166 files changed, 2655 insertions, 2750 deletions
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index c95df0b8c880..5d9248526d78 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -235,17 +235,6 @@ config ACPI_INITRD_TABLE_OVERRIDE
          initrd, therefore it's safe to say Y.
          See Documentation/acpi/initrd_table_override.txt for details
-config ACPI_BLACKLIST_YEAR
-        int "Disable ACPI for systems before Jan 1st this year" if X86_32
-        default 0
-        help
-          Enter a 4-digit year, e.g., 2001, to disable ACPI by default
-          on platforms with DMI BIOS date before January 1st that year.
-          "acpi=force" can be used to override this mechanism.
-          Enter 0 to disable this mechanism and allow ACPI to
-          run by default no matter what the year.  (default)
 config ACPI_DEBUG
        bool "Debug Statements"
        default n
diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index b9f0d5f4bba5..8711e3797165 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -56,7 +56,6 @@ static int ac_sleep_before_get_state_ms;
 struct acpi_ac {
        struct power_supply charger;
-        struct acpi_device *adev;
        struct platform_device *pdev;
        unsigned long long state;
 };
@@ -70,8 +69,9 @@ struct acpi_ac {
 static int acpi_ac_get_state(struct acpi_ac *ac)
 {
        acpi_status status;
+        acpi_handle handle = ACPI_HANDLE(&ac->pdev->dev);
-        status = acpi_evaluate_integer(ac->adev->handle, "_PSR", NULL,
+        status = acpi_evaluate_integer(handle, "_PSR", NULL,
                                       &ac->state);
        if (ACPI_FAILURE(status)) {
                ACPI_EXCEPTION((AE_INFO, status,
@@ -119,6 +119,7 @@ static enum power_supply_property ac_props[] = {
 static void acpi_ac_notify_handler(acpi_handle handle, u32 event, void *data)
 {
        struct acpi_ac *ac = data;
+        struct acpi_device *adev;
        if (!ac)
                return;
@@ -141,10 +142,11 @@ static void acpi_ac_notify_handler(acpi_handle handle, u32 event, void *data)
                        msleep(ac_sleep_before_get_state_ms);
                acpi_ac_get_state(ac);
-                acpi_bus_generate_netlink_event(ac->adev->pnp.device_class,
+                adev = ACPI_COMPANION(&ac->pdev->dev);
+                acpi_bus_generate_netlink_event(adev->pnp.device_class,
                                                dev_name(&ac->pdev->dev),
                                                event, (u32) ac->state);
-                acpi_notifier_call_chain(ac->adev, event, (u32) ac->state);
+                acpi_notifier_call_chain(adev, event, (u32) ac->state);
                kobject_uevent(&ac->charger.dev->kobj, KOBJ_CHANGE);
        }
@@ -178,8 +180,8 @@ static int acpi_ac_probe(struct platform_device *pdev)
        if (!pdev)
                return -EINVAL;
-        result = acpi_bus_get_device(ACPI_HANDLE(&pdev->dev), &adev);
+        adev = ACPI_COMPANION(&pdev->dev);
-        if (result)
+        if (!adev)
                return -ENODEV;
        ac = kzalloc(sizeof(struct acpi_ac), GFP_KERNEL);
@@ -188,7 +190,6 @@ static int acpi_ac_probe(struct platform_device *pdev)
        strcpy(acpi_device_name(adev), ACPI_AC_DEVICE_NAME);
        strcpy(acpi_device_class(adev), ACPI_AC_CLASS);
-        ac->adev = adev;
        ac->pdev = pdev;
        platform_set_drvdata(pdev, ac);
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index d3961014aad7..6745fe137b9e 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -163,6 +163,15 @@ static const struct acpi_device_id acpi_lpss_device_ids[] = {
        { "80860F41", (unsigned long)&byt_i2c_dev_desc },
        { "INT33B2", },
+        { "INT3430", (unsigned long)&lpt_dev_desc },
+        { "INT3431", (unsigned long)&lpt_dev_desc },
+        { "INT3432", (unsigned long)&lpt_dev_desc },
+        { "INT3433", (unsigned long)&lpt_dev_desc },
+        { "INT3434", (unsigned long)&lpt_uart_dev_desc },
+        { "INT3435", (unsigned long)&lpt_uart_dev_desc },
+        { "INT3436", (unsigned long)&lpt_sdio_dev_desc },
+        { "INT3437", },
        { }
 };
diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c
index 8a4cfc7e71f0..dbfe49e5fd63 100644
--- a/drivers/acpi/acpi_platform.c
+++ b/drivers/acpi/acpi_platform.c
@@ -111,7 +111,7 @@ int acpi_create_platform_device(struct acpi_device *adev,
        pdevinfo.id = -1;
        pdevinfo.res = resources;
        pdevinfo.num_res = count;
-        pdevinfo.acpi_node.handle = adev->handle;
+        pdevinfo.acpi_node.companion = adev;
        pdev = platform_device_register_full(&pdevinfo);
        if (IS_ERR(pdev)) {
                dev_err(&adev->dev, "platform device creation failed: %ld\n",
diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c
index fb848378d582..078c4f7fe2dd 100644
--- a/drivers/acpi/blacklist.c
+++ b/drivers/acpi/blacklist.c
@@ -75,39 +75,6 @@ static struct acpi_blacklist_item acpi_blacklist[] __initdata = {
        {""}
 };
-#if     CONFIG_ACPI_BLACKLIST_YEAR
-static int __init blacklist_by_year(void)
-{
-        int year;
-        /* Doesn't exist? Likely an old system */
-        if (!dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL)) {
-                printk(KERN_ERR PREFIX "no DMI BIOS year, "
-                        "acpi=force is required to enable ACPI\n" );
-                return 1;
-        }
-        /* 0? Likely a buggy new BIOS */
-        if (year == 0) {
-                printk(KERN_ERR PREFIX "DMI BIOS year==0, "
-                        "assuming ACPI-capable machine\n" );
-                return 0;
-        }
-        if (year < CONFIG_ACPI_BLACKLIST_YEAR) {
-                printk(KERN_ERR PREFIX "BIOS age (%d) fails cutoff (%d), "
-                       "acpi=force is required to enable ACPI\n",
-                       year, CONFIG_ACPI_BLACKLIST_YEAR);
-                return 1;
-        }
-        return 0;
-}
-#else
-static inline int blacklist_by_year(void)
-{
-        return 0;
-}
-#endif
 int __init acpi_blacklisted(void)
 {
        int i = 0;
@@ -166,8 +133,6 @@ int __init acpi_blacklisted(void)
                }
        }
-        blacklisted += blacklist_by_year();
        dmi_check_system(acpi_osi_dmi_table);
        return blacklisted;
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index d42b2fb5a7e9..b3480cf7db1a 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -22,16 +22,12 @@
 * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
-#include <linux/device.h>
+#include <linux/acpi.h>
 #include <linux/export.h>
 #include <linux/mutex.h>
 #include <linux/pm_qos.h>
 #include <linux/pm_runtime.h>
-#include <acpi/acpi.h>
-#include <acpi/acpi_bus.h>
-#include <acpi/acpi_drivers.h>
 #include "internal.h"
 #define _COMPONENT      ACPI_POWER_COMPONENT
@@ -548,7 +544,7 @@ static int acpi_dev_pm_get_state(struct device *dev, struct acpi_device *adev,
 */
 int acpi_pm_device_sleep_state(struct device *dev, int *d_min_p, int d_max_in)
 {
-        acpi_handle handle = DEVICE_ACPI_HANDLE(dev);
+        acpi_handle handle = ACPI_HANDLE(dev);
        struct acpi_device *adev;
        int ret, d_min, d_max;
@@ -656,7 +652,7 @@ int acpi_pm_device_run_wake(struct device *phys_dev, bool enable)
        if (!device_run_wake(phys_dev))
                return -EINVAL;
-        handle = DEVICE_ACPI_HANDLE(phys_dev);
+        handle = ACPI_HANDLE(phys_dev);
        if (!handle || acpi_bus_get_device(handle, &adev)) {
                dev_dbg(phys_dev, "ACPI handle without context in %s!\n",
                        __func__);
@@ -700,7 +696,7 @@ int acpi_pm_device_sleep_wake(struct device *dev, bool enable)
        if (!device_can_wakeup(dev))
                return -EINVAL;
-        handle = DEVICE_ACPI_HANDLE(dev);
+        handle = ACPI_HANDLE(dev);
        if (!handle || acpi_bus_get_device(handle, &adev)) {
                dev_dbg(dev, "ACPI handle without context in %s!\n", __func__);
                return -ENODEV;
@@ -722,7 +718,7 @@ int acpi_pm_device_sleep_wake(struct device *dev, bool enable)
 */
 struct acpi_device *acpi_dev_pm_get_node(struct device *dev)
 {
-        acpi_handle handle = DEVICE_ACPI_HANDLE(dev);
+        acpi_handle handle = ACPI_HANDLE(dev);
        struct acpi_device *adev;
        return handle && !acpi_bus_get_device(handle, &adev) ? adev : NULL;
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index d5309fd49458..ba5b56db9d27 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -173,9 +173,10 @@ static void start_transaction(struct acpi_ec *ec)
 static void advance_transaction(struct acpi_ec *ec, u8 status)
 {
        unsigned long flags;
-        struct transaction *t = ec->curr;
+        struct transaction *t;
        spin_lock_irqsave(&ec->lock, flags);
+        t = ec->curr;
        if (!t)
                goto unlock;
        if (t->wlen > t->wi) {
diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c
index fdef416c0ff6..cae3b387b867 100644
--- a/drivers/acpi/event.c
+++ b/drivers/acpi/event.c
@@ -78,15 +78,17 @@ enum {
 #define ACPI_GENL_VERSION               0x01
 #define ACPI_GENL_MCAST_GROUP_NAME      "acpi_mc_group"
+static const struct genl_multicast_group acpi_event_mcgrps[] = {
+        { .name = ACPI_GENL_MCAST_GROUP_NAME, },
+};
 static struct genl_family acpi_event_genl_family = {
        .id = GENL_ID_GENERATE,
        .name = ACPI_GENL_FAMILY_NAME,
        .version = ACPI_GENL_VERSION,
        .maxattr = ACPI_GENL_ATTR_MAX,
-};
+        .mcgrps = acpi_event_mcgrps,
+        .n_mcgrps = ARRAY_SIZE(acpi_event_mcgrps),
-static struct genl_multicast_group acpi_event_mcgrp = {
-        .name = ACPI_GENL_MCAST_GROUP_NAME,
 };
 int acpi_bus_generate_netlink_event(const char *device_class,
@@ -141,7 +143,7 @@ int acpi_bus_generate_netlink_event(const char *device_class,
                return result;
        }
-        genlmsg_multicast(skb, 0, acpi_event_mcgrp.id, GFP_ATOMIC);
+        genlmsg_multicast(&acpi_event_genl_family, skb, 0, 0, GFP_ATOMIC);
        return 0;
 }
@@ -149,18 +151,7 @@ EXPORT_SYMBOL(acpi_bus_generate_netlink_event);
 static int acpi_event_genetlink_init(void)
 {
-        int result;
+        return genl_register_family(&acpi_event_genl_family);
-        result = genl_register_family(&acpi_event_genl_family);
-        if (result)
-                return result;
-        result = genl_register_mc_group(&acpi_event_genl_family,
-                                        &acpi_event_mcgrp);
-        if (result)
-                genl_unregister_family(&acpi_event_genl_family);
-        return result;
 }
 #else
diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c
index 10f0f40587bb..a22a295edb69 100644
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@@ -197,30 +197,28 @@ static void acpi_physnode_link_name(char *buf, unsigned int node_id)
 int acpi_bind_one(struct device *dev, acpi_handle handle)
 {
-        struct acpi_device *acpi_dev;
+        struct acpi_device *acpi_dev = NULL;
-        acpi_status status;
        struct acpi_device_physical_node *physical_node, *pn;
        char physical_node_name[PHYSICAL_NODE_NAME_SIZE];
        struct list_head *physnode_list;
        unsigned int node_id;
        int retval = -EINVAL;
-        if (ACPI_HANDLE(dev)) {
+        if (ACPI_COMPANION(dev)) {
                if (handle) {
-                        dev_warn(dev, "ACPI handle is already set\n");
+                        dev_warn(dev, "ACPI companion already set\n");
                        return -EINVAL;
                } else {
-                        handle = ACPI_HANDLE(dev);
+                        acpi_dev = ACPI_COMPANION(dev);
                }
+        } else {
+                acpi_bus_get_device(handle, &acpi_dev);
        }
-        if (!handle)
+        if (!acpi_dev)
                return -EINVAL;
+        get_device(&acpi_dev->dev);
        get_device(dev);
-        status = acpi_bus_get_device(handle, &acpi_dev);
-        if (ACPI_FAILURE(status))
-                goto err;
        physical_node = kzalloc(sizeof(*physical_node), GFP_KERNEL);
        if (!physical_node) {
                retval = -ENOMEM;
@@ -242,10 +240,11 @@ int acpi_bind_one(struct device *dev, acpi_handle handle)
                        dev_warn(dev, "Already associated with ACPI node\n");
                        kfree(physical_node);
-                        if (ACPI_HANDLE(dev) != handle)
+                        if (ACPI_COMPANION(dev) != acpi_dev)
                                goto err;
                        put_device(dev);
+                        put_device(&acpi_dev->dev);
                        return 0;
                }
                if (pn->node_id == node_id) {
@@ -259,8 +258,8 @@ int acpi_bind_one(struct device *dev, acpi_handle handle)
        list_add(&physical_node->node, physnode_list);
        acpi_dev->physical_node_count++;
-        if (!ACPI_HANDLE(dev))
+        if (!ACPI_COMPANION(dev))
-                ACPI_HANDLE_SET(dev, acpi_dev->handle);
+                ACPI_COMPANION_SET(dev, acpi_dev);
        acpi_physnode_link_name(physical_node_name, node_id);
        retval = sysfs_create_link(&acpi_dev->dev.kobj, &dev->kobj,
@@ -283,27 +282,21 @@ int acpi_bind_one(struct device *dev, acpi_handle handle)
        return 0;
 err:
-        ACPI_HANDLE_SET(dev, NULL);
+        ACPI_COMPANION_SET(dev, NULL);
        put_device(dev);
+        put_device(&acpi_dev->dev);
        return retval;
 }
 EXPORT_SYMBOL_GPL(acpi_bind_one);
 int acpi_unbind_one(struct device *dev)
 {
+        struct acpi_device *acpi_dev = ACPI_COMPANION(dev);
        struct acpi_device_physical_node *entry;
-        struct acpi_device *acpi_dev;
-        acpi_status status;
-        if (!ACPI_HANDLE(dev))
+        if (!acpi_dev)
                return 0;
-        status = acpi_bus_get_device(ACPI_HANDLE(dev), &acpi_dev);
-        if (ACPI_FAILURE(status)) {
-                dev_err(dev, "Oops, ACPI handle corrupt in %s()\n", __func__);
-                return -EINVAL;
-        }
        mutex_lock(&acpi_dev->physical_node_lock);
        list_for_each_entry(entry, &acpi_dev->physical_node_list, node)
@@ -316,9 +309,10 @@ int acpi_unbind_one(struct device *dev)
                        acpi_physnode_link_name(physnode_name, entry->node_id);
                        sysfs_remove_link(&acpi_dev->dev.kobj, physnode_name);
                        sysfs_remove_link(&dev->kobj, "firmware_node");
-                        ACPI_HANDLE_SET(dev, NULL);
+                        ACPI_COMPANION_SET(dev, NULL);
-                        /* acpi_bind_one() increase refcnt by one. */
+                        /* Drop references taken by acpi_bind_one(). */
                        put_device(dev);
+                        put_device(&acpi_dev->dev);
                        kfree(entry);
                        break;
                }
@@ -328,6 +322,15 @@ int acpi_unbind_one(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(acpi_unbind_one);
+void acpi_preset_companion(struct device *dev, acpi_handle parent, u64 addr)
+{
+        struct acpi_device *adev;
+        if (!acpi_bus_get_device(acpi_get_child(parent, addr), &adev))
+                ACPI_COMPANION_SET(dev, adev);
+}
+EXPORT_SYMBOL_GPL(acpi_preset_companion);
 static int acpi_platform_notify(struct device *dev)
 {
        struct acpi_bus_type *type = acpi_get_bus_type(dev);
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 56f05869b08d..0703bff5e60e 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -575,6 +575,7 @@ static int acpi_pci_root_add(struct acpi_device *device,
                dev_err(&device->dev,
                        "Bus %04x:%02x not present in PCI namespace\n",
                        root->segment, (unsigned int)root->secondary.start);
+                device->driver_data = NULL;
                result = -ENODEV;
                goto end;
        }
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 55f9dedbbf9f..15daa21fcd05 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -289,24 +289,17 @@ void acpi_bus_device_eject(void *data, u32 ost_src)
 {
        struct acpi_device *device = data;
        acpi_handle handle = device->handle;
-        struct acpi_scan_handler *handler;
        u32 ost_code = ACPI_OST_SC_NON_SPECIFIC_FAILURE;
        int error;
        lock_device_hotplug();
        mutex_lock(&acpi_scan_lock);
-        handler = device->handler;
-        if (!handler || !handler->hotplug.enabled) {
-                put_device(&device->dev);
-                goto err_support;
-        }
        if (ost_src == ACPI_NOTIFY_EJECT_REQUEST)
                acpi_evaluate_hotplug_ost(handle, ACPI_NOTIFY_EJECT_REQUEST,
                                          ACPI_OST_SC_EJECT_IN_PROGRESS, NULL);
-        if (handler->hotplug.mode == AHM_CONTAINER)
+        if (device->handler && device->handler->hotplug.mode == AHM_CONTAINER)
                kobject_uevent(&device->dev.kobj, KOBJ_OFFLINE);
        error = acpi_scan_hot_remove(device);
@@ -411,8 +404,7 @@ static void acpi_hotplug_notify_cb(acpi_handle handle, u32 type, void *data)
                break;
        case ACPI_NOTIFY_EJECT_REQUEST:
                acpi_handle_debug(handle, "ACPI_NOTIFY_EJECT_REQUEST event\n");
-                status = acpi_bus_get_device(handle, &adev);
+                if (acpi_bus_get_device(handle, &adev))
-                if (ACPI_FAILURE(status))
                        goto err_out;
                get_device(&adev->dev);
@@ -1997,6 +1989,7 @@ static int acpi_bus_scan_fixed(void)
                if (result)
                        return result;
+                device->flags.match_driver = true;
                result = device_attach(&device->dev);
                if (result < 0)
                        return result;
@@ -2013,6 +2006,7 @@ static int acpi_bus_scan_fixed(void)
                if (result)
                        return result;
+                device->flags.match_driver = true;
                result = device_attach(&device->dev);
        }
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index 18dbdff4656e..995e91bcb97b 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -82,13 +82,6 @@ static bool allow_duplicates;
 module_param(allow_duplicates, bool, 0644);
 /*
- * Some BIOSes claim they use minimum backlight at boot,
- * and this may bring dimming screen after boot
- */
-static bool use_bios_initial_backlight = 1;
-module_param(use_bios_initial_backlight, bool, 0644);
-/*
 * For Windows 8 systems: if set ture and the GPU driver has
 * registered a backlight interface, skip registering ACPI video's.
 */
@@ -406,12 +399,6 @@ static int __init video_set_bqc_offset(const struct dmi_system_id *d)
        return 0;
 }
-static int video_ignore_initial_backlight(const struct dmi_system_id *d)
-{
-        use_bios_initial_backlight = 0;
-        return 0;
-}
 static struct dmi_system_id video_dmi_table[] __initdata = {
        /*
         * Broken _BQC workaround http://bugzilla.kernel.org/show_bug.cgi?id=13121
@@ -456,54 +443,6 @@ static struct dmi_system_id video_dmi_table[] __initdata = {
                DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 7720"),
                },
        },
-        {
-         .callback = video_ignore_initial_backlight,
-         .ident = "HP Folio 13-2000",
-         .matches = {
-                DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"),
-                DMI_MATCH(DMI_PRODUCT_NAME, "HP Folio 13 - 2000 Notebook PC"),
-                },
-        },
-        {
-         .callback = video_ignore_initial_backlight,
-         .ident = "Fujitsu E753",
-         .matches = {
-                DMI_MATCH(DMI_BOARD_VENDOR, "FUJITSU"),
-                DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E753"),
-                },
-        },
-        {
-         .callback = video_ignore_initial_backlight,
-         .ident = "HP Pavilion dm4",
-         .matches = {
-                DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"),
-                DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dm4 Notebook PC"),
-                },
-        },
-        {
-         .callback = video_ignore_initial_backlight,
-         .ident = "HP Pavilion g6 Notebook PC",
-         .matches = {
-                 DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"),
-                 DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion g6 Notebook PC"),
-                },
-        },
-        {
-         .callback = video_ignore_initial_backlight,
-         .ident = "HP 1000 Notebook PC",
-         .matches = {
-                DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"),
-                DMI_MATCH(DMI_PRODUCT_NAME, "HP 1000 Notebook PC"),
-                },
-        },
-        {
-         .callback = video_ignore_initial_backlight,
-         .ident = "HP Pavilion m4",
-         .matches = {
-                DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"),
-                DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion m4 Notebook PC"),
-                },
-        },
        {}
 };
@@ -839,20 +778,18 @@ acpi_video_init_brightness(struct acpi_video_device *device)
        if (!device->cap._BQC)
                goto set_level;
-        if (use_bios_initial_backlight) {
+        level = acpi_video_bqc_value_to_level(device, level_old);
-                level = acpi_video_bqc_value_to_level(device, level_old);
+        /*
-                /*
+         * On some buggy laptops, _BQC returns an uninitialized
-                 * On some buggy laptops, _BQC returns an uninitialized
+         * value when invoked for the first time, i.e.
-                 * value when invoked for the first time, i.e.
+         * level_old is invalid (no matter whether it's a level
-                 * level_old is invalid (no matter whether it's a level
+         * or an index). Set the backlight to max_level in this case.
-                 * or an index). Set the backlight to max_level in this case.
+         */
-                 */
+        for (i = 2; i < br->count; i++)
-                for (i = 2; i < br->count; i++)
+                if (level == br->levels[i])
-                        if (level == br->levels[i])
+                        break;
-                                break;
+        if (i == br->count || !level)
-                if (i == br->count || !level)
+                level = max_level;
-                        level = max_level;
-        }
 set_level:
        result = acpi_video_device_lcd_set_level(device, level);
diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c
index ab714d2ad978..4372cfa883c9 100644
--- a/drivers/ata/libata-acpi.c
+++ b/drivers/ata/libata-acpi.c
@@ -185,7 +185,7 @@ void ata_acpi_bind_port(struct ata_port *ap)
        if (libata_noacpi || ap->flags & ATA_FLAG_ACPI_SATA || !host_handle)
                return;
-        ACPI_HANDLE_SET(&ap->tdev, acpi_get_child(host_handle, ap->port_no));
+        acpi_preset_companion(&ap->tdev, host_handle, ap->port_no);
        if (ata_acpi_gtm(ap, &ap->__acpi_init_gtm) == 0)
                ap->pflags |= ATA_PFLAG_INIT_GTM_VALID;
@@ -222,7 +222,7 @@ void ata_acpi_bind_dev(struct ata_device *dev)
                parent_handle = port_handle;
        }
-        ACPI_HANDLE_SET(&dev->tdev, acpi_get_child(parent_handle, adr));
+        acpi_preset_companion(&dev->tdev, parent_handle, adr);
        register_hotplug_dock_device(ata_dev_acpi_handle(dev),
                                     &ata_acpi_dev_dock_ops, dev, NULL, NULL);
diff --git a/drivers/ata/pata_arasan_cf.c b/drivers/ata/pata_arasan_cf.c
index 853f610af28f..e88690ebfd82 100644
--- a/drivers/ata/pata_arasan_cf.c
+++ b/drivers/ata/pata_arasan_cf.c
@@ -396,8 +396,7 @@ dma_xfer(struct arasan_cf_dev *acdev, dma_addr_t src, dma_addr_t dest, u32 len)
        struct dma_async_tx_descriptor *tx;
        struct dma_chan *chan = acdev->dma_chan;
        dma_cookie_t cookie;
-        unsigned long flags = DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP |
+        unsigned long flags = DMA_PREP_INTERRUPT;
-                DMA_COMPL_SKIP_DEST_UNMAP;
        int ret = 0;
        tx = chan->device->device_prep_dma_memcpy(chan, dest, src, len, flags);
diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c
index 272f00927761..1bdf104e90bb 100644
--- a/drivers/atm/idt77252.c
+++ b/drivers/atm/idt77252.c
@@ -3511,7 +3511,7 @@ static int init_card(struct atm_dev *dev)
        tmp = dev_get_by_name(&init_net, tname);        /* jhs: was "tmp = dev_get(tname);" */
        if (tmp) {
                memcpy(card->atmdev->esi, tmp->dev_addr, 6);
+                dev_put(tmp);
                printk("%s: ESI %pM\n", card->name, card->atmdev->esi);
        }
        /*
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 47051cd25113..3a94b799f166 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -432,7 +432,7 @@ struct platform_device *platform_device_register_full(
                goto err_alloc;
        pdev->dev.parent = pdevinfo->parent;
-        ACPI_HANDLE_SET(&pdev->dev, pdevinfo->acpi_node.handle);
+        ACPI_COMPANION_SET(&pdev->dev, pdevinfo->acpi_node.companion);
        if (pdevinfo->dma_mask) {
                /*
@@ -463,7 +463,7 @@ struct platform_device *platform_device_register_full(
        ret = platform_device_add(pdev);
        if (ret) {
 err:
-                ACPI_HANDLE_SET(&pdev->dev, NULL);
+                ACPI_COMPANION_SET(&pdev->dev, NULL);
                kfree(pdev->dev.dma_mask);
 err_alloc:
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index c12e9b9556be..1b41fca3d65a 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1350,6 +1350,9 @@ static int device_prepare(struct device *dev, pm_message_t state)
        device_unlock(dev);
+        if (error)
+                pm_runtime_put(dev);
        return error;
 }
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 588479d58f52..6a680d4de7f1 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -199,15 +199,16 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
        spin_lock_irqsave(&vblk->vq_lock, flags);
        if (__virtblk_add_req(vblk->vq, vbr, vbr->sg, num) < 0) {
+                virtqueue_kick(vblk->vq);
                spin_unlock_irqrestore(&vblk->vq_lock, flags);
                blk_mq_stop_hw_queue(hctx);
-                virtqueue_kick(vblk->vq);
                return BLK_MQ_RQ_QUEUE_BUSY;
        }
-        spin_unlock_irqrestore(&vblk->vq_lock, flags);
        if (last)
                virtqueue_kick(vblk->vq);
+        spin_unlock_irqrestore(&vblk->vq_lock, flags);
        return BLK_MQ_RQ_QUEUE_OK;
 }
diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index c73fc2b74de2..18c5b9b16645 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -32,11 +32,23 @@
 #include <linux/atomic.h>
 #include <linux/pid_namespace.h>
-#include <asm/unaligned.h>
 #include <linux/cn_proc.h>
-#define CN_PROC_MSG_SIZE (sizeof(struct cn_msg) + sizeof(struct proc_event))
+/*
+ * Size of a cn_msg followed by a proc_event structure.  Since the
+ * sizeof struct cn_msg is a multiple of 4 bytes, but not 8 bytes, we
+ * add one 4-byte word to the size here, and then start the actual
+ * cn_msg structure 4 bytes into the stack buffer.  The result is that
+ * the immediately following proc_event structure is aligned to 8 bytes.
+ */
+#define CN_PROC_MSG_SIZE (sizeof(struct cn_msg) + sizeof(struct proc_event) + 4)
+/* See comment above; we test our assumption about sizeof struct cn_msg here. */
+static inline struct cn_msg *buffer_to_cn_msg(__u8 *buffer)
+{
+        BUILD_BUG_ON(sizeof(struct cn_msg) != 20);
+        return (struct cn_msg *)(buffer + 4);
+}
 static atomic_t proc_event_num_listeners = ATOMIC_INIT(0);
 static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC };
@@ -56,19 +68,19 @@ void proc_fork_connector(struct task_struct *task)
 {
        struct cn_msg *msg;
        struct proc_event *ev;
-        __u8 buffer[CN_PROC_MSG_SIZE];
+        __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
        struct timespec ts;
        struct task_struct *parent;
        if (atomic_read(&proc_event_num_listeners) < 1)
                return;
-        msg = (struct cn_msg *)buffer;
+        msg = buffer_to_cn_msg(buffer);
        ev = (struct proc_event *)msg->data;
        memset(&ev->event_data, 0, sizeof(ev->event_data));
        get_seq(&msg->seq, &ev->cpu);
        ktime_get_ts(&ts); /* get high res monotonic timestamp */
-        put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+        ev->timestamp_ns = timespec_to_ns(&ts);
        ev->what = PROC_EVENT_FORK;
        rcu_read_lock();
        parent = rcu_dereference(task->real_parent);
@@ -91,17 +103,17 @@ void proc_exec_connector(struct task_struct *task)
        struct cn_msg *msg;
        struct proc_event *ev;
        struct timespec ts;
-        __u8 buffer[CN_PROC_MSG_SIZE];
+        __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
        if (atomic_read(&proc_event_num_listeners) < 1)
                return;
-        msg = (struct cn_msg *)buffer;
+        msg = buffer_to_cn_msg(buffer);
        ev = (struct proc_event *)msg->data;
        memset(&ev->event_data, 0, sizeof(ev->event_data));
        get_seq(&msg->seq, &ev->cpu);
        ktime_get_ts(&ts); /* get high res monotonic timestamp */
-        put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+        ev->timestamp_ns = timespec_to_ns(&ts);
        ev->what = PROC_EVENT_EXEC;
        ev->event_data.exec.process_pid = task->pid;
        ev->event_data.exec.process_tgid = task->tgid;
@@ -117,14 +129,14 @@ void proc_id_connector(struct task_struct *task, int which_id)
 {
        struct cn_msg *msg;
        struct proc_event *ev;
-        __u8 buffer[CN_PROC_MSG_SIZE];
+        __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
        struct timespec ts;
        const struct cred *cred;
        if (atomic_read(&proc_event_num_listeners) < 1)
                return;
-        msg = (struct cn_msg *)buffer;
+        msg = buffer_to_cn_msg(buffer);
        ev = (struct proc_event *)msg->data;
        memset(&ev->event_data, 0, sizeof(ev->event_data));
        ev->what = which_id;
@@ -145,7 +157,7 @@ void proc_id_connector(struct task_struct *task, int which_id)
        rcu_read_unlock();
        get_seq(&msg->seq, &ev->cpu);
        ktime_get_ts(&ts); /* get high res monotonic timestamp */
-        put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+        ev->timestamp_ns = timespec_to_ns(&ts);
        memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
        msg->ack = 0; /* not used */
@@ -159,17 +171,17 @@ void proc_sid_connector(struct task_struct *task)
        struct cn_msg *msg;
        struct proc_event *ev;
        struct timespec ts;
-        __u8 buffer[CN_PROC_MSG_SIZE];
+        __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
        if (atomic_read(&proc_event_num_listeners) < 1)
                return;
-        msg = (struct cn_msg *)buffer;
+        msg = buffer_to_cn_msg(buffer);
        ev = (struct proc_event *)msg->data;
        memset(&ev->event_data, 0, sizeof(ev->event_data));
        get_seq(&msg->seq, &ev->cpu);
        ktime_get_ts(&ts); /* get high res monotonic timestamp */
-        put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+        ev->timestamp_ns = timespec_to_ns(&ts);
        ev->what = PROC_EVENT_SID;
        ev->event_data.sid.process_pid = task->pid;
        ev->event_data.sid.process_tgid = task->tgid;
@@ -186,17 +198,17 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id)
        struct cn_msg *msg;
        struct proc_event *ev;
        struct timespec ts;
-        __u8 buffer[CN_PROC_MSG_SIZE];
+        __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
        if (atomic_read(&proc_event_num_listeners) < 1)
                return;
-        msg = (struct cn_msg *)buffer;
+        msg = buffer_to_cn_msg(buffer);
        ev = (struct proc_event *)msg->data;
        memset(&ev->event_data, 0, sizeof(ev->event_data));
        get_seq(&msg->seq, &ev->cpu);
        ktime_get_ts(&ts); /* get high res monotonic timestamp */
-        put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+        ev->timestamp_ns = timespec_to_ns(&ts);
        ev->what = PROC_EVENT_PTRACE;
        ev->event_data.ptrace.process_pid  = task->pid;
        ev->event_data.ptrace.process_tgid = task->tgid;
@@ -221,17 +233,17 @@ void proc_comm_connector(struct task_struct *task)
        struct cn_msg *msg;
        struct proc_event *ev;
        struct timespec ts;
-        __u8 buffer[CN_PROC_MSG_SIZE];
+        __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
        if (atomic_read(&proc_event_num_listeners) < 1)
                return;
-        msg = (struct cn_msg *)buffer;
+        msg = buffer_to_cn_msg(buffer);
        ev = (struct proc_event *)msg->data;
        memset(&ev->event_data, 0, sizeof(ev->event_data));
        get_seq(&msg->seq, &ev->cpu);
        ktime_get_ts(&ts); /* get high res monotonic timestamp */
-        put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+        ev->timestamp_ns = timespec_to_ns(&ts);
        ev->what = PROC_EVENT_COMM;
        ev->event_data.comm.process_pid  = task->pid;
        ev->event_data.comm.process_tgid = task->tgid;
@@ -248,18 +260,18 @@ void proc_coredump_connector(struct task_struct *task)
 {
        struct cn_msg *msg;
        struct proc_event *ev;
-        __u8 buffer[CN_PROC_MSG_SIZE];
+        __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
        struct timespec ts;
        if (atomic_read(&proc_event_num_listeners) < 1)
                return;
-        msg = (struct cn_msg *)buffer;
+        msg = buffer_to_cn_msg(buffer);
        ev = (struct proc_event *)msg->data;
        memset(&ev->event_data, 0, sizeof(ev->event_data));
        get_seq(&msg->seq, &ev->cpu);
        ktime_get_ts(&ts); /* get high res monotonic timestamp */
-        put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+        ev->timestamp_ns = timespec_to_ns(&ts);
        ev->what = PROC_EVENT_COREDUMP;
        ev->event_data.coredump.process_pid = task->pid;
        ev->event_data.coredump.process_tgid = task->tgid;
@@ -275,18 +287,18 @@ void proc_exit_connector(struct task_struct *task)
 {
        struct cn_msg *msg;
        struct proc_event *ev;
-        __u8 buffer[CN_PROC_MSG_SIZE];
+        __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
        struct timespec ts;
        if (atomic_read(&proc_event_num_listeners) < 1)
                return;
-        msg = (struct cn_msg *)buffer;
+        msg = buffer_to_cn_msg(buffer);
        ev = (struct proc_event *)msg->data;
        memset(&ev->event_data, 0, sizeof(ev->event_data));
        get_seq(&msg->seq, &ev->cpu);
        ktime_get_ts(&ts); /* get high res monotonic timestamp */
-        put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+        ev->timestamp_ns = timespec_to_ns(&ts);
        ev->what = PROC_EVENT_EXIT;
        ev->event_data.exit.process_pid = task->pid;
        ev->event_data.exit.process_tgid = task->tgid;
@@ -312,18 +324,18 @@ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack)
 {
        struct cn_msg *msg;
        struct proc_event *ev;
-        __u8 buffer[CN_PROC_MSG_SIZE];
+        __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
        struct timespec ts;
        if (atomic_read(&proc_event_num_listeners) < 1)
                return;
-        msg = (struct cn_msg *)buffer;
+        msg = buffer_to_cn_msg(buffer);
        ev = (struct proc_event *)msg->data;
        memset(&ev->event_data, 0, sizeof(ev->event_data));
        msg->seq = rcvd_seq;
        ktime_get_ts(&ts); /* get high res monotonic timestamp */
-        put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+        ev->timestamp_ns = timespec_to_ns(&ts);
        ev->cpu = -1;
        ev->what = PROC_EVENT_NONE;
        ev->event_data.ack.err = err;
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 218460fcd2e4..25a70d06c5bf 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -68,6 +68,9 @@ static void cs_check_cpu(int cpu, unsigned int load)
                dbs_info->requested_freq += get_freq_target(cs_tuners, policy);
+                if (dbs_info->requested_freq > policy->max)
+                        dbs_info->requested_freq = policy->max;
                __cpufreq_driver_target(policy, dbs_info->requested_freq,
                        CPUFREQ_RELATION_H);
                return;
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 0806c31e5764..e6be63561fa6 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -328,10 +328,6 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy,
                                             dbs_data->cdata->gov_dbs_timer);
                }
-                /*
-                 * conservative does not implement micro like ondemand
-                 * governor, thus we are bound to jiffes/HZ
-                 */
                if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
                        cs_dbs_info->down_skip = 0;
                        cs_dbs_info->enable = 1;
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index be6d14307aa8..a0acd0bfba40 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -53,6 +53,7 @@ static unsigned int omap_getspeed(unsigned int cpu)
 static int omap_target(struct cpufreq_policy *policy, unsigned int index)
 {
+        int r, ret;
        struct dev_pm_opp *opp;
        unsigned long freq, volt = 0, volt_old = 0, tol = 0;
        unsigned int old_freq, new_freq;
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index dd2874ec1927..446687cc2334 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -89,14 +89,15 @@ config AT_HDMAC
          Support the Atmel AHB DMA controller.
 config FSL_DMA
-        tristate "Freescale Elo and Elo Plus DMA support"
+        tristate "Freescale Elo series DMA support"
        depends on FSL_SOC
        select DMA_ENGINE
        select ASYNC_TX_ENABLE_CHANNEL_SWITCH
        ---help---
-          Enable support for the Freescale Elo and Elo Plus DMA controllers.
+          Enable support for the Freescale Elo series DMA controllers.
-          The Elo is the DMA controller on some 82xx and 83xx parts, and the
+          The Elo is the DMA controller on some mpc82xx and mpc83xx parts, the
-          Elo Plus is the DMA controller on 85xx and 86xx parts.
+          EloPlus is on mpc85xx and mpc86xx and Pxxx parts, and the Elo3 is on
+          some Txxx and Bxxx parts.
 config MPC512X_DMA
        tristate "Freescale MPC512x built-in DMA engine support"
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index e51a9832ef0d..16a2aa28f856 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -1164,42 +1164,12 @@ static void pl08x_free_txd(struct pl08x_driver_data *pl08x,
        kfree(txd);
 }
-static void pl08x_unmap_buffers(struct pl08x_txd *txd)
-{
-        struct device *dev = txd->vd.tx.chan->device->dev;
-        struct pl08x_sg *dsg;
-        if (!(txd->vd.tx.flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-                if (txd->vd.tx.flags & DMA_COMPL_SRC_UNMAP_SINGLE)
-                        list_for_each_entry(dsg, &txd->dsg_list, node)
-                                dma_unmap_single(dev, dsg->src_addr, dsg->len,
-                                                DMA_TO_DEVICE);
-                else {
-                        list_for_each_entry(dsg, &txd->dsg_list, node)
-                                dma_unmap_page(dev, dsg->src_addr, dsg->len,
-                                                DMA_TO_DEVICE);
-                }
-        }
-        if (!(txd->vd.tx.flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-                if (txd->vd.tx.flags & DMA_COMPL_DEST_UNMAP_SINGLE)
-                        list_for_each_entry(dsg, &txd->dsg_list, node)
-                                dma_unmap_single(dev, dsg->dst_addr, dsg->len,
-                                                DMA_FROM_DEVICE);
-                else
-                        list_for_each_entry(dsg, &txd->dsg_list, node)
-                                dma_unmap_page(dev, dsg->dst_addr, dsg->len,
-                                                DMA_FROM_DEVICE);
-        }
-}
 static void pl08x_desc_free(struct virt_dma_desc *vd)
 {
        struct pl08x_txd *txd = to_pl08x_txd(&vd->tx);
        struct pl08x_dma_chan *plchan = to_pl08x_chan(vd->tx.chan);
-        if (!plchan->slave)
+        dma_descriptor_unmap(txd);
-                pl08x_unmap_buffers(txd);
        if (!txd->done)
                pl08x_release_mux(plchan);
@@ -1252,7 +1222,7 @@ static enum dma_status pl08x_dma_tx_status(struct dma_chan *chan,
        size_t bytes = 0;
        ret = dma_cookie_status(chan, cookie, txstate);
-        if (ret == DMA_SUCCESS)
+        if (ret == DMA_COMPLETE)
                return ret;
        /*
@@ -1267,7 +1237,7 @@ static enum dma_status pl08x_dma_tx_status(struct dma_chan *chan,
        spin_lock_irqsave(&plchan->vc.lock, flags);
        ret = dma_cookie_status(chan, cookie, txstate);
-        if (ret != DMA_SUCCESS) {
+        if (ret != DMA_COMPLETE) {
                vd = vchan_find_desc(&plchan->vc, cookie);
                if (vd) {
                        /* On the issued list, so hasn't been processed yet */
@@ -2138,8 +2108,7 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
        writel(0x000000FF, pl08x->base + PL080_ERR_CLEAR);
        writel(0x000000FF, pl08x->base + PL080_TC_CLEAR);
-        ret = request_irq(adev->irq[0], pl08x_irq, IRQF_DISABLED,
+        ret = request_irq(adev->irq[0], pl08x_irq, 0, DRIVER_NAME, pl08x);
-                          DRIVER_NAME, pl08x);
        if (ret) {
                dev_err(&adev->dev, "%s failed to request interrupt %d\n",
                        __func__, adev->irq[0]);
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index c787f38a186a..e2c04dc81e2a 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -344,31 +344,7 @@ atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
        /* move myself to free_list */
        list_move(&desc->desc_node, &atchan->free_list);
-        /* unmap dma addresses (not on slave channels) */
+        dma_descriptor_unmap(txd);
-        if (!atchan->chan_common.private) {
-                struct device *parent = chan2parent(&atchan->chan_common);
-                if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-                        if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
-                                dma_unmap_single(parent,
-                                                desc->lli.daddr,
-                                                desc->len, DMA_FROM_DEVICE);
-                        else
-                                dma_unmap_page(parent,
-                                                desc->lli.daddr,
-                                                desc->len, DMA_FROM_DEVICE);
-                }
-                if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-                        if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
-                                dma_unmap_single(parent,
-                                                desc->lli.saddr,
-                                                desc->len, DMA_TO_DEVICE);
-                        else
-                                dma_unmap_page(parent,
-                                                desc->lli.saddr,
-                                                desc->len, DMA_TO_DEVICE);
-                }
-        }
        /* for cyclic transfers,
         * no need to replay callback function while stopping */
        if (!atc_chan_is_cyclic(atchan)) {
@@ -1102,7 +1078,7 @@ atc_tx_status(struct dma_chan *chan,
        int bytes = 0;
        ret = dma_cookie_status(chan, cookie, txstate);
-        if (ret == DMA_SUCCESS)
+        if (ret == DMA_COMPLETE)
                return ret;
        /*
         * There's no point calculating the residue if there's
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index 31011d2a26fc..3c6716e0b78e 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -2369,7 +2369,7 @@ coh901318_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
        enum dma_status ret;
        ret = dma_cookie_status(chan, cookie, txstate);
-        if (ret == DMA_SUCCESS)
+        if (ret == DMA_COMPLETE)
                return ret;
        dma_set_residue(txstate, coh901318_get_bytes_left(chan));
@@ -2694,7 +2694,7 @@ static int __init coh901318_probe(struct platform_device *pdev)
        if (irq < 0)
                return irq;
-        err = devm_request_irq(&pdev->dev, irq, dma_irq_handler, IRQF_DISABLED,
+        err = devm_request_irq(&pdev->dev, irq, dma_irq_handler, 0,
                               "coh901318", base);
        if (err)
                return err;
diff --git a/drivers/dma/cppi41.c b/drivers/dma/cppi41.c
index 7c82b92f9b16..c29dacff66fa 100644
--- a/drivers/dma/cppi41.c
+++ b/drivers/dma/cppi41.c
@@ -141,6 +141,9 @@ struct cppi41_dd {
        const struct chan_queues *queues_rx;
        const struct chan_queues *queues_tx;
        struct chan_queues td_queue;
+        /* context for suspend/resume */
+        unsigned int dma_tdfdq;
 };
 #define FIST_COMPLETION_QUEUE   93
@@ -263,6 +266,15 @@ static u32 pd_trans_len(u32 val)
        return val & ((1 << (DESC_LENGTH_BITS_NUM + 1)) - 1);
 }
+static u32 cppi41_pop_desc(struct cppi41_dd *cdd, unsigned queue_num)
+{
+        u32 desc;
+        desc = cppi_readl(cdd->qmgr_mem + QMGR_QUEUE_D(queue_num));
+        desc &= ~0x1f;
+        return desc;
+}
 static irqreturn_t cppi41_irq(int irq, void *data)
 {
        struct cppi41_dd *cdd = data;
@@ -300,8 +312,7 @@ static irqreturn_t cppi41_irq(int irq, void *data)
                        q_num = __fls(val);
                        val &= ~(1 << q_num);
                        q_num += 32 * i;
-                        desc = cppi_readl(cdd->qmgr_mem + QMGR_QUEUE_D(q_num));
+                        desc = cppi41_pop_desc(cdd, q_num);
-                        desc &= ~0x1f;
                        c = desc_to_chan(cdd, desc);
                        if (WARN_ON(!c)) {
                                pr_err("%s() q %d desc %08x\n", __func__,
@@ -353,7 +364,7 @@ static enum dma_status cppi41_dma_tx_status(struct dma_chan *chan,
        /* lock */
        ret = dma_cookie_status(chan, cookie, txstate);
-        if (txstate && ret == DMA_SUCCESS)
+        if (txstate && ret == DMA_COMPLETE)
                txstate->residue = c->residue;
        /* unlock */
@@ -517,15 +528,6 @@ static void cppi41_compute_td_desc(struct cppi41_desc *d)
        d->pd0 = DESC_TYPE_TEARD << DESC_TYPE;
 }
-static u32 cppi41_pop_desc(struct cppi41_dd *cdd, unsigned queue_num)
-{
-        u32 desc;
-        desc = cppi_readl(cdd->qmgr_mem + QMGR_QUEUE_D(queue_num));
-        desc &= ~0x1f;
-        return desc;
-}
 static int cppi41_tear_down_chan(struct cppi41_channel *c)
 {
        struct cppi41_dd *cdd = c->cdd;
@@ -561,36 +563,26 @@ static int cppi41_tear_down_chan(struct cppi41_channel *c)
                c->td_retry = 100;
        }
-        if (!c->td_seen) {
+        if (!c->td_seen || !c->td_desc_seen) {
-                unsigned td_comp_queue;
-                if (c->is_tx)
+                desc_phys = cppi41_pop_desc(cdd, cdd->td_queue.complete);
-                        td_comp_queue =  cdd->td_queue.complete;
+                if (!desc_phys)
-                else
+                        desc_phys = cppi41_pop_desc(cdd, c->q_comp_num);
-                        td_comp_queue =  c->q_comp_num;
-                desc_phys = cppi41_pop_desc(cdd, td_comp_queue);
+                if (desc_phys == c->desc_phys) {
-                if (desc_phys) {
+                        c->td_desc_seen = 1;
-                        __iormb();
+                } else if (desc_phys == td_desc_phys) {
+                        u32 pd0;
-                        if (desc_phys == td_desc_phys) {
-                                u32 pd0;
-                                pd0 = td->pd0;
-                                WARN_ON((pd0 >> DESC_TYPE) != DESC_TYPE_TEARD);
-                                WARN_ON(!c->is_tx && !(pd0 & TD_DESC_IS_RX));
-                                WARN_ON((pd0 & 0x1f) != c->port_num);
-                        } else {
-                                WARN_ON_ONCE(1);
-                        }
-                        c->td_seen = 1;
-                }
-        }
-        if (!c->td_desc_seen) {
-                desc_phys = cppi41_pop_desc(cdd, c->q_comp_num);
-                if (desc_phys) {
                        __iormb();
-                        WARN_ON(c->desc_phys != desc_phys);
+                        pd0 = td->pd0;
-                        c->td_desc_seen = 1;
+                        WARN_ON((pd0 >> DESC_TYPE) != DESC_TYPE_TEARD);
+                        WARN_ON(!c->is_tx && !(pd0 & TD_DESC_IS_RX));
+                        WARN_ON((pd0 & 0x1f) != c->port_num);
+                        c->td_seen = 1;
+                } else if (desc_phys) {
+                        WARN_ON_ONCE(1);
                }
        }
        c->td_retry--;
@@ -609,7 +601,7 @@ static int cppi41_tear_down_chan(struct cppi41_channel *c)
        WARN_ON(!c->td_retry);
        if (!c->td_desc_seen) {
-                desc_phys = cppi_readl(cdd->qmgr_mem + QMGR_QUEUE_D(c->q_num));
+                desc_phys = cppi41_pop_desc(cdd, c->q_num);
                WARN_ON(!desc_phys);
        }
@@ -674,14 +666,14 @@ static void cleanup_chans(struct cppi41_dd *cdd)
        }
 }
-static int cppi41_add_chans(struct platform_device *pdev, struct cppi41_dd *cdd)
+static int cppi41_add_chans(struct device *dev, struct cppi41_dd *cdd)
 {
        struct cppi41_channel *cchan;
        int i;
        int ret;
        u32 n_chans;
-        ret = of_property_read_u32(pdev->dev.of_node, "#dma-channels",
+        ret = of_property_read_u32(dev->of_node, "#dma-channels",
                        &n_chans);
        if (ret)
                return ret;
@@ -719,7 +711,7 @@ err:
        return -ENOMEM;
 }
-static void purge_descs(struct platform_device *pdev, struct cppi41_dd *cdd)
+static void purge_descs(struct device *dev, struct cppi41_dd *cdd)
 {
        unsigned int mem_decs;
        int i;
@@ -731,7 +723,7 @@ static void purge_descs(struct platform_device *pdev, struct cppi41_dd *cdd)
                cppi_writel(0, cdd->qmgr_mem + QMGR_MEMBASE(i));
                cppi_writel(0, cdd->qmgr_mem + QMGR_MEMCTRL(i));
-                dma_free_coherent(&pdev->dev, mem_decs, cdd->cd,
+                dma_free_coherent(dev, mem_decs, cdd->cd,
                                cdd->descs_phys);
        }
 }
@@ -741,19 +733,19 @@ static void disable_sched(struct cppi41_dd *cdd)
        cppi_writel(0, cdd->sched_mem + DMA_SCHED_CTRL);
 }
-static void deinit_cpii41(struct platform_device *pdev, struct cppi41_dd *cdd)
+static void deinit_cppi41(struct device *dev, struct cppi41_dd *cdd)
 {
        disable_sched(cdd);
-        purge_descs(pdev, cdd);
+        purge_descs(dev, cdd);
        cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM0_BASE);
        cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM0_BASE);
-        dma_free_coherent(&pdev->dev, QMGR_SCRATCH_SIZE, cdd->qmgr_scratch,
+        dma_free_coherent(dev, QMGR_SCRATCH_SIZE, cdd->qmgr_scratch,
                        cdd->scratch_phys);
 }
-static int init_descs(struct platform_device *pdev, struct cppi41_dd *cdd)
+static int init_descs(struct device *dev, struct cppi41_dd *cdd)
 {
        unsigned int desc_size;
        unsigned int mem_decs;
@@ -777,7 +769,7 @@ static int init_descs(struct platform_device *pdev, struct cppi41_dd *cdd)
                reg |= ilog2(ALLOC_DECS_NUM) - 5;
                BUILD_BUG_ON(DESCS_AREAS != 1);
-                cdd->cd = dma_alloc_coherent(&pdev->dev, mem_decs,
+                cdd->cd = dma_alloc_coherent(dev, mem_decs,
                                &cdd->descs_phys, GFP_KERNEL);
                if (!cdd->cd)
                        return -ENOMEM;
@@ -813,12 +805,12 @@ static void init_sched(struct cppi41_dd *cdd)
        cppi_writel(reg, cdd->sched_mem + DMA_SCHED_CTRL);
 }
-static int init_cppi41(struct platform_device *pdev, struct cppi41_dd *cdd)
+static int init_cppi41(struct device *dev, struct cppi41_dd *cdd)
 {
        int ret;
        BUILD_BUG_ON(QMGR_SCRATCH_SIZE > ((1 << 14) - 1));
-        cdd->qmgr_scratch = dma_alloc_coherent(&pdev->dev, QMGR_SCRATCH_SIZE,
+        cdd->qmgr_scratch = dma_alloc_coherent(dev, QMGR_SCRATCH_SIZE,
                        &cdd->scratch_phys, GFP_KERNEL);
        if (!cdd->qmgr_scratch)
                return -ENOMEM;
@@ -827,7 +819,7 @@ static int init_cppi41(struct platform_device *pdev, struct cppi41_dd *cdd)
        cppi_writel(QMGR_SCRATCH_SIZE, cdd->qmgr_mem + QMGR_LRAM_SIZE);
        cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM1_BASE);
-        ret = init_descs(pdev, cdd);
+        ret = init_descs(dev, cdd);
        if (ret)
                goto err_td;
@@ -835,7 +827,7 @@ static int init_cppi41(struct platform_device *pdev, struct cppi41_dd *cdd)
        init_sched(cdd);
        return 0;
 err_td:
-        deinit_cpii41(pdev, cdd);
+        deinit_cppi41(dev, cdd);
        return ret;
 }
@@ -914,11 +906,11 @@ static const struct of_device_id cppi41_dma_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, cppi41_dma_ids);
-static const struct cppi_glue_infos *get_glue_info(struct platform_device *pdev)
+static const struct cppi_glue_infos *get_glue_info(struct device *dev)
 {
        const struct of_device_id *of_id;
-        of_id = of_match_node(cppi41_dma_ids, pdev->dev.of_node);
+        of_id = of_match_node(cppi41_dma_ids, dev->of_node);
        if (!of_id)
                return NULL;
        return of_id->data;
@@ -927,11 +919,12 @@ static const struct cppi_glue_infos *get_glue_info(struct platform_device *pdev)
 static int cppi41_dma_probe(struct platform_device *pdev)
 {
        struct cppi41_dd *cdd;
+        struct device *dev = &pdev->dev;
        const struct cppi_glue_infos *glue_info;
        int irq;
        int ret;
-        glue_info = get_glue_info(pdev);
+        glue_info = get_glue_info(dev);
        if (!glue_info)
                return -EINVAL;
@@ -946,14 +939,14 @@ static int cppi41_dma_probe(struct platform_device *pdev)
        cdd->ddev.device_issue_pending = cppi41_dma_issue_pending;
        cdd->ddev.device_prep_slave_sg = cppi41_dma_prep_slave_sg;
        cdd->ddev.device_control = cppi41_dma_control;
-        cdd->ddev.dev = &pdev->dev;
+        cdd->ddev.dev = dev;
        INIT_LIST_HEAD(&cdd->ddev.channels);
        cpp41_dma_info.dma_cap = cdd->ddev.cap_mask;
-        cdd->usbss_mem = of_iomap(pdev->dev.of_node, 0);
+        cdd->usbss_mem = of_iomap(dev->of_node, 0);
-        cdd->ctrl_mem = of_iomap(pdev->dev.of_node, 1);
+        cdd->ctrl_mem = of_iomap(dev->of_node, 1);
-        cdd->sched_mem = of_iomap(pdev->dev.of_node, 2);
+        cdd->sched_mem = of_iomap(dev->of_node, 2);
-        cdd->qmgr_mem = of_iomap(pdev->dev.of_node, 3);
+        cdd->qmgr_mem = of_iomap(dev->of_node, 3);
        if (!cdd->usbss_mem || !cdd->ctrl_mem || !cdd->sched_mem ||
                        !cdd->qmgr_mem) {
@@ -961,31 +954,31 @@ static int cppi41_dma_probe(struct platform_device *pdev)
                goto err_remap;
        }
-        pm_runtime_enable(&pdev->dev);
+        pm_runtime_enable(dev);
-        ret = pm_runtime_get_sync(&pdev->dev);
+        ret = pm_runtime_get_sync(dev);
-        if (ret)
+        if (ret < 0)
                goto err_get_sync;
        cdd->queues_rx = glue_info->queues_rx;
        cdd->queues_tx = glue_info->queues_tx;
        cdd->td_queue = glue_info->td_queue;
-        ret = init_cppi41(pdev, cdd);
+        ret = init_cppi41(dev, cdd);
        if (ret)
                goto err_init_cppi;
-        ret = cppi41_add_chans(pdev, cdd);
+        ret = cppi41_add_chans(dev, cdd);
        if (ret)
                goto err_chans;
-        irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
+        irq = irq_of_parse_and_map(dev->of_node, 0);
        if (!irq)
                goto err_irq;
        cppi_writel(USBSS_IRQ_PD_COMP, cdd->usbss_mem + USBSS_IRQ_ENABLER);
        ret = request_irq(irq, glue_info->isr, IRQF_SHARED,
-                        dev_name(&pdev->dev), cdd);
+                        dev_name(dev), cdd);
        if (ret)
                goto err_irq;
        cdd->irq = irq;
@@ -994,7 +987,7 @@ static int cppi41_dma_probe(struct platform_device *pdev)
        if (ret)
                goto err_dma_reg;
-        ret = of_dma_controller_register(pdev->dev.of_node,
+        ret = of_dma_controller_register(dev->of_node,
                        cppi41_dma_xlate, &cpp41_dma_info);
        if (ret)
                goto err_of;
@@ -1009,11 +1002,11 @@ err_irq:
        cppi_writel(0, cdd->usbss_mem + USBSS_IRQ_CLEARR);
        cleanup_chans(cdd);
 err_chans:
-        deinit_cpii41(pdev, cdd);
+        deinit_cppi41(dev, cdd);
 err_init_cppi:
-        pm_runtime_put(&pdev->dev);
+        pm_runtime_put(dev);
 err_get_sync:
-        pm_runtime_disable(&pdev->dev);
+        pm_runtime_disable(dev);
        iounmap(cdd->usbss_mem);
        iounmap(cdd->ctrl_mem);
        iounmap(cdd->sched_mem);
@@ -1033,7 +1026,7 @@ static int cppi41_dma_remove(struct platform_device *pdev)
        cppi_writel(0, cdd->usbss_mem + USBSS_IRQ_CLEARR);
        free_irq(cdd->irq, cdd);
        cleanup_chans(cdd);
-        deinit_cpii41(pdev, cdd);
+        deinit_cppi41(&pdev->dev, cdd);
        iounmap(cdd->usbss_mem);
        iounmap(cdd->ctrl_mem);
        iounmap(cdd->sched_mem);
@@ -1044,12 +1037,53 @@ static int cppi41_dma_remove(struct platform_device *pdev)
        return 0;
 }
+#ifdef CONFIG_PM_SLEEP
+static int cppi41_suspend(struct device *dev)
+{
+        struct cppi41_dd *cdd = dev_get_drvdata(dev);
+        cdd->dma_tdfdq = cppi_readl(cdd->ctrl_mem + DMA_TDFDQ);
+        cppi_writel(0, cdd->usbss_mem + USBSS_IRQ_CLEARR);
+        disable_sched(cdd);
+        return 0;
+}
+static int cppi41_resume(struct device *dev)
+{
+        struct cppi41_dd *cdd = dev_get_drvdata(dev);
+        struct cppi41_channel *c;
+        int i;
+        for (i = 0; i < DESCS_AREAS; i++)
+                cppi_writel(cdd->descs_phys, cdd->qmgr_mem + QMGR_MEMBASE(i));
+        list_for_each_entry(c, &cdd->ddev.channels, chan.device_node)
+                if (!c->is_tx)
+                        cppi_writel(c->q_num, c->gcr_reg + RXHPCRA0);
+        init_sched(cdd);
+        cppi_writel(cdd->dma_tdfdq, cdd->ctrl_mem + DMA_TDFDQ);
+        cppi_writel(cdd->scratch_phys, cdd->qmgr_mem + QMGR_LRAM0_BASE);
+        cppi_writel(QMGR_SCRATCH_SIZE, cdd->qmgr_mem + QMGR_LRAM_SIZE);
+        cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM1_BASE);
+        cppi_writel(USBSS_IRQ_PD_COMP, cdd->usbss_mem + USBSS_IRQ_ENABLER);
+        return 0;
+}
+#endif
+static SIMPLE_DEV_PM_OPS(cppi41_pm_ops, cppi41_suspend, cppi41_resume);
 static struct platform_driver cpp41_dma_driver = {
        .probe  = cppi41_dma_probe,
        .remove = cppi41_dma_remove,
        .driver = {
                .name = "cppi41-dma-engine",
                .owner = THIS_MODULE,
+                .pm = &cppi41_pm_ops,
                .of_match_table = of_match_ptr(cppi41_dma_ids),
        },
 };
diff --git a/drivers/dma/dma-jz4740.c b/drivers/dma/dma-jz4740.c
index b0c0c8268d42..94c380f07538 100644
--- a/drivers/dma/dma-jz4740.c
+++ b/drivers/dma/dma-jz4740.c
@@ -491,7 +491,7 @@ static enum dma_status jz4740_dma_tx_status(struct dma_chan *c,
        unsigned long flags;
        status = dma_cookie_status(c, cookie, state);
-        if (status == DMA_SUCCESS || !state)
+        if (status == DMA_COMPLETE || !state)
                return status;
        spin_lock_irqsave(&chan->vchan.lock, flags);
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 9162ac80c18f..ea806bdc12ef 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -65,6 +65,7 @@
 #include <linux/acpi.h>
 #include <linux/acpi_dma.h>
 #include <linux/of_dma.h>
+#include <linux/mempool.h>
 static DEFINE_MUTEX(dma_list_mutex);
 static DEFINE_IDR(dma_idr);
@@ -901,98 +902,132 @@ void dma_async_device_unregister(struct dma_device *device)
 }
 EXPORT_SYMBOL(dma_async_device_unregister);
-/**
+struct dmaengine_unmap_pool {
- * dma_async_memcpy_buf_to_buf - offloaded copy between virtual addresses
+        struct kmem_cache *cache;
- * @chan: DMA channel to offload copy to
+        const char *name;
- * @dest: destination address (virtual)
+        mempool_t *pool;
- * @src: source address (virtual)
+        size_t size;
- * @len: length
+};
- *
- * Both @dest and @src must be mappable to a bus address according to the
- * DMA mapping API rules for streaming mappings.
