Add the rt linux 4.1.3-rt3 as base

Import the rt linux 4.1.3-rt3 as OPNFV kvm base.

It's from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git linux-4.1.y-rt and
the base is:

commit 0917f823c59692d751951bf5ea699a2d1e2f26a2
Author: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date:   Sat Jul 25 12:13:34 2015 +0200

    Prepare v4.1.3-rt3

    Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

We lose all the git history this way and it's not good. We
should apply another opnfv project repo in future.

Change-Id: I87543d81c9df70d99c5001fbdf646b202c19f423
Signed-off-by: Yunhong Jiang <yunhong.jiang@intel.com>

7 files changed, 3636 insertions, 0 deletions

diff --git a/kernel/drivers/scsi/device_handler/Kconfig b/kernel/drivers/scsi/device_handler/Kconfig
new file mode 100644
index 000000000..69abd0ad4
--- /dev/null
+++ b/kernel/drivers/scsi/device_handler/Kconfig
@@ -0,0 +1,40 @@
+#
+# SCSI Device Handler configuration
+#
+
+menuconfig SCSI_DH
+	tristate "SCSI Device Handlers"
+	depends on SCSI
+	default n
+	help
+	  SCSI Device Handlers provide device specific support for
+	  devices utilized in multipath configurations. Say Y here to
+	  select support for specific hardware.
+
+config SCSI_DH_RDAC
+	tristate "LSI RDAC Device Handler"
+	depends on SCSI_DH
+	help
+	If you have a LSI RDAC select y. Otherwise, say N.
+
+config SCSI_DH_HP_SW
+	tristate "HP/COMPAQ MSA Device Handler"
+	depends on SCSI_DH
+	help
+	If you have a HP/COMPAQ MSA device that requires START_STOP to
+	be sent to start it and cannot upgrade the firmware then select y.
+	Otherwise, say N.
+
+config SCSI_DH_EMC
+	tristate "EMC CLARiiON Device Handler"
+	depends on SCSI_DH
+	help
+	If you have a EMC CLARiiON select y. Otherwise, say N.
+
+config SCSI_DH_ALUA
+	tristate "SPC-3 ALUA Device Handler"
+	depends on SCSI_DH
+	help
+	  SCSI Device handler for generic SPC-3 Asymmetric Logical Unit
+	  Access (ALUA).
+
diff --git a/kernel/drivers/scsi/device_handler/Makefile b/kernel/drivers/scsi/device_handler/Makefile
new file mode 100644
index 000000000..e1d2ea083
--- /dev/null
+++ b/kernel/drivers/scsi/device_handler/Makefile
@@ -0,0 +1,8 @@
+#
+# SCSI Device Handler
+#
+obj-$(CONFIG_SCSI_DH)		+= scsi_dh.o
+obj-$(CONFIG_SCSI_DH_RDAC)	+= scsi_dh_rdac.o
+obj-$(CONFIG_SCSI_DH_HP_SW)	+= scsi_dh_hp_sw.o
+obj-$(CONFIG_SCSI_DH_EMC)	+= scsi_dh_emc.o
+obj-$(CONFIG_SCSI_DH_ALUA)	+= scsi_dh_alua.o
diff --git a/kernel/drivers/scsi/device_handler/scsi_dh.c b/kernel/drivers/scsi/device_handler/scsi_dh.c
new file mode 100644
index 000000000..1efebc9ee
--- /dev/null
+++ b/kernel/drivers/scsi/device_handler/scsi_dh.c
@@ -0,0 +1,621 @@
+/*
+ * SCSI device handler infrastruture.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright IBM Corporation, 2007
+ *      Authors:
+ *               Chandra Seetharaman <sekharan@us.ibm.com>
+ *               Mike Anderson <andmike@linux.vnet.ibm.com>
+ */
+
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <scsi/scsi_dh.h>
+#include "../scsi_priv.h"
+
+static DEFINE_SPINLOCK(list_lock);
+static LIST_HEAD(scsi_dh_list);
+
+static struct scsi_device_handler *get_device_handler(const char *name)
+{
+	struct scsi_device_handler *tmp, *found = NULL;
+
+	spin_lock(&list_lock);
+	list_for_each_entry(tmp, &scsi_dh_list, list) {
+		if (!strncmp(tmp->name, name, strlen(tmp->name))) {
+			found = tmp;
+			break;
+		}
+	}
+	spin_unlock(&list_lock);
+	return found;
+}
+
+/*
+ * device_handler_match_function - Match a device handler to a device
+ * @sdev - SCSI device to be tested
+ *
+ * Tests @sdev against the match function of all registered device_handler.
+ * Returns the found device handler or NULL if not found.
+ */
+static struct scsi_device_handler *
+device_handler_match_function(struct scsi_device *sdev)
+{
+	struct scsi_device_handler *tmp_dh, *found_dh = NULL;
+
+	spin_lock(&list_lock);
+	list_for_each_entry(tmp_dh, &scsi_dh_list, list) {
+		if (tmp_dh->match && tmp_dh->match(sdev)) {
+			found_dh = tmp_dh;
+			break;
+		}
+	}
+	spin_unlock(&list_lock);
+	return found_dh;
+}
+
+/*
+ * device_handler_match - Attach a device handler to a device
+ * @scsi_dh - The device handler to match against or NULL
+ * @sdev - SCSI device to be tested against @scsi_dh
+ *
+ * Tests @sdev against the device handler @scsi_dh or against
+ * all registered device_handler if @scsi_dh == NULL.
+ * Returns the found device handler or NULL if not found.
+ */
+static struct scsi_device_handler *
+device_handler_match(struct scsi_device_handler *scsi_dh,
+		     struct scsi_device *sdev)
+{
+	struct scsi_device_handler *found_dh;
+
+	found_dh = device_handler_match_function(sdev);
+
+	if (scsi_dh && found_dh != scsi_dh)
+		found_dh = NULL;
+
+	return found_dh;
+}
+
+/*
+ * scsi_dh_handler_attach - Attach a device handler to a device
+ * @sdev - SCSI device the device handler should attach to
+ * @scsi_dh - The device handler to attach
+ */
+static int scsi_dh_handler_attach(struct scsi_device *sdev,
+				  struct scsi_device_handler *scsi_dh)
+{
+	struct scsi_dh_data *d;
+
+	if (sdev->scsi_dh_data) {
+		if (sdev->scsi_dh_data->scsi_dh != scsi_dh)
+			return -EBUSY;
+
+		kref_get(&sdev->scsi_dh_data->kref);
+		return 0;
+	}
+
+	if (!try_module_get(scsi_dh->module))
+		return -EINVAL;
+
+	d = scsi_dh->attach(sdev);
+	if (IS_ERR(d)) {
+		sdev_printk(KERN_ERR, sdev, "%s: Attach failed (%ld)\n",
+			    scsi_dh->name, PTR_ERR(d));
+		module_put(scsi_dh->module);
+		return PTR_ERR(d);
+	}
+
+	d->scsi_dh = scsi_dh;
+	kref_init(&d->kref);
+	d->sdev = sdev;
+
+	spin_lock_irq(sdev->request_queue->queue_lock);
+	sdev->scsi_dh_data = d;
+	spin_unlock_irq(sdev->request_queue->queue_lock);
+	return 0;
+}
+
+static void __detach_handler (struct kref *kref)
+{
+	struct scsi_dh_data *scsi_dh_data =
+		container_of(kref, struct scsi_dh_data, kref);
+	struct scsi_device_handler *scsi_dh = scsi_dh_data->scsi_dh;
+	struct scsi_device *sdev = scsi_dh_data->sdev;
+
+	scsi_dh->detach(sdev);
+
+	spin_lock_irq(sdev->request_queue->queue_lock);
+	sdev->scsi_dh_data = NULL;
+	spin_unlock_irq(sdev->request_queue->queue_lock);
+
+	sdev_printk(KERN_NOTICE, sdev, "%s: Detached\n", scsi_dh->name);
+	module_put(scsi_dh->module);
+}
+
+/*
+ * scsi_dh_handler_detach - Detach a device handler from a device
+ * @sdev - SCSI device the device handler should be detached from
+ * @scsi_dh - Device handler to be detached
+ *
+ * Detach from a device handler. If a device handler is specified,
+ * only detach if the currently attached handler matches @scsi_dh.
+ */
+static void scsi_dh_handler_detach(struct scsi_device *sdev,
+				   struct scsi_device_handler *scsi_dh)
+{
+	if (!sdev->scsi_dh_data)
+		return;
+
+	if (scsi_dh && scsi_dh != sdev->scsi_dh_data->scsi_dh)
+		return;
+
+	if (!scsi_dh)
+		scsi_dh = sdev->scsi_dh_data->scsi_dh;
+
+	if (scsi_dh)
+		kref_put(&sdev->scsi_dh_data->kref, __detach_handler);
+}
+
+/*
+ * Functions for sysfs attribute 'dh_state'
+ */
+static ssize_t
+store_dh_state(struct device *dev, struct device_attribute *attr,
+	       const char *buf, size_t count)
+{
+	struct scsi_device *sdev = to_scsi_device(dev);
+	struct scsi_device_handler *scsi_dh;
+	int err = -EINVAL;
+
+	if (sdev->sdev_state == SDEV_CANCEL ||
+	    sdev->sdev_state == SDEV_DEL)
+		return -ENODEV;
+
+	if (!sdev->scsi_dh_data) {
+		/*
+		 * Attach to a device handler
+		 */
+		if (!(scsi_dh = get_device_handler(buf)))
+			return err;
+		err = scsi_dh_handler_attach(sdev, scsi_dh);
+	} else {
+		scsi_dh = sdev->scsi_dh_data->scsi_dh;
+		if (!strncmp(buf, "detach", 6)) {
+			/*
+			 * Detach from a device handler
+			 */
+			scsi_dh_handler_detach(sdev, scsi_dh);
+			err = 0;
+		} else if (!strncmp(buf, "activate", 8)) {
+			/*
+			 * Activate a device handler
+			 */
+			if (scsi_dh->activate)
+				err = scsi_dh->activate(sdev, NULL, NULL);
+			else
+				err = 0;
+		}
+	}
+
+	return err<0?err:count;
+}
+
+static ssize_t
+show_dh_state(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct scsi_device *sdev = to_scsi_device(dev);
+
+	if (!sdev->scsi_dh_data)
+		return snprintf(buf, 20, "detached\n");
+
+	return snprintf(buf, 20, "%s\n", sdev->scsi_dh_data->scsi_dh->name);
+}
+
+static struct device_attribute scsi_dh_state_attr =
+	__ATTR(dh_state, S_IRUGO | S_IWUSR, show_dh_state,
+	       store_dh_state);
+
+/*
+ * scsi_dh_sysfs_attr_add - Callback for scsi_init_dh
+ */
+static int scsi_dh_sysfs_attr_add(struct device *dev, void *data)
+{
+	struct scsi_device *sdev;
+	int err;
+
+	if (!scsi_is_sdev_device(dev))
+		return 0;
+
+	sdev = to_scsi_device(dev);
+
+	err = device_create_file(&sdev->sdev_gendev,
+				 &scsi_dh_state_attr);
+
+	return 0;
+}
+
+/*
+ * scsi_dh_sysfs_attr_remove - Callback for scsi_exit_dh
+ */
+static int scsi_dh_sysfs_attr_remove(struct device *dev, void *data)
+{
+	struct scsi_device *sdev;
+
+	if (!scsi_is_sdev_device(dev))
+		return 0;
+
+	sdev = to_scsi_device(dev);
+
+	device_remove_file(&sdev->sdev_gendev,
+			   &scsi_dh_state_attr);
+
+	return 0;
+}
+
+/*
+ * scsi_dh_notifier - notifier chain callback
+ */
+static int scsi_dh_notifier(struct notifier_block *nb,
+			    unsigned long action, void *data)
+{
+	struct device *dev = data;
+	struct scsi_device *sdev;
+	int err = 0;
+	struct scsi_device_handler *devinfo = NULL;
+
+	if (!scsi_is_sdev_device(dev))
+		return 0;
+
+	sdev = to_scsi_device(dev);
+
+	if (action == BUS_NOTIFY_ADD_DEVICE) {
+		err = device_create_file(dev, &scsi_dh_state_attr);
+		/* don't care about err */
+		devinfo = device_handler_match(NULL, sdev);
+		if (devinfo)
+			err = scsi_dh_handler_attach(sdev, devinfo);
+	} else if (action == BUS_NOTIFY_DEL_DEVICE) {
+		device_remove_file(dev, &scsi_dh_state_attr);
+		scsi_dh_handler_detach(sdev, NULL);
+	}
+	return err;
+}
+
+/*
+ * scsi_dh_notifier_add - Callback for scsi_register_device_handler
+ */
+static int scsi_dh_notifier_add(struct device *dev, void *data)
+{
+	struct scsi_device_handler *scsi_dh = data;
+	struct scsi_device *sdev;
+
+	if (!scsi_is_sdev_device(dev))
+		return 0;
+
+	if (!get_device(dev))
+		return 0;
+
+	sdev = to_scsi_device(dev);
+
+	if (device_handler_match(scsi_dh, sdev))
+		scsi_dh_handler_attach(sdev, scsi_dh);
+
+	put_device(dev);
+
+	return 0;
+}
+
+/*
+ * scsi_dh_notifier_remove - Callback for scsi_unregister_device_handler
+ */
+static int scsi_dh_notifier_remove(struct device *dev, void *data)
+{
+	struct scsi_device_handler *scsi_dh = data;
+	struct scsi_device *sdev;
+
+	if (!scsi_is_sdev_device(dev))
+		return 0;
+
+	if (!get_device(dev))
+		return 0;
+
+	sdev = to_scsi_device(dev);
+
+	scsi_dh_handler_detach(sdev, scsi_dh);
+
+	put_device(dev);
+
+	return 0;
+}
+
+/*
+ * scsi_register_device_handler - register a device handler personality
+ *      module.
+ * @scsi_dh - device handler to be registered.
+ *
+ * Returns 0 on success, -EBUSY if handler already registered.
+ */
+int scsi_register_device_handler(struct scsi_device_handler *scsi_dh)
+{
+
+	if (get_device_handler(scsi_dh->name))
+		return -EBUSY;
+
+	if (!scsi_dh->attach || !scsi_dh->detach)
+		return -EINVAL;
+
+	spin_lock(&list_lock);
+	list_add(&scsi_dh->list, &scsi_dh_list);
+	spin_unlock(&list_lock);
+
+	bus_for_each_dev(&scsi_bus_type, NULL, scsi_dh, scsi_dh_notifier_add);
+	printk(KERN_INFO "%s: device handler registered\n", scsi_dh->name);
+
+	return SCSI_DH_OK;
+}
+EXPORT_SYMBOL_GPL(scsi_register_device_handler);
+
+/*
+ * scsi_unregister_device_handler - register a device handler personality
+ *      module.
+ * @scsi_dh - device handler to be unregistered.
+ *
+ * Returns 0 on success, -ENODEV if handler not registered.
+ */
+int scsi_unregister_device_handler(struct scsi_device_handler *scsi_dh)
+{
+
+	if (!get_device_handler(scsi_dh->name))
+		return -ENODEV;
+
+	bus_for_each_dev(&scsi_bus_type, NULL, scsi_dh,
+			 scsi_dh_notifier_remove);
+
+	spin_lock(&list_lock);
+	list_del(&scsi_dh->list);
+	spin_unlock(&list_lock);
+	printk(KERN_INFO "%s: device handler unregistered\n", scsi_dh->name);
+
+	return SCSI_DH_OK;
+}
+EXPORT_SYMBOL_GPL(scsi_unregister_device_handler);
+
+/*
+ * scsi_dh_activate - activate the path associated with the scsi_device
+ *      corresponding to the given request queue.
+ *     Returns immediately without waiting for activation to be completed.
+ * @q    - Request queue that is associated with the scsi_device to be
+ *         activated.
