Merge branch 'jejb-scsi' into misc

381 files changed, 7595 insertions, 3493 deletions

diff --git a/drivers/Makefile b/drivers/Makefile
index 73d039156ea7..795d0ca714bf 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -63,6 +63,7 @@ obj-$(CONFIG_FB_I810)           += video/fbdev/i810/
 obj-$(CONFIG_FB_INTEL)          += video/fbdev/intelfb/
 
 obj-$(CONFIG_PARPORT)		+= parport/
+obj-$(CONFIG_NVM)		+= lightnvm/
 obj-y				+= base/ block/ misc/ mfd/ nfc/
 obj-$(CONFIG_LIBNVDIMM)		+= nvdimm/
 obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/
@@ -70,7 +71,6 @@ obj-$(CONFIG_NUBUS)		+= nubus/
 obj-y				+= macintosh/
 obj-$(CONFIG_IDE)		+= ide/
 obj-$(CONFIG_SCSI)		+= scsi/
-obj-$(CONFIG_NVM)		+= lightnvm/
 obj-y				+= nvme/
 obj-$(CONFIG_ATA)		+= ata/
 obj-$(CONFIG_TARGET_CORE)	+= target/
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 25dbb76c02cc..5eef4cb4f70e 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -58,10 +58,10 @@ config ACPI_CCA_REQUIRED
 	bool
 
 config ACPI_DEBUGGER
-	bool "In-kernel debugger (EXPERIMENTAL)"
+	bool "AML debugger interface (EXPERIMENTAL)"
 	select ACPI_DEBUG
 	help
-	  Enable in-kernel debugging facilities: statistics, internal
+	  Enable in-kernel debugging of AML facilities: statistics, internal
 	  object dump, single step control method execution.
 	  This is still under development, currently enabling this only
 	  results in the compilation of the ACPICA debugger files.
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 3c083d2cc434..6730f965b379 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -304,7 +304,7 @@ EXPORT_SYMBOL_GPL(acpi_get_psd_map);
 
 static int register_pcc_channel(int pcc_subspace_idx)
 {
-	struct acpi_pcct_subspace *cppc_ss;
+	struct acpi_pcct_hw_reduced *cppc_ss;
 	unsigned int len;
 
 	if (pcc_subspace_idx >= 0) {
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index f61a7c834540..b420fb46669d 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1103,7 +1103,7 @@ static int acpi_ec_query(struct acpi_ec *ec, u8 *data)
 	}
 
 err_exit:
-	if (result && q)
+	if (result)
 		acpi_ec_delete_query(q);
 	if (data)
 		*data = value;
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index f7dab53b352a..e7ed39bab97d 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -233,11 +233,12 @@ static bool add_spa(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_table_prev *prev,
 		struct acpi_nfit_system_address *spa)
 {
+	size_t length = min_t(size_t, sizeof(*spa), spa->header.length);
 	struct device *dev = acpi_desc->dev;
 	struct nfit_spa *nfit_spa;
 
 	list_for_each_entry(nfit_spa, &prev->spas, list) {
-		if (memcmp(nfit_spa->spa, spa, sizeof(*spa)) == 0) {
+		if (memcmp(nfit_spa->spa, spa, length) == 0) {
 			list_move_tail(&nfit_spa->list, &acpi_desc->spas);
 			return true;
 		}
@@ -259,11 +260,12 @@ static bool add_memdev(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_table_prev *prev,
 		struct acpi_nfit_memory_map *memdev)
 {
+	size_t length = min_t(size_t, sizeof(*memdev), memdev->header.length);
 	struct device *dev = acpi_desc->dev;
 	struct nfit_memdev *nfit_memdev;
 
 	list_for_each_entry(nfit_memdev, &prev->memdevs, list)
-		if (memcmp(nfit_memdev->memdev, memdev, sizeof(*memdev)) == 0) {
+		if (memcmp(nfit_memdev->memdev, memdev, length) == 0) {
 			list_move_tail(&nfit_memdev->list, &acpi_desc->memdevs);
 			return true;
 		}
@@ -284,11 +286,12 @@ static bool add_dcr(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_table_prev *prev,
 		struct acpi_nfit_control_region *dcr)
 {
+	size_t length = min_t(size_t, sizeof(*dcr), dcr->header.length);
 	struct device *dev = acpi_desc->dev;
 	struct nfit_dcr *nfit_dcr;
 
 	list_for_each_entry(nfit_dcr, &prev->dcrs, list)
-		if (memcmp(nfit_dcr->dcr, dcr, sizeof(*dcr)) == 0) {
+		if (memcmp(nfit_dcr->dcr, dcr, length) == 0) {
 			list_move_tail(&nfit_dcr->list, &acpi_desc->dcrs);
 			return true;
 		}
@@ -308,11 +311,12 @@ static bool add_bdw(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_table_prev *prev,
 		struct acpi_nfit_data_region *bdw)
 {
+	size_t length = min_t(size_t, sizeof(*bdw), bdw->header.length);
 	struct device *dev = acpi_desc->dev;
 	struct nfit_bdw *nfit_bdw;
 
 	list_for_each_entry(nfit_bdw, &prev->bdws, list)
-		if (memcmp(nfit_bdw->bdw, bdw, sizeof(*bdw)) == 0) {
+		if (memcmp(nfit_bdw->bdw, bdw, length) == 0) {
 			list_move_tail(&nfit_bdw->list, &acpi_desc->bdws);
 			return true;
 		}
@@ -332,11 +336,12 @@ static bool add_idt(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_table_prev *prev,
 		struct acpi_nfit_interleave *idt)
 {
+	size_t length = min_t(size_t, sizeof(*idt), idt->header.length);
 	struct device *dev = acpi_desc->dev;
 	struct nfit_idt *nfit_idt;
 
 	list_for_each_entry(nfit_idt, &prev->idts, list)
-		if (memcmp(nfit_idt->idt, idt, sizeof(*idt)) == 0) {
+		if (memcmp(nfit_idt->idt, idt, length) == 0) {
 			list_move_tail(&nfit_idt->list, &acpi_desc->idts);
 			return true;
 		}
@@ -356,11 +361,12 @@ static bool add_flush(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_table_prev *prev,
 		struct acpi_nfit_flush_address *flush)
 {
+	size_t length = min_t(size_t, sizeof(*flush), flush->header.length);
 	struct device *dev = acpi_desc->dev;
 	struct nfit_flush *nfit_flush;
 
 	list_for_each_entry(nfit_flush, &prev->flushes, list)
-		if (memcmp(nfit_flush->flush, flush, sizeof(*flush)) == 0) {
+		if (memcmp(nfit_flush->flush, flush, length) == 0) {
 			list_move_tail(&nfit_flush->list, &acpi_desc->flushes);
 			return true;
 		}
@@ -655,7 +661,7 @@ static ssize_t revision_show(struct device *dev,
 	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
 	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
 
-	return sprintf(buf, "%d\n", acpi_desc->nfit->header.revision);
+	return sprintf(buf, "%d\n", acpi_desc->acpi_header.revision);
 }
 static DEVICE_ATTR_RO(revision);
 
@@ -1652,7 +1658,6 @@ int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, acpi_size sz)
 
 	data = (u8 *) acpi_desc->nfit;
 	end = data + sz;
-	data += sizeof(struct acpi_table_nfit);
 	while (!IS_ERR_OR_NULL(data))
 		data = add_table(acpi_desc, &prev, data, end);
 
@@ -1748,13 +1753,29 @@ static int acpi_nfit_add(struct acpi_device *adev)
 		return PTR_ERR(acpi_desc);
 	}
 
-	acpi_desc->nfit = (struct acpi_table_nfit *) tbl;
+	/*
+	 * Save the acpi header for later and then skip it,
+	 * making nfit point to the first nfit table header.
+	 */
+	acpi_desc->acpi_header = *tbl;
+	acpi_desc->nfit = (void *) tbl + sizeof(struct acpi_table_nfit);
+	sz -= sizeof(struct acpi_table_nfit);
 
 	/* Evaluate _FIT and override with that if present */
 	status = acpi_evaluate_object(adev->handle, "_FIT", NULL, &buf);
 	if (ACPI_SUCCESS(status) && buf.length > 0) {
-		acpi_desc->nfit = (struct acpi_table_nfit *)buf.pointer;
-		sz = buf.length;
+		union acpi_object *obj;
+		/*
+		 * Adjust for the acpi_object header of the _FIT
+		 */
+		obj = buf.pointer;
+		if (obj->type == ACPI_TYPE_BUFFER) {
+			acpi_desc->nfit =
+				(struct acpi_nfit_header *)obj->buffer.pointer;
+			sz = obj->buffer.length;
+		} else
+			dev_dbg(dev, "%s invalid type %d, ignoring _FIT\n",
+				 __func__, (int) obj->type);
 	}
 
 	rc = acpi_nfit_init(acpi_desc, sz);
@@ -1777,7 +1798,8 @@ static void acpi_nfit_notify(struct acpi_device *adev, u32 event)
 {
 	struct acpi_nfit_desc *acpi_desc = dev_get_drvdata(&adev->dev);
 	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
-	struct acpi_table_nfit *nfit_saved;
+	struct acpi_nfit_header *nfit_saved;
+	union acpi_object *obj;
 	struct device *dev = &adev->dev;
 	acpi_status status;
 	int ret;
@@ -1808,12 +1830,19 @@ static void acpi_nfit_notify(struct acpi_device *adev, u32 event)
 	}
 
 	nfit_saved = acpi_desc->nfit;
-	acpi_desc->nfit = (struct acpi_table_nfit *)buf.pointer;
-	ret = acpi_nfit_init(acpi_desc, buf.length);
-	if (!ret) {
-		/* Merge failed, restore old nfit, and exit */
-		acpi_desc->nfit = nfit_saved;
-		dev_err(dev, "failed to merge updated NFIT\n");
+	obj = buf.pointer;
+	if (obj->type == ACPI_TYPE_BUFFER) {
+		acpi_desc->nfit =
+			(struct acpi_nfit_header *)obj->buffer.pointer;
+		ret = acpi_nfit_init(acpi_desc, obj->buffer.length);
+		if (ret) {
+			/* Merge failed, restore old nfit, and exit */
+			acpi_desc->nfit = nfit_saved;
+			dev_err(dev, "failed to merge updated NFIT\n");
+		}
+	} else {
+		/* Bad _FIT, restore old nfit */
+		dev_err(dev, "Invalid _FIT\n");
 	}
 	kfree(buf.pointer);
 
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
index 2ea5c0797c8f..3d549a383659 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit.h
@@ -96,7 +96,8 @@ struct nfit_mem {
 
 struct acpi_nfit_desc {
 	struct nvdimm_bus_descriptor nd_desc;
-	struct acpi_table_nfit *nfit;
+	struct acpi_table_header acpi_header;
+	struct acpi_nfit_header *nfit;
 	struct mutex spa_map_mutex;
 	struct mutex init_mutex;
 	struct list_head spa_maps;
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 850d7bf0c873..ae3fe4e64203 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -768,6 +768,13 @@ static void pci_acpi_root_add_resources(struct acpi_pci_root_info *info)
 		else
 			continue;
 
+		/*
+		 * Some legacy x86 host bridge drivers use iomem_resource and
+		 * ioport_resource as default resource pool, skip it.
+		 */
+		if (res == root)
+			continue;
+
 		conflict = insert_resource_conflict(root, res);
 		if (conflict) {
 			dev_info(&info->bridge->dev,
diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c
index bf034f8b7c1a..2fa8304171e0 100644
--- a/drivers/acpi/sbshc.c
+++ b/drivers/acpi/sbshc.c
@@ -14,7 +14,6 @@
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
-#include <linux/dmi.h>
 #include "sbshc.h"
 
 #define PREFIX "ACPI: "
@@ -30,6 +29,7 @@ struct acpi_smb_hc {
 	u8 query_bit;
 	smbus_alarm_callback callback;
 	void *context;
+	bool done;
 };
 
 static int acpi_smbus_hc_add(struct acpi_device *device);
@@ -88,8 +88,6 @@ enum acpi_smb_offset {
 	ACPI_SMB_ALARM_DATA = 0x26,	/* 2 bytes alarm data */
 };
 
-static bool macbook;
-
 static inline int smb_hc_read(struct acpi_smb_hc *hc, u8 address, u8 *data)
 {
 	return ec_read(hc->offset + address, data);
@@ -100,27 +98,11 @@ static inline int smb_hc_write(struct acpi_smb_hc *hc, u8 address, u8 data)
 	return ec_write(hc->offset + address, data);
 }
 
-static inline int smb_check_done(struct acpi_smb_hc *hc)
-{
-	union acpi_smb_status status = {.raw = 0};
-	smb_hc_read(hc, ACPI_SMB_STATUS, &status.raw);
-	return status.fields.done && (status.fields.status == SMBUS_OK);
-}
-
 static int wait_transaction_complete(struct acpi_smb_hc *hc, int timeout)
 {
-	if (wait_event_timeout(hc->wait, smb_check_done(hc),
-			       msecs_to_jiffies(timeout)))
+	if (wait_event_timeout(hc->wait, hc->done, msecs_to_jiffies(timeout)))
 		return 0;
-	/*
-	 * After the timeout happens, OS will try to check the status of SMbus.
-	 * If the status is what OS expected, it will be regarded as the bogus
-	 * timeout.
-	 */
-	if (smb_check_done(hc))
-		return 0;
-	else
-		return -ETIME;
+	return -ETIME;
 }
 
 static int acpi_smbus_transaction(struct acpi_smb_hc *hc, u8 protocol,
@@ -135,8 +117,7 @@ static int acpi_smbus_transaction(struct acpi_smb_hc *hc, u8 protocol,
 	}
 
 	mutex_lock(&hc->lock);
-	if (macbook)
-		udelay(5);
+	hc->done = false;
 	if (smb_hc_read(hc, ACPI_SMB_PROTOCOL, &temp))
 		goto end;
 	if (temp) {
@@ -235,8 +216,10 @@ static int smbus_alarm(void *context)
 	if (smb_hc_read(hc, ACPI_SMB_STATUS, &status.raw))
 		return 0;
 	/* Check if it is only a completion notify */
-	if (status.fields.done)
+	if (status.fields.done && status.fields.status == SMBUS_OK) {
+		hc->done = true;
 		wake_up(&hc->wait);
+	}
 	if (!status.fields.alarm)
 		return 0;
 	mutex_lock(&hc->lock);
@@ -262,29 +245,12 @@ extern int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit,
 			      acpi_handle handle, acpi_ec_query_func func,
 			      void *data);
 
-static int macbook_dmi_match(const struct dmi_system_id *d)
-{
-	pr_debug("Detected MacBook, enabling workaround\n");
-	macbook = true;
-	return 0;
-}
-
-static struct dmi_system_id acpi_smbus_dmi_table[] = {
-	{ macbook_dmi_match, "Apple MacBook", {
-	  DMI_MATCH(DMI_BOARD_VENDOR, "Apple"),
-	  DMI_MATCH(DMI_PRODUCT_NAME, "MacBook") },
-	},
-	{ },
-};
-
 static int acpi_smbus_hc_add(struct acpi_device *device)
 {
 	int status;
 	unsigned long long val;
 	struct acpi_smb_hc *hc;
 
-	dmi_check_system(acpi_smbus_dmi_table);
-
 	if (!device)
 		return -EINVAL;
 
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index e03b1ad25a90..167418e73445 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1775,10 +1775,10 @@ int genpd_dev_pm_attach(struct device *dev)
 	}
 
 	pd = of_genpd_get_from_provider(&pd_args);
+	of_node_put(pd_args.np);
 	if (IS_ERR(pd)) {
 		dev_dbg(dev, "%s() failed to find PM domain: %ld\n",
 			__func__, PTR_ERR(pd));
-		of_node_put(dev->of_node);
 		return -EPROBE_DEFER;
 	}
 
@@ -1796,7 +1796,6 @@ int genpd_dev_pm_attach(struct device *dev)
 	if (ret < 0) {
 		dev_err(dev, "failed to add to PM domain %s: %d",
 			pd->name, ret);
-		of_node_put(dev->of_node);
 		goto out;
 	}
 
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index e60dd12e23aa..1e937ac5f456 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -160,9 +160,6 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 		struct gpd_timing_data *td;
 		s64 constraint_ns;
 
-		if (!pdd->dev->driver)
-			continue;
-
 		/*
 		 * Check if the device is allowed to be off long enough for the
 		 * domain to turn off and on (that's how much time it will
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
index eb6e67451dec..0d77cd6fd8d1 100644
--- a/drivers/base/power/wakeirq.c
+++ b/drivers/base/power/wakeirq.c
@@ -68,6 +68,9 @@ int dev_pm_set_wake_irq(struct device *dev, int irq)
 	struct wake_irq *wirq;
 	int err;
 
+	if (irq < 0)
+		return -EINVAL;
+
 	wirq = kzalloc(sizeof(*wirq), GFP_KERNEL);
 	if (!wirq)
 		return -ENOMEM;
@@ -167,6 +170,9 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq)
 	struct wake_irq *wirq;
 	int err;
 
+	if (irq < 0)
+		return -EINVAL;
+
 	wirq = kzalloc(sizeof(*wirq), GFP_KERNEL);
 	if (!wirq)
 		return -ENOMEM;
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index a28a562f7b7f..3457ac8c03e2 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3810,7 +3810,6 @@ static int mtip_block_initialize(struct driver_data *dd)
 	sector_t capacity;
 	unsigned int index = 0;
 	struct kobject *kobj;
-	unsigned char thd_name[16];
 
 	if (dd->disk)
 		goto skip_create_disk; /* hw init done, before rebuild */
@@ -3958,10 +3957,9 @@ skip_create_disk:
 	}
 
 start_service_thread:
-	sprintf(thd_name, "mtip_svc_thd_%02d", index);
 	dd->mtip_svc_handler = kthread_create_on_node(mtip_service_thread,
-						dd, dd->numa_node, "%s",
-						thd_name);
+						dd, dd->numa_node,
+						"mtip_svc_thd_%02d", index);
 
 	if (IS_ERR(dd->mtip_svc_handler)) {
 		dev_err(&dd->pdev->dev, "service thread failed to start\n");
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 6255d1c4bba4..0c3940ec5e62 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -8,6 +8,7 @@
 #include <linux/slab.h>
 #include <linux/blk-mq.h>
 #include <linux/hrtimer.h>
+#include <linux/lightnvm.h>
 
 struct nullb_cmd {
 	struct list_head list;
@@ -17,6 +18,7 @@ struct nullb_cmd {
 	struct bio *bio;
 	unsigned int tag;
 	struct nullb_queue *nq;
+	struct hrtimer timer;
 };
 
 struct nullb_queue {
@@ -39,23 +41,14 @@ struct nullb {
 
 	struct nullb_queue *queues;
 	unsigned int nr_queues;
+	char disk_name[DISK_NAME_LEN];
 };
 
 static LIST_HEAD(nullb_list);
 static struct mutex lock;
 static int null_major;
 static int nullb_indexes;
-
-struct completion_queue {
-	struct llist_head list;
-	struct hrtimer timer;
-};
-
-/*
- * These are per-cpu for now, they will need to be configured by the
- * complete_queues parameter and appropriately mapped.
- */
-static DEFINE_PER_CPU(struct completion_queue, completion_queues);
+static struct kmem_cache *ppa_cache;
 
 enum {
 	NULL_IRQ_NONE		= 0,
@@ -119,6 +112,10 @@ static int nr_devices = 2;
 module_param(nr_devices, int, S_IRUGO);
 MODULE_PARM_DESC(nr_devices, "Number of devices to register");
 
+static bool use_lightnvm;
+module_param(use_lightnvm, bool, S_IRUGO);
+MODULE_PARM_DESC(use_lightnvm, "Register as a LightNVM device");
+
 static int irqmode = NULL_IRQ_SOFTIRQ;
 
 static int null_set_irqmode(const char *str, const struct kernel_param *kp)
@@ -135,8 +132,8 @@ static const struct kernel_param_ops null_irqmode_param_ops = {
 device_param_cb(irqmode, &null_irqmode_param_ops, &irqmode, S_IRUGO);
 MODULE_PARM_DESC(irqmode, "IRQ completion handler. 0-none, 1-softirq, 2-timer");
 
-static int completion_nsec = 10000;
-module_param(completion_nsec, int, S_IRUGO);
+static unsigned long completion_nsec = 10000;
+module_param(completion_nsec, ulong, S_IRUGO);
 MODULE_PARM_DESC(completion_nsec, "Time in ns to complete a request in hardware. Default: 10,000ns");
 
 static int hw_queue_depth = 64;
@@ -173,6 +170,8 @@ static void free_cmd(struct nullb_cmd *cmd)
 	put_tag(cmd->nq, cmd->tag);
 }
 
+static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer);
+
 static struct nullb_cmd *__alloc_cmd(struct nullb_queue *nq)
 {
 	struct nullb_cmd *cmd;
@@ -183,6 +182,11 @@ static struct nullb_cmd *__alloc_cmd(struct nullb_queue *nq)
 		cmd = &nq->cmds[tag];
 		cmd->tag = tag;
 		cmd->nq = nq;
+		if (irqmode == NULL_IRQ_TIMER) {
+			hrtimer_init(&cmd->timer, CLOCK_MONOTONIC,
+				     HRTIMER_MODE_REL);
+			cmd->timer.function = null_cmd_timer_expired;
+		}
 		return cmd;
 	}
 
@@ -213,6 +217,8 @@ static struct nullb_cmd *alloc_cmd(struct nullb_queue *nq, int can_wait)
 
 static void end_cmd(struct nullb_cmd *cmd)
 {
+	struct request_queue *q = NULL;
+
 	switch (queue_mode)  {
 	case NULL_Q_MQ:
 		blk_mq_end_request(cmd->rq, 0);
@@ -223,55 +229,37 @@ static void end_cmd(struct nullb_cmd *cmd)
 		break;
 	case NULL_Q_BIO:
 		bio_endio(cmd->bio);
-		break;
+		goto free_cmd;
 	}
 
+	if (cmd->rq)
+		q = cmd->rq->q;
+
+	/* Restart queue if needed, as we are freeing a tag */
+	if (q && !q->mq_ops && blk_queue_stopped(q)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(q->queue_lock, flags);
+		if (blk_queue_stopped(q))
+			blk_start_queue(q);
+		spin_unlock_irqrestore(q->queue_lock, flags);
+	}
+free_cmd:
 	free_cmd(cmd);
 }
 
 static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer)
 {
-	struct completion_queue *cq;
-	struct llist_node *entry;
-	struct nullb_cmd *cmd;
-
-	cq = &per_cpu(completion_queues, smp_processor_id());
-
-	while ((entry = llist_del_all(&cq->list)) != NULL) {
-		entry = llist_reverse_order(entry);
-		do {
-			struct request_queue *q = NULL;
-
-			cmd = container_of(entry, struct nullb_cmd, ll_list);
-			entry = entry->next;
-			if (cmd->rq)
-				q = cmd->rq->q;
-			end_cmd(cmd);
-
-			if (q && !q->mq_ops && blk_queue_stopped(q)) {
-				spin_lock(q->queue_lock);
-				if (blk_queue_stopped(q))
-					blk_start_queue(q);
-				spin_unlock(q->queue_lock);
-			}
-		} while (entry);
-	}
+	end_cmd(container_of(timer, struct nullb_cmd, timer));
 
 	return HRTIMER_NORESTART;
 }
 
 static void null_cmd_end_timer(struct nullb_cmd *cmd)
 {
-	struct completion_queue *cq = &per_cpu(completion_queues, get_cpu());
-
-	cmd->ll_list.next = NULL;
-	if (llist_add(&cmd->ll_list, &cq->list)) {
-		ktime_t kt = ktime_set(0, completion_nsec);
+	ktime_t kt = ktime_set(0, completion_nsec);
 
-		hrtimer_start(&cq->timer, kt, HRTIMER_MODE_REL_PINNED);
-	}
-
-	put_cpu();
+	hrtimer_start(&cmd->timer, kt, HRTIMER_MODE_REL);
 }
 
 static void null_softirq_done_fn(struct request *rq)
@@ -369,6 +357,10 @@ static int null_queue_rq(struct blk_mq_hw_ctx *hctx,
 {
 	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
 
+	if (irqmode == NULL_IRQ_TIMER) {
+		hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+		cmd->timer.function = null_cmd_timer_expired;
+	}
 	cmd->rq = bd->rq;
 	cmd->nq = hctx->driver_data;
 
@@ -427,15 +419,156 @@ static void null_del_dev(struct nullb *nullb)
 {
 	list_del_init(&nullb->list);
 
-	del_gendisk(nullb->disk);
+	if (use_lightnvm)
+		nvm_unregister(nullb->disk_name);
+	else
+		del_gendisk(nullb->disk);
 	blk_cleanup_queue(nullb->q);
 	if (queue_mode == NULL_Q_MQ)
 		blk_mq_free_tag_set(&nullb->tag_set);
-	put_disk(nullb->disk);
+	if (!use_lightnvm)
+		put_disk(nullb->disk);
 	cleanup_queues(nullb);
 	kfree(nullb);
 }
 
+#ifdef CONFIG_NVM
+
+static void null_lnvm_end_io(struct request *rq, int error)
+{
+	struct nvm_rq *rqd = rq->end_io_data;
+	struct nvm_dev *dev = rqd->dev;
+
+	dev->mt->end_io(rqd, error);
+
+	blk_put_request(rq);
+}
+
+static int null_lnvm_submit_io(struct request_queue *q, struct nvm_rq *rqd)
+{
+	struct request *rq;
+	struct bio *bio = rqd->bio;
+
+	rq = blk_mq_alloc_request(q, bio_rw(bio), GFP_KERNEL, 0);
+	if (IS_ERR(rq))
+		return -ENOMEM;
+
+	rq->cmd_type = REQ_TYPE_DRV_PRIV;
+	rq->__sector = bio->bi_iter.bi_sector;
+	rq->ioprio = bio_prio(bio);
+
+	if (bio_has_data(bio))
+		rq->nr_phys_segments = bio_phys_segments(q, bio);
+
+	rq->__data_len = bio->bi_iter.bi_size;
+	rq->bio = rq->biotail = bio;
+
+	rq->end_io_data = rqd;
+
+	blk_execute_rq_nowait(q, NULL, rq, 0, null_lnvm_end_io);
+
+	return 0;
+}
+
+static int null_lnvm_id(struct request_queue *q, struct nvm_id *id)
+{
+	sector_t size = gb * 1024 * 1024 * 1024ULL;
+	sector_t blksize;
+	struct nvm_id_group *grp;
+
+	id->ver_id = 0x1;
+	id->vmnt = 0;
+	id->cgrps = 1;
+	id->cap = 0x3;
+	id->dom = 0x1;
+
+	id->ppaf.blk_offset = 0;
+	id->ppaf.blk_len = 16;
+	id->ppaf.pg_offset = 16;
+	id->ppaf.pg_len = 16;
+	id->ppaf.sect_offset = 32;
+	id->ppaf.sect_len = 8;
+	id->ppaf.pln_offset = 40;
+	id->ppaf.pln_len = 8;
+	id->ppaf.lun_offset = 48;
+	id->ppaf.lun_len = 8;
+	id->ppaf.ch_offset = 56;
+	id->ppaf.ch_len = 8;
+
+	do_div(size, bs); /* convert size to pages */
+	do_div(size, 256); /* concert size to pgs pr blk */
+	grp = &id->groups[0];
+	grp->mtype = 0;
+	grp->fmtype = 0;
+	grp->num_ch = 1;
+	grp->num_pg = 256;
+	blksize = size;
+	do_div(size, (1 << 16));
+	grp->num_lun = size + 1;
+	do_div(blksize, grp->num_lun);
+	grp->num_blk = blksize;
+	grp->num_pln = 1;
+
+	grp->fpg_sz = bs;
+	grp->csecs = bs;
+	grp->trdt = 25000;
+	grp->trdm = 25000;
+	grp->tprt = 500000;
+	grp->tprm = 500000;
+	grp->tbet = 1500000;
+	grp->tbem = 1500000;
+	grp->mpos = 0x010101; /* single plane rwe */
+	grp->cpar = hw_queue_depth;
+
+	return 0;
+}
+
+static void *null_lnvm_create_dma_pool(struct request_queue *q, char *name)
+{
+	mempool_t *virtmem_pool;
+
+	virtmem_pool = mempool_create_slab_pool(64, ppa_cache);
+	if (!virtmem_pool) {
+		pr_err("null_blk: Unable to create virtual memory pool\n");
+		return NULL;
+	}
+
+	return virtmem_pool;
+}
+
+static void null_lnvm_destroy_dma_pool(void *pool)
+{
+	mempool_destroy(pool);
+}
+
+static void *null_lnvm_dev_dma_alloc(struct request_queue *q, void *pool,
+				gfp_t mem_flags, dma_addr_t *dma_handler)
+{
+	return mempool_alloc(pool, mem_flags);
+}
+
+static void null_lnvm_dev_dma_free(void *pool, void *entry,
+							dma_addr_t dma_handler)
+{
+	mempool_free(entry, pool);
+}
+
+static struct nvm_dev_ops null_lnvm_dev_ops = {
+	.identity		= null_lnvm_id,
+	.submit_io		= null_lnvm_submit_io,
+
+	.create_dma_pool	= null_lnvm_create_dma_pool,
+	.destroy_dma_pool	= null_lnvm_destroy_dma_pool,
+	.dev_dma_alloc		= null_lnvm_dev_dma_alloc,
+	.dev_dma_free		= null_lnvm_dev_dma_free,
+
+	/* Simulate nvme protocol restriction */
+	.max_phys_sect		= 64,
+};
+#else
+static struct nvm_dev_ops null_lnvm_dev_ops;
+#endif /* CONFIG_NVM */
+
 static int null_open(struct block_device *bdev, fmode_t mode)
 {
 	return 0;
@@ -575,11 +708,6 @@ static int null_add_dev(void)
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, nullb->q);
 	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, nullb->q);
 
-	disk = nullb->disk = alloc_disk_node(1, home_node);
-	if (!disk) {
-		rv = -ENOMEM;
-		goto out_cleanup_blk_queue;
-	}
 
 	mutex_lock(&lock);
 	list_add_tail(&nullb->list, &nullb_list);
@@ -589,6 +717,21 @@ static int null_add_dev(void)
 	blk_queue_logical_block_size(nullb->q, bs);
 	blk_queue_physical_block_size(nullb->q, bs);
 
+	sprintf(nullb->disk_name, "nullb%d", nullb->index);
+
+	if (use_lightnvm) {
+		rv = nvm_register(nullb->q, nullb->disk_name,
+							&null_lnvm_dev_ops);
+		if (rv)
+			goto out_cleanup_blk_queue;
+		goto done;
+	}
+
+	disk = nullb->disk = alloc_disk_node(1, home_node);
+	if (!disk) {
+		rv = -ENOMEM;
+		goto out_cleanup_lightnvm;
+	}
 	size = gb * 1024 * 1024 * 1024ULL;
 	set_capacity(disk, size >> 9);
 
@@ -598,10 +741,15 @@ static int null_add_dev(void)
 	disk->fops		= &null_fops;
 	disk->private_data	= nullb;
 	disk->queue		= nullb->q;
-	sprintf(disk->disk_name, "nullb%d", nullb->index);
+	strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
+
 	add_disk(disk);
+done:
 	return 0;
 
+out_cleanup_lightnvm:
+	if (use_lightnvm)
+		nvm_unregister(nullb->disk_name);
 out_cleanup_blk_queue:
 	blk_cleanup_queue(nullb->q);
 out_cleanup_tags:
@@ -625,6 +773,18 @@ static int __init null_init(void)
 		bs = PAGE_SIZE;
 	}
 
+	if (use_lightnvm && bs != 4096) {
+		pr_warn("null_blk: LightNVM only supports 4k block size\n");
+		pr_warn("null_blk: defaults block size to 4k\n");
+		bs = 4096;
+	}
+
+	if (use_lightnvm && queue_mode != NULL_Q_MQ) {
+		pr_warn("null_blk: LightNVM only supported for blk-mq\n");
+		pr_warn("null_blk: defaults queue mode to blk-mq\n");
+		queue_mode = NULL_Q_MQ;
+	}
+
 	if (queue_mode == NULL_Q_MQ && use_per_node_hctx) {
 		if (submit_queues < nr_online_nodes) {
 			pr_warn("null_blk: submit_queues param is set to %u.",
@@ -638,32 +798,31 @@ static int __init null_init(void)
 
 	mutex_init(&lock);
 
-	/* Initialize a separate list for each CPU for issuing softirqs */
-	for_each_possible_cpu(i) {
-		struct completion_queue *cq = &per_cpu(completion_queues, i);
-
-		init_llist_head(&cq->list);
-
-		if (irqmode != NULL_IRQ_TIMER)
-			continue;
-
-		hrtimer_init(&cq->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		cq->timer.function = null_cmd_timer_expired;
-	}
-
 	null_major = register_blkdev(0, "nullb");
 	if (null_major < 0)
 		return null_major;
 
+	if (use_lightnvm) {
+		ppa_cache = kmem_cache_create("ppa_cache", 64 * sizeof(u64),
+								0, 0, NULL);
+		if (!ppa_cache) {
+			pr_err("null_blk: unable to create ppa cache\n");
+			return -ENOMEM;
+		}
+	}
+
 	for (i = 0; i < nr_devices; i++) {
 		if (null_add_dev()) {
 			unregister_blkdev(null_major, "nullb");
-			return -EINVAL;
+			goto err_ppa;
 		}
 	}
 
 	pr_info("null: module loaded\n");
 	return 0;
+err_ppa:
+	kmem_cache_destroy(ppa_cache);
+	return -EINVAL;
 }
 
 static void __exit null_exit(void)
@@ -678,6 +837,8 @@ static void __exit null_exit(void)
 		null_del_dev(nullb);
 	}
 	mutex_unlock(&lock);
+
+	kmem_cache_destroy(ppa_cache);
 }
 
 module_init(null_init);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 235708c7c46e..81ea69fee7ca 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -3442,6 +3442,7 @@ static void rbd_queue_workfn(struct work_struct *work)
 		goto err_rq;
 	}
 	img_request->rq = rq;
+	snapc = NULL; /* img_request consumes a ref */
 
 	if (op_type == OBJ_OP_DISCARD)
 		result = rbd_img_request_fill(img_request, OBJ_REQUEST_NODATA,
diff --git a/drivers/bus/omap-ocp2scp.c b/drivers/bus/omap-ocp2scp.c
index 9f1856948758..bf500e0e7362 100644
--- a/drivers/bus/omap-ocp2scp.c
+++ b/drivers/bus/omap-ocp2scp.c
@@ -117,7 +117,7 @@ static struct platform_driver omap_ocp2scp_driver = {
 
 module_platform_driver(omap_ocp2scp_driver);
 
-MODULE_ALIAS("platform: omap-ocp2scp");
+MODULE_ALIAS("platform:omap-ocp2scp");
 MODULE_AUTHOR("Texas Instruments Inc.");
 MODULE_DESCRIPTION("OMAP OCP2SCP driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 654f6f36a071..55fe9020459f 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -412,18 +412,42 @@ static enum si_sm_result start_next_msg(struct smi_info *smi_info)
 	return rv;
 }
 
-static void start_check_enables(struct smi_info *smi_info)
+static void smi_mod_timer(struct smi_info *smi_info, unsigned long new_val)
+{
+	smi_info->last_timeout_jiffies = jiffies;
+	mod_timer(&smi_info->si_timer, new_val);
+	smi_info->timer_running = true;
+}
+
+/*
+ * Start a new message and (re)start the timer and thread.
+ */
+static void start_new_msg(struct smi_info *smi_info, unsigned char *msg,
+			  unsigned int size)
+{
+	smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_JIFFIES);
+
+	if (smi_info->thread)
+		wake_up_process(smi_info->thread);
+
+	smi_info->handlers->start_transaction(smi_info->si_sm, msg, size);
+}
+
+static void start_check_enables(struct smi_info *smi_info, bool start_timer)
 {
 	unsigned char msg[2];
 
 	msg[0] = (IPMI_NETFN_APP_REQUEST << 2);
 	msg[1] = IPMI_GET_BMC_GLOBAL_ENABLES_CMD;
 
-	smi_info->handlers->start_transaction(smi_info->si_sm, msg, 2);
+	if (start_timer)
+		start_new_msg(smi_info, msg, 2);
+	else
+		smi_info->handlers->start_transaction(smi_info->si_sm, msg, 2);
 	smi_info->si_state = SI_CHECKING_ENABLES;
 }
 
-static void start_clear_flags(struct smi_info *smi_info)
+static void start_clear_flags(struct smi_info *smi_info, bool start_timer)
 {
 	unsigned char msg[3];
 
@@ -432,7 +456,10 @@ static void start_clear_flags(struct smi_info *smi_info)
 	msg[1] = IPMI_CLEAR_MSG_FLAGS_CMD;
 	msg[2] = WDT_PRE_TIMEOUT_INT;
 
-	smi_info->handlers->start_transaction(smi_info->si_sm, msg, 3);
+	if (start_timer)
+		start_new_msg(smi_info, msg, 3);
+	else
+		smi_info->handlers->start_transaction(smi_info->si_sm, msg, 3);
 	smi_info->si_state = SI_CLEARING_FLAGS;
 }
 
@@ -442,10 +469,8 @@ static void start_getting_msg_queue(struct smi_info *smi_info)
 	smi_info->curr_msg->data[1] = IPMI_GET_MSG_CMD;
 	smi_info->curr_msg->data_size = 2;
 
-	smi_info->handlers->start_transaction(
-		smi_info->si_sm,
-		smi_info->curr_msg->data,
-		smi_info->curr_msg->data_size);
+	start_new_msg(smi_info, smi_info->curr_msg->data,
+		      smi_info->curr_msg->data_size);
 	smi_info->si_state = SI_GETTING_MESSAGES;
 }
 
@@ -455,20 +480,11 @@ static void start_getting_events(struct smi_info *smi_info)
 	smi_info->curr_msg->data[1] = IPMI_READ_EVENT_MSG_BUFFER_CMD;
 	smi_info->curr_msg->data_size = 2;
 
-	smi_info->handlers->start_transaction(
-		smi_info->si_sm,
-		smi_info->curr_msg->data,
-		smi_info->curr_msg->data_size);
+	start_new_msg(smi_info, smi_info->curr_msg->data,
+		      smi_info->curr_msg->data_size);
 	smi_info->si_state = SI_GETTING_EVENTS;
 }
 
-static void smi_mod_timer(struct smi_info *smi_info, unsigned long new_val)
-{
-	smi_info->last_timeout_jiffies = jiffies;
-	mod_timer(&smi_info->si_timer, new_val);
-	smi_info->timer_running = true;
-}
-
 /*
  * When we have a situtaion where we run out of memory and cannot
  * allocate messages, we just leave them in the BMC and run the system
@@ -478,11 +494,11 @@ static void smi_mod_timer(struct smi_info *smi_info, unsigned long new_val)
  * Note that we cannot just use disable_irq(), since the interrupt may
  * be shared.
  */
-static inline bool disable_si_irq(struct smi_info *smi_info)
+static inline bool disable_si_irq(struct smi_info *smi_info, bool start_timer)
 {
 	if ((smi_info->irq) && (!smi_info->interrupt_disabled)) {
 		smi_info->interrupt_disabled = true;
-		start_check_enables(smi_info);
+		start_check_enables(smi_info, start_timer);
 		return true;
 	}
 	return false;
@@ -492,7 +508,7 @@ static inline bool enable_si_irq(struct smi_info *smi_info)
 {
 	if ((smi_info->irq) && (smi_info->interrupt_disabled)) {
 		smi_info->interrupt_disabled = false;
-		start_check_enables(smi_info);
+		start_check_enables(smi_info, true);
 		return true;
 	}
 	return false;
@@ -510,7 +526,7 @@ static struct ipmi_smi_msg *alloc_msg_handle_irq(struct smi_info *smi_info)
 
 	msg = ipmi_alloc_smi_msg();
 	if (!msg) {
-		if (!disable_si_irq(smi_info))
+		if (!disable_si_irq(smi_info, true))
 			smi_info->si_state = SI_NORMAL;
 	} else if (enable_si_irq(smi_info)) {
 		ipmi_free_smi_msg(msg);
@@ -526,7 +542,7 @@ static void handle_flags(struct smi_info *smi_info)
 		/* Watchdog pre-timeout */
 		smi_inc_stat(smi_info, watchdog_pretimeouts);
 
-		start_clear_flags(smi_info);
+		start_clear_flags(smi_info, true);
 		smi_info->msg_flags &= ~WDT_PRE_TIMEOUT_INT;
 		if (smi_info->intf)
 			ipmi_smi_watchdog_pretimeout(smi_info->intf);
@@ -879,8 +895,7 @@ static enum si_sm_result smi_event_handler(struct smi_info *smi_info,
 			msg[0] = (IPMI_NETFN_APP_REQUEST << 2);
 			msg[1] = IPMI_GET_MSG_FLAGS_CMD;
 
-			smi_info->handlers->start_transaction(
-				smi_info->si_sm, msg, 2);
+			start_new_msg(smi_info, msg, 2);
 			smi_info->si_state = SI_GETTING_FLAGS;
 			goto restart;
 		}
@@ -910,7 +925,7 @@ static enum si_sm_result smi_event_handler(struct smi_info *smi_info,
 		 * disable and messages disabled.
 		 */
 		if (smi_info->supports_event_msg_buff || smi_info->irq) {
-			start_check_enables(smi_info);
+			start_check_enables(smi_info, true);
 		} else {
 			smi_info->curr_msg = alloc_msg_handle_irq(smi_info);
 			if (!smi_info->curr_msg)
@@ -920,6 +935,13 @@ static enum si_sm_result smi_event_handler(struct smi_info *smi_info,
 		}
 		goto restart;
 	}
+
+	if (si_sm_result == SI_SM_IDLE && smi_info->timer_running) {
+		/* Ok it if fails, the timer will just go off. */
+		if (del_timer(&smi_info->si_timer))
+			smi_info->timer_running = false;
+	}
+
  out:
 	return si_sm_result;
 }
@@ -2560,6 +2582,7 @@ static const struct of_device_id of_ipmi_match[] = {
 	  .data = (void *)(unsigned long) SI_BT },
 	{},
 };
+MODULE_DEVICE_TABLE(of, of_ipmi_match);
 
 static int of_ipmi_probe(struct platform_device *dev)
 {
@@ -2646,7 +2669,6 @@ static int of_ipmi_probe(struct platform_device *dev)
 	}
 	return 0;
 }
-MODULE_DEVICE_TABLE(of, of_ipmi_match);
 #else
 #define of_ipmi_match NULL
 static int of_ipmi_probe(struct platform_device *dev)
@@ -3613,7 +3635,7 @@ static int try_smi_init(struct smi_info *new_smi)
 	 * Start clearing the flags before we enable interrupts or the
 	 * timer to avoid racing with the timer.
 	 */
-	start_clear_flags(new_smi);
+	start_clear_flags(new_smi, false);
 
 	/*
 	 * IRQ is defined to be set when non-zero.  req_events will
@@ -3908,7 +3930,7 @@ static void cleanup_one_si(struct smi_info *to_clean)
 		poll(to_clean);
 		schedule_timeout_uninterruptible(1);
 	}
-	disable_si_irq(to_clean);
+	disable_si_irq(to_clean, false);
 	while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) {
 		poll(to_clean);
 		schedule_timeout_uninterruptible(1);
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index 0ac3bd1a5497..096f0cef4da1 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -153,6 +153,9 @@ static int timeout = 10;
 /* The pre-timeout is disabled by default. */
 static int pretimeout;
 
+/* Default timeout to set on panic */
+static int panic_wdt_timeout = 255;
+
 /* Default action is to reset the board on a timeout. */
 static unsigned char action_val = WDOG_TIMEOUT_RESET;
 
@@ -293,6 +296,9 @@ MODULE_PARM_DESC(timeout, "Timeout value in seconds.");
 module_param(pretimeout, timeout, 0644);
 MODULE_PARM_DESC(pretimeout, "Pretimeout value in seconds.");
 
+module_param(panic_wdt_timeout, timeout, 0644);
+MODULE_PARM_DESC(timeout, "Timeout value on kernel panic in seconds.");
+
 module_param_cb(action, &param_ops_str, action_op, 0644);
 MODULE_PARM_DESC(action, "Timeout action. One of: "
 		 "reset, none, power_cycle, power_off.");
@@ -1189,7 +1195,7 @@ static int wdog_panic_handler(struct notifier_block *this,
 		/* Make sure we do this only once. */
 		panic_event_handled = 1;
 
-		timeout = 255;
+		timeout = panic_wdt_timeout;
 		pretimeout = 0;
 		panic_halt_ipmi_set_timeout();
 	}
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 71cfdf7c9708..2eb5f0efae90 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -1,4 +1,5 @@
 menu "Clock Source drivers"
+	depends on !ARCH_USES_GETTIMEOFFSET
 
 config CLKSRC_OF
 	bool
diff --git a/drivers/clocksource/fsl_ftm_timer.c b/drivers/clocksource/fsl_ftm_timer.c
index 10202f1fdfd7..517e1c7624d4 100644
--- a/drivers/clocksource/fsl_ftm_timer.c
+++ b/drivers/clocksource/fsl_ftm_timer.c
@@ -203,7 +203,7 @@ static int __init ftm_clockevent_init(unsigned long freq, int irq)
 	int err;
 
 	ftm_writel(0x00, priv->clkevt_base + FTM_CNTIN);
-	ftm_writel(~0UL, priv->clkevt_base + FTM_MOD);
+	ftm_writel(~0u, priv->clkevt_base + FTM_MOD);
 
 	ftm_reset_counter(priv->clkevt_base);
 
@@ -230,7 +230,7 @@ static int __init ftm_clocksource_init(unsigned long freq)
 	int err;
 
 	ftm_writel(0x00, priv->clksrc_base + FTM_CNTIN);
-	ftm_writel(~0UL, priv->clksrc_base + FTM_MOD);
+	ftm_writel(~0u, priv->clksrc_base + FTM_MOD);
 
 	ftm_reset_counter(priv->clksrc_base);
 
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 1582c1c016b0..235a1ba73d92 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -84,6 +84,7 @@ config ARM_KIRKWOOD_CPUFREQ
 config ARM_MT8173_CPUFREQ
 	bool "Mediatek MT8173 CPUFreq support"
 	depends on ARCH_MEDIATEK && REGULATOR
+	depends on ARM64 || (ARM_CPU_TOPOLOGY && COMPILE_TEST)
 	depends on !CPU_THERMAL || THERMAL=y
 	select PM_OPP
 	help
@@ -201,7 +202,7 @@ config ARM_SA1110_CPUFREQ
 
 config ARM_SCPI_CPUFREQ
         tristate "SCPI based CPUfreq driver"
-	depends on ARM_BIG_LITTLE_CPUFREQ && ARM_SCPI_PROTOCOL
+	depends on ARM_BIG_LITTLE_CPUFREQ && ARM_SCPI_PROTOCOL && COMMON_CLK_SCPI
         help
 	  This adds the CPUfreq driver support for ARM big.LITTLE platforms
 	  using SCPI protocol for CPU power management.
diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86
index adbd1de1cea5..c59bdcb83217 100644
--- a/drivers/cpufreq/Kconfig.x86
+++ b/drivers/cpufreq/Kconfig.x86
@@ -5,7 +5,6 @@
 config X86_INTEL_PSTATE
        bool "Intel P state control"
        depends on X86
-       select ACPI_PROCESSOR if ACPI
        help
           This driver provides a P state for Intel core processors.
 	  The driver implements an internal governor and will become
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index e8cb334094b0..7c0bdfb1a2ca 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -98,10 +98,11 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	policy->max = cpu->perf_caps.highest_perf;
 	policy->cpuinfo.min_freq = policy->min;
 	policy->cpuinfo.max_freq = policy->max;
+	policy->shared_type = cpu->shared_type;
 
 	if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY)
 		cpumask_copy(policy->cpus, cpu->shared_cpu_map);
-	else {
+	else if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL) {
 		/* Support only SW_ANY for now. */
 		pr_debug("Unsupported CPU co-ord type\n");
 		return -EFAULT;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 7c48e7316d91..8412ce5f93a7 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -976,10 +976,14 @@ static int cpufreq_init_policy(struct cpufreq_policy *policy)
 
 	new_policy.governor = gov;
 
-	/* Use the default policy if its valid. */
-	if (cpufreq_driver->setpolicy)
-		cpufreq_parse_governor(gov->name, &new_policy.policy, NULL);
-
+	/* Use the default policy if there is no last_policy. */
+	if (cpufreq_driver->setpolicy) {
+		if (policy->last_policy)
+			new_policy.policy = policy->last_policy;
+		else
+			cpufreq_parse_governor(gov->name, &new_policy.policy,
+					       NULL);
+	}
 	/* set default policy */
 	return cpufreq_set_policy(policy, &new_policy);
 }
@@ -1330,6 +1334,8 @@ static void cpufreq_offline_prepare(unsigned int cpu)
 		if (has_target())
 			strncpy(policy->last_governor, policy->governor->name,
 				CPUFREQ_NAME_LEN);
+		else
+			policy->last_policy = policy->policy;
 	} else if (cpu == policy->cpu) {
 		/* Nominate new CPU */
 		policy->cpu = cpumask_any(policy->cpus);
@@ -1401,13 +1407,10 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 	}
 
 	cpumask_clear_cpu(cpu, policy->real_cpus);
+	remove_cpu_dev_symlink(policy, cpu);
 
-	if (cpumask_empty(policy->real_cpus)) {
+	if (cpumask_empty(policy->real_cpus))
 		cpufreq_policy_free(policy, true);
-		return;
-	}
-
-	remove_cpu_dev_symlink(policy, cpu);
 }
 
 static void handle_update(struct work_struct *work)
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 2e31d097def6..4d07cbd2b23c 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -34,14 +34,10 @@
 #include <asm/cpu_device_id.h>
 #include <asm/cpufeature.h>
 
-#if IS_ENABLED(CONFIG_ACPI)
-#include <acpi/processor.h>
-#endif
-
-#define BYT_RATIOS		0x66a
-#define BYT_VIDS		0x66b
-#define BYT_TURBO_RATIOS	0x66c
-#define BYT_TURBO_VIDS		0x66d
+#define ATOM_RATIOS		0x66a
+#define ATOM_VIDS		0x66b
+#define ATOM_TURBO_RATIOS	0x66c
+#define ATOM_TURBO_VIDS		0x66d
 
 #define FRAC_BITS 8
 #define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
@@ -117,9 +113,6 @@ struct cpudata {
 	u64	prev_mperf;
 	u64	prev_tsc;
 	struct sample sample;
-#if IS_ENABLED(CONFIG_ACPI)
-	struct acpi_processor_performance acpi_perf_data;
-#endif
 };
 
 static struct cpudata **all_cpu_data;
@@ -150,7 +143,6 @@ struct cpu_defaults {
 static struct pstate_adjust_policy pid_params;
 static struct pstate_funcs pstate_funcs;
 static int hwp_active;
-static int no_acpi_perf;
 
 struct perf_limits {
 	int no_turbo;
@@ -163,8 +155,6 @@ struct perf_limits {
 	int max_sysfs_pct;
 	int min_policy_pct;
 	int min_sysfs_pct;
-	int max_perf_ctl;
-	int min_perf_ctl;
 };
 
 static struct perf_limits performance_limits = {
@@ -191,8 +181,6 @@ static struct perf_limits powersave_limits = {
 	.max_sysfs_pct = 100,
 	.min_policy_pct = 0,
 	.min_sysfs_pct = 0,
-	.max_perf_ctl = 0,
-	.min_perf_ctl = 0,
 };
 
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE
@@ -201,153 +189,6 @@ static struct perf_limits *limits = &performance_limits;
 static struct perf_limits *limits = &powersave_limits;
 #endif
 
-#if IS_ENABLED(CONFIG_ACPI)
-/*
- * The max target pstate ratio is a 8 bit value in both PLATFORM_INFO MSR and
- * in TURBO_RATIO_LIMIT MSR, which pstate driver stores in max_pstate and
- * max_turbo_pstate fields. The PERF_CTL MSR contains 16 bit value for P state
- * ratio, out of it only high 8 bits are used. For example 0x1700 is setting
- * target ratio 0x17. The _PSS control value stores in a format which can be
- * directly written to PERF_CTL MSR. But in intel_pstate driver this shift
- * occurs during write to PERF_CTL (E.g. for cores core_set_pstate()).
- * This function converts the _PSS control value to intel pstate driver format
- * for comparison and assignment.
- */
-static int convert_to_native_pstate_format(struct cpudata *cpu, int index)
-{
-	return cpu->acpi_perf_data.states[index].control >> 8;
-}
-
-static int intel_pstate_init_perf_limits(struct cpufreq_policy *policy)
-{
-	struct cpudata *cpu;
-	int ret;
-	bool turbo_absent = false;
-	int max_pstate_index;
-	int min_pss_ctl, max_pss_ctl, turbo_pss_ctl;
-	int i;
-
-	cpu = all_cpu_data[policy->cpu];
-
-	pr_debug("intel_pstate: default limits 0x%x 0x%x 0x%x\n",
-		 cpu->pstate.min_pstate, cpu->pstate.max_pstate,
-		 cpu->pstate.turbo_pstate);
-
-	if (!cpu->acpi_perf_data.shared_cpu_map &&
-	    zalloc_cpumask_var_node(&cpu->acpi_perf_data.shared_cpu_map,
-				    GFP_KERNEL, cpu_to_node(policy->cpu))) {
-		return -ENOMEM;
-	}
-
-	ret = acpi_processor_register_performance(&cpu->acpi_perf_data,
-						  policy->cpu);
-	if (ret)
-		return ret;
-
-	/*
-	 * Check if the control value in _PSS is for PERF_CTL MSR, which should
-	 * guarantee that the states returned by it map to the states in our
-	 * list directly.
-	 */
-	if (cpu->acpi_perf_data.control_register.space_id !=
-						ACPI_ADR_SPACE_FIXED_HARDWARE)
-		return -EIO;
-
-	pr_debug("intel_pstate: CPU%u - ACPI _PSS perf data\n", policy->cpu);
-	for (i = 0; i < cpu->acpi_perf_data.state_count; i++)
-		pr_debug("     %cP%d: %u MHz, %u mW, 0x%x\n",
-			 (i == cpu->acpi_perf_data.state ? '*' : ' '), i,
-			 (u32) cpu->acpi_perf_data.states[i].core_frequency,
-			 (u32) cpu->acpi_perf_data.states[i].power,
-			 (u32) cpu->acpi_perf_data.states[i].control);
-
-	/*
-	 * If there is only one entry _PSS, simply ignore _PSS and continue as
-	 * usual without taking _PSS into account
-	 */
-	if (cpu->acpi_perf_data.state_count < 2)
-		return 0;
-
-	turbo_pss_ctl = convert_to_native_pstate_format(cpu, 0);
-	min_pss_ctl = convert_to_native_pstate_format(cpu,
-					cpu->acpi_perf_data.state_count - 1);
-	/* Check if there is a turbo freq in _PSS */
-	if (turbo_pss_ctl <= cpu->pstate.max_pstate &&
-	    turbo_pss_ctl > cpu->pstate.min_pstate) {
-		pr_debug("intel_pstate: no turbo range exists in _PSS\n");
-		limits->no_turbo = limits->turbo_disabled = 1;
-		cpu->pstate.turbo_pstate = cpu->pstate.max_pstate;
-		turbo_absent = true;
-	}
-
-	/* Check if the max non turbo p state < Intel P state max */
-	max_pstate_index = turbo_absent ? 0 : 1;
-	max_pss_ctl = convert_to_native_pstate_format(cpu, max_pstate_index);
-	if (max_pss_ctl < cpu->pstate.max_pstate &&
-	    max_pss_ctl > cpu->pstate.min_pstate)
-		cpu->pstate.max_pstate = max_pss_ctl;
-
-	/* check If min perf > Intel P State min */
-	if (min_pss_ctl > cpu->pstate.min_pstate &&
-	    min_pss_ctl < cpu->pstate.max_pstate) {
-		cpu->pstate.min_pstate = min_pss_ctl;
-		policy->cpuinfo.min_freq = min_pss_ctl * cpu->pstate.scaling;
-	}
-
-	if (turbo_absent)
-		policy->cpuinfo.max_freq = cpu->pstate.max_pstate *
-						cpu->pstate.scaling;
-	else {
-		policy->cpuinfo.max_freq = cpu->pstate.turbo_pstate *
-						cpu->pstate.scaling;
-		/*
-		 * The _PSS table doesn't contain whole turbo frequency range.
-		 * This just contains +1 MHZ above the max non turbo frequency,
-		 * with control value corresponding to max turbo ratio. But
-		 * when cpufreq set policy is called, it will call with this
-		 * max frequency, which will cause a reduced performance as
-		 * this driver uses real max turbo frequency as the max
-		 * frequeny. So correct this frequency in _PSS table to
-		 * correct max turbo frequency based on the turbo ratio.
-		 * Also need to convert to MHz as _PSS freq is in MHz.
-		 */
-		cpu->acpi_perf_data.states[0].core_frequency =
-						turbo_pss_ctl * 100;
-	}
-
-	pr_debug("intel_pstate: Updated limits using _PSS 0x%x 0x%x 0x%x\n",
-		 cpu->pstate.min_pstate, cpu->pstate.max_pstate,
-		 cpu->pstate.turbo_pstate);
-	pr_debug("intel_pstate: policy max_freq=%d Khz min_freq = %d KHz\n",
-		 policy->cpuinfo.max_freq, policy->cpuinfo.min_freq);
-
-	return 0;
-}
-
-static int intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
-{
-	struct cpudata *cpu;
-
-	if (!no_acpi_perf)
-		return 0;
-
-	cpu = all_cpu_data[policy->cpu];
-	acpi_processor_unregister_performance(policy->cpu);
-	return 0;
-}
-
-#else
-static int intel_pstate_init_perf_limits(struct cpufreq_policy *policy)
-{
-	return 0;
-}
-
-static int intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
-{
-	return 0;
-}
-#endif
-
 static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
 			     int deadband, int integral) {
 	pid->setpoint = setpoint;
@@ -687,31 +528,31 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
 }
 
-static int byt_get_min_pstate(void)
+static int atom_get_min_pstate(void)
 {
 	u64 value;
 
-	rdmsrl(BYT_RATIOS, value);
+	rdmsrl(ATOM_RATIOS, value);
 	return (value >> 8) & 0x7F;
 }
 
-static int byt_get_max_pstate(void)
+static int atom_get_max_pstate(void)
 {
 	u64 value;
 
-	rdmsrl(BYT_RATIOS, value);
+	rdmsrl(ATOM_RATIOS, value);
 	return (value >> 16) & 0x7F;
 }
 
-static int byt_get_turbo_pstate(void)
+static int atom_get_turbo_pstate(void)
 {
 	u64 value;
 
-	rdmsrl(BYT_TURBO_RATIOS, value);
+	rdmsrl(ATOM_TURBO_RATIOS, value);
 	return value & 0x7F;
 }
 
-static void byt_set_pstate(struct cpudata *cpudata, int pstate)
+static void atom_set_pstate(struct cpudata *cpudata, int pstate)
 {
 	u64 val;
 	int32_t vid_fp;
@@ -736,27 +577,42 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate)
 	wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val);
 }
 
-#define BYT_BCLK_FREQS 5
-static int byt_freq_table[BYT_BCLK_FREQS] = { 833, 1000, 1333, 1167, 800};
-
-static int byt_get_scaling(void)
+static int silvermont_get_scaling(void)
 {
 	u64 value;
 	int i;
+	/* Defined in Table 35-6 from SDM (Sept 2015) */
+	static int silvermont_freq_table[] = {
+		83300, 100000, 133300, 116700, 80000};
 
 	rdmsrl(MSR_FSB_FREQ, value);
-	i = value & 0x3;
+	i = value & 0x7;
+	WARN_ON(i > 4);
 
-	BUG_ON(i > BYT_BCLK_FREQS);
+	return silvermont_freq_table[i];
+}
 
-	return byt_freq_table[i] * 100;
+static int airmont_get_scaling(void)
+{
+	u64 value;
+	int i;
+	/* Defined in Table 35-10 from SDM (Sept 2015) */
+	static int airmont_freq_table[] = {
+		83300, 100000, 133300, 116700, 80000,
+		93300, 90000, 88900, 87500};
+
+	rdmsrl(MSR_FSB_FREQ, value);
+	i = value & 0xF;
+	WARN_ON(i > 8);
+
+	return airmont_freq_table[i];
 }
 
-static void byt_get_vid(struct cpudata *cpudata)
+static void atom_get_vid(struct cpudata *cpudata)
 {
 	u64 value;
 
-	rdmsrl(BYT_VIDS, value);
+	rdmsrl(ATOM_VIDS, value);
 	cpudata->vid.min = int_tofp((value >> 8) & 0x7f);
 	cpudata->vid.max = int_tofp((value >> 16) & 0x7f);
 	cpudata->vid.ratio = div_fp(
@@ -764,7 +620,7 @@ static void byt_get_vid(struct cpudata *cpudata)
 		int_tofp(cpudata->pstate.max_pstate -
 			cpudata->pstate.min_pstate));
 
-	rdmsrl(BYT_TURBO_VIDS, value);
+	rdmsrl(ATOM_TURBO_VIDS, value);
 	cpudata->vid.turbo = value & 0x7f;
 }
 
@@ -885,7 +741,7 @@ static struct cpu_defaults core_params = {
 	},
 };
 
-static struct cpu_defaults byt_params = {
+static struct cpu_defaults silvermont_params = {
 	.pid_policy = {
 		.sample_rate_ms = 10,
 		.deadband = 0,
@@ -895,13 +751,33 @@ static struct cpu_defaults byt_params = {
 		.i_gain_pct = 4,
 	},
 	.funcs = {
-		.get_max = byt_get_max_pstate,
-		.get_max_physical = byt_get_max_pstate,
-		.get_min = byt_get_min_pstate,
-		.get_turbo = byt_get_turbo_pstate,
-		.set = byt_set_pstate,
-		.get_scaling = byt_get_scaling,
-		.get_vid = byt_get_vid,
+		.get_max = atom_get_max_pstate,
+		.get_max_physical = atom_get_max_pstate,
+		.get_min = atom_get_min_pstate,
+		.get_turbo = atom_get_turbo_pstate,
+		.set = atom_set_pstate,
+		.get_scaling = silvermont_get_scaling,
+		.get_vid = atom_get_vid,
+	},
+};
+
+static struct cpu_defaults airmont_params = {
+	.pid_policy = {
+		.sample_rate_ms = 10,
+		.deadband = 0,
+		.setpoint = 60,
+		.p_gain_pct = 14,
+		.d_gain_pct = 0,
+		.i_gain_pct = 4,
+	},
+	.funcs = {
+		.get_max = atom_get_max_pstate,
+		.get_max_physical = atom_get_max_pstate,
+		.get_min = atom_get_min_pstate,
+		.get_turbo = atom_get_turbo_pstate,
+		.set = atom_set_pstate,
+		.get_scaling = airmont_get_scaling,
+		.get_vid = atom_get_vid,
 	},
 };
 
@@ -938,23 +814,12 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
 	 * policy, or by cpu specific default values determined through
 	 * experimentation.
 	 */
-	if (limits->max_perf_ctl && limits->max_sysfs_pct >=
-						limits->max_policy_pct) {
-		*max = limits->max_perf_ctl;
-	} else {
-		max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf),
-					limits->max_perf));
-		*max = clamp_t(int, max_perf_adj, cpu->pstate.min_pstate,
-			       cpu->pstate.turbo_pstate);
-	}
+	max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf), limits->max_perf));
+	*max = clamp_t(int, max_perf_adj,
+			cpu->pstate.min_pstate, cpu->pstate.turbo_pstate);
 
-	if (limits->min_perf_ctl) {
-		*min = limits->min_perf_ctl;
-	} else {
-		min_perf = fp_toint(mul_fp(int_tofp(max_perf),
-				    limits->min_perf));
-		*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
-	}
+	min_perf = fp_toint(mul_fp(int_tofp(max_perf), limits->min_perf));
+	*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
 }
 
 static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate, bool force)
@@ -1153,7 +1018,7 @@ static void intel_pstate_timer_func(unsigned long __data)
 static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	ICPU(0x2a, core_params),
 	ICPU(0x2d, core_params),
-	ICPU(0x37, byt_params),
+	ICPU(0x37, silvermont_params),
 	ICPU(0x3a, core_params),
 	ICPU(0x3c, core_params),
 	ICPU(0x3d, core_params),
@@ -1162,7 +1027,7 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	ICPU(0x45, core_params),
 	ICPU(0x46, core_params),
 	ICPU(0x47, core_params),
-	ICPU(0x4c, byt_params),
+	ICPU(0x4c, airmont_params),
 	ICPU(0x4e, core_params),
 	ICPU(0x4f, core_params),
 	ICPU(0x5e, core_params),
@@ -1229,12 +1094,6 @@ static unsigned int intel_pstate_get(unsigned int cpu_num)
 
 static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 {
-#if IS_ENABLED(CONFIG_ACPI)
-	struct cpudata *cpu;
-	int i;
-#endif
-	pr_debug("intel_pstate: %s max %u policy->max %u\n", __func__,
-		 policy->cpuinfo.max_freq, policy->max);
 	if (!policy->cpuinfo.max_freq)
 		return -ENODEV;
 
@@ -1242,6 +1101,8 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	    policy->max >= policy->cpuinfo.max_freq) {
 		pr_debug("intel_pstate: set performance\n");
 		limits = &performance_limits;
+		if (hwp_active)
+			intel_pstate_hwp_set();
 		return 0;
 	}
 
@@ -1249,7 +1110,8 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	limits = &powersave_limits;
 	limits->min_policy_pct = (policy->min * 100) / policy->cpuinfo.max_freq;
 	limits->min_policy_pct = clamp_t(int, limits->min_policy_pct, 0 , 100);
-	limits->max_policy_pct = (policy->max * 100) / policy->cpuinfo.max_freq;
+	limits->max_policy_pct = DIV_ROUND_UP(policy->max * 100,
+					      policy->cpuinfo.max_freq);
 	limits->max_policy_pct = clamp_t(int, limits->max_policy_pct, 0 , 100);
 
 	/* Normalize user input to [min_policy_pct, max_policy_pct] */
@@ -1261,6 +1123,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 				   limits->max_sysfs_pct);
 	limits->max_perf_pct = max(limits->min_policy_pct,
 				   limits->max_perf_pct);
+	limits->max_perf = round_up(limits->max_perf, 8);
 
 	/* Make sure min_perf_pct <= max_perf_pct */
 	limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct);
@@ -1270,23 +1133,6 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	limits->max_perf = div_fp(int_tofp(limits->max_perf_pct),
 				  int_tofp(100));
 
-#if IS_ENABLED(CONFIG_ACPI)
-	cpu = all_cpu_data[policy->cpu];
-	for (i = 0; i < cpu->acpi_perf_data.state_count; i++) {
-		int control;
-
-		control = convert_to_native_pstate_format(cpu, i);
-		if (control * cpu->pstate.scaling == policy->max)
-			limits->max_perf_ctl = control;
-		if (control * cpu->pstate.scaling == policy->min)
-			limits->min_perf_ctl = control;
-	}
-
-	pr_debug("intel_pstate: max %u policy_max %u perf_ctl [0x%x-0x%x]\n",
-		 policy->cpuinfo.max_freq, policy->max, limits->min_perf_ctl,
-		 limits->max_perf_ctl);
-#endif
-
 	if (hwp_active)
 		intel_pstate_hwp_set();
 
@@ -1341,30 +1187,18 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
 	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
 	policy->cpuinfo.max_freq =
 		cpu->pstate.turbo_pstate * cpu->pstate.scaling;
-	if (!no_acpi_perf)
-		intel_pstate_init_perf_limits(policy);
-	/*
-	 * If there is no acpi perf data or error, we ignore and use Intel P
-	 * state calculated limits, So this is not fatal error.
-	 */
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
 	cpumask_set_cpu(policy->cpu, policy->cpus);
 
 	return 0;
 }
 
-static int intel_pstate_cpu_exit(struct cpufreq_policy *policy)
-{
-	return intel_pstate_exit_perf_limits(policy);
-}
-
 static struct cpufreq_driver intel_pstate_driver = {
 	.flags		= CPUFREQ_CONST_LOOPS,
 	.verify		= intel_pstate_verify_policy,
 	.setpolicy	= intel_pstate_set_policy,
 	.get		= intel_pstate_get,
 	.init		= intel_pstate_cpu_init,
-	.exit		= intel_pstate_cpu_exit,
 	.stop_cpu	= intel_pstate_stop_cpu,
 	.name		= "intel_pstate",
 };
@@ -1406,6 +1240,7 @@ static void copy_cpu_funcs(struct pstate_funcs *funcs)
 }
 
 #if IS_ENABLED(CONFIG_ACPI)
+#include <acpi/processor.h>
 
 static bool intel_pstate_no_acpi_pss(void)
 {
@@ -1601,9 +1436,6 @@ static int __init intel_pstate_setup(char *str)
 		force_load = 1;
 	if (!strcmp(str, "hwp_only"))
 		hwp_only = 1;
-	if (!strcmp(str, "no_acpi"))
-		no_acpi_perf = 1;
-
 	return 0;
 }
 early_param("intel_pstate", intel_pstate_setup);
diff --git a/drivers/crypto/nx/nx-aes-ccm.c b/drivers/crypto/nx/nx-aes-ccm.c
index 73ef49922788..7038f364acb5 100644
--- a/drivers/crypto/nx/nx-aes-ccm.c
+++ b/drivers/crypto/nx/nx-aes-ccm.c
@@ -409,7 +409,7 @@ static int ccm_nx_decrypt(struct aead_request   *req,
 		processed += to_process;
 	} while (processed < nbytes);
 
-	rc = memcmp(csbcpb->cpb.aes_ccm.out_pat_or_mac, priv->oauth_tag,
+	rc = crypto_memneq(csbcpb->cpb.aes_ccm.out_pat_or_mac, priv->oauth_tag,
 		    authsize) ? -EBADMSG : 0;
 out:
 	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
diff --git a/drivers/crypto/nx/nx-aes-gcm.c b/drivers/crypto/nx/nx-aes-gcm.c
index eee624f589b6..abd465f479c4 100644
--- a/drivers/crypto/nx/nx-aes-gcm.c
+++ b/drivers/crypto/nx/nx-aes-gcm.c
@@ -21,6 +21,7 @@
 
 #include <crypto/internal/aead.h>
 #include <crypto/aes.h>
+#include <crypto/algapi.h>
 #include <crypto/scatterwalk.h>
 #include <linux/module.h>
 #include <linux/types.h>
@@ -418,7 +419,7 @@ mac:
 			itag, req->src, req->assoclen + nbytes,
 			crypto_aead_authsize(crypto_aead_reqtfm(req)),
 			SCATTERWALK_FROM_SG);
-		rc = memcmp(itag, otag,
+		rc = crypto_memneq(itag, otag,
 			    crypto_aead_authsize(crypto_aead_reqtfm(req))) ?
 		     -EBADMSG : 0;
 	}
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index 46f531e19ccf..b6f9f42e2985 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -977,7 +977,7 @@ static void ipsec_esp_decrypt_swauth_done(struct device *dev,
 		} else
 			oicv = (char *)&edesc->link_tbl[0];
 
-		err = memcmp(oicv, icv, authsize) ? -EBADMSG : 0;
+		err = crypto_memneq(oicv, icv, authsize) ? -EBADMSG : 0;
 	}
 
 	kfree(edesc);
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 4e55239c7a30..53d22eb73b56 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -729,8 +729,8 @@ atc_prep_dma_interleaved(struct dma_chan *chan,
 		return NULL;
 
 	dev_info(chan2dev(chan),
-		 "%s: src=0x%08x, dest=0x%08x, numf=%d, frame_size=%d, flags=0x%lx\n",
-		__func__, xt->src_start, xt->dst_start, xt->numf,
+		 "%s: src=%pad, dest=%pad, numf=%d, frame_size=%d, flags=0x%lx\n",
+		__func__, &xt->src_start, &xt->dst_start, xt->numf,
 		xt->frame_size, flags);
 
 	/*
@@ -824,8 +824,8 @@ atc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	u32			ctrla;
 	u32			ctrlb;
 
-	dev_vdbg(chan2dev(chan), "prep_dma_memcpy: d0x%x s0x%x l0x%zx f0x%lx\n",
-			dest, src, len, flags);
+	dev_vdbg(chan2dev(chan), "prep_dma_memcpy: d%pad s%pad l0x%zx f0x%lx\n",
+			&dest, &src, len, flags);
 
 	if (unlikely(!len)) {
 		dev_dbg(chan2dev(chan), "prep_dma_memcpy: length is zero!\n");
@@ -938,8 +938,8 @@ atc_prep_dma_memset(struct dma_chan *chan, dma_addr_t dest, int value,
 	void __iomem		*vaddr;
 	dma_addr_t		paddr;
 
-	dev_vdbg(chan2dev(chan), "%s: d0x%x v0x%x l0x%zx f0x%lx\n", __func__,
-		dest, value, len, flags);
+	dev_vdbg(chan2dev(chan), "%s: d%pad v0x%x l0x%zx f0x%lx\n", __func__,
+		&dest, value, len, flags);
 
 	if (unlikely(!len)) {
 		dev_dbg(chan2dev(chan), "%s: length is zero!\n", __func__);
@@ -1022,8 +1022,8 @@ atc_prep_dma_memset_sg(struct dma_chan *chan,
 		dma_addr_t dest = sg_dma_address(sg);
 		size_t len = sg_dma_len(sg);
 
-		dev_vdbg(chan2dev(chan), "%s: d0x%08x, l0x%zx\n",
-			 __func__, dest, len);
+		dev_vdbg(chan2dev(chan), "%s: d%pad, l0x%zx\n",
+			 __func__, &dest, len);
 
 		if (!is_dma_fill_aligned(chan->device, dest, 0, len)) {
 			dev_err(chan2dev(chan), "%s: buffer is not aligned\n",
@@ -1439,9 +1439,9 @@ atc_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
 	unsigned int		periods = buf_len / period_len;
 	unsigned int		i;
 
-	dev_vdbg(chan2dev(chan), "prep_dma_cyclic: %s buf@0x%08x - %d (%d/%d)\n",
+	dev_vdbg(chan2dev(chan), "prep_dma_cyclic: %s buf@%pad - %d (%d/%d)\n",
 			direction == DMA_MEM_TO_DEV ? "TO DEVICE" : "FROM DEVICE",
-			buf_addr,
+			&buf_addr,
 			periods, buf_len, period_len);
 
 	if (unlikely(!atslave || !buf_len || !period_len)) {
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index d1cfc8c876f9..7f58f06157f6 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -385,9 +385,9 @@ static void vdbg_dump_regs(struct at_dma_chan *atchan) {}
 static void atc_dump_lli(struct at_dma_chan *atchan, struct at_lli *lli)
 {
 	dev_crit(chan2dev(&atchan->chan_common),
-		 "  desc: s0x%x d0x%x ctrl0x%x:0x%x l0x%x\n",
-		 lli->saddr, lli->daddr,
-		 lli->ctrla, lli->ctrlb, lli->dscr);
+		 "  desc: s%pad d%pad ctrl0x%x:0x%x l0x%pad\n",
+		 &lli->saddr, &lli->daddr,
+		 lli->ctrla, lli->ctrlb, &lli->dscr);
 }
 
 
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index b5e132d4bae5..7f039de143f0 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -920,8 +920,8 @@ at_xdmac_interleaved_queue_desc(struct dma_chan *chan,
 	desc->lld.mbr_cfg = chan_cc;
 
 	dev_dbg(chan2dev(chan),
-		"%s: lld: mbr_sa=0x%08x, mbr_da=0x%08x, mbr_ubc=0x%08x, mbr_cfg=0x%08x\n",
-		__func__, desc->lld.mbr_sa, desc->lld.mbr_da,
+		"%s: lld: mbr_sa=%pad, mbr_da=%pad, mbr_ubc=0x%08x, mbr_cfg=0x%08x\n",
+		__func__, &desc->lld.mbr_sa, &desc->lld.mbr_da,
 		desc->lld.mbr_ubc, desc->lld.mbr_cfg);
 
 	/* Chain lld. */
@@ -953,8 +953,8 @@ at_xdmac_prep_interleaved(struct dma_chan *chan,
 	if ((xt->numf > 1) && (xt->frame_size > 1))
 		return NULL;
 
-	dev_dbg(chan2dev(chan), "%s: src=0x%08x, dest=0x%08x, numf=%d, frame_size=%d, flags=0x%lx\n",
-		__func__, xt->src_start, xt->dst_start,	xt->numf,
+	dev_dbg(chan2dev(chan), "%s: src=%pad, dest=%pad, numf=%d, frame_size=%d, flags=0x%lx\n",
+		__func__, &xt->src_start, &xt->dst_start,	xt->numf,
 		xt->frame_size, flags);
 
 	src_addr = xt->src_start;
@@ -1179,8 +1179,8 @@ static struct at_xdmac_desc *at_xdmac_memset_create_desc(struct dma_chan *chan,
 	desc->lld.mbr_cfg = chan_cc;
 
 	dev_dbg(chan2dev(chan),
-		"%s: lld: mbr_da=0x%08x, mbr_ds=0x%08x, mbr_ubc=0x%08x, mbr_cfg=0x%08x\n",
-		__func__, desc->lld.mbr_da, desc->lld.mbr_ds, desc->lld.mbr_ubc,
+		"%s: lld: mbr_da=%pad, mbr_ds=%pad, mbr_ubc=0x%08x, mbr_cfg=0x%08x\n",
+		__func__, &desc->lld.mbr_da, &desc->lld.mbr_ds, desc->lld.mbr_ubc,
 		desc->lld.mbr_cfg);
 
 	return desc;
@@ -1193,8 +1193,8 @@ at_xdmac_prep_dma_memset(struct dma_chan *chan, dma_addr_t dest, int value,
 	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
 	struct at_xdmac_desc	*desc;
 
-	dev_dbg(chan2dev(chan), "%s: dest=0x%08x, len=%d, pattern=0x%x, flags=0x%lx\n",
-		__func__, dest, len, value, flags);
+	dev_dbg(chan2dev(chan), "%s: dest=%pad, len=%d, pattern=0x%x, flags=0x%lx\n",
+		__func__, &dest, len, value, flags);
 
 	if (unlikely(!len))
 		return NULL;
@@ -1229,8 +1229,8 @@ at_xdmac_prep_dma_memset_sg(struct dma_chan *chan, struct scatterlist *sgl,
 
 	/* Prepare descriptors. */
 	for_each_sg(sgl, sg, sg_len, i) {
-		dev_dbg(chan2dev(chan), "%s: dest=0x%08x, len=%d, pattern=0x%x, flags=0x%lx\n",
-			__func__, sg_dma_address(sg), sg_dma_len(sg),
+		dev_dbg(chan2dev(chan), "%s: dest=%pad, len=%d, pattern=0x%x, flags=0x%lx\n",
+			__func__, &sg_dma_address(sg), sg_dma_len(sg),
 			value, flags);
 		desc = at_xdmac_memset_create_desc(chan, atchan,
 						   sg_dma_address(sg),
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index 6b03e4e84e6b..0675e268d577 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -107,7 +107,7 @@
 
 /* CCCFG register */
 #define GET_NUM_DMACH(x)	(x & 0x7) /* bits 0-2 */
-#define GET_NUM_QDMACH(x)	(x & 0x70 >> 4) /* bits 4-6 */
+#define GET_NUM_QDMACH(x)	((x & 0x70) >> 4) /* bits 4-6 */
 #define GET_NUM_PAENTRY(x)	((x & 0x7000) >> 12) /* bits 12-14 */
 #define GET_NUM_EVQUE(x)	((x & 0x70000) >> 16) /* bits 16-18 */
 #define GET_NUM_REGN(x)		((x & 0x300000) >> 20) /* bits 20-21 */
@@ -1565,7 +1565,7 @@ static void edma_tc_set_pm_state(struct edma_tc *tc, bool enable)
 	struct platform_device *tc_pdev;
 	int ret;
 
-	if (!tc)
+	if (!IS_ENABLED(CONFIG_OF) || !tc)
 		return;
 
 	tc_pdev = of_find_device_by_node(tc->node);
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 7058d58ba588..0f6fd42f55ca 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -1462,7 +1462,7 @@ err_firmware:
 
 #define EVENT_REMAP_CELLS 3
 
-static int __init sdma_event_remap(struct sdma_engine *sdma)
+static int sdma_event_remap(struct sdma_engine *sdma)
 {
 	struct device_node *np = sdma->dev->of_node;
 	struct device_node *gpr_np = of_parse_phandle(np, "gpr", 0);
diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c
index ebd8a5f398b0..f1bcc2a163b3 100644
--- a/drivers/dma/sh/usb-dmac.c
+++ b/drivers/dma/sh/usb-dmac.c
@@ -679,8 +679,11 @@ static int usb_dmac_runtime_suspend(struct device *dev)
 	struct usb_dmac *dmac = dev_get_drvdata(dev);
 	int i;
 
-	for (i = 0; i < dmac->n_channels; ++i)
+	for (i = 0; i < dmac->n_channels; ++i) {
+		if (!dmac->channels[i].iomem)
+			break;
 		usb_dmac_chan_halt(&dmac->channels[i]);
+	}
 
 	return 0;
 }
@@ -799,11 +802,10 @@ static int usb_dmac_probe(struct platform_device *pdev)
 	ret = pm_runtime_get_sync(&pdev->dev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "runtime PM get sync failed (%d)\n", ret);
-		return ret;
+		goto error_pm;
 	}
 
 	ret = usb_dmac_init(dmac);
-	pm_runtime_put(&pdev->dev);
 
 	if (ret) {
 		dev_err(&pdev->dev, "failed to reset device\n");
@@ -851,10 +853,13 @@ static int usb_dmac_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto error;
 