- * Both @dest and @src must stay memory resident (kernel memory or locked
- * user space pages).
- */
-dma_cookie_t
-dma_async_memcpy_buf_to_buf(struct dma_chan *chan, void *dest,
-                        void *src, size_t len)
-{
-        struct dma_device *dev = chan->device;
-        struct dma_async_tx_descriptor *tx;
-        dma_addr_t dma_dest, dma_src;
-        dma_cookie_t cookie;
-        unsigned long flags;
-        dma_src = dma_map_single(dev->dev, src, len, DMA_TO_DEVICE);
+#define __UNMAP_POOL(x) { .size = x, .name = "dmaengine-unmap-" __stringify(x) }
-        dma_dest = dma_map_single(dev->dev, dest, len, DMA_FROM_DEVICE);
+static struct dmaengine_unmap_pool unmap_pool[] = {
-        flags = DMA_CTRL_ACK |
+        __UNMAP_POOL(2),
-                DMA_COMPL_SRC_UNMAP_SINGLE |
+        #if IS_ENABLED(CONFIG_ASYNC_TX_DMA)
-                DMA_COMPL_DEST_UNMAP_SINGLE;
+        __UNMAP_POOL(16),
-        tx = dev->device_prep_dma_memcpy(chan, dma_dest, dma_src, len, flags);
+        __UNMAP_POOL(128),
+        __UNMAP_POOL(256),
+        #endif
+};
-        if (!tx) {
+static struct dmaengine_unmap_pool *__get_unmap_pool(int nr)
-                dma_unmap_single(dev->dev, dma_src, len, DMA_TO_DEVICE);
+{
-                dma_unmap_single(dev->dev, dma_dest, len, DMA_FROM_DEVICE);
+        int order = get_count_order(nr);
-                return -ENOMEM;
+        switch (order) {
+        case 0 ... 1:
+                return &unmap_pool[0];
+        case 2 ... 4:
+                return &unmap_pool[1];
+        case 5 ... 7:
+                return &unmap_pool[2];
+        case 8:
+                return &unmap_pool[3];
+        default:
+                BUG();
+                return NULL;
        }
+}
-        tx->callback = NULL;
+static void dmaengine_unmap(struct kref *kref)
-        cookie = tx->tx_submit(tx);
+{
+        struct dmaengine_unmap_data *unmap = container_of(kref, typeof(*unmap), kref);
+        struct device *dev = unmap->dev;
+        int cnt, i;
+        cnt = unmap->to_cnt;
+        for (i = 0; i < cnt; i++)
+                dma_unmap_page(dev, unmap->addr[i], unmap->len,
+                               DMA_TO_DEVICE);
+        cnt += unmap->from_cnt;
+        for (; i < cnt; i++)
+                dma_unmap_page(dev, unmap->addr[i], unmap->len,
+                               DMA_FROM_DEVICE);
+        cnt += unmap->bidi_cnt;
+        for (; i < cnt; i++) {
+                if (unmap->addr[i] == 0)
+                        continue;
+                dma_unmap_page(dev, unmap->addr[i], unmap->len,
+                               DMA_BIDIRECTIONAL);
+        }
+        mempool_free(unmap, __get_unmap_pool(cnt)->pool);
+}
-        preempt_disable();
+void dmaengine_unmap_put(struct dmaengine_unmap_data *unmap)
-        __this_cpu_add(chan->local->bytes_transferred, len);
+{
-        __this_cpu_inc(chan->local->memcpy_count);
+        if (unmap)
-        preempt_enable();
+                kref_put(&unmap->kref, dmaengine_unmap);
+}
+EXPORT_SYMBOL_GPL(dmaengine_unmap_put);
-        return cookie;
+static void dmaengine_destroy_unmap_pool(void)
+{
+        int i;
+        for (i = 0; i < ARRAY_SIZE(unmap_pool); i++) {
+                struct dmaengine_unmap_pool *p = &unmap_pool[i];
+                if (p->pool)
+                        mempool_destroy(p->pool);
+                p->pool = NULL;
+                if (p->cache)
+                        kmem_cache_destroy(p->cache);
+                p->cache = NULL;
+        }
 }
-EXPORT_SYMBOL(dma_async_memcpy_buf_to_buf);
-/**
+static int __init dmaengine_init_unmap_pool(void)
- * dma_async_memcpy_buf_to_pg - offloaded copy from address to page
- * @chan: DMA channel to offload copy to
- * @page: destination page
- * @offset: offset in page to copy to
- * @kdata: source address (virtual)
- * @len: length
- *
- * Both @page/@offset and @kdata must be mappable to a bus address according
- * to the DMA mapping API rules for streaming mappings.
- * Both @page/@offset and @kdata must stay memory resident (kernel memory or
- * locked user space pages)
- */
-dma_cookie_t
-dma_async_memcpy_buf_to_pg(struct dma_chan *chan, struct page *page,
-                        unsigned int offset, void *kdata, size_t len)
 {
-        struct dma_device *dev = chan->device;
+        int i;
-        struct dma_async_tx_descriptor *tx;
-        dma_addr_t dma_dest, dma_src;
-        dma_cookie_t cookie;
-        unsigned long flags;
-        dma_src = dma_map_single(dev->dev, kdata, len, DMA_TO_DEVICE);
+        for (i = 0; i < ARRAY_SIZE(unmap_pool); i++) {
-        dma_dest = dma_map_page(dev->dev, page, offset, len, DMA_FROM_DEVICE);
+                struct dmaengine_unmap_pool *p = &unmap_pool[i];
-        flags = DMA_CTRL_ACK | DMA_COMPL_SRC_UNMAP_SINGLE;
+                size_t size;
-        tx = dev->device_prep_dma_memcpy(chan, dma_dest, dma_src, len, flags);
-        if (!tx) {
+                size = sizeof(struct dmaengine_unmap_data) +
-                dma_unmap_single(dev->dev, dma_src, len, DMA_TO_DEVICE);
+                       sizeof(dma_addr_t) * p->size;
-                dma_unmap_page(dev->dev, dma_dest, len, DMA_FROM_DEVICE);
-                return -ENOMEM;
+                p->cache = kmem_cache_create(p->name, size, 0,
+                                             SLAB_HWCACHE_ALIGN, NULL);
+                if (!p->cache)
+                        break;
+                p->pool = mempool_create_slab_pool(1, p->cache);
+                if (!p->pool)
+                        break;
        }
-        tx->callback = NULL;
+        if (i == ARRAY_SIZE(unmap_pool))
-        cookie = tx->tx_submit(tx);
+                return 0;
-        preempt_disable();
+        dmaengine_destroy_unmap_pool();
-        __this_cpu_add(chan->local->bytes_transferred, len);
+        return -ENOMEM;
-        __this_cpu_inc(chan->local->memcpy_count);
+}
-        preempt_enable();
-        return cookie;
+struct dmaengine_unmap_data *
+dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags)
+{
+        struct dmaengine_unmap_data *unmap;
+        unmap = mempool_alloc(__get_unmap_pool(nr)->pool, flags);
+        if (!unmap)
+                return NULL;
+        memset(unmap, 0, sizeof(*unmap));
+        kref_init(&unmap->kref);
+        unmap->dev = dev;
+        return unmap;
 }
-EXPORT_SYMBOL(dma_async_memcpy_buf_to_pg);
+EXPORT_SYMBOL(dmaengine_get_unmap_data);
 /**
 * dma_async_memcpy_pg_to_pg - offloaded copy from page to page
@@ -1015,24 +1050,33 @@ dma_async_memcpy_pg_to_pg(struct dma_chan *chan, struct page *dest_pg,
 {
        struct dma_device *dev = chan->device;
        struct dma_async_tx_descriptor *tx;
-        dma_addr_t dma_dest, dma_src;
+        struct dmaengine_unmap_data *unmap;
        dma_cookie_t cookie;
        unsigned long flags;
-        dma_src = dma_map_page(dev->dev, src_pg, src_off, len, DMA_TO_DEVICE);
+        unmap = dmaengine_get_unmap_data(dev->dev, 2, GFP_NOIO);
-        dma_dest = dma_map_page(dev->dev, dest_pg, dest_off, len,
+        if (!unmap)
-                                DMA_FROM_DEVICE);
+                return -ENOMEM;
+        unmap->to_cnt = 1;
+        unmap->from_cnt = 1;
+        unmap->addr[0] = dma_map_page(dev->dev, src_pg, src_off, len,
+                                      DMA_TO_DEVICE);
+        unmap->addr[1] = dma_map_page(dev->dev, dest_pg, dest_off, len,
+                                      DMA_FROM_DEVICE);
+        unmap->len = len;
        flags = DMA_CTRL_ACK;
-        tx = dev->device_prep_dma_memcpy(chan, dma_dest, dma_src, len, flags);
+        tx = dev->device_prep_dma_memcpy(chan, unmap->addr[1], unmap->addr[0],
+                                         len, flags);
        if (!tx) {
-                dma_unmap_page(dev->dev, dma_src, len, DMA_TO_DEVICE);
+                dmaengine_unmap_put(unmap);
-                dma_unmap_page(dev->dev, dma_dest, len, DMA_FROM_DEVICE);
                return -ENOMEM;
        }
-        tx->callback = NULL;
+        dma_set_unmap(tx, unmap);
        cookie = tx->tx_submit(tx);
+        dmaengine_unmap_put(unmap);
        preempt_disable();
        __this_cpu_add(chan->local->bytes_transferred, len);
@@ -1043,6 +1087,52 @@ dma_async_memcpy_pg_to_pg(struct dma_chan *chan, struct page *dest_pg,
 }
 EXPORT_SYMBOL(dma_async_memcpy_pg_to_pg);
+/**
+ * dma_async_memcpy_buf_to_buf - offloaded copy between virtual addresses
+ * @chan: DMA channel to offload copy to
+ * @dest: destination address (virtual)
+ * @src: source address (virtual)
+ * @len: length
+ *
+ * Both @dest and @src must be mappable to a bus address according to the
+ * DMA mapping API rules for streaming mappings.
+ * Both @dest and @src must stay memory resident (kernel memory or locked
+ * user space pages).
+ */
+dma_cookie_t
+dma_async_memcpy_buf_to_buf(struct dma_chan *chan, void *dest,
+                            void *src, size_t len)
+{
+        return dma_async_memcpy_pg_to_pg(chan, virt_to_page(dest),
+                                         (unsigned long) dest & ~PAGE_MASK,
+                                         virt_to_page(src),
+                                         (unsigned long) src & ~PAGE_MASK, len);
+}
+EXPORT_SYMBOL(dma_async_memcpy_buf_to_buf);
+/**
+ * dma_async_memcpy_buf_to_pg - offloaded copy from address to page
+ * @chan: DMA channel to offload copy to
+ * @page: destination page
+ * @offset: offset in page to copy to
+ * @kdata: source address (virtual)
+ * @len: length
+ *
+ * Both @page/@offset and @kdata must be mappable to a bus address according
+ * to the DMA mapping API rules for streaming mappings.
+ * Both @page/@offset and @kdata must stay memory resident (kernel memory or
+ * locked user space pages)
+ */
+dma_cookie_t
+dma_async_memcpy_buf_to_pg(struct dma_chan *chan, struct page *page,
+                           unsigned int offset, void *kdata, size_t len)
+{
+        return dma_async_memcpy_pg_to_pg(chan, page, offset,
+                                         virt_to_page(kdata),
+                                         (unsigned long) kdata & ~PAGE_MASK, len);
+}
+EXPORT_SYMBOL(dma_async_memcpy_buf_to_pg);
 void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx,
        struct dma_chan *chan)
 {
@@ -1062,7 +1152,7 @@ dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx)
        unsigned long dma_sync_wait_timeout = jiffies + msecs_to_jiffies(5000);
        if (!tx)
-                return DMA_SUCCESS;
+                return DMA_COMPLETE;
        while (tx->cookie == -EBUSY) {
                if (time_after_eq(jiffies, dma_sync_wait_timeout)) {
@@ -1116,6 +1206,10 @@ EXPORT_SYMBOL_GPL(dma_run_dependencies);
 static int __init dma_bus_init(void)
 {
+        int err = dmaengine_init_unmap_pool();
+        if (err)
+                return err;
        return class_register(&dma_devclass);
 }
 arch_initcall(dma_bus_init);
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 92f796cdc6ab..20f9a3aaf926 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -8,6 +8,8 @@
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
@@ -19,10 +21,6 @@
 #include <linux/random.h>
 #include <linux/slab.h>
 #include <linux/wait.h>
-#include <linux/ctype.h>
-#include <linux/debugfs.h>
-#include <linux/uaccess.h>
-#include <linux/seq_file.h>
 static unsigned int test_buf_size = 16384;
 module_param(test_buf_size, uint, S_IRUGO | S_IWUSR);
@@ -68,92 +66,13 @@ module_param(timeout, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(timeout, "Transfer Timeout in msec (default: 3000), "
                 "Pass -1 for infinite timeout");
-/* Maximum amount of mismatched bytes in buffer to print */
+static bool noverify;
-#define MAX_ERROR_COUNT         32
+module_param(noverify, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(noverify, "Disable random data setup and verification");
-/*
- * Initialization patterns. All bytes in the source buffer has bit 7
- * set, all bytes in the destination buffer has bit 7 cleared.
- *
- * Bit 6 is set for all bytes which are to be copied by the DMA
- * engine. Bit 5 is set for all bytes which are to be overwritten by
- * the DMA engine.
- *
- * The remaining bits are the inverse of a counter which increments by
- * one for each byte address.
- */
-#define PATTERN_SRC             0x80
-#define PATTERN_DST             0x00
-#define PATTERN_COPY            0x40
-#define PATTERN_OVERWRITE       0x20
-#define PATTERN_COUNT_MASK      0x1f
-enum dmatest_error_type {
-        DMATEST_ET_OK,
-        DMATEST_ET_MAP_SRC,
-        DMATEST_ET_MAP_DST,
-        DMATEST_ET_PREP,
-        DMATEST_ET_SUBMIT,
-        DMATEST_ET_TIMEOUT,
-        DMATEST_ET_DMA_ERROR,
-        DMATEST_ET_DMA_IN_PROGRESS,
-        DMATEST_ET_VERIFY,
-        DMATEST_ET_VERIFY_BUF,
-};
-struct dmatest_verify_buffer {
-        unsigned int    index;
-        u8              expected;
-        u8              actual;
-};
-struct dmatest_verify_result {
-        unsigned int                    error_count;
-        struct dmatest_verify_buffer    data[MAX_ERROR_COUNT];
-        u8                              pattern;
-        bool                            is_srcbuf;
-};
-struct dmatest_thread_result {
-        struct list_head        node;
-        unsigned int            n;
-        unsigned int            src_off;
-        unsigned int            dst_off;
-        unsigned int            len;
-        enum dmatest_error_type type;
-        union {
-                unsigned long                   data;
-                dma_cookie_t                    cookie;
-                enum dma_status                 status;
-                int                             error;
-                struct dmatest_verify_result    *vr;
-        };
-};
-struct dmatest_result {
-        struct list_head        node;
-        char                    *name;
-        struct list_head        results;
-};
-struct dmatest_info;
-struct dmatest_thread {
-        struct list_head        node;
-        struct dmatest_info     *info;
-        struct task_struct      *task;
-        struct dma_chan         *chan;
-        u8                      **srcs;
-        u8                      **dsts;
-        enum dma_transaction_type type;
-        bool                    done;
-};
-struct dmatest_chan {
+static bool verbose;
-        struct list_head        node;
+module_param(verbose, bool, S_IRUGO | S_IWUSR);
-        struct dma_chan         *chan;
+MODULE_PARM_DESC(verbose, "Enable \"success\" result messages (default: off)");
-        struct list_head        threads;
-};
 /**
 * struct dmatest_params - test parameters.
@@ -177,6 +96,7 @@ struct dmatest_params {
        unsigned int    xor_sources;
        unsigned int    pq_sources;
        int             timeout;
+        bool            noverify;
 };
 /**
@@ -184,7 +104,7 @@ struct dmatest_params {
 * @params:             test parameters
 * @lock:               access protection to the fields of this structure
 */
-struct dmatest_info {
+static struct dmatest_info {
        /* Test parameters */
        struct dmatest_params   params;
@@ -192,16 +112,95 @@ struct dmatest_info {
        struct list_head        channels;
        unsigned int            nr_channels;
        struct mutex            lock;
+        bool                    did_init;
+} test_info = {
+        .channels = LIST_HEAD_INIT(test_info.channels),
+        .lock = __MUTEX_INITIALIZER(test_info.lock),
+};
+static int dmatest_run_set(const char *val, const struct kernel_param *kp);
+static int dmatest_run_get(char *val, const struct kernel_param *kp);
+static struct kernel_param_ops run_ops = {
+        .set = dmatest_run_set,
+        .get = dmatest_run_get,
+};
+static bool dmatest_run;
+module_param_cb(run, &run_ops, &dmatest_run, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(run, "Run the test (default: false)");
+/* Maximum amount of mismatched bytes in buffer to print */
+#define MAX_ERROR_COUNT         32
+/*
+ * Initialization patterns. All bytes in the source buffer has bit 7
+ * set, all bytes in the destination buffer has bit 7 cleared.
+ *
+ * Bit 6 is set for all bytes which are to be copied by the DMA
+ * engine. Bit 5 is set for all bytes which are to be overwritten by
+ * the DMA engine.
+ *
+ * The remaining bits are the inverse of a counter which increments by
+ * one for each byte address.
+ */
+#define PATTERN_SRC             0x80
+#define PATTERN_DST             0x00
+#define PATTERN_COPY            0x40
+#define PATTERN_OVERWRITE       0x20
+#define PATTERN_COUNT_MASK      0x1f
-        /* debugfs related stuff */
+struct dmatest_thread {
-        struct dentry           *root;
+        struct list_head        node;
+        struct dmatest_info     *info;
+        struct task_struct      *task;
+        struct dma_chan         *chan;
+        u8                      **srcs;
+        u8                      **dsts;
+        enum dma_transaction_type type;
+        bool                    done;
+};
-        /* Test results */
+struct dmatest_chan {
-        struct list_head        results;
+        struct list_head        node;
-        struct mutex            results_lock;
+        struct dma_chan         *chan;
+        struct list_head        threads;
 };
-static struct dmatest_info test_info;
+static DECLARE_WAIT_QUEUE_HEAD(thread_wait);
+static bool wait;
+static bool is_threaded_test_run(struct dmatest_info *info)
+{
+        struct dmatest_chan *dtc;
+        list_for_each_entry(dtc, &info->channels, node) {
+                struct dmatest_thread *thread;
+                list_for_each_entry(thread, &dtc->threads, node) {
+                        if (!thread->done)
+                                return true;
+                }
+        }
+        return false;
+}
+static int dmatest_wait_get(char *val, const struct kernel_param *kp)
+{
+        struct dmatest_info *info = &test_info;
+        struct dmatest_params *params = &info->params;
+        if (params->iterations)
+                wait_event(thread_wait, !is_threaded_test_run(info));
+        wait = true;
+        return param_get_bool(val, kp);
+}
+static struct kernel_param_ops wait_ops = {
+        .get = dmatest_wait_get,
+        .set = param_set_bool,
+};
+module_param_cb(wait, &wait_ops, &wait, S_IRUGO);
+MODULE_PARM_DESC(wait, "Wait for tests to complete (default: false)");
 static bool dmatest_match_channel(struct dmatest_params *params,
                struct dma_chan *chan)
@@ -223,7 +222,7 @@ static unsigned long dmatest_random(void)
 {
        unsigned long buf;
-        get_random_bytes(&buf, sizeof(buf));
+        prandom_bytes(&buf, sizeof(buf));
        return buf;
 }
@@ -262,9 +261,31 @@ static void dmatest_init_dsts(u8 **bufs, unsigned int start, unsigned int len,
        }
 }
-static unsigned int dmatest_verify(struct dmatest_verify_result *vr, u8 **bufs,
+static void dmatest_mismatch(u8 actual, u8 pattern, unsigned int index,
-                unsigned int start, unsigned int end, unsigned int counter,
+                unsigned int counter, bool is_srcbuf)
-                u8 pattern, bool is_srcbuf)
+{
+        u8              diff = actual ^ pattern;
+        u8              expected = pattern | (~counter & PATTERN_COUNT_MASK);
+        const char      *thread_name = current->comm;
+        if (is_srcbuf)
+                pr_warn("%s: srcbuf[0x%x] overwritten! Expected %02x, got %02x\n",
+                        thread_name, index, expected, actual);
+        else if ((pattern & PATTERN_COPY)
+                        && (diff & (PATTERN_COPY | PATTERN_OVERWRITE)))
+                pr_warn("%s: dstbuf[0x%x] not copied! Expected %02x, got %02x\n",
+                        thread_name, index, expected, actual);
+        else if (diff & PATTERN_SRC)
+                pr_warn("%s: dstbuf[0x%x] was copied! Expected %02x, got %02x\n",
+                        thread_name, index, expected, actual);
+        else
+                pr_warn("%s: dstbuf[0x%x] mismatch! Expected %02x, got %02x\n",
+                        thread_name, index, expected, actual);
+}
+static unsigned int dmatest_verify(u8 **bufs, unsigned int start,
+                unsigned int end, unsigned int counter, u8 pattern,
+                bool is_srcbuf)
 {
        unsigned int i;
        unsigned int error_count = 0;
@@ -272,7 +293,6 @@ static unsigned int dmatest_verify(struct dmatest_verify_result *vr, u8 **bufs,
        u8 expected;
        u8 *buf;
        unsigned int counter_orig = counter;
-        struct dmatest_verify_buffer *vb;
        for (; (buf = *bufs); bufs++) {
                counter = counter_orig;
@@ -280,12 +300,9 @@ static unsigned int dmatest_verify(struct dmatest_verify_result *vr, u8 **bufs,
                        actual = buf[i];
                        expected = pattern | (~counter & PATTERN_COUNT_MASK);
                        if (actual != expected) {
-                                if (error_count < MAX_ERROR_COUNT && vr) {
+                                if (error_count < MAX_ERROR_COUNT)
-                                        vb = &vr->data[error_count];
+                                        dmatest_mismatch(actual, pattern, i,
-                                        vb->index = i;
+                                                         counter, is_srcbuf);
-                                        vb->expected = expected;
-                                        vb->actual = actual;
-                                }
                                error_count++;
                        }
                        counter++;
@@ -293,7 +310,7 @@ static unsigned int dmatest_verify(struct dmatest_verify_result *vr, u8 **bufs,
        }
        if (error_count > MAX_ERROR_COUNT)
-                pr_warning("%s: %u errors suppressed\n",
+                pr_warn("%s: %u errors suppressed\n",
                        current->comm, error_count - MAX_ERROR_COUNT);
        return error_count;
@@ -313,20 +330,6 @@ static void dmatest_callback(void *arg)
        wake_up_all(done->wait);
 }
-static inline void unmap_src(struct device *dev, dma_addr_t *addr, size_t len,
-                             unsigned int count)
-{
-        while (count--)
-                dma_unmap_single(dev, addr[count], len, DMA_TO_DEVICE);
-}
-static inline void unmap_dst(struct device *dev, dma_addr_t *addr, size_t len,
-                             unsigned int count)
-{
-        while (count--)
-                dma_unmap_single(dev, addr[count], len, DMA_BIDIRECTIONAL);
-}
 static unsigned int min_odd(unsigned int x, unsigned int y)
 {
        unsigned int val = min(x, y);
@@ -334,172 +337,49 @@ static unsigned int min_odd(unsigned int x, unsigned int y)
        return val % 2 ? val : val - 1;
 }
-static char *verify_result_get_one(struct dmatest_verify_result *vr,
+static void result(const char *err, unsigned int n, unsigned int src_off,
-                unsigned int i)
+                   unsigned int dst_off, unsigned int len, unsigned long data)
 {
-        struct dmatest_verify_buffer *vb = &vr->data[i];
+        pr_info("%s: result #%u: '%s' with src_off=0x%x dst_off=0x%x len=0x%x (%lu)",
-        u8 diff = vb->actual ^ vr->pattern;
+                current->comm, n, err, src_off, dst_off, len, data);
-        static char buf[512];
-        char *msg;
-        if (vr->is_srcbuf)
-                msg = "srcbuf overwritten!";
-        else if ((vr->pattern & PATTERN_COPY)
-                        && (diff & (PATTERN_COPY | PATTERN_OVERWRITE)))
-                msg = "dstbuf not copied!";
-        else if (diff & PATTERN_SRC)
-                msg = "dstbuf was copied!";
-        else
-                msg = "dstbuf mismatch!";
-        snprintf(buf, sizeof(buf) - 1, "%s [0x%x] Expected %02x, got %02x", msg,
-                 vb->index, vb->expected, vb->actual);
-        return buf;
 }
-static char *thread_result_get(const char *name,
+static void dbg_result(const char *err, unsigned int n, unsigned int src_off,
-                struct dmatest_thread_result *tr)
+                       unsigned int dst_off, unsigned int len,
+                       unsigned long data)
 {
-        static const char * const messages[] = {
+        pr_debug("%s: result #%u: '%s' with src_off=0x%x dst_off=0x%x len=0x%x (%lu)",
-                [DMATEST_ET_OK]                 = "No errors",
+                   current->comm, n, err, src_off, dst_off, len, data);
-                [DMATEST_ET_MAP_SRC]            = "src mapping error",
-                [DMATEST_ET_MAP_DST]            = "dst mapping error",
-                [DMATEST_ET_PREP]               = "prep error",
-                [DMATEST_ET_SUBMIT]             = "submit error",
-                [DMATEST_ET_TIMEOUT]            = "test timed out",
-                [DMATEST_ET_DMA_ERROR]          =
-                        "got completion callback (DMA_ERROR)",
-                [DMATEST_ET_DMA_IN_PROGRESS]    =
-                        "got completion callback (DMA_IN_PROGRESS)",
-                [DMATEST_ET_VERIFY]             = "errors",
-                [DMATEST_ET_VERIFY_BUF]         = "verify errors",
-        };
-        static char buf[512];
-        snprintf(buf, sizeof(buf) - 1,
-                 "%s: #%u: %s with src_off=0x%x ""dst_off=0x%x len=0x%x (%lu)",
-                 name, tr->n, messages[tr->type], tr->src_off, tr->dst_off,
-                 tr->len, tr->data);
-        return buf;
 }
-static int thread_result_add(struct dmatest_info *info,
+#define verbose_result(err, n, src_off, dst_off, len, data) ({ \
-                struct dmatest_result *r, enum dmatest_error_type type,
+        if (verbose) \
-                unsigned int n, unsigned int src_off, unsigned int dst_off,
+                result(err, n, src_off, dst_off, len, data); \
-                unsigned int len, unsigned long data)
+        else \
-{
+                dbg_result(err, n, src_off, dst_off, len, data); \
-        struct dmatest_thread_result *tr;
+})
-        tr = kzalloc(sizeof(*tr), GFP_KERNEL);
-        if (!tr)
-                return -ENOMEM;
-        tr->type = type;
-        tr->n = n;
-        tr->src_off = src_off;
-        tr->dst_off = dst_off;
-        tr->len = len;
-        tr->data = data;
-        mutex_lock(&info->results_lock);
+static unsigned long long dmatest_persec(s64 runtime, unsigned int val)
-        list_add_tail(&tr->node, &r->results);
-        mutex_unlock(&info->results_lock);
-        if (tr->type == DMATEST_ET_OK)
-                pr_debug("%s\n", thread_result_get(r->name, tr));
-        else
-                pr_warn("%s\n", thread_result_get(r->name, tr));
-        return 0;
-}
-static unsigned int verify_result_add(struct dmatest_info *info,
-                struct dmatest_result *r, unsigned int n,
-                unsigned int src_off, unsigned int dst_off, unsigned int len,
-                u8 **bufs, int whence, unsigned int counter, u8 pattern,
-                bool is_srcbuf)
 {
-        struct dmatest_verify_result *vr;
+        unsigned long long per_sec = 1000000;
-        unsigned int error_count;
-        unsigned int buf_off = is_srcbuf ? src_off : dst_off;
-        unsigned int start, end;
-        if (whence < 0) {
-                start = 0;
-                end = buf_off;
-        } else if (whence > 0) {
-                start = buf_off + len;
-                end = info->params.buf_size;
-        } else {
-                start = buf_off;
-                end = buf_off + len;
-        }
-        vr = kmalloc(sizeof(*vr), GFP_KERNEL);
+        if (runtime <= 0)
-        if (!vr) {
+                return 0;
-                pr_warn("dmatest: No memory to store verify result\n");
-                return dmatest_verify(NULL, bufs, start, end, counter, pattern,
-                                      is_srcbuf);
-        }
-        vr->pattern = pattern;
-        vr->is_srcbuf = is_srcbuf;
-        error_count = dmatest_verify(vr, bufs, start, end, counter, pattern,
-                                     is_srcbuf);
-        if (error_count) {
-                vr->error_count = error_count;
-                thread_result_add(info, r, DMATEST_ET_VERIFY_BUF, n, src_off,
-                                  dst_off, len, (unsigned long)vr);
-                return error_count;
-        }
-        kfree(vr);
-        return 0;
-}
-static void result_free(struct dmatest_info *info, const char *name)
-{
-        struct dmatest_result *r, *_r;
-        mutex_lock(&info->results_lock);
-        list_for_each_entry_safe(r, _r, &info->results, node) {
-                struct dmatest_thread_result *tr, *_tr;
-                if (name && strcmp(r->name, name))
-                        continue;
-                list_for_each_entry_safe(tr, _tr, &r->results, node) {
-                        if (tr->type == DMATEST_ET_VERIFY_BUF)
-                                kfree(tr->vr);
-                        list_del(&tr->node);
-                        kfree(tr);
-                }
-                kfree(r->name);
+        /* drop precision until runtime is 32-bits */
-                list_del(&r->node);
+        while (runtime > UINT_MAX) {
-                kfree(r);
+                runtime >>= 1;
+                per_sec <<= 1;
        }
-        mutex_unlock(&info->results_lock);
+        per_sec *= val;
+        do_div(per_sec, runtime);
+        return per_sec;
 }
-static struct dmatest_result *result_init(struct dmatest_info *info,
+static unsigned long long dmatest_KBs(s64 runtime, unsigned long long len)
-                const char *name)
 {
-        struct dmatest_result *r;
+        return dmatest_persec(runtime, len >> 10);
-        r = kzalloc(sizeof(*r), GFP_KERNEL);
-        if (r) {
-                r->name = kstrdup(name, GFP_KERNEL);
-                INIT_LIST_HEAD(&r->results);
-                mutex_lock(&info->results_lock);
-                list_add_tail(&r->node, &info->results);
-                mutex_unlock(&info->results_lock);
-        }
-        return r;
 }
 /*
@@ -525,7 +405,6 @@ static int dmatest_func(void *data)
        struct dmatest_params   *params;
        struct dma_chan         *chan;
        struct dma_device       *dev;
-        const char              *thread_name;
        unsigned int            src_off, dst_off, len;
        unsigned int            error_count;
        unsigned int            failed_tests = 0;
@@ -538,9 +417,10 @@ static int dmatest_func(void *data)
        int                     src_cnt;
        int                     dst_cnt;
        int                     i;
-        struct dmatest_result   *result;
+        ktime_t                 ktime;
+        s64                     runtime = 0;
+        unsigned long long      total_len = 0;
-        thread_name = current->comm;
        set_freezable();
        ret = -ENOMEM;
@@ -570,10 +450,6 @@ static int dmatest_func(void *data)
        } else
                goto err_thread_type;
-        result = result_init(info, thread_name);
-        if (!result)
-                goto err_srcs;
        thread->srcs = kcalloc(src_cnt+1, sizeof(u8 *), GFP_KERNEL);
        if (!thread->srcs)
                goto err_srcs;
@@ -597,17 +473,17 @@ static int dmatest_func(void *data)
        set_user_nice(current, 10);
        /*
-         * src buffers are freed by the DMAEngine code with dma_unmap_single()
+         * src and dst buffers are freed by ourselves below
-         * dst buffers are freed by ourselves below
         */
-        flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT
+        flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
-              | DMA_COMPL_SKIP_DEST_UNMAP | DMA_COMPL_SRC_UNMAP_SINGLE;
+        ktime = ktime_get();
        while (!kthread_should_stop()
               && !(params->iterations && total_tests >= params->iterations)) {
                struct dma_async_tx_descriptor *tx = NULL;
-                dma_addr_t dma_srcs[src_cnt];
+                struct dmaengine_unmap_data *um;
-                dma_addr_t dma_dsts[dst_cnt];
+                dma_addr_t srcs[src_cnt];
+                dma_addr_t *dsts;
                u8 align = 0;
                total_tests++;
@@ -626,81 +502,103 @@ static int dmatest_func(void *data)
                        break;
                }
-                len = dmatest_random() % params->buf_size + 1;
+                if (params->noverify) {
+                        len = params->buf_size;
+                        src_off = 0;
+                        dst_off = 0;
+                } else {
+                        len = dmatest_random() % params->buf_size + 1;
+                        len = (len >> align) << align;
+                        if (!len)
+                                len = 1 << align;
+                        src_off = dmatest_random() % (params->buf_size - len + 1);
+                        dst_off = dmatest_random() % (params->buf_size - len + 1);
+                        src_off = (src_off >> align) << align;
+                        dst_off = (dst_off >> align) << align;
+                        dmatest_init_srcs(thread->srcs, src_off, len,
+                                          params->buf_size);
+                        dmatest_init_dsts(thread->dsts, dst_off, len,
+                                          params->buf_size);
+                }
                len = (len >> align) << align;
                if (!len)
                        len = 1 << align;
-                src_off = dmatest_random() % (params->buf_size - len + 1);
+                total_len += len;
-                dst_off = dmatest_random() % (params->buf_size - len + 1);
-                src_off = (src_off >> align) << align;
+                um = dmaengine_get_unmap_data(dev->dev, src_cnt+dst_cnt,
-                dst_off = (dst_off >> align) << align;
+                                              GFP_KERNEL);
+                if (!um) {
-                dmatest_init_srcs(thread->srcs, src_off, len, params->buf_size);
+                        failed_tests++;
-                dmatest_init_dsts(thread->dsts, dst_off, len, params->buf_size);
+                        result("unmap data NULL", total_tests,
+                               src_off, dst_off, len, ret);
+                        continue;
+                }
+                um->len = params->buf_size;
                for (i = 0; i < src_cnt; i++) {
-                        u8 *buf = thread->srcs[i] + src_off;
+                        unsigned long buf = (unsigned long) thread->srcs[i];
+                        struct page *pg = virt_to_page(buf);
-                        dma_srcs[i] = dma_map_single(dev->dev, buf, len,
+                        unsigned pg_off = buf & ~PAGE_MASK;
-                                                     DMA_TO_DEVICE);
-                        ret = dma_mapping_error(dev->dev, dma_srcs[i]);
+                        um->addr[i] = dma_map_page(dev->dev, pg, pg_off,
+                                                   um->len, DMA_TO_DEVICE);
+                        srcs[i] = um->addr[i] + src_off;
+                        ret = dma_mapping_error(dev->dev, um->addr[i]);
                        if (ret) {
-                                unmap_src(dev->dev, dma_srcs, len, i);
+                                dmaengine_unmap_put(um);
-                                thread_result_add(info, result,
+                                result("src mapping error", total_tests,
-                                                  DMATEST_ET_MAP_SRC,
+                                       src_off, dst_off, len, ret);
-                                                  total_tests, src_off, dst_off,
-                                                  len, ret);
                                failed_tests++;
                                continue;
                        }
+                        um->to_cnt++;
                }
                /* map with DMA_BIDIRECTIONAL to force writeback/invalidate */
+                dsts = &um->addr[src_cnt];
                for (i = 0; i < dst_cnt; i++) {
-                        dma_dsts[i] = dma_map_single(dev->dev, thread->dsts[i],
+                        unsigned long buf = (unsigned long) thread->dsts[i];
-                                                     params->buf_size,
+                        struct page *pg = virt_to_page(buf);
-                                                     DMA_BIDIRECTIONAL);
+                        unsigned pg_off = buf & ~PAGE_MASK;
-                        ret = dma_mapping_error(dev->dev, dma_dsts[i]);
+                        dsts[i] = dma_map_page(dev->dev, pg, pg_off, um->len,
+                                               DMA_BIDIRECTIONAL);
+                        ret = dma_mapping_error(dev->dev, dsts[i]);
                        if (ret) {
-                                unmap_src(dev->dev, dma_srcs, len, src_cnt);
+                                dmaengine_unmap_put(um);
-                                unmap_dst(dev->dev, dma_dsts, params->buf_size,
+                                result("dst mapping error", total_tests,
-                                          i);
+                                       src_off, dst_off, len, ret);
-                                thread_result_add(info, result,
-                                                  DMATEST_ET_MAP_DST,
-                                                  total_tests, src_off, dst_off,
-                                                  len, ret);
                                failed_tests++;
                                continue;
                        }
+                        um->bidi_cnt++;
                }
                if (thread->type == DMA_MEMCPY)
                        tx = dev->device_prep_dma_memcpy(chan,
-                                                         dma_dsts[0] + dst_off,
+                                                         dsts[0] + dst_off,
-                                                         dma_srcs[0], len,
+                                                         srcs[0], len, flags);
-                                                         flags);
                else if (thread->type == DMA_XOR)
                        tx = dev->device_prep_dma_xor(chan,
-                                                      dma_dsts[0] + dst_off,
+                                                      dsts[0] + dst_off,
-                                                      dma_srcs, src_cnt,
+                                                      srcs, src_cnt,
                                                      len, flags);
                else if (thread->type == DMA_PQ) {
                        dma_addr_t dma_pq[dst_cnt];
                        for (i = 0; i < dst_cnt; i++)
-                                dma_pq[i] = dma_dsts[i] + dst_off;
+                                dma_pq[i] = dsts[i] + dst_off;
-                        tx = dev->device_prep_dma_pq(chan, dma_pq, dma_srcs,
+                        tx = dev->device_prep_dma_pq(chan, dma_pq, srcs,
                                                     src_cnt, pq_coefs,
                                                     len, flags);
                }
                if (!tx) {
-                        unmap_src(dev->dev, dma_srcs, len, src_cnt);
+                        dmaengine_unmap_put(um);
-                        unmap_dst(dev->dev, dma_dsts, params->buf_size,
+                        result("prep error", total_tests, src_off,
-                                  dst_cnt);
+                               dst_off, len, ret);
-                        thread_result_add(info, result, DMATEST_ET_PREP,
-                                          total_tests, src_off, dst_off,
-                                          len, 0);
                        msleep(100);
                        failed_tests++;
                        continue;
@@ -712,9 +610,9 @@ static int dmatest_func(void *data)
                cookie = tx->tx_submit(tx);
                if (dma_submit_error(cookie)) {
-                        thread_result_add(info, result, DMATEST_ET_SUBMIT,
+                        dmaengine_unmap_put(um);
-                                          total_tests, src_off, dst_off,
+                        result("submit error", total_tests, src_off,
-                                          len, cookie);
+                               dst_off, len, ret);
                        msleep(100);
                        failed_tests++;
                        continue;
@@ -735,59 +633,59 @@ static int dmatest_func(void *data)
                         * free it this time?" dancing.  For now, just
                         * leave it dangling.
                         */
-                        thread_result_add(info, result, DMATEST_ET_TIMEOUT,
+                        dmaengine_unmap_put(um);
-                                          total_tests, src_off, dst_off,
+                        result("test timed out", total_tests, src_off, dst_off,
-                                          len, 0);
+                               len, 0);
                        failed_tests++;
                        continue;
-                } else if (status != DMA_SUCCESS) {
+                } else if (status != DMA_COMPLETE) {
-                        enum dmatest_error_type type = (status == DMA_ERROR) ?
+                        dmaengine_unmap_put(um);
-                                DMATEST_ET_DMA_ERROR : DMATEST_ET_DMA_IN_PROGRESS;
+                        result(status == DMA_ERROR ?