+ * @fn   - Function to be called upon completion of the activation.
+ *         Function fn is called with data (below) and the error code.
+ *         Function fn may be called from the same calling context. So,
+ *         do not hold the lock in the caller which may be needed in fn.
+ * @data - data passed to the function fn upon completion.
+ *
+ */
+int scsi_dh_activate(struct request_queue *q, activate_complete fn, void *data)
+{
+	int err = 0;
+	unsigned long flags;
+	struct scsi_device *sdev;
+	struct scsi_device_handler *scsi_dh = NULL;
+	struct device *dev = NULL;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	sdev = q->queuedata;
+	if (!sdev) {
+		spin_unlock_irqrestore(q->queue_lock, flags);
+		err = SCSI_DH_NOSYS;
+		if (fn)
+			fn(data, err);
+		return err;
+	}
+
+	if (sdev->scsi_dh_data)
+		scsi_dh = sdev->scsi_dh_data->scsi_dh;
+	dev = get_device(&sdev->sdev_gendev);
+	if (!scsi_dh || !dev ||
+	    sdev->sdev_state == SDEV_CANCEL ||
+	    sdev->sdev_state == SDEV_DEL)
+		err = SCSI_DH_NOSYS;
+	if (sdev->sdev_state == SDEV_OFFLINE)
+		err = SCSI_DH_DEV_OFFLINED;
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	if (err) {
+		if (fn)
+			fn(data, err);
+		goto out;
+	}
+
+	if (scsi_dh->activate)
+		err = scsi_dh->activate(sdev, fn, data);
+out:
+	put_device(dev);
+	return err;
+}
+EXPORT_SYMBOL_GPL(scsi_dh_activate);
+
+/*
+ * scsi_dh_set_params - set the parameters for the device as per the
+ *      string specified in params.
+ * @q - Request queue that is associated with the scsi_device for
+ *      which the parameters to be set.
+ * @params - parameters in the following format
+ *      "no_of_params\0param1\0param2\0param3\0...\0"
+ *      for example, string for 2 parameters with value 10 and 21
+ *      is specified as "2\010\021\0".
+ */
+int scsi_dh_set_params(struct request_queue *q, const char *params)
+{
+	int err = -SCSI_DH_NOSYS;
+	unsigned long flags;
+	struct scsi_device *sdev;
+	struct scsi_device_handler *scsi_dh = NULL;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	sdev = q->queuedata;
+	if (sdev && sdev->scsi_dh_data)
+		scsi_dh = sdev->scsi_dh_data->scsi_dh;
+	if (scsi_dh && scsi_dh->set_params && get_device(&sdev->sdev_gendev))
+		err = 0;
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	if (err)
+		return err;
+	err = scsi_dh->set_params(sdev, params);
+	put_device(&sdev->sdev_gendev);
+	return err;
+}
+EXPORT_SYMBOL_GPL(scsi_dh_set_params);
+
+/*
+ * scsi_dh_handler_exist - Return TRUE(1) if a device handler exists for
+ *	the given name. FALSE(0) otherwise.
+ * @name - name of the device handler.
+ */
+int scsi_dh_handler_exist(const char *name)
+{
+	return (get_device_handler(name) != NULL);
+}
+EXPORT_SYMBOL_GPL(scsi_dh_handler_exist);
+
+/*
+ * scsi_dh_attach - Attach device handler
+ * @q - Request queue that is associated with the scsi_device
+ *      the handler should be attached to
+ * @name - name of the handler to attach
+ */
+int scsi_dh_attach(struct request_queue *q, const char *name)
+{
+	unsigned long flags;
+	struct scsi_device *sdev;
+	struct scsi_device_handler *scsi_dh;
+	int err = 0;
+
+	scsi_dh = get_device_handler(name);
+	if (!scsi_dh)
+		return -EINVAL;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	sdev = q->queuedata;
+	if (!sdev || !get_device(&sdev->sdev_gendev))
+		err = -ENODEV;
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	if (!err) {
+		err = scsi_dh_handler_attach(sdev, scsi_dh);
+		put_device(&sdev->sdev_gendev);
+	}
+	return err;
+}
+EXPORT_SYMBOL_GPL(scsi_dh_attach);
+
+/*
+ * scsi_dh_detach - Detach device handler
+ * @q - Request queue that is associated with the scsi_device
+ *      the handler should be detached from
+ *
+ * This function will detach the device handler only
+ * if the sdev is not part of the internal list, ie
+ * if it has been attached manually.
+ */
+void scsi_dh_detach(struct request_queue *q)
+{
+	unsigned long flags;
+	struct scsi_device *sdev;
+	struct scsi_device_handler *scsi_dh = NULL;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	sdev = q->queuedata;
+	if (!sdev || !get_device(&sdev->sdev_gendev))
+		sdev = NULL;
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	if (!sdev)
+		return;
+
+	if (sdev->scsi_dh_data) {
+		scsi_dh = sdev->scsi_dh_data->scsi_dh;
+		scsi_dh_handler_detach(sdev, scsi_dh);
+	}
+	put_device(&sdev->sdev_gendev);
+}
+EXPORT_SYMBOL_GPL(scsi_dh_detach);
+
+/*
+ * scsi_dh_attached_handler_name - Get attached device handler's name
+ * @q - Request queue that is associated with the scsi_device
+ *      that may have a device handler attached
+ * @gfp - the GFP mask used in the kmalloc() call when allocating memory
+ *
+ * Returns name of attached handler, NULL if no handler is attached.
+ * Caller must take care to free the returned string.
+ */
+const char *scsi_dh_attached_handler_name(struct request_queue *q, gfp_t gfp)
+{
+	unsigned long flags;
+	struct scsi_device *sdev;
+	const char *handler_name = NULL;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	sdev = q->queuedata;
+	if (!sdev || !get_device(&sdev->sdev_gendev))
+		sdev = NULL;
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	if (!sdev)
+		return NULL;
+
+	if (sdev->scsi_dh_data)
+		handler_name = kstrdup(sdev->scsi_dh_data->scsi_dh->name, gfp);
+
+	put_device(&sdev->sdev_gendev);
+	return handler_name;
+}
+EXPORT_SYMBOL_GPL(scsi_dh_attached_handler_name);
+
+static struct notifier_block scsi_dh_nb = {
+	.notifier_call = scsi_dh_notifier
+};
+
+static int __init scsi_dh_init(void)
+{
+	int r;
+
+	r = bus_register_notifier(&scsi_bus_type, &scsi_dh_nb);
+
+	if (!r)
+		bus_for_each_dev(&scsi_bus_type, NULL, NULL,
+				 scsi_dh_sysfs_attr_add);
+
+	return r;
+}
+
+static void __exit scsi_dh_exit(void)
+{
+	bus_for_each_dev(&scsi_bus_type, NULL, NULL,
+			 scsi_dh_sysfs_attr_remove);
+	bus_unregister_notifier(&scsi_bus_type, &scsi_dh_nb);
+}
+
+module_init(scsi_dh_init);
+module_exit(scsi_dh_exit);
+
+MODULE_DESCRIPTION("SCSI device handler");
+MODULE_AUTHOR("Chandra Seetharaman <sekharan@us.ibm.com>");
+MODULE_LICENSE("GPL");
diff --git a/kernel/drivers/scsi/device_handler/scsi_dh_alua.c b/kernel/drivers/scsi/device_handler/scsi_dh_alua.c
new file mode 100644
index 000000000..854b568b9
--- /dev/null
+++ b/kernel/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -0,0 +1,905 @@
+/*
+ * Generic SCSI-3 ALUA SCSI Device Handler
+ *
+ * Copyright (C) 2007-2010 Hannes Reinecke, SUSE Linux Products GmbH.
+ * All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <scsi/scsi.h>
+#include <scsi/scsi_eh.h>
+#include <scsi/scsi_dh.h>
+
+#define ALUA_DH_NAME "alua"
+#define ALUA_DH_VER "1.3"
+
+#define TPGS_STATE_OPTIMIZED		0x0
+#define TPGS_STATE_NONOPTIMIZED		0x1
+#define TPGS_STATE_STANDBY		0x2
+#define TPGS_STATE_UNAVAILABLE		0x3
+#define TPGS_STATE_LBA_DEPENDENT	0x4
+#define TPGS_STATE_OFFLINE		0xe
+#define TPGS_STATE_TRANSITIONING	0xf
+
+#define TPGS_SUPPORT_NONE		0x00
+#define TPGS_SUPPORT_OPTIMIZED		0x01
+#define TPGS_SUPPORT_NONOPTIMIZED	0x02
+#define TPGS_SUPPORT_STANDBY		0x04
+#define TPGS_SUPPORT_UNAVAILABLE	0x08
+#define TPGS_SUPPORT_LBA_DEPENDENT	0x10
+#define TPGS_SUPPORT_OFFLINE		0x40
+#define TPGS_SUPPORT_TRANSITION		0x80
+
+#define RTPG_FMT_MASK			0x70
+#define RTPG_FMT_EXT_HDR		0x10
+
+#define TPGS_MODE_UNINITIALIZED		 -1
+#define TPGS_MODE_NONE			0x0
+#define TPGS_MODE_IMPLICIT		0x1
+#define TPGS_MODE_EXPLICIT		0x2
+
+#define ALUA_INQUIRY_SIZE		36
+#define ALUA_FAILOVER_TIMEOUT		60
+#define ALUA_FAILOVER_RETRIES		5
+
+/* flags passed from user level */
+#define ALUA_OPTIMIZE_STPG		1
+
+struct alua_dh_data {
+	struct scsi_dh_data	dh_data;
+	int			group_id;
+	int			rel_port;
+	int			tpgs;
+	int			state;
+	int			pref;
+	unsigned		flags; /* used for optimizing STPG */
+	unsigned char		inq[ALUA_INQUIRY_SIZE];
+	unsigned char		*buff;
+	int			bufflen;
+	unsigned char		transition_tmo;
+	unsigned char		sense[SCSI_SENSE_BUFFERSIZE];
+	int			senselen;
+	struct scsi_device	*sdev;
+	activate_complete	callback_fn;
+	void			*callback_data;
+};
+
+#define ALUA_POLICY_SWITCH_CURRENT	0
+#define ALUA_POLICY_SWITCH_ALL		1
+
+static char print_alua_state(int);
+static int alua_check_sense(struct scsi_device *, struct scsi_sense_hdr *);
+
+static inline struct alua_dh_data *get_alua_data(struct scsi_device *sdev)
+{
+	return container_of(sdev->scsi_dh_data, struct alua_dh_data, dh_data);
+}
+
+static int realloc_buffer(struct alua_dh_data *h, unsigned len)
+{
+	if (h->buff && h->buff != h->inq)
+		kfree(h->buff);
+
+	h->buff = kmalloc(len, GFP_NOIO);
+	if (!h->buff) {
+		h->buff = h->inq;
+		h->bufflen = ALUA_INQUIRY_SIZE;
+		return 1;
+	}
+	h->bufflen = len;
+	return 0;
+}
+
+static struct request *get_alua_req(struct scsi_device *sdev,
+				    void *buffer, unsigned buflen, int rw)
+{
+	struct request *rq;
+	struct request_queue *q = sdev->request_queue;
+
+	rq = blk_get_request(q, rw, GFP_NOIO);
+
+	if (IS_ERR(rq)) {
+		sdev_printk(KERN_INFO, sdev,
+			    "%s: blk_get_request failed\n", __func__);
+		return NULL;
+	}
+	blk_rq_set_block_pc(rq);
+
+	if (buflen && blk_rq_map_kern(q, rq, buffer, buflen, GFP_NOIO)) {
+		blk_put_request(rq);
+		sdev_printk(KERN_INFO, sdev,
+			    "%s: blk_rq_map_kern failed\n", __func__);
+		return NULL;
+	}
+
+	rq->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+			 REQ_FAILFAST_DRIVER;
+	rq->retries = ALUA_FAILOVER_RETRIES;
+	rq->timeout = ALUA_FAILOVER_TIMEOUT * HZ;
+
+	return rq;
+}
+
+/*
+ * submit_vpd_inquiry - Issue an INQUIRY VPD page 0x83 command
+ * @sdev: sdev the command should be sent to
+ */
+static int submit_vpd_inquiry(struct scsi_device *sdev, struct alua_dh_data *h)
+{
+	struct request *rq;
+	int err = SCSI_DH_RES_TEMP_UNAVAIL;
+
+	rq = get_alua_req(sdev, h->buff, h->bufflen, READ);
+	if (!rq)
+		goto done;
+
+	/* Prepare the command. */
+	rq->cmd[0] = INQUIRY;
+	rq->cmd[1] = 1;
+	rq->cmd[2] = 0x83;
+	rq->cmd[4] = h->bufflen;
+	rq->cmd_len = COMMAND_SIZE(INQUIRY);
+
+	rq->sense = h->sense;
+	memset(rq->sense, 0, SCSI_SENSE_BUFFERSIZE);
+	rq->sense_len = h->senselen = 0;
+
+	err = blk_execute_rq(rq->q, NULL, rq, 1);
+	if (err == -EIO) {
+		sdev_printk(KERN_INFO, sdev,
+			    "%s: evpd inquiry failed with %x\n",
+			    ALUA_DH_NAME, rq->errors);
+		h->senselen = rq->sense_len;
+		err = SCSI_DH_IO;
+	}
+	blk_put_request(rq);
+done:
+	return err;
+}
+
+/*
+ * submit_rtpg - Issue a REPORT TARGET GROUP STATES command
+ * @sdev: sdev the command should be sent to
+ */
+static unsigned submit_rtpg(struct scsi_device *sdev, struct alua_dh_data *h,
+			    bool rtpg_ext_hdr_req)
+{
+	struct request *rq;
+	int err = SCSI_DH_RES_TEMP_UNAVAIL;
+
+	rq = get_alua_req(sdev, h->buff, h->bufflen, READ);
+	if (!rq)
+		goto done;
+
+	/* Prepare the command. */
+	rq->cmd[0] = MAINTENANCE_IN;
+	if (rtpg_ext_hdr_req)
+		rq->cmd[1] = MI_REPORT_TARGET_PGS | MI_EXT_HDR_PARAM_FMT;
+	else
+		rq->cmd[1] = MI_REPORT_TARGET_PGS;
+	rq->cmd[6] = (h->bufflen >> 24) & 0xff;
+	rq->cmd[7] = (h->bufflen >> 16) & 0xff;
+	rq->cmd[8] = (h->bufflen >>  8) & 0xff;
+	rq->cmd[9] = h->bufflen & 0xff;
+	rq->cmd_len = COMMAND_SIZE(MAINTENANCE_IN);
+
+	rq->sense = h->sense;
+	memset(rq->sense, 0, SCSI_SENSE_BUFFERSIZE);
+	rq->sense_len = h->senselen = 0;
+
+	err = blk_execute_rq(rq->q, NULL, rq, 1);
+	if (err == -EIO) {
+		sdev_printk(KERN_INFO, sdev,
+			    "%s: rtpg failed with %x\n",
+			    ALUA_DH_NAME, rq->errors);
+		h->senselen = rq->sense_len;
+		err = SCSI_DH_IO;
+	}
+	blk_put_request(rq);
+done:
+	return err;
+}
+
+/*
+ * alua_stpg - Evaluate SET TARGET GROUP STATES
+ * @sdev: the device to be evaluated
+ * @state: the new target group state
+ *
+ * Send a SET TARGET GROUP STATES command to the device.
+ * We only have to test here if we should resubmit the command;
+ * any other error is assumed as a failure.
