[PATCH 1/1] ibmvscsi: requeue while CRQ closed

[Robert Jennings <rcj@linux.vnet.ibm.com>]

CRQ send errors that return with H_CLOSED should return with
SCSI_MLQUEUE_HOST_BUSY until firmware alerts the client of a CRQ
transport event.  The transport event will either reinitialize and
requeue the requests, or fail and return IO with DID_ERROR.

To avoid failing the eh_* functions while re-attaching to the server
adapter this will retry for a period of time while ibmvscsi_send_srp_event
returns SCSI_MLQUEUE_HOST_BUSY.

Signed-off-by: Robert Jennings <rcj@linux.vnet.ibm.com>
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>

---
 drivers/scsi/ibmvscsi/ibmvscsi.c |   59 ++++++++++++++++++++++++++++++++-------
 1 file changed, 48 insertions(+), 11 deletions(-)

Index: linux-2.6/drivers/scsi/ibmvscsi/ibmvscsi.c
===================================================================
--- linux-2.6.orig/drivers/scsi/ibmvscsi/ibmvscsi.c	2007-11-09 08:53:02.000000000 -0600
+++ linux-2.6/drivers/scsi/ibmvscsi/ibmvscsi.c	2007-11-09 08:53:36.000000000 -0600
@@ -629,6 +629,16 @@
 		list_del(&evt_struct->list);
 		del_timer(&evt_struct->timer);
 
+		/* If send_crq returns H_CLOSED, return SCSI_MLQUEUE_HOST_BUSY.
+		 * Firmware will send a CRQ with a transport event (0xFF) to
+		 * tell this client what has happened to the transport.  This
+		 * will be handled in ibmvscsi_handle_crq()
+		 */
+		if (rc == H_CLOSED) {
+			dev_warn(hostdata->dev, "send warning. "
+			         "Receive queue closed, will retry.\n");
+			goto send_busy;
+		}
 		dev_err(hostdata->dev, "send error %d\n", rc);
 		atomic_inc(&hostdata->request_limit);
 		goto send_error;
@@ -976,6 +986,7 @@
 	int rsp_rc;
 	unsigned long flags;
 	u16 lun = lun_from_dev(cmd->device);
+	unsigned long wait_switch = 0;
 
 	/* First, find this command in our sent list so we can figure
 	 * out the correct tag
@@ -1019,15 +1030,30 @@
 		    tsk_mgmt->lun, tsk_mgmt->task_tag);
 
 	evt->sync_srp = &srp_rsp;
-	init_completion(&evt->comp);
-	rsp_rc = ibmvscsi_send_srp_event(evt, hostdata, init_timeout * 2);
-	spin_unlock_irqrestore(hostdata->host->host_lock, flags);
+
+	wait_switch = jiffies + (init_timeout * HZ);
+	do {
+		init_completion(&evt->comp);
+		rsp_rc = ibmvscsi_send_srp_event(evt, hostdata, init_timeout * 2);
+
+		if (rsp_rc != SCSI_MLQUEUE_HOST_BUSY)
+			break;
+
+		spin_unlock_irqrestore(hostdata->host->host_lock, flags);
+		msleep(10);
+		spin_lock_irqsave(hostdata->host->host_lock, flags);
+	} while (time_before(jiffies, wait_switch));
+
 	if (rsp_rc != 0) {
+		free_event_struct(&found_evt->hostdata->pool, found_evt);
+		spin_unlock_irqrestore(hostdata->host->host_lock, flags);
 		sdev_printk(KERN_ERR, cmd->device,
 			    "failed to send abort() event. rc=%d\n", rsp_rc);
 		return FAILED;
 	}
 
+	spin_unlock_irqrestore(hostdata->host->host_lock, flags);
+
 	wait_for_completion(&evt->comp);
 
 	/* make sure we got a good response */
@@ -1099,6 +1125,7 @@
 	int rsp_rc;
 	unsigned long flags;
 	u16 lun = lun_from_dev(cmd->device);
+	unsigned long wait_switch = 0;
 
 	spin_lock_irqsave(hostdata->host->host_lock, flags);
 	evt = get_event_struct(&hostdata->pool);
@@ -1125,9 +1152,20 @@
 		    tsk_mgmt->lun);
 
 	evt->sync_srp = &srp_rsp;
-	init_completion(&evt->comp);
-	rsp_rc = ibmvscsi_send_srp_event(evt, hostdata, init_timeout * 2);
-	spin_unlock_irqrestore(hostdata->host->host_lock, flags);
+
+	wait_switch = jiffies + (init_timeout * HZ);
+	do {
+		init_completion(&evt->comp);
+		rsp_rc = ibmvscsi_send_srp_event(evt, hostdata, init_timeout * 2);
+		spin_unlock_irqrestore(hostdata->host->host_lock, flags);
+
+		if (rsp_rc != SCSI_MLQUEUE_HOST_BUSY)
+			break;
+
+		msleep(10);
+		spin_lock_irqsave(hostdata->host->host_lock, flags);
+	} while (time_before(jiffies, wait_switch));
+
 	if (rsp_rc != 0) {
 		sdev_printk(KERN_ERR, cmd->device,
 			    "failed to send reset event. rc=%d\n", rsp_rc);