-                        thread_result_add(info, result, type,
+                               "completion error status" :
-                                          total_tests, src_off, dst_off,
+                               "completion busy status", total_tests, src_off,
-                                          len, status);
+                               dst_off, len, ret);
                        failed_tests++;
                        continue;
                }
-                /* Unmap by myself (see DMA_COMPL_SKIP_DEST_UNMAP above) */
+                dmaengine_unmap_put(um);
-                unmap_dst(dev->dev, dma_dsts, params->buf_size, dst_cnt);
-                error_count = 0;
+                if (params->noverify) {
+                        verbose_result("test passed", total_tests, src_off,
+                                       dst_off, len, 0);
+                        continue;
+                }
-                pr_debug("%s: verifying source buffer...\n", thread_name);
+                pr_debug("%s: verifying source buffer...\n", current->comm);
-                error_count += verify_result_add(info, result, total_tests,
+                error_count = dmatest_verify(thread->srcs, 0, src_off,
-                                src_off, dst_off, len, thread->srcs, -1,
                                0, PATTERN_SRC, true);
-                error_count += verify_result_add(info, result, total_tests,
+                error_count += dmatest_verify(thread->srcs, src_off,
-                                src_off, dst_off, len, thread->srcs, 0,
+                                src_off + len, src_off,
-                                src_off, PATTERN_SRC | PATTERN_COPY, true);
+                                PATTERN_SRC | PATTERN_COPY, true);
-                error_count += verify_result_add(info, result, total_tests,
+                error_count += dmatest_verify(thread->srcs, src_off + len,
-                                src_off, dst_off, len, thread->srcs, 1,
+                                params->buf_size, src_off + len,
-                                src_off + len, PATTERN_SRC, true);
+                                PATTERN_SRC, true);
-                pr_debug("%s: verifying dest buffer...\n", thread_name);
+                pr_debug("%s: verifying dest buffer...\n", current->comm);
-                error_count += verify_result_add(info, result, total_tests,
+                error_count += dmatest_verify(thread->dsts, 0, dst_off,
-                                src_off, dst_off, len, thread->dsts, -1,
                                0, PATTERN_DST, false);
-                error_count += verify_result_add(info, result, total_tests,
+                error_count += dmatest_verify(thread->dsts, dst_off,
-                                src_off, dst_off, len, thread->dsts, 0,
+                                dst_off + len, src_off,
-                                src_off, PATTERN_SRC | PATTERN_COPY, false);
+                                PATTERN_SRC | PATTERN_COPY, false);
-                error_count += verify_result_add(info, result, total_tests,
+                error_count += dmatest_verify(thread->dsts, dst_off + len,
-                                src_off, dst_off, len, thread->dsts, 1,
+                                params->buf_size, dst_off + len,
-                                dst_off + len, PATTERN_DST, false);
+                                PATTERN_DST, false);
                if (error_count) {
-                        thread_result_add(info, result, DMATEST_ET_VERIFY,
+                        result("data error", total_tests, src_off, dst_off,
-                                          total_tests, src_off, dst_off,
+                               len, error_count);
-                                          len, error_count);
                        failed_tests++;
                } else {
-                        thread_result_add(info, result, DMATEST_ET_OK,
+                        verbose_result("test passed", total_tests, src_off,
-                                          total_tests, src_off, dst_off,
+                                       dst_off, len, 0);
-                                          len, 0);
                }
        }
+        runtime = ktime_us_delta(ktime_get(), ktime);
        ret = 0;
        for (i = 0; thread->dsts[i]; i++)
@@ -802,20 +700,17 @@ err_srcbuf:
 err_srcs:
        kfree(pq_coefs);
 err_thread_type:
-        pr_notice("%s: terminating after %u tests, %u failures (status %d)\n",
+        pr_info("%s: summary %u tests, %u failures %llu iops %llu KB/s (%d)\n",
-                        thread_name, total_tests, failed_tests, ret);
+                current->comm, total_tests, failed_tests,
+                dmatest_persec(runtime, total_tests),
+                dmatest_KBs(runtime, total_len), ret);
        /* terminate all transfers on specified channels */
        if (ret)
                dmaengine_terminate_all(chan);
        thread->done = true;
+        wake_up(&thread_wait);
-        if (params->iterations > 0)
-                while (!kthread_should_stop()) {
-                        DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wait_dmatest_exit);
-                        interruptible_sleep_on(&wait_dmatest_exit);
-                }
        return ret;
 }
@@ -828,9 +723,10 @@ static void dmatest_cleanup_channel(struct dmatest_chan *dtc)
        list_for_each_entry_safe(thread, _thread, &dtc->threads, node) {
                ret = kthread_stop(thread->task);
-                pr_debug("dmatest: thread %s exited with status %d\n",
+                pr_debug("thread %s exited with status %d\n",
-                                thread->task->comm, ret);
+                         thread->task->comm, ret);
                list_del(&thread->node);
+                put_task_struct(thread->task);
                kfree(thread);
        }
@@ -861,27 +757,27 @@ static int dmatest_add_threads(struct dmatest_info *info,
        for (i = 0; i < params->threads_per_chan; i++) {
                thread = kzalloc(sizeof(struct dmatest_thread), GFP_KERNEL);
                if (!thread) {
-                        pr_warning("dmatest: No memory for %s-%s%u\n",
+                        pr_warn("No memory for %s-%s%u\n",
-                                   dma_chan_name(chan), op, i);
+                                dma_chan_name(chan), op, i);
                        break;
                }
                thread->info = info;
                thread->chan = dtc->chan;
                thread->type = type;
                smp_wmb();
-                thread->task = kthread_run(dmatest_func, thread, "%s-%s%u",
+                thread->task = kthread_create(dmatest_func, thread, "%s-%s%u",
                                dma_chan_name(chan), op, i);
                if (IS_ERR(thread->task)) {
-                        pr_warning("dmatest: Failed to run thread %s-%s%u\n",
+                        pr_warn("Failed to create thread %s-%s%u\n",
-                                        dma_chan_name(chan), op, i);
+                                dma_chan_name(chan), op, i);
                        kfree(thread);
                        break;
                }
                /* srcbuf and dstbuf are allocated by the thread itself */
+                get_task_struct(thread->task);
                list_add_tail(&thread->node, &dtc->threads);
+                wake_up_process(thread->task);
        }
        return i;
@@ -897,7 +793,7 @@ static int dmatest_add_channel(struct dmatest_info *info,
        dtc = kmalloc(sizeof(struct dmatest_chan), GFP_KERNEL);
        if (!dtc) {
-                pr_warning("dmatest: No memory for %s\n", dma_chan_name(chan));
+                pr_warn("No memory for %s\n", dma_chan_name(chan));
                return -ENOMEM;
        }
@@ -917,7 +813,7 @@ static int dmatest_add_channel(struct dmatest_info *info,
                thread_count += cnt > 0 ? cnt : 0;
        }
-        pr_info("dmatest: Started %u threads using %s\n",
+        pr_info("Started %u threads using %s\n",
                thread_count, dma_chan_name(chan));
        list_add_tail(&dtc->node, &info->channels);
@@ -937,20 +833,20 @@ static bool filter(struct dma_chan *chan, void *param)
                return true;
 }
-static int __run_threaded_test(struct dmatest_info *info)
+static void request_channels(struct dmatest_info *info,
+                             enum dma_transaction_type type)
 {
        dma_cap_mask_t mask;
-        struct dma_chan *chan;
-        struct dmatest_params *params = &info->params;
-        int err = 0;
        dma_cap_zero(mask);
-        dma_cap_set(DMA_MEMCPY, mask);
+        dma_cap_set(type, mask);
        for (;;) {
+                struct dmatest_params *params = &info->params;
+                struct dma_chan *chan;
                chan = dma_request_channel(mask, filter, params);
                if (chan) {
-                        err = dmatest_add_channel(info, chan);
+                        if (dmatest_add_channel(info, chan)) {
-                        if (err) {
                                dma_release_channel(chan);
                                break; /* add_channel failed, punt */
                        }
@@ -960,22 +856,30 @@ static int __run_threaded_test(struct dmatest_info *info)
                    info->nr_channels >= params->max_channels)
                        break; /* we have all we need */
        }
-        return err;
 }
-#ifndef MODULE
+static void run_threaded_test(struct dmatest_info *info)
-static int run_threaded_test(struct dmatest_info *info)
 {
-        int ret;
+        struct dmatest_params *params = &info->params;
-        mutex_lock(&info->lock);
+        /* Copy test parameters */
-        ret = __run_threaded_test(info);
+        params->buf_size = test_buf_size;
-        mutex_unlock(&info->lock);
+        strlcpy(params->channel, strim(test_channel), sizeof(params->channel));
-        return ret;
+        strlcpy(params->device, strim(test_device), sizeof(params->device));
+        params->threads_per_chan = threads_per_chan;
+        params->max_channels = max_channels;
+        params->iterations = iterations;
+        params->xor_sources = xor_sources;
+        params->pq_sources = pq_sources;
+        params->timeout = timeout;
+        params->noverify = noverify;
+        request_channels(info, DMA_MEMCPY);
+        request_channels(info, DMA_XOR);
+        request_channels(info, DMA_PQ);
 }
-#endif
-static void __stop_threaded_test(struct dmatest_info *info)
+static void stop_threaded_test(struct dmatest_info *info)
 {
        struct dmatest_chan *dtc, *_dtc;
        struct dma_chan *chan;
@@ -984,203 +888,86 @@ static void __stop_threaded_test(struct dmatest_info *info)
                list_del(&dtc->node);
                chan = dtc->chan;
                dmatest_cleanup_channel(dtc);
-                pr_debug("dmatest: dropped channel %s\n", dma_chan_name(chan));
+                pr_debug("dropped channel %s\n", dma_chan_name(chan));
                dma_release_channel(chan);
        }
        info->nr_channels = 0;
 }
-static void stop_threaded_test(struct dmatest_info *info)
+static void restart_threaded_test(struct dmatest_info *info, bool run)
 {
-        mutex_lock(&info->lock);
+        /* we might be called early to set run=, defer running until all
-        __stop_threaded_test(info);
+         * parameters have been evaluated
-        mutex_unlock(&info->lock);
+         */
-}
+        if (!info->did_init)
+                return;
-static int __restart_threaded_test(struct dmatest_info *info, bool run)
-{
-        struct dmatest_params *params = &info->params;
        /* Stop any running test first */
-        __stop_threaded_test(info);
+        stop_threaded_test(info);
-        if (run == false)
-                return 0;
-        /* Clear results from previous run */
-        result_free(info, NULL);
-        /* Copy test parameters */
-        params->buf_size = test_buf_size;
-        strlcpy(params->channel, strim(test_channel), sizeof(params->channel));
-        strlcpy(params->device, strim(test_device), sizeof(params->device));
-        params->threads_per_chan = threads_per_chan;
-        params->max_channels = max_channels;
-        params->iterations = iterations;
-        params->xor_sources = xor_sources;
-        params->pq_sources = pq_sources;
-        params->timeout = timeout;
        /* Run test with new parameters */
-        return __run_threaded_test(info);
+        run_threaded_test(info);
-}
-static bool __is_threaded_test_run(struct dmatest_info *info)
-{
-        struct dmatest_chan *dtc;
-        list_for_each_entry(dtc, &info->channels, node) {
-                struct dmatest_thread *thread;
-                list_for_each_entry(thread, &dtc->threads, node) {
-                        if (!thread->done)
-                                return true;
-                }
-        }
-        return false;
 }
-static ssize_t dtf_read_run(struct file *file, char __user *user_buf,
+static int dmatest_run_get(char *val, const struct kernel_param *kp)
-                size_t count, loff_t *ppos)
 {
-        struct dmatest_info *info = file->private_data;
+        struct dmatest_info *info = &test_info;
-        char buf[3];
        mutex_lock(&info->lock);
+        if (is_threaded_test_run(info)) {
-        if (__is_threaded_test_run(info)) {
+                dmatest_run = true;
-                buf[0] = 'Y';
        } else {
-                __stop_threaded_test(info);
+                stop_threaded_test(info);
-                buf[0] = 'N';
+                dmatest_run = false;
        }
        mutex_unlock(&info->lock);
-        buf[1] = '\n';
-        buf[2] = 0x00;
-        return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
-}
-static ssize_t dtf_write_run(struct file *file, const char __user *user_buf,
-                size_t count, loff_t *ppos)
-{
-        struct dmatest_info *info = file->private_data;
-        char buf[16];
-        bool bv;
-        int ret = 0;
-        if (copy_from_user(buf, user_buf, min(count, (sizeof(buf) - 1))))
+        return param_get_bool(val, kp);
-                return -EFAULT;
-        if (strtobool(buf, &bv) == 0) {
-                mutex_lock(&info->lock);
-                if (__is_threaded_test_run(info))
-                        ret = -EBUSY;
-                else
-                        ret = __restart_threaded_test(info, bv);
-                mutex_unlock(&info->lock);
-        }
-        return ret ? ret : count;
 }
-static const struct file_operations dtf_run_fops = {
+static int dmatest_run_set(const char *val, const struct kernel_param *kp)
-        .read   = dtf_read_run,
-        .write  = dtf_write_run,
-        .open   = simple_open,
-        .llseek = default_llseek,
-};
-static int dtf_results_show(struct seq_file *sf, void *data)
 {
-        struct dmatest_info *info = sf->private;
+        struct dmatest_info *info = &test_info;
-        struct dmatest_result *result;
+        int ret;
-        struct dmatest_thread_result *tr;
-        unsigned int i;
-        mutex_lock(&info->results_lock);
+        mutex_lock(&info->lock);
-        list_for_each_entry(result, &info->results, node) {
+        ret = param_set_bool(val, kp);
-                list_for_each_entry(tr, &result->results, node) {
+        if (ret) {
-                        seq_printf(sf, "%s\n",
+                mutex_unlock(&info->lock);
-                                thread_result_get(result->name, tr));
+                return ret;
-                        if (tr->type == DMATEST_ET_VERIFY_BUF) {
-                                for (i = 0; i < tr->vr->error_count; i++) {
-                                        seq_printf(sf, "\t%s\n",
-                                                verify_result_get_one(tr->vr, i));
-                                }
-                        }
-                }
        }
-        mutex_unlock(&info->results_lock);
+        if (is_threaded_test_run(info))
-        return 0;
+                ret = -EBUSY;
-}
+        else if (dmatest_run)
+                restart_threaded_test(info, dmatest_run);
-static int dtf_results_open(struct inode *inode, struct file *file)
-{
-        return single_open(file, dtf_results_show, inode->i_private);
-}
-static const struct file_operations dtf_results_fops = {
-        .open           = dtf_results_open,
-        .read           = seq_read,
-        .llseek         = seq_lseek,
-        .release        = single_release,
-};
-static int dmatest_register_dbgfs(struct dmatest_info *info)
-{
-        struct dentry *d;
-        d = debugfs_create_dir("dmatest", NULL);
-        if (IS_ERR(d))
-                return PTR_ERR(d);
-        if (!d)
-                goto err_root;
-        info->root = d;
+        mutex_unlock(&info->lock);
-        /* Run or stop threaded test */
-        debugfs_create_file("run", S_IWUSR | S_IRUGO, info->root, info,
-                            &dtf_run_fops);
-        /* Results of test in progress */
-        debugfs_create_file("results", S_IRUGO, info->root, info,
-                            &dtf_results_fops);
-        return 0;
-err_root:
+        return ret;
-        pr_err("dmatest: Failed to initialize debugfs\n");
-        return -ENOMEM;
 }
 static int __init dmatest_init(void)
 {
        struct dmatest_info *info = &test_info;
-        int ret;
+        struct dmatest_params *params = &info->params;
-        memset(info, 0, sizeof(*info));
-        mutex_init(&info->lock);
+        if (dmatest_run) {
-        INIT_LIST_HEAD(&info->channels);
+                mutex_lock(&info->lock);
+                run_threaded_test(info);
+                mutex_unlock(&info->lock);
+        }
-        mutex_init(&info->results_lock);
+        if (params->iterations && wait)
-        INIT_LIST_HEAD(&info->results);
+                wait_event(thread_wait, !is_threaded_test_run(info));
-        ret = dmatest_register_dbgfs(info);
+        /* module parameters are stable, inittime tests are started,
-        if (ret)
+         * let userspace take over 'run' control
-                return ret;
+         */
+        info->did_init = true;
-#ifdef MODULE
        return 0;
-#else
-        return run_threaded_test(info);
-#endif
 }
 /* when compiled-in wait for drivers to load first */
 late_initcall(dmatest_init);
@@ -1189,9 +976,9 @@ static void __exit dmatest_exit(void)
 {
        struct dmatest_info *info = &test_info;
-        debugfs_remove_recursive(info->root);
+        mutex_lock(&info->lock);
        stop_threaded_test(info);
-        result_free(info, NULL);
+        mutex_unlock(&info->lock);
 }
 module_exit(dmatest_exit);
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 89eb89f22284..7516be4677cf 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -85,10 +85,6 @@ static struct device *chan2dev(struct dma_chan *chan)
 {
        return &chan->dev->device;
 }
-static struct device *chan2parent(struct dma_chan *chan)
-{
-        return chan->dev->device.parent;
-}
 static struct dw_desc *dwc_first_active(struct dw_dma_chan *dwc)
 {
@@ -311,26 +307,7 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc,
        list_splice_init(&desc->tx_list, &dwc->free_list);
        list_move(&desc->desc_node, &dwc->free_list);
-        if (!is_slave_direction(dwc->direction)) {
+        dma_descriptor_unmap(txd);
-                struct device *parent = chan2parent(&dwc->chan);
-                if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-                        if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
-                                dma_unmap_single(parent, desc->lli.dar,
-                                        desc->total_len, DMA_FROM_DEVICE);
-                        else
-                                dma_unmap_page(parent, desc->lli.dar,
-                                        desc->total_len, DMA_FROM_DEVICE);
-                }
-                if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-                        if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
-                                dma_unmap_single(parent, desc->lli.sar,
-                                        desc->total_len, DMA_TO_DEVICE);
-                        else
-                                dma_unmap_page(parent, desc->lli.sar,
-                                        desc->total_len, DMA_TO_DEVICE);
-                }
-        }
        spin_unlock_irqrestore(&dwc->lock, flags);
        if (callback)
@@ -1098,13 +1075,13 @@ dwc_tx_status(struct dma_chan *chan,
        enum dma_status         ret;
        ret = dma_cookie_status(chan, cookie, txstate);
-        if (ret == DMA_SUCCESS)
+        if (ret == DMA_COMPLETE)
                return ret;
        dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
        ret = dma_cookie_status(chan, cookie, txstate);
-        if (ret != DMA_SUCCESS)
+        if (ret != DMA_COMPLETE)
                dma_set_residue(txstate, dwc_get_residue(dwc));
        if (dwc->paused && ret == DMA_IN_PROGRESS)
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index bef8a368c8dd..2539ea0cbc63 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -46,14 +46,21 @@
 #define EDMA_CHANS      64
 #endif /* CONFIG_ARCH_DAVINCI_DA8XX */
-/* Max of 16 segments per channel to conserve PaRAM slots */
+/*
-#define MAX_NR_SG               16
+ * Max of 20 segments per channel to conserve PaRAM slots
+ * Also note that MAX_NR_SG should be atleast the no.of periods
+ * that are required for ASoC, otherwise DMA prep calls will
+ * fail. Today davinci-pcm is the only user of this driver and
+ * requires atleast 17 slots, so we setup the default to 20.
+ */
+#define MAX_NR_SG               20
 #define EDMA_MAX_SLOTS          MAX_NR_SG
 #define EDMA_DESCRIPTORS        16
 struct edma_desc {
        struct virt_dma_desc            vdesc;
        struct list_head                node;
+        int                             cyclic;
        int                             absync;
        int                             pset_nr;
        int                             processed;
@@ -167,8 +174,13 @@ static void edma_execute(struct edma_chan *echan)
         * then setup a link to the dummy slot, this results in all future
         * events being absorbed and that's OK because we're done
         */
-        if (edesc->processed == edesc->pset_nr)
+        if (edesc->processed == edesc->pset_nr) {
-                edma_link(echan->slot[nslots-1], echan->ecc->dummy_slot);
+                if (edesc->cyclic)
+                        edma_link(echan->slot[nslots-1], echan->slot[1]);
+                else
+                        edma_link(echan->slot[nslots-1],
+                                  echan->ecc->dummy_slot);
+        }
        edma_resume(echan->ch_num);
@@ -250,6 +262,117 @@ static int edma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
        return ret;
 }
+/*
+ * A PaRAM set configuration abstraction used by other modes
+ * @chan: Channel who's PaRAM set we're configuring
+ * @pset: PaRAM set to initialize and setup.
+ * @src_addr: Source address of the DMA
+ * @dst_addr: Destination address of the DMA
+ * @burst: In units of dev_width, how much to send
+ * @dev_width: How much is the dev_width
+ * @dma_length: Total length of the DMA transfer
+ * @direction: Direction of the transfer
+ */
+static int edma_config_pset(struct dma_chan *chan, struct edmacc_param *pset,
+        dma_addr_t src_addr, dma_addr_t dst_addr, u32 burst,
+        enum dma_slave_buswidth dev_width, unsigned int dma_length,
+        enum dma_transfer_direction direction)
+{
+        struct edma_chan *echan = to_edma_chan(chan);
+        struct device *dev = chan->device->dev;
+        int acnt, bcnt, ccnt, cidx;
+        int src_bidx, dst_bidx, src_cidx, dst_cidx;
+        int absync;
+        acnt = dev_width;
+        /*
+         * If the maxburst is equal to the fifo width, use
+         * A-synced transfers. This allows for large contiguous
+         * buffer transfers using only one PaRAM set.
+         */
+        if (burst == 1) {
+                /*
+                 * For the A-sync case, bcnt and ccnt are the remainder
+                 * and quotient respectively of the division of:
+                 * (dma_length / acnt) by (SZ_64K -1). This is so
+                 * that in case bcnt over flows, we have ccnt to use.
+                 * Note: In A-sync tranfer only, bcntrld is used, but it
+                 * only applies for sg_dma_len(sg) >= SZ_64K.
+                 * In this case, the best way adopted is- bccnt for the
+                 * first frame will be the remainder below. Then for
+                 * every successive frame, bcnt will be SZ_64K-1. This
+                 * is assured as bcntrld = 0xffff in end of function.
+                 */
+                absync = false;
+                ccnt = dma_length / acnt / (SZ_64K - 1);
+                bcnt = dma_length / acnt - ccnt * (SZ_64K - 1);
+                /*
+                 * If bcnt is non-zero, we have a remainder and hence an
+                 * extra frame to transfer, so increment ccnt.
+                 */
+                if (bcnt)
+                        ccnt++;
+                else
+                        bcnt = SZ_64K - 1;
+                cidx = acnt;
+        } else {
+                /*
+                 * If maxburst is greater than the fifo address_width,
+                 * use AB-synced transfers where A count is the fifo
+                 * address_width and B count is the maxburst. In this
+                 * case, we are limited to transfers of C count frames
+                 * of (address_width * maxburst) where C count is limited
+                 * to SZ_64K-1. This places an upper bound on the length
+                 * of an SG segment that can be handled.
+                 */
+                absync = true;
+                bcnt = burst;
+                ccnt = dma_length / (acnt * bcnt);
+                if (ccnt > (SZ_64K - 1)) {
+                        dev_err(dev, "Exceeded max SG segment size\n");
+                        return -EINVAL;
+                }
+                cidx = acnt * bcnt;
+        }
+        if (direction == DMA_MEM_TO_DEV) {
+                src_bidx = acnt;
+                src_cidx = cidx;
+                dst_bidx = 0;
+                dst_cidx = 0;
+        } else if (direction == DMA_DEV_TO_MEM)  {
+                src_bidx = 0;
+                src_cidx = 0;
+                dst_bidx = acnt;
+                dst_cidx = cidx;
+        } else {
+                dev_err(dev, "%s: direction not implemented yet\n", __func__);
+                return -EINVAL;
+        }
+        pset->opt = EDMA_TCC(EDMA_CHAN_SLOT(echan->ch_num));
+        /* Configure A or AB synchronized transfers */
+        if (absync)
+                pset->opt |= SYNCDIM;
+        pset->src = src_addr;
+        pset->dst = dst_addr;
+        pset->src_dst_bidx = (dst_bidx << 16) | src_bidx;
+        pset->src_dst_cidx = (dst_cidx << 16) | src_cidx;
+        pset->a_b_cnt = bcnt << 16 | acnt;
+        pset->ccnt = ccnt;
+        /*
+         * Only time when (bcntrld) auto reload is required is for
+         * A-sync case, and in this case, a requirement of reload value
+         * of SZ_64K-1 only is assured. 'link' is initially set to NULL
+         * and then later will be populated by edma_execute.
+         */
+        pset->link_bcntrld = 0xffffffff;
+        return absync;
+}
 static struct dma_async_tx_descriptor *edma_prep_slave_sg(
        struct dma_chan *chan, struct scatterlist *sgl,
        unsigned int sg_len, enum dma_transfer_direction direction,
@@ -258,23 +381,21 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg(
        struct edma_chan *echan = to_edma_chan(chan);
        struct device *dev = chan->device->dev;
        struct edma_desc *edesc;
-        dma_addr_t dev_addr;
+        dma_addr_t src_addr = 0, dst_addr = 0;
        enum dma_slave_buswidth dev_width;
        u32 burst;
        struct scatterlist *sg;
-        int acnt, bcnt, ccnt, src, dst, cidx;
+        int i, nslots, ret;
-        int src_bidx, dst_bidx, src_cidx, dst_cidx;
-        int i, nslots;
        if (unlikely(!echan || !sgl || !sg_len))
                return NULL;
        if (direction == DMA_DEV_TO_MEM) {
-                dev_addr = echan->cfg.src_addr;
+                src_addr = echan->cfg.src_addr;
                dev_width = echan->cfg.src_addr_width;
                burst = echan->cfg.src_maxburst;
        } else if (direction == DMA_MEM_TO_DEV) {
-                dev_addr = echan->cfg.dst_addr;
+                dst_addr = echan->cfg.dst_addr;
                dev_width = echan->cfg.dst_addr_width;
                burst = echan->cfg.dst_maxburst;
        } else {
@@ -307,7 +428,6 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg(
                        if (echan->slot[i] < 0) {
                                kfree(edesc);
                                dev_err(dev, "Failed to allocate slot\n");
-                                kfree(edesc);
                                return NULL;
                        }
                }
@@ -315,64 +435,21 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg(
        /* Configure PaRAM sets for each SG */
        for_each_sg(sgl, sg, sg_len, i) {
+                /* Get address for each SG */
-                acnt = dev_width;
+                if (direction == DMA_DEV_TO_MEM)
+                        dst_addr = sg_dma_address(sg);
-                /*
+                else
-                 * If the maxburst is equal to the fifo width, use
+                        src_addr = sg_dma_address(sg);
-                 * A-synced transfers. This allows for large contiguous
-                 * buffer transfers using only one PaRAM set.
+                ret = edma_config_pset(chan, &edesc->pset[i], src_addr,
-                 */
+                                       dst_addr, burst, dev_width,
-                if (burst == 1) {
+                                       sg_dma_len(sg), direction);
-                        edesc->absync = false;
+                if (ret < 0) {
-                        ccnt = sg_dma_len(sg) / acnt / (SZ_64K - 1);
+                        kfree(edesc);
-                        bcnt = sg_dma_len(sg) / acnt - ccnt * (SZ_64K - 1);
+                        return NULL;
-                        if (bcnt)
-                                ccnt++;
-                        else
-                                bcnt = SZ_64K - 1;
-                        cidx = acnt;
-                /*
-                 * If maxburst is greater than the fifo address_width,
-                 * use AB-synced transfers where A count is the fifo
-                 * address_width and B count is the maxburst. In this
-                 * case, we are limited to transfers of C count frames
-                 * of (address_width * maxburst) where C count is limited
-                 * to SZ_64K-1. This places an upper bound on the length
-                 * of an SG segment that can be handled.
-                 */
-                } else {
-                        edesc->absync = true;
-                        bcnt = burst;
-                        ccnt = sg_dma_len(sg) / (acnt * bcnt);
-                        if (ccnt > (SZ_64K - 1)) {
-                                dev_err(dev, "Exceeded max SG segment size\n");
-                                kfree(edesc);
-                                return NULL;
-                        }
-                        cidx = acnt * bcnt;
                }
-                if (direction == DMA_MEM_TO_DEV) {
+                edesc->absync = ret;
-                        src = sg_dma_address(sg);
-                        dst = dev_addr;
-                        src_bidx = acnt;
-                        src_cidx = cidx;
-                        dst_bidx = 0;
-                        dst_cidx = 0;
-                } else {
-                        src = dev_addr;
-                        dst = sg_dma_address(sg);
-                        src_bidx = 0;
-                        src_cidx = 0;
-                        dst_bidx = acnt;
-                        dst_cidx = cidx;
-                }
-                edesc->pset[i].opt = EDMA_TCC(EDMA_CHAN_SLOT(echan->ch_num));
-                /* Configure A or AB synchronized transfers */
-                if (edesc->absync)
-                        edesc->pset[i].opt |= SYNCDIM;
                /* If this is the last in a current SG set of transactions,
                   enable interrupts so that next set is processed */
@@ -382,17 +459,138 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg(
                /* If this is the last set, enable completion interrupt flag */
                if (i == sg_len - 1)
                        edesc->pset[i].opt |= TCINTEN;
+        }
-                edesc->pset[i].src = src;
+        return vchan_tx_prep(&echan->vchan, &edesc->vdesc, tx_flags);
-                edesc->pset[i].dst = dst;
+}
-                edesc->pset[i].src_dst_bidx = (dst_bidx << 16) | src_bidx;
+static struct dma_async_tx_descriptor *edma_prep_dma_cyclic(
-                edesc->pset[i].src_dst_cidx = (dst_cidx << 16) | src_cidx;
+        struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
+        size_t period_len, enum dma_transfer_direction direction,
+        unsigned long tx_flags, void *context)
+{
+        struct edma_chan *echan = to_edma_chan(chan);
+        struct device *dev = chan->device->dev;
+        struct edma_desc *edesc;
+        dma_addr_t src_addr, dst_addr;
+        enum dma_slave_buswidth dev_width;
+        u32 burst;
+        int i, ret, nslots;
+        if (unlikely(!echan || !buf_len || !period_len))
+                return NULL;
+        if (direction == DMA_DEV_TO_MEM) {
+                src_addr = echan->cfg.src_addr;
+                dst_addr = buf_addr;
+                dev_width = echan->cfg.src_addr_width;
+                burst = echan->cfg.src_maxburst;
+        } else if (direction == DMA_MEM_TO_DEV) {
+                src_addr = buf_addr;
+                dst_addr = echan->cfg.dst_addr;
+                dev_width = echan->cfg.dst_addr_width;
+                burst = echan->cfg.dst_maxburst;
+        } else {
+                dev_err(dev, "%s: bad direction?\n", __func__);
+                return NULL;
+        }
+        if (dev_width == DMA_SLAVE_BUSWIDTH_UNDEFINED) {
+                dev_err(dev, "Undefined slave buswidth\n");
+                return NULL;
+        }
+        if (unlikely(buf_len % period_len)) {
+                dev_err(dev, "Period should be multiple of Buffer length\n");
+                return NULL;
+        }
+        nslots = (buf_len / period_len) + 1;
+        /*
+         * Cyclic DMA users such as audio cannot tolerate delays introduced
+         * by cases where the number of periods is more than the maximum
+         * number of SGs the EDMA driver can handle at a time. For DMA types
+         * such as Slave SGs, such delays are tolerable and synchronized,
+         * but the synchronization is difficult to achieve with Cyclic and
+         * cannot be guaranteed, so we error out early.
+         */
+        if (nslots > MAX_NR_SG)
+                return NULL;
+        edesc = kzalloc(sizeof(*edesc) + nslots *
+                sizeof(edesc->pset[0]), GFP_ATOMIC);
+        if (!edesc) {
+                dev_dbg(dev, "Failed to allocate a descriptor\n");
+                return NULL;
+        }
+        edesc->cyclic = 1;
+        edesc->pset_nr = nslots;
+        dev_dbg(dev, "%s: nslots=%d\n", __func__, nslots);
+        dev_dbg(dev, "%s: period_len=%d\n", __func__, period_len);
+        dev_dbg(dev, "%s: buf_len=%d\n", __func__, buf_len);
+        for (i = 0; i < nslots; i++) {
+                /* Allocate a PaRAM slot, if needed */
+                if (echan->slot[i] < 0) {
+                        echan->slot[i] =
+                                edma_alloc_slot(EDMA_CTLR(echan->ch_num),
+                                                EDMA_SLOT_ANY);
+                        if (echan->slot[i] < 0) {
+                                dev_err(dev, "Failed to allocate slot\n");
+                                return NULL;
+                        }
+                }
+                if (i == nslots - 1) {
+                        memcpy(&edesc->pset[i], &edesc->pset[0],
+                               sizeof(edesc->pset[0]));
+                        break;
+                }
+                ret = edma_config_pset(chan, &edesc->pset[i], src_addr,
+                                       dst_addr, burst, dev_width, period_len,
+                                       direction);
+                if (ret < 0)
+                        return NULL;
-                edesc->pset[i].a_b_cnt = bcnt << 16 | acnt;
+                if (direction == DMA_DEV_TO_MEM)
-                edesc->pset[i].ccnt = ccnt;
+                        dst_addr += period_len;
-                edesc->pset[i].link_bcntrld = 0xffffffff;
+                else
+                        src_addr += period_len;
+                dev_dbg(dev, "%s: Configure period %d of buf:\n", __func__, i);
+                dev_dbg(dev,
+                        "\n pset[%d]:\n"
+                        "  chnum\t%d\n"
+                        "  slot\t%d\n"
+                        "  opt\t%08x\n"
+                        "  src\t%08x\n"
+                        "  dst\t%08x\n"
+                        "  abcnt\t%08x\n"
+                        "  ccnt\t%08x\n"
+                        "  bidx\t%08x\n"
+                        "  cidx\t%08x\n"
+                        "  lkrld\t%08x\n",
+                        i, echan->ch_num, echan->slot[i],
+                        edesc->pset[i].opt,
+                        edesc->pset[i].src,
+                        edesc->pset[i].dst,
+                        edesc->pset[i].a_b_cnt,
+                        edesc->pset[i].ccnt,
+                        edesc->pset[i].src_dst_bidx,
+                        edesc->pset[i].src_dst_cidx,
+                        edesc->pset[i].link_bcntrld);
+                edesc->absync = ret;
+                /*
+                 * Enable interrupts for every period because callback
+                 * has to be called for every period.
+                 */
+                edesc->pset[i].opt |= TCINTEN;
        }
        return vchan_tx_prep(&echan->vchan, &edesc->vdesc, tx_flags);
@@ -406,30 +604,34 @@ static void edma_callback(unsigned ch_num, u16 ch_status, void *data)
        unsigned long flags;
        struct edmacc_param p;
-        /* Pause the channel */
+        edesc = echan->edesc;
-        edma_pause(echan->ch_num);
+        /* Pause the channel for non-cyclic */
+        if (!edesc || (edesc && !edesc->cyclic))
+                edma_pause(echan->ch_num);
        switch (ch_status) {
-        case DMA_COMPLETE:
+        case EDMA_DMA_COMPLETE:
                spin_lock_irqsave(&echan->vchan.lock, flags);
-                edesc = echan->edesc;
                if (edesc) {
-                        if (edesc->processed == edesc->pset_nr) {
+                        if (edesc->cyclic) {
+                                vchan_cyclic_callback(&edesc->vdesc);
+                        } else if (edesc->processed == edesc->pset_nr) {
                                dev_dbg(dev, "Transfer complete, stopping channel %d\n", ch_num);
                                edma_stop(echan->ch_num);
                                vchan_cookie_complete(&edesc->vdesc);
+                                edma_execute(echan);
                        } else {
                                dev_dbg(dev, "Intermediate transfer complete on channel %d\n", ch_num);
+                                edma_execute(echan);
                        }
-                        edma_execute(echan);
                }
                spin_unlock_irqrestore(&echan->vchan.lock, flags);
                break;
-        case DMA_CC_ERROR:
+        case EDMA_DMA_CC_ERROR:
                spin_lock_irqsave(&echan->vchan.lock, flags);
                edma_read_slot(EDMA_CHAN_SLOT(echan->slot[0]), &p);
@@ -579,7 +781,7 @@ static enum dma_status edma_tx_status(struct dma_chan *chan,
        unsigned long flags;
        ret = dma_cookie_status(chan, cookie, txstate);
-        if (ret == DMA_SUCCESS || !txstate)
+        if (ret == DMA_COMPLETE || !txstate)
                return ret;
        spin_lock_irqsave(&echan->vchan.lock, flags);
@@ -619,6 +821,7 @@ static void edma_dma_init(struct edma_cc *ecc, struct dma_device *dma,
                          struct device *dev)
 {
        dma->device_prep_slave_sg = edma_prep_slave_sg;
+        dma->device_prep_dma_cyclic = edma_prep_dma_cyclic;
        dma->device_alloc_chan_resources = edma_alloc_chan_resources;
        dma->device_free_chan_resources = edma_free_chan_resources;
        dma->device_issue_pending = edma_issue_pending;
diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c
index 591cd8c63abb..cb4bf682a708 100644
--- a/drivers/dma/ep93xx_dma.c
+++ b/drivers/dma/ep93xx_dma.c
@@ -733,28 +733,6 @@ static void ep93xx_dma_advance_work(struct ep93xx_dma_chan *edmac)
        spin_unlock_irqrestore(&edmac->lock, flags);
 }
-static void ep93xx_dma_unmap_buffers(struct ep93xx_dma_desc *desc)
-{
-        struct device *dev = desc->txd.chan->device->dev;
-        if (!(desc->txd.flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-                if (desc->txd.flags & DMA_COMPL_SRC_UNMAP_SINGLE)
-                        dma_unmap_single(dev, desc->src_addr, desc->size,
-                                         DMA_TO_DEVICE);
-                else
-                        dma_unmap_page(dev, desc->src_addr, desc->size,
-                                       DMA_TO_DEVICE);
-        }
-        if (!(desc->txd.flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-                if (desc->txd.flags & DMA_COMPL_DEST_UNMAP_SINGLE)
-                        dma_unmap_single(dev, desc->dst_addr, desc->size,
-                                         DMA_FROM_DEVICE);
-                else
-                        dma_unmap_page(dev, desc->dst_addr, desc->size,
-                                       DMA_FROM_DEVICE);
-        }
-}
 static void ep93xx_dma_tasklet(unsigned long data)
 {
        struct ep93xx_dma_chan *edmac = (struct ep93xx_dma_chan *)data;
@@ -787,13 +765,7 @@ static void ep93xx_dma_tasklet(unsigned long data)
        /* Now we can release all the chained descriptors */
        list_for_each_entry_safe(desc, d, &list, node) {
-                /*
+                dma_descriptor_unmap(&desc->txd);
-                 * For the memcpy channels the API requires us to unmap the
-                 * buffers unless requested otherwise.
-                 */
-                if (!edmac->chan.private)
-                        ep93xx_dma_unmap_buffers(desc);
                ep93xx_dma_desc_put(edmac, desc);
        }
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index 61517dd0d0b7..7086a16a55f2 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -870,22 +870,7 @@ static void fsldma_cleanup_descriptor(struct fsldma_chan *chan,
        /* Run any dependencies */
        dma_run_dependencies(txd);
-        /* Unmap the dst buffer, if requested */
+        dma_descriptor_unmap(txd);
-        if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-                if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
-                        dma_unmap_single(dev, dst, len, DMA_FROM_DEVICE);
-                else
-                        dma_unmap_page(dev, dst, len, DMA_FROM_DEVICE);
-        }
-        /* Unmap the src buffer, if requested */
-        if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-                if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
-                        dma_unmap_single(dev, src, len, DMA_TO_DEVICE);
-                else
-                        dma_unmap_page(dev, src, len, DMA_TO_DEVICE);
-        }
 #ifdef FSL_DMA_LD_DEBUG
        chan_dbg(chan, "LD %p free\n", desc);
 #endif
@@ -1255,7 +1240,9 @@ static int fsl_dma_chan_probe(struct fsldma_device *fdev,
        WARN_ON(fdev->feature != chan->feature);
        chan->dev = fdev->dev;
-        chan->id = ((res.start - 0x100) & 0xfff) >> 7;
+        chan->id = (res.start & 0xfff) < 0x300 ?
+                   ((res.start - 0x100) & 0xfff) >> 7 :
+                   ((res.start - 0x200) & 0xfff) >> 7;
        if (chan->id >= FSL_DMA_MAX_CHANS_PER_DEVICE) {
                dev_err(fdev->dev, "too many channels for device\n");
                err = -EINVAL;
@@ -1428,6 +1415,7 @@ static int fsldma_of_remove(struct platform_device *op)
 }
 static const struct of_device_id fsldma_of_ids[] = {
+        { .compatible = "fsl,elo3-dma", },
        { .compatible = "fsl,eloplus-dma", },
        { .compatible = "fsl,elo-dma", },
        {}
@@ -1449,7 +1437,7 @@ static struct platform_driver fsldma_of_driver = {
 static __init int fsldma_init(void)
 {
-        pr_info("Freescale Elo / Elo Plus DMA driver\n");
+        pr_info("Freescale Elo series DMA driver\n");
        return platform_driver_register(&fsldma_of_driver);
 }
@@ -1461,5 +1449,5 @@ static void __exit fsldma_exit(void)
 subsys_initcall(fsldma_init);
 module_exit(fsldma_exit);
-MODULE_DESCRIPTION("Freescale Elo / Elo Plus DMA driver");
+MODULE_DESCRIPTION("Freescale Elo series DMA driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/dma/fsldma.h b/drivers/dma/fsldma.h
index f5c38791fc74..1ffc24484d23 100644
--- a/drivers/dma/fsldma.h
+++ b/drivers/dma/fsldma.h
@@ -112,7 +112,7 @@ struct fsldma_chan_regs {
 };
 struct fsldma_chan;
-#define FSL_DMA_MAX_CHANS_PER_DEVICE 4
+#define FSL_DMA_MAX_CHANS_PER_DEVICE 8
 struct fsldma_device {
        void __iomem *regs;     /* DGSR register base */
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index 55852c026791..6f9ac2022abd 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -572,9 +572,11 @@ static int imxdma_xfer_desc(struct imxdma_desc *d)
                imx_dmav1_writel(imxdma, d->len, DMA_CNTR(imxdmac->channel));
-                dev_dbg(imxdma->dev, "%s channel: %d dest=0x%08x src=0x%08x "
+                dev_dbg(imxdma->dev,
-                        "dma_length=%d\n", __func__, imxdmac->channel,
+                        "%s channel: %d dest=0x%08llx src=0x%08llx dma_length=%zu\n",
-                        d->dest, d->src, d->len);
+                        __func__, imxdmac->channel,
+                        (unsigned long long)d->dest,
+                        (unsigned long long)d->src, d->len);
                break;
        /* Cyclic transfer is the same as slave_sg with special sg configuration. */
@@ -586,20 +588,22 @@ static int imxdma_xfer_desc(struct imxdma_desc *d)
                        imx_dmav1_writel(imxdma, imxdmac->ccr_from_device,
                                         DMA_CCR(imxdmac->channel));
-                        dev_dbg(imxdma->dev, "%s channel: %d sg=%p sgcount=%d "
+                        dev_dbg(imxdma->dev,
-                                "total length=%d dev_addr=0x%08x (dev2mem)\n",
+                                "%s channel: %d sg=%p sgcount=%d total length=%zu dev_addr=0x%08llx (dev2mem)\n",
-                                __func__, imxdmac->channel, d->sg, d->sgcount,
+                                __func__, imxdmac->channel,
-                                d->len, imxdmac->per_address);
+                                d->sg, d->sgcount, d->len,
+                                (unsigned long long)imxdmac->per_address);
                } else if (d->direction == DMA_MEM_TO_DEV) {
                        imx_dmav1_writel(imxdma, imxdmac->per_address,
                                         DMA_DAR(imxdmac->channel));
                        imx_dmav1_writel(imxdma, imxdmac->ccr_to_device,
                                         DMA_CCR(imxdmac->channel));
-                        dev_dbg(imxdma->dev, "%s channel: %d sg=%p sgcount=%d "
+                        dev_dbg(imxdma->dev,
-                                "total length=%d dev_addr=0x%08x (mem2dev)\n",
+                                "%s channel: %d sg=%p sgcount=%d total length=%zu dev_addr=0x%08llx (mem2dev)\n",
-                                __func__, imxdmac->channel, d->sg, d->sgcount,
+                                __func__, imxdmac->channel,
-                                d->len, imxdmac->per_address);
+                                d->sg, d->sgcount, d->len,
+                                (unsigned long long)imxdmac->per_address);
                } else {
                        dev_err(imxdma->dev, "%s channel: %d bad dma mode\n",
                                __func__, imxdmac->channel);
@@ -771,7 +775,7 @@ static int imxdma_alloc_chan_resources(struct dma_chan *chan)
                desc->desc.tx_submit = imxdma_tx_submit;
                /* txd.flags will be overwritten in prep funcs */
                desc->desc.flags = DMA_CTRL_ACK;
-                desc->status = DMA_SUCCESS;
+                desc->status = DMA_COMPLETE;
                list_add_tail(&desc->node, &imxdmac->ld_free);
                imxdmac->descs_allocated++;
@@ -870,7 +874,7 @@ static struct dma_async_tx_descriptor *imxdma_prep_dma_cyclic(
        int i;
        unsigned int periods = buf_len / period_len;
-        dev_dbg(imxdma->dev, "%s channel: %d buf_len=%d period_len=%d\n",
+        dev_dbg(imxdma->dev, "%s channel: %d buf_len=%zu period_len=%zu\n",
                        __func__, imxdmac->channel, buf_len, period_len);
        if (list_empty(&imxdmac->ld_free) ||
@@ -926,8 +930,9 @@ static struct dma_async_tx_descriptor *imxdma_prep_dma_memcpy(
        struct imxdma_engine *imxdma = imxdmac->imxdma;
        struct imxdma_desc *desc;
-        dev_dbg(imxdma->dev, "%s channel: %d src=0x%x dst=0x%x len=%d\n",
+        dev_dbg(imxdma->dev, "%s channel: %d src=0x%llx dst=0x%llx len=%zu\n",
-                        __func__, imxdmac->channel, src, dest, len);
+                __func__, imxdmac->channel, (unsigned long long)src,
+                (unsigned long long)dest, len);
        if (list_empty(&imxdmac->ld_free) ||
            imxdma_chan_is_doing_cyclic(imxdmac))
@@ -956,9 +961,10 @@ static struct dma_async_tx_descriptor *imxdma_prep_dma_interleaved(
        struct imxdma_engine *imxdma = imxdmac->imxdma;
        struct imxdma_desc *desc;
-        dev_dbg(imxdma->dev, "%s channel: %d src_start=0x%x dst_start=0x%x\n"
+        dev_dbg(imxdma->dev, "%s channel: %d src_start=0x%llx dst_start=0x%llx\n"
-                "   src_sgl=%s dst_sgl=%s numf=%d frame_size=%d\n", __func__,
+                "   src_sgl=%s dst_sgl=%s numf=%zu frame_size=%zu\n", __func__,
-                imxdmac->channel, xt->src_start, xt->dst_start,
+                imxdmac->channel, (unsigned long long)xt->src_start,
+                (unsigned long long) xt->dst_start,
                xt->src_sgl ? "true" : "false", xt->dst_sgl ? "true" : "false",
                xt->numf, xt->frame_size);
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index c1fd504cae28..c75679d42028 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -638,7 +638,7 @@ static void mxc_sdma_handle_channel_normal(struct sdma_channel *sdmac)
        if (error)
                sdmac->status = DMA_ERROR;
        else
-                sdmac->status = DMA_SUCCESS;
+                sdmac->status = DMA_COMPLETE;
        dma_cookie_complete(&sdmac->desc);
        if (sdmac->desc.callback)
@@ -1089,8 +1089,8 @@ static struct dma_async_tx_descriptor *sdma_prep_slave_sg(
                        param &= ~BD_CONT;
                }
-                dev_dbg(sdma->dev, "entry %d: count: %d dma: 0x%08x %s%s\n",
+                dev_dbg(sdma->dev, "entry %d: count: %d dma: %#llx %s%s\n",
-                                i, count, sg->dma_address,
+                                i, count, (u64)sg->dma_address,
                                param & BD_WRAP ? "wrap" : "",
                                param & BD_INTR ? " intr" : "");
@@ -1163,8 +1163,8 @@ static struct dma_async_tx_descriptor *sdma_prep_dma_cyclic(
                if (i + 1 == num_periods)
                        param |= BD_WRAP;
-                dev_dbg(sdma->dev, "entry %d: count: %d dma: 0x%08x %s%s\n",
+                dev_dbg(sdma->dev, "entry %d: count: %d dma: %#llx %s%s\n",
-                                i, period_len, dma_addr,
+                                i, period_len, (u64)dma_addr,
                                param & BD_WRAP ? "wrap" : "",
                                param & BD_INTR ? " intr" : "");
diff --git a/drivers/dma/intel_mid_dma.c b/drivers/dma/intel_mid_dma.c
index a975ebebea8a..1aab8130efa1 100644
--- a/drivers/dma/intel_mid_dma.c
+++ b/drivers/dma/intel_mid_dma.c
@@ -309,7 +309,7 @@ static void midc_descriptor_complete(struct intel_mid_dma_chan *midc,
                callback_txd(param_txd);
        }
        if (midc->raw_tfr) {
-                desc->status = DMA_SUCCESS;
+                desc->status = DMA_COMPLETE;
                if (desc->lli != NULL) {
                        pci_pool_free(desc->lli_pool, desc->lli,
                                                desc->lli_phys);
@@ -481,7 +481,7 @@ static enum dma_status intel_mid_dma_tx_status(struct dma_chan *chan,
        enum dma_status ret;
        ret = dma_cookie_status(chan, cookie, txstate);
-        if (ret != DMA_SUCCESS) {
+        if (ret != DMA_COMPLETE) {
                spin_lock_bh(&midc->lock);
                midc_scan_descriptors(to_middma_device(chan->device), midc);
                spin_unlock_bh(&midc->lock);
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 5ff6fc1819dc..1a49c777607c 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -531,21 +531,6 @@ static void ioat1_cleanup_event(unsigned long data)
        writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
 }
-void ioat_dma_unmap(struct ioat_chan_common *chan, enum dma_ctrl_flags flags,
-                    size_t len, struct ioat_dma_descriptor *hw)
-{
-        struct pci_dev *pdev = chan->device->pdev;
-        size_t offset = len - hw->size;
-        if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP))
-                ioat_unmap(pdev, hw->dst_addr - offset, len,
-                           PCI_DMA_FROMDEVICE, flags, 1);
-        if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP))
-                ioat_unmap(pdev, hw->src_addr - offset, len,
-                           PCI_DMA_TODEVICE, flags, 0);
-}
 dma_addr_t ioat_get_current_completion(struct ioat_chan_common *chan)
 {
        dma_addr_t phys_complete;
@@ -602,7 +587,7 @@ static void __cleanup(struct ioat_dma_chan *ioat, dma_addr_t phys_complete)
                dump_desc_dbg(ioat, desc);
                if (tx->cookie) {
                        dma_cookie_complete(tx);
-                        ioat_dma_unmap(chan, tx->flags, desc->len, desc->hw);
+                        dma_descriptor_unmap(tx);
                        ioat->active -= desc->hw->tx_cnt;
                        if (tx->callback) {
                                tx->callback(tx->callback_param);
@@ -733,7 +718,7 @@ ioat_dma_tx_status(struct dma_chan *c, dma_cookie_t cookie,
        enum dma_status ret;
        ret = dma_cookie_status(c, cookie, txstate);
-        if (ret == DMA_SUCCESS)
+        if (ret == DMA_COMPLETE)
                return ret;
        device->cleanup_fn((unsigned long) c);
@@ -833,8 +818,7 @@ int ioat_dma_self_test(struct ioatdma_device *device)
        dma_src = dma_map_single(dev, src, IOAT_TEST_SIZE, DMA_TO_DEVICE);
        dma_dest = dma_map_single(dev, dest, IOAT_TEST_SIZE, DMA_FROM_DEVICE);
-        flags = DMA_COMPL_SKIP_SRC_UNMAP | DMA_COMPL_SKIP_DEST_UNMAP |
+        flags = DMA_PREP_INTERRUPT;
-                DMA_PREP_INTERRUPT;
        tx = device->common.device_prep_dma_memcpy(dma_chan, dma_dest, dma_src,
                                                   IOAT_TEST_SIZE, flags);
        if (!tx) {
@@ -859,7 +843,7 @@ int ioat_dma_self_test(struct ioatdma_device *device)
        if (tmo == 0 ||
            dma->device_tx_status(dma_chan, cookie, NULL)
-                                        != DMA_SUCCESS) {
+                                        != DMA_COMPLETE) {
                dev_err(dev, "Self-test copy timed out, disabling\n");
                err = -ENODEV;
                goto unmap_dma;
@@ -885,8 +869,7 @@ static char ioat_interrupt_style[32] = "msix";
 module_param_string(ioat_interrupt_style, ioat_interrupt_style,
                    sizeof(ioat_interrupt_style), 0644);
 MODULE_PARM_DESC(ioat_interrupt_style,
-                 "set ioat interrupt style: msix (default), "
+                 "set ioat interrupt style: msix (default), msi, intx");
-                 "msix-single-vector, msi, intx)");
 /**
 * ioat_dma_setup_interrupts - setup interrupt handler
@@ -904,8 +887,6 @@ int ioat_dma_setup_interrupts(struct ioatdma_device *device)
        if (!strcmp(ioat_interrupt_style, "msix"))
                goto msix;
-        if (!strcmp(ioat_interrupt_style, "msix-single-vector"))
-                goto msix_single_vector;
        if (!strcmp(ioat_interrupt_style, "msi"))
                goto msi;
        if (!strcmp(ioat_interrupt_style, "intx"))
@@ -920,10 +901,8 @@ msix:
                device->msix_entries[i].entry = i;
        err = pci_enable_msix(pdev, device->msix_entries, msixcnt);
-        if (err < 0)
+        if (err)
                goto msi;
-        if (err > 0)
-                goto msix_single_vector;
        for (i = 0; i < msixcnt; i++) {
                msix = &device->msix_entries[i];
@@ -937,29 +916,13 @@ msix:
                                chan = ioat_chan_by_index(device, j);
                                devm_free_irq(dev, msix->vector, chan);
                        }
-                        goto msix_single_vector;
+                        goto msi;
                }
        }
        intrctrl |= IOAT_INTRCTRL_MSIX_VECTOR_CONTROL;
        device->irq_mode = IOAT_MSIX;
        goto done;
-msix_single_vector:
-        msix = &device->msix_entries[0];
-        msix->entry = 0;
-        err = pci_enable_msix(pdev, device->msix_entries, 1);
-        if (err)
-                goto msi;
-        err = devm_request_irq(dev, msix->vector, ioat_dma_do_interrupt, 0,
-                               "ioat-msix", device);
-        if (err) {
-                pci_disable_msix(pdev);
-                goto msi;
-        }
-        device->irq_mode = IOAT_MSIX_SINGLE;
-        goto done;
 msi:
        err = pci_enable_msi(pdev);
        if (err)
@@ -971,7 +934,7 @@ msi:
                pci_disable_msi(pdev);
                goto intx;
        }
-        device->irq_mode = IOAT_MSIX;
+        device->irq_mode = IOAT_MSI;
        goto done;
 intx:
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index 54fb7b9ff9aa..11fb877ddca9 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -52,7 +52,6 @@
 enum ioat_irq_mode {
        IOAT_NOIRQ = 0,
        IOAT_MSIX,
-        IOAT_MSIX_SINGLE,
        IOAT_MSI,
        IOAT_INTX
 };
@@ -83,7 +82,6 @@ struct ioatdma_device {
        struct pci_pool *completion_pool;
 #define MAX_SED_POOLS   5
        struct dma_pool *sed_hw_pool[MAX_SED_POOLS];
-        struct kmem_cache *sed_pool;
        struct dma_device common;
        u8 version;
        struct msix_entry msix_entries[4];
@@ -342,16 +340,6 @@ static inline bool is_ioat_bug(unsigned long err)
        return !!err;
 }
-static inline void ioat_unmap(struct pci_dev *pdev, dma_addr_t addr, size_t len,
-                              int direction, enum dma_ctrl_flags flags, bool dst)
-{
-        if ((dst && (flags & DMA_COMPL_DEST_UNMAP_SINGLE)) ||
-            (!dst && (flags & DMA_COMPL_SRC_UNMAP_SINGLE)))
-                pci_unmap_single(pdev, addr, len, direction);
-        else
-                pci_unmap_page(pdev, addr, len, direction);
-}
 int ioat_probe(struct ioatdma_device *device);
 int ioat_register(struct ioatdma_device *device);
 int ioat1_dma_probe(struct ioatdma_device *dev, int dca);
@@ -363,8 +351,6 @@ void ioat_init_channel(struct ioatdma_device *device,
                       struct ioat_chan_common *chan, int idx);
 enum dma_status ioat_dma_tx_status(struct dma_chan *c, dma_cookie_t cookie,
                                   struct dma_tx_state *txstate);
-void ioat_dma_unmap(struct ioat_chan_common *chan, enum dma_ctrl_flags flags,
-                    size_t len, struct ioat_dma_descriptor *hw);
 bool ioat_cleanup_preamble(struct ioat_chan_common *chan,
                           dma_addr_t *phys_complete);
 void ioat_kobject_add(struct ioatdma_device *device, struct kobj_type *type);
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
index b925e1b1d139..5d3affe7e976 100644
--- a/drivers/dma/ioat/dma_v2.c
+++ b/drivers/dma/ioat/dma_v2.c
@@ -148,7 +148,7 @@ static void __cleanup(struct ioat2_dma_chan *ioat, dma_addr_t phys_complete)
                tx = &desc->txd;
                dump_desc_dbg(ioat, desc);
                if (tx->cookie) {
-                        ioat_dma_unmap(chan, tx->flags, desc->len, desc->hw);
+                        dma_descriptor_unmap(tx);
                        dma_cookie_complete(tx);
                        if (tx->callback) {
                                tx->callback(tx->callback_param);
diff --git a/drivers/dma/ioat/dma_v2.h b/drivers/dma/ioat/dma_v2.h
index 212d584fe427..470292767e68 100644
--- a/drivers/dma/ioat/dma_v2.h
+++ b/drivers/dma/ioat/dma_v2.h
@@ -157,7 +157,6 @@ static inline void ioat2_set_chainaddr(struct ioat2_dma_chan *ioat, u64 addr)
 int ioat2_dma_probe(struct ioatdma_device *dev, int dca);
 int ioat3_dma_probe(struct ioatdma_device *dev, int dca);
-void ioat3_dma_remove(struct ioatdma_device *dev);
 struct dca_provider *ioat2_dca_init(struct pci_dev *pdev, void __iomem *iobase);
 struct dca_provider *ioat3_dca_init(struct pci_dev *pdev, void __iomem *iobase);
 int ioat2_check_space_lock(struct ioat2_dma_chan *ioat, int num_descs);
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
index d8ececaf1b57..820817e97e62 100644
--- a/drivers/dma/ioat/dma_v3.c
+++ b/drivers/dma/ioat/dma_v3.c
@@ -67,6 +67,8 @@
 #include "dma.h"
 #include "dma_v2.h"
+extern struct kmem_cache *ioat3_sed_cache;
 /* ioat hardware assumes at least two sources for raid operations */
 #define src_cnt_to_sw(x) ((x) + 2)
 #define src_cnt_to_hw(x) ((x) - 2)
@@ -87,22 +89,8 @@ static const u8 pq_idx_to_field[] = { 1, 4, 5, 0, 1, 2, 4, 5 };
 static const u8 pq16_idx_to_field[] = { 1, 4, 1, 2, 3, 4, 5, 6, 7,
                                        0, 1, 2, 3, 4, 5, 6 };
-/*
- * technically sources 1 and 2 do not require SED, but the op will have
- * at least 9 descriptors so that's irrelevant.