+ */
+static void stpg_endio(struct request *req, int error)
+{
+	struct alua_dh_data *h = req->end_io_data;
+	struct scsi_sense_hdr sense_hdr;
+	unsigned err = SCSI_DH_OK;
+
+	if (host_byte(req->errors) != DID_OK ||
+	    msg_byte(req->errors) != COMMAND_COMPLETE) {
+		err = SCSI_DH_IO;
+		goto done;
+	}
+
+	if (req->sense_len > 0) {
+		err = scsi_normalize_sense(h->sense, SCSI_SENSE_BUFFERSIZE,
+					   &sense_hdr);
+		if (!err) {
+			err = SCSI_DH_IO;
+			goto done;
+		}
+		err = alua_check_sense(h->sdev, &sense_hdr);
+		if (err == ADD_TO_MLQUEUE) {
+			err = SCSI_DH_RETRY;
+			goto done;
+		}
+		sdev_printk(KERN_INFO, h->sdev,
+			    "%s: stpg sense code: %02x/%02x/%02x\n",
+			    ALUA_DH_NAME, sense_hdr.sense_key,
+			    sense_hdr.asc, sense_hdr.ascq);
+		err = SCSI_DH_IO;
+	} else if (error)
+		err = SCSI_DH_IO;
+
+	if (err == SCSI_DH_OK) {
+		h->state = TPGS_STATE_OPTIMIZED;
+		sdev_printk(KERN_INFO, h->sdev,
+			    "%s: port group %02x switched to state %c\n",
+			    ALUA_DH_NAME, h->group_id,
+			    print_alua_state(h->state));
+	}
+done:
+	req->end_io_data = NULL;
+	__blk_put_request(req->q, req);
+	if (h->callback_fn) {
+		h->callback_fn(h->callback_data, err);
+		h->callback_fn = h->callback_data = NULL;
+	}
+	return;
+}
+
+/*
+ * submit_stpg - Issue a SET TARGET GROUP STATES command
+ *
+ * Currently we're only setting the current target port group state
+ * to 'active/optimized' and let the array firmware figure out
+ * the states of the remaining groups.
+ */
+static unsigned submit_stpg(struct alua_dh_data *h)
+{
+	struct request *rq;
+	int stpg_len = 8;
+	struct scsi_device *sdev = h->sdev;
+
+	/* Prepare the data buffer */
+	memset(h->buff, 0, stpg_len);
+	h->buff[4] = TPGS_STATE_OPTIMIZED & 0x0f;
+	h->buff[6] = (h->group_id >> 8) & 0xff;
+	h->buff[7] = h->group_id & 0xff;
+
+	rq = get_alua_req(sdev, h->buff, stpg_len, WRITE);
+	if (!rq)
+		return SCSI_DH_RES_TEMP_UNAVAIL;
+
+	/* Prepare the command. */
+	rq->cmd[0] = MAINTENANCE_OUT;
+	rq->cmd[1] = MO_SET_TARGET_PGS;
+	rq->cmd[6] = (stpg_len >> 24) & 0xff;
+	rq->cmd[7] = (stpg_len >> 16) & 0xff;
+	rq->cmd[8] = (stpg_len >>  8) & 0xff;
+	rq->cmd[9] = stpg_len & 0xff;
+	rq->cmd_len = COMMAND_SIZE(MAINTENANCE_OUT);
+
+	rq->sense = h->sense;
+	memset(rq->sense, 0, SCSI_SENSE_BUFFERSIZE);
+	rq->sense_len = h->senselen = 0;
+	rq->end_io_data = h;
+
+	blk_execute_rq_nowait(rq->q, NULL, rq, 1, stpg_endio);
+	return SCSI_DH_OK;
+}
+
+/*
+ * alua_check_tpgs - Evaluate TPGS setting
+ * @sdev: device to be checked
+ *
+ * Examine the TPGS setting of the sdev to find out if ALUA
+ * is supported.
+ */
+static int alua_check_tpgs(struct scsi_device *sdev, struct alua_dh_data *h)
+{
+	int err = SCSI_DH_OK;
+
+	h->tpgs = scsi_device_tpgs(sdev);
+	switch (h->tpgs) {
+	case TPGS_MODE_EXPLICIT|TPGS_MODE_IMPLICIT:
+		sdev_printk(KERN_INFO, sdev,
+			    "%s: supports implicit and explicit TPGS\n",
+			    ALUA_DH_NAME);
+		break;
+	case TPGS_MODE_EXPLICIT:
+		sdev_printk(KERN_INFO, sdev, "%s: supports explicit TPGS\n",
+			    ALUA_DH_NAME);
+		break;
+	case TPGS_MODE_IMPLICIT:
+		sdev_printk(KERN_INFO, sdev, "%s: supports implicit TPGS\n",
+			    ALUA_DH_NAME);
+		break;
+	default:
+		h->tpgs = TPGS_MODE_NONE;
+		sdev_printk(KERN_INFO, sdev, "%s: not supported\n",
+			    ALUA_DH_NAME);
+		err = SCSI_DH_DEV_UNSUPP;
+		break;
+	}
+
+	return err;
+}
+
+/*
+ * alua_vpd_inquiry - Evaluate INQUIRY vpd page 0x83
+ * @sdev: device to be checked
+ *
+ * Extract the relative target port and the target port group
+ * descriptor from the list of identificators.
+ */
+static int alua_vpd_inquiry(struct scsi_device *sdev, struct alua_dh_data *h)
+{
+	int len;
+	unsigned err;
+	unsigned char *d;
+
+ retry:
+	err = submit_vpd_inquiry(sdev, h);
+
+	if (err != SCSI_DH_OK)
+		return err;
+
+	/* Check if vpd page exceeds initial buffer */
+	len = (h->buff[2] << 8) + h->buff[3] + 4;
+	if (len > h->bufflen) {
+		/* Resubmit with the correct length */
+		if (realloc_buffer(h, len)) {
+			sdev_printk(KERN_WARNING, sdev,
+				    "%s: kmalloc buffer failed\n",
+				    ALUA_DH_NAME);
+			/* Temporary failure, bypass */
+			return SCSI_DH_DEV_TEMP_BUSY;
+		}
+		goto retry;
+	}
+
+	/*
+	 * Now look for the correct descriptor.
+	 */
+	d = h->buff + 4;
+	while (d < h->buff + len) {
+		switch (d[1] & 0xf) {
+		case 0x4:
+			/* Relative target port */
+			h->rel_port = (d[6] << 8) + d[7];
+			break;
+		case 0x5:
+			/* Target port group */
+			h->group_id = (d[6] << 8) + d[7];
+			break;
+		default:
+			break;
+		}
+		d += d[3] + 4;
+	}
+
+	if (h->group_id == -1) {
+		/*
+		 * Internal error; TPGS supported but required
+		 * VPD identification descriptors not present.
+		 * Disable ALUA support
+		 */
+		sdev_printk(KERN_INFO, sdev,
+			    "%s: No target port descriptors found\n",
+			    ALUA_DH_NAME);
+		h->state = TPGS_STATE_OPTIMIZED;
+		h->tpgs = TPGS_MODE_NONE;
+		err = SCSI_DH_DEV_UNSUPP;
+	} else {
+		sdev_printk(KERN_INFO, sdev,
+			    "%s: port group %02x rel port %02x\n",
+			    ALUA_DH_NAME, h->group_id, h->rel_port);
+	}
+
+	return err;
+}
+
+static char print_alua_state(int state)
+{
+	switch (state) {
+	case TPGS_STATE_OPTIMIZED:
+		return 'A';
+	case TPGS_STATE_NONOPTIMIZED:
+		return 'N';
+	case TPGS_STATE_STANDBY:
+		return 'S';
+	case TPGS_STATE_UNAVAILABLE:
+		return 'U';
+	case TPGS_STATE_LBA_DEPENDENT:
+		return 'L';
+	case TPGS_STATE_OFFLINE:
+		return 'O';
+	case TPGS_STATE_TRANSITIONING:
+		return 'T';
+	default:
+		return 'X';
+	}
+}
+
+static int alua_check_sense(struct scsi_device *sdev,
+			    struct scsi_sense_hdr *sense_hdr)
+{
+	switch (sense_hdr->sense_key) {
+	case NOT_READY:
+		if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x0a)
+			/*
+			 * LUN Not Accessible - ALUA state transition
+			 */
+			return ADD_TO_MLQUEUE;
+		if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x0b)
+			/*
+			 * LUN Not Accessible -- Target port in standby state
+			 */
+			return SUCCESS;
+		if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x0c)
+			/*
+			 * LUN Not Accessible -- Target port in unavailable state
+			 */
+			return SUCCESS;
+		if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x12)
+			/*
+			 * LUN Not Ready -- Offline
+			 */
+			return SUCCESS;
+		if (sdev->allow_restart &&
+		    sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x02)
+			/*
+			 * if the device is not started, we need to wake
+			 * the error handler to start the motor
+			 */
+			return FAILED;
+		break;
+	case UNIT_ATTENTION:
+		if (sense_hdr->asc == 0x29 && sense_hdr->ascq == 0x00)
+			/*
+			 * Power On, Reset, or Bus Device Reset, just retry.
+			 */
+			return ADD_TO_MLQUEUE;
+		if (sense_hdr->asc == 0x29 && sense_hdr->ascq == 0x04)
+			/*
+			 * Device internal reset
+			 */
+			return ADD_TO_MLQUEUE;
+		if (sense_hdr->asc == 0x2a && sense_hdr->ascq == 0x01)
+			/*
+			 * Mode Parameters Changed
+			 */
+			return ADD_TO_MLQUEUE;
+		if (sense_hdr->asc == 0x2a && sense_hdr->ascq == 0x06)
+			/*
+			 * ALUA state changed
+			 */
+			return ADD_TO_MLQUEUE;
+		if (sense_hdr->asc == 0x2a && sense_hdr->ascq == 0x07)
+			/*
+			 * Implicit ALUA state transition failed
+			 */
+			return ADD_TO_MLQUEUE;
+		if (sense_hdr->asc == 0x3f && sense_hdr->ascq == 0x03)
+			/*
+			 * Inquiry data has changed
+			 */
+			return ADD_TO_MLQUEUE;
+		if (sense_hdr->asc == 0x3f && sense_hdr->ascq == 0x0e)
+			/*
+			 * REPORTED_LUNS_DATA_HAS_CHANGED is reported
+			 * when switching controllers on targets like
+			 * Intel Multi-Flex. We can just retry.
+			 */
+			return ADD_TO_MLQUEUE;
+		break;
+	}
+
+	return SCSI_RETURN_NOT_HANDLED;
+}
+
+/*
+ * alua_rtpg - Evaluate REPORT TARGET GROUP STATES
+ * @sdev: the device to be evaluated.
+ * @wait_for_transition: if nonzero, wait ALUA_FAILOVER_TIMEOUT seconds for device to exit transitioning state
+ *
+ * Evaluate the Target Port Group State.
+ * Returns SCSI_DH_DEV_OFFLINED if the path is
+ * found to be unusable.
+ */
+static int alua_rtpg(struct scsi_device *sdev, struct alua_dh_data *h, int wait_for_transition)
+{
+	struct scsi_sense_hdr sense_hdr;
+	int len, k, off, valid_states = 0;
+	unsigned char *ucp;
+	unsigned err;
+	bool rtpg_ext_hdr_req = 1;
+	unsigned long expiry, interval = 0;
+	unsigned int tpg_desc_tbl_off;
+	unsigned char orig_transition_tmo;
+
+	if (!h->transition_tmo)
+		expiry = round_jiffies_up(jiffies + ALUA_FAILOVER_TIMEOUT * HZ);
+	else
+		expiry = round_jiffies_up(jiffies + h->transition_tmo * HZ);
+
+ retry:
+	err = submit_rtpg(sdev, h, rtpg_ext_hdr_req);
+
+	if (err == SCSI_DH_IO && h->senselen > 0) {
+		err = scsi_normalize_sense(h->sense, SCSI_SENSE_BUFFERSIZE,
+					   &sense_hdr);
+		if (!err)
+			return SCSI_DH_IO;
+
+		/*
+		 * submit_rtpg() has failed on existing arrays
+		 * when requesting extended header info, and
+		 * the array doesn't support extended headers,
+		 * even though it shouldn't according to T10.
+		 * The retry without rtpg_ext_hdr_req set
+		 * handles this.
+		 */
+		if (rtpg_ext_hdr_req == 1 &&
+		    sense_hdr.sense_key == ILLEGAL_REQUEST &&
+		    sense_hdr.asc == 0x24 && sense_hdr.ascq == 0) {
+			rtpg_ext_hdr_req = 0;
+			goto retry;
+		}
+
+		err = alua_check_sense(sdev, &sense_hdr);
+		if (err == ADD_TO_MLQUEUE && time_before(jiffies, expiry))
+			goto retry;
+		sdev_printk(KERN_INFO, sdev,
+			    "%s: rtpg sense code %02x/%02x/%02x\n",
+			    ALUA_DH_NAME, sense_hdr.sense_key,
+			    sense_hdr.asc, sense_hdr.ascq);
+		err = SCSI_DH_IO;
+	}
+	if (err != SCSI_DH_OK)
+		return err;
+
+	len = (h->buff[0] << 24) + (h->buff[1] << 16) +
+		(h->buff[2] << 8) + h->buff[3] + 4;
+
+	if (len > h->bufflen) {
+		/* Resubmit with the correct length */
+		if (realloc_buffer(h, len)) {
+			sdev_printk(KERN_WARNING, sdev,
+				    "%s: kmalloc buffer failed\n",__func__);
+			/* Temporary failure, bypass */
+			return SCSI_DH_DEV_TEMP_BUSY;
+		}
+		goto retry;
+	}
+
+	orig_transition_tmo = h->transition_tmo;
+	if ((h->buff[4] & RTPG_FMT_MASK) == RTPG_FMT_EXT_HDR && h->buff[5] != 0)
+		h->transition_tmo = h->buff[5];
+	else
+		h->transition_tmo = ALUA_FAILOVER_TIMEOUT;
+
+	if (wait_for_transition && (orig_transition_tmo != h->transition_tmo)) {
+		sdev_printk(KERN_INFO, sdev,
+			    "%s: transition timeout set to %d seconds\n",
+			    ALUA_DH_NAME, h->transition_tmo);
+		expiry = jiffies + h->transition_tmo * HZ;
+	}
+
+	if ((h->buff[4] & RTPG_FMT_MASK) == RTPG_FMT_EXT_HDR)
+		tpg_desc_tbl_off = 8;
+	else
+		tpg_desc_tbl_off = 4;
+
+	for (k = tpg_desc_tbl_off, ucp = h->buff + tpg_desc_tbl_off;
+	     k < len;
+	     k += off, ucp += off) {
+
+		if (h->group_id == (ucp[2] << 8) + ucp[3]) {
+			h->state = ucp[0] & 0x0f;
+			h->pref = ucp[0] >> 7;
+			valid_states = ucp[1];
+		}
+		off = 8 + (ucp[7] * 4);
+	}
+
+	sdev_printk(KERN_INFO, sdev,
+		    "%s: port group %02x state %c %s supports %c%c%c%c%c%c%c\n",
+		    ALUA_DH_NAME, h->group_id, print_alua_state(h->state),
+		    h->pref ? "preferred" : "non-preferred",
+		    valid_states&TPGS_SUPPORT_TRANSITION?'T':'t',
+		    valid_states&TPGS_SUPPORT_OFFLINE?'O':'o',
+		    valid_states&TPGS_SUPPORT_LBA_DEPENDENT?'L':'l',
+		    valid_states&TPGS_SUPPORT_UNAVAILABLE?'U':'u',
+		    valid_states&TPGS_SUPPORT_STANDBY?'S':'s',
+		    valid_states&TPGS_SUPPORT_NONOPTIMIZED?'N':'n',
+		    valid_states&TPGS_SUPPORT_OPTIMIZED?'A':'a');
+
+	switch (h->state) {
+	case TPGS_STATE_TRANSITIONING:
+		if (wait_for_transition) {
+			if (time_before(jiffies, expiry)) {
+				/* State transition, retry */
+				interval += 2000;
+				msleep(interval);
+				goto retry;
+			}
+			err = SCSI_DH_RETRY;
+		} else {
+			err = SCSI_DH_OK;
+		}
+
+		/* Transitioning time exceeded, set port to standby */
+		h->state = TPGS_STATE_STANDBY;
+		break;
+	case TPGS_STATE_OFFLINE:
+		/* Path unusable */
+		err = SCSI_DH_DEV_OFFLINED;
+		break;
+	default:
+		/* Useable path if active */
+		err = SCSI_DH_OK;
+		break;
+	}
+	return err;
+}
+
+/*
+ * alua_initialize - Initialize ALUA state
+ * @sdev: the device to be initialized
+ *
+ * For the prep_fn to work correctly we have
+ * to initialize the ALUA state for the device.