+	pm_runtime_put(&pdev->dev);
 	return 0;
 
 error:
 	of_dma_controller_free(pdev->dev.of_node);
+	pm_runtime_put(&pdev->dev);
+error_pm:
 	pm_runtime_disable(&pdev->dev);
 	return ret;
 }
diff --git a/drivers/gpio/gpio-74xx-mmio.c b/drivers/gpio/gpio-74xx-mmio.c
index 6ed7c0fb3378..6b186829087c 100644
--- a/drivers/gpio/gpio-74xx-mmio.c
+++ b/drivers/gpio/gpio-74xx-mmio.c
@@ -113,13 +113,16 @@ static int mmio_74xx_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 
 static int mmio_74xx_gpio_probe(struct platform_device *pdev)
 {
-	const struct of_device_id *of_id =
-		of_match_device(mmio_74xx_gpio_ids, &pdev->dev);
+	const struct of_device_id *of_id;
 	struct mmio_74xx_gpio_priv *priv;
 	struct resource *res;
 	void __iomem *dat;
 	int err;
 
+	of_id = of_match_device(mmio_74xx_gpio_ids, &pdev->dev);
+	if (!of_id)
+		return -ENODEV;
+
 	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index 56d2d026e62e..f7fbb46d5d79 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -1122,8 +1122,6 @@ static int omap_gpio_chip_init(struct gpio_bank *bank, struct irq_chip *irqc)
 	/* MPUIO is a bit different, reading IRQ status clears it */
 	if (bank->is_mpuio) {
 		irqc->irq_ack = dummy_irq_chip.irq_ack;
-		irqc->irq_mask = irq_gc_mask_set_bit;
-		irqc->irq_unmask = irq_gc_mask_clr_bit;
 		if (!bank->regs->wkup_en)
 			irqc->irq_set_wake = NULL;
 	}
diff --git a/drivers/gpio/gpio-palmas.c b/drivers/gpio/gpio-palmas.c
index 171a6389f9ce..52b447c071cb 100644
--- a/drivers/gpio/gpio-palmas.c
+++ b/drivers/gpio/gpio-palmas.c
@@ -167,6 +167,8 @@ static int palmas_gpio_probe(struct platform_device *pdev)
 	const struct palmas_device_data *dev_data;
 
 	match = of_match_device(of_palmas_gpio_match, &pdev->dev);
+	if (!match)
+		return -ENODEV;
 	dev_data = match->data;
 	if (!dev_data)
 		dev_data = &palmas_dev_data;
diff --git a/drivers/gpio/gpio-syscon.c b/drivers/gpio/gpio-syscon.c
index 045a952576c7..7b25fdf64802 100644
--- a/drivers/gpio/gpio-syscon.c
+++ b/drivers/gpio/gpio-syscon.c
@@ -187,11 +187,15 @@ MODULE_DEVICE_TABLE(of, syscon_gpio_ids);
 static int syscon_gpio_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	const struct of_device_id *of_id = of_match_device(syscon_gpio_ids, dev);
+	const struct of_device_id *of_id;
 	struct syscon_gpio_priv *priv;
 	struct device_node *np = dev->of_node;
 	int ret;
 
+	of_id = of_match_device(syscon_gpio_ids, dev);
+	if (!of_id)
+		return -ENODEV;
+
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index 027e5f47dd28..896bf29776b0 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -375,6 +375,60 @@ static int tegra_gpio_irq_set_wake(struct irq_data *d, unsigned int enable)
 }
 #endif
 
+#ifdef	CONFIG_DEBUG_FS
+
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+static int dbg_gpio_show(struct seq_file *s, void *unused)
+{
+	int i;
+	int j;
+
+	for (i = 0; i < tegra_gpio_bank_count; i++) {
+		for (j = 0; j < 4; j++) {
+			int gpio = tegra_gpio_compose(i, j, 0);
+			seq_printf(s,
+				"%d:%d %02x %02x %02x %02x %02x %02x %06x\n",
+				i, j,
+				tegra_gpio_readl(GPIO_CNF(gpio)),
+				tegra_gpio_readl(GPIO_OE(gpio)),
+				tegra_gpio_readl(GPIO_OUT(gpio)),
+				tegra_gpio_readl(GPIO_IN(gpio)),
+				tegra_gpio_readl(GPIO_INT_STA(gpio)),
+				tegra_gpio_readl(GPIO_INT_ENB(gpio)),
+				tegra_gpio_readl(GPIO_INT_LVL(gpio)));
+		}
+	}
+	return 0;
+}
+
+static int dbg_gpio_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, dbg_gpio_show, &inode->i_private);
+}
+
+static const struct file_operations debug_fops = {
+	.open		= dbg_gpio_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static void tegra_gpio_debuginit(void)
+{
+	(void) debugfs_create_file("tegra_gpio", S_IRUGO,
+					NULL, NULL, &debug_fops);
+}
+
+#else
+
+static inline void tegra_gpio_debuginit(void)
+{
+}
+
+#endif
+
 static struct irq_chip tegra_gpio_irq_chip = {
 	.name		= "GPIO",
 	.irq_ack	= tegra_gpio_irq_ack,
@@ -519,6 +573,8 @@ static int tegra_gpio_probe(struct platform_device *pdev)
 			spin_lock_init(&bank->lvl_lock[j]);
 	}
 
+	tegra_gpio_debuginit();
+
 	return 0;
 }
 
@@ -536,52 +592,3 @@ static int __init tegra_gpio_init(void)
 	return platform_driver_register(&tegra_gpio_driver);
 }
 postcore_initcall(tegra_gpio_init);
-
-#ifdef	CONFIG_DEBUG_FS
-
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
-
-static int dbg_gpio_show(struct seq_file *s, void *unused)
-{
-	int i;
-	int j;
-
-	for (i = 0; i < tegra_gpio_bank_count; i++) {
-		for (j = 0; j < 4; j++) {
-			int gpio = tegra_gpio_compose(i, j, 0);
-			seq_printf(s,
-				"%d:%d %02x %02x %02x %02x %02x %02x %06x\n",
-				i, j,
-				tegra_gpio_readl(GPIO_CNF(gpio)),
-				tegra_gpio_readl(GPIO_OE(gpio)),
-				tegra_gpio_readl(GPIO_OUT(gpio)),
-				tegra_gpio_readl(GPIO_IN(gpio)),
-				tegra_gpio_readl(GPIO_INT_STA(gpio)),
-				tegra_gpio_readl(GPIO_INT_ENB(gpio)),
-				tegra_gpio_readl(GPIO_INT_LVL(gpio)));
-		}
-	}
-	return 0;
-}
-
-static int dbg_gpio_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, dbg_gpio_show, &inode->i_private);
-}
-
-static const struct file_operations debug_fops = {
-	.open		= dbg_gpio_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int __init tegra_gpio_debuginit(void)
-{
-	(void) debugfs_create_file("tegra_gpio", S_IRUGO,
-					NULL, NULL, &debug_fops);
-	return 0;
-}
-late_initcall(tegra_gpio_debuginit);
-#endif
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index a18f00fc1bb8..2a91f3287e3b 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -233,7 +233,7 @@ static struct gpio_desc *gpio_name_to_desc(const char * const name)
 		for (i = 0; i != chip->ngpio; ++i) {
 			struct gpio_desc *gpio = &chip->desc[i];
 
-			if (!gpio->name)
+			if (!gpio->name || !name)
 				continue;
 
 			if (!strcmp(gpio->name, name)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 615ce6d464fb..5a5f04d0902d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -389,7 +389,6 @@ struct amdgpu_clock {
  * Fences.
  */
 struct amdgpu_fence_driver {
-	struct amdgpu_ring		*ring;
 	uint64_t			gpu_addr;
 	volatile uint32_t		*cpu_addr;
 	/* sync_seq is protected by ring emission lock */
@@ -398,7 +397,7 @@ struct amdgpu_fence_driver {
 	bool				initialized;
 	struct amdgpu_irq_src		*irq_src;
 	unsigned			irq_type;
-	struct delayed_work             lockup_work;
+	struct timer_list		fallback_timer;
 	wait_queue_head_t		fence_queue;
 };
 
@@ -497,6 +496,7 @@ struct amdgpu_bo_va_mapping {
 
 /* bo virtual addresses in a specific vm */
 struct amdgpu_bo_va {
+	struct mutex		        mutex;
 	/* protected by bo being reserved */
 	struct list_head		bo_list;
 	struct fence		        *last_pt_update;
@@ -539,6 +539,7 @@ struct amdgpu_bo {
 	/* Constant after initialization */
 	struct amdgpu_device		*adev;
 	struct drm_gem_object		gem_base;
+	struct amdgpu_bo		*parent;
 
 	struct ttm_bo_kmap_obj		dma_buf_vmap;
 	pid_t				pid;
@@ -917,8 +918,8 @@ struct amdgpu_ring {
 #define AMDGPU_VM_FAULT_STOP_ALWAYS	2
 
 struct amdgpu_vm_pt {
-	struct amdgpu_bo		*bo;
-	uint64_t			addr;
+	struct amdgpu_bo	*bo;
+	uint64_t		addr;
 };
 
 struct amdgpu_vm_id {
@@ -926,13 +927,9 @@ struct amdgpu_vm_id {
 	uint64_t		pd_gpu_addr;
 	/* last flushed PD/PT update */
 	struct fence	        *flushed_updates;
-	/* last use of vmid */
-	struct fence		*last_id_use;
 };
 
 struct amdgpu_vm {
-	struct mutex		mutex;
-
 	struct rb_root		va;
 
 	/* protecting invalidated */
@@ -957,24 +954,72 @@ struct amdgpu_vm {
 
 	/* for id and flush management per ring */
 	struct amdgpu_vm_id	ids[AMDGPU_MAX_RINGS];
+	/* for interval tree */
+	spinlock_t		it_lock;
+	/* protecting freed */
+	spinlock_t		freed_lock;
 };
 
 struct amdgpu_vm_manager {
-	struct fence			*active[AMDGPU_NUM_VM];
-	uint32_t			max_pfn;
+	struct {
+		struct fence	*active;
+		atomic_long_t	owner;
+	} ids[AMDGPU_NUM_VM];
+
+	uint32_t				max_pfn;
 	/* number of VMIDs */
-	unsigned			nvm;
+	unsigned				nvm;
 	/* vram base address for page table entry  */
-	u64				vram_base_offset;
+	u64					vram_base_offset;
 	/* is vm enabled? */
-	bool				enabled;
-	/* for hw to save the PD addr on suspend/resume */
-	uint32_t			saved_table_addr[AMDGPU_NUM_VM];
+	bool					enabled;
 	/* vm pte handling */
 	const struct amdgpu_vm_pte_funcs        *vm_pte_funcs;
 	struct amdgpu_ring                      *vm_pte_funcs_ring;
 };
 
+void amdgpu_vm_manager_fini(struct amdgpu_device *adev);
+int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm);
+void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
+struct amdgpu_bo_list_entry *amdgpu_vm_get_bos(struct amdgpu_device *adev,
+					       struct amdgpu_vm *vm,
+					       struct list_head *head);
+int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
+		      struct amdgpu_sync *sync);
+void amdgpu_vm_flush(struct amdgpu_ring *ring,
+		     struct amdgpu_vm *vm,
+		     struct fence *updates);
+void amdgpu_vm_fence(struct amdgpu_device *adev,
+		     struct amdgpu_vm *vm,
+		     struct fence *fence);
+uint64_t amdgpu_vm_map_gart(struct amdgpu_device *adev, uint64_t addr);
+int amdgpu_vm_update_page_directory(struct amdgpu_device *adev,
+				    struct amdgpu_vm *vm);
+int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
+			  struct amdgpu_vm *vm);
+int amdgpu_vm_clear_invalids(struct amdgpu_device *adev, struct amdgpu_vm *vm,
+			     struct amdgpu_sync *sync);
+int amdgpu_vm_bo_update(struct amdgpu_device *adev,
+			struct amdgpu_bo_va *bo_va,
+			struct ttm_mem_reg *mem);
+void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
+			     struct amdgpu_bo *bo);
+struct amdgpu_bo_va *amdgpu_vm_bo_find(struct amdgpu_vm *vm,
+				       struct amdgpu_bo *bo);
+struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev,
+				      struct amdgpu_vm *vm,
+				      struct amdgpu_bo *bo);
+int amdgpu_vm_bo_map(struct amdgpu_device *adev,
+		     struct amdgpu_bo_va *bo_va,
+		     uint64_t addr, uint64_t offset,
+		     uint64_t size, uint32_t flags);
+int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
+		       struct amdgpu_bo_va *bo_va,
+		       uint64_t addr);
+void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
+		      struct amdgpu_bo_va *bo_va);
+int amdgpu_vm_free_job(struct amdgpu_job *job);
+
 /*
  * context related structures
  */
@@ -1211,6 +1256,7 @@ struct amdgpu_cs_parser {
 	/* relocations */
 	struct amdgpu_bo_list_entry	*vm_bos;
 	struct list_head	validated;
+	struct fence		*fence;
 
 	struct amdgpu_ib	*ibs;
 	uint32_t		num_ibs;
@@ -1226,7 +1272,7 @@ struct amdgpu_job {
 	struct amdgpu_device	*adev;
 	struct amdgpu_ib	*ibs;
 	uint32_t		num_ibs;
-	struct mutex            job_lock;
+	void			*owner;
 	struct amdgpu_user_fence uf;
 	int (*free_job)(struct amdgpu_job *job);
 };
@@ -2257,11 +2303,6 @@ void amdgpu_pci_config_reset(struct amdgpu_device *adev);
 bool amdgpu_card_posted(struct amdgpu_device *adev);
 void amdgpu_update_display_priority(struct amdgpu_device *adev);
 bool amdgpu_boot_test_post_card(struct amdgpu_device *adev);
-struct amdgpu_cs_parser *amdgpu_cs_parser_create(struct amdgpu_device *adev,
-						 struct drm_file *filp,
-						 struct amdgpu_ctx *ctx,
-						 struct amdgpu_ib *ibs,
-						 uint32_t num_ibs);
 
 int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data);
 int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type,
@@ -2319,49 +2360,6 @@ long amdgpu_kms_compat_ioctl(struct file *filp, unsigned int cmd,
 			     unsigned long arg);
 
 /*
- * vm
- */
-int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm);
-void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
-struct amdgpu_bo_list_entry *amdgpu_vm_get_bos(struct amdgpu_device *adev,
-					  struct amdgpu_vm *vm,
-					  struct list_head *head);
-int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
-		      struct amdgpu_sync *sync);
-void amdgpu_vm_flush(struct amdgpu_ring *ring,
-		     struct amdgpu_vm *vm,
-		     struct fence *updates);
-void amdgpu_vm_fence(struct amdgpu_device *adev,
-		     struct amdgpu_vm *vm,
-		     struct amdgpu_fence *fence);
-uint64_t amdgpu_vm_map_gart(struct amdgpu_device *adev, uint64_t addr);
-int amdgpu_vm_update_page_directory(struct amdgpu_device *adev,
-				    struct amdgpu_vm *vm);
-int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
-				struct amdgpu_vm *vm);
-int amdgpu_vm_clear_invalids(struct amdgpu_device *adev,
-				struct amdgpu_vm *vm, struct amdgpu_sync *sync);
-int amdgpu_vm_bo_update(struct amdgpu_device *adev,
-			struct amdgpu_bo_va *bo_va,
-			struct ttm_mem_reg *mem);
-void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
-			     struct amdgpu_bo *bo);
-struct amdgpu_bo_va *amdgpu_vm_bo_find(struct amdgpu_vm *vm,
-				       struct amdgpu_bo *bo);
-struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev,
-				      struct amdgpu_vm *vm,
-				      struct amdgpu_bo *bo);
-int amdgpu_vm_bo_map(struct amdgpu_device *adev,
-		     struct amdgpu_bo_va *bo_va,
-		     uint64_t addr, uint64_t offset,
-		     uint64_t size, uint32_t flags);
-int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
-		       struct amdgpu_bo_va *bo_va,
-		       uint64_t addr);
-void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
-		      struct amdgpu_bo_va *bo_va);
-int amdgpu_vm_free_job(struct amdgpu_job *job);
-/*
  * functions used by amdgpu_encoder.c
  */
 struct amdgpu_afmt_acr {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index dfc4d02c7a38..4f352ec9dec4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -127,30 +127,6 @@ int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type,
 	return 0;
 }
 
-struct amdgpu_cs_parser *amdgpu_cs_parser_create(struct amdgpu_device *adev,
-                                               struct drm_file *filp,
-                                               struct amdgpu_ctx *ctx,
-                                               struct amdgpu_ib *ibs,
-                                               uint32_t num_ibs)
-{
-	struct amdgpu_cs_parser *parser;
-	int i;
-
-	parser = kzalloc(sizeof(struct amdgpu_cs_parser), GFP_KERNEL);
-	if (!parser)
-		return NULL;
-
-	parser->adev = adev;
-	parser->filp = filp;
-	parser->ctx = ctx;
-	parser->ibs = ibs;
-	parser->num_ibs = num_ibs;
-	for (i = 0; i < num_ibs; i++)
-		ibs[i].ctx = ctx;
-
-	return parser;
-}
-
 int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 {
 	union drm_amdgpu_cs *cs = data;
@@ -246,6 +222,8 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 				}
 
 				p->uf.bo = gem_to_amdgpu_bo(gobj);
+				amdgpu_bo_ref(p->uf.bo);
+				drm_gem_object_unreference_unlocked(gobj);
 				p->uf.offset = fence_data->offset;
 			} else {
 				ret = -EINVAL;
@@ -463,8 +441,18 @@ static int cmp_size_smaller_first(void *priv, struct list_head *a,
 	return (int)la->robj->tbo.num_pages - (int)lb->robj->tbo.num_pages;
 }
 
-static void amdgpu_cs_parser_fini_early(struct amdgpu_cs_parser *parser, int error, bool backoff)
+/**
+ * cs_parser_fini() - clean parser states
+ * @parser:	parser structure holding parsing context.
+ * @error:	error number
+ *
+ * If error is set than unvalidate buffer, otherwise just free memory
+ * used by parsing context.
+ **/
+static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, bool backoff)
 {
+	unsigned i;
+
 	if (!error) {
 		/* Sort the buffer list from the smallest to largest buffer,
 		 * which affects the order of buffers in the LRU list.
@@ -479,17 +467,14 @@ static void amdgpu_cs_parser_fini_early(struct amdgpu_cs_parser *parser, int err
 		list_sort(NULL, &parser->validated, cmp_size_smaller_first);
 
 		ttm_eu_fence_buffer_objects(&parser->ticket,
-				&parser->validated,
-				&parser->ibs[parser->num_ibs-1].fence->base);
+					    &parser->validated,
+					    parser->fence);
 	} else if (backoff) {
 		ttm_eu_backoff_reservation(&parser->ticket,
 					   &parser->validated);
 	}
-}
+	fence_put(parser->fence);
 
-static void amdgpu_cs_parser_fini_late(struct amdgpu_cs_parser *parser)
-{
-	unsigned i;
 	if (parser->ctx)
 		amdgpu_ctx_put(parser->ctx);
 	if (parser->bo_list)
@@ -499,31 +484,12 @@ static void amdgpu_cs_parser_fini_late(struct amdgpu_cs_parser *parser)
 	for (i = 0; i < parser->nchunks; i++)
 		drm_free_large(parser->chunks[i].kdata);
 	kfree(parser->chunks);
-	if (!amdgpu_enable_scheduler)
-	{
-		if (parser->ibs)
-			for (i = 0; i < parser->num_ibs; i++)
-				amdgpu_ib_free(parser->adev, &parser->ibs[i]);
-		kfree(parser->ibs);
-		if (parser->uf.bo)
-			drm_gem_object_unreference_unlocked(&parser->uf.bo->gem_base);
-	}
-
-	kfree(parser);
-}
-
-/**
- * cs_parser_fini() - clean parser states
- * @parser:	parser structure holding parsing context.
- * @error:	error number
- *
- * If error is set than unvalidate buffer, otherwise just free memory
- * used by parsing context.
- **/
-static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, bool backoff)
-{
-       amdgpu_cs_parser_fini_early(parser, error, backoff);
-       amdgpu_cs_parser_fini_late(parser);
+	if (parser->ibs)
+		for (i = 0; i < parser->num_ibs; i++)
+			amdgpu_ib_free(parser->adev, &parser->ibs[i]);
+	kfree(parser->ibs);
+	if (parser->uf.bo)
+		amdgpu_bo_unref(&parser->uf.bo);
 }
 
 static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p,
@@ -610,15 +576,9 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 	}
 
 	r = amdgpu_bo_vm_update_pte(parser, vm);
-	if (r) {
-		goto out;
-	}
-	amdgpu_cs_sync_rings(parser);
-	if (!amdgpu_enable_scheduler)
-		r = amdgpu_ib_schedule(adev, parser->num_ibs, parser->ibs,
-				       parser->filp);
+	if (!r)
+		amdgpu_cs_sync_rings(parser);
 
-out:
 	return r;
 }
 
@@ -818,7 +778,7 @@ static int amdgpu_cs_free_job(struct amdgpu_job *job)
 			amdgpu_ib_free(job->adev, &job->ibs[i]);
 	kfree(job->ibs);
 	if (job->uf.bo)
-		drm_gem_object_unreference_unlocked(&job->uf.bo->gem_base);
+		amdgpu_bo_unref(&job->uf.bo);
 	return 0;
 }
 
@@ -826,38 +786,35 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 {
 	struct amdgpu_device *adev = dev->dev_private;
 	union drm_amdgpu_cs *cs = data;
-	struct amdgpu_fpriv *fpriv = filp->driver_priv;
-	struct amdgpu_vm *vm = &fpriv->vm;
-	struct amdgpu_cs_parser *parser;
+	struct amdgpu_cs_parser parser = {};
 	bool reserved_buffers = false;
 	int i, r;
 
 	if (!adev->accel_working)
 		return -EBUSY;
 
-	parser = amdgpu_cs_parser_create(adev, filp, NULL, NULL, 0);
-	if (!parser)
-		return -ENOMEM;
-	r = amdgpu_cs_parser_init(parser, data);
+	parser.adev = adev;
+	parser.filp = filp;
+
+	r = amdgpu_cs_parser_init(&parser, data);
 	if (r) {
 		DRM_ERROR("Failed to initialize parser !\n");
-		amdgpu_cs_parser_fini(parser, r, false);
+		amdgpu_cs_parser_fini(&parser, r, false);
 		r = amdgpu_cs_handle_lockup(adev, r);
 		return r;
 	}
-	mutex_lock(&vm->mutex);
-	r = amdgpu_cs_parser_relocs(parser);
+	r = amdgpu_cs_parser_relocs(&parser);
 	if (r == -ENOMEM)
 		DRM_ERROR("Not enough memory for command submission!\n");
 	else if (r && r != -ERESTARTSYS)
 		DRM_ERROR("Failed to process the buffer list %d!\n", r);
 	else if (!r) {
 		reserved_buffers = true;
-		r = amdgpu_cs_ib_fill(adev, parser);
+		r = amdgpu_cs_ib_fill(adev, &parser);
 	}
 
 	if (!r) {
-		r = amdgpu_cs_dependencies(adev, parser);
+		r = amdgpu_cs_dependencies(adev, &parser);
 		if (r)
 			DRM_ERROR("Failed in the dependencies handling %d!\n", r);
 	}
@@ -865,63 +822,71 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	if (r)
 		goto out;
 
-	for (i = 0; i < parser->num_ibs; i++)
-		trace_amdgpu_cs(parser, i);
+	for (i = 0; i < parser.num_ibs; i++)
+		trace_amdgpu_cs(&parser, i);
 
-	r = amdgpu_cs_ib_vm_chunk(adev, parser);
+	r = amdgpu_cs_ib_vm_chunk(adev, &parser);
 	if (r)
 		goto out;
 
-	if (amdgpu_enable_scheduler && parser->num_ibs) {
+	if (amdgpu_enable_scheduler && parser.num_ibs) {
+		struct amdgpu_ring * ring = parser.ibs->ring;
+		struct amd_sched_fence *fence;
 		struct amdgpu_job *job;
-		struct amdgpu_ring * ring =  parser->ibs->ring;
+
 		job = kzalloc(sizeof(struct amdgpu_job), GFP_KERNEL);
 		if (!job) {
 			r = -ENOMEM;
 			goto out;
 		}
+
 		job->base.sched = &ring->sched;
-		job->base.s_entity = &parser->ctx->rings[ring->idx].entity;
-		job->adev = parser->adev;
-		job->ibs = parser->ibs;
-		job->num_ibs = parser->num_ibs;
-		job->base.owner = parser->filp;
-		mutex_init(&job->job_lock);
+		job->base.s_entity = &parser.ctx->rings[ring->idx].entity;
+		job->adev = parser.adev;
+		job->owner = parser.filp;
+		job->free_job = amdgpu_cs_free_job;
+
+		job->ibs = parser.ibs;
+		job->num_ibs = parser.num_ibs;
+		parser.ibs = NULL;
+		parser.num_ibs = 0;
+
 		if (job->ibs[job->num_ibs - 1].user) {
-			memcpy(&job->uf,  &parser->uf,
-			       sizeof(struct amdgpu_user_fence));
+			job->uf = parser.uf;
 			job->ibs[job->num_ibs - 1].user = &job->uf;
+			parser.uf.bo = NULL;
 		}
 
-		job->free_job = amdgpu_cs_free_job;
-		mutex_lock(&job->job_lock);
-		r = amd_sched_entity_push_job(&job->base);
-		if (r) {
-			mutex_unlock(&job->job_lock);
+		fence = amd_sched_fence_create(job->base.s_entity,
+					       parser.filp);
+		if (!fence) {
+			r = -ENOMEM;
 			amdgpu_cs_free_job(job);
 			kfree(job);
 			goto out;
 		}
-		cs->out.handle =
-			amdgpu_ctx_add_fence(parser->ctx, ring,
-					     &job->base.s_fence->base);
-		parser->ibs[parser->num_ibs - 1].sequence = cs->out.handle;
+		job->base.s_fence = fence;
+		parser.fence = fence_get(&fence->base);
 
-		list_sort(NULL, &parser->validated, cmp_size_smaller_first);
-		ttm_eu_fence_buffer_objects(&parser->ticket,
-				&parser->validated,
-				&job->base.s_fence->base);
+		cs->out.handle = amdgpu_ctx_add_fence(parser.ctx, ring,
+						      &fence->base);
+		job->ibs[job->num_ibs - 1].sequence = cs->out.handle;
 
-		mutex_unlock(&job->job_lock);
-		amdgpu_cs_parser_fini_late(parser);
-		mutex_unlock(&vm->mutex);
-		return 0;
+		trace_amdgpu_cs_ioctl(job);
+		amd_sched_entity_push_job(&job->base);
+
+	} else {
+		struct amdgpu_fence *fence;
+
+		r = amdgpu_ib_schedule(adev, parser.num_ibs, parser.ibs,
+				       parser.filp);
+		fence = parser.ibs[parser.num_ibs - 1].fence;
+		parser.fence = fence_get(&fence->base);
+		cs->out.handle = parser.ibs[parser.num_ibs - 1].sequence;
 	}
 
-	cs->out.handle = parser->ibs[parser->num_ibs - 1].sequence;
 out:
-	amdgpu_cs_parser_fini(parser, r, reserved_buffers);
-	mutex_unlock(&vm->mutex);
+	amdgpu_cs_parser_fini(&parser, r, reserved_buffers);
 	r = amdgpu_cs_handle_lockup(adev, r);
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index e173a5a02f0d..5580d3420c3a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -73,6 +73,8 @@ static void amdgpu_flip_work_func(struct work_struct *__work)
 	struct drm_crtc *crtc = &amdgpuCrtc->base;
 	unsigned long flags;
 	unsigned i;
+	int vpos, hpos, stat, min_udelay;
+	struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id];
 
 	amdgpu_flip_wait_fence(adev, &work->excl);
 	for (i = 0; i < work->shared_count; ++i)
@@ -81,6 +83,41 @@ static void amdgpu_flip_work_func(struct work_struct *__work)
 	/* We borrow the event spin lock for protecting flip_status */
 	spin_lock_irqsave(&crtc->dev->event_lock, flags);
 
+	/* If this happens to execute within the "virtually extended" vblank
+	 * interval before the start of the real vblank interval then it needs
+	 * to delay programming the mmio flip until the real vblank is entered.
+	 * This prevents completing a flip too early due to the way we fudge
+	 * our vblank counter and vblank timestamps in order to work around the
+	 * problem that the hw fires vblank interrupts before actual start of
+	 * vblank (when line buffer refilling is done for a frame). It
+	 * complements the fudging logic in amdgpu_get_crtc_scanoutpos() for
+	 * timestamping and amdgpu_get_vblank_counter_kms() for vblank counts.
+	 *
+	 * In practice this won't execute very often unless on very fast
+	 * machines because the time window for this to happen is very small.
+	 */
+	for (;;) {
+		/* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank
+		 * start in hpos, and to the "fudged earlier" vblank start in
+		 * vpos.
+		 */
+		stat = amdgpu_get_crtc_scanoutpos(adev->ddev, work->crtc_id,
+						  GET_DISTANCE_TO_VBLANKSTART,
+						  &vpos, &hpos, NULL, NULL,
+						  &crtc->hwmode);
+
+		if ((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) !=
+		    (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE) ||
+		    !(vpos >= 0 && hpos <= 0))
+			break;
+
+		/* Sleep at least until estimated real start of hw vblank */
+		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+		min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5);
+		usleep_range(min_udelay, 2 * min_udelay);
+		spin_lock_irqsave(&crtc->dev->event_lock, flags);
+	};
+
 	/* do the flip (mmio) */
 	adev->mode_info.funcs->page_flip(adev, work->crtc_id, work->base);
 	/* set the flip status */
@@ -109,7 +146,7 @@ static void amdgpu_unpin_work_func(struct work_struct *__work)
 	} else
 		DRM_ERROR("failed to reserve buffer after flip\n");
 
-	drm_gem_object_unreference_unlocked(&work->old_rbo->gem_base);
+	amdgpu_bo_unref(&work->old_rbo);
 	kfree(work->shared);
 	kfree(work);
 }
@@ -148,8 +185,8 @@ int amdgpu_crtc_page_flip(struct drm_crtc *crtc,
 	obj = old_amdgpu_fb->obj;
 
 	/* take a reference to the old object */
-	drm_gem_object_reference(obj);
 	work->old_rbo = gem_to_amdgpu_bo(obj);
+	amdgpu_bo_ref(work->old_rbo);
 
 	new_amdgpu_fb = to_amdgpu_framebuffer(fb);
 	obj = new_amdgpu_fb->obj;
@@ -222,7 +259,7 @@ pflip_cleanup:
 	amdgpu_bo_unreserve(new_rbo);
 
 cleanup:
-	drm_gem_object_unreference_unlocked(&work->old_rbo->gem_base);
+	amdgpu_bo_unref(&work->old_rbo);
 	fence_put(work->excl);
 	for (i = 0; i < work->shared_count; ++i)
 		fence_put(work->shared[i]);
@@ -712,6 +749,15 @@ bool amdgpu_crtc_scaling_mode_fixup(struct drm_crtc *crtc,
  * \param dev Device to query.
  * \param pipe Crtc to query.
  * \param flags Flags from caller (DRM_CALLED_FROM_VBLIRQ or 0).
+ *              For driver internal use only also supports these flags:
+ *
+ *              USE_REAL_VBLANKSTART to use the real start of vblank instead
+ *              of a fudged earlier start of vblank.
+ *
+ *              GET_DISTANCE_TO_VBLANKSTART to return distance to the
+ *              fudged earlier start of vblank in *vpos and the distance
+ *              to true start of vblank in *hpos.
+ *
  * \param *vpos Location where vertical scanout position should be stored.
  * \param *hpos Location where horizontal scanout position should go.
  * \param *stime Target location for timestamp taken immediately before
@@ -776,10 +822,40 @@ int amdgpu_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
 		vbl_end = 0;
 	}
 
+	/* Called from driver internal vblank counter query code? */
+	if (flags & GET_DISTANCE_TO_VBLANKSTART) {
+	    /* Caller wants distance from real vbl_start in *hpos */
+	    *hpos = *vpos - vbl_start;
+	}
+
+	/* Fudge vblank to start a few scanlines earlier to handle the
+	 * problem that vblank irqs fire a few scanlines before start
+	 * of vblank. Some driver internal callers need the true vblank
+	 * start to be used and signal this via the USE_REAL_VBLANKSTART flag.
+	 *
+	 * The cause of the "early" vblank irq is that the irq is triggered
+	 * by the line buffer logic when the line buffer read position enters
+	 * the vblank, whereas our crtc scanout position naturally lags the
+	 * line buffer read position.
+	 */
+	if (!(flags & USE_REAL_VBLANKSTART))
+		vbl_start -= adev->mode_info.crtcs[pipe]->lb_vblank_lead_lines;
+
 	/* Test scanout position against vblank region. */
 	if ((*vpos < vbl_start) && (*vpos >= vbl_end))
 		in_vbl = false;
 
+	/* In vblank? */
+	if (in_vbl)
+	    ret |= DRM_SCANOUTPOS_IN_VBLANK;
+
+	/* Called from driver internal vblank counter query code? */
+	if (flags & GET_DISTANCE_TO_VBLANKSTART) {
+		/* Caller wants distance from fudged earlier vbl_start */
+		*vpos -= vbl_start;
+		return ret;
+	}
+
 	/* Check if inside vblank area and apply corrective offsets:
 	 * vpos will then be >=0 in video scanout area, but negative
 	 * within vblank area, counting down the number of lines until
@@ -795,32 +871,6 @@ int amdgpu_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
 	/* Correct for shifted end of vbl at vbl_end. */
 	*vpos = *vpos - vbl_end;
 
-	/* In vblank? */
-	if (in_vbl)
-		ret |= DRM_SCANOUTPOS_IN_VBLANK;
-
-	/* Is vpos outside nominal vblank area, but less than
-	 * 1/100 of a frame height away from start of vblank?
-	 * If so, assume this isn't a massively delayed vblank
-	 * interrupt, but a vblank interrupt that fired a few
-	 * microseconds before true start of vblank. Compensate
-	 * by adding a full frame duration to the final timestamp.
-	 * Happens, e.g., on ATI R500, R600.
-	 *
-	 * We only do this if DRM_CALLED_FROM_VBLIRQ.
-	 */
-	if ((flags & DRM_CALLED_FROM_VBLIRQ) && !in_vbl) {
-		vbl_start = mode->crtc_vdisplay;
-		vtotal = mode->crtc_vtotal;
-
-		if (vbl_start - *vpos < vtotal / 100) {
-			*vpos -= vtotal;
-
-			/* Signal this correction as "applied". */
-			ret |= 0x8;
-		}
-	}
-
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 257d72205bb5..3671f9f220bd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -47,6 +47,9 @@
  * that the the relevant GPU caches have been flushed.
  */
 
+static struct kmem_cache *amdgpu_fence_slab;
+static atomic_t amdgpu_fence_slab_ref = ATOMIC_INIT(0);
+
 /**
  * amdgpu_fence_write - write a fence value
  *
@@ -85,24 +88,6 @@ static u32 amdgpu_fence_read(struct amdgpu_ring *ring)
 }
 
 /**
- * amdgpu_fence_schedule_check - schedule lockup check
- *
- * @ring: pointer to struct amdgpu_ring
- *
- * Queues a delayed work item to check for lockups.
- */
-static void amdgpu_fence_schedule_check(struct amdgpu_ring *ring)
-{
-	/*
-	 * Do not reset the timer here with mod_delayed_work,
-	 * this can livelock in an interaction with TTM delayed destroy.
-	 */
-	queue_delayed_work(system_power_efficient_wq,
-		&ring->fence_drv.lockup_work,
-		AMDGPU_FENCE_JIFFIES_TIMEOUT);
-}
-
-/**
  * amdgpu_fence_emit - emit a fence on the requested ring
  *
  * @ring: ring the fence is associated with
@@ -118,7 +103,7 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, void *owner,
 	struct amdgpu_device *adev = ring->adev;
 
 	/* we are protected by the ring emission mutex */
-	*fence = kmalloc(sizeof(struct amdgpu_fence), GFP_KERNEL);
+	*fence = kmem_cache_alloc(amdgpu_fence_slab, GFP_KERNEL);
 	if ((*fence) == NULL) {
 		return -ENOMEM;
 	}
@@ -132,11 +117,23 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, void *owner,
 	amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
 			       (*fence)->seq,
 			       AMDGPU_FENCE_FLAG_INT);
-	trace_amdgpu_fence_emit(ring->adev->ddev, ring->idx, (*fence)->seq);
 	return 0;
 }
 
 /**
+ * amdgpu_fence_schedule_fallback - schedule fallback check
+ *
+ * @ring: pointer to struct amdgpu_ring
+ *
+ * Start a timer as fallback to our interrupts.
+ */
+static void amdgpu_fence_schedule_fallback(struct amdgpu_ring *ring)
+{
+	mod_timer(&ring->fence_drv.fallback_timer,
+		  jiffies + AMDGPU_FENCE_JIFFIES_TIMEOUT);
+}
+
+/**
  * amdgpu_fence_activity - check for fence activity
  *
  * @ring: pointer to struct amdgpu_ring
@@ -202,45 +199,38 @@ static bool amdgpu_fence_activity(struct amdgpu_ring *ring)
 	} while (atomic64_xchg(&ring->fence_drv.last_seq, seq) > seq);
 
 	if (seq < last_emitted)
-		amdgpu_fence_schedule_check(ring);
+		amdgpu_fence_schedule_fallback(ring);
 
 	return wake;
 }
 
 /**
- * amdgpu_fence_check_lockup - check for hardware lockup
+ * amdgpu_fence_process - process a fence
  *
- * @work: delayed work item
+ * @adev: amdgpu_device pointer
+ * @ring: ring index the fence is associated with
  *
- * Checks for fence activity and if there is none probe
- * the hardware if a lockup occured.
+ * Checks the current fence value and wakes the fence queue
+ * if the sequence number has increased (all asics).
  */
-static void amdgpu_fence_check_lockup(struct work_struct *work)
+void amdgpu_fence_process(struct amdgpu_ring *ring)
 {
-	struct amdgpu_fence_driver *fence_drv;
-	struct amdgpu_ring *ring;
-
-	fence_drv = container_of(work, struct amdgpu_fence_driver,
-				lockup_work.work);
-	ring = fence_drv->ring;
-
 	if (amdgpu_fence_activity(ring))
 		wake_up_all(&ring->fence_drv.fence_queue);
 }
 
 /**
- * amdgpu_fence_process - process a fence
+ * amdgpu_fence_fallback - fallback for hardware interrupts
  *
- * @adev: amdgpu_device pointer
- * @ring: ring index the fence is associated with
+ * @work: delayed work item
  *
- * Checks the current fence value and wakes the fence queue
- * if the sequence number has increased (all asics).
+ * Checks for fence activity.
  */
-void amdgpu_fence_process(struct amdgpu_ring *ring)
+static void amdgpu_fence_fallback(unsigned long arg)
 {
-	if (amdgpu_fence_activity(ring))
-		wake_up_all(&ring->fence_drv.fence_queue);
+	struct amdgpu_ring *ring = (void *)arg;
+
+	amdgpu_fence_process(ring);
 }
 
 /**
@@ -290,7 +280,7 @@ static int amdgpu_fence_ring_wait_seq(struct amdgpu_ring *ring, uint64_t seq)
 	if (atomic64_read(&ring->fence_drv.last_seq) >= seq)
 		return 0;
 
-	amdgpu_fence_schedule_check(ring);
+	amdgpu_fence_schedule_fallback(ring);
 	wait_event(ring->fence_drv.fence_queue, (
 		   (signaled = amdgpu_fence_seq_signaled(ring, seq))));
 
@@ -491,9 +481,8 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring)
 	atomic64_set(&ring->fence_drv.last_seq, 0);
 	ring->fence_drv.initialized = false;
 
-	INIT_DELAYED_WORK(&ring->fence_drv.lockup_work,
-			amdgpu_fence_check_lockup);
-	ring->fence_drv.ring = ring;
+	setup_timer(&ring->fence_drv.fallback_timer, amdgpu_fence_fallback,
+		    (unsigned long)ring);
 
 	init_waitqueue_head(&ring->fence_drv.fence_queue);
 
@@ -536,6 +525,13 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring)
  */
 int amdgpu_fence_driver_init(struct amdgpu_device *adev)
 {
+	if (atomic_inc_return(&amdgpu_fence_slab_ref) == 1) {
+		amdgpu_fence_slab = kmem_cache_create(
+			"amdgpu_fence", sizeof(struct amdgpu_fence), 0,
+			SLAB_HWCACHE_ALIGN, NULL);
+		if (!amdgpu_fence_slab)
+			return -ENOMEM;
+	}
 	if (amdgpu_debugfs_fence_init(adev))
 		dev_err(adev->dev, "fence debugfs file creation failed\n");
 
@@ -554,9 +550,12 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
 {
 	int i, r;
 
+	if (atomic_dec_and_test(&amdgpu_fence_slab_ref))
+		kmem_cache_destroy(amdgpu_fence_slab);
 	mutex_lock(&adev->ring_lock);
 	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
 		struct amdgpu_ring *ring = adev->rings[i];
+
 		if (!ring || !ring->fence_drv.initialized)
 			continue;
 		r = amdgpu_fence_wait_empty(ring);
@@ -568,6 +567,7 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
 		amdgpu_irq_put(adev, ring->fence_drv.irq_src,
 			       ring->fence_drv.irq_type);
 		amd_sched_fini(&ring->sched);
+		del_timer_sync(&ring->fence_drv.fallback_timer);
 		ring->fence_drv.initialized = false;
 	}
 	mutex_unlock(&adev->ring_lock);
@@ -751,18 +751,25 @@ static bool amdgpu_fence_enable_signaling(struct fence *f)
 	fence->fence_wake.func = amdgpu_fence_check_signaled;
 	__add_wait_queue(&ring->fence_drv.fence_queue, &fence->fence_wake);
 	fence_get(f);
-	amdgpu_fence_schedule_check(ring);
+	if (!timer_pending(&ring->fence_drv.fallback_timer))
+		amdgpu_fence_schedule_fallback(ring);
 	FENCE_TRACE(&fence->base, "armed on ring %i!\n", ring->idx);
 	return true;
 }
 
+static void amdgpu_fence_release(struct fence *f)
+{
+	struct amdgpu_fence *fence = to_amdgpu_fence(f);
+	kmem_cache_free(amdgpu_fence_slab, fence);
+}
+
 const struct fence_ops amdgpu_fence_ops = {
 	.get_driver_name = amdgpu_fence_get_driver_name,
 	.get_timeline_name = amdgpu_fence_get_timeline_name,
 	.enable_signaling = amdgpu_fence_enable_signaling,
 	.signaled = amdgpu_fence_is_signaled,
 	.wait = fence_default_wait,
-	.release = NULL,
+	.release = amdgpu_fence_release,
 };
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 087332858853..f6ea4b43a60c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -115,12 +115,9 @@ int amdgpu_gem_object_open(struct drm_gem_object *obj, struct drm_file *file_pri
 	struct amdgpu_vm *vm = &fpriv->vm;
 	struct amdgpu_bo_va *bo_va;
 	int r;
-	mutex_lock(&vm->mutex);
 	r = amdgpu_bo_reserve(rbo, false);
-	if (r) {
-		mutex_unlock(&vm->mutex);
+	if (r)
 		return r;
-	}
 
 	bo_va = amdgpu_vm_bo_find(vm, rbo);
 	if (!bo_va) {
@@ -129,7 +126,6 @@ int amdgpu_gem_object_open(struct drm_gem_object *obj, struct drm_file *file_pri
 		++bo_va->ref_count;
 	}
 	amdgpu_bo_unreserve(rbo);
-	mutex_unlock(&vm->mutex);
 	return 0;
 }
 
@@ -142,10 +138,8 @@ void amdgpu_gem_object_close(struct drm_gem_object *obj,
 	struct amdgpu_vm *vm = &fpriv->vm;
 	struct amdgpu_bo_va *bo_va;
 	int r;
-	mutex_lock(&vm->mutex);
 	r = amdgpu_bo_reserve(rbo, true);
 	if (r) {
-		mutex_unlock(&vm->mutex);
 		dev_err(adev->dev, "leaking bo va because "
 			"we fail to reserve bo (%d)\n", r);
 		return;
@@ -157,7 +151,6 @@ void amdgpu_gem_object_close(struct drm_gem_object *obj,
 		}
 	}
 	amdgpu_bo_unreserve(rbo);
-	mutex_unlock(&vm->mutex);
 }
 
 static int amdgpu_gem_handle_lockup(struct amdgpu_device *adev, int r)
@@ -242,8 +235,9 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
 	    AMDGPU_GEM_USERPTR_REGISTER))
 		return -EINVAL;
 
-	if (!(args->flags & AMDGPU_GEM_USERPTR_ANONONLY) ||
-		   !(args->flags & AMDGPU_GEM_USERPTR_REGISTER)) {
+	if (!(args->flags & AMDGPU_GEM_USERPTR_READONLY) && (
+	     !(args->flags & AMDGPU_GEM_USERPTR_ANONONLY) ||
+	     !(args->flags & AMDGPU_GEM_USERPTR_REGISTER))) {
 
 		/* if we want to write to it we must require anonymous
 		   memory and install a MMU notifier */
@@ -483,6 +477,9 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
 		if (domain == AMDGPU_GEM_DOMAIN_CPU)
 			goto error_unreserve;
 	}
+	r = amdgpu_vm_update_page_directory(adev, bo_va->vm);
+	if (r)
+		goto error_unreserve;
 
 	r = amdgpu_vm_clear_freed(adev, bo_va->vm);
 	if (r)
@@ -512,6 +509,9 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 	struct amdgpu_bo *rbo;
 	struct amdgpu_bo_va *bo_va;
+	struct ttm_validate_buffer tv, tv_pd;
+	struct ww_acquire_ctx ticket;
+	struct list_head list, duplicates;
 	uint32_t invalid_flags, va_flags = 0;
 	int r = 0;
 
@@ -547,19 +547,28 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 	gobj = drm_gem_object_lookup(dev, filp, args->handle);
 	if (gobj == NULL)
 		return -ENOENT;
-	mutex_lock(&fpriv->vm.mutex);
 	rbo = gem_to_amdgpu_bo(gobj);
-	r = amdgpu_bo_reserve(rbo, false);
+	INIT_LIST_HEAD(&list);
+	INIT_LIST_HEAD(&duplicates);
+	tv.bo = &rbo->tbo;
+	tv.shared = true;
+	list_add(&tv.head, &list);
+
+	if (args->operation == AMDGPU_VA_OP_MAP) {
+		tv_pd.bo = &fpriv->vm.page_directory->tbo;
+		tv_pd.shared = true;
+		list_add(&tv_pd.head, &list);
+	}
+	r = ttm_eu_reserve_buffers(&ticket, &list, true, &duplicates);
 	if (r) {
-		mutex_unlock(&fpriv->vm.mutex);
 		drm_gem_object_unreference_unlocked(gobj);
 		return r;
 	}
 
 	bo_va = amdgpu_vm_bo_find(&fpriv->vm, rbo);
 	if (!bo_va) {
-		amdgpu_bo_unreserve(rbo);
-		mutex_unlock(&fpriv->vm.mutex);
+		ttm_eu_backoff_reservation(&ticket, &list);
+		drm_gem_object_unreference_unlocked(gobj);
 		return -ENOENT;
 	}
 
@@ -581,10 +590,10 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 	default:
 		break;
 	}
-
+	ttm_eu_backoff_reservation(&ticket, &list);
 	if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE))
 		amdgpu_gem_va_update_vm(adev, bo_va, args->operation);
-	mutex_unlock(&fpriv->vm.mutex);
+
 	drm_gem_object_unreference_unlocked(gobj);
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index e65987743871..9e25edafa721 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -62,7 +62,7 @@ int amdgpu_ib_get(struct amdgpu_ring *ring, struct amdgpu_vm *vm,
 	int r;
 
 	if (size) {
-		r = amdgpu_sa_bo_new(adev, &adev->ring_tmp_bo,
+		r = amdgpu_sa_bo_new(&adev->ring_tmp_bo,
 				      &ib->sa_bo, size, 256);
 		if (r) {
 			dev_err(adev->dev, "failed to get a new IB (%d)\n", r);
@@ -216,7 +216,7 @@ int amdgpu_ib_schedule(struct amdgpu_device *adev, unsigned num_ibs,
 	}
 
 	if (ib->vm)
-		amdgpu_vm_fence(adev, ib->vm, ib->fence);
+		amdgpu_vm_fence(adev, ib->vm, &ib->fence->base);
 
 	amdgpu_ring_unlock_commit(ring);
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 1618e2294a16..e23843f4d877 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -611,13 +611,59 @@ void amdgpu_driver_preclose_kms(struct drm_device *dev,
 u32 amdgpu_get_vblank_counter_kms(struct drm_device *dev, unsigned int pipe)
 {
 	struct amdgpu_device *adev = dev->dev_private;
+	int vpos, hpos, stat;
+	u32 count;
 
 	if (pipe >= adev->mode_info.num_crtc) {
 		DRM_ERROR("Invalid crtc %u\n", pipe);
 		return -EINVAL;
 	}
 
-	return amdgpu_display_vblank_get_counter(adev, pipe);
+	/* The hw increments its frame counter at start of vsync, not at start
+	 * of vblank, as is required by DRM core vblank counter handling.
+	 * Cook the hw count here to make it appear to the caller as if it
+	 * incremented at start of vblank. We measure distance to start of
+	 * vblank in vpos. vpos therefore will be >= 0 between start of vblank
+	 * and start of vsync, so vpos >= 0 means to bump the hw frame counter
+	 * result by 1 to give the proper appearance to caller.
+	 */
+	if (adev->mode_info.crtcs[pipe]) {
+		/* Repeat readout if needed to provide stable result if
+		 * we cross start of vsync during the queries.
+		 */
+		do {
+			count = amdgpu_display_vblank_get_counter(adev, pipe);
+			/* Ask amdgpu_get_crtc_scanoutpos to return vpos as
+			 * distance to start of vblank, instead of regular
+			 * vertical scanout pos.
+			 */
+			stat = amdgpu_get_crtc_scanoutpos(
+				dev, pipe, GET_DISTANCE_TO_VBLANKSTART,
+				&vpos, &hpos, NULL, NULL,
+				&adev->mode_info.crtcs[pipe]->base.hwmode);
+		} while (count != amdgpu_display_vblank_get_counter(adev, pipe));
+
+		if (((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) !=
+		    (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE))) {
+			DRM_DEBUG_VBL("Query failed! stat %d\n", stat);
+		} else {
+			DRM_DEBUG_VBL("crtc %d: dist from vblank start %d\n",
+				      pipe, vpos);
+
+			/* Bump counter if we are at >= leading edge of vblank,
+			 * but before vsync where vpos would turn negative and
+			 * the hw counter really increments.
+			 */
+			if (vpos >= 0)
+				count++;
+		}
+	} else {
+		/* Fallback to use value as is. */
+		count = amdgpu_display_vblank_get_counter(adev, pipe);
+		DRM_DEBUG_VBL("NULL mode info! Returned count may be wrong.\n");
+	}
+
+	return count;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index b62c1710cab6..064ebb347074 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -407,6 +407,7 @@ struct amdgpu_crtc {
 	u32 line_time;
 	u32 wm_low;
 	u32 wm_high;
+	u32 lb_vblank_lead_lines;
 	struct drm_display_mode hw_mode;
 };
 
@@ -528,6 +529,10 @@ struct amdgpu_framebuffer {
 #define ENCODER_MODE_IS_DP(em) (((em) == ATOM_ENCODER_MODE_DP) || \
 				((em) == ATOM_ENCODER_MODE_DP_MST))
 
+/* Driver internal use only flags of amdgpu_get_crtc_scanoutpos() */
+#define USE_REAL_VBLANKSTART 		(1 << 30)
+#define GET_DISTANCE_TO_VBLANKSTART	(1 << 31)
+
 void amdgpu_link_encoder_connector(struct drm_device *dev);
 
 struct drm_connector *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 0d524384ff79..c3ce103b6a33 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -100,6 +100,7 @@ static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
 	list_del_init(&bo->list);
 	mutex_unlock(&bo->adev->gem.mutex);
 	drm_gem_object_release(&bo->gem_base);
+	amdgpu_bo_unref(&bo->parent);
 	kfree(bo->metadata);
 	kfree(bo);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 3c2ff4567798..ea756e77b023 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -189,10 +189,9 @@ int amdgpu_sa_bo_manager_start(struct amdgpu_device *adev,
 				      struct amdgpu_sa_manager *sa_manager);
 int amdgpu_sa_bo_manager_suspend(struct amdgpu_device *adev,
 					struct amdgpu_sa_manager *sa_manager);
-int amdgpu_sa_bo_new(struct amdgpu_device *adev,
-			    struct amdgpu_sa_manager *sa_manager,
-			    struct amdgpu_sa_bo **sa_bo,
-			    unsigned size, unsigned align);
+int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager,
+		     struct amdgpu_sa_bo **sa_bo,
+		     unsigned size, unsigned align);
 void amdgpu_sa_bo_free(struct amdgpu_device *adev,
 			      struct amdgpu_sa_bo **sa_bo,
 			      struct fence *fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
index 0212b31dc194..8b88edb0434b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
@@ -311,8 +311,7 @@ static bool amdgpu_sa_bo_next_hole(struct amdgpu_sa_manager *sa_manager,
 	return false;
 }
 
-int amdgpu_sa_bo_new(struct amdgpu_device *adev,
-		     struct amdgpu_sa_manager *sa_manager,
+int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager,
 		     struct amdgpu_sa_bo **sa_bo,
 		     unsigned size, unsigned align)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
index dcf4a8aca680..438c05254695 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
@@ -26,6 +26,7 @@
 #include <linux/sched.h>
 #include <drm/drmP.h>
 #include "amdgpu.h"
+#include "amdgpu_trace.h"
 
 static struct fence *amdgpu_sched_dependency(struct amd_sched_job *sched_job)
 {
@@ -44,11 +45,8 @@ static struct fence *amdgpu_sched_run_job(struct amd_sched_job *sched_job)
 		return NULL;
 	}
 	job = to_amdgpu_job(sched_job);
-	mutex_lock(&job->job_lock);
-	r = amdgpu_ib_schedule(job->adev,
-			       job->num_ibs,
-			       job->ibs,
-			       job->base.owner);
+	trace_amdgpu_sched_run_job(job);
+	r = amdgpu_ib_schedule(job->adev, job->num_ibs, job->ibs, job->owner);
 	if (r) {
 		DRM_ERROR("Error scheduling IBs (%d)\n", r);
 		goto err;
@@ -61,8 +59,6 @@ err:
 	if (job->free_job)
 		job->free_job(job);
 
-	mutex_unlock(&job->job_lock);
-	fence_put(&job->base.s_fence->base);
 	kfree(job);
 	return fence ? &fence->base : NULL;
 }
@@ -88,21 +84,19 @@ int amdgpu_sched_ib_submit_kernel_helper(struct amdgpu_device *adev,
 			return -ENOMEM;
 		job->base.sched = &ring->sched;
 		job->base.s_entity = &adev->kernel_ctx.rings[ring->idx].entity;
+		job->base.s_fence = amd_sched_fence_create(job->base.s_entity, owner);
+		if (!job->base.s_fence) {
+			kfree(job);
+			return -ENOMEM;
+		}
+		*f = fence_get(&job->base.s_fence->base);
+
 		job->adev = adev;
 		job->ibs = ibs;
 		job->num_ibs = num_ibs;
-		job->base.owner = owner;
-		mutex_init(&job->job_lock);
+		job->owner = owner;
 		job->free_job = free_job;
-		mutex_lock(&job->job_lock);
-		r = amd_sched_entity_push_job(&job->base);
-		if (r) {
-			mutex_unlock(&job->job_lock);
-			kfree(job);
-			return r;
-		}
-		*f = fence_get(&job->base.s_fence->base);
-		mutex_unlock(&job->job_lock);
+		amd_sched_entity_push_job(&job->base);
 	} else {
 		r = amdgpu_ib_schedule(adev, num_ibs, ibs, owner);
 		if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c
index ff3ca52ec6fe..1caaf201b708 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c
@@ -40,7 +40,7 @@ int amdgpu_semaphore_create(struct amdgpu_device *adev,
 	if (*semaphore == NULL) {
 		return -ENOMEM;
 	}
-	r = amdgpu_sa_bo_new(adev, &adev->ring_tmp_bo,
+	r = amdgpu_sa_bo_new(&adev->ring_tmp_bo,
 			     &(*semaphore)->sa_bo, 8, 8);
 	if (r) {
 		kfree(*semaphore);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
index a6697fd05217..dd005c336c97 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
@@ -302,8 +302,14 @@ int amdgpu_sync_rings(struct amdgpu_sync *sync,
 			return -EINVAL;
 		}
 
-		if (amdgpu_enable_scheduler || !amdgpu_enable_semaphores ||
-		    (count >= AMDGPU_NUM_SYNCS)) {
+		if (amdgpu_enable_scheduler || !amdgpu_enable_semaphores) {
+			r = fence_wait(&fence->base, true);
+			if (r)
+				return r;
+			continue;
+		}
+
+		if (count >= AMDGPU_NUM_SYNCS) {
 			/* not enough room, wait manually */
 			r = fence_wait(&fence->base, false);
 			if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index 76ecbaf72a2e..8f9834ab1bd5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -48,6 +48,57 @@ TRACE_EVENT(amdgpu_cs,
 		      __entry->fences)
 );
 
+TRACE_EVENT(amdgpu_cs_ioctl,
+	    TP_PROTO(struct amdgpu_job *job),
+	    TP_ARGS(job),
+	    TP_STRUCT__entry(
+			     __field(struct amdgpu_device *, adev)
+			     __field(struct amd_sched_job *, sched_job)
+			     __field(struct amdgpu_ib *, ib)
+			     __field(struct fence *, fence)
+			     __field(char *, ring_name)
+			     __field(u32, num_ibs)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->adev = job->adev;
+			   __entry->sched_job = &job->base;
+			   __entry->ib = job->ibs;
+			   __entry->fence = &job->base.s_fence->base;
+			   __entry->ring_name = job->ibs[0].ring->name;
+			   __entry->num_ibs = job->num_ibs;
+			   ),
+	    TP_printk("adev=%p, sched_job=%p, first ib=%p, sched fence=%p, ring name:%s, num_ibs:%u",
+		      __entry->adev, __entry->sched_job, __entry->ib,
+		      __entry->fence, __entry->ring_name, __entry->num_ibs)
+);
+
+TRACE_EVENT(amdgpu_sched_run_job,
+	    TP_PROTO(struct amdgpu_job *job),
+	    TP_ARGS(job),
+	    TP_STRUCT__entry(
+			     __field(struct amdgpu_device *, adev)
+			     __field(struct amd_sched_job *, sched_job)
+			     __field(struct amdgpu_ib *, ib)
+			     __field(struct fence *, fence)
+			     __field(char *, ring_name)
+			     __field(u32, num_ibs)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->adev = job->adev;
+			   __entry->sched_job = &job->base;
+			   __entry->ib = job->ibs;
+			   __entry->fence = &job->base.s_fence->base;
+			   __entry->ring_name = job->ibs[0].ring->name;
+			   __entry->num_ibs = job->num_ibs;
+			   ),
+	    TP_printk("adev=%p, sched_job=%p, first ib=%p, sched fence=%p, ring name:%s, num_ibs:%u",
+		      __entry->adev, __entry->sched_job, __entry->ib,
+		      __entry->fence, __entry->ring_name, __entry->num_ibs)
+);
+
+
 TRACE_EVENT(amdgpu_vm_grab_id,
 	    TP_PROTO(unsigned vmid, int ring),
 	    TP_ARGS(vmid, ring),
@@ -196,49 +247,6 @@ TRACE_EVENT(amdgpu_bo_list_set,
 	    TP_printk("list=%p, bo=%p", __entry->list, __entry->bo)
 );
 
-DECLARE_EVENT_CLASS(amdgpu_fence_request,
-
-	    TP_PROTO(struct drm_device *dev, int ring, u32 seqno),
-
-	    TP_ARGS(dev, ring, seqno),
-
-	    TP_STRUCT__entry(
-			     __field(u32, dev)
-			     __field(int, ring)
-			     __field(u32, seqno)
-			     ),
-
-	    TP_fast_assign(
-			   __entry->dev = dev->primary->index;
-			   __entry->ring = ring;
-			   __entry->seqno = seqno;
-			   ),
-
-	    TP_printk("dev=%u, ring=%d, seqno=%u",
-		      __entry->dev, __entry->ring, __entry->seqno)
-);
-
-DEFINE_EVENT(amdgpu_fence_request, amdgpu_fence_emit,
-
-	    TP_PROTO(struct drm_device *dev, int ring, u32 seqno),
-
-	    TP_ARGS(dev, ring, seqno)
-);
-
-DEFINE_EVENT(amdgpu_fence_request, amdgpu_fence_wait_begin,
-
-	    TP_PROTO(struct drm_device *dev, int ring, u32 seqno),
-
-	    TP_ARGS(dev, ring, seqno)
-);
-
-DEFINE_EVENT(amdgpu_fence_request, amdgpu_fence_wait_end,
-
-	    TP_PROTO(struct drm_device *dev, int ring, u32 seqno),
-
-	    TP_ARGS(dev, ring, seqno)
-);
-
 DECLARE_EVENT_CLASS(amdgpu_semaphore_request,
 
 	    TP_PROTO(int ring, struct amdgpu_semaphore *sem),
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 81bb8e9fc26d..8a1752ff3d8e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -587,9 +587,13 @@ static int amdgpu_ttm_backend_bind(struct ttm_tt *ttm,
 	uint32_t flags = amdgpu_ttm_tt_pte_flags(gtt->adev, ttm, bo_mem);
 	int r;
 
-	if (gtt->userptr)
-		amdgpu_ttm_tt_pin_userptr(ttm);
-
+	if (gtt->userptr) {
+		r = amdgpu_ttm_tt_pin_userptr(ttm);
+		if (r) {
+			DRM_ERROR("failed to pin userptr\n");
+			return r;
+		}
+	}
 	gtt->offset = (unsigned long)(bo_mem->start << PAGE_SHIFT);
 	if (!ttm->num_pages) {
 		WARN(1, "nothing to bind %lu pages for mreg %p back %p!\n",
@@ -797,11 +801,12 @@ uint32_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm,
 	if (mem && mem->mem_type != TTM_PL_SYSTEM)
 		flags |= AMDGPU_PTE_VALID;
 
-	if (mem && mem->mem_type == TTM_PL_TT)
+	if (mem && mem->mem_type == TTM_PL_TT) {
 		flags |= AMDGPU_PTE_SYSTEM;
 
-	if (!ttm || ttm->caching_state == tt_cached)
-		flags |= AMDGPU_PTE_SNOOPED;
+		if (ttm->caching_state == tt_cached)
+			flags |= AMDGPU_PTE_SNOOPED;
+	}
 
 	if (adev->asic_type >= CHIP_TOPAZ)
 		flags |= AMDGPU_PTE_EXECUTABLE;
@@ -1073,10 +1078,10 @@ static int amdgpu_mm_dump_table(struct seq_file *m, void *data)
 	ret = drm_mm_dump_table(m, mm);
 	spin_unlock(&glob->lru_lock);
 	if (ttm_pl == TTM_PL_VRAM)
-		seq_printf(m, "man size:%llu pages, ram usage:%luMB, vis usage:%luMB\n",
+		seq_printf(m, "man size:%llu pages, ram usage:%lluMB, vis usage:%lluMB\n",
 			   adev->mman.bdev.man[ttm_pl].size,
-			   atomic64_read(&adev->vram_usage) >> 20,
-			   atomic64_read(&adev->vram_vis_usage) >> 20);
+			   (u64)atomic64_read(&adev->vram_usage) >> 20,
+			   (u64)atomic64_read(&adev->vram_vis_usage) >> 20);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 03f0c3bae516..a745eeeb5d82 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -392,7 +392,10 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
 	ib->ptr[ib->length_dw++] = 0x00000001; /* session cmd */
 	ib->ptr[ib->length_dw++] = handle;
 
-	ib->ptr[ib->length_dw++] = 0x00000030; /* len */
+	if ((ring->adev->vce.fw_version >> 24) >= 52)
+		ib->ptr[ib->length_dw++] = 0x00000040; /* len */
+	else
+		ib->ptr[ib->length_dw++] = 0x00000030; /* len */
 	ib->ptr[ib->length_dw++] = 0x01000001; /* create cmd */
 	ib->ptr[ib->length_dw++] = 0x00000000;
 	ib->ptr[ib->length_dw++] = 0x00000042;
@@ -404,6 +407,12 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
 	ib->ptr[ib->length_dw++] = 0x00000100;
 	ib->ptr[ib->length_dw++] = 0x0000000c;
 	ib->ptr[ib->length_dw++] = 0x00000000;
+	if ((ring->adev->vce.fw_version >> 24) >= 52) {
+		ib->ptr[ib->length_dw++] = 0x00000000;
+		ib->ptr[ib->length_dw++] = 0x00000000;
+		ib->ptr[ib->length_dw++] = 0x00000000;
+		ib->ptr[ib->length_dw++] = 0x00000000;
+	}
 
 	ib->ptr[ib->length_dw++] = 0x00000014; /* len */
 	ib->ptr[ib->length_dw++] = 0x05000005; /* feedback buffer */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 633a32a48560..b53d273eb7a1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -143,10 +143,15 @@ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 	unsigned i;
 
 	/* check if the id is still valid */
-	if (vm_id->id && vm_id->last_id_use &&
-	    vm_id->last_id_use == adev->vm_manager.active[vm_id->id]) {
-		trace_amdgpu_vm_grab_id(vm_id->id, ring->idx);
-		return 0;
+	if (vm_id->id) {
+		unsigned id = vm_id->id;
+		long owner;
+
+		owner = atomic_long_read(&adev->vm_manager.ids[id].owner);
+		if (owner == (long)vm) {
+			trace_amdgpu_vm_grab_id(vm_id->id, ring->idx);
+			return 0;
+		}
 	}
 
 	/* we definately need to flush */
@@ -154,7 +159,7 @@ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 
 	/* skip over VMID 0, since it is the system VM */
 	for (i = 1; i < adev->vm_manager.nvm; ++i) {
-		struct fence *fence = adev->vm_manager.active[i];
+		struct fence *fence = adev->vm_manager.ids[i].active;
 		struct amdgpu_ring *fring;
 
 		if (fence == NULL) {
@@ -176,7 +181,7 @@ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 		if (choices[i]) {
 			struct fence *fence;
 
-			fence  = adev->vm_manager.active[choices[i]];
+			fence  = adev->vm_manager.ids[choices[i]].active;
 			vm_id->id = choices[i];
 
 			trace_amdgpu_vm_grab_id(choices[i], ring->idx);
@@ -207,24 +212,21 @@ void amdgpu_vm_flush(struct amdgpu_ring *ring,
 	uint64_t pd_addr = amdgpu_bo_gpu_offset(vm->page_directory);
 	struct amdgpu_vm_id *vm_id = &vm->ids[ring->idx];
 	struct fence *flushed_updates = vm_id->flushed_updates;
-	bool is_earlier = false;
+	bool is_later;
 
-	if (flushed_updates && updates) {
-		BUG_ON(flushed_updates->context != updates->context);
-		is_earlier = (updates->seqno - flushed_updates->seqno <=
-			      INT_MAX) ? true : false;
-	}
-
-	if (pd_addr != vm_id->pd_gpu_addr || !flushed_updates ||
-	    is_earlier) {
+	if (!flushed_updates)
+		is_later = true;
+	else if (!updates)
+		is_later = false;
+	else
+		is_later = fence_is_later(updates, flushed_updates);
 
+	if (pd_addr != vm_id->pd_gpu_addr || is_later) {
 		trace_amdgpu_vm_flush(pd_addr, ring->idx, vm_id->id);
-		if (is_earlier) {
+		if (is_later) {
 			vm_id->flushed_updates = fence_get(updates);
 			fence_put(flushed_updates);
 		}
-		if (!flushed_updates)
-			vm_id->flushed_updates = fence_get(updates);
 		vm_id->pd_gpu_addr = pd_addr;
 		amdgpu_ring_emit_vm_flush(ring, vm_id->id, vm_id->pd_gpu_addr);
 	}
@@ -244,16 +246,14 @@ void amdgpu_vm_flush(struct amdgpu_ring *ring,
  */
 void amdgpu_vm_fence(struct amdgpu_device *adev,
 		     struct amdgpu_vm *vm,
-		     struct amdgpu_fence *fence)
+		     struct fence *fence)
 {
-	unsigned ridx = fence->ring->idx;
-	unsigned vm_id = vm->ids[ridx].id;
-
-	fence_put(adev->vm_manager.active[vm_id]);
-	adev->vm_manager.active[vm_id] = fence_get(&fence->base);
+	struct amdgpu_ring *ring = amdgpu_ring_from_fence(fence);
+	unsigned vm_id = vm->ids[ring->idx].id;
 
-	fence_put(vm->ids[ridx].last_id_use);
-	vm->ids[ridx].last_id_use = fence_get(&fence->base);
+	fence_put(adev->vm_manager.ids[vm_id].active);
+	adev->vm_manager.ids[vm_id].active = fence_get(fence);
+	atomic_long_set(&adev->vm_manager.ids[vm_id].owner, (long)vm);
 }
 
 /**
@@ -332,6 +332,8 @@ int amdgpu_vm_free_job(struct amdgpu_job *job)
  *
  * @adev: amdgpu_device pointer
  * @bo: bo to clear
+ *
+ * need to reserve bo first before calling it.
  */
 static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
 			      struct amdgpu_bo *bo)
@@ -343,24 +345,20 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
 	uint64_t addr;
 	int r;
 
-	r = amdgpu_bo_reserve(bo, false);
-	if (r)
-		return r;
-
 	r = reservation_object_reserve_shared(bo->tbo.resv);
 	if (r)
 		return r;
 
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
 	if (r)
-		goto error_unreserve;
+		goto error;
 
 	addr = amdgpu_bo_gpu_offset(bo);
 	entries = amdgpu_bo_size(bo) / 8;
 
 	ib = kzalloc(sizeof(struct amdgpu_ib), GFP_KERNEL);
 	if (!ib)
-		goto error_unreserve;
+		goto error;
 
 	r = amdgpu_ib_get(ring, NULL, entries * 2 + 64, ib);
 	if (r)
@@ -378,16 +376,14 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
 	if (!r)
 		amdgpu_bo_fence(bo, fence, true);
 	fence_put(fence);
-	if (amdgpu_enable_scheduler) {
-		amdgpu_bo_unreserve(bo);
+	if (amdgpu_enable_scheduler)
 		return 0;
-	}
+
 error_free:
 	amdgpu_ib_free(adev, ib);
 	kfree(ib);
 
-error_unreserve:
-	amdgpu_bo_unreserve(bo);
+error:
 	return r;
 }
 
@@ -889,17 +885,21 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
 	struct amdgpu_bo_va_mapping *mapping;
 	int r;
 
+	spin_lock(&vm->freed_lock);
 	while (!list_empty(&vm->freed)) {
 		mapping = list_first_entry(&vm->freed,
 			struct amdgpu_bo_va_mapping, list);
 		list_del(&mapping->list);
-
+		spin_unlock(&vm->freed_lock);
 		r = amdgpu_vm_bo_update_mapping(adev, vm, mapping, 0, 0, NULL);
 		kfree(mapping);
 		if (r)
 			return r;
 
+		spin_lock(&vm->freed_lock);
 	}
+	spin_unlock(&vm->freed_lock);
+
 	return 0;
 
 }
@@ -926,8 +926,9 @@ int amdgpu_vm_clear_invalids(struct amdgpu_device *adev,
 		bo_va = list_first_entry(&vm->invalidated,
 			struct amdgpu_bo_va, vm_status);
 		spin_unlock(&vm->status_lock);
-
+		mutex_lock(&bo_va->mutex);
 		r = amdgpu_vm_bo_update(adev, bo_va, NULL);
+		mutex_unlock(&bo_va->mutex);
 		if (r)
 			return r;
 
@@ -971,7 +972,7 @@ struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev,
 	INIT_LIST_HEAD(&bo_va->valids);
 	INIT_LIST_HEAD(&bo_va->invalids);
 	INIT_LIST_HEAD(&bo_va->vm_status);
-
+	mutex_init(&bo_va->mutex);
 	list_add_tail(&bo_va->bo_list, &bo->va);
 
 	return bo_va;
@@ -989,7 +990,7 @@ struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev,
  * Add a mapping of the BO at the specefied addr into the VM.
  * Returns 0 for success, error for failure.
  *
- * Object has to be reserved and gets unreserved by this function!
+ * Object has to be reserved and unreserved outside!
  */
 int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 		     struct amdgpu_bo_va *bo_va,
@@ -1005,30 +1006,27 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 
 	/* validate the parameters */
 	if (saddr & AMDGPU_GPU_PAGE_MASK || offset & AMDGPU_GPU_PAGE_MASK ||
-	    size == 0 || size & AMDGPU_GPU_PAGE_MASK) {
-		amdgpu_bo_unreserve(bo_va->bo);
+	    size == 0 || size & AMDGPU_GPU_PAGE_MASK)
 		return -EINVAL;
-	}
 
 	/* make sure object fit at this offset */
 	eaddr = saddr + size;
-	if ((saddr >= eaddr) || (offset + size > amdgpu_bo_size(bo_va->bo))) {
-		amdgpu_bo_unreserve(bo_va->bo);
+	if ((saddr >= eaddr) || (offset + size > amdgpu_bo_size(bo_va->bo)))
 		return -EINVAL;
-	}
 
 	last_pfn = eaddr / AMDGPU_GPU_PAGE_SIZE;
 	if (last_pfn > adev->vm_manager.max_pfn) {
 		dev_err(adev->dev, "va above limit (0x%08X > 0x%08X)\n",
 			last_pfn, adev->vm_manager.max_pfn);
-		amdgpu_bo_unreserve(bo_va->bo);
 		return -EINVAL;
 	}
 
 	saddr /= AMDGPU_GPU_PAGE_SIZE;
 	eaddr /= AMDGPU_GPU_PAGE_SIZE;
 
+	spin_lock(&vm->it_lock);
 	it = interval_tree_iter_first(&vm->va, saddr, eaddr - 1);
+	spin_unlock(&vm->it_lock);
 	if (it) {
 		struct amdgpu_bo_va_mapping *tmp;
 		tmp = container_of(it, struct amdgpu_bo_va_mapping, it);
@@ -1036,14 +1034,12 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 		dev_err(adev->dev, "bo %p va 0x%010Lx-0x%010Lx conflict with "
 			"0x%010lx-0x%010lx\n", bo_va->bo, saddr, eaddr,
 			tmp->it.start, tmp->it.last + 1);
-		amdgpu_bo_unreserve(bo_va->bo);
 		r = -EINVAL;
 		goto error;
 	}
 
 	mapping = kmalloc(sizeof(*mapping), GFP_KERNEL);
 	if (!mapping) {
-		amdgpu_bo_unreserve(bo_va->bo);
 		r = -ENOMEM;
 		goto error;
 	}
@@ -1054,8 +1050,12 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 	mapping->offset = offset;
 	mapping->flags = flags;
 
+	mutex_lock(&bo_va->mutex);
 	list_add(&mapping->list, &bo_va->invalids);
+	mutex_unlock(&bo_va->mutex);
+	spin_lock(&vm->it_lock);
 	interval_tree_insert(&mapping->it, &vm->va);
+	spin_unlock(&vm->it_lock);
 	trace_amdgpu_vm_bo_map(bo_va, mapping);
 
 	/* Make sure the page tables are allocated */
@@ -1067,8 +1067,6 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 	if (eaddr > vm->max_pde_used)
 		vm->max_pde_used = eaddr;
 
-	amdgpu_bo_unreserve(bo_va->bo);
-
 	/* walk over the address space and allocate the page tables */
 	for (pt_idx = saddr; pt_idx <= eaddr; ++pt_idx) {
 		struct reservation_object *resv = vm->page_directory->tbo.resv;
@@ -1077,16 +1075,19 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 		if (vm->page_tables[pt_idx].bo)
 			continue;
 
-		ww_mutex_lock(&resv->lock, NULL);
 		r = amdgpu_bo_create(adev, AMDGPU_VM_PTE_COUNT * 8,
 				     AMDGPU_GPU_PAGE_SIZE, true,
 				     AMDGPU_GEM_DOMAIN_VRAM,
 				     AMDGPU_GEM_CREATE_NO_CPU_ACCESS,
 				     NULL, resv, &pt);
-		ww_mutex_unlock(&resv->lock);
 		if (r)
 			goto error_free;
 
+		/* Keep a reference to the page table to avoid freeing
+		 * them up in the wrong order.
+		 */
+		pt->parent = amdgpu_bo_ref(vm->page_directory);
+
 		r = amdgpu_vm_clear_bo(adev, pt);
 		if (r) {
 			amdgpu_bo_unref(&pt);
@@ -1101,7 +1102,9 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 
 error_free:
 	list_del(&mapping->list);
+	spin_lock(&vm->it_lock);
 	interval_tree_remove(&mapping->it, &vm->va);
+	spin_unlock(&vm->it_lock);
 	trace_amdgpu_vm_bo_unmap(bo_va, mapping);
 	kfree(mapping);
 
@@ -1119,7 +1122,7 @@ error:
  * Remove a mapping of the BO at the specefied addr from the VM.
  * Returns 0 for success, error for failure.
  *
- * Object has to be reserved and gets unreserved by this function!
+ * Object has to be reserved and unreserved outside!
  */
 int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
 		       struct amdgpu_bo_va *bo_va,
@@ -1130,7 +1133,7 @@ int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
 	bool valid = true;
 
 	saddr /= AMDGPU_GPU_PAGE_SIZE;
-
+	mutex_lock(&bo_va->mutex);
 	list_for_each_entry(mapping, &bo_va->valids, list) {
 		if (mapping->it.start == saddr)
 			break;
@@ -1145,20 +1148,24 @@ int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
 		}
 
 		if (&mapping->list == &bo_va->invalids) {
-			amdgpu_bo_unreserve(bo_va->bo);
+			mutex_unlock(&bo_va->mutex);
 			return -ENOENT;
 		}
 	}
-
+	mutex_unlock(&bo_va->mutex);
 	list_del(&mapping->list);
+	spin_lock(&vm->it_lock);
 	interval_tree_remove(&mapping->it, &vm->va);
+	spin_unlock(&vm->it_lock);
 	trace_amdgpu_vm_bo_unmap(bo_va, mapping);
 
-	if (valid)
+	if (valid) {
+		spin_lock(&vm->freed_lock);
 		list_add(&mapping->list, &vm->freed);
-	else
+		spin_unlock(&vm->freed_lock);
+	} else {
 		kfree(mapping);
-	amdgpu_bo_unreserve(bo_va->bo);
+	}
 
 	return 0;
 }
@@ -1187,17 +1194,23 @@ void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
 
 	list_for_each_entry_safe(mapping, next, &bo_va->valids, list) {
 		list_del(&mapping->list);
+		spin_lock(&vm->it_lock);
 		interval_tree_remove(&mapping->it, &vm->va);
+		spin_unlock(&vm->it_lock);
 		trace_amdgpu_vm_bo_unmap(bo_va, mapping);
+		spin_lock(&vm->freed_lock);
 		list_add(&mapping->list, &vm->freed);
+		spin_unlock(&vm->freed_lock);
 	}
 	list_for_each_entry_safe(mapping, next, &bo_va->invalids, list) {
 		list_del(&mapping->list);
+		spin_lock(&vm->it_lock);
 		interval_tree_remove(&mapping->it, &vm->va);
+		spin_unlock(&vm->it_lock);
 		kfree(mapping);
 	}
-
 	fence_put(bo_va->last_pt_update);
+	mutex_destroy(&bo_va->mutex);
 	kfree(bo_va);
 }
 
@@ -1241,15 +1254,14 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		vm->ids[i].id = 0;
 		vm->ids[i].flushed_updates = NULL;
-		vm->ids[i].last_id_use = NULL;
 	}
-	mutex_init(&vm->mutex);
 	vm->va = RB_ROOT;
 	spin_lock_init(&vm->status_lock);
 	INIT_LIST_HEAD(&vm->invalidated);
 	INIT_LIST_HEAD(&vm->cleared);
 	INIT_LIST_HEAD(&vm->freed);
-
+	spin_lock_init(&vm->it_lock);
+	spin_lock_init(&vm->freed_lock);
 	pd_size = amdgpu_vm_directory_size(adev);
 	pd_entries = amdgpu_vm_num_pdes(adev);
 
@@ -1269,8 +1281,14 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 			     NULL, NULL, &vm->page_directory);
 	if (r)
 		return r;
-
+	r = amdgpu_bo_reserve(vm->page_directory, false);
+	if (r) {
+		amdgpu_bo_unref(&vm->page_directory);
+		vm->page_directory = NULL;
+		return r;
+	}
 	r = amdgpu_vm_clear_bo(adev, vm->page_directory);
+	amdgpu_bo_unreserve(vm->page_directory);
 	if (r) {
 		amdgpu_bo_unref(&vm->page_directory);
 		vm->page_directory = NULL;
@@ -1313,11 +1331,27 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 
 	amdgpu_bo_unref(&vm->page_directory);
 	fence_put(vm->page_directory_fence);
-
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+		unsigned id = vm->ids[i].id;
+
+		atomic_long_cmpxchg(&adev->vm_manager.ids[id].owner,
+				    (long)vm, 0);
 		fence_put(vm->ids[i].flushed_updates);
-		fence_put(vm->ids[i].last_id_use);
 	}
 