- */
-static const u8 pq16_idx_to_sed[] = { 0, 0, 0, 0, 0, 0, 0, 0, 0,
-                                      1, 1, 1, 1, 1, 1, 1 };
 static void ioat3_eh(struct ioat2_dma_chan *ioat);
-static dma_addr_t xor_get_src(struct ioat_raw_descriptor *descs[2], int idx)
-{
-        struct ioat_raw_descriptor *raw = descs[xor_idx_to_desc >> idx & 1];
-        return raw->field[xor_idx_to_field[idx]];
-}
 static void xor_set_src(struct ioat_raw_descriptor *descs[2],
                        dma_addr_t addr, u32 offset, int idx)
 {
@@ -135,12 +123,6 @@ static void pq_set_src(struct ioat_raw_descriptor *descs[2],
        pq->coef[idx] = coef;
 }
-static int sed_get_pq16_pool_idx(int src_cnt)
-{
-        return pq16_idx_to_sed[src_cnt];
-}
 static bool is_jf_ioat(struct pci_dev *pdev)
 {
        switch (pdev->device) {
@@ -272,7 +254,7 @@ ioat3_alloc_sed(struct ioatdma_device *device, unsigned int hw_pool)
        struct ioat_sed_ent *sed;
        gfp_t flags = __GFP_ZERO | GFP_ATOMIC;
-        sed = kmem_cache_alloc(device->sed_pool, flags);
+        sed = kmem_cache_alloc(ioat3_sed_cache, flags);
        if (!sed)
                return NULL;
@@ -280,7 +262,7 @@ ioat3_alloc_sed(struct ioatdma_device *device, unsigned int hw_pool)
        sed->hw = dma_pool_alloc(device->sed_hw_pool[hw_pool],
                                 flags, &sed->dma);
        if (!sed->hw) {
-                kmem_cache_free(device->sed_pool, sed);
+                kmem_cache_free(ioat3_sed_cache, sed);
                return NULL;
        }
@@ -293,165 +275,7 @@ static void ioat3_free_sed(struct ioatdma_device *device, struct ioat_sed_ent *s
                return;
        dma_pool_free(device->sed_hw_pool[sed->hw_pool], sed->hw, sed->dma);
-        kmem_cache_free(device->sed_pool, sed);
+        kmem_cache_free(ioat3_sed_cache, sed);
-}
-static void ioat3_dma_unmap(struct ioat2_dma_chan *ioat,
-                            struct ioat_ring_ent *desc, int idx)
-{
-        struct ioat_chan_common *chan = &ioat->base;
-        struct pci_dev *pdev = chan->device->pdev;
-        size_t len = desc->len;
-        size_t offset = len - desc->hw->size;
-        struct dma_async_tx_descriptor *tx = &desc->txd;
-        enum dma_ctrl_flags flags = tx->flags;
-        switch (desc->hw->ctl_f.op) {
-        case IOAT_OP_COPY:
-                if (!desc->hw->ctl_f.null) /* skip 'interrupt' ops */
-                        ioat_dma_unmap(chan, flags, len, desc->hw);
-                break;
-        case IOAT_OP_XOR_VAL:
-        case IOAT_OP_XOR: {
-                struct ioat_xor_descriptor *xor = desc->xor;
-                struct ioat_ring_ent *ext;
-                struct ioat_xor_ext_descriptor *xor_ex = NULL;
-                int src_cnt = src_cnt_to_sw(xor->ctl_f.src_cnt);
-                struct ioat_raw_descriptor *descs[2];
-                int i;
-                if (src_cnt > 5) {
-                        ext = ioat2_get_ring_ent(ioat, idx + 1);
-                        xor_ex = ext->xor_ex;
-                }
-                if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-                        descs[0] = (struct ioat_raw_descriptor *) xor;
-                        descs[1] = (struct ioat_raw_descriptor *) xor_ex;
-                        for (i = 0; i < src_cnt; i++) {
-                                dma_addr_t src = xor_get_src(descs, i);
-                                ioat_unmap(pdev, src - offset, len,
-                                           PCI_DMA_TODEVICE, flags, 0);
-                        }
-                        /* dest is a source in xor validate operations */
-                        if (xor->ctl_f.op == IOAT_OP_XOR_VAL) {
-                                ioat_unmap(pdev, xor->dst_addr - offset, len,
-                                           PCI_DMA_TODEVICE, flags, 1);
-                                break;
-                        }
-                }
-                if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP))
-                        ioat_unmap(pdev, xor->dst_addr - offset, len,
-                                   PCI_DMA_FROMDEVICE, flags, 1);
-                break;
-        }
-        case IOAT_OP_PQ_VAL:
-        case IOAT_OP_PQ: {
-                struct ioat_pq_descriptor *pq = desc->pq;
-                struct ioat_ring_ent *ext;
-                struct ioat_pq_ext_descriptor *pq_ex = NULL;
-                int src_cnt = src_cnt_to_sw(pq->ctl_f.src_cnt);
-                struct ioat_raw_descriptor *descs[2];
-                int i;
-                if (src_cnt > 3) {
-                        ext = ioat2_get_ring_ent(ioat, idx + 1);
-                        pq_ex = ext->pq_ex;
-                }
-                /* in the 'continue' case don't unmap the dests as sources */
-                if (dmaf_p_disabled_continue(flags))
-                        src_cnt--;
-                else if (dmaf_continue(flags))
-                        src_cnt -= 3;
-                if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-                        descs[0] = (struct ioat_raw_descriptor *) pq;
-                        descs[1] = (struct ioat_raw_descriptor *) pq_ex;
-                        for (i = 0; i < src_cnt; i++) {
-                                dma_addr_t src = pq_get_src(descs, i);
-                                ioat_unmap(pdev, src - offset, len,
-                                           PCI_DMA_TODEVICE, flags, 0);
-                        }
-                        /* the dests are sources in pq validate operations */
-                        if (pq->ctl_f.op == IOAT_OP_XOR_VAL) {
-                                if (!(flags & DMA_PREP_PQ_DISABLE_P))
-                                        ioat_unmap(pdev, pq->p_addr - offset,
-                                                   len, PCI_DMA_TODEVICE, flags, 0);
-                                if (!(flags & DMA_PREP_PQ_DISABLE_Q))
-                                        ioat_unmap(pdev, pq->q_addr - offset,
-                                                   len, PCI_DMA_TODEVICE, flags, 0);
-                                break;
-                        }
-                }
-                if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-                        if (!(flags & DMA_PREP_PQ_DISABLE_P))
-                                ioat_unmap(pdev, pq->p_addr - offset, len,
-                                           PCI_DMA_BIDIRECTIONAL, flags, 1);
-                        if (!(flags & DMA_PREP_PQ_DISABLE_Q))
-                                ioat_unmap(pdev, pq->q_addr - offset, len,
-                                           PCI_DMA_BIDIRECTIONAL, flags, 1);
-                }
-                break;
-        }
-        case IOAT_OP_PQ_16S:
-        case IOAT_OP_PQ_VAL_16S: {
-                struct ioat_pq_descriptor *pq = desc->pq;
-                int src_cnt = src16_cnt_to_sw(pq->ctl_f.src_cnt);
-                struct ioat_raw_descriptor *descs[4];
-                int i;
-                /* in the 'continue' case don't unmap the dests as sources */
-                if (dmaf_p_disabled_continue(flags))
-                        src_cnt--;
-                else if (dmaf_continue(flags))
-                        src_cnt -= 3;
-                if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-                        descs[0] = (struct ioat_raw_descriptor *)pq;
-                        descs[1] = (struct ioat_raw_descriptor *)(desc->sed->hw);
-                        descs[2] = (struct ioat_raw_descriptor *)(&desc->sed->hw->b[0]);
-                        for (i = 0; i < src_cnt; i++) {
-                                dma_addr_t src = pq16_get_src(descs, i);
-                                ioat_unmap(pdev, src - offset, len,
-                                           PCI_DMA_TODEVICE, flags, 0);
-                        }
-                        /* the dests are sources in pq validate operations */
-                        if (pq->ctl_f.op == IOAT_OP_XOR_VAL) {
-                                if (!(flags & DMA_PREP_PQ_DISABLE_P))
-                                        ioat_unmap(pdev, pq->p_addr - offset,
-                                                   len, PCI_DMA_TODEVICE,
-                                                   flags, 0);
-                                if (!(flags & DMA_PREP_PQ_DISABLE_Q))
-                                        ioat_unmap(pdev, pq->q_addr - offset,
-                                                   len, PCI_DMA_TODEVICE,
-                                                   flags, 0);
-                                break;
-                        }
-                }
-                if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-                        if (!(flags & DMA_PREP_PQ_DISABLE_P))
-                                ioat_unmap(pdev, pq->p_addr - offset, len,
-                                           PCI_DMA_BIDIRECTIONAL, flags, 1);
-                        if (!(flags & DMA_PREP_PQ_DISABLE_Q))
-                                ioat_unmap(pdev, pq->q_addr - offset, len,
-                                           PCI_DMA_BIDIRECTIONAL, flags, 1);
-                }
-                break;
-        }
-        default:
-                dev_err(&pdev->dev, "%s: unknown op type: %#x\n",
-                        __func__, desc->hw->ctl_f.op);
-        }
 }
 static bool desc_has_ext(struct ioat_ring_ent *desc)
@@ -577,7 +401,7 @@ static void __cleanup(struct ioat2_dma_chan *ioat, dma_addr_t phys_complete)
                tx = &desc->txd;
                if (tx->cookie) {
                        dma_cookie_complete(tx);
-                        ioat3_dma_unmap(ioat, desc, idx + i);
+                        dma_descriptor_unmap(tx);
                        if (tx->callback) {
                                tx->callback(tx->callback_param);
                                tx->callback = NULL;
@@ -807,7 +631,7 @@ ioat3_tx_status(struct dma_chan *c, dma_cookie_t cookie,
        enum dma_status ret;
        ret = dma_cookie_status(c, cookie, txstate);
-        if (ret == DMA_SUCCESS)
+        if (ret == DMA_COMPLETE)
                return ret;
        ioat3_cleanup(ioat);
@@ -1129,9 +953,6 @@ __ioat3_prep_pq16_lock(struct dma_chan *c, enum sum_check_flags *result,
        u8 op;
        int i, s, idx, num_descs;
-        /* this function only handles src_cnt 9 - 16 */
-        BUG_ON(src_cnt < 9);
        /* this function is only called with 9-16 sources */
        op = result ? IOAT_OP_PQ_VAL_16S : IOAT_OP_PQ_16S;
@@ -1159,8 +980,7 @@ __ioat3_prep_pq16_lock(struct dma_chan *c, enum sum_check_flags *result,
                descs[0] = (struct ioat_raw_descriptor *) pq;
-                desc->sed = ioat3_alloc_sed(device,
+                desc->sed = ioat3_alloc_sed(device, (src_cnt-2) >> 3);
-                                            sed_get_pq16_pool_idx(src_cnt));
                if (!desc->sed) {
                        dev_err(to_dev(chan),
                                "%s: no free sed entries\n", __func__);
@@ -1218,13 +1038,21 @@ __ioat3_prep_pq16_lock(struct dma_chan *c, enum sum_check_flags *result,
        return &desc->txd;
 }
+static int src_cnt_flags(unsigned int src_cnt, unsigned long flags)
+{
+        if (dmaf_p_disabled_continue(flags))
+                return src_cnt + 1;
+        else if (dmaf_continue(flags))
+                return src_cnt + 3;
+        else
+                return src_cnt;
+}
 static struct dma_async_tx_descriptor *
 ioat3_prep_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src,
              unsigned int src_cnt, const unsigned char *scf, size_t len,
              unsigned long flags)
 {
-        struct dma_device *dma = chan->device;
        /* specify valid address for disabled result */
        if (flags & DMA_PREP_PQ_DISABLE_P)
                dst[0] = dst[1];
@@ -1244,7 +1072,7 @@ ioat3_prep_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src,
                single_source_coef[0] = scf[0];
                single_source_coef[1] = 0;
-                return (src_cnt > 8) && (dma->max_pq > 8) ?
+                return src_cnt_flags(src_cnt, flags) > 8 ?
                        __ioat3_prep_pq16_lock(chan, NULL, dst, single_source,
                                               2, single_source_coef, len,
                                               flags) :
@@ -1252,7 +1080,7 @@ ioat3_prep_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src,
                                             single_source_coef, len, flags);
        } else {
-                return (src_cnt > 8) && (dma->max_pq > 8) ?
+                return src_cnt_flags(src_cnt, flags) > 8 ?
                        __ioat3_prep_pq16_lock(chan, NULL, dst, src, src_cnt,
                                               scf, len, flags) :
                        __ioat3_prep_pq_lock(chan, NULL, dst, src, src_cnt,
@@ -1265,8 +1093,6 @@ ioat3_prep_pq_val(struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src,
                  unsigned int src_cnt, const unsigned char *scf, size_t len,
                  enum sum_check_flags *pqres, unsigned long flags)
 {
-        struct dma_device *dma = chan->device;
        /* specify valid address for disabled result */
        if (flags & DMA_PREP_PQ_DISABLE_P)
                pq[0] = pq[1];
@@ -1278,7 +1104,7 @@ ioat3_prep_pq_val(struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src,
         */
        *pqres = 0;
-        return (src_cnt > 8) && (dma->max_pq > 8) ?
+        return src_cnt_flags(src_cnt, flags) > 8 ?
                __ioat3_prep_pq16_lock(chan, pqres, pq, src, src_cnt, scf, len,
                                       flags) :
                __ioat3_prep_pq_lock(chan, pqres, pq, src, src_cnt, scf, len,
@@ -1289,7 +1115,6 @@ static struct dma_async_tx_descriptor *
 ioat3_prep_pqxor(struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src,
                 unsigned int src_cnt, size_t len, unsigned long flags)
 {
-        struct dma_device *dma = chan->device;
        unsigned char scf[src_cnt];
        dma_addr_t pq[2];
@@ -1298,7 +1123,7 @@ ioat3_prep_pqxor(struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src,
        flags |= DMA_PREP_PQ_DISABLE_Q;
        pq[1] = dst; /* specify valid address for disabled result */
-        return (src_cnt > 8) && (dma->max_pq > 8) ?
+        return src_cnt_flags(src_cnt, flags) > 8 ?
                __ioat3_prep_pq16_lock(chan, NULL, pq, src, src_cnt, scf, len,
                                       flags) :
                __ioat3_prep_pq_lock(chan, NULL, pq, src, src_cnt, scf, len,
@@ -1310,7 +1135,6 @@ ioat3_prep_pqxor_val(struct dma_chan *chan, dma_addr_t *src,
                     unsigned int src_cnt, size_t len,
                     enum sum_check_flags *result, unsigned long flags)
 {
-        struct dma_device *dma = chan->device;
        unsigned char scf[src_cnt];
        dma_addr_t pq[2];
@@ -1324,8 +1148,7 @@ ioat3_prep_pqxor_val(struct dma_chan *chan, dma_addr_t *src,
        flags |= DMA_PREP_PQ_DISABLE_Q;
        pq[1] = pq[0]; /* specify valid address for disabled result */
+        return src_cnt_flags(src_cnt, flags) > 8 ?
-        return (src_cnt > 8) && (dma->max_pq > 8) ?
                __ioat3_prep_pq16_lock(chan, result, pq, &src[1], src_cnt - 1,
                                       scf, len, flags) :
                __ioat3_prep_pq_lock(chan, result, pq, &src[1], src_cnt - 1,
@@ -1444,9 +1267,7 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
                                           DMA_TO_DEVICE);
        tx = dma->device_prep_dma_xor(dma_chan, dest_dma, dma_srcs,
                                      IOAT_NUM_SRC_TEST, PAGE_SIZE,
-                                      DMA_PREP_INTERRUPT |
+                                      DMA_PREP_INTERRUPT);
-                                      DMA_COMPL_SKIP_SRC_UNMAP |
-                                      DMA_COMPL_SKIP_DEST_UNMAP);
        if (!tx) {
                dev_err(dev, "Self-test xor prep failed\n");
@@ -1468,7 +1289,7 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
        tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
-        if (dma->device_tx_status(dma_chan, cookie, NULL) != DMA_SUCCESS) {
+        if (dma->device_tx_status(dma_chan, cookie, NULL) != DMA_COMPLETE) {
                dev_err(dev, "Self-test xor timed out\n");
                err = -ENODEV;
                goto dma_unmap;
@@ -1507,9 +1328,7 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
                                           DMA_TO_DEVICE);
        tx = dma->device_prep_dma_xor_val(dma_chan, dma_srcs,
                                          IOAT_NUM_SRC_TEST + 1, PAGE_SIZE,
-                                          &xor_val_result, DMA_PREP_INTERRUPT |
+                                          &xor_val_result, DMA_PREP_INTERRUPT);
-                                          DMA_COMPL_SKIP_SRC_UNMAP |
-                                          DMA_COMPL_SKIP_DEST_UNMAP);
        if (!tx) {
                dev_err(dev, "Self-test zero prep failed\n");
                err = -ENODEV;
@@ -1530,7 +1349,7 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
        tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
-        if (dma->device_tx_status(dma_chan, cookie, NULL) != DMA_SUCCESS) {
+        if (dma->device_tx_status(dma_chan, cookie, NULL) != DMA_COMPLETE) {
                dev_err(dev, "Self-test validate timed out\n");
                err = -ENODEV;
                goto dma_unmap;
@@ -1545,6 +1364,8 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
                goto free_resources;
        }
+        memset(page_address(dest), 0, PAGE_SIZE);
        /* test for non-zero parity sum */
        op = IOAT_OP_XOR_VAL;
@@ -1554,9 +1375,7 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
                                           DMA_TO_DEVICE);
        tx = dma->device_prep_dma_xor_val(dma_chan, dma_srcs,
                                          IOAT_NUM_SRC_TEST + 1, PAGE_SIZE,
-                                          &xor_val_result, DMA_PREP_INTERRUPT |
+                                          &xor_val_result, DMA_PREP_INTERRUPT);
-                                          DMA_COMPL_SKIP_SRC_UNMAP |
-                                          DMA_COMPL_SKIP_DEST_UNMAP);
        if (!tx) {
                dev_err(dev, "Self-test 2nd zero prep failed\n");
                err = -ENODEV;
@@ -1577,7 +1396,7 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device)
        tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
-        if (dma->device_tx_status(dma_chan, cookie, NULL) != DMA_SUCCESS) {
+        if (dma->device_tx_status(dma_chan, cookie, NULL) != DMA_COMPLETE) {
                dev_err(dev, "Self-test 2nd validate timed out\n");
                err = -ENODEV;
                goto dma_unmap;
@@ -1630,52 +1449,36 @@ static int ioat3_dma_self_test(struct ioatdma_device *device)
 static int ioat3_irq_reinit(struct ioatdma_device *device)
 {
-        int msixcnt = device->common.chancnt;
        struct pci_dev *pdev = device->pdev;
-        int i;
+        int irq = pdev->irq, i;
-        struct msix_entry *msix;
-        struct ioat_chan_common *chan;
+        if (!is_bwd_ioat(pdev))
-        int err = 0;
+                return 0;
        switch (device->irq_mode) {
        case IOAT_MSIX:
+                for (i = 0; i < device->common.chancnt; i++) {
+                        struct msix_entry *msix = &device->msix_entries[i];
+                        struct ioat_chan_common *chan;
-                for (i = 0; i < msixcnt; i++) {
-                        msix = &device->msix_entries[i];
                        chan = ioat_chan_by_index(device, i);
                        devm_free_irq(&pdev->dev, msix->vector, chan);
                }
                pci_disable_msix(pdev);
                break;
-        case IOAT_MSIX_SINGLE:
-                msix = &device->msix_entries[0];
-                chan = ioat_chan_by_index(device, 0);
-                devm_free_irq(&pdev->dev, msix->vector, chan);
-                pci_disable_msix(pdev);
-                break;
        case IOAT_MSI:
-                chan = ioat_chan_by_index(device, 0);
-                devm_free_irq(&pdev->dev, pdev->irq, chan);
                pci_disable_msi(pdev);
-                break;
+                /* fall through */
        case IOAT_INTX:
-                chan = ioat_chan_by_index(device, 0);
+                devm_free_irq(&pdev->dev, irq, device);
-                devm_free_irq(&pdev->dev, pdev->irq, chan);
                break;
        default:
                return 0;
        }
        device->irq_mode = IOAT_NOIRQ;
-        err = ioat_dma_setup_interrupts(device);
+        return ioat_dma_setup_interrupts(device);
-        return err;
 }
 static int ioat3_reset_hw(struct ioat_chan_common *chan)
@@ -1718,14 +1521,12 @@ static int ioat3_reset_hw(struct ioat_chan_common *chan)
        }
        err = ioat2_reset_sync(chan, msecs_to_jiffies(200));
-        if (err) {
+        if (!err)
-                dev_err(&pdev->dev, "Failed to reset!\n");
-                return err;
-        }
-        if (device->irq_mode != IOAT_NOIRQ && is_bwd_ioat(pdev))
                err = ioat3_irq_reinit(device);
+        if (err)
+                dev_err(&pdev->dev, "Failed to reset: %d\n", err);
        return err;
 }
@@ -1835,21 +1636,15 @@ int ioat3_dma_probe(struct ioatdma_device *device, int dca)
                char pool_name[14];
                int i;
-                /* allocate sw descriptor pool for SED */
-                device->sed_pool = kmem_cache_create("ioat_sed",
-                                sizeof(struct ioat_sed_ent), 0, 0, NULL);
-                if (!device->sed_pool)
-                        return -ENOMEM;
                for (i = 0; i < MAX_SED_POOLS; i++) {
                        snprintf(pool_name, 14, "ioat_hw%d_sed", i);
                        /* allocate SED DMA pool */
-                        device->sed_hw_pool[i] = dma_pool_create(pool_name,
+                        device->sed_hw_pool[i] = dmam_pool_create(pool_name,
                                        &pdev->dev,
                                        SED_SIZE * (i + 1), 64, 0);
                        if (!device->sed_hw_pool[i])
-                                goto sed_pool_cleanup;
+                                return -ENOMEM;
                }
        }
@@ -1875,28 +1670,4 @@ int ioat3_dma_probe(struct ioatdma_device *device, int dca)
                device->dca = ioat3_dca_init(pdev, device->reg_base);
        return 0;
-sed_pool_cleanup:
-        if (device->sed_pool) {
-                int i;
-                kmem_cache_destroy(device->sed_pool);
-                for (i = 0; i < MAX_SED_POOLS; i++)
-                        if (device->sed_hw_pool[i])
-                                dma_pool_destroy(device->sed_hw_pool[i]);
-        }
-        return -ENOMEM;
-}
-void ioat3_dma_remove(struct ioatdma_device *device)
-{
-        if (device->sed_pool) {
-                int i;
-                kmem_cache_destroy(device->sed_pool);
-                for (i = 0; i < MAX_SED_POOLS; i++)
-                        if (device->sed_hw_pool[i])
-                                dma_pool_destroy(device->sed_hw_pool[i]);
-        }
 }
diff --git a/drivers/dma/ioat/pci.c b/drivers/dma/ioat/pci.c
index 2c8d560e6334..1d051cd045db 100644
--- a/drivers/dma/ioat/pci.c
+++ b/drivers/dma/ioat/pci.c
@@ -123,6 +123,7 @@ module_param(ioat_dca_enabled, int, 0644);
 MODULE_PARM_DESC(ioat_dca_enabled, "control support of dca service (default: 1)");
 struct kmem_cache *ioat2_cache;
+struct kmem_cache *ioat3_sed_cache;
 #define DRV_NAME "ioatdma"
@@ -207,9 +208,6 @@ static void ioat_remove(struct pci_dev *pdev)
        if (!device)
                return;
-        if (device->version >= IOAT_VER_3_0)
-                ioat3_dma_remove(device);
        dev_err(&pdev->dev, "Removing dma and dca services\n");
        if (device->dca) {
                unregister_dca_provider(device->dca, &pdev->dev);
@@ -221,7 +219,7 @@ static void ioat_remove(struct pci_dev *pdev)
 static int __init ioat_init_module(void)
 {
-        int err;
+        int err = -ENOMEM;
        pr_info("%s: Intel(R) QuickData Technology Driver %s\n",
                DRV_NAME, IOAT_DMA_VERSION);
@@ -231,9 +229,21 @@ static int __init ioat_init_module(void)
        if (!ioat2_cache)
                return -ENOMEM;
+        ioat3_sed_cache = KMEM_CACHE(ioat_sed_ent, 0);
+        if (!ioat3_sed_cache)
+                goto err_ioat2_cache;
        err = pci_register_driver(&ioat_pci_driver);
        if (err)
-                kmem_cache_destroy(ioat2_cache);
+                goto err_ioat3_cache;
+        return 0;
+ err_ioat3_cache:
+        kmem_cache_destroy(ioat3_sed_cache);
+ err_ioat2_cache:
+        kmem_cache_destroy(ioat2_cache);
        return err;
 }
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index dd8b44a56e5d..c56137bc3868 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -61,80 +61,6 @@ static void iop_adma_free_slots(struct iop_adma_desc_slot *slot)
        }
 }
-static void
-iop_desc_unmap(struct iop_adma_chan *iop_chan, struct iop_adma_desc_slot *desc)
-{
-        struct dma_async_tx_descriptor *tx = &desc->async_tx;
-        struct iop_adma_desc_slot *unmap = desc->group_head;
-        struct device *dev = &iop_chan->device->pdev->dev;
-        u32 len = unmap->unmap_len;
-        enum dma_ctrl_flags flags = tx->flags;
-        u32 src_cnt;
-        dma_addr_t addr;
-        dma_addr_t dest;
-        src_cnt = unmap->unmap_src_cnt;
-        dest = iop_desc_get_dest_addr(unmap, iop_chan);
-        if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-                enum dma_data_direction dir;
-                if (src_cnt > 1) /* is xor? */
-                        dir = DMA_BIDIRECTIONAL;
-                else
-                        dir = DMA_FROM_DEVICE;
-                dma_unmap_page(dev, dest, len, dir);
-        }
-        if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-                while (src_cnt--) {
-                        addr = iop_desc_get_src_addr(unmap, iop_chan, src_cnt);
-                        if (addr == dest)
-                                continue;
-                        dma_unmap_page(dev, addr, len, DMA_TO_DEVICE);
-                }
-        }
-        desc->group_head = NULL;
-}
-static void
-iop_desc_unmap_pq(struct iop_adma_chan *iop_chan, struct iop_adma_desc_slot *desc)
-{
-        struct dma_async_tx_descriptor *tx = &desc->async_tx;
-        struct iop_adma_desc_slot *unmap = desc->group_head;
-        struct device *dev = &iop_chan->device->pdev->dev;
-        u32 len = unmap->unmap_len;
-        enum dma_ctrl_flags flags = tx->flags;
-        u32 src_cnt = unmap->unmap_src_cnt;
-        dma_addr_t pdest = iop_desc_get_dest_addr(unmap, iop_chan);
-        dma_addr_t qdest = iop_desc_get_qdest_addr(unmap, iop_chan);
-        int i;
-        if (tx->flags & DMA_PREP_CONTINUE)
-                src_cnt -= 3;
-        if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP) && !desc->pq_check_result) {
-                dma_unmap_page(dev, pdest, len, DMA_BIDIRECTIONAL);
-                dma_unmap_page(dev, qdest, len, DMA_BIDIRECTIONAL);
-        }
-        if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-                dma_addr_t addr;
-                for (i = 0; i < src_cnt; i++) {
-                        addr = iop_desc_get_src_addr(unmap, iop_chan, i);
-                        dma_unmap_page(dev, addr, len, DMA_TO_DEVICE);
-                }
-                if (desc->pq_check_result) {
-                        dma_unmap_page(dev, pdest, len, DMA_TO_DEVICE);
-                        dma_unmap_page(dev, qdest, len, DMA_TO_DEVICE);
-                }
-        }
-        desc->group_head = NULL;
-}
 static dma_cookie_t
 iop_adma_run_tx_complete_actions(struct iop_adma_desc_slot *desc,
        struct iop_adma_chan *iop_chan, dma_cookie_t cookie)
@@ -152,15 +78,9 @@ iop_adma_run_tx_complete_actions(struct iop_adma_desc_slot *desc,
                if (tx->callback)
                        tx->callback(tx->callback_param);
-                /* unmap dma addresses
+                dma_descriptor_unmap(tx);
-                 * (unmap_single vs unmap_page?)
+                if (desc->group_head)
-                 */
+                        desc->group_head = NULL;
-                if (desc->group_head && desc->unmap_len) {
-                        if (iop_desc_is_pq(desc))
-                                iop_desc_unmap_pq(iop_chan, desc);
-                        else
-                                iop_desc_unmap(iop_chan, desc);
-                }
        }
        /* run dependent operations */
@@ -591,7 +511,6 @@ iop_adma_prep_dma_interrupt(struct dma_chan *chan, unsigned long flags)
        if (sw_desc) {
                grp_start = sw_desc->group_head;
                iop_desc_init_interrupt(grp_start, iop_chan);
-                grp_start->unmap_len = 0;
                sw_desc->async_tx.flags = flags;
        }
        spin_unlock_bh(&iop_chan->lock);
@@ -623,8 +542,6 @@ iop_adma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dma_dest,
                iop_desc_set_byte_count(grp_start, iop_chan, len);
                iop_desc_set_dest_addr(grp_start, iop_chan, dma_dest);
                iop_desc_set_memcpy_src_addr(grp_start, dma_src);
-                sw_desc->unmap_src_cnt = 1;
-                sw_desc->unmap_len = len;
                sw_desc->async_tx.flags = flags;
        }
        spin_unlock_bh(&iop_chan->lock);
@@ -657,8 +574,6 @@ iop_adma_prep_dma_xor(struct dma_chan *chan, dma_addr_t dma_dest,
                iop_desc_init_xor(grp_start, src_cnt, flags);
                iop_desc_set_byte_count(grp_start, iop_chan, len);
                iop_desc_set_dest_addr(grp_start, iop_chan, dma_dest);
-                sw_desc->unmap_src_cnt = src_cnt;
-                sw_desc->unmap_len = len;
                sw_desc->async_tx.flags = flags;
                while (src_cnt--)
                        iop_desc_set_xor_src_addr(grp_start, src_cnt,
@@ -694,8 +609,6 @@ iop_adma_prep_dma_xor_val(struct dma_chan *chan, dma_addr_t *dma_src,
                grp_start->xor_check_result = result;
                pr_debug("\t%s: grp_start->xor_check_result: %p\n",
                        __func__, grp_start->xor_check_result);
-                sw_desc->unmap_src_cnt = src_cnt;
-                sw_desc->unmap_len = len;
                sw_desc->async_tx.flags = flags;
                while (src_cnt--)
                        iop_desc_set_zero_sum_src_addr(grp_start, src_cnt,
@@ -748,8 +661,6 @@ iop_adma_prep_dma_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src,
                        dst[0] = dst[1] & 0x7;
                iop_desc_set_pq_addr(g, dst);
-                sw_desc->unmap_src_cnt = src_cnt;
-                sw_desc->unmap_len = len;
                sw_desc->async_tx.flags = flags;
                for (i = 0; i < src_cnt; i++)
                        iop_desc_set_pq_src_addr(g, i, src[i], scf[i]);
@@ -804,8 +715,6 @@ iop_adma_prep_dma_pq_val(struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src,
                g->pq_check_result = pqres;
                pr_debug("\t%s: g->pq_check_result: %p\n",
                        __func__, g->pq_check_result);
-                sw_desc->unmap_src_cnt = src_cnt+2;
-                sw_desc->unmap_len = len;
                sw_desc->async_tx.flags = flags;
                while (src_cnt--)
                        iop_desc_set_pq_zero_sum_src_addr(g, src_cnt,
@@ -864,7 +773,7 @@ static enum dma_status iop_adma_status(struct dma_chan *chan,
        int ret;
        ret = dma_cookie_status(chan, cookie, txstate);
-        if (ret == DMA_SUCCESS)
+        if (ret == DMA_COMPLETE)
                return ret;
        iop_adma_slot_cleanup(iop_chan);
@@ -983,7 +892,7 @@ static int iop_adma_memcpy_self_test(struct iop_adma_device *device)
        msleep(1);
        if (iop_adma_status(dma_chan, cookie, NULL) !=
-                        DMA_SUCCESS) {
+                        DMA_COMPLETE) {
                dev_err(dma_chan->device->dev,
                        "Self-test copy timed out, disabling\n");
                err = -ENODEV;
@@ -1083,7 +992,7 @@ iop_adma_xor_val_self_test(struct iop_adma_device *device)
        msleep(8);
        if (iop_adma_status(dma_chan, cookie, NULL) !=
-                DMA_SUCCESS) {
+                DMA_COMPLETE) {
                dev_err(dma_chan->device->dev,
                        "Self-test xor timed out, disabling\n");
                err = -ENODEV;
@@ -1129,7 +1038,7 @@ iop_adma_xor_val_self_test(struct iop_adma_device *device)
        iop_adma_issue_pending(dma_chan);
        msleep(8);
-        if (iop_adma_status(dma_chan, cookie, NULL) != DMA_SUCCESS) {
+        if (iop_adma_status(dma_chan, cookie, NULL) != DMA_COMPLETE) {
                dev_err(dma_chan->device->dev,
                        "Self-test zero sum timed out, disabling\n");
                err = -ENODEV;
@@ -1158,7 +1067,7 @@ iop_adma_xor_val_self_test(struct iop_adma_device *device)
        iop_adma_issue_pending(dma_chan);
        msleep(8);
-        if (iop_adma_status(dma_chan, cookie, NULL) != DMA_SUCCESS) {
+        if (iop_adma_status(dma_chan, cookie, NULL) != DMA_COMPLETE) {
                dev_err(dma_chan->device->dev,
                        "Self-test non-zero sum timed out, disabling\n");
                err = -ENODEV;
@@ -1254,7 +1163,7 @@ iop_adma_pq_zero_sum_self_test(struct iop_adma_device *device)
        msleep(8);
        if (iop_adma_status(dma_chan, cookie, NULL) !=
-                DMA_SUCCESS) {
+                DMA_COMPLETE) {
                dev_err(dev, "Self-test pq timed out, disabling\n");
                err = -ENODEV;
                goto free_resources;
@@ -1291,7 +1200,7 @@ iop_adma_pq_zero_sum_self_test(struct iop_adma_device *device)
        msleep(8);
        if (iop_adma_status(dma_chan, cookie, NULL) !=
-                DMA_SUCCESS) {
+                DMA_COMPLETE) {
                dev_err(dev, "Self-test pq-zero-sum timed out, disabling\n");
                err = -ENODEV;
                goto free_resources;
@@ -1323,7 +1232,7 @@ iop_adma_pq_zero_sum_self_test(struct iop_adma_device *device)
        msleep(8);
        if (iop_adma_status(dma_chan, cookie, NULL) !=
-                DMA_SUCCESS) {
+                DMA_COMPLETE) {
                dev_err(dev, "Self-test !pq-zero-sum timed out, disabling\n");
                err = -ENODEV;
                goto free_resources;
diff --git a/drivers/dma/ipu/ipu_idmac.c b/drivers/dma/ipu/ipu_idmac.c
index cb9c0bc317e8..128ca143486d 100644
--- a/drivers/dma/ipu/ipu_idmac.c
+++ b/drivers/dma/ipu/ipu_idmac.c
@@ -1232,8 +1232,10 @@ static irqreturn_t idmac_interrupt(int irq, void *dev_id)
        desc = list_entry(ichan->queue.next, struct idmac_tx_desc, list);
        descnew = desc;
-        dev_dbg(dev, "IDMAC irq %d, dma 0x%08x, next dma 0x%08x, current %d, curbuf 0x%08x\n",
+        dev_dbg(dev, "IDMAC irq %d, dma %#llx, next dma %#llx, current %d, curbuf %#x\n",
-                irq, sg_dma_address(*sg), sgnext ? sg_dma_address(sgnext) : 0, ichan->active_buffer, curbuf);
+                irq, (u64)sg_dma_address(*sg),
+                sgnext ? (u64)sg_dma_address(sgnext) : 0,
+                ichan->active_buffer, curbuf);
        /* Find the descriptor of sgnext */
        sgnew = idmac_sg_next(ichan, &descnew, *sg);
diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c
index a2c330f5f952..e26075408e9b 100644
--- a/drivers/dma/k3dma.c
+++ b/drivers/dma/k3dma.c
@@ -344,7 +344,7 @@ static enum dma_status k3_dma_tx_status(struct dma_chan *chan,
        size_t bytes = 0;
        ret = dma_cookie_status(&c->vc.chan, cookie, state);
-        if (ret == DMA_SUCCESS)
+        if (ret == DMA_COMPLETE)
                return ret;
        spin_lock_irqsave(&c->vc.lock, flags);
@@ -693,7 +693,7 @@ static int k3_dma_probe(struct platform_device *op)
        irq = platform_get_irq(op, 0);
        ret = devm_request_irq(&op->dev, irq,
-                        k3_dma_int_handler, IRQF_DISABLED, DRIVER_NAME, d);
+                        k3_dma_int_handler, 0, DRIVER_NAME, d);
        if (ret)
                return ret;
diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c
index ff8d7827f8cb..dcb1e05149a7 100644
--- a/drivers/dma/mmp_pdma.c
+++ b/drivers/dma/mmp_pdma.c
@@ -798,8 +798,7 @@ static void dma_do_tasklet(unsigned long data)
                 * move the descriptors to a temporary list so we can drop
                 * the lock during the entire cleanup operation
                 */
-                list_del(&desc->node);
+                list_move(&desc->node, &chain_cleanup);
-                list_add(&desc->node, &chain_cleanup);
                /*
                 * Look for the first list entry which has the ENDIRQEN flag
@@ -863,7 +862,7 @@ static int mmp_pdma_chan_init(struct mmp_pdma_device *pdev,
        if (irq) {
                ret = devm_request_irq(pdev->dev, irq,
-                        mmp_pdma_chan_handler, IRQF_DISABLED, "pdma", phy);
+                        mmp_pdma_chan_handler, 0, "pdma", phy);
                if (ret) {
                        dev_err(pdev->dev, "channel request irq fail!\n");
                        return ret;
@@ -970,7 +969,7 @@ static int mmp_pdma_probe(struct platform_device *op)
                /* all chan share one irq, demux inside */
                irq = platform_get_irq(op, 0);
                ret = devm_request_irq(pdev->dev, irq,
-                        mmp_pdma_int_handler, IRQF_DISABLED, "pdma", pdev);
+                        mmp_pdma_int_handler, 0, "pdma", pdev);
                if (ret)
                        return ret;
        }
diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c
index d3b6358e5a27..3ddacc14a736 100644
--- a/drivers/dma/mmp_tdma.c
+++ b/drivers/dma/mmp_tdma.c
@@ -62,6 +62,11 @@
 #define TDCR_BURSTSZ_16B        (0x3 << 6)
 #define TDCR_BURSTSZ_32B        (0x6 << 6)
 #define TDCR_BURSTSZ_64B        (0x7 << 6)
+#define TDCR_BURSTSZ_SQU_1B             (0x5 << 6)
+#define TDCR_BURSTSZ_SQU_2B             (0x6 << 6)
+#define TDCR_BURSTSZ_SQU_4B             (0x0 << 6)
+#define TDCR_BURSTSZ_SQU_8B             (0x1 << 6)
+#define TDCR_BURSTSZ_SQU_16B    (0x3 << 6)
 #define TDCR_BURSTSZ_SQU_32B    (0x7 << 6)
 #define TDCR_BURSTSZ_128B       (0x5 << 6)
 #define TDCR_DSTDIR_MSK         (0x3 << 4)      /* Dst Direction */
@@ -158,7 +163,7 @@ static void mmp_tdma_disable_chan(struct mmp_tdma_chan *tdmac)
        /* disable irq */
        writel(0, tdmac->reg_base + TDIMR);
-        tdmac->status = DMA_SUCCESS;
+        tdmac->status = DMA_COMPLETE;
 }
 static void mmp_tdma_resume_chan(struct mmp_tdma_chan *tdmac)
@@ -228,8 +233,31 @@ static int mmp_tdma_config_chan(struct mmp_tdma_chan *tdmac)
                        return -EINVAL;
                }
        } else if (tdmac->type == PXA910_SQU) {
-                tdcr |= TDCR_BURSTSZ_SQU_32B;
                tdcr |= TDCR_SSPMOD;
+                switch (tdmac->burst_sz) {
+                case 1:
+                        tdcr |= TDCR_BURSTSZ_SQU_1B;
+                        break;
+                case 2:
+                        tdcr |= TDCR_BURSTSZ_SQU_2B;
+                        break;
+                case 4:
+                        tdcr |= TDCR_BURSTSZ_SQU_4B;
+                        break;
+                case 8:
+                        tdcr |= TDCR_BURSTSZ_SQU_8B;
+                        break;
+                case 16:
+                        tdcr |= TDCR_BURSTSZ_SQU_16B;
+                        break;
+                case 32:
+                        tdcr |= TDCR_BURSTSZ_SQU_32B;
+                        break;
+                default:
+                        dev_err(tdmac->dev, "mmp_tdma: unknown burst size.\n");
+                        return -EINVAL;
+                }
        }
        writel(tdcr, tdmac->reg_base + TDCR);
@@ -324,7 +352,7 @@ static int mmp_tdma_alloc_chan_resources(struct dma_chan *chan)
        if (tdmac->irq) {
                ret = devm_request_irq(tdmac->dev, tdmac->irq,
-                        mmp_tdma_chan_handler, IRQF_DISABLED, "tdma", tdmac);
+                        mmp_tdma_chan_handler, 0, "tdma", tdmac);
                if (ret)
                        return ret;
        }
@@ -365,7 +393,7 @@ static struct dma_async_tx_descriptor *mmp_tdma_prep_dma_cyclic(
        int num_periods = buf_len / period_len;
        int i = 0, buf = 0;
-        if (tdmac->status != DMA_SUCCESS)
+        if (tdmac->status != DMA_COMPLETE)
                return NULL;
        if (period_len > TDMA_MAX_XFER_BYTES) {
@@ -499,7 +527,7 @@ static int mmp_tdma_chan_init(struct mmp_tdma_device *tdev,
        tdmac->idx         = idx;
        tdmac->type        = type;
        tdmac->reg_base    = (unsigned long)tdev->base + idx * 4;
-        tdmac->status = DMA_SUCCESS;
+        tdmac->status = DMA_COMPLETE;
        tdev->tdmac[tdmac->idx] = tdmac;
        tasklet_init(&tdmac->tasklet, dma_do_tasklet, (unsigned long)tdmac);
@@ -554,7 +582,7 @@ static int mmp_tdma_probe(struct platform_device *pdev)
        if (irq_num != chan_num) {
                irq = platform_get_irq(pdev, 0);
                ret = devm_request_irq(&pdev->dev, irq,
-                        mmp_tdma_int_handler, IRQF_DISABLED, "tdma", tdev);
+                        mmp_tdma_int_handler, 0, "tdma", tdev);
                if (ret)
                        return ret;
        }
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 536dcb8ba5fd..7807f0ef4e20 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -60,14 +60,6 @@ static u32 mv_desc_get_dest_addr(struct mv_xor_desc_slot *desc)
        return hw_desc->phy_dest_addr;
 }
-static u32 mv_desc_get_src_addr(struct mv_xor_desc_slot *desc,
-                                int src_idx)
-{
-        struct mv_xor_desc *hw_desc = desc->hw_desc;
-        return hw_desc->phy_src_addr[mv_phy_src_idx(src_idx)];
-}
 static void mv_desc_set_byte_count(struct mv_xor_desc_slot *desc,
                                   u32 byte_count)
 {
@@ -278,42 +270,9 @@ mv_xor_run_tx_complete_actions(struct mv_xor_desc_slot *desc,
                        desc->async_tx.callback(
                                desc->async_tx.callback_param);
-                /* unmap dma addresses
+                dma_descriptor_unmap(&desc->async_tx);
-                 * (unmap_single vs unmap_page?)
+                if (desc->group_head)
-                 */
-                if (desc->group_head && desc->unmap_len) {
-                        struct mv_xor_desc_slot *unmap = desc->group_head;
-                        struct device *dev = mv_chan_to_devp(mv_chan);
-                        u32 len = unmap->unmap_len;
-                        enum dma_ctrl_flags flags = desc->async_tx.flags;
-                        u32 src_cnt;
-                        dma_addr_t addr;
-                        dma_addr_t dest;
-                        src_cnt = unmap->unmap_src_cnt;
-                        dest = mv_desc_get_dest_addr(unmap);
-                        if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-                                enum dma_data_direction dir;
-                                if (src_cnt > 1) /* is xor ? */
-                                        dir = DMA_BIDIRECTIONAL;
-                                else
-                                        dir = DMA_FROM_DEVICE;
-                                dma_unmap_page(dev, dest, len, dir);
-                        }
-                        if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-                                while (src_cnt--) {
-                                        addr = mv_desc_get_src_addr(unmap,
-                                                                    src_cnt);
-                                        if (addr == dest)
-                                                continue;
-                                        dma_unmap_page(dev, addr, len,
-                                                       DMA_TO_DEVICE);
-                                }
-                        }
                        desc->group_head = NULL;
-                }
        }
        /* run dependent operations */
@@ -749,7 +708,7 @@ static enum dma_status mv_xor_status(struct dma_chan *chan,
        enum dma_status ret;
        ret = dma_cookie_status(chan, cookie, txstate);
-        if (ret == DMA_SUCCESS) {
+        if (ret == DMA_COMPLETE) {
                mv_xor_clean_completed_slots(mv_chan);
                return ret;
        }
@@ -874,7 +833,7 @@ static int mv_xor_memcpy_self_test(struct mv_xor_chan *mv_chan)
        msleep(1);
        if (mv_xor_status(dma_chan, cookie, NULL) !=
-            DMA_SUCCESS) {
+            DMA_COMPLETE) {
                dev_err(dma_chan->device->dev,
                        "Self-test copy timed out, disabling\n");
                err = -ENODEV;
@@ -968,7 +927,7 @@ mv_xor_xor_self_test(struct mv_xor_chan *mv_chan)
        msleep(8);
        if (mv_xor_status(dma_chan, cookie, NULL) !=
-            DMA_SUCCESS) {
+            DMA_COMPLETE) {
                dev_err(dma_chan->device->dev,
                        "Self-test xor timed out, disabling\n");
                err = -ENODEV;
@@ -1076,10 +1035,7 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
        }
        mv_chan->mmr_base = xordev->xor_base;
-        if (!mv_chan->mmr_base) {
+        mv_chan->mmr_high_base = xordev->xor_high_base;
-                ret = -ENOMEM;
-                goto err_free_dma;
-        }
        tasklet_init(&mv_chan->irq_tasklet, mv_xor_tasklet, (unsigned long)
                     mv_chan);
@@ -1138,7 +1094,7 @@ static void
 mv_xor_conf_mbus_windows(struct mv_xor_device *xordev,
                         const struct mbus_dram_target_info *dram)
 {
-        void __iomem *base = xordev->xor_base;
+        void __iomem *base = xordev->xor_high_base;
        u32 win_enable = 0;
        int i;
diff --git a/drivers/dma/mv_xor.h b/drivers/dma/mv_xor.h
index 06b067f24c9b..d0749229c875 100644
--- a/drivers/dma/mv_xor.h
+++ b/drivers/dma/mv_xor.h
@@ -34,13 +34,13 @@
 #define XOR_OPERATION_MODE_MEMCPY       2
 #define XOR_DESCRIPTOR_SWAP             BIT(14)
-#define XOR_CURR_DESC(chan)     (chan->mmr_base + 0x210 + (chan->idx * 4))
+#define XOR_CURR_DESC(chan)     (chan->mmr_high_base + 0x10 + (chan->idx * 4))
-#define XOR_NEXT_DESC(chan)     (chan->mmr_base + 0x200 + (chan->idx * 4))
+#define XOR_NEXT_DESC(chan)     (chan->mmr_high_base + 0x00 + (chan->idx * 4))
-#define XOR_BYTE_COUNT(chan)    (chan->mmr_base + 0x220 + (chan->idx * 4))
+#define XOR_BYTE_COUNT(chan)    (chan->mmr_high_base + 0x20 + (chan->idx * 4))
-#define XOR_DEST_POINTER(chan)  (chan->mmr_base + 0x2B0 + (chan->idx * 4))
+#define XOR_DEST_POINTER(chan)  (chan->mmr_high_base + 0xB0 + (chan->idx * 4))
-#define XOR_BLOCK_SIZE(chan)    (chan->mmr_base + 0x2C0 + (chan->idx * 4))
+#define XOR_BLOCK_SIZE(chan)    (chan->mmr_high_base + 0xC0 + (chan->idx * 4))
-#define XOR_INIT_VALUE_LOW(chan)        (chan->mmr_base + 0x2E0)
+#define XOR_INIT_VALUE_LOW(chan)        (chan->mmr_high_base + 0xE0)
-#define XOR_INIT_VALUE_HIGH(chan)       (chan->mmr_base + 0x2E4)
+#define XOR_INIT_VALUE_HIGH(chan)       (chan->mmr_high_base + 0xE4)
 #define XOR_CONFIG(chan)        (chan->mmr_base + 0x10 + (chan->idx * 4))
 #define XOR_ACTIVATION(chan)    (chan->mmr_base + 0x20 + (chan->idx * 4))
@@ -50,11 +50,11 @@
 #define XOR_ERROR_ADDR(chan)    (chan->mmr_base + 0x60)
 #define XOR_INTR_MASK_VALUE     0x3F5
-#define WINDOW_BASE(w)          (0x250 + ((w) << 2))
+#define WINDOW_BASE(w)          (0x50 + ((w) << 2))
-#define WINDOW_SIZE(w)          (0x270 + ((w) << 2))
+#define WINDOW_SIZE(w)          (0x70 + ((w) << 2))
-#define WINDOW_REMAP_HIGH(w)    (0x290 + ((w) << 2))
+#define WINDOW_REMAP_HIGH(w)    (0x90 + ((w) << 2))
-#define WINDOW_BAR_ENABLE(chan) (0x240 + ((chan) << 2))
+#define WINDOW_BAR_ENABLE(chan) (0x40 + ((chan) << 2))
-#define WINDOW_OVERRIDE_CTRL(chan)      (0x2A0 + ((chan) << 2))
+#define WINDOW_OVERRIDE_CTRL(chan)      (0xA0 + ((chan) << 2))
 struct mv_xor_device {
        void __iomem         *xor_base;
@@ -82,6 +82,7 @@ struct mv_xor_chan {
        int                     pending;
        spinlock_t              lock; /* protects the descriptor slot pool */
        void __iomem            *mmr_base;
+        void __iomem            *mmr_high_base;
        unsigned int            idx;
        int                     irq;
        enum dma_transaction_type       current_type;
diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c
index ccd13df841db..ead491346da7 100644
--- a/drivers/dma/mxs-dma.c
+++ b/drivers/dma/mxs-dma.c
@@ -27,6 +27,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/of_dma.h>
+#include <linux/list.h>
 #include <asm/irq.h>
@@ -57,6 +58,9 @@
        (((dma_is_apbh(d) && apbh_is_old(d)) ? 0x050 : 0x110) + (n) * 0x70)
 #define HW_APBHX_CHn_SEMA(d, n) \
        (((dma_is_apbh(d) && apbh_is_old(d)) ? 0x080 : 0x140) + (n) * 0x70)
+#define HW_APBHX_CHn_BAR(d, n) \
+        (((dma_is_apbh(d) && apbh_is_old(d)) ? 0x070 : 0x130) + (n) * 0x70)
+#define HW_APBX_CHn_DEBUG1(d, n) (0x150 + (n) * 0x70)
 /*
 * ccw bits definitions
@@ -115,7 +119,9 @@ struct mxs_dma_chan {
        int                             desc_count;
        enum dma_status                 status;
        unsigned int                    flags;
+        bool                            reset;
 #define MXS_DMA_SG_LOOP                 (1 << 0)
+#define MXS_DMA_USE_SEMAPHORE           (1 << 1)
 };
 #define MXS_DMA_CHANNELS                16
@@ -201,12 +207,47 @@ static void mxs_dma_reset_chan(struct mxs_dma_chan *mxs_chan)
        struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
        int chan_id = mxs_chan->chan.chan_id;
-        if (dma_is_apbh(mxs_dma) && apbh_is_old(mxs_dma))
+        /*
+         * mxs dma channel resets can cause a channel stall. To recover from a
+         * channel stall, we have to reset the whole DMA engine. To avoid this,
+         * we use cyclic DMA with semaphores, that are enhanced in
+         * mxs_dma_int_handler. To reset the channel, we can simply stop writing
+         * into the semaphore counter.
+         */
+        if (mxs_chan->flags & MXS_DMA_USE_SEMAPHORE &&
+                        mxs_chan->flags & MXS_DMA_SG_LOOP) {
+                mxs_chan->reset = true;
+        } else if (dma_is_apbh(mxs_dma) && apbh_is_old(mxs_dma)) {
                writel(1 << (chan_id + BP_APBH_CTRL0_RESET_CHANNEL),
                        mxs_dma->base + HW_APBHX_CTRL0 + STMP_OFFSET_REG_SET);
-        else
+        } else {
+                unsigned long elapsed = 0;
+                const unsigned long max_wait = 50000; /* 50ms */
+                void __iomem *reg_dbg1 = mxs_dma->base +
+                                HW_APBX_CHn_DEBUG1(mxs_dma, chan_id);
+                /*
+                 * On i.MX28 APBX, the DMA channel can stop working if we reset
+                 * the channel while it is in READ_FLUSH (0x08) state.
+                 * We wait here until we leave the state. Then we trigger the
+                 * reset. Waiting a maximum of 50ms, the kernel shouldn't crash
+                 * because of this.
+                 */
+                while ((readl(reg_dbg1) & 0xf) == 0x8 && elapsed < max_wait) {
+                        udelay(100);
+                        elapsed += 100;
+                }
+                if (elapsed >= max_wait)
+                        dev_err(&mxs_chan->mxs_dma->pdev->dev,
+                                        "Failed waiting for the DMA channel %d to leave state READ_FLUSH, trying to reset channel in READ_FLUSH state now\n",
+                                        chan_id);
                writel(1 << (chan_id + BP_APBHX_CHANNEL_CTRL_RESET_CHANNEL),
                        mxs_dma->base + HW_APBHX_CHANNEL_CTRL + STMP_OFFSET_REG_SET);
+        }
+        mxs_chan->status = DMA_COMPLETE;
 }
 static void mxs_dma_enable_chan(struct mxs_dma_chan *mxs_chan)
@@ -219,12 +260,21 @@ static void mxs_dma_enable_chan(struct mxs_dma_chan *mxs_chan)
                mxs_dma->base + HW_APBHX_CHn_NXTCMDAR(mxs_dma, chan_id));
        /* write 1 to SEMA to kick off the channel */
-        writel(1, mxs_dma->base + HW_APBHX_CHn_SEMA(mxs_dma, chan_id));
+        if (mxs_chan->flags & MXS_DMA_USE_SEMAPHORE &&
+                        mxs_chan->flags & MXS_DMA_SG_LOOP) {
+                /* A cyclic DMA consists of at least 2 segments, so initialize
+                 * the semaphore with 2 so we have enough time to add 1 to the
+                 * semaphore if we need to */
+                writel(2, mxs_dma->base + HW_APBHX_CHn_SEMA(mxs_dma, chan_id));
+        } else {
+                writel(1, mxs_dma->base + HW_APBHX_CHn_SEMA(mxs_dma, chan_id));
+        }
+        mxs_chan->reset = false;
 }
 static void mxs_dma_disable_chan(struct mxs_dma_chan *mxs_chan)
 {
-        mxs_chan->status = DMA_SUCCESS;
+        mxs_chan->status = DMA_COMPLETE;
 }
 static void mxs_dma_pause_chan(struct mxs_dma_chan *mxs_chan)
@@ -272,58 +322,88 @@ static void mxs_dma_tasklet(unsigned long data)
                mxs_chan->desc.callback(mxs_chan->desc.callback_param);
 }
+static int mxs_dma_irq_to_chan(struct mxs_dma_engine *mxs_dma, int irq)
+{
+        int i;
+        for (i = 0; i != mxs_dma->nr_channels; ++i)
+                if (mxs_dma->mxs_chans[i].chan_irq == irq)
+                        return i;
+        return -EINVAL;
+}
 static irqreturn_t mxs_dma_int_handler(int irq, void *dev_id)
 {
        struct mxs_dma_engine *mxs_dma = dev_id;
-        u32 stat1, stat2;
+        struct mxs_dma_chan *mxs_chan;
+        u32 completed;
+        u32 err;
+        int chan = mxs_dma_irq_to_chan(mxs_dma, irq);
+        if (chan < 0)
+                return IRQ_NONE;
        /* completion status */
-        stat1 = readl(mxs_dma->base + HW_APBHX_CTRL1);
+        completed = readl(mxs_dma->base + HW_APBHX_CTRL1);
-        stat1 &= MXS_DMA_CHANNELS_MASK;
+        completed = (completed >> chan) & 0x1;
-        writel(stat1, mxs_dma->base + HW_APBHX_CTRL1 + STMP_OFFSET_REG_CLR);
+        /* Clear interrupt */
+        writel((1 << chan),
+                        mxs_dma->base + HW_APBHX_CTRL1 + STMP_OFFSET_REG_CLR);
        /* error status */
-        stat2 = readl(mxs_dma->base + HW_APBHX_CTRL2);
+        err = readl(mxs_dma->base + HW_APBHX_CTRL2);
-        writel(stat2, mxs_dma->base + HW_APBHX_CTRL2 + STMP_OFFSET_REG_CLR);
+        err &= (1 << (MXS_DMA_CHANNELS + chan)) | (1 << chan);
+        /*
+         * error status bit is in the upper 16 bits, error irq bit in the lower
+         * 16 bits. We transform it into a simpler error code:
+         * err: 0x00 = no error, 0x01 = TERMINATION, 0x02 = BUS_ERROR
+         */
+        err = (err >> (MXS_DMA_CHANNELS + chan)) + (err >> chan);
+        /* Clear error irq */
+        writel((1 << chan),
+                        mxs_dma->base + HW_APBHX_CTRL2 + STMP_OFFSET_REG_CLR);
        /*
         * When both completion and error of termination bits set at the
         * same time, we do not take it as an error.  IOW, it only becomes
-         * an error we need to handle here in case of either it's (1) a bus
+         * an error we need to handle here in case of either it's a bus
-         * error or (2) a termination error with no completion.