+ */
+static int alua_initialize(struct scsi_device *sdev, struct alua_dh_data *h)
+{
+	int err;
+
+	err = alua_check_tpgs(sdev, h);
+	if (err != SCSI_DH_OK)
+		goto out;
+
+	err = alua_vpd_inquiry(sdev, h);
+	if (err != SCSI_DH_OK)
+		goto out;
+
+	err = alua_rtpg(sdev, h, 0);
+	if (err != SCSI_DH_OK)
+		goto out;
+
+out:
+	return err;
+}
+/*
+ * alua_set_params - set/unset the optimize flag
+ * @sdev: device on the path to be activated
+ * params - parameters in the following format
+ *      "no_of_params\0param1\0param2\0param3\0...\0"
+ * For example, to set the flag pass the following parameters
+ * from multipath.conf
+ *     hardware_handler        "2 alua 1"
+ */
+static int alua_set_params(struct scsi_device *sdev, const char *params)
+{
+	struct alua_dh_data *h = get_alua_data(sdev);
+	unsigned int optimize = 0, argc;
+	const char *p = params;
+	int result = SCSI_DH_OK;
+
+	if ((sscanf(params, "%u", &argc) != 1) || (argc != 1))
+		return -EINVAL;
+
+	while (*p++)
+		;
+	if ((sscanf(p, "%u", &optimize) != 1) || (optimize > 1))
+		return -EINVAL;
+
+	if (optimize)
+		h->flags |= ALUA_OPTIMIZE_STPG;
+	else
+		h->flags &= ~ALUA_OPTIMIZE_STPG;
+
+	return result;
+}
+
+static uint optimize_stpg;
+module_param(optimize_stpg, uint, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(optimize_stpg, "Allow use of a non-optimized path, rather than sending a STPG, when implicit TPGS is supported (0=No,1=Yes). Default is 0.");
+
+/*
+ * alua_activate - activate a path
+ * @sdev: device on the path to be activated
+ *
+ * We're currently switching the port group to be activated only and
+ * let the array figure out the rest.
+ * There may be other arrays which require us to switch all port groups
+ * based on a certain policy. But until we actually encounter them it
+ * should be okay.
+ */
+static int alua_activate(struct scsi_device *sdev,
+			activate_complete fn, void *data)
+{
+	struct alua_dh_data *h = get_alua_data(sdev);
+	int err = SCSI_DH_OK;
+	int stpg = 0;
+
+	err = alua_rtpg(sdev, h, 1);
+	if (err != SCSI_DH_OK)
+		goto out;
+
+	if (optimize_stpg)
+		h->flags |= ALUA_OPTIMIZE_STPG;
+
+	if (h->tpgs & TPGS_MODE_EXPLICIT) {
+		switch (h->state) {
+		case TPGS_STATE_NONOPTIMIZED:
+			stpg = 1;
+			if ((h->flags & ALUA_OPTIMIZE_STPG) &&
+			    (!h->pref) &&
+			    (h->tpgs & TPGS_MODE_IMPLICIT))
+				stpg = 0;
+			break;
+		case TPGS_STATE_STANDBY:
+		case TPGS_STATE_UNAVAILABLE:
+			stpg = 1;
+			break;
+		case TPGS_STATE_OFFLINE:
+			err = SCSI_DH_IO;
+			break;
+		case TPGS_STATE_TRANSITIONING:
+			err = SCSI_DH_RETRY;
+			break;
+		default:
+			break;
+		}
+	}
+
+	if (stpg) {
+		h->callback_fn = fn;
+		h->callback_data = data;
+		err = submit_stpg(h);
+		if (err == SCSI_DH_OK)
+			return 0;
+		h->callback_fn = h->callback_data = NULL;
+	}
+
+out:
+	if (fn)
+		fn(data, err);
+	return 0;
+}
+
+/*
+ * alua_prep_fn - request callback
+ *
+ * Fail I/O to all paths not in state
+ * active/optimized or active/non-optimized.
+ */
+static int alua_prep_fn(struct scsi_device *sdev, struct request *req)
+{
+	struct alua_dh_data *h = get_alua_data(sdev);
+	int ret = BLKPREP_OK;
+
+	if (h->state == TPGS_STATE_TRANSITIONING)
+		ret = BLKPREP_DEFER;
+	else if (h->state != TPGS_STATE_OPTIMIZED &&
+		 h->state != TPGS_STATE_NONOPTIMIZED &&
+		 h->state != TPGS_STATE_LBA_DEPENDENT) {
+		ret = BLKPREP_KILL;
+		req->cmd_flags |= REQ_QUIET;
+	}
+	return ret;
+
+}
+
+static bool alua_match(struct scsi_device *sdev)
+{
+	return (scsi_device_tpgs(sdev) != 0);
+}
+
+/*
+ * alua_bus_attach - Attach device handler
+ * @sdev: device to be attached to
+ */
+static struct scsi_dh_data *alua_bus_attach(struct scsi_device *sdev)
+{
+	struct alua_dh_data *h;
+	int err;
+
+	h = kzalloc(sizeof(*h) , GFP_KERNEL);
+	if (!h)
+		return ERR_PTR(-ENOMEM);
+	h->tpgs = TPGS_MODE_UNINITIALIZED;
+	h->state = TPGS_STATE_OPTIMIZED;
+	h->group_id = -1;
+	h->rel_port = -1;
+	h->buff = h->inq;
+	h->bufflen = ALUA_INQUIRY_SIZE;
+	h->sdev = sdev;
+
+	err = alua_initialize(sdev, h);
+	if (err != SCSI_DH_OK && err != SCSI_DH_DEV_OFFLINED)
+		goto failed;
+
+	sdev_printk(KERN_NOTICE, sdev, "%s: Attached\n", ALUA_DH_NAME);
+	return &h->dh_data;
+failed:
+	kfree(h);
+	return ERR_PTR(-EINVAL);
+}
+
+/*
+ * alua_bus_detach - Detach device handler
+ * @sdev: device to be detached from
+ */
+static void alua_bus_detach(struct scsi_device *sdev)
+{
+	struct alua_dh_data *h = get_alua_data(sdev);
+
+	if (h->buff && h->inq != h->buff)
+		kfree(h->buff);
+	kfree(h);
+}
+
+static struct scsi_device_handler alua_dh = {
+	.name = ALUA_DH_NAME,
+	.module = THIS_MODULE,
+	.attach = alua_bus_attach,
+	.detach = alua_bus_detach,
+	.prep_fn = alua_prep_fn,
+	.check_sense = alua_check_sense,
+	.activate = alua_activate,
+	.set_params = alua_set_params,
+	.match = alua_match,
+};
+
+static int __init alua_init(void)
+{
+	int r;
+
+	r = scsi_register_device_handler(&alua_dh);
+	if (r != 0)
+		printk(KERN_ERR "%s: Failed to register scsi device handler",
+			ALUA_DH_NAME);
+	return r;
+}
+
+static void __exit alua_exit(void)
+{
+	scsi_unregister_device_handler(&alua_dh);
+}
+
+module_init(alua_init);
+module_exit(alua_exit);
+
+MODULE_DESCRIPTION("DM Multipath ALUA support");
+MODULE_AUTHOR("Hannes Reinecke <hare@suse.de>");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(ALUA_DH_VER);
diff --git a/kernel/drivers/scsi/device_handler/scsi_dh_emc.c b/kernel/drivers/scsi/device_handler/scsi_dh_emc.c
new file mode 100644
index 000000000..6ed1caadb
--- /dev/null
+++ b/kernel/drivers/scsi/device_handler/scsi_dh_emc.c
@@ -0,0 +1,725 @@
+/*
+ * Target driver for EMC CLARiiON AX/CX-series hardware.
+ * Based on code from Lars Marowsky-Bree <lmb@suse.de>
+ * and Ed Goggin <egoggin@emc.com>.
+ *
+ * Copyright (C) 2006 Red Hat, Inc.  All rights reserved.
+ * Copyright (C) 2006 Mike Christie
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <scsi/scsi.h>
+#include <scsi/scsi_eh.h>
+#include <scsi/scsi_dh.h>
+#include <scsi/scsi_device.h>
+
+#define CLARIION_NAME			"emc"
+
+#define CLARIION_TRESPASS_PAGE		0x22
+#define CLARIION_BUFFER_SIZE		0xFC
+#define CLARIION_TIMEOUT		(60 * HZ)
+#define CLARIION_RETRIES		3
+#define CLARIION_UNBOUND_LU		-1
+#define CLARIION_SP_A			0
+#define CLARIION_SP_B			1
+
+/* Flags */
+#define CLARIION_SHORT_TRESPASS		1
+#define CLARIION_HONOR_RESERVATIONS	2
+
+/* LUN states */
+#define CLARIION_LUN_UNINITIALIZED	-1
+#define CLARIION_LUN_UNBOUND		0
+#define CLARIION_LUN_BOUND		1
+#define CLARIION_LUN_OWNED		2
+
+static unsigned char long_trespass[] = {
+	0, 0, 0, 0, 0, 0, 0, 0,
+	CLARIION_TRESPASS_PAGE,	/* Page code */
+	0x09,			/* Page length - 2 */
+	0x01,			/* Trespass code */
+	0xff, 0xff,		/* Trespass target */
+	0, 0, 0, 0, 0, 0	/* Reserved bytes / unknown */
+};
+
+static unsigned char short_trespass[] = {
+	0, 0, 0, 0,
+	CLARIION_TRESPASS_PAGE,	/* Page code */
+	0x02,			/* Page length - 2 */
+	0x01,			/* Trespass code */
+	0xff,			/* Trespass target */
+};
+
+static const char * lun_state[] =
+{
+    "not bound",
+    "bound",
+    "owned",
+};
+
+struct clariion_dh_data {
+	struct scsi_dh_data dh_data;
+	/*
+	 * Flags:
+	 *  CLARIION_SHORT_TRESPASS
+	 * Use short trespass command (FC-series) or the long version
+	 * (default for AX/CX CLARiiON arrays).
+	 *
+	 *  CLARIION_HONOR_RESERVATIONS
+	 * Whether or not (default) to honor SCSI reservations when
+	 * initiating a switch-over.
+	 */
+	unsigned flags;
+	/*
+	 * I/O buffer for both MODE_SELECT and INQUIRY commands.
+	 */
+	unsigned char buffer[CLARIION_BUFFER_SIZE];
+	/*
+	 * SCSI sense buffer for commands -- assumes serial issuance
+	 * and completion sequence of all commands for same multipath.
+	 */
+	unsigned char sense[SCSI_SENSE_BUFFERSIZE];
+	unsigned int senselen;
+	/*
+	 * LUN state
+	 */
+	int lun_state;
+	/*
+	 * SP Port number
+	 */
+	int port;
+	/*
+	 * which SP (A=0,B=1,UNBOUND=-1) is the default SP for this
+	 * path's mapped LUN
+	 */
+	int default_sp;
+	/*
+	 * which SP (A=0,B=1,UNBOUND=-1) is the active SP for this
+	 * path's mapped LUN
+	 */
+	int current_sp;
+};
+
+static inline struct clariion_dh_data
+			*get_clariion_data(struct scsi_device *sdev)
+{
+	return container_of(sdev->scsi_dh_data, struct clariion_dh_data,
+			dh_data);
+}
+
+/*
+ * Parse MODE_SELECT cmd reply.
+ */
+static int trespass_endio(struct scsi_device *sdev, char *sense)
+{
+	int err = SCSI_DH_IO;
+	struct scsi_sense_hdr sshdr;
+
+	if (!scsi_normalize_sense(sense, SCSI_SENSE_BUFFERSIZE, &sshdr)) {
+		sdev_printk(KERN_ERR, sdev, "%s: Found valid sense data 0x%2x, "
+			    "0x%2x, 0x%2x while sending CLARiiON trespass "
+			    "command.\n", CLARIION_NAME, sshdr.sense_key,
+			    sshdr.asc, sshdr.ascq);
+
+		if ((sshdr.sense_key == 0x05) && (sshdr.asc == 0x04) &&
+		     (sshdr.ascq == 0x00)) {
+			/*
+			 * Array based copy in progress -- do not send
+			 * mode_select or copy will be aborted mid-stream.
+			 */
+			sdev_printk(KERN_INFO, sdev, "%s: Array Based Copy in "
+				    "progress while sending CLARiiON trespass "
+				    "command.\n", CLARIION_NAME);
+			err = SCSI_DH_DEV_TEMP_BUSY;
+		} else if ((sshdr.sense_key == 0x02) && (sshdr.asc == 0x04) &&
+			    (sshdr.ascq == 0x03)) {
+			/*
+			 * LUN Not Ready - Manual Intervention Required
+			 * indicates in-progress ucode upgrade (NDU).
+			 */
+			sdev_printk(KERN_INFO, sdev, "%s: Detected in-progress "
+				    "ucode upgrade NDU operation while sending "
+				    "CLARiiON trespass command.\n", CLARIION_NAME);
+			err = SCSI_DH_DEV_TEMP_BUSY;
+		} else
+			err = SCSI_DH_DEV_FAILED;
+	} else {
+		sdev_printk(KERN_INFO, sdev,
+			    "%s: failed to send MODE SELECT, no sense available\n",
+			    CLARIION_NAME);
+	}
+	return err;
+}
+
+static int parse_sp_info_reply(struct scsi_device *sdev,
+			       struct clariion_dh_data *csdev)
+{
+	int err = SCSI_DH_OK;
+
+	/* check for in-progress ucode upgrade (NDU) */
+	if (csdev->buffer[48] != 0) {
+		sdev_printk(KERN_NOTICE, sdev, "%s: Detected in-progress "
+			    "ucode upgrade NDU operation while finding "
+			    "current active SP.", CLARIION_NAME);
+		err = SCSI_DH_DEV_TEMP_BUSY;
+		goto out;
+	}
+	if (csdev->buffer[4] > 2) {
+		/* Invalid buffer format */
+		sdev_printk(KERN_NOTICE, sdev,
+			    "%s: invalid VPD page 0xC0 format\n",
+			    CLARIION_NAME);
+		err = SCSI_DH_NOSYS;
+		goto out;
+	}
+	switch (csdev->buffer[28] & 0x0f) {
+	case 6:
+		sdev_printk(KERN_NOTICE, sdev,
+			    "%s: ALUA failover mode detected\n",
+			    CLARIION_NAME);
+		break;
+	case 4:
+		/* Linux failover */
+		break;
+	default:
+		sdev_printk(KERN_WARNING, sdev,
+			    "%s: Invalid failover mode %d\n",
+			    CLARIION_NAME, csdev->buffer[28] & 0x0f);
+		err = SCSI_DH_NOSYS;
+		goto out;
+	}
+
+	csdev->default_sp = csdev->buffer[5];
+	csdev->lun_state = csdev->buffer[4];
+	csdev->current_sp = csdev->buffer[8];
+	csdev->port = csdev->buffer[7];
+
+out:
+	return err;
+}
+
+#define emc_default_str "FC (Legacy)"
+
+static char * parse_sp_model(struct scsi_device *sdev, unsigned char *buffer)
+{
+	unsigned char len = buffer[4] + 5;
+	char *sp_model = NULL;
+	unsigned char sp_len, serial_len;
+
+	if (len < 160) {
+		sdev_printk(KERN_WARNING, sdev,
+			    "%s: Invalid information section length %d\n",
+			    CLARIION_NAME, len);
+		/* Check for old FC arrays */
+		if (!strncmp(buffer + 8, "DGC", 3)) {
+			/* Old FC array, not supporting extended information */
+			sp_model = emc_default_str;
+		}
+		goto out;
+	}
+
+	/*
+	 * Parse extended information for SP model number
+	 */
+	serial_len = buffer[160];
+	if (serial_len == 0 || serial_len + 161 > len) {
+		sdev_printk(KERN_WARNING, sdev,
+			    "%s: Invalid array serial number length %d\n",
+			    CLARIION_NAME, serial_len);
+		goto out;
+	}
+	sp_len = buffer[99];
+	if (sp_len == 0 || serial_len + sp_len + 161 > len) {
+		sdev_printk(KERN_WARNING, sdev,
+			    "%s: Invalid model number length %d\n",
+			    CLARIION_NAME, sp_len);
+		goto out;
+	}
+	sp_model = &buffer[serial_len + 161];
+	/* Strip whitespace at the end */
+	while (sp_len > 1 && sp_model[sp_len - 1] == ' ')
+		sp_len--;
+
+	sp_model[sp_len] = '\0';
+
+out:
+	return sp_model;
+}
+
+/*
+ * Get block request for REQ_BLOCK_PC command issued to path.  Currently
+ * limited to MODE_SELECT (trespass) and INQUIRY (VPD page 0xC0) commands.
