1 files changed, 68 insertions, 68 deletions

diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 159aa8b..5ccf87e 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -506,6 +506,7 @@ static void reset_connection(struct ceph_connection *con)
 {
 	/* reset connection, out_queue, msg_ and connect_seq */
 	/* discard existing out_queue and msg_seq */
+	dout("reset_connection %p\n", con);
 	ceph_msg_remove_list(&con->out_queue);
 	ceph_msg_remove_list(&con->out_sent);
 
@@ -561,7 +562,7 @@ void ceph_con_open(struct ceph_connection *con,
 	mutex_lock(&con->mutex);
 	dout("con_open %p %s\n", con, ceph_pr_addr(&addr->in_addr));
 
-	BUG_ON(con->state != CON_STATE_CLOSED);
+	WARN_ON(con->state != CON_STATE_CLOSED);
 	con->state = CON_STATE_PREOPEN;
 
 	con->peer_name.type = (__u8) entity_type;
@@ -1506,13 +1507,6 @@ static int process_banner(struct ceph_connection *con)
 	return 0;
 }
 
-static void fail_protocol(struct ceph_connection *con)
-{
-	reset_connection(con);
-	BUG_ON(con->state != CON_STATE_NEGOTIATING);
-	con->state = CON_STATE_CLOSED;
-}
-
 static int process_connect(struct ceph_connection *con)
 {
 	u64 sup_feat = con->msgr->supported_features;
@@ -1530,7 +1524,7 @@ static int process_connect(struct ceph_connection *con)
 		       ceph_pr_addr(&con->peer_addr.in_addr),
 		       sup_feat, server_feat, server_feat & ~sup_feat);
 		con->error_msg = "missing required protocol features";
-		fail_protocol(con);
+		reset_connection(con);
 		return -1;
 
 	case CEPH_MSGR_TAG_BADPROTOVER:
@@ -1541,7 +1535,7 @@ static int process_connect(struct ceph_connection *con)
 		       le32_to_cpu(con->out_connect.protocol_version),
 		       le32_to_cpu(con->in_reply.protocol_version));
 		con->error_msg = "protocol version mismatch";
-		fail_protocol(con);
+		reset_connection(con);
 		return -1;
 
 	case CEPH_MSGR_TAG_BADAUTHORIZER:
@@ -1631,11 +1625,11 @@ static int process_connect(struct ceph_connection *con)
 			       ceph_pr_addr(&con->peer_addr.in_addr),
 			       req_feat, server_feat, req_feat & ~server_feat);
 			con->error_msg = "missing required protocol features";
-			fail_protocol(con);
+			reset_connection(con);
 			return -1;
 		}
 
-		BUG_ON(con->state != CON_STATE_NEGOTIATING);
+		WARN_ON(con->state != CON_STATE_NEGOTIATING);
 		con->state = CON_STATE_OPEN;
 
 		con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq);
@@ -2132,7 +2126,6 @@ more:
 		if (ret < 0)
 			goto out;
 
-		BUG_ON(con->state != CON_STATE_CONNECTING);
 		con->state = CON_STATE_NEGOTIATING;
 
 		/*
@@ -2160,7 +2153,7 @@ more:
 		goto more;
 	}
 
-	BUG_ON(con->state != CON_STATE_OPEN);
+	WARN_ON(con->state != CON_STATE_OPEN);
 
 	if (con->in_base_pos < 0) {
 		/*
@@ -2244,22 +2237,62 @@ bad_tag:
 
 
 /*
- * Atomically queue work on a connection.  Bump @con reference to
- * avoid races with connection teardown.
+ * Atomically queue work on a connection after the specified delay.
+ * Bump @con reference to avoid races with connection teardown.
+ * Returns 0 if work was queued, or an error code otherwise.
  */
-static void queue_con(struct ceph_connection *con)
+static int queue_con_delay(struct ceph_connection *con, unsigned long delay)
 {
 	if (!con->ops->get(con)) {
-		dout("queue_con %p ref count 0\n", con);
-		return;
+		dout("%s %p ref count 0\n", __func__, con);
+
+		return -ENOENT;
 	}
 