-	mutex_destroy(&vm->mutex);
+}
+
+/**
+ * amdgpu_vm_manager_fini - cleanup VM manager
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Cleanup the VM manager and free resources.
+ */
+void amdgpu_vm_manager_fini(struct amdgpu_device *adev)
+{
+	unsigned i;
+
+	for (i = 0; i < AMDGPU_NUM_VM; ++i)
+		fence_put(adev->vm_manager.ids[i].active);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index a1a35a5df8e7..57a2e347f04d 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -6569,12 +6569,12 @@ static int ci_dpm_set_interrupt_state(struct amdgpu_device *adev,
 		switch (state) {
 		case AMDGPU_IRQ_STATE_DISABLE:
 			cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT);
-			cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK;
+			cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK;
 			WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int);
 			break;
 		case AMDGPU_IRQ_STATE_ENABLE:
 			cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT);
-			cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK;
+			cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK;
 			WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int);
 			break;
 		default:
@@ -6586,12 +6586,12 @@ static int ci_dpm_set_interrupt_state(struct amdgpu_device *adev,
 		switch (state) {
 		case AMDGPU_IRQ_STATE_DISABLE:
 			cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT);
-			cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK;
+			cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK;
 			WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int);
 			break;
 		case AMDGPU_IRQ_STATE_ENABLE:
 			cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT);
-			cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK;
+			cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK;
 			WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int);
 			break;
 		default:
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index cb0f7747e3dc..4dcc8fba5792 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -1250,7 +1250,7 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev,
 	u32 pixel_period;
 	u32 line_time = 0;
 	u32 latency_watermark_a = 0, latency_watermark_b = 0;
-	u32 tmp, wm_mask;
+	u32 tmp, wm_mask, lb_vblank_lead_lines = 0;
 
 	if (amdgpu_crtc->base.enabled && num_heads && mode) {
 		pixel_period = 1000000 / (u32)mode->clock;
@@ -1333,6 +1333,7 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev,
 		    (adev->mode_info.disp_priority == 2)) {
 			DRM_DEBUG_KMS("force priority to high\n");
 		}
+		lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
 	}
 
 	/* select wm A */
@@ -1357,6 +1358,8 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev,
 	amdgpu_crtc->line_time = line_time;
 	amdgpu_crtc->wm_high = latency_watermark_a;
 	amdgpu_crtc->wm_low = latency_watermark_b;
+	/* Save number of lines the linebuffer leads before the scanout */
+	amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index 5af3721851d6..8f1e51128b33 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -1238,7 +1238,7 @@ static void dce_v11_0_program_watermarks(struct amdgpu_device *adev,
 	u32 pixel_period;
 	u32 line_time = 0;
 	u32 latency_watermark_a = 0, latency_watermark_b = 0;
-	u32 tmp, wm_mask;
+	u32 tmp, wm_mask, lb_vblank_lead_lines = 0;
 
 	if (amdgpu_crtc->base.enabled && num_heads && mode) {
 		pixel_period = 1000000 / (u32)mode->clock;
@@ -1321,6 +1321,7 @@ static void dce_v11_0_program_watermarks(struct amdgpu_device *adev,
 		    (adev->mode_info.disp_priority == 2)) {
 			DRM_DEBUG_KMS("force priority to high\n");
 		}
+		lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
 	}
 
 	/* select wm A */
@@ -1345,6 +1346,8 @@ static void dce_v11_0_program_watermarks(struct amdgpu_device *adev,
 	amdgpu_crtc->line_time = line_time;
 	amdgpu_crtc->wm_high = latency_watermark_a;
 	amdgpu_crtc->wm_low = latency_watermark_b;
+	/* Save number of lines the linebuffer leads before the scanout */
+	amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 4f7b49a6dc50..42d954dc436d 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -1193,7 +1193,7 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev,
 	u32 pixel_period;
 	u32 line_time = 0;
 	u32 latency_watermark_a = 0, latency_watermark_b = 0;
-	u32 tmp, wm_mask;
+	u32 tmp, wm_mask, lb_vblank_lead_lines = 0;
 
 	if (amdgpu_crtc->base.enabled && num_heads && mode) {
 		pixel_period = 1000000 / (u32)mode->clock;
@@ -1276,6 +1276,7 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev,
 		    (adev->mode_info.disp_priority == 2)) {
 			DRM_DEBUG_KMS("force priority to high\n");
 		}
+		lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
 	}
 
 	/* select wm A */
@@ -1302,6 +1303,8 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev,
 	amdgpu_crtc->line_time = line_time;
 	amdgpu_crtc->wm_high = latency_watermark_a;
 	amdgpu_crtc->wm_low = latency_watermark_b;
+	/* Save number of lines the linebuffer leads before the scanout */
+	amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 6776cf756d40..e1dcab98e249 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -268,7 +268,6 @@ static const u32 fiji_mgcg_cgcg_init[] =
 	mmCGTT_CP_CLK_CTRL, 0xffffffff, 0x00000100,
 	mmCGTT_CPC_CLK_CTRL, 0xffffffff, 0x00000100,
 	mmCGTT_CPF_CLK_CTRL, 0xffffffff, 0x40000100,
-	mmCGTT_DRM_CLK_CTRL0, 0xffffffff, 0x00600100,
 	mmCGTT_GDS_CLK_CTRL, 0xffffffff, 0x00000100,
 	mmCGTT_IA_CLK_CTRL, 0xffffffff, 0x06000100,
 	mmCGTT_PA_CLK_CTRL, 0xffffffff, 0x00000100,
@@ -296,10 +295,6 @@ static const u32 fiji_mgcg_cgcg_init[] =
 	mmCGTS_SM_CTRL_REG, 0xffffffff, 0x96e00200,
 	mmCP_RB_WPTR_POLL_CNTL, 0xffffffff, 0x00900100,
 	mmRLC_CGCG_CGLS_CTRL, 0xffffffff, 0x0020003c,
-	mmPCIE_INDEX, 0xffffffff, 0x0140001c,
-	mmPCIE_DATA, 0x000f0000, 0x00000000,
-	mmCGTT_DRM_CLK_CTRL0, 0xff000fff, 0x00000100,
-	mmHDP_XDP_CGTT_BLK_CTRL, 0xc0000fff, 0x00000104,
 	mmCP_MEM_SLP_CNTL, 0x00000001, 0x00000001,
 };
 
@@ -1000,7 +995,7 @@ static void gfx_v8_0_gpu_early_init(struct amdgpu_device *adev)
 		adev->gfx.config.max_cu_per_sh = 16;
 		adev->gfx.config.max_sh_per_se = 1;
 		adev->gfx.config.max_backends_per_se = 4;
-		adev->gfx.config.max_texture_channel_caches = 8;
+		adev->gfx.config.max_texture_channel_caches = 16;
 		adev->gfx.config.max_gprs = 256;
 		adev->gfx.config.max_gs_threads = 32;
 		adev->gfx.config.max_hw_contexts = 8;
@@ -1613,6 +1608,296 @@ static void gfx_v8_0_tiling_mode_table_init(struct amdgpu_device *adev)
 			WREG32(mmGB_MACROTILE_MODE0 + reg_offset, gb_tile_moden);
 		}
 	case CHIP_FIJI:
+		for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) {
+			switch (reg_offset) {
+			case 0:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 1:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 2:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 3:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 4:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 5:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 6:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 7:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P4_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 8:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_LINEAR_ALIGNED) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16));
+				break;
+			case 9:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 10:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 11:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8));
+				break;
+			case 12:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P4_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8));
+				break;
+			case 13:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 14:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 15:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_3D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 16:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8));
+				break;
+			case 17:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P4_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8));
+				break;
+			case 18:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 19:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 20:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 21:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_3D_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 22:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 23:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P4_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 24:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 25:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_XTHICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 26:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_3D_TILED_XTHICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 27:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 28:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 29:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8));
+				break;
+			case 30:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P4_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8));
+				break;
+			default:
+				gb_tile_moden = 0;
+				break;
+			}
+			adev->gfx.config.tile_mode_array[reg_offset] = gb_tile_moden;
+			WREG32(mmGB_TILE_MODE0 + reg_offset, gb_tile_moden);
+		}
+		for (reg_offset = 0; reg_offset < num_secondary_tile_mode_states; reg_offset++) {
+			switch (reg_offset) {
+			case 0:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 1:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 2:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 3:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 4:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 5:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 6:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 8:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_8) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 9:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 10:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 11:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 12:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 13:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 14:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						NUM_BANKS(ADDR_SURF_4_BANK));
+				break;
+			case 7:
+				/* unused idx */
+				continue;
+			default:
+				gb_tile_moden = 0;
+				break;
+			}
+			adev->gfx.config.macrotile_mode_array[reg_offset] = gb_tile_moden;
+			WREG32(mmGB_MACROTILE_MODE0 + reg_offset, gb_tile_moden);
+		}
+		break;
 	case CHIP_TONGA:
 		for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) {
 			switch (reg_offset) {
@@ -2971,10 +3256,13 @@ static int gfx_v8_0_cp_gfx_start(struct amdgpu_device *adev)
 	amdgpu_ring_write(ring, mmPA_SC_RASTER_CONFIG - PACKET3_SET_CONTEXT_REG_START);
 	switch (adev->asic_type) {
 	case CHIP_TONGA:
-	case CHIP_FIJI:
 		amdgpu_ring_write(ring, 0x16000012);
 		amdgpu_ring_write(ring, 0x0000002A);
 		break;
+	case CHIP_FIJI:
+		amdgpu_ring_write(ring, 0x3a00161a);
+		amdgpu_ring_write(ring, 0x0000002e);
+		break;
 	case CHIP_TOPAZ:
 	case CHIP_CARRIZO:
 		amdgpu_ring_write(ring, 0x00000002);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 85bbcdc73fff..ed8abb58a785 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -40,7 +40,7 @@
 static void gmc_v7_0_set_gart_funcs(struct amdgpu_device *adev);
 static void gmc_v7_0_set_irq_funcs(struct amdgpu_device *adev);
 
-MODULE_FIRMWARE("radeon/boniare_mc.bin");
+MODULE_FIRMWARE("radeon/bonaire_mc.bin");
 MODULE_FIRMWARE("radeon/hawaii_mc.bin");
 
 /**
@@ -501,6 +501,7 @@ static int gmc_v7_0_gart_enable(struct amdgpu_device *adev)
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_PDE0_CACHE_LRU_UPDATE_BY_WRITE, 1);
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, EFFECTIVE_L2_QUEUE_SIZE, 7);
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, CONTEXT1_IDENTITY_ACCESS_MODE, 1);
+	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_DEFAULT_PAGE_OUT_TO_SYSTEM_MEMORY, 1);
 	WREG32(mmVM_L2_CNTL, tmp);
 	tmp = REG_SET_FIELD(0, VM_L2_CNTL2, INVALIDATE_ALL_L1_TLBS, 1);
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_L2_CACHE, 1);
@@ -512,7 +513,7 @@ static int gmc_v7_0_gart_enable(struct amdgpu_device *adev)
 	WREG32(mmVM_L2_CNTL3, tmp);
 	/* setup context0 */
 	WREG32(mmVM_CONTEXT0_PAGE_TABLE_START_ADDR, adev->mc.gtt_start >> 12);
-	WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, (adev->mc.gtt_end >> 12) - 1);
+	WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, adev->mc.gtt_end >> 12);
 	WREG32(mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR, adev->gart.table_addr >> 12);
 	WREG32(mmVM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR,
 			(u32)(adev->dummy_page.addr >> 12));
@@ -960,12 +961,10 @@ static int gmc_v7_0_sw_init(void *handle)
 
 static int gmc_v7_0_sw_fini(void *handle)
 {
-	int i;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	if (adev->vm_manager.enabled) {
-		for (i = 0; i < AMDGPU_NUM_VM; ++i)
-			fence_put(adev->vm_manager.active[i]);
+		amdgpu_vm_manager_fini(adev);
 		gmc_v7_0_vm_fini(adev);
 		adev->vm_manager.enabled = false;
 	}
@@ -1010,12 +1009,10 @@ static int gmc_v7_0_hw_fini(void *handle)
 
 static int gmc_v7_0_suspend(void *handle)
 {
-	int i;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	if (adev->vm_manager.enabled) {
-		for (i = 0; i < AMDGPU_NUM_VM; ++i)
-			fence_put(adev->vm_manager.active[i]);
+		amdgpu_vm_manager_fini(adev);
 		gmc_v7_0_vm_fini(adev);
 		adev->vm_manager.enabled = false;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 1bcc4e74e3b4..d39028440814 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -629,6 +629,7 @@ static int gmc_v8_0_gart_enable(struct amdgpu_device *adev)
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_PDE0_CACHE_LRU_UPDATE_BY_WRITE, 1);
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, EFFECTIVE_L2_QUEUE_SIZE, 7);
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, CONTEXT1_IDENTITY_ACCESS_MODE, 1);
+	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_DEFAULT_PAGE_OUT_TO_SYSTEM_MEMORY, 1);
 	WREG32(mmVM_L2_CNTL, tmp);
 	tmp = RREG32(mmVM_L2_CNTL2);
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_ALL_L1_TLBS, 1);
@@ -656,7 +657,7 @@ static int gmc_v8_0_gart_enable(struct amdgpu_device *adev)
 	WREG32(mmVM_L2_CNTL4, tmp);
 	/* setup context0 */
 	WREG32(mmVM_CONTEXT0_PAGE_TABLE_START_ADDR, adev->mc.gtt_start >> 12);
-	WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, (adev->mc.gtt_end >> 12) - 1);
+	WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, adev->mc.gtt_end >> 12);
 	WREG32(mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR, adev->gart.table_addr >> 12);
 	WREG32(mmVM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR,
 			(u32)(adev->dummy_page.addr >> 12));
@@ -979,12 +980,10 @@ static int gmc_v8_0_sw_init(void *handle)
 
 static int gmc_v8_0_sw_fini(void *handle)
 {
-	int i;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	if (adev->vm_manager.enabled) {
-		for (i = 0; i < AMDGPU_NUM_VM; ++i)
-			fence_put(adev->vm_manager.active[i]);
+		amdgpu_vm_manager_fini(adev);
 		gmc_v8_0_vm_fini(adev);
 		adev->vm_manager.enabled = false;
 	}
@@ -1031,12 +1030,10 @@ static int gmc_v8_0_hw_fini(void *handle)
 
 static int gmc_v8_0_suspend(void *handle)
 {
-	int i;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	if (adev->vm_manager.enabled) {
-		for (i = 0; i < AMDGPU_NUM_VM; ++i)
-			fence_put(adev->vm_manager.active[i]);
+		amdgpu_vm_manager_fini(adev);
 		gmc_v8_0_vm_fini(adev);
 		adev->vm_manager.enabled = false;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 6a52db6ad8d7..370c6c9d81c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -40,6 +40,9 @@
 
 #define GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT	0x04
 #define GRBM_GFX_INDEX__VCE_INSTANCE_MASK	0x10
+#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR0 	0x8616
+#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR1 	0x8617
+#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR2 	0x8618
 
 #define VCE_V3_0_FW_SIZE	(384 * 1024)
 #define VCE_V3_0_STACK_SIZE	(64 * 1024)
@@ -130,9 +133,11 @@ static int vce_v3_0_start(struct amdgpu_device *adev)
 
 		/* set BUSY flag */
 		WREG32_P(mmVCE_STATUS, 1, ~1);
-
-		WREG32_P(mmVCE_VCPU_CNTL, VCE_VCPU_CNTL__CLK_EN_MASK,
-			~VCE_VCPU_CNTL__CLK_EN_MASK);
+		if (adev->asic_type >= CHIP_STONEY)
+			WREG32_P(mmVCE_VCPU_CNTL, 1, ~0x200001);
+		else
+			WREG32_P(mmVCE_VCPU_CNTL, VCE_VCPU_CNTL__CLK_EN_MASK,
+				~VCE_VCPU_CNTL__CLK_EN_MASK);
 
 		WREG32_P(mmVCE_SOFT_RESET,
 			 VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK,
@@ -391,8 +396,12 @@ static void vce_v3_0_mc_resume(struct amdgpu_device *adev, int idx)
 	WREG32(mmVCE_LMI_SWAP_CNTL, 0);
 	WREG32(mmVCE_LMI_SWAP_CNTL1, 0);
 	WREG32(mmVCE_LMI_VM_CTRL, 0);
-
-	WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR, (adev->vce.gpu_addr >> 8));
+	if (adev->asic_type >= CHIP_STONEY) {
+		WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR0, (adev->vce.gpu_addr >> 8));
+		WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR1, (adev->vce.gpu_addr >> 8));
+		WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR2, (adev->vce.gpu_addr >> 8));
+	} else
+		WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR, (adev->vce.gpu_addr >> 8));
 	offset = AMDGPU_VCE_FIRMWARE_OFFSET;
 	size = VCE_V3_0_FW_SIZE;
 	WREG32(mmVCE_VCPU_CACHE_OFFSET0, offset & 0x7fffffff);
@@ -576,6 +585,11 @@ static int vce_v3_0_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_iv_entry *entry)
 {
 	DRM_DEBUG("IH: VCE\n");
+
+	WREG32_P(mmVCE_SYS_INT_STATUS,
+		VCE_SYS_INT_STATUS__VCE_SYS_INT_TRAP_INTERRUPT_INT_MASK,
+		~VCE_SYS_INT_STATUS__VCE_SYS_INT_TRAP_INTERRUPT_INT_MASK);
+
 	switch (entry->src_data) {
 	case 0:
 		amdgpu_fence_process(&adev->vce.ring[0]);
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h b/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h
index 144f50acc971..c89dc777768f 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h
+++ b/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h
@@ -16,6 +16,8 @@ TRACE_EVENT(amd_sched_job,
 	    TP_ARGS(sched_job),
 	    TP_STRUCT__entry(
 			     __field(struct amd_sched_entity *, entity)
+			     __field(struct amd_sched_job *, sched_job)
+			     __field(struct fence *, fence)
 			     __field(const char *, name)
 			     __field(u32, job_count)
 			     __field(int, hw_job_count)
@@ -23,16 +25,32 @@ TRACE_EVENT(amd_sched_job,
 
 	    TP_fast_assign(
 			   __entry->entity = sched_job->s_entity;
+			   __entry->sched_job = sched_job;
+			   __entry->fence = &sched_job->s_fence->base;
 			   __entry->name = sched_job->sched->name;
 			   __entry->job_count = kfifo_len(
 				   &sched_job->s_entity->job_queue) / sizeof(sched_job);
 			   __entry->hw_job_count = atomic_read(
 				   &sched_job->sched->hw_rq_count);
 			   ),
-	    TP_printk("entity=%p, ring=%s, job count:%u, hw job count:%d",
-		      __entry->entity, __entry->name, __entry->job_count,
-		      __entry->hw_job_count)
+	    TP_printk("entity=%p, sched job=%p, fence=%p, ring=%s, job count:%u, hw job count:%d",
+		      __entry->entity, __entry->sched_job, __entry->fence, __entry->name,
+		      __entry->job_count, __entry->hw_job_count)
 );
+
+TRACE_EVENT(amd_sched_process_job,
+	    TP_PROTO(struct amd_sched_fence *fence),
+	    TP_ARGS(fence),
+	    TP_STRUCT__entry(
+		    __field(struct fence *, fence)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->fence = &fence->base;
+		    ),
+	    TP_printk("fence=%p signaled", __entry->fence)
+);
+
 #endif
 
 /* This part must be outside protection */
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index 89619a5a4289..3a4820e863ec 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -30,10 +30,12 @@
 #define CREATE_TRACE_POINTS
 #include "gpu_sched_trace.h"
 
-static struct amd_sched_job *
-amd_sched_entity_pop_job(struct amd_sched_entity *entity);
+static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity);
 static void amd_sched_wakeup(struct amd_gpu_scheduler *sched);
 
+struct kmem_cache *sched_fence_slab;
+atomic_t sched_fence_slab_ref = ATOMIC_INIT(0);
+
 /* Initialize a given run queue struct */
 static void amd_sched_rq_init(struct amd_sched_rq *rq)
 {
@@ -61,36 +63,36 @@ static void amd_sched_rq_remove_entity(struct amd_sched_rq *rq,
 }
 
 /**
- * Select next job from a specified run queue with round robin policy.
- * Return NULL if nothing available.
+ * Select an entity which could provide a job to run
+ *
+ * @rq		The run queue to check.
+ *
+ * Try to find a ready entity, returns NULL if none found.
  */
-static struct amd_sched_job *
-amd_sched_rq_select_job(struct amd_sched_rq *rq)
+static struct amd_sched_entity *
+amd_sched_rq_select_entity(struct amd_sched_rq *rq)
 {
 	struct amd_sched_entity *entity;
-	struct amd_sched_job *sched_job;
 
 	spin_lock(&rq->lock);
 
 	entity = rq->current_entity;
 	if (entity) {
 		list_for_each_entry_continue(entity, &rq->entities, list) {
-			sched_job = amd_sched_entity_pop_job(entity);
-			if (sched_job) {
+			if (amd_sched_entity_is_ready(entity)) {
 				rq->current_entity = entity;
 				spin_unlock(&rq->lock);
-				return sched_job;
+				return entity;
 			}
 		}
 	}
 
 	list_for_each_entry(entity, &rq->entities, list) {
 
-		sched_job = amd_sched_entity_pop_job(entity);
-		if (sched_job) {
+		if (amd_sched_entity_is_ready(entity)) {
 			rq->current_entity = entity;
 			spin_unlock(&rq->lock);
-			return sched_job;
+			return entity;
 		}
 
 		if (entity == rq->current_entity)
@@ -174,6 +176,24 @@ static bool amd_sched_entity_is_idle(struct amd_sched_entity *entity)
 }
 
 /**
+ * Check if entity is ready
+ *
+ * @entity	The pointer to a valid scheduler entity
+ *
+ * Return true if entity could provide a job.
+ */
+static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity)
+{
+	if (kfifo_is_empty(&entity->job_queue))
+		return false;
+
+	if (ACCESS_ONCE(entity->dependency))
+		return false;
+
+	return true;
+}
+
+/**
  * Destroy a context entity
  *
  * @sched       Pointer to scheduler instance
@@ -208,32 +228,53 @@ static void amd_sched_entity_wakeup(struct fence *f, struct fence_cb *cb)
 	amd_sched_wakeup(entity->sched);
 }
 
+static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity)
+{
+	struct amd_gpu_scheduler *sched = entity->sched;
+	struct fence * fence = entity->dependency;
+	struct amd_sched_fence *s_fence;
+
+	if (fence->context == entity->fence_context) {
+		/* We can ignore fences from ourself */
+		fence_put(entity->dependency);
+		return false;
+	}
+
+	s_fence = to_amd_sched_fence(fence);
+	if (s_fence && s_fence->sched == sched) {
+		/* Fence is from the same scheduler */
+		if (test_bit(AMD_SCHED_FENCE_SCHEDULED_BIT, &fence->flags)) {
+			/* Ignore it when it is already scheduled */
+			fence_put(entity->dependency);
+			return false;
+		}
+
+		/* Wait for fence to be scheduled */
+		entity->cb.func = amd_sched_entity_wakeup;
+		list_add_tail(&entity->cb.node, &s_fence->scheduled_cb);
+		return true;
+	}
+
+	if (!fence_add_callback(entity->dependency, &entity->cb,
+				amd_sched_entity_wakeup))
+		return true;
+
+	fence_put(entity->dependency);
+	return false;
+}
+
 static struct amd_sched_job *
 amd_sched_entity_pop_job(struct amd_sched_entity *entity)
 {
 	struct amd_gpu_scheduler *sched = entity->sched;
 	struct amd_sched_job *sched_job;
 
-	if (ACCESS_ONCE(entity->dependency))
-		return NULL;
-
 	if (!kfifo_out_peek(&entity->job_queue, &sched_job, sizeof(sched_job)))
 		return NULL;
 
-	while ((entity->dependency = sched->ops->dependency(sched_job))) {
-
-		if (entity->dependency->context == entity->fence_context) {
-			/* We can ignore fences from ourself */
-			fence_put(entity->dependency);
-			continue;
-		}
-
-		if (fence_add_callback(entity->dependency, &entity->cb,
-				       amd_sched_entity_wakeup))
-			fence_put(entity->dependency);
-		else
+	while ((entity->dependency = sched->ops->dependency(sched_job)))
+		if (amd_sched_entity_add_dependency_cb(entity))
 			return NULL;
-	}
 
 	return sched_job;
 }
@@ -247,6 +288,7 @@ amd_sched_entity_pop_job(struct amd_sched_entity *entity)
  */
 static bool amd_sched_entity_in(struct amd_sched_job *sched_job)
 {
+	struct amd_gpu_scheduler *sched = sched_job->sched;
 	struct amd_sched_entity *entity = sched_job->s_entity;
 	bool added, first = false;
 
@@ -261,7 +303,7 @@ static bool amd_sched_entity_in(struct amd_sched_job *sched_job)
 
 	/* first job wakes up scheduler */
 	if (first)
-		amd_sched_wakeup(sched_job->sched);
+		amd_sched_wakeup(sched);
 
 	return added;
 }
@@ -273,22 +315,13 @@ static bool amd_sched_entity_in(struct amd_sched_job *sched_job)
  *
  * Returns 0 for success, negative error code otherwise.
  */
-int amd_sched_entity_push_job(struct amd_sched_job *sched_job)
+void amd_sched_entity_push_job(struct amd_sched_job *sched_job)
 {
 	struct amd_sched_entity *entity = sched_job->s_entity;
-	struct amd_sched_fence *fence = amd_sched_fence_create(
-		entity, sched_job->owner);
-
-	if (!fence)
-		return -ENOMEM;
-
-	fence_get(&fence->base);
-	sched_job->s_fence = fence;
 
+	trace_amd_sched_job(sched_job);
 	wait_event(entity->sched->job_scheduled,
 		   amd_sched_entity_in(sched_job));
-	trace_amd_sched_job(sched_job);
-	return 0;
 }
 
 /**
@@ -310,22 +343,22 @@ static void amd_sched_wakeup(struct amd_gpu_scheduler *sched)
 }
 
 /**
- * Select next to run
+ * Select next entity to process
 */
-static struct amd_sched_job *
-amd_sched_select_job(struct amd_gpu_scheduler *sched)
+static struct amd_sched_entity *
+amd_sched_select_entity(struct amd_gpu_scheduler *sched)
 {
-	struct amd_sched_job *sched_job;
+	struct amd_sched_entity *entity;
 
 	if (!amd_sched_ready(sched))
 		return NULL;
 
 	/* Kernel run queue has higher priority than normal run queue*/
-	sched_job = amd_sched_rq_select_job(&sched->kernel_rq);
-	if (sched_job == NULL)
-		sched_job = amd_sched_rq_select_job(&sched->sched_rq);
+	entity = amd_sched_rq_select_entity(&sched->kernel_rq);
+	if (entity == NULL)
+		entity = amd_sched_rq_select_entity(&sched->sched_rq);
 
-	return sched_job;
+	return entity;
 }
 
 static void amd_sched_process_job(struct fence *f, struct fence_cb *cb)
@@ -343,6 +376,7 @@ static void amd_sched_process_job(struct fence *f, struct fence_cb *cb)
 		list_del_init(&s_fence->list);
 		spin_unlock_irqrestore(&sched->fence_list_lock, flags);
 	}
+	trace_amd_sched_process_job(s_fence);
 	fence_put(&s_fence->base);
 	wake_up_interruptible(&sched->wake_up_worker);
 }
@@ -386,13 +420,16 @@ static int amd_sched_main(void *param)
 		unsigned long flags;
 
 		wait_event_interruptible(sched->wake_up_worker,
-			kthread_should_stop() ||
-			(sched_job = amd_sched_select_job(sched)));
+			(entity = amd_sched_select_entity(sched)) ||
+			kthread_should_stop());
 
+		if (!entity)
+			continue;
+
+		sched_job = amd_sched_entity_pop_job(entity);
 		if (!sched_job)
 			continue;
 
-		entity = sched_job->s_entity;
 		s_fence = sched_job->s_fence;
 
 		if (sched->timeout != MAX_SCHEDULE_TIMEOUT) {
@@ -405,6 +442,7 @@ static int amd_sched_main(void *param)
 
 		atomic_inc(&sched->hw_rq_count);
 		fence = sched->ops->run_job(sched_job);
+		amd_sched_fence_scheduled(s_fence);
 		if (fence) {
 			r = fence_add_callback(fence, &s_fence->cb,
 					       amd_sched_process_job);
@@ -450,6 +488,13 @@ int amd_sched_init(struct amd_gpu_scheduler *sched,
 	init_waitqueue_head(&sched->wake_up_worker);
 	init_waitqueue_head(&sched->job_scheduled);
 	atomic_set(&sched->hw_rq_count, 0);
+	if (atomic_inc_return(&sched_fence_slab_ref) == 1) {
+		sched_fence_slab = kmem_cache_create(
+			"amd_sched_fence", sizeof(struct amd_sched_fence), 0,
+			SLAB_HWCACHE_ALIGN, NULL);
+		if (!sched_fence_slab)
+			return -ENOMEM;
+	}
 
 	/* Each scheduler will run on a seperate kernel thread */
 	sched->thread = kthread_run(amd_sched_main, sched, sched->name);
@@ -470,4 +515,6 @@ void amd_sched_fini(struct amd_gpu_scheduler *sched)
 {
 	if (sched->thread)
 		kthread_stop(sched->thread);
+	if (atomic_dec_and_test(&sched_fence_slab_ref))
+		kmem_cache_destroy(sched_fence_slab);
 }
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
index 929e9aced041..a0f0ae53aacd 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
@@ -27,9 +27,14 @@
 #include <linux/kfifo.h>
 #include <linux/fence.h>
 
+#define AMD_SCHED_FENCE_SCHEDULED_BIT	FENCE_FLAG_USER_BITS
+
 struct amd_gpu_scheduler;
 struct amd_sched_rq;
 
+extern struct kmem_cache *sched_fence_slab;
+extern atomic_t sched_fence_slab_ref;
+
 /**
  * A scheduler entity is a wrapper around a job queue or a group
  * of other entities. Entities take turns emitting jobs from their 
@@ -65,6 +70,7 @@ struct amd_sched_rq {
 struct amd_sched_fence {
 	struct fence                    base;
 	struct fence_cb                 cb;
+	struct list_head		scheduled_cb;
 	struct amd_gpu_scheduler	*sched;
 	spinlock_t			lock;
 	void                            *owner;
@@ -76,7 +82,6 @@ struct amd_sched_job {
 	struct amd_gpu_scheduler        *sched;
 	struct amd_sched_entity         *s_entity;
 	struct amd_sched_fence          *s_fence;
-	void		                *owner;
 };
 
 extern const struct fence_ops amd_sched_fence_ops;
@@ -128,11 +133,11 @@ int amd_sched_entity_init(struct amd_gpu_scheduler *sched,
 			  uint32_t jobs);
 void amd_sched_entity_fini(struct amd_gpu_scheduler *sched,
 			   struct amd_sched_entity *entity);
-int amd_sched_entity_push_job(struct amd_sched_job *sched_job);
+void amd_sched_entity_push_job(struct amd_sched_job *sched_job);
 
 struct amd_sched_fence *amd_sched_fence_create(
 	struct amd_sched_entity *s_entity, void *owner);
+void amd_sched_fence_scheduled(struct amd_sched_fence *fence);
 void amd_sched_fence_signal(struct amd_sched_fence *fence);
 
-
 #endif
diff --git a/drivers/gpu/drm/amd/scheduler/sched_fence.c b/drivers/gpu/drm/amd/scheduler/sched_fence.c
index d802638094f4..87c78eecea64 100644
--- a/drivers/gpu/drm/amd/scheduler/sched_fence.c
+++ b/drivers/gpu/drm/amd/scheduler/sched_fence.c
@@ -32,9 +32,11 @@ struct amd_sched_fence *amd_sched_fence_create(struct amd_sched_entity *s_entity
 	struct amd_sched_fence *fence = NULL;
 	unsigned seq;
 
-	fence = kzalloc(sizeof(struct amd_sched_fence), GFP_KERNEL);
+	fence = kmem_cache_zalloc(sched_fence_slab, GFP_KERNEL);
 	if (fence == NULL)
 		return NULL;
+
+	INIT_LIST_HEAD(&fence->scheduled_cb);
 	fence->owner = owner;
 	fence->sched = s_entity->sched;
 	spin_lock_init(&fence->lock);
@@ -55,6 +57,17 @@ void amd_sched_fence_signal(struct amd_sched_fence *fence)
 		FENCE_TRACE(&fence->base, "was already signaled\n");
 }
 
+void amd_sched_fence_scheduled(struct amd_sched_fence *s_fence)
+{
+	struct fence_cb *cur, *tmp;
+
+	set_bit(AMD_SCHED_FENCE_SCHEDULED_BIT, &s_fence->base.flags);
+	list_for_each_entry_safe(cur, tmp, &s_fence->scheduled_cb, node) {
+		list_del_init(&cur->node);
+		cur->func(&s_fence->base, cur);
+	}
+}
+
 static const char *amd_sched_fence_get_driver_name(struct fence *fence)
 {
 	return "amd_sched";
@@ -71,11 +84,17 @@ static bool amd_sched_fence_enable_signaling(struct fence *f)
 	return true;
 }
 
+static void amd_sched_fence_release(struct fence *f)
+{
+	struct amd_sched_fence *fence = to_amd_sched_fence(f);
+	kmem_cache_free(sched_fence_slab, fence);
+}
+
 const struct fence_ops amd_sched_fence_ops = {
 	.get_driver_name = amd_sched_fence_get_driver_name,
 	.get_timeline_name = amd_sched_fence_get_timeline_name,
 	.enable_signaling = amd_sched_fence_enable_signaling,
 	.signaled = NULL,
 	.wait = fence_default_wait,
-	.release = NULL,
+	.release = amd_sched_fence_release,
 };
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 7bb3845d9974..aeee083c7f95 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -1432,6 +1432,45 @@ static int atomic_set_prop(struct drm_atomic_state *state,
 	return ret;
 }
 
+/**
+ * drm_atomic_update_old_fb -- Unset old_fb pointers and set plane->fb pointers.
+ *
+ * @dev: drm device to check.
+ * @plane_mask: plane mask for planes that were updated.
+ * @ret: return value, can be -EDEADLK for a retry.
+ *
+ * Before doing an update plane->old_fb is set to plane->fb,
+ * but before dropping the locks old_fb needs to be set to NULL
+ * and plane->fb updated. This is a common operation for each
+ * atomic update, so this call is split off as a helper.
+ */
+void drm_atomic_clean_old_fb(struct drm_device *dev,
+			     unsigned plane_mask,
+			     int ret)
+{
+	struct drm_plane *plane;
+
+	/* if succeeded, fixup legacy plane crtc/fb ptrs before dropping
+	 * locks (ie. while it is still safe to deref plane->state).  We
+	 * need to do this here because the driver entry points cannot
+	 * distinguish between legacy and atomic ioctls.
+	 */
+	drm_for_each_plane_mask(plane, dev, plane_mask) {
+		if (ret == 0) {
+			struct drm_framebuffer *new_fb = plane->state->fb;
+			if (new_fb)
+				drm_framebuffer_reference(new_fb);
+			plane->fb = new_fb;
+			plane->crtc = plane->state->crtc;
+
+			if (plane->old_fb)
+				drm_framebuffer_unreference(plane->old_fb);
+		}
+		plane->old_fb = NULL;
+	}
+}
+EXPORT_SYMBOL(drm_atomic_clean_old_fb);
+
 int drm_mode_atomic_ioctl(struct drm_device *dev,
 			  void *data, struct drm_file *file_priv)
 {
@@ -1446,7 +1485,7 @@ int drm_mode_atomic_ioctl(struct drm_device *dev,
 	struct drm_plane *plane;
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
-	unsigned plane_mask = 0;
+	unsigned plane_mask;
 	int ret = 0;
 	unsigned int i, j;
 
@@ -1486,6 +1525,7 @@ int drm_mode_atomic_ioctl(struct drm_device *dev,
 	state->allow_modeset = !!(arg->flags & DRM_MODE_ATOMIC_ALLOW_MODESET);
 
 retry:
+	plane_mask = 0;
 	copied_objs = 0;
 	copied_props = 0;
 
@@ -1576,24 +1616,7 @@ retry:
 	}
 
 out:
-	/* if succeeded, fixup legacy plane crtc/fb ptrs before dropping
-	 * locks (ie. while it is still safe to deref plane->state).  We
-	 * need to do this here because the driver entry points cannot
-	 * distinguish between legacy and atomic ioctls.
-	 */
-	drm_for_each_plane_mask(plane, dev, plane_mask) {
-		if (ret == 0) {
-			struct drm_framebuffer *new_fb = plane->state->fb;
-			if (new_fb)
-				drm_framebuffer_reference(new_fb);
-			plane->fb = new_fb;
-			plane->crtc = plane->state->crtc;
-
-			if (plane->old_fb)
-				drm_framebuffer_unreference(plane->old_fb);
-		}
-		plane->old_fb = NULL;
-	}
+	drm_atomic_clean_old_fb(dev, plane_mask, ret);
 
 	if (ret && arg->flags & DRM_MODE_PAGE_FLIP_EVENT) {
 		/*
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 0c6f62168776..e5aec45bf985 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -210,6 +210,14 @@ update_connector_routing(struct drm_atomic_state *state, int conn_idx)
 		return -EINVAL;
 	}
 
+	if (!drm_encoder_crtc_ok(new_encoder, connector_state->crtc)) {
+		DRM_DEBUG_ATOMIC("[ENCODER:%d:%s] incompatible with [CRTC:%d]\n",
+				 new_encoder->base.id,
+				 new_encoder->name,
+				 connector_state->crtc->base.id);
+		return -EINVAL;
+	}
+
 	if (new_encoder == connector_state->best_encoder) {
 		DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] keeps [ENCODER:%d:%s], now on [CRTC:%d]\n",
 				 connector->base.id,
@@ -1553,6 +1561,9 @@ retry:
 		goto fail;
 	}
 
+	if (plane_state->crtc && (plane == plane->crtc->cursor))
+		plane_state->state->legacy_cursor_update = true;
+
 	ret = __drm_atomic_helper_disable_plane(plane, plane_state);
 	if (ret != 0)
 		goto fail;
@@ -1605,9 +1616,6 @@ int __drm_atomic_helper_disable_plane(struct drm_plane *plane,
 	plane_state->src_h = 0;
 	plane_state->src_w = 0;
 
-	if (plane->crtc && (plane == plane->crtc->cursor))
-		plane_state->state->legacy_cursor_update = true;
-
 	return 0;
 }
 
@@ -1741,6 +1749,7 @@ int __drm_atomic_helper_set_config(struct drm_mode_set *set,
 	struct drm_crtc_state *crtc_state;
 	struct drm_plane_state *primary_state;
 	struct drm_crtc *crtc = set->crtc;
+	int hdisplay, vdisplay;
 	int ret;
 
 	crtc_state = drm_atomic_get_crtc_state(state, crtc);
@@ -1783,19 +1792,21 @@ int __drm_atomic_helper_set_config(struct drm_mode_set *set,
 	if (ret != 0)
 		return ret;
 
+	drm_crtc_get_hv_timing(set->mode, &hdisplay, &vdisplay);
+
 	drm_atomic_set_fb_for_plane(primary_state, set->fb);
 	primary_state->crtc_x = 0;
 	primary_state->crtc_y = 0;
-	primary_state->crtc_h = set->mode->vdisplay;
-	primary_state->crtc_w = set->mode->hdisplay;
+	primary_state->crtc_h = vdisplay;
+	primary_state->crtc_w = hdisplay;
 	primary_state->src_x = set->x << 16;
 	primary_state->src_y = set->y << 16;
 	if (primary_state->rotation & (BIT(DRM_ROTATE_90) | BIT(DRM_ROTATE_270))) {
-		primary_state->src_h = set->mode->hdisplay << 16;
-		primary_state->src_w = set->mode->vdisplay << 16;
+		primary_state->src_h = hdisplay << 16;
+		primary_state->src_w = vdisplay << 16;
 	} else {
-		primary_state->src_h = set->mode->vdisplay << 16;
-		primary_state->src_w = set->mode->hdisplay << 16;
+		primary_state->src_h = vdisplay << 16;
+		primary_state->src_w = hdisplay << 16;
 	}
 
 commit:
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 9362609df38a..7dd6728dd092 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -160,6 +160,11 @@ int drm_setmaster_ioctl(struct drm_device *dev, void *data,
 		goto out_unlock;
 	}
 
+	if (!file_priv->allowed_master) {
+		ret = drm_new_set_master(dev, file_priv);
+		goto out_unlock;
+	}
+
 	file_priv->minor->master = drm_master_get(file_priv->master);
 	file_priv->is_master = 1;
 	if (dev->driver->master_set) {
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index e673c13c7391..69cbab5e5c81 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -342,6 +342,7 @@ static int restore_fbdev_mode_atomic(struct drm_fb_helper *fb_helper)
 	struct drm_plane *plane;
 	struct drm_atomic_state *state;
 	int i, ret;
+	unsigned plane_mask;
 
 	state = drm_atomic_state_alloc(dev);
 	if (!state)
@@ -349,11 +350,10 @@ static int restore_fbdev_mode_atomic(struct drm_fb_helper *fb_helper)
 
 	state->acquire_ctx = dev->mode_config.acquire_ctx;
 retry:
+	plane_mask = 0;
 	drm_for_each_plane(plane, dev) {
 		struct drm_plane_state *plane_state;
 
-		plane->old_fb = plane->fb;
-
 		plane_state = drm_atomic_get_plane_state(state, plane);
 		if (IS_ERR(plane_state)) {
 			ret = PTR_ERR(plane_state);
@@ -362,6 +362,9 @@ retry:
 
 		plane_state->rotation = BIT(DRM_ROTATE_0);
 
+		plane->old_fb = plane->fb;
+		plane_mask |= 1 << drm_plane_index(plane);
+
 		/* disable non-primary: */
 		if (plane->type == DRM_PLANE_TYPE_PRIMARY)
 			continue;
@@ -382,19 +385,7 @@ retry:
 	ret = drm_atomic_commit(state);
 
 fail:
-	drm_for_each_plane(plane, dev) {
-		if (ret == 0) {
-			struct drm_framebuffer *new_fb = plane->state->fb;
-			if (new_fb)
-				drm_framebuffer_reference(new_fb);
-			plane->fb = new_fb;
-			plane->crtc = plane->state->crtc;
-
-			if (plane->old_fb)
-				drm_framebuffer_unreference(plane->old_fb);
-		}
-		plane->old_fb = NULL;
-	}
+	drm_atomic_clean_old_fb(dev, plane_mask, ret);
 
 	if (ret == -EDEADLK)
 		goto backoff;
@@ -1236,7 +1227,9 @@ static int pan_display_atomic(struct fb_var_screeninfo *var,
 	struct drm_fb_helper *fb_helper = info->par;
 	struct drm_device *dev = fb_helper->dev;
 	struct drm_atomic_state *state;
+	struct drm_plane *plane;
 	int i, ret;
+	unsigned plane_mask;
 
 	state = drm_atomic_state_alloc(dev);
 	if (!state)
@@ -1244,19 +1237,22 @@ static int pan_display_atomic(struct fb_var_screeninfo *var,
 
 	state->acquire_ctx = dev->mode_config.acquire_ctx;
 retry:
+	plane_mask = 0;
 	for(i = 0; i < fb_helper->crtc_count; i++) {
 		struct drm_mode_set *mode_set;
 
 		mode_set = &fb_helper->crtc_info[i].mode_set;
 
-		mode_set->crtc->primary->old_fb = mode_set->crtc->primary->fb;
-
 		mode_set->x = var->xoffset;
 		mode_set->y = var->yoffset;
 
 		ret = __drm_atomic_helper_set_config(mode_set, state);
 		if (ret != 0)
 			goto fail;
+
+		plane = mode_set->crtc->primary;
+		plane_mask |= drm_plane_index(plane);
+		plane->old_fb = plane->fb;
 	}
 
 	ret = drm_atomic_commit(state);
@@ -1268,26 +1264,7 @@ retry:
 
 
 fail:
-	for(i = 0; i < fb_helper->crtc_count; i++) {
-		struct drm_mode_set *mode_set;
-		struct drm_plane *plane;
-
-		mode_set = &fb_helper->crtc_info[i].mode_set;
-		plane = mode_set->crtc->primary;
-
-		if (ret == 0) {
-			struct drm_framebuffer *new_fb = plane->state->fb;
-
-			if (new_fb)
-				drm_framebuffer_reference(new_fb);
-			plane->fb = new_fb;
-			plane->crtc = plane->state->crtc;
-
-			if (plane->old_fb)
-				drm_framebuffer_unreference(plane->old_fb);
-		}
-		plane->old_fb = NULL;
-	}
+	drm_atomic_clean_old_fb(dev, plane_mask, ret);
 
 	if (ret == -EDEADLK)
 		goto backoff;
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index c59ce4d0ef75..6b5625e66119 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -126,6 +126,60 @@ static int drm_cpu_valid(void)
 }
 
 /**
+ * drm_new_set_master - Allocate a new master object and become master for the
+ * associated master realm.
+ *
+ * @dev: The associated device.
+ * @fpriv: File private identifying the client.
+ *
+ * This function must be called with dev::struct_mutex held.
+ * Returns negative error code on failure. Zero on success.
+ */
+int drm_new_set_master(struct drm_device *dev, struct drm_file *fpriv)
+{
+	struct drm_master *old_master;
+	int ret;
+
+	lockdep_assert_held_once(&dev->master_mutex);
+
+	/* create a new master */
+	fpriv->minor->master = drm_master_create(fpriv->minor);
+	if (!fpriv->minor->master)
+		return -ENOMEM;
+
+	/* take another reference for the copy in the local file priv */
+	old_master = fpriv->master;
+	fpriv->master = drm_master_get(fpriv->minor->master);
+
+	if (dev->driver->master_create) {
+		ret = dev->driver->master_create(dev, fpriv->master);
+		if (ret)
+			goto out_err;
+	}
+	if (dev->driver->master_set) {
+		ret = dev->driver->master_set(dev, fpriv, true);
+		if (ret)
+			goto out_err;
+	}
+
+	fpriv->is_master = 1;
+	fpriv->allowed_master = 1;
+	fpriv->authenticated = 1;
+	if (old_master)
+		drm_master_put(&old_master);
+
+	return 0;
+
+out_err:
+	/* drop both references and restore old master on failure */
+	drm_master_put(&fpriv->minor->master);
+	drm_master_put(&fpriv->master);
+	fpriv->master = old_master;
+
+	return ret;
+}
+
+/**
  * Called whenever a process opens /dev/drm.
  *
  * \param filp file pointer.
@@ -189,35 +243,9 @@ static int drm_open_helper(struct file *filp, struct drm_minor *minor)
 	mutex_lock(&dev->master_mutex);
 	if (drm_is_primary_client(priv) && !priv->minor->master) {
 		/* create a new master */
-		priv->minor->master = drm_master_create(priv->minor);
-		if (!priv->minor->master) {
-			ret = -ENOMEM;
+		ret = drm_new_set_master(dev, priv);
+		if (ret)
 			goto out_close;
-		}
-
-		priv->is_master = 1;
-		/* take another reference for the copy in the local file priv */
-		priv->master = drm_master_get(priv->minor->master);
-		priv->authenticated = 1;
-
-		if (dev->driver->master_create) {
-			ret = dev->driver->master_create(dev, priv->master);
-			if (ret) {
-				/* drop both references if this fails */
-				drm_master_put(&priv->minor->master);
-				drm_master_put(&priv->master);
-				goto out_close;
-			}
-		}
-		if (dev->driver->master_set) {
-			ret = dev->driver->master_set(dev, priv, true);
-			if (ret) {
-				/* drop both references if this fails */
-				drm_master_put(&priv->minor->master);
-				drm_master_put(&priv->master);
-				goto out_close;
-			}
-		}
 	} else if (drm_is_primary_client(priv)) {
 		/* get a reference to the master */
 		priv->master = drm_master_get(priv->minor->master);
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 2151ea551d3b..607f493ae801 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -980,7 +980,8 @@ static void send_vblank_event(struct drm_device *dev,
 		struct drm_pending_vblank_event *e,
 		unsigned long seq, struct timeval *now)
 {
-	WARN_ON_SMP(!spin_is_locked(&dev->event_lock));
+	assert_spin_locked(&dev->event_lock);
+
 	e->event.sequence = seq;
 	e->event.tv_sec = now->tv_sec;
 	e->event.tv_usec = now->tv_usec;
@@ -993,6 +994,57 @@ static void send_vblank_event(struct drm_device *dev,
 }
 
 /**
+ * drm_arm_vblank_event - arm vblank event after pageflip
+ * @dev: DRM device
+ * @pipe: CRTC index
+ * @e: the event to prepare to send
+ *
+ * A lot of drivers need to generate vblank events for the very next vblank
+ * interrupt. For example when the page flip interrupt happens when the page
+ * flip gets armed, but not when it actually executes within the next vblank
+ * period. This helper function implements exactly the required vblank arming
+ * behaviour.
+ *
+ * Caller must hold event lock. Caller must also hold a vblank reference for
+ * the event @e, which will be dropped when the next vblank arrives.
+ *
+ * This is the legacy version of drm_crtc_arm_vblank_event().
+ */
+void drm_arm_vblank_event(struct drm_device *dev, unsigned int pipe,
+			  struct drm_pending_vblank_event *e)
+{
+	assert_spin_locked(&dev->event_lock);
+
+	e->pipe = pipe;
+	e->event.sequence = drm_vblank_count(dev, pipe);
+	list_add_tail(&e->base.link, &dev->vblank_event_list);
+}
+EXPORT_SYMBOL(drm_arm_vblank_event);
+
+/**
+ * drm_crtc_arm_vblank_event - arm vblank event after pageflip
+ * @crtc: the source CRTC of the vblank event
+ * @e: the event to send
+ *
+ * A lot of drivers need to generate vblank events for the very next vblank
+ * interrupt. For example when the page flip interrupt happens when the page
+ * flip gets armed, but not when it actually executes within the next vblank
+ * period. This helper function implements exactly the required vblank arming
+ * behaviour.
+ *
+ * Caller must hold event lock. Caller must also hold a vblank reference for
+ * the event @e, which will be dropped when the next vblank arrives.
+ *
+ * This is the native KMS version of drm_arm_vblank_event().
+ */
+void drm_crtc_arm_vblank_event(struct drm_crtc *crtc,
+			       struct drm_pending_vblank_event *e)
+{
+	drm_arm_vblank_event(crtc->dev, drm_crtc_index(crtc), e);
+}
+EXPORT_SYMBOL(drm_crtc_arm_vblank_event);
+
+/**
  * drm_send_vblank_event - helper to send vblank event after pageflip
  * @dev: DRM device
  * @pipe: CRTC index
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index a3b22bdacd44..8aab974b0564 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2734,6 +2734,8 @@ static const char *power_domain_str(enum intel_display_power_domain domain)
 		return "AUX_C";
 	case POWER_DOMAIN_AUX_D:
 		return "AUX_D";
+	case POWER_DOMAIN_GMBUS:
+		return "GMBUS";
 	case POWER_DOMAIN_INIT:
 		return "INIT";
 	default:
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 8afda459a26e..a01e51581c4c 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -199,6 +199,7 @@ enum intel_display_power_domain {
 	POWER_DOMAIN_AUX_B,
 	POWER_DOMAIN_AUX_C,
 	POWER_DOMAIN_AUX_D,
+	POWER_DOMAIN_GMBUS,
 	POWER_DOMAIN_INIT,
 
 	POWER_DOMAIN_NUM,
@@ -351,6 +352,8 @@ enum intel_dpll_id {
 	/* hsw/bdw */
 	DPLL_ID_WRPLL1 = 0,
 	DPLL_ID_WRPLL2 = 1,
+	DPLL_ID_SPLL = 2,
+
 	/* skl */
 	DPLL_ID_SKL_DPLL1 = 0,
 	DPLL_ID_SKL_DPLL2 = 1,
@@ -367,6 +370,7 @@ struct intel_dpll_hw_state {
 
 	/* hsw, bdw */
 	uint32_t wrpll;
+	uint32_t spll;
 
 	/* skl */
 	/*
@@ -2648,6 +2652,7 @@ struct i915_params {
 	int enable_cmd_parser;
 	/* leave bools at the end to not create holes */
 	bool enable_hangcheck;
+	bool fastboot;
 	bool prefault_disable;
 	bool load_detect_test;
 	bool reset;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5cf4a1998273..32e6aade6223 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1210,8 +1210,16 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
 	if (i915_gem_request_completed(req, true))
 		return 0;
 
-	timeout_expire = timeout ?
-		jiffies + nsecs_to_jiffies_timeout((u64)*timeout) : 0;
+	timeout_expire = 0;
+	if (timeout) {
+		if (WARN_ON(*timeout < 0))
+			return -EINVAL;
+
+		if (*timeout == 0)
+			return -ETIME;
+
+		timeout_expire = jiffies + nsecs_to_jiffies_timeout(*timeout);
+	}
 
 	if (INTEL_INFO(dev_priv)->gen >= 6)
 		gen6_rps_boost(dev_priv, rps, req->emitted_jiffies);
@@ -3809,6 +3817,7 @@ int i915_gem_get_caching_ioctl(struct drm_device *dev, void *data,
 int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 			       struct drm_file *file)
 {
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_caching *args = data;
 	struct drm_i915_gem_object *obj;
 	enum i915_cache_level level;
@@ -3837,9 +3846,11 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
+	intel_runtime_pm_get(dev_priv);
+
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
-		return ret;
+		goto rpm_put;
 
 	obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle));
 	if (&obj->base == NULL) {
@@ -3852,6 +3863,9 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 	drm_gem_object_unreference(&obj->base);
 unlock:
 	mutex_unlock(&dev->struct_mutex);
+rpm_put:
+	intel_runtime_pm_put(dev_priv);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem_fence.c b/drivers/gpu/drm/i915/i915_gem_fence.c
index 40a10b25956c..f010391b87f5 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence.c
@@ -642,11 +642,10 @@ i915_gem_detect_bit_6_swizzle(struct drm_device *dev)
 		}
 
 		/* check for L-shaped memory aka modified enhanced addressing */
-		if (IS_GEN4(dev)) {
-			uint32_t ddc2 = I915_READ(DCC2);
-
-			if (!(ddc2 & DCC2_MODIFIED_ENHANCED_DISABLE))
-				dev_priv->quirks |= QUIRK_PIN_SWIZZLED_PAGES;
+		if (IS_GEN4(dev) &&
+		    !(I915_READ(DCC2) & DCC2_MODIFIED_ENHANCED_DISABLE)) {
+			swizzle_x = I915_BIT_6_SWIZZLE_UNKNOWN;
+			swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN;
 		}
 
 		if (dcc == 0xffffffff) {
@@ -675,16 +674,35 @@ i915_gem_detect_bit_6_swizzle(struct drm_device *dev)
 		 * matching, which was the case for the swizzling required in
 		 * the table above, or from the 1-ch value being less than
 		 * the minimum size of a rank.
+		 *
+		 * Reports indicate that the swizzling actually
+		 * varies depending upon page placement inside the
+		 * channels, i.e. we see swizzled pages where the
+		 * banks of memory are paired and unswizzled on the
+		 * uneven portion, so leave that as unknown.
 		 */
-		if (I915_READ16(C0DRB3) != I915_READ16(C1DRB3)) {
-			swizzle_x = I915_BIT_6_SWIZZLE_NONE;
-			swizzle_y = I915_BIT_6_SWIZZLE_NONE;
-		} else {
+		if (I915_READ16(C0DRB3) == I915_READ16(C1DRB3)) {
 			swizzle_x = I915_BIT_6_SWIZZLE_9_10;
 			swizzle_y = I915_BIT_6_SWIZZLE_9;
 		}
 	}
 
+	if (swizzle_x == I915_BIT_6_SWIZZLE_UNKNOWN ||
+	    swizzle_y == I915_BIT_6_SWIZZLE_UNKNOWN) {
+		/* Userspace likes to explode if it sees unknown swizzling,
+		 * so lie. We will finish the lie when reporting through
+		 * the get-tiling-ioctl by reporting the physical swizzle
+		 * mode as unknown instead.
+		 *
+		 * As we don't strictly know what the swizzling is, it may be
+		 * bit17 dependent, and so we need to also prevent the pages
+		 * from being moved.
+		 */
+		dev_priv->quirks |= QUIRK_PIN_SWIZZLED_PAGES;
+		swizzle_x = I915_BIT_6_SWIZZLE_NONE;
+		swizzle_y = I915_BIT_6_SWIZZLE_NONE;
+	}
+
 	dev_priv->mm.bit_6_swizzle_x = swizzle_x;
 	dev_priv->mm.bit_6_swizzle_y = swizzle_y;
 }
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index 96bb23865eac..4be13a5eb932 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -40,6 +40,7 @@ struct i915_params i915 __read_mostly = {
 	.preliminary_hw_support = IS_ENABLED(CONFIG_DRM_I915_PRELIMINARY_HW_SUPPORT),
 	.disable_power_well = -1,
 	.enable_ips = 1,
+	.fastboot = 0,
 	.prefault_disable = 0,
 	.load_detect_test = 0,
 	.reset = true,
@@ -133,6 +134,10 @@ MODULE_PARM_DESC(disable_power_well,
 module_param_named_unsafe(enable_ips, i915.enable_ips, int, 0600);
 MODULE_PARM_DESC(enable_ips, "Enable IPS (default: true)");
 
+module_param_named(fastboot, i915.fastboot, bool, 0600);
+MODULE_PARM_DESC(fastboot,
+	"Try to skip unnecessary mode sets at boot time (default: false)");
+
 module_param_named_unsafe(prefault_disable, i915.prefault_disable, bool, 0600);
 MODULE_PARM_DESC(prefault_disable,
 	"Disable page prefaulting for pread/pwrite/reloc (default:false). "
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index b84aaa0bb48a..6a2c76e367a5 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -138,18 +138,6 @@ static void hsw_crt_get_config(struct intel_encoder *encoder,
 	pipe_config->base.adjusted_mode.flags |= intel_crt_get_flags(encoder);
 }
 
-static void hsw_crt_pre_enable(struct intel_encoder *encoder)
-{
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	WARN(I915_READ(SPLL_CTL) & SPLL_PLL_ENABLE, "SPLL already enabled\n");
-	I915_WRITE(SPLL_CTL,
-		   SPLL_PLL_ENABLE | SPLL_PLL_FREQ_1350MHz | SPLL_PLL_SSC);
-	POSTING_READ(SPLL_CTL);
-	udelay(20);
-}
-
 /* Note: The caller is required to filter out dpms modes not supported by the
  * platform. */
 static void intel_crt_set_dpms(struct intel_encoder *encoder, int mode)
@@ -216,19 +204,6 @@ static void pch_post_disable_crt(struct intel_encoder *encoder)
 	intel_disable_crt(encoder);
 }
 
-static void hsw_crt_post_disable(struct intel_encoder *encoder)
-{
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	uint32_t val;
-
-	DRM_DEBUG_KMS("Disabling SPLL\n");
-	val = I915_READ(SPLL_CTL);
-	WARN_ON(!(val & SPLL_PLL_ENABLE));
-	I915_WRITE(SPLL_CTL, val & ~SPLL_PLL_ENABLE);
-	POSTING_READ(SPLL_CTL);
-}
-
 static void intel_enable_crt(struct intel_encoder *encoder)
 {
 	struct intel_crt *crt = intel_encoder_to_crt(encoder);
@@ -280,6 +255,10 @@ static bool intel_crt_compute_config(struct intel_encoder *encoder,
 	if (HAS_DDI(dev)) {
 		pipe_config->ddi_pll_sel = PORT_CLK_SEL_SPLL;
 		pipe_config->port_clock = 135000 * 2;
+
+		pipe_config->dpll_hw_state.wrpll = 0;
+		pipe_config->dpll_hw_state.spll =
+			SPLL_PLL_ENABLE | SPLL_PLL_FREQ_1350MHz | SPLL_PLL_SSC;
 	}
 
 	return true;
@@ -860,8 +839,6 @@ void intel_crt_init(struct drm_device *dev)
 	if (HAS_DDI(dev)) {
 		crt->base.get_config = hsw_crt_get_config;
 		crt->base.get_hw_state = intel_ddi_get_hw_state;
-		crt->base.pre_enable = hsw_crt_pre_enable;
-		crt->base.post_disable = hsw_crt_post_disable;
 	} else {
 		crt->base.get_config = intel_crt_get_config;
 		crt->base.get_hw_state = intel_crt_get_hw_state;
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index b25e99a432fb..a6752a61d99f 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1286,6 +1286,18 @@ hsw_ddi_pll_select(struct intel_crtc *intel_crtc,
 		}
 
 		crtc_state->ddi_pll_sel = PORT_CLK_SEL_WRPLL(pll->id);
+	} else if (crtc_state->ddi_pll_sel == PORT_CLK_SEL_SPLL) {
+		struct drm_atomic_state *state = crtc_state->base.state;
+		struct intel_shared_dpll_config *spll =
+			&intel_atomic_get_shared_dpll_state(state)[DPLL_ID_SPLL];
+
+		if (spll->crtc_mask &&
+		    WARN_ON(spll->hw_state.spll != crtc_state->dpll_hw_state.spll))
+			return false;
+
+		crtc_state->shared_dpll = DPLL_ID_SPLL;
+		spll->hw_state.spll = crtc_state->dpll_hw_state.spll;
+		spll->crtc_mask |= 1 << intel_crtc->pipe;
 	}
 
 	return true;
@@ -2437,7 +2449,7 @@ static void intel_disable_ddi(struct intel_encoder *intel_encoder)
 	}
 }
 
-static void hsw_ddi_pll_enable(struct drm_i915_private *dev_priv,
+static void hsw_ddi_wrpll_enable(struct drm_i915_private *dev_priv,
 			       struct intel_shared_dpll *pll)
 {
 	I915_WRITE(WRPLL_CTL(pll->id), pll->config.hw_state.wrpll);
@@ -2445,9 +2457,17 @@ static void hsw_ddi_pll_enable(struct drm_i915_private *dev_priv,
 	udelay(20);
 }
 
-static void hsw_ddi_pll_disable(struct drm_i915_private *dev_priv,
+static void hsw_ddi_spll_enable(struct drm_i915_private *dev_priv,
 				struct intel_shared_dpll *pll)
 {
+	I915_WRITE(SPLL_CTL, pll->config.hw_state.spll);
+	POSTING_READ(SPLL_CTL);
+	udelay(20);
+}
+
+static void hsw_ddi_wrpll_disable(struct drm_i915_private *dev_priv,
+				  struct intel_shared_dpll *pll)
+{
 	uint32_t val;
 
 	val = I915_READ(WRPLL_CTL(pll->id));
@@ -2455,9 +2475,19 @@ static void hsw_ddi_pll_disable(struct drm_i915_private *dev_priv,
 	POSTING_READ(WRPLL_CTL(pll->id));
 }
 
-static bool hsw_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
-				     struct intel_shared_dpll *pll,
-				     struct intel_dpll_hw_state *hw_state)
+static void hsw_ddi_spll_disable(struct drm_i915_private *dev_priv,
+				 struct intel_shared_dpll *pll)
+{
+	uint32_t val;
+
+	val = I915_READ(SPLL_CTL);
+	I915_WRITE(SPLL_CTL, val & ~SPLL_PLL_ENABLE);
+	POSTING_READ(SPLL_CTL);
+}
+
+static bool hsw_ddi_wrpll_get_hw_state(struct drm_i915_private *dev_priv,
+				       struct intel_shared_dpll *pll,
+				       struct intel_dpll_hw_state *hw_state)
 {
 	uint32_t val;
 
@@ -2470,25 +2500,50 @@ static bool hsw_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
 	return val & WRPLL_PLL_ENABLE;
 }
 
+static bool hsw_ddi_spll_get_hw_state(struct drm_i915_private *dev_priv,
+				      struct intel_shared_dpll *pll,
+				      struct intel_dpll_hw_state *hw_state)
+{
+	uint32_t val;
+
+	if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS))
+		return false;
+
+	val = I915_READ(SPLL_CTL);
+	hw_state->spll = val;
+
+	return val & SPLL_PLL_ENABLE;
+}
+
+
 static const char * const hsw_ddi_pll_names[] = {
 	"WRPLL 1",
 	"WRPLL 2",
+	"SPLL"
 };
 
 static void hsw_shared_dplls_init(struct drm_i915_private *dev_priv)
 {
 	int i;
 
-	dev_priv->num_shared_dpll = 2;
+	dev_priv->num_shared_dpll = 3;
 
-	for (i = 0; i < dev_priv->num_shared_dpll; i++) {
+	for (i = 0; i < 2; i++) {
 		dev_priv->shared_dplls[i].id = i;
 		dev_priv->shared_dplls[i].name = hsw_ddi_pll_names[i];
-		dev_priv->shared_dplls[i].disable = hsw_ddi_pll_disable;
-		dev_priv->shared_dplls[i].enable = hsw_ddi_pll_enable;
+		dev_priv->shared_dplls[i].disable = hsw_ddi_wrpll_disable;
+		dev_priv->shared_dplls[i].enable = hsw_ddi_wrpll_enable;
 		dev_priv->shared_dplls[i].get_hw_state =
-			hsw_ddi_pll_get_hw_state;
+			hsw_ddi_wrpll_get_hw_state;
 	}
+
+	/* SPLL is special, but needs to be initialized anyway.. */
+	dev_priv->shared_dplls[i].id = i;
+	dev_priv->shared_dplls[i].name = hsw_ddi_pll_names[i];
+	dev_priv->shared_dplls[i].disable = hsw_ddi_spll_disable;
+	dev_priv->shared_dplls[i].enable = hsw_ddi_spll_enable;
+	dev_priv->shared_dplls[i].get_hw_state = hsw_ddi_spll_get_hw_state;
+
 }
 
 static const char * const skl_ddi_pll_names[] = {
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index f62ffc04c21d..22e86d2e408d 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2646,11 +2646,13 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 	return;
 
 valid_fb:
-	plane_state->src_x = plane_state->src_y = 0;
+	plane_state->src_x = 0;
+	plane_state->src_y = 0;
 	plane_state->src_w = fb->width << 16;
 	plane_state->src_h = fb->height << 16;
 
-	plane_state->crtc_x = plane_state->src_y = 0;
+	plane_state->crtc_x = 0;
+	plane_state->crtc_y = 0;
 	plane_state->crtc_w = fb->width;
 	plane_state->crtc_h = fb->height;
 
@@ -4237,6 +4239,7 @@ struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc,
 	struct intel_shared_dpll *pll;
 	struct intel_shared_dpll_config *shared_dpll;
 	enum intel_dpll_id i;
+	int max = dev_priv->num_shared_dpll;
 
 	shared_dpll = intel_atomic_get_shared_dpll_state(crtc_state->base.state);
 
@@ -4271,9 +4274,11 @@ struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc,
 		WARN_ON(shared_dpll[i].crtc_mask);
 
 		goto found;
-	}
+	} else if (INTEL_INFO(dev_priv)->gen < 9 && HAS_DDI(dev_priv))
+		/* Do not consider SPLL */
+		max = 2;
 
-	for (i = 0; i < dev_priv->num_shared_dpll; i++) {
+	for (i = 0; i < max; i++) {
 		pll = &dev_priv->shared_dplls[i];
 
 		/* Only want to check enabled timings first */
@@ -5189,11 +5194,31 @@ static enum intel_display_power_domain port_to_power_domain(enum port port)
 	case PORT_E:
 		return POWER_DOMAIN_PORT_DDI_E_2_LANES;
 	default:
-		WARN_ON_ONCE(1);
+		MISSING_CASE(port);
 		return POWER_DOMAIN_PORT_OTHER;
 	}
 }
 
+static enum intel_display_power_domain port_to_aux_power_domain(enum port port)
+{
+	switch (port) {
+	case PORT_A:
+		return POWER_DOMAIN_AUX_A;
+	case PORT_B:
+		return POWER_DOMAIN_AUX_B;
+	case PORT_C:
+		return POWER_DOMAIN_AUX_C;
+	case PORT_D:
+		return POWER_DOMAIN_AUX_D;
+	case PORT_E:
+		/* FIXME: Check VBT for actual wiring of PORT E */
+		return POWER_DOMAIN_AUX_D;
+	default:
+		MISSING_CASE(port);
+		return POWER_DOMAIN_AUX_A;
+	}
+}
+
 #define for_each_power_domain(domain, mask)				\
 	for ((domain) = 0; (domain) < POWER_DOMAIN_NUM; (domain)++)	\
 		if ((1 << (domain)) & (mask))
@@ -5225,6 +5250,36 @@ intel_display_port_power_domain(struct intel_encoder *intel_encoder)
 	}
 }
 
+enum intel_display_power_domain
+intel_display_port_aux_power_domain(struct intel_encoder *intel_encoder)
+{
+	struct drm_device *dev = intel_encoder->base.dev;
+	struct intel_digital_port *intel_dig_port;
+
+	switch (intel_encoder->type) {
+	case INTEL_OUTPUT_UNKNOWN:
+	case INTEL_OUTPUT_HDMI:
+		/*
+		 * Only DDI platforms should ever use these output types.
+		 * We can get here after the HDMI detect code has already set
+		 * the type of the shared encoder. Since we can't be sure
+		 * what's the status of the given connectors, play safe and
+		 * run the DP detection too.
+		 */
+		WARN_ON_ONCE(!HAS_DDI(dev));
+	case INTEL_OUTPUT_DISPLAYPORT:
+	case INTEL_OUTPUT_EDP:
+		intel_dig_port = enc_to_dig_port(&intel_encoder->base);
+		return port_to_aux_power_domain(intel_dig_port->port);
+	case INTEL_OUTPUT_DP_MST:
+		intel_dig_port = enc_to_mst(&intel_encoder->base)->primary;
+		return port_to_aux_power_domain(intel_dig_port->port);
+	default:
+		MISSING_CASE(intel_encoder->type);
+		return POWER_DOMAIN_AUX_A;
+	}
+}
+
 static unsigned long get_crtc_power_domains(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
@@ -9723,6 +9778,8 @@ static void haswell_get_ddi_pll(struct drm_i915_private *dev_priv,
 	case PORT_CLK_SEL_WRPLL2:
 		pipe_config->shared_dpll = DPLL_ID_WRPLL2;
 		break;
+	case PORT_CLK_SEL_SPLL:
+		pipe_config->shared_dpll = DPLL_ID_SPLL;
 	}
 }
 
@@ -12003,9 +12060,10 @@ static void intel_dump_pipe_config(struct intel_crtc *crtc,
 			      pipe_config->dpll_hw_state.cfgcr1,
 			      pipe_config->dpll_hw_state.cfgcr2);
 	} else if (HAS_DDI(dev)) {
-		DRM_DEBUG_KMS("ddi_pll_sel: %u; dpll_hw_state: wrpll: 0x%x\n",
+		DRM_DEBUG_KMS("ddi_pll_sel: %u; dpll_hw_state: wrpll: 0x%x spll: 0x%x\n",
 			      pipe_config->ddi_pll_sel,
-			      pipe_config->dpll_hw_state.wrpll);
+			      pipe_config->dpll_hw_state.wrpll,
+			      pipe_config->dpll_hw_state.spll);
 	} else {
 		DRM_DEBUG_KMS("dpll_hw_state: dpll: 0x%x, dpll_md: 0x%x, "
 			      "fp0: 0x%x, fp1: 0x%x\n",
@@ -12452,7 +12510,6 @@ intel_pipe_config_compare(struct drm_device *dev,
 	if (INTEL_INFO(dev)->gen < 8) {
 		PIPE_CONF_CHECK_M_N(dp_m_n);
 
-		PIPE_CONF_CHECK_I(has_drrs);
 		if (current_config->has_drrs)
 			PIPE_CONF_CHECK_M_N(dp_m2_n2);
 	} else
@@ -12528,6 +12585,7 @@ intel_pipe_config_compare(struct drm_device *dev,
 	PIPE_CONF_CHECK_X(dpll_hw_state.fp0);
 	PIPE_CONF_CHECK_X(dpll_hw_state.fp1);
 	PIPE_CONF_CHECK_X(dpll_hw_state.wrpll);
+	PIPE_CONF_CHECK_X(dpll_hw_state.spll);
 	PIPE_CONF_CHECK_X(dpll_hw_state.ctrl1);
 	PIPE_CONF_CHECK_X(dpll_hw_state.cfgcr1);
 	PIPE_CONF_CHECK_X(dpll_hw_state.cfgcr2);
@@ -13032,6 +13090,9 @@ static int intel_atomic_check(struct drm_device *dev,
 		struct intel_crtc_state *pipe_config =
 			to_intel_crtc_state(crtc_state);
 
+		memset(&to_intel_crtc(crtc)->atomic, 0,
+		       sizeof(struct intel_crtc_atomic_commit));
+
 		/* Catch I915_MODE_FLAG_INHERITED */
 		if (crtc_state->mode.private_flags != crtc->state->mode.private_flags)
 			crtc_state->mode_changed = true;
@@ -13056,7 +13117,8 @@ static int intel_atomic_check(struct drm_device *dev,
 		if (ret)
 			return ret;
 
-		if (intel_pipe_config_compare(state->dev,
+		if (i915.fastboot &&
+		    intel_pipe_config_compare(state->dev,
 					to_intel_crtc_state(crtc->state),
 					pipe_config, true)) {
 			crtc_state->mode_changed = false;
@@ -14364,16 +14426,17 @@ static int intel_framebuffer_init(struct drm_device *dev,
 static struct drm_framebuffer *
 intel_user_framebuffer_create(struct drm_device *dev,
 			      struct drm_file *filp,
-			      struct drm_mode_fb_cmd2 *mode_cmd)
+			      struct drm_mode_fb_cmd2 *user_mode_cmd)
 {
 	struct drm_i915_gem_object *obj;
+	struct drm_mode_fb_cmd2 mode_cmd = *user_mode_cmd;
 
 	obj = to_intel_bo(drm_gem_object_lookup(dev, filp,
-						mode_cmd->handles[0]));
+						mode_cmd.handles[0]));
 	if (&obj->base == NULL)
 		return ERR_PTR(-ENOENT);
 
-	return intel_framebuffer_create(dev, mode_cmd, obj);
+	return intel_framebuffer_create(dev, &mode_cmd, obj);
 }
 
 #ifndef CONFIG_DRM_FBDEV_EMULATION
@@ -14705,6 +14768,9 @@ static struct intel_quirk intel_quirks[] = {
 	/* Apple Macbook 2,1 (Core 2 T7400) */
 	{ 0x27a2, 0x8086, 0x7270, quirk_backlight_present },
 
+	/* Apple Macbook 4,1 */
+	{ 0x2a02, 0x106b, 0x00a1, quirk_backlight_present },
+
 	/* Toshiba CB35 Chromebook (Celeron 2955U) */
 	{ 0x0a06, 0x1179, 0x0a88, quirk_backlight_present },
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 09bdd94ca3ba..78b8ec84d576 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -277,7 +277,7 @@ static void pps_lock(struct intel_dp *intel_dp)
 	 * See vlv_power_sequencer_reset() why we need
 	 * a power domain reference here.
 	 */
-	power_domain = intel_display_port_power_domain(encoder);
+	power_domain = intel_display_port_aux_power_domain(encoder);
 	intel_display_power_get(dev_priv, power_domain);
 
 	mutex_lock(&dev_priv->pps_mutex);
@@ -293,7 +293,7 @@ static void pps_unlock(struct intel_dp *intel_dp)
 
 	mutex_unlock(&dev_priv->pps_mutex);
 
-	power_domain = intel_display_port_power_domain(encoder);
+	power_domain = intel_display_port_aux_power_domain(encoder);
 	intel_display_power_put(dev_priv, power_domain);
 }
 
@@ -816,8 +816,6 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 
 	intel_dp_check_edp(intel_dp);
 
-	intel_aux_display_runtime_get(dev_priv);
-
 	/* Try to wait for any previous AUX channel activity */
 	for (try = 0; try < 3; try++) {
 		status = I915_READ_NOTRACE(ch_ctl);
@@ -926,7 +924,6 @@ done:
 	ret = recv_bytes;
 out:
 	pm_qos_update_request(&dev_priv->pm_qos, PM_QOS_DEFAULT_VALUE);
-	intel_aux_display_runtime_put(dev_priv);
 
 	if (vdd)
 		edp_panel_vdd_off(intel_dp, false);
@@ -1784,7 +1781,7 @@ static bool edp_panel_vdd_on(struct intel_dp *intel_dp)
 	if (edp_have_panel_vdd(intel_dp))
 		return need_to_disable;
 
-	power_domain = intel_display_port_power_domain(intel_encoder);
+	power_domain = intel_display_port_aux_power_domain(intel_encoder);
 	intel_display_power_get(dev_priv, power_domain);
 
 	DRM_DEBUG_KMS("Turning eDP port %c VDD on\n",
@@ -1874,7 +1871,7 @@ static void edp_panel_vdd_off_sync(struct intel_dp *intel_dp)
 	if ((pp & POWER_TARGET_ON) == 0)
 		intel_dp->last_power_cycle = jiffies;
 
-	power_domain = intel_display_port_power_domain(intel_encoder);
+	power_domain = intel_display_port_aux_power_domain(intel_encoder);
 	intel_display_power_put(dev_priv, power_domain);
 }
 
@@ -2025,7 +2022,7 @@ static void edp_panel_off(struct intel_dp *intel_dp)
 	wait_panel_off(intel_dp);
 
 	/* We got a reference when we enabled the VDD. */
-	power_domain = intel_display_port_power_domain(intel_encoder);
+	power_domain = intel_display_port_aux_power_domain(intel_encoder);
 	intel_display_power_put(dev_priv, power_domain);
 }
 
@@ -4765,26 +4762,6 @@ intel_dp_unset_edid(struct intel_dp *intel_dp)
 	intel_dp->has_audio = false;
 }
 
-static enum intel_display_power_domain
-intel_dp_power_get(struct intel_dp *dp)
-{
-	struct intel_encoder *encoder = &dp_to_dig_port(dp)->base;
-	enum intel_display_power_domain power_domain;
-
-	power_domain = intel_display_port_power_domain(encoder);
-	intel_display_power_get(to_i915(encoder->base.dev), power_domain);
-
-	return power_domain;
-}
-
-static void
-intel_dp_power_put(struct intel_dp *dp,
-		   enum intel_display_power_domain power_domain)
-{
-	struct intel_encoder *encoder = &dp_to_dig_port(dp)->base;
-	intel_display_power_put(to_i915(encoder->base.dev), power_domain);
-}
-
 static enum drm_connector_status
 intel_dp_detect(struct drm_connector *connector, bool force)
 {
@@ -4808,7 +4785,8 @@ intel_dp_detect(struct drm_connector *connector, bool force)
 		return connector_status_disconnected;
 	}
 
-	power_domain = intel_dp_power_get(intel_dp);
+	power_domain = intel_display_port_aux_power_domain(intel_encoder);
+	intel_display_power_get(to_i915(dev), power_domain);
 
 	/* Can't disconnect eDP, but you can close the lid... */
 	if (is_edp(intel_dp))
@@ -4853,7 +4831,7 @@ intel_dp_detect(struct drm_connector *connector, bool force)
 	}
 
 out:
-	intel_dp_power_put(intel_dp, power_domain);
+	intel_display_power_put(to_i915(dev), power_domain);
 	return status;
 }
 
@@ -4862,6 +4840,7 @@ intel_dp_force(struct drm_connector *connector)
 {
 	struct intel_dp *intel_dp = intel_attached_dp(connector);
 	struct intel_encoder *intel_encoder = &dp_to_dig_port(intel_dp)->base;
+	struct drm_i915_private *dev_priv = to_i915(intel_encoder->base.dev);
 	enum intel_display_power_domain power_domain;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
@@ -4871,11 +4850,12 @@ intel_dp_force(struct drm_connector *connector)
 	if (connector->status != connector_status_connected)
 		return;
 
-	power_domain = intel_dp_power_get(intel_dp);
+	power_domain = intel_display_port_aux_power_domain(intel_encoder);
+	intel_display_power_get(dev_priv, power_domain);
 
 	intel_dp_set_edid(intel_dp);
 
-	intel_dp_power_put(intel_dp, power_domain);
+	intel_display_power_put(dev_priv, power_domain);
 
 	if (intel_encoder->type != INTEL_OUTPUT_EDP)
 		intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT;
@@ -5091,7 +5071,7 @@ static void intel_edp_panel_vdd_sanitize(struct intel_dp *intel_dp)
 	 * indefinitely.
 	 */
 	DRM_DEBUG_KMS("VDD left on by BIOS, adjusting state tracking\n");
-	power_domain = intel_display_port_power_domain(&intel_dig_port->base);
+	power_domain = intel_display_port_aux_power_domain(&intel_dig_port->base);
 	intel_display_power_get(dev_priv, power_domain);
 
 	edp_panel_vdd_schedule_off(intel_dp);
@@ -5153,7 +5133,8 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd)
 	enum intel_display_power_domain power_domain;
 	enum irqreturn ret = IRQ_NONE;
 
-	if (intel_dig_port->base.type != INTEL_OUTPUT_EDP)
+	if (intel_dig_port->base.type != INTEL_OUTPUT_EDP &&
+	    intel_dig_port->base.type != INTEL_OUTPUT_HDMI)
 		intel_dig_port->base.type = INTEL_OUTPUT_DISPLAYPORT;
 
 	if (long_hpd && intel_dig_port->base.type == INTEL_OUTPUT_EDP) {
@@ -5172,7 +5153,7 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd)
 		      port_name(intel_dig_port->port),
 		      long_hpd ? "long" : "short");
 
-	power_domain = intel_display_port_power_domain(intel_encoder);
+	power_domain = intel_display_port_aux_power_domain(intel_encoder);
 	intel_display_power_get(dev_priv, power_domain);
 
 	if (long_hpd) {
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 0598932ce623..f2a1142bff34 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1169,6 +1169,8 @@ void hsw_enable_ips(struct intel_crtc *crtc);
 void hsw_disable_ips(struct intel_crtc *crtc);
 enum intel_display_power_domain
 intel_display_port_power_domain(struct intel_encoder *intel_encoder);
+enum intel_display_power_domain
+intel_display_port_aux_power_domain(struct intel_encoder *intel_encoder);
 void intel_mode_from_pipe_config(struct drm_display_mode *mode,
 				 struct intel_crtc_state *pipe_config);
 void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc);
@@ -1377,8 +1379,6 @@ void intel_display_power_get(struct drm_i915_private *dev_priv,
 			     enum intel_display_power_domain domain);
 void intel_display_power_put(struct drm_i915_private *dev_priv,
 			     enum intel_display_power_domain domain);
-void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv);
-void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv);
 void intel_runtime_pm_get(struct drm_i915_private *dev_priv);
 void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv);
 void intel_runtime_pm_put(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 9eafa191cee2..81cdd9ff3892 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -1335,21 +1335,17 @@ intel_hdmi_set_edid(struct drm_connector *connector, bool force)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
-	struct intel_encoder *intel_encoder =
-		&hdmi_to_dig_port(intel_hdmi)->base;
-	enum intel_display_power_domain power_domain;
 	struct edid *edid = NULL;
 	bool connected = false;
 
