scsi: ibmvfc: Send Cancel MAD down each hw SCSI channel

In general the client needs to send Cancel MADs and task management
commands down the same channel as the command(s) intended to cancel or
abort. The client assigns cancel keys per LUN and thus must send a Cancel
down each channel commands were submitted for that LUN. Further, the client
then must wait for those cancel completions prior to submitting a LUN RESET
or ABORT TASK SET.

Add a cancel rsp iu syncronization field to the ibmvfc_queue struct such
that the cancel routine can sync the cancel response to each queue that
requires a cancel command. Build a list of each cancel event sent and wait
for the completion of each submitted cancel.

Link: https://lore.kernel.org/r/20210114203148.246656-19-tyreld@linux.ibm.com
Reviewed-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: Tyrel Datwyler <tyreld@linux.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

2 files changed, 100 insertions, 12 deletions

diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index fba2556af1da..fc94665ead68 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -2418,18 +2418,82 @@ static struct ibmvfc_event *ibmvfc_init_tmf(struct ibmvfc_queue *queue,
 	return evt;
 }
 
-/**
- * ibmvfc_cancel_all - Cancel all outstanding commands to the device
- * @sdev:	scsi device to cancel commands
- * @type:	type of error recovery being performed
- *
- * This sends a cancel to the VIOS for the specified device. This does
- * NOT send any abort to the actual device. That must be done separately.
- *
- * Returns:
- *	0 on success / other on failure
- **/
-static int ibmvfc_cancel_all(struct scsi_device *sdev, int type)
+static int ibmvfc_cancel_all_mq(struct scsi_device *sdev, int type)
+{
+	struct ibmvfc_host *vhost = shost_priv(sdev->host);
+	struct ibmvfc_event *evt, *found_evt, *temp;
+	struct ibmvfc_queue *queues = vhost->scsi_scrqs.scrqs;
+	unsigned long flags;
+	int num_hwq, i;
+	int fail = 0;
+	LIST_HEAD(cancelq);
+	u16 status;
+
+	ENTER;
+	spin_lock_irqsave(vhost->host->host_lock, flags);
+	num_hwq = vhost->scsi_scrqs.active_queues;
+	for (i = 0; i < num_hwq; i++) {
+		spin_lock(queues[i].q_lock);
+		spin_lock(&queues[i].l_lock);
+		found_evt = NULL;
+		list_for_each_entry(evt, &queues[i].sent, queue_list) {
+			if (evt->cmnd && evt->cmnd->device == sdev) {
+				found_evt = evt;
+				break;
+			}
+		}
+		spin_unlock(&queues[i].l_lock);
+
+		if (found_evt && vhost->logged_in) {
+			evt = ibmvfc_init_tmf(&queues[i], sdev, type);
+			evt->sync_iu = &queues[i].cancel_rsp;
+			ibmvfc_send_event(evt, vhost, default_timeout);
+			list_add_tail(&evt->cancel, &cancelq);
+		}
+
+		spin_unlock(queues[i].q_lock);
+	}
+	spin_unlock_irqrestore(vhost->host->host_lock, flags);
+
+	if (list_empty(&cancelq)) {
+		if (vhost->log_level > IBMVFC_DEFAULT_LOG_LEVEL)
+			sdev_printk(KERN_INFO, sdev, "No events found to cancel\n");
+		return 0;
+	}
+
+	sdev_printk(KERN_INFO, sdev, "Cancelling outstanding commands.\n");
+
+	list_for_each_entry_safe(evt, temp, &cancelq, cancel) {
+		wait_for_completion(&evt->comp);
+		status = be16_to_cpu(evt->queue->cancel_rsp.mad_common.status);
+		list_del(&evt->cancel);
+		ibmvfc_free_event(evt);
+
+		if (status != IBMVFC_MAD_SUCCESS) {
+			sdev_printk(KERN_WARNING, sdev, "Cancel failed with rc=%x\n", status);
+			switch (status) {
+			case IBMVFC_MAD_DRIVER_FAILED:
+			case IBMVFC_MAD_CRQ_ERROR:
+			/* Host adapter most likely going through reset, return success to
+			 * the caller will wait for the command being cancelled to get returned
+			 */
+				break;
+			default:
+				fail = 1;
+				break;
+			}
+		}
+	}
+
+	if (fail)
+		return -EIO;
+
+	sdev_printk(KERN_INFO, sdev, "Successfully cancelled outstanding commands\n");
+	LEAVE;
+	return 0;
+}
+
+static int ibmvfc_cancel_all_sq(struct scsi_device *sdev, int type)
 {
 	struct ibmvfc_host *vhost = shost_priv(sdev->host);
 	struct ibmvfc_event *evt, *found_evt;
@@ -2499,6 +2563,27 @@ static int ibmvfc_cancel_all(struct scsi_device *sdev, int type)
 }
 
 /**
+ * ibmvfc_cancel_all - Cancel all outstanding commands to the device
+ * @sdev:	scsi device to cancel commands
+ * @type:	type of error recovery being performed
+ *
+ * This sends a cancel to the VIOS for the specified device. This does
+ * NOT send any abort to the actual device. That must be done separately.
+ *
+ * Returns:
+ *	0 on success / other on failure
+ **/
+static int ibmvfc_cancel_all(struct scsi_device *sdev, int type)
+{
+	struct ibmvfc_host *vhost = shost_priv(sdev->host);
+
+	if (vhost->mq_enabled && vhost->using_channels)
+		return ibmvfc_cancel_all_mq(sdev, type);
+	else
+		return ibmvfc_cancel_all_sq(sdev, type);
+}
+
+/**
  * ibmvfc_match_key - Match function for specified cancel key
  * @evt:	ibmvfc event struct
  * @key:	cancel key to match
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.h b/drivers/scsi/ibmvscsi/ibmvfc.h
index 2dbce7071409..c3bb83c9d8a6 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.h
+++ b/drivers/scsi/ibmvscsi/ibmvfc.h
@@ -737,6 +737,7 @@ struct ibmvfc_target {
 /* a unit of work for the hosting partition */
 struct ibmvfc_event {
 	struct list_head queue_list;
+	struct list_head cancel;
 	struct ibmvfc_host *vhost;
 	struct ibmvfc_queue *queue;
 	struct ibmvfc_target *tgt;
@@ -790,6 +791,8 @@ struct ibmvfc_queue {
 	struct list_head free;
 	spinlock_t l_lock;
 
+	union ibmvfc_iu cancel_rsp;
+
 	/* Sub-CRQ fields */
 	struct ibmvfc_host *vhost;
 	unsigned long cookie;