+         * error or a termination error with no completion. 0x01 is termination
+         * error, so we can subtract err & completed to get the real error case.
         */
-        stat2 = ((stat2 >> MXS_DMA_CHANNELS) & stat2) | /* (1) */
+        err -= err & completed;
-                (~(stat2 >> MXS_DMA_CHANNELS) & stat2 & ~stat1); /* (2) */
-        /* combine error and completion status for checking */
-        stat1 = (stat2 << MXS_DMA_CHANNELS) | stat1;
-        while (stat1) {
-                int channel = fls(stat1) - 1;
-                struct mxs_dma_chan *mxs_chan =
-                        &mxs_dma->mxs_chans[channel % MXS_DMA_CHANNELS];
-                if (channel >= MXS_DMA_CHANNELS) {
-                        dev_dbg(mxs_dma->dma_device.dev,
-                                "%s: error in channel %d\n", __func__,
-                                channel - MXS_DMA_CHANNELS);
-                        mxs_chan->status = DMA_ERROR;
-                        mxs_dma_reset_chan(mxs_chan);
-                } else {
-                        if (mxs_chan->flags & MXS_DMA_SG_LOOP)
-                                mxs_chan->status = DMA_IN_PROGRESS;
-                        else
-                                mxs_chan->status = DMA_SUCCESS;
-                }
-                stat1 &= ~(1 << channel);
+        mxs_chan = &mxs_dma->mxs_chans[chan];
-                if (mxs_chan->status == DMA_SUCCESS)
+        if (err) {
-                        dma_cookie_complete(&mxs_chan->desc);
+                dev_dbg(mxs_dma->dma_device.dev,
+                        "%s: error in channel %d\n", __func__,
+                        chan);
+                mxs_chan->status = DMA_ERROR;
+                mxs_dma_reset_chan(mxs_chan);
+        } else if (mxs_chan->status != DMA_COMPLETE) {
+                if (mxs_chan->flags & MXS_DMA_SG_LOOP) {
+                        mxs_chan->status = DMA_IN_PROGRESS;
+                        if (mxs_chan->flags & MXS_DMA_USE_SEMAPHORE)
+                                writel(1, mxs_dma->base +
+                                        HW_APBHX_CHn_SEMA(mxs_dma, chan));
+                } else {
+                        mxs_chan->status = DMA_COMPLETE;
+                }
+        }
-                /* schedule tasklet on this channel */
+        if (mxs_chan->status == DMA_COMPLETE) {
-                tasklet_schedule(&mxs_chan->tasklet);
+                if (mxs_chan->reset)
+                        return IRQ_HANDLED;
+                dma_cookie_complete(&mxs_chan->desc);
        }
+        /* schedule tasklet on this channel */
+        tasklet_schedule(&mxs_chan->tasklet);
        return IRQ_HANDLED;
 }
@@ -523,6 +603,7 @@ static struct dma_async_tx_descriptor *mxs_dma_prep_dma_cyclic(
        mxs_chan->status = DMA_IN_PROGRESS;
        mxs_chan->flags |= MXS_DMA_SG_LOOP;
+        mxs_chan->flags |= MXS_DMA_USE_SEMAPHORE;
        if (num_periods > NUM_CCW) {
                dev_err(mxs_dma->dma_device.dev,
@@ -554,6 +635,7 @@ static struct dma_async_tx_descriptor *mxs_dma_prep_dma_cyclic(
                ccw->bits |= CCW_IRQ;
                ccw->bits |= CCW_HALT_ON_TERM;
                ccw->bits |= CCW_TERM_FLUSH;
+                ccw->bits |= CCW_DEC_SEM;
                ccw->bits |= BF_CCW(direction == DMA_DEV_TO_MEM ?
                                MXS_DMA_CMD_WRITE : MXS_DMA_CMD_READ, COMMAND);
@@ -599,8 +681,24 @@ static enum dma_status mxs_dma_tx_status(struct dma_chan *chan,
                        dma_cookie_t cookie, struct dma_tx_state *txstate)
 {
        struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(chan);
+        struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
+        u32 residue = 0;
+        if (mxs_chan->status == DMA_IN_PROGRESS &&
+                        mxs_chan->flags & MXS_DMA_SG_LOOP) {
+                struct mxs_dma_ccw *last_ccw;
+                u32 bar;
+                last_ccw = &mxs_chan->ccw[mxs_chan->desc_count - 1];
+                residue = last_ccw->xfer_bytes + last_ccw->bufaddr;
+                bar = readl(mxs_dma->base +
+                                HW_APBHX_CHn_BAR(mxs_dma, chan->chan_id));
+                residue -= bar;
+        }
-        dma_set_tx_state(txstate, chan->completed_cookie, chan->cookie, 0);
+        dma_set_tx_state(txstate, chan->completed_cookie, chan->cookie,
+                        residue);
        return mxs_chan->status;
 }
diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c
index ec3fc4fd9160..2f66cf4e54fe 100644
--- a/drivers/dma/omap-dma.c
+++ b/drivers/dma/omap-dma.c
@@ -248,7 +248,7 @@ static enum dma_status omap_dma_tx_status(struct dma_chan *chan,
        unsigned long flags;
        ret = dma_cookie_status(chan, cookie, txstate);
-        if (ret == DMA_SUCCESS || !txstate)
+        if (ret == DMA_COMPLETE || !txstate)
                return ret;
        spin_lock_irqsave(&c->vc.lock, flags);
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index df8b10fd1726..cdf0483b8f2d 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -2268,6 +2268,8 @@ static void pl330_tasklet(unsigned long data)
                        list_move_tail(&desc->node, &pch->dmac->desc_pool);
                }
+                dma_descriptor_unmap(&desc->txd);
                if (callback) {
                        spin_unlock_irqrestore(&pch->lock, flags);
                        callback(callback_param);
@@ -2314,7 +2316,7 @@ bool pl330_filter(struct dma_chan *chan, void *param)
                return false;
        peri_id = chan->private;
-        return *peri_id == (unsigned)param;
+        return *peri_id == (unsigned long)param;
 }
 EXPORT_SYMBOL(pl330_filter);
@@ -2926,16 +2928,23 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
        amba_set_drvdata(adev, pdmac);
-        irq = adev->irq[0];
+        for (i = 0; i < AMBA_NR_IRQS; i++) {
-        ret = request_irq(irq, pl330_irq_handler, 0,
+                irq = adev->irq[i];
-                        dev_name(&adev->dev), pi);
+                if (irq) {
-        if (ret)
+                        ret = devm_request_irq(&adev->dev, irq,
-                return ret;
+                                               pl330_irq_handler, 0,
+                                               dev_name(&adev->dev), pi);
+                        if (ret)
+                                return ret;
+                } else {
+                        break;
+                }
+        }
        pi->pcfg.periph_id = adev->periphid;
        ret = pl330_add(pi);
        if (ret)
-                goto probe_err1;
+                return ret;
        INIT_LIST_HEAD(&pdmac->desc_pool);
        spin_lock_init(&pdmac->pool_lock);
@@ -3033,8 +3042,6 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
        return 0;
 probe_err3:
-        amba_set_drvdata(adev, NULL);
        /* Idle the DMAC */
        list_for_each_entry_safe(pch, _p, &pdmac->ddma.channels,
                        chan.device_node) {
@@ -3048,8 +3055,6 @@ probe_err3:
        }
 probe_err2:
        pl330_del(pi);
-probe_err1:
-        free_irq(irq, pi);
        return ret;
 }
@@ -3059,7 +3064,6 @@ static int pl330_remove(struct amba_device *adev)
        struct dma_pl330_dmac *pdmac = amba_get_drvdata(adev);
        struct dma_pl330_chan *pch, *_p;
        struct pl330_info *pi;
-        int irq;
        if (!pdmac)
                return 0;
@@ -3068,7 +3072,6 @@ static int pl330_remove(struct amba_device *adev)
                of_dma_controller_free(adev->dev.of_node);
        dma_async_device_unregister(&pdmac->ddma);
-        amba_set_drvdata(adev, NULL);
        /* Idle the DMAC */
        list_for_each_entry_safe(pch, _p, &pdmac->ddma.channels,
@@ -3086,9 +3089,6 @@ static int pl330_remove(struct amba_device *adev)
        pl330_del(pi);
-        irq = adev->irq[0];
-        free_irq(irq, pi);
        return 0;
 }
diff --git a/drivers/dma/ppc4xx/adma.c b/drivers/dma/ppc4xx/adma.c
index e24b5ef486b5..8da48c6b2a38 100644
--- a/drivers/dma/ppc4xx/adma.c
+++ b/drivers/dma/ppc4xx/adma.c
@@ -804,218 +804,6 @@ static void ppc440spe_desc_set_link(struct ppc440spe_adma_chan *chan,
 }
 /**
- * ppc440spe_desc_get_src_addr - extract the source address from the descriptor
- */
-static u32 ppc440spe_desc_get_src_addr(struct ppc440spe_adma_desc_slot *desc,
-                                struct ppc440spe_adma_chan *chan, int src_idx)
-{
-        struct dma_cdb *dma_hw_desc;
-        struct xor_cb *xor_hw_desc;
-        switch (chan->device->id) {
-        case PPC440SPE_DMA0_ID:
-        case PPC440SPE_DMA1_ID:
-                dma_hw_desc = desc->hw_desc;
-                /* May have 0, 1, 2, or 3 sources */
-                switch (dma_hw_desc->opc) {
-                case DMA_CDB_OPC_NO_OP:
-                case DMA_CDB_OPC_DFILL128:
-                        return 0;
-                case DMA_CDB_OPC_DCHECK128:
-                        if (unlikely(src_idx)) {
-                                printk(KERN_ERR "%s: try to get %d source for"
-                                    " DCHECK128\n", __func__, src_idx);
-                                BUG();
-                        }
-                        return le32_to_cpu(dma_hw_desc->sg1l);
-                case DMA_CDB_OPC_MULTICAST:
-                case DMA_CDB_OPC_MV_SG1_SG2:
-                        if (unlikely(src_idx > 2)) {
-                                printk(KERN_ERR "%s: try to get %d source from"
-                                    " DMA descr\n", __func__, src_idx);
-                                BUG();
-                        }
-                        if (src_idx) {
-                                if (le32_to_cpu(dma_hw_desc->sg1u) &
-                                    DMA_CUED_XOR_WIN_MSK) {
-                                        u8 region;
-                                        if (src_idx == 1)
-                                                return le32_to_cpu(
-                                                    dma_hw_desc->sg1l) +
-                                                        desc->unmap_len;
-                                        region = (le32_to_cpu(
-                                            dma_hw_desc->sg1u)) >>
-                                                DMA_CUED_REGION_OFF;
-                                        region &= DMA_CUED_REGION_MSK;
-                                        switch (region) {
-                                        case DMA_RXOR123:
-                                                return le32_to_cpu(
-                                                    dma_hw_desc->sg1l) +
-                                                        (desc->unmap_len << 1);
-                                        case DMA_RXOR124:
-                                                return le32_to_cpu(
-                                                    dma_hw_desc->sg1l) +
-                                                        (desc->unmap_len * 3);
-                                        case DMA_RXOR125:
-                                                return le32_to_cpu(
-                                                    dma_hw_desc->sg1l) +
-                                                        (desc->unmap_len << 2);
-                                        default:
-                                                printk(KERN_ERR
-                                                    "%s: try to"
-                                                    " get src3 for region %02x"
-                                                    "PPC440SPE_DESC_RXOR12?\n",
-                                                    __func__, region);
-                                                BUG();
-                                        }
-                                } else {
-                                        printk(KERN_ERR
-                                                "%s: try to get %d"
-                                                " source for non-cued descr\n",
-                                                __func__, src_idx);
-                                        BUG();
-                                }
-                        }
-                        return le32_to_cpu(dma_hw_desc->sg1l);
-                default:
-                        printk(KERN_ERR "%s: unknown OPC 0x%02x\n",
-                                __func__, dma_hw_desc->opc);
-                        BUG();
-                }
-                return le32_to_cpu(dma_hw_desc->sg1l);
-        case PPC440SPE_XOR_ID:
-                /* May have up to 16 sources */
-                xor_hw_desc = desc->hw_desc;
-                return xor_hw_desc->ops[src_idx].l;
-        }
-        return 0;
-}
-/**
- * ppc440spe_desc_get_dest_addr - extract the destination address from the
- * descriptor
- */
-static u32 ppc440spe_desc_get_dest_addr(struct ppc440spe_adma_desc_slot *desc,
-                                struct ppc440spe_adma_chan *chan, int idx)
-{
-        struct dma_cdb *dma_hw_desc;
-        struct xor_cb *xor_hw_desc;
-        switch (chan->device->id) {
-        case PPC440SPE_DMA0_ID:
-        case PPC440SPE_DMA1_ID:
-                dma_hw_desc = desc->hw_desc;
-                if (likely(!idx))
-                        return le32_to_cpu(dma_hw_desc->sg2l);
-                return le32_to_cpu(dma_hw_desc->sg3l);
-        case PPC440SPE_XOR_ID:
-                xor_hw_desc = desc->hw_desc;
-                return xor_hw_desc->cbtal;
-        }
-        return 0;
-}
-/**
- * ppc440spe_desc_get_src_num - extract the number of source addresses from
- * the descriptor
- */
-static u32 ppc440spe_desc_get_src_num(struct ppc440spe_adma_desc_slot *desc,
-                                struct ppc440spe_adma_chan *chan)
-{
-        struct dma_cdb *dma_hw_desc;
-        struct xor_cb *xor_hw_desc;
-        switch (chan->device->id) {
-        case PPC440SPE_DMA0_ID:
-        case PPC440SPE_DMA1_ID:
-                dma_hw_desc = desc->hw_desc;
-                switch (dma_hw_desc->opc) {
-                case DMA_CDB_OPC_NO_OP:
-                case DMA_CDB_OPC_DFILL128:
-                        return 0;
-                case DMA_CDB_OPC_DCHECK128:
-                        return 1;
-                case DMA_CDB_OPC_MV_SG1_SG2:
-                case DMA_CDB_OPC_MULTICAST:
-                        /*
-                         * Only for RXOR operations we have more than
-                         * one source
-                         */
-                        if (le32_to_cpu(dma_hw_desc->sg1u) &
-                            DMA_CUED_XOR_WIN_MSK) {
-                                /* RXOR op, there are 2 or 3 sources */
-                                if (((le32_to_cpu(dma_hw_desc->sg1u) >>
-                                    DMA_CUED_REGION_OFF) &
-                                      DMA_CUED_REGION_MSK) == DMA_RXOR12) {
-                                        /* RXOR 1-2 */
-                                        return 2;
-                                } else {
-                                        /* RXOR 1-2-3/1-2-4/1-2-5 */
-                                        return 3;
-                                }
-                        }
-                        return 1;
-                default:
-                        printk(KERN_ERR "%s: unknown OPC 0x%02x\n",
-                                __func__, dma_hw_desc->opc);
-                        BUG();
-                }
-        case PPC440SPE_XOR_ID:
-                /* up to 16 sources */
-                xor_hw_desc = desc->hw_desc;
-                return xor_hw_desc->cbc & XOR_CDCR_OAC_MSK;
-        default:
-                BUG();
-        }
-        return 0;
-}
-/**
- * ppc440spe_desc_get_dst_num - get the number of destination addresses in
- * this descriptor
- */
-static u32 ppc440spe_desc_get_dst_num(struct ppc440spe_adma_desc_slot *desc,
-                                struct ppc440spe_adma_chan *chan)
-{
-        struct dma_cdb *dma_hw_desc;
-        switch (chan->device->id) {
-        case PPC440SPE_DMA0_ID:
-        case PPC440SPE_DMA1_ID:
-                /* May be 1 or 2 destinations */
-                dma_hw_desc = desc->hw_desc;
-                switch (dma_hw_desc->opc) {
-                case DMA_CDB_OPC_NO_OP:
-                case DMA_CDB_OPC_DCHECK128:
-                        return 0;
-                case DMA_CDB_OPC_MV_SG1_SG2:
-                case DMA_CDB_OPC_DFILL128:
-                        return 1;
-                case DMA_CDB_OPC_MULTICAST:
-                        if (desc->dst_cnt == 2)
-                                return 2;
-                        else
-                                return 1;
-                default:
-                        printk(KERN_ERR "%s: unknown OPC 0x%02x\n",
-                                __func__, dma_hw_desc->opc);
-                        BUG();
-                }
-        case PPC440SPE_XOR_ID:
-                /* Always only 1 destination */
-                return 1;
-        default:
-                BUG();
-        }
-        return 0;
-}
-/**
 * ppc440spe_desc_get_link - get the address of the descriptor that
 * follows this one
 */
@@ -1707,43 +1495,6 @@ static void ppc440spe_adma_free_slots(struct ppc440spe_adma_desc_slot *slot,
        }
 }
-static void ppc440spe_adma_unmap(struct ppc440spe_adma_chan *chan,
-                                 struct ppc440spe_adma_desc_slot *desc)
-{
-        u32 src_cnt, dst_cnt;
-        dma_addr_t addr;
-        /*
-         * get the number of sources & destination
-         * included in this descriptor and unmap
-         * them all
-         */
-        src_cnt = ppc440spe_desc_get_src_num(desc, chan);
-        dst_cnt = ppc440spe_desc_get_dst_num(desc, chan);
-        /* unmap destinations */
-        if (!(desc->async_tx.flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-                while (dst_cnt--) {
-                        addr = ppc440spe_desc_get_dest_addr(
-                                desc, chan, dst_cnt);
-                        dma_unmap_page(chan->device->dev,
-                                        addr, desc->unmap_len,
-                                        DMA_FROM_DEVICE);
-                }
-        }
-        /* unmap sources */
-        if (!(desc->async_tx.flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-                while (src_cnt--) {
-                        addr = ppc440spe_desc_get_src_addr(
-                                desc, chan, src_cnt);
-                        dma_unmap_page(chan->device->dev,
-                                        addr, desc->unmap_len,
-                                        DMA_TO_DEVICE);
-                }
-        }
-}
 /**
 * ppc440spe_adma_run_tx_complete_actions - call functions to be called
 * upon completion
@@ -1767,26 +1518,7 @@ static dma_cookie_t ppc440spe_adma_run_tx_complete_actions(
                        desc->async_tx.callback(
                                desc->async_tx.callback_param);
-                /* unmap dma addresses
+                dma_descriptor_unmap(&desc->async_tx);
-                 * (unmap_single vs unmap_page?)
-                 *
-                 * actually, ppc's dma_unmap_page() functions are empty, so
-                 * the following code is just for the sake of completeness
-                 */
-                if (chan && chan->needs_unmap && desc->group_head &&
-                     desc->unmap_len) {
-                        struct ppc440spe_adma_desc_slot *unmap =
-                                                        desc->group_head;
-                        /* assume 1 slot per op always */
-                        u32 slot_count = unmap->slot_cnt;
-                        /* Run through the group list and unmap addresses */
-                        for (i = 0; i < slot_count; i++) {
-                                BUG_ON(!unmap);
-                                ppc440spe_adma_unmap(chan, unmap);
-                                unmap = unmap->hw_next;
-                        }
-                }
        }
        /* run dependent operations */
@@ -3893,7 +3625,7 @@ static enum dma_status ppc440spe_adma_tx_status(struct dma_chan *chan,
        ppc440spe_chan = to_ppc440spe_adma_chan(chan);
        ret = dma_cookie_status(chan, cookie, txstate);
-        if (ret == DMA_SUCCESS)
+        if (ret == DMA_COMPLETE)
                return ret;
        ppc440spe_adma_slot_cleanup(ppc440spe_chan);
diff --git a/drivers/dma/sa11x0-dma.c b/drivers/dma/sa11x0-dma.c
index 461a91ab70bb..ab26d46bbe15 100644
--- a/drivers/dma/sa11x0-dma.c
+++ b/drivers/dma/sa11x0-dma.c
@@ -436,7 +436,7 @@ static enum dma_status sa11x0_dma_tx_status(struct dma_chan *chan,
        enum dma_status ret;
        ret = dma_cookie_status(&c->vc.chan, cookie, state);
-        if (ret == DMA_SUCCESS)
+        if (ret == DMA_COMPLETE)
                return ret;
        if (!state)
diff --git a/drivers/dma/sh/shdma-base.c b/drivers/dma/sh/shdma-base.c
index d94ab592cc1b..2e7b394def80 100644
--- a/drivers/dma/sh/shdma-base.c
+++ b/drivers/dma/sh/shdma-base.c
@@ -724,7 +724,7 @@ static enum dma_status shdma_tx_status(struct dma_chan *chan,
         * If we don't find cookie on the queue, it has been aborted and we have
         * to report error
         */
-        if (status != DMA_SUCCESS) {
+        if (status != DMA_COMPLETE) {
                struct shdma_desc *sdesc;
                status = DMA_ERROR;
                list_for_each_entry(sdesc, &schan->ld_queue, node)
diff --git a/drivers/dma/sh/shdmac.c b/drivers/dma/sh/shdmac.c
index 1069e8869f20..0d765c0e21ec 100644
--- a/drivers/dma/sh/shdmac.c
+++ b/drivers/dma/sh/shdmac.c
@@ -685,7 +685,7 @@ MODULE_DEVICE_TABLE(of, sh_dmae_of_match);
 static int sh_dmae_probe(struct platform_device *pdev)
 {
        const struct sh_dmae_pdata *pdata;
-        unsigned long irqflags = IRQF_DISABLED,
+        unsigned long irqflags = 0,
                chan_flag[SH_DMAE_MAX_CHANNELS] = {};
        int errirq, chan_irq[SH_DMAE_MAX_CHANNELS];
        int err, i, irq_cnt = 0, irqres = 0, irq_cap = 0;
@@ -838,7 +838,7 @@ static int sh_dmae_probe(struct platform_device *pdev)
                                    IORESOURCE_IRQ_SHAREABLE)
                                        chan_flag[irq_cnt] = IRQF_SHARED;
                                else
-                                        chan_flag[irq_cnt] = IRQF_DISABLED;
+                                        chan_flag[irq_cnt] = 0;
                                dev_dbg(&pdev->dev,
                                        "Found IRQ %d for channel %d\n",
                                        i, irq_cnt);
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 82d2b97ad942..b8c031b7de4e 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -14,6 +14,7 @@
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
+#include <linux/log2.h>
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
 #include <linux/err.h>
@@ -2626,7 +2627,7 @@ static enum dma_status d40_tx_status(struct dma_chan *chan,
        }
        ret = dma_cookie_status(chan, cookie, txstate);
-        if (ret != DMA_SUCCESS)
+        if (ret != DMA_COMPLETE)
                dma_set_residue(txstate, stedma40_residue(chan));
        if (d40_is_paused(d40c))
@@ -2796,8 +2797,8 @@ static int d40_set_runtime_config(struct dma_chan *chan,
            src_addr_width >  DMA_SLAVE_BUSWIDTH_8_BYTES   ||
            dst_addr_width <= DMA_SLAVE_BUSWIDTH_UNDEFINED ||
            dst_addr_width >  DMA_SLAVE_BUSWIDTH_8_BYTES   ||
-            ((src_addr_width > 1) && (src_addr_width & 1)) ||
+            !is_power_of_2(src_addr_width) ||
-            ((dst_addr_width > 1) && (dst_addr_width & 1)))
+            !is_power_of_2(dst_addr_width))
                return -EINVAL;
        cfg->src_info.data_width = src_addr_width;
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index 5d4986e5f5fa..73654e33f13b 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -570,7 +570,7 @@ static void handle_once_dma_done(struct tegra_dma_channel *tdc,
        list_del(&sgreq->node);
        if (sgreq->last_sg) {
-                dma_desc->dma_status = DMA_SUCCESS;
+                dma_desc->dma_status = DMA_COMPLETE;
                dma_cookie_complete(&dma_desc->txd);
                if (!dma_desc->cb_count)
                        list_add_tail(&dma_desc->cb_node, &tdc->cb_desc);
@@ -768,7 +768,7 @@ static enum dma_status tegra_dma_tx_status(struct dma_chan *dc,
        unsigned int residual;
        ret = dma_cookie_status(dc, cookie, txstate);
-        if (ret == DMA_SUCCESS)
+        if (ret == DMA_COMPLETE)
                return ret;
        spin_lock_irqsave(&tdc->lock, flags);
@@ -1018,7 +1018,7 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_slave_sg(
        return &dma_desc->txd;
 }
-struct dma_async_tx_descriptor *tegra_dma_prep_dma_cyclic(
+static struct dma_async_tx_descriptor *tegra_dma_prep_dma_cyclic(
        struct dma_chan *dc, dma_addr_t buf_addr, size_t buf_len,
        size_t period_len, enum dma_transfer_direction direction,
        unsigned long flags, void *context)
diff --git a/drivers/dma/timb_dma.c b/drivers/dma/timb_dma.c
index 28af214fce04..4506a7b4f972 100644
--- a/drivers/dma/timb_dma.c
+++ b/drivers/dma/timb_dma.c
@@ -154,38 +154,6 @@ static bool __td_dma_done_ack(struct timb_dma_chan *td_chan)
        return done;
 }
-static void __td_unmap_desc(struct timb_dma_chan *td_chan, const u8 *dma_desc,
-        bool single)
-{
-        dma_addr_t addr;
-        int len;
-        addr = (dma_desc[7] << 24) | (dma_desc[6] << 16) | (dma_desc[5] << 8) |
-                dma_desc[4];
-        len = (dma_desc[3] << 8) | dma_desc[2];
-        if (single)
-                dma_unmap_single(chan2dev(&td_chan->chan), addr, len,
-                        DMA_TO_DEVICE);
-        else
-                dma_unmap_page(chan2dev(&td_chan->chan), addr, len,
-                        DMA_TO_DEVICE);
-}
-static void __td_unmap_descs(struct timb_dma_desc *td_desc, bool single)
-{
-        struct timb_dma_chan *td_chan = container_of(td_desc->txd.chan,
-                struct timb_dma_chan, chan);
-        u8 *descs;
-        for (descs = td_desc->desc_list; ; descs += TIMB_DMA_DESC_SIZE) {
-                __td_unmap_desc(td_chan, descs, single);
-                if (descs[0] & 0x02)
-                        break;
-        }
-}
 static int td_fill_desc(struct timb_dma_chan *td_chan, u8 *dma_desc,
        struct scatterlist *sg, bool last)
 {
@@ -293,10 +261,7 @@ static void __td_finish(struct timb_dma_chan *td_chan)
        list_move(&td_desc->desc_node, &td_chan->free_list);
-        if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP))
+        dma_descriptor_unmap(txd);
-                __td_unmap_descs(td_desc,
-                        txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE);
        /*
         * The API requires that no submissions are done from a
         * callback, so we don't need to drop the lock here
diff --git a/drivers/dma/txx9dmac.c b/drivers/dma/txx9dmac.c
index 71e8e775189e..bae6c29f5502 100644
--- a/drivers/dma/txx9dmac.c
+++ b/drivers/dma/txx9dmac.c
@@ -419,30 +419,7 @@ txx9dmac_descriptor_complete(struct txx9dmac_chan *dc,
        list_splice_init(&desc->tx_list, &dc->free_list);
        list_move(&desc->desc_node, &dc->free_list);
-        if (!ds) {
+        dma_descriptor_unmap(txd);
-                dma_addr_t dmaaddr;
-                if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-                        dmaaddr = is_dmac64(dc) ?
-                                desc->hwdesc.DAR : desc->hwdesc32.DAR;
-                        if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
-                                dma_unmap_single(chan2parent(&dc->chan),
-                                        dmaaddr, desc->len, DMA_FROM_DEVICE);
-                        else
-                                dma_unmap_page(chan2parent(&dc->chan),
-                                        dmaaddr, desc->len, DMA_FROM_DEVICE);
-                }
-                if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-                        dmaaddr = is_dmac64(dc) ?
-                                desc->hwdesc.SAR : desc->hwdesc32.SAR;
-                        if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
-                                dma_unmap_single(chan2parent(&dc->chan),
-                                        dmaaddr, desc->len, DMA_TO_DEVICE);
-                        else
-                                dma_unmap_page(chan2parent(&dc->chan),
-                                        dmaaddr, desc->len, DMA_TO_DEVICE);
-                }
-        }
        /*
         * The API requires that no submissions are done from a
         * callback, so we don't need to drop the lock here
@@ -962,8 +939,8 @@ txx9dmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
        enum dma_status ret;
        ret = dma_cookie_status(chan, cookie, txstate);
-        if (ret == DMA_SUCCESS)
+        if (ret == DMA_COMPLETE)
-                return DMA_SUCCESS;
+                return DMA_COMPLETE;
        spin_lock_bh(&dc->lock);
        txx9dmac_scan_descriptors(dc);
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 7dd446150294..4e10b10d3ddd 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -13,6 +13,7 @@
 #include <linux/acpi_gpio.h>
 #include <linux/idr.h>
 #include <linux/slab.h>
+#include <linux/acpi.h>
 #define CREATE_TRACE_POINTS
 #include <trace/events/gpio.h>
diff --git a/drivers/gpu/drm/i915/intel_acpi.c b/drivers/gpu/drm/i915/intel_acpi.c
index 43959edd4291..dfff0907f70e 100644
--- a/drivers/gpu/drm/i915/intel_acpi.c
+++ b/drivers/gpu/drm/i915/intel_acpi.c
@@ -196,7 +196,7 @@ static bool intel_dsm_pci_probe(struct pci_dev *pdev)
        acpi_handle dhandle;
        int ret;
-        dhandle = DEVICE_ACPI_HANDLE(&pdev->dev);
+        dhandle = ACPI_HANDLE(&pdev->dev);
        if (!dhandle)
                return false;
diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c
index 1b2f41c3f191..6d69a9bad865 100644
--- a/drivers/gpu/drm/i915/intel_opregion.c
+++ b/drivers/gpu/drm/i915/intel_opregion.c
@@ -638,7 +638,7 @@ static void intel_didl_outputs(struct drm_device *dev)
        u32 temp;
        int i = 0;
-        handle = DEVICE_ACPI_HANDLE(&dev->pdev->dev);
+        handle = ACPI_HANDLE(&dev->pdev->dev);
        if (!handle || acpi_bus_get_device(handle, &acpi_dev))
                return;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mxm/base.c b/drivers/gpu/drm/nouveau/core/subdev/mxm/base.c
index e286e132c7e7..129120473f6c 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mxm/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mxm/base.c
@@ -116,7 +116,7 @@ mxm_shadow_dsm(struct nouveau_mxm *mxm, u8 version)
        acpi_handle handle;
        int ret;
-        handle = DEVICE_ACPI_HANDLE(&device->pdev->dev);
+        handle = ACPI_HANDLE(&device->pdev->dev);
        if (!handle)
                return false;
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index 07273a2ae62f..95c740454049 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -256,7 +256,7 @@ static int nouveau_dsm_pci_probe(struct pci_dev *pdev)
        acpi_handle dhandle;
        int retval = 0;
-        dhandle = DEVICE_ACPI_HANDLE(&pdev->dev);
+        dhandle = ACPI_HANDLE(&pdev->dev);
        if (!dhandle)
                return false;
@@ -414,7 +414,7 @@ bool nouveau_acpi_rom_supported(struct pci_dev *pdev)
        if (!nouveau_dsm_priv.dsm_detected && !nouveau_dsm_priv.optimus_detected)
                return false;
-        dhandle = DEVICE_ACPI_HANDLE(&pdev->dev);
+        dhandle = ACPI_HANDLE(&pdev->dev);
        if (!dhandle)
                return false;
@@ -448,7 +448,7 @@ nouveau_acpi_edid(struct drm_device *dev, struct drm_connector *connector)
                return NULL;
        }
-        handle = DEVICE_ACPI_HANDLE(&dev->pdev->dev);
+        handle = ACPI_HANDLE(&dev->pdev->dev);
        if (!handle)
                return NULL;
diff --git a/drivers/gpu/drm/radeon/radeon_acpi.c b/drivers/gpu/drm/radeon/radeon_acpi.c
index 10f98c7742d8..98a9074b306b 100644
--- a/drivers/gpu/drm/radeon/radeon_acpi.c
+++ b/drivers/gpu/drm/radeon/radeon_acpi.c
@@ -369,7 +369,7 @@ int radeon_atif_handler(struct radeon_device *rdev,
                return NOTIFY_DONE;
        /* Check pending SBIOS requests */
-        handle = DEVICE_ACPI_HANDLE(&rdev->pdev->dev);
+        handle = ACPI_HANDLE(&rdev->pdev->dev);
        count = radeon_atif_get_sbios_requests(handle, &req);
        if (count <= 0)
@@ -556,7 +556,7 @@ int radeon_acpi_pcie_notify_device_ready(struct radeon_device *rdev)
        struct radeon_atcs *atcs = &rdev->atcs;
        /* Get the device handle */
-        handle = DEVICE_ACPI_HANDLE(&rdev->pdev->dev);
+        handle = ACPI_HANDLE(&rdev->pdev->dev);
        if (!handle)
                return -EINVAL;
@@ -596,7 +596,7 @@ int radeon_acpi_pcie_performance_request(struct radeon_device *rdev,
        u32 retry = 3;
        /* Get the device handle */
-        handle = DEVICE_ACPI_HANDLE(&rdev->pdev->dev);
+        handle = ACPI_HANDLE(&rdev->pdev->dev);
        if (!handle)
                return -EINVAL;
@@ -699,7 +699,7 @@ int radeon_acpi_init(struct radeon_device *rdev)
        int ret;
        /* Get the device handle */
-        handle = DEVICE_ACPI_HANDLE(&rdev->pdev->dev);
+        handle = ACPI_HANDLE(&rdev->pdev->dev);
        /* No need to proceed if we're sure that ATIF is not supported */
        if (!ASIC_IS_AVIVO(rdev) || !rdev->bios || !handle)
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index 6153ec18943a..9d302eaeea15 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -8,8 +8,7 @@
 */
 #include <linux/vga_switcheroo.h>
 #include <linux/slab.h>
-#include <acpi/acpi.h>
+#include <linux/acpi.h>
-#include <acpi/acpi_bus.h>
 #include <linux/pci.h>
 #include "radeon_acpi.h"
@@ -447,7 +446,7 @@ static bool radeon_atpx_pci_probe_handle(struct pci_dev *pdev)
        acpi_handle dhandle, atpx_handle;
        acpi_status status;
-        dhandle = DEVICE_ACPI_HANDLE(&pdev->dev);
+        dhandle = ACPI_HANDLE(&pdev->dev);
        if (!dhandle)
                return false;
@@ -493,7 +492,7 @@ static int radeon_atpx_init(void)
 */
 static int radeon_atpx_get_client_id(struct pci_dev *pdev)
 {
-        if (radeon_atpx_priv.dhandle == DEVICE_ACPI_HANDLE(&pdev->dev))
+        if (radeon_atpx_priv.dhandle == ACPI_HANDLE(&pdev->dev))
                return VGA_SWITCHEROO_IGD;
        else
                return VGA_SWITCHEROO_DIS;
diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c
index c155d6f3fa68..b3633d9a5317 100644
--- a/drivers/gpu/drm/radeon/radeon_bios.c
+++ b/drivers/gpu/drm/radeon/radeon_bios.c
@@ -185,7 +185,7 @@ static bool radeon_atrm_get_bios(struct radeon_device *rdev)
                return false;
        while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) {
-                dhandle = DEVICE_ACPI_HANDLE(&pdev->dev);
+                dhandle = ACPI_HANDLE(&pdev->dev);
                if (!dhandle)
                        continue;
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index ae48d18ee315..5f7e55f4b7f0 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -1008,7 +1008,7 @@ static int i2c_hid_probe(struct i2c_client *client,
        hid->hid_get_raw_report = i2c_hid_get_raw_report;
        hid->hid_output_raw_report = i2c_hid_output_raw_report;
        hid->dev.parent = &client->dev;
-        ACPI_HANDLE_SET(&hid->dev, ACPI_HANDLE(&client->dev));
+        ACPI_COMPANION_SET(&hid->dev, ACPI_COMPANION(&client->dev));
        hid->bus = BUS_I2C;
        hid->version = le16_to_cpu(ihid->hdesc.bcdVersion);
        hid->vendor = le16_to_cpu(ihid->hdesc.wVendorID);
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 5923cfa390c8..d74c0b34248e 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -615,6 +615,22 @@ void i2c_unlock_adapter(struct i2c_adapter *adapter)
 }
 EXPORT_SYMBOL_GPL(i2c_unlock_adapter);
+static void i2c_dev_set_name(struct i2c_adapter *adap,
+                             struct i2c_client *client)
+{
+        struct acpi_device *adev = ACPI_COMPANION(&client->dev);
+        if (adev) {
+                dev_set_name(&client->dev, "i2c-%s", acpi_dev_name(adev));
+                return;
+        }
+        /* For 10-bit clients, add an arbitrary offset to avoid collisions */
+        dev_set_name(&client->dev, "%d-%04x", i2c_adapter_id(adap),
+                     client->addr | ((client->flags & I2C_CLIENT_TEN)
+                                     ? 0xa000 : 0));
+}
 /**
 * i2c_new_device - instantiate an i2c device
 * @adap: the adapter managing the device
@@ -671,12 +687,9 @@ i2c_new_device(struct i2c_adapter *adap, struct i2c_board_info const *info)
        client->dev.bus = &i2c_bus_type;
        client->dev.type = &i2c_client_type;
        client->dev.of_node = info->of_node;
-        ACPI_HANDLE_SET(&client->dev, info->acpi_node.handle);
+        ACPI_COMPANION_SET(&client->dev, info->acpi_node.companion);
-        /* For 10-bit clients, add an arbitrary offset to avoid collisions */
+        i2c_dev_set_name(adap, client);
-        dev_set_name(&client->dev, "%d-%04x", i2c_adapter_id(adap),
-                     client->addr | ((client->flags & I2C_CLIENT_TEN)
-                                     ? 0xa000 : 0));
        status = device_register(&client->dev);
        if (status)
                goto out_err;
@@ -1100,7 +1113,7 @@ static acpi_status acpi_i2c_add_device(acpi_handle handle, u32 level,
                return AE_OK;
        memset(&info, 0, sizeof(info));
-        info.acpi_node.handle = handle;
+        info.acpi_node.companion = adev;
        info.irq = -1;
        INIT_LIST_HEAD(&resource_list);
diff --git a/drivers/ide/ide-acpi.c b/drivers/ide/ide-acpi.c
index 140c8ef50529..d9e1f7ccfe6f 100644
--- a/drivers/ide/ide-acpi.c
+++ b/drivers/ide/ide-acpi.c
@@ -7,6 +7,7 @@
 * Copyright (C) 2006 Hannes Reinecke
 */
+#include <linux/acpi.h>
 #include <linux/ata.h>
 #include <linux/delay.h>
 #include <linux/device.h>
@@ -19,8 +20,6 @@
 #include <linux/dmi.h>
 #include <linux/module.h>
-#include <acpi/acpi_bus.h>
 #define REGS_PER_GTF            7
 struct GTM_buffer {
@@ -128,7 +127,7 @@ static int ide_get_dev_handle(struct device *dev, acpi_handle *handle,
        DEBPRINT("ENTER: pci %02x:%02x.%01x\n", bus, devnum, func);
-        dev_handle = DEVICE_ACPI_HANDLE(dev);
+        dev_handle = ACPI_HANDLE(dev);
        if (!dev_handle) {
                DEBPRINT("no acpi handle for device\n");
                goto err;
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 3226ce98fb18..cbd4e9abc47e 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -1,7 +1,7 @@
 /*
 * intel_idle.c - native hardware idle loop for modern Intel processors
 *
- * Copyright (c) 2010, Intel Corporation.
+ * Copyright (c) 2013, Intel Corporation.
 * Len Brown <len.brown@intel.com>
 *
 * This program is free software; you can redistribute it and/or modify it
@@ -329,6 +329,22 @@ static struct cpuidle_state atom_cstates[] __initdata = {
        {
                .enter = NULL }
 };
+static struct cpuidle_state avn_cstates[CPUIDLE_STATE_MAX] = {
+        {
+                .name = "C1-AVN",
+                .desc = "MWAIT 0x00",
+                .flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
+                .exit_latency = 2,
+                .target_residency = 2,
+                .enter = &intel_idle },
+        {
+                .name = "C6-AVN",
+                .desc = "MWAIT 0x51",
+                .flags = MWAIT2flg(0x58) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+                .exit_latency = 15,
+                .target_residency = 45,
+                .enter = &intel_idle },
+};
 /**
 * intel_idle
@@ -462,6 +478,11 @@ static const struct idle_cpu idle_cpu_hsw = {
        .disable_promotion_to_c1e = true,
 };
+static const struct idle_cpu idle_cpu_avn = {
+        .state_table = avn_cstates,
+        .disable_promotion_to_c1e = true,
+};
 #define ICPU(model, cpu) \
        { X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT, (unsigned long)&cpu }
@@ -483,6 +504,7 @@ static const struct x86_cpu_id intel_idle_ids[] = {
        ICPU(0x3f, idle_cpu_hsw),
        ICPU(0x45, idle_cpu_hsw),
        ICPU(0x46, idle_cpu_hsw),
+        ICPU(0x4D, idle_cpu_avn),
        {}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_idle_ids);
diff --git a/drivers/isdn/isdnloop/isdnloop.c b/drivers/isdn/isdnloop/isdnloop.c
index baf2686aa8eb..02125e6a9109 100644
--- a/drivers/isdn/isdnloop/isdnloop.c
+++ b/drivers/isdn/isdnloop/isdnloop.c
@@ -1083,8 +1083,10 @@ isdnloop_start(isdnloop_card *card, isdnloop_sdef *sdefp)
                        spin_unlock_irqrestore(&card->isdnloop_lock, flags);
                        return -ENOMEM;
                }
-                for (i = 0; i < 3; i++)
+                for (i = 0; i < 3; i++) {
-                        strcpy(card->s0num[i], sdef.num[i]);
+                        strlcpy(card->s0num[i], sdef.num[i],
+                                sizeof(card->s0num[0]));
+                }
                break;
        case ISDN_PTYPE_1TR6:
                if (isdnloop_fake(card, "DRV1.04TC-1TR6-CAPI-CNS-BASIS-29.11.95",
@@ -1097,7 +1099,7 @@ isdnloop_start(isdnloop_card *card, isdnloop_sdef *sdefp)
                        spin_unlock_irqrestore(&card->isdnloop_lock, flags);
                        return -ENOMEM;
                }
-                strcpy(card->s0num[0], sdef.num[0]);
+                strlcpy(card->s0num[0], sdef.num[0], sizeof(card->s0num[0]));
                card->s0num[1][0] = '\0';
                card->s0num[2][0] = '\0';
                break;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 8766eabb0014..b6b7a2866c9e 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -112,7 +112,7 @@ static inline int speed_max(struct mddev *mddev)
 static struct ctl_table_header *raid_table_header;
-static ctl_table raid_table[] = {
+static struct ctl_table raid_table[] = {
        {
                .procname       = "speed_limit_min",
                .data           = &sysctl_speed_limit_min,
@@ -130,7 +130,7 @@ static ctl_table raid_table[] = {
        { }
 };
-static ctl_table raid_dir_table[] = {
+static struct ctl_table raid_dir_table[] = {
        {
                .procname       = "raid",
                .maxlen         = 0,
@@ -140,7 +140,7 @@ static ctl_table raid_dir_table[] = {
        { }
 };
-static ctl_table raid_root_table[] = {
+static struct ctl_table raid_root_table[] = {
        {
                .procname       = "dev",
                .maxlen         = 0,
@@ -562,11 +562,19 @@ static struct mddev * mddev_find(dev_t unit)
        goto retry;
 }
-static inline int mddev_lock(struct mddev * mddev)
+static inline int __must_check mddev_lock(struct mddev * mddev)
 {
        return mutex_lock_interruptible(&mddev->reconfig_mutex);
 }
+/* Sometimes we need to take the lock in a situation where
+ * failure due to interrupts is not acceptable.
+ */
+static inline void mddev_lock_nointr(struct mddev * mddev)
+{
+        mutex_lock(&mddev->reconfig_mutex);
+}
 static inline int mddev_is_locked(struct mddev *mddev)
 {
        return mutex_is_locked(&mddev->reconfig_mutex);
@@ -2978,7 +2986,7 @@ rdev_size_store(struct md_rdev *rdev, const char *buf, size_t len)
                for_each_mddev(mddev, tmp) {
                        struct md_rdev *rdev2;
-                        mddev_lock(mddev);
+                        mddev_lock_nointr(mddev);
                        rdev_for_each(rdev2, mddev)
                                if (rdev->bdev == rdev2->bdev &&
                                    rdev != rdev2 &&
@@ -2994,7 +3002,7 @@ rdev_size_store(struct md_rdev *rdev, const char *buf, size_t len)
                                break;
                        }
                }
-                mddev_lock(my_mddev);
+                mddev_lock_nointr(my_mddev);
                if (overlap) {
                        /* Someone else could have slipped in a size
                         * change here, but doing so is just silly.
@@ -3580,6 +3588,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
                mddev->in_sync = 1;
                del_timer_sync(&mddev->safemode_timer);
        }
+        blk_set_stacking_limits(&mddev->queue->limits);
        pers->run(mddev);
        set_bit(MD_CHANGE_DEVS, &mddev->flags);
        mddev_resume(mddev);
@@ -5258,7 +5267,7 @@ static void __md_stop_writes(struct mddev *mddev)
 void md_stop_writes(struct mddev *mddev)
 {
-        mddev_lock(mddev);
+        mddev_lock_nointr(mddev);
        __md_stop_writes(mddev);
        mddev_unlock(mddev);
 }
@@ -5291,20 +5300,35 @@ EXPORT_SYMBOL_GPL(md_stop);
 static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 {
        int err = 0;
+        int did_freeze = 0;
+        if (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) {
+                did_freeze = 1;
+                set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+                md_wakeup_thread(mddev->thread);
+        }
+        if (mddev->sync_thread) {
+                set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+                /* Thread might be blocked waiting for metadata update
+                 * which will now never happen */
+                wake_up_process(mddev->sync_thread->tsk);
+        }
+        mddev_unlock(mddev);
+        wait_event(resync_wait, mddev->sync_thread == NULL);
+        mddev_lock_nointr(mddev);
        mutex_lock(&mddev->open_mutex);
-        if (atomic_read(&mddev->openers) > !!bdev) {
+        if (atomic_read(&mddev->openers) > !!bdev ||
+            mddev->sync_thread ||
+            (bdev && !test_bit(MD_STILL_CLOSED, &mddev->flags))) {
                printk("md: %s still in use.\n",mdname(mddev));
+                if (did_freeze) {
+                        clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+                        md_wakeup_thread(mddev->thread);
+                }
                err = -EBUSY;
                goto out;
        }
-        if (bdev && !test_bit(MD_STILL_CLOSED, &mddev->flags)) {
-                /* Someone opened the device since we flushed it
-                 * so page cache could be dirty and it is too late
-                 * to flush.  So abort
-                 */
-                mutex_unlock(&mddev->open_mutex);
-                return -EBUSY;
-        }
        if (mddev->pers) {
                __md_stop_writes(mddev);
@@ -5315,7 +5339,7 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
                set_disk_ro(mddev->gendisk, 1);
                clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
                sysfs_notify_dirent_safe(mddev->sysfs_state);
-                err = 0;        
+                err = 0;
        }
 out:
        mutex_unlock(&mddev->open_mutex);
@@ -5331,20 +5355,34 @@ static int do_md_stop(struct mddev * mddev, int mode,
 {
        struct gendisk *disk = mddev->gendisk;
        struct md_rdev *rdev;
+        int did_freeze = 0;
+        if (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) {
+                did_freeze = 1;
+                set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+                md_wakeup_thread(mddev->thread);
+        }
+        if (mddev->sync_thread) {
+                set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+                /* Thread might be blocked waiting for metadata update
+                 * which will now never happen */
+                wake_up_process(mddev->sync_thread->tsk);
+        }
+        mddev_unlock(mddev);
+        wait_event(resync_wait, mddev->sync_thread == NULL);
+        mddev_lock_nointr(mddev);
        mutex_lock(&mddev->open_mutex);
        if (atomic_read(&mddev->openers) > !!bdev ||
-            mddev->sysfs_active) {
+            mddev->sysfs_active ||
+            mddev->sync_thread ||
+            (bdev && !test_bit(MD_STILL_CLOSED, &mddev->flags))) {
                printk("md: %s still in use.\n",mdname(mddev));
                mutex_unlock(&mddev->open_mutex);
-                return -EBUSY;
+                if (did_freeze) {
-        }
+                        clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-        if (bdev && !test_bit(MD_STILL_CLOSED, &mddev->flags)) {
+                        md_wakeup_thread(mddev->thread);
-                /* Someone opened the device since we flushed it
+                }
-                 * so page cache could be dirty and it is too late
-                 * to flush.  So abort
-                 */
-                mutex_unlock(&mddev->open_mutex);
                return -EBUSY;
        }
        if (mddev->pers) {
@@ -6551,7 +6589,7 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
                                wait_event(mddev->sb_wait,
                                           !test_bit(MD_CHANGE_DEVS, &mddev->flags) &&
                                           !test_bit(MD_CHANGE_PENDING, &mddev->flags));
-                                mddev_lock(mddev);
+                                mddev_lock_nointr(mddev);
                        }
                } else {
                        err = -EROFS;
@@ -7361,9 +7399,6 @@ void md_do_sync(struct md_thread *thread)
                mddev->curr_resync = 2;
        try_again:
-                if (kthread_should_stop())
-                        set_bit(MD_RECOVERY_INTR, &mddev->recovery);
                if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
                        goto skip;
                for_each_mddev(mddev2, tmp) {
@@ -7388,7 +7423,7 @@ void md_do_sync(struct md_thread *thread)
                                 * be caught by 'softlockup'
                                 */
                                prepare_to_wait(&resync_wait, &wq, TASK_INTERRUPTIBLE);
-                                if (!kthread_should_stop() &&
+                                if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
                                    mddev2->curr_resync >= mddev->curr_resync) {
                                        printk(KERN_INFO "md: delaying %s of %s"
                                               " until %s has finished (they"
@@ -7464,7 +7499,7 @@ void md_do_sync(struct md_thread *thread)
        last_check = 0;
        if (j>2) {
-                printk(KERN_INFO 
+                printk(KERN_INFO
                       "md: resuming %s of %s from checkpoint.\n",
                       desc, mdname(mddev));
                mddev->curr_resync = j;
@@ -7501,7 +7536,8 @@ void md_do_sync(struct md_thread *thread)
                        sysfs_notify(&mddev->kobj, NULL, "sync_completed");
                }
-                while (j >= mddev->resync_max && !kthread_should_stop()) {
+                while (j >= mddev->resync_max &&
+                       !test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
                        /* As this condition is controlled by user-space,
                         * we can block indefinitely, so use '_interruptible'
                         * to avoid triggering warnings.
@@ -7509,17 +7545,18 @@ void md_do_sync(struct md_thread *thread)
                        flush_signals(current); /* just in case */
                        wait_event_interruptible(mddev->recovery_wait,
                                                 mddev->resync_max > j
-                                                 || kthread_should_stop());
+                                                 || test_bit(MD_RECOVERY_INTR,
+                                                             &mddev->recovery));
                }
-                if (kthread_should_stop())
+                if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
-                        goto interrupted;
+                        break;
                sectors = mddev->pers->sync_request(mddev, j, &skipped,
                                                  currspeed < speed_min(mddev));
                if (sectors == 0) {
                        set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-                        goto out;
+                        break;
                }
                if (!skipped) { /* actual IO requested */
@@ -7556,10 +7593,8 @@ void md_do_sync(struct md_thread *thread)
                        last_mark = next;
                }
+                if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
-                if (kthread_should_stop())
+                        break;
-                        goto interrupted;
                /*
                 * this loop exits only if either when we are slower than
@@ -7582,11 +7617,12 @@ void md_do_sync(struct md_thread *thread)
                        }
                }
        }
-        printk(KERN_INFO "md: %s: %s done.\n",mdname(mddev), desc);
+        printk(KERN_INFO "md: %s: %s %s.\n",mdname(mddev), desc,
+               test_bit(MD_RECOVERY_INTR, &mddev->recovery)
+               ? "interrupted" : "done");
        /*
         * this also signals 'finished resyncing' to md_stop
         */
- out:
        blk_finish_plug(&plug);
        wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active));
@@ -7640,16 +7676,6 @@ void md_do_sync(struct md_thread *thread)
        set_bit(MD_RECOVERY_DONE, &mddev->recovery);
        md_wakeup_thread(mddev->thread);
        return;
- interrupted:
-        /*
-         * got a signal, exit.
-         */
-        printk(KERN_INFO
-               "md: md_do_sync() got signal ... exiting\n");
-        set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-        goto out;
 }
 EXPORT_SYMBOL_GPL(md_do_sync);
@@ -7894,6 +7920,7 @@ void md_reap_sync_thread(struct mddev *mddev)
        /* resync has finished, collect result */
        md_unregister_thread(&mddev->sync_thread);
+        wake_up(&resync_wait);
        if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
            !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
                /* success...*/
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index af6681b19776..1e5a540995e9 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -66,7 +66,8 @@
 */
 static int max_queued_requests = 1024;
-static void allow_barrier(struct r1conf *conf);
+static void allow_barrier(struct r1conf *conf, sector_t start_next_window,
+                          sector_t bi_sector);
 static void lower_barrier(struct r1conf *conf);
 static void * r1bio_pool_alloc(gfp_t gfp_flags, void *data)
@@ -84,10 +85,12 @@ static void r1bio_pool_free(void *r1_bio, void *data)
 }
 #define RESYNC_BLOCK_SIZE (64*1024)
-//#define RESYNC_BLOCK_SIZE PAGE_SIZE
+#define RESYNC_DEPTH 32
 #define RESYNC_SECTORS (RESYNC_BLOCK_SIZE >> 9)
 #define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)
-#define RESYNC_WINDOW (2048*1024)
+#define RESYNC_WINDOW (RESYNC_BLOCK_SIZE * RESYNC_DEPTH)
+#define RESYNC_WINDOW_SECTORS (RESYNC_WINDOW >> 9)
+#define NEXT_NORMALIO_DISTANCE (3 * RESYNC_WINDOW_SECTORS)
 static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 {
@@ -225,6 +228,8 @@ static void call_bio_endio(struct r1bio *r1_bio)
        struct bio *bio = r1_bio->master_bio;
        int done;
        struct r1conf *conf = r1_bio->mddev->private;
+        sector_t start_next_window = r1_bio->start_next_window;
+        sector_t bi_sector = bio->bi_sector;
        if (bio->bi_phys_segments) {
                unsigned long flags;
@@ -232,6 +237,11 @@ static void call_bio_endio(struct r1bio *r1_bio)
                bio->bi_phys_segments--;
                done = (bio->bi_phys_segments == 0);
                spin_unlock_irqrestore(&conf->device_lock, flags);
+                /*
+                 * make_request() might be waiting for
+                 * bi_phys_segments to decrease
+                 */
+                wake_up(&conf->wait_barrier);
        } else
                done = 1;
@@ -243,7 +253,7 @@ static void call_bio_endio(struct r1bio *r1_bio)
                 * Wake up any possible resync thread that waits for the device
                 * to go idle.