-	power_domain = intel_display_port_power_domain(intel_encoder);
-	intel_display_power_get(dev_priv, power_domain);
+	intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
 
 	if (force)
 		edid = drm_get_edid(connector,
 				    intel_gmbus_get_adapter(dev_priv,
 				    intel_hdmi->ddc_bus));
 
-	intel_display_power_put(dev_priv, power_domain);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS);
 
 	to_intel_connector(connector)->detect_edid = edid;
 	if (edid && edid->input & DRM_EDID_INPUT_DIGITAL) {
@@ -1383,6 +1379,8 @@ intel_hdmi_detect(struct drm_connector *connector, bool force)
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
 		      connector->base.id, connector->name);
 
+	intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
+
 	while (!live_status && --retry) {
 		live_status = intel_digital_port_connected(dev_priv,
 				hdmi_to_dig_port(intel_hdmi));
@@ -1402,6 +1400,8 @@ intel_hdmi_detect(struct drm_connector *connector, bool force)
 	} else
 		status = connector_status_disconnected;
 
+	intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS);
+
 	return status;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 1369fc41d039..8324654037b6 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -483,7 +483,7 @@ gmbus_xfer(struct i2c_adapter *adapter,
 	int i = 0, inc, try = 0;
 	int ret = 0;
 
-	intel_aux_display_runtime_get(dev_priv);
+	intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
 	mutex_lock(&dev_priv->gmbus_mutex);
 
 	if (bus->force_bit) {
@@ -595,7 +595,9 @@ timeout:
 
 out:
 	mutex_unlock(&dev_priv->gmbus_mutex);
-	intel_aux_display_runtime_put(dev_priv);
+
+	intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index d52a15df6917..071a76b9ac52 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4449,7 +4449,7 @@ static void gen6_set_rps(struct drm_device *dev, u8 val)
 	POSTING_READ(GEN6_RPNSWREQ);
 
 	dev_priv->rps.cur_freq = val;
-	trace_intel_gpu_freq_change(val * 50);
+	trace_intel_gpu_freq_change(intel_gpu_freq(dev_priv, val));
 }
 
 static void valleyview_set_rps(struct drm_device *dev, u8 val)
@@ -7255,7 +7255,8 @@ static int chv_freq_opcode(struct drm_i915_private *dev_priv, int val)
 int intel_gpu_freq(struct drm_i915_private *dev_priv, int val)
 {
 	if (IS_GEN9(dev_priv->dev))
-		return (val * GT_FREQUENCY_MULTIPLIER) / GEN9_FREQ_SCALER;
+		return DIV_ROUND_CLOSEST(val * GT_FREQUENCY_MULTIPLIER,
+					 GEN9_FREQ_SCALER);
 	else if (IS_CHERRYVIEW(dev_priv->dev))
 		return chv_gpu_freq(dev_priv, val);
 	else if (IS_VALLEYVIEW(dev_priv->dev))
@@ -7267,13 +7268,14 @@ int intel_gpu_freq(struct drm_i915_private *dev_priv, int val)
 int intel_freq_opcode(struct drm_i915_private *dev_priv, int val)
 {
 	if (IS_GEN9(dev_priv->dev))
-		return (val * GEN9_FREQ_SCALER) / GT_FREQUENCY_MULTIPLIER;
+		return DIV_ROUND_CLOSEST(val * GEN9_FREQ_SCALER,
+					 GT_FREQUENCY_MULTIPLIER);
 	else if (IS_CHERRYVIEW(dev_priv->dev))
 		return chv_freq_opcode(dev_priv, val);
 	else if (IS_VALLEYVIEW(dev_priv->dev))
 		return byt_freq_opcode(dev_priv, val);
 	else
-		return val / GT_FREQUENCY_MULTIPLIER;
+		return DIV_ROUND_CLOSEST(val, GT_FREQUENCY_MULTIPLIER);
 }
 
 struct request_boost {
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index d89c1d0aa1b7..7e23d65c9b24 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -362,6 +362,7 @@ static void hsw_set_power_well(struct drm_i915_private *dev_priv,
 	BIT(POWER_DOMAIN_AUX_C) |			\
 	BIT(POWER_DOMAIN_AUDIO) |			\
 	BIT(POWER_DOMAIN_VGA) |				\
+	BIT(POWER_DOMAIN_GMBUS) |			\
 	BIT(POWER_DOMAIN_INIT))
 #define BXT_DISPLAY_POWERWELL_1_POWER_DOMAINS (		\
 	BXT_DISPLAY_POWERWELL_2_POWER_DOMAINS |		\
@@ -1483,6 +1484,7 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 	BIT(POWER_DOMAIN_AUX_B) |			\
 	BIT(POWER_DOMAIN_AUX_C) |			\
 	BIT(POWER_DOMAIN_AUX_D) |			\
+	BIT(POWER_DOMAIN_GMBUS) |			\
 	BIT(POWER_DOMAIN_INIT))
 #define HSW_DISPLAY_POWER_DOMAINS (				\
 	(POWER_DOMAIN_MASK & ~HSW_ALWAYS_ON_POWER_DOMAINS) |	\
@@ -1845,6 +1847,8 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv)
 	i915.disable_power_well = sanitize_disable_power_well_option(dev_priv,
 						     i915.disable_power_well);
 
+	BUILD_BUG_ON(POWER_DOMAIN_NUM > 31);
+
 	mutex_init(&power_domains->lock);
 
 	/*
@@ -2064,36 +2068,6 @@ void intel_power_domains_init_hw(struct drm_i915_private *dev_priv)
 }
 
 /**
- * intel_aux_display_runtime_get - grab an auxiliary power domain reference
- * @dev_priv: i915 device instance
- *
- * This function grabs a power domain reference for the auxiliary power domain
- * (for access to the GMBUS and DP AUX blocks) and ensures that it and all its
- * parents are powered up. Therefore users should only grab a reference to the
- * innermost power domain they need.
- *
- * Any power domain reference obtained by this function must have a symmetric
- * call to intel_aux_display_runtime_put() to release the reference again.
- */
-void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv)
-{
-	intel_runtime_pm_get(dev_priv);
-}
-
-/**
- * intel_aux_display_runtime_put - release an auxiliary power domain reference
- * @dev_priv: i915 device instance
- *
- * This function drops the auxiliary power domain reference obtained by
- * intel_aux_display_runtime_get() and might power down the corresponding
- * hardware block right away if this is the last reference.
- */
-void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv)
-{
-	intel_runtime_pm_put(dev_priv);
-}
-
-/**
  * intel_runtime_pm_get - grab a runtime pm reference
  * @dev_priv: i915 device instance
  *
diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index 64f16ea779ef..7b990b4e96d2 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -63,8 +63,7 @@ static void imx_drm_driver_lastclose(struct drm_device *drm)
 #if IS_ENABLED(CONFIG_DRM_IMX_FB_HELPER)
 	struct imx_drm_device *imxdrm = drm->dev_private;
 
-	if (imxdrm->fbhelper)
-		drm_fbdev_cma_restore_mode(imxdrm->fbhelper);
+	drm_fbdev_cma_restore_mode(imxdrm->fbhelper);
 #endif
 }
 
@@ -340,7 +339,7 @@ err_kms:
  * imx_drm_add_crtc - add a new crtc
  */
 int imx_drm_add_crtc(struct drm_device *drm, struct drm_crtc *crtc,
-		struct imx_drm_crtc **new_crtc,
+		struct imx_drm_crtc **new_crtc, struct drm_plane *primary_plane,
 		const struct imx_drm_crtc_helper_funcs *imx_drm_helper_funcs,
 		struct device_node *port)
 {
@@ -379,7 +378,7 @@ int imx_drm_add_crtc(struct drm_device *drm, struct drm_crtc *crtc,
 	drm_crtc_helper_add(crtc,
 			imx_drm_crtc->imx_drm_helper_funcs.crtc_helper_funcs);
 
-	drm_crtc_init(drm, crtc,
+	drm_crtc_init_with_planes(drm, crtc, primary_plane, NULL,
 			imx_drm_crtc->imx_drm_helper_funcs.crtc_funcs);
 
 	return 0;
diff --git a/drivers/gpu/drm/imx/imx-drm.h b/drivers/gpu/drm/imx/imx-drm.h
index 28e776d8d9d2..83284b4d4be1 100644
--- a/drivers/gpu/drm/imx/imx-drm.h
+++ b/drivers/gpu/drm/imx/imx-drm.h
@@ -9,6 +9,7 @@ struct drm_display_mode;
 struct drm_encoder;
 struct drm_fbdev_cma;
 struct drm_framebuffer;
+struct drm_plane;
 struct imx_drm_crtc;
 struct platform_device;
 
@@ -24,7 +25,7 @@ struct imx_drm_crtc_helper_funcs {
 };
 
 int imx_drm_add_crtc(struct drm_device *drm, struct drm_crtc *crtc,
-		struct imx_drm_crtc **new_crtc,
+		struct imx_drm_crtc **new_crtc, struct drm_plane *primary_plane,
 		const struct imx_drm_crtc_helper_funcs *imx_helper_funcs,
 		struct device_node *port);
 int imx_drm_remove_crtc(struct imx_drm_crtc *);
diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c
index e671ad369416..f9597146dc67 100644
--- a/drivers/gpu/drm/imx/imx-tve.c
+++ b/drivers/gpu/drm/imx/imx-tve.c
@@ -721,6 +721,7 @@ static const struct of_device_id imx_tve_dt_ids[] = {
 	{ .compatible = "fsl,imx53-tve", },
 	{ /* sentinel */ }
 };
+MODULE_DEVICE_TABLE(of, imx_tve_dt_ids);
 
 static struct platform_driver imx_tve_driver = {
 	.probe		= imx_tve_probe,
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index 7bc8301fafff..4ab841eebee1 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -212,7 +212,8 @@ static void ipu_crtc_handle_pageflip(struct ipu_crtc *ipu_crtc)
 
 	spin_lock_irqsave(&drm->event_lock, flags);
 	if (ipu_crtc->page_flip_event)
-		drm_send_vblank_event(drm, -1, ipu_crtc->page_flip_event);
+		drm_crtc_send_vblank_event(&ipu_crtc->base,
+					   ipu_crtc->page_flip_event);
 	ipu_crtc->page_flip_event = NULL;
 	imx_drm_crtc_vblank_put(ipu_crtc->imx_crtc);
 	spin_unlock_irqrestore(&drm->event_lock, flags);
@@ -349,7 +350,6 @@ static int ipu_crtc_init(struct ipu_crtc *ipu_crtc,
 	struct ipu_soc *ipu = dev_get_drvdata(ipu_crtc->dev->parent);
 	int dp = -EINVAL;
 	int ret;
-	int id;
 
 	ret = ipu_get_resources(ipu_crtc, pdata);
 	if (ret) {
@@ -358,18 +358,23 @@ static int ipu_crtc_init(struct ipu_crtc *ipu_crtc,
 		return ret;
 	}
 
+	if (pdata->dp >= 0)
+		dp = IPU_DP_FLOW_SYNC_BG;
+	ipu_crtc->plane[0] = ipu_plane_init(drm, ipu, pdata->dma[0], dp, 0,
+					    DRM_PLANE_TYPE_PRIMARY);
+	if (IS_ERR(ipu_crtc->plane[0])) {
+		ret = PTR_ERR(ipu_crtc->plane[0]);
+		goto err_put_resources;
+	}
+
 	ret = imx_drm_add_crtc(drm, &ipu_crtc->base, &ipu_crtc->imx_crtc,
-			&ipu_crtc_helper_funcs, ipu_crtc->dev->of_node);
+			&ipu_crtc->plane[0]->base, &ipu_crtc_helper_funcs,
+			ipu_crtc->dev->of_node);
 	if (ret) {
 		dev_err(ipu_crtc->dev, "adding crtc failed with %d.\n", ret);
 		goto err_put_resources;
 	}
 
-	if (pdata->dp >= 0)
-		dp = IPU_DP_FLOW_SYNC_BG;
-	id = imx_drm_crtc_id(ipu_crtc->imx_crtc);
-	ipu_crtc->plane[0] = ipu_plane_init(ipu_crtc->base.dev, ipu,
-					    pdata->dma[0], dp, BIT(id), true);
 	ret = ipu_plane_get_resources(ipu_crtc->plane[0]);
 	if (ret) {
 		dev_err(ipu_crtc->dev, "getting plane 0 resources failed with %d.\n",
@@ -379,10 +384,10 @@ static int ipu_crtc_init(struct ipu_crtc *ipu_crtc,
 
 	/* If this crtc is using the DP, add an overlay plane */
 	if (pdata->dp >= 0 && pdata->dma[1] > 0) {
-		ipu_crtc->plane[1] = ipu_plane_init(ipu_crtc->base.dev, ipu,
-						    pdata->dma[1],
-						    IPU_DP_FLOW_SYNC_FG,
-						    BIT(id), false);
+		ipu_crtc->plane[1] = ipu_plane_init(drm, ipu, pdata->dma[1],
+						IPU_DP_FLOW_SYNC_FG,
+						drm_crtc_mask(&ipu_crtc->base),
+						DRM_PLANE_TYPE_OVERLAY);
 		if (IS_ERR(ipu_crtc->plane[1]))
 			ipu_crtc->plane[1] = NULL;
 	}
@@ -407,28 +412,6 @@ err_put_resources:
 	return ret;
 }
 
-static struct device_node *ipu_drm_get_port_by_id(struct device_node *parent,
-						  int port_id)
-{
-	struct device_node *port;
-	int id, ret;
-
-	port = of_get_child_by_name(parent, "port");
-	while (port) {
-		ret = of_property_read_u32(port, "reg", &id);
-		if (!ret && id == port_id)
-			return port;
-
-		do {
-			port = of_get_next_child(parent, port);
-			if (!port)
-				return NULL;
-		} while (of_node_cmp(port->name, "port"));
-	}
-
-	return NULL;
-}
-
 static int ipu_drm_bind(struct device *dev, struct device *master, void *data)
 {
 	struct ipu_client_platformdata *pdata = dev->platform_data;
@@ -470,23 +453,11 @@ static const struct component_ops ipu_crtc_ops = {
 static int ipu_drm_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct ipu_client_platformdata *pdata = dev->platform_data;
 	int ret;
 
 	if (!dev->platform_data)
 		return -EINVAL;
 
-	if (!dev->of_node) {
-		/* Associate crtc device with the corresponding DI port node */
-		dev->of_node = ipu_drm_get_port_by_id(dev->parent->of_node,
-						      pdata->di + 2);
-		if (!dev->of_node) {
-			dev_err(dev, "missing port@%d node in %s\n",
-				pdata->di + 2, dev->parent->of_node->full_name);
-			return -ENODEV;
-		}
-	}
-
 	ret = dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c
index 575f4c84388f..e2ff410bab74 100644
--- a/drivers/gpu/drm/imx/ipuv3-plane.c
+++ b/drivers/gpu/drm/imx/ipuv3-plane.c
@@ -381,7 +381,7 @@ static struct drm_plane_funcs ipu_plane_funcs = {
 
 struct ipu_plane *ipu_plane_init(struct drm_device *dev, struct ipu_soc *ipu,
 				 int dma, int dp, unsigned int possible_crtcs,
-				 bool priv)
+				 enum drm_plane_type type)
 {
 	struct ipu_plane *ipu_plane;
 	int ret;
@@ -399,10 +399,9 @@ struct ipu_plane *ipu_plane_init(struct drm_device *dev, struct ipu_soc *ipu,
 	ipu_plane->dma = dma;
 	ipu_plane->dp_flow = dp;
 
-	ret = drm_plane_init(dev, &ipu_plane->base, possible_crtcs,
-			     &ipu_plane_funcs, ipu_plane_formats,
-			     ARRAY_SIZE(ipu_plane_formats),
-			     priv);
+	ret = drm_universal_plane_init(dev, &ipu_plane->base, possible_crtcs,
+				       &ipu_plane_funcs, ipu_plane_formats,
+				       ARRAY_SIZE(ipu_plane_formats), type);
 	if (ret) {
 		DRM_ERROR("failed to initialize plane\n");
 		kfree(ipu_plane);
diff --git a/drivers/gpu/drm/imx/ipuv3-plane.h b/drivers/gpu/drm/imx/ipuv3-plane.h
index 9b5eff18f5b8..3a443b413c60 100644
--- a/drivers/gpu/drm/imx/ipuv3-plane.h
+++ b/drivers/gpu/drm/imx/ipuv3-plane.h
@@ -34,7 +34,7 @@ struct ipu_plane {
 
 struct ipu_plane *ipu_plane_init(struct drm_device *dev, struct ipu_soc *ipu,
 				 int dma, int dp, unsigned int possible_crtcs,
-				 bool priv);
+				 enum drm_plane_type type);
 
 /* Init IDMAC, DMFC, DP */
 int ipu_plane_mode_set(struct ipu_plane *plane, struct drm_crtc *crtc,
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index b4deb9cf9d71..2e9b9f1b5cd2 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -54,7 +54,11 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector)
 
 	if (imxpd->panel && imxpd->panel->funcs &&
 	    imxpd->panel->funcs->get_modes) {
+		struct drm_display_info *di = &connector->display_info;
+
 		num_modes = imxpd->panel->funcs->get_modes(imxpd->panel);
+		if (!imxpd->bus_format && di->num_bus_formats)
+			imxpd->bus_format = di->bus_formats[0];
 		if (num_modes > 0)
 			return num_modes;
 	}
diff --git a/drivers/gpu/drm/mgag200/mgag200_cursor.c b/drivers/gpu/drm/mgag200/mgag200_cursor.c
index 4f2068fe5d88..a7bf6a90eae5 100644
--- a/drivers/gpu/drm/mgag200/mgag200_cursor.c
+++ b/drivers/gpu/drm/mgag200/mgag200_cursor.c
@@ -70,6 +70,11 @@ int mga_crtc_cursor_set(struct drm_crtc *crtc,
 	BUG_ON(pixels_2 != pixels_current && pixels_2 != pixels_prev);
 	BUG_ON(pixels_current == pixels_prev);
 
+	if (!handle || !file_priv) {
+		mga_hide_cursor(mdev);
+		return 0;
+	}
+
 	obj = drm_gem_object_lookup(dev, file_priv, handle);
 	if (!obj)
 		return -ENOENT;
@@ -88,12 +93,6 @@ int mga_crtc_cursor_set(struct drm_crtc *crtc,
 		goto out_unreserve1;
 	}
 
-	if (!handle) {
-		mga_hide_cursor(mdev);
-		ret = 0;
-		goto out1;
-	}
-
 	/* Move cursor buffers into VRAM if they aren't already */
 	if (!pixels_1->pin_count) {
 		ret = mgag200_bo_pin(pixels_1, TTM_PL_FLAG_VRAM,
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/instmem.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/instmem.h
index 28bc202f9753..40f845e31272 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/instmem.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/instmem.h
@@ -7,6 +7,7 @@ struct nvkm_instmem {
 	const struct nvkm_instmem_func *func;
 	struct nvkm_subdev subdev;
 
+	spinlock_t lock;
 	struct list_head list;
 	u32 reserved;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index 8b8332e46f24..d5e6938cc6bc 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -367,6 +367,7 @@ static int nouveau_rom_call(acpi_handle rom_handle, uint8_t *bios,
 		return -ENODEV;
 	}
 	obj = (union acpi_object *)buffer.pointer;
+	len = min(len, (int)obj->buffer.length);
 	memcpy(bios+offset, obj->buffer.pointer, len);
 	kfree(buffer.pointer);
 	return len;
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index db6bc6760545..64c8d932d5f1 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -829,7 +829,6 @@ nouveau_finish_page_flip(struct nouveau_channel *chan,
 	struct drm_device *dev = drm->dev;
 	struct nouveau_page_flip_state *s;
 	unsigned long flags;
-	int crtcid = -1;
 
 	spin_lock_irqsave(&dev->event_lock, flags);
 
@@ -841,15 +840,19 @@ nouveau_finish_page_flip(struct nouveau_channel *chan,
 
 	s = list_first_entry(&fctx->flip, struct nouveau_page_flip_state, head);
 	if (s->event) {
-		/* Vblank timestamps/counts are only correct on >= NV-50 */
-		if (drm->device.info.family >= NV_DEVICE_INFO_V0_TESLA)
-			crtcid = s->crtc;
+		if (drm->device.info.family < NV_DEVICE_INFO_V0_TESLA) {
+			drm_arm_vblank_event(dev, s->crtc, s->event);
+		} else {
+			drm_send_vblank_event(dev, s->crtc, s->event);
 
-		drm_send_vblank_event(dev, crtcid, s->event);
+			/* Give up ownership of vblank for page-flipped crtc */
+			drm_vblank_put(dev, s->crtc);
+		}
+	}
+	else {
+		/* Give up ownership of vblank for page-flipped crtc */
+		drm_vblank_put(dev, s->crtc);
 	}
-
-	/* Give up ownership of vblank for page-flipped crtc */
-	drm_vblank_put(dev, s->crtc);
 
 	list_del(&s->head);
 	if (ps)
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.h b/drivers/gpu/drm/nouveau/nouveau_drm.h
index 3050042e6c6d..a02813e994ec 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.h
@@ -39,6 +39,7 @@
 
 #include <nvif/client.h>
 #include <nvif/device.h>
+#include <nvif/ioctl.h>
 
 #include <drmP.h>
 
@@ -65,9 +66,10 @@ struct nouveau_drm_tile {
 };
 
 enum nouveau_drm_object_route {
-	NVDRM_OBJECT_NVIF = 0,
+	NVDRM_OBJECT_NVIF = NVIF_IOCTL_V0_OWNER_NVIF,
 	NVDRM_OBJECT_USIF,
 	NVDRM_OBJECT_ABI16,
+	NVDRM_OBJECT_ANY = NVIF_IOCTL_V0_OWNER_ANY,
 };
 
 enum nouveau_drm_notify_route {
diff --git a/drivers/gpu/drm/nouveau/nouveau_usif.c b/drivers/gpu/drm/nouveau/nouveau_usif.c
index 89dc4ce63490..6ae1b3494bcd 100644
--- a/drivers/gpu/drm/nouveau/nouveau_usif.c
+++ b/drivers/gpu/drm/nouveau/nouveau_usif.c
@@ -313,7 +313,10 @@ usif_ioctl(struct drm_file *filp, void __user *user, u32 argc)
 	if (nvif_unpack(argv->v0, 0, 0, true)) {
 		/* block access to objects not created via this interface */
 		owner = argv->v0.owner;
-		argv->v0.owner = NVDRM_OBJECT_USIF;
+		if (argv->v0.object == 0ULL)
+			argv->v0.owner = NVDRM_OBJECT_ANY; /* except client */
+		else
+			argv->v0.owner = NVDRM_OBJECT_USIF;
 	} else
 		goto done;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c
index e3c783d0e2ab..caf22b589edc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c
@@ -279,6 +279,12 @@ nvkm_device_pci_10de_0fe3[] = {
 };
 
 static const struct nvkm_device_pci_vendor
+nvkm_device_pci_10de_0fe4[] = {
+	{ 0x144d, 0xc740, NULL, { .War00C800_0 = true } },
+	{}
+};
+
+static const struct nvkm_device_pci_vendor
 nvkm_device_pci_10de_104b[] = {
 	{ 0x1043, 0x844c, "GeForce GT 625" },
 	{ 0x1043, 0x846b, "GeForce GT 625" },
@@ -689,6 +695,12 @@ nvkm_device_pci_10de_1199[] = {
 };
 
 static const struct nvkm_device_pci_vendor
+nvkm_device_pci_10de_11e0[] = {
+	{ 0x1558, 0x5106, NULL, { .War00C800_0 = true } },
+	{}
+};
+
+static const struct nvkm_device_pci_vendor
 nvkm_device_pci_10de_11e3[] = {
 	{ 0x17aa, 0x3683, "GeForce GTX 760A" },
 	{}
@@ -1370,7 +1382,7 @@ nvkm_device_pci_10de[] = {
 	{ 0x0fe1, "GeForce GT 730M" },
 	{ 0x0fe2, "GeForce GT 745M" },
 	{ 0x0fe3, "GeForce GT 745M", nvkm_device_pci_10de_0fe3 },
-	{ 0x0fe4, "GeForce GT 750M" },
+	{ 0x0fe4, "GeForce GT 750M", nvkm_device_pci_10de_0fe4 },
 	{ 0x0fe9, "GeForce GT 750M" },
 	{ 0x0fea, "GeForce GT 755M" },
 	{ 0x0fec, "GeForce 710A" },
@@ -1485,7 +1497,7 @@ nvkm_device_pci_10de[] = {
 	{ 0x11c6, "GeForce GTX 650 Ti" },
 	{ 0x11c8, "GeForce GTX 650" },
 	{ 0x11cb, "GeForce GT 740" },
-	{ 0x11e0, "GeForce GTX 770M" },
+	{ 0x11e0, "GeForce GTX 770M", nvkm_device_pci_10de_11e0 },
 	{ 0x11e1, "GeForce GTX 765M" },
 	{ 0x11e2, "GeForce GTX 765M" },
 	{ 0x11e3, "GeForce GTX 760M", nvkm_device_pci_10de_11e3 },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c
index b5b875928aba..74de7a96c22a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c
@@ -207,6 +207,8 @@ gf117_grctx_generate_attrib(struct gf100_grctx *info)
 			const u32 b =  beta * gr->ppc_tpc_nr[gpc][ppc];
 			const u32 t = timeslice_mode;
 			const u32 o = PPC_UNIT(gpc, ppc, 0);
+			if (!(gr->ppc_mask[gpc] & (1 << ppc)))
+				continue;
 			mmio_skip(info, o + 0xc0, (t << 28) | (b << 16) | ++bo);
 			mmio_wr32(info, o + 0xc0, (t << 28) | (b << 16) | --bo);
 			bo += grctx->attrib_nr_max * gr->ppc_tpc_nr[gpc][ppc];
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpc.fuc b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpc.fuc
index 194afe910d21..7dacb3cc0668 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpc.fuc
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpc.fuc
@@ -52,10 +52,12 @@ mmio_list_base:
 #endif
 
 #ifdef INCLUDE_CODE
+#define gpc_addr(reg,addr)                                                    /*
+*/	imm32(reg,addr)                                                       /*
+*/	or reg NV_PGRAPH_GPCX_GPCCS_MMIO_CTRL_BASE_ENABLE
 #define gpc_wr32(addr,reg)                                                    /*
+*/	gpc_addr($r14,addr)                                                   /*
 */	mov b32 $r15 reg                                                      /*
-*/	imm32($r14, addr)                                                     /*
-*/	or $r14 NV_PGRAPH_GPCX_GPCCS_MMIO_CTRL_BASE_ENABLE                    /*
 */	call(nv_wr32)
 
 // reports an exception to the host
@@ -161,7 +163,7 @@ init:
 
 #if NV_PGRAPH_GPCX_UNK__SIZE > 0
 	// figure out which, and how many, UNKs are actually present
-	imm32($r14, 0x500c30)
+	gpc_addr($r14, 0x500c30)
 	clear b32 $r2
 	clear b32 $r3
 	clear b32 $r4
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgf117.fuc3.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgf117.fuc3.h
index 64d07df4b8b1..bb820ff28621 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgf117.fuc3.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgf117.fuc3.h
@@ -314,7 +314,7 @@ uint32_t gf117_grgpc_code[] = {
 	0x03f01200,
 	0x0002d000,
 	0x17f104bd,
-	0x10fe0542,
+	0x10fe0545,
 	0x0007f100,
 	0x0003f007,
 	0xbd0000d0,
@@ -338,184 +338,184 @@ uint32_t gf117_grgpc_code[] = {
 	0x02d00103,
 	0xf104bd00,
 	0xf00c30e7,
-	0x24bd50e3,
-	0x44bd34bd,
-/* 0x0430: init_unk_loop */
-	0xb06821f4,
-	0x0bf400f6,
-	0x01f7f00f,
-	0xfd04f2bb,
-	0x30b6054f,
-/* 0x0445: init_unk_next */
-	0x0120b601,
-	0xb004e0b6,
-	0x1bf40126,
-/* 0x0451: init_unk_done */
-	0x070380e2,
-	0xf1080480,
-	0xf0010027,
-	0x22cf0223,
-	0x9534bd00,
-	0x07f10825,
-	0x03f0c000,
-	0x0005d001,
-	0x07f104bd,
-	0x03f0c100,
-	0x0005d001,
-	0x0e9804bd,
-	0x010f9800,
-	0x015021f5,
-	0xbb002fbb,
-	0x0e98003f,
-	0x020f9801,
-	0x015021f5,
-	0xfd050e98,
-	0x2ebb00ef,
-	0x003ebb00,
-	0x98020e98,
-	0x21f5030f,
-	0x0e980150,
-	0x00effd07,
-	0xbb002ebb,
-	0x35b6003e,
-	0x0007f102,
-	0x0103f0d3,
-	0xbd0003d0,
-	0x0825b604,
-	0xb60635b6,
-	0x30b60120,
-	0x0824b601,
-	0xb90834b6,
-	0x21f5022f,
-	0x2fbb02d3,
-	0x003fbb00,
-	0x010007f1,
-	0xd00203f0,
+	0xe5f050e3,
+	0xbd24bd01,
+/* 0x0433: init_unk_loop */
+	0xf444bd34,
+	0xf6b06821,
+	0x0f0bf400,
+	0xbb01f7f0,
+	0x4ffd04f2,
+	0x0130b605,
+/* 0x0448: init_unk_next */
+	0xb60120b6,
+	0x26b004e0,
+	0xe21bf401,
+/* 0x0454: init_unk_done */
+	0x80070380,
+	0x27f10804,
+	0x23f00100,
+	0x0022cf02,
+	0x259534bd,
+	0x0007f108,
+	0x0103f0c0,
+	0xbd0005d0,
+	0x0007f104,
+	0x0103f0c1,
+	0xbd0005d0,
+	0x000e9804,
+	0xf5010f98,
+	0xbb015021,
+	0x3fbb002f,
+	0x010e9800,
+	0xf5020f98,
+	0x98015021,
+	0xeffd050e,
+	0x002ebb00,
+	0x98003ebb,
+	0x0f98020e,
+	0x5021f503,
+	0x070e9801,
+	0xbb00effd,
+	0x3ebb002e,
+	0x0235b600,
+	0xd30007f1,
+	0xd00103f0,
 	0x04bd0003,
-	0x29f024bd,
-	0x0007f11f,
-	0x0203f008,
-	0xbd0002d0,
-/* 0x0505: main */
-	0x0031f404,
-	0xf00028f4,
-	0x21f424d7,
-	0xf401f439,
-	0xf404e4b0,
-	0x81fe1e18,
-	0x0627f001,
-	0x12fd20bd,
-	0x01e4b604,
-	0xfe051efd,
-	0x21f50018,
-	0x0ef405fa,
-/* 0x0535: main_not_ctx_xfer */
-	0x10ef94d3,
-	0xf501f5f0,
-	0xf4037e21,
-/* 0x0542: ih */
-	0x80f9c60e,
-	0xf90188fe,
-	0xf990f980,
-	0xf9b0f9a0,
-	0xf9e0f9d0,
-	0xf104bdf0,
-	0xf00200a7,
-	0xaacf00a3,
-	0x04abc400,
-	0xf02c0bf4,
-	0xe7f124d7,
-	0xe3f01a00,
-	0x00eecf00,
-	0x1900f7f1,
-	0xcf00f3f0,
-	0x21f400ff,
-	0x01e7f004,
-	0x1d0007f1,
-	0xd00003f0,
-	0x04bd000e,
-/* 0x0590: ih_no_fifo */
-	0x010007f1,
-	0xd00003f0,
-	0x04bd000a,
-	0xe0fcf0fc,
-	0xb0fcd0fc,
-	0x90fca0fc,
-	0x88fe80fc,
-	0xf480fc00,
-	0x01f80032,
-/* 0x05b4: hub_barrier_done */
-	0x9801f7f0,
-	0xfebb040e,
-	0x02ffb904,
-	0x9418e7f1,
-	0xf440e3f0,
-	0x00f89d21,
-/* 0x05cc: ctx_redswitch */
-	0xf120f7f0,
+	0xb60825b6,
+	0x20b60635,
+	0x0130b601,
+	0xb60824b6,
+	0x2fb90834,
+	0xd321f502,
+	0x002fbb02,
+	0xf1003fbb,
+	0xf0010007,
+	0x03d00203,
+	0xbd04bd00,
+	0x1f29f024,
+	0x080007f1,
+	0xd00203f0,
+	0x04bd0002,
+/* 0x0508: main */
+	0xf40031f4,
+	0xd7f00028,
+	0x3921f424,
+	0xb0f401f4,
+	0x18f404e4,
+	0x0181fe1e,
+	0xbd0627f0,
+	0x0412fd20,
+	0xfd01e4b6,
+	0x18fe051e,
+	0xfd21f500,
+	0xd30ef405,
+/* 0x0538: main_not_ctx_xfer */
+	0xf010ef94,
+	0x21f501f5,
+	0x0ef4037e,
+/* 0x0545: ih */
+	0xfe80f9c6,
+	0x80f90188,
+	0xa0f990f9,
+	0xd0f9b0f9,
+	0xf0f9e0f9,
+	0xa7f104bd,
+	0xa3f00200,
+	0x00aacf00,
+	0xf404abc4,
+	0xd7f02c0b,
+	0x00e7f124,
+	0x00e3f01a,
+	0xf100eecf,
+	0xf01900f7,
+	0xffcf00f3,
+	0x0421f400,
+	0xf101e7f0,
+	0xf01d0007,
+	0x0ed00003,
+/* 0x0593: ih_no_fifo */
+	0xf104bd00,
+	0xf0010007,
+	0x0ad00003,
+	0xfc04bd00,
+	0xfce0fcf0,
+	0xfcb0fcd0,
+	0xfc90fca0,
+	0x0088fe80,
+	0x32f480fc,
+/* 0x05b7: hub_barrier_done */
+	0xf001f800,
+	0x0e9801f7,
+	0x04febb04,
+	0xf102ffb9,
+	0xf09418e7,
+	0x21f440e3,
+/* 0x05cf: ctx_redswitch */
+	0xf000f89d,
+	0x07f120f7,
+	0x03f08500,
+	0x000fd001,
+	0xe7f004bd,
+/* 0x05e1: ctx_redswitch_delay */
+	0x01e2b608,
+	0xf1fd1bf4,
+	0xf10800f5,
+	0xf10200f5,
 	0xf0850007,
 	0x0fd00103,
-	0xf004bd00,
-/* 0x05de: ctx_redswitch_delay */
-	0xe2b608e7,
-	0xfd1bf401,
-	0x0800f5f1,
-	0x0200f5f1,
-	0x850007f1,
-	0xd00103f0,
-	0x04bd000f,
-/* 0x05fa: ctx_xfer */
-	0x07f100f8,
-	0x03f08100,
-	0x000fd002,
-	0x11f404bd,
-	0xcc21f507,
-/* 0x060d: ctx_xfer_not_load */
-	0x6a21f505,
-	0xf124bd02,
-	0xf047fc07,
-	0x02d00203,
-	0xf004bd00,
-	0x20b6012c,
-	0xfc07f103,
-	0x0203f04a,
-	0xbd0002d0,
-	0x01acf004,
-	0xf102a5f0,
-	0xf00000b7,
-	0x0c9850b3,
-	0x0fc4b604,
-	0x9800bcbb,
-	0x0d98000c,
-	0x00e7f001,
-	0x016f21f5,
-	0xf101acf0,
-	0xf04000b7,
-	0x0c9850b3,
-	0x0fc4b604,
-	0x9800bcbb,
-	0x0d98010c,
-	0x060f9802,
-	0x0800e7f1,
-	0x016f21f5,
+	0xf804bd00,
+/* 0x05fd: ctx_xfer */
+	0x0007f100,
+	0x0203f081,
+	0xbd000fd0,
+	0x0711f404,
+	0x05cf21f5,
+/* 0x0610: ctx_xfer_not_load */
+	0x026a21f5,
+	0x07f124bd,
+	0x03f047fc,
+	0x0002d002,
+	0x2cf004bd,
+	0x0320b601,
+	0x4afc07f1,
+	0xd00203f0,
+	0x04bd0002,
 	0xf001acf0,
-	0xb7f104a5,
-	0xb3f03000,
+	0xb7f102a5,
+	0xb3f00000,
 	0x040c9850,
 	0xbb0fc4b6,
 	0x0c9800bc,
-	0x030d9802,
-	0xf1080f98,
-	0xf50200e7,
-	0xf5016f21,
-	0xf4025e21,
-	0x12f40601,
-/* 0x06a9: ctx_xfer_post */
-	0x7f21f507,
-/* 0x06ad: ctx_xfer_done */
-	0xb421f502,
-	0x0000f805,
-	0x00000000,
+	0x010d9800,
+	0xf500e7f0,
+	0xf0016f21,
+	0xb7f101ac,
+	0xb3f04000,
+	0x040c9850,
+	0xbb0fc4b6,
+	0x0c9800bc,
+	0x020d9801,
+	0xf1060f98,
+	0xf50800e7,
+	0xf0016f21,
+	0xa5f001ac,
+	0x00b7f104,
+	0x50b3f030,
+	0xb6040c98,
+	0xbcbb0fc4,
+	0x020c9800,
+	0x98030d98,
+	0xe7f1080f,
+	0x21f50200,
+	0x21f5016f,
+	0x01f4025e,
+	0x0712f406,
+/* 0x06ac: ctx_xfer_post */
+	0x027f21f5,
+/* 0x06b0: ctx_xfer_done */
+	0x05b721f5,
+	0x000000f8,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk104.fuc3.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk104.fuc3.h
index 2f596433c222..911976d20940 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk104.fuc3.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk104.fuc3.h
@@ -314,7 +314,7 @@ uint32_t gk104_grgpc_code[] = {
 	0x03f01200,
 	0x0002d000,
 	0x17f104bd,
-	0x10fe0542,
+	0x10fe0545,
 	0x0007f100,
 	0x0003f007,
 	0xbd0000d0,
@@ -338,184 +338,184 @@ uint32_t gk104_grgpc_code[] = {
 	0x02d00103,
 	0xf104bd00,
 	0xf00c30e7,
-	0x24bd50e3,
-	0x44bd34bd,
-/* 0x0430: init_unk_loop */
-	0xb06821f4,
-	0x0bf400f6,
-	0x01f7f00f,
-	0xfd04f2bb,
-	0x30b6054f,
-/* 0x0445: init_unk_next */
-	0x0120b601,
-	0xb004e0b6,
-	0x1bf40126,
-/* 0x0451: init_unk_done */
-	0x070380e2,
-	0xf1080480,
-	0xf0010027,
-	0x22cf0223,
-	0x9534bd00,
-	0x07f10825,
-	0x03f0c000,
-	0x0005d001,
-	0x07f104bd,
-	0x03f0c100,
-	0x0005d001,
-	0x0e9804bd,
-	0x010f9800,
-	0x015021f5,
-	0xbb002fbb,
-	0x0e98003f,
-	0x020f9801,
-	0x015021f5,
-	0xfd050e98,
-	0x2ebb00ef,
-	0x003ebb00,
-	0x98020e98,
-	0x21f5030f,
-	0x0e980150,
-	0x00effd07,
-	0xbb002ebb,
-	0x35b6003e,
-	0x0007f102,
-	0x0103f0d3,
-	0xbd0003d0,
-	0x0825b604,
-	0xb60635b6,
-	0x30b60120,
-	0x0824b601,
-	0xb90834b6,
-	0x21f5022f,
-	0x2fbb02d3,
-	0x003fbb00,
-	0x010007f1,
-	0xd00203f0,
+	0xe5f050e3,
+	0xbd24bd01,
+/* 0x0433: init_unk_loop */
+	0xf444bd34,
+	0xf6b06821,
+	0x0f0bf400,
+	0xbb01f7f0,
+	0x4ffd04f2,
+	0x0130b605,
+/* 0x0448: init_unk_next */
+	0xb60120b6,
+	0x26b004e0,
+	0xe21bf401,
+/* 0x0454: init_unk_done */
+	0x80070380,
+	0x27f10804,
+	0x23f00100,
+	0x0022cf02,
+	0x259534bd,
+	0x0007f108,
+	0x0103f0c0,
+	0xbd0005d0,
+	0x0007f104,
+	0x0103f0c1,
+	0xbd0005d0,
+	0x000e9804,
+	0xf5010f98,
+	0xbb015021,
+	0x3fbb002f,
+	0x010e9800,
+	0xf5020f98,
+	0x98015021,
+	0xeffd050e,
+	0x002ebb00,
+	0x98003ebb,
+	0x0f98020e,
+	0x5021f503,
+	0x070e9801,
+	0xbb00effd,
+	0x3ebb002e,
+	0x0235b600,
+	0xd30007f1,
+	0xd00103f0,
 	0x04bd0003,
-	0x29f024bd,
-	0x0007f11f,
-	0x0203f008,
-	0xbd0002d0,
-/* 0x0505: main */
-	0x0031f404,
-	0xf00028f4,
-	0x21f424d7,
-	0xf401f439,
-	0xf404e4b0,
-	0x81fe1e18,
-	0x0627f001,
-	0x12fd20bd,
-	0x01e4b604,
-	0xfe051efd,
-	0x21f50018,
-	0x0ef405fa,
-/* 0x0535: main_not_ctx_xfer */
-	0x10ef94d3,
-	0xf501f5f0,
-	0xf4037e21,
-/* 0x0542: ih */
-	0x80f9c60e,
-	0xf90188fe,
-	0xf990f980,
-	0xf9b0f9a0,
-	0xf9e0f9d0,
-	0xf104bdf0,
-	0xf00200a7,
-	0xaacf00a3,
-	0x04abc400,
-	0xf02c0bf4,
-	0xe7f124d7,
-	0xe3f01a00,
-	0x00eecf00,
-	0x1900f7f1,
-	0xcf00f3f0,
-	0x21f400ff,
-	0x01e7f004,
-	0x1d0007f1,
-	0xd00003f0,
-	0x04bd000e,
-/* 0x0590: ih_no_fifo */
-	0x010007f1,
-	0xd00003f0,
-	0x04bd000a,
-	0xe0fcf0fc,
-	0xb0fcd0fc,
-	0x90fca0fc,
-	0x88fe80fc,
-	0xf480fc00,
-	0x01f80032,
-/* 0x05b4: hub_barrier_done */
-	0x9801f7f0,
-	0xfebb040e,
-	0x02ffb904,
-	0x9418e7f1,
-	0xf440e3f0,
-	0x00f89d21,
-/* 0x05cc: ctx_redswitch */
-	0xf120f7f0,
+	0xb60825b6,
+	0x20b60635,
+	0x0130b601,
+	0xb60824b6,
+	0x2fb90834,
+	0xd321f502,
+	0x002fbb02,
+	0xf1003fbb,
+	0xf0010007,
+	0x03d00203,
+	0xbd04bd00,
+	0x1f29f024,
+	0x080007f1,
+	0xd00203f0,
+	0x04bd0002,
+/* 0x0508: main */
+	0xf40031f4,
+	0xd7f00028,
+	0x3921f424,
+	0xb0f401f4,
+	0x18f404e4,
+	0x0181fe1e,
+	0xbd0627f0,
+	0x0412fd20,
+	0xfd01e4b6,
+	0x18fe051e,
+	0xfd21f500,
+	0xd30ef405,
+/* 0x0538: main_not_ctx_xfer */
+	0xf010ef94,
+	0x21f501f5,
+	0x0ef4037e,
+/* 0x0545: ih */
+	0xfe80f9c6,
+	0x80f90188,
+	0xa0f990f9,
+	0xd0f9b0f9,
+	0xf0f9e0f9,
+	0xa7f104bd,
+	0xa3f00200,
+	0x00aacf00,
+	0xf404abc4,
+	0xd7f02c0b,
+	0x00e7f124,
+	0x00e3f01a,
+	0xf100eecf,
+	0xf01900f7,
+	0xffcf00f3,
+	0x0421f400,
+	0xf101e7f0,
+	0xf01d0007,
+	0x0ed00003,
+/* 0x0593: ih_no_fifo */
+	0xf104bd00,
+	0xf0010007,
+	0x0ad00003,
+	0xfc04bd00,
+	0xfce0fcf0,
+	0xfcb0fcd0,
+	0xfc90fca0,
+	0x0088fe80,
+	0x32f480fc,
+/* 0x05b7: hub_barrier_done */
+	0xf001f800,
+	0x0e9801f7,
+	0x04febb04,
+	0xf102ffb9,
+	0xf09418e7,
+	0x21f440e3,
+/* 0x05cf: ctx_redswitch */
+	0xf000f89d,
+	0x07f120f7,
+	0x03f08500,
+	0x000fd001,
+	0xe7f004bd,
+/* 0x05e1: ctx_redswitch_delay */
+	0x01e2b608,
+	0xf1fd1bf4,
+	0xf10800f5,
+	0xf10200f5,
 	0xf0850007,
 	0x0fd00103,
-	0xf004bd00,
-/* 0x05de: ctx_redswitch_delay */
-	0xe2b608e7,
-	0xfd1bf401,
-	0x0800f5f1,
-	0x0200f5f1,
-	0x850007f1,
-	0xd00103f0,
-	0x04bd000f,
-/* 0x05fa: ctx_xfer */
-	0x07f100f8,
-	0x03f08100,
-	0x000fd002,
-	0x11f404bd,
-	0xcc21f507,
-/* 0x060d: ctx_xfer_not_load */
-	0x6a21f505,
-	0xf124bd02,
-	0xf047fc07,
-	0x02d00203,
-	0xf004bd00,
-	0x20b6012c,
-	0xfc07f103,
-	0x0203f04a,
-	0xbd0002d0,
-	0x01acf004,
-	0xf102a5f0,
-	0xf00000b7,
-	0x0c9850b3,
-	0x0fc4b604,
-	0x9800bcbb,
-	0x0d98000c,
-	0x00e7f001,
-	0x016f21f5,
-	0xf101acf0,
-	0xf04000b7,
-	0x0c9850b3,
-	0x0fc4b604,
-	0x9800bcbb,
-	0x0d98010c,
-	0x060f9802,
-	0x0800e7f1,
-	0x016f21f5,
+	0xf804bd00,
+/* 0x05fd: ctx_xfer */
+	0x0007f100,
+	0x0203f081,
+	0xbd000fd0,
+	0x0711f404,
+	0x05cf21f5,
+/* 0x0610: ctx_xfer_not_load */
+	0x026a21f5,
+	0x07f124bd,
+	0x03f047fc,
+	0x0002d002,
+	0x2cf004bd,
+	0x0320b601,
+	0x4afc07f1,
+	0xd00203f0,
+	0x04bd0002,
 	0xf001acf0,
-	0xb7f104a5,
-	0xb3f03000,
+	0xb7f102a5,
+	0xb3f00000,
 	0x040c9850,
 	0xbb0fc4b6,
 	0x0c9800bc,
-	0x030d9802,
-	0xf1080f98,
-	0xf50200e7,
-	0xf5016f21,
-	0xf4025e21,
-	0x12f40601,
-/* 0x06a9: ctx_xfer_post */
-	0x7f21f507,
-/* 0x06ad: ctx_xfer_done */
-	0xb421f502,
-	0x0000f805,
-	0x00000000,
+	0x010d9800,
+	0xf500e7f0,
+	0xf0016f21,
+	0xb7f101ac,
+	0xb3f04000,
+	0x040c9850,
+	0xbb0fc4b6,
+	0x0c9800bc,
+	0x020d9801,
+	0xf1060f98,
+	0xf50800e7,
+	0xf0016f21,
+	0xa5f001ac,
+	0x00b7f104,
+	0x50b3f030,
+	0xb6040c98,
+	0xbcbb0fc4,
+	0x020c9800,
+	0x98030d98,
+	0xe7f1080f,
+	0x21f50200,
+	0x21f5016f,
+	0x01f4025e,
+	0x0712f406,
+/* 0x06ac: ctx_xfer_post */
+	0x027f21f5,
+/* 0x06b0: ctx_xfer_done */
+	0x05b721f5,
+	0x000000f8,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk110.fuc3.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk110.fuc3.h
index ee8e54db8fc9..1c6e11b05df2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk110.fuc3.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk110.fuc3.h
@@ -314,7 +314,7 @@ uint32_t gk110_grgpc_code[] = {
 	0x03f01200,
 	0x0002d000,
 	0x17f104bd,
-	0x10fe0542,
+	0x10fe0545,
 	0x0007f100,
 	0x0003f007,
 	0xbd0000d0,
@@ -338,184 +338,184 @@ uint32_t gk110_grgpc_code[] = {
 	0x02d00103,
 	0xf104bd00,
 	0xf00c30e7,
-	0x24bd50e3,
-	0x44bd34bd,
-/* 0x0430: init_unk_loop */
-	0xb06821f4,
-	0x0bf400f6,
-	0x01f7f00f,
-	0xfd04f2bb,
-	0x30b6054f,
-/* 0x0445: init_unk_next */
-	0x0120b601,
-	0xb004e0b6,
-	0x1bf40226,
-/* 0x0451: init_unk_done */
-	0x070380e2,
-	0xf1080480,
-	0xf0010027,
-	0x22cf0223,
-	0x9534bd00,
-	0x07f10825,
-	0x03f0c000,
-	0x0005d001,
-	0x07f104bd,
-	0x03f0c100,
-	0x0005d001,
-	0x0e9804bd,
-	0x010f9800,
-	0x015021f5,
-	0xbb002fbb,
-	0x0e98003f,
-	0x020f9801,
-	0x015021f5,
-	0xfd050e98,
-	0x2ebb00ef,
-	0x003ebb00,
-	0x98020e98,
-	0x21f5030f,
-	0x0e980150,
-	0x00effd07,
-	0xbb002ebb,
-	0x35b6003e,
-	0x0007f102,
-	0x0103f0d3,
-	0xbd0003d0,
-	0x0825b604,
-	0xb60635b6,
-	0x30b60120,
-	0x0824b601,
-	0xb90834b6,
-	0x21f5022f,
-	0x2fbb02d3,
-	0x003fbb00,
-	0x010007f1,
-	0xd00203f0,
+	0xe5f050e3,
+	0xbd24bd01,
+/* 0x0433: init_unk_loop */
+	0xf444bd34,
+	0xf6b06821,
+	0x0f0bf400,
+	0xbb01f7f0,
+	0x4ffd04f2,
+	0x0130b605,
+/* 0x0448: init_unk_next */
+	0xb60120b6,
+	0x26b004e0,
+	0xe21bf402,
+/* 0x0454: init_unk_done */
+	0x80070380,
+	0x27f10804,
+	0x23f00100,
+	0x0022cf02,
+	0x259534bd,
+	0x0007f108,
+	0x0103f0c0,
+	0xbd0005d0,
+	0x0007f104,
+	0x0103f0c1,
+	0xbd0005d0,
+	0x000e9804,
+	0xf5010f98,
+	0xbb015021,
+	0x3fbb002f,
+	0x010e9800,
+	0xf5020f98,
+	0x98015021,
+	0xeffd050e,
+	0x002ebb00,
+	0x98003ebb,
+	0x0f98020e,
+	0x5021f503,
+	0x070e9801,
+	0xbb00effd,
+	0x3ebb002e,
+	0x0235b600,
+	0xd30007f1,
+	0xd00103f0,
 	0x04bd0003,
-	0x29f024bd,
-	0x0007f11f,
-	0x0203f030,
-	0xbd0002d0,
-/* 0x0505: main */
-	0x0031f404,
-	0xf00028f4,
-	0x21f424d7,
-	0xf401f439,
-	0xf404e4b0,
-	0x81fe1e18,
-	0x0627f001,
-	0x12fd20bd,
-	0x01e4b604,
-	0xfe051efd,
-	0x21f50018,
-	0x0ef405fa,
-/* 0x0535: main_not_ctx_xfer */
-	0x10ef94d3,
-	0xf501f5f0,
-	0xf4037e21,
-/* 0x0542: ih */
-	0x80f9c60e,
-	0xf90188fe,
-	0xf990f980,
-	0xf9b0f9a0,
-	0xf9e0f9d0,
-	0xf104bdf0,
-	0xf00200a7,
-	0xaacf00a3,
-	0x04abc400,
-	0xf02c0bf4,
-	0xe7f124d7,
-	0xe3f01a00,
-	0x00eecf00,
-	0x1900f7f1,
-	0xcf00f3f0,
-	0x21f400ff,
-	0x01e7f004,
-	0x1d0007f1,
-	0xd00003f0,
-	0x04bd000e,
-/* 0x0590: ih_no_fifo */
-	0x010007f1,
-	0xd00003f0,
-	0x04bd000a,
-	0xe0fcf0fc,
-	0xb0fcd0fc,
-	0x90fca0fc,
-	0x88fe80fc,
-	0xf480fc00,
-	0x01f80032,
-/* 0x05b4: hub_barrier_done */
-	0x9801f7f0,
-	0xfebb040e,
-	0x02ffb904,
-	0x9418e7f1,
-	0xf440e3f0,
-	0x00f89d21,
-/* 0x05cc: ctx_redswitch */
-	0xf120f7f0,
+	0xb60825b6,
+	0x20b60635,
+	0x0130b601,
+	0xb60824b6,
+	0x2fb90834,
+	0xd321f502,
+	0x002fbb02,
+	0xf1003fbb,
+	0xf0010007,
+	0x03d00203,
+	0xbd04bd00,
+	0x1f29f024,
+	0x300007f1,
+	0xd00203f0,
+	0x04bd0002,
+/* 0x0508: main */
+	0xf40031f4,
+	0xd7f00028,
+	0x3921f424,
+	0xb0f401f4,
+	0x18f404e4,
+	0x0181fe1e,
+	0xbd0627f0,
+	0x0412fd20,
+	0xfd01e4b6,
+	0x18fe051e,
+	0xfd21f500,
+	0xd30ef405,
+/* 0x0538: main_not_ctx_xfer */
+	0xf010ef94,
+	0x21f501f5,
+	0x0ef4037e,
+/* 0x0545: ih */
+	0xfe80f9c6,
+	0x80f90188,
+	0xa0f990f9,
+	0xd0f9b0f9,
+	0xf0f9e0f9,
+	0xa7f104bd,
+	0xa3f00200,
+	0x00aacf00,
+	0xf404abc4,
+	0xd7f02c0b,
+	0x00e7f124,
+	0x00e3f01a,
+	0xf100eecf,
+	0xf01900f7,
+	0xffcf00f3,
+	0x0421f400,
+	0xf101e7f0,
+	0xf01d0007,
+	0x0ed00003,
+/* 0x0593: ih_no_fifo */
+	0xf104bd00,
+	0xf0010007,
+	0x0ad00003,
+	0xfc04bd00,
+	0xfce0fcf0,
+	0xfcb0fcd0,
+	0xfc90fca0,
+	0x0088fe80,
+	0x32f480fc,
+/* 0x05b7: hub_barrier_done */
+	0xf001f800,
+	0x0e9801f7,
+	0x04febb04,
+	0xf102ffb9,
+	0xf09418e7,
+	0x21f440e3,
+/* 0x05cf: ctx_redswitch */
+	0xf000f89d,
+	0x07f120f7,
+	0x03f08500,
+	0x000fd001,
+	0xe7f004bd,
+/* 0x05e1: ctx_redswitch_delay */
+	0x01e2b608,
+	0xf1fd1bf4,
+	0xf10800f5,
+	0xf10200f5,
 	0xf0850007,
 	0x0fd00103,
-	0xf004bd00,
-/* 0x05de: ctx_redswitch_delay */
-	0xe2b608e7,
-	0xfd1bf401,
-	0x0800f5f1,
-	0x0200f5f1,
-	0x850007f1,
-	0xd00103f0,
-	0x04bd000f,
-/* 0x05fa: ctx_xfer */
-	0x07f100f8,
-	0x03f08100,
-	0x000fd002,
-	0x11f404bd,
-	0xcc21f507,
-/* 0x060d: ctx_xfer_not_load */
-	0x6a21f505,
-	0xf124bd02,
-	0xf047fc07,
-	0x02d00203,
-	0xf004bd00,
-	0x20b6012c,
-	0xfc07f103,
-	0x0203f04a,
-	0xbd0002d0,
-	0x01acf004,
-	0xf102a5f0,
-	0xf00000b7,
-	0x0c9850b3,
-	0x0fc4b604,
-	0x9800bcbb,
-	0x0d98000c,
-	0x00e7f001,
-	0x016f21f5,
-	0xf101acf0,
-	0xf04000b7,
-	0x0c9850b3,
-	0x0fc4b604,
-	0x9800bcbb,
-	0x0d98010c,
-	0x060f9802,
-	0x0800e7f1,
-	0x016f21f5,
+	0xf804bd00,
+/* 0x05fd: ctx_xfer */
+	0x0007f100,
+	0x0203f081,
+	0xbd000fd0,
+	0x0711f404,
+	0x05cf21f5,
+/* 0x0610: ctx_xfer_not_load */
+	0x026a21f5,
+	0x07f124bd,
+	0x03f047fc,
+	0x0002d002,
+	0x2cf004bd,
+	0x0320b601,
+	0x4afc07f1,
+	0xd00203f0,
+	0x04bd0002,
 	0xf001acf0,
-	0xb7f104a5,
-	0xb3f03000,
+	0xb7f102a5,
+	0xb3f00000,
 	0x040c9850,
 	0xbb0fc4b6,
 	0x0c9800bc,
-	0x030d9802,
-	0xf1080f98,
-	0xf50200e7,
-	0xf5016f21,
-	0xf4025e21,
-	0x12f40601,
-/* 0x06a9: ctx_xfer_post */
-	0x7f21f507,
-/* 0x06ad: ctx_xfer_done */
-	0xb421f502,
-	0x0000f805,
-	0x00000000,
+	0x010d9800,
+	0xf500e7f0,
+	0xf0016f21,
+	0xb7f101ac,
+	0xb3f04000,
+	0x040c9850,
+	0xbb0fc4b6,
+	0x0c9800bc,
+	0x020d9801,
+	0xf1060f98,
+	0xf50800e7,
+	0xf0016f21,
+	0xa5f001ac,
+	0x00b7f104,
+	0x50b3f030,
+	0xb6040c98,
+	0xbcbb0fc4,
+	0x020c9800,
+	0x98030d98,
+	0xe7f1080f,
+	0x21f50200,
+	0x21f5016f,
+	0x01f4025e,
+	0x0712f406,
+/* 0x06ac: ctx_xfer_post */
+	0x027f21f5,
+/* 0x06b0: ctx_xfer_done */
+	0x05b721f5,
+	0x000000f8,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk208.fuc5.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk208.fuc5.h
index fbcc342f896f..84af7ec6a78e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk208.fuc5.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk208.fuc5.h
@@ -276,7 +276,7 @@ uint32_t gk208_grgpc_code[] = {
 	0x02020014,
 	0xf6120040,
 	0x04bd0002,
-	0xfe048141,
+	0xfe048441,
 	0x00400010,
 	0x0000f607,
 	0x040204bd,
@@ -295,165 +295,165 @@ uint32_t gk208_grgpc_code[] = {
 	0x01c90080,
 	0xbd0002f6,
 	0x0c308e04,
-	0xbd24bd50,
-/* 0x0383: init_unk_loop */
-	0x7e44bd34,
-	0xb0000065,
-	0x0bf400f6,
-	0xbb010f0e,
-	0x4ffd04f2,
-	0x0130b605,
-/* 0x0398: init_unk_next */
-	0xb60120b6,
-	0x26b004e0,
-	0xe21bf401,
-/* 0x03a4: init_unk_done */
-	0xb50703b5,
-	0x00820804,
-	0x22cf0201,
-	0x9534bd00,
-	0x00800825,
-	0x05f601c0,
-	0x8004bd00,
-	0xf601c100,
-	0x04bd0005,
-	0x98000e98,
-	0x207e010f,
-	0x2fbb0001,
-	0x003fbb00,
-	0x98010e98,
-	0x207e020f,
-	0x0e980001,
-	0x00effd05,
-	0xbb002ebb,
-	0x0e98003e,
-	0x030f9802,
-	0x0001207e,
-	0xfd070e98,
-	0x2ebb00ef,
-	0x003ebb00,
-	0x800235b6,
-	0xf601d300,
-	0x04bd0003,
-	0xb60825b6,
-	0x20b60635,
-	0x0130b601,
-	0xb60824b6,
-	0x2fb20834,
-	0x0002687e,
-	0xbb002fbb,
-	0x0080003f,
-	0x03f60201,
-	0xbd04bd00,
-	0x1f29f024,
-	0x02300080,
-	0xbd0002f6,
-/* 0x0445: main */
-	0x0031f404,
-	0x0d0028f4,
-	0x00377e24,
-	0xf401f400,
-	0xf404e4b0,
-	0x81fe1d18,
-	0xbd060201,
-	0x0412fd20,
-	0xfd01e4b6,
-	0x18fe051e,
-	0x05187e00,
-	0xd40ef400,
-/* 0x0474: main_not_ctx_xfer */
-	0xf010ef94,
-	0xf87e01f5,
-	0x0ef40002,
-/* 0x0481: ih */
-	0xfe80f9c7,
-	0x80f90188,
-	0xa0f990f9,
-	0xd0f9b0f9,
-	0xf0f9e0f9,
-	0x004a04bd,
-	0x00aacf02,
-	0xf404abc4,
-	0x240d1f0b,
-	0xcf1a004e,
-	0x004f00ee,
-	0x00ffcf19,
-	0x0000047e,
-	0x0040010e,
-	0x000ef61d,
-/* 0x04be: ih_no_fifo */
-	0x004004bd,
-	0x000af601,
-	0xf0fc04bd,
-	0xd0fce0fc,
-	0xa0fcb0fc,
-	0x80fc90fc,
-	0xfc0088fe,
-	0x0032f480,
-/* 0x04de: hub_barrier_done */
-	0x010f01f8,
-	0xbb040e98,
-	0xffb204fe,
-	0x4094188e,
-	0x00008f7e,
-/* 0x04f2: ctx_redswitch */
-	0x200f00f8,
+	0x01e5f050,
+	0x34bd24bd,
+/* 0x0386: init_unk_loop */
+	0x657e44bd,
+	0xf6b00000,
+	0x0e0bf400,
+	0xf2bb010f,
+	0x054ffd04,
+/* 0x039b: init_unk_next */
+	0xb60130b6,
+	0xe0b60120,
+	0x0126b004,
+/* 0x03a7: init_unk_done */
+	0xb5e21bf4,
+	0x04b50703,
+	0x01008208,
+	0x0022cf02,
+	0x259534bd,
+	0xc0008008,
+	0x0005f601,
+	0x008004bd,
+	0x05f601c1,
+	0x9804bd00,
+	0x0f98000e,
+	0x01207e01,
+	0x002fbb00,
+	0x98003fbb,
+	0x0f98010e,
+	0x01207e02,
+	0x050e9800,
+	0xbb00effd,
+	0x3ebb002e,
+	0x020e9800,
+	0x7e030f98,
+	0x98000120,
+	0xeffd070e,
+	0x002ebb00,
+	0xb6003ebb,
+	0x00800235,
+	0x03f601d3,
+	0xb604bd00,
+	0x35b60825,
+	0x0120b606,
+	0xb60130b6,
+	0x34b60824,
+	0x7e2fb208,
+	0xbb000268,
+	0x3fbb002f,
+	0x01008000,
+	0x0003f602,
+	0x24bd04bd,
+	0x801f29f0,
+	0xf6023000,
+	0x04bd0002,
+/* 0x0448: main */
+	0xf40031f4,
+	0x240d0028,
+	0x0000377e,
+	0xb0f401f4,
+	0x18f404e4,
+	0x0181fe1d,
+	0x20bd0602,
+	0xb60412fd,
+	0x1efd01e4,
+	0x0018fe05,
+	0x00051b7e,
+/* 0x0477: main_not_ctx_xfer */
+	0x94d40ef4,
+	0xf5f010ef,
+	0x02f87e01,
+	0xc70ef400,
+/* 0x0484: ih */
+	0x88fe80f9,
+	0xf980f901,
+	0xf9a0f990,
+	0xf9d0f9b0,
+	0xbdf0f9e0,
+	0x02004a04,
+	0xc400aacf,
+	0x0bf404ab,
+	0x4e240d1f,
+	0xeecf1a00,
+	0x19004f00,
+	0x7e00ffcf,
+	0x0e000004,
+	0x1d004001,
+	0xbd000ef6,
+/* 0x04c1: ih_no_fifo */
+	0x01004004,
+	0xbd000af6,
+	0xfcf0fc04,
+	0xfcd0fce0,
+	0xfca0fcb0,
+	0xfe80fc90,
+	0x80fc0088,
+	0xf80032f4,
+/* 0x04e1: hub_barrier_done */
+	0x98010f01,
+	0xfebb040e,
+	0x8effb204,
+	0x7e409418,
+	0xf800008f,
+/* 0x04f5: ctx_redswitch */
+	0x80200f00,
+	0xf6018500,
+	0x04bd000f,
+/* 0x0502: ctx_redswitch_delay */
+	0xe2b6080e,
+	0xfd1bf401,
+	0x0800f5f1,
+	0x0200f5f1,
 	0x01850080,
 	0xbd000ff6,
-/* 0x04ff: ctx_redswitch_delay */
-	0xb6080e04,
-	0x1bf401e2,
-	0x00f5f1fd,
-	0x00f5f108,
-	0x85008002,
-	0x000ff601,
-	0x00f804bd,
-/* 0x0518: ctx_xfer */
-	0x02810080,
-	0xbd000ff6,
-	0x0711f404,
-	0x0004f27e,
-/* 0x0528: ctx_xfer_not_load */
-	0x0002167e,
-	0xfc8024bd,
-	0x02f60247,
-	0xf004bd00,
-	0x20b6012c,
-	0x4afc8003,
+/* 0x051b: ctx_xfer */
+	0x8000f804,
+	0xf6028100,
+	0x04bd000f,
+	0x7e0711f4,
+/* 0x052b: ctx_xfer_not_load */
+	0x7e0004f5,
+	0xbd000216,
+	0x47fc8024,
 	0x0002f602,
-	0xacf004bd,
-	0x02a5f001,
-	0x5000008b,
-	0xb6040c98,
-	0xbcbb0fc4,
-	0x000c9800,
-	0x0e010d98,
-	0x013d7e00,
-	0x01acf000,
-	0x5040008b,
-	0xb6040c98,
-	0xbcbb0fc4,
-	0x010c9800,
-	0x98020d98,
-	0x004e060f,
-	0x013d7e08,
-	0x01acf000,
-	0x8b04a5f0,
-	0x98503000,
+	0x2cf004bd,
+	0x0320b601,
+	0x024afc80,
+	0xbd0002f6,
+	0x01acf004,
+	0x8b02a5f0,
+	0x98500000,
 	0xc4b6040c,
 	0x00bcbb0f,
-	0x98020c98,
-	0x0f98030d,
-	0x02004e08,
+	0x98000c98,
+	0x000e010d,
 	0x00013d7e,
-	0x00020a7e,
-	0xf40601f4,
-/* 0x05b2: ctx_xfer_post */
-	0x277e0712,
-/* 0x05b6: ctx_xfer_done */
-	0xde7e0002,
-	0x00f80004,
-	0x00000000,
+	0x8b01acf0,
+	0x98504000,
+	0xc4b6040c,
+	0x00bcbb0f,
+	0x98010c98,
+	0x0f98020d,
+	0x08004e06,
+	0x00013d7e,
+	0xf001acf0,
+	0x008b04a5,
+	0x0c985030,
+	0x0fc4b604,
+	0x9800bcbb,
+	0x0d98020c,
+	0x080f9803,
+	0x7e02004e,
+	0x7e00013d,
+	0xf400020a,
+	0x12f40601,
+/* 0x05b5: ctx_xfer_post */
+	0x02277e07,
+/* 0x05b9: ctx_xfer_done */
+	0x04e17e00,
+	0x0000f800,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgm107.fuc5.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgm107.fuc5.h
index 51f5c3c6e966..11bf363a6ae9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgm107.fuc5.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgm107.fuc5.h
@@ -289,7 +289,7 @@ uint32_t gm107_grgpc_code[] = {
 	0x020014fe,
 	0x12004002,
 	0xbd0002f6,
-	0x05b04104,
+	0x05b34104,
 	0x400010fe,
 	0x00f60700,
 	0x0204bd00,
@@ -308,259 +308,259 @@ uint32_t gm107_grgpc_code[] = {
 	0xc900800f,
 	0x0002f601,
 	0x308e04bd,
-	0x24bd500c,
-	0x44bd34bd,
-/* 0x03b0: init_unk_loop */
-	0x0000657e,
-	0xf400f6b0,
-	0x010f0e0b,
-	0xfd04f2bb,
-	0x30b6054f,
-/* 0x03c5: init_unk_next */
-	0x0120b601,
-	0xb004e0b6,
-	0x1bf40226,
-/* 0x03d1: init_unk_done */
-	0x0703b5e2,
-	0x820804b5,
-	0xcf020100,
-	0x34bd0022,
-	0x80082595,
-	0xf601c000,
+	0xe5f0500c,
+	0xbd24bd01,
+/* 0x03b3: init_unk_loop */
+	0x7e44bd34,
+	0xb0000065,
+	0x0bf400f6,
+	0xbb010f0e,
+	0x4ffd04f2,
+	0x0130b605,
+/* 0x03c8: init_unk_next */
+	0xb60120b6,
+	0x26b004e0,
+	0xe21bf402,
+/* 0x03d4: init_unk_done */
+	0xb50703b5,
+	0x00820804,
+	0x22cf0201,
+	0x9534bd00,
+	0x00800825,
+	0x05f601c0,
+	0x8004bd00,
+	0xf601c100,
 	0x04bd0005,
-	0x01c10080,
-	0xbd0005f6,
-	0x000e9804,
-	0x7e010f98,
-	0xbb000120,
-	0x3fbb002f,
-	0x010e9800,
-	0x7e020f98,
-	0x98000120,
-	0xeffd050e,
-	0x002ebb00,
-	0x98003ebb,
-	0x0f98020e,
-	0x01207e03,
-	0x070e9800,
-	0xbb00effd,
-	0x3ebb002e,
-	0x0235b600,
-	0x01d30080,
-	0xbd0003f6,
-	0x0825b604,
-	0xb60635b6,
-	0x30b60120,
-	0x0824b601,
-	0xb20834b6,
-	0x02687e2f,
-	0x002fbb00,
-	0x0f003fbb,
-	0x8effb23f,
-	0xf0501d60,
-	0x8f7e01e5,
-	0x0c0f0000,
-	0xa88effb2,
-	0xe5f0501d,
-	0x008f7e01,
-	0x03147e00,
-	0xb23f0f00,
-	0x1d608eff,
-	0x01e5f050,
-	0x00008f7e,
-	0xffb2000f,
-	0x501d9c8e,
-	0x7e01e5f0,
-	0x0f00008f,
-	0x03147e01,
-	0x8effb200,
+	0x98000e98,
+	0x207e010f,
+	0x2fbb0001,
+	0x003fbb00,
+	0x98010e98,
+	0x207e020f,
+	0x0e980001,
+	0x00effd05,
+	0xbb002ebb,
+	0x0e98003e,
+	0x030f9802,
+	0x0001207e,
+	0xfd070e98,
+	0x2ebb00ef,
+	0x003ebb00,
+	0x800235b6,
+	0xf601d300,
+	0x04bd0003,
+	0xb60825b6,
+	0x20b60635,
+	0x0130b601,
+	0xb60824b6,
+	0x2fb20834,
+	0x0002687e,
+	0xbb002fbb,
+	0x3f0f003f,
+	0x501d608e,
+	0xb201e5f0,
+	0x008f7eff,
+	0x8e0c0f00,
 	0xf0501da8,
-	0x8f7e01e5,
-	0xff0f0000,
-	0x988effb2,
+	0xffb201e5,
+	0x00008f7e,
+	0x0003147e,
+	0x608e3f0f,
 	0xe5f0501d,
-	0x008f7e01,
-	0xb2020f00,
-	0x1da88eff,
+	0x7effb201,
+	0x0f00008f,
+	0x1d9c8e00,
 	0x01e5f050,
-	0x00008f7e,
+	0x8f7effb2,
+	0x010f0000,
 	0x0003147e,
-	0x85050498,
-	0x98504000,
-	0x64b60406,
-	0x0056bb0f,
-/* 0x04e0: tpc_strand_init_tpc_loop */
-	0x05705eb8,
-	0x00657e00,
-	0xbdf6b200,
-/* 0x04ed: tpc_strand_init_idx_loop */
-	0x605eb874,
-	0x7fb20005,
-	0x00008f7e,
-	0x05885eb8,
-	0x082f9500,
-	0x00008f7e,
-	0x058c5eb8,
-	0x082f9500,
+	0x501da88e,
+	0xb201e5f0,
+	0x008f7eff,
+	0x8eff0f00,
+	0xf0501d98,
+	0xffb201e5,
 	0x00008f7e,
-	0x05905eb8,
-	0x00657e00,
-	0x06f5b600,
-	0xb601f0b6,
-	0x2fbb08f4,
-	0x003fbb00,
-	0xb60170b6,
-	0x1bf40162,
-	0x0050b7bf,
-	0x0142b608,
-	0x0fa81bf4,
-	0x8effb23f,
-	0xf0501d60,
-	0x8f7e01e5,
-	0x0d0f0000,
-	0xa88effb2,
+	0xa88e020f,
 	0xe5f0501d,
-	0x008f7e01,
-	0x03147e00,
-	0x01008000,
-	0x0003f602,
-	0x24bd04bd,
-	0x801f29f0,
-	0xf6023000,
-	0x04bd0002,
-/* 0x0574: main */
-	0xf40031f4,
-	0x240d0028,
-	0x0000377e,
-	0xb0f401f4,
-	0x18f404e4,
-	0x0181fe1d,
-	0x20bd0602,
-	0xb60412fd,
-	0x1efd01e4,
-	0x0018fe05,
-	0x0006477e,
-/* 0x05a3: main_not_ctx_xfer */
-	0x94d40ef4,
-	0xf5f010ef,
-	0x02f87e01,
-	0xc70ef400,
-/* 0x05b0: ih */
-	0x88fe80f9,
-	0xf980f901,
-	0xf9a0f990,
-	0xf9d0f9b0,
-	0xbdf0f9e0,
-	0x02004a04,
-	0xc400aacf,
-	0x0bf404ab,
-	0x4e240d1f,
-	0xeecf1a00,
-	0x19004f00,
-	0x7e00ffcf,
-	0x0e000004,
-	0x1d004001,
-	0xbd000ef6,
-/* 0x05ed: ih_no_fifo */
-	0x01004004,
-	0xbd000af6,
-	0xfcf0fc04,
-	0xfcd0fce0,
-	0xfca0fcb0,
-	0xfe80fc90,
-	0x80fc0088,
-	0xf80032f4,
-/* 0x060d: hub_barrier_done */
-	0x98010f01,
-	0xfebb040e,
-	0x8effb204,
-	0x7e409418,
-	0xf800008f,
-/* 0x0621: ctx_redswitch */
-	0x80200f00,
+	0x7effb201,
+	0x7e00008f,
+	0x98000314,
+	0x00850504,
+	0x06985040,
+	0x0f64b604,
+/* 0x04e3: tpc_strand_init_tpc_loop */
+	0xb80056bb,
+	0x0005705e,
+	0x0000657e,
+	0x74bdf6b2,
+/* 0x04f0: tpc_strand_init_idx_loop */
+	0x05605eb8,
+	0x7e7fb200,
+	0xb800008f,
+	0x0005885e,
+	0x7e082f95,
+	0xb800008f,
+	0x00058c5e,
+	0x7e082f95,
+	0xb800008f,
+	0x0005905e,
+	0x0000657e,
+	0xb606f5b6,
+	0xf4b601f0,
+	0x002fbb08,
+	0xb6003fbb,
+	0x62b60170,
+	0xbf1bf401,
+	0x080050b7,
+	0xf40142b6,
+	0x3f0fa81b,
+	0x501d608e,
+	0xb201e5f0,
+	0x008f7eff,
+	0x8e0d0f00,
+	0xf0501da8,
+	0xffb201e5,
+	0x00008f7e,
+	0x0003147e,
+	0x02010080,
+	0xbd0003f6,
+	0xf024bd04,
+	0x00801f29,
+	0x02f60230,
+/* 0x0577: main */
+	0xf404bd00,
+	0x28f40031,
+	0x7e240d00,
+	0xf4000037,
+	0xe4b0f401,
+	0x1d18f404,
+	0x020181fe,
+	0xfd20bd06,
+	0xe4b60412,
+	0x051efd01,
+	0x7e0018fe,
+	0xf400064a,
+/* 0x05a6: main_not_ctx_xfer */
+	0xef94d40e,
+	0x01f5f010,
+	0x0002f87e,
+/* 0x05b3: ih */
+	0xf9c70ef4,
+	0x0188fe80,
+	0x90f980f9,
+	0xb0f9a0f9,
+	0xe0f9d0f9,
+	0x04bdf0f9,
+	0xcf02004a,
+	0xabc400aa,
+	0x1f0bf404,
+	0x004e240d,
+	0x00eecf1a,
+	0xcf19004f,
+	0x047e00ff,
+	0x010e0000,
+	0xf61d0040,
+	0x04bd000e,
+/* 0x05f0: ih_no_fifo */
+	0xf6010040,
+	0x04bd000a,
+	0xe0fcf0fc,
+	0xb0fcd0fc,
+	0x90fca0fc,
+	0x88fe80fc,
+	0xf480fc00,
+	0x01f80032,
+/* 0x0610: hub_barrier_done */
+	0x0e98010f,
+	0x04febb04,
+	0x188effb2,
+	0x8f7e4094,
+	0x00f80000,
+/* 0x0624: ctx_redswitch */
+	0x0080200f,
+	0x0ff60185,
+	0x0e04bd00,
+/* 0x0631: ctx_redswitch_delay */
+	0x01e2b608,
+	0xf1fd1bf4,
+	0xf10800f5,
+	0x800200f5,
 	0xf6018500,
 	0x04bd000f,
-/* 0x062e: ctx_redswitch_delay */
-	0xe2b6080e,
-	0xfd1bf401,
-	0x0800f5f1,
-	0x0200f5f1,
-	0x01850080,
-	0xbd000ff6,
-/* 0x0647: ctx_xfer */
-	0x8000f804,
-	0xf6028100,
-	0x04bd000f,
-	0xc48effb2,
-	0xe5f0501d,
-	0x008f7e01,
-	0x0711f400,
-	0x0006217e,
-/* 0x0664: ctx_xfer_not_load */
-	0x0002167e,
-	0xfc8024bd,
-	0x02f60247,
-	0xf004bd00,
-	0x20b6012c,
-	0x4afc8003,
+/* 0x064a: ctx_xfer */
+	0x008000f8,
+	0x0ff60281,
+	0x8e04bd00,
+	0xf0501dc4,
+	0xffb201e5,
+	0x00008f7e,
+	0x7e0711f4,
+/* 0x0667: ctx_xfer_not_load */
+	0x7e000624,
+	0xbd000216,
+	0x47fc8024,
 	0x0002f602,
-	0x0c0f04bd,
-	0xa88effb2,
-	0xe5f0501d,
-	0x008f7e01,
-	0x03147e00,
-	0xb23f0f00,
-	0x1d608eff,
-	0x01e5f050,
+	0x2cf004bd,
+	0x0320b601,
+	0x024afc80,
+	0xbd0002f6,
+	0x8e0c0f04,
+	0xf0501da8,
+	0xffb201e5,
 	0x00008f7e,
-	0xffb2000f,
-	0x501d9c8e,
-	0x7e01e5f0,
+	0x0003147e,
+	0x608e3f0f,
+	0xe5f0501d,
+	0x7effb201,
 	0x0f00008f,
-	0x03147e01,
-	0x01fcf000,
-	0xb203f0b6,
-	0x1da88eff,
+	0x1d9c8e00,
 	0x01e5f050,
-	0x00008f7e,
-	0xf001acf0,
-	0x008b02a5,
-	0x0c985000,
-	0x0fc4b604,
-	0x9800bcbb,
-	0x0d98000c,
-	0x7e000e01,
-	0xf000013d,
-	0x008b01ac,
-	0x0c985040,
-	0x0fc4b604,
-	0x9800bcbb,
-	0x0d98010c,
-	0x060f9802,
-	0x7e08004e,
-	0xf000013d,
+	0x8f7effb2,
+	0x010f0000,
+	0x0003147e,
+	0xb601fcf0,
+	0xa88e03f0,
+	0xe5f0501d,
+	0x7effb201,
+	0xf000008f,
 	0xa5f001ac,
-	0x30008b04,
+	0x00008b02,
 	0x040c9850,
 	0xbb0fc4b6,
 	0x0c9800bc,
-	0x030d9802,
-	0x4e080f98,
-	0x3d7e0200,
-	0x0a7e0001,
-	0x147e0002,
-	0x01f40003,
-	0x1a12f406,
-/* 0x073c: ctx_xfer_post */
-	0x0002277e,
-	0xffb20d0f,
-	0x501da88e,
-	0x7e01e5f0,
-	0x7e00008f,
-/* 0x0753: ctx_xfer_done */
-	0x7e000314,
-	0xf800060d,
-	0x00000000,
+	0x010d9800,
+	0x3d7e000e,
+	0xacf00001,
+	0x40008b01,
+	0x040c9850,
+	0xbb0fc4b6,
+	0x0c9800bc,
+	0x020d9801,
+	0x4e060f98,
+	0x3d7e0800,
+	0xacf00001,
+	0x04a5f001,
+	0x5030008b,
+	0xb6040c98,
+	0xbcbb0fc4,
+	0x020c9800,
+	0x98030d98,
+	0x004e080f,
+	0x013d7e02,
+	0x020a7e00,
+	0x03147e00,
+	0x0601f400,
+/* 0x073f: ctx_xfer_post */
+	0x7e1a12f4,
+	0x0f000227,
+	0x1da88e0d,
+	0x01e5f050,
+	0x8f7effb2,
+	0x147e0000,
+/* 0x0756: ctx_xfer_done */
+	0x107e0003,
+	0x00f80006,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
index dda7a7d224c9..9f5dfc85147a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
@@ -143,7 +143,7 @@ gf100_gr_zbc_depth_get(struct gf100_gr *gr, int format,
 static int
 gf100_fermi_mthd_zbc_color(struct nvkm_object *object, void *data, u32 size)
 {
-	struct gf100_gr *gr = (void *)object->engine;
+	struct gf100_gr *gr = gf100_gr(nvkm_gr(object->engine));
 	union {
 		struct fermi_a_zbc_color_v0 v0;
 	} *args = data;
@@ -189,7 +189,7 @@ gf100_fermi_mthd_zbc_color(struct nvkm_object *object, void *data, u32 size)
 static int
 gf100_fermi_mthd_zbc_depth(struct nvkm_object *object, void *data, u32 size)
 {
-	struct gf100_gr *gr = (void *)object->engine;
+	struct gf100_gr *gr = gf100_gr(nvkm_gr(object->engine));
 	union {
 		struct fermi_a_zbc_depth_v0 v0;
 	} *args = data;
@@ -1530,6 +1530,8 @@ gf100_gr_oneinit(struct nvkm_gr *base)
 		gr->ppc_nr[i]  = gr->func->ppc_nr;
 		for (j = 0; j < gr->ppc_nr[i]; j++) {
 			u8 mask = nvkm_rd32(device, GPC_UNIT(i, 0x0c30 + (j * 4)));
+			if (mask)
+				gr->ppc_mask[i] |= (1 << j);
 			gr->ppc_tpc_nr[i][j] = hweight8(mask);
 		}
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
index 4611961b1187..02e78b8d93f6 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
@@ -97,6 +97,7 @@ struct gf100_gr {
 	u8 tpc_nr[GPC_MAX];
 	u8 tpc_total;
 	u8 ppc_nr[GPC_MAX];
+	u8 ppc_mask[GPC_MAX];
 	u8 ppc_tpc_nr[GPC_MAX][4];
 
 	struct nvkm_memory *unk4188b4;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/base.c
index 895ba74057d4..1d7dd38292b3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/base.c
@@ -97,7 +97,9 @@ static void *
 nvkm_instobj_dtor(struct nvkm_memory *memory)
 {
 	struct nvkm_instobj *iobj = nvkm_instobj(memory);
+	spin_lock(&iobj->imem->lock);
 	list_del(&iobj->head);
+	spin_unlock(&iobj->imem->lock);
 	nvkm_memory_del(&iobj->parent);
 	return iobj;
 }
@@ -190,7 +192,9 @@ nvkm_instobj_new(struct nvkm_instmem *imem, u32 size, u32 align, bool zero,
 		nvkm_memory_ctor(&nvkm_instobj_func_slow, &iobj->memory);
 		iobj->parent = memory;
 		iobj->imem = imem;
+		spin_lock(&iobj->imem->lock);
 		list_add_tail(&iobj->head, &imem->list);
+		spin_unlock(&iobj->imem->lock);
 		memory = &iobj->memory;
 	}
 