+ *
+ * Uses data and sense buffers in hardware handler context structure and
+ * assumes serial servicing of commands, both issuance and completion.
+ */
+static struct request *get_req(struct scsi_device *sdev, int cmd,
+				unsigned char *buffer)
+{
+	struct request *rq;
+	int len = 0;
+
+	rq = blk_get_request(sdev->request_queue,
+			(cmd != INQUIRY) ? WRITE : READ, GFP_NOIO);
+	if (IS_ERR(rq)) {
+		sdev_printk(KERN_INFO, sdev, "get_req: blk_get_request failed");
+		return NULL;
+	}
+
+	blk_rq_set_block_pc(rq);
+	rq->cmd_len = COMMAND_SIZE(cmd);
+	rq->cmd[0] = cmd;
+
+	switch (cmd) {
+	case MODE_SELECT:
+		len = sizeof(short_trespass);
+		rq->cmd[1] = 0x10;
+		rq->cmd[4] = len;
+		break;
+	case MODE_SELECT_10:
+		len = sizeof(long_trespass);
+		rq->cmd[1] = 0x10;
+		rq->cmd[8] = len;
+		break;
+	case INQUIRY:
+		len = CLARIION_BUFFER_SIZE;
+		rq->cmd[4] = len;
+		memset(buffer, 0, len);
+		break;
+	default:
+		BUG_ON(1);
+		break;
+	}
+
+	rq->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+			 REQ_FAILFAST_DRIVER;
+	rq->timeout = CLARIION_TIMEOUT;
+	rq->retries = CLARIION_RETRIES;
+
+	if (blk_rq_map_kern(rq->q, rq, buffer, len, GFP_NOIO)) {
+		blk_put_request(rq);
+		return NULL;
+	}
+
+	return rq;
+}
+
+static int send_inquiry_cmd(struct scsi_device *sdev, int page,
+			    struct clariion_dh_data *csdev)
+{
+	struct request *rq = get_req(sdev, INQUIRY, csdev->buffer);
+	int err;
+
+	if (!rq)
+		return SCSI_DH_RES_TEMP_UNAVAIL;
+
+	rq->sense = csdev->sense;
+	memset(rq->sense, 0, SCSI_SENSE_BUFFERSIZE);
+	rq->sense_len = csdev->senselen = 0;
+
+	rq->cmd[0] = INQUIRY;
+	if (page != 0) {
+		rq->cmd[1] = 1;
+		rq->cmd[2] = page;
+	}
+	err = blk_execute_rq(sdev->request_queue, NULL, rq, 1);
+	if (err == -EIO) {
+		sdev_printk(KERN_INFO, sdev,
+			    "%s: failed to send %s INQUIRY: %x\n",
+			    CLARIION_NAME, page?"EVPD":"standard",
+			    rq->errors);
+		csdev->senselen = rq->sense_len;
+		err = SCSI_DH_IO;
+	}
+
+	blk_put_request(rq);
+
+	return err;
+}
+
+static int send_trespass_cmd(struct scsi_device *sdev,
+			    struct clariion_dh_data *csdev)
+{
+	struct request *rq;
+	unsigned char *page22;
+	int err, len, cmd;
+
+	if (csdev->flags & CLARIION_SHORT_TRESPASS) {
+		page22 = short_trespass;
+		if (!(csdev->flags & CLARIION_HONOR_RESERVATIONS))
+			/* Set Honor Reservations bit */
+			page22[6] |= 0x80;
+		len = sizeof(short_trespass);
+		cmd = MODE_SELECT;
+	} else {
+		page22 = long_trespass;
+		if (!(csdev->flags & CLARIION_HONOR_RESERVATIONS))
+			/* Set Honor Reservations bit */
+			page22[10] |= 0x80;
+		len = sizeof(long_trespass);
+		cmd = MODE_SELECT_10;
+	}
+	BUG_ON((len > CLARIION_BUFFER_SIZE));
+	memcpy(csdev->buffer, page22, len);
+
+	rq = get_req(sdev, cmd, csdev->buffer);
+	if (!rq)
+		return SCSI_DH_RES_TEMP_UNAVAIL;
+
+	rq->sense = csdev->sense;
+	memset(rq->sense, 0, SCSI_SENSE_BUFFERSIZE);
+	rq->sense_len = csdev->senselen = 0;
+
+	err = blk_execute_rq(sdev->request_queue, NULL, rq, 1);
+	if (err == -EIO) {
+		if (rq->sense_len) {
+			err = trespass_endio(sdev, csdev->sense);
+		} else {
+			sdev_printk(KERN_INFO, sdev,
+				    "%s: failed to send MODE SELECT: %x\n",
+				    CLARIION_NAME, rq->errors);
+		}
+	}
+
+	blk_put_request(rq);
+
+	return err;
+}
+
+static int clariion_check_sense(struct scsi_device *sdev,
+				struct scsi_sense_hdr *sense_hdr)
+{
+	switch (sense_hdr->sense_key) {
+	case NOT_READY:
+		if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x03)
+			/*
+			 * LUN Not Ready - Manual Intervention Required
+			 * indicates this is a passive path.
+			 *
+			 * FIXME: However, if this is seen and EVPD C0
+			 * indicates that this is due to a NDU in
+			 * progress, we should set FAIL_PATH too.
+			 * This indicates we might have to do a SCSI
+			 * inquiry in the end_io path. Ugh.
+			 *
+			 * Can return FAILED only when we want the error
+			 * recovery process to kick in.
+			 */
+			return SUCCESS;
+		break;
+	case ILLEGAL_REQUEST:
+		if (sense_hdr->asc == 0x25 && sense_hdr->ascq == 0x01)
+			/*
+			 * An array based copy is in progress. Do not
+			 * fail the path, do not bypass to another PG,
+			 * do not retry. Fail the IO immediately.
+			 * (Actually this is the same conclusion as in
+			 * the default handler, but lets make sure.)
+			 *
+			 * Can return FAILED only when we want the error
+			 * recovery process to kick in.
+			 */
+			return SUCCESS;
+		break;
+	case UNIT_ATTENTION:
+		if (sense_hdr->asc == 0x29 && sense_hdr->ascq == 0x00)
+			/*
+			 * Unit Attention Code. This is the first IO
+			 * to the new path, so just retry.
+			 */
+			return ADD_TO_MLQUEUE;
+		break;
+	}
+
+	return SCSI_RETURN_NOT_HANDLED;
+}
+
+static int clariion_prep_fn(struct scsi_device *sdev, struct request *req)
+{
+	struct clariion_dh_data *h = get_clariion_data(sdev);
+	int ret = BLKPREP_OK;
+
+	if (h->lun_state != CLARIION_LUN_OWNED) {
+		ret = BLKPREP_KILL;
+		req->cmd_flags |= REQ_QUIET;
+	}
+	return ret;
+
+}
+
+static int clariion_std_inquiry(struct scsi_device *sdev,
+				struct clariion_dh_data *csdev)
+{
+	int err;
+	char *sp_model;
+
+	err = send_inquiry_cmd(sdev, 0, csdev);
+	if (err != SCSI_DH_OK && csdev->senselen) {
+		struct scsi_sense_hdr sshdr;
+
+		if (scsi_normalize_sense(csdev->sense, SCSI_SENSE_BUFFERSIZE,
+					 &sshdr)) {
+			sdev_printk(KERN_ERR, sdev, "%s: INQUIRY sense code "
+				    "%02x/%02x/%02x\n", CLARIION_NAME,
+				    sshdr.sense_key, sshdr.asc, sshdr.ascq);
+		}
+		err = SCSI_DH_IO;
+		goto out;
+	}
+
+	sp_model = parse_sp_model(sdev, csdev->buffer);
+	if (!sp_model) {
+		err = SCSI_DH_DEV_UNSUPP;
+		goto out;
+	}
+
+	/*
+	 * FC Series arrays do not support long trespass
+	 */
+	if (!strlen(sp_model) || !strncmp(sp_model, "FC",2))
+		csdev->flags |= CLARIION_SHORT_TRESPASS;
+
+	sdev_printk(KERN_INFO, sdev,
+		    "%s: detected Clariion %s, flags %x\n",
+		    CLARIION_NAME, sp_model, csdev->flags);
+out:
+	return err;
+}
+
+static int clariion_send_inquiry(struct scsi_device *sdev,
+				 struct clariion_dh_data *csdev)
+{
+	int err, retry = CLARIION_RETRIES;
+
+retry:
+	err = send_inquiry_cmd(sdev, 0xC0, csdev);
+	if (err != SCSI_DH_OK && csdev->senselen) {
+		struct scsi_sense_hdr sshdr;
+
+		err = scsi_normalize_sense(csdev->sense, SCSI_SENSE_BUFFERSIZE,
+					   &sshdr);
+		if (!err)
+			return SCSI_DH_IO;
+
+		err = clariion_check_sense(sdev, &sshdr);
+		if (retry > 0 && err == ADD_TO_MLQUEUE) {
+			retry--;
+			goto retry;
+		}
+		sdev_printk(KERN_ERR, sdev, "%s: INQUIRY sense code "
+			    "%02x/%02x/%02x\n", CLARIION_NAME,
+			      sshdr.sense_key, sshdr.asc, sshdr.ascq);
+		err = SCSI_DH_IO;
+	} else {
+		err = parse_sp_info_reply(sdev, csdev);
+	}
+	return err;
+}
+
+static int clariion_activate(struct scsi_device *sdev,
+				activate_complete fn, void *data)
+{
+	struct clariion_dh_data *csdev = get_clariion_data(sdev);
+	int result;
+
+	result = clariion_send_inquiry(sdev, csdev);
+	if (result != SCSI_DH_OK)
+		goto done;
+
+	if (csdev->lun_state == CLARIION_LUN_OWNED)
+		goto done;
+
+	result = send_trespass_cmd(sdev, csdev);
+	if (result != SCSI_DH_OK)
+		goto done;
+	sdev_printk(KERN_INFO, sdev,"%s: %s trespass command sent\n",
+		    CLARIION_NAME,
+		    csdev->flags&CLARIION_SHORT_TRESPASS?"short":"long" );
+
+	/* Update status */
+	result = clariion_send_inquiry(sdev, csdev);
+	if (result != SCSI_DH_OK)
+		goto done;
+
+done:
+	sdev_printk(KERN_INFO, sdev,
+		    "%s: at SP %c Port %d (%s, default SP %c)\n",
+		    CLARIION_NAME, csdev->current_sp + 'A',
+		    csdev->port, lun_state[csdev->lun_state],
+		    csdev->default_sp + 'A');
+
+	if (fn)
+		fn(data, result);
+	return 0;
+}
+/*
+ * params - parameters in the following format
+ *      "no_of_params\0param1\0param2\0param3\0...\0"
+ *      for example, string for 2 parameters with value 10 and 21
+ *      is specified as "2\010\021\0".
+ */
+static int clariion_set_params(struct scsi_device *sdev, const char *params)
+{
+	struct clariion_dh_data *csdev = get_clariion_data(sdev);
+	unsigned int hr = 0, st = 0, argc;
+	const char *p = params;
+	int result = SCSI_DH_OK;
+
+	if ((sscanf(params, "%u", &argc) != 1) || (argc != 2))
+		return -EINVAL;
+
+	while (*p++)
+		;
+	if ((sscanf(p, "%u", &st) != 1) || (st > 1))
+		return -EINVAL;
+
+	while (*p++)
+		;
+	if ((sscanf(p, "%u", &hr) != 1) || (hr > 1))
+		return -EINVAL;
+
+	if (st)
+		csdev->flags |= CLARIION_SHORT_TRESPASS;
+	else
+		csdev->flags &= ~CLARIION_SHORT_TRESPASS;
+
+	if (hr)
+		csdev->flags |= CLARIION_HONOR_RESERVATIONS;
+	else
+		csdev->flags &= ~CLARIION_HONOR_RESERVATIONS;
+
+	/*
+	 * If this path is owned, we have to send a trespass command
+	 * with the new parameters. If not, simply return. Next trespass
+	 * command would use the parameters.
+	 */
+	if (csdev->lun_state != CLARIION_LUN_OWNED)
+		goto done;
+
+	csdev->lun_state = CLARIION_LUN_UNINITIALIZED;
+	result = send_trespass_cmd(sdev, csdev);
+	if (result != SCSI_DH_OK)
+		goto done;
+
+	/* Update status */
+	result = clariion_send_inquiry(sdev, csdev);
+
+done:
+	return result;
+}
+
+static const struct {
+	char *vendor;
+	char *model;
+} clariion_dev_list[] = {
+	{"DGC", "RAID"},
+	{"DGC", "DISK"},
+	{"DGC", "VRAID"},
+	{NULL, NULL},
+};
+
+static bool clariion_match(struct scsi_device *sdev)
+{
+	int i;
+
+	if (scsi_device_tpgs(sdev))
+		return false;
+
+	for (i = 0; clariion_dev_list[i].vendor; i++) {
+		if (!strncmp(sdev->vendor, clariion_dev_list[i].vendor,
+			strlen(clariion_dev_list[i].vendor)) &&
+		    !strncmp(sdev->model, clariion_dev_list[i].model,
+			strlen(clariion_dev_list[i].model))) {
+			return true;
+		}
+	}
+	return false;
+}
+
+static struct scsi_dh_data *clariion_bus_attach(struct scsi_device *sdev)
+{
+	struct clariion_dh_data *h;
+	int err;
+
+	h = kzalloc(sizeof(*h) , GFP_KERNEL);
+	if (!h)
+		return ERR_PTR(-ENOMEM);
+	h->lun_state = CLARIION_LUN_UNINITIALIZED;
+	h->default_sp = CLARIION_UNBOUND_LU;
+	h->current_sp = CLARIION_UNBOUND_LU;
+
+	err = clariion_std_inquiry(sdev, h);
+	if (err != SCSI_DH_OK)
+		goto failed;
+
+	err = clariion_send_inquiry(sdev, h);
+	if (err != SCSI_DH_OK)
+		goto failed;
+
+	sdev_printk(KERN_INFO, sdev,
+		    "%s: connected to SP %c Port %d (%s, default SP %c)\n",
+		    CLARIION_NAME, h->current_sp + 'A',
+		    h->port, lun_state[h->lun_state],
+		    h->default_sp + 'A');
+	return &h->dh_data;
+
+failed:
+	kfree(h);
+	return ERR_PTR(-EINVAL);
+}
+
+static void clariion_bus_detach(struct scsi_device *sdev)
+{
+	struct clariion_dh_data *h = get_clariion_data(sdev);
+
+	kfree(h);
+}
+
+static struct scsi_device_handler clariion_dh = {
+	.name		= CLARIION_NAME,
+	.module		= THIS_MODULE,
+	.attach		= clariion_bus_attach,
+	.detach		= clariion_bus_detach,
+	.check_sense	= clariion_check_sense,
+	.activate	= clariion_activate,
+	.prep_fn	= clariion_prep_fn,
+	.set_params	= clariion_set_params,
+	.match		= clariion_match,
+};
+
+static int __init clariion_init(void)
+{
+	int r;
+
+	r = scsi_register_device_handler(&clariion_dh);
+	if (r != 0)
+		printk(KERN_ERR "%s: Failed to register scsi device handler.",
+			CLARIION_NAME);
+	return r;
+}
+
+static void __exit clariion_exit(void)
+{
+	scsi_unregister_device_handler(&clariion_dh);
+}
+
+module_init(clariion_init);
+module_exit(clariion_exit);
+
+MODULE_DESCRIPTION("EMC CX/AX/FC-family driver");
+MODULE_AUTHOR("Mike Christie <michaelc@cs.wisc.edu>, Chandra Seetharaman <sekharan@us.ibm.com>");
+MODULE_LICENSE("GPL");
diff --git a/kernel/drivers/scsi/device_handler/scsi_dh_hp_sw.c b/kernel/drivers/scsi/device_handler/scsi_dh_hp_sw.c
new file mode 100644
index 000000000..485d99544
--- /dev/null
+++ b/kernel/drivers/scsi/device_handler/scsi_dh_hp_sw.c
@@ -0,0 +1,400 @@
+/*
+ * Basic HP/COMPAQ MSA 1000 support. This is only needed if your HW cannot be
+ * upgraded.