                 */
-                allow_barrier(conf);
+                allow_barrier(conf, start_next_window, bi_sector);
        }
 }
@@ -814,8 +824,6 @@ static void flush_pending_writes(struct r1conf *conf)
 *    there is no normal IO happeing.  It must arrange to call
 *    lower_barrier when the particular background IO completes.
 */
-#define RESYNC_DEPTH 32
 static void raise_barrier(struct r1conf *conf)
 {
        spin_lock_irq(&conf->resync_lock);
@@ -827,9 +835,19 @@ static void raise_barrier(struct r1conf *conf)
        /* block any new IO from starting */
        conf->barrier++;
-        /* Now wait for all pending IO to complete */
+        /* For these conditions we must wait:
+         * A: while the array is in frozen state
+         * B: while barrier >= RESYNC_DEPTH, meaning resync reach
+         *    the max count which allowed.
+         * C: next_resync + RESYNC_SECTORS > start_next_window, meaning
+         *    next resync will reach to the window which normal bios are
+         *    handling.
+         */
        wait_event_lock_irq(conf->wait_barrier,
-                            !conf->nr_pending && conf->barrier < RESYNC_DEPTH,
+                            !conf->array_frozen &&
+                            conf->barrier < RESYNC_DEPTH &&
+                            (conf->start_next_window >=
+                             conf->next_resync + RESYNC_SECTORS),
                            conf->resync_lock);
        spin_unlock_irq(&conf->resync_lock);
@@ -845,10 +863,33 @@ static void lower_barrier(struct r1conf *conf)
        wake_up(&conf->wait_barrier);
 }
-static void wait_barrier(struct r1conf *conf)
+static bool need_to_wait_for_sync(struct r1conf *conf, struct bio *bio)
 {
+        bool wait = false;
+        if (conf->array_frozen || !bio)
+                wait = true;
+        else if (conf->barrier && bio_data_dir(bio) == WRITE) {
+                if (conf->next_resync < RESYNC_WINDOW_SECTORS)
+                        wait = true;
+                else if ((conf->next_resync - RESYNC_WINDOW_SECTORS
+                                >= bio_end_sector(bio)) ||
+                         (conf->next_resync + NEXT_NORMALIO_DISTANCE
+                                <= bio->bi_sector))
+                        wait = false;
+                else
+                        wait = true;
+        }
+        return wait;
+}
+static sector_t wait_barrier(struct r1conf *conf, struct bio *bio)
+{
+        sector_t sector = 0;
        spin_lock_irq(&conf->resync_lock);
-        if (conf->barrier) {
+        if (need_to_wait_for_sync(conf, bio)) {
                conf->nr_waiting++;
                /* Wait for the barrier to drop.
                 * However if there are already pending
@@ -860,22 +901,67 @@ static void wait_barrier(struct r1conf *conf)
                 * count down.
                 */
                wait_event_lock_irq(conf->wait_barrier,
-                                    !conf->barrier ||
+                                    !conf->array_frozen &&
-                                    (conf->nr_pending &&
+                                    (!conf->barrier ||
+                                    ((conf->start_next_window <
+                                      conf->next_resync + RESYNC_SECTORS) &&
                                     current->bio_list &&
-                                     !bio_list_empty(current->bio_list)),
+                                     !bio_list_empty(current->bio_list))),
                                    conf->resync_lock);
                conf->nr_waiting--;
        }
+        if (bio && bio_data_dir(bio) == WRITE) {
+                if (conf->next_resync + NEXT_NORMALIO_DISTANCE
+                    <= bio->bi_sector) {
+                        if (conf->start_next_window == MaxSector)
+                                conf->start_next_window =
+                                        conf->next_resync +
+                                        NEXT_NORMALIO_DISTANCE;
+                        if ((conf->start_next_window + NEXT_NORMALIO_DISTANCE)
+                            <= bio->bi_sector)
+                                conf->next_window_requests++;
+                        else
+                                conf->current_window_requests++;
+                }
+                if (bio->bi_sector >= conf->start_next_window)
+                        sector = conf->start_next_window;
+        }
        conf->nr_pending++;
        spin_unlock_irq(&conf->resync_lock);
+        return sector;
 }
-static void allow_barrier(struct r1conf *conf)
+static void allow_barrier(struct r1conf *conf, sector_t start_next_window,
+                          sector_t bi_sector)
 {
        unsigned long flags;
        spin_lock_irqsave(&conf->resync_lock, flags);
        conf->nr_pending--;
+        if (start_next_window) {
+                if (start_next_window == conf->start_next_window) {
+                        if (conf->start_next_window + NEXT_NORMALIO_DISTANCE
+                            <= bi_sector)
+                                conf->next_window_requests--;
+                        else
+                                conf->current_window_requests--;
+                } else
+                        conf->current_window_requests--;
+                if (!conf->current_window_requests) {
+                        if (conf->next_window_requests) {
+                                conf->current_window_requests =
+                                        conf->next_window_requests;
+                                conf->next_window_requests = 0;
+                                conf->start_next_window +=
+                                        NEXT_NORMALIO_DISTANCE;
+                        } else
+                                conf->start_next_window = MaxSector;
+                }
+        }
        spin_unlock_irqrestore(&conf->resync_lock, flags);
        wake_up(&conf->wait_barrier);
 }
@@ -884,8 +970,7 @@ static void freeze_array(struct r1conf *conf, int extra)
 {
        /* stop syncio and normal IO and wait for everything to
         * go quite.
-         * We increment barrier and nr_waiting, and then
+         * We wait until nr_pending match nr_queued+extra
-         * wait until nr_pending match nr_queued+extra
         * This is called in the context of one normal IO request
         * that has failed. Thus any sync request that might be pending
         * will be blocked by nr_pending, and we need to wait for
@@ -895,8 +980,7 @@ static void freeze_array(struct r1conf *conf, int extra)
         * we continue.
         */
        spin_lock_irq(&conf->resync_lock);
-        conf->barrier++;
+        conf->array_frozen = 1;
-        conf->nr_waiting++;
        wait_event_lock_irq_cmd(conf->wait_barrier,
                                conf->nr_pending == conf->nr_queued+extra,
                                conf->resync_lock,
@@ -907,8 +991,7 @@ static void unfreeze_array(struct r1conf *conf)
 {
        /* reverse the effect of the freeze */
        spin_lock_irq(&conf->resync_lock);
-        conf->barrier--;
+        conf->array_frozen = 0;
-        conf->nr_waiting--;
        wake_up(&conf->wait_barrier);
        spin_unlock_irq(&conf->resync_lock);
 }
@@ -1013,6 +1096,7 @@ static void make_request(struct mddev *mddev, struct bio * bio)
        int first_clone;
        int sectors_handled;
        int max_sectors;
+        sector_t start_next_window;
        /*
         * Register the new request and wait if the reconstruction
@@ -1042,7 +1126,7 @@ static void make_request(struct mddev *mddev, struct bio * bio)
                finish_wait(&conf->wait_barrier, &w);
        }
-        wait_barrier(conf);
+        start_next_window = wait_barrier(conf, bio);
        bitmap = mddev->bitmap;
@@ -1163,6 +1247,7 @@ read_again:
        disks = conf->raid_disks * 2;
 retry_write:
+        r1_bio->start_next_window = start_next_window;
        blocked_rdev = NULL;
        rcu_read_lock();
        max_sectors = r1_bio->sectors;
@@ -1231,14 +1316,24 @@ read_again:
        if (unlikely(blocked_rdev)) {
                /* Wait for this device to become unblocked */
                int j;
+                sector_t old = start_next_window;
                for (j = 0; j < i; j++)
                        if (r1_bio->bios[j])
                                rdev_dec_pending(conf->mirrors[j].rdev, mddev);
                r1_bio->state = 0;
-                allow_barrier(conf);
+                allow_barrier(conf, start_next_window, bio->bi_sector);
                md_wait_for_blocked_rdev(blocked_rdev, mddev);
-                wait_barrier(conf);
+                start_next_window = wait_barrier(conf, bio);
+                /*
+                 * We must make sure the multi r1bios of bio have
+                 * the same value of bi_phys_segments
+                 */
+                if (bio->bi_phys_segments && old &&
+                    old != start_next_window)
+                        /* Wait for the former r1bio(s) to complete */
+                        wait_event(conf->wait_barrier,
+                                   bio->bi_phys_segments == 1);
                goto retry_write;
        }
@@ -1438,11 +1533,14 @@ static void print_conf(struct r1conf *conf)
 static void close_sync(struct r1conf *conf)
 {
-        wait_barrier(conf);
+        wait_barrier(conf, NULL);
-        allow_barrier(conf);
+        allow_barrier(conf, 0, 0);
        mempool_destroy(conf->r1buf_pool);
        conf->r1buf_pool = NULL;
+        conf->next_resync = 0;
+        conf->start_next_window = MaxSector;
 }
 static int raid1_spare_active(struct mddev *mddev)
@@ -2714,6 +2812,9 @@ static struct r1conf *setup_conf(struct mddev *mddev)
        conf->pending_count = 0;
        conf->recovery_disabled = mddev->recovery_disabled - 1;
+        conf->start_next_window = MaxSector;
+        conf->current_window_requests = conf->next_window_requests = 0;
        err = -EIO;
        for (i = 0; i < conf->raid_disks * 2; i++) {
@@ -2871,8 +2972,8 @@ static int stop(struct mddev *mddev)
                           atomic_read(&bitmap->behind_writes) == 0);
        }
-        raise_barrier(conf);
+        freeze_array(conf, 0);
-        lower_barrier(conf);
+        unfreeze_array(conf);
        md_unregister_thread(&mddev->thread);
        if (conf->r1bio_pool)
@@ -3031,10 +3132,10 @@ static void raid1_quiesce(struct mddev *mddev, int state)
                wake_up(&conf->wait_barrier);
                break;
        case 1:
-                raise_barrier(conf);
+                freeze_array(conf, 0);
                break;
        case 0:
-                lower_barrier(conf);
+                unfreeze_array(conf);
                break;
        }
 }
@@ -3051,7 +3152,8 @@ static void *raid1_takeover(struct mddev *mddev)
                mddev->new_chunk_sectors = 0;
                conf = setup_conf(mddev);
                if (!IS_ERR(conf))
-                        conf->barrier = 1;
+                        /* Array must appear to be quiesced */
+                        conf->array_frozen = 1;
                return conf;
        }
        return ERR_PTR(-EINVAL);
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
index 0ff3715fb7eb..9bebca7bff2f 100644
--- a/drivers/md/raid1.h
+++ b/drivers/md/raid1.h
@@ -41,6 +41,19 @@ struct r1conf {
         */
        sector_t                next_resync;
+        /* When raid1 starts resync, we divide array into four partitions
+         * |---------|--------------|---------------------|-------------|
+         *        next_resync   start_next_window       end_window
+         * start_next_window = next_resync + NEXT_NORMALIO_DISTANCE
+         * end_window = start_next_window + NEXT_NORMALIO_DISTANCE
+         * current_window_requests means the count of normalIO between
+         *   start_next_window and end_window.
+         * next_window_requests means the count of normalIO after end_window.
+         * */
+        sector_t                start_next_window;
+        int                     current_window_requests;
+        int                     next_window_requests;
        spinlock_t              device_lock;
        /* list of 'struct r1bio' that need to be processed by raid1d,
@@ -65,6 +78,7 @@ struct r1conf {
        int                     nr_waiting;
        int                     nr_queued;
        int                     barrier;
+        int                     array_frozen;
        /* Set to 1 if a full sync is needed, (fresh device added).
         * Cleared when a sync completes.
@@ -111,6 +125,7 @@ struct r1bio {
                                                 * in this BehindIO request
                                                 */
        sector_t                sector;
+        sector_t                start_next_window;
        int                     sectors;
        unsigned long           state;
        struct mddev            *mddev;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 7c3508abb5e1..c504e8389e69 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -4384,7 +4384,11 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
                set_bit(MD_CHANGE_DEVS, &mddev->flags);
                md_wakeup_thread(mddev->thread);
                wait_event(mddev->sb_wait, mddev->flags == 0 ||
-                           kthread_should_stop());
+                           test_bit(MD_RECOVERY_INTR, &mddev->recovery));
+                if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
+                        allow_barrier(conf);
+                        return sectors_done;
+                }
                conf->reshape_safe = mddev->reshape_position;
                allow_barrier(conf);
        }
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 7f0e17a27aeb..47da0af6322b 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -85,6 +85,42 @@ static inline struct hlist_head *stripe_hash(struct r5conf *conf, sector_t sect)
        return &conf->stripe_hashtbl[hash];
 }
+static inline int stripe_hash_locks_hash(sector_t sect)
+{
+        return (sect >> STRIPE_SHIFT) & STRIPE_HASH_LOCKS_MASK;
+}
+static inline void lock_device_hash_lock(struct r5conf *conf, int hash)
+{
+        spin_lock_irq(conf->hash_locks + hash);
+        spin_lock(&conf->device_lock);
+}
+static inline void unlock_device_hash_lock(struct r5conf *conf, int hash)
+{
+        spin_unlock(&conf->device_lock);
+        spin_unlock_irq(conf->hash_locks + hash);
+}
+static inline void lock_all_device_hash_locks_irq(struct r5conf *conf)
+{
+        int i;
+        local_irq_disable();
+        spin_lock(conf->hash_locks);
+        for (i = 1; i < NR_STRIPE_HASH_LOCKS; i++)
+                spin_lock_nest_lock(conf->hash_locks + i, conf->hash_locks);
+        spin_lock(&conf->device_lock);
+}
+static inline void unlock_all_device_hash_locks_irq(struct r5conf *conf)
+{
+        int i;
+        spin_unlock(&conf->device_lock);
+        for (i = NR_STRIPE_HASH_LOCKS; i; i--)
+                spin_unlock(conf->hash_locks + i - 1);
+        local_irq_enable();
+}
 /* bio's attached to a stripe+device for I/O are linked together in bi_sector
 * order without overlap.  There may be several bio's per stripe+device, and
 * a bio could span several devices.
@@ -249,7 +285,8 @@ static void raid5_wakeup_stripe_thread(struct stripe_head *sh)
        }
 }
-static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh)
+static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
+                              struct list_head *temp_inactive_list)
 {
        BUG_ON(!list_empty(&sh->lru));
        BUG_ON(atomic_read(&conf->active_stripes)==0);
@@ -278,23 +315,68 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh)
                            < IO_THRESHOLD)
                                md_wakeup_thread(conf->mddev->thread);
                atomic_dec(&conf->active_stripes);
-                if (!test_bit(STRIPE_EXPANDING, &sh->state)) {
+                if (!test_bit(STRIPE_EXPANDING, &sh->state))
-                        list_add_tail(&sh->lru, &conf->inactive_list);
+                        list_add_tail(&sh->lru, temp_inactive_list);
-                        wake_up(&conf->wait_for_stripe);
-                        if (conf->retry_read_aligned)
-                                md_wakeup_thread(conf->mddev->thread);
-                }
        }
 }
-static void __release_stripe(struct r5conf *conf, struct stripe_head *sh)
+static void __release_stripe(struct r5conf *conf, struct stripe_head *sh,
+                             struct list_head *temp_inactive_list)
 {
        if (atomic_dec_and_test(&sh->count))
-                do_release_stripe(conf, sh);
+                do_release_stripe(conf, sh, temp_inactive_list);
+}
+/*
+ * @hash could be NR_STRIPE_HASH_LOCKS, then we have a list of inactive_list
+ *
+ * Be careful: Only one task can add/delete stripes from temp_inactive_list at
+ * given time. Adding stripes only takes device lock, while deleting stripes
+ * only takes hash lock.
+ */
+static void release_inactive_stripe_list(struct r5conf *conf,
+                                         struct list_head *temp_inactive_list,
+                                         int hash)
+{
+        int size;
+        bool do_wakeup = false;
+        unsigned long flags;
+        if (hash == NR_STRIPE_HASH_LOCKS) {
+                size = NR_STRIPE_HASH_LOCKS;
+                hash = NR_STRIPE_HASH_LOCKS - 1;
+        } else
+                size = 1;
+        while (size) {
+                struct list_head *list = &temp_inactive_list[size - 1];
+                /*
+                 * We don't hold any lock here yet, get_active_stripe() might
+                 * remove stripes from the list
+                 */
+                if (!list_empty_careful(list)) {
+                        spin_lock_irqsave(conf->hash_locks + hash, flags);
+                        if (list_empty(conf->inactive_list + hash) &&
+                            !list_empty(list))
+                                atomic_dec(&conf->empty_inactive_list_nr);
+                        list_splice_tail_init(list, conf->inactive_list + hash);
+                        do_wakeup = true;
+                        spin_unlock_irqrestore(conf->hash_locks + hash, flags);
+                }
+                size--;
+                hash--;
+        }
+        if (do_wakeup) {
+                wake_up(&conf->wait_for_stripe);
+                if (conf->retry_read_aligned)
+                        md_wakeup_thread(conf->mddev->thread);
+        }
 }
 /* should hold conf->device_lock already */
-static int release_stripe_list(struct r5conf *conf)
+static int release_stripe_list(struct r5conf *conf,
+                               struct list_head *temp_inactive_list)
 {
        struct stripe_head *sh;
        int count = 0;
@@ -303,6 +385,8 @@ static int release_stripe_list(struct r5conf *conf)
        head = llist_del_all(&conf->released_stripes);
        head = llist_reverse_order(head);
        while (head) {
+                int hash;
                sh = llist_entry(head, struct stripe_head, release_list);
                head = llist_next(head);
                /* sh could be readded after STRIPE_ON_RELEASE_LIST is cleard */
@@ -313,7 +397,8 @@ static int release_stripe_list(struct r5conf *conf)
                 * again, the count is always > 1. This is true for
                 * STRIPE_ON_UNPLUG_LIST bit too.
                 */
-                __release_stripe(conf, sh);
+                hash = sh->hash_lock_index;
+                __release_stripe(conf, sh, &temp_inactive_list[hash]);
                count++;
        }
@@ -324,9 +409,12 @@ static void release_stripe(struct stripe_head *sh)
 {
        struct r5conf *conf = sh->raid_conf;
        unsigned long flags;
+        struct list_head list;
+        int hash;
        bool wakeup;
-        if (test_and_set_bit(STRIPE_ON_RELEASE_LIST, &sh->state))
+        if (unlikely(!conf->mddev->thread) ||
+                test_and_set_bit(STRIPE_ON_RELEASE_LIST, &sh->state))
                goto slow_path;
        wakeup = llist_add(&sh->release_list, &conf->released_stripes);
        if (wakeup)
@@ -336,8 +424,11 @@ slow_path:
        local_irq_save(flags);
        /* we are ok here if STRIPE_ON_RELEASE_LIST is set or not */
        if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) {
-                do_release_stripe(conf, sh);
+                INIT_LIST_HEAD(&list);
+                hash = sh->hash_lock_index;
+                do_release_stripe(conf, sh, &list);
                spin_unlock(&conf->device_lock);
+                release_inactive_stripe_list(conf, &list, hash);
        }
        local_irq_restore(flags);
 }
@@ -362,18 +453,21 @@ static inline void insert_hash(struct r5conf *conf, struct stripe_head *sh)
 /* find an idle stripe, make sure it is unhashed, and return it. */
-static struct stripe_head *get_free_stripe(struct r5conf *conf)
+static struct stripe_head *get_free_stripe(struct r5conf *conf, int hash)
 {
        struct stripe_head *sh = NULL;
        struct list_head *first;
-        if (list_empty(&conf->inactive_list))
+        if (list_empty(conf->inactive_list + hash))
                goto out;
-        first = conf->inactive_list.next;
+        first = (conf->inactive_list + hash)->next;
        sh = list_entry(first, struct stripe_head, lru);
        list_del_init(first);
        remove_hash(sh);
        atomic_inc(&conf->active_stripes);
+        BUG_ON(hash != sh->hash_lock_index);
+        if (list_empty(conf->inactive_list + hash))
+                atomic_inc(&conf->empty_inactive_list_nr);
 out:
        return sh;
 }
@@ -416,7 +510,7 @@ static void stripe_set_idx(sector_t stripe, struct r5conf *conf, int previous,
 static void init_stripe(struct stripe_head *sh, sector_t sector, int previous)
 {
        struct r5conf *conf = sh->raid_conf;
-        int i;
+        int i, seq;
        BUG_ON(atomic_read(&sh->count) != 0);
        BUG_ON(test_bit(STRIPE_HANDLE, &sh->state));
@@ -426,7 +520,8 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int previous)
                (unsigned long long)sh->sector);
        remove_hash(sh);
+retry:
+        seq = read_seqcount_begin(&conf->gen_lock);
        sh->generation = conf->generation - previous;
        sh->disks = previous ? conf->previous_raid_disks : conf->raid_disks;
        sh->sector = sector;
@@ -448,6 +543,8 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int previous)
                dev->flags = 0;
                raid5_build_block(sh, i, previous);
        }
+        if (read_seqcount_retry(&conf->gen_lock, seq))
+                goto retry;
        insert_hash(conf, sh);
        sh->cpu = smp_processor_id();
 }
@@ -552,29 +649,31 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
                  int previous, int noblock, int noquiesce)
 {
        struct stripe_head *sh;
+        int hash = stripe_hash_locks_hash(sector);
        pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector);
-        spin_lock_irq(&conf->device_lock);
+        spin_lock_irq(conf->hash_locks + hash);
        do {
                wait_event_lock_irq(conf->wait_for_stripe,
                                    conf->quiesce == 0 || noquiesce,
-                                    conf->device_lock);
+                                    *(conf->hash_locks + hash));
                sh = __find_stripe(conf, sector, conf->generation - previous);
                if (!sh) {
                        if (!conf->inactive_blocked)
-                                sh = get_free_stripe(conf);
+                                sh = get_free_stripe(conf, hash);
                        if (noblock && sh == NULL)
                                break;
                        if (!sh) {
                                conf->inactive_blocked = 1;
-                                wait_event_lock_irq(conf->wait_for_stripe,
+                                wait_event_lock_irq(
-                                                    !list_empty(&conf->inactive_list) &&
+                                        conf->wait_for_stripe,
-                                                    (atomic_read(&conf->active_stripes)
+                                        !list_empty(conf->inactive_list + hash) &&
-                                                     < (conf->max_nr_stripes *3/4)
+                                        (atomic_read(&conf->active_stripes)
-                                                     || !conf->inactive_blocked),
+                                         < (conf->max_nr_stripes * 3 / 4)
-                                                    conf->device_lock);
+                                         || !conf->inactive_blocked),
+                                        *(conf->hash_locks + hash));
                                conf->inactive_blocked = 0;
                        } else
                                init_stripe(sh, sector, previous);
@@ -585,9 +684,11 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
                                    && !test_bit(STRIPE_ON_UNPLUG_LIST, &sh->state)
                                    && !test_bit(STRIPE_ON_RELEASE_LIST, &sh->state));
                        } else {
+                                spin_lock(&conf->device_lock);
                                if (!test_bit(STRIPE_HANDLE, &sh->state))
                                        atomic_inc(&conf->active_stripes);
                                if (list_empty(&sh->lru) &&
+                                    !test_bit(STRIPE_ON_RELEASE_LIST, &sh->state) &&
                                    !test_bit(STRIPE_EXPANDING, &sh->state))
                                        BUG();
                                list_del_init(&sh->lru);
@@ -595,6 +696,7 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
                                        sh->group->stripes_cnt--;
                                        sh->group = NULL;
                                }
+                                spin_unlock(&conf->device_lock);
                        }
                }
        } while (sh == NULL);
@@ -602,7 +704,7 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
        if (sh)
                atomic_inc(&sh->count);
-        spin_unlock_irq(&conf->device_lock);
+        spin_unlock_irq(conf->hash_locks + hash);
        return sh;
 }
@@ -758,7 +860,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
                                bi->bi_sector = (sh->sector
                                                 + rdev->data_offset);
                        if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
-                                bi->bi_rw |= REQ_FLUSH;
+                                bi->bi_rw |= REQ_NOMERGE;
                        bi->bi_vcnt = 1;
                        bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
@@ -1582,7 +1684,7 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
        put_cpu();
 }
-static int grow_one_stripe(struct r5conf *conf)
+static int grow_one_stripe(struct r5conf *conf, int hash)
 {
        struct stripe_head *sh;
        sh = kmem_cache_zalloc(conf->slab_cache, GFP_KERNEL);
@@ -1598,6 +1700,7 @@ static int grow_one_stripe(struct r5conf *conf)
                kmem_cache_free(conf->slab_cache, sh);
                return 0;
        }
+        sh->hash_lock_index = hash;
        /* we just created an active stripe so... */
        atomic_set(&sh->count, 1);
        atomic_inc(&conf->active_stripes);
@@ -1610,6 +1713,7 @@ static int grow_stripes(struct r5conf *conf, int num)
 {
        struct kmem_cache *sc;
        int devs = max(conf->raid_disks, conf->previous_raid_disks);
+        int hash;
        if (conf->mddev->gendisk)
                sprintf(conf->cache_name[0],
@@ -1627,9 +1731,13 @@ static int grow_stripes(struct r5conf *conf, int num)
                return 1;
        conf->slab_cache = sc;
        conf->pool_size = devs;
-        while (num--)
+        hash = conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS;
-                if (!grow_one_stripe(conf))
+        while (num--) {
+                if (!grow_one_stripe(conf, hash))
                        return 1;
+                conf->max_nr_stripes++;
+                hash = (hash + 1) % NR_STRIPE_HASH_LOCKS;
+        }
        return 0;
 }
@@ -1687,6 +1795,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
        int err;
        struct kmem_cache *sc;
        int i;
+        int hash, cnt;
        if (newsize <= conf->pool_size)
                return 0; /* never bother to shrink */
@@ -1726,19 +1835,29 @@ static int resize_stripes(struct r5conf *conf, int newsize)
         * OK, we have enough stripes, start collecting inactive
         * stripes and copying them over
         */
+        hash = 0;
+        cnt = 0;
        list_for_each_entry(nsh, &newstripes, lru) {
-                spin_lock_irq(&conf->device_lock);
+                lock_device_hash_lock(conf, hash);
-                wait_event_lock_irq(conf->wait_for_stripe,
+                wait_event_cmd(conf->wait_for_stripe,
-                                    !list_empty(&conf->inactive_list),
+                                    !list_empty(conf->inactive_list + hash),
-                                    conf->device_lock);
+                                    unlock_device_hash_lock(conf, hash),
-                osh = get_free_stripe(conf);
+                                    lock_device_hash_lock(conf, hash));
-                spin_unlock_irq(&conf->device_lock);
+                osh = get_free_stripe(conf, hash);
+                unlock_device_hash_lock(conf, hash);
                atomic_set(&nsh->count, 1);
                for(i=0; i<conf->pool_size; i++)
                        nsh->dev[i].page = osh->dev[i].page;
                for( ; i<newsize; i++)
                        nsh->dev[i].page = NULL;
+                nsh->hash_lock_index = hash;
                kmem_cache_free(conf->slab_cache, osh);
+                cnt++;
+                if (cnt >= conf->max_nr_stripes / NR_STRIPE_HASH_LOCKS +
+                    !!((conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS) > hash)) {
+                        hash++;
+                        cnt = 0;
+                }
        }
        kmem_cache_destroy(conf->slab_cache);
@@ -1797,13 +1916,13 @@ static int resize_stripes(struct r5conf *conf, int newsize)
        return err;
 }
-static int drop_one_stripe(struct r5conf *conf)
+static int drop_one_stripe(struct r5conf *conf, int hash)
 {
        struct stripe_head *sh;
-        spin_lock_irq(&conf->device_lock);
+        spin_lock_irq(conf->hash_locks + hash);
-        sh = get_free_stripe(conf);
+        sh = get_free_stripe(conf, hash);
-        spin_unlock_irq(&conf->device_lock);
+        spin_unlock_irq(conf->hash_locks + hash);
        if (!sh)
                return 0;
        BUG_ON(atomic_read(&sh->count));
@@ -1815,8 +1934,10 @@ static int drop_one_stripe(struct r5conf *conf)
 static void shrink_stripes(struct r5conf *conf)
 {
-        while (drop_one_stripe(conf))
+        int hash;
-                ;
+        for (hash = 0; hash < NR_STRIPE_HASH_LOCKS; hash++)
+                while (drop_one_stripe(conf, hash))
+                        ;
        if (conf->slab_cache)
                kmem_cache_destroy(conf->slab_cache);
@@ -1921,6 +2042,9 @@ static void raid5_end_read_request(struct bio * bi, int error)
                               mdname(conf->mddev), bdn);
                else
                        retry = 1;
+                if (set_bad && test_bit(In_sync, &rdev->flags)
+                    && !test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
+                        retry = 1;
                if (retry)
                        if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) {
                                set_bit(R5_ReadError, &sh->dev[i].flags);
@@ -3900,7 +4024,8 @@ static void raid5_activate_delayed(struct r5conf *conf)
        }
 }
-static void activate_bit_delay(struct r5conf *conf)
+static void activate_bit_delay(struct r5conf *conf,
+        struct list_head *temp_inactive_list)
 {
        /* device_lock is held */
        struct list_head head;
@@ -3908,9 +4033,11 @@ static void activate_bit_delay(struct r5conf *conf)
        list_del_init(&conf->bitmap_list);
        while (!list_empty(&head)) {
                struct stripe_head *sh = list_entry(head.next, struct stripe_head, lru);
+                int hash;
                list_del_init(&sh->lru);
                atomic_inc(&sh->count);
-                __release_stripe(conf, sh);
+                hash = sh->hash_lock_index;
+                __release_stripe(conf, sh, &temp_inactive_list[hash]);
        }
 }
@@ -3926,7 +4053,7 @@ int md_raid5_congested(struct mddev *mddev, int bits)
                return 1;
        if (conf->quiesce)
                return 1;
-        if (list_empty_careful(&conf->inactive_list))
+        if (atomic_read(&conf->empty_inactive_list_nr))
                return 1;
        return 0;
@@ -4256,6 +4383,7 @@ static struct stripe_head *__get_priority_stripe(struct r5conf *conf, int group)
 struct raid5_plug_cb {
        struct blk_plug_cb      cb;
        struct list_head        list;
+        struct list_head        temp_inactive_list[NR_STRIPE_HASH_LOCKS];
 };
 static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule)
@@ -4266,6 +4394,7 @@ static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule)
        struct mddev *mddev = cb->cb.data;
        struct r5conf *conf = mddev->private;
        int cnt = 0;
+        int hash;
        if (cb->list.next && !list_empty(&cb->list)) {
                spin_lock_irq(&conf->device_lock);
@@ -4283,11 +4412,14 @@ static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule)
                         * STRIPE_ON_RELEASE_LIST could be set here. In that
                         * case, the count is always > 1 here
                         */
-                        __release_stripe(conf, sh);
+                        hash = sh->hash_lock_index;
+                        __release_stripe(conf, sh, &cb->temp_inactive_list[hash]);
                        cnt++;
                }
                spin_unlock_irq(&conf->device_lock);
        }
+        release_inactive_stripe_list(conf, cb->temp_inactive_list,
+                                     NR_STRIPE_HASH_LOCKS);
        if (mddev->queue)
                trace_block_unplug(mddev->queue, cnt, !from_schedule);
        kfree(cb);
@@ -4308,8 +4440,12 @@ static void release_stripe_plug(struct mddev *mddev,
        cb = container_of(blk_cb, struct raid5_plug_cb, cb);
-        if (cb->list.next == NULL)
+        if (cb->list.next == NULL) {
+                int i;
                INIT_LIST_HEAD(&cb->list);
+                for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++)
+                        INIT_LIST_HEAD(cb->temp_inactive_list + i);
+        }
        if (!test_and_set_bit(STRIPE_ON_UNPLUG_LIST, &sh->state))
                list_add_tail(&sh->lru, &cb->list);
@@ -4692,14 +4828,19 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
            time_after(jiffies, conf->reshape_checkpoint + 10*HZ)) {
                /* Cannot proceed until we've updated the superblock... */
                wait_event(conf->wait_for_overlap,
-                           atomic_read(&conf->reshape_stripes)==0);
+                           atomic_read(&conf->reshape_stripes)==0
+                           || test_bit(MD_RECOVERY_INTR, &mddev->recovery));
+                if (atomic_read(&conf->reshape_stripes) != 0)
+                        return 0;
                mddev->reshape_position = conf->reshape_progress;
                mddev->curr_resync_completed = sector_nr;
                conf->reshape_checkpoint = jiffies;
                set_bit(MD_CHANGE_DEVS, &mddev->flags);
                md_wakeup_thread(mddev->thread);
                wait_event(mddev->sb_wait, mddev->flags == 0 ||
-                           kthread_should_stop());
+                           test_bit(MD_RECOVERY_INTR, &mddev->recovery));
+                if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
+                        return 0;
                spin_lock_irq(&conf->device_lock);
                conf->reshape_safe = mddev->reshape_position;
                spin_unlock_irq(&conf->device_lock);
@@ -4782,7 +4923,10 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
            >= mddev->resync_max - mddev->curr_resync_completed) {
                /* Cannot proceed until we've updated the superblock... */
                wait_event(conf->wait_for_overlap,
-                           atomic_read(&conf->reshape_stripes) == 0);
+                           atomic_read(&conf->reshape_stripes) == 0
+                           || test_bit(MD_RECOVERY_INTR, &mddev->recovery));
+                if (atomic_read(&conf->reshape_stripes) != 0)
+                        goto ret;
                mddev->reshape_position = conf->reshape_progress;
                mddev->curr_resync_completed = sector_nr;
                conf->reshape_checkpoint = jiffies;
@@ -4790,13 +4934,16 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
                md_wakeup_thread(mddev->thread);
                wait_event(mddev->sb_wait,
                           !test_bit(MD_CHANGE_DEVS, &mddev->flags)
-                           || kthread_should_stop());
+                           || test_bit(MD_RECOVERY_INTR, &mddev->recovery));
+                if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
+                        goto ret;
                spin_lock_irq(&conf->device_lock);
                conf->reshape_safe = mddev->reshape_position;
                spin_unlock_irq(&conf->device_lock);
                wake_up(&conf->wait_for_overlap);
                sysfs_notify(&mddev->kobj, NULL, "sync_completed");
        }
+ret:
        return reshape_sectors;
 }
@@ -4954,27 +5101,45 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 }
 static int handle_active_stripes(struct r5conf *conf, int group,
-                                 struct r5worker *worker)
+                                 struct r5worker *worker,
+                                 struct list_head *temp_inactive_list)
 {
        struct stripe_head *batch[MAX_STRIPE_BATCH], *sh;
-        int i, batch_size = 0;
+        int i, batch_size = 0, hash;
+        bool release_inactive = false;
        while (batch_size < MAX_STRIPE_BATCH &&
                        (sh = __get_priority_stripe(conf, group)) != NULL)
                batch[batch_size++] = sh;
-        if (batch_size == 0)
+        if (batch_size == 0) {
-                return batch_size;
+                for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++)
+                        if (!list_empty(temp_inactive_list + i))
+                                break;
+                if (i == NR_STRIPE_HASH_LOCKS)
+                        return batch_size;
+                release_inactive = true;
+        }
        spin_unlock_irq(&conf->device_lock);
+        release_inactive_stripe_list(conf, temp_inactive_list,
+                                     NR_STRIPE_HASH_LOCKS);
+        if (release_inactive) {
+                spin_lock_irq(&conf->device_lock);
+                return 0;
+        }
        for (i = 0; i < batch_size; i++)
                handle_stripe(batch[i]);
        cond_resched();
        spin_lock_irq(&conf->device_lock);
-        for (i = 0; i < batch_size; i++)
+        for (i = 0; i < batch_size; i++) {
-                __release_stripe(conf, batch[i]);
+                hash = batch[i]->hash_lock_index;
+                __release_stripe(conf, batch[i], &temp_inactive_list[hash]);
+        }
        return batch_size;
 }
@@ -4995,9 +5160,10 @@ static void raid5_do_work(struct work_struct *work)
        while (1) {
                int batch_size, released;
-                released = release_stripe_list(conf);
+                released = release_stripe_list(conf, worker->temp_inactive_list);
-                batch_size = handle_active_stripes(conf, group_id, worker);
+                batch_size = handle_active_stripes(conf, group_id, worker,
+                                                   worker->temp_inactive_list);
                worker->working = false;
                if (!batch_size && !released)
                        break;
@@ -5036,7 +5202,7 @@ static void raid5d(struct md_thread *thread)
                struct bio *bio;
                int batch_size, released;
-                released = release_stripe_list(conf);
+                released = release_stripe_list(conf, conf->temp_inactive_list);
                if (
                    !list_empty(&conf->bitmap_list)) {
@@ -5046,7 +5212,7 @@ static void raid5d(struct md_thread *thread)
                        bitmap_unplug(mddev->bitmap);
                        spin_lock_irq(&conf->device_lock);
                        conf->seq_write = conf->seq_flush;
-                        activate_bit_delay(conf);
+                        activate_bit_delay(conf, conf->temp_inactive_list);
                }
                raid5_activate_delayed(conf);
@@ -5060,7 +5226,8 @@ static void raid5d(struct md_thread *thread)
                        handled++;
                }
-                batch_size = handle_active_stripes(conf, ANY_GROUP, NULL);
+                batch_size = handle_active_stripes(conf, ANY_GROUP, NULL,
+                                                   conf->temp_inactive_list);
                if (!batch_size && !released)
                        break;
                handled += batch_size;
@@ -5096,22 +5263,29 @@ raid5_set_cache_size(struct mddev *mddev, int size)
 {
        struct r5conf *conf = mddev->private;
        int err;
+        int hash;
        if (size <= 16 || size > 32768)
                return -EINVAL;
+        hash = (conf->max_nr_stripes - 1) % NR_STRIPE_HASH_LOCKS;
        while (size < conf->max_nr_stripes) {
-                if (drop_one_stripe(conf))
+                if (drop_one_stripe(conf, hash))
                        conf->max_nr_stripes--;
                else
                        break;
+                hash--;
+                if (hash < 0)
+                        hash = NR_STRIPE_HASH_LOCKS - 1;
        }
        err = md_allow_write(mddev);
        if (err)
                return err;
+        hash = conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS;
        while (size > conf->max_nr_stripes) {
-                if (grow_one_stripe(conf))
+                if (grow_one_stripe(conf, hash))
                        conf->max_nr_stripes++;
                else break;
+                hash = (hash + 1) % NR_STRIPE_HASH_LOCKS;
        }
        return 0;
 }
@@ -5199,15 +5373,18 @@ raid5_show_group_thread_cnt(struct mddev *mddev, char *page)
                return 0;
 }
-static int alloc_thread_groups(struct r5conf *conf, int cnt);
+static int alloc_thread_groups(struct r5conf *conf, int cnt,
+                               int *group_cnt,
+                               int *worker_cnt_per_group,
+                               struct r5worker_group **worker_groups);
 static ssize_t
 raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len)
 {
        struct r5conf *conf = mddev->private;
        unsigned long new;
        int err;
-        struct r5worker_group *old_groups;
+        struct r5worker_group *new_groups, *old_groups;
-        int old_group_cnt;
+        int group_cnt, worker_cnt_per_group;
        if (len >= PAGE_SIZE)
                return -EINVAL;
@@ -5223,14 +5400,19 @@ raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len)
        mddev_suspend(mddev);
        old_groups = conf->worker_groups;
-        old_group_cnt = conf->worker_cnt_per_group;
+        if (old_groups)
+                flush_workqueue(raid5_wq);
+        err = alloc_thread_groups(conf, new,
+                                  &group_cnt, &worker_cnt_per_group,
+                                  &new_groups);
+        if (!err) {
+                spin_lock_irq(&conf->device_lock);
+                conf->group_cnt = group_cnt;
+                conf->worker_cnt_per_group = worker_cnt_per_group;
+                conf->worker_groups = new_groups;
+                spin_unlock_irq(&conf->device_lock);
-        conf->worker_groups = NULL;
-        err = alloc_thread_groups(conf, new);
-        if (err) {
-                conf->worker_groups = old_groups;
-                conf->worker_cnt_per_group = old_group_cnt;
-        } else {
                if (old_groups)
                        kfree(old_groups[0].workers);
                kfree(old_groups);
@@ -5260,40 +5442,47 @@ static struct attribute_group raid5_attrs_group = {
        .attrs = raid5_attrs,
 };
-static int alloc_thread_groups(struct r5conf *conf, int cnt)
+static int alloc_thread_groups(struct r5conf *conf, int cnt,
+                               int *group_cnt,
+                               int *worker_cnt_per_group,
+                               struct r5worker_group **worker_groups)
 {
-        int i, j;
+        int i, j, k;
        ssize_t size;
        struct r5worker *workers;
-        conf->worker_cnt_per_group = cnt;
+        *worker_cnt_per_group = cnt;
        if (cnt == 0) {
-                conf->worker_groups = NULL;
+                *group_cnt = 0;
+                *worker_groups = NULL;
                return 0;
        }
-        conf->group_cnt = num_possible_nodes();
+        *group_cnt = num_possible_nodes();
        size = sizeof(struct r5worker) * cnt;
-        workers = kzalloc(size * conf->group_cnt, GFP_NOIO);
+        workers = kzalloc(size * *group_cnt, GFP_NOIO);
-        conf->worker_groups = kzalloc(sizeof(struct r5worker_group) *
+        *worker_groups = kzalloc(sizeof(struct r5worker_group) *
-                                conf->group_cnt, GFP_NOIO);
+                                *group_cnt, GFP_NOIO);
-        if (!conf->worker_groups || !workers) {
+        if (!*worker_groups || !workers) {
                kfree(workers);
-                kfree(conf->worker_groups);
+                kfree(*worker_groups);
-                conf->worker_groups = NULL;
                return -ENOMEM;
        }
-        for (i = 0; i < conf->group_cnt; i++) {
+        for (i = 0; i < *group_cnt; i++) {
                struct r5worker_group *group;
-                group = &conf->worker_groups[i];
+                group = worker_groups[i];
                INIT_LIST_HEAD(&group->handle_list);
                group->conf = conf;
                group->workers = workers + i * cnt;
                for (j = 0; j < cnt; j++) {
-                        group->workers[j].group = group;
+                        struct r5worker *worker = group->workers + j;
-                        INIT_WORK(&group->workers[j].work, raid5_do_work);
+                        worker->group = group;
+                        INIT_WORK(&worker->work, raid5_do_work);
+                        for (k = 0; k < NR_STRIPE_HASH_LOCKS; k++)
+                                INIT_LIST_HEAD(worker->temp_inactive_list + k);
                }
        }
@@ -5444,6 +5633,9 @@ static struct r5conf *setup_conf(struct mddev *mddev)
        struct md_rdev *rdev;
        struct disk_info *disk;
        char pers_name[6];
+        int i;
+        int group_cnt, worker_cnt_per_group;
+        struct r5worker_group *new_group;
        if (mddev->new_level != 5
            && mddev->new_level != 4
@@ -5478,7 +5670,12 @@ static struct r5conf *setup_conf(struct mddev *mddev)
        if (conf == NULL)
                goto abort;
        /* Don't enable multi-threading by default*/
-        if (alloc_thread_groups(conf, 0))
+        if (!alloc_thread_groups(conf, 0, &group_cnt, &worker_cnt_per_group,
+                                 &new_group)) {
+                conf->group_cnt = group_cnt;
+                conf->worker_cnt_per_group = worker_cnt_per_group;
+                conf->worker_groups = new_group;
+        } else
                goto abort;
        spin_lock_init(&conf->device_lock);
        seqcount_init(&conf->gen_lock);
@@ -5488,7 +5685,6 @@ static struct r5conf *setup_conf(struct mddev *mddev)
        INIT_LIST_HEAD(&conf->hold_list);
        INIT_LIST_HEAD(&conf->delayed_list);
        INIT_LIST_HEAD(&conf->bitmap_list);
-        INIT_LIST_HEAD(&conf->inactive_list);
        init_llist_head(&conf->released_stripes);
        atomic_set(&conf->active_stripes, 0);
        atomic_set(&conf->preread_active_stripes, 0);
@@ -5514,6 +5710,21 @@ static struct r5conf *setup_conf(struct mddev *mddev)
        if ((conf->stripe_hashtbl = kzalloc(PAGE_SIZE, GFP_KERNEL)) == NULL)
                goto abort;
+        /* We init hash_locks[0] separately to that it can be used
+         * as the reference lock in the spin_lock_nest_lock() call
+         * in lock_all_device_hash_locks_irq in order to convince
+         * lockdep that we know what we are doing.
+         */
+        spin_lock_init(conf->hash_locks);
+        for (i = 1; i < NR_STRIPE_HASH_LOCKS; i++)
+                spin_lock_init(conf->hash_locks + i);
+        for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++)
+                INIT_LIST_HEAD(conf->inactive_list + i);
+        for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++)
+                INIT_LIST_HEAD(conf->temp_inactive_list + i);
        conf->level = mddev->new_level;
        if (raid5_alloc_percpu(conf) != 0)
                goto abort;
@@ -5554,7 +5765,6 @@ static struct r5conf *setup_conf(struct mddev *mddev)
        else
                conf->max_degraded = 1;
        conf->algorithm = mddev->new_layout;
-        conf->max_nr_stripes = NR_STRIPES;
        conf->reshape_progress = mddev->reshape_position;
        if (conf->reshape_progress != MaxSector) {
                conf->prev_chunk_sectors = mddev->chunk_sectors;
@@ -5563,7 +5773,8 @@ static struct r5conf *setup_conf(struct mddev *mddev)
        memory = conf->max_nr_stripes * (sizeof(struct stripe_head) +
                 max_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024;
-        if (grow_stripes(conf, conf->max_nr_stripes)) {
+        atomic_set(&conf->empty_inactive_list_nr, NR_STRIPE_HASH_LOCKS);
+        if (grow_stripes(conf, NR_STRIPES)) {
                printk(KERN_ERR
                       "md/raid:%s: couldn't allocate %dkB for buffers\n",
                       mdname(mddev), memory);
@@ -6369,12 +6580,18 @@ static int raid5_start_reshape(struct mddev *mddev)
        if (!mddev->sync_thread) {
                mddev->recovery = 0;
                spin_lock_irq(&conf->device_lock);
+                write_seqcount_begin(&conf->gen_lock);
                mddev->raid_disks = conf->raid_disks = conf->previous_raid_disks;
+                mddev->new_chunk_sectors =
+                        conf->chunk_sectors = conf->prev_chunk_sectors;
+                mddev->new_layout = conf->algorithm = conf->prev_algo;
                rdev_for_each(rdev, mddev)
                        rdev->new_data_offset = rdev->data_offset;
                smp_wmb();
+                conf->generation --;
                conf->reshape_progress = MaxSector;
                mddev->reshape_position = MaxSector;
+                write_seqcount_end(&conf->gen_lock);
                spin_unlock_irq(&conf->device_lock);
                return -EAGAIN;
        }
@@ -6462,27 +6679,28 @@ static void raid5_quiesce(struct mddev *mddev, int state)
                break;
        case 1: /* stop all writes */
-                spin_lock_irq(&conf->device_lock);
+                lock_all_device_hash_locks_irq(conf);
                /* '2' tells resync/reshape to pause so that all
                 * active stripes can drain
                 */
                conf->quiesce = 2;
-                wait_event_lock_irq(conf->wait_for_stripe,
+                wait_event_cmd(conf->wait_for_stripe,
                                    atomic_read(&conf->active_stripes) == 0 &&
                                    atomic_read(&conf->active_aligned_reads) == 0,
-                                    conf->device_lock);
+                                    unlock_all_device_hash_locks_irq(conf),
+                                    lock_all_device_hash_locks_irq(conf));
                conf->quiesce = 1;
-                spin_unlock_irq(&conf->device_lock);
+                unlock_all_device_hash_locks_irq(conf);
                /* allow reshape to continue */
                wake_up(&conf->wait_for_overlap);
                break;
        case 0: /* re-enable writes */
-                spin_lock_irq(&conf->device_lock);
+                lock_all_device_hash_locks_irq(conf);
                conf->quiesce = 0;
                wake_up(&conf->wait_for_stripe);
                wake_up(&conf->wait_for_overlap);
-                spin_unlock_irq(&conf->device_lock);
+                unlock_all_device_hash_locks_irq(conf);
                break;
        }
 }
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index b42e6b462eda..01ad8ae8f578 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -205,6 +205,7 @@ struct stripe_head {
        short                   pd_idx;         /* parity disk index */
        short                   qd_idx;         /* 'Q' disk index for raid6 */
        short                   ddf_layout;/* use DDF ordering to calculate Q */
+        short                   hash_lock_index;
        unsigned long           state;          /* state flags */
        atomic_t                count;        /* nr of active thread/requests */
        int                     bm_seq; /* sequence number for bitmap flushes */
@@ -367,9 +368,18 @@ struct disk_info {
        struct md_rdev  *rdev, *replacement;
 };
+/* NOTE NR_STRIPE_HASH_LOCKS must remain below 64.
+ * This is because we sometimes take all the spinlocks
+ * and creating that much locking depth can cause
+ * problems.
+ */
+#define NR_STRIPE_HASH_LOCKS 8
+#define STRIPE_HASH_LOCKS_MASK (NR_STRIPE_HASH_LOCKS - 1)
 struct r5worker {
        struct work_struct work;
        struct r5worker_group *group;
+        struct list_head temp_inactive_list[NR_STRIPE_HASH_LOCKS];
        bool working;
 };
@@ -382,6 +392,8 @@ struct r5worker_group {
 struct r5conf {
        struct hlist_head       *stripe_hashtbl;
+        /* only protect corresponding hash list and inactive_list */
+        spinlock_t              hash_locks[NR_STRIPE_HASH_LOCKS];
        struct mddev            *mddev;
        int                     chunk_sectors;
        int                     level, algorithm;
@@ -462,7 +474,8 @@ struct r5conf {
         * Free stripes pool
         */
        atomic_t                active_stripes;
-        struct list_head        inactive_list;
+        struct list_head        inactive_list[NR_STRIPE_HASH_LOCKS];
+        atomic_t                empty_inactive_list_nr;
        struct llist_head       released_stripes;
        wait_queue_head_t       wait_for_stripe;
        wait_queue_head_t       wait_for_overlap;
@@ -477,6 +490,7 @@ struct r5conf {
         * the new thread here until we fully activate the array.
         */
        struct md_thread        *thread;
+        struct list_head        temp_inactive_list[NR_STRIPE_HASH_LOCKS];
        struct r5worker_group   *worker_groups;
        int                     group_cnt;
        int                     worker_cnt_per_group;
diff --git a/drivers/media/platform/m2m-deinterlace.c b/drivers/media/platform/m2m-deinterlace.c
index 36513e896413..65cab70fefcb 100644
--- a/drivers/media/platform/m2m-deinterlace.c
+++ b/drivers/media/platform/m2m-deinterlace.c
@@ -341,8 +341,7 @@ static void deinterlace_issue_dma(struct deinterlace_ctx *ctx, int op,
        ctx->xt->dir = DMA_MEM_TO_MEM;
        ctx->xt->src_sgl = false;
        ctx->xt->dst_sgl = true;
-        flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT |
+        flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
-                DMA_COMPL_SKIP_DEST_UNMAP | DMA_COMPL_SKIP_SRC_UNMAP;
        tx = dmadev->device_prep_interleaved_dma(chan, ctx->xt, flags);
        if (tx == NULL) {
diff --git a/drivers/media/platform/timblogiw.c b/drivers/media/platform/timblogiw.c
index 6a74ce040d28..ccdadd623a3a 100644
--- a/drivers/media/platform/timblogiw.c
+++ b/drivers/media/platform/timblogiw.c
@@ -565,7 +565,7 @@ static void buffer_queue(struct videobuf_queue *vq, struct videobuf_buffer *vb)
        desc = dmaengine_prep_slave_sg(fh->chan,
                buf->sg, sg_elems, DMA_DEV_TO_MEM,
-                DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP);
+                DMA_PREP_INTERRUPT);
        if (!desc) {
                spin_lock_irq(&fh->queue_lock);
                list_del_init(&vb->queue);
diff --git a/drivers/misc/carma/carma-fpga.c b/drivers/misc/carma/carma-fpga.c
index 08b18f3f5264..9e2b985293fc 100644
--- a/drivers/misc/carma/carma-fpga.c
+++ b/drivers/misc/carma/carma-fpga.c
@@ -633,8 +633,7 @@ static int data_submit_dma(struct fpga_device *priv, struct data_buf *buf)
        struct dma_async_tx_descriptor *tx;
        dma_cookie_t cookie;
        dma_addr_t dst, src;
-        unsigned long dma_flags = DMA_COMPL_SKIP_DEST_UNMAP |
+        unsigned long dma_flags = 0;
-                                  DMA_COMPL_SKIP_SRC_UNMAP;
        dst_sg = buf->vb.sglist;
        dst_nents = buf->vb.sglen;
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index ef8956568c3a..157b570ba343 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -308,8 +308,7 @@ static void sdio_acpi_set_handle(struct sdio_func *func)
        struct mmc_host *host = func->card->host;
        u64 addr = (host->slotno << 16) | func->num;
-        ACPI_HANDLE_SET(&func->dev,
+        acpi_preset_companion(&func->dev, ACPI_HANDLE(host->parent), addr);
-                        acpi_get_child(ACPI_HANDLE(host->parent), addr));
 }
 #else
 static inline void sdio_acpi_set_handle(struct sdio_func *func) {}
diff --git a/drivers/mtd/nand/atmel_nand.c b/drivers/mtd/nand/atmel_nand.c
index d78a97d4153a..59f08c44abdb 100644
--- a/drivers/mtd/nand/atmel_nand.c
+++ b/drivers/mtd/nand/atmel_nand.c
@@ -375,8 +375,7 @@ static int atmel_nand_dma_op(struct mtd_info *mtd, void *buf, int len,
        dma_dev = host->dma_chan->device;
-        flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP |
+        flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
-                DMA_COMPL_SKIP_DEST_UNMAP;
        phys_addr = dma_map_single(dma_dev->dev, p, len, dir);
        if (dma_mapping_error(dma_dev->dev, phys_addr)) {
diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c
index 3dc1a7564d87..8b2752263db9 100644
--- a/drivers/mtd/nand/fsmc_nand.c
+++ b/drivers/mtd/nand/fsmc_nand.c
@@ -573,8 +573,6 @@ static int dma_xfer(struct fsmc_nand_data *host, void *buffer, int len,
        dma_dev = chan->device;
        dma_addr = dma_map_single(dma_dev->dev, buffer, len, direction);
-        flags |= DMA_COMPL_SKIP_SRC_UNMAP | DMA_COMPL_SKIP_DEST_UNMAP;
        if (direction == DMA_TO_DEVICE) {
                dma_src = dma_addr;
                dma_dst = host->data_pa;
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index bc8fd362a5aa..0ec2a7e8c8a9 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -524,8 +524,9 @@ static ssize_t bonding_store_arp_interval(struct device *d,
                goto out;
        }
        if (bond->params.mode == BOND_MODE_ALB ||
-            bond->params.mode == BOND_MODE_TLB) {
+            bond->params.mode == BOND_MODE_TLB ||
-                pr_info("%s: ARP monitoring cannot be used with ALB/TLB. Only MII monitoring is supported on %s.\n",
+            bond->params.mode == BOND_MODE_8023AD) {
+                pr_info("%s: ARP monitoring cannot be used with ALB/TLB/802.3ad. Only MII monitoring is supported on %s.\n",
                        bond->dev->name, bond->dev->name);
                ret = -EINVAL;
                goto out;
@@ -603,15 +604,14 @@ static ssize_t bonding_store_arp_targets(struct device *d,
                return restart_syscall();
        targets = bond->params.arp_targets;
-        newtarget = in_aton(buf + 1);
+        if (!in4_pton(buf + 1, -1, (u8 *)&newtarget, -1, NULL) ||
+            IS_IP_TARGET_UNUSABLE_ADDRESS(newtarget)) {
+                pr_err("%s: invalid ARP target %pI4 specified for addition\n",
+                       bond->dev->name, &newtarget);
+                goto out;
+        }
        /* look for adds */
        if (buf[0] == '+') {
-                if ((newtarget == 0) || (newtarget == htonl(INADDR_BROADCAST))) {
-                        pr_err("%s: invalid ARP target %pI4 specified for addition\n",
-                               bond->dev->name, &newtarget);
-                        goto out;
-                }
                if (bond_get_targets_ip(targets, newtarget) != -1) { /* dup */
                        pr_err("%s: ARP target %pI4 is already present\n",
                               bond->dev->name, &newtarget);
@@ -634,12 +634,6 @@ static ssize_t bonding_store_arp_targets(struct device *d,
                targets[ind] = newtarget;
                write_unlock_bh(&bond->lock);
        } else if (buf[0] == '-')       {
-                if ((newtarget == 0) || (newtarget == htonl(INADDR_BROADCAST))) {
-                        pr_err("%s: invalid ARP target %pI4 specified for removal\n",
-                               bond->dev->name, &newtarget);
-                        goto out;
-                }
                ind = bond_get_targets_ip(targets, newtarget);
                if (ind == -1) {
                        pr_err("%s: unable to remove nonexistent ARP target %pI4.\n",
@@ -701,6 +695,8 @@ static ssize_t bonding_store_downdelay(struct device *d,
        int new_value, ret = count;
        struct bonding *bond = to_bond(d);
+        if (!rtnl_trylock())
+                return restart_syscall();
        if (!(bond->params.miimon)) {
                pr_err("%s: Unable to set down delay as MII monitoring is disabled\n",
                       bond->dev->name);
@@ -734,6 +730,7 @@ static ssize_t bonding_store_downdelay(struct device *d,
        }
 out:
+        rtnl_unlock();
        return ret;
 }
 static DEVICE_ATTR(downdelay, S_IRUGO | S_IWUSR,
@@ -756,6 +753,8 @@ static ssize_t bonding_store_updelay(struct device *d,
        int new_value, ret = count;
        struct bonding *bond = to_bond(d);
+        if (!rtnl_trylock())
+                return restart_syscall();
        if (!(bond->params.miimon)) {
                pr_err("%s: Unable to set up delay as MII monitoring is disabled\n",
                       bond->dev->name);
@@ -789,6 +788,7 @@ static ssize_t bonding_store_updelay(struct device *d,
        }
 out:
+        rtnl_unlock();
        return ret;
 }
 static DEVICE_ATTR(updelay, S_IRUGO | S_IWUSR,
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 77a07a12e77f..ca31286aa028 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -63,6 +63,9 @@
                (((mode) == BOND_MODE_TLB) ||   \
                 ((mode) == BOND_MODE_ALB))
+#define IS_IP_TARGET_UNUSABLE_ADDRESS(a)        \
+        ((htonl(INADDR_BROADCAST) == a) ||      \
+         ipv4_is_zeronet(a))
 /*
 * Less bad way to call ioctl from within the kernel; this needs to be
 * done some other way to get the call out of interrupt context.