@@ -309,5 +313,6 @@ nvkm_instmem_ctor(const struct nvkm_instmem_func *func,
 {
 	nvkm_subdev_ctor(&nvkm_instmem, device, index, 0, &imem->subdev);
 	imem->func = func;
+	spin_lock_init(&imem->lock);
 	INIT_LIST_HEAD(&imem->list);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk104.c
index b61509e26ec9..b735173a18ff 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk104.c
@@ -59,7 +59,7 @@ gk104_volt_set(struct nvkm_volt *base, u32 uv)
 	duty = (uv - bios->base) * div / bios->pwm_range;
 
 	nvkm_wr32(device, 0x20340, div);
-	nvkm_wr32(device, 0x20344, 0x8000000 | duty);
+	nvkm_wr32(device, 0x20344, 0x80000000 | duty);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 248953d2fdb7..0154db43860c 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -8472,7 +8472,7 @@ restart_ih:
 	if (queue_dp)
 		schedule_work(&rdev->dp_work);
 	if (queue_hotplug)
-		schedule_work(&rdev->hotplug_work);
+		schedule_delayed_work(&rdev->hotplug_work, 0);
 	if (queue_reset) {
 		rdev->needs_reset = true;
 		wake_up_all(&rdev->fence_queue);
@@ -9630,6 +9630,9 @@ static void dce8_program_watermarks(struct radeon_device *rdev,
 		    (rdev->disp_priority == 2)) {
 			DRM_DEBUG_KMS("force priority to high\n");
 		}
+
+		/* Save number of lines the linebuffer leads before the scanout */
+		radeon_crtc->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
 	}
 
 	/* select wm A */
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 7f33767d7ed6..2ad462896896 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2372,6 +2372,9 @@ static void evergreen_program_watermarks(struct radeon_device *rdev,
 		c.full = dfixed_div(c, a);
 		priority_b_mark = dfixed_trunc(c);
 		priority_b_cnt |= priority_b_mark & PRIORITY_MARK_MASK;
+
+		/* Save number of lines the linebuffer leads before the scanout */
+		radeon_crtc->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
 	}
 
 	/* select wm A */
@@ -5344,7 +5347,7 @@ restart_ih:
 	if (queue_dp)
 		schedule_work(&rdev->dp_work);
 	if (queue_hotplug)
-		schedule_work(&rdev->hotplug_work);
+		schedule_delayed_work(&rdev->hotplug_work, 0);
 	if (queue_hdmi)
 		schedule_work(&rdev->audio_work);
 	if (queue_thermal && rdev->pm.dpm_enabled)
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 238b13f045c1..9e7e2bf03b81 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -806,7 +806,7 @@ int r100_irq_process(struct radeon_device *rdev)
 		status = r100_irq_ack(rdev);
 	}
 	if (queue_hotplug)
-		schedule_work(&rdev->hotplug_work);
+		schedule_delayed_work(&rdev->hotplug_work, 0);
 	if (rdev->msi_enabled) {
 		switch (rdev->family) {
 		case CHIP_RS400:
@@ -3217,6 +3217,9 @@ void r100_bandwidth_update(struct radeon_device *rdev)
 	uint32_t pixel_bytes1 = 0;
 	uint32_t pixel_bytes2 = 0;
 
+	/* Guess line buffer size to be 8192 pixels */
+	u32 lb_size = 8192;
+
 	if (!rdev->mode_info.mode_config_initialized)
 		return;
 
@@ -3631,6 +3634,13 @@ void r100_bandwidth_update(struct radeon_device *rdev)
 		DRM_DEBUG_KMS("GRPH2_BUFFER_CNTL from to %x\n",
 			  (unsigned int)RREG32(RADEON_GRPH2_BUFFER_CNTL));
 	}
+
+	/* Save number of lines the linebuffer leads before the scanout */
+	if (mode1)
+	    rdev->mode_info.crtcs[0]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode1->crtc_hdisplay);
+
+	if (mode2)
+	    rdev->mode_info.crtcs[1]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode2->crtc_hdisplay);
 }
 
 int r100_ring_test(struct radeon_device *rdev, struct radeon_ring *ring)
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 4ea5b10ff5f4..cc2fdf0be37a 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -4276,7 +4276,7 @@ restart_ih:
 		WREG32(IH_RB_RPTR, rptr);
 	}
 	if (queue_hotplug)
-		schedule_work(&rdev->hotplug_work);
+		schedule_delayed_work(&rdev->hotplug_work, 0);
 	if (queue_hdmi)
 		schedule_work(&rdev->audio_work);
 	if (queue_thermal && rdev->pm.dpm_enabled)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index b6cbd816537e..87db64983ea8 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -2414,7 +2414,7 @@ struct radeon_device {
 	struct r600_ih ih; /* r6/700 interrupt ring */
 	struct radeon_rlc rlc;
 	struct radeon_mec mec;
-	struct work_struct hotplug_work;
+	struct delayed_work hotplug_work;
 	struct work_struct dp_work;
 	struct work_struct audio_work;
 	int num_crtc; /* number of crtcs */
diff --git a/drivers/gpu/drm/radeon/radeon_agp.c b/drivers/gpu/drm/radeon/radeon_agp.c
index fe994aac3b04..c77d349c561c 100644
--- a/drivers/gpu/drm/radeon/radeon_agp.c
+++ b/drivers/gpu/drm/radeon/radeon_agp.c
@@ -54,6 +54,9 @@ static struct radeon_agpmode_quirk radeon_agpmode_quirk_list[] = {
 	/* Intel 82855PM host bridge / Mobility 9600 M10 RV350 Needs AGPMode 1 (lp #195051) */
 	{ PCI_VENDOR_ID_INTEL, 0x3340, PCI_VENDOR_ID_ATI, 0x4e50,
 		PCI_VENDOR_ID_IBM, 0x0550, 1},
+	/* Intel 82855PM host bridge / RV250/M9 GL [Mobility FireGL 9000/Radeon 9000] needs AGPMode 1 (Thinkpad T40p) */
+	{ PCI_VENDOR_ID_INTEL, 0x3340, PCI_VENDOR_ID_ATI, 0x4c66,
+		PCI_VENDOR_ID_IBM, 0x054d, 1},
 	/* Intel 82855PM host bridge / Mobility M7 needs AGPMode 1 */
 	{ PCI_VENDOR_ID_INTEL, 0x3340, PCI_VENDOR_ID_ATI, 0x4c57,
 		PCI_VENDOR_ID_IBM, 0x0530, 1},
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 5a2cafb4f1bc..340f3f549f29 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1234,13 +1234,32 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
 	if (r < 0)
 		return connector_status_disconnected;
 
+	if (radeon_connector->detected_hpd_without_ddc) {
+		force = true;
+		radeon_connector->detected_hpd_without_ddc = false;
+	}
+
 	if (!force && radeon_check_hpd_status_unchanged(connector)) {
 		ret = connector->status;
 		goto exit;
 	}
 
-	if (radeon_connector->ddc_bus)
+	if (radeon_connector->ddc_bus) {
 		dret = radeon_ddc_probe(radeon_connector, false);
+
+		/* Sometimes the pins required for the DDC probe on DVI
+		 * connectors don't make contact at the same time that the ones
+		 * for HPD do. If the DDC probe fails even though we had an HPD
+		 * signal, try again later */
+		if (!dret && !force &&
+		    connector->status != connector_status_connected) {
+			DRM_DEBUG_KMS("hpd detected without ddc, retrying in 1 second\n");
+			radeon_connector->detected_hpd_without_ddc = true;
+			schedule_delayed_work(&rdev->hotplug_work,
+					      msecs_to_jiffies(1000));
+			goto exit;
+		}
+	}
 	if (dret) {
 		radeon_connector->detected_by_load = false;
 		radeon_connector_free_edid(connector);
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index a8d9927ed9eb..1eca0acac016 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -322,7 +322,9 @@ void radeon_crtc_handle_vblank(struct radeon_device *rdev, int crtc_id)
 	 * to complete in this vblank?
 	 */
 	if (update_pending &&
-	    (DRM_SCANOUTPOS_VALID & radeon_get_crtc_scanoutpos(rdev->ddev, crtc_id, 0,
+	    (DRM_SCANOUTPOS_VALID & radeon_get_crtc_scanoutpos(rdev->ddev,
+							       crtc_id,
+							       USE_REAL_VBLANKSTART,
 							       &vpos, &hpos, NULL, NULL,
 							       &rdev->mode_info.crtcs[crtc_id]->base.hwmode)) &&
 	    ((vpos >= (99 * rdev->mode_info.crtcs[crtc_id]->base.hwmode.crtc_vdisplay)/100) ||
@@ -401,6 +403,8 @@ static void radeon_flip_work_func(struct work_struct *__work)
 	struct drm_crtc *crtc = &radeon_crtc->base;
 	unsigned long flags;
 	int r;
+	int vpos, hpos, stat, min_udelay;
+	struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id];
 
         down_read(&rdev->exclusive_lock);
 	if (work->fence) {
@@ -437,6 +441,41 @@ static void radeon_flip_work_func(struct work_struct *__work)
 	/* set the proper interrupt */
 	radeon_irq_kms_pflip_irq_get(rdev, radeon_crtc->crtc_id);
 
+	/* If this happens to execute within the "virtually extended" vblank
+	 * interval before the start of the real vblank interval then it needs
+	 * to delay programming the mmio flip until the real vblank is entered.
+	 * This prevents completing a flip too early due to the way we fudge
+	 * our vblank counter and vblank timestamps in order to work around the
+	 * problem that the hw fires vblank interrupts before actual start of
+	 * vblank (when line buffer refilling is done for a frame). It
+	 * complements the fudging logic in radeon_get_crtc_scanoutpos() for
+	 * timestamping and radeon_get_vblank_counter_kms() for vblank counts.
+	 *
+	 * In practice this won't execute very often unless on very fast
+	 * machines because the time window for this to happen is very small.
+	 */
+	for (;;) {
+		/* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank
+		 * start in hpos, and to the "fudged earlier" vblank start in
+		 * vpos.
+		 */
+		stat = radeon_get_crtc_scanoutpos(rdev->ddev, work->crtc_id,
+						  GET_DISTANCE_TO_VBLANKSTART,
+						  &vpos, &hpos, NULL, NULL,
+						  &crtc->hwmode);
+
+		if ((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) !=
+		    (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE) ||
+		    !(vpos >= 0 && hpos <= 0))
+			break;
+
+		/* Sleep at least until estimated real start of hw vblank */
+		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+		min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5);
+		usleep_range(min_udelay, 2 * min_udelay);
+		spin_lock_irqsave(&crtc->dev->event_lock, flags);
+	};
+
 	/* do the flip (mmio) */
 	radeon_page_flip(rdev, radeon_crtc->crtc_id, work->base);
 
@@ -1768,6 +1807,15 @@ bool radeon_crtc_scaling_mode_fixup(struct drm_crtc *crtc,
  * \param dev Device to query.
  * \param crtc Crtc to query.
  * \param flags Flags from caller (DRM_CALLED_FROM_VBLIRQ or 0).
+ *              For driver internal use only also supports these flags:
+ *
+ *              USE_REAL_VBLANKSTART to use the real start of vblank instead
+ *              of a fudged earlier start of vblank.
+ *
+ *              GET_DISTANCE_TO_VBLANKSTART to return distance to the
+ *              fudged earlier start of vblank in *vpos and the distance
+ *              to true start of vblank in *hpos.
+ *
  * \param *vpos Location where vertical scanout position should be stored.
  * \param *hpos Location where horizontal scanout position should go.
  * \param *stime Target location for timestamp taken immediately before
@@ -1911,10 +1959,40 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
 		vbl_end = 0;
 	}
 
+	/* Called from driver internal vblank counter query code? */
+	if (flags & GET_DISTANCE_TO_VBLANKSTART) {
+	    /* Caller wants distance from real vbl_start in *hpos */
+	    *hpos = *vpos - vbl_start;
+	}
+
+	/* Fudge vblank to start a few scanlines earlier to handle the
+	 * problem that vblank irqs fire a few scanlines before start
+	 * of vblank. Some driver internal callers need the true vblank
+	 * start to be used and signal this via the USE_REAL_VBLANKSTART flag.
+	 *
+	 * The cause of the "early" vblank irq is that the irq is triggered
+	 * by the line buffer logic when the line buffer read position enters
+	 * the vblank, whereas our crtc scanout position naturally lags the
+	 * line buffer read position.
+	 */
+	if (!(flags & USE_REAL_VBLANKSTART))
+		vbl_start -= rdev->mode_info.crtcs[pipe]->lb_vblank_lead_lines;
+
 	/* Test scanout position against vblank region. */
 	if ((*vpos < vbl_start) && (*vpos >= vbl_end))
 		in_vbl = false;
 
+	/* In vblank? */
+	if (in_vbl)
+	    ret |= DRM_SCANOUTPOS_IN_VBLANK;
+
+	/* Called from driver internal vblank counter query code? */
+	if (flags & GET_DISTANCE_TO_VBLANKSTART) {
+		/* Caller wants distance from fudged earlier vbl_start */
+		*vpos -= vbl_start;
+		return ret;
+	}
+
 	/* Check if inside vblank area and apply corrective offsets:
 	 * vpos will then be >=0 in video scanout area, but negative
 	 * within vblank area, counting down the number of lines until
@@ -1930,31 +2008,5 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
 	/* Correct for shifted end of vbl at vbl_end. */
 	*vpos = *vpos - vbl_end;
 
-	/* In vblank? */
-	if (in_vbl)
-		ret |= DRM_SCANOUTPOS_IN_VBLANK;
-
-	/* Is vpos outside nominal vblank area, but less than
-	 * 1/100 of a frame height away from start of vblank?
-	 * If so, assume this isn't a massively delayed vblank
-	 * interrupt, but a vblank interrupt that fired a few
-	 * microseconds before true start of vblank. Compensate
-	 * by adding a full frame duration to the final timestamp.
-	 * Happens, e.g., on ATI R500, R600.
-	 *
-	 * We only do this if DRM_CALLED_FROM_VBLIRQ.
-	 */
-	if ((flags & DRM_CALLED_FROM_VBLIRQ) && !in_vbl) {
-		vbl_start = mode->crtc_vdisplay;
-		vtotal = mode->crtc_vtotal;
-
-		if (vbl_start - *vpos < vtotal / 100) {
-			*vpos -= vtotal;
-
-			/* Signal this correction as "applied". */
-			ret |= 0x8;
-		}
-	}
-
 	return ret;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c
index 171d3e43c30c..979f3bf65f2c 100644
--- a/drivers/gpu/drm/radeon/radeon_irq_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c
@@ -74,7 +74,7 @@ irqreturn_t radeon_driver_irq_handler_kms(int irq, void *arg)
 static void radeon_hotplug_work_func(struct work_struct *work)
 {
 	struct radeon_device *rdev = container_of(work, struct radeon_device,
-						  hotplug_work);
+						  hotplug_work.work);
 	struct drm_device *dev = rdev->ddev;
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct drm_connector *connector;
@@ -302,7 +302,7 @@ int radeon_irq_kms_init(struct radeon_device *rdev)
 		}
 	}
 
-	INIT_WORK(&rdev->hotplug_work, radeon_hotplug_work_func);
+	INIT_DELAYED_WORK(&rdev->hotplug_work, radeon_hotplug_work_func);
 	INIT_WORK(&rdev->dp_work, radeon_dp_work_func);
 	INIT_WORK(&rdev->audio_work, r600_audio_update_hdmi);
 
@@ -310,7 +310,7 @@ int radeon_irq_kms_init(struct radeon_device *rdev)
 	r = drm_irq_install(rdev->ddev, rdev->ddev->pdev->irq);
 	if (r) {
 		rdev->irq.installed = false;
-		flush_work(&rdev->hotplug_work);
+		flush_delayed_work(&rdev->hotplug_work);
 		return r;
 	}
 
@@ -333,7 +333,7 @@ void radeon_irq_kms_fini(struct radeon_device *rdev)
 		rdev->irq.installed = false;
 		if (rdev->msi_enabled)
 			pci_disable_msi(rdev->pdev);
-		flush_work(&rdev->hotplug_work);
+		flush_delayed_work(&rdev->hotplug_work);
 	}
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 0ec6fcca16d3..d290a8a09036 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -755,6 +755,8 @@ void radeon_driver_preclose_kms(struct drm_device *dev,
  */
 u32 radeon_get_vblank_counter_kms(struct drm_device *dev, int crtc)
 {
+	int vpos, hpos, stat;
+	u32 count;
 	struct radeon_device *rdev = dev->dev_private;
 
 	if (crtc < 0 || crtc >= rdev->num_crtc) {
@@ -762,7 +764,53 @@ u32 radeon_get_vblank_counter_kms(struct drm_device *dev, int crtc)
 		return -EINVAL;
 	}
 
-	return radeon_get_vblank_counter(rdev, crtc);
+	/* The hw increments its frame counter at start of vsync, not at start
+	 * of vblank, as is required by DRM core vblank counter handling.
+	 * Cook the hw count here to make it appear to the caller as if it
+	 * incremented at start of vblank. We measure distance to start of
+	 * vblank in vpos. vpos therefore will be >= 0 between start of vblank
+	 * and start of vsync, so vpos >= 0 means to bump the hw frame counter
+	 * result by 1 to give the proper appearance to caller.
+	 */
+	if (rdev->mode_info.crtcs[crtc]) {
+		/* Repeat readout if needed to provide stable result if
+		 * we cross start of vsync during the queries.
+		 */
+		do {
+			count = radeon_get_vblank_counter(rdev, crtc);
+			/* Ask radeon_get_crtc_scanoutpos to return vpos as
+			 * distance to start of vblank, instead of regular
+			 * vertical scanout pos.
+			 */
+			stat = radeon_get_crtc_scanoutpos(
+				dev, crtc, GET_DISTANCE_TO_VBLANKSTART,
+				&vpos, &hpos, NULL, NULL,
+				&rdev->mode_info.crtcs[crtc]->base.hwmode);
+		} while (count != radeon_get_vblank_counter(rdev, crtc));
+
+		if (((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) !=
+		    (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE))) {
+			DRM_DEBUG_VBL("Query failed! stat %d\n", stat);
+		}
+		else {
+			DRM_DEBUG_VBL("crtc %d: dist from vblank start %d\n",
+				      crtc, vpos);
+
+			/* Bump counter if we are at >= leading edge of vblank,
+			 * but before vsync where vpos would turn negative and
+			 * the hw counter really increments.
+			 */
+			if (vpos >= 0)
+				count++;
+		}
+	}
+	else {
+	    /* Fallback to use value as is. */
+	    count = radeon_get_vblank_counter(rdev, crtc);
+	    DRM_DEBUG_VBL("NULL mode info! Returned count may be wrong.\n");
+	}
+
+	return count;
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index 830e171c3a9e..bba112628b47 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -367,6 +367,7 @@ struct radeon_crtc {
 	u32 line_time;
 	u32 wm_low;
 	u32 wm_high;
+	u32 lb_vblank_lead_lines;
 	struct drm_display_mode hw_mode;
 	enum radeon_output_csc output_csc;
 };
@@ -553,6 +554,7 @@ struct radeon_connector {
 	void *con_priv;
 	bool dac_load_detect;
 	bool detected_by_load; /* if the connection status was determined by load */
+	bool detected_hpd_without_ddc; /* if an HPD signal was detected on DVI, but ddc probing failed */
 	uint16_t connector_object_id;
 	struct radeon_hpd hpd;
 	struct radeon_router router;
@@ -686,6 +688,9 @@ struct atom_voltage_table
 	struct atom_voltage_table_entry entries[MAX_VOLTAGE_ENTRIES];
 };
 
+/* Driver internal use only flags of radeon_get_crtc_scanoutpos() */
+#define USE_REAL_VBLANKSTART 		(1 << 30)
+#define GET_DISTANCE_TO_VBLANKSTART	(1 << 31)
 
 extern void
 radeon_add_atom_connector(struct drm_device *dev,
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index d3024883b844..84d45633d28c 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -221,11 +221,17 @@ int radeon_bo_create(struct radeon_device *rdev,
 	if (!(rdev->flags & RADEON_IS_PCIE))
 		bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC);
 
+	/* Write-combined CPU mappings of GTT cause GPU hangs with RV6xx
+	 * See https://bugs.freedesktop.org/show_bug.cgi?id=91268
+	 */
+	if (rdev->family >= CHIP_RV610 && rdev->family <= CHIP_RV635)
+		bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC);
+
 #ifdef CONFIG_X86_32
 	/* XXX: Write-combined CPU mappings of GTT seem broken on 32-bit
 	 * See https://bugs.freedesktop.org/show_bug.cgi?id=84627
 	 */
-	bo->flags &= ~RADEON_GEM_GTT_WC;
+	bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC);
 #elif defined(CONFIG_X86) && !defined(CONFIG_X86_PAT)
 	/* Don't try to enable write-combining when it can't work, or things
 	 * may be slow
@@ -235,9 +241,10 @@ int radeon_bo_create(struct radeon_device *rdev,
 #warning Please enable CONFIG_MTRR and CONFIG_X86_PAT for better performance \
 	 thanks to write-combining
 
-	DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for "
-		      "better performance thanks to write-combining\n");
-	bo->flags &= ~RADEON_GEM_GTT_WC;
+	if (bo->flags & RADEON_GEM_GTT_WC)
+		DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for "
+			      "better performance thanks to write-combining\n");
+	bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC);
 #endif
 
 	radeon_ttm_placement_from_domain(bo, domain);
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 6d80dde23400..59abebd6b5dc 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -1542,8 +1542,7 @@ int radeon_pm_late_init(struct radeon_device *rdev)
 				ret = device_create_file(rdev->dev, &dev_attr_power_method);
 				if (ret)
 					DRM_ERROR("failed to create device file for power method\n");
-				if (!ret)
-					rdev->pm.sysfs_initialized = true;
+				rdev->pm.sysfs_initialized = true;
 			}
 
 			mutex_lock(&rdev->pm.mutex);
@@ -1757,7 +1756,9 @@ static bool radeon_pm_in_vbl(struct radeon_device *rdev)
 	 */
 	for (crtc = 0; (crtc < rdev->num_crtc) && in_vbl; crtc++) {
 		if (rdev->pm.active_crtcs & (1 << crtc)) {
-			vbl_status = radeon_get_crtc_scanoutpos(rdev->ddev, crtc, 0,
+			vbl_status = radeon_get_crtc_scanoutpos(rdev->ddev,
+								crtc,
+								USE_REAL_VBLANKSTART,
 								&vpos, &hpos, NULL, NULL,
 								&rdev->mode_info.crtcs[crtc]->base.hwmode);
 			if ((vbl_status & DRM_SCANOUTPOS_VALID) &&
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 97a904835759..6244f4e44e9a 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -813,7 +813,7 @@ int rs600_irq_process(struct radeon_device *rdev)
 		status = rs600_irq_ack(rdev);
 	}
 	if (queue_hotplug)
-		schedule_work(&rdev->hotplug_work);
+		schedule_delayed_work(&rdev->hotplug_work, 0);
 	if (queue_hdmi)
 		schedule_work(&rdev->audio_work);
 	if (rdev->msi_enabled) {
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index 516ca27cfa12..6bc44c24e837 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -207,6 +207,9 @@ void rs690_line_buffer_adjust(struct radeon_device *rdev,
 {
 	u32 tmp;
 
+	/* Guess line buffer size to be 8192 pixels */
+	u32 lb_size = 8192;
+
 	/*
 	 * Line Buffer Setup
 	 * There is a single line buffer shared by both display controllers.
@@ -243,6 +246,13 @@ void rs690_line_buffer_adjust(struct radeon_device *rdev,
 		tmp |= V_006520_DC_LB_MEMORY_SPLIT_D1_1Q_D2_3Q;
 	}
 	WREG32(R_006520_DC_LB_MEMORY_SPLIT, tmp);
+
+	/* Save number of lines the linebuffer leads before the scanout */
+	if (mode1)
+		rdev->mode_info.crtcs[0]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode1->crtc_hdisplay);
+
+	if (mode2)
+		rdev->mode_info.crtcs[1]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode2->crtc_hdisplay);
 }
 
 struct rs690_watermark {
diff --git a/drivers/gpu/drm/radeon/rv730_dpm.c b/drivers/gpu/drm/radeon/rv730_dpm.c
index 3f5e1cf138ba..d37ba2cb886e 100644
--- a/drivers/gpu/drm/radeon/rv730_dpm.c
+++ b/drivers/gpu/drm/radeon/rv730_dpm.c
@@ -464,7 +464,7 @@ void rv730_stop_dpm(struct radeon_device *rdev)
 	result = rv770_send_msg_to_smc(rdev, PPSMC_MSG_TwoLevelsDisabled);
 
 	if (result != PPSMC_Result_OK)
-		DRM_ERROR("Could not force DPM to low\n");
+		DRM_DEBUG("Could not force DPM to low\n");
 
 	WREG32_P(GENERAL_PWRMGT, 0, ~GLOBAL_PWRMGT_EN);
 
diff --git a/drivers/gpu/drm/radeon/rv770_dpm.c b/drivers/gpu/drm/radeon/rv770_dpm.c
index b9c770745a7a..e830c8935db0 100644
--- a/drivers/gpu/drm/radeon/rv770_dpm.c
+++ b/drivers/gpu/drm/radeon/rv770_dpm.c
@@ -193,7 +193,7 @@ void rv770_stop_dpm(struct radeon_device *rdev)
 	result = rv770_send_msg_to_smc(rdev, PPSMC_MSG_TwoLevelsDisabled);
 
 	if (result != PPSMC_Result_OK)
-		DRM_ERROR("Could not force DPM to low.\n");
+		DRM_DEBUG("Could not force DPM to low.\n");
 
 	WREG32_P(GENERAL_PWRMGT, 0, ~GLOBAL_PWRMGT_EN);
 
@@ -1418,7 +1418,7 @@ int rv770_resume_smc(struct radeon_device *rdev)
 int rv770_set_sw_state(struct radeon_device *rdev)
 {
 	if (rv770_send_msg_to_smc(rdev, PPSMC_MSG_SwitchToSwState) != PPSMC_Result_OK)
-		return -EINVAL;
+		DRM_DEBUG("rv770_set_sw_state failed\n");
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 07037e32dea3..f878d6962da5 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2376,6 +2376,9 @@ static void dce6_program_watermarks(struct radeon_device *rdev,
 		c.full = dfixed_div(c, a);
 		priority_b_mark = dfixed_trunc(c);
 		priority_b_cnt |= priority_b_mark & PRIORITY_MARK_MASK;
+
+		/* Save number of lines the linebuffer leads before the scanout */
+		radeon_crtc->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
 	}
 
 	/* select wm A */
@@ -6848,7 +6851,7 @@ restart_ih:
 	if (queue_dp)
 		schedule_work(&rdev->dp_work);
 	if (queue_hotplug)
-		schedule_work(&rdev->hotplug_work);
+		schedule_delayed_work(&rdev->hotplug_work, 0);
 	if (queue_thermal && rdev->pm.dpm_enabled)
 		schedule_work(&rdev->pm.dpm.thermal.work);
 	rdev->ih.rptr = rptr;
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index e72bf46042e0..a82b891ae1fe 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2927,7 +2927,7 @@ static struct si_dpm_quirk si_dpm_quirk_list[] = {
 	{ PCI_VENDOR_ID_ATI, 0x6810, 0x1462, 0x3036, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0xe271, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6810, 0x174b, 0xe271, 85000, 90000 },
-	{ PCI_VENDOR_ID_ATI, 0x6811, 0x1762, 0x2015, 0, 120000 },
+	{ PCI_VENDOR_ID_ATI, 0x6811, 0x1462, 0x2015, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6811, 0x1043, 0x2015, 0, 120000 },
 	{ 0, 0, 0, 0 },
 };
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
index 8caea0a33dd8..d908321b94ce 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
@@ -67,6 +67,7 @@ static int rockchip_drm_gem_object_mmap(struct drm_gem_object *obj,
 	 * VM_PFNMAP flag that was set by drm_gem_mmap_obj()/drm_gem_mmap().
 	 */
 	vma->vm_flags &= ~VM_PFNMAP;
+	vma->vm_pgoff = 0;
 
 	ret = dma_mmap_attrs(drm->dev, vma, rk_obj->kvaddr, rk_obj->dma_addr,
 			     obj->size, &rk_obj->dma_attrs);
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index 5d8ae5e49c44..03c47eeadc81 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -374,6 +374,7 @@ static const struct of_device_id vop_driver_dt_match[] = {
 	  .data = &rk3288_vop },
 	{},
 };
+MODULE_DEVICE_TABLE(of, vop_driver_dt_match);
 
 static inline void vop_writel(struct vop *vop, uint32_t offset, uint32_t v)
 {
@@ -959,8 +960,8 @@ static int vop_update_plane_event(struct drm_plane *plane,
 	val = (dest.y2 - dest.y1 - 1) << 16;
 	val |= (dest.x2 - dest.x1 - 1) & 0xffff;
 	VOP_WIN_SET(vop, win, dsp_info, val);
-	val = (dsp_sty - 1) << 16;
-	val |= (dsp_stx - 1) & 0xffff;
+	val = dsp_sty << 16;
+	val |= dsp_stx & 0xffff;
 	VOP_WIN_SET(vop, win, dsp_st, val);
 	VOP_WIN_SET(vop, win, rb_swap, rb_swap);
 
@@ -1289,7 +1290,7 @@ static void vop_win_state_complete(struct vop_win *vop_win,
 
 	if (state->event) {
 		spin_lock_irqsave(&drm->event_lock, flags);
-		drm_send_vblank_event(drm, -1, state->event);
+		drm_crtc_send_vblank_event(crtc, state->event);
 		spin_unlock_irqrestore(&drm->event_lock, flags);
 	}
 
@@ -1575,32 +1576,25 @@ static int vop_initial(struct vop *vop)
 		return PTR_ERR(vop->dclk);
 	}
 
-	ret = clk_prepare(vop->hclk);
-	if (ret < 0) {
-		dev_err(vop->dev, "failed to prepare hclk\n");
-		return ret;
-	}
-
 	ret = clk_prepare(vop->dclk);
 	if (ret < 0) {
 		dev_err(vop->dev, "failed to prepare dclk\n");
-		goto err_unprepare_hclk;
+		return ret;
 	}
 
-	ret = clk_prepare(vop->aclk);
+	/* Enable both the hclk and aclk to setup the vop */
+	ret = clk_prepare_enable(vop->hclk);
 	if (ret < 0) {
-		dev_err(vop->dev, "failed to prepare aclk\n");
+		dev_err(vop->dev, "failed to prepare/enable hclk\n");
 		goto err_unprepare_dclk;
 	}
 
-	/*
-	 * enable hclk, so that we can config vop register.
-	 */
-	ret = clk_enable(vop->hclk);
+	ret = clk_prepare_enable(vop->aclk);
 	if (ret < 0) {
-		dev_err(vop->dev, "failed to prepare aclk\n");
-		goto err_unprepare_aclk;
+		dev_err(vop->dev, "failed to prepare/enable aclk\n");
+		goto err_disable_hclk;
 	}
+
 	/*
 	 * do hclk_reset, reset all vop registers.
 	 */
@@ -1608,7 +1602,7 @@ static int vop_initial(struct vop *vop)
 	if (IS_ERR(ahb_rst)) {
 		dev_err(vop->dev, "failed to get ahb reset\n");
 		ret = PTR_ERR(ahb_rst);
-		goto err_disable_hclk;
+		goto err_disable_aclk;
 	}
 	reset_control_assert(ahb_rst);
 	usleep_range(10, 20);
@@ -1634,26 +1628,25 @@ static int vop_initial(struct vop *vop)
 	if (IS_ERR(vop->dclk_rst)) {
 		dev_err(vop->dev, "failed to get dclk reset\n");
 		ret = PTR_ERR(vop->dclk_rst);
-		goto err_unprepare_aclk;
+		goto err_disable_aclk;
 	}
 	reset_control_assert(vop->dclk_rst);
 	usleep_range(10, 20);
 	reset_control_deassert(vop->dclk_rst);
 
 	clk_disable(vop->hclk);
+	clk_disable(vop->aclk);
 
 	vop->is_enabled = false;
 
 	return 0;
 
+err_disable_aclk:
+	clk_disable_unprepare(vop->aclk);
 err_disable_hclk:
-	clk_disable(vop->hclk);
-err_unprepare_aclk:
-	clk_unprepare(vop->aclk);
+	clk_disable_unprepare(vop->hclk);
 err_unprepare_dclk:
 	clk_unprepare(vop->dclk);
-err_unprepare_hclk:
-	clk_unprepare(vop->hclk);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index 7a9f4768591e..265064c62d49 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -168,7 +168,7 @@ static int vc4_get_clock_select(struct drm_crtc *crtc)
 	struct drm_connector *connector;
 
 	drm_for_each_connector(connector, crtc->dev) {
-		if (connector && connector->state->crtc == crtc) {
+		if (connector->state->crtc == crtc) {
 			struct drm_encoder *encoder = connector->encoder;
 			struct vc4_encoder *vc4_encoder =
 				to_vc4_encoder(encoder);
@@ -401,7 +401,8 @@ static void vc4_crtc_atomic_flush(struct drm_crtc *crtc,
 		dlist_next++;
 
 		HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel),
-			  (u32 *)vc4_crtc->dlist - (u32 *)vc4->hvs->dlist);
+			  (u32 __iomem *)vc4_crtc->dlist -
+			  (u32 __iomem *)vc4->hvs->dlist);
 
 		/* Make the next display list start after ours. */
 		vc4_crtc->dlist_size -= (dlist_next - vc4_crtc->dlist);
@@ -591,14 +592,14 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data)
 	 * that will take too much.
 	 */
 	primary_plane = vc4_plane_init(drm, DRM_PLANE_TYPE_PRIMARY);
-	if (!primary_plane) {
+	if (IS_ERR(primary_plane)) {
 		dev_err(dev, "failed to construct primary plane\n");
 		ret = PTR_ERR(primary_plane);
 		goto err;
 	}
 
 	cursor_plane = vc4_plane_init(drm, DRM_PLANE_TYPE_CURSOR);
-	if (!cursor_plane) {
+	if (IS_ERR(cursor_plane)) {
 		dev_err(dev, "failed to construct cursor plane\n");
 		ret = PTR_ERR(cursor_plane);
 		goto err_primary;
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 6e730605edcc..d5db9e0f3b73 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -259,7 +259,6 @@ static struct platform_driver vc4_platform_driver = {
 	.remove		= vc4_platform_drm_remove,
 	.driver		= {
 		.name	= "vc4-drm",
-		.owner	= THIS_MODULE,
 		.of_match_table = vc4_of_match,
 	},
 };
diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c
index ab1673f672a4..8098c5b21ba4 100644
--- a/drivers/gpu/drm/vc4/vc4_hvs.c
+++ b/drivers/gpu/drm/vc4/vc4_hvs.c
@@ -75,10 +75,10 @@ void vc4_hvs_dump_state(struct drm_device *dev)
 	for (i = 0; i < 64; i += 4) {
 		DRM_INFO("0x%08x (%s): 0x%08x 0x%08x 0x%08x 0x%08x\n",
 			 i * 4, i < HVS_BOOTLOADER_DLIST_END ? "B" : "D",
-			 ((uint32_t *)vc4->hvs->dlist)[i + 0],
-			 ((uint32_t *)vc4->hvs->dlist)[i + 1],
-			 ((uint32_t *)vc4->hvs->dlist)[i + 2],
-			 ((uint32_t *)vc4->hvs->dlist)[i + 3]);
+			 readl((u32 __iomem *)vc4->hvs->dlist + i + 0),
+			 readl((u32 __iomem *)vc4->hvs->dlist + i + 1),
+			 readl((u32 __iomem *)vc4->hvs->dlist + i + 2),
+			 readl((u32 __iomem *)vc4->hvs->dlist + i + 3));
 	}
 }
 
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index cdd8b10c0147..887f3caad0be 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -70,7 +70,7 @@ static bool plane_enabled(struct drm_plane_state *state)
 	return state->fb && state->crtc;
 }
 
-struct drm_plane_state *vc4_plane_duplicate_state(struct drm_plane *plane)
+static struct drm_plane_state *vc4_plane_duplicate_state(struct drm_plane *plane)
 {
 	struct vc4_plane_state *vc4_state;
 
@@ -97,8 +97,8 @@ struct drm_plane_state *vc4_plane_duplicate_state(struct drm_plane *plane)
 	return &vc4_state->base;
 }
 
-void vc4_plane_destroy_state(struct drm_plane *plane,
-			     struct drm_plane_state *state)
+static void vc4_plane_destroy_state(struct drm_plane *plane,
+				    struct drm_plane_state *state)
 {
 	struct vc4_plane_state *vc4_state = to_vc4_plane_state(state);
 
@@ -108,7 +108,7 @@ void vc4_plane_destroy_state(struct drm_plane *plane,
 }
 
 /* Called during init to allocate the plane's atomic state. */
-void vc4_plane_reset(struct drm_plane *plane)
+static void vc4_plane_reset(struct drm_plane *plane)
 {
 	struct vc4_plane_state *vc4_state;
 
@@ -157,6 +157,16 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 	int crtc_w = state->crtc_w;
 	int crtc_h = state->crtc_h;
 
+	if (state->crtc_w << 16 != state->src_w ||
+	    state->crtc_h << 16 != state->src_h) {
+		/* We don't support scaling yet, which involves
+		 * allocating the LBM memory for scaling temporary
+		 * storage, and putting filter kernels in the HVS
+		 * context.
+		 */
+		return -EINVAL;
+	}
+
 	if (crtc_x < 0) {
 		offset += drm_format_plane_cpp(fb->pixel_format, 0) * -crtc_x;
 		crtc_w += crtc_x;
diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c
index f545913a56c7..578fe0a9324c 100644
--- a/drivers/gpu/drm/virtio/virtgpu_display.c
+++ b/drivers/gpu/drm/virtio/virtgpu_display.c
@@ -412,7 +412,7 @@ static const struct drm_connector_funcs virtio_gpu_connector_funcs = {
 	.save = virtio_gpu_conn_save,
 	.restore = virtio_gpu_conn_restore,
 	.detect = virtio_gpu_conn_detect,
-	.fill_modes = drm_helper_probe_single_connector_modes,
+	.fill_modes = drm_helper_probe_single_connector_modes_nomerge,
 	.destroy = virtio_gpu_conn_destroy,
 	.reset = drm_atomic_helper_connector_reset,
 	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index ba47b30d28fa..f2e13eb8339f 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -28,6 +28,7 @@
 #include <linux/irqchip/chained_irq.h>
 #include <linux/irqdomain.h>
 #include <linux/of_device.h>
+#include <linux/of_graph.h>
 
 #include <drm/drm_fourcc.h>
 
@@ -993,12 +994,26 @@ static void platform_device_unregister_children(struct platform_device *pdev)
 struct ipu_platform_reg {
 	struct ipu_client_platformdata pdata;
 	const char *name;
-	int reg_offset;
 };
 
+/* These must be in the order of the corresponding device tree port nodes */
 static const struct ipu_platform_reg client_reg[] = {
 	{
 		.pdata = {
+			.csi = 0,
+			.dma[0] = IPUV3_CHANNEL_CSI0,
+			.dma[1] = -EINVAL,
+		},
+		.name = "imx-ipuv3-camera",
+	}, {
+		.pdata = {
+			.csi = 1,
+			.dma[0] = IPUV3_CHANNEL_CSI1,
+			.dma[1] = -EINVAL,
+		},
+		.name = "imx-ipuv3-camera",
+	}, {
+		.pdata = {
 			.di = 0,
 			.dc = 5,
 			.dp = IPU_DP_FLOW_SYNC_BG,
@@ -1015,22 +1030,6 @@ static const struct ipu_platform_reg client_reg[] = {
 			.dma[1] = -EINVAL,
 		},
 		.name = "imx-ipuv3-crtc",
-	}, {
-		.pdata = {
-			.csi = 0,
-			.dma[0] = IPUV3_CHANNEL_CSI0,
-			.dma[1] = -EINVAL,
-		},
-		.reg_offset = IPU_CM_CSI0_REG_OFS,
-		.name = "imx-ipuv3-camera",
-	}, {
-		.pdata = {
-			.csi = 1,
-			.dma[0] = IPUV3_CHANNEL_CSI1,
-			.dma[1] = -EINVAL,
-		},
-		.reg_offset = IPU_CM_CSI1_REG_OFS,
-		.name = "imx-ipuv3-camera",
 	},
 };
 
@@ -1051,22 +1050,30 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base)
 	for (i = 0; i < ARRAY_SIZE(client_reg); i++) {
 		const struct ipu_platform_reg *reg = &client_reg[i];
 		struct platform_device *pdev;
-		struct resource res;
-
-		if (reg->reg_offset) {
-			memset(&res, 0, sizeof(res));
-			res.flags = IORESOURCE_MEM;
-			res.start = ipu_base + ipu->devtype->cm_ofs + reg->reg_offset;
-			res.end = res.start + PAGE_SIZE - 1;
-			pdev = platform_device_register_resndata(dev, reg->name,
-				id++, &res, 1, &reg->pdata, sizeof(reg->pdata));
-		} else {
-			pdev = platform_device_register_data(dev, reg->name,
-				id++, &reg->pdata, sizeof(reg->pdata));
+
+		pdev = platform_device_alloc(reg->name, id++);
+		if (!pdev) {
+			ret = -ENOMEM;
+			goto err_register;
+		}
+
+		pdev->dev.parent = dev;
+
+		/* Associate subdevice with the corresponding port node */
+		pdev->dev.of_node = of_graph_get_port_by_id(dev->of_node, i);
+		if (!pdev->dev.of_node) {
+			dev_err(dev, "missing port@%d node in %s\n", i,
+				dev->of_node->full_name);
+			ret = -ENODEV;
+			goto err_register;
 		}
 
-		if (IS_ERR(pdev)) {
-			ret = PTR_ERR(pdev);
+		ret = platform_device_add_data(pdev, &reg->pdata,
+					       sizeof(reg->pdata));
+		if (!ret)
+			ret = platform_device_add(pdev);
+		if (ret) {
+			platform_device_put(pdev);
 			goto err_register;
 		}
 	}
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index ac1feea51be3..9024a3de4032 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -609,6 +609,7 @@
 #define USB_DEVICE_ID_LOGITECH_HARMONY_FIRST  0xc110
 #define USB_DEVICE_ID_LOGITECH_HARMONY_LAST 0xc14f
 #define USB_DEVICE_ID_LOGITECH_HARMONY_PS3 0x0306
+#define USB_DEVICE_ID_LOGITECH_KEYBOARD_G710_PLUS 0xc24d
 #define USB_DEVICE_ID_LOGITECH_MOUSE_C01A	0xc01a
 #define USB_DEVICE_ID_LOGITECH_MOUSE_C05A	0xc05a
 #define USB_DEVICE_ID_LOGITECH_MOUSE_C06A	0xc06a
diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c
index c20ac76c0a8c..c690fae02cf8 100644
--- a/drivers/hid/hid-lg.c
+++ b/drivers/hid/hid-lg.c
@@ -665,8 +665,9 @@ static int lg_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	struct lg_drv_data *drv_data;
 	int ret;
 
-	/* Only work with the 1st interface (G29 presents multiple) */
-	if (iface_num != 0) {
+	/* G29 only work with the 1st interface */
+	if ((hdev->product == USB_DEVICE_ID_LOGITECH_G29_WHEEL) &&
+	    (iface_num != 0)) {
 		dbg_hid("%s: ignoring ifnum %d\n", __func__, iface_num);
 		return -ENODEV;
 	}
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index 94bb137abe32..2324520b006d 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -84,6 +84,7 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0B4A, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C077, HID_QUIRK_ALWAYS_POLL },
+	{ USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_KEYBOARD_G710_PLUS, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C01A, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C05A, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C06A, HID_QUIRK_ALWAYS_POLL },
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 8b29949507d1..01a4f05c1642 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -2481,7 +2481,7 @@ void wacom_setup_device_quirks(struct wacom *wacom)
 		if (features->pktlen == WACOM_PKGLEN_BBTOUCH3) {
 			if (features->touch_max)
 				features->device_type |= WACOM_DEVICETYPE_TOUCH;
-			if (features->type >= INTUOSHT || features->type <= BAMBOO_PT)
+			if (features->type >= INTUOSHT && features->type <= BAMBOO_PT)
 				features->device_type |= WACOM_DEVICETYPE_PAD;
 
 			features->x_max = 4096;
@@ -3213,7 +3213,8 @@ static const struct wacom_features wacom_features_0x32F =
 	  WACOM_DTU_OFFSET, WACOM_DTU_OFFSET };
 static const struct wacom_features wacom_features_0x336 =
 	{ "Wacom DTU1141", 23472, 13203, 1023, 0,
-	  DTUS, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 4 };
+	  DTUS, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 4,
+	  WACOM_DTU_OFFSET, WACOM_DTU_OFFSET };
 static const struct wacom_features wacom_features_0x57 =
 	{ "Wacom DTK2241", 95640, 54060, 2047, 63,
 	  DTK, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, 6,
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 842b0043ad94..8f59f057cdf4 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -324,6 +324,7 @@ config SENSORS_APPLESMC
 config SENSORS_ARM_SCPI
 	tristate "ARM SCPI Sensors"
 	depends on ARM_SCPI_PROTOCOL
+	depends on THERMAL || !THERMAL_OF
 	help
 	  This driver provides support for temperature, voltage, current
 	  and power sensors available on ARM Ltd's SCP based platforms. The
@@ -1471,6 +1472,7 @@ config SENSORS_INA209
 config SENSORS_INA2XX
 	tristate "Texas Instruments INA219 and compatibles"
 	depends on I2C
+	select REGMAP_I2C
 	help
 	  If you say yes here you get support for INA219, INA220, INA226,
 	  INA230, and INA231 power monitor chips.
diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c
index 1f5e956941b1..0af7fd311979 100644
--- a/drivers/hwmon/applesmc.c
+++ b/drivers/hwmon/applesmc.c
@@ -537,7 +537,7 @@ static int applesmc_init_index(struct applesmc_registers *s)
 static int applesmc_init_smcreg_try(void)
 {
 	struct applesmc_registers *s = &smcreg;
-	bool left_light_sensor, right_light_sensor;
+	bool left_light_sensor = 0, right_light_sensor = 0;
 	unsigned int count;
 	u8 tmp[1];
 	int ret;
diff --git a/drivers/hwmon/scpi-hwmon.c b/drivers/hwmon/scpi-hwmon.c
index 2c1241bbf9af..7e20567bc369 100644
--- a/drivers/hwmon/scpi-hwmon.c
+++ b/drivers/hwmon/scpi-hwmon.c
@@ -117,7 +117,7 @@ static int scpi_hwmon_probe(struct platform_device *pdev)
 	struct scpi_ops *scpi_ops;
 	struct device *hwdev, *dev = &pdev->dev;
 	struct scpi_sensors *scpi_sensors;
-	int ret;
+	int ret, idx;
 
 	scpi_ops = get_scpi_ops();
 	if (!scpi_ops)
@@ -146,8 +146,8 @@ static int scpi_hwmon_probe(struct platform_device *pdev)
 
 	scpi_sensors->scpi_ops = scpi_ops;
 
-	for (i = 0; i < nr_sensors; i++) {
-		struct sensor_data *sensor = &scpi_sensors->data[i];
+	for (i = 0, idx = 0; i < nr_sensors; i++) {
+		struct sensor_data *sensor = &scpi_sensors->data[idx];
 
 		ret = scpi_ops->sensor_get_info(i, &sensor->info);
 		if (ret)
@@ -183,7 +183,7 @@ static int scpi_hwmon_probe(struct platform_device *pdev)
 			num_power++;
 			break;
 		default:
-			break;
+			continue;
 		}
 
 		sensor->dev_attr_input.attr.mode = S_IRUGO;
@@ -194,11 +194,12 @@ static int scpi_hwmon_probe(struct platform_device *pdev)
 		sensor->dev_attr_label.show = scpi_show_label;
 		sensor->dev_attr_label.attr.name = sensor->label;
 
-		scpi_sensors->attrs[i << 1] = &sensor->dev_attr_input.attr;
-		scpi_sensors->attrs[(i << 1) + 1] = &sensor->dev_attr_label.attr;
+		scpi_sensors->attrs[idx << 1] = &sensor->dev_attr_input.attr;
+		scpi_sensors->attrs[(idx << 1) + 1] = &sensor->dev_attr_label.attr;
 
-		sysfs_attr_init(scpi_sensors->attrs[i << 1]);
-		sysfs_attr_init(scpi_sensors->attrs[(i << 1) + 1]);
+		sysfs_attr_init(scpi_sensors->attrs[idx << 1]);
+		sysfs_attr_init(scpi_sensors->attrs[(idx << 1) + 1]);
+		idx++;
 	}
 
 	scpi_sensors->group.attrs = scpi_sensors->attrs;
@@ -236,8 +237,8 @@ static int scpi_hwmon_probe(struct platform_device *pdev)
 
 		zone->sensor_id = i;
 		zone->scpi_sensors = scpi_sensors;
-		zone->tzd = thermal_zone_of_sensor_register(dev, i, zone,
-							    &scpi_sensor_ops);
+		zone->tzd = thermal_zone_of_sensor_register(dev,
+				sensor->info.sensor_id, zone, &scpi_sensor_ops);
 		/*
 		 * The call to thermal_zone_of_sensor_register returns
 		 * an error for sensors that are not associated with
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index e24c2b680b47..7b0aa82ea38b 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -126,6 +126,7 @@ config I2C_I801
 	    Sunrise Point-LP (PCH)
 	    DNV (SOC)
 	    Broxton (SOC)
+	    Lewisburg (PCH)
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called i2c-i801.
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index c306751ceadb..f62d69799a9c 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -62,6 +62,8 @@
  * Sunrise Point-LP (PCH)	0x9d23	32	hard	yes	yes	yes
  * DNV (SOC)			0x19df	32	hard	yes	yes	yes
  * Broxton (SOC)		0x5ad4	32	hard	yes	yes	yes
+ * Lewisburg (PCH)		0xa1a3	32	hard	yes	yes	yes
+ * Lewisburg Supersku (PCH)	0xa223	32	hard	yes	yes	yes
  *
  * Features supported by this driver:
  * Software PEC				no
@@ -206,6 +208,8 @@
 #define PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_SMBUS	0x9d23
 #define PCI_DEVICE_ID_INTEL_DNV_SMBUS			0x19df
 #define PCI_DEVICE_ID_INTEL_BROXTON_SMBUS		0x5ad4
+#define PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS		0xa1a3
+#define PCI_DEVICE_ID_INTEL_LEWISBURG_SSKU_SMBUS	0xa223
 
 struct i801_mux_config {
 	char *gpio_chip;
@@ -869,6 +873,8 @@ static const struct pci_device_id i801_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_DNV_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BROXTON_SMBUS) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_LEWISBURG_SSKU_SMBUS) },
 	{ 0, }
 };
 
diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index 1e4d99da4164..9bb0b056b25f 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -50,6 +50,7 @@
 #include <linux/of_device.h>
 #include <linux/of_dma.h>
 #include <linux/of_gpio.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_data/i2c-imx.h>
 #include <linux/platform_device.h>
 #include <linux/sched.h>
diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c
index e23a7b068c60..0b20449e48cf 100644
--- a/drivers/i2c/busses/i2c-xiic.c
+++ b/drivers/i2c/busses/i2c-xiic.c
@@ -662,8 +662,10 @@ static void __xiic_start_xfer(struct xiic_i2c *i2c)
 
 static void xiic_start_xfer(struct xiic_i2c *i2c)
 {
-
+	spin_lock(&i2c->lock);
+	xiic_reinit(i2c);
 	__xiic_start_xfer(i2c);
+	spin_unlock(&i2c->lock);
 }
 
 static int xiic_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num)
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 040af5cc8143..ba8eb087f224 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -715,7 +715,7 @@ static int i2c_device_probe(struct device *dev)
 		if (wakeirq > 0 && wakeirq != client->irq)
 			status = dev_pm_set_dedicated_wake_irq(dev, wakeirq);
 		else if (client->irq > 0)
-			status = dev_pm_set_wake_irq(dev, wakeirq);
+			status = dev_pm_set_wake_irq(dev, client->irq);
 		else
 			status = 0;
 
diff --git a/drivers/iio/adc/ad7793.c b/drivers/iio/adc/ad7793.c
index eea0c79111e7..4d960d3b93c0 100644
--- a/drivers/iio/adc/ad7793.c
+++ b/drivers/iio/adc/ad7793.c
@@ -101,7 +101,7 @@
 #define AD7795_CH_AIN1M_AIN1M	8 /* AIN1(-) - AIN1(-) */
 
 /* ID Register Bit Designations (AD7793_REG_ID) */
-#define AD7785_ID		0xB
+#define AD7785_ID		0x3
 #define AD7792_ID		0xA
 #define AD7793_ID		0xB
 #define AD7794_ID		0xF
diff --git a/drivers/iio/adc/vf610_adc.c b/drivers/iio/adc/vf610_adc.c
index 599cde3d03a1..b10f629cc44b 100644
--- a/drivers/iio/adc/vf610_adc.c
+++ b/drivers/iio/adc/vf610_adc.c
@@ -106,6 +106,13 @@
 
 #define DEFAULT_SAMPLE_TIME		1000
 
+/* V at 25°C of 696 mV */
+#define VF610_VTEMP25_3V0		950
+/* V at 25°C of 699 mV */
+#define VF610_VTEMP25_3V3		867
+/* Typical sensor slope coefficient at all temperatures */
+#define VF610_TEMP_SLOPE_COEFF		1840
+
 enum clk_sel {
 	VF610_ADCIOC_BUSCLK_SET,
 	VF610_ADCIOC_ALTCLK_SET,
@@ -197,6 +204,8 @@ static inline void vf610_adc_calculate_rates(struct vf610_adc *info)
 		adc_feature->clk_div = 8;
 	}
 
+	adck_rate = ipg_rate / adc_feature->clk_div;
+
 	/*
 	 * Determine the long sample time adder value to be used based
 	 * on the default minimum sample time provided.
@@ -221,7 +230,6 @@ static inline void vf610_adc_calculate_rates(struct vf610_adc *info)
 	 * BCT (Base Conversion Time): fixed to 25 ADCK cycles for 12 bit mode
 	 * LSTAdder(Long Sample Time): 3, 5, 7, 9, 13, 17, 21, 25 ADCK cycles
 	 */
-	adck_rate = ipg_rate / info->adc_feature.clk_div;
 	for (i = 0; i < ARRAY_SIZE(vf610_hw_avgs); i++)
 		info->sample_freq_avail[i] =
 			adck_rate / (6 + vf610_hw_avgs[i] *
@@ -663,11 +671,13 @@ static int vf610_read_raw(struct iio_dev *indio_dev,
 			break;
 		case IIO_TEMP:
 			/*
-			* Calculate in degree Celsius times 1000
-			* Using sensor slope of 1.84 mV/°C and
-			* V at 25°C of 696 mV
-			*/
-			*val = 25000 - ((int)info->value - 864) * 1000000 / 1840;
+			 * Calculate in degree Celsius times 1000
+			 * Using the typical sensor slope of 1.84 mV/°C
+			 * and VREFH_ADC at 3.3V, V at 25°C of 699 mV
+			 */
+			*val = 25000 - ((int)info->value - VF610_VTEMP25_3V3) *
+					1000000 / VF610_TEMP_SLOPE_COEFF;
+
 			break;
 		default:
 			mutex_unlock(&indio_dev->mlock);
diff --git a/drivers/iio/adc/xilinx-xadc-core.c b/drivers/iio/adc/xilinx-xadc-core.c
index 0370624a35db..02e636a1c49a 100644
--- a/drivers/iio/adc/xilinx-xadc-core.c
+++ b/drivers/iio/adc/xilinx-xadc-core.c
@@ -841,6 +841,7 @@ static int xadc_read_raw(struct iio_dev *indio_dev,
 			case XADC_REG_VCCINT:
 			case XADC_REG_VCCAUX:
 			case XADC_REG_VREFP:
+			case XADC_REG_VREFN:
 			case XADC_REG_VCCBRAM:
 			case XADC_REG_VCCPINT:
 			case XADC_REG_VCCPAUX:
diff --git a/drivers/iio/dac/ad5064.c b/drivers/iio/dac/ad5064.c
index 9e4d2c18b554..81ca0081a019 100644
--- a/drivers/iio/dac/ad5064.c
+++ b/drivers/iio/dac/ad5064.c
@@ -113,12 +113,16 @@ enum ad5064_type {
 	ID_AD5065,
 	ID_AD5628_1,
 	ID_AD5628_2,
+	ID_AD5629_1,
+	ID_AD5629_2,
 	ID_AD5648_1,
 	ID_AD5648_2,
 	ID_AD5666_1,
 	ID_AD5666_2,
 	ID_AD5668_1,
 	ID_AD5668_2,
+	ID_AD5669_1,
+	ID_AD5669_2,
 };
 
 static int ad5064_write(struct ad5064_state *st, unsigned int cmd,
@@ -291,7 +295,7 @@ static const struct iio_chan_spec_ext_info ad5064_ext_info[] = {
 	{ },
 };
 
-#define AD5064_CHANNEL(chan, addr, bits) {			\
+#define AD5064_CHANNEL(chan, addr, bits, _shift) {		\
 	.type = IIO_VOLTAGE,					\
 	.indexed = 1,						\
 	.output = 1,						\
@@ -303,36 +307,39 @@ static const struct iio_chan_spec_ext_info ad5064_ext_info[] = {
 		.sign = 'u',					\
 		.realbits = (bits),				\
 		.storagebits = 16,				\
-		.shift = 20 - bits,				\
+		.shift = (_shift),				\
 	},							\
 	.ext_info = ad5064_ext_info,				\
 }
 
-#define DECLARE_AD5064_CHANNELS(name, bits) \
+#define DECLARE_AD5064_CHANNELS(name, bits, shift) \
 const struct iio_chan_spec name[] = { \
-	AD5064_CHANNEL(0, 0, bits), \
-	AD5064_CHANNEL(1, 1, bits), \
-	AD5064_CHANNEL(2, 2, bits), \
-	AD5064_CHANNEL(3, 3, bits), \
-	AD5064_CHANNEL(4, 4, bits), \
-	AD5064_CHANNEL(5, 5, bits), \
-	AD5064_CHANNEL(6, 6, bits), \
-	AD5064_CHANNEL(7, 7, bits), \
+	AD5064_CHANNEL(0, 0, bits, shift), \
+	AD5064_CHANNEL(1, 1, bits, shift), \
+	AD5064_CHANNEL(2, 2, bits, shift), \
+	AD5064_CHANNEL(3, 3, bits, shift), \
+	AD5064_CHANNEL(4, 4, bits, shift), \
+	AD5064_CHANNEL(5, 5, bits, shift), \
+	AD5064_CHANNEL(6, 6, bits, shift), \
+	AD5064_CHANNEL(7, 7, bits, shift), \
 }
 
-#define DECLARE_AD5065_CHANNELS(name, bits) \
+#define DECLARE_AD5065_CHANNELS(name, bits, shift) \
 const struct iio_chan_spec name[] = { \
-	AD5064_CHANNEL(0, 0, bits), \
-	AD5064_CHANNEL(1, 3, bits), \
+	AD5064_CHANNEL(0, 0, bits, shift), \
+	AD5064_CHANNEL(1, 3, bits, shift), \
 }
 
-static DECLARE_AD5064_CHANNELS(ad5024_channels, 12);
-static DECLARE_AD5064_CHANNELS(ad5044_channels, 14);
-static DECLARE_AD5064_CHANNELS(ad5064_channels, 16);
+static DECLARE_AD5064_CHANNELS(ad5024_channels, 12, 8);
+static DECLARE_AD5064_CHANNELS(ad5044_channels, 14, 6);
+static DECLARE_AD5064_CHANNELS(ad5064_channels, 16, 4);
 
-static DECLARE_AD5065_CHANNELS(ad5025_channels, 12);
-static DECLARE_AD5065_CHANNELS(ad5045_channels, 14);
-static DECLARE_AD5065_CHANNELS(ad5065_channels, 16);
+static DECLARE_AD5065_CHANNELS(ad5025_channels, 12, 8);
+static DECLARE_AD5065_CHANNELS(ad5045_channels, 14, 6);
+static DECLARE_AD5065_CHANNELS(ad5065_channels, 16, 4);
+
+static DECLARE_AD5064_CHANNELS(ad5629_channels, 12, 4);
+static DECLARE_AD5064_CHANNELS(ad5669_channels, 16, 0);
 
 static const struct ad5064_chip_info ad5064_chip_info_tbl[] = {
 	[ID_AD5024] = {
@@ -382,6 +389,18 @@ static const struct ad5064_chip_info ad5064_chip_info_tbl[] = {
 		.channels = ad5024_channels,
 		.num_channels = 8,
 	},
+	[ID_AD5629_1] = {
+		.shared_vref = true,
+		.internal_vref = 2500000,
+		.channels = ad5629_channels,
+		.num_channels = 8,
+	},
+	[ID_AD5629_2] = {
+		.shared_vref = true,
+		.internal_vref = 5000000,
+		.channels = ad5629_channels,
+		.num_channels = 8,
+	},
 	[ID_AD5648_1] = {
 		.shared_vref = true,
 		.internal_vref = 2500000,
@@ -418,6 +437,18 @@ static const struct ad5064_chip_info ad5064_chip_info_tbl[] = {
 		.channels = ad5064_channels,
 		.num_channels = 8,
 	},
+	[ID_AD5669_1] = {
+		.shared_vref = true,
+		.internal_vref = 2500000,
+		.channels = ad5669_channels,
+		.num_channels = 8,
+	},
+	[ID_AD5669_2] = {
+		.shared_vref = true,
+		.internal_vref = 5000000,
+		.channels = ad5669_channels,
+		.num_channels = 8,
+	},
 };
 
 static inline unsigned int ad5064_num_vref(struct ad5064_state *st)
@@ -597,10 +628,16 @@ static int ad5064_i2c_write(struct ad5064_state *st, unsigned int cmd,
 	unsigned int addr, unsigned int val)
 {
 	struct i2c_client *i2c = to_i2c_client(st->dev);
+	int ret;
 
 	st->data.i2c[0] = (cmd << 4) | addr;
 	put_unaligned_be16(val, &st->data.i2c[1]);
-	return i2c_master_send(i2c, st->data.i2c, 3);
+
+	ret = i2c_master_send(i2c, st->data.i2c, 3);
+	if (ret < 0)
+		return ret;
+
+	return 0;
 }
 
 static int ad5064_i2c_probe(struct i2c_client *i2c,
@@ -616,12 +653,12 @@ static int ad5064_i2c_remove(struct i2c_client *i2c)
 }
 
 static const struct i2c_device_id ad5064_i2c_ids[] = {
-	{"ad5629-1", ID_AD5628_1},
-	{"ad5629-2", ID_AD5628_2},
-	{"ad5629-3", ID_AD5628_2}, /* similar enough to ad5629-2 */
-	{"ad5669-1", ID_AD5668_1},
-	{"ad5669-2", ID_AD5668_2},
-	{"ad5669-3", ID_AD5668_2}, /* similar enough to ad5669-2 */
+	{"ad5629-1", ID_AD5629_1},
+	{"ad5629-2", ID_AD5629_2},
+	{"ad5629-3", ID_AD5629_2}, /* similar enough to ad5629-2 */
+	{"ad5669-1", ID_AD5669_1},
+	{"ad5669-2", ID_AD5669_2},
+	{"ad5669-3", ID_AD5669_2}, /* similar enough to ad5669-2 */
 	{}
 };
 MODULE_DEVICE_TABLE(i2c, ad5064_i2c_ids);
diff --git a/drivers/iio/humidity/si7020.c b/drivers/iio/humidity/si7020.c
index 12128d1ca570..71991b5c0658 100644
--- a/drivers/iio/humidity/si7020.c
+++ b/drivers/iio/humidity/si7020.c
@@ -50,10 +50,10 @@ static int si7020_read_raw(struct iio_dev *indio_dev,
 
 	switch (mask) {
 	case IIO_CHAN_INFO_RAW:
-		ret = i2c_smbus_read_word_data(*client,
-					       chan->type == IIO_TEMP ?
-					       SI7020CMD_TEMP_HOLD :
-					       SI7020CMD_RH_HOLD);
+		ret = i2c_smbus_read_word_swapped(*client,
+						  chan->type == IIO_TEMP ?
+						  SI7020CMD_TEMP_HOLD :
+						  SI7020CMD_RH_HOLD);
 		if (ret < 0)
 			return ret;
 		*val = ret >> 2;
diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c
index cbe198cb3699..471ee36b9c6e 100644
--- a/drivers/iommu/s390-iommu.c
+++ b/drivers/iommu/s390-iommu.c
@@ -216,6 +216,7 @@ static int s390_iommu_update_trans(struct s390_domain *s390_domain,
 	u8 *page_addr = (u8 *) (pa & PAGE_MASK);
 	dma_addr_t start_dma_addr = dma_addr;
 	unsigned long irq_flags, nr_pages, i;
+	unsigned long *entry;
 	int rc = 0;
 
 	if (dma_addr < s390_domain->domain.geometry.aperture_start ||
@@ -228,8 +229,12 @@ static int s390_iommu_update_trans(struct s390_domain *s390_domain,
 
 	spin_lock_irqsave(&s390_domain->dma_table_lock, irq_flags);
 	for (i = 0; i < nr_pages; i++) {
-		dma_update_cpu_trans(s390_domain->dma_table, page_addr,
-				     dma_addr, flags);
+		entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr);
+		if (!entry) {
+			rc = -ENOMEM;
+			goto undo_cpu_trans;
+		}
+		dma_update_cpu_trans(entry, page_addr, flags);
 		page_addr += PAGE_SIZE;
 		dma_addr += PAGE_SIZE;
 	}
@@ -242,6 +247,20 @@ static int s390_iommu_update_trans(struct s390_domain *s390_domain,
 			break;
 	}
 	spin_unlock(&s390_domain->list_lock);
+
+undo_cpu_trans:
+	if (rc && ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID)) {
+		flags = ZPCI_PTE_INVALID;
+		while (i-- > 0) {
+			page_addr -= PAGE_SIZE;
+			dma_addr -= PAGE_SIZE;
+			entry = dma_walk_cpu_trans(s390_domain->dma_table,
+						   dma_addr);
+			if (!entry)
+				break;
+			dma_update_cpu_trans(entry, page_addr, flags);
+		}
+	}
 	spin_unlock_irqrestore(&s390_domain->dma_table_lock, irq_flags);
 
 	return rc;
diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c
index 44a077f3a4a2..f174ce0ca361 100644
--- a/drivers/irqchip/irq-gic-common.c
+++ b/drivers/irqchip/irq-gic-common.c
@@ -84,12 +84,15 @@ void __init gic_dist_config(void __iomem *base, int gic_irqs,
 		writel_relaxed(GICD_INT_DEF_PRI_X4, base + GIC_DIST_PRI + i);
 
 	/*
-	 * Disable all interrupts.  Leave the PPI and SGIs alone
-	 * as they are enabled by redistributor registers.
+	 * Deactivate and disable all SPIs. Leave the PPI and SGIs
+	 * alone as they are in the redistributor registers on GICv3.
 	 */
-	for (i = 32; i < gic_irqs; i += 32)
+	for (i = 32; i < gic_irqs; i += 32) {
 		writel_relaxed(GICD_INT_EN_CLR_X32,
-					base + GIC_DIST_ENABLE_CLEAR + i / 8);
+			       base + GIC_DIST_ACTIVE_CLEAR + i / 8);
+		writel_relaxed(GICD_INT_EN_CLR_X32,
+			       base + GIC_DIST_ENABLE_CLEAR + i / 8);
+	}
 
 	if (sync_access)
 		sync_access();
@@ -102,7 +105,9 @@ void gic_cpu_config(void __iomem *base, void (*sync_access)(void))
 	/*
 	 * Deal with the banked PPI and SGI interrupts - disable all
 	 * PPI interrupts, ensure all SGI interrupts are enabled.
+	 * Make sure everything is deactivated.
 	 */
+	writel_relaxed(GICD_INT_EN_CLR_X32, base + GIC_DIST_ACTIVE_CLEAR);
 	writel_relaxed(GICD_INT_EN_CLR_PPI, base + GIC_DIST_ENABLE_CLEAR);
 	writel_relaxed(GICD_INT_EN_SET_SGI, base + GIC_DIST_ENABLE_SET);
 
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 515c823c1c95..abf2ffaed392 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -73,9 +73,11 @@ struct gic_chip_data {
 	union gic_base cpu_base;
 #ifdef CONFIG_CPU_PM
 	u32 saved_spi_enable[DIV_ROUND_UP(1020, 32)];
+	u32 saved_spi_active[DIV_ROUND_UP(1020, 32)];
 	u32 saved_spi_conf[DIV_ROUND_UP(1020, 16)];
 	u32 saved_spi_target[DIV_ROUND_UP(1020, 4)];
 	u32 __percpu *saved_ppi_enable;
+	u32 __percpu *saved_ppi_active;
 	u32 __percpu *saved_ppi_conf;
 #endif
 	struct irq_domain *domain;
@@ -566,6 +568,10 @@ static void gic_dist_save(unsigned int gic_nr)
 	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++)
 		gic_data[gic_nr].saved_spi_enable[i] =
 			readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++)
+		gic_data[gic_nr].saved_spi_active[i] =
+			readl_relaxed(dist_base + GIC_DIST_ACTIVE_SET + i * 4);
 }
 
 /*
@@ -604,9 +610,19 @@ static void gic_dist_restore(unsigned int gic_nr)
 		writel_relaxed(gic_data[gic_nr].saved_spi_target[i],
 			dist_base + GIC_DIST_TARGET + i * 4);
 
-	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++)
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++) {
+		writel_relaxed(GICD_INT_EN_CLR_X32,
+			dist_base + GIC_DIST_ENABLE_CLEAR + i * 4);
 		writel_relaxed(gic_data[gic_nr].saved_spi_enable[i],
 			dist_base + GIC_DIST_ENABLE_SET + i * 4);
+	}
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++) {
+		writel_relaxed(GICD_INT_EN_CLR_X32,
+			dist_base + GIC_DIST_ACTIVE_CLEAR + i * 4);
+		writel_relaxed(gic_data[gic_nr].saved_spi_active[i],
+			dist_base + GIC_DIST_ACTIVE_SET + i * 4);
+	}
 
 	writel_relaxed(GICD_ENABLE, dist_base + GIC_DIST_CTRL);
 }
@@ -631,6 +647,10 @@ static void gic_cpu_save(unsigned int gic_nr)
 	for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
 		ptr[i] = readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4);
 
+	ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_active);
+	for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
+		ptr[i] = readl_relaxed(dist_base + GIC_DIST_ACTIVE_SET + i * 4);
+
 	ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
 	for (i = 0; i < DIV_ROUND_UP(32, 16); i++)
 		ptr[i] = readl_relaxed(dist_base + GIC_DIST_CONFIG + i * 4);
@@ -654,8 +674,18 @@ static void gic_cpu_restore(unsigned int gic_nr)
 		return;
 
 	ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_enable);
-	for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
+	for (i = 0; i < DIV_ROUND_UP(32, 32); i++) {
+		writel_relaxed(GICD_INT_EN_CLR_X32,
+			       dist_base + GIC_DIST_ENABLE_CLEAR + i * 4);
 		writel_relaxed(ptr[i], dist_base + GIC_DIST_ENABLE_SET + i * 4);
+	}
+
+	ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_active);
+	for (i = 0; i < DIV_ROUND_UP(32, 32); i++) {
+		writel_relaxed(GICD_INT_EN_CLR_X32,
+			       dist_base + GIC_DIST_ACTIVE_CLEAR + i * 4);
+		writel_relaxed(ptr[i], dist_base + GIC_DIST_ACTIVE_SET + i * 4);
+	}
 
 	ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
 	for (i = 0; i < DIV_ROUND_UP(32, 16); i++)
@@ -710,6 +740,10 @@ static void __init gic_pm_init(struct gic_chip_data *gic)
 		sizeof(u32));
 	BUG_ON(!gic->saved_ppi_enable);
 
+	gic->saved_ppi_active = __alloc_percpu(DIV_ROUND_UP(32, 32) * 4,
+		sizeof(u32));
+	BUG_ON(!gic->saved_ppi_active);
+
 	gic->saved_ppi_conf = __alloc_percpu(DIV_ROUND_UP(32, 16) * 4,
 		sizeof(u32));
 	BUG_ON(!gic->saved_ppi_conf);
diff --git a/drivers/isdn/hisax/config.c b/drivers/isdn/hisax/config.c
index b33f53b3ca93..bf04d2a3cf4a 100644
--- a/drivers/isdn/hisax/config.c
+++ b/drivers/isdn/hisax/config.c
@@ -1896,7 +1896,7 @@ static void EChannel_proc_rcv(struct hisax_d_if *d_if)
 				ptr--;
 				*ptr++ = '\n';
 				*ptr = 0;
-				HiSax_putstatus(cs, NULL, "%s", cs->dlog);
+				HiSax_putstatus(cs, NULL, cs->dlog);
 			} else
 				HiSax_putstatus(cs, "LogEcho: ",
 						"warning Frame too big (%d)",
diff --git a/drivers/isdn/hisax/hfc_pci.c b/drivers/isdn/hisax/hfc_pci.c
index 4a4825528188..90449e1e91e5 100644
--- a/drivers/isdn/hisax/hfc_pci.c
+++ b/drivers/isdn/hisax/hfc_pci.c
@@ -901,7 +901,7 @@ Begin:
 					ptr--;
 					*ptr++ = '\n';
 					*ptr = 0;
-					HiSax_putstatus(cs, NULL, "%s", cs->dlog);
+					HiSax_putstatus(cs, NULL, cs->dlog);
 				} else
 					HiSax_putstatus(cs, "LogEcho: ", "warning Frame too big (%d)", total - 3);
 			}
diff --git a/drivers/isdn/hisax/hfc_sx.c b/drivers/isdn/hisax/hfc_sx.c
index b1fad81f0722..13b2151c10f5 100644
--- a/drivers/isdn/hisax/hfc_sx.c
+++ b/drivers/isdn/hisax/hfc_sx.c
@@ -674,7 +674,7 @@ receive_emsg(struct IsdnCardState *cs)
 					ptr--;
 					*ptr++ = '\n';
 					*ptr = 0;
-					HiSax_putstatus(cs, NULL, "%s", cs->dlog);
+					HiSax_putstatus(cs, NULL, cs->dlog);
 				} else
 					HiSax_putstatus(cs, "LogEcho: ", "warning Frame too big (%d)", skb->len);
 			}
diff --git a/drivers/isdn/hisax/q931.c b/drivers/isdn/hisax/q931.c
index b420f8bd862e..ba4beb25d872 100644
--- a/drivers/isdn/hisax/q931.c
+++ b/drivers/isdn/hisax/q931.c
@@ -1179,7 +1179,7 @@ LogFrame(struct IsdnCardState *cs, u_char *buf, int size)
 		dp--;
 		*dp++ = '\n';
 		*dp = 0;
-		HiSax_putstatus(cs, NULL, "%s", cs->dlog);
+		HiSax_putstatus(cs, NULL, cs->dlog);
 	} else
 		HiSax_putstatus(cs, "LogFrame: ", "warning Frame too big (%d)", size);
 }
@@ -1246,7 +1246,7 @@ dlogframe(struct IsdnCardState *cs, struct sk_buff *skb, int dir)
 	}
 	if (finish) {
 		*dp = 0;
-		HiSax_putstatus(cs, NULL, "%s", cs->dlog);
+		HiSax_putstatus(cs, NULL, cs->dlog);
 		return;
 	}
 	if ((0xfe & buf[0]) == PROTO_DIS_N0) {	/* 1TR6 */
@@ -1509,5 +1509,5 @@ dlogframe(struct IsdnCardState *cs, struct sk_buff *skb, int dir)
 		dp += sprintf(dp, "Unknown protocol %x!", buf[0]);
 	}
 	*dp = 0;
-	HiSax_putstatus(cs, NULL, "%s", cs->dlog);
+	HiSax_putstatus(cs, NULL, cs->dlog);
 }
diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index f659e605a406..86ce887b2ed6 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -123,6 +123,26 @@ void nvm_unregister_mgr(struct nvmm_type *mt)
 }
 EXPORT_SYMBOL(nvm_unregister_mgr);
 
+/* register with device with a supported manager */
+static int register_mgr(struct nvm_dev *dev)
+{
+	struct nvmm_type *mt;
+	int ret = 0;
+
+	list_for_each_entry(mt, &nvm_mgrs, list) {
+		ret = mt->register_mgr(dev);
+		if (ret > 0) {
+			dev->mt = mt;
+			break; /* successfully initialized */
+		}
+	}
+
+	if (!ret)
+		pr_info("nvm: no compatible nvm manager found.\n");
+
+	return ret;
+}
+
 static struct nvm_dev *nvm_find_nvm_dev(const char *name)
 {
 	struct nvm_dev *dev;
@@ -160,11 +180,6 @@ int nvm_erase_blk(struct nvm_dev *dev, struct nvm_block *blk)
 }
 EXPORT_SYMBOL(nvm_erase_blk);
 
-static void nvm_core_free(struct nvm_dev *dev)
-{
-	kfree(dev);
-}
-
 static int nvm_core_init(struct nvm_dev *dev)
 {
 	struct nvm_id *id = &dev->identity;
@@ -179,12 +194,21 @@ static int nvm_core_init(struct nvm_dev *dev)
 	dev->sec_size = grp->csecs;
 	dev->oob_size = grp->sos;
 	dev->sec_per_pg = grp->fpg_sz / grp->csecs;
-	dev->addr_mode = id->ppat;
-	dev->addr_format = id->ppaf;
+	memcpy(&dev->ppaf, &id->ppaf, sizeof(struct nvm_addr_format));
 
 	dev->plane_mode = NVM_PLANE_SINGLE;
 	dev->max_rq_size = dev->ops->max_phys_sect * dev->sec_size;
 
+	if (grp->mtype != 0) {
+		pr_err("nvm: memory type not supported\n");
+		return -EINVAL;
+	}
+
+	if (grp->fmtype != 0 && grp->fmtype != 1) {
+		pr_err("nvm: flash type not supported\n");
+		return -EINVAL;
+	}
+
 	if (grp->mpos & 0x020202)
 		dev->plane_mode = NVM_PLANE_DOUBLE;
 	if (grp->mpos & 0x040404)
@@ -213,21 +237,17 @@ static void nvm_free(struct nvm_dev *dev)
 
 	if (dev->mt)
 		dev->mt->unregister_mgr(dev);
-
-	nvm_core_free(dev);
 }
 
 static int nvm_init(struct nvm_dev *dev)
 {
-	struct nvmm_type *mt;
-	int ret = 0;
+	int ret = -EINVAL;
 
 	if (!dev->q || !dev->ops)
-		return -EINVAL;
+		return ret;
 
 	if (dev->ops->identity(dev->q, &dev->identity)) {
 		pr_err("nvm: device could not be identified\n");
-		ret = -EINVAL;
 		goto err;
 	}
 