+ *
+ * Copyright (C) 2006 Red Hat, Inc.  All rights reserved.
+ * Copyright (C) 2006 Mike Christie
+ * Copyright (C) 2008 Hannes Reinecke <hare@suse.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <scsi/scsi.h>
+#include <scsi/scsi_dbg.h>
+#include <scsi/scsi_eh.h>
+#include <scsi/scsi_dh.h>
+
+#define HP_SW_NAME			"hp_sw"
+
+#define HP_SW_TIMEOUT			(60 * HZ)
+#define HP_SW_RETRIES			3
+
+#define HP_SW_PATH_UNINITIALIZED	-1
+#define HP_SW_PATH_ACTIVE		0
+#define HP_SW_PATH_PASSIVE		1
+
+struct hp_sw_dh_data {
+	struct scsi_dh_data dh_data;
+	unsigned char sense[SCSI_SENSE_BUFFERSIZE];
+	int path_state;
+	int retries;
+	int retry_cnt;
+	struct scsi_device *sdev;
+	activate_complete	callback_fn;
+	void			*callback_data;
+};
+
+static int hp_sw_start_stop(struct hp_sw_dh_data *);
+
+static inline struct hp_sw_dh_data *get_hp_sw_data(struct scsi_device *sdev)
+{
+	return container_of(sdev->scsi_dh_data, struct hp_sw_dh_data, dh_data);
+}
+
+/*
+ * tur_done - Handle TEST UNIT READY return status
+ * @sdev: sdev the command has been sent to
+ * @errors: blk error code
+ *
+ * Returns SCSI_DH_DEV_OFFLINED if the sdev is on the passive path
+ */
+static int tur_done(struct scsi_device *sdev, unsigned char *sense)
+{
+	struct scsi_sense_hdr sshdr;
+	int ret;
+
+	ret = scsi_normalize_sense(sense, SCSI_SENSE_BUFFERSIZE, &sshdr);
+	if (!ret) {
+		sdev_printk(KERN_WARNING, sdev,
+			    "%s: sending tur failed, no sense available\n",
+			    HP_SW_NAME);
+		ret = SCSI_DH_IO;
+		goto done;
+	}
+	switch (sshdr.sense_key) {
+	case UNIT_ATTENTION:
+		ret = SCSI_DH_IMM_RETRY;
+		break;
+	case NOT_READY:
+		if ((sshdr.asc == 0x04) && (sshdr.ascq == 2)) {
+			/*
+			 * LUN not ready - Initialization command required
+			 *
+			 * This is the passive path
+			 */
+			ret = SCSI_DH_DEV_OFFLINED;
+			break;
+		}
+		/* Fallthrough */
+	default:
+		sdev_printk(KERN_WARNING, sdev,
+			   "%s: sending tur failed, sense %x/%x/%x\n",
+			   HP_SW_NAME, sshdr.sense_key, sshdr.asc,
+			   sshdr.ascq);
+		break;
+	}
+
+done:
+	return ret;
+}
+
+/*
+ * hp_sw_tur - Send TEST UNIT READY
+ * @sdev: sdev command should be sent to
+ *
+ * Use the TEST UNIT READY command to determine
+ * the path state.
+ */
+static int hp_sw_tur(struct scsi_device *sdev, struct hp_sw_dh_data *h)
+{
+	struct request *req;
+	int ret;
+
+retry:
+	req = blk_get_request(sdev->request_queue, WRITE, GFP_NOIO);
+	if (IS_ERR(req))
+		return SCSI_DH_RES_TEMP_UNAVAIL;
+
+	blk_rq_set_block_pc(req);
+	req->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+			  REQ_FAILFAST_DRIVER;
+	req->cmd_len = COMMAND_SIZE(TEST_UNIT_READY);
+	req->cmd[0] = TEST_UNIT_READY;
+	req->timeout = HP_SW_TIMEOUT;
+	req->sense = h->sense;
+	memset(req->sense, 0, SCSI_SENSE_BUFFERSIZE);
+	req->sense_len = 0;
+
+	ret = blk_execute_rq(req->q, NULL, req, 1);
+	if (ret == -EIO) {
+		if (req->sense_len > 0) {
+			ret = tur_done(sdev, h->sense);
+		} else {
+			sdev_printk(KERN_WARNING, sdev,
+				    "%s: sending tur failed with %x\n",
+				    HP_SW_NAME, req->errors);
+			ret = SCSI_DH_IO;
+		}
+	} else {
+		h->path_state = HP_SW_PATH_ACTIVE;
+		ret = SCSI_DH_OK;
+	}
+	if (ret == SCSI_DH_IMM_RETRY) {
+		blk_put_request(req);
+		goto retry;
+	}
+	if (ret == SCSI_DH_DEV_OFFLINED) {
+		h->path_state = HP_SW_PATH_PASSIVE;
+		ret = SCSI_DH_OK;
+	}
+
+	blk_put_request(req);
+
+	return ret;
+}
+
+/*
+ * start_done - Handle START STOP UNIT return status
+ * @sdev: sdev the command has been sent to
+ * @errors: blk error code
+ */
+static int start_done(struct scsi_device *sdev, unsigned char *sense)
+{
+	struct scsi_sense_hdr sshdr;
+	int rc;
+
+	rc = scsi_normalize_sense(sense, SCSI_SENSE_BUFFERSIZE, &sshdr);
+	if (!rc) {
+		sdev_printk(KERN_WARNING, sdev,
+			    "%s: sending start_stop_unit failed, "
+			    "no sense available\n",
+			    HP_SW_NAME);
+		return SCSI_DH_IO;
+	}
+	switch (sshdr.sense_key) {
+	case NOT_READY:
+		if ((sshdr.asc == 0x04) && (sshdr.ascq == 3)) {
+			/*
+			 * LUN not ready - manual intervention required
+			 *
+			 * Switch-over in progress, retry.
+			 */
+			rc = SCSI_DH_RETRY;
+			break;
+		}
+		/* fall through */
+	default:
+		sdev_printk(KERN_WARNING, sdev,
+			   "%s: sending start_stop_unit failed, sense %x/%x/%x\n",
+			   HP_SW_NAME, sshdr.sense_key, sshdr.asc,
+			   sshdr.ascq);
+		rc = SCSI_DH_IO;
+	}
+
+	return rc;
+}
+
+static void start_stop_endio(struct request *req, int error)
+{
+	struct hp_sw_dh_data *h = req->end_io_data;
+	unsigned err = SCSI_DH_OK;
+
+	if (error || host_byte(req->errors) != DID_OK ||
+			msg_byte(req->errors) != COMMAND_COMPLETE) {
+		sdev_printk(KERN_WARNING, h->sdev,
+			    "%s: sending start_stop_unit failed with %x\n",
+			    HP_SW_NAME, req->errors);
+		err = SCSI_DH_IO;
+		goto done;
+	}
+
+	if (req->sense_len > 0) {
+		err = start_done(h->sdev, h->sense);
+		if (err == SCSI_DH_RETRY) {
+			err = SCSI_DH_IO;
+			if (--h->retry_cnt) {
+				blk_put_request(req);
+				err = hp_sw_start_stop(h);
+				if (err == SCSI_DH_OK)
+					return;
+			}
+		}
+	}
+done:
+	req->end_io_data = NULL;
+	__blk_put_request(req->q, req);
+	if (h->callback_fn) {
+		h->callback_fn(h->callback_data, err);
+		h->callback_fn = h->callback_data = NULL;
+	}
+	return;
+
+}
+
+/*
+ * hp_sw_start_stop - Send START STOP UNIT command
+ * @sdev: sdev command should be sent to
+ *
+ * Sending START STOP UNIT activates the SP.
+ */
+static int hp_sw_start_stop(struct hp_sw_dh_data *h)
+{
+	struct request *req;
+
+	req = blk_get_request(h->sdev->request_queue, WRITE, GFP_ATOMIC);
+	if (IS_ERR(req))
+		return SCSI_DH_RES_TEMP_UNAVAIL;
+
+	blk_rq_set_block_pc(req);
+	req->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+			  REQ_FAILFAST_DRIVER;
+	req->cmd_len = COMMAND_SIZE(START_STOP);
+	req->cmd[0] = START_STOP;
+	req->cmd[4] = 1;	/* Start spin cycle */
+	req->timeout = HP_SW_TIMEOUT;
+	req->sense = h->sense;
+	memset(req->sense, 0, SCSI_SENSE_BUFFERSIZE);
+	req->sense_len = 0;
+	req->end_io_data = h;
+
+	blk_execute_rq_nowait(req->q, NULL, req, 1, start_stop_endio);
+	return SCSI_DH_OK;
+}
+
+static int hp_sw_prep_fn(struct scsi_device *sdev, struct request *req)
+{
+	struct hp_sw_dh_data *h = get_hp_sw_data(sdev);
+	int ret = BLKPREP_OK;
+
+	if (h->path_state != HP_SW_PATH_ACTIVE) {
+		ret = BLKPREP_KILL;
+		req->cmd_flags |= REQ_QUIET;
+	}
+	return ret;
+
+}
+
+/*
+ * hp_sw_activate - Activate a path
+ * @sdev: sdev on the path to be activated
+ *
+ * The HP Active/Passive firmware is pretty simple;
+ * the passive path reports NOT READY with sense codes
+ * 0x04/0x02; a START STOP UNIT command will then
+ * activate the passive path (and deactivate the
+ * previously active one).
+ */
+static int hp_sw_activate(struct scsi_device *sdev,
+				activate_complete fn, void *data)
+{
+	int ret = SCSI_DH_OK;
+	struct hp_sw_dh_data *h = get_hp_sw_data(sdev);
+
+	ret = hp_sw_tur(sdev, h);
+
+	if (ret == SCSI_DH_OK && h->path_state == HP_SW_PATH_PASSIVE) {
+		h->retry_cnt = h->retries;
+		h->callback_fn = fn;
+		h->callback_data = data;
+		ret = hp_sw_start_stop(h);
+		if (ret == SCSI_DH_OK)
+			return 0;
+		h->callback_fn = h->callback_data = NULL;
+	}
+
+	if (fn)
+		fn(data, ret);
+	return 0;
+}
+
+static const struct {
+	char *vendor;
+	char *model;
+} hp_sw_dh_data_list[] = {
+	{"COMPAQ", "MSA1000 VOLUME"},
+	{"COMPAQ", "HSV110"},
+	{"HP", "HSV100"},
+	{"DEC", "HSG80"},
+	{NULL, NULL},
+};
+
+static bool hp_sw_match(struct scsi_device *sdev)
+{
+	int i;
+
+	if (scsi_device_tpgs(sdev))
+		return false;
+
+	for (i = 0; hp_sw_dh_data_list[i].vendor; i++) {
+		if (!strncmp(sdev->vendor, hp_sw_dh_data_list[i].vendor,
+			strlen(hp_sw_dh_data_list[i].vendor)) &&
+		    !strncmp(sdev->model, hp_sw_dh_data_list[i].model,
+			strlen(hp_sw_dh_data_list[i].model))) {
+			return true;
+		}
+	}
+	return false;
+}
+
+static struct scsi_dh_data *hp_sw_bus_attach(struct scsi_device *sdev)
+{
+	struct hp_sw_dh_data *h;
+	int ret;
+
+	h = kzalloc(sizeof(*h), GFP_KERNEL);
+	if (!h)
+		return ERR_PTR(-ENOMEM);
+	h->path_state = HP_SW_PATH_UNINITIALIZED;
+	h->retries = HP_SW_RETRIES;
+	h->sdev = sdev;
+
+	ret = hp_sw_tur(sdev, h);
+	if (ret != SCSI_DH_OK || h->path_state == HP_SW_PATH_UNINITIALIZED)
+		goto failed;
+
+	sdev_printk(KERN_INFO, sdev, "%s: attached to %s path\n",
+		    HP_SW_NAME, h->path_state == HP_SW_PATH_ACTIVE?
+		    "active":"passive");
+	return &h->dh_data;
+failed:
+	kfree(h);
+	return ERR_PTR(-EINVAL);
+}
+
+static void hp_sw_bus_detach( struct scsi_device *sdev )
+{
+	struct hp_sw_dh_data *h = get_hp_sw_data(sdev);
+
+	kfree(h);
+}
+
+static struct scsi_device_handler hp_sw_dh = {
+	.name		= HP_SW_NAME,
+	.module		= THIS_MODULE,
+	.attach		= hp_sw_bus_attach,
+	.detach		= hp_sw_bus_detach,
+	.activate	= hp_sw_activate,
+	.prep_fn	= hp_sw_prep_fn,
+	.match		= hp_sw_match,
+};
+
+static int __init hp_sw_init(void)
+{
+	return scsi_register_device_handler(&hp_sw_dh);
+}
+
+static void __exit hp_sw_exit(void)
+{
+	scsi_unregister_device_handler(&hp_sw_dh);
+}
+
+module_init(hp_sw_init);
+module_exit(hp_sw_exit);
+
+MODULE_DESCRIPTION("HP Active/Passive driver");
+MODULE_AUTHOR("Mike Christie <michaelc@cs.wisc.edu");
+MODULE_LICENSE("GPL");
diff --git a/kernel/drivers/scsi/device_handler/scsi_dh_rdac.c b/kernel/drivers/scsi/device_handler/scsi_dh_rdac.c
new file mode 100644
index 000000000..b46ace3d4
--- /dev/null
+++ b/kernel/drivers/scsi/device_handler/scsi_dh_rdac.c
@@ -0,0 +1,937 @@
+/*
+ * LSI/Engenio/NetApp E-Series RDAC SCSI Device Handler
+ *
+ * Copyright (C) 2005 Mike Christie. All rights reserved.
+ * Copyright (C) Chandra Seetharaman, IBM Corp. 2007
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+#include <scsi/scsi.h>
+#include <scsi/scsi_eh.h>
+#include <scsi/scsi_dh.h>
+#include <linux/workqueue.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+
+#define RDAC_NAME "rdac"
+#define RDAC_RETRY_COUNT 5
+
+/*
+ * LSI mode page stuff
+ *
+ * These struct definitions and the forming of the
+ * mode page were taken from the LSI RDAC 2.4 GPL'd
+ * driver, and then converted to Linux conventions.