-	if (!queue_delayed_work(ceph_msgr_wq, &con->work, 0)) {
-		dout("queue_con %p - already queued\n", con);
+	if (!queue_delayed_work(ceph_msgr_wq, &con->work, delay)) {
+		dout("%s %p - already queued\n", __func__, con);
 		con->ops->put(con);
-	} else {
-		dout("queue_con %p\n", con);
+
+		return -EBUSY;
+	}
+
+	dout("%s %p %lu\n", __func__, con, delay);
+
+	return 0;
+}
+
+static void queue_con(struct ceph_connection *con)
+{
+	(void) queue_con_delay(con, 0);
+}
+
+static bool con_sock_closed(struct ceph_connection *con)
+{
+	if (!test_and_clear_bit(CON_FLAG_SOCK_CLOSED, &con->flags))
+		return false;
+
+#define CASE(x)								\
+	case CON_STATE_ ## x:						\
+		con->error_msg = "socket closed (con state " #x ")";	\
+		break;
+
+	switch (con->state) {
+	CASE(CLOSED);
+	CASE(PREOPEN);
+	CASE(CONNECTING);
+	CASE(NEGOTIATING);
+	CASE(OPEN);
+	CASE(STANDBY);
+	default:
+		pr_warning("%s con %p unrecognized state %lu\n",
+			__func__, con, con->state);
+		con->error_msg = "unrecognized con state";
+		BUG();
+		break;
 	}
+#undef CASE
+
+	return true;
 }
 
 /*
@@ -2273,37 +2306,19 @@ static void con_work(struct work_struct *work)
 
 	mutex_lock(&con->mutex);
 restart:
-	if (test_and_clear_bit(CON_FLAG_SOCK_CLOSED, &con->flags)) {
-		switch (con->state) {
-		case CON_STATE_CONNECTING:
-			con->error_msg = "connection failed";
-			break;
-		case CON_STATE_NEGOTIATING:
-			con->error_msg = "negotiation failed";
-			break;
-		case CON_STATE_OPEN:
-			con->error_msg = "socket closed";
-			break;
-		default:
-			dout("unrecognized con state %d\n", (int)con->state);
-			con->error_msg = "unrecognized con state";
-			BUG();
-		}
+	if (con_sock_closed(con))
 		goto fault;
-	}
 
 	if (test_and_clear_bit(CON_FLAG_BACKOFF, &con->flags)) {
 		dout("con_work %p backing off\n", con);
-		if (queue_delayed_work(ceph_msgr_wq, &con->work,
-				       round_jiffies_relative(con->delay))) {
-			dout("con_work %p backoff %lu\n", con, con->delay);
-			mutex_unlock(&con->mutex);
-			return;
-		} else {
-			con->ops->put(con);
+		ret = queue_con_delay(con, round_jiffies_relative(con->delay));
+		if (ret) {
 			dout("con_work %p FAILED to back off %lu\n", con,
 			     con->delay);
+			BUG_ON(ret == -ENOENT);
+			set_bit(CON_FLAG_BACKOFF, &con->flags);
 		}
+		goto done;
 	}
 
 	if (con->state == CON_STATE_STANDBY) {
@@ -2355,12 +2370,12 @@ fault:
 static void ceph_fault(struct ceph_connection *con)
 	__releases(con->mutex)
 {
-	pr_err("%s%lld %s %s\n", ENTITY_NAME(con->peer_name),
+	pr_warning("%s%lld %s %s\n", ENTITY_NAME(con->peer_name),
 	       ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg);
 	dout("fault %p state %lu to peer %s\n",
 	     con, con->state, ceph_pr_addr(&con->peer_addr.in_addr));
 
-	BUG_ON(con->state != CON_STATE_CONNECTING &&
+	WARN_ON(con->state != CON_STATE_CONNECTING &&
 	       con->state != CON_STATE_NEGOTIATING &&
 	       con->state != CON_STATE_OPEN);
 
@@ -2397,24 +2412,8 @@ static void ceph_fault(struct ceph_connection *con)
 			con->delay = BASE_DELAY_INTERVAL;
 		else if (con->delay < MAX_DELAY_INTERVAL)
 			con->delay *= 2;
-		con->ops->get(con);
-		if (queue_delayed_work(ceph_msgr_wq, &con->work,
-				       round_jiffies_relative(con->delay))) {
-			dout("fault queued %p delay %lu\n", con, con->delay);
-		} else {
-			con->ops->put(con);
-			dout("fault failed to queue %p delay %lu, backoff\n",
-			     con, con->delay);
-			/*
-			 * In many cases we see a socket state change
-			 * while con_work is running and end up
-			 * queuing (non-delayed) work, such that we
-			 * can't backoff with a delay.  Set a flag so
-			 * that when con_work restarts we schedule the
-			 * delay then.
-			 */
-			set_bit(CON_FLAG_BACKOFF, &con->flags);
-		}
+		set_bit(CON_FLAG_BACKOFF, &con->flags);
+		queue_con(con);
 	}
 
 out_unlock:
@@ -2749,7 +2748,8 @@ static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip)
 		msg = con->ops->alloc_msg(con, hdr, skip);
 		mutex_lock(&con->mutex);
 		if (con->state != CON_STATE_OPEN) {
-			ceph_msg_put(msg);
+			if (msg)
+				ceph_msg_put(msg);
 			return -EAGAIN;
 		}
 		con->in_msg = msg;