,16 @@ enum smc_state {		/* possible states of an SMC socket */
 	SMC_INIT	= 2,
 	SMC_CLOSED	= 7,
 	SMC_LISTEN	= 10,
+	/* normal close */
+	SMC_PEERCLOSEWAIT1	= 20,
+	SMC_PEERCLOSEWAIT2	= 21,
+	SMC_APPFINCLOSEWAIT	= 24,
+	SMC_APPCLOSEWAIT1	= 22,
+	SMC_APPCLOSEWAIT2	= 23,
+	SMC_PEERFINCLOSEWAIT	= 25,
+	/* abnormal close */
+	SMC_PEERABORTWAIT	= 26,
+	SMC_PROCESSABORT	= 27,
 };
 
 struct smc_link_group;
@@ -164,7 +174,13 @@ struct smc_sock {				/* smc sock container */
 	struct work_struct	smc_listen_work;/* prepare new accept socket */
 	struct list_head	accept_q;	/* sockets to be accepted */
 	spinlock_t		accept_q_lock;	/* protects accept_q */
+	struct delayed_work	sock_put_work;	/* final socket freeing */
 	bool			use_fallback;	/* fallback to tcp */
+	u8			wait_close_tx_prepared : 1;
+						/* shutdown wr or close
+						 * started, waiting for unsent
+						 * data to be sent
+						 */
 };
 
 static inline struct smc_sock *smc_sk(const struct sock *sk)
@@ -250,5 +266,7 @@ void smc_conn_free(struct smc_connection *conn);
 int smc_conn_create(struct smc_sock *smc, __be32 peer_in_addr,
 		    struct smc_ib_device *smcibdev, u8 ibport,
 		    struct smc_clc_msg_local *lcl, int srv_first_contact);
+struct sock *smc_accept_dequeue(struct sock *parent, struct socket *new_sock);
+void smc_close_non_accepted(struct sock *sk);
 
 #endif	/* __SMC_H */

net/smc/smc_cdc.c

@@ -16,6 +16,7 @@
 #include "smc_cdc.h"
 #include "smc_tx.h"
 #include "smc_rx.h"
+#include "smc_close.h"
 
 /********************************** send *************************************/
 
@@ -55,6 +56,9 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
 			       cdcpend->conn);
 	}
 	smc_tx_sndbuf_nonfull(smc);
+	if (smc->sk.sk_state != SMC_ACTIVE)
+		/* wake up smc_close_wait_tx_pends() */
+		smc->sk.sk_state_change(&smc->sk);
 	bh_unlock_sock(&smc->sk);
 }
 
@@ -149,6 +153,14 @@ void smc_cdc_tx_dismiss_slots(struct smc_connection *conn)
 				(unsigned long)conn);
 }
 
+bool smc_cdc_tx_has_pending(struct smc_connection *conn)
+{
+	struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK];
+
+	return smc_wr_tx_has_pending(link, SMC_CDC_MSG_TYPE,
+				     smc_cdc_tx_filter, (unsigned long)conn);
+}
+
 /********************************* receive ***********************************/
 
 static inline bool smc_cdc_before(u16 seq1, u16 seq2)
@@ -201,15 +213,20 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
 		smc->sk.sk_data_ready(&smc->sk);
 	}
 
-	if (conn->local_rx_ctrl.conn_state_flags.peer_conn_abort)
+	if (conn->local_rx_ctrl.conn_state_flags.peer_conn_abort) {
 		smc->sk.sk_err = ECONNRESET;
+		conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1;
+	}
 	if (smc_cdc_rxed_any_close_or_senddone(conn))
-		/* subsequent patch: terminate connection */
+		smc_close_passive_received(smc);
 
 	/* piggy backed tx info */
 	/* trigger sndbuf consumer: RDMA write into peer RMBE and CDC */
-	if (diff_cons && smc_tx_prepared_sends(conn))
+	if (diff_cons && smc_tx_prepared_sends(conn)) {
 		smc_tx_sndbuf_nonempty(conn);
+		/* trigger socket release if connection closed */
+		smc_close_wake_tx_prepared(smc);
+	}
 
 	/* subsequent patch: trigger socket release if connection closed */
 

net/smc/smc_cdc.h

@@ -212,6 +212,7 @@ void smc_cdc_tx_dismiss_slots(struct smc_connection *conn);
 int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf,
 		     struct smc_cdc_tx_pend *pend);
 int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn);
+bool smc_cdc_tx_has_pending(struct smc_connection *conn);
 int smc_cdc_init(void) __init;
 
 #endif /* SMC_CDC_H */