@@ -251,21 +271,13 @@ static int nvm_init(struct nvm_dev *dev)
 		goto err;
 	}
 
-	/* register with device with a supported manager */
-	list_for_each_entry(mt, &nvm_mgrs, list) {
-		ret = mt->register_mgr(dev);
-		if (ret < 0)
-			goto err; /* initialization failed */
-		if (ret > 0) {
-			dev->mt = mt;
-			break; /* successfully initialized */
-		}
-	}
-
-	if (!ret) {
-		pr_info("nvm: no compatible manager found.\n");
+	down_write(&nvm_lock);
+	ret = register_mgr(dev);
+	up_write(&nvm_lock);
+	if (ret < 0)
+		goto err;
+	if (!ret)
 		return 0;
-	}
 
 	pr_info("nvm: registered %s [%u/%u/%u/%u/%u/%u]\n",
 			dev->name, dev->sec_per_pg, dev->nr_planes,
@@ -273,7 +285,6 @@ static int nvm_init(struct nvm_dev *dev)
 			dev->nr_chnls);
 	return 0;
 err:
-	nvm_free(dev);
 	pr_err("nvm: failed to initialize nvm\n");
 	return ret;
 }
@@ -308,22 +319,26 @@ int nvm_register(struct request_queue *q, char *disk_name,
 	if (ret)
 		goto err_init;
 
-	down_write(&nvm_lock);
-	list_add(&dev->devices, &nvm_devices);
-	up_write(&nvm_lock);
+	if (dev->ops->max_phys_sect > 256) {
+		pr_info("nvm: max sectors supported is 256.\n");
+		ret = -EINVAL;
+		goto err_init;
+	}
 
 	if (dev->ops->max_phys_sect > 1) {
 		dev->ppalist_pool = dev->ops->create_dma_pool(dev->q,
 								"ppalist");
 		if (!dev->ppalist_pool) {
 			pr_err("nvm: could not create ppa pool\n");
-			return -ENOMEM;
+			ret = -ENOMEM;
+			goto err_init;
 		}
-	} else if (dev->ops->max_phys_sect > 256) {
-		pr_info("nvm: max sectors supported is 256.\n");
-		return -EINVAL;
 	}
 
+	down_write(&nvm_lock);
+	list_add(&dev->devices, &nvm_devices);
+	up_write(&nvm_lock);
+
 	return 0;
 err_init:
 	kfree(dev);
@@ -333,19 +348,22 @@ EXPORT_SYMBOL(nvm_register);
 
 void nvm_unregister(char *disk_name)
 {
-	struct nvm_dev *dev = nvm_find_nvm_dev(disk_name);
+	struct nvm_dev *dev;
 
+	down_write(&nvm_lock);
+	dev = nvm_find_nvm_dev(disk_name);
 	if (!dev) {
 		pr_err("nvm: could not find device %s to unregister\n",
 								disk_name);
+		up_write(&nvm_lock);
 		return;
 	}
 
-	nvm_exit(dev);
-
-	down_write(&nvm_lock);
 	list_del(&dev->devices);
 	up_write(&nvm_lock);
+
+	nvm_exit(dev);
+	kfree(dev);
 }
 EXPORT_SYMBOL(nvm_unregister);
 
@@ -358,38 +376,30 @@ static int nvm_create_target(struct nvm_dev *dev,
 {
 	struct nvm_ioctl_create_simple *s = &create->conf.s;
 	struct request_queue *tqueue;
-	struct nvmm_type *mt;
 	struct gendisk *tdisk;
 	struct nvm_tgt_type *tt;
 	struct nvm_target *t;
 	void *targetdata;
 	int ret = 0;
 
+	down_write(&nvm_lock);
 	if (!dev->mt) {
-		/* register with device with a supported NVM manager */
-		list_for_each_entry(mt, &nvm_mgrs, list) {
-			ret = mt->register_mgr(dev);
-			if (ret < 0)
-				return ret; /* initialization failed */
-			if (ret > 0) {
-				dev->mt = mt;
-				break; /* successfully initialized */
-			}
-		}
-
-		if (!ret) {
-			pr_info("nvm: no compatible nvm manager found.\n");
-			return -ENODEV;
+		ret = register_mgr(dev);
+		if (!ret)
+			ret = -ENODEV;
+		if (ret < 0) {
+			up_write(&nvm_lock);
+			return ret;
 		}
 	}
 
 	tt = nvm_find_target_type(create->tgttype);
 	if (!tt) {
 		pr_err("nvm: target type %s not found\n", create->tgttype);
+		up_write(&nvm_lock);
 		return -EINVAL;
 	}
 
-	down_write(&nvm_lock);
 	list_for_each_entry(t, &dev->online_targets, list) {
 		if (!strcmp(create->tgtname, t->disk->disk_name)) {
 			pr_err("nvm: target name already exists.\n");
@@ -457,11 +467,11 @@ static void nvm_remove_target(struct nvm_target *t)
 	lockdep_assert_held(&nvm_lock);
 
 	del_gendisk(tdisk);
+	blk_cleanup_queue(q);
+
 	if (tt->exit)
 		tt->exit(tdisk->private_data);
 
-	blk_cleanup_queue(q);
-
 	put_disk(tdisk);
 
 	list_del(&t->list);
@@ -473,7 +483,9 @@ static int __nvm_configure_create(struct nvm_ioctl_create *create)
 	struct nvm_dev *dev;
 	struct nvm_ioctl_create_simple *s;
 
+	down_write(&nvm_lock);
 	dev = nvm_find_nvm_dev(create->dev);
+	up_write(&nvm_lock);
 	if (!dev) {
 		pr_err("nvm: device not found\n");
 		return -EINVAL;
@@ -532,7 +544,9 @@ static int nvm_configure_show(const char *val)
 		return -EINVAL;
 	}
 
+	down_write(&nvm_lock);
 	dev = nvm_find_nvm_dev(devname);
+	up_write(&nvm_lock);
 	if (!dev) {
 		pr_err("nvm: device not found\n");
 		return -EINVAL;
@@ -541,7 +555,7 @@ static int nvm_configure_show(const char *val)
 	if (!dev->mt)
 		return 0;
 
-	dev->mt->free_blocks_print(dev);
+	dev->mt->lun_info_print(dev);
 
 	return 0;
 }
@@ -677,8 +691,10 @@ static long nvm_ioctl_info(struct file *file, void __user *arg)
 	info->tgtsize = tgt_iter;
 	up_write(&nvm_lock);
 
-	if (copy_to_user(arg, info, sizeof(struct nvm_ioctl_info)))
+	if (copy_to_user(arg, info, sizeof(struct nvm_ioctl_info))) {
+		kfree(info);
 		return -EFAULT;
+	}
 
 	kfree(info);
 	return 0;
@@ -721,8 +737,11 @@ static long nvm_ioctl_get_devices(struct file *file, void __user *arg)
 
 	devices->nr_devices = i;
 
-	if (copy_to_user(arg, devices, sizeof(struct nvm_ioctl_get_devices)))
+	if (copy_to_user(arg, devices,
+			 sizeof(struct nvm_ioctl_get_devices))) {
+		kfree(devices);
 		return -EFAULT;
+	}
 
 	kfree(devices);
 	return 0;
diff --git a/drivers/lightnvm/gennvm.c b/drivers/lightnvm/gennvm.c
index ae1fb2bdc5f4..35dde84b71e9 100644
--- a/drivers/lightnvm/gennvm.c
+++ b/drivers/lightnvm/gennvm.c
@@ -60,23 +60,27 @@ static int gennvm_luns_init(struct nvm_dev *dev, struct gen_nvm *gn)
 		lun->vlun.lun_id = i % dev->luns_per_chnl;
 		lun->vlun.chnl_id = i / dev->luns_per_chnl;
 		lun->vlun.nr_free_blocks = dev->blks_per_lun;
+		lun->vlun.nr_inuse_blocks = 0;
+		lun->vlun.nr_bad_blocks = 0;
 	}
 	return 0;
 }
 
-static int gennvm_block_bb(u32 lun_id, void *bb_bitmap, unsigned int nr_blocks,
+static int gennvm_block_bb(struct ppa_addr ppa, int nr_blocks, u8 *blks,
 								void *private)
 {
 	struct gen_nvm *gn = private;
-	struct gen_lun *lun = &gn->luns[lun_id];
+	struct nvm_dev *dev = gn->dev;
+	struct gen_lun *lun;
 	struct nvm_block *blk;
 	int i;
 
-	if (unlikely(bitmap_empty(bb_bitmap, nr_blocks)))
-		return 0;
+	lun = &gn->luns[(dev->nr_luns * ppa.g.ch) + ppa.g.lun];
+
+	for (i = 0; i < nr_blocks; i++) {
+		if (blks[i] == 0)
+			continue;
 
-	i = -1;
-	while ((i = find_next_bit(bb_bitmap, nr_blocks, i + 1)) < nr_blocks) {
 		blk = &lun->vlun.blocks[i];
 		if (!blk) {
 			pr_err("gennvm: BB data is out of bounds.\n");
@@ -84,6 +88,7 @@ static int gennvm_block_bb(u32 lun_id, void *bb_bitmap, unsigned int nr_blocks,
 		}
 
 		list_move_tail(&blk->list, &lun->bb_list);
+		lun->vlun.nr_bad_blocks++;
 	}
 
 	return 0;
@@ -136,6 +141,7 @@ static int gennvm_block_map(u64 slba, u32 nlb, __le64 *entries, void *private)
 			list_move_tail(&blk->list, &lun->used_list);
 			blk->type = 1;
 			lun->vlun.nr_free_blocks--;
+			lun->vlun.nr_inuse_blocks++;
 		}
 	}
 
@@ -164,15 +170,25 @@ static int gennvm_blocks_init(struct nvm_dev *dev, struct gen_nvm *gn)
 			block->id = cur_block_id++;
 
 			/* First block is reserved for device */
-			if (unlikely(lun_iter == 0 && blk_iter == 0))
+			if (unlikely(lun_iter == 0 && blk_iter == 0)) {
+				lun->vlun.nr_free_blocks--;
 				continue;
+			}
 
 			list_add_tail(&block->list, &lun->free_list);
 		}
 
 		if (dev->ops->get_bb_tbl) {
-			ret = dev->ops->get_bb_tbl(dev->q, lun->vlun.id,
-					dev->blks_per_lun, gennvm_block_bb, gn);
+			struct ppa_addr ppa;
+
+			ppa.ppa = 0;
+			ppa.g.ch = lun->vlun.chnl_id;
+			ppa.g.lun = lun->vlun.id;
+			ppa = generic_to_dev_addr(dev, ppa);
+
+			ret = dev->ops->get_bb_tbl(dev, ppa,
+						dev->blks_per_lun,
+						gennvm_block_bb, gn);
 			if (ret)
 				pr_err("gennvm: could not read BB table\n");
 		}
@@ -190,6 +206,14 @@ static int gennvm_blocks_init(struct nvm_dev *dev, struct gen_nvm *gn)
 	return 0;
 }
 
+static void gennvm_free(struct nvm_dev *dev)
+{
+	gennvm_blocks_free(dev);
+	gennvm_luns_free(dev);
+	kfree(dev->mp);
+	dev->mp = NULL;
+}
+
 static int gennvm_register(struct nvm_dev *dev)
 {
 	struct gen_nvm *gn;
@@ -199,6 +223,7 @@ static int gennvm_register(struct nvm_dev *dev)
 	if (!gn)
 		return -ENOMEM;
 
+	gn->dev = dev;
 	gn->nr_luns = dev->nr_luns;
 	dev->mp = gn;
 
@@ -216,16 +241,13 @@ static int gennvm_register(struct nvm_dev *dev)
 
 	return 1;
 err:
-	kfree(gn);
+	gennvm_free(dev);
 	return ret;
 }
 
 static void gennvm_unregister(struct nvm_dev *dev)
 {
-	gennvm_blocks_free(dev);
-	gennvm_luns_free(dev);
-	kfree(dev->mp);
-	dev->mp = NULL;
+	gennvm_free(dev);
 }
 
 static struct nvm_block *gennvm_get_blk(struct nvm_dev *dev,
@@ -254,6 +276,7 @@ static struct nvm_block *gennvm_get_blk(struct nvm_dev *dev,
 	blk->type = 1;
 
 	lun->vlun.nr_free_blocks--;
+	lun->vlun.nr_inuse_blocks++;
 
 	spin_unlock(&vlun->lock);
 out:
@@ -271,16 +294,21 @@ static void gennvm_put_blk(struct nvm_dev *dev, struct nvm_block *blk)
 	case 1:
 		list_move_tail(&blk->list, &lun->free_list);
 		lun->vlun.nr_free_blocks++;
+		lun->vlun.nr_inuse_blocks--;
 		blk->type = 0;
 		break;
 	case 2:
 		list_move_tail(&blk->list, &lun->bb_list);
+		lun->vlun.nr_bad_blocks++;
+		lun->vlun.nr_inuse_blocks--;
 		break;
 	default:
 		WARN_ON_ONCE(1);
 		pr_err("gennvm: erroneous block type (%lu -> %u)\n",
 							blk->id, blk->type);
 		list_move_tail(&blk->list, &lun->bb_list);
+		lun->vlun.nr_bad_blocks++;
+		lun->vlun.nr_inuse_blocks--;
 	}
 
 	spin_unlock(&vlun->lock);
@@ -292,10 +320,10 @@ static void gennvm_addr_to_generic_mode(struct nvm_dev *dev, struct nvm_rq *rqd)
 
 	if (rqd->nr_pages > 1) {
 		for (i = 0; i < rqd->nr_pages; i++)
-			rqd->ppa_list[i] = addr_to_generic_mode(dev,
+			rqd->ppa_list[i] = dev_to_generic_addr(dev,
 							rqd->ppa_list[i]);
 	} else {
-		rqd->ppa_addr = addr_to_generic_mode(dev, rqd->ppa_addr);
+		rqd->ppa_addr = dev_to_generic_addr(dev, rqd->ppa_addr);
 	}
 }
 
@@ -305,10 +333,10 @@ static void gennvm_generic_to_addr_mode(struct nvm_dev *dev, struct nvm_rq *rqd)
 
 	if (rqd->nr_pages > 1) {
 		for (i = 0; i < rqd->nr_pages; i++)
-			rqd->ppa_list[i] = generic_to_addr_mode(dev,
+			rqd->ppa_list[i] = generic_to_dev_addr(dev,
 							rqd->ppa_list[i]);
 	} else {
-		rqd->ppa_addr = generic_to_addr_mode(dev, rqd->ppa_addr);
+		rqd->ppa_addr = generic_to_dev_addr(dev, rqd->ppa_addr);
 	}
 }
 
@@ -354,10 +382,10 @@ static void gennvm_mark_blk_bad(struct nvm_dev *dev, struct nvm_rq *rqd)
 {
 	int i;
 
-	if (!dev->ops->set_bb)
+	if (!dev->ops->set_bb_tbl)
 		return;
 
-	if (dev->ops->set_bb(dev->q, rqd, 1))
+	if (dev->ops->set_bb_tbl(dev->q, rqd, 1))
 		return;
 
 	gennvm_addr_to_generic_mode(dev, rqd);
@@ -440,15 +468,24 @@ static struct nvm_lun *gennvm_get_lun(struct nvm_dev *dev, int lunid)
 	return &gn->luns[lunid].vlun;
 }
 
-static void gennvm_free_blocks_print(struct nvm_dev *dev)
+static void gennvm_lun_info_print(struct nvm_dev *dev)
 {
 	struct gen_nvm *gn = dev->mp;
 	struct gen_lun *lun;
 	unsigned int i;
 
-	gennvm_for_each_lun(gn, lun, i)
-		pr_info("%s: lun%8u\t%u\n",
-					dev->name, i, lun->vlun.nr_free_blocks);
+
+	gennvm_for_each_lun(gn, lun, i) {
+		spin_lock(&lun->vlun.lock);
+
+		pr_info("%s: lun%8u\t%u\t%u\t%u\n",
+				dev->name, i,
+				lun->vlun.nr_free_blocks,
+				lun->vlun.nr_inuse_blocks,
+				lun->vlun.nr_bad_blocks);
+
+		spin_unlock(&lun->vlun.lock);
+	}
 }
 
 static struct nvmm_type gennvm = {
@@ -466,7 +503,7 @@ static struct nvmm_type gennvm = {
 	.erase_blk	= gennvm_erase_blk,
 
 	.get_lun	= gennvm_get_lun,
-	.free_blocks_print = gennvm_free_blocks_print,
+	.lun_info_print = gennvm_lun_info_print,
 };
 
 static int __init gennvm_module_init(void)
diff --git a/drivers/lightnvm/gennvm.h b/drivers/lightnvm/gennvm.h
index d23bd3501ddc..9c24b5b32dac 100644
--- a/drivers/lightnvm/gennvm.h
+++ b/drivers/lightnvm/gennvm.h
@@ -35,6 +35,8 @@ struct gen_lun {
 };
 
 struct gen_nvm {
+	struct nvm_dev *dev;
+
 	int nr_luns;
 	struct gen_lun *luns;
 };
diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c
index 7ba64c87ba1c..75e59c3a3f96 100644
--- a/drivers/lightnvm/rrpc.c
+++ b/drivers/lightnvm/rrpc.c
@@ -123,12 +123,42 @@ static u64 block_to_addr(struct rrpc *rrpc, struct rrpc_block *rblk)
 	return blk->id * rrpc->dev->pgs_per_blk;
 }
 
+static struct ppa_addr linear_to_generic_addr(struct nvm_dev *dev,
+							struct ppa_addr r)
+{
+	struct ppa_addr l;
+	int secs, pgs, blks, luns;
+	sector_t ppa = r.ppa;
+
+	l.ppa = 0;
+
+	div_u64_rem(ppa, dev->sec_per_pg, &secs);
+	l.g.sec = secs;
+
+	sector_div(ppa, dev->sec_per_pg);
+	div_u64_rem(ppa, dev->sec_per_blk, &pgs);
+	l.g.pg = pgs;
+
+	sector_div(ppa, dev->pgs_per_blk);
+	div_u64_rem(ppa, dev->blks_per_lun, &blks);
+	l.g.blk = blks;
+
+	sector_div(ppa, dev->blks_per_lun);
+	div_u64_rem(ppa, dev->luns_per_chnl, &luns);
+	l.g.lun = luns;
+
+	sector_div(ppa, dev->luns_per_chnl);
+	l.g.ch = ppa;
+
+	return l;
+}
+
 static struct ppa_addr rrpc_ppa_to_gaddr(struct nvm_dev *dev, u64 addr)
 {
 	struct ppa_addr paddr;
 
 	paddr.ppa = addr;
-	return __linear_to_generic_addr(dev, paddr);
+	return linear_to_generic_addr(dev, paddr);
 }
 
 /* requires lun->lock taken */
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 917d47e290ae..3147c8d09ea8 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -112,7 +112,8 @@ struct iv_tcw_private {
  * and encrypts / decrypts at the same time.
  */
 enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID,
-	     DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD };
+	     DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD,
+	     DM_CRYPT_EXIT_THREAD};
 
 /*
  * The fields in here must be read only after initialization.
@@ -1203,20 +1204,18 @@ continue_locked:
 		if (!RB_EMPTY_ROOT(&cc->write_tree))
 			goto pop_from_list;
 
+		if (unlikely(test_bit(DM_CRYPT_EXIT_THREAD, &cc->flags))) {
+			spin_unlock_irq(&cc->write_thread_wait.lock);
+			break;
+		}
+
 		__set_current_state(TASK_INTERRUPTIBLE);
 		__add_wait_queue(&cc->write_thread_wait, &wait);
 
 		spin_unlock_irq(&cc->write_thread_wait.lock);
 
-		if (unlikely(kthread_should_stop())) {
-			set_task_state(current, TASK_RUNNING);
-			remove_wait_queue(&cc->write_thread_wait, &wait);
-			break;
-		}
-
 		schedule();
 
-		set_task_state(current, TASK_RUNNING);
 		spin_lock_irq(&cc->write_thread_wait.lock);
 		__remove_wait_queue(&cc->write_thread_wait, &wait);
 		goto continue_locked;
@@ -1531,8 +1530,13 @@ static void crypt_dtr(struct dm_target *ti)
 	if (!cc)
 		return;
 
-	if (cc->write_thread)
+	if (cc->write_thread) {
+		spin_lock_irq(&cc->write_thread_wait.lock);
+		set_bit(DM_CRYPT_EXIT_THREAD, &cc->flags);
+		wake_up_locked(&cc->write_thread_wait);
+		spin_unlock_irq(&cc->write_thread_wait.lock);
 		kthread_stop(cc->write_thread);
+	}
 
 	if (cc->io_queue)
 		destroy_workqueue(cc->io_queue);
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index aaa6caa46a9f..cfa29f574c2a 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1537,32 +1537,34 @@ static int multipath_prepare_ioctl(struct dm_target *ti,
 		struct block_device **bdev, fmode_t *mode)
 {
 	struct multipath *m = ti->private;
-	struct pgpath *pgpath;
 	unsigned long flags;
 	int r;
 
-	r = 0;
-
 	spin_lock_irqsave(&m->lock, flags);
 
 	if (!m->current_pgpath)
 		__choose_pgpath(m, 0);
 
-	pgpath = m->current_pgpath;
-
-	if (pgpath) {
-		*bdev = pgpath->path.dev->bdev;
-		*mode = pgpath->path.dev->mode;
+	if (m->current_pgpath) {
+		if (!m->queue_io) {
+			*bdev = m->current_pgpath->path.dev->bdev;
+			*mode = m->current_pgpath->path.dev->mode;
+			r = 0;
+		} else {
+			/* pg_init has not started or completed */
+			r = -ENOTCONN;
+		}
+	} else {
+		/* No path is available */
+		if (m->queue_if_no_path)
+			r = -ENOTCONN;
+		else
+			r = -EIO;
 	}
 
-	if ((pgpath && m->queue_io) || (!pgpath && m->queue_if_no_path))
-		r = -ENOTCONN;
-	else if (!*bdev)
-		r = -EIO;
-
 	spin_unlock_irqrestore(&m->lock, flags);
 
-	if (r == -ENOTCONN && !fatal_signal_pending(current)) {
+	if (r == -ENOTCONN) {
 		spin_lock_irqsave(&m->lock, flags);
 		if (!m->current_pg) {
 			/* Path status changed, redo selection */
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 3897b90bd462..63903a5a5d9e 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -2432,6 +2432,7 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 	case PM_WRITE:
 		if (old_mode != new_mode)
 			notify_of_pool_mode_change(pool, "write");
+		pool->pf.error_if_no_space = pt->requested_pf.error_if_no_space;
 		dm_pool_metadata_read_write(pool->pmd);
 		pool->process_bio = process_bio;
 		pool->process_discard = process_discard_bio;
@@ -4249,10 +4250,9 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
 	struct thin_c *tc = ti->private;
 	struct pool *pool = tc->pool;
-	struct queue_limits *pool_limits = dm_get_queue_limits(pool->pool_md);
 
-	if (!pool_limits->discard_granularity)
-		return; /* pool's discard support is disabled */
+	if (!pool->pf.discard_enabled)
+		return;
 
 	limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT;
 	limits->max_discard_sectors = 2048 * 1024 * 16; /* 16G */
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 6e15f3565892..5df40480228b 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -591,7 +591,7 @@ retry:
 
 out:
 	dm_put_live_table(md, *srcu_idx);
-	if (r == -ENOTCONN) {
+	if (r == -ENOTCONN && !fatal_signal_pending(current)) {
 		msleep(10);
 		goto retry;
 	}
@@ -603,9 +603,10 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
 {
 	struct mapped_device *md = bdev->bd_disk->private_data;
 	struct dm_target *tgt;
+	struct block_device *tgt_bdev = NULL;
 	int srcu_idx, r;
 
-	r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+	r = dm_get_live_table_for_ioctl(md, &tgt, &tgt_bdev, &mode, &srcu_idx);
 	if (r < 0)
 		return r;
 
@@ -620,7 +621,7 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
 			goto out;
 	}
 
-	r =  __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+	r =  __blkdev_driver_ioctl(tgt_bdev, mode, cmd, arg);
 out:
 	dm_put_live_table(md, srcu_idx);
 	return r;
diff --git a/drivers/media/pci/cx23885/cx23885-core.c b/drivers/media/pci/cx23885/cx23885-core.c
index 35759a91d47d..e8f847226a19 100644
--- a/drivers/media/pci/cx23885/cx23885-core.c
+++ b/drivers/media/pci/cx23885/cx23885-core.c
@@ -1992,9 +1992,9 @@ static int cx23885_initdev(struct pci_dev *pci_dev,
 		(unsigned long long)pci_resource_start(pci_dev, 0));
 
 	pci_set_master(pci_dev);
-	if (!pci_set_dma_mask(pci_dev, 0xffffffff)) {
+	err = pci_set_dma_mask(pci_dev, 0xffffffff);
+	if (err) {
 		printk("%s/0: Oops: no 32bit PCI DMA ???\n", dev->name);
-		err = -EIO;
 		goto fail_context;
 	}
 
diff --git a/drivers/media/pci/cx25821/cx25821-core.c b/drivers/media/pci/cx25821/cx25821-core.c
index dbc695f32760..0042803a9de7 100644
--- a/drivers/media/pci/cx25821/cx25821-core.c
+++ b/drivers/media/pci/cx25821/cx25821-core.c
@@ -1319,7 +1319,8 @@ static int cx25821_initdev(struct pci_dev *pci_dev,
 		dev->pci_lat, (unsigned long long)dev->base_io_addr);
 
 	pci_set_master(pci_dev);
-	if (!pci_set_dma_mask(pci_dev, 0xffffffff)) {
+	err = pci_set_dma_mask(pci_dev, 0xffffffff);
+	if (err) {
 		pr_err("%s/0: Oops: no 32bit PCI DMA ???\n", dev->name);
 		err = -EIO;
 		goto fail_irq;
diff --git a/drivers/media/pci/cx88/cx88-alsa.c b/drivers/media/pci/cx88/cx88-alsa.c
index 0ed1b6530374..1b5268f9bb24 100644
--- a/drivers/media/pci/cx88/cx88-alsa.c
+++ b/drivers/media/pci/cx88/cx88-alsa.c
@@ -890,9 +890,9 @@ static int snd_cx88_create(struct snd_card *card, struct pci_dev *pci,
 		return err;
 	}
 
-	if (!pci_set_dma_mask(pci,DMA_BIT_MASK(32))) {
+	err = pci_set_dma_mask(pci,DMA_BIT_MASK(32));
+	if (err) {
 		dprintk(0, "%s/1: Oops: no 32bit PCI DMA ???\n",core->name);
-		err = -EIO;
 		cx88_core_put(core, pci);
 		return err;
 	}
diff --git a/drivers/media/pci/cx88/cx88-mpeg.c b/drivers/media/pci/cx88/cx88-mpeg.c
index 9db7767d1fe0..f34c229f9b37 100644
--- a/drivers/media/pci/cx88/cx88-mpeg.c
+++ b/drivers/media/pci/cx88/cx88-mpeg.c
@@ -393,7 +393,8 @@ static int cx8802_init_common(struct cx8802_dev *dev)
 	if (pci_enable_device(dev->pci))
 		return -EIO;
 	pci_set_master(dev->pci);
-	if (!pci_set_dma_mask(dev->pci,DMA_BIT_MASK(32))) {
+	err = pci_set_dma_mask(dev->pci,DMA_BIT_MASK(32));
+	if (err) {
 		printk("%s/2: Oops: no 32bit PCI DMA ???\n",dev->core->name);
 		return -EIO;
 	}
diff --git a/drivers/media/pci/cx88/cx88-video.c b/drivers/media/pci/cx88/cx88-video.c
index 0de1ad5a977d..aef9acf351f6 100644
--- a/drivers/media/pci/cx88/cx88-video.c
+++ b/drivers/media/pci/cx88/cx88-video.c
@@ -1314,9 +1314,9 @@ static int cx8800_initdev(struct pci_dev *pci_dev,
 	       dev->pci_lat,(unsigned long long)pci_resource_start(pci_dev,0));
 
 	pci_set_master(pci_dev);
-	if (!pci_set_dma_mask(pci_dev,DMA_BIT_MASK(32))) {
+	err = pci_set_dma_mask(pci_dev,DMA_BIT_MASK(32));
+	if (err) {
 		printk("%s/0: Oops: no 32bit PCI DMA ???\n",core->name);
-		err = -EIO;
 		goto fail_core;
 	}
 	dev->alloc_ctx = vb2_dma_sg_init_ctx(&pci_dev->dev);
diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c
index 60b2d462f98d..3fdbd81b5580 100644
--- a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c
+++ b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c
@@ -810,7 +810,7 @@ static int netup_unidvb_initdev(struct pci_dev *pci_dev,
 		"%s(): board vendor 0x%x, revision 0x%x\n",
 		__func__, board_vendor, board_revision);
 	pci_set_master(pci_dev);
-	if (!pci_set_dma_mask(pci_dev, 0xffffffff)) {
+	if (pci_set_dma_mask(pci_dev, 0xffffffff) < 0) {
 		dev_err(&pci_dev->dev,
 			"%s(): 32bit PCI DMA is not supported\n", __func__);
 		goto pci_detect_err;
diff --git a/drivers/media/pci/saa7134/saa7134-core.c b/drivers/media/pci/saa7134/saa7134-core.c
index e79d63eb774e..f720cea80e28 100644
--- a/drivers/media/pci/saa7134/saa7134-core.c
+++ b/drivers/media/pci/saa7134/saa7134-core.c
@@ -951,9 +951,9 @@ static int saa7134_initdev(struct pci_dev *pci_dev,
 	       pci_name(pci_dev), dev->pci_rev, pci_dev->irq,
 	       dev->pci_lat,(unsigned long long)pci_resource_start(pci_dev,0));
 	pci_set_master(pci_dev);
-	if (!pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32))) {
+	err = pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32));
+	if (err) {
 		pr_warn("%s: Oops: no 32bit PCI DMA ???\n", dev->name);
-		err = -EIO;
 		goto fail1;
 	}
 
diff --git a/drivers/media/pci/saa7164/saa7164-core.c b/drivers/media/pci/saa7164/saa7164-core.c
index 8f36b48ef733..8bbd092fbe1d 100644
--- a/drivers/media/pci/saa7164/saa7164-core.c
+++ b/drivers/media/pci/saa7164/saa7164-core.c
@@ -1264,9 +1264,9 @@ static int saa7164_initdev(struct pci_dev *pci_dev,
 
 	pci_set_master(pci_dev);
 	/* TODO */
-	if (!pci_set_dma_mask(pci_dev, 0xffffffff)) {
+	err = pci_set_dma_mask(pci_dev, 0xffffffff);
+	if (err) {
 		printk("%s/0: Oops: no 32bit PCI DMA ???\n", dev->name);
-		err = -EIO;
 		goto fail_irq;
 	}
 
diff --git a/drivers/media/pci/tw68/tw68-core.c b/drivers/media/pci/tw68/tw68-core.c
index 8c5655d351d3..4e77618fbb2b 100644
--- a/drivers/media/pci/tw68/tw68-core.c
+++ b/drivers/media/pci/tw68/tw68-core.c
@@ -257,9 +257,9 @@ static int tw68_initdev(struct pci_dev *pci_dev,
 		dev->name, pci_name(pci_dev), dev->pci_rev, pci_dev->irq,
 		dev->pci_lat, (u64)pci_resource_start(pci_dev, 0));
 	pci_set_master(pci_dev);
-	if (!pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32))) {
+	err = pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32));
+	if (err) {
 		pr_info("%s: Oops: no 32bit PCI DMA ???\n", dev->name);
-		err = -EIO;
 		goto fail1;
 	}
 
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 23b6c8e8701c..d8486168415a 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -65,8 +65,7 @@ MODULE_ALIAS("mmc:block");
 #define MMC_SANITIZE_REQ_TIMEOUT 240000
 #define MMC_EXTRACT_INDEX_FROM_ARG(x) ((x & 0x00FF0000) >> 16)
 
-#define mmc_req_rel_wr(req)	(((req->cmd_flags & REQ_FUA) || \
-				  (req->cmd_flags & REQ_META)) && \
+#define mmc_req_rel_wr(req)	((req->cmd_flags & REQ_FUA) && \
 				  (rq_data_dir(req) == WRITE))
 #define PACKED_CMD_VER	0x01
 #define PACKED_CMD_WR	0x02
@@ -1467,13 +1466,9 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 
 	/*
 	 * Reliable writes are used to implement Forced Unit Access and
-	 * REQ_META accesses, and are supported only on MMCs.
-	 *
-	 * XXX: this really needs a good explanation of why REQ_META
-	 * is treated special.
+	 * are supported only on MMCs.
 	 */
-	bool do_rel_wr = ((req->cmd_flags & REQ_FUA) ||
-			  (req->cmd_flags & REQ_META)) &&
+	bool do_rel_wr = (req->cmd_flags & REQ_FUA) &&
 		(rq_data_dir(req) == WRITE) &&
 		(md->flags & MMC_BLK_REL_WR);
 
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index c793fda27321..3a9a79ec4343 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1040,9 +1040,24 @@ static int mmc_select_hs_ddr(struct mmc_card *card)
 	return err;
 }
 
+/* Caller must hold re-tuning */
+static int mmc_switch_status(struct mmc_card *card)
+{
+	u32 status;
+	int err;
+
+	err = mmc_send_status(card, &status);
+	if (err)
+		return err;
+
+	return mmc_switch_status_error(card->host, status);
+}
+
 static int mmc_select_hs400(struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
+	bool send_status = true;
+	unsigned int max_dtr;
 	int err = 0;
 	u8 val;
 
@@ -1053,25 +1068,36 @@ static int mmc_select_hs400(struct mmc_card *card)
 	      host->ios.bus_width == MMC_BUS_WIDTH_8))
 		return 0;
 
-	/*
-	 * Before switching to dual data rate operation for HS400,
-	 * it is required to convert from HS200 mode to HS mode.
-	 */
-	mmc_set_timing(card->host, MMC_TIMING_MMC_HS);
-	mmc_set_bus_speed(card);
+	if (host->caps & MMC_CAP_WAIT_WHILE_BUSY)
+		send_status = false;
 
+	/* Reduce frequency to HS frequency */
+	max_dtr = card->ext_csd.hs_max_dtr;
+	mmc_set_clock(host, max_dtr);
+
+	/* Switch card to HS mode */
 	val = EXT_CSD_TIMING_HS |
 	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
 	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 			   EXT_CSD_HS_TIMING, val,
 			   card->ext_csd.generic_cmd6_time,
-			   true, true, true);
+			   true, send_status, true);
 	if (err) {
 		pr_err("%s: switch to high-speed from hs200 failed, err:%d\n",
 			mmc_hostname(host), err);
 		return err;
 	}
 
+	/* Set host controller to HS timing */
+	mmc_set_timing(card->host, MMC_TIMING_MMC_HS);
+
+	if (!send_status) {
+		err = mmc_switch_status(card);
+		if (err)
+			goto out_err;
+	}
+
+	/* Switch card to DDR */
 	err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 			 EXT_CSD_BUS_WIDTH,
 			 EXT_CSD_DDR_BUS_WIDTH_8,
@@ -1082,22 +1108,35 @@ static int mmc_select_hs400(struct mmc_card *card)
 		return err;
 	}
 
+	/* Switch card to HS400 */
 	val = EXT_CSD_TIMING_HS400 |
 	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
 	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 			   EXT_CSD_HS_TIMING, val,
 			   card->ext_csd.generic_cmd6_time,
-			   true, true, true);
+			   true, send_status, true);
 	if (err) {
 		pr_err("%s: switch to hs400 failed, err:%d\n",
 			 mmc_hostname(host), err);
 		return err;
 	}
 
+	/* Set host controller to HS400 timing and frequency */
 	mmc_set_timing(host, MMC_TIMING_MMC_HS400);
 	mmc_set_bus_speed(card);
 
+	if (!send_status) {
+		err = mmc_switch_status(card);
+		if (err)
+			goto out_err;
+	}
+
 	return 0;
+
+out_err:
+	pr_err("%s: %s failed, error %d\n", mmc_hostname(card->host),
+	       __func__, err);
+	return err;
 }
 
 int mmc_hs200_to_hs400(struct mmc_card *card)
@@ -1105,19 +1144,6 @@ int mmc_hs200_to_hs400(struct mmc_card *card)
 	return mmc_select_hs400(card);
 }
 
-/* Caller must hold re-tuning */
-static int mmc_switch_status(struct mmc_card *card)
-{
-	u32 status;
-	int err;
-
-	err = mmc_send_status(card, &status);
-	if (err)
-		return err;
-
-	return mmc_switch_status_error(card->host, status);
-}
-
 int mmc_hs400_to_hs200(struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
@@ -1219,6 +1245,8 @@ static void mmc_select_driver_type(struct mmc_card *card)
 static int mmc_select_hs200(struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
+	bool send_status = true;
+	unsigned int old_timing;
 	int err = -EINVAL;
 	u8 val;
 
@@ -1234,6 +1262,9 @@ static int mmc_select_hs200(struct mmc_card *card)
 
 	mmc_select_driver_type(card);
 
+	if (host->caps & MMC_CAP_WAIT_WHILE_BUSY)
+		send_status = false;
+
 	/*
 	 * Set the bus width(4 or 8) with host's support and
 	 * switch to HS200 mode if bus width is set successfully.
@@ -1245,11 +1276,25 @@ static int mmc_select_hs200(struct mmc_card *card)
 		err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 				   EXT_CSD_HS_TIMING, val,
 				   card->ext_csd.generic_cmd6_time,
-				   true, true, true);
-		if (!err)
-			mmc_set_timing(host, MMC_TIMING_MMC_HS200);
+				   true, send_status, true);
+		if (err)
+			goto err;
+		old_timing = host->ios.timing;
+		mmc_set_timing(host, MMC_TIMING_MMC_HS200);
+		if (!send_status) {
+			err = mmc_switch_status(card);
+			/*
+			 * mmc_select_timing() assumes timing has not changed if
+			 * it is a switch error.
+			 */
+			if (err == -EBADMSG)
+				mmc_set_timing(host, old_timing);
+		}
 	}
 err:
+	if (err)
+		pr_err("%s: %s failed, error %d\n", mmc_hostname(card->host),
+		       __func__, err);
 	return err;
 }
 
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index af71de5fda3b..1dee533634c9 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -473,6 +473,7 @@ config MMC_DAVINCI
 
 config MMC_GOLDFISH
 	tristate "goldfish qemu Multimedia Card Interface support"
+	depends on HAS_DMA
 	depends on GOLDFISH || COMPILE_TEST
 	help
 	  This selects the Goldfish Multimedia card Interface emulation
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 39568cc29a2a..33dfd7e72516 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -1276,7 +1276,7 @@ static struct msdc_delay_phase get_best_delay(struct msdc_host *host, u32 delay)
 	int start = 0, len = 0;
 	int start_final = 0, len_final = 0;
 	u8 final_phase = 0xff;
-	struct msdc_delay_phase delay_phase;
+	struct msdc_delay_phase delay_phase = { 0, };
 
 	if (delay == 0) {
 		dev_err(host->dev, "phase error: [map:%x]\n", delay);
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index 8cadd74e8407..ce08896b9d69 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -805,7 +805,7 @@ static int pxamci_probe(struct platform_device *pdev)
 		goto out;
 	} else {
 		mmc->caps |= host->pdata->gpio_card_ro_invert ?
-			MMC_CAP2_RO_ACTIVE_HIGH : 0;
+			0 : MMC_CAP2_RO_ACTIVE_HIGH;
 	}
 
 	if (gpio_is_valid(gpio_cd))
diff --git a/drivers/mtd/nand/jz4740_nand.c b/drivers/mtd/nand/jz4740_nand.c
index dc4e8446f1ff..5a99a93ed025 100644
--- a/drivers/mtd/nand/jz4740_nand.c
+++ b/drivers/mtd/nand/jz4740_nand.c
@@ -25,6 +25,7 @@
 
 #include <linux/gpio.h>
 
+#include <asm/mach-jz4740/gpio.h>
 #include <asm/mach-jz4740/jz4740_nand.h>
 
 #define JZ_REG_NAND_CTRL	0x50
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index cc74142938b0..ece544efccc3 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -3110,7 +3110,7 @@ static void nand_resume(struct mtd_info *mtd)
  */
 static void nand_shutdown(struct mtd_info *mtd)
 {
-	nand_get_device(mtd, FL_SHUTDOWN);
+	nand_get_device(mtd, FL_PM_SUSPENDED);
 }
 
 /* Set default functions */
diff --git a/drivers/net/can/bfin_can.c b/drivers/net/can/bfin_can.c
index 57dadd52b428..1deb8ff90a89 100644
--- a/drivers/net/can/bfin_can.c
+++ b/drivers/net/can/bfin_can.c
@@ -501,8 +501,6 @@ static int bfin_can_err(struct net_device *dev, u16 isrc, u16 status)
 			cf->data[2] |= CAN_ERR_PROT_FORM;
 		else if (status & SER)
 			cf->data[2] |= CAN_ERR_PROT_STUFF;
-		else
-			cf->data[2] |= CAN_ERR_PROT_UNSPEC;
 	}
 
 	priv->can.state = state;
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index 5d214d135332..f91b094288da 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -962,7 +962,6 @@ static int c_can_handle_bus_err(struct net_device *dev,
 	 * type of the last error to occur on the CAN bus
 	 */
 	cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR;
-	cf->data[2] |= CAN_ERR_PROT_UNSPEC;
 
 	switch (lec_type) {
 	case LEC_STUFF_ERROR:
@@ -975,8 +974,7 @@ static int c_can_handle_bus_err(struct net_device *dev,
 		break;
 	case LEC_ACK_ERROR:
 		netdev_dbg(dev, "ack error\n");
-		cf->data[3] |= (CAN_ERR_PROT_LOC_ACK |
-				CAN_ERR_PROT_LOC_ACK_DEL);
+		cf->data[3] = CAN_ERR_PROT_LOC_ACK;
 		break;
 	case LEC_BIT1_ERROR:
 		netdev_dbg(dev, "bit1 error\n");
@@ -988,8 +986,7 @@ static int c_can_handle_bus_err(struct net_device *dev,
 		break;
 	case LEC_CRC_ERROR:
 		netdev_dbg(dev, "CRC error\n");
-		cf->data[3] |= (CAN_ERR_PROT_LOC_CRC_SEQ |
-				CAN_ERR_PROT_LOC_CRC_DEL);
+		cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
 		break;
 	default:
 		break;
diff --git a/drivers/net/can/cc770/cc770.c b/drivers/net/can/cc770/cc770.c
index 70a8cbb29e75..1e37313054f3 100644
--- a/drivers/net/can/cc770/cc770.c
+++ b/drivers/net/can/cc770/cc770.c
@@ -578,7 +578,7 @@ static int cc770_err(struct net_device *dev, u8 status)
 				cf->data[2] |= CAN_ERR_PROT_BIT0;
 				break;
 			case STAT_LEC_CRC:
-				cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ;
+				cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
 				break;
 			}
 		}
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 868fe945e35a..41c0fc9f3b14 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -535,13 +535,13 @@ static void do_bus_err(struct net_device *dev,
 	if (reg_esr & FLEXCAN_ESR_ACK_ERR) {
 		netdev_dbg(dev, "ACK_ERR irq\n");
 		cf->can_id |= CAN_ERR_ACK;
-		cf->data[3] |= CAN_ERR_PROT_LOC_ACK;
+		cf->data[3] = CAN_ERR_PROT_LOC_ACK;
 		tx_errors = 1;
 	}
 	if (reg_esr & FLEXCAN_ESR_CRC_ERR) {
 		netdev_dbg(dev, "CRC_ERR irq\n");
 		cf->data[2] |= CAN_ERR_PROT_BIT;
-		cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ;
+		cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
 		rx_errors = 1;
 	}
 	if (reg_esr & FLEXCAN_ESR_FRM_ERR) {
diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c
index c1e85368a198..5d04f5464faf 100644
--- a/drivers/net/can/janz-ican3.c
+++ b/drivers/net/can/janz-ican3.c
@@ -1096,7 +1096,6 @@ static int ican3_handle_cevtind(struct ican3_dev *mod, struct ican3_msg *msg)
 			cf->data[2] |= CAN_ERR_PROT_STUFF;
 			break;
 		default:
-			cf->data[2] |= CAN_ERR_PROT_UNSPEC;
 			cf->data[3] = ecc & ECC_SEG;
 			break;
 		}
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index ef655177bb5e..39cf911f7a1e 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -487,7 +487,6 @@ static int m_can_handle_lec_err(struct net_device *dev,
 	 * type of the last error to occur on the CAN bus
 	 */
 	cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR;
-	cf->data[2] |= CAN_ERR_PROT_UNSPEC;
 
 	switch (lec_type) {
 	case LEC_STUFF_ERROR:
@@ -500,8 +499,7 @@ static int m_can_handle_lec_err(struct net_device *dev,
 		break;
 	case LEC_ACK_ERROR:
 		netdev_dbg(dev, "ack error\n");
-		cf->data[3] |= (CAN_ERR_PROT_LOC_ACK |
-				CAN_ERR_PROT_LOC_ACK_DEL);
+		cf->data[3] = CAN_ERR_PROT_LOC_ACK;
 		break;
 	case LEC_BIT1_ERROR:
 		netdev_dbg(dev, "bit1 error\n");
@@ -513,8 +511,7 @@ static int m_can_handle_lec_err(struct net_device *dev,
 		break;
 	case LEC_CRC_ERROR:
 		netdev_dbg(dev, "CRC error\n");
-		cf->data[3] |= (CAN_ERR_PROT_LOC_CRC_SEQ |
-				CAN_ERR_PROT_LOC_CRC_DEL);
+		cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
 		break;
 	default:
 		break;
diff --git a/drivers/net/can/pch_can.c b/drivers/net/can/pch_can.c
index e187ca783da0..c1317889d3d8 100644
--- a/drivers/net/can/pch_can.c
+++ b/drivers/net/can/pch_can.c
@@ -559,8 +559,7 @@ static void pch_can_error(struct net_device *ndev, u32 status)
 		stats->rx_errors++;
 		break;
 	case PCH_CRC_ERR:
-		cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ |
-			       CAN_ERR_PROT_LOC_CRC_DEL;
+		cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
 		priv->can.can_stats.bus_error++;
 		stats->rx_errors++;
 		break;
diff --git a/drivers/net/can/rcar_can.c b/drivers/net/can/rcar_can.c
index 7bd54191f962..bc46be39549d 100644
--- a/drivers/net/can/rcar_can.c
+++ b/drivers/net/can/rcar_can.c
@@ -241,17 +241,16 @@ static void rcar_can_error(struct net_device *ndev)
 		u8 ecsr;
 
 		netdev_dbg(priv->ndev, "Bus error interrupt:\n");
-		if (skb) {
+		if (skb)
 			cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT;
-			cf->data[2] = CAN_ERR_PROT_UNSPEC;
-		}
+
 		ecsr = readb(&priv->regs->ecsr);
 		if (ecsr & RCAR_CAN_ECSR_ADEF) {
 			netdev_dbg(priv->ndev, "ACK Delimiter Error\n");
 			tx_errors++;
 			writeb(~RCAR_CAN_ECSR_ADEF, &priv->regs->ecsr);
 			if (skb)
-				cf->data[3] |= CAN_ERR_PROT_LOC_ACK_DEL;
+				cf->data[3] = CAN_ERR_PROT_LOC_ACK_DEL;
 		}
 		if (ecsr & RCAR_CAN_ECSR_BE0F) {
 			netdev_dbg(priv->ndev, "Bit Error (dominant)\n");
@@ -272,7 +271,7 @@ static void rcar_can_error(struct net_device *ndev)
 			rx_errors++;
 			writeb(~RCAR_CAN_ECSR_CEF, &priv->regs->ecsr);
 			if (skb)
-				cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ;
+				cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
 		}
 		if (ecsr & RCAR_CAN_ECSR_AEF) {
 			netdev_dbg(priv->ndev, "ACK Error\n");
@@ -280,7 +279,7 @@ static void rcar_can_error(struct net_device *ndev)
 			writeb(~RCAR_CAN_ECSR_AEF, &priv->regs->ecsr);
 			if (skb) {
 				cf->can_id |= CAN_ERR_ACK;
-				cf->data[3] |= CAN_ERR_PROT_LOC_ACK;
+				cf->data[3] = CAN_ERR_PROT_LOC_ACK;
 			}
 		}
 		if (ecsr & RCAR_CAN_ECSR_FEF) {
diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c
index 7b92e911a616..8dda3b703d39 100644
--- a/drivers/net/can/sja1000/sja1000.c
+++ b/drivers/net/can/sja1000/sja1000.c
@@ -218,6 +218,9 @@ static void sja1000_start(struct net_device *dev)
 	priv->write_reg(priv, SJA1000_RXERR, 0x0);
 	priv->read_reg(priv, SJA1000_ECC);
 
+	/* clear interrupt flags */
+	priv->read_reg(priv, SJA1000_IR);
+
 	/* leave reset mode */
 	set_normal_mode(dev);
 }
@@ -446,7 +449,6 @@ static int sja1000_err(struct net_device *dev, uint8_t isrc, uint8_t status)
 			cf->data[2] |= CAN_ERR_PROT_STUFF;
 			break;
 		default:
-			cf->data[2] |= CAN_ERR_PROT_UNSPEC;
 			cf->data[3] = ecc & ECC_SEG;
 			break;
 		}
diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c
index d9a42c646783..68ef0a4cd821 100644
--- a/drivers/net/can/sun4i_can.c
+++ b/drivers/net/can/sun4i_can.c
@@ -575,7 +575,6 @@ static int sun4i_can_err(struct net_device *dev, u8 isrc, u8 status)
 				cf->data[2] |= CAN_ERR_PROT_STUFF;
 				break;
 			default:
-				cf->data[2] |= CAN_ERR_PROT_UNSPEC;
 				cf->data[3] = (ecc & SUN4I_STA_ERR_SEG_CODE)
 					       >> 16;
 				break;
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index cf345cbfe819..680d1ff07a55 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -722,7 +722,6 @@ static int ti_hecc_error(struct net_device *ndev, int int_status,
 	if (err_status & HECC_BUS_ERROR) {
 		++priv->can.can_stats.bus_error;
 		cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT;
-		cf->data[2] |= CAN_ERR_PROT_UNSPEC;
 		if (err_status & HECC_CANES_FE) {
 			hecc_set_bit(priv, HECC_CANES, HECC_CANES_FE);
 			cf->data[2] |= CAN_ERR_PROT_FORM;
@@ -737,13 +736,11 @@ static int ti_hecc_error(struct net_device *ndev, int int_status,
 		}
 		if (err_status & HECC_CANES_CRCE) {
 			hecc_set_bit(priv, HECC_CANES, HECC_CANES_CRCE);
-			cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ |
-					CAN_ERR_PROT_LOC_CRC_DEL;
+			cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
 		}
 		if (err_status & HECC_CANES_ACKE) {
 			hecc_set_bit(priv, HECC_CANES, HECC_CANES_ACKE);
-			cf->data[3] |= CAN_ERR_PROT_LOC_ACK |
-					CAN_ERR_PROT_LOC_ACK_DEL;
+			cf->data[3] = CAN_ERR_PROT_LOC_ACK;
 		}
 	}
 
diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c
index 2d390384ef3b..fc5b75675cd8 100644
--- a/drivers/net/can/usb/ems_usb.c
+++ b/drivers/net/can/usb/ems_usb.c
@@ -377,7 +377,6 @@ static void ems_usb_rx_err(struct ems_usb *dev, struct ems_cpc_msg *msg)
 			cf->data[2] |= CAN_ERR_PROT_STUFF;
 			break;
 		default:
-			cf->data[2] |= CAN_ERR_PROT_UNSPEC;
 			cf->data[3] = ecc & SJA1000_ECC_SEG;
 			break;
 		}
diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c
index 0e5a4493ba4f..113e64fcd73b 100644
--- a/drivers/net/can/usb/esd_usb2.c
+++ b/drivers/net/can/usb/esd_usb2.c
@@ -282,7 +282,6 @@ static void esd_usb2_rx_event(struct esd_usb2_net_priv *priv,
 				cf->data[2] |= CAN_ERR_PROT_STUFF;
 				break;
 			default:
-				cf->data[2] |= CAN_ERR_PROT_UNSPEC;
 				cf->data[3] = ecc & SJA1000_ECC_SEG;
 				break;
 			}
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 8b17a9065b0b..022bfa13ebfa 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -944,10 +944,9 @@ static void kvaser_usb_rx_error(const struct kvaser_usb *dev,
 			cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT;
 
 			if (es->leaf.error_factor & M16C_EF_ACKE)
-				cf->data[3] |= (CAN_ERR_PROT_LOC_ACK);
+				cf->data[3] = CAN_ERR_PROT_LOC_ACK;
 			if (es->leaf.error_factor & M16C_EF_CRCE)
-				cf->data[3] |= (CAN_ERR_PROT_LOC_CRC_SEQ |
-						CAN_ERR_PROT_LOC_CRC_DEL);
+				cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
 			if (es->leaf.error_factor & M16C_EF_FORME)
 				cf->data[2] |= CAN_ERR_PROT_FORM;
 			if (es->leaf.error_factor & M16C_EF_STFE)
diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c
index de95b1ccba3e..a731720f1d13 100644
--- a/drivers/net/can/usb/usb_8dev.c
+++ b/drivers/net/can/usb/usb_8dev.c
@@ -401,9 +401,7 @@ static void usb_8dev_rx_err_msg(struct usb_8dev_priv *priv,
 		tx_errors = 1;
 		break;
 	case USB_8DEV_STATUSMSG_CRC:
-		cf->data[2] |= CAN_ERR_PROT_UNSPEC;
-		cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ |
-			       CAN_ERR_PROT_LOC_CRC_DEL;
+		cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
 		rx_errors = 1;
 		break;
 	case USB_8DEV_STATUSMSG_BIT0:
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index fc55e8e0351d..51670b322409 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -608,17 +608,15 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
 
 	/* Check for error interrupt */
 	if (isr & XCAN_IXR_ERROR_MASK) {
-		if (skb) {
+		if (skb)
 			cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR;
-			cf->data[2] |= CAN_ERR_PROT_UNSPEC;
-		}
 
 		/* Check for Ack error interrupt */
 		if (err_status & XCAN_ESR_ACKER_MASK) {
 			stats->tx_errors++;
 			if (skb) {
 				cf->can_id |= CAN_ERR_ACK;
-				cf->data[3] |= CAN_ERR_PROT_LOC_ACK;
+				cf->data[3] = CAN_ERR_PROT_LOC_ACK;
 			}
 		}
 
@@ -654,8 +652,7 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
 			stats->rx_errors++;
 			if (skb) {
 				cf->can_id |= CAN_ERR_PROT;
-				cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ |
-						CAN_ERR_PROT_LOC_CRC_DEL;
+				cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
 			}
 		}
 			priv->can.can_stats.bus_error++;
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 955d06b9cdba..31c5e476fd64 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -29,6 +29,7 @@ source "drivers/net/ethernet/apm/Kconfig"
 source "drivers/net/ethernet/apple/Kconfig"
 source "drivers/net/ethernet/arc/Kconfig"
 source "drivers/net/ethernet/atheros/Kconfig"
+source "drivers/net/ethernet/aurora/Kconfig"
 source "drivers/net/ethernet/cadence/Kconfig"
 source "drivers/net/ethernet/adi/Kconfig"
 source "drivers/net/ethernet/broadcom/Kconfig"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 4a2ee98738f0..071f84eb6f3f 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -15,6 +15,7 @@ obj-$(CONFIG_NET_XGENE) += apm/
 obj-$(CONFIG_NET_VENDOR_APPLE) += apple/
 obj-$(CONFIG_NET_VENDOR_ARC) += arc/
 obj-$(CONFIG_NET_VENDOR_ATHEROS) += atheros/
+obj-$(CONFIG_NET_VENDOR_AURORA) += aurora/
 obj-$(CONFIG_NET_CADENCE) += cadence/
 obj-$(CONFIG_NET_BFIN) += adi/
 obj-$(CONFIG_NET_VENDOR_BROADCOM) += broadcom/
diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index e2afabf3a465..7ccebae9cb48 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -1500,10 +1500,11 @@ pcnet32_probe_pci(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return -ENODEV;
 	}
 
-	if (!pci_set_dma_mask(pdev, PCNET32_DMA_MASK)) {
+	err = pci_set_dma_mask(pdev, PCNET32_DMA_MASK);
+	if (err) {
 		if (pcnet32_debug & NETIF_MSG_PROBE)
 			pr_err("architecture does not support 32bit PCI busmaster DMA\n");
-		return -ENODEV;
+		return err;
 	}
 	if (!request_region(ioaddr, PCNET32_TOTAL_SIZE, "pcnet32_probe_pci")) {
 		if (pcnet32_debug & NETIF_MSG_PROBE)
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index 991412ce6f48..9147a0107c44 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -450,12 +450,12 @@ static netdev_tx_t xgene_enet_start_xmit(struct sk_buff *skb,
 		return NETDEV_TX_OK;
 	}
 
-	pdata->ring_ops->wr_cmd(tx_ring, count);
 	skb_tx_timestamp(skb);
 
 	pdata->stats.tx_packets++;
 	pdata->stats.tx_bytes += skb->len;
 
+	pdata->ring_ops->wr_cmd(tx_ring, count);
 	return NETDEV_TX_OK;
 }
 
@@ -688,10 +688,10 @@ static int xgene_enet_open(struct net_device *ndev)
 	mac_ops->tx_enable(pdata);
 	mac_ops->rx_enable(pdata);
 
+	xgene_enet_napi_enable(pdata);
 	ret = xgene_enet_register_irq(ndev);
 	if (ret)
 		return ret;
-	xgene_enet_napi_enable(pdata);
 
 	if (pdata->phy_mode == PHY_INTERFACE_MODE_RGMII)
 		phy_start(pdata->phy_dev);
@@ -715,13 +715,13 @@ static int xgene_enet_close(struct net_device *ndev)
 	else
 		cancel_delayed_work_sync(&pdata->link_work);
 
-	xgene_enet_napi_disable(pdata);
-	xgene_enet_free_irq(ndev);
-	xgene_enet_process_ring(pdata->rx_ring, -1);
-
 	mac_ops->tx_disable(pdata);
 	mac_ops->rx_disable(pdata);
 
+	xgene_enet_free_irq(ndev);
+	xgene_enet_napi_disable(pdata);
+	xgene_enet_process_ring(pdata->rx_ring, -1);
+
 	return 0;
 }
 
@@ -1474,15 +1474,15 @@ static int xgene_enet_probe(struct platform_device *pdev)
 	}
 	ndev->hw_features = ndev->features;
 
-	ret = register_netdev(ndev);
+	ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(64));
 	if (ret) {
-		netdev_err(ndev, "Failed to register netdev\n");
+		netdev_err(ndev, "No usable DMA configuration\n");
 		goto err;
 	}
 
-	ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(64));
+	ret = register_netdev(ndev);
 	if (ret) {
-		netdev_err(ndev, "No usable DMA configuration\n");
+		netdev_err(ndev, "Failed to register netdev\n");
 		goto err;
 	}
 
@@ -1490,14 +1490,17 @@ static int xgene_enet_probe(struct platform_device *pdev)
 	if (ret)
 		goto err;
 
-	xgene_enet_napi_add(pdata);
 	mac_ops = pdata->mac_ops;
-	if (pdata->phy_mode == PHY_INTERFACE_MODE_RGMII)
+	if (pdata->phy_mode == PHY_INTERFACE_MODE_RGMII) {
 		ret = xgene_enet_mdio_config(pdata);
-	else
+		if (ret)
+			goto err;
+	} else {
 		INIT_DELAYED_WORK(&pdata->link_work, mac_ops->link_state);
+	}
 
-	return ret;
+	xgene_enet_napi_add(pdata);
+	return 0;
 err:
 	unregister_netdev(ndev);
 	free_netdev(ndev);
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index c8af3ce3ea38..bd377a6b067d 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1534,6 +1534,8 @@ static const struct pci_device_id alx_pci_tbl[] = {
 	  .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
 	{ PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_E2200),
 	  .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
+	{ PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_E2400),
+	  .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
 	{ PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_AR8162),
 	  .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
 	{ PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_AR8171) },
diff --git a/drivers/net/ethernet/atheros/alx/reg.h b/drivers/net/ethernet/atheros/alx/reg.h
index af006b44b2a6..0959e6824cb6 100644
--- a/drivers/net/ethernet/atheros/alx/reg.h
+++ b/drivers/net/ethernet/atheros/alx/reg.h
@@ -37,6 +37,7 @@
 