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 5aa5e8146496..c3c4c266b846 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1388,6 +1388,9 @@ static int alx_resume(struct device *dev)
 {
        struct pci_dev *pdev = to_pci_dev(dev);
        struct alx_priv *alx = pci_get_drvdata(pdev);
+        struct alx_hw *hw = &alx->hw;
+        alx_reset_phy(hw);
        if (!netif_running(alx->dev))
                return 0;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 4e01c57d8c8d..a1f66e2c9a86 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -1376,7 +1376,6 @@ enum {
        BNX2X_SP_RTNL_RX_MODE,
        BNX2X_SP_RTNL_HYPERVISOR_VLAN,
        BNX2X_SP_RTNL_TX_STOP,
-        BNX2X_SP_RTNL_TX_RESUME,
 };
 struct bnx2x_prev_path_list {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index dcafbda3e5be..ec96130533cc 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -2959,6 +2959,10 @@ int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode, bool keep_link)
        bp->port.pmf = 0;
+        /* clear pending work in rtnl task */
+        bp->sp_rtnl_state = 0;
+        smp_mb();
        /* Free SKBs, SGEs, TPA pool and driver internals */
        bnx2x_free_skbs(bp);
        if (CNIC_LOADED(bp))
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
index fcf2761d8828..fdace204b054 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
@@ -778,11 +778,6 @@ void bnx2x_dcbx_set_params(struct bnx2x *bp, u32 state)
                /* ets may affect cmng configuration: reinit it in hw */
                bnx2x_set_local_cmng(bp);
-                set_bit(BNX2X_SP_RTNL_TX_RESUME, &bp->sp_rtnl_state);
-                schedule_delayed_work(&bp->sp_rtnl_task, 0);
                return;
        case BNX2X_DCBX_STATE_TX_RELEASED:
                DP(BNX2X_MSG_DCB, "BNX2X_DCBX_STATE_TX_RELEASED\n");
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index e622cc1f96ff..814d0eca9b33 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -577,7 +577,9 @@ void bnx2x_write_dmae(struct bnx2x *bp, dma_addr_t dma_addr, u32 dst_addr,
        rc = bnx2x_issue_dmae_with_comp(bp, &dmae, bnx2x_sp(bp, wb_comp));
        if (rc) {
                BNX2X_ERR("DMAE returned failure %d\n", rc);
+#ifdef BNX2X_STOP_ON_ERROR
                bnx2x_panic();
+#endif
        }
 }
@@ -614,7 +616,9 @@ void bnx2x_read_dmae(struct bnx2x *bp, u32 src_addr, u32 len32)
        rc = bnx2x_issue_dmae_with_comp(bp, &dmae, bnx2x_sp(bp, wb_comp));
        if (rc) {
                BNX2X_ERR("DMAE returned failure %d\n", rc);
+#ifdef BNX2X_STOP_ON_ERROR
                bnx2x_panic();
+#endif
        }
 }
@@ -5231,18 +5235,18 @@ static void bnx2x_eq_int(struct bnx2x *bp)
                case EVENT_RING_OPCODE_STOP_TRAFFIC:
                        DP(BNX2X_MSG_SP | BNX2X_MSG_DCB, "got STOP TRAFFIC\n");
+                        bnx2x_dcbx_set_params(bp, BNX2X_DCBX_STATE_TX_PAUSED);
                        if (f_obj->complete_cmd(bp, f_obj,
                                                BNX2X_F_CMD_TX_STOP))
                                break;
-                        bnx2x_dcbx_set_params(bp, BNX2X_DCBX_STATE_TX_PAUSED);
                        goto next_spqe;
                case EVENT_RING_OPCODE_START_TRAFFIC:
                        DP(BNX2X_MSG_SP | BNX2X_MSG_DCB, "got START TRAFFIC\n");
+                        bnx2x_dcbx_set_params(bp, BNX2X_DCBX_STATE_TX_RELEASED);
                        if (f_obj->complete_cmd(bp, f_obj,
                                                BNX2X_F_CMD_TX_START))
                                break;
-                        bnx2x_dcbx_set_params(bp, BNX2X_DCBX_STATE_TX_RELEASED);
                        goto next_spqe;
                case EVENT_RING_OPCODE_FUNCTION_UPDATE:
@@ -9352,6 +9356,10 @@ static int bnx2x_process_kill(struct bnx2x *bp, bool global)
        bnx2x_process_kill_chip_reset(bp, global);
        barrier();
+        /* clear errors in PGB */
+        if (!CHIP_IS_E1x(bp))
+                REG_WR(bp, PGLUE_B_REG_LATCHED_ERRORS_CLR, 0x7f);
        /* Recover after reset: */
        /* MCP */
        if (global && bnx2x_reset_mcp_comp(bp, val))
@@ -9706,11 +9714,10 @@ sp_rtnl_not_reset:
                               &bp->sp_rtnl_state))
                bnx2x_pf_set_vfs_vlan(bp);
-        if (test_and_clear_bit(BNX2X_SP_RTNL_TX_STOP, &bp->sp_rtnl_state))
+        if (test_and_clear_bit(BNX2X_SP_RTNL_TX_STOP, &bp->sp_rtnl_state)) {
                bnx2x_dcbx_stop_hw_tx(bp);
-        if (test_and_clear_bit(BNX2X_SP_RTNL_TX_RESUME, &bp->sp_rtnl_state))
                bnx2x_dcbx_resume_hw_tx(bp);
+        }
        /* work which needs rtnl lock not-taken (as it takes the lock itself and
         * can be called from other contexts as well)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
index 5ecf267dc4cc..3efbb35267c8 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
@@ -2864,6 +2864,17 @@
 #define PGLUE_B_REG_INTERNAL_PFID_ENABLE_TARGET_READ             0x9430
 #define PGLUE_B_REG_INTERNAL_PFID_ENABLE_TARGET_WRITE            0x9434
 #define PGLUE_B_REG_INTERNAL_VFID_ENABLE                         0x9438
+/* [W 7] Writing 1 to each bit in this register clears a corresponding error
+ * details register and enables logging new error details. Bit 0 - clears
+ * INCORRECT_RCV_DETAILS; Bit 1 - clears RX_ERR_DETAILS; Bit 2 - clears
+ * TX_ERR_WR_ADD_31_0 TX_ERR_WR_ADD_63_32 TX_ERR_WR_DETAILS
+ * TX_ERR_WR_DETAILS2 TX_ERR_RD_ADD_31_0 TX_ERR_RD_ADD_63_32
+ * TX_ERR_RD_DETAILS TX_ERR_RD_DETAILS2 TX_ERR_WR_DETAILS_ICPL; Bit 3 -
+ * clears VF_LENGTH_VIOLATION_DETAILS. Bit 4 - clears
+ * VF_GRC_SPACE_VIOLATION_DETAILS. Bit 5 - clears RX_TCPL_ERR_DETAILS. Bit 6
+ * - clears TCPL_IN_TWO_RCBS_DETAILS. */
+#define PGLUE_B_REG_LATCHED_ERRORS_CLR                           0x943c
 /* [R 9] Interrupt register #0 read */
 #define PGLUE_B_REG_PGLUE_B_INT_STS                              0x9298
 /* [RC 9] Interrupt register #0 read clear */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index 9199adf32d33..efa8a151d789 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -152,7 +152,7 @@ static int bnx2x_send_msg2pf(struct bnx2x *bp, u8 *done, dma_addr_t msg_mapping)
        if (bp->old_bulletin.valid_bitmap & 1 << CHANNEL_DOWN) {
                DP(BNX2X_MSG_IOV, "detecting channel down. Aborting message\n");
                *done = PFVF_STATUS_SUCCESS;
-                return 0;
+                return -EINVAL;
        }
        /* Write message address */
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 00c5be8c55b8..a9e068423ba0 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -13618,16 +13618,9 @@ static int tg3_hwtstamp_ioctl(struct net_device *dev,
        if (stmpconf.flags)
                return -EINVAL;
-        switch (stmpconf.tx_type) {
+        if (stmpconf.tx_type != HWTSTAMP_TX_ON &&
-        case HWTSTAMP_TX_ON:
+            stmpconf.tx_type != HWTSTAMP_TX_OFF)
-                tg3_flag_set(tp, TX_TSTAMP_EN);
-                break;
-        case HWTSTAMP_TX_OFF:
-                tg3_flag_clear(tp, TX_TSTAMP_EN);
-                break;
-        default:
                return -ERANGE;
-        }
        switch (stmpconf.rx_filter) {
        case HWTSTAMP_FILTER_NONE:
@@ -13689,6 +13682,11 @@ static int tg3_hwtstamp_ioctl(struct net_device *dev,
                tw32(TG3_RX_PTP_CTL,
                     tp->rxptpctl | TG3_RX_PTP_CTL_HWTS_INTERLOCK);
+        if (stmpconf.tx_type == HWTSTAMP_TX_ON)
+                tg3_flag_set(tp, TX_TSTAMP_EN);
+        else
+                tg3_flag_clear(tp, TX_TSTAMP_EN);
        return copy_to_user(ifr->ifr_data, &stmpconf, sizeof(stmpconf)) ?
                -EFAULT : 0;
 }
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 7fb0edfe3d24..dbcd5262c016 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -1758,7 +1758,7 @@ err:
 /* Uses sycnhronous mcc */
 int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
-                        u32 num, bool untagged, bool promiscuous)
+                       u32 num, bool promiscuous)
 {
        struct be_mcc_wrb *wrb;
        struct be_cmd_req_vlan_config *req;
@@ -1778,7 +1778,7 @@ int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
        req->interface_id = if_id;
        req->promiscuous = promiscuous;
-        req->untagged = untagged;
+        req->untagged = BE_IF_FLAGS_UNTAGGED & be_if_cap_flags(adapter) ? 1 : 0;
        req->num_vlan = num;
        if (!promiscuous) {
                memcpy(req->normal_vlan, vtag_array,
@@ -1847,7 +1847,19 @@ int be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 value)
                        memcpy(req->mcast_mac[i++].byte, ha->addr, ETH_ALEN);
        }
+        if ((req->if_flags_mask & cpu_to_le32(be_if_cap_flags(adapter))) !=
+             req->if_flags_mask) {
+                dev_warn(&adapter->pdev->dev,
+                         "Cannot set rx filter flags 0x%x\n",
+                         req->if_flags_mask);
+                dev_warn(&adapter->pdev->dev,
+                         "Interface is capable of 0x%x flags only\n",
+                         be_if_cap_flags(adapter));
+        }
+        req->if_flags_mask &= cpu_to_le32(be_if_cap_flags(adapter));
        status = be_mcc_notify_wait(adapter);
 err:
        spin_unlock_bh(&adapter->mcc_lock);
        return status;
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index edf3e8a0ff83..0075686276aa 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -1984,7 +1984,7 @@ int be_cmd_get_fw_ver(struct be_adapter *adapter, char *fw_ver,
                      char *fw_on_flash);
 int be_cmd_modify_eqd(struct be_adapter *adapter, struct be_set_eqd *, int num);
 int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
-                       u32 num, bool untagged, bool promiscuous);
+                       u32 num, bool promiscuous);
 int be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 status);
 int be_cmd_set_flow_control(struct be_adapter *adapter, u32 tx_fc, u32 rx_fc);
 int be_cmd_get_flow_control(struct be_adapter *adapter, u32 *tx_fc, u32 *rx_fc);
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index eaecaadfa8c5..abde97471636 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1079,7 +1079,7 @@ static int be_vid_config(struct be_adapter *adapter)
                        vids[num++] = cpu_to_le16(i);
        status = be_cmd_vlan_config(adapter, adapter->if_handle,
-                                    vids, num, 1, 0);
+                                    vids, num, 0);
        if (status) {
                /* Set to VLAN promisc mode as setting VLAN filter failed */
@@ -2676,6 +2676,11 @@ static int be_close(struct net_device *netdev)
        be_rx_qs_destroy(adapter);
+        for (i = 1; i < (adapter->uc_macs + 1); i++)
+                be_cmd_pmac_del(adapter, adapter->if_handle,
+                                adapter->pmac_id[i], 0);
+        adapter->uc_macs = 0;
        for_all_evt_queues(adapter, eqo, i) {
                if (msix_enabled(adapter))
                        synchronize_irq(be_msix_vec_get(adapter, eqo));
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index b2793b91cc55..4cbebf3d80eb 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -386,7 +386,14 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
         */
        bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, bufaddr,
                        FEC_ENET_TX_FRSIZE, DMA_TO_DEVICE);
+        if (dma_mapping_error(&fep->pdev->dev, bdp->cbd_bufaddr)) {
+                bdp->cbd_bufaddr = 0;
+                fep->tx_skbuff[index] = NULL;
+                dev_kfree_skb_any(skb);
+                if (net_ratelimit())
+                        netdev_err(ndev, "Tx DMA memory map failed\n");
+                return NETDEV_TX_OK;
+        }
        /* Send it on its way.  Tell FEC it's ready, interrupt when done,
         * it's the last BD of the frame, and to put the CRC on the end.
         */
@@ -861,6 +868,7 @@ fec_enet_rx(struct net_device *ndev, int budget)
        struct  bufdesc_ex *ebdp = NULL;
        bool    vlan_packet_rcvd = false;
        u16     vlan_tag;
+        int     index = 0;
 #ifdef CONFIG_M532x
        flush_cache_all();
@@ -916,10 +924,15 @@ fec_enet_rx(struct net_device *ndev, int budget)
                ndev->stats.rx_packets++;
                pkt_len = bdp->cbd_datlen;
                ndev->stats.rx_bytes += pkt_len;
-                data = (__u8*)__va(bdp->cbd_bufaddr);
-                dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr,
+                if (fep->bufdesc_ex)
-                                FEC_ENET_TX_FRSIZE, DMA_FROM_DEVICE);
+                        index = (struct bufdesc_ex *)bdp -
+                                (struct bufdesc_ex *)fep->rx_bd_base;
+                else
+                        index = bdp - fep->rx_bd_base;
+                data = fep->rx_skbuff[index]->data;
+                dma_sync_single_for_cpu(&fep->pdev->dev, bdp->cbd_bufaddr,
+                                        FEC_ENET_RX_FRSIZE, DMA_FROM_DEVICE);
                if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
                        swap_buffer(data, pkt_len);
@@ -999,8 +1012,8 @@ fec_enet_rx(struct net_device *ndev, int budget)
                        napi_gro_receive(&fep->napi, skb);
                }
-                bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, data,
+                dma_sync_single_for_device(&fep->pdev->dev, bdp->cbd_bufaddr,
-                                FEC_ENET_TX_FRSIZE, DMA_FROM_DEVICE);
+                                        FEC_ENET_RX_FRSIZE, DMA_FROM_DEVICE);
 rx_processing_done:
                /* Clear the status flags for this buffer */
                status &= ~BD_ENET_RX_STATS;
@@ -1719,6 +1732,12 @@ static int fec_enet_alloc_buffers(struct net_device *ndev)
                bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, skb->data,
                                FEC_ENET_RX_FRSIZE, DMA_FROM_DEVICE);
+                if (dma_mapping_error(&fep->pdev->dev, bdp->cbd_bufaddr)) {
+                        fec_enet_free_buffers(ndev);
+                        if (net_ratelimit())
+                                netdev_err(ndev, "Rx DMA memory map failed\n");
+                        return -ENOMEM;
+                }
                bdp->cbd_sc = BD_ENET_RX_EMPTY;
                if (fep->bufdesc_ex) {
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index aedd5736a87d..8d3945ab7334 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -3482,10 +3482,10 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
 * specified. Matching the kind of event packet is not supported, with the
 * exception of "all V2 events regardless of level 2 or 4".
 **/
-static int e1000e_config_hwtstamp(struct e1000_adapter *adapter)
+static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
+                                  struct hwtstamp_config *config)
 {
        struct e1000_hw *hw = &adapter->hw;
-        struct hwtstamp_config *config = &adapter->hwtstamp_config;
        u32 tsync_tx_ctl = E1000_TSYNCTXCTL_ENABLED;
        u32 tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED;
        u32 rxmtrl = 0;
@@ -3586,6 +3586,8 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter)
                return -ERANGE;
        }
+        adapter->hwtstamp_config = *config;
        /* enable/disable Tx h/w time stamping */
        regval = er32(TSYNCTXCTL);
        regval &= ~E1000_TSYNCTXCTL_ENABLED;
@@ -3874,7 +3876,7 @@ void e1000e_reset(struct e1000_adapter *adapter)
        e1000e_reset_adaptive(hw);
        /* initialize systim and reset the ns time counter */
-        e1000e_config_hwtstamp(adapter);
+        e1000e_config_hwtstamp(adapter, &adapter->hwtstamp_config);
        /* Set EEE advertisement as appropriate */
        if (adapter->flags2 & FLAG2_HAS_EEE) {
@@ -5797,14 +5799,10 @@ static int e1000e_hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr)
        if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
                return -EFAULT;
-        adapter->hwtstamp_config = config;
+        ret_val = e1000e_config_hwtstamp(adapter, &config);
-        ret_val = e1000e_config_hwtstamp(adapter);
        if (ret_val)
                return ret_val;
-        config = adapter->hwtstamp_config;
        switch (config.rx_filter) {
        case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
        case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index 00cd36e08601..61088a6a9424 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -2890,7 +2890,8 @@ static int mv643xx_eth_probe(struct platform_device *pdev)
                                         PHY_INTERFACE_MODE_GMII);
                if (!mp->phy)
                        err = -ENODEV;
-                phy_addr_set(mp, mp->phy->addr);
+                else
+                        phy_addr_set(mp, mp->phy->addr);
        } else if (pd->phy_addr != MV643XX_ETH_PHY_NONE) {
                mp->phy = phy_scan(mp, pd->phy_addr);
diff --git a/drivers/net/ethernet/micrel/ks8842.c b/drivers/net/ethernet/micrel/ks8842.c
index 0951f7aca1ef..822616e3c375 100644
--- a/drivers/net/ethernet/micrel/ks8842.c
+++ b/drivers/net/ethernet/micrel/ks8842.c
@@ -459,8 +459,7 @@ static int ks8842_tx_frame_dma(struct sk_buff *skb, struct net_device *netdev)
                sg_dma_len(&ctl->sg) += 4 - sg_dma_len(&ctl->sg) % 4;
        ctl->adesc = dmaengine_prep_slave_sg(ctl->chan,
-                &ctl->sg, 1, DMA_MEM_TO_DEV,
+                &ctl->sg, 1, DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT);
-                DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP);
        if (!ctl->adesc)
                return NETDEV_TX_BUSY;
@@ -571,8 +570,7 @@ static int __ks8842_start_new_rx_dma(struct net_device *netdev)
                sg_dma_len(sg) = DMA_BUFFER_SIZE;
                ctl->adesc = dmaengine_prep_slave_sg(ctl->chan,
-                        sg, 1, DMA_DEV_TO_MEM,
+                        sg, 1, DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT);
-                        DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP);
                if (!ctl->adesc)
                        goto out;
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 5a0f04c2c813..27ffe0ebf0a6 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -245,16 +245,8 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
        /* Get ieee1588's dev information */
        pdev = adapter->ptp_pdev;
-        switch (cfg.tx_type) {
+        if (cfg.tx_type != HWTSTAMP_TX_OFF && cfg.tx_type != HWTSTAMP_TX_ON)
-        case HWTSTAMP_TX_OFF:
-                adapter->hwts_tx_en = 0;
-                break;
-        case HWTSTAMP_TX_ON:
-                adapter->hwts_tx_en = 1;
-                break;
-        default:
                return -ERANGE;
-        }
        switch (cfg.rx_filter) {
        case HWTSTAMP_FILTER_NONE:
@@ -284,6 +276,8 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
                return -ERANGE;
        }
+        adapter->hwts_tx_en = cfg.tx_type == HWTSTAMP_TX_ON;
        /* Clear out any old time stamps. */
        pch_ch_event_write(pdev, TX_SNAPSHOT_LOCKED | RX_SNAPSHOT_LOCKED);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 8d4ccd35a016..8a7a23a84ac5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -435,16 +435,9 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
        if (config.flags)
                return -EINVAL;
-        switch (config.tx_type) {
+        if (config.tx_type != HWTSTAMP_TX_OFF &&
-        case HWTSTAMP_TX_OFF:
+            config.tx_type != HWTSTAMP_TX_ON)
-                priv->hwts_tx_en = 0;
-                break;
-        case HWTSTAMP_TX_ON:
-                priv->hwts_tx_en = 1;
-                break;
-        default:
                return -ERANGE;
-        }
        if (priv->adv_ts) {
                switch (config.rx_filter) {
@@ -576,6 +569,7 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
                }
        }
        priv->hwts_rx_en = ((config.rx_filter == HWTSTAMP_FILTER_NONE) ? 0 : 1);
+        priv->hwts_tx_en = config.tx_type == HWTSTAMP_TX_ON;
        if (!priv->hwts_tx_en && !priv->hwts_rx_en)
                priv->hw->ptp->config_hw_tstamping(priv->ioaddr, 0);
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 90d41d26ec6d..7536a4c01293 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -967,14 +967,19 @@ static inline void cpsw_add_dual_emac_def_ale_entries(
                priv->host_port, ALE_VLAN, slave->port_vlan);
 }
-static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
+static void soft_reset_slave(struct cpsw_slave *slave)
 {
        char name[32];
-        u32 slave_port;
-        sprintf(name, "slave-%d", slave->slave_num);
+        snprintf(name, sizeof(name), "slave-%d", slave->slave_num);
        soft_reset(name, &slave->sliver->soft_reset);
+}
+static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
+{
+        u32 slave_port;
+        soft_reset_slave(slave);
        /* setup priority mapping */
        __raw_writel(RX_PRIORITY_MAPPING, &slave->sliver->rx_pri_map);
@@ -1323,6 +1328,10 @@ static int cpsw_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
        struct cpts *cpts = priv->cpts;
        struct hwtstamp_config cfg;
+        if (priv->version != CPSW_VERSION_1 &&
+            priv->version != CPSW_VERSION_2)
+                return -EOPNOTSUPP;
        if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
                return -EFAULT;
@@ -1330,16 +1339,8 @@ static int cpsw_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
        if (cfg.flags)
                return -EINVAL;
-        switch (cfg.tx_type) {
+        if (cfg.tx_type != HWTSTAMP_TX_OFF && cfg.tx_type != HWTSTAMP_TX_ON)
-        case HWTSTAMP_TX_OFF:
-                cpts->tx_enable = 0;
-                break;
-        case HWTSTAMP_TX_ON:
-                cpts->tx_enable = 1;
-                break;
-        default:
                return -ERANGE;
-        }
        switch (cfg.rx_filter) {
        case HWTSTAMP_FILTER_NONE:
@@ -1366,6 +1367,8 @@ static int cpsw_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
                return -ERANGE;
        }
+        cpts->tx_enable = cfg.tx_type == HWTSTAMP_TX_ON;
        switch (priv->version) {
        case CPSW_VERSION_1:
                cpsw_hwtstamp_v1(priv);
@@ -1374,7 +1377,7 @@ static int cpsw_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
                cpsw_hwtstamp_v2(priv);
                break;
        default:
-                return -ENOTSUPP;
+                WARN_ON(1);
        }
        return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
@@ -2173,8 +2176,9 @@ static int cpsw_suspend(struct device *dev)
        if (netif_running(ndev))
                cpsw_ndo_stop(ndev);
-        soft_reset("sliver 0", &priv->slaves[0].sliver->soft_reset);
-        soft_reset("sliver 1", &priv->slaves[1].sliver->soft_reset);
+        for_each_slave(priv, soft_reset_slave);
        pm_runtime_put_sync(&pdev->dev);
        /* Select sleep pin state */
diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index e78802e75ea6..bcc224a83734 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -389,16 +389,8 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
        ch = PORT2CHANNEL(port);
        regs = (struct ixp46x_ts_regs __iomem *) IXP4XX_TIMESYNC_BASE_VIRT;
-        switch (cfg.tx_type) {
+        if (cfg.tx_type != HWTSTAMP_TX_OFF && cfg.tx_type != HWTSTAMP_TX_ON)
-        case HWTSTAMP_TX_OFF:
-                port->hwts_tx_en = 0;
-                break;
-        case HWTSTAMP_TX_ON:
-                port->hwts_tx_en = 1;
-                break;
-        default:
                return -ERANGE;
-        }
        switch (cfg.rx_filter) {
        case HWTSTAMP_FILTER_NONE:
@@ -416,6 +408,8 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
                return -ERANGE;
        }
+        port->hwts_tx_en = cfg.tx_type == HWTSTAMP_TX_ON;
        /* Clear out any old time stamps. */
        __raw_writel(TX_SNAPSHOT_LOCKED | RX_SNAPSHOT_LOCKED,
                     &regs->channel[ch].ch_event);
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 9dccb1edfd2a..dc76670c2f2a 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -628,6 +628,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
                                const struct iovec *iv, unsigned long total_len,
                                size_t count, int noblock)
 {
+        int good_linear = SKB_MAX_HEAD(NET_IP_ALIGN);
        struct sk_buff *skb;
        struct macvlan_dev *vlan;
        unsigned long len = total_len;
@@ -670,6 +671,8 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
        if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) {
                copylen = vnet_hdr.hdr_len ? vnet_hdr.hdr_len : GOODCOPY_LEN;
+                if (copylen > good_linear)
+                        copylen = good_linear;
                linear = copylen;
                if (iov_pages(iv, vnet_hdr_len + copylen, count)
                    <= MAX_SKB_FRAGS)
@@ -678,7 +681,10 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
        if (!zerocopy) {
                copylen = len;
-                linear = vnet_hdr.hdr_len;
+                if (vnet_hdr.hdr_len > good_linear)
+                        linear = good_linear;
+                else
+                        linear = vnet_hdr.hdr_len;
        }
        skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, copylen,
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 6574eb8766f9..34b0de09d881 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2650,7 +2650,7 @@ static int team_nl_cmd_port_list_get(struct sk_buff *skb,
        return err;
 }
-static struct genl_ops team_nl_ops[] = {
+static const struct genl_ops team_nl_ops[] = {
        {
                .cmd = TEAM_CMD_NOOP,
                .doit = team_nl_cmd_noop,
@@ -2676,15 +2676,15 @@ static struct genl_ops team_nl_ops[] = {
        },
 };
-static struct genl_multicast_group team_change_event_mcgrp = {
+static const struct genl_multicast_group team_nl_mcgrps[] = {
-        .name = TEAM_GENL_CHANGE_EVENT_MC_GRP_NAME,
+        { .name = TEAM_GENL_CHANGE_EVENT_MC_GRP_NAME, },
 };
 static int team_nl_send_multicast(struct sk_buff *skb,
                                  struct team *team, u32 portid)
 {
-        return genlmsg_multicast_netns(dev_net(team->dev), skb, 0,
+        return genlmsg_multicast_netns(&team_nl_family, dev_net(team->dev),
-                                       team_change_event_mcgrp.id, GFP_KERNEL);
+                                       skb, 0, 0, GFP_KERNEL);
 }
 static int team_nl_send_event_options_get(struct team *team,
@@ -2703,23 +2703,8 @@ static int team_nl_send_event_port_get(struct team *team,
 static int team_nl_init(void)
 {
-        int err;
+        return genl_register_family_with_ops_groups(&team_nl_family, team_nl_ops,
+                                                    team_nl_mcgrps);
-        err = genl_register_family_with_ops(&team_nl_family, team_nl_ops,
-                                            ARRAY_SIZE(team_nl_ops));
-        if (err)
-                return err;
-        err = genl_register_mc_group(&team_nl_family, &team_change_event_mcgrp);
-        if (err)
-                goto err_change_event_grp_reg;
-        return 0;
-err_change_event_grp_reg:
-        genl_unregister_family(&team_nl_family);
-        return err;
 }
 static void team_nl_fini(void)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 7cb105c103fe..782e38bfc1ee 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -981,6 +981,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
        struct sk_buff *skb;
        size_t len = total_len, align = NET_SKB_PAD, linear;
        struct virtio_net_hdr gso = { 0 };
+        int good_linear;
        int offset = 0;
        int copylen;
        bool zerocopy = false;
@@ -1021,12 +1022,16 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
                        return -EINVAL;
        }
+        good_linear = SKB_MAX_HEAD(align);
        if (msg_control) {
                /* There are 256 bytes to be copied in skb, so there is
                 * enough room for skb expand head in case it is used.
                 * The rest of the buffer is mapped from userspace.
                 */
                copylen = gso.hdr_len ? gso.hdr_len : GOODCOPY_LEN;
+                if (copylen > good_linear)
+                        copylen = good_linear;
                linear = copylen;
                if (iov_pages(iv, offset + copylen, count) <= MAX_SKB_FRAGS)
                        zerocopy = true;
@@ -1034,7 +1039,10 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
        if (!zerocopy) {
                copylen = len;
-                linear = gso.hdr_len;
+                if (gso.hdr_len > good_linear)
+                        linear = good_linear;
+                else
+                        linear = gso.hdr_len;
        }
        skb = tun_alloc_skb(tfile, align, copylen, linear, noblock);
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index f74786aa37be..e15ec2b12035 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -66,7 +66,7 @@ static void cdc_ncm_tx_timeout_start(struct cdc_ncm_ctx *ctx);
 static enum hrtimer_restart cdc_ncm_tx_timer_cb(struct hrtimer *hr_timer);
 static struct usb_driver cdc_ncm_driver;
-static u8 cdc_ncm_setup(struct usbnet *dev)
+static int cdc_ncm_setup(struct usbnet *dev)
 {
        struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
        struct usb_cdc_ncm_ntb_parameters ncm_parm;
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 90a429b7ebad..8494bb53ebdc 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -204,9 +204,6 @@ static void intr_complete (struct urb *urb)
                break;
        }
-        if (!netif_running (dev->net))
-                return;
        status = usb_submit_urb (urb, GFP_ATOMIC);
        if (status != 0)
                netif_err(dev, timer, dev->net,
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index cdc7c90a6a9e..7bab4de658a9 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -36,7 +36,10 @@ module_param(csum, bool, 0444);
 module_param(gso, bool, 0444);
 /* FIXME: MTU in config. */
-#define MAX_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN)
+#define GOOD_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN)
+#define MERGE_BUFFER_LEN (ALIGN(GOOD_PACKET_LEN + \
+                                sizeof(struct virtio_net_hdr_mrg_rxbuf), \
+                                L1_CACHE_BYTES))
 #define GOOD_COPY_LEN   128
 #define VIRTNET_DRIVER_VERSION "1.0.0"
@@ -314,10 +317,10 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *head_skb)
                        head_skb->dev->stats.rx_length_errors++;
                        return -EINVAL;
                }
-                if (unlikely(len > MAX_PACKET_LEN)) {
+                if (unlikely(len > MERGE_BUFFER_LEN)) {
                        pr_debug("%s: rx error: merge buffer too long\n",
                                 head_skb->dev->name);
-                        len = MAX_PACKET_LEN;
+                        len = MERGE_BUFFER_LEN;
                }
                if (unlikely(num_skb_frags == MAX_SKB_FRAGS)) {
                        struct sk_buff *nskb = alloc_skb(0, GFP_ATOMIC);
@@ -336,18 +339,17 @@ static int receive_mergeable(struct receive_queue *rq, struct sk_buff *head_skb)
                if (curr_skb != head_skb) {
                        head_skb->data_len += len;
                        head_skb->len += len;
-                        head_skb->truesize += MAX_PACKET_LEN;
+                        head_skb->truesize += MERGE_BUFFER_LEN;
                }
                page = virt_to_head_page(buf);
                offset = buf - (char *)page_address(page);
                if (skb_can_coalesce(curr_skb, num_skb_frags, page, offset)) {
                        put_page(page);
                        skb_coalesce_rx_frag(curr_skb, num_skb_frags - 1,
-                                             len, MAX_PACKET_LEN);
+                                             len, MERGE_BUFFER_LEN);
                } else {
                        skb_add_rx_frag(curr_skb, num_skb_frags, page,
-                                        offset, len,
+                                        offset, len, MERGE_BUFFER_LEN);
-                                        MAX_PACKET_LEN);
                }
                --rq->num;
        }
@@ -383,7 +385,7 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
                struct page *page = virt_to_head_page(buf);
                skb = page_to_skb(rq, page,
                                  (char *)buf - (char *)page_address(page),
-                                  len, MAX_PACKET_LEN);
+                                  len, MERGE_BUFFER_LEN);
                if (unlikely(!skb)) {
                        dev->stats.rx_dropped++;
                        put_page(page);
@@ -471,11 +473,11 @@ static int add_recvbuf_small(struct receive_queue *rq, gfp_t gfp)
        struct skb_vnet_hdr *hdr;
        int err;
-        skb = __netdev_alloc_skb_ip_align(vi->dev, MAX_PACKET_LEN, gfp);
+        skb = __netdev_alloc_skb_ip_align(vi->dev, GOOD_PACKET_LEN, gfp);
        if (unlikely(!skb))
                return -ENOMEM;
-        skb_put(skb, MAX_PACKET_LEN);
+        skb_put(skb, GOOD_PACKET_LEN);
        hdr = skb_vnet_hdr(skb);
        sg_set_buf(rq->sg, &hdr->hdr, sizeof hdr->hdr);
@@ -542,20 +544,20 @@ static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp)
        int err;
        if (gfp & __GFP_WAIT) {
-                if (skb_page_frag_refill(MAX_PACKET_LEN, &vi->alloc_frag,
+                if (skb_page_frag_refill(MERGE_BUFFER_LEN, &vi->alloc_frag,
                                         gfp)) {
                        buf = (char *)page_address(vi->alloc_frag.page) +
                              vi->alloc_frag.offset;
                        get_page(vi->alloc_frag.page);
-                        vi->alloc_frag.offset += MAX_PACKET_LEN;
+                        vi->alloc_frag.offset += MERGE_BUFFER_LEN;
                }
        } else {
-                buf = netdev_alloc_frag(MAX_PACKET_LEN);
+                buf = netdev_alloc_frag(MERGE_BUFFER_LEN);
        }
        if (!buf)
                return -ENOMEM;
-        sg_init_one(rq->sg, buf, MAX_PACKET_LEN);
+        sg_init_one(rq->sg, buf, MERGE_BUFFER_LEN);
        err = virtqueue_add_inbuf(rq->vq, rq->sg, 1, buf, gfp);
        if (err < 0)
                put_page(virt_to_head_page(buf));
@@ -1619,8 +1621,8 @@ static int virtnet_probe(struct virtio_device *vdev)
        if (err)
                goto free_stats;
-        netif_set_real_num_tx_queues(dev, 1);
+        netif_set_real_num_tx_queues(dev, vi->curr_queue_pairs);
-        netif_set_real_num_rx_queues(dev, 1);
+        netif_set_real_num_rx_queues(dev, vi->curr_queue_pairs);
        err = register_netdev(dev);
        if (err) {
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_hw.c b/drivers/net/wireless/ath/ath9k/ar9003_hw.c
index b07f164d65cf..20e49095db2a 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_hw.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_hw.c
@@ -187,17 +187,17 @@ static void ar9003_hw_init_mode_regs(struct ath_hw *ah)
                INIT_INI_ARRAY(&ah->iniCckfirJapan2484,
                               ar9485_1_1_baseband_core_txfir_coeff_japan_2484);
-                /* Load PCIE SERDES settings from INI */
+                if (ah->config.no_pll_pwrsave) {
+                        INIT_INI_ARRAY(&ah->iniPcieSerdes,
-                /* Awake Setting */
+                                       ar9485_1_1_pcie_phy_clkreq_disable_L1);
+                        INIT_INI_ARRAY(&ah->iniPcieSerdesLowPower,
-                INIT_INI_ARRAY(&ah->iniPcieSerdes,
+                                       ar9485_1_1_pcie_phy_clkreq_disable_L1);
-                                ar9485_1_1_pcie_phy_clkreq_disable_L1);
+                } else {
+                        INIT_INI_ARRAY(&ah->iniPcieSerdes,
-                /* Sleep Setting */
+                                       ar9485_1_1_pll_on_cdr_on_clkreq_disable_L1);
+                        INIT_INI_ARRAY(&ah->iniPcieSerdesLowPower,
-                INIT_INI_ARRAY(&ah->iniPcieSerdesLowPower,
+                                       ar9485_1_1_pll_on_cdr_on_clkreq_disable_L1);
-                                ar9485_1_1_pcie_phy_clkreq_disable_L1);
+                }
        } else if (AR_SREV_9462_21(ah)) {
                INIT_INI_ARRAY(&ah->iniMac[ATH_INI_CORE],
                               ar9462_2p1_mac_core);
diff --git a/drivers/net/wireless/ath/ath9k/ar9485_initvals.h b/drivers/net/wireless/ath/ath9k/ar9485_initvals.h
index 6f899c692647..7c1845221e1c 100644
--- a/drivers/net/wireless/ath/ath9k/ar9485_initvals.h
+++ b/drivers/net/wireless/ath/ath9k/ar9485_initvals.h
@@ -32,13 +32,6 @@ static const u32 ar9485_1_1_mac_postamble[][5] = {
        {0x00008318, 0x00003e80, 0x00007d00, 0x00006880, 0x00003440},
 };
-static const u32 ar9485_1_1_pcie_phy_pll_on_clkreq_disable_L1[][2] = {
-        /* Addr      allmodes  */
-        {0x00018c00, 0x18012e5e},
-        {0x00018c04, 0x000801d8},
-        {0x00018c08, 0x0000080c},
-};
 static const u32 ar9485Common_wo_xlna_rx_gain_1_1[][2] = {
        /* Addr      allmodes  */
        {0x00009e00, 0x037216a0},
@@ -1101,20 +1094,6 @@ static const u32 ar9485_common_rx_gain_1_1[][2] = {
        {0x0000a1fc, 0x00000296},
 };
-static const u32 ar9485_1_1_pcie_phy_pll_on_clkreq_enable_L1[][2] = {
-        /* Addr      allmodes  */
-        {0x00018c00, 0x18052e5e},
-        {0x00018c04, 0x000801d8},
-        {0x00018c08, 0x0000080c},
-};
-static const u32 ar9485_1_1_pcie_phy_clkreq_enable_L1[][2] = {
-        /* Addr      allmodes  */
-        {0x00018c00, 0x18053e5e},
-        {0x00018c04, 0x000801d8},
-        {0x00018c08, 0x0000080c},
-};
 static const u32 ar9485_1_1_soc_preamble[][2] = {
        /* Addr      allmodes  */
        {0x00004014, 0xba280400},
@@ -1173,13 +1152,6 @@ static const u32 ar9485_1_1_baseband_postamble[][5] = {
        {0x0000be18, 0x00000000, 0x00000000, 0x00000000, 0x00000000},
 };
-static const u32 ar9485_1_1_pcie_phy_clkreq_disable_L1[][2] = {
-        /* Addr      allmodes  */
-        {0x00018c00, 0x18013e5e},
-        {0x00018c04, 0x000801d8},
-        {0x00018c08, 0x0000080c},
-};
 static const u32 ar9485_1_1_radio_postamble[][2] = {
        /* Addr      allmodes  */
        {0x0001609c, 0x0b283f31},
@@ -1358,4 +1330,18 @@ static const u32 ar9485_1_1_baseband_core_txfir_coeff_japan_2484[][2] = {
        {0x0000a3a0, 0xca9228ee},
 };
+static const u32 ar9485_1_1_pcie_phy_clkreq_disable_L1[][2] = {
+        /* Addr      allmodes  */
+        {0x00018c00, 0x18013e5e},
+        {0x00018c04, 0x000801d8},
+        {0x00018c08, 0x0000080c},
+};
+static const u32 ar9485_1_1_pll_on_cdr_on_clkreq_disable_L1[][2] = {
+        /* Addr      allmodes  */
+        {0x00018c00, 0x1801265e},
+        {0x00018c04, 0x000801d8},
+        {0x00018c08, 0x0000080c},
+};
 #endif /* INITVALS_9485_H */
diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h
index e7a38d844a6a..60a5da53668f 100644
--- a/drivers/net/wireless/ath/ath9k/ath9k.h
+++ b/drivers/net/wireless/ath/ath9k/ath9k.h
@@ -632,15 +632,16 @@ void ath_ant_comb_scan(struct ath_softc *sc, struct ath_rx_status *rs);
 /* Main driver core */
 /********************/
-#define ATH9K_PCI_CUS198      0x0001
+#define ATH9K_PCI_CUS198          0x0001
-#define ATH9K_PCI_CUS230      0x0002
+#define ATH9K_PCI_CUS230          0x0002
-#define ATH9K_PCI_CUS217      0x0004
+#define ATH9K_PCI_CUS217          0x0004
-#define ATH9K_PCI_CUS252      0x0008
+#define ATH9K_PCI_CUS252          0x0008
-#define ATH9K_PCI_WOW         0x0010
+#define ATH9K_PCI_WOW             0x0010
-#define ATH9K_PCI_BT_ANT_DIV  0x0020
+#define ATH9K_PCI_BT_ANT_DIV      0x0020
-#define ATH9K_PCI_D3_L1_WAR   0x0040
+#define ATH9K_PCI_D3_L1_WAR       0x0040
-#define ATH9K_PCI_AR9565_1ANT 0x0080
+#define ATH9K_PCI_AR9565_1ANT     0x0080
-#define ATH9K_PCI_AR9565_2ANT 0x0100
+#define ATH9K_PCI_AR9565_2ANT     0x0100
+#define ATH9K_PCI_NO_PLL_PWRSAVE  0x0200
 /*
 * Default cache line size, in bytes.
diff --git a/drivers/net/wireless/ath/ath9k/dfs_debug.c b/drivers/net/wireless/ath/ath9k/dfs_debug.c
index 90b8342d1ed4..8824610c21fb 100644
--- a/drivers/net/wireless/ath/ath9k/dfs_debug.c
+++ b/drivers/net/wireless/ath/ath9k/dfs_debug.c
@@ -44,14 +44,20 @@ static ssize_t read_file_dfs(struct file *file, char __user *user_buf,
        if (buf == NULL)
                return -ENOMEM;
-        if (sc->dfs_detector)
-                dfs_pool_stats = sc->dfs_detector->get_stats(sc->dfs_detector);
        len += scnprintf(buf + len, size - len, "DFS support for "
                         "macVersion = 0x%x, macRev = 0x%x: %s\n",
                         hw_ver->macVersion, hw_ver->macRev,
                         (sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_DFS) ?
