From: Jeff Skirvin <jeffrey.d.skirvin@xxxxxxxxx>
This change adds timeouts to the RNC suspension wait. It makes the
suspend and resume timeouts the same.
The previous resume timeout of 5 ms was too short, and timeouts were
seen in resumptions of devices in the abort task/LUN reset path - which
would receive an RNC resumed message within a tenth of a second later.
Signed-off-by: Jeff Skirvin <jeffrey.d.skirvin@xxxxxxxxx>
Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
---
drivers/scsi/isci/remote_device.c | 58 +++++++++++++++++++++++++++----
drivers/scsi/isci/remote_node_context.c | 8 ++--
2 files changed, 55 insertions(+), 11 deletions(-)
diff --git a/drivers/scsi/isci/remote_device.c b/drivers/scsi/isci/remote_device.c
index 37e9bde..be9f0e0 100644
--- a/drivers/scsi/isci/remote_device.c
+++ b/drivers/scsi/isci/remote_device.c
@@ -207,23 +207,67 @@ enum sci_status isci_remote_device_terminate_requests(
"about to wait\n",
__func__, idev, ireq, idev->started_request_count,
rnc_suspend_count, idev->rnc.suspend_count);
+
+ #define MAX_SUSPEND_MSECS 10000
if (ireq) {
/* Terminate a specific TC. */
set_bit(IREQ_NO_AUTO_FREE_TAG, &ireq->flags);
sci_remote_device_terminate_req(ihost, idev, 0, ireq);
spin_unlock_irqrestore(&ihost->scic_lock, flags);
- wait_event(ihost->eventq,
- isci_check_reqterm(ihost, idev, ireq,
- rnc_suspend_count));
+ if (!wait_event_timeout(ihost->eventq,
+ isci_check_reqterm(ihost, idev, ireq,
+ rnc_suspend_count),
+ msecs_to_jiffies(MAX_SUSPEND_MSECS))) {
+
+ dev_warn(&ihost->pdev->dev, "%s host%d timeout single\n",
+ __func__, ihost->id);
+ dev_dbg(&ihost->pdev->dev,
+ "%s: ******* Timeout waiting for "
+ "suspend; idev=%p, current state %s; "
+ "started_request_count=%d, flags=%lx\n\t"
+ "rnc_suspend_count=%d, rnc.suspend_count=%d "
+ "RNC: current state %s, current "
+ "suspend_type %x dest state %d;\n"
+ "ireq=%p, ireq->flags = %lx\n",
+ __func__, idev,
+ dev_state_name(idev->sm.current_state_id),
+ idev->started_request_count, idev->flags,
+ rnc_suspend_count, idev->rnc.suspend_count,
+ rnc_state_name(idev->rnc.sm.current_state_id),
+ idev->rnc.suspend_type,
+ idev->rnc.destination_state,
+ ireq, ireq->flags);
+ }
clear_bit(IREQ_NO_AUTO_FREE_TAG, &ireq->flags);
isci_free_tag(ihost, ireq->io_tag);
} else {
/* Terminate all TCs. */
sci_remote_device_terminate_requests(idev);
spin_unlock_irqrestore(&ihost->scic_lock, flags);
- wait_event(ihost->eventq,
- isci_check_devempty(ihost, idev,
- rnc_suspend_count));
+ if (!wait_event_timeout(ihost->eventq,
+ isci_check_devempty(ihost, idev,
+ rnc_suspend_count),
+ msecs_to_jiffies(MAX_SUSPEND_MSECS))) {
+
+ dev_warn(&ihost->pdev->dev, "%s host%d timeout all\n",
+ __func__, ihost->id);
+ dev_dbg(&ihost->pdev->dev,
+ "%s: ******* Timeout waiting for "
+ "suspend; idev=%p, current state %s; "
+ "started_request_count=%d, flags=%lx\n\t"
+ "rnc_suspend_count=%d, "
+ "RNC: current state %s, "
+ "rnc.suspend_count=%d, current "
+ "suspend_type %x dest state %d\n",
+ __func__, idev,
+ dev_state_name(idev->sm.current_state_id),
+ idev->started_request_count, idev->flags,
+ rnc_suspend_count,
+ rnc_state_name(idev->rnc.sm.current_state_id),
+ idev->rnc.suspend_count,
+ idev->rnc.suspend_type,
+ idev->rnc.destination_state);
+ }
}
dev_dbg(&ihost->pdev->dev, "%s: idev=%p, wait done\n",
__func__, idev);
@@ -1315,7 +1359,7 @@ void isci_remote_device_wait_for_resume_from_abort(
dev_dbg(scirdev_to_dev(idev), "%s: starting resume wait: %p\n",
__func__, idev);
- #define MAX_RESUME_MSECS 5
+ #define MAX_RESUME_MSECS 10000
if (!wait_event_timeout(ihost->eventq,
(!test_bit(IDEV_ABORT_PATH_RESUME_PENDING,
&idev->flags)
diff --git a/drivers/scsi/isci/remote_node_context.c b/drivers/scsi/isci/remote_node_context.c
index b698081..a0a62e3 100644
--- a/drivers/scsi/isci/remote_node_context.c
+++ b/drivers/scsi/isci/remote_node_context.c
@@ -445,7 +445,7 @@ enum sci_status sci_remote_node_context_event_handler(struct sci_remote_node_con
case SCU_EVENT_TYPE_RNC_SUSPEND_TX_RX:
/* We really dont care if the hardware is going to suspend
* the device since it's being invalidated anyway */
- dev_dbg(scirdev_to_dev(rnc_to_dev(sci_rnc)),
+ dev_warn(scirdev_to_dev(rnc_to_dev(sci_rnc)),
"%s: SCIC Remote Node Context 0x%p was "
"suspeneded by hardware while being "
"invalidated.\n", __func__, sci_rnc);
@@ -464,7 +464,7 @@ enum sci_status sci_remote_node_context_event_handler(struct sci_remote_node_con
case SCU_EVENT_TYPE_RNC_SUSPEND_TX_RX:
/* We really dont care if the hardware is going to suspend
* the device since it's being resumed anyway */
- dev_dbg(scirdev_to_dev(rnc_to_dev(sci_rnc)),
+ dev_warn(scirdev_to_dev(rnc_to_dev(sci_rnc)),
"%s: SCIC Remote Node Context 0x%p was "
"suspeneded by hardware while being resumed.\n",
__func__, sci_rnc);
@@ -568,9 +568,9 @@ enum sci_status sci_remote_node_context_suspend(
RNC_DEST_UNSPECIFIED;
dev_dbg(scirdev_to_dev(idev),
- "%s: current state %d, current suspend_type %x dest state %d,"
+ "%s: current state %s, current suspend_type %x dest state %d,"
" arg suspend_reason %d, arg suspend_type %x",
- __func__, state, sci_rnc->suspend_type,
+ __func__, rnc_state_name(state), sci_rnc->suspend_type,
sci_rnc->destination_state, suspend_reason,
suspend_type);
--
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