 #define ALX_DEV_ID_AR8161				0x1091
 #define ALX_DEV_ID_E2200				0xe091
+#define ALX_DEV_ID_E2400				0xe0a1
 #define ALX_DEV_ID_AR8162				0x1090
 #define ALX_DEV_ID_AR8171				0x10A1
 #define ALX_DEV_ID_AR8172				0x10A0
diff --git a/drivers/net/ethernet/aurora/Kconfig b/drivers/net/ethernet/aurora/Kconfig
new file mode 100644
index 000000000000..a3c7106fdf85
--- /dev/null
+++ b/drivers/net/ethernet/aurora/Kconfig
@@ -0,0 +1,20 @@
+config NET_VENDOR_AURORA
+	bool "Aurora VLSI devices"
+	help
+	  If you have a network (Ethernet) device belonging to this class,
+	  say Y.
+
+	  Note that the answer to this question doesn't directly affect the
+	  kernel: saying N will just cause the configurator to skip all
+	  questions about Aurora devices. If you say Y, you will be asked
+	  for your specific device in the following questions.
+
+if NET_VENDOR_AURORA
+
+config AURORA_NB8800
+	tristate "Aurora AU-NB8800 support"
+	select PHYLIB
+	help
+	 Support for the AU-NB8800 gigabit Ethernet controller.
+
+endif
diff --git a/drivers/net/ethernet/aurora/Makefile b/drivers/net/ethernet/aurora/Makefile
new file mode 100644
index 000000000000..6cb528a2fc26
--- /dev/null
+++ b/drivers/net/ethernet/aurora/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_AURORA_NB8800) += nb8800.o
diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
new file mode 100644
index 000000000000..ecc4a334c507
--- /dev/null
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -0,0 +1,1552 @@
+/*
+ * Copyright (C) 2015 Mans Rullgard <mans@mansr.com>
+ *
+ * Mostly rewritten, based on driver from Sigma Designs.  Original
+ * copyright notice below.
+ *
+ *
+ * Driver for tangox SMP864x/SMP865x/SMP867x/SMP868x builtin Ethernet Mac.
+ *
+ * Copyright (C) 2005 Maxime Bizon <mbizon@freebox.fr>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/etherdevice.h>
+#include <linux/delay.h>
+#include <linux/ethtool.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/of_device.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include <linux/dma-mapping.h>
+#include <linux/phy.h>
+#include <linux/cache.h>
+#include <linux/jiffies.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <asm/barrier.h>
+
+#include "nb8800.h"
+
+static void nb8800_tx_done(struct net_device *dev);
+static int nb8800_dma_stop(struct net_device *dev);
+
+static inline u8 nb8800_readb(struct nb8800_priv *priv, int reg)
+{
+	return readb_relaxed(priv->base + reg);
+}
+
+static inline u32 nb8800_readl(struct nb8800_priv *priv, int reg)
+{
+	return readl_relaxed(priv->base + reg);
+}
+
+static inline void nb8800_writeb(struct nb8800_priv *priv, int reg, u8 val)
+{
+	writeb_relaxed(val, priv->base + reg);
+}
+
+static inline void nb8800_writew(struct nb8800_priv *priv, int reg, u16 val)
+{
+	writew_relaxed(val, priv->base + reg);
+}
+
+static inline void nb8800_writel(struct nb8800_priv *priv, int reg, u32 val)
+{
+	writel_relaxed(val, priv->base + reg);
+}
+
+static inline void nb8800_maskb(struct nb8800_priv *priv, int reg,
+				u32 mask, u32 val)
+{
+	u32 old = nb8800_readb(priv, reg);
+	u32 new = (old & ~mask) | (val & mask);
+
+	if (new != old)
+		nb8800_writeb(priv, reg, new);
+}
+
+static inline void nb8800_maskl(struct nb8800_priv *priv, int reg,
+				u32 mask, u32 val)
+{
+	u32 old = nb8800_readl(priv, reg);
+	u32 new = (old & ~mask) | (val & mask);
+
+	if (new != old)
+		nb8800_writel(priv, reg, new);
+}
+
+static inline void nb8800_modb(struct nb8800_priv *priv, int reg, u8 bits,
+			       bool set)
+{
+	nb8800_maskb(priv, reg, bits, set ? bits : 0);
+}
+
+static inline void nb8800_setb(struct nb8800_priv *priv, int reg, u8 bits)
+{
+	nb8800_maskb(priv, reg, bits, bits);
+}
+
+static inline void nb8800_clearb(struct nb8800_priv *priv, int reg, u8 bits)
+{
+	nb8800_maskb(priv, reg, bits, 0);
+}
+
+static inline void nb8800_modl(struct nb8800_priv *priv, int reg, u32 bits,
+			       bool set)
+{
+	nb8800_maskl(priv, reg, bits, set ? bits : 0);
+}
+
+static inline void nb8800_setl(struct nb8800_priv *priv, int reg, u32 bits)
+{
+	nb8800_maskl(priv, reg, bits, bits);
+}
+
+static inline void nb8800_clearl(struct nb8800_priv *priv, int reg, u32 bits)
+{
+	nb8800_maskl(priv, reg, bits, 0);
+}
+
+static int nb8800_mdio_wait(struct mii_bus *bus)
+{
+	struct nb8800_priv *priv = bus->priv;
+	u32 val;
+
+	return readl_poll_timeout_atomic(priv->base + NB8800_MDIO_CMD,
+					 val, !(val & MDIO_CMD_GO), 1, 1000);
+}
+
+static int nb8800_mdio_cmd(struct mii_bus *bus, u32 cmd)
+{
+	struct nb8800_priv *priv = bus->priv;
+	int err;
+
+	err = nb8800_mdio_wait(bus);
+	if (err)
+		return err;
+
+	nb8800_writel(priv, NB8800_MDIO_CMD, cmd);
+	udelay(10);
+	nb8800_writel(priv, NB8800_MDIO_CMD, cmd | MDIO_CMD_GO);
+
+	return nb8800_mdio_wait(bus);
+}
+
+static int nb8800_mdio_read(struct mii_bus *bus, int phy_id, int reg)
+{
+	struct nb8800_priv *priv = bus->priv;
+	u32 val;
+	int err;
+
+	err = nb8800_mdio_cmd(bus, MDIO_CMD_ADDR(phy_id) | MDIO_CMD_REG(reg));
+	if (err)
+		return err;
+
+	val = nb8800_readl(priv, NB8800_MDIO_STS);
+	if (val & MDIO_STS_ERR)
+		return 0xffff;
+
+	return val & 0xffff;
+}
+
+static int nb8800_mdio_write(struct mii_bus *bus, int phy_id, int reg, u16 val)
+{
+	u32 cmd = MDIO_CMD_ADDR(phy_id) | MDIO_CMD_REG(reg) |
+		MDIO_CMD_DATA(val) | MDIO_CMD_WR;
+
+	return nb8800_mdio_cmd(bus, cmd);
+}
+
+static void nb8800_mac_tx(struct net_device *dev, bool enable)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+
+	while (nb8800_readl(priv, NB8800_TXC_CR) & TCR_EN)
+		cpu_relax();
+
+	nb8800_modb(priv, NB8800_TX_CTL1, TX_EN, enable);
+}
+
+static void nb8800_mac_rx(struct net_device *dev, bool enable)
+{
+	nb8800_modb(netdev_priv(dev), NB8800_RX_CTL, RX_EN, enable);
+}
+
+static void nb8800_mac_af(struct net_device *dev, bool enable)
+{
+	nb8800_modb(netdev_priv(dev), NB8800_RX_CTL, RX_AF_EN, enable);
+}
+
+static void nb8800_start_rx(struct net_device *dev)
+{
+	nb8800_setl(netdev_priv(dev), NB8800_RXC_CR, RCR_EN);
+}
+
+static int nb8800_alloc_rx(struct net_device *dev, unsigned int i, bool napi)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	struct nb8800_rx_desc *rxd = &priv->rx_descs[i];
+	struct nb8800_rx_buf *rxb = &priv->rx_bufs[i];
+	int size = L1_CACHE_ALIGN(RX_BUF_SIZE);
+	dma_addr_t dma_addr;
+	struct page *page;
+	unsigned long offset;
+	void *data;
+
+	data = napi ? napi_alloc_frag(size) : netdev_alloc_frag(size);
+	if (!data)
+		return -ENOMEM;
+
+	page = virt_to_head_page(data);
+	offset = data - page_address(page);
+
+	dma_addr = dma_map_page(&dev->dev, page, offset, RX_BUF_SIZE,
+				DMA_FROM_DEVICE);
+
+	if (dma_mapping_error(&dev->dev, dma_addr)) {
+		skb_free_frag(data);
+		return -ENOMEM;
+	}
+
+	rxb->page = page;
+	rxb->offset = offset;
+	rxd->desc.s_addr = dma_addr;
+
+	return 0;
+}
+
+static void nb8800_receive(struct net_device *dev, unsigned int i,
+			   unsigned int len)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	struct nb8800_rx_desc *rxd = &priv->rx_descs[i];
+	struct page *page = priv->rx_bufs[i].page;
+	int offset = priv->rx_bufs[i].offset;
+	void *data = page_address(page) + offset;
+	dma_addr_t dma = rxd->desc.s_addr;
+	struct sk_buff *skb;
+	unsigned int size;
+	int err;
+
+	size = len <= RX_COPYBREAK ? len : RX_COPYHDR;
+
+	skb = napi_alloc_skb(&priv->napi, size);
+	if (!skb) {
+		netdev_err(dev, "rx skb allocation failed\n");
+		dev->stats.rx_dropped++;
+		return;
+	}
+
+	if (len <= RX_COPYBREAK) {
+		dma_sync_single_for_cpu(&dev->dev, dma, len, DMA_FROM_DEVICE);
+		memcpy(skb_put(skb, len), data, len);
+		dma_sync_single_for_device(&dev->dev, dma, len,
+					   DMA_FROM_DEVICE);
+	} else {
+		err = nb8800_alloc_rx(dev, i, true);
+		if (err) {
+			netdev_err(dev, "rx buffer allocation failed\n");
+			dev->stats.rx_dropped++;
+			return;
+		}
+
+		dma_unmap_page(&dev->dev, dma, RX_BUF_SIZE, DMA_FROM_DEVICE);
+		memcpy(skb_put(skb, RX_COPYHDR), data, RX_COPYHDR);
+		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
+				offset + RX_COPYHDR, len - RX_COPYHDR,
+				RX_BUF_SIZE);
+	}
+
+	skb->protocol = eth_type_trans(skb, dev);
+	napi_gro_receive(&priv->napi, skb);
+}
+
+static void nb8800_rx_error(struct net_device *dev, u32 report)
+{
+	if (report & RX_LENGTH_ERR)
+		dev->stats.rx_length_errors++;
+
+	if (report & RX_FCS_ERR)
+		dev->stats.rx_crc_errors++;
+
+	if (report & RX_FIFO_OVERRUN)
+		dev->stats.rx_fifo_errors++;
+
+	if (report & RX_ALIGNMENT_ERROR)
+		dev->stats.rx_frame_errors++;
+
+	dev->stats.rx_errors++;
+}
+
+static int nb8800_poll(struct napi_struct *napi, int budget)
+{
+	struct net_device *dev = napi->dev;
+	struct nb8800_priv *priv = netdev_priv(dev);
+	struct nb8800_rx_desc *rxd;
+	unsigned int last = priv->rx_eoc;
+	unsigned int next;
+	int work = 0;
+
+	nb8800_tx_done(dev);
+
+again:
+	while (work < budget) {
+		struct nb8800_rx_buf *rxb;
+		unsigned int len;
+
+		next = (last + 1) % RX_DESC_COUNT;
+
+		rxb = &priv->rx_bufs[next];
+		rxd = &priv->rx_descs[next];
+
+		if (!rxd->report)
+			break;
+
+		len = RX_BYTES_TRANSFERRED(rxd->report);
+
+		if (IS_RX_ERROR(rxd->report))
+			nb8800_rx_error(dev, rxd->report);
+		else
+			nb8800_receive(dev, next, len);
+
+		dev->stats.rx_packets++;
+		dev->stats.rx_bytes += len;
+
+		if (rxd->report & RX_MULTICAST_PKT)
+			dev->stats.multicast++;
+
+		rxd->report = 0;
+		last = next;
+		work++;
+	}
+
+	if (work) {
+		priv->rx_descs[last].desc.config |= DESC_EOC;
+		wmb();	/* ensure new EOC is written before clearing old */
+		priv->rx_descs[priv->rx_eoc].desc.config &= ~DESC_EOC;
+		priv->rx_eoc = last;
+		nb8800_start_rx(dev);
+	}
+
+	if (work < budget) {
+		nb8800_writel(priv, NB8800_RX_ITR, priv->rx_itr_irq);
+
+		/* If a packet arrived after we last checked but
+		 * before writing RX_ITR, the interrupt will be
+		 * delayed, so we retrieve it now.
+		 */
+		if (priv->rx_descs[next].report)
+			goto again;
+
+		napi_complete_done(napi, work);
+	}
+
+	return work;
+}
+
+static void __nb8800_tx_dma_start(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	struct nb8800_tx_buf *txb;
+	u32 txc_cr;
+
+	txb = &priv->tx_bufs[priv->tx_queue];
+	if (!txb->ready)
+		return;
+
+	txc_cr = nb8800_readl(priv, NB8800_TXC_CR);
+	if (txc_cr & TCR_EN)
+		return;
+
+	nb8800_writel(priv, NB8800_TX_DESC_ADDR, txb->dma_desc);
+	wmb();		/* ensure desc addr is written before starting DMA */
+	nb8800_writel(priv, NB8800_TXC_CR, txc_cr | TCR_EN);
+
+	priv->tx_queue = (priv->tx_queue + txb->chain_len) % TX_DESC_COUNT;
+}
+
+static void nb8800_tx_dma_start(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+
+	spin_lock_irq(&priv->tx_lock);
+	__nb8800_tx_dma_start(dev);
+	spin_unlock_irq(&priv->tx_lock);
+}
+
+static void nb8800_tx_dma_start_irq(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+
+	spin_lock(&priv->tx_lock);
+	__nb8800_tx_dma_start(dev);
+	spin_unlock(&priv->tx_lock);
+}
+
+static int nb8800_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	struct nb8800_tx_desc *txd;
+	struct nb8800_tx_buf *txb;
+	struct nb8800_dma_desc *desc;
+	dma_addr_t dma_addr;
+	unsigned int dma_len;
+	unsigned int align;
+	unsigned int next;
+
+	if (atomic_read(&priv->tx_free) <= NB8800_DESC_LOW) {
+		netif_stop_queue(dev);
+		return NETDEV_TX_BUSY;
+	}
+
+	align = (8 - (uintptr_t)skb->data) & 7;
+
+	dma_len = skb->len - align;
+	dma_addr = dma_map_single(&dev->dev, skb->data + align,
+				  dma_len, DMA_TO_DEVICE);
+
+	if (dma_mapping_error(&dev->dev, dma_addr)) {
+		netdev_err(dev, "tx dma mapping error\n");
+		kfree_skb(skb);
+		dev->stats.tx_dropped++;
+		return NETDEV_TX_OK;
+	}
+
+	if (atomic_dec_return(&priv->tx_free) <= NB8800_DESC_LOW) {
+		netif_stop_queue(dev);
+		skb->xmit_more = 0;
+	}
+
+	next = priv->tx_next;
+	txb = &priv->tx_bufs[next];
+	txd = &priv->tx_descs[next];
+	desc = &txd->desc[0];
+
+	next = (next + 1) % TX_DESC_COUNT;
+
+	if (align) {
+		memcpy(txd->buf, skb->data, align);
+
+		desc->s_addr =
+			txb->dma_desc + offsetof(struct nb8800_tx_desc, buf);
+		desc->n_addr = txb->dma_desc + sizeof(txd->desc[0]);
+		desc->config = DESC_BTS(2) | DESC_DS | align;
+
+		desc++;
+	}
+
+	desc->s_addr = dma_addr;
+	desc->n_addr = priv->tx_bufs[next].dma_desc;
+	desc->config = DESC_BTS(2) | DESC_DS | DESC_EOF | dma_len;
+
+	if (!skb->xmit_more)
+		desc->config |= DESC_EOC;
+
+	txb->skb = skb;
+	txb->dma_addr = dma_addr;
+	txb->dma_len = dma_len;
+
+	if (!priv->tx_chain) {
+		txb->chain_len = 1;
+		priv->tx_chain = txb;
+	} else {
+		priv->tx_chain->chain_len++;
+	}
+
+	netdev_sent_queue(dev, skb->len);
+
+	priv->tx_next = next;
+
+	if (!skb->xmit_more) {
+		smp_wmb();
+		priv->tx_chain->ready = true;
+		priv->tx_chain = NULL;
+		nb8800_tx_dma_start(dev);
+	}
+
+	return NETDEV_TX_OK;
+}
+
+static void nb8800_tx_error(struct net_device *dev, u32 report)
+{
+	if (report & TX_LATE_COLLISION)
+		dev->stats.collisions++;
+
+	if (report & TX_PACKET_DROPPED)
+		dev->stats.tx_dropped++;
+
+	if (report & TX_FIFO_UNDERRUN)
+		dev->stats.tx_fifo_errors++;
+
+	dev->stats.tx_errors++;
+}
+
+static void nb8800_tx_done(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	unsigned int limit = priv->tx_next;
+	unsigned int done = priv->tx_done;
+	unsigned int packets = 0;
+	unsigned int len = 0;
+
+	while (done != limit) {
+		struct nb8800_tx_desc *txd = &priv->tx_descs[done];
+		struct nb8800_tx_buf *txb = &priv->tx_bufs[done];
+		struct sk_buff *skb;
+
+		if (!txd->report)
+			break;
+
+		skb = txb->skb;
+		len += skb->len;
+
+		dma_unmap_single(&dev->dev, txb->dma_addr, txb->dma_len,
+				 DMA_TO_DEVICE);
+
+		if (IS_TX_ERROR(txd->report)) {
+			nb8800_tx_error(dev, txd->report);
+			kfree_skb(skb);
+		} else {
+			consume_skb(skb);
+		}
+
+		dev->stats.tx_packets++;
+		dev->stats.tx_bytes += TX_BYTES_TRANSFERRED(txd->report);
+		dev->stats.collisions += TX_EARLY_COLLISIONS(txd->report);
+
+		txb->skb = NULL;
+		txb->ready = false;
+		txd->report = 0;
+
+		done = (done + 1) % TX_DESC_COUNT;
+		packets++;
+	}
+
+	if (packets) {
+		smp_mb__before_atomic();
+		atomic_add(packets, &priv->tx_free);
+		netdev_completed_queue(dev, packets, len);
+		netif_wake_queue(dev);
+		priv->tx_done = done;
+	}
+}
+
+static irqreturn_t nb8800_irq(int irq, void *dev_id)
+{
+	struct net_device *dev = dev_id;
+	struct nb8800_priv *priv = netdev_priv(dev);
+	irqreturn_t ret = IRQ_NONE;
+	u32 val;
+
+	/* tx interrupt */
+	val = nb8800_readl(priv, NB8800_TXC_SR);
+	if (val) {
+		nb8800_writel(priv, NB8800_TXC_SR, val);
+
+		if (val & TSR_DI)
+			nb8800_tx_dma_start_irq(dev);
+
+		if (val & TSR_TI)
+			napi_schedule_irqoff(&priv->napi);
+
+		if (unlikely(val & TSR_DE))
+			netdev_err(dev, "TX DMA error\n");
+
+		/* should never happen with automatic status retrieval */
+		if (unlikely(val & TSR_TO))
+			netdev_err(dev, "TX Status FIFO overflow\n");
+
+		ret = IRQ_HANDLED;
+	}
+
+	/* rx interrupt */
+	val = nb8800_readl(priv, NB8800_RXC_SR);
+	if (val) {
+		nb8800_writel(priv, NB8800_RXC_SR, val);
+
+		if (likely(val & (RSR_RI | RSR_DI))) {
+			nb8800_writel(priv, NB8800_RX_ITR, priv->rx_itr_poll);
+			napi_schedule_irqoff(&priv->napi);
+		}
+
+		if (unlikely(val & RSR_DE))
+			netdev_err(dev, "RX DMA error\n");
+
+		/* should never happen with automatic status retrieval */
+		if (unlikely(val & RSR_RO))
+			netdev_err(dev, "RX Status FIFO overflow\n");
+
+		ret = IRQ_HANDLED;
+	}
+
+	return ret;
+}
+
+static void nb8800_mac_config(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	bool gigabit = priv->speed == SPEED_1000;
+	u32 mac_mode_mask = RGMII_MODE | HALF_DUPLEX | GMAC_MODE;
+	u32 mac_mode = 0;
+	u32 slot_time;
+	u32 phy_clk;
+	u32 ict;
+
+	if (!priv->duplex)
+		mac_mode |= HALF_DUPLEX;
+
+	if (gigabit) {
+		if (priv->phy_mode == PHY_INTERFACE_MODE_RGMII)
+			mac_mode |= RGMII_MODE;
+
+		mac_mode |= GMAC_MODE;
+		phy_clk = 125000000;
+
+		/* Should be 512 but register is only 8 bits */
+		slot_time = 255;
+	} else {
+		phy_clk = 25000000;
+		slot_time = 128;
+	}
+
+	ict = DIV_ROUND_UP(phy_clk, clk_get_rate(priv->clk));
+
+	nb8800_writeb(priv, NB8800_IC_THRESHOLD, ict);
+	nb8800_writeb(priv, NB8800_SLOT_TIME, slot_time);
+	nb8800_maskb(priv, NB8800_MAC_MODE, mac_mode_mask, mac_mode);
+}
+
+static void nb8800_pause_config(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	struct phy_device *phydev = priv->phydev;
+	u32 rxcr;
+
+	if (priv->pause_aneg) {
+		if (!phydev || !phydev->link)
+			return;
+
+		priv->pause_rx = phydev->pause;
+		priv->pause_tx = phydev->pause ^ phydev->asym_pause;
+	}
+
+	nb8800_modb(priv, NB8800_RX_CTL, RX_PAUSE_EN, priv->pause_rx);
+
+	rxcr = nb8800_readl(priv, NB8800_RXC_CR);
+	if (!!(rxcr & RCR_FL) == priv->pause_tx)
+		return;
+
+	if (netif_running(dev)) {
+		napi_disable(&priv->napi);
+		netif_tx_lock_bh(dev);
+		nb8800_dma_stop(dev);
+		nb8800_modl(priv, NB8800_RXC_CR, RCR_FL, priv->pause_tx);
+		nb8800_start_rx(dev);
+		netif_tx_unlock_bh(dev);
+		napi_enable(&priv->napi);
+	} else {
+		nb8800_modl(priv, NB8800_RXC_CR, RCR_FL, priv->pause_tx);
+	}
+}
+
+static void nb8800_link_reconfigure(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	struct phy_device *phydev = priv->phydev;
+	int change = 0;
+
+	if (phydev->link) {
+		if (phydev->speed != priv->speed) {
+			priv->speed = phydev->speed;
+			change = 1;
+		}
+
+		if (phydev->duplex != priv->duplex) {
+			priv->duplex = phydev->duplex;
+			change = 1;
+		}
+
+		if (change)
+			nb8800_mac_config(dev);
+
+		nb8800_pause_config(dev);
+	}
+
+	if (phydev->link != priv->link) {
+		priv->link = phydev->link;
+		change = 1;
+	}
+
+	if (change)
+		phy_print_status(priv->phydev);
+}
+
+static void nb8800_update_mac_addr(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	int i;
+
+	for (i = 0; i < ETH_ALEN; i++)
+		nb8800_writeb(priv, NB8800_SRC_ADDR(i), dev->dev_addr[i]);
+
+	for (i = 0; i < ETH_ALEN; i++)
+		nb8800_writeb(priv, NB8800_UC_ADDR(i), dev->dev_addr[i]);
+}
+
+static int nb8800_set_mac_address(struct net_device *dev, void *addr)
+{
+	struct sockaddr *sock = addr;
+
+	if (netif_running(dev))
+		return -EBUSY;
+
+	ether_addr_copy(dev->dev_addr, sock->sa_data);
+	nb8800_update_mac_addr(dev);
+
+	return 0;
+}
+
+static void nb8800_mc_init(struct net_device *dev, int val)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+
+	nb8800_writeb(priv, NB8800_MC_INIT, val);
+	readb_poll_timeout_atomic(priv->base + NB8800_MC_INIT, val, !val,
+				  1, 1000);
+}
+
+static void nb8800_set_rx_mode(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	struct netdev_hw_addr *ha;
+	int i;
+
+	if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) {
+		nb8800_mac_af(dev, false);
+		return;
+	}
+
+	nb8800_mac_af(dev, true);
+	nb8800_mc_init(dev, 0);
+
+	netdev_for_each_mc_addr(ha, dev) {
+		for (i = 0; i < ETH_ALEN; i++)
+			nb8800_writeb(priv, NB8800_MC_ADDR(i), ha->addr[i]);
+
+		nb8800_mc_init(dev, 0xff);
+	}
+}
+
+#define RX_DESC_SIZE (RX_DESC_COUNT * sizeof(struct nb8800_rx_desc))
+#define TX_DESC_SIZE (TX_DESC_COUNT * sizeof(struct nb8800_tx_desc))
+
+static void nb8800_dma_free(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	unsigned int i;
+
+	if (priv->rx_bufs) {
+		for (i = 0; i < RX_DESC_COUNT; i++)
+			if (priv->rx_bufs[i].page)
+				put_page(priv->rx_bufs[i].page);
+
+		kfree(priv->rx_bufs);
+		priv->rx_bufs = NULL;
+	}
+
+	if (priv->tx_bufs) {
+		for (i = 0; i < TX_DESC_COUNT; i++)
+			kfree_skb(priv->tx_bufs[i].skb);
+
+		kfree(priv->tx_bufs);
+		priv->tx_bufs = NULL;
+	}
+
+	if (priv->rx_descs) {
+		dma_free_coherent(dev->dev.parent, RX_DESC_SIZE, priv->rx_descs,
+				  priv->rx_desc_dma);
+		priv->rx_descs = NULL;
+	}
+
+	if (priv->tx_descs) {
+		dma_free_coherent(dev->dev.parent, TX_DESC_SIZE, priv->tx_descs,
+				  priv->tx_desc_dma);
+		priv->tx_descs = NULL;
+	}
+}
+
+static void nb8800_dma_reset(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	struct nb8800_rx_desc *rxd;
+	struct nb8800_tx_desc *txd;
+	unsigned int i;
+
+	for (i = 0; i < RX_DESC_COUNT; i++) {
+		dma_addr_t rx_dma = priv->rx_desc_dma + i * sizeof(*rxd);
+
+		rxd = &priv->rx_descs[i];
+		rxd->desc.n_addr = rx_dma + sizeof(*rxd);
+		rxd->desc.r_addr =
+			rx_dma + offsetof(struct nb8800_rx_desc, report);
+		rxd->desc.config = priv->rx_dma_config;
+		rxd->report = 0;
+	}
+
+	rxd->desc.n_addr = priv->rx_desc_dma;
+	rxd->desc.config |= DESC_EOC;
+
+	priv->rx_eoc = RX_DESC_COUNT - 1;
+
+	for (i = 0; i < TX_DESC_COUNT; i++) {
+		struct nb8800_tx_buf *txb = &priv->tx_bufs[i];
+		dma_addr_t r_dma = txb->dma_desc +
+			offsetof(struct nb8800_tx_desc, report);
+
+		txd = &priv->tx_descs[i];
+		txd->desc[0].r_addr = r_dma;
+		txd->desc[1].r_addr = r_dma;
+		txd->report = 0;
+	}
+
+	priv->tx_next = 0;
+	priv->tx_queue = 0;
+	priv->tx_done = 0;
+	atomic_set(&priv->tx_free, TX_DESC_COUNT);
+
+	nb8800_writel(priv, NB8800_RX_DESC_ADDR, priv->rx_desc_dma);
+
+	wmb();		/* ensure all setup is written before starting */
+}
+
+static int nb8800_dma_init(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	unsigned int n_rx = RX_DESC_COUNT;
+	unsigned int n_tx = TX_DESC_COUNT;
+	unsigned int i;
+	int err;
+
+	priv->rx_descs = dma_alloc_coherent(dev->dev.parent, RX_DESC_SIZE,
+					    &priv->rx_desc_dma, GFP_KERNEL);
+	if (!priv->rx_descs)
+		goto err_out;
+
+	priv->rx_bufs = kcalloc(n_rx, sizeof(*priv->rx_bufs), GFP_KERNEL);
+	if (!priv->rx_bufs)
+		goto err_out;
+
+	for (i = 0; i < n_rx; i++) {
+		err = nb8800_alloc_rx(dev, i, false);
+		if (err)
+			goto err_out;
+	}
+
+	priv->tx_descs = dma_alloc_coherent(dev->dev.parent, TX_DESC_SIZE,
+					    &priv->tx_desc_dma, GFP_KERNEL);
+	if (!priv->tx_descs)
+		goto err_out;
+
+	priv->tx_bufs = kcalloc(n_tx, sizeof(*priv->tx_bufs), GFP_KERNEL);
+	if (!priv->tx_bufs)
+		goto err_out;
+
+	for (i = 0; i < n_tx; i++)
+		priv->tx_bufs[i].dma_desc =
+			priv->tx_desc_dma + i * sizeof(struct nb8800_tx_desc);
+
+	nb8800_dma_reset(dev);
+
+	return 0;
+
+err_out:
+	nb8800_dma_free(dev);
+
+	return -ENOMEM;
+}
+
+static int nb8800_dma_stop(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	struct nb8800_tx_buf *txb = &priv->tx_bufs[0];
+	struct nb8800_tx_desc *txd = &priv->tx_descs[0];
+	int retry = 5;
+	u32 txcr;
+	u32 rxcr;
+	int err;
+	unsigned int i;
+
+	/* wait for tx to finish */
+	err = readl_poll_timeout_atomic(priv->base + NB8800_TXC_CR, txcr,
+					!(txcr & TCR_EN) &&
+					priv->tx_done == priv->tx_next,
+					1000, 1000000);
+	if (err)
+		return err;
+
+	/* The rx DMA only stops if it reaches the end of chain.
+	 * To make this happen, we set the EOC flag on all rx
+	 * descriptors, put the device in loopback mode, and send
+	 * a few dummy frames.  The interrupt handler will ignore
+	 * these since NAPI is disabled and no real frames are in
+	 * the tx queue.
+	 */
+
+	for (i = 0; i < RX_DESC_COUNT; i++)
+		priv->rx_descs[i].desc.config |= DESC_EOC;
+
+	txd->desc[0].s_addr =
+		txb->dma_desc + offsetof(struct nb8800_tx_desc, buf);
+	txd->desc[0].config = DESC_BTS(2) | DESC_DS | DESC_EOF | DESC_EOC | 8;
+	memset(txd->buf, 0, sizeof(txd->buf));
+
+	nb8800_mac_af(dev, false);
+	nb8800_setb(priv, NB8800_MAC_MODE, LOOPBACK_EN);
+
+	do {
+		nb8800_writel(priv, NB8800_TX_DESC_ADDR, txb->dma_desc);
+		wmb();
+		nb8800_writel(priv, NB8800_TXC_CR, txcr | TCR_EN);
+
+		err = readl_poll_timeout_atomic(priv->base + NB8800_RXC_CR,
+						rxcr, !(rxcr & RCR_EN),
+						1000, 100000);
+	} while (err && --retry);
+
+	nb8800_mac_af(dev, true);
+	nb8800_clearb(priv, NB8800_MAC_MODE, LOOPBACK_EN);
+	nb8800_dma_reset(dev);
+
+	return retry ? 0 : -ETIMEDOUT;
+}
+
+static void nb8800_pause_adv(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	u32 adv = 0;
+
+	if (!priv->phydev)
+		return;
+
+	if (priv->pause_rx)
+		adv |= ADVERTISED_Pause | ADVERTISED_Asym_Pause;
+	if (priv->pause_tx)
+		adv ^= ADVERTISED_Asym_Pause;
+
+	priv->phydev->supported |= adv;
+	priv->phydev->advertising |= adv;
+}
+
+static int nb8800_open(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	int err;
+
+	/* clear any pending interrupts */
+	nb8800_writel(priv, NB8800_RXC_SR, 0xf);
+	nb8800_writel(priv, NB8800_TXC_SR, 0xf);
+
+	err = nb8800_dma_init(dev);
+	if (err)
+		return err;
+
+	err = request_irq(dev->irq, nb8800_irq, 0, dev_name(&dev->dev), dev);
+	if (err)
+		goto err_free_dma;
+
+	nb8800_mac_rx(dev, true);
+	nb8800_mac_tx(dev, true);
+
+	priv->phydev = of_phy_connect(dev, priv->phy_node,
+				      nb8800_link_reconfigure, 0,
+				      priv->phy_mode);
+	if (!priv->phydev)
+		goto err_free_irq;
+
+	nb8800_pause_adv(dev);
+
+	netdev_reset_queue(dev);
+	napi_enable(&priv->napi);
+	netif_start_queue(dev);
+
+	nb8800_start_rx(dev);
+	phy_start(priv->phydev);
+
+	return 0;
+
+err_free_irq:
+	free_irq(dev->irq, dev);
+err_free_dma:
+	nb8800_dma_free(dev);
+
+	return err;
+}
+
+static int nb8800_stop(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+
+	phy_stop(priv->phydev);
+
+	netif_stop_queue(dev);
+	napi_disable(&priv->napi);
+
+	nb8800_dma_stop(dev);
+	nb8800_mac_rx(dev, false);
+	nb8800_mac_tx(dev, false);
+
+	phy_disconnect(priv->phydev);
+	priv->phydev = NULL;
+
+	free_irq(dev->irq, dev);
+
+	nb8800_dma_free(dev);
+
+	return 0;
+}
+
+static int nb8800_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+
+	return phy_mii_ioctl(priv->phydev, rq, cmd);
+}
+
+static const struct net_device_ops nb8800_netdev_ops = {
+	.ndo_open		= nb8800_open,
+	.ndo_stop		= nb8800_stop,
+	.ndo_start_xmit		= nb8800_xmit,
+	.ndo_set_mac_address	= nb8800_set_mac_address,
+	.ndo_set_rx_mode	= nb8800_set_rx_mode,
+	.ndo_do_ioctl		= nb8800_ioctl,
+	.ndo_change_mtu		= eth_change_mtu,
+	.ndo_validate_addr	= eth_validate_addr,
+};
+
+static int nb8800_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+
+	if (!priv->phydev)
+		return -ENODEV;
+
+	return phy_ethtool_gset(priv->phydev, cmd);
+}
+
+static int nb8800_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+
+	if (!priv->phydev)
+		return -ENODEV;
+
+	return phy_ethtool_sset(priv->phydev, cmd);
+}
+
+static int nb8800_nway_reset(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+
+	if (!priv->phydev)
+		return -ENODEV;
+
+	return genphy_restart_aneg(priv->phydev);
+}
+
+static void nb8800_get_pauseparam(struct net_device *dev,
+				  struct ethtool_pauseparam *pp)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+
+	pp->autoneg = priv->pause_aneg;
+	pp->rx_pause = priv->pause_rx;
+	pp->tx_pause = priv->pause_tx;
+}
+
+static int nb8800_set_pauseparam(struct net_device *dev,
+				 struct ethtool_pauseparam *pp)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+
+	priv->pause_aneg = pp->autoneg;
+	priv->pause_rx = pp->rx_pause;
+	priv->pause_tx = pp->tx_pause;
+
+	nb8800_pause_adv(dev);
+
+	if (!priv->pause_aneg)
+		nb8800_pause_config(dev);
+	else if (priv->phydev)
+		phy_start_aneg(priv->phydev);
+
+	return 0;
+}
+
+static const char nb8800_stats_names[][ETH_GSTRING_LEN] = {
+	"rx_bytes_ok",
+	"rx_frames_ok",
+	"rx_undersize_frames",
+	"rx_fragment_frames",
+	"rx_64_byte_frames",
+	"rx_127_byte_frames",
+	"rx_255_byte_frames",
+	"rx_511_byte_frames",
+	"rx_1023_byte_frames",
+	"rx_max_size_frames",
+	"rx_oversize_frames",
+	"rx_bad_fcs_frames",
+	"rx_broadcast_frames",
+	"rx_multicast_frames",
+	"rx_control_frames",
+	"rx_pause_frames",
+	"rx_unsup_control_frames",
+	"rx_align_error_frames",
+	"rx_overrun_frames",
+	"rx_jabber_frames",
+	"rx_bytes",
+	"rx_frames",
+
+	"tx_bytes_ok",
+	"tx_frames_ok",
+	"tx_64_byte_frames",
+	"tx_127_byte_frames",
+	"tx_255_byte_frames",
+	"tx_511_byte_frames",
+	"tx_1023_byte_frames",
+	"tx_max_size_frames",
+	"tx_oversize_frames",
+	"tx_broadcast_frames",
+	"tx_multicast_frames",
+	"tx_control_frames",
+	"tx_pause_frames",
+	"tx_underrun_frames",
+	"tx_single_collision_frames",
+	"tx_multi_collision_frames",
+	"tx_deferred_collision_frames",
+	"tx_late_collision_frames",
+	"tx_excessive_collision_frames",
+	"tx_bytes",
+	"tx_frames",
+	"tx_collisions",
+};
+
+#define NB8800_NUM_STATS ARRAY_SIZE(nb8800_stats_names)
+
+static int nb8800_get_sset_count(struct net_device *dev, int sset)
+{
+	if (sset == ETH_SS_STATS)
+		return NB8800_NUM_STATS;
+
+	return -EOPNOTSUPP;
+}
+
+static void nb8800_get_strings(struct net_device *dev, u32 sset, u8 *buf)
+{
+	if (sset == ETH_SS_STATS)
+		memcpy(buf, &nb8800_stats_names, sizeof(nb8800_stats_names));
+}
+
+static u32 nb8800_read_stat(struct net_device *dev, int index)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+
+	nb8800_writeb(priv, NB8800_STAT_INDEX, index);
+
+	return nb8800_readl(priv, NB8800_STAT_DATA);
+}
+
+static void nb8800_get_ethtool_stats(struct net_device *dev,
+				     struct ethtool_stats *estats, u64 *st)
+{
+	unsigned int i;
+	u32 rx, tx;
+
+	for (i = 0; i < NB8800_NUM_STATS / 2; i++) {
+		rx = nb8800_read_stat(dev, i);
+		tx = nb8800_read_stat(dev, i | 0x80);
+		st[i] = rx;
+		st[i + NB8800_NUM_STATS / 2] = tx;
+	}
+}
+
+static const struct ethtool_ops nb8800_ethtool_ops = {
+	.get_settings		= nb8800_get_settings,
+	.set_settings		= nb8800_set_settings,
+	.nway_reset		= nb8800_nway_reset,
+	.get_link		= ethtool_op_get_link,
+	.get_pauseparam		= nb8800_get_pauseparam,
+	.set_pauseparam		= nb8800_set_pauseparam,
+	.get_sset_count		= nb8800_get_sset_count,
+	.get_strings		= nb8800_get_strings,
+	.get_ethtool_stats	= nb8800_get_ethtool_stats,
+};
+
+static int nb8800_hw_init(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	u32 val;
+
+	val = TX_RETRY_EN | TX_PAD_EN | TX_APPEND_FCS;
+	nb8800_writeb(priv, NB8800_TX_CTL1, val);
+
+	/* Collision retry count */
+	nb8800_writeb(priv, NB8800_TX_CTL2, 5);
+
+	val = RX_PAD_STRIP | RX_AF_EN;
+	nb8800_writeb(priv, NB8800_RX_CTL, val);
+
+	/* Chosen by fair dice roll */
+	nb8800_writeb(priv, NB8800_RANDOM_SEED, 4);
+
+	/* TX cycles per deferral period */
+	nb8800_writeb(priv, NB8800_TX_SDP, 12);
+
+	/* The following three threshold values have been
+	 * experimentally determined for good results.
+	 */
+
+	/* RX/TX FIFO threshold for partial empty (64-bit entries) */
+	nb8800_writeb(priv, NB8800_PE_THRESHOLD, 0);
+
+	/* RX/TX FIFO threshold for partial full (64-bit entries) */
+	nb8800_writeb(priv, NB8800_PF_THRESHOLD, 255);
+
+	/* Buffer size for transmit (64-bit entries) */
+	nb8800_writeb(priv, NB8800_TX_BUFSIZE, 64);
+
+	/* Configure tx DMA */
+
+	val = nb8800_readl(priv, NB8800_TXC_CR);
+	val &= TCR_LE;		/* keep endian setting */
+	val |= TCR_DM;		/* DMA descriptor mode */
+	val |= TCR_RS;		/* automatically store tx status  */
+	val |= TCR_DIE;		/* interrupt on DMA chain completion */
+	val |= TCR_TFI(7);	/* interrupt after 7 frames transmitted */
+	val |= TCR_BTS(2);	/* 32-byte bus transaction size */
+	nb8800_writel(priv, NB8800_TXC_CR, val);
+
+	/* TX complete interrupt after 10 ms or 7 frames (see above) */
+	val = clk_get_rate(priv->clk) / 100;
+	nb8800_writel(priv, NB8800_TX_ITR, val);
+
+	/* Configure rx DMA */
+
+	val = nb8800_readl(priv, NB8800_RXC_CR);
+	val &= RCR_LE;		/* keep endian setting */
+	val |= RCR_DM;		/* DMA descriptor mode */
+	val |= RCR_RS;		/* automatically store rx status */
+	val |= RCR_DIE;		/* interrupt at end of DMA chain */
+	val |= RCR_RFI(7);	/* interrupt after 7 frames received */
+	val |= RCR_BTS(2);	/* 32-byte bus transaction size */
+	nb8800_writel(priv, NB8800_RXC_CR, val);
+
+	/* The rx interrupt can fire before the DMA has completed
+	 * unless a small delay is added.  50 us is hopefully enough.
+	 */
+	priv->rx_itr_irq = clk_get_rate(priv->clk) / 20000;
+
+	/* In NAPI poll mode we want to disable interrupts, but the
+	 * hardware does not permit this.  Delay 10 ms instead.
+	 */
+	priv->rx_itr_poll = clk_get_rate(priv->clk) / 100;
+
+	nb8800_writel(priv, NB8800_RX_ITR, priv->rx_itr_irq);
+
+	priv->rx_dma_config = RX_BUF_SIZE | DESC_BTS(2) | DESC_DS | DESC_EOF;
+
+	/* Flow control settings */
+
+	/* Pause time of 0.1 ms */
+	val = 100000 / 512;
+	nb8800_writeb(priv, NB8800_PQ1, val >> 8);
+	nb8800_writeb(priv, NB8800_PQ2, val & 0xff);
+
+	/* Auto-negotiate by default */
+	priv->pause_aneg = true;
+	priv->pause_rx = true;
+	priv->pause_tx = true;
+
+	nb8800_mc_init(dev, 0);
+
+	return 0;
+}
+
+static int nb8800_tangox_init(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	u32 pad_mode = PAD_MODE_MII;
+
+	switch (priv->phy_mode) {
+	case PHY_INTERFACE_MODE_MII:
+	case PHY_INTERFACE_MODE_GMII:
+		pad_mode = PAD_MODE_MII;
+		break;
+
+	case PHY_INTERFACE_MODE_RGMII:
+		pad_mode = PAD_MODE_RGMII;
+		break;
+
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		pad_mode = PAD_MODE_RGMII | PAD_MODE_GTX_CLK_DELAY;
+		break;
+
+	default:
+		dev_err(dev->dev.parent, "unsupported phy mode %s\n",
+			phy_modes(priv->phy_mode));
+		return -EINVAL;
+	}
+
+	nb8800_writeb(priv, NB8800_TANGOX_PAD_MODE, pad_mode);
+
+	return 0;
+}
+
+static int nb8800_tangox_reset(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	int clk_div;
+
+	nb8800_writeb(priv, NB8800_TANGOX_RESET, 0);
+	usleep_range(1000, 10000);
+	nb8800_writeb(priv, NB8800_TANGOX_RESET, 1);
+
+	wmb();		/* ensure reset is cleared before proceeding */
+
+	clk_div = DIV_ROUND_UP(clk_get_rate(priv->clk), 2 * MAX_MDC_CLOCK);
+	nb8800_writew(priv, NB8800_TANGOX_MDIO_CLKDIV, clk_div);
+
+	return 0;
+}
+
+static const struct nb8800_ops nb8800_tangox_ops = {
+	.init	= nb8800_tangox_init,
+	.reset	= nb8800_tangox_reset,
+};
+
+static int nb8800_tango4_init(struct net_device *dev)
+{
+	struct nb8800_priv *priv = netdev_priv(dev);
+	int err;
+
+	err = nb8800_tangox_init(dev);
+	if (err)
+		return err;
+
+	/* On tango4 interrupt on DMA completion per frame works and gives
+	 * better performance despite generating more rx interrupts.
+	 */
+
+	/* Disable unnecessary interrupt on rx completion */
+	nb8800_clearl(priv, NB8800_RXC_CR, RCR_RFI(7));
+
+	/* Request interrupt on descriptor DMA completion */
+	priv->rx_dma_config |= DESC_ID;
+
+	return 0;
+}
+
+static const struct nb8800_ops nb8800_tango4_ops = {
+	.init	= nb8800_tango4_init,
+	.reset	= nb8800_tangox_reset,
+};
+
+static const struct of_device_id nb8800_dt_ids[] = {
+	{
+		.compatible = "aurora,nb8800",
+	},
+	{
+		.compatible = "sigma,smp8642-ethernet",
+		.data = &nb8800_tangox_ops,
+	},
+	{
+		.compatible = "sigma,smp8734-ethernet",
+		.data = &nb8800_tango4_ops,
+	},
+	{ }
+};
+
+static int nb8800_probe(struct platform_device *pdev)
+{
+	const struct of_device_id *match;
+	const struct nb8800_ops *ops = NULL;
+	struct nb8800_priv *priv;
+	struct resource *res;
+	struct net_device *dev;
+	struct mii_bus *bus;
+	const unsigned char *mac;
+	void __iomem *base;
+	int irq;
+	int ret;
+
+	match = of_match_device(nb8800_dt_ids, &pdev->dev);
+	if (match)
+		ops = match->data;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq <= 0) {
+		dev_err(&pdev->dev, "No IRQ\n");
+		return -EINVAL;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	dev_dbg(&pdev->dev, "AU-NB8800 Ethernet at %pa\n", &res->start);
+
+	dev = alloc_etherdev(sizeof(*priv));
+	if (!dev)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, dev);
+	SET_NETDEV_DEV(dev, &pdev->dev);
+
+	priv = netdev_priv(dev);
+	priv->base = base;
+
+	priv->phy_mode = of_get_phy_mode(pdev->dev.of_node);
+	if (priv->phy_mode < 0)
+		priv->phy_mode = PHY_INTERFACE_MODE_RGMII;
+
+	priv->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(priv->clk)) {
+		dev_err(&pdev->dev, "failed to get clock\n");
+		ret = PTR_ERR(priv->clk);
+		goto err_free_dev;
+	}
+
+	ret = clk_prepare_enable(priv->clk);
+	if (ret)
+		goto err_free_dev;
+
+	spin_lock_init(&priv->tx_lock);
+
+	if (ops && ops->reset) {
+		ret = ops->reset(dev);
+		if (ret)
+			goto err_free_dev;
+	}
+
+	bus = devm_mdiobus_alloc(&pdev->dev);
+	if (!bus) {
+		ret = -ENOMEM;
+		goto err_disable_clk;
+	}
+
+	bus->name = "nb8800-mii";
+	bus->read = nb8800_mdio_read;
+	bus->write = nb8800_mdio_write;
+	bus->parent = &pdev->dev;
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%lx.nb8800-mii",
+		 (unsigned long)res->start);
+	bus->priv = priv;
+
+	ret = of_mdiobus_register(bus, pdev->dev.of_node);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to register MII bus\n");
+		goto err_disable_clk;
+	}
+
+	priv->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0);
+	if (!priv->phy_node) {
+		dev_err(&pdev->dev, "no PHY specified\n");
+		ret = -ENODEV;
+		goto err_free_bus;
+	}
+
+	priv->mii_bus = bus;
+
+	ret = nb8800_hw_init(dev);
+	if (ret)
+		goto err_free_bus;
+
+	if (ops && ops->init) {
+		ret = ops->init(dev);
+		if (ret)
+			goto err_free_bus;
+	}
+
+	dev->netdev_ops = &nb8800_netdev_ops;
+	dev->ethtool_ops = &nb8800_ethtool_ops;
+	dev->flags |= IFF_MULTICAST;
+	dev->irq = irq;
+
+	mac = of_get_mac_address(pdev->dev.of_node);
+	if (mac)
+		ether_addr_copy(dev->dev_addr, mac);
+
+	if (!is_valid_ether_addr(dev->dev_addr))
+		eth_hw_addr_random(dev);
+
+	nb8800_update_mac_addr(dev);
+
+	netif_carrier_off(dev);
+
+	ret = register_netdev(dev);
+	if (ret) {
+		netdev_err(dev, "failed to register netdev\n");
+		goto err_free_dma;
+	}
+
+	netif_napi_add(dev, &priv->napi, nb8800_poll, NAPI_POLL_WEIGHT);
+
+	netdev_info(dev, "MAC address %pM\n", dev->dev_addr);
+
+	return 0;
+
+err_free_dma:
+	nb8800_dma_free(dev);
+err_free_bus:
+	mdiobus_unregister(bus);
+err_disable_clk:
+	clk_disable_unprepare(priv->clk);
+err_free_dev:
+	free_netdev(dev);
+
+	return ret;
+}
+
+static int nb8800_remove(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct nb8800_priv *priv = netdev_priv(ndev);
+
+	unregister_netdev(ndev);
+
+	mdiobus_unregister(priv->mii_bus);
+
+	clk_disable_unprepare(priv->clk);
+
+	nb8800_dma_free(ndev);
+	free_netdev(ndev);
+
+	return 0;
+}
+
+static struct platform_driver nb8800_driver = {
+	.driver = {
+		.name		= "nb8800",
+		.of_match_table	= nb8800_dt_ids,
+	},
+	.probe	= nb8800_probe,
+	.remove	= nb8800_remove,
+};
+
+module_platform_driver(nb8800_driver);
+
+MODULE_DESCRIPTION("Aurora AU-NB8800 Ethernet driver");
+MODULE_AUTHOR("Mans Rullgard <mans@mansr.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/aurora/nb8800.h b/drivers/net/ethernet/aurora/nb8800.h
new file mode 100644
index 000000000000..e5adbc2aac9f
--- /dev/null
+++ b/drivers/net/ethernet/aurora/nb8800.h
@@ -0,0 +1,316 @@
+#ifndef _NB8800_H_
+#define _NB8800_H_
+
+#include <linux/types.h>
+#include <linux/skbuff.h>
+#include <linux/phy.h>
+#include <linux/clk.h>
+#include <linux/bitops.h>
+
+#define RX_DESC_COUNT			256
+#define TX_DESC_COUNT			256
+
+#define NB8800_DESC_LOW			4
+
+#define RX_BUF_SIZE			1552
+
+#define RX_COPYBREAK			256
+#define RX_COPYHDR			128
+
+#define MAX_MDC_CLOCK			2500000
+
+/* Stargate Solutions SSN8800 core registers */
+#define NB8800_TX_CTL1			0x000
+#define TX_TPD				BIT(5)
+#define TX_APPEND_FCS			BIT(4)
+#define TX_PAD_EN			BIT(3)
+#define TX_RETRY_EN			BIT(2)
+#define TX_EN				BIT(0)
+
+#define NB8800_TX_CTL2			0x001
+
+#define NB8800_RX_CTL			0x004
+#define RX_BC_DISABLE			BIT(7)
+#define RX_RUNT				BIT(6)
+#define RX_AF_EN			BIT(5)
+#define RX_PAUSE_EN			BIT(3)
+#define RX_SEND_CRC			BIT(2)
+#define RX_PAD_STRIP			BIT(1)
+#define RX_EN				BIT(0)
+
+#define NB8800_RANDOM_SEED		0x008
+#define NB8800_TX_SDP			0x14
+#define NB8800_TX_TPDP1			0x18
+#define NB8800_TX_TPDP2			0x19
+#define NB8800_SLOT_TIME		0x1c
+
+#define NB8800_MDIO_CMD			0x020
+#define MDIO_CMD_GO			BIT(31)
+#define MDIO_CMD_WR			BIT(26)
+#define MDIO_CMD_ADDR(x)		((x) << 21)
+#define MDIO_CMD_REG(x)			((x) << 16)
+#define MDIO_CMD_DATA(x)		((x) <<	 0)
+
+#define NB8800_MDIO_STS			0x024
+#define MDIO_STS_ERR			BIT(31)
+
+#define NB8800_MC_ADDR(i)		(0x028 + (i))
+#define NB8800_MC_INIT			0x02e
+#define NB8800_UC_ADDR(i)		(0x03c + (i))
+
+#define NB8800_MAC_MODE			0x044
+#define RGMII_MODE			BIT(7)
+#define HALF_DUPLEX			BIT(4)
+#define BURST_EN			BIT(3)
+#define LOOPBACK_EN			BIT(2)
+#define GMAC_MODE			BIT(0)
+
+#define NB8800_IC_THRESHOLD		0x050
+#define NB8800_PE_THRESHOLD		0x051
+#define NB8800_PF_THRESHOLD		0x052
+#define NB8800_TX_BUFSIZE		0x054
+#define NB8800_FIFO_CTL			0x056
+#define NB8800_PQ1			0x060
+#define NB8800_PQ2			0x061
+#define NB8800_SRC_ADDR(i)		(0x06a + (i))
+#define NB8800_STAT_DATA		0x078
+#define NB8800_STAT_INDEX		0x07c
+#define NB8800_STAT_CLEAR		0x07d
+
+#define NB8800_SLEEP_MODE		0x07e
+#define SLEEP_MODE			BIT(0)
+
+#define NB8800_WAKEUP			0x07f
+#define WAKEUP				BIT(0)
+
+/* Aurora NB8800 host interface registers */
+#define NB8800_TXC_CR			0x100
+#define TCR_LK				BIT(12)
+#define TCR_DS				BIT(11)
+#define TCR_BTS(x)			(((x) & 0x7) << 8)
+#define TCR_DIE				BIT(7)
+#define TCR_TFI(x)			(((x) & 0x7) << 4)
+#define TCR_LE				BIT(3)
+#define TCR_RS				BIT(2)
+#define TCR_DM				BIT(1)
+#define TCR_EN				BIT(0)
+
+#define NB8800_TXC_SR			0x104
+#define TSR_DE				BIT(3)
+#define TSR_DI				BIT(2)
+#define TSR_TO				BIT(1)
+#define TSR_TI				BIT(0)
+
+#define NB8800_TX_SAR			0x108
+#define NB8800_TX_DESC_ADDR		0x10c
+
+#define NB8800_TX_REPORT_ADDR		0x110
+#define TX_BYTES_TRANSFERRED(x)		(((x) >> 16) & 0xffff)
+#define TX_FIRST_DEFERRAL		BIT(7)
+#define TX_EARLY_COLLISIONS(x)		(((x) >> 3) & 0xf)
+#define TX_LATE_COLLISION		BIT(2)
+#define TX_PACKET_DROPPED		BIT(1)
+#define TX_FIFO_UNDERRUN		BIT(0)
+#define IS_TX_ERROR(r)			((r) & 0x07)
+
+#define NB8800_TX_FIFO_SR		0x114
+#define NB8800_TX_ITR			0x118
+
+#define NB8800_RXC_CR			0x200
+#define RCR_FL				BIT(13)
+#define RCR_LK				BIT(12)
+#define RCR_DS				BIT(11)
+#define RCR_BTS(x)			(((x) & 7) << 8)
+#define RCR_DIE				BIT(7)
+#define RCR_RFI(x)			(((x) & 7) << 4)
+#define RCR_LE				BIT(3)
+#define RCR_RS				BIT(2)
+#define RCR_DM				BIT(1)
+#define RCR_EN				BIT(0)
+
+#define NB8800_RXC_SR			0x204
+#define RSR_DE				BIT(3)
+#define RSR_DI				BIT(2)
+#define RSR_RO				BIT(1)
+#define RSR_RI				BIT(0)
+
+#define NB8800_RX_SAR			0x208
+#define NB8800_RX_DESC_ADDR		0x20c
+
+#define NB8800_RX_REPORT_ADDR		0x210
+#define RX_BYTES_TRANSFERRED(x)		(((x) >> 16) & 0xFFFF)
+#define RX_MULTICAST_PKT		BIT(9)
+#define RX_BROADCAST_PKT		BIT(8)
+#define RX_LENGTH_ERR			BIT(7)
+#define RX_FCS_ERR			BIT(6)
+#define RX_RUNT_PKT			BIT(5)
+#define RX_FIFO_OVERRUN			BIT(4)
+#define RX_LATE_COLLISION		BIT(3)
+#define RX_ALIGNMENT_ERROR		BIT(2)
+#define RX_ERROR_MASK			0xfc
+#define IS_RX_ERROR(r)			((r) & RX_ERROR_MASK)
+
+#define NB8800_RX_FIFO_SR		0x214
+#define NB8800_RX_ITR			0x218
+
+/* Sigma Designs SMP86xx additional registers */
+#define NB8800_TANGOX_PAD_MODE		0x400
+#define PAD_MODE_MASK			0x7
+#define PAD_MODE_MII			0x0
+#define PAD_MODE_RGMII			0x1
+#define PAD_MODE_GTX_CLK_INV		BIT(3)
+#define PAD_MODE_GTX_CLK_DELAY		BIT(4)
+
+#define NB8800_TANGOX_MDIO_CLKDIV	0x420
+#define NB8800_TANGOX_RESET		0x424
+
+/* Hardware DMA descriptor */
+struct nb8800_dma_desc {
+	u32				s_addr;	/* start address */
+	u32				n_addr;	/* next descriptor address */
+	u32				r_addr;	/* report address */
+	u32				config;
+} __aligned(8);
+
+#define DESC_ID				BIT(23)
+#define DESC_EOC			BIT(22)
+#define DESC_EOF			BIT(21)
+#define DESC_LK				BIT(20)
+#define DESC_DS				BIT(19)
+#define DESC_BTS(x)			(((x) & 0x7) << 16)
+
+/* DMA descriptor and associated data for rx.
+ * Allocated from coherent memory.
+ */
+struct nb8800_rx_desc {
+	/* DMA descriptor */
+	struct nb8800_dma_desc		desc;
+
+	/* Status report filled in by hardware */
+	u32				report;
+};
+
+/* Address of buffer on rx ring */
+struct nb8800_rx_buf {
+	struct page			*page;
+	unsigned long			offset;
+};
+
+/* DMA descriptors and associated data for tx.
+ * Allocated from coherent memory.
+ */
+struct nb8800_tx_desc {
+	/* DMA descriptor.  The second descriptor is used if packet
+	 * data is unaligned.
+	 */
+	struct nb8800_dma_desc		desc[2];
+
+	/* Status report filled in by hardware */
+	u32				report;
+
+	/* Bounce buffer for initial unaligned part of packet */
+	u8				buf[8] __aligned(8);
+};
+
+/* Packet in tx queue */
+struct nb8800_tx_buf {
+	/* Currently queued skb */
+	struct sk_buff			*skb;
+
+	/* DMA address of the first descriptor */
+	dma_addr_t			dma_desc;
+
+	/* DMA address of packet data */
+	dma_addr_t			dma_addr;
+
+	/* Length of DMA mapping, less than skb->len if alignment
+	 * buffer is used.
+	 */
+	unsigned int			dma_len;
+
+	/* Number of packets in chain starting here */
+	unsigned int			chain_len;
+
+	/* Packet chain ready to be submitted to hardware */
+	bool				ready;
+};
+
+struct nb8800_priv {
+	struct napi_struct		napi;
+
+	void __iomem			*base;
+
+	/* RX DMA descriptors */
+	struct nb8800_rx_desc		*rx_descs;
+
+	/* RX buffers referenced by DMA descriptors */
+	struct nb8800_rx_buf		*rx_bufs;
+
+	/* Current end of chain */
+	u32				rx_eoc;
+
+	/* Value for rx interrupt time register in NAPI interrupt mode */
+	u32				rx_itr_irq;
+
+	/* Value for rx interrupt time register in NAPI poll mode */
+	u32				rx_itr_poll;
+
+	/* Value for config field of rx DMA descriptors */
+	u32				rx_dma_config;
+
+	/* TX DMA descriptors */
+	struct nb8800_tx_desc		*tx_descs;
+
+	/* TX packet queue */
+	struct nb8800_tx_buf		*tx_bufs;
+
+	/* Number of free tx queue entries */
+	atomic_t			tx_free;
+
+	/* First free tx queue entry */
+	u32				tx_next;
+
+	/* Next buffer to transmit */
+	u32				tx_queue;
+
+	/* Start of current packet chain */
+	struct nb8800_tx_buf		*tx_chain;
+
+	/* Next buffer to reclaim */
+	u32				tx_done;
+
+	/* Lock for DMA activation */
+	spinlock_t			tx_lock;
+
+	struct mii_bus			*mii_bus;
+	struct device_node		*phy_node;
+	struct phy_device		*phydev;
+
+	/* PHY connection type from DT */
+	int				phy_mode;
+
+	/* Current link status */
+	int				speed;
+	int				duplex;
+	int				link;
+
+	/* Pause settings */
+	bool				pause_aneg;
+	bool				pause_rx;
+	bool				pause_tx;
+
+	/* DMA base address of rx descriptors, see rx_descs above */
+	dma_addr_t			rx_desc_dma;
+
+	/* DMA base address of tx descriptors, see tx_descs above */
+	dma_addr_t			tx_desc_dma;
+
+	struct clk			*clk;
+};
+
+struct nb8800_ops {
+	int				(*init)(struct net_device *dev);
+	int				(*reset)(struct net_device *dev);
+};
+
+#endif /* _NB8800_H_ */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index c9b036789184..2e611dc5f162 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -10139,8 +10139,8 @@ static void __bnx2x_del_vxlan_port(struct bnx2x *bp, u16 port)
 		DP(BNX2X_MSG_SP, "Invalid vxlan port\n");
 		return;
 	}
-	bp->vxlan_dst_port--;
-	if (bp->vxlan_dst_port)
+	bp->vxlan_dst_port_count--;
+	if (bp->vxlan_dst_port_count)
 		return;
 
 	if (netif_running(bp->dev)) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index db15c5ee09c5..bdf094fb6ef9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3625,6 +3625,7 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		pf->fw_fid = le16_to_cpu(resp->fid);
 		pf->port_id = le16_to_cpu(resp->port_id);
 		memcpy(pf->mac_addr, resp->perm_mac_address, ETH_ALEN);
+		memcpy(bp->dev->dev_addr, pf->mac_addr, ETH_ALEN);
 		pf->max_rsscos_ctxs = le16_to_cpu(resp->max_rsscos_ctx);
 		pf->max_cp_rings = le16_to_cpu(resp->max_cmpl_rings);
 		pf->max_tx_rings = le16_to_cpu(resp->max_tx_rings);
@@ -3648,8 +3649,11 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp)
 
 		vf->fw_fid = le16_to_cpu(resp->fid);
 		memcpy(vf->mac_addr, resp->perm_mac_address, ETH_ALEN);
-		if (!is_valid_ether_addr(vf->mac_addr))
-			random_ether_addr(vf->mac_addr);
+		if (is_valid_ether_addr(vf->mac_addr))
+			/* overwrite netdev dev_adr with admin VF MAC */
+			memcpy(bp->dev->dev_addr, vf->mac_addr, ETH_ALEN);
+		else
+			random_ether_addr(bp->dev->dev_addr);
 
 		vf->max_rsscos_ctxs = le16_to_cpu(resp->max_rsscos_ctx);
 		vf->max_cp_rings = le16_to_cpu(resp->max_cmpl_rings);
@@ -3880,6 +3884,8 @@ static int bnxt_alloc_rfs_vnics(struct bnxt *bp)
 #endif
 }
 
+static int bnxt_cfg_rx_mode(struct bnxt *);
+
 static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init)
 {
 	int rc = 0;
@@ -3946,11 +3952,9 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init)
 		bp->vnic_info[0].rx_mask |=
 				CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS;
 
-	rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0);
-	if (rc) {
-		netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %x\n", rc);
+	rc = bnxt_cfg_rx_mode(bp);
+	if (rc)
 		goto err_out;
-	}
 
 	rc = bnxt_hwrm_set_coal(bp);
 	if (rc)
@@ -4865,7 +4869,7 @@ static void bnxt_set_rx_mode(struct net_device *dev)
 	}
 }
 
-static void bnxt_cfg_rx_mode(struct bnxt *bp)
+static int bnxt_cfg_rx_mode(struct bnxt *bp)
 {
 	struct net_device *dev = bp->dev;
 	struct bnxt_vnic_info *vnic = &bp->vnic_info[0];
@@ -4914,6 +4918,7 @@ static void bnxt_cfg_rx_mode(struct bnxt *bp)
 			netdev_err(bp->dev, "HWRM vnic filter failure rc: %x\n",
 				   rc);
 			vnic->uc_filter_count = i;
+			return rc;
 		}
 	}
 
@@ -4922,6 +4927,8 @@ skip_uc:
 	if (rc)
 		netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %x\n",
 			   rc);
+
+	return rc;
 }
 
 static netdev_features_t bnxt_fix_features(struct net_device *dev,
@@ -5212,13 +5219,27 @@ init_err:
 static int bnxt_change_mac_addr(struct net_device *dev, void *p)
 {
 	struct sockaddr *addr = p;
+	struct bnxt *bp = netdev_priv(dev);
+	int rc = 0;
 
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
+#ifdef CONFIG_BNXT_SRIOV
+	if (BNXT_VF(bp) && is_valid_ether_addr(bp->vf.mac_addr))
+		return -EADDRNOTAVAIL;
+#endif
+
+	if (ether_addr_equal(addr->sa_data, dev->dev_addr))
+		return 0;
+
 	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
+	if (netif_running(dev)) {
+		bnxt_close_nic(bp, false, false);
+		rc = bnxt_open_nic(bp, false, false);
+	}
 
-	return 0;
+	return rc;
 }
 
 /* rtnl_lock held */
@@ -5686,15 +5707,12 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	bnxt_set_tpa_flags(bp);
 	bnxt_set_ring_params(bp);
 	dflt_rings = netif_get_num_default_rss_queues();
-	if (BNXT_PF(bp)) {
-		memcpy(dev->dev_addr, bp->pf.mac_addr, ETH_ALEN);
+	if (BNXT_PF(bp))
 		bp->pf.max_irqs = max_irqs;
-	} else {
 #if defined(CONFIG_BNXT_SRIOV)
-		memcpy(dev->dev_addr, bp->vf.mac_addr, ETH_ALEN);
+	else
 		bp->vf.max_irqs = max_irqs;
 #endif
-	}
 	bnxt_get_max_rings(bp, &max_rx_rings, &max_tx_rings);
 	bp->rx_nr_rings = min_t(int, dflt_rings, max_rx_rings);
 	bp->tx_nr_rings_per_tc = min_t(int, dflt_rings, max_tx_rings);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index f4cf68861069..7a9af2887d8e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -804,10 +804,9 @@ void bnxt_update_vf_mac(struct bnxt *bp)
 	if (!is_valid_ether_addr(resp->perm_mac_address))
 		goto update_vf_mac_exit;
 
-	if (ether_addr_equal(resp->perm_mac_address, bp->vf.mac_addr))
-		goto update_vf_mac_exit;
-
-	memcpy(bp->vf.mac_addr, resp->perm_mac_address, ETH_ALEN);
+	if (!ether_addr_equal(resp->perm_mac_address, bp->vf.mac_addr))
+		memcpy(bp->vf.mac_addr, resp->perm_mac_address, ETH_ALEN);
+	/* overwrite netdev dev_adr with admin VF MAC */
 	memcpy(bp->dev->dev_addr, bp->vf.mac_addr, ETH_ALEN);
 update_vf_mac_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 88c1e1a834f8..169059c92f80 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -1682,6 +1682,8 @@ static void macb_init_hw(struct macb *bp)
 	macb_set_hwaddr(bp);
 
 	config = macb_mdc_clk_div(bp);
+	if (bp->phy_interface == PHY_INTERFACE_MODE_SGMII)
+		config |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL);
 	config |= MACB_BF(RBOF, NET_IP_ALIGN);	/* Make eth data aligned */
 	config |= MACB_BIT(PAE);		/* PAuse Enable */
 	config |= MACB_BIT(DRFCS);		/* Discard Rx FCS */
@@ -2416,6 +2418,8 @@ static int macb_init(struct platform_device *pdev)
 	/* Set MII management clock divider */
 	val = macb_mdc_clk_div(bp);
 	val |= macb_dbw(bp);
+	if (bp->phy_interface == PHY_INTERFACE_MODE_SGMII)
+		val |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL);
 	macb_writel(bp, NCFGR, val);
 
 	return 0;
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 6e1faea00ca8..d83b0db77821 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -215,12 +215,17 @@
 /* GEM specific NCFGR bitfields. */
 #define GEM_GBE_OFFSET		10 /* Gigabit mode enable */
 #define GEM_GBE_SIZE		1
+#define GEM_PCSSEL_OFFSET	11
+#define GEM_PCSSEL_SIZE		1
 #define GEM_CLK_OFFSET		18 /* MDC clock division */
 #define GEM_CLK_SIZE		3
 #define GEM_DBW_OFFSET		21 /* Data bus width */
 #define GEM_DBW_SIZE		2
 #define GEM_RXCOEN_OFFSET	24
 #define GEM_RXCOEN_SIZE		1
+#define GEM_SGMIIEN_OFFSET	27
+#define GEM_SGMIIEN_SIZE	1
+
 
 /* Constants for data bus width. */
 #define GEM_DBW32		0 /* 32 bit AMBA AHB data bus width */
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index d3950b20feb9..39ca6744a4e6 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -120,10 +120,9 @@
  * Calculated for SCLK of 700Mhz
  * value written should be a 1/16th of what is expected
  *
- * 1 tick per 0.05usec = value of 2.2
- * This 10% would be covered in CQ timer thresh value
+ * 1 tick per 0.025usec
  */
-#define NICPF_CLK_PER_INT_TICK		2
+#define NICPF_CLK_PER_INT_TICK		1
 
 /* Time to wait before we decide that a SQ is stuck.
  *
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index c561fdcb79a7..4b7fd63ae57c 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -37,6 +37,7 @@ struct nicpf {
 #define	NIC_GET_BGX_FROM_VF_LMAC_MAP(map)	((map >> 4) & 0xF)
 #define	NIC_GET_LMAC_FROM_VF_LMAC_MAP(map)	(map & 0xF)
 	u8			vf_lmac_map[MAX_LMAC];
+	u8			lmac_cnt;
 	struct delayed_work     dwork;
 	struct workqueue_struct *check_link;
 	u8			link[MAX_LMAC];
@@ -279,6 +280,7 @@ static void nic_set_lmac_vf_mapping(struct nicpf *nic)
 	u64 lmac_credit;
 
 	nic->num_vf_en = 0;
+	nic->lmac_cnt = 0;
 
 	for (bgx = 0; bgx < NIC_MAX_BGX; bgx++) {
 		if (!(bgx_map & (1 << bgx)))
@@ -288,6 +290,7 @@ static void nic_set_lmac_vf_mapping(struct nicpf *nic)
 			nic->vf_lmac_map[next_bgx_lmac++] =
 						NIC_SET_VF_LMAC_MAP(bgx, lmac);
 		nic->num_vf_en += lmac_cnt;
+		nic->lmac_cnt += lmac_cnt;
 
 		/* Program LMAC credits */
 		lmac_credit = (1ull << 1); /* channel credit enable */
@@ -715,6 +718,13 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 	case NIC_MBOX_MSG_CFG_DONE:
 		/* Last message of VF config msg sequence */
 		nic->vf_enabled[vf] = true;
+		if (vf >= nic->lmac_cnt)
+			goto unlock;
+
+		bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+		lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+
+		bgx_lmac_rx_tx_enable(nic->node, bgx, lmac, true);
 		goto unlock;
 	case NIC_MBOX_MSG_SHUTDOWN:
 		/* First msg in VF teardown sequence */
@@ -722,6 +732,14 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 		if (vf >= nic->num_vf_en)
 			nic->sqs_used[vf - nic->num_vf_en] = false;
 		nic->pqs_vf[vf] = 0;
+
+		if (vf >= nic->lmac_cnt)
+			break;
+
+		bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+		lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+
+		bgx_lmac_rx_tx_enable(nic->node, bgx, lmac, false);
 		break;
 	case NIC_MBOX_MSG_ALLOC_SQS:
 		nic_alloc_sqs(nic, &mbx.sqs_alloc);
@@ -940,7 +958,7 @@ static void nic_poll_for_link(struct work_struct *work)
 
 	mbx.link_status.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE;
 
-	for (vf = 0; vf < nic->num_vf_en; vf++) {
+	for (vf = 0; vf < nic->lmac_cnt; vf++) {
 		/* Poll only if VF is UP */
 		if (!nic->vf_enabled[vf])
 			continue;
@@ -1074,8 +1092,7 @@ static void nic_remove(struct pci_dev *pdev)
 
 	if (nic->check_link) {
 		/* Destroy work Queue */
-		cancel_delayed_work(&nic->dwork);
-		flush_workqueue(nic->check_link);
+		cancel_delayed_work_sync(&nic->dwork);
 		destroy_workqueue(nic->check_link);
 	}
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index af54c10945c2..a12b2e38cf61 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -112,6 +112,13 @@ static int nicvf_get_settings(struct net_device *netdev,
 
 	cmd->supported = 0;
 	cmd->transceiver = XCVR_EXTERNAL;
+
+	if (!nic->link_up) {
+		cmd->duplex = DUPLEX_UNKNOWN;
+		ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN);
+		return 0;
+	}
+
 	if (nic->speed <= 1000) {
 		cmd->port = PORT_MII;
 		cmd->autoneg = AUTONEG_ENABLE;
@@ -125,6 +132,13 @@ static int nicvf_get_settings(struct net_device *netdev,
 	return 0;
 }
 
+static u32 nicvf_get_link(struct net_device *netdev)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+
+	return nic->link_up;
+}
+
 static void nicvf_get_drvinfo(struct net_device *netdev,
 			      struct ethtool_drvinfo *info)
 {
@@ -660,7 +674,7 @@ static int nicvf_set_channels(struct net_device *dev,
 
 static const struct ethtool_ops nicvf_ethtool_ops = {
 	.get_settings		= nicvf_get_settings,
-	.get_link		= ethtool_op_get_link,
+	.get_link		= nicvf_get_link,
 	.get_drvinfo		= nicvf_get_drvinfo,
 	.get_msglevel		= nicvf_get_msglevel,
 	.set_msglevel		= nicvf_set_msglevel,
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 7f709cbdcd87..dde8dc720cd3 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1057,6 +1057,7 @@ int nicvf_stop(struct net_device *netdev)
 
 	netif_carrier_off(netdev);
 	netif_tx_stop_all_queues(nic->netdev);
+	nic->link_up = false;
 
 	/* Teardown secondary qsets first */
 	if (!nic->sqs_mode) {
@@ -1211,9 +1212,6 @@ int nicvf_open(struct net_device *netdev)
 	nic->drv_stats.txq_stop = 0;
 	nic->drv_stats.txq_wake = 0;
 
-	netif_carrier_on(netdev);
-	netif_tx_start_all_queues(netdev);
-
 	return 0;
 cleanup:
 	nicvf_disable_intr(nic, NICVF_INTR_MBOX, 0);
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index e404ea837727..206b6a71a545 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -592,7 +592,7 @@ void nicvf_cmp_queue_config(struct nicvf *nic, struct queue_set *qs,
 	/* Set threshold value for interrupt generation */
 	nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_THRESH, qidx, cq->thresh);
 	nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_CFG2,
-			      qidx, nic->cq_coalesce_usecs);
+			      qidx, CMP_QUEUE_TIMER_THRESH);
 }
 
 /* Configures transmit queue */
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
index fb4957d09914..033e8306e91c 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
@@ -76,7 +76,7 @@
 #define CMP_QSIZE		CMP_QUEUE_SIZE2
 #define CMP_QUEUE_LEN		(1ULL << (CMP_QSIZE + 10))
 #define CMP_QUEUE_CQE_THRESH	0
-#define CMP_QUEUE_TIMER_THRESH	220 /* 10usec */
+#define CMP_QUEUE_TIMER_THRESH	80 /* ~2usec */
 
 #define RBDR_SIZE		RBDR_SIZE0
 #define RCV_BUF_COUNT		(1ULL << (RBDR_SIZE + 13))
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 180aa9fabf48..9df26c2263bc 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -186,6 +186,23 @@ void bgx_set_lmac_mac(int node, int bgx_idx, int lmacid, const u8 *mac)
 }
 EXPORT_SYMBOL(bgx_set_lmac_mac);
 
+void bgx_lmac_rx_tx_enable(int node, int bgx_idx, int lmacid, bool enable)
+{
+	struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx];
+	u64 cfg;
+
+	if (!bgx)
+		return;
+
+	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+	if (enable)
+		cfg |= CMR_PKT_RX_EN | CMR_PKT_TX_EN;
+	else
+		cfg &= ~(CMR_PKT_RX_EN | CMR_PKT_TX_EN);
+	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+}
+EXPORT_SYMBOL(bgx_lmac_rx_tx_enable);
+
 static void bgx_sgmii_change_link_state(struct lmac *lmac)
 {
 	struct bgx *bgx = lmac->bgx;
@@ -612,6 +629,8 @@ static void bgx_poll_for_link(struct work_struct *work)
 		lmac->last_duplex = 1;
 	} else {
 		lmac->link_up = 0;
+		lmac->last_speed = SPEED_UNKNOWN;
+		lmac->last_duplex = DUPLEX_UNKNOWN;
 	}
 
 	if (lmac->last_link != lmac->link_up) {
@@ -654,8 +673,7 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
 	}
 
 	/* Enable lmac */
-	bgx_reg_modify(bgx, lmacid, BGX_CMRX_CFG,
-		       CMR_EN | CMR_PKT_RX_EN | CMR_PKT_TX_EN);
+	bgx_reg_modify(bgx, lmacid, BGX_CMRX_CFG, CMR_EN);
 
 	/* Restore default cfg, incase low level firmware changed it */
 	bgx_reg_write(bgx, lmacid, BGX_CMRX_RX_DMAC_CTL, 0x03);
@@ -695,8 +713,7 @@ static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid)
 	lmac = &bgx->lmac[lmacid];
 	if (lmac->check_link) {
 		/* Destroy work queue */
-		cancel_delayed_work(&lmac->dwork);
-		flush_workqueue(lmac->check_link);
+		cancel_delayed_work_sync(&lmac->dwork);
 		destroy_workqueue(lmac->check_link);
 	}
 
@@ -1009,6 +1026,9 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct bgx *bgx = NULL;
 	u8 lmac;
 
+	/* Load octeon mdio driver */
+	octeon_mdiobus_force_mod_depencency();
+
 	bgx = devm_kzalloc(dev, sizeof(*bgx), GFP_KERNEL);
 	if (!bgx)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index 07b7ec66c60d..149e179363a1 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -182,6 +182,8 @@ enum MCAST_MODE {
 #define BCAST_ACCEPT	1
 #define CAM_ACCEPT	1
 
+void octeon_mdiobus_force_mod_depencency(void);
+void bgx_lmac_rx_tx_enable(int node, int bgx_idx, int lmacid, bool enable);
 void bgx_add_dmac_addr(u64 dmac, int node, int bgx_idx, int lmac);
 unsigned bgx_get_map(int node);
 int bgx_get_lmac_count(int node, int bgx);
diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c
index ed41559bae77..b553409e04ad 100644
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -98,8 +98,7 @@ static int csr0 = 0x01A00000 | 0x4800;
 #elif defined(__mips__)
 static int csr0 = 0x00200000 | 0x4000;
 #else
-#warning Processor architecture undefined!
-static int csr0 = 0x00A00000 | 0x4800;
+static int csr0;
 #endif
 
 /* Operational parameters that usually are not changed. */
@@ -1982,6 +1981,12 @@ static int __init tulip_init (void)
 	pr_info("%s", version);
 #endif
 
+	if (!csr0) {
+		pr_warn("tulip: unknown CPU architecture, using default csr0\n");
+		/* default to 8 longword cache line alignment */
+		csr0 = 0x00A00000 | 0x4800;
+	}
+
 	/* copy module parms into globals */
 	tulip_rx_copybreak = rx_copybreak;
 	tulip_max_interrupt_work = max_interrupt_work;
diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c
index 9beb3d34d4ba..3c0e4d5c5fef 100644
--- a/drivers/net/ethernet/dec/tulip/winbond-840.c
+++ b/drivers/net/ethernet/dec/tulip/winbond-840.c
@@ -907,7 +907,7 @@ static void init_registers(struct net_device *dev)
 #elif defined(CONFIG_SPARC) || defined (CONFIG_PARISC) || defined(CONFIG_ARM)
 	i |= 0x4800;
 #else
-#warning Processor architecture undefined
+	dev_warn(&dev->dev, "unknown CPU architecture, using default csr0 setting\n");
 	i |= 0x4800;
 #endif
 	iowrite32(i, ioaddr + PCIBusCfg);
diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig
index ff76d4e9dc1b..bee32a9d9876 100644
--- a/drivers/net/ethernet/freescale/Kconfig
+++ b/drivers/net/ethernet/freescale/Kconfig
@@ -7,7 +7,8 @@ config NET_VENDOR_FREESCALE
 	default y
 	depends on FSL_SOC || QUICC_ENGINE || CPM1 || CPM2 || PPC_MPC512x || \
 		   M523x || M527x || M5272 || M528x || M520x || M532x || \
-		   ARCH_MXC || ARCH_MXS || (PPC_MPC52xx && PPC_BESTCOMM)
+		   ARCH_MXC || ARCH_MXS || (PPC_MPC52xx && PPC_BESTCOMM) || \
+		   ARCH_LAYERSCAPE
 	---help---
 	  If you have a network (Ethernet) card belonging to this class, say Y.
 
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 3e6b9b437497..7cf898455e60 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -647,9 +647,9 @@ static int gfar_parse_group(struct device_node *np,
 	if (model && strcasecmp(model, "FEC")) {
 		gfar_irq(grp, RX)->irq = irq_of_parse_and_map(np, 1);
 		gfar_irq(grp, ER)->irq = irq_of_parse_and_map(np, 2);
-		if (gfar_irq(grp, TX)->irq == NO_IRQ ||
-		    gfar_irq(grp, RX)->irq == NO_IRQ ||
-		    gfar_irq(grp, ER)->irq == NO_IRQ)
+		if (!gfar_irq(grp, TX)->irq ||
+		    !gfar_irq(grp, RX)->irq ||
+		    !gfar_irq(grp, ER)->irq)
 			return -EINVAL;
 	}
 
diff --git a/drivers/net/ethernet/freescale/gianfar_ptp.c b/drivers/net/ethernet/freescale/gianfar_ptp.c
index 664d0c261269..b40fba929d65 100644
--- a/drivers/net/ethernet/freescale/gianfar_ptp.c
+++ b/drivers/net/ethernet/freescale/gianfar_ptp.c
@@ -467,7 +467,7 @@ static int gianfar_ptp_probe(struct platform_device *dev)
 
 	etsects->irq = platform_get_irq(dev, 0);
 
-	if (etsects->irq == NO_IRQ) {
+	if (etsects->irq < 0) {
 		pr_err("irq not in device tree\n");
 		goto no_node;
 	}
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
index 639263d5e833..7781e80896a6 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
@@ -627,8 +627,10 @@ static netdev_tx_t fm10k_xmit_frame(struct sk_buff *skb, struct net_device *dev)
 
 		/* verify the skb head is not shared */
 		err = skb_cow_head(skb, 0);
-		if (err)
+		if (err) {
+			dev_kfree_skb(skb);
 			return NETDEV_TX_OK;
+		}
 
 		/* locate vlan header */
 		vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN);
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index e84c7f2634d3..ed622fa29dfa 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -36,7 +36,7 @@
 
 /* Registers */
 #define MVNETA_RXQ_CONFIG_REG(q)                (0x1400 + ((q) << 2))
-#define      MVNETA_RXQ_HW_BUF_ALLOC            BIT(1)
+#define      MVNETA_RXQ_HW_BUF_ALLOC            BIT(0)
 #define      MVNETA_RXQ_PKT_OFFSET_ALL_MASK     (0xf    << 8)
 #define      MVNETA_RXQ_PKT_OFFSET_MASK(offs)   ((offs) << 8)
 #define MVNETA_RXQ_THRESHOLD_REG(q)             (0x14c0 + ((q) << 2))
@@ -62,6 +62,7 @@
 #define MVNETA_WIN_SIZE(w)                      (0x2204 + ((w) << 3))
 #define MVNETA_WIN_REMAP(w)                     (0x2280 + ((w) << 2))
 #define MVNETA_BASE_ADDR_ENABLE                 0x2290
+#define MVNETA_ACCESS_PROTECT_ENABLE            0x2294
 #define MVNETA_PORT_CONFIG                      0x2400
 #define      MVNETA_UNI_PROMISC_MODE            BIT(0)
 #define      MVNETA_DEF_RXQ(q)                  ((q) << 1)
@@ -159,7 +160,7 @@
 
 #define MVNETA_INTR_ENABLE                       0x25b8
 #define      MVNETA_TXQ_INTR_ENABLE_ALL_MASK     0x0000ff00
-#define      MVNETA_RXQ_INTR_ENABLE_ALL_MASK     0xff000000  // note: neta says it's 0x000000FF
+#define      MVNETA_RXQ_INTR_ENABLE_ALL_MASK     0x000000ff
 
 #define MVNETA_RXQ_CMD                           0x2680
 #define      MVNETA_RXQ_DISABLE_SHIFT            8
@@ -242,6 +243,7 @@
 #define MVNETA_VLAN_TAG_LEN             4
 
 #define MVNETA_CPU_D_CACHE_LINE_SIZE    32
+#define MVNETA_TX_CSUM_DEF_SIZE		1600
 #define MVNETA_TX_CSUM_MAX_SIZE		9800
 #define MVNETA_ACC_MODE_EXT		1
 
@@ -1579,12 +1581,16 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
 		}
 
 		skb = build_skb(data, pp->frag_size > PAGE_SIZE ? 0 : pp->frag_size);
-		if (!skb)
-			goto err_drop_frame;
 
+		/* After refill old buffer has to be unmapped regardless
+		 * the skb is successfully built or not.
+		 */
 		dma_unmap_single(dev->dev.parent, phys_addr,
 				 MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE);
 
+		if (!skb)
+			goto err_drop_frame;
+
 		rcvd_pkts++;
 		rcvd_bytes += rx_bytes;
 
@@ -3191,6 +3197,7 @@ static void mvneta_conf_mbus_windows(struct mvneta_port *pp,
 	}
 
 	mvreg_write(pp, MVNETA_BASE_ADDR_ENABLE, win_enable);
+	mvreg_write(pp, MVNETA_ACCESS_PROTECT_ENABLE, win_protect);
 }
 
 /* Power up the port */
@@ -3250,6 +3257,7 @@ static int mvneta_probe(struct platform_device *pdev)
 	char hw_mac_addr[ETH_ALEN];
 	const char *mac_from;
 	const char *managed;
+	int tx_csum_limit;
 	int phy_mode;
 	int err;
 	int cpu;
@@ -3350,8 +3358,21 @@ static int mvneta_probe(struct platform_device *pdev)
 		}
 	}
 
-	if (of_device_is_compatible(dn, "marvell,armada-370-neta"))
-		pp->tx_csum_limit = 1600;
+	if (!of_property_read_u32(dn, "tx-csum-limit", &tx_csum_limit)) {
+		if (tx_csum_limit < 0 ||
+		    tx_csum_limit > MVNETA_TX_CSUM_MAX_SIZE) {
+			tx_csum_limit = MVNETA_TX_CSUM_DEF_SIZE;
+			dev_info(&pdev->dev,
+				 "Wrong TX csum limit in DT, set to %dB\n",
+				 MVNETA_TX_CSUM_DEF_SIZE);
+		}
+	} else if (of_device_is_compatible(dn, "marvell,armada-370-neta")) {
+		tx_csum_limit = MVNETA_TX_CSUM_DEF_SIZE;
+	} else {
+		tx_csum_limit = MVNETA_TX_CSUM_MAX_SIZE;
+	}
+
+	pp->tx_csum_limit = tx_csum_limit;
 
 	pp->tx_ring_size = MVNETA_MAX_TXD;
 	pp->rx_ring_size = MVNETA_MAX_RXD;
diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index b159ef8303cc..057665180f13 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -1326,7 +1326,7 @@ static int lpc_eth_drv_probe(struct platform_device *pdev)
 	/* Get platform resources */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	irq = platform_get_irq(pdev, 0);
-	if ((!res) || (irq < 0) || (irq >= NR_IRQS)) {
+	if (!res || irq < 0) {
 		dev_err(&pdev->dev, "error getting resources.\n");
 		ret = -ENXIO;
 		goto err_exit;
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index ee8d1ec61fab..ed5da4d47668 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1225,7 +1225,7 @@ static int ravb_open(struct net_device *ndev)
 	/* Device init */
 	error = ravb_dmac_init(ndev);
 	if (error)
-		goto out_free_irq;
+		goto out_free_irq2;
 	ravb_emac_init(ndev);
 
 	/* Initialise PTP Clock driver */
@@ -1243,9 +1243,11 @@ static int ravb_open(struct net_device *ndev)
 out_ptp_stop:
 	/* Stop PTP Clock driver */
 	ravb_ptp_stop(ndev);
+out_free_irq2:
+	if (priv->chip_id == RCAR_GEN3)
+		free_irq(priv->emac_irq, ndev);
 out_free_irq:
 	free_irq(ndev->irq, ndev);
-	free_irq(priv->emac_irq, ndev);
 out_napi_off:
 	napi_disable(&priv->napi[RAVB_NC]);
 	napi_disable(&priv->napi[RAVB_BE]);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
index 7f6f4a4fcc70..58c05acc2aab 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
@@ -299,16 +299,17 @@ static int sti_dwmac_parse_data(struct sti_dwmac *dwmac,
 	if (IS_PHY_IF_MODE_GBIT(dwmac->interface)) {
 		const char *rs;
 
+		dwmac->tx_retime_src = TX_RETIME_SRC_CLKGEN;
+
 		err = of_property_read_string(np, "st,tx-retime-src", &rs);
 		if (err < 0) {
 			dev_warn(dev, "Use internal clock source\n");
-			dwmac->tx_retime_src = TX_RETIME_SRC_CLKGEN;
-		} else if (!strcasecmp(rs, "clk_125")) {
-			dwmac->tx_retime_src = TX_RETIME_SRC_CLK_125;
-		} else if (!strcasecmp(rs, "txclk")) {
-			dwmac->tx_retime_src = TX_RETIME_SRC_TXCLK;
+		} else {
+			if (!strcasecmp(rs, "clk_125"))
+				dwmac->tx_retime_src = TX_RETIME_SRC_CLK_125;
+			else if (!strcasecmp(rs, "txclk"))
+				dwmac->tx_retime_src = TX_RETIME_SRC_TXCLK;
 		}
-
 		dwmac->speed = SPEED_1000;
 	}
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 64d8aa4e0cad..3c6549aee11d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -185,7 +185,7 @@ static void stmmac_clk_csr_set(struct stmmac_priv *priv)
 			priv->clk_csr = STMMAC_CSR_100_150M;
 		else if ((clk_rate >= CSR_F_150M) && (clk_rate < CSR_F_250M))
 			priv->clk_csr = STMMAC_CSR_150_250M;
-		else if ((clk_rate >= CSR_F_250M) && (clk_rate < CSR_F_300M))
+		else if ((clk_rate >= CSR_F_250M) && (clk_rate <= CSR_F_300M))
 			priv->clk_csr = STMMAC_CSR_250_300M;
 	}
 }
@@ -2232,6 +2232,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 
 			frame_len = priv->hw->desc->get_rx_frame_len(p, coe);
 
+			/*  check if frame_len fits the preallocated memory */
+			if (frame_len > priv->dma_buf_sz) {
+				priv->dev->stats.rx_length_errors++;
+				break;
+			}
+
 			/* ACS is set; GMAC core strips PAD/FCS for IEEE 802.3
 			 * Type frames (LLC/LLC-SNAP)
 			 */
@@ -3102,6 +3108,7 @@ int stmmac_resume(struct net_device *ndev)
 	init_dma_desc_rings(ndev, GFP_ATOMIC);
 	stmmac_hw_setup(ndev, false);
 	stmmac_init_tx_coalesce(priv);
+	stmmac_set_rx_mode(ndev);
 
 	napi_enable(&priv->napi);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index ebf6abc4853f..bba670c42e37 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -138,7 +138,6 @@ int stmmac_mdio_reset(struct mii_bus *bus)
 
 #ifdef CONFIG_OF
 	if (priv->device->of_node) {
-		int reset_gpio, active_low;
 
 		if (data->reset_gpio < 0) {
 			struct device_node *np = priv->device->of_node;
@@ -154,24 +153,23 @@ int stmmac_mdio_reset(struct mii_bus *bus)
 						"snps,reset-active-low");
 			of_property_read_u32_array(np,
 				"snps,reset-delays-us", data->delays, 3);
-		}
 
-		reset_gpio = data->reset_gpio;
-		active_low = data->active_low;
+			if (gpio_request(data->reset_gpio, "mdio-reset"))
+				return 0;
+		}
 
-		if (!gpio_request(reset_gpio, "mdio-reset")) {
-			gpio_direction_output(reset_gpio, active_low ? 1 : 0);
-			if (data->delays[0])
-				msleep(DIV_ROUND_UP(data->delays[0], 1000));
+		gpio_direction_output(data->reset_gpio,
+				      data->active_low ? 1 : 0);
+		if (data->delays[0])
+			msleep(DIV_ROUND_UP(data->delays[0], 1000));
 
-			gpio_set_value(reset_gpio, active_low ? 0 : 1);
-			if (data->delays[1])
-				msleep(DIV_ROUND_UP(data->delays[1], 1000));
+		gpio_set_value(data->reset_gpio, data->active_low ? 0 : 1);
+		if (data->delays[1])
+			msleep(DIV_ROUND_UP(data->delays[1], 1000));
 
-			gpio_set_value(reset_gpio, active_low ? 1 : 0);
-			if (data->delays[2])
-				msleep(DIV_ROUND_UP(data->delays[2], 1000));
-		}
+		gpio_set_value(data->reset_gpio, data->active_low ? 1 : 0);
+		if (data->delays[2])
+			msleep(DIV_ROUND_UP(data->delays[2], 1000));
 	}
 #endif
 
diff --git a/drivers/net/ethernet/ti/cpsw-common.c b/drivers/net/ethernet/ti/cpsw-common.c
index c08be62bceba..1562ab4151e1 100644
--- a/drivers/net/ethernet/ti/cpsw-common.c
+++ b/drivers/net/ethernet/ti/cpsw-common.c
@@ -78,6 +78,9 @@ static int cpsw_am33xx_cm_get_macid(struct device *dev, u16 offset, int slave,
 
 int ti_cm_get_macid(struct device *dev, int slave, u8 *mac_addr)
 {
+	if (of_machine_is_compatible("ti,dm8148"))
+		return cpsw_am33xx_cm_get_macid(dev, 0x630, slave, mac_addr);
+
 	if (of_machine_is_compatible("ti,am33xx"))
 		return cpsw_am33xx_cm_get_macid(dev, 0x630, slave, mac_addr);
 
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 54036ae0a388..0fc521941c71 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -498,7 +498,7 @@ static void macvtap_sock_write_space(struct sock *sk)
 	wait_queue_head_t *wqueue;
 
 	if (!sock_writeable(sk) ||
-	    !test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags))
+	    !test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags))
 		return;
 
 	wqueue = sk_sleep(sk);
@@ -585,7 +585,7 @@ static unsigned int macvtap_poll(struct file *file, poll_table * wait)
 		mask |= POLLIN | POLLRDNORM;
 
 	if (sock_writeable(&q->sk) ||
-	    (!test_and_set_bit(SOCK_ASYNC_NOSPACE, &q->sock.flags) &&
+	    (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &q->sock.flags) &&
 	     sock_writeable(&q->sk)))
 		mask |= POLLOUT | POLLWRNORM;
 
diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 07a6119121c3..3ce5d9514623 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -614,7 +614,7 @@ static struct mdio_device_id __maybe_unused broadcom_tbl[] = {
 	{ PHY_ID_BCM5461, 0xfffffff0 },
 	{ PHY_ID_BCM54616S, 0xfffffff0 },
 	{ PHY_ID_BCM5464, 0xfffffff0 },
-	{ PHY_ID_BCM5482, 0xfffffff0 },
+	{ PHY_ID_BCM5481, 0xfffffff0 },
 	{ PHY_ID_BCM5482, 0xfffffff0 },
 	{ PHY_ID_BCM50610, 0xfffffff0 },
 	{ PHY_ID_BCM50610M, 0xfffffff0 },
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 48ce6ef400fe..47cd306dbb3c 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -448,7 +448,8 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
 		mdiobus_write(phydev->bus, mii_data->phy_id,
 			      mii_data->reg_num, val);
 
-		if (mii_data->reg_num == MII_BMCR &&
+		if (mii_data->phy_id == phydev->addr &&
+		    mii_data->reg_num == MII_BMCR &&
 		    val & BMCR_RESET)
 			return phy_init_hw(phydev);
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index b1878faea397..f0db770e8b2f 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1040,7 +1040,7 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
 		mask |= POLLIN | POLLRDNORM;
 
 	if (sock_writeable(sk) ||
-	    (!test_and_set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
+	    (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
 	     sock_writeable(sk)))
 		mask |= POLLOUT | POLLWRNORM;
 
@@ -1488,7 +1488,7 @@ static void tun_sock_write_space(struct sock *sk)
 	if (!sock_writeable(sk))
 		return;
 
-	if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags))
+	if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags))
 		return;
 
 	wqueue = sk_sleep(sk);
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index a187f08113ec..3b1ba8237768 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -691,7 +691,6 @@ static void cdc_ncm_free(struct cdc_ncm_ctx *ctx)
 
 int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting, int drvflags)
 {
-	const struct usb_cdc_union_desc *union_desc = NULL;
 	struct cdc_ncm_ctx *ctx;
 	struct usb_driver *driver;
 	u8 *buf;
@@ -725,15 +724,16 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 	/* parse through descriptors associated with control interface */
 	cdc_parse_cdc_header(&hdr, intf, buf, len);
 
-	ctx->data = usb_ifnum_to_if(dev->udev,
-				    hdr.usb_cdc_union_desc->bSlaveInterface0);
+	if (hdr.usb_cdc_union_desc)
+		ctx->data = usb_ifnum_to_if(dev->udev,
+					    hdr.usb_cdc_union_desc->bSlaveInterface0);
 	ctx->ether_desc = hdr.usb_cdc_ether_desc;
 	ctx->func_desc = hdr.usb_cdc_ncm_desc;
 	ctx->mbim_desc = hdr.usb_cdc_mbim_desc;
 	ctx->mbim_extended_desc = hdr.usb_cdc_mbim_extended_desc;
 
 	/* some buggy devices have an IAD but no CDC Union */
-	if (!union_desc && intf->intf_assoc && intf->intf_assoc->bInterfaceCount == 2) {
+	if (!hdr.usb_cdc_union_desc && intf->intf_assoc && intf->intf_assoc->bInterfaceCount == 2) {
 		ctx->data = usb_ifnum_to_if(dev->udev, intf->cur_altsetting->desc.bInterfaceNumber + 1);
 		dev_dbg(&intf->dev, "CDC Union missing - got slave from IAD\n");
 	}
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 34799eaace41..9a5be8b85186 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -725,6 +725,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1201, 2)},	/* Telit LE920 */
+	{QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)},	/* XS Stick W100-2 from 4G Systems */
 	{QMI_FIXED_INTF(0x0b3c, 0xc000, 4)},	/* Olivetti Olicard 100 */
 	{QMI_FIXED_INTF(0x0b3c, 0xc001, 4)},	/* Olivetti Olicard 120 */
 	{QMI_FIXED_INTF(0x0b3c, 0xc002, 4)},	/* Olivetti Olicard 140 */
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 899ea4288197..417903715437 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -587,6 +587,12 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx,
 						&adapter->pdev->dev,
 						rbi->skb->data, rbi->len,
 						PCI_DMA_FROMDEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      rbi->dma_addr)) {
+					dev_kfree_skb_any(rbi->skb);
+					rq->stats.rx_buf_alloc_failure++;
+					break;
+				}
 			} else {
 				/* rx buffer skipped by the device */
 			}
@@ -605,13 +611,18 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx,
 						&adapter->pdev->dev,
 						rbi->page, 0, PAGE_SIZE,
 						PCI_DMA_FROMDEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      rbi->dma_addr)) {
+					put_page(rbi->page);
+					rq->stats.rx_buf_alloc_failure++;
+					break;
+				}
 			} else {
 				/* rx buffers skipped by the device */
 			}
 			val = VMXNET3_RXD_BTYPE_BODY << VMXNET3_RXD_BTYPE_SHIFT;
 		}
 
-		BUG_ON(rbi->dma_addr == 0);
 		gd->rxd.addr = cpu_to_le64(rbi->dma_addr);
 		gd->dword[2] = cpu_to_le32((!ring->gen << VMXNET3_RXD_GEN_SHIFT)
 					   | val | rbi->len);
@@ -655,7 +666,7 @@ vmxnet3_append_frag(struct sk_buff *skb, struct Vmxnet3_RxCompDesc *rcd,
 }
 
 
-static void
+static int
 vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
 		struct vmxnet3_tx_queue *tq, struct pci_dev *pdev,
 		struct vmxnet3_adapter *adapter)
@@ -715,6 +726,8 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
 		tbi->dma_addr = dma_map_single(&adapter->pdev->dev,
 				skb->data + buf_offset, buf_size,
 				PCI_DMA_TODEVICE);
+		if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr))
+			return -EFAULT;
 
 		tbi->len = buf_size;
 
@@ -755,6 +768,8 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
 			tbi->dma_addr = skb_frag_dma_map(&adapter->pdev->dev, frag,
 							 buf_offset, buf_size,
 							 DMA_TO_DEVICE);
+			if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr))
+				return -EFAULT;
 
 			tbi->len = buf_size;
 
@@ -782,6 +797,8 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
 	/* set the last buf_info for the pkt */
 	tbi->skb = skb;
 	tbi->sop_idx = ctx->sop_txd - tq->tx_ring.base;
+
+	return 0;
 }
 
 
@@ -1020,7 +1037,8 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 	}
 
 	/* fill tx descs related to addr & len */
-	vmxnet3_map_pkt(skb, &ctx, tq, adapter->pdev, adapter);
+	if (vmxnet3_map_pkt(skb, &ctx, tq, adapter->pdev, adapter))
+		goto unlock_drop_pkt;
 
