During hot-plugging of a disk(having a flaky link) the disk addition
stops and any further disk addition or removal doesn't happen on that controller.
This is because, when driver receives DELAY_NOT_RESPONDING for a disk when it is undergoing
addition in the SCSI Mid layer, the driver would block the I/O to that disk
resulting in a deadlock. i.e the disk addition work couldn't be completed
as it can't send any I/O to the disk as I/Os are blocked. Any device removal (TARGET_NOT_RESPONDING)
or link update(RC_PHY_CHANGED) couldn't be processed as they are in the queue
to get processed after disk addition.
Description of Change:
To handle such cases, unblock the I/Os to the disk in ISR context if the disk is undergoing
addition. The I/Os would get unblocked only if the driver receives RC_PHY_CHANGED reason
code when the device addition is within the SAS Transport layer.
An module parameter 'unblock_io' is introduced which needs to be set to have this
functionality enabled. By default this functionality is disabled.
Signed-off-by: Sreekanth Reddy <[email protected]>
---
drivers/scsi/mpt2sas/mpt2sas_base.h | 3 +
drivers/scsi/mpt2sas/mpt2sas_scsih.c | 67 ++++++++++++++++++++++++++---
drivers/scsi/mpt2sas/mpt2sas_transport.c | 13 ++++++
3 files changed, 76 insertions(+), 7 deletions(-)
diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.h b/drivers/scsi/mpt2sas/mpt2sas_base.h
index 32181a6..7de7ba4 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_base.h
+++ b/drivers/scsi/mpt2sas/mpt2sas_base.h
@@ -356,6 +356,8 @@ struct _internal_cmd {
* @phy: phy identifier provided in sas device page 0
* @responding: used in _scsih_sas_device_mark_responding
* @pfa_led_on: flag for PFA LED status
+ * @pend_sas_rphy_add: flag to check if device is in sas_rphy_add()
+ * addition routine
*/
struct _sas_device {
struct list_head list;
@@ -375,6 +377,7 @@ struct _sas_device {
u8 phy;
u8 responding;
u8 pfa_led_on;
+ u8 pend_sas_rphy_add;
};
/**
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
index 4a0728a..b08d8fd 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
@@ -105,6 +105,11 @@ static int missing_delay[2] = {-1, -1};
module_param_array(missing_delay, int, NULL, 0);
MODULE_PARM_DESC(missing_delay, " device missing delay , io missing delay");
+static int unblock_io;
+module_param(unblock_io, int, 0);
+MODULE_PARM_DESC(unblock_io,
+"unblocks I/O if set to 1 when device is undergoing addition (default=0)");
+
/* scsi-mid layer global parmeter is max_report_luns, which is 511 */
#define MPT2SAS_MAX_LUN (16895)
static int max_lun = MPT2SAS_MAX_LUN;
@@ -2972,6 +2977,34 @@ _scsih_ublock_io_device(struct MPT2SAS_ADAPTER *ioc, u64 sas_address)
}
/**
+ * _scsih_ublock_io_device_to_running - set the device state to SDEV_RUNNING
+ * @ioc: per adapter object
+ * @sas_addr: sas address
+ *
+ * unblock the device to receive IO during device addition. Device
+ * responsiveness is not checked before unblocking
+ */
+static void
+_scsih_ublock_io_device_to_running(struct MPT2SAS_ADAPTER *ioc, u64 sas_address)
+{
+ struct MPT2SAS_DEVICE *sas_device_priv_data;
+ struct scsi_device *sdev;
+
+ shost_for_each_device(sdev, ioc->shost) {
+ sas_device_priv_data = sdev->hostdata;
+ if (!sas_device_priv_data)
+ continue;
+ if (sas_device_priv_data->sas_target->sas_address
+ != sas_address)
+ continue;
+ if (sas_device_priv_data->block) {
+ sas_device_priv_data->block = 0;
+ scsi_internal_device_unblock(sdev, SDEV_RUNNING);
+ }
+ }
+}
+
+/**
* _scsih_block_io_all_device - set the device state to SDEV_BLOCK
* @ioc: per adapter object
* @handle: device handle
@@ -3081,21 +3114,23 @@ _scsih_block_io_to_children_attached_to_ex(struct MPT2SAS_ADAPTER *ioc,
}
/**
- * _scsih_block_io_to_children_attached_directly
+ * _scsih_handle_io_to_children_attached_directly
* @ioc: per adapter object
* @event_data: topology change event data
*
- * This routine set sdev state to SDEV_BLOCK for all devices
- * direct attached during device pull.
+ * This routine set sdev state to SDEV_BLOCK or SDEV_RUNNING for all devices
+ * direct attached during device pull/reconnect.