+ */
+#define RDAC_QUIESCENCE_TIME 20
+/*
+ * Page Codes
+ */
+#define RDAC_PAGE_CODE_REDUNDANT_CONTROLLER 0x2c
+
+/*
+ * Controller modes definitions
+ */
+#define RDAC_MODE_TRANSFER_SPECIFIED_LUNS	0x02
+
+/*
+ * RDAC Options field
+ */
+#define RDAC_FORCED_QUIESENCE 0x02
+
+#define RDAC_TIMEOUT	(60 * HZ)
+#define RDAC_RETRIES	3
+
+struct rdac_mode_6_hdr {
+	u8	data_len;
+	u8	medium_type;
+	u8	device_params;
+	u8	block_desc_len;
+};
+
+struct rdac_mode_10_hdr {
+	u16	data_len;
+	u8	medium_type;
+	u8	device_params;
+	u16	reserved;
+	u16	block_desc_len;
+};
+
+struct rdac_mode_common {
+	u8	controller_serial[16];
+	u8	alt_controller_serial[16];
+	u8	rdac_mode[2];
+	u8	alt_rdac_mode[2];
+	u8	quiescence_timeout;
+	u8	rdac_options;
+};
+
+struct rdac_pg_legacy {
+	struct rdac_mode_6_hdr hdr;
+	u8	page_code;
+	u8	page_len;
+	struct rdac_mode_common common;
+#define MODE6_MAX_LUN	32
+	u8	lun_table[MODE6_MAX_LUN];
+	u8	reserved2[32];
+	u8	reserved3;
+	u8	reserved4;
+};
+
+struct rdac_pg_expanded {
+	struct rdac_mode_10_hdr hdr;
+	u8	page_code;
+	u8	subpage_code;
+	u8	page_len[2];
+	struct rdac_mode_common common;
+	u8	lun_table[256];
+	u8	reserved3;
+	u8	reserved4;
+};
+
+struct c9_inquiry {
+	u8	peripheral_info;
+	u8	page_code;	/* 0xC9 */
+	u8	reserved1;
+	u8	page_len;
+	u8	page_id[4];	/* "vace" */
+	u8	avte_cvp;
+	u8	path_prio;
+	u8	reserved2[38];
+};
+
+#define SUBSYS_ID_LEN	16
+#define SLOT_ID_LEN	2
+#define ARRAY_LABEL_LEN	31
+
+struct c4_inquiry {
+	u8	peripheral_info;
+	u8	page_code;	/* 0xC4 */
+	u8	reserved1;
+	u8	page_len;
+	u8	page_id[4];	/* "subs" */
+	u8	subsys_id[SUBSYS_ID_LEN];
+	u8	revision[4];
+	u8	slot_id[SLOT_ID_LEN];
+	u8	reserved[2];
+};
+
+#define UNIQUE_ID_LEN 16
+struct c8_inquiry {
+	u8	peripheral_info;
+	u8	page_code; /* 0xC8 */
+	u8	reserved1;
+	u8	page_len;
+	u8	page_id[4]; /* "edid" */
+	u8	reserved2[3];
+	u8	vol_uniq_id_len;
+	u8	vol_uniq_id[16];
+	u8	vol_user_label_len;
+	u8	vol_user_label[60];
+	u8	array_uniq_id_len;
+	u8	array_unique_id[UNIQUE_ID_LEN];
+	u8	array_user_label_len;
+	u8	array_user_label[60];
+	u8	lun[8];
+};
+
+struct rdac_controller {
+	u8			array_id[UNIQUE_ID_LEN];
+	int			use_ms10;
+	struct kref		kref;
+	struct list_head	node; /* list of all controllers */
+	union			{
+		struct rdac_pg_legacy legacy;
+		struct rdac_pg_expanded expanded;
+	} mode_select;
+	u8	index;
+	u8	array_name[ARRAY_LABEL_LEN];
+	struct Scsi_Host	*host;
+	spinlock_t		ms_lock;
+	int			ms_queued;
+	struct work_struct	ms_work;
+	struct scsi_device	*ms_sdev;
+	struct list_head	ms_head;
+};
+
+struct c2_inquiry {
+	u8	peripheral_info;
+	u8	page_code;	/* 0xC2 */
+	u8	reserved1;
+	u8	page_len;
+	u8	page_id[4];	/* "swr4" */
+	u8	sw_version[3];
+	u8	sw_date[3];
+	u8	features_enabled;
+	u8	max_lun_supported;
+	u8	partitions[239]; /* Total allocation length should be 0xFF */
+};
+
+struct rdac_dh_data {
+	struct scsi_dh_data	dh_data;
+	struct rdac_controller	*ctlr;
+#define UNINITIALIZED_LUN	(1 << 8)
+	unsigned		lun;
+
+#define RDAC_MODE		0
+#define RDAC_MODE_AVT		1
+#define RDAC_MODE_IOSHIP	2
+	unsigned char		mode;
+
+#define RDAC_STATE_ACTIVE	0
+#define RDAC_STATE_PASSIVE	1
+	unsigned char		state;
+
+#define RDAC_LUN_UNOWNED	0
+#define RDAC_LUN_OWNED		1
+	char			lun_state;
+
+#define RDAC_PREFERRED		0
+#define RDAC_NON_PREFERRED	1
+	char			preferred;
+
+	unsigned char		sense[SCSI_SENSE_BUFFERSIZE];
+	union			{
+		struct c2_inquiry c2;
+		struct c4_inquiry c4;
+		struct c8_inquiry c8;
+		struct c9_inquiry c9;
+	} inq;
+};
+
+static const char *mode[] = {
+	"RDAC",
+	"AVT",
+	"IOSHIP",
+};
+static const char *lun_state[] =
+{
+	"unowned",
+	"owned",
+};
+
+struct rdac_queue_data {
+	struct list_head	entry;
+	struct rdac_dh_data	*h;
+	activate_complete	callback_fn;
+	void			*callback_data;
+};
+
+static LIST_HEAD(ctlr_list);
+static DEFINE_SPINLOCK(list_lock);
+static struct workqueue_struct *kmpath_rdacd;
+static void send_mode_select(struct work_struct *work);
+
+/*
+ * module parameter to enable rdac debug logging.
+ * 2 bits for each type of logging, only two types defined for now
+ * Can be enhanced if required at later point
+ */
+static int rdac_logging = 1;
+module_param(rdac_logging, int, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(rdac_logging, "A bit mask of rdac logging levels, "
+		"Default is 1 - failover logging enabled, "
+		"set it to 0xF to enable all the logs");
+
+#define RDAC_LOG_FAILOVER	0
+#define RDAC_LOG_SENSE		2
+
+#define RDAC_LOG_BITS		2
+
+#define RDAC_LOG_LEVEL(SHIFT)  \
+	((rdac_logging >> (SHIFT)) & ((1 << (RDAC_LOG_BITS)) - 1))
+
+#define RDAC_LOG(SHIFT, sdev, f, arg...) \
+do { \
+	if (unlikely(RDAC_LOG_LEVEL(SHIFT))) \
+		sdev_printk(KERN_INFO, sdev, RDAC_NAME ": " f "\n", ## arg); \
+} while (0);
+
+static inline struct rdac_dh_data *get_rdac_data(struct scsi_device *sdev)
+{
+	return container_of(sdev->scsi_dh_data, struct rdac_dh_data, dh_data);
+}
+
+static struct request *get_rdac_req(struct scsi_device *sdev,
+			void *buffer, unsigned buflen, int rw)
+{
+	struct request *rq;
+	struct request_queue *q = sdev->request_queue;
+
+	rq = blk_get_request(q, rw, GFP_NOIO);
+
+	if (IS_ERR(rq)) {
+		sdev_printk(KERN_INFO, sdev,
+				"get_rdac_req: blk_get_request failed.\n");
+		return NULL;
+	}
+	blk_rq_set_block_pc(rq);
+
+	if (buflen && blk_rq_map_kern(q, rq, buffer, buflen, GFP_NOIO)) {
+		blk_put_request(rq);
+		sdev_printk(KERN_INFO, sdev,
+				"get_rdac_req: blk_rq_map_kern failed.\n");
+		return NULL;
+	}
+
+	rq->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+			 REQ_FAILFAST_DRIVER;
+	rq->retries = RDAC_RETRIES;
+	rq->timeout = RDAC_TIMEOUT;
+
+	return rq;
+}
+
+static struct request *rdac_failover_get(struct scsi_device *sdev,
+			struct rdac_dh_data *h, struct list_head *list)
+{
+	struct request *rq;
+	struct rdac_mode_common *common;
+	unsigned data_size;
+	struct rdac_queue_data *qdata;
+	u8 *lun_table;
+
+	if (h->ctlr->use_ms10) {
+		struct rdac_pg_expanded *rdac_pg;
+
+		data_size = sizeof(struct rdac_pg_expanded);
+		rdac_pg = &h->ctlr->mode_select.expanded;
+		memset(rdac_pg, 0, data_size);
+		common = &rdac_pg->common;
+		rdac_pg->page_code = RDAC_PAGE_CODE_REDUNDANT_CONTROLLER + 0x40;
+		rdac_pg->subpage_code = 0x1;
+		rdac_pg->page_len[0] = 0x01;
+		rdac_pg->page_len[1] = 0x28;
+		lun_table = rdac_pg->lun_table;
+	} else {
+		struct rdac_pg_legacy *rdac_pg;
+
+		data_size = sizeof(struct rdac_pg_legacy);
+		rdac_pg = &h->ctlr->mode_select.legacy;
+		memset(rdac_pg, 0, data_size);
+		common = &rdac_pg->common;
+		rdac_pg->page_code = RDAC_PAGE_CODE_REDUNDANT_CONTROLLER;
+		rdac_pg->page_len = 0x68;
+		lun_table = rdac_pg->lun_table;
+	}
+	common->rdac_mode[1] = RDAC_MODE_TRANSFER_SPECIFIED_LUNS;
+	common->quiescence_timeout = RDAC_QUIESCENCE_TIME;
+	common->rdac_options = RDAC_FORCED_QUIESENCE;
+
+	list_for_each_entry(qdata, list, entry) {
+		lun_table[qdata->h->lun] = 0x81;
+	}
+
+	/* get request for block layer packet command */
+	rq = get_rdac_req(sdev, &h->ctlr->mode_select, data_size, WRITE);
+	if (!rq)
+		return NULL;
+
+	/* Prepare the command. */
+	if (h->ctlr->use_ms10) {
+		rq->cmd[0] = MODE_SELECT_10;
+		rq->cmd[7] = data_size >> 8;
+		rq->cmd[8] = data_size & 0xff;
+	} else {
+		rq->cmd[0] = MODE_SELECT;
+		rq->cmd[4] = data_size;
+	}
+	rq->cmd_len = COMMAND_SIZE(rq->cmd[0]);
+
+	rq->sense = h->sense;
+	memset(rq->sense, 0, SCSI_SENSE_BUFFERSIZE);
+	rq->sense_len = 0;
+
+	return rq;
+}
+
+static void release_controller(struct kref *kref)
+{
+	struct rdac_controller *ctlr;
+	ctlr = container_of(kref, struct rdac_controller, kref);
+
+	list_del(&ctlr->node);
+	kfree(ctlr);
+}
+
+static struct rdac_controller *get_controller(int index, char *array_name,
+			u8 *array_id, struct scsi_device *sdev)
+{
+	struct rdac_controller *ctlr, *tmp;
+
+	list_for_each_entry(tmp, &ctlr_list, node) {
+		if ((memcmp(tmp->array_id, array_id, UNIQUE_ID_LEN) == 0) &&
+			  (tmp->index == index) &&
+			  (tmp->host == sdev->host)) {
+			kref_get(&tmp->kref);
+			return tmp;
+		}
+	}
+	ctlr = kmalloc(sizeof(*ctlr), GFP_ATOMIC);
+	if (!ctlr)
+		return NULL;
+
+	/* initialize fields of controller */
+	memcpy(ctlr->array_id, array_id, UNIQUE_ID_LEN);
+	ctlr->index = index;
+	ctlr->host = sdev->host;
+	memcpy(ctlr->array_name, array_name, ARRAY_LABEL_LEN);
+
+	kref_init(&ctlr->kref);
+	ctlr->use_ms10 = -1;
+	ctlr->ms_queued = 0;
+	ctlr->ms_sdev = NULL;
+	spin_lock_init(&ctlr->ms_lock);
+	INIT_WORK(&ctlr->ms_work, send_mode_select);
+	INIT_LIST_HEAD(&ctlr->ms_head);
+	list_add(&ctlr->node, &ctlr_list);
+
+	return ctlr;
+}
+
+static int submit_inquiry(struct scsi_device *sdev, int page_code,
+			  unsigned int len, struct rdac_dh_data *h)
+{
+	struct request *rq;
+	struct request_queue *q = sdev->request_queue;
+	int err = SCSI_DH_RES_TEMP_UNAVAIL;
+
+	rq = get_rdac_req(sdev, &h->inq, len, READ);
+	if (!rq)
+		goto done;
+
+	/* Prepare the command. */
+	rq->cmd[0] = INQUIRY;
+	rq->cmd[1] = 1;
+	rq->cmd[2] = page_code;
+	rq->cmd[4] = len;
+	rq->cmd_len = COMMAND_SIZE(INQUIRY);
+
+	rq->sense = h->sense;
+	memset(rq->sense, 0, SCSI_SENSE_BUFFERSIZE);
+	rq->sense_len = 0;
+
+	err = blk_execute_rq(q, NULL, rq, 1);
+	if (err == -EIO)
+		err = SCSI_DH_IO;
+
+	blk_put_request(rq);
+done:
+	return err;
+}
+
+static int get_lun_info(struct scsi_device *sdev, struct rdac_dh_data *h,
+			char *array_name, u8 *array_id)
+{
+	int err, i;
+	struct c8_inquiry *inqp;
+
+	err = submit_inquiry(sdev, 0xC8, sizeof(struct c8_inquiry), h);
+	if (err == SCSI_DH_OK) {
+		inqp = &h->inq.c8;
+		if (inqp->page_code != 0xc8)
+			return SCSI_DH_NOSYS;
+		if (inqp->page_id[0] != 'e' || inqp->page_id[1] != 'd' ||
+		    inqp->page_id[2] != 'i' || inqp->page_id[3] != 'd')
+			return SCSI_DH_NOSYS;
+		h->lun = inqp->lun[7]; /* Uses only the last byte */
+
+		for(i=0; i<ARRAY_LABEL_LEN-1; ++i)
+			*(array_name+i) = inqp->array_user_label[(2*i)+1];
+
+		*(array_name+ARRAY_LABEL_LEN-1) = '\0';
+		memset(array_id, 0, UNIQUE_ID_LEN);
+		memcpy(array_id, inqp->array_unique_id, inqp->array_uniq_id_len);
+	}
+	return err;
+}
+
+static int check_ownership(struct scsi_device *sdev, struct rdac_dh_data *h)
+{
+	int err;
+	struct c9_inquiry *inqp;
+
+	h->state = RDAC_STATE_ACTIVE;
+	err = submit_inquiry(sdev, 0xC9, sizeof(struct c9_inquiry), h);
+	if (err == SCSI_DH_OK) {
+		inqp = &h->inq.c9;
+		/* detect the operating mode */
+		if ((inqp->avte_cvp >> 5) & 0x1)
+			h->mode = RDAC_MODE_IOSHIP; /* LUN in IOSHIP mode */
+		else if (inqp->avte_cvp >> 7)
+			h->mode = RDAC_MODE_AVT; /* LUN in AVT mode */
+		else
+			h->mode = RDAC_MODE; /* LUN in RDAC mode */
+
+		/* Update ownership */
+		if (inqp->avte_cvp & 0x1)
+			h->lun_state = RDAC_LUN_OWNED;
+		else {
+			h->lun_state = RDAC_LUN_UNOWNED;
+			if (h->mode == RDAC_MODE)
+				h->state = RDAC_STATE_PASSIVE;
+		}
+
+		/* Update path prio*/
+		if (inqp->path_prio & 0x1)