                                        "enabled" : "disabled");
+        if (!sc->dfs_detector) {
+                len += scnprintf(buf + len, size - len,
+                                 "DFS detector not enabled\n");
+                goto exit;
+        }
+        dfs_pool_stats = sc->dfs_detector->get_stats(sc->dfs_detector);
        len += scnprintf(buf + len, size - len, "Pulse detector statistics:\n");
        ATH9K_DFS_STAT("pulse events reported   ", pulses_total);
        ATH9K_DFS_STAT("invalid pulse events    ", pulses_no_dfs);
@@ -76,6 +82,7 @@ static ssize_t read_file_dfs(struct file *file, char __user *user_buf,
        ATH9K_DFS_POOL_STAT("Seqs. alloc error       ", pseq_alloc_error);
        ATH9K_DFS_POOL_STAT("Seqs. in use            ", pseq_used);
+exit:
        if (len > size)
                len = size;
diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h
index 9ea24f1cba73..a2c9a5dbac6b 100644
--- a/drivers/net/wireless/ath/ath9k/hw.h
+++ b/drivers/net/wireless/ath/ath9k/hw.h
@@ -316,6 +316,7 @@ struct ath9k_ops_config {
        u32 ant_ctrl_comm2g_switch_enable;
        bool xatten_margin_cfg;
        bool alt_mingainidx;
+        bool no_pll_pwrsave;
 };
 enum ath9k_int {
diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c
index d8643ebabd30..710192ed27ed 100644
--- a/drivers/net/wireless/ath/ath9k/init.c
+++ b/drivers/net/wireless/ath/ath9k/init.c
@@ -609,6 +609,11 @@ static void ath9k_init_platform(struct ath_softc *sc)
                ah->config.pcie_waen = 0x0040473b;
                ath_info(common, "Enable WAR for ASPM D3/L1\n");
        }
+        if (sc->driver_data & ATH9K_PCI_NO_PLL_PWRSAVE) {
+                ah->config.no_pll_pwrsave = true;
+                ath_info(common, "Disable PLL PowerSave\n");
+        }
 }
 static void ath9k_eeprom_request_cb(const struct firmware *eeprom_blob,
@@ -863,8 +868,8 @@ static const struct ieee80211_iface_combination if_comb[] = {
                .max_interfaces = 1,
                .num_different_channels = 1,
                .beacon_int_infra_match = true,
-                .radar_detect_widths =  BIT(NL80211_CHAN_NO_HT) |
+                .radar_detect_widths =  BIT(NL80211_CHAN_WIDTH_20_NOHT) |
-                                        BIT(NL80211_CHAN_HT20),
+                                        BIT(NL80211_CHAN_WIDTH_20),
        }
 };
diff --git a/drivers/net/wireless/ath/ath9k/pci.c b/drivers/net/wireless/ath/ath9k/pci.c
index 7e4c2524b630..b5656fce4ff5 100644
--- a/drivers/net/wireless/ath/ath9k/pci.c
+++ b/drivers/net/wireless/ath/ath9k/pci.c
@@ -195,6 +195,93 @@ static DEFINE_PCI_DEVICE_TABLE(ath_pci_id_table) = {
                         0x3219),
          .driver_data = ATH9K_PCI_BT_ANT_DIV },
+        /* AR9485 cards with PLL power-save disabled by default. */
+        { PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
+                         0x0032,
+                         PCI_VENDOR_ID_AZWAVE,
+                         0x2C97),
+          .driver_data = ATH9K_PCI_NO_PLL_PWRSAVE },
+        { PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
+                         0x0032,
+                         PCI_VENDOR_ID_AZWAVE,
+                         0x2100),
+          .driver_data = ATH9K_PCI_NO_PLL_PWRSAVE },
+        { PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
+                         0x0032,
+                         0x1C56, /* ASKEY */
+                         0x4001),
+          .driver_data = ATH9K_PCI_NO_PLL_PWRSAVE },
+        { PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
+                         0x0032,
+                         0x11AD, /* LITEON */
+                         0x6627),
+          .driver_data = ATH9K_PCI_NO_PLL_PWRSAVE },
+        { PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
+                         0x0032,
+                         0x11AD, /* LITEON */
+                         0x6628),
+          .driver_data = ATH9K_PCI_NO_PLL_PWRSAVE },
+        { PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
+                         0x0032,
+                         PCI_VENDOR_ID_FOXCONN,
+                         0xE04E),
+          .driver_data = ATH9K_PCI_NO_PLL_PWRSAVE },
+        { PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
+                         0x0032,
+                         PCI_VENDOR_ID_FOXCONN,
+                         0xE04F),
+          .driver_data = ATH9K_PCI_NO_PLL_PWRSAVE },
+        { PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
+                         0x0032,
+                         0x144F, /* ASKEY */
+                         0x7197),
+          .driver_data = ATH9K_PCI_NO_PLL_PWRSAVE },
+        { PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
+                         0x0032,
+                         0x1B9A, /* XAVI */
+                         0x2000),
+          .driver_data = ATH9K_PCI_NO_PLL_PWRSAVE },
+        { PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
+                         0x0032,
+                         0x1B9A, /* XAVI */
+                         0x2001),
+          .driver_data = ATH9K_PCI_NO_PLL_PWRSAVE },
+        { PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
+                         0x0032,
+                         PCI_VENDOR_ID_AZWAVE,
+                         0x1186),
+          .driver_data = ATH9K_PCI_NO_PLL_PWRSAVE },
+        { PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
+                         0x0032,
+                         PCI_VENDOR_ID_AZWAVE,
+                         0x1F86),
+          .driver_data = ATH9K_PCI_NO_PLL_PWRSAVE },
+        { PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
+                         0x0032,
+                         PCI_VENDOR_ID_AZWAVE,
+                         0x1195),
+          .driver_data = ATH9K_PCI_NO_PLL_PWRSAVE },
+        { PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
+                         0x0032,
+                         PCI_VENDOR_ID_AZWAVE,
+                         0x1F95),
+          .driver_data = ATH9K_PCI_NO_PLL_PWRSAVE },
+        { PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
+                         0x0032,
+                         0x1B9A, /* XAVI */
+                         0x1C00),
+          .driver_data = ATH9K_PCI_NO_PLL_PWRSAVE },
+        { PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
+                         0x0032,
+                         0x1B9A, /* XAVI */
+                         0x1C01),
+          .driver_data = ATH9K_PCI_NO_PLL_PWRSAVE },
+        { PCI_DEVICE_SUB(PCI_VENDOR_ID_ATHEROS,
+                         0x0032,
+                         PCI_VENDOR_ID_ASUSTEK,
+                         0x850D),
+          .driver_data = ATH9K_PCI_NO_PLL_PWRSAVE },
        { PCI_VDEVICE(ATHEROS, 0x0032) }, /* PCI-E  AR9485 */
        { PCI_VDEVICE(ATHEROS, 0x0033) }, /* PCI-E  AR9580 */
diff --git a/drivers/net/wireless/ath/wcn36xx/debug.c b/drivers/net/wireless/ath/wcn36xx/debug.c
index 5b84f7ae0b1e..ef44a2da644d 100644
--- a/drivers/net/wireless/ath/wcn36xx/debug.c
+++ b/drivers/net/wireless/ath/wcn36xx/debug.c
@@ -126,7 +126,7 @@ static ssize_t write_file_dump(struct file *file,
                if (begin == NULL)
                        break;
-                if (kstrtoul(begin, 0, (unsigned long *)(arg + i)) != 0)
+                if (kstrtou32(begin, 0, &arg[i]) != 0)
                        break;
        }
diff --git a/drivers/net/wireless/ath/wcn36xx/smd.c b/drivers/net/wireless/ath/wcn36xx/smd.c
index f8c3a10510c2..de9eb2cfbf4b 100644
--- a/drivers/net/wireless/ath/wcn36xx/smd.c
+++ b/drivers/net/wireless/ath/wcn36xx/smd.c
@@ -1286,7 +1286,8 @@ int wcn36xx_smd_send_beacon(struct wcn36xx *wcn, struct ieee80211_vif *vif,
        } else {
                wcn36xx_err("Beacon is to big: beacon size=%d\n",
                              msg_body.beacon_length);
-                return -ENOMEM;
+                ret = -ENOMEM;
+                goto out;
        }
        memcpy(msg_body.bssid, vif->addr, ETH_ALEN);
@@ -1327,7 +1328,8 @@ int wcn36xx_smd_update_proberesp_tmpl(struct wcn36xx *wcn,
        if (skb->len > BEACON_TEMPLATE_SIZE) {
                wcn36xx_warn("probe response template is too big: %d\n",
                             skb->len);
-                return -E2BIG;
+                ret = -E2BIG;
+                goto out;
        }
        msg.probe_resp_template_len = skb->len;
@@ -1606,7 +1608,8 @@ int wcn36xx_smd_keep_alive_req(struct wcn36xx *wcn,
                /* TODO: it also support ARP response type */
        } else {
                wcn36xx_warn("unknow keep alive packet type %d\n", packet_type);
-                return -EINVAL;
+                ret = -EINVAL;
+                goto out;
        }
        PREPARE_HAL_BUF(wcn->hal_buf, msg_body);
diff --git a/drivers/net/wireless/libertas/debugfs.c b/drivers/net/wireless/libertas/debugfs.c
index 668dd27616a0..cc6a0a586f0b 100644
--- a/drivers/net/wireless/libertas/debugfs.c
+++ b/drivers/net/wireless/libertas/debugfs.c
@@ -913,7 +913,10 @@ static ssize_t lbs_debugfs_write(struct file *f, const char __user *buf,
        char *p2;
        struct debug_data *d = f->private_data;
-        pdata = kmalloc(cnt, GFP_KERNEL);
+        if (cnt == 0)
+                return 0;
+        pdata = kmalloc(cnt + 1, GFP_KERNEL);
        if (pdata == NULL)
                return 0;
@@ -922,6 +925,7 @@ static ssize_t lbs_debugfs_write(struct file *f, const char __user *buf,
                kfree(pdata);
                return 0;
        }
+        pdata[cnt] = '\0';
        p0 = pdata;
        for (i = 0; i < num_of_items; i++) {
diff --git a/drivers/net/wireless/libertas/if_cs.c b/drivers/net/wireless/libertas/if_cs.c
index ef8c98e21098..f499efc6abcf 100644
--- a/drivers/net/wireless/libertas/if_cs.c
+++ b/drivers/net/wireless/libertas/if_cs.c
@@ -902,6 +902,7 @@ static int if_cs_probe(struct pcmcia_device *p_dev)
        if (card->model == MODEL_UNKNOWN) {
                pr_err("unsupported manf_id 0x%04x / card_id 0x%04x\n",
                       p_dev->manf_id, p_dev->card_id);
+                ret = -ENODEV;
                goto out2;
        }
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index de0df86704e7..9df7bc91a26f 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -2097,7 +2097,7 @@ out:
 }
 /* Generic Netlink operations array */
-static struct genl_ops hwsim_ops[] = {
+static const struct genl_ops hwsim_ops[] = {
        {
                .cmd = HWSIM_CMD_REGISTER,
                .policy = hwsim_genl_policy,
@@ -2148,8 +2148,7 @@ static int hwsim_init_netlink(void)
        printk(KERN_INFO "mac80211_hwsim: initializing netlink\n");
-        rc = genl_register_family_with_ops(&hwsim_genl_family,
+        rc = genl_register_family_with_ops(&hwsim_genl_family, hwsim_ops);
-                hwsim_ops, ARRAY_SIZE(hwsim_ops));
        if (rc)
                goto failure;
diff --git a/drivers/net/wireless/mwifiex/fw.h b/drivers/net/wireless/mwifiex/fw.h
index f80f30b6160e..c8385ec77a86 100644
--- a/drivers/net/wireless/mwifiex/fw.h
+++ b/drivers/net/wireless/mwifiex/fw.h
@@ -1020,8 +1020,8 @@ struct mwifiex_power_group {
 } __packed;
 struct mwifiex_types_power_group {
-        u16 type;
+        __le16 type;
-        u16 length;
+        __le16 length;
 } __packed;
 struct host_cmd_ds_txpwr_cfg {
diff --git a/drivers/net/wireless/mwifiex/ie.c b/drivers/net/wireless/mwifiex/ie.c
index 220af4fe0fc6..81ac001ee741 100644
--- a/drivers/net/wireless/mwifiex/ie.c
+++ b/drivers/net/wireless/mwifiex/ie.c
@@ -82,7 +82,7 @@ mwifiex_update_autoindex_ies(struct mwifiex_private *priv,
                             struct mwifiex_ie_list *ie_list)
 {
        u16 travel_len, index, mask;
-        s16 input_len;
+        s16 input_len, tlv_len;
        struct mwifiex_ie *ie;
        u8 *tmp;
@@ -91,11 +91,13 @@ mwifiex_update_autoindex_ies(struct mwifiex_private *priv,
        ie_list->len = 0;
-        while (input_len > 0) {
+        while (input_len >= sizeof(struct mwifiex_ie_types_header)) {
                ie = (struct mwifiex_ie *)(((u8 *)ie_list) + travel_len);
-                input_len -= le16_to_cpu(ie->ie_length) + MWIFIEX_IE_HDR_SIZE;
+                tlv_len = le16_to_cpu(ie->ie_length);
-                travel_len += le16_to_cpu(ie->ie_length) + MWIFIEX_IE_HDR_SIZE;
+                travel_len += tlv_len + MWIFIEX_IE_HDR_SIZE;
+                if (input_len < tlv_len + MWIFIEX_IE_HDR_SIZE)
+                        return -1;
                index = le16_to_cpu(ie->ie_index);
                mask = le16_to_cpu(ie->mgmt_subtype_mask);
@@ -132,6 +134,7 @@ mwifiex_update_autoindex_ies(struct mwifiex_private *priv,
                le16_add_cpu(&ie_list->len,
                             le16_to_cpu(priv->mgmt_ie[index].ie_length) +
                             MWIFIEX_IE_HDR_SIZE);
+                input_len -= tlv_len + MWIFIEX_IE_HDR_SIZE;
        }
        if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_UAP)
diff --git a/drivers/net/wireless/mwifiex/sdio.c b/drivers/net/wireless/mwifiex/sdio.c
index 1576104e3d95..9bf8898743ab 100644
--- a/drivers/net/wireless/mwifiex/sdio.c
+++ b/drivers/net/wireless/mwifiex/sdio.c
@@ -1029,7 +1029,10 @@ static int mwifiex_decode_rx_packet(struct mwifiex_adapter *adapter,
                                    struct sk_buff *skb, u32 upld_typ)
 {
        u8 *cmd_buf;
+        __le16 *curr_ptr = (__le16 *)skb->data;
+        u16 pkt_len = le16_to_cpu(*curr_ptr);
+        skb_trim(skb, pkt_len);
        skb_pull(skb, INTF_HEADER_LEN);
        switch (upld_typ) {
diff --git a/drivers/net/wireless/mwifiex/sta_cmd.c b/drivers/net/wireless/mwifiex/sta_cmd.c
index 7d66018a2e33..2181ee283d82 100644
--- a/drivers/net/wireless/mwifiex/sta_cmd.c
+++ b/drivers/net/wireless/mwifiex/sta_cmd.c
@@ -239,14 +239,14 @@ static int mwifiex_cmd_tx_power_cfg(struct host_cmd_ds_command *cmd,
                        memmove(cmd_txp_cfg, txp,
                                sizeof(struct host_cmd_ds_txpwr_cfg) +
                                sizeof(struct mwifiex_types_power_group) +
-                                pg_tlv->length);
+                                le16_to_cpu(pg_tlv->length));
                        pg_tlv = (struct mwifiex_types_power_group *) ((u8 *)
                                  cmd_txp_cfg +
                                  sizeof(struct host_cmd_ds_txpwr_cfg));
                        cmd->size = cpu_to_le16(le16_to_cpu(cmd->size) +
                                  sizeof(struct mwifiex_types_power_group) +
-                                  pg_tlv->length);
+                                  le16_to_cpu(pg_tlv->length));
                } else {
                        memmove(cmd_txp_cfg, txp, sizeof(*txp));
                }
diff --git a/drivers/net/wireless/mwifiex/sta_cmdresp.c b/drivers/net/wireless/mwifiex/sta_cmdresp.c
index 58a6013712d2..2675ca7f8d14 100644
--- a/drivers/net/wireless/mwifiex/sta_cmdresp.c
+++ b/drivers/net/wireless/mwifiex/sta_cmdresp.c
@@ -274,17 +274,20 @@ static int mwifiex_ret_tx_rate_cfg(struct mwifiex_private *priv,
        struct host_cmd_ds_tx_rate_cfg *rate_cfg = &resp->params.tx_rate_cfg;
        struct mwifiex_rate_scope *rate_scope;
        struct mwifiex_ie_types_header *head;
-        u16 tlv, tlv_buf_len;
+        u16 tlv, tlv_buf_len, tlv_buf_left;
        u8 *tlv_buf;
        u32 i;
-        tlv_buf = ((u8 *)rate_cfg) +
+        tlv_buf = ((u8 *)rate_cfg) + sizeof(struct host_cmd_ds_tx_rate_cfg);
-                        sizeof(struct host_cmd_ds_tx_rate_cfg);
+        tlv_buf_left = le16_to_cpu(resp->size) - S_DS_GEN - sizeof(*rate_cfg);
-        tlv_buf_len = le16_to_cpu(*(__le16 *) (tlv_buf + sizeof(u16)));
-        while (tlv_buf && tlv_buf_len > 0) {
+        while (tlv_buf_left >= sizeof(*head)) {
-                tlv = (*tlv_buf);
+                head = (struct mwifiex_ie_types_header *)tlv_buf;
-                tlv = tlv | (*(tlv_buf + 1) << 8);
+                tlv = le16_to_cpu(head->type);
+                tlv_buf_len = le16_to_cpu(head->len);
+                if (tlv_buf_left < (sizeof(*head) + tlv_buf_len))
+                        break;
                switch (tlv) {
                case TLV_TYPE_RATE_SCOPE:
@@ -304,9 +307,8 @@ static int mwifiex_ret_tx_rate_cfg(struct mwifiex_private *priv,
                        /* Add RATE_DROP tlv here */
                }
-                head = (struct mwifiex_ie_types_header *) tlv_buf;
+                tlv_buf += (sizeof(*head) + tlv_buf_len);
-                tlv_buf += le16_to_cpu(head->len) + sizeof(*head);
+                tlv_buf_left -= (sizeof(*head) + tlv_buf_len);
-                tlv_buf_len -= le16_to_cpu(head->len);
        }
        priv->is_data_rate_auto = mwifiex_is_rate_auto(priv);
@@ -340,13 +342,17 @@ static int mwifiex_get_power_level(struct mwifiex_private *priv, void *data_buf)
                ((u8 *) data_buf + sizeof(struct host_cmd_ds_txpwr_cfg));
        pg = (struct mwifiex_power_group *)
                ((u8 *) pg_tlv_hdr + sizeof(struct mwifiex_types_power_group));
-        length = pg_tlv_hdr->length;
+        length = le16_to_cpu(pg_tlv_hdr->length);
-        if (length > 0) {
-                max_power = pg->power_max;
+        /* At least one structure required to update power */
-                min_power = pg->power_min;
+        if (length < sizeof(struct mwifiex_power_group))
-                length -= sizeof(struct mwifiex_power_group);
+                return 0;
-        }
-        while (length) {
+        max_power = pg->power_max;
+        min_power = pg->power_min;
+        length -= sizeof(struct mwifiex_power_group);
+        while (length >= sizeof(struct mwifiex_power_group)) {
                pg++;
                if (max_power < pg->power_max)
                        max_power = pg->power_max;
@@ -356,10 +362,8 @@ static int mwifiex_get_power_level(struct mwifiex_private *priv, void *data_buf)
                length -= sizeof(struct mwifiex_power_group);
        }
-        if (pg_tlv_hdr->length > 0) {
+        priv->min_tx_power_level = (u8) min_power;
-                priv->min_tx_power_level = (u8) min_power;
+        priv->max_tx_power_level = (u8) max_power;
-                priv->max_tx_power_level = (u8) max_power;
-        }
        return 0;
 }
diff --git a/drivers/net/wireless/mwifiex/sta_ioctl.c b/drivers/net/wireless/mwifiex/sta_ioctl.c
index f084412eee0b..c8e029df770e 100644
--- a/drivers/net/wireless/mwifiex/sta_ioctl.c
+++ b/drivers/net/wireless/mwifiex/sta_ioctl.c
@@ -638,8 +638,9 @@ int mwifiex_set_tx_power(struct mwifiex_private *priv,
                txp_cfg->mode = cpu_to_le32(1);
                pg_tlv = (struct mwifiex_types_power_group *)
                         (buf + sizeof(struct host_cmd_ds_txpwr_cfg));
-                pg_tlv->type = TLV_TYPE_POWER_GROUP;
+                pg_tlv->type = cpu_to_le16(TLV_TYPE_POWER_GROUP);
-                pg_tlv->length = 4 * sizeof(struct mwifiex_power_group);
+                pg_tlv->length =
+                        cpu_to_le16(4 * sizeof(struct mwifiex_power_group));
                pg = (struct mwifiex_power_group *)
                     (buf + sizeof(struct host_cmd_ds_txpwr_cfg)
                      + sizeof(struct mwifiex_types_power_group));
diff --git a/drivers/net/wireless/mwifiex/uap_txrx.c b/drivers/net/wireless/mwifiex/uap_txrx.c
index 1cfe5a738c47..92f76d655e6c 100644
--- a/drivers/net/wireless/mwifiex/uap_txrx.c
+++ b/drivers/net/wireless/mwifiex/uap_txrx.c
@@ -97,6 +97,7 @@ static void mwifiex_uap_queue_bridged_pkt(struct mwifiex_private *priv,
        struct mwifiex_txinfo *tx_info;
        int hdr_chop;
        struct timeval tv;
+        struct ethhdr *p_ethhdr;
        u8 rfc1042_eth_hdr[ETH_ALEN] = { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0x00 };
        uap_rx_pd = (struct uap_rxpd *)(skb->data);
@@ -112,14 +113,36 @@ static void mwifiex_uap_queue_bridged_pkt(struct mwifiex_private *priv,
        }
        if (!memcmp(&rx_pkt_hdr->rfc1042_hdr,
-                    rfc1042_eth_hdr, sizeof(rfc1042_eth_hdr)))
+                    rfc1042_eth_hdr, sizeof(rfc1042_eth_hdr))) {
+                /* Replace the 803 header and rfc1042 header (llc/snap) with
+                 * an Ethernet II header, keep the src/dst and snap_type
+                 * (ethertype).
+                 *
+                 * The firmware only passes up SNAP frames converting all RX
+                 * data from 802.11 to 802.2/LLC/SNAP frames.
+                 *
+                 * To create the Ethernet II, just move the src, dst address
+                 * right before the snap_type.
+                 */
+                p_ethhdr = (struct ethhdr *)
+                        ((u8 *)(&rx_pkt_hdr->eth803_hdr)
+                         + sizeof(rx_pkt_hdr->eth803_hdr)
+                         + sizeof(rx_pkt_hdr->rfc1042_hdr)
+                         - sizeof(rx_pkt_hdr->eth803_hdr.h_dest)
+                         - sizeof(rx_pkt_hdr->eth803_hdr.h_source)
+                         - sizeof(rx_pkt_hdr->rfc1042_hdr.snap_type));
+                memcpy(p_ethhdr->h_source, rx_pkt_hdr->eth803_hdr.h_source,
+                       sizeof(p_ethhdr->h_source));
+                memcpy(p_ethhdr->h_dest, rx_pkt_hdr->eth803_hdr.h_dest,
+                       sizeof(p_ethhdr->h_dest));
                /* Chop off the rxpd + the excess memory from
                 * 802.2/llc/snap header that was removed.
                 */
-                hdr_chop = (u8 *)eth_hdr - (u8 *)uap_rx_pd;
+                hdr_chop = (u8 *)p_ethhdr - (u8 *)uap_rx_pd;
-        else
+        } else {
                /* Chop off the rxpd */
                hdr_chop = (u8 *)&rx_pkt_hdr->eth803_hdr - (u8 *)uap_rx_pd;
+        }
        /* Chop off the leading header bytes so the it points
         * to the start of either the reconstructed EthII frame
diff --git a/drivers/net/wireless/mwifiex/wmm.c b/drivers/net/wireless/mwifiex/wmm.c
index 5dd0ccc70b86..13eaeed03898 100644
--- a/drivers/net/wireless/mwifiex/wmm.c
+++ b/drivers/net/wireless/mwifiex/wmm.c
@@ -722,6 +722,9 @@ int mwifiex_ret_wmm_get_status(struct mwifiex_private *priv,
                tlv_hdr = (struct mwifiex_ie_types_data *) curr;
                tlv_len = le16_to_cpu(tlv_hdr->header.len);
+                if (resp_len < tlv_len + sizeof(tlv_hdr->header))
+                        break;
                switch (le16_to_cpu(tlv_hdr->header.type)) {
                case TLV_TYPE_WMMQSTATUS:
                        tlv_wmm_qstatus =
diff --git a/drivers/net/wireless/prism54/islpci_dev.c b/drivers/net/wireless/prism54/islpci_dev.c
index 41a16d30c79c..e05d9b4c8317 100644
--- a/drivers/net/wireless/prism54/islpci_dev.c
+++ b/drivers/net/wireless/prism54/islpci_dev.c
@@ -811,6 +811,10 @@ static const struct net_device_ops islpci_netdev_ops = {
        .ndo_validate_addr      = eth_validate_addr,
 };
+static struct device_type wlan_type = {
+        .name   = "wlan",
+};
 struct net_device *
 islpci_setup(struct pci_dev *pdev)
 {
@@ -821,9 +825,8 @@ islpci_setup(struct pci_dev *pdev)
                return ndev;
        pci_set_drvdata(pdev, ndev);
-#if defined(SET_NETDEV_DEV)
        SET_NETDEV_DEV(ndev, &pdev->dev);
-#endif
+        SET_NETDEV_DEVTYPE(ndev, &wlan_type);
        /* setup the structure members */
        ndev->base_addr = pci_resource_start(pdev, 0);
diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c
index c5738f14c4ba..776aff3678ff 100644
--- a/drivers/net/wireless/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/rt2x00/rt2800lib.c
@@ -2640,7 +2640,7 @@ static void rt2800_config_channel_rf53xx(struct rt2x00_dev *rt2x00dev,
        if (rt2x00_rt(rt2x00dev, RT5392)) {
                rt2800_rfcsr_read(rt2x00dev, 50, &rfcsr);
-                if (info->default_power1 > POWER_BOUND)
+                if (info->default_power2 > POWER_BOUND)
                        rt2x00_set_field8(&rfcsr, RFCSR50_TX, POWER_BOUND);
                else
                        rt2x00_set_field8(&rfcsr, RFCSR50_TX,
diff --git a/drivers/net/wireless/rt2x00/rt2x00lib.h b/drivers/net/wireless/rt2x00/rt2x00lib.h
index a0935987fa3a..7f40ab8e1bd8 100644
--- a/drivers/net/wireless/rt2x00/rt2x00lib.h
+++ b/drivers/net/wireless/rt2x00/rt2x00lib.h
@@ -146,7 +146,7 @@ void rt2x00queue_remove_l2pad(struct sk_buff *skb, unsigned int header_length);
 * @local: frame is not from mac80211
 */
 int rt2x00queue_write_tx_frame(struct data_queue *queue, struct sk_buff *skb,
-                               bool local);
+                               struct ieee80211_sta *sta, bool local);
 /**
 * rt2x00queue_update_beacon - Send new beacon from mac80211
diff --git a/drivers/net/wireless/rt2x00/rt2x00mac.c b/drivers/net/wireless/rt2x00/rt2x00mac.c
index 7c157857f5ce..2183e7978399 100644
--- a/drivers/net/wireless/rt2x00/rt2x00mac.c
+++ b/drivers/net/wireless/rt2x00/rt2x00mac.c
@@ -90,7 +90,7 @@ static int rt2x00mac_tx_rts_cts(struct rt2x00_dev *rt2x00dev,
                                  frag_skb->data, data_length, tx_info,
                                  (struct ieee80211_rts *)(skb->data));
-        retval = rt2x00queue_write_tx_frame(queue, skb, true);
+        retval = rt2x00queue_write_tx_frame(queue, skb, NULL, true);
        if (retval) {
                dev_kfree_skb_any(skb);
                rt2x00_warn(rt2x00dev, "Failed to send RTS/CTS frame\n");
@@ -151,7 +151,7 @@ void rt2x00mac_tx(struct ieee80211_hw *hw,
                        goto exit_fail;
        }
-        if (unlikely(rt2x00queue_write_tx_frame(queue, skb, false)))
+        if (unlikely(rt2x00queue_write_tx_frame(queue, skb, control->sta, false)))
                goto exit_fail;
        /*
diff --git a/drivers/net/wireless/rt2x00/rt2x00queue.c b/drivers/net/wireless/rt2x00/rt2x00queue.c
index 50590b1420a5..a5d38e8ad9e4 100644
--- a/drivers/net/wireless/rt2x00/rt2x00queue.c
+++ b/drivers/net/wireless/rt2x00/rt2x00queue.c
@@ -635,7 +635,7 @@ static void rt2x00queue_bar_check(struct queue_entry *entry)
 }
 int rt2x00queue_write_tx_frame(struct data_queue *queue, struct sk_buff *skb,
-                               bool local)
+                               struct ieee80211_sta *sta, bool local)
 {
        struct ieee80211_tx_info *tx_info;
        struct queue_entry *entry;
@@ -649,7 +649,7 @@ int rt2x00queue_write_tx_frame(struct data_queue *queue, struct sk_buff *skb,
         * after that we are free to use the skb->cb array
         * for our information.
         */
-        rt2x00queue_create_tx_descriptor(queue->rt2x00dev, skb, &txdesc, NULL);
+        rt2x00queue_create_tx_descriptor(queue->rt2x00dev, skb, &txdesc, sta);
        /*
         * All information is retrieved from the skb->cb array,
diff --git a/drivers/net/wireless/rtlwifi/base.c b/drivers/net/wireless/rtlwifi/base.c
index 9a78e3daf742..ff784072fb42 100644
--- a/drivers/net/wireless/rtlwifi/base.c
+++ b/drivers/net/wireless/rtlwifi/base.c
@@ -37,6 +37,7 @@
 #include <linux/ip.h>
 #include <linux/module.h>
+#include <linux/udp.h>
 /*
 *NOTICE!!!: This file will be very big, we should
@@ -1074,64 +1075,52 @@ u8 rtl_is_special_data(struct ieee80211_hw *hw, struct sk_buff *skb, u8 is_tx)
        if (!ieee80211_is_data(fc))
                return false;
+        ip = (const struct iphdr *)(skb->data + mac_hdr_len +
+                                    SNAP_SIZE + PROTOC_TYPE_SIZE);
+        ether_type = be16_to_cpup((__be16 *)
+                                  (skb->data + mac_hdr_len + SNAP_SIZE));
-        ip = (struct iphdr *)((u8 *) skb->data + mac_hdr_len +
+        switch (ether_type) {
-                              SNAP_SIZE + PROTOC_TYPE_SIZE);
+        case ETH_P_IP: {
-        ether_type = *(u16 *) ((u8 *) skb->data + mac_hdr_len + SNAP_SIZE);
+                struct udphdr *udp;
-        /*      ether_type = ntohs(ether_type); */
+                u16 src;
+                u16 dst;
-        if (ETH_P_IP == ether_type) {
-                if (IPPROTO_UDP == ip->protocol) {
-                        struct udphdr *udp = (struct udphdr *)((u8 *) ip +
-                                                               (ip->ihl << 2));
-                        if (((((u8 *) udp)[1] == 68) &&
-                             (((u8 *) udp)[3] == 67)) ||
-                            ((((u8 *) udp)[1] == 67) &&
-                             (((u8 *) udp)[3] == 68))) {
-                                /*
-                                 * 68 : UDP BOOTP client
-                                 * 67 : UDP BOOTP server
-                                 */
-                                RT_TRACE(rtlpriv, (COMP_SEND | COMP_RECV),
-                                         DBG_DMESG, "dhcp %s !!\n",
-                                         is_tx ? "Tx" : "Rx");
-                                if (is_tx) {
-                                        rtlpriv->enter_ps = false;
-                                        schedule_work(&rtlpriv->
-                                                      works.lps_change_work);
-                                        ppsc->last_delaylps_stamp_jiffies =
-                                            jiffies;
-                                }
-                                return true;
+                if (ip->protocol != IPPROTO_UDP)
-                        }
+                        return false;
-                }
+                udp = (struct udphdr *)((u8 *)ip + (ip->ihl << 2));
-        } else if (ETH_P_ARP == ether_type) {
+                src = be16_to_cpu(udp->source);
-                if (is_tx) {
+                dst = be16_to_cpu(udp->dest);
-                        rtlpriv->enter_ps = false;
-                        schedule_work(&rtlpriv->works.lps_change_work);
-                        ppsc->last_delaylps_stamp_jiffies = jiffies;
-                }
-                return true;
+                /* If this case involves port 68 (UDP BOOTP client) connecting
-        } else if (ETH_P_PAE == ether_type) {
+                 * with port 67 (UDP BOOTP server), then return true so that
+                 * the lowest speed is used.
+                 */
+                if (!((src == 68 && dst == 67) || (src == 67 && dst == 68)))
+                        return false;
+                RT_TRACE(rtlpriv, (COMP_SEND | COMP_RECV), DBG_DMESG,
+                         "dhcp %s !!\n", is_tx ? "Tx" : "Rx");
+                break;
+        }
+        case ETH_P_ARP:
+                break;
+        case ETH_P_PAE:
                RT_TRACE(rtlpriv, (COMP_SEND | COMP_RECV), DBG_DMESG,
                         "802.1X %s EAPOL pkt!!\n", is_tx ? "Tx" : "Rx");
+                break;
-                if (is_tx) {
+        case ETH_P_IPV6:
-                        rtlpriv->enter_ps = false;
+                /* TODO: Is this right? */
-                        schedule_work(&rtlpriv->works.lps_change_work);
+                return false;
-                        ppsc->last_delaylps_stamp_jiffies = jiffies;
+        default:
-                }
+                return false;
-                return true;
-        } else if (ETH_P_IPV6 == ether_type) {
-                /* IPv6 */
-                return true;
        }
+        if (is_tx) {
-        return false;
+                rtlpriv->enter_ps = false;
+                schedule_work(&rtlpriv->works.lps_change_work);
+                ppsc->last_delaylps_stamp_jiffies = jiffies;
+        }
+        return true;
 }
 EXPORT_SYMBOL_GPL(rtl_is_special_data);
diff --git a/drivers/net/wireless/rtlwifi/efuse.c b/drivers/net/wireless/rtlwifi/efuse.c
index ae13fb94b2e8..2ffc7298f686 100644
--- a/drivers/net/wireless/rtlwifi/efuse.c
+++ b/drivers/net/wireless/rtlwifi/efuse.c
@@ -262,9 +262,9 @@ void read_efuse(struct ieee80211_hw *hw, u16 _offset, u16 _size_byte, u8 *pbuf)
                            sizeof(u8), GFP_ATOMIC);
        if (!efuse_tbl)
                return;
-        efuse_word = kmalloc(EFUSE_MAX_WORD_UNIT * sizeof(u16 *), GFP_ATOMIC);
+        efuse_word = kzalloc(EFUSE_MAX_WORD_UNIT * sizeof(u16 *), GFP_ATOMIC);
        if (!efuse_word)
-                goto done;
+                goto out;
        for (i = 0; i < EFUSE_MAX_WORD_UNIT; i++) {
                efuse_word[i] = kmalloc(efuse_max_section * sizeof(u16),
                                        GFP_ATOMIC);
@@ -378,6 +378,7 @@ done:
        for (i = 0; i < EFUSE_MAX_WORD_UNIT; i++)
                kfree(efuse_word[i]);
        kfree(efuse_word);
+out:
        kfree(efuse_tbl);
 }
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c b/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c
index 25e50ffc44ec..b0c346a9e4b8 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c
@@ -349,7 +349,7 @@ bool rtl92cu_rx_query_desc(struct ieee80211_hw *hw,
                                                 p_drvinfo);
        }
        /*rx_status->qual = stats->signal; */
-        rx_status->signal = stats->rssi + 10;
+        rx_status->signal = stats->recvsignalpower + 10;
        return true;
 }
diff --git a/drivers/net/wireless/rtlwifi/rtl8192de/trx.c b/drivers/net/wireless/rtlwifi/rtl8192de/trx.c
index 945ddecf90c9..0eb0f4ae5920 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192de/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192de/trx.c
@@ -525,7 +525,7 @@ bool rtl92de_rx_query_desc(struct ieee80211_hw *hw,	struct rtl_stats *stats,
                                                   p_drvinfo);
        }
        /*rx_status->qual = stats->signal; */
-        rx_status->signal = stats->rssi + 10;
+        rx_status->signal = stats->recvsignalpower + 10;
        return true;
 }
diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/rf.c b/drivers/net/wireless/rtlwifi/rtl8192se/rf.c
index 5061f1db3f02..92d38ab3c60e 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192se/rf.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192se/rf.c
@@ -265,7 +265,7 @@ static void _rtl92s_get_txpower_writeval_byregulatory(struct ieee80211_hw *hw,
                                    rtlefuse->pwrgroup_ht40
                                    [RF90_PATH_A][chnl - 1]) {
                                        pwrdiff_limit[i] =
-                                          rtlefuse->pwrgroup_ht20
+                                          rtlefuse->pwrgroup_ht40
                                          [RF90_PATH_A][chnl - 1];
                                }
                        } else {
diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/trx.c b/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
index 222d2e792ca6..27efbcdac6a9 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
@@ -329,7 +329,7 @@ bool rtl92se_rx_query_desc(struct ieee80211_hw *hw, struct rtl_stats *stats,
        }
        /*rx_status->qual = stats->signal; */
-        rx_status->signal = stats->rssi + 10;
+        rx_status->signal = stats->recvsignalpower + 10;
        return true;
 }
diff --git a/drivers/net/wireless/rtlwifi/wifi.h b/drivers/net/wireless/rtlwifi/wifi.h
index d224dc3bb092..0c65386fa30d 100644
--- a/drivers/net/wireless/rtlwifi/wifi.h
+++ b/drivers/net/wireless/rtlwifi/wifi.h
@@ -77,11 +77,7 @@
 #define RTL_SLOT_TIME_9                         9
 #define RTL_SLOT_TIME_20                        20
-/*related with tcp/ip. */
+/*related to tcp/ip. */
-/*if_ehther.h*/
-#define ETH_P_PAE               0x888E  /*Port Access Entity (IEEE 802.1X) */
-#define ETH_P_IP                0x0800  /*Internet Protocol packet */
-#define ETH_P_ARP               0x0806  /*Address Resolution packet */
 #define SNAP_SIZE               6
 #define PROTOC_TYPE_SIZE        2
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index d85e66979711..e59acb1daa23 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -277,12 +277,13 @@ static void xennet_alloc_rx_buffers(struct net_device *dev)
                if (!page) {
                        kfree_skb(skb);
 no_skb:
-                        /* Any skbuffs queued for refill? Force them out. */
-                        if (i != 0)
-                                goto refill;
                        /* Could not allocate any skbuffs. Try again later. */
                        mod_timer(&np->rx_refill_timer,
                                  jiffies + (HZ/10));
+                        /* Any skbuffs queued for refill? Force them out. */
+                        if (i != 0)
+                                goto refill;
                        break;
                }
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index 12a9e83c008b..d0222f13d154 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -1034,10 +1034,9 @@ static void ntb_async_rx(struct ntb_queue_entry *entry, void *offset,
        struct dma_chan *chan = qp->dma_chan;
        struct dma_device *device;
        size_t pay_off, buff_off;
-        dma_addr_t src, dest;
+        struct dmaengine_unmap_data *unmap;
        dma_cookie_t cookie;
        void *buf = entry->buf;
-        unsigned long flags;
        entry->len = len;
@@ -1045,35 +1044,49 @@ static void ntb_async_rx(struct ntb_queue_entry *entry, void *offset,
                goto err;
        if (len < copy_bytes) 
-                goto err1;
+                goto err_wait;
        device = chan->device;
        pay_off = (size_t) offset & ~PAGE_MASK;
        buff_off = (size_t) buf & ~PAGE_MASK;
        if (!is_dma_copy_aligned(device, pay_off, buff_off, len))
-                goto err1;
+                goto err_wait;
-        dest = dma_map_single(device->dev, buf, len, DMA_FROM_DEVICE);
+        unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOWAIT);
-        if (dma_mapping_error(device->dev, dest))
+        if (!unmap)
-                goto err1;
+                goto err_wait;
-        src = dma_map_single(device->dev, offset, len, DMA_TO_DEVICE);
+        unmap->len = len;
-        if (dma_mapping_error(device->dev, src))
+        unmap->addr[0] = dma_map_page(device->dev, virt_to_page(offset),
-                goto err2;
+                                      pay_off, len, DMA_TO_DEVICE);
+        if (dma_mapping_error(device->dev, unmap->addr[0]))
+                goto err_get_unmap;
+        unmap->to_cnt = 1;
-        flags = DMA_COMPL_DEST_UNMAP_SINGLE | DMA_COMPL_SRC_UNMAP_SINGLE |
+        unmap->addr[1] = dma_map_page(device->dev, virt_to_page(buf),
-                DMA_PREP_INTERRUPT;
+                                      buff_off, len, DMA_FROM_DEVICE);
-        txd = device->device_prep_dma_memcpy(chan, dest, src, len, flags);
+        if (dma_mapping_error(device->dev, unmap->addr[1]))
+                goto err_get_unmap;
+        unmap->from_cnt = 1;
+        txd = device->device_prep_dma_memcpy(chan, unmap->addr[1],
+                                             unmap->addr[0], len,
+                                             DMA_PREP_INTERRUPT);
        if (!txd)
-                goto err3;
+                goto err_get_unmap;
        txd->callback = ntb_rx_copy_callback;
        txd->callback_param = entry;
+        dma_set_unmap(txd, unmap);
        cookie = dmaengine_submit(txd);
        if (dma_submit_error(cookie))
-                goto err3;
+                goto err_set_unmap;
+        dmaengine_unmap_put(unmap);
        qp->last_cookie = cookie;
@@ -1081,11 +1094,11 @@ static void ntb_async_rx(struct ntb_queue_entry *entry, void *offset,
        return;
-err3:
+err_set_unmap:
-        dma_unmap_single(device->dev, src, len, DMA_TO_DEVICE);
+        dmaengine_unmap_put(unmap);
-err2:
+err_get_unmap:
-        dma_unmap_single(device->dev, dest, len, DMA_FROM_DEVICE);
+        dmaengine_unmap_put(unmap);
-err1:
+err_wait:
        /* If the callbacks come out of order, the writing of the index to the
         * last completed will be out of order.  This may result in the
         * receive stalling forever.
@@ -1245,12 +1258,12 @@ static void ntb_async_tx(struct ntb_transport_qp *qp,
        struct dma_chan *chan = qp->dma_chan;
        struct dma_device *device;
        size_t dest_off, buff_off;
-        dma_addr_t src, dest;
+        struct dmaengine_unmap_data *unmap;
+        dma_addr_t dest;
        dma_cookie_t cookie;
        void __iomem *offset;
        size_t len = entry->len;
        void *buf = entry->buf;
-        unsigned long flags;
        offset = qp->tx_mw + qp->tx_max_frame * qp->tx_index;
        hdr = offset + qp->tx_max_frame - sizeof(struct ntb_payload_header);
@@ -1273,28 +1286,41 @@ static void ntb_async_tx(struct ntb_transport_qp *qp,
        if (!is_dma_copy_aligned(device, buff_off, dest_off, len))
                goto err;
-        src = dma_map_single(device->dev, buf, len, DMA_TO_DEVICE);
+        unmap = dmaengine_get_unmap_data(device->dev, 1, GFP_NOWAIT);
-        if (dma_mapping_error(device->dev, src))
+        if (!unmap)
                goto err;
-        flags = DMA_COMPL_SRC_UNMAP_SINGLE | DMA_PREP_INTERRUPT;
+        unmap->len = len;
-        txd = device->device_prep_dma_memcpy(chan, dest, src, len, flags);
+        unmap->addr[0] = dma_map_page(device->dev, virt_to_page(buf),
+                                      buff_off, len, DMA_TO_DEVICE);
+        if (dma_mapping_error(device->dev, unmap->addr[0]))
+                goto err_get_unmap;
+        unmap->to_cnt = 1;
+        txd = device->device_prep_dma_memcpy(chan, dest, unmap->addr[0], len,
+                                             DMA_PREP_INTERRUPT);
        if (!txd)
-                goto err1;
+                goto err_get_unmap;
        txd->callback = ntb_tx_copy_callback;
        txd->callback_param = entry;
+        dma_set_unmap(txd, unmap);
        cookie = dmaengine_submit(txd);
        if (dma_submit_error(cookie))
-                goto err1;
+                goto err_set_unmap;
+        dmaengine_unmap_put(unmap);
        dma_async_issue_pending(chan);
        qp->tx_async++;
        return;
-err1:
+err_set_unmap:
-        dma_unmap_single(device->dev, src, len, DMA_TO_DEVICE);
+        dmaengine_unmap_put(unmap);
+err_get_unmap:
+        dmaengine_unmap_put(unmap);
 err:
        ntb_memcpy_tx(entry, offset);
        qp->tx_memcpy++;
diff --git a/drivers/pci/hotplug/acpi_pcihp.c b/drivers/pci/hotplug/acpi_pcihp.c
index 1ce8ee054f1a..a94d850ae228 100644
--- a/drivers/pci/hotplug/acpi_pcihp.c
+++ b/drivers/pci/hotplug/acpi_pcihp.c
@@ -367,7 +367,7 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev, u32 flags)
                string = (struct acpi_buffer){ ACPI_ALLOCATE_BUFFER, NULL };
        }
-        handle = DEVICE_ACPI_HANDLE(&pdev->dev);
+        handle = ACPI_HANDLE(&pdev->dev);
        if (!handle) {
                /*
                 * This hotplug controller was not listed in the ACPI name
diff --git a/drivers/pci/hotplug/acpiphp.h b/drivers/pci/hotplug/acpiphp.h
index 26100f510b10..1592dbe4f904 100644
--- a/drivers/pci/hotplug/acpiphp.h
+++ b/drivers/pci/hotplug/acpiphp.h
@@ -176,7 +176,6 @@ u8 acpiphp_get_latch_status(struct acpiphp_slot *slot);
 u8 acpiphp_get_adapter_status(struct acpiphp_slot *slot);
 /* variables */
-extern bool acpiphp_debug;
 extern bool acpiphp_disabled;
 #endif /* _ACPIPHP_H */
diff --git a/drivers/pci/hotplug/pciehp_acpi.c b/drivers/pci/hotplug/pciehp_acpi.c
index ead7c534095e..cff7cadfc2e4 100644
--- a/drivers/pci/hotplug/pciehp_acpi.c
+++ b/drivers/pci/hotplug/pciehp_acpi.c
@@ -54,7 +54,7 @@ int pciehp_acpi_slot_detection_check(struct pci_dev *dev)
 {
        if (slot_detection_mode != PCIEHP_DETECT_ACPI)
                return 0;
-        if (acpi_pci_detect_ejectable(DEVICE_ACPI_HANDLE(&dev->dev)))
+        if (acpi_pci_detect_ejectable(ACPI_HANDLE(&dev->dev)))
                return 0;
        return -ENODEV;
 }
@@ -96,7 +96,7 @@ static int __init dummy_probe(struct pcie_device *dev)
                        dup_slot_id++;
        }
        list_add_tail(&slot->list, &dummy_slots);
-        handle = DEVICE_ACPI_HANDLE(&pdev->dev);
+        handle = ACPI_HANDLE(&pdev->dev);
        if (!acpi_slot_detected && acpi_pci_detect_ejectable(handle))
                acpi_slot_detected = 1;
        return -ENODEV;         /* dummy driver always returns error */
diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c
index b2781dfe60e9..5b05a68cca6c 100644
--- a/drivers/pci/hotplug/sgi_hotplug.c
+++ b/drivers/pci/hotplug/sgi_hotplug.c
@@ -9,6 +9,7 @@
 * Work to add BIOS PROM support was completed by Mike Habeck.
 */
+#include <linux/acpi.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -29,7 +30,6 @@
 #include <asm/sn/sn_feature_sets.h>
 #include <asm/sn/sn_sal.h>
 #include <asm/sn/types.h>
-#include <linux/acpi.h>
 #include <asm/sn/acpi.h>
 #include "../pci.h"
@@ -414,7 +414,7 @@ static int enable_slot(struct hotplug_slot *bss_hotplug_slot)
                acpi_handle rethandle;
                acpi_status ret;
-                phandle = PCI_CONTROLLER(slot->pci_bus)->acpi_handle;
+                phandle = acpi_device_handle(PCI_CONTROLLER(slot->pci_bus)->companion);
                if (acpi_bus_get_device(phandle, &pdevice)) {
                        dev_dbg(&slot->pci_bus->self->dev,
@@ -495,7 +495,7 @@ static int disable_slot(struct hotplug_slot *bss_hotplug_slot)
        /* free the ACPI resources for the slot */
        if (SN_ACPI_BASE_SUPPORT() &&
-            PCI_CONTROLLER(slot->pci_bus)->acpi_handle) {
+            PCI_CONTROLLER(slot->pci_bus)->companion) {
                unsigned long long adr;
                struct acpi_device *device;
                acpi_handle phandle;
@@ -504,7 +504,7 @@ static int disable_slot(struct hotplug_slot *bss_hotplug_slot)
                acpi_status ret;
                /* Get the rootbus node pointer */
-                phandle = PCI_CONTROLLER(slot->pci_bus)->acpi_handle;
+                phandle = acpi_device_handle(PCI_CONTROLLER(slot->pci_bus)->companion);
                acpi_scan_lock_acquire();
                /*
diff --git a/drivers/pci/ioapic.c b/drivers/pci/ioapic.c
index 1b90579b233a..50ce68098298 100644
--- a/drivers/pci/ioapic.c
+++ b/drivers/pci/ioapic.c
@@ -37,7 +37,7 @@ static int ioapic_probe(struct pci_dev *dev, const struct pci_device_id *ent)
        char *type;
        struct resource *res;
-        handle = DEVICE_ACPI_HANDLE(&dev->dev);
+        handle = ACPI_HANDLE(&dev->dev);
        if (!handle)
                return -EINVAL;
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index dfd1f59de729..f166126e28d1 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -173,14 +173,14 @@ static pci_power_t acpi_pci_choose_state(struct pci_dev *pdev)
 static bool acpi_pci_power_manageable(struct pci_dev *dev)
 {
-        acpi_handle handle = DEVICE_ACPI_HANDLE(&dev->dev);
+        acpi_handle handle = ACPI_HANDLE(&dev->dev);
        return handle ? acpi_bus_power_manageable(handle) : false;
 }
 static int acpi_pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 {
-        acpi_handle handle = DEVICE_ACPI_HANDLE(&dev->dev);
+        acpi_handle handle = ACPI_HANDLE(&dev->dev);
        static const u8 state_conv[] = {
                [PCI_D0] = ACPI_STATE_D0,
                [PCI_D1] = ACPI_STATE_D1,
@@ -217,7 +217,7 @@ static int acpi_pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 static bool acpi_pci_can_wakeup(struct pci_dev *dev)
 {
-        acpi_handle handle = DEVICE_ACPI_HANDLE(&dev->dev);
+        acpi_handle handle = ACPI_HANDLE(&dev->dev);
        return handle ? acpi_bus_can_wakeup(handle) : false;
 }
diff --git a/drivers/pci/pci-label.c b/drivers/pci/pci-label.c
index edaed6f4da6c..d51f45aa669e 100644
--- a/drivers/pci/pci-label.c
+++ b/drivers/pci/pci-label.c
@@ -263,7 +263,7 @@ device_has_dsm(struct device *dev)
        acpi_handle handle;
        struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
-        handle = DEVICE_ACPI_HANDLE(dev);
+        handle = ACPI_HANDLE(dev);
        if (!handle)
                return FALSE;
@@ -295,7 +295,7 @@ acpilabel_show(struct device *dev, struct device_attribute *attr, char *buf)
        acpi_handle handle;
        int length;
-        handle = DEVICE_ACPI_HANDLE(dev);
+        handle = ACPI_HANDLE(dev);
        if (!handle)
                return -1;
@@ -316,7 +316,7 @@ acpiindex_show(struct device *dev, struct device_attribute *attr, char *buf)
        acpi_handle handle;
        int length;
-        handle = DEVICE_ACPI_HANDLE(dev);
+        handle = ACPI_HANDLE(dev);
        if (!handle)
                return -1;
diff --git a/drivers/platform/x86/apple-gmux.c b/drivers/platform/x86/apple-gmux.c
index 605a9be55129..b9429fbf1cd8 100644
--- a/drivers/platform/x86/apple-gmux.c
+++ b/drivers/platform/x86/apple-gmux.c
@@ -519,7 +519,7 @@ static int gmux_probe(struct pnp_dev *pnp, const struct pnp_device_id *id)
        gmux_data->power_state = VGA_SWITCHEROO_ON;
-        gmux_data->dhandle = DEVICE_ACPI_HANDLE(&pnp->dev);
+        gmux_data->dhandle = ACPI_HANDLE(&pnp->dev);
        if (!gmux_data->dhandle) {
                pr_err("Cannot find acpi handle for pnp device %s\n",
                       dev_name(&pnp->dev));
diff --git a/drivers/pnp/pnpacpi/core.c b/drivers/pnp/pnpacpi/core.c
index 747826d99059..14655a0f0431 100644
--- a/drivers/pnp/pnpacpi/core.c
+++ b/drivers/pnp/pnpacpi/core.c
@@ -89,7 +89,7 @@ static int pnpacpi_set_resources(struct pnp_dev *dev)
        pnp_dbg(&dev->dev, "set resources\n");
-        handle = DEVICE_ACPI_HANDLE(&dev->dev);
+        handle = ACPI_HANDLE(&dev->dev);
        if (!handle || acpi_bus_get_device(handle, &acpi_dev)) {
                dev_dbg(&dev->dev, "ACPI device not found in %s!\n", __func__);
                return -ENODEV;
@@ -122,7 +122,7 @@ static int pnpacpi_disable_resources(struct pnp_dev *dev)
        dev_dbg(&dev->dev, "disable resources\n");
-        handle = DEVICE_ACPI_HANDLE(&dev->dev);
+        handle = ACPI_HANDLE(&dev->dev);
        if (!handle || acpi_bus_get_device(handle, &acpi_dev)) {
                dev_dbg(&dev->dev, "ACPI device not found in %s!\n", __func__);
                return 0;
@@ -144,7 +144,7 @@ static bool pnpacpi_can_wakeup(struct pnp_dev *dev)
        struct acpi_device *acpi_dev;
        acpi_handle handle;
-        handle = DEVICE_ACPI_HANDLE(&dev->dev);
+        handle = ACPI_HANDLE(&dev->dev);
        if (!handle || acpi_bus_get_device(handle, &acpi_dev)) {
                dev_dbg(&dev->dev, "ACPI device not found in %s!\n", __func__);
                return false;
@@ -159,7 +159,7 @@ static int pnpacpi_suspend(struct pnp_dev *dev, pm_message_t state)
        acpi_handle handle;
        int error = 0;
-        handle = DEVICE_ACPI_HANDLE(&dev->dev);
+        handle = ACPI_HANDLE(&dev->dev);
        if (!handle || acpi_bus_get_device(handle, &acpi_dev)) {
                dev_dbg(&dev->dev, "ACPI device not found in %s!\n", __func__);
                return 0;
@@ -194,7 +194,7 @@ static int pnpacpi_suspend(struct pnp_dev *dev, pm_message_t state)
 static int pnpacpi_resume(struct pnp_dev *dev)
 {
        struct acpi_device *acpi_dev;
-        acpi_handle handle = DEVICE_ACPI_HANDLE(&dev->dev);
+        acpi_handle handle = ACPI_HANDLE(&dev->dev);
        int error = 0;
        if (!handle || acpi_bus_get_device(handle, &acpi_dev)) {
diff --git a/drivers/scsi/aacraid/commctrl.c b/drivers/scsi/aacraid/commctrl.c
index d85ac1a9d2c0..fbcd48d0bfc3 100644
--- a/drivers/scsi/aacraid/commctrl.c
+++ b/drivers/scsi/aacraid/commctrl.c
@@ -511,7 +511,8 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
                goto cleanup;
        }
-        if (fibsize > (dev->max_fib_size - sizeof(struct aac_fibhdr))) {
+        if ((fibsize < (sizeof(struct user_aac_srb) - sizeof(struct user_sgentry))) ||
+            (fibsize > (dev->max_fib_size - sizeof(struct aac_fibhdr)))) {
                rcode = -EINVAL;
                goto cleanup;
        }
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index e43db7742047..bd6f743d87a7 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -1512,7 +1512,8 @@ static int pmcraid_notify_aen(
        }
        result =
-                genlmsg_multicast(skb, 0, pmcraid_event_family.id, GFP_ATOMIC);
+                genlmsg_multicast(&pmcraid_event_family, skb, 0,
+                                  pmcraid_event_family.id, GFP_ATOMIC);
        /* If there are no listeners, genlmsg_multicast may return non-zero
         * value.
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
index b9f0192758d6..6d207afec8cb 100644
--- a/drivers/spi/spi-dw-mid.c
+++ b/drivers/spi/spi-dw-mid.c
@@ -150,7 +150,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change)
                                &dws->tx_sgl,
                                1,
                                DMA_MEM_TO_DEV,
-                                DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_DEST_UNMAP);
+                                DMA_PREP_INTERRUPT);
        txdesc->callback = dw_spi_dma_done;
        txdesc->callback_param = dws;
@@ -173,7 +173,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change)
                                &dws->rx_sgl,
                                1,
                                DMA_DEV_TO_MEM,
-                                DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_DEST_UNMAP);
+                                DMA_PREP_INTERRUPT);
        rxdesc->callback = dw_spi_dma_done;
        rxdesc->callback_param = dws;
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 8d85ddc46011..18cc625d887f 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -357,6 +357,19 @@ struct spi_device *spi_alloc_device(struct spi_master *master)
 }
 EXPORT_SYMBOL_GPL(spi_alloc_device);
+static void spi_dev_set_name(struct spi_device *spi)
+{
+        struct acpi_device *adev = ACPI_COMPANION(&spi->dev);
+        if (adev) {
+                dev_set_name(&spi->dev, "spi-%s", acpi_dev_name(adev));
+                return;
+        }
+        dev_set_name(&spi->dev, "%s.%u", dev_name(&spi->master->dev),
+                     spi->chip_select);
+}
 /**
 * spi_add_device - Add spi_device allocated with spi_alloc_device
 * @spi: spi_device to register
@@ -383,9 +396,7 @@ int spi_add_device(struct spi_device *spi)
        }
        /* Set the bus ID string */
-        dev_set_name(&spi->dev, "%s.%u", dev_name(&spi->master->dev),
+        spi_dev_set_name(spi);
-                        spi->chip_select);
        /* We need to make sure there's no other device with this
         * chipselect **BEFORE** we call setup(), else we'll trash
@@ -1144,7 +1155,7 @@ static acpi_status acpi_spi_add_device(acpi_handle handle, u32 level,
                return AE_NO_MEMORY;
        }
-        ACPI_HANDLE_SET(&spi->dev, handle);
+        ACPI_COMPANION_SET(&spi->dev, adev);
        spi->irq = -1;
        INIT_LIST_HEAD(&resource_list);
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 03a567199bbe..f1d511a9475b 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1608,15 +1608,17 @@ exit:
 EXPORT_SYMBOL_GPL(thermal_zone_get_zone_by_name);
 #ifdef CONFIG_NET
+static const struct genl_multicast_group thermal_event_mcgrps[] = {
+        { .name = THERMAL_GENL_MCAST_GROUP_NAME, },
+};
 static struct genl_family thermal_event_genl_family = {
        .id = GENL_ID_GENERATE,
        .name = THERMAL_GENL_FAMILY_NAME,
        .version = THERMAL_GENL_VERSION,
        .maxattr = THERMAL_GENL_ATTR_MAX,
-};
+        .mcgrps = thermal_event_mcgrps,
+        .n_mcgrps = ARRAY_SIZE(thermal_event_mcgrps),
-static struct genl_multicast_group thermal_event_mcgrp = {
-        .name = THERMAL_GENL_MCAST_GROUP_NAME,
 };
 int thermal_generate_netlink_event(struct thermal_zone_device *tz,
@@ -1677,7 +1679,8 @@ int thermal_generate_netlink_event(struct thermal_zone_device *tz,
                return result;
        }
-        result = genlmsg_multicast(skb, 0, thermal_event_mcgrp.id, GFP_ATOMIC);
+        result = genlmsg_multicast(&thermal_event_genl_family, skb, 0,
+                                   0, GFP_ATOMIC);
        if (result)
                dev_err(&tz->device, "Failed to send netlink event:%d", result);
@@ -1687,17 +1690,7 @@ EXPORT_SYMBOL_GPL(thermal_generate_netlink_event);
 static int genetlink_init(void)
 {
-        int result;
+        return genl_register_family(&thermal_event_genl_family);
-        result = genl_register_family(&thermal_event_genl_family);
-        if (result)
-                return result;
-        result = genl_register_mc_group(&thermal_event_genl_family,
-                                        &thermal_event_mcgrp);
-        if (result)
-                genl_unregister_family(&thermal_event_genl_family);
-        return result;
 }
 static void genetlink_exit(void)
diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index 537750261aaa..7d8103cd3e2e 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -1433,7 +1433,7 @@ static void work_fn_rx(struct work_struct *work)
        desc = s->desc_rx[new];
        if (dma_async_is_tx_complete(s->chan_rx, s->active_rx, NULL, NULL) !=
-            DMA_SUCCESS) {
+            DMA_COMPLETE) {
                /* Handle incomplete DMA receive */
                struct dma_chan *chan = s->chan_rx;
                struct shdma_desc *sh_desc = container_of(desc,
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 06cec635e703..a7c04e24ca48 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -5501,6 +5501,6 @@ acpi_handle usb_get_hub_port_acpi_handle(struct usb_device *hdev,
        if (!hub)
                return NULL;
-        return DEVICE_ACPI_HANDLE(&hub->ports[port1 - 1]->dev);
+        return ACPI_HANDLE(&hub->ports[port1 - 1]->dev);
 }
 #endif
diff --git a/drivers/usb/core/usb-acpi.c b/drivers/usb/core/usb-acpi.c
index 255c14464bf2..4e243c37f17f 100644
--- a/drivers/usb/core/usb-acpi.c
+++ b/drivers/usb/core/usb-acpi.c
@@ -173,7 +173,7 @@ static int usb_acpi_find_device(struct device *dev, acpi_handle *handle)
                }
                /* root hub's parent is the usb hcd. */
-                parent_handle = DEVICE_ACPI_HANDLE(dev->parent);
+                parent_handle = ACPI_HANDLE(dev->parent);
                *handle = acpi_get_child(parent_handle, udev->portnum);
                if (!*handle)
                        return -ENODEV;
@@ -194,7 +194,7 @@ static int usb_acpi_find_device(struct device *dev, acpi_handle *handle)
                        raw_port_num = usb_hcd_find_raw_port_number(hcd,
                                port_num);
-                        *handle = acpi_get_child(DEVICE_ACPI_HANDLE(&udev->dev),
+                        *handle = acpi_get_child(ACPI_HANDLE(&udev->dev),
                                raw_port_num);
                        if (!*handle)
                                return -ENODEV;
diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c
index d15f6e80479f..188825122aae 100644
--- a/drivers/xen/pci.c
+++ b/drivers/xen/pci.c
@@ -59,12 +59,12 @@ static int xen_add_device(struct device *dev)
                        add.flags = XEN_PCI_DEV_EXTFN;
 #ifdef CONFIG_ACPI
-                handle = DEVICE_ACPI_HANDLE(&pci_dev->dev);
+                handle = ACPI_HANDLE(&pci_dev->dev);
                if (!handle && pci_dev->bus->bridge)
-                        handle = DEVICE_ACPI_HANDLE(pci_dev->bus->bridge);
+                        handle = ACPI_HANDLE(pci_dev->bus->bridge);
 #ifdef CONFIG_PCI_IOV
                if (!handle && pci_dev->is_virtfn)
-                        handle = DEVICE_ACPI_HANDLE(physfn->bus->bridge);
+                        handle = ACPI_HANDLE(physfn->bus->bridge);
 #endif
                if (handle) {
                        acpi_status status;