*/
static void
-_scsih_block_io_to_children_attached_directly(struct MPT2SAS_ADAPTER *ioc,
- Mpi2EventDataSasTopologyChangeList_t *event_data)
+_scsih_handle_io_to_children_attached_directly(struct MPT2SAS_ADAPTER *ioc,
+ Mpi2EventDataSasTopologyChangeList_t *event_data)
{
int i;
u16 handle;
u16 reason_code;
u8 phy_number;
+ struct _sas_device *sas_device;
+ u8 link_rate, prev_link_rate;
for (i = 0; i < event_data->NumEntries; i++) {
handle = le16_to_cpu(event_data->PHY[i].AttachedDevHandle);
@@ -3106,6 +3141,24 @@ _scsih_block_io_to_children_attached_directly(struct MPT2SAS_ADAPTER *ioc,
MPI2_EVENT_SAS_TOPO_RC_MASK;
if (reason_code == MPI2_EVENT_SAS_TOPO_RC_DELAY_NOT_RESPONDING)
_scsih_block_io_device(ioc, handle);
+ else if ((reason_code == MPI2_EVENT_SAS_TOPO_RC_PHY_CHANGED) &&
+ (unblock_io == 1)) {
+ /* unblock only if device is in the process of addition
+ * within the SCSI Mid Layer (sas_rphy_add) to prevent
+ * deadlock. Unblocking in other cases can lead to data
+ * corruption */
+
+ link_rate = event_data->PHY[i].LinkRate >> 4;
+ prev_link_rate = event_data->PHY[i].LinkRate & 0xF;
+ sas_device = _scsih_sas_device_find_by_handle(ioc,
+ handle);
+ if (!sas_device)
+ continue;
+ if ((link_rate > prev_link_rate) &&
+ (sas_device->pend_sas_rphy_add == 1))
+ _scsih_ublock_io_device_to_running(ioc,
+ sas_device->sas_address);
+ }
}
}
@@ -3497,7 +3550,7 @@ _scsih_check_topo_delete_events(struct MPT2SAS_ADAPTER *ioc,
expander_handle = le16_to_cpu(event_data->ExpanderDevHandle);
if (expander_handle < ioc->sas_hba.num_phys) {
- _scsih_block_io_to_children_attached_directly(ioc, event_data);
+ _scsih_handle_io_to_children_attached_directly(ioc, event_data);
return;
}
if (event_data->ExpStatus ==
@@ -3515,7 +3568,7 @@ _scsih_check_topo_delete_events(struct MPT2SAS_ADAPTER *ioc,
_scsih_block_io_device(ioc, handle);
} while (test_and_clear_bit(handle, ioc->blocking_handles));
} else if (event_data->ExpStatus == MPI2_EVENT_SAS_TOPO_ES_RESPONDING)
- _scsih_block_io_to_children_attached_directly(ioc, event_data);
+ _scsih_handle_io_to_children_attached_directly(ioc, event_data);
if (event_data->ExpStatus != MPI2_EVENT_SAS_TOPO_ES_NOT_RESPONDING)
return;
diff --git a/drivers/scsi/mpt2sas/mpt2sas_transport.c b/drivers/scsi/mpt2sas/mpt2sas_transport.c
index 0d1d064..f09f5f3 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_transport.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_transport.c
@@ -654,6 +654,7 @@ mpt2sas_transport_port_add(struct MPT2SAS_ADAPTER *ioc, u16 handle,
unsigned long flags;
struct _sas_node *sas_node;
struct sas_rphy *rphy;
+ struct _sas_device *sas_device = NULL;
int i;
struct sas_port *port;
@@ -736,10 +737,22 @@ mpt2sas_transport_port_add(struct MPT2SAS_ADAPTER *ioc, u16 handle,
mpt2sas_port->remote_identify.device_type);
rphy->identify = mpt2sas_port->remote_identify;
+ if (mpt2sas_port->remote_identify.device_type == SAS_END_DEVICE) {
+ sas_device = mpt2sas_scsih_sas_device_find_by_sas_address(ioc,
+ mpt2sas_port->remote_identify.sas_address);
+ if (!sas_device) {
+ printk(MPT2SAS_ERR_FMT "failure at %s:%d/%s()!\n",
+ ioc->name, __FILE__, __LINE__, __func__);
+ goto out_fail;
+ }
+ sas_device->pend_sas_rphy_add = 1;
+ }
if ((sas_rphy_add(rphy))) {
printk(MPT2SAS_ERR_FMT "failure at %s:%d/%s()!\n",
ioc->name, __FILE__, __LINE__, __func__);
}
+ if (mpt2sas_port->remote_identify.device_type == SAS_END_DEVICE)
+ sas_device->pend_sas_rphy_add = 0;
if ((ioc->logging_level & MPT_DEBUG_TRANSPORT))
dev_printk(KERN_INFO, &rphy->dev, "add: handle(0x%04x), "
"sas_addr(0x%016llx)\n", handle,
--
1.7.1