+			h->preferred = RDAC_PREFERRED;
+		else
+			h->preferred = RDAC_NON_PREFERRED;
+	}
+
+	return err;
+}
+
+static int initialize_controller(struct scsi_device *sdev,
+		struct rdac_dh_data *h, char *array_name, u8 *array_id)
+{
+	int err, index;
+	struct c4_inquiry *inqp;
+
+	err = submit_inquiry(sdev, 0xC4, sizeof(struct c4_inquiry), h);
+	if (err == SCSI_DH_OK) {
+		inqp = &h->inq.c4;
+		/* get the controller index */
+		if (inqp->slot_id[1] == 0x31)
+			index = 0;
+		else
+			index = 1;
+
+		spin_lock(&list_lock);
+		h->ctlr = get_controller(index, array_name, array_id, sdev);
+		if (!h->ctlr)
+			err = SCSI_DH_RES_TEMP_UNAVAIL;
+		spin_unlock(&list_lock);
+	}
+	return err;
+}
+
+static int set_mode_select(struct scsi_device *sdev, struct rdac_dh_data *h)
+{
+	int err;
+	struct c2_inquiry *inqp;
+
+	err = submit_inquiry(sdev, 0xC2, sizeof(struct c2_inquiry), h);
+	if (err == SCSI_DH_OK) {
+		inqp = &h->inq.c2;
+		/*
+		 * If more than MODE6_MAX_LUN luns are supported, use
+		 * mode select 10
+		 */
+		if (inqp->max_lun_supported >= MODE6_MAX_LUN)
+			h->ctlr->use_ms10 = 1;
+		else
+			h->ctlr->use_ms10 = 0;
+	}
+	return err;
+}
+
+static int mode_select_handle_sense(struct scsi_device *sdev,
+					unsigned char *sensebuf)
+{
+	struct scsi_sense_hdr sense_hdr;
+	int err = SCSI_DH_IO, ret;
+	struct rdac_dh_data *h = get_rdac_data(sdev);
+
+	ret = scsi_normalize_sense(sensebuf, SCSI_SENSE_BUFFERSIZE, &sense_hdr);
+	if (!ret)
+		goto done;
+
+	switch (sense_hdr.sense_key) {
+	case NO_SENSE:
+	case ABORTED_COMMAND:
+	case UNIT_ATTENTION:
+		err = SCSI_DH_RETRY;
+		break;
+	case NOT_READY:
+		if (sense_hdr.asc == 0x04 && sense_hdr.ascq == 0x01)
+			/* LUN Not Ready and is in the Process of Becoming
+			 * Ready
+			 */
+			err = SCSI_DH_RETRY;
+		break;
+	case ILLEGAL_REQUEST:
+		if (sense_hdr.asc == 0x91 && sense_hdr.ascq == 0x36)
+			/*
+			 * Command Lock contention
+			 */
+			err = SCSI_DH_RETRY;
+		break;
+	default:
+		break;
+	}
+
+	RDAC_LOG(RDAC_LOG_FAILOVER, sdev, "array %s, ctlr %d, "
+		"MODE_SELECT returned with sense %02x/%02x/%02x",
+		(char *) h->ctlr->array_name, h->ctlr->index,
+		sense_hdr.sense_key, sense_hdr.asc, sense_hdr.ascq);
+
+done:
+	return err;
+}
+
+static void send_mode_select(struct work_struct *work)
+{
+	struct rdac_controller *ctlr =
+		container_of(work, struct rdac_controller, ms_work);
+	struct request *rq;
+	struct scsi_device *sdev = ctlr->ms_sdev;
+	struct rdac_dh_data *h = get_rdac_data(sdev);
+	struct request_queue *q = sdev->request_queue;
+	int err, retry_cnt = RDAC_RETRY_COUNT;
+	struct rdac_queue_data *tmp, *qdata;
+	LIST_HEAD(list);
+
+	spin_lock(&ctlr->ms_lock);
+	list_splice_init(&ctlr->ms_head, &list);
+	ctlr->ms_queued = 0;
+	ctlr->ms_sdev = NULL;
+	spin_unlock(&ctlr->ms_lock);
+
+retry:
+	err = SCSI_DH_RES_TEMP_UNAVAIL;
+	rq = rdac_failover_get(sdev, h, &list);
+	if (!rq)
+		goto done;
+
+	RDAC_LOG(RDAC_LOG_FAILOVER, sdev, "array %s, ctlr %d, "
+		"%s MODE_SELECT command",
+		(char *) h->ctlr->array_name, h->ctlr->index,
+		(retry_cnt == RDAC_RETRY_COUNT) ? "queueing" : "retrying");
+
+	err = blk_execute_rq(q, NULL, rq, 1);
+	blk_put_request(rq);
+	if (err != SCSI_DH_OK) {
+		err = mode_select_handle_sense(sdev, h->sense);
+		if (err == SCSI_DH_RETRY && retry_cnt--)
+			goto retry;
+	}
+	if (err == SCSI_DH_OK) {
+		h->state = RDAC_STATE_ACTIVE;
+		RDAC_LOG(RDAC_LOG_FAILOVER, sdev, "array %s, ctlr %d, "
+				"MODE_SELECT completed",
+				(char *) h->ctlr->array_name, h->ctlr->index);
+	}
+
+done:
+	list_for_each_entry_safe(qdata, tmp, &list, entry) {
+		list_del(&qdata->entry);
+		if (err == SCSI_DH_OK)
+			qdata->h->state = RDAC_STATE_ACTIVE;
+		if (qdata->callback_fn)
+			qdata->callback_fn(qdata->callback_data, err);
+		kfree(qdata);
+	}
+	return;
+}
+
+static int queue_mode_select(struct scsi_device *sdev,
+				activate_complete fn, void *data)
+{
+	struct rdac_queue_data *qdata;
+	struct rdac_controller *ctlr;
+
+	qdata = kzalloc(sizeof(*qdata), GFP_KERNEL);
+	if (!qdata)
+		return SCSI_DH_RETRY;
+
+	qdata->h = get_rdac_data(sdev);
+	qdata->callback_fn = fn;
+	qdata->callback_data = data;
+
+	ctlr = qdata->h->ctlr;
+	spin_lock(&ctlr->ms_lock);
+	list_add_tail(&qdata->entry, &ctlr->ms_head);
+	if (!ctlr->ms_queued) {
+		ctlr->ms_queued = 1;
+		ctlr->ms_sdev = sdev;
+		queue_work(kmpath_rdacd, &ctlr->ms_work);
+	}
+	spin_unlock(&ctlr->ms_lock);
+	return SCSI_DH_OK;
+}
+
+static int rdac_activate(struct scsi_device *sdev,
+			activate_complete fn, void *data)
+{
+	struct rdac_dh_data *h = get_rdac_data(sdev);
+	int err = SCSI_DH_OK;
+	int act = 0;
+
+	err = check_ownership(sdev, h);
+	if (err != SCSI_DH_OK)
+		goto done;
+
+	switch (h->mode) {
+	case RDAC_MODE:
+		if (h->lun_state == RDAC_LUN_UNOWNED)
+			act = 1;
+		break;
+	case RDAC_MODE_IOSHIP:
+		if ((h->lun_state == RDAC_LUN_UNOWNED) &&
+		    (h->preferred == RDAC_PREFERRED))
+			act = 1;
+		break;
+	default:
+		break;
+	}
+
+	if (act) {
+		err = queue_mode_select(sdev, fn, data);
+		if (err == SCSI_DH_OK)
+			return 0;
+	}
+done:
+	if (fn)
+		fn(data, err);
+	return 0;
+}
+
+static int rdac_prep_fn(struct scsi_device *sdev, struct request *req)
+{
+	struct rdac_dh_data *h = get_rdac_data(sdev);
+	int ret = BLKPREP_OK;
+
+	if (h->state != RDAC_STATE_ACTIVE) {
+		ret = BLKPREP_KILL;
+		req->cmd_flags |= REQ_QUIET;
+	}
+	return ret;
+
+}
+
+static int rdac_check_sense(struct scsi_device *sdev,
+				struct scsi_sense_hdr *sense_hdr)
+{
+	struct rdac_dh_data *h = get_rdac_data(sdev);
+
+	RDAC_LOG(RDAC_LOG_SENSE, sdev, "array %s, ctlr %d, "
+			"I/O returned with sense %02x/%02x/%02x",
+			(char *) h->ctlr->array_name, h->ctlr->index,
+			sense_hdr->sense_key, sense_hdr->asc, sense_hdr->ascq);
+
+	switch (sense_hdr->sense_key) {
+	case NOT_READY:
+		if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x01)
+			/* LUN Not Ready - Logical Unit Not Ready and is in
+			* the process of becoming ready
+			* Just retry.
+			*/
+			return ADD_TO_MLQUEUE;
+		if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x81)
+			/* LUN Not Ready - Storage firmware incompatible
+			 * Manual code synchonisation required.
+			 *
+			 * Nothing we can do here. Try to bypass the path.
+			 */
+			return SUCCESS;
+		if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0xA1)
+			/* LUN Not Ready - Quiescense in progress
+			 *
+			 * Just retry and wait.
+			 */
+			return ADD_TO_MLQUEUE;
+		if (sense_hdr->asc == 0xA1  && sense_hdr->ascq == 0x02)
+			/* LUN Not Ready - Quiescense in progress
+			 * or has been achieved
+			 * Just retry.
+			 */
+			return ADD_TO_MLQUEUE;
+		break;
+	case ILLEGAL_REQUEST:
+		if (sense_hdr->asc == 0x94 && sense_hdr->ascq == 0x01) {
+			/* Invalid Request - Current Logical Unit Ownership.
+			 * Controller is not the current owner of the LUN,
+			 * Fail the path, so that the other path be used.
+			 */
+			h->state = RDAC_STATE_PASSIVE;
+			return SUCCESS;
+		}
+		break;
+	case UNIT_ATTENTION:
+		if (sense_hdr->asc == 0x29 && sense_hdr->ascq == 0x00)
+			/*
+			 * Power On, Reset, or Bus Device Reset, just retry.
+			 */
+			return ADD_TO_MLQUEUE;
+		if (sense_hdr->asc == 0x8b && sense_hdr->ascq == 0x02)
+			/*
+			 * Quiescence in progress , just retry.
+			 */
+			return ADD_TO_MLQUEUE;
+		break;
+	}
+	/* success just means we do not care what scsi-ml does */
+	return SCSI_RETURN_NOT_HANDLED;
+}
+
+static const struct {
+	char *vendor;
+	char *model;
+} rdac_dev_list[] = {
+	{"IBM", "1722"},
+	{"IBM", "1724"},
+	{"IBM", "1726"},
+	{"IBM", "1742"},
+	{"IBM", "1745"},
+	{"IBM", "1746"},
+	{"IBM", "1813"},
+	{"IBM", "1814"},
+	{"IBM", "1815"},
+	{"IBM", "1818"},
+	{"IBM", "3526"},
+	{"SGI", "TP9"},
+	{"SGI", "IS"},
+	{"STK", "OPENstorage D280"},
+	{"STK", "FLEXLINE 380"},
+	{"SUN", "CSM"},
+	{"SUN", "LCSM100"},
+	{"SUN", "STK6580_6780"},
+	{"SUN", "SUN_6180"},
+	{"SUN", "ArrayStorage"},
+	{"DELL", "MD3"},
+	{"NETAPP", "INF-01-00"},
+	{"LSI", "INF-01-00"},
+	{"ENGENIO", "INF-01-00"},
+	{NULL, NULL},
+};
+
+static bool rdac_match(struct scsi_device *sdev)
+{
+	int i;
+
+	if (scsi_device_tpgs(sdev))
+		return false;
+
+	for (i = 0; rdac_dev_list[i].vendor; i++) {
+		if (!strncmp(sdev->vendor, rdac_dev_list[i].vendor,
+			strlen(rdac_dev_list[i].vendor)) &&
+		    !strncmp(sdev->model, rdac_dev_list[i].model,
+			strlen(rdac_dev_list[i].model))) {
+			return true;
+		}
+	}
+	return false;
+}
+
+static struct scsi_dh_data *rdac_bus_attach(struct scsi_device *sdev)
+{
+	struct rdac_dh_data *h;
+	int err;
+	char array_name[ARRAY_LABEL_LEN];
+	char array_id[UNIQUE_ID_LEN];
+
+	h = kzalloc(sizeof(*h) , GFP_KERNEL);
+	if (!h)
+		return ERR_PTR(-ENOMEM);
+	h->lun = UNINITIALIZED_LUN;
+	h->state = RDAC_STATE_ACTIVE;
+
+	err = get_lun_info(sdev, h, array_name, array_id);
+	if (err != SCSI_DH_OK)
+		goto failed;
+
+	err = initialize_controller(sdev, h, array_name, array_id);
+	if (err != SCSI_DH_OK)
+		goto failed;
+
+	err = check_ownership(sdev, h);
+	if (err != SCSI_DH_OK)
+		goto clean_ctlr;
+
+	err = set_mode_select(sdev, h);
+	if (err != SCSI_DH_OK)
+		goto clean_ctlr;
+
+	sdev_printk(KERN_NOTICE, sdev,
+		    "%s: LUN %d (%s) (%s)\n",
+		    RDAC_NAME, h->lun, mode[(int)h->mode],
+		    lun_state[(int)h->lun_state]);
+
+	return &h->dh_data;
+
+clean_ctlr:
+	spin_lock(&list_lock);
+	kref_put(&h->ctlr->kref, release_controller);
+	spin_unlock(&list_lock);
+
+failed:
+	kfree(h);
+	return ERR_PTR(-EINVAL);
+}
+
+static void rdac_bus_detach( struct scsi_device *sdev )
+{
+	struct rdac_dh_data *h = get_rdac_data(sdev);
+
+	if (h->ctlr && h->ctlr->ms_queued)
+		flush_workqueue(kmpath_rdacd);
+
+	spin_lock(&list_lock);
+	if (h->ctlr)
+		kref_put(&h->ctlr->kref, release_controller);
+	spin_unlock(&list_lock);
+	kfree(h);
+}
+
+static struct scsi_device_handler rdac_dh = {
+	.name = RDAC_NAME,
+	.module = THIS_MODULE,
+	.prep_fn = rdac_prep_fn,
+	.check_sense = rdac_check_sense,
+	.attach = rdac_bus_attach,
+	.detach = rdac_bus_detach,
+	.activate = rdac_activate,
+	.match = rdac_match,
+};
+
+static int __init rdac_init(void)
+{
+	int r;
+
+	r = scsi_register_device_handler(&rdac_dh);
+	if (r != 0) {
+		printk(KERN_ERR "Failed to register scsi device handler.");
+		goto done;
+	}
+
+	/*
+	 * Create workqueue to handle mode selects for rdac
+	 */
+	kmpath_rdacd = create_singlethread_workqueue("kmpath_rdacd");
+	if (!kmpath_rdacd) {
+		scsi_unregister_device_handler(&rdac_dh);
+		printk(KERN_ERR "kmpath_rdacd creation failed.\n");
+
+		r = -EINVAL;
+	}
+done:
+	return r;
+}
+
+static void __exit rdac_exit(void)
+{
+	destroy_workqueue(kmpath_rdacd);
+	scsi_unregister_device_handler(&rdac_dh);
+}
+
+module_init(rdac_init);
+module_exit(rdac_exit);
+
+MODULE_DESCRIPTION("Multipath LSI/Engenio/NetApp E-Series RDAC driver");
+MODULE_AUTHOR("Mike Christie, Chandra Seetharaman");
+MODULE_VERSION("01.00.0000.0000");
+MODULE_LICENSE("GPL");