 	/* setup the EOP desc */
 	ctx.eop_txd->dword[3] = cpu_to_le32(VMXNET3_TXD_CQ | VMXNET3_TXD_EOP);
@@ -1231,6 +1249,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 		struct vmxnet3_rx_buf_info *rbi;
 		struct sk_buff *skb, *new_skb = NULL;
 		struct page *new_page = NULL;
+		dma_addr_t new_dma_addr;
 		int num_to_alloc;
 		struct Vmxnet3_RxDesc *rxd;
 		u32 idx, ring_idx;
@@ -1287,6 +1306,21 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 				skip_page_frags = true;
 				goto rcd_done;
 			}
+			new_dma_addr = dma_map_single(&adapter->pdev->dev,
+						      new_skb->data, rbi->len,
+						      PCI_DMA_FROMDEVICE);
+			if (dma_mapping_error(&adapter->pdev->dev,
+					      new_dma_addr)) {
+				dev_kfree_skb(new_skb);
+				/* Skb allocation failed, do not handover this
+				 * skb to stack. Reuse it. Drop the existing pkt
+				 */
+				rq->stats.rx_buf_alloc_failure++;
+				ctx->skb = NULL;
+				rq->stats.drop_total++;
+				skip_page_frags = true;
+				goto rcd_done;
+			}
 
 			dma_unmap_single(&adapter->pdev->dev, rbi->dma_addr,
 					 rbi->len,
@@ -1303,9 +1337,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 
 			/* Immediate refill */
 			rbi->skb = new_skb;
-			rbi->dma_addr = dma_map_single(&adapter->pdev->dev,
-						       rbi->skb->data, rbi->len,
-						       PCI_DMA_FROMDEVICE);
+			rbi->dma_addr = new_dma_addr;
 			rxd->addr = cpu_to_le64(rbi->dma_addr);
 			rxd->len = rbi->len;
 			if (adapter->version == 2 &&
@@ -1348,6 +1380,19 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 					skip_page_frags = true;
 					goto rcd_done;
 				}
+				new_dma_addr = dma_map_page(&adapter->pdev->dev
+							, rbi->page,
+							0, PAGE_SIZE,
+							PCI_DMA_FROMDEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      new_dma_addr)) {
+					put_page(new_page);
+					rq->stats.rx_buf_alloc_failure++;
+					dev_kfree_skb(ctx->skb);
+					ctx->skb = NULL;
+					skip_page_frags = true;
+					goto rcd_done;
+				}
 
 				dma_unmap_page(&adapter->pdev->dev,
 					       rbi->dma_addr, rbi->len,
@@ -1357,10 +1402,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 
 				/* Immediate refill */
 				rbi->page = new_page;
-				rbi->dma_addr = dma_map_page(&adapter->pdev->dev
-							, rbi->page,
-							0, PAGE_SIZE,
-							PCI_DMA_FROMDEVICE);
+				rbi->dma_addr = new_dma_addr;
 				rxd->addr = cpu_to_le64(rbi->dma_addr);
 				rxd->len = rbi->len;
 			}
@@ -2167,7 +2209,8 @@ vmxnet3_set_mc(struct net_device *netdev)
 							PCI_DMA_TODEVICE);
 			}
 
-			if (new_table_pa) {
+			if (!dma_mapping_error(&adapter->pdev->dev,
+					       new_table_pa)) {
 				new_mode |= VMXNET3_RXM_MCAST;
 				rxConf->mfTablePA = cpu_to_le64(new_table_pa);
 			} else {
@@ -3075,6 +3118,11 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 	adapter->adapter_pa = dma_map_single(&adapter->pdev->dev, adapter,
 					     sizeof(struct vmxnet3_adapter),
 					     PCI_DMA_TODEVICE);
+	if (dma_mapping_error(&adapter->pdev->dev, adapter->adapter_pa)) {
+		dev_err(&pdev->dev, "Failed to map dma\n");
+		err = -EFAULT;
+		goto err_dma_map;
+	}
 	adapter->shared = dma_alloc_coherent(
 				&adapter->pdev->dev,
 				sizeof(struct Vmxnet3_DriverShared),
@@ -3233,6 +3281,7 @@ err_alloc_queue_desc:
 err_alloc_shared:
 	dma_unmap_single(&adapter->pdev->dev, adapter->adapter_pa,
 			 sizeof(struct vmxnet3_adapter), PCI_DMA_TODEVICE);
+err_dma_map:
 	free_netdev(netdev);
 	return err;
 }
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 92fa3e1ea65c..4f9748457f5a 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -907,7 +907,6 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev,
 		       struct nlattr *tb[], struct nlattr *data[])
 {
 	struct net_vrf *vrf = netdev_priv(dev);
-	int err;
 
 	if (!data || !data[IFLA_VRF_TABLE])
 		return -EINVAL;
@@ -916,15 +915,7 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev,
 
 	dev->priv_flags |= IFF_L3MDEV_MASTER;
 
-	err = register_netdevice(dev);
-	if (err < 0)
-		goto out_fail;
-
-	return 0;
-
-out_fail:
-	free_netdev(dev);
-	return err;
+	return register_netdevice(dev);
 }
 
 static size_t vrf_nl_getsize(const struct net_device *dev)
diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c
index e92aaf615901..89541cc90e87 100644
--- a/drivers/net/wan/hdlc_fr.c
+++ b/drivers/net/wan/hdlc_fr.c
@@ -1075,11 +1075,10 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type)
 
 	used = pvc_is_used(pvc);
 
-	if (type == ARPHRD_ETHER) {
+	if (type == ARPHRD_ETHER)
 		dev = alloc_netdev(0, "pvceth%d", NET_NAME_UNKNOWN,
 				   ether_setup);
-		dev->priv_flags &= ~IFF_TX_SKB_SHARING;
-	} else
+	else
 		dev = alloc_netdev(0, "pvc%d", NET_NAME_UNKNOWN, pvc_setup);
 
 	if (!dev) {
@@ -1088,9 +1087,10 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type)
 		return -ENOBUFS;
 	}
 
-	if (type == ARPHRD_ETHER)
+	if (type == ARPHRD_ETHER) {
+		dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 		eth_hw_addr_random(dev);
-	else {
+	} else {
 		*(__be16*)dev->dev_addr = htons(dlci);
 		dlci_to_q922(dev->broadcast, dlci);
 	}
diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c
index 5c47b011a9d7..cd39025d2abf 100644
--- a/drivers/net/wan/x25_asy.c
+++ b/drivers/net/wan/x25_asy.c
@@ -549,16 +549,12 @@ static void x25_asy_receive_buf(struct tty_struct *tty,
 
 static int x25_asy_open_tty(struct tty_struct *tty)
 {
-	struct x25_asy *sl = tty->disc_data;
+	struct x25_asy *sl;
 	int err;
 
 	if (tty->ops->write == NULL)
 		return -EOPNOTSUPP;
 
-	/* First make sure we're not already connected. */
-	if (sl && sl->magic == X25_ASY_MAGIC)
-		return -EEXIST;
-
 	/* OK.  Find a free X.25 channel to use. */
 	sl = x25_asy_alloc();
 	if (sl == NULL)
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index aa9bd92ac4ed..0947cc271e69 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -51,6 +51,7 @@ MODULE_PARM_DESC(rawmode, "Use raw 802.11 frame datapath");
 static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 	{
 		.id = QCA988X_HW_2_0_VERSION,
+		.dev_id = QCA988X_2_0_DEVICE_ID,
 		.name = "qca988x hw2.0",
 		.patch_load_addr = QCA988X_HW_2_0_PATCH_LOAD_ADDR,
 		.uart_pin = 7,
@@ -69,6 +70,25 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 	},
 	{
 		.id = QCA6174_HW_2_1_VERSION,
+		.dev_id = QCA6164_2_1_DEVICE_ID,
+		.name = "qca6164 hw2.1",
+		.patch_load_addr = QCA6174_HW_2_1_PATCH_LOAD_ADDR,
+		.uart_pin = 6,
+		.otp_exe_param = 0,
+		.channel_counters_freq_hz = 88000,
+		.max_probe_resp_desc_thres = 0,
+		.fw = {
+			.dir = QCA6174_HW_2_1_FW_DIR,
+			.fw = QCA6174_HW_2_1_FW_FILE,
+			.otp = QCA6174_HW_2_1_OTP_FILE,
+			.board = QCA6174_HW_2_1_BOARD_DATA_FILE,
+			.board_size = QCA6174_BOARD_DATA_SZ,
+			.board_ext_size = QCA6174_BOARD_EXT_DATA_SZ,
+		},
+	},
+	{
+		.id = QCA6174_HW_2_1_VERSION,
+		.dev_id = QCA6174_2_1_DEVICE_ID,
 		.name = "qca6174 hw2.1",
 		.patch_load_addr = QCA6174_HW_2_1_PATCH_LOAD_ADDR,
 		.uart_pin = 6,
@@ -86,6 +106,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 	},
 	{
 		.id = QCA6174_HW_3_0_VERSION,
+		.dev_id = QCA6174_2_1_DEVICE_ID,
 		.name = "qca6174 hw3.0",
 		.patch_load_addr = QCA6174_HW_3_0_PATCH_LOAD_ADDR,
 		.uart_pin = 6,
@@ -103,6 +124,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 	},
 	{
 		.id = QCA6174_HW_3_2_VERSION,
+		.dev_id = QCA6174_2_1_DEVICE_ID,
 		.name = "qca6174 hw3.2",
 		.patch_load_addr = QCA6174_HW_3_0_PATCH_LOAD_ADDR,
 		.uart_pin = 6,
@@ -121,6 +143,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 	},
 	{
 		.id = QCA99X0_HW_2_0_DEV_VERSION,
+		.dev_id = QCA99X0_2_0_DEVICE_ID,
 		.name = "qca99x0 hw2.0",
 		.patch_load_addr = QCA99X0_HW_2_0_PATCH_LOAD_ADDR,
 		.uart_pin = 7,
@@ -139,10 +162,31 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 	},
 	{
 		.id = QCA9377_HW_1_0_DEV_VERSION,
+		.dev_id = QCA9377_1_0_DEVICE_ID,
 		.name = "qca9377 hw1.0",
 		.patch_load_addr = QCA9377_HW_1_0_PATCH_LOAD_ADDR,
-		.uart_pin = 7,
+		.uart_pin = 6,
 		.otp_exe_param = 0,
+		.channel_counters_freq_hz = 88000,
+		.max_probe_resp_desc_thres = 0,
+		.fw = {
+			.dir = QCA9377_HW_1_0_FW_DIR,
+			.fw = QCA9377_HW_1_0_FW_FILE,
+			.otp = QCA9377_HW_1_0_OTP_FILE,
+			.board = QCA9377_HW_1_0_BOARD_DATA_FILE,
+			.board_size = QCA9377_BOARD_DATA_SZ,
+			.board_ext_size = QCA9377_BOARD_EXT_DATA_SZ,
+		},
+	},
+	{
+		.id = QCA9377_HW_1_1_DEV_VERSION,
+		.dev_id = QCA9377_1_0_DEVICE_ID,
+		.name = "qca9377 hw1.1",
+		.patch_load_addr = QCA9377_HW_1_0_PATCH_LOAD_ADDR,
+		.uart_pin = 6,
+		.otp_exe_param = 0,
+		.channel_counters_freq_hz = 88000,
+		.max_probe_resp_desc_thres = 0,
 		.fw = {
 			.dir = QCA9377_HW_1_0_FW_DIR,
 			.fw = QCA9377_HW_1_0_FW_FILE,
@@ -1263,7 +1307,8 @@ static int ath10k_init_hw_params(struct ath10k *ar)
 	for (i = 0; i < ARRAY_SIZE(ath10k_hw_params_list); i++) {
 		hw_params = &ath10k_hw_params_list[i];
 
-		if (hw_params->id == ar->target_version)
+		if (hw_params->id == ar->target_version &&
+		    hw_params->dev_id == ar->dev_id)
 			break;
 	}
 
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 018c64f4fd25..858d75f49a9f 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -636,6 +636,7 @@ struct ath10k {
 
 	struct ath10k_hw_params {
 		u32 id;
+		u16 dev_id;
 		const char *name;
 		u32 patch_load_addr;
 		int uart_pin;
diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h
index 39966a05c1cc..713c2bcea178 100644
--- a/drivers/net/wireless/ath/ath10k/hw.h
+++ b/drivers/net/wireless/ath/ath10k/hw.h
@@ -22,6 +22,12 @@
 
 #define ATH10K_FW_DIR			"ath10k"
 
+#define QCA988X_2_0_DEVICE_ID   (0x003c)
+#define QCA6164_2_1_DEVICE_ID   (0x0041)
+#define QCA6174_2_1_DEVICE_ID   (0x003e)
+#define QCA99X0_2_0_DEVICE_ID   (0x0040)
+#define QCA9377_1_0_DEVICE_ID   (0x0042)
+
 /* QCA988X 1.0 definitions (unsupported) */
 #define QCA988X_HW_1_0_CHIP_ID_REV	0x0
 
@@ -42,6 +48,10 @@
 #define QCA6174_HW_3_0_VERSION		0x05020000
 #define QCA6174_HW_3_2_VERSION		0x05030000
 
+/* QCA9377 target BMI version signatures */
+#define QCA9377_HW_1_0_DEV_VERSION	0x05020000
+#define QCA9377_HW_1_1_DEV_VERSION	0x05020001
+
 enum qca6174_pci_rev {
 	QCA6174_PCI_REV_1_1 = 0x11,
 	QCA6174_PCI_REV_1_3 = 0x13,
@@ -60,6 +70,11 @@ enum qca6174_chip_id_rev {
 	QCA6174_HW_3_2_CHIP_ID_REV = 10,
 };
 
+enum qca9377_chip_id_rev {
+	QCA9377_HW_1_0_CHIP_ID_REV = 0x0,
+	QCA9377_HW_1_1_CHIP_ID_REV = 0x1,
+};
+
 #define QCA6174_HW_2_1_FW_DIR		"ath10k/QCA6174/hw2.1"
 #define QCA6174_HW_2_1_FW_FILE		"firmware.bin"
 #define QCA6174_HW_2_1_OTP_FILE		"otp.bin"
@@ -85,8 +100,6 @@ enum qca6174_chip_id_rev {
 #define QCA99X0_HW_2_0_PATCH_LOAD_ADDR	0x1234
 
 /* QCA9377 1.0 definitions */
-#define QCA9377_HW_1_0_DEV_VERSION     0x05020001
-#define QCA9377_HW_1_0_CHIP_ID_REV     0x1
 #define QCA9377_HW_1_0_FW_DIR          ATH10K_FW_DIR "/QCA9377/hw1.0"
 #define QCA9377_HW_1_0_FW_FILE         "firmware.bin"
 #define QCA9377_HW_1_0_OTP_FILE        "otp.bin"
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index a7411fe90cc4..95a55405ebf0 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -4225,7 +4225,7 @@ static int ath10k_config(struct ieee80211_hw *hw, u32 changed)
 
 static u32 get_nss_from_chainmask(u16 chain_mask)
 {
-	if ((chain_mask & 0x15) == 0x15)
+	if ((chain_mask & 0xf) == 0xf)
 		return 4;
 	else if ((chain_mask & 0x7) == 0x7)
 		return 3;
diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c
index 3fca200b986c..930785a724e1 100644
--- a/drivers/net/wireless/ath/ath10k/pci.c
+++ b/drivers/net/wireless/ath/ath10k/pci.c
@@ -57,12 +57,6 @@ MODULE_PARM_DESC(reset_mode, "0: auto, 1: warm only (default: 0)");
 #define ATH10K_PCI_TARGET_WAIT 3000
 #define ATH10K_PCI_NUM_WARM_RESET_ATTEMPTS 3
 
-#define QCA988X_2_0_DEVICE_ID	(0x003c)
-#define QCA6164_2_1_DEVICE_ID	(0x0041)
-#define QCA6174_2_1_DEVICE_ID	(0x003e)
-#define QCA99X0_2_0_DEVICE_ID	(0x0040)
-#define QCA9377_1_0_DEVICE_ID	(0x0042)
-
 static const struct pci_device_id ath10k_pci_id_table[] = {
 	{ PCI_VDEVICE(ATHEROS, QCA988X_2_0_DEVICE_ID) }, /* PCI-E QCA988X V2 */
 	{ PCI_VDEVICE(ATHEROS, QCA6164_2_1_DEVICE_ID) }, /* PCI-E QCA6164 V2.1 */
@@ -92,7 +86,9 @@ static const struct ath10k_pci_supp_chip ath10k_pci_supp_chips[] = {
 	{ QCA6174_2_1_DEVICE_ID, QCA6174_HW_3_2_CHIP_ID_REV },
 
 	{ QCA99X0_2_0_DEVICE_ID, QCA99X0_HW_2_0_CHIP_ID_REV },
+
 	{ QCA9377_1_0_DEVICE_ID, QCA9377_HW_1_0_CHIP_ID_REV },
+	{ QCA9377_1_0_DEVICE_ID, QCA9377_HW_1_1_CHIP_ID_REV },
 };
 
 static void ath10k_pci_buffer_cleanup(struct ath10k *ar);
@@ -111,8 +107,9 @@ static void ath10k_pci_htc_tx_cb(struct ath10k_ce_pipe *ce_state);
 static void ath10k_pci_htc_rx_cb(struct ath10k_ce_pipe *ce_state);
 static void ath10k_pci_htt_tx_cb(struct ath10k_ce_pipe *ce_state);
 static void ath10k_pci_htt_rx_cb(struct ath10k_ce_pipe *ce_state);
+static void ath10k_pci_htt_htc_rx_cb(struct ath10k_ce_pipe *ce_state);
 
-static const struct ce_attr host_ce_config_wlan[] = {
+static struct ce_attr host_ce_config_wlan[] = {
 	/* CE0: host->target HTC control and raw streams */
 	{
 		.flags = CE_ATTR_FLAGS,
@@ -128,7 +125,7 @@ static const struct ce_attr host_ce_config_wlan[] = {
 		.src_nentries = 0,
 		.src_sz_max = 2048,
 		.dest_nentries = 512,
-		.recv_cb = ath10k_pci_htc_rx_cb,
+		.recv_cb = ath10k_pci_htt_htc_rx_cb,
 	},
 
 	/* CE2: target->host WMI */
@@ -217,7 +214,7 @@ static const struct ce_attr host_ce_config_wlan[] = {
 };
 
 /* Target firmware's Copy Engine configuration. */
-static const struct ce_pipe_config target_ce_config_wlan[] = {
+static struct ce_pipe_config target_ce_config_wlan[] = {
 	/* CE0: host->target HTC control and raw streams */
 	{
 		.pipenum = __cpu_to_le32(0),
@@ -330,7 +327,7 @@ static const struct ce_pipe_config target_ce_config_wlan[] = {
  * This table is derived from the CE_PCI TABLE, above.
  * It is passed to the Target at startup for use by firmware.
  */
-static const struct service_to_pipe target_service_to_ce_map_wlan[] = {
+static struct service_to_pipe target_service_to_ce_map_wlan[] = {
 	{
 		__cpu_to_le32(ATH10K_HTC_SVC_ID_WMI_DATA_VO),
 		__cpu_to_le32(PIPEDIR_OUT),	/* out = UL = host -> target */
@@ -1208,6 +1205,16 @@ static void ath10k_pci_htc_rx_cb(struct ath10k_ce_pipe *ce_state)
 	ath10k_pci_process_rx_cb(ce_state, ath10k_htc_rx_completion_handler);
 }
 
+static void ath10k_pci_htt_htc_rx_cb(struct ath10k_ce_pipe *ce_state)
+{
+	/* CE4 polling needs to be done whenever CE pipe which transports
+	 * HTT Rx (target->host) is processed.
+	 */
+	ath10k_ce_per_engine_service(ce_state->ar, 4);
+
+	ath10k_pci_process_rx_cb(ce_state, ath10k_htc_rx_completion_handler);
+}
+
 /* Called by lower (CE) layer when a send to HTT Target completes. */
 static void ath10k_pci_htt_tx_cb(struct ath10k_ce_pipe *ce_state)
 {
@@ -2027,6 +2034,29 @@ static int ath10k_pci_init_config(struct ath10k *ar)
 	return 0;
 }
 
+static void ath10k_pci_override_ce_config(struct ath10k *ar)
+{
+	struct ce_attr *attr;
+	struct ce_pipe_config *config;
+
+	/* For QCA6174 we're overriding the Copy Engine 5 configuration,
+	 * since it is currently used for other feature.
+	 */
+
+	/* Override Host's Copy Engine 5 configuration */
+	attr = &host_ce_config_wlan[5];
+	attr->src_sz_max = 0;
+	attr->dest_nentries = 0;
+
+	/* Override Target firmware's Copy Engine configuration */
+	config = &target_ce_config_wlan[5];
+	config->pipedir = __cpu_to_le32(PIPEDIR_OUT);
+	config->nbytes_max = __cpu_to_le32(2048);
+
+	/* Map from service/endpoint to Copy Engine */
+	target_service_to_ce_map_wlan[15].pipenum = __cpu_to_le32(1);
+}
+
 static int ath10k_pci_alloc_pipes(struct ath10k *ar)
 {
 	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
@@ -3020,6 +3050,9 @@ static int ath10k_pci_probe(struct pci_dev *pdev,
 		goto err_core_destroy;
 	}
 
+	if (QCA_REV_6174(ar))
+		ath10k_pci_override_ce_config(ar);
+
 	ret = ath10k_pci_alloc_pipes(ar);
 	if (ret) {
 		ath10k_err(ar, "failed to allocate copy engine pipes: %d\n",
diff --git a/drivers/net/wireless/iwlwifi/iwl-7000.c b/drivers/net/wireless/iwlwifi/iwl-7000.c
index 1a73c7a1da77..bf88ec3a65fa 100644
--- a/drivers/net/wireless/iwlwifi/iwl-7000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-7000.c
@@ -69,7 +69,7 @@
 #include "iwl-agn-hw.h"
 
 /* Highest firmware API version supported */
-#define IWL7260_UCODE_API_MAX	17
+#define IWL7260_UCODE_API_MAX	19
 
 /* Oldest version we won't warn about */
 #define IWL7260_UCODE_API_OK	13
diff --git a/drivers/net/wireless/iwlwifi/iwl-8000.c b/drivers/net/wireless/iwlwifi/iwl-8000.c
index 0116e5a4c393..9bcc0bf937d8 100644
--- a/drivers/net/wireless/iwlwifi/iwl-8000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-8000.c
@@ -69,7 +69,7 @@
 #include "iwl-agn-hw.h"
 
 /* Highest firmware API version supported */
-#define IWL8000_UCODE_API_MAX	17
+#define IWL8000_UCODE_API_MAX	19
 
 /* Oldest version we won't warn about */
 #define IWL8000_UCODE_API_OK	13
diff --git a/drivers/net/wireless/iwlwifi/mvm/d3.c b/drivers/net/wireless/iwlwifi/mvm/d3.c
index 85ae902df7c0..29ae58ebf223 100644
--- a/drivers/net/wireless/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/iwlwifi/mvm/d3.c
@@ -309,9 +309,9 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw,
 	 * to transmit packets to the AP, i.e. the PTK.
 	 */
 	if (key->flags & IEEE80211_KEY_FLAG_PAIRWISE) {
-		key->hw_key_idx = 0;
 		mvm->ptk_ivlen = key->iv_len;
 		mvm->ptk_icvlen = key->icv_len;
+		ret = iwl_mvm_set_sta_key(mvm, vif, sta, key, 0);
 	} else {
 		/*
 		 * firmware only supports TSC/RSC for a single key,
@@ -319,12 +319,11 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw,
 		 * with new ones -- this relies on mac80211 doing
 		 * list_add_tail().
 		 */
-		key->hw_key_idx = 1;
 		mvm->gtk_ivlen = key->iv_len;
 		mvm->gtk_icvlen = key->icv_len;
+		ret = iwl_mvm_set_sta_key(mvm, vif, sta, key, 1);
 	}
 
-	ret = iwl_mvm_set_sta_key(mvm, vif, sta, key, true);
 	data->error = ret != 0;
 out_unlock:
 	mutex_unlock(&mvm->mutex);
@@ -772,9 +771,6 @@ static int iwl_mvm_switch_to_d3(struct iwl_mvm *mvm)
 	 */
 	set_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status);
 
-	/* We reprogram keys and shouldn't allocate new key indices */
-	memset(mvm->fw_key_table, 0, sizeof(mvm->fw_key_table));
-
 	mvm->ptk_ivlen = 0;
 	mvm->ptk_icvlen = 0;
 	mvm->ptk_ivlen = 0;
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
index 1fb684693040..e88afac51c5d 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
@@ -2941,6 +2941,7 @@ static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw,
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 	int ret;
+	u8 key_offset;
 
 	if (iwlwifi_mod_params.sw_crypto) {
 		IWL_DEBUG_MAC80211(mvm, "leave - hwcrypto disabled\n");
@@ -3006,10 +3007,14 @@ static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw,
 			break;
 		}
 
+		/* in HW restart reuse the index, otherwise request a new one */
+		if (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status))
+			key_offset = key->hw_key_idx;
+		else
+			key_offset = STA_KEY_IDX_INVALID;
+
 		IWL_DEBUG_MAC80211(mvm, "set hwcrypto key\n");
-		ret = iwl_mvm_set_sta_key(mvm, vif, sta, key,
-					  test_bit(IWL_MVM_STATUS_IN_HW_RESTART,
-						   &mvm->status));
+		ret = iwl_mvm_set_sta_key(mvm, vif, sta, key, key_offset);
 		if (ret) {
 			IWL_WARN(mvm, "set key failed\n");
 			/*
diff --git a/drivers/net/wireless/iwlwifi/mvm/sta.c b/drivers/net/wireless/iwlwifi/mvm/sta.c
index 300a249486e4..354acbde088e 100644
--- a/drivers/net/wireless/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/iwlwifi/mvm/sta.c
@@ -1201,7 +1201,8 @@ static int iwl_mvm_set_fw_key_idx(struct iwl_mvm *mvm)
 	return max_offs;
 }
 
-static u8 iwl_mvm_get_key_sta_id(struct ieee80211_vif *vif,
+static u8 iwl_mvm_get_key_sta_id(struct iwl_mvm *mvm,
+				 struct ieee80211_vif *vif,
 				 struct ieee80211_sta *sta)
 {
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
@@ -1218,8 +1219,21 @@ static u8 iwl_mvm_get_key_sta_id(struct ieee80211_vif *vif,
 	 * station ID, then use AP's station ID.
 	 */
 	if (vif->type == NL80211_IFTYPE_STATION &&
-	    mvmvif->ap_sta_id != IWL_MVM_STATION_COUNT)
-		return mvmvif->ap_sta_id;
+	    mvmvif->ap_sta_id != IWL_MVM_STATION_COUNT) {
+		u8 sta_id = mvmvif->ap_sta_id;
+
+		sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[sta_id],
+						lockdep_is_held(&mvm->mutex));
+		/*
+		 * It is possible that the 'sta' parameter is NULL,
+		 * for example when a GTK is removed - the sta_id will then
+		 * be the AP ID, and no station was passed by mac80211.
+		 */
+		if (IS_ERR_OR_NULL(sta))
+			return IWL_MVM_STATION_COUNT;
+
+		return sta_id;
+	}
 
 	return IWL_MVM_STATION_COUNT;
 }
@@ -1227,7 +1241,8 @@ static u8 iwl_mvm_get_key_sta_id(struct ieee80211_vif *vif,
 static int iwl_mvm_send_sta_key(struct iwl_mvm *mvm,
 				struct iwl_mvm_sta *mvm_sta,
 				struct ieee80211_key_conf *keyconf, bool mcast,
-				u32 tkip_iv32, u16 *tkip_p1k, u32 cmd_flags)
+				u32 tkip_iv32, u16 *tkip_p1k, u32 cmd_flags,
+				u8 key_offset)
 {
 	struct iwl_mvm_add_sta_key_cmd cmd = {};
 	__le16 key_flags;
@@ -1269,7 +1284,7 @@ static int iwl_mvm_send_sta_key(struct iwl_mvm *mvm,
 	if (mcast)
 		key_flags |= cpu_to_le16(STA_KEY_MULTICAST);
 
-	cmd.key_offset = keyconf->hw_key_idx;
+	cmd.key_offset = key_offset;
 	cmd.key_flags = key_flags;
 	cmd.sta_id = sta_id;
 
@@ -1360,6 +1375,7 @@ static int __iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
 				 struct ieee80211_vif *vif,
 				 struct ieee80211_sta *sta,
 				 struct ieee80211_key_conf *keyconf,
+				 u8 key_offset,
 				 bool mcast)
 {
 	struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta);
@@ -1375,17 +1391,17 @@ static int __iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
 		ieee80211_get_key_rx_seq(keyconf, 0, &seq);
 		ieee80211_get_tkip_rx_p1k(keyconf, addr, seq.tkip.iv32, p1k);
 		ret = iwl_mvm_send_sta_key(mvm, mvm_sta, keyconf, mcast,
-					   seq.tkip.iv32, p1k, 0);
+					   seq.tkip.iv32, p1k, 0, key_offset);
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
 	case WLAN_CIPHER_SUITE_WEP40:
 	case WLAN_CIPHER_SUITE_WEP104:
 		ret = iwl_mvm_send_sta_key(mvm, mvm_sta, keyconf, mcast,
-					   0, NULL, 0);
+					   0, NULL, 0, key_offset);
 		break;
 	default:
 		ret = iwl_mvm_send_sta_key(mvm, mvm_sta, keyconf, mcast,
-					   0, NULL, 0);
+					   0, NULL, 0, key_offset);
 	}
 
 	return ret;
@@ -1433,7 +1449,7 @@ int iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
 			struct ieee80211_vif *vif,
 			struct ieee80211_sta *sta,
 			struct ieee80211_key_conf *keyconf,
-			bool have_key_offset)
+			u8 key_offset)
 {
 	bool mcast = !(keyconf->flags & IEEE80211_KEY_FLAG_PAIRWISE);
 	u8 sta_id;
@@ -1443,7 +1459,7 @@ int iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
 	lockdep_assert_held(&mvm->mutex);
 
 	/* Get the station id from the mvm local station table */
-	sta_id = iwl_mvm_get_key_sta_id(vif, sta);
+	sta_id = iwl_mvm_get_key_sta_id(mvm, vif, sta);
 	if (sta_id == IWL_MVM_STATION_COUNT) {
 		IWL_ERR(mvm, "Failed to find station id\n");
 		return -EINVAL;
@@ -1470,18 +1486,25 @@ int iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
 	if (WARN_ON_ONCE(iwl_mvm_sta_from_mac80211(sta)->vif != vif))
 		return -EINVAL;
 
-	if (!have_key_offset) {
-		/*
-		 * The D3 firmware hardcodes the PTK offset to 0, so we have to
-		 * configure it there. As a result, this workaround exists to
-		 * let the caller set the key offset (hw_key_idx), see d3.c.
-		 */
-		keyconf->hw_key_idx = iwl_mvm_set_fw_key_idx(mvm);
-		if (keyconf->hw_key_idx == STA_KEY_IDX_INVALID)
+	/* If the key_offset is not pre-assigned, we need to find a
+	 * new offset to use.  In normal cases, the offset is not
+	 * pre-assigned, but during HW_RESTART we want to reuse the
+	 * same indices, so we pass them when this function is called.
+	 *
+	 * In D3 entry, we need to hardcoded the indices (because the
+	 * firmware hardcodes the PTK offset to 0).  In this case, we
+	 * need to make sure we don't overwrite the hw_key_idx in the
+	 * keyconf structure, because otherwise we cannot configure
+	 * the original ones back when resuming.
+	 */
+	if (key_offset == STA_KEY_IDX_INVALID) {
+		key_offset  = iwl_mvm_set_fw_key_idx(mvm);
+		if (key_offset == STA_KEY_IDX_INVALID)
 			return -ENOSPC;
+		keyconf->hw_key_idx = key_offset;
 	}
 
-	ret = __iwl_mvm_set_sta_key(mvm, vif, sta, keyconf, mcast);
+	ret = __iwl_mvm_set_sta_key(mvm, vif, sta, keyconf, key_offset, mcast);
 	if (ret) {
 		__clear_bit(keyconf->hw_key_idx, mvm->fw_key_table);
 		goto end;
@@ -1495,7 +1518,8 @@ int iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
 	 */
 	if (keyconf->cipher == WLAN_CIPHER_SUITE_WEP40 ||
 	    keyconf->cipher == WLAN_CIPHER_SUITE_WEP104) {
-		ret = __iwl_mvm_set_sta_key(mvm, vif, sta, keyconf, !mcast);
+		ret = __iwl_mvm_set_sta_key(mvm, vif, sta, keyconf,
+					    key_offset, !mcast);
 		if (ret) {
 			__clear_bit(keyconf->hw_key_idx, mvm->fw_key_table);
 			__iwl_mvm_remove_sta_key(mvm, sta_id, keyconf, mcast);
@@ -1521,7 +1545,7 @@ int iwl_mvm_remove_sta_key(struct iwl_mvm *mvm,
 	lockdep_assert_held(&mvm->mutex);
 
 	/* Get the station id from the mvm local station table */
-	sta_id = iwl_mvm_get_key_sta_id(vif, sta);
+	sta_id = iwl_mvm_get_key_sta_id(mvm, vif, sta);
 
 	IWL_DEBUG_WEP(mvm, "mvm remove dynamic key: idx=%d sta=%d\n",
 		      keyconf->keyidx, sta_id);
@@ -1547,24 +1571,6 @@ int iwl_mvm_remove_sta_key(struct iwl_mvm *mvm,
 		return 0;
 	}
 
-	/*
-	 * It is possible that the 'sta' parameter is NULL, and thus
-	 * there is a need to retrieve the sta from the local station table,
-	 * for example when a GTK is removed (where the sta_id will then be
-	 * the AP ID, and no station was passed by mac80211.)
-	 */
-	if (!sta) {
-		sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[sta_id],
-						lockdep_is_held(&mvm->mutex));
-		if (!sta) {
-			IWL_ERR(mvm, "Invalid station id\n");
-			return -EINVAL;
-		}
-	}
-
-	if (WARN_ON_ONCE(iwl_mvm_sta_from_mac80211(sta)->vif != vif))
-		return -EINVAL;
-
 	ret = __iwl_mvm_remove_sta_key(mvm, sta_id, keyconf, mcast);
 	if (ret)
 		return ret;
@@ -1584,7 +1590,7 @@ void iwl_mvm_update_tkip_key(struct iwl_mvm *mvm,
 			     u16 *phase1key)
 {
 	struct iwl_mvm_sta *mvm_sta;
-	u8 sta_id = iwl_mvm_get_key_sta_id(vif, sta);
+	u8 sta_id = iwl_mvm_get_key_sta_id(mvm, vif, sta);
 	bool mcast = !(keyconf->flags & IEEE80211_KEY_FLAG_PAIRWISE);
 
 	if (WARN_ON_ONCE(sta_id == IWL_MVM_STATION_COUNT))
@@ -1602,7 +1608,7 @@ void iwl_mvm_update_tkip_key(struct iwl_mvm *mvm,
 
 	mvm_sta = iwl_mvm_sta_from_mac80211(sta);
 	iwl_mvm_send_sta_key(mvm, mvm_sta, keyconf, mcast,
-			     iv32, phase1key, CMD_ASYNC);
+			     iv32, phase1key, CMD_ASYNC, keyconf->hw_key_idx);
 	rcu_read_unlock();
 }
 
diff --git a/drivers/net/wireless/iwlwifi/mvm/sta.h b/drivers/net/wireless/iwlwifi/mvm/sta.h
index eedb215eba3f..0631cc0a6d3c 100644
--- a/drivers/net/wireless/iwlwifi/mvm/sta.h
+++ b/drivers/net/wireless/iwlwifi/mvm/sta.h
@@ -365,8 +365,8 @@ int iwl_mvm_rm_sta_id(struct iwl_mvm *mvm,
 int iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
 			struct ieee80211_vif *vif,
 			struct ieee80211_sta *sta,
-			struct ieee80211_key_conf *key,
-			bool have_key_offset);
+			struct ieee80211_key_conf *keyconf,
+			u8 key_offset);
 int iwl_mvm_remove_sta_key(struct iwl_mvm *mvm,
 			   struct ieee80211_vif *vif,
 			   struct ieee80211_sta *sta,
diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c
index 644b58bc5226..639761fb2bfb 100644
--- a/drivers/net/wireless/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/iwlwifi/pcie/drv.c
@@ -423,14 +423,21 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 /* 8000 Series */
 	{IWL_PCI_DEVICE(0x24F3, 0x0010, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0x1010, iwl8260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0130, iwl8260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x1130, iwl8260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0132, iwl8260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x1132, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0x0110, iwl8260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x01F0, iwl8260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0012, iwl8260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x1012, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0x1110, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0x0050, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0x0250, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0x1050, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0x0150, iwl8260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x1150, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F4, 0x0030, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F4, 0x1130, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F4, 0x1030, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0xC010, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0xC110, iwl8260_2ac_cfg)},
@@ -438,18 +445,28 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x24F3, 0xC050, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0xD050, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0x8010, iwl8260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x8110, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0x9010, iwl8260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x9110, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F4, 0x8030, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F4, 0x9030, iwl8260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x8130, iwl8260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x9130, iwl8260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x8132, iwl8260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x9132, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0x8050, iwl8260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x8150, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0x9050, iwl8260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x9150, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0x0004, iwl8260_2n_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0044, iwl8260_2n_cfg)},
 	{IWL_PCI_DEVICE(0x24F5, 0x0010, iwl4165_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F6, 0x0030, iwl4165_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0x0810, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0x0910, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0x0850, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0x0950, iwl8260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0x0930, iwl8260_2ac_cfg)},
 #endif /* CONFIG_IWLMVM */
 
 	{0}
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
index 6e9418ed90c2..bbb789f8990b 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
@@ -2272,7 +2272,7 @@ void rtl8821ae_enable_interrupt(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
-	if (!rtlpci->int_clear)
+	if (rtlpci->int_clear)
 		rtl8821ae_clear_interrupt(hw);/*clear it here first*/
 
 	rtl_write_dword(rtlpriv, REG_HIMR, rtlpci->irq_mask[0] & 0xFFFFFFFF);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
index 8ee141a55bc5..142bdff4ed60 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
@@ -448,7 +448,7 @@ MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n");
 MODULE_PARM_DESC(msi, "Set to 1 to use MSI interrupts mode (default 1)\n");
 MODULE_PARM_DESC(debug, "Set debug level (0-5) (default 0)");
 MODULE_PARM_DESC(disable_watchdog, "Set to 1 to disable the watchdog (default 0)\n");
-MODULE_PARM_DESC(int_clear, "Set to 1 to disable interrupt clear before set (default 0)\n");
+MODULE_PARM_DESC(int_clear, "Set to 0 to disable interrupt clear before set (default 1)\n");
 
 static SIMPLE_DEV_PM_OPS(rtlwifi_pm_ops, rtl_pci_suspend, rtl_pci_resume);
 
diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile
index 219dc206fa5f..a5fe23952586 100644
--- a/drivers/nvme/host/Makefile
+++ b/drivers/nvme/host/Makefile
@@ -1,4 +1,5 @@
 
 obj-$(CONFIG_BLK_DEV_NVME)     += nvme.o
 
-nvme-y		+= pci.o scsi.o lightnvm.o
+lightnvm-$(CONFIG_NVM)	:= lightnvm.o
+nvme-y		+= pci.o scsi.o $(lightnvm-y)
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index e0b7b95813bc..06c336410235 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -22,8 +22,6 @@
 
 #include "nvme.h"
 
-#ifdef CONFIG_NVM
-
 #include <linux/nvme.h>
 #include <linux/bitops.h>
 #include <linux/lightnvm.h>
@@ -93,7 +91,7 @@ struct nvme_nvm_l2ptbl {
 	__le16			cdw14[6];
 };
 
-struct nvme_nvm_bbtbl {
+struct nvme_nvm_getbbtbl {
 	__u8			opcode;
 	__u8			flags;
 	__u16			command_id;
@@ -101,10 +99,23 @@ struct nvme_nvm_bbtbl {
 	__u64			rsvd[2];
 	__le64			prp1;
 	__le64			prp2;
-	__le32			prp1_len;
-	__le32			prp2_len;
-	__le32			lbb;
-	__u32			rsvd11[3];
+	__le64			spba;
+	__u32			rsvd4[4];
+};
+
+struct nvme_nvm_setbbtbl {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__le32			nsid;
+	__le64			rsvd[2];
+	__le64			prp1;
+	__le64			prp2;
+	__le64			spba;
+	__le16			nlb;
+	__u8			value;
+	__u8			rsvd3;
+	__u32			rsvd4[3];
 };
 
 struct nvme_nvm_erase_blk {
@@ -129,8 +140,8 @@ struct nvme_nvm_command {
 		struct nvme_nvm_hb_rw hb_rw;
 		struct nvme_nvm_ph_rw ph_rw;
 		struct nvme_nvm_l2ptbl l2p;
-		struct nvme_nvm_bbtbl get_bb;
-		struct nvme_nvm_bbtbl set_bb;
+		struct nvme_nvm_getbbtbl get_bb;
+		struct nvme_nvm_setbbtbl set_bb;
 		struct nvme_nvm_erase_blk erase;
 	};
 };
@@ -142,11 +153,13 @@ struct nvme_nvm_id_group {
 	__u8			num_ch;
 	__u8			num_lun;
 	__u8			num_pln;
+	__u8			rsvd1;
 	__le16			num_blk;
 	__le16			num_pg;
 	__le16			fpg_sz;
 	__le16			csecs;
 	__le16			sos;
+	__le16			rsvd2;
 	__le32			trdt;
 	__le32			trdm;
 	__le32			tprt;
@@ -154,8 +167,9 @@ struct nvme_nvm_id_group {
 	__le32			tbet;
 	__le32			tbem;
 	__le32			mpos;
+	__le32			mccap;
 	__le16			cpar;
-	__u8			reserved[913];
+	__u8			reserved[906];
 } __packed;
 
 struct nvme_nvm_addr_format {
@@ -178,15 +192,28 @@ struct nvme_nvm_id {
 	__u8			ver_id;
 	__u8			vmnt;
 	__u8			cgrps;
-	__u8			res[5];
+	__u8			res;
 	__le32			cap;
 	__le32			dom;
 	struct nvme_nvm_addr_format ppaf;
-	__u8			ppat;
-	__u8			resv[223];
+	__u8			resv[228];
 	struct nvme_nvm_id_group groups[4];
 } __packed;
 
+struct nvme_nvm_bb_tbl {
+	__u8	tblid[4];
+	__le16	verid;
+	__le16	revid;
+	__le32	rvsd1;
+	__le32	tblks;
+	__le32	tfact;
+	__le32	tgrown;
+	__le32	tdresv;
+	__le32	thresv;
+	__le32	rsvd2[8];
+	__u8	blk[0];
+};
+
 /*
  * Check we didn't inadvertently grow the command struct
  */
@@ -195,12 +222,14 @@ static inline void _nvme_nvm_check_size(void)
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_identity) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_hb_rw) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_ph_rw) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_nvm_bbtbl) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_nvm_getbbtbl) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_nvm_setbbtbl) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_l2ptbl) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_erase_blk) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_id_group) != 960);
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_addr_format) != 128);
 	BUILD_BUG_ON(sizeof(struct nvme_nvm_id) != 4096);
+	BUILD_BUG_ON(sizeof(struct nvme_nvm_bb_tbl) != 512);
 }
 
 static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id)
@@ -234,6 +263,7 @@ static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id)
 		dst->tbet = le32_to_cpu(src->tbet);
 		dst->tbem = le32_to_cpu(src->tbem);
 		dst->mpos = le32_to_cpu(src->mpos);
+		dst->mccap = le32_to_cpu(src->mccap);
 
 		dst->cpar = le16_to_cpu(src->cpar);
 	}
@@ -244,6 +274,7 @@ static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id)
 static int nvme_nvm_identity(struct request_queue *q, struct nvm_id *nvm_id)
 {
 	struct nvme_ns *ns = q->queuedata;
+	struct nvme_dev *dev = ns->dev;
 	struct nvme_nvm_id *nvme_nvm_id;
 	struct nvme_nvm_command c = {};
 	int ret;
@@ -256,8 +287,8 @@ static int nvme_nvm_identity(struct request_queue *q, struct nvm_id *nvm_id)
 	if (!nvme_nvm_id)
 		return -ENOMEM;
 
-	ret = nvme_submit_sync_cmd(q, (struct nvme_command *)&c, nvme_nvm_id,
-						sizeof(struct nvme_nvm_id));
+	ret = nvme_submit_sync_cmd(dev->admin_q, (struct nvme_command *)&c,
+				nvme_nvm_id, sizeof(struct nvme_nvm_id));
 	if (ret) {
 		ret = -EIO;
 		goto out;
@@ -268,6 +299,8 @@ static int nvme_nvm_identity(struct request_queue *q, struct nvm_id *nvm_id)
 	nvm_id->cgrps = nvme_nvm_id->cgrps;
 	nvm_id->cap = le32_to_cpu(nvme_nvm_id->cap);
 	nvm_id->dom = le32_to_cpu(nvme_nvm_id->dom);
+	memcpy(&nvm_id->ppaf, &nvme_nvm_id->ppaf,
+					sizeof(struct nvme_nvm_addr_format));
 
 	ret = init_grps(nvm_id, nvme_nvm_id);
 out:
@@ -281,7 +314,7 @@ static int nvme_nvm_get_l2p_tbl(struct request_queue *q, u64 slba, u32 nlb,
 	struct nvme_ns *ns = q->queuedata;
 	struct nvme_dev *dev = ns->dev;
 	struct nvme_nvm_command c = {};
-	u32 len = queue_max_hw_sectors(q) << 9;
+	u32 len = queue_max_hw_sectors(dev->admin_q) << 9;
 	u32 nlb_pr_rq = len / sizeof(u64);
 	u64 cmd_slba = slba;
 	void *entries;
@@ -299,8 +332,8 @@ static int nvme_nvm_get_l2p_tbl(struct request_queue *q, u64 slba, u32 nlb,
 		c.l2p.slba = cpu_to_le64(cmd_slba);
 		c.l2p.nlb = cpu_to_le32(cmd_nlb);
 
-		ret = nvme_submit_sync_cmd(q, (struct nvme_command *)&c,
-								entries, len);
+		ret = nvme_submit_sync_cmd(dev->admin_q,
+				(struct nvme_command *)&c, entries, len);
 		if (ret) {
 			dev_err(dev->dev, "L2P table transfer failed (%d)\n",
 									ret);
@@ -322,43 +355,84 @@ out:
 	return ret;
 }
 
-static int nvme_nvm_get_bb_tbl(struct request_queue *q, int lunid,
-				unsigned int nr_blocks,
-				nvm_bb_update_fn *update_bbtbl, void *priv)
+static int nvme_nvm_get_bb_tbl(struct nvm_dev *nvmdev, struct ppa_addr ppa,
+				int nr_blocks, nvm_bb_update_fn *update_bbtbl,
+				void *priv)
 {
+	struct request_queue *q = nvmdev->q;
 	struct nvme_ns *ns = q->queuedata;
 	struct nvme_dev *dev = ns->dev;
 	struct nvme_nvm_command c = {};
-	void *bb_bitmap;
-	u16 bb_bitmap_size;
+	struct nvme_nvm_bb_tbl *bb_tbl;
+	int tblsz = sizeof(struct nvme_nvm_bb_tbl) + nr_blocks;
 	int ret = 0;
 
 	c.get_bb.opcode = nvme_nvm_admin_get_bb_tbl;
 	c.get_bb.nsid = cpu_to_le32(ns->ns_id);
-	c.get_bb.lbb = cpu_to_le32(lunid);
-	bb_bitmap_size = ((nr_blocks >> 15) + 1) * PAGE_SIZE;
-	bb_bitmap = kmalloc(bb_bitmap_size, GFP_KERNEL);
-	if (!bb_bitmap)
-		return -ENOMEM;
+	c.get_bb.spba = cpu_to_le64(ppa.ppa);
 
-	bitmap_zero(bb_bitmap, nr_blocks);
+	bb_tbl = kzalloc(tblsz, GFP_KERNEL);
+	if (!bb_tbl)
+		return -ENOMEM;
 
-	ret = nvme_submit_sync_cmd(q, (struct nvme_command *)&c, bb_bitmap,
-								bb_bitmap_size);
+	ret = nvme_submit_sync_cmd(dev->admin_q, (struct nvme_command *)&c,
+								bb_tbl, tblsz);
 	if (ret) {
 		dev_err(dev->dev, "get bad block table failed (%d)\n", ret);
 		ret = -EIO;
 		goto out;
 	}
 
-	ret = update_bbtbl(lunid, bb_bitmap, nr_blocks, priv);
+	if (bb_tbl->tblid[0] != 'B' || bb_tbl->tblid[1] != 'B' ||
+		bb_tbl->tblid[2] != 'L' || bb_tbl->tblid[3] != 'T') {
+		dev_err(dev->dev, "bbt format mismatch\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (le16_to_cpu(bb_tbl->verid) != 1) {
+		ret = -EINVAL;
+		dev_err(dev->dev, "bbt version not supported\n");
+		goto out;
+	}
+
+	if (le32_to_cpu(bb_tbl->tblks) != nr_blocks) {
+		ret = -EINVAL;
+		dev_err(dev->dev, "bbt unsuspected blocks returned (%u!=%u)",
+					le32_to_cpu(bb_tbl->tblks), nr_blocks);
+		goto out;
+	}
+
+	ppa = dev_to_generic_addr(nvmdev, ppa);
+	ret = update_bbtbl(ppa, nr_blocks, bb_tbl->blk, priv);
 	if (ret) {
 		ret = -EINTR;
 		goto out;
 	}
 
 out:
-	kfree(bb_bitmap);
+	kfree(bb_tbl);
+	return ret;
+}
+
+static int nvme_nvm_set_bb_tbl(struct request_queue *q, struct nvm_rq *rqd,
+								int type)
+{
+	struct nvme_ns *ns = q->queuedata;
+	struct nvme_dev *dev = ns->dev;
+	struct nvme_nvm_command c = {};
+	int ret = 0;
+
+	c.set_bb.opcode = nvme_nvm_admin_set_bb_tbl;
+	c.set_bb.nsid = cpu_to_le32(ns->ns_id);
+	c.set_bb.spba = cpu_to_le64(rqd->ppa_addr.ppa);
+	c.set_bb.nlb = cpu_to_le16(rqd->nr_pages - 1);
+	c.set_bb.value = type;
+
+	ret = nvme_submit_sync_cmd(dev->admin_q, (struct nvme_command *)&c,
+								NULL, 0);
+	if (ret)
+		dev_err(dev->dev, "set bad block table failed (%d)\n", ret);
 	return ret;
 }
 
@@ -474,6 +548,7 @@ static struct nvm_dev_ops nvme_nvm_dev_ops = {
 	.get_l2p_tbl		= nvme_nvm_get_l2p_tbl,
 
 	.get_bb_tbl		= nvme_nvm_get_bb_tbl,
+	.set_bb_tbl		= nvme_nvm_set_bb_tbl,
 
 	.submit_io		= nvme_nvm_submit_io,
 	.erase_block		= nvme_nvm_erase_block,
@@ -496,31 +571,27 @@ void nvme_nvm_unregister(struct request_queue *q, char *disk_name)
 	nvm_unregister(disk_name);
 }
 
+/* move to shared place when used in multiple places. */
+#define PCI_VENDOR_ID_CNEX 0x1d1d
+#define PCI_DEVICE_ID_CNEX_WL 0x2807
+#define PCI_DEVICE_ID_CNEX_QEMU 0x1f1f
+
 int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *id)
 {
 	struct nvme_dev *dev = ns->dev;
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
 	/* QEMU NVMe simulator - PCI ID + Vendor specific bit */
-	if (pdev->vendor == PCI_VENDOR_ID_INTEL && pdev->device == 0x5845 &&
+	if (pdev->vendor == PCI_VENDOR_ID_CNEX &&
+				pdev->device == PCI_DEVICE_ID_CNEX_QEMU &&
 							id->vs[0] == 0x1)
 		return 1;
 
 	/* CNEX Labs - PCI ID + Vendor specific bit */
-	if (pdev->vendor == 0x1d1d && pdev->device == 0x2807 &&
+	if (pdev->vendor == PCI_VENDOR_ID_CNEX &&
+				pdev->device == PCI_DEVICE_ID_CNEX_WL &&
 							id->vs[0] == 0x1)
 		return 1;
 
 	return 0;
 }
-#else
-int nvme_nvm_register(struct request_queue *q, char *disk_name)
-{
-	return 0;
-}
-void nvme_nvm_unregister(struct request_queue *q, char *disk_name) {};
-int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *id)
-{
-	return 0;
-}
-#endif /* CONFIG_NVM */
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index fdb4e5bad9ac..044253dca30a 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -136,8 +136,22 @@ int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr);
 int nvme_sg_io32(struct nvme_ns *ns, unsigned long arg);
 int nvme_sg_get_version_num(int __user *ip);
 
+#ifdef CONFIG_NVM
 int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *id);
 int nvme_nvm_register(struct request_queue *q, char *disk_name);
 void nvme_nvm_unregister(struct request_queue *q, char *disk_name);
+#else
+static inline int nvme_nvm_register(struct request_queue *q, char *disk_name)
+{
+	return 0;
+}
+
+static inline void nvme_nvm_unregister(struct request_queue *q, char *disk_name) {};
+
+static inline int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *id)
+{
+	return 0;
+}
+#endif /* CONFIG_NVM */
 
 #endif /* _NVME_H */
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 8187df204695..9e294ff4e652 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -896,19 +896,28 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 			goto retry_cmd;
 		}
 		if (blk_integrity_rq(req)) {
-			if (blk_rq_count_integrity_sg(req->q, req->bio) != 1)
+			if (blk_rq_count_integrity_sg(req->q, req->bio) != 1) {
+				dma_unmap_sg(dev->dev, iod->sg, iod->nents,
+						dma_dir);
 				goto error_cmd;
+			}
 
 			sg_init_table(iod->meta_sg, 1);
 			if (blk_rq_map_integrity_sg(
-					req->q, req->bio, iod->meta_sg) != 1)
+					req->q, req->bio, iod->meta_sg) != 1) {
+				dma_unmap_sg(dev->dev, iod->sg, iod->nents,
+						dma_dir);
 				goto error_cmd;
+			}
 
 			if (rq_data_dir(req))
 				nvme_dif_remap(req, nvme_dif_prep);
 
-			if (!dma_map_sg(nvmeq->q_dmadev, iod->meta_sg, 1, dma_dir))
+			if (!dma_map_sg(nvmeq->q_dmadev, iod->meta_sg, 1, dma_dir)) {
+				dma_unmap_sg(dev->dev, iod->sg, iod->nents,
+						dma_dir);
 				goto error_cmd;
+			}
 		}
 	}
 
@@ -968,7 +977,8 @@ static void __nvme_process_cq(struct nvme_queue *nvmeq, unsigned int *tag)
 	if (head == nvmeq->cq_head && phase == nvmeq->cq_phase)
 		return;
 
-	writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
+	if (likely(nvmeq->cq_vector >= 0))
+		writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
 	nvmeq->cq_head = head;
 	nvmeq->cq_phase = phase;
 
@@ -1727,9 +1737,13 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 	u32 aqa;
 	u64 cap = lo_hi_readq(&dev->bar->cap);
 	struct nvme_queue *nvmeq;
-	unsigned page_shift = PAGE_SHIFT;
+	/*
+	 * default to a 4K page size, with the intention to update this
+	 * path in the future to accomodate architectures with differing
+	 * kernel and IO page sizes.
+	 */
+	unsigned page_shift = 12;
 	unsigned dev_page_min = NVME_CAP_MPSMIN(cap) + 12;
-	unsigned dev_page_max = NVME_CAP_MPSMAX(cap) + 12;
 
 	if (page_shift < dev_page_min) {
 		dev_err(dev->dev,
@@ -1738,13 +1752,6 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 				1 << page_shift);
 		return -ENODEV;
 	}
-	if (page_shift > dev_page_max) {
-		dev_info(dev->dev,
-				"Device maximum page size (%u) smaller than "
-				"host (%u); enabling work-around\n",
-				1 << dev_page_max, 1 << page_shift);
-		page_shift = dev_page_max;
-	}
 
 	dev->subsystem = readl(&dev->bar->vs) >= NVME_VS(1, 1) ?
 						NVME_CAP_NSSRC(cap) : 0;
@@ -2268,7 +2275,7 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
 	if (dev->max_hw_sectors) {
 		blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors);
 		blk_queue_max_segments(ns->queue,
-			((dev->max_hw_sectors << 9) / dev->page_size) + 1);
+			(dev->max_hw_sectors / (dev->page_size >> 9)) + 1);
 	}
 	if (dev->stripe_size)
 		blk_queue_chunk_sectors(ns->queue, dev->stripe_size >> 9);
@@ -2701,6 +2708,18 @@ static int nvme_dev_map(struct nvme_dev *dev)
 	dev->q_depth = min_t(int, NVME_CAP_MQES(cap) + 1, NVME_Q_DEPTH);
 	dev->db_stride = 1 << NVME_CAP_STRIDE(cap);
 	dev->dbs = ((void __iomem *)dev->bar) + 4096;
+
+	/*
+	 * Temporary fix for the Apple controller found in the MacBook8,1 and
+	 * some MacBook7,1 to avoid controller resets and data loss.
+	 */
+	if (pdev->vendor == PCI_VENDOR_ID_APPLE && pdev->device == 0x2001) {
+		dev->q_depth = 2;
+		dev_warn(dev->dev, "detected Apple NVMe controller, set "
+			"queue depth=%u to work around controller resets\n",
+			dev->q_depth);
+	}
+
 	if (readl(&dev->bar->vs) >= NVME_VS(1, 2))
 		dev->cmb = nvme_map_cmb(dev);
 
@@ -2787,6 +2806,10 @@ static void nvme_del_queue_end(struct nvme_queue *nvmeq)
 {
 	struct nvme_delq_ctx *dq = nvmeq->cmdinfo.ctx;
 	nvme_put_dq(dq);
+
+	spin_lock_irq(&nvmeq->q_lock);
+	nvme_process_cq(nvmeq);
+	spin_unlock_irq(&nvmeq->q_lock);
 }
 
 static int adapter_async_del_queue(struct nvme_queue *nvmeq, u8 opcode,
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index 540f077c37ea..02a7452bdf23 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -440,7 +440,6 @@ int dw_pcie_host_init(struct pcie_port *pp)
 					 ret, pp->io);
 				continue;
 			}
-			pp->io_base = pp->io->start;
 			break;
 		case IORESOURCE_MEM:
 			pp->mem = win->res;
diff --git a/drivers/pci/host/pcie-hisi.c b/drivers/pci/host/pcie-hisi.c
index 35457ecd8e70..163671a4f798 100644
--- a/drivers/pci/host/pcie-hisi.c
+++ b/drivers/pci/host/pcie-hisi.c
@@ -111,7 +111,7 @@ static struct pcie_host_ops hisi_pcie_host_ops = {
 	.link_up = hisi_pcie_link_up,
 };
 
-static int __init hisi_add_pcie_port(struct pcie_port *pp,
+static int hisi_add_pcie_port(struct pcie_port *pp,
 				     struct platform_device *pdev)
 {
 	int ret;
@@ -139,7 +139,7 @@ static int __init hisi_add_pcie_port(struct pcie_port *pp,
 	return 0;
 }
 
-static int __init hisi_pcie_probe(struct platform_device *pdev)
+static int hisi_pcie_probe(struct platform_device *pdev)
 {
 	struct hisi_pcie *hisi_pcie;
 	struct pcie_port *pp;
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 4446fcb5effd..d7ffd66814bb 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -1146,9 +1146,21 @@ static int pci_pm_runtime_suspend(struct device *dev)
 	pci_dev->state_saved = false;
 	pci_dev->no_d3cold = false;
 	error = pm->runtime_suspend(dev);
-	suspend_report_result(pm->runtime_suspend, error);
-	if (error)
+	if (error) {
+		/*
+		 * -EBUSY and -EAGAIN is used to request the runtime PM core
+		 * to schedule a new suspend, so log the event only with debug
+		 * log level.
+		 */
+		if (error == -EBUSY || error == -EAGAIN)
+			dev_dbg(dev, "can't suspend now (%pf returned %d)\n",
+				pm->runtime_suspend, error);
+		else
+			dev_err(dev, "can't suspend (%pf returned %d)\n",
+				pm->runtime_suspend, error);
+
 		return error;
+	}
 	if (!pci_dev->d3cold_allowed)
 		pci_dev->no_d3cold = true;
 
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 92618686604c..eead54cd01b2 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -216,7 +216,10 @@ static ssize_t numa_node_store(struct device *dev,
 	if (ret)
 		return ret;
 
-	if (node >= MAX_NUMNODES || !node_online(node))
+	if ((node < 0 && node != NUMA_NO_NODE) || node >= MAX_NUMNODES)
+		return -EINVAL;
+
+	if (node != NUMA_NO_NODE && !node_online(node))
 		return -EINVAL;
 
 	add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index fd2f03fa53f3..d390fc1475ec 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -337,6 +337,4 @@ static inline int pci_dev_specific_reset(struct pci_dev *dev, int probe)
 }
 #endif
 
-struct pci_host_bridge *pci_find_host_bridge(struct pci_bus *bus);
-
 #endif /* DRIVERS_PCI_H */
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index e735c728e3b3..edb1984201e9 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1685,8 +1685,8 @@ static void pci_dma_configure(struct pci_dev *dev)
 {
 	struct device *bridge = pci_get_host_bridge_device(dev);
 
-	if (IS_ENABLED(CONFIG_OF) && dev->dev.of_node) {
-		if (bridge->parent)
+	if (IS_ENABLED(CONFIG_OF) &&
+		bridge->parent && bridge->parent->of_node) {
 			of_dma_configure(&dev->dev, bridge->parent->of_node);
 	} else if (has_acpi_companion(bridge)) {
 		struct acpi_device *adev = to_acpi_device_node(bridge->fwnode);
diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index b422e4ed73f4..312c78b27a32 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -5,8 +5,6 @@
 config PINCTRL
 	bool
 
-if PINCTRL
-
 menu "Pin controllers"
 	depends on PINCTRL
 
@@ -274,5 +272,3 @@ config PINCTRL_TB10X
 	select GPIOLIB
 
 endmenu
-
-endif
diff --git a/drivers/pinctrl/freescale/pinctrl-imx1-core.c b/drivers/pinctrl/freescale/pinctrl-imx1-core.c
index 88a7fac11bd4..acaf84cadca3 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx1-core.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx1-core.c
@@ -538,8 +538,10 @@ static int imx1_pinctrl_parse_functions(struct device_node *np,
 		func->groups[i] = child->name;
 		grp = &info->groups[grp_index++];
 		ret = imx1_pinctrl_parse_groups(child, grp, info, i++);
-		if (ret == -ENOMEM)
+		if (ret == -ENOMEM) {
+			of_node_put(child);
 			return ret;
+		}
 	}
 
 	return 0;
@@ -582,8 +584,10 @@ static int imx1_pinctrl_parse_dt(struct platform_device *pdev,
 
 	for_each_child_of_node(np, child) {
 		ret = imx1_pinctrl_parse_functions(child, info, ifunc++);
-		if (ret == -ENOMEM)
+		if (ret == -ENOMEM) {
+			of_node_put(child);
 			return -ENOMEM;
+		}
 	}
 
 	return 0;
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
index f307f1d27d64..5c717275a7fa 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
@@ -747,7 +747,7 @@ static int mtk_gpio_get_direction(struct gpio_chip *chip, unsigned offset)
 	reg_addr =  mtk_get_port(pctl, offset) + pctl->devdata->dir_offset;
 	bit = BIT(offset & 0xf);
 	regmap_read(pctl->regmap1, reg_addr, &read_val);
-	return !!(read_val & bit);
+	return !(read_val & bit);
 }
 
 static int mtk_gpio_get(struct gpio_chip *chip, unsigned offset)
@@ -757,12 +757,8 @@ static int mtk_gpio_get(struct gpio_chip *chip, unsigned offset)
 	unsigned int read_val = 0;
 	struct mtk_pinctrl *pctl = dev_get_drvdata(chip->dev);
 
-	if (mtk_gpio_get_direction(chip, offset))
-		reg_addr = mtk_get_port(pctl, offset) +
-			pctl->devdata->dout_offset;
-	else
-		reg_addr = mtk_get_port(pctl, offset) +
-			pctl->devdata->din_offset;
+	reg_addr = mtk_get_port(pctl, offset) +
+		pctl->devdata->din_offset;
 
 	bit = BIT(offset & 0xf);
 	regmap_read(pctl->regmap1, reg_addr, &read_val);
@@ -997,6 +993,7 @@ static struct gpio_chip mtk_gpio_chip = {
 	.owner			= THIS_MODULE,
 	.request		= gpiochip_generic_request,
 	.free			= gpiochip_generic_free,
+	.get_direction		= mtk_gpio_get_direction,
 	.direction_input	= mtk_gpio_direction_input,
 	.direction_output	= mtk_gpio_direction_output,
 	.get			= mtk_gpio_get,
diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
index d809c9eaa323..19a3c3bc2f1f 100644
--- a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
+++ b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
@@ -672,7 +672,7 @@ static int pm8xxx_gpio_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	pctrl->dev = &pdev->dev;
-	pctrl->npins = (unsigned)of_device_get_match_data(&pdev->dev);
+	pctrl->npins = (unsigned long)of_device_get_match_data(&pdev->dev);
 
 	pctrl->regmap = dev_get_regmap(pdev->dev.parent, NULL);
 	if (!pctrl->regmap) {
diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c b/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c
index 8982027de8e8..b868ef1766a0 100644
--- a/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c
+++ b/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c
@@ -763,7 +763,7 @@ static int pm8xxx_mpp_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	pctrl->dev = &pdev->dev;
-	pctrl->npins = (unsigned)of_device_get_match_data(&pdev->dev);
+	pctrl->npins = (unsigned long)of_device_get_match_data(&pdev->dev);
 
 	pctrl->regmap = dev_get_regmap(pdev->dev.parent, NULL);
 	if (!pctrl->regmap) {
diff --git a/drivers/pinctrl/sh-pfc/pfc-sh7734.c b/drivers/pinctrl/sh-pfc/pfc-sh7734.c
index e7deb51de7dc..9842bb106796 100644
--- a/drivers/pinctrl/sh-pfc/pfc-sh7734.c
+++ b/drivers/pinctrl/sh-pfc/pfc-sh7734.c
@@ -31,11 +31,11 @@
 	PORT_GP_12(5, fn, sfx)
 
 #undef _GP_DATA
-#define _GP_DATA(bank, pin, name, sfx)					\
+#define _GP_DATA(bank, pin, name, sfx, cfg)				\
 	PINMUX_DATA(name##_DATA, name##_FN, name##_IN, name##_OUT)
 
-#define _GP_INOUTSEL(bank, pin, name, sfx)	name##_IN, name##_OUT
-#define _GP_INDT(bank, pin, name, sfx)		name##_DATA
+#define _GP_INOUTSEL(bank, pin, name, sfx, cfg)	name##_IN, name##_OUT
+#define _GP_INDT(bank, pin, name, sfx, cfg)	name##_DATA
 #define GP_INOUTSEL(bank)	PORT_GP_32_REV(bank, _GP_INOUTSEL, unused)
 #define GP_INDT(bank)		PORT_GP_32_REV(bank, _GP_INDT, unused)
 
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 8b3130f22b42..9e03d158f411 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -1478,6 +1478,8 @@ module_init(remoteproc_init);
 
 static void __exit remoteproc_exit(void)
 {
+	ida_destroy(&rproc_dev_index);
+
 	rproc_exit_debugfs();
 }
 module_exit(remoteproc_exit);
diff --git a/drivers/remoteproc/remoteproc_debugfs.c b/drivers/remoteproc/remoteproc_debugfs.c
index 9d30809bb407..916af5096f57 100644
--- a/drivers/remoteproc/remoteproc_debugfs.c
+++ b/drivers/remoteproc/remoteproc_debugfs.c
@@ -156,7 +156,7 @@ rproc_recovery_write(struct file *filp, const char __user *user_buf,
 	char buf[10];
 	int ret;
 
-	if (count > sizeof(buf))
+	if (count < 1 || count > sizeof(buf))
 		return count;
 
 	ret = copy_from_user(buf, user_buf, count);
diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c
index 188006c55ce0..aa705bb4748c 100644
--- a/drivers/rtc/rtc-ds1307.c
+++ b/drivers/rtc/rtc-ds1307.c
@@ -15,9 +15,6 @@
 #include <linux/i2c.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
-#include <linux/of_irq.h>
-#include <linux/pm_wakeirq.h>
 #include <linux/rtc/ds1307.h>
 #include <linux/rtc.h>
 #include <linux/slab.h>
@@ -117,7 +114,6 @@ struct ds1307 {
 #define HAS_ALARM	1		/* bit 1 == irq claimed */
 	struct i2c_client	*client;
 	struct rtc_device	*rtc;
-	int			wakeirq;
 	s32 (*read_block_data)(const struct i2c_client *client, u8 command,
 			       u8 length, u8 *values);
 	s32 (*write_block_data)(const struct i2c_client *client, u8 command,
@@ -1138,7 +1134,10 @@ read_rtc:
 				bin2bcd(tmp));
 	}
 
-	device_set_wakeup_capable(&client->dev, want_irq);
+	if (want_irq) {
+		device_set_wakeup_capable(&client->dev, true);
+		set_bit(HAS_ALARM, &ds1307->flags);
+	}
 	ds1307->rtc = devm_rtc_device_register(&client->dev, client->name,
 				rtc_ops, THIS_MODULE);
 	if (IS_ERR(ds1307->rtc)) {
@@ -1146,43 +1145,19 @@ read_rtc:
 	}
 
 	if (want_irq) {
-		struct device_node *node = client->dev.of_node;
-
 		err = devm_request_threaded_irq(&client->dev,
 						client->irq, NULL, irq_handler,
 						IRQF_SHARED | IRQF_ONESHOT,
 						ds1307->rtc->name, client);
 		if (err) {
 			client->irq = 0;
+			device_set_wakeup_capable(&client->dev, false);
+			clear_bit(HAS_ALARM, &ds1307->flags);
 			dev_err(&client->dev, "unable to request IRQ!\n");
-			goto no_irq;
-		}
-
-		set_bit(HAS_ALARM, &ds1307->flags);
-		dev_dbg(&client->dev, "got IRQ %d\n", client->irq);
-
-		/* Currently supported by OF code only! */
-		if (!node)
-			goto no_irq;
-
-		err = of_irq_get(node, 1);
-		if (err <= 0) {
-			if (err == -EPROBE_DEFER)
-				goto exit;
-			goto no_irq;
-		}
-		ds1307->wakeirq = err;
-
-		err = dev_pm_set_dedicated_wake_irq(&client->dev,
-						    ds1307->wakeirq);
-		if (err) {
-			dev_err(&client->dev, "unable to setup wakeIRQ %d!\n",
-				err);
-			goto exit;
-		}
+		} else
+			dev_dbg(&client->dev, "got IRQ %d\n", client->irq);
 	}
 
-no_irq:
 	if (chip->nvram_size) {
 
 		ds1307->nvram = devm_kzalloc(&client->dev,
@@ -1226,9 +1201,6 @@ static int ds1307_remove(struct i2c_client *client)
 {
 	struct ds1307 *ds1307 = i2c_get_clientdata(client);
 
-	if (ds1307->wakeirq)
-		dev_pm_clear_wake_irq(&client->dev);
-
 	if (test_and_clear_bit(HAS_NVRAM, &ds1307->flags))
 		sysfs_remove_bin_file(&client->dev.kobj, ds1307->nvram);
 
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index 548a18916a31..a831d18596a5 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -1080,28 +1080,10 @@ void __init chsc_init_cleanup(void)
 	free_page((unsigned long)sei_page);
 }
 
-int chsc_enable_facility(int operation_code)
+int __chsc_enable_facility(struct chsc_sda_area *sda_area, int operation_code)
 {
-	unsigned long flags;
 	int ret;
-	struct {
-		struct chsc_header request;
-		u8 reserved1:4;
-		u8 format:4;
-		u8 reserved2;
-		u16 operation_code;
-		u32 reserved3;
-		u32 reserved4;
-		u32 operation_data_area[252];
-		struct chsc_header response;
-		u32 reserved5:4;
-		u32 format2:4;
-		u32 reserved6:24;
-	} __attribute__ ((packed)) *sda_area;
 
-	spin_lock_irqsave(&chsc_page_lock, flags);
-	memset(chsc_page, 0, PAGE_SIZE);
-	sda_area = chsc_page;
 	sda_area->request.length = 0x0400;
 	sda_area->request.code = 0x0031;
 	sda_area->operation_code = operation_code;
@@ -1119,10 +1101,25 @@ int chsc_enable_facility(int operation_code)
 	default:
 		ret = chsc_error_from_response(sda_area->response.code);
 	}
+out:
+	return ret;
+}
+
+int chsc_enable_facility(int operation_code)
+{
+	struct chsc_sda_area *sda_area;
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&chsc_page_lock, flags);
+	memset(chsc_page, 0, PAGE_SIZE);
+	sda_area = chsc_page;
+
+	ret = __chsc_enable_facility(sda_area, operation_code);
 	if (ret != 0)
 		CIO_CRW_EVENT(2, "chsc: sda (oc=%x) failed (rc=%04x)\n",
 			      operation_code, sda_area->response.code);
-out:
+
 	spin_unlock_irqrestore(&chsc_page_lock, flags);
 	return ret;
 }
diff --git a/drivers/s390/cio/chsc.h b/drivers/s390/cio/chsc.h
index 76c9b50700b2..0de134c3a204 100644
--- a/drivers/s390/cio/chsc.h
+++ b/drivers/s390/cio/chsc.h
@@ -115,6 +115,20 @@ struct chsc_scpd {
 	u8 data[PAGE_SIZE - 20];
 } __attribute__ ((packed));
 
+struct chsc_sda_area {
+	struct chsc_header request;
+	u8 :4;
+	u8 format:4;
+	u8 :8;
+	u16 operation_code;
+	u32 :32;
+	u32 :32;
+	u32 operation_data_area[252];
+	struct chsc_header response;
+	u32 :4;
+	u32 format2:4;
+	u32 :24;
+} __packed __aligned(PAGE_SIZE);
 
 extern int chsc_get_ssd_info(struct subchannel_id schid,
 			     struct chsc_ssd_info *ssd);
@@ -122,6 +136,7 @@ extern int chsc_determine_css_characteristics(void);
 extern int chsc_init(void);
 extern void chsc_init_cleanup(void);
 
+int __chsc_enable_facility(struct chsc_sda_area *sda_area, int operation_code);
 extern int chsc_enable_facility(int);
 struct channel_subsystem;
 extern int chsc_secm(struct channel_subsystem *, int);
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index b5620e818d6b..690b8547e828 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -925,18 +925,32 @@ void reipl_ccw_dev(struct ccw_dev_id *devid)
 
 int __init cio_get_iplinfo(struct cio_iplinfo *iplinfo)
 {
+	static struct chsc_sda_area sda_area __initdata;
 	struct subchannel_id schid;
 	struct schib schib;
 
 	schid = *(struct subchannel_id *)&S390_lowcore.subchannel_id;
 	if (!schid.one)
 		return -ENODEV;
+
+	if (schid.ssid) {
+		/*
+		 * Firmware should have already enabled MSS but whoever started
+		 * the kernel might have initiated a channel subsystem reset.
+		 * Ensure that MSS is enabled.
+		 */
+		memset(&sda_area, 0, sizeof(sda_area));
+		if (__chsc_enable_facility(&sda_area, CHSC_SDA_OC_MSS))
+			return -ENODEV;
+	}
 	if (stsch_err(schid, &schib))
 		return -ENODEV;
 	if (schib.pmcw.st != SUBCHANNEL_TYPE_IO)
 		return -ENODEV;
 	if (!schib.pmcw.dnv)
 		return -ENODEV;
+
+	iplinfo->ssid = schid.ssid;
 	iplinfo->devno = schib.pmcw.dev;
 	iplinfo->is_qdio = schib.pmcw.qf;
 	return 0;
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index 2ee3053bdc12..489e703dc82d 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -702,17 +702,12 @@ css_generate_pgid(struct channel_subsystem *css, u32 tod_high)
 		css->global_pgid.pgid_high.ext_cssid.version = 0x80;
 		css->global_pgid.pgid_high.ext_cssid.cssid = css->cssid;
 	} else {
-#ifdef CONFIG_SMP
 		css->global_pgid.pgid_high.cpu_addr = stap();
-#else
-		css->global_pgid.pgid_high.cpu_addr = 0;
-#endif
 	}
 	get_cpu_id(&cpu_id);
 	css->global_pgid.cpu_id = cpu_id.ident;
 	css->global_pgid.cpu_model = cpu_id.machine;
 	css->global_pgid.tod_high = tod_high;
-
 }
 
 static void
diff --git a/drivers/s390/crypto/Makefile b/drivers/s390/crypto/Makefile
index 57f710b3c8a4..b8ab18676e69 100644
--- a/drivers/s390/crypto/Makefile
+++ b/drivers/s390/crypto/Makefile
@@ -3,6 +3,9 @@
 #
 
 ap-objs := ap_bus.o
-obj-$(CONFIG_ZCRYPT) += ap.o zcrypt_api.o zcrypt_pcixcc.o
-obj-$(CONFIG_ZCRYPT) += zcrypt_cex2a.o zcrypt_cex4.o
+# zcrypt_api depends on ap
+obj-$(CONFIG_ZCRYPT) += ap.o zcrypt_api.o
+# msgtype* depend on zcrypt_api
 obj-$(CONFIG_ZCRYPT) += zcrypt_msgtype6.o zcrypt_msgtype50.o
+# adapter drivers depend on ap, zcrypt_api and msgtype*
+obj-$(CONFIG_ZCRYPT) += zcrypt_pcixcc.o zcrypt_cex2a.o zcrypt_cex4.o
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 9cb3dfbcaddb..61f768518a34 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -74,6 +74,7 @@ static struct device *ap_root_device = NULL;
 static struct ap_config_info *ap_configuration;
 static DEFINE_SPINLOCK(ap_device_list_lock);
 static LIST_HEAD(ap_device_list);
+static bool initialised;
 
 /*
  * Workqueue timer for bus rescan.
@@ -1384,6 +1385,9 @@ int ap_driver_register(struct ap_driver *ap_drv, struct module *owner,
 {
 	struct device_driver *drv = &ap_drv->driver;
 
+	if (!initialised)
+		return -ENODEV;
+
 	drv->bus = &ap_bus_type;
 	drv->probe = ap_device_probe;
 	drv->remove = ap_device_remove;
@@ -1808,6 +1812,7 @@ int __init ap_module_init(void)
 		goto out_pm;
 
 	queue_work(system_long_wq, &ap_scan_work);
+	initialised = true;
 
 	return 0;
 
@@ -1837,6 +1842,7 @@ void ap_module_exit(void)
 {
 	int i;
 
+	initialised = false;
 	ap_reset_domain();
 	ap_poll_thread_stop();
 	del_timer_sync(&ap_config_timer);
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index a9603ebbc1f8..9f8fa42c062c 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -317,11 +317,9 @@ EXPORT_SYMBOL(zcrypt_device_unregister);
 
 void zcrypt_msgtype_register(struct zcrypt_ops *zops)
 {
-	if (zops->owner) {
-		spin_lock_bh(&zcrypt_ops_list_lock);
-		list_add_tail(&zops->list, &zcrypt_ops_list);
-		spin_unlock_bh(&zcrypt_ops_list_lock);
-	}
+	spin_lock_bh(&zcrypt_ops_list_lock);
+	list_add_tail(&zops->list, &zcrypt_ops_list);
+	spin_unlock_bh(&zcrypt_ops_list_lock);
 }
 EXPORT_SYMBOL(zcrypt_msgtype_register);
 
@@ -342,7 +340,7 @@ struct zcrypt_ops *__ops_lookup(unsigned char *name, int variant)
 	spin_lock_bh(&zcrypt_ops_list_lock);
 	list_for_each_entry(zops, &zcrypt_ops_list, list) {
 		if ((zops->variant == variant) &&
-		    (!strncmp(zops->owner->name, name, MODULE_NAME_LEN))) {
+		    (!strncmp(zops->name, name, sizeof(zops->name)))) {
 			found = 1;
 			break;
 		}
diff --git a/drivers/s390/crypto/zcrypt_api.h b/drivers/s390/crypto/zcrypt_api.h
index 750876891931..38618f05ad92 100644
--- a/drivers/s390/crypto/zcrypt_api.h
+++ b/drivers/s390/crypto/zcrypt_api.h
@@ -96,6 +96,7 @@ struct zcrypt_ops {
 	struct list_head list;		/* zcrypt ops list. */
 	struct module *owner;
 	int variant;
+	char name[128];
 };
 
 struct zcrypt_device {
diff --git a/drivers/s390/crypto/zcrypt_msgtype50.c b/drivers/s390/crypto/zcrypt_msgtype50.c
index 71ceee9137a8..74edf2934e7c 100644
--- a/drivers/s390/crypto/zcrypt_msgtype50.c
+++ b/drivers/s390/crypto/zcrypt_msgtype50.c
@@ -513,6 +513,7 @@ static struct zcrypt_ops zcrypt_msgtype50_ops = {
 	.rsa_modexpo = zcrypt_cex2a_modexpo,
 	.rsa_modexpo_crt = zcrypt_cex2a_modexpo_crt,
 	.owner = THIS_MODULE,
+	.name = MSGTYPE50_NAME,
 	.variant = MSGTYPE50_VARIANT_DEFAULT,
 };
 
diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c
index 74762214193b..9a2dd472c1cc 100644
--- a/drivers/s390/crypto/zcrypt_msgtype6.c
+++ b/drivers/s390/crypto/zcrypt_msgtype6.c
@@ -1119,6 +1119,7 @@ static long zcrypt_msgtype6_rng(struct zcrypt_device *zdev,
  */
 static struct zcrypt_ops zcrypt_msgtype6_norng_ops = {
 	.owner = THIS_MODULE,
+	.name = MSGTYPE06_NAME,
 	.variant = MSGTYPE06_VARIANT_NORNG,
 	.rsa_modexpo = zcrypt_msgtype6_modexpo,
 	.rsa_modexpo_crt = zcrypt_msgtype6_modexpo_crt,
@@ -1127,6 +1128,7 @@ static struct zcrypt_ops zcrypt_msgtype6_norng_ops = {
 
 static struct zcrypt_ops zcrypt_msgtype6_ops = {
 	.owner = THIS_MODULE,
+	.name = MSGTYPE06_NAME,
 	.variant = MSGTYPE06_VARIANT_DEFAULT,
 	.rsa_modexpo = zcrypt_msgtype6_modexpo,
 	.rsa_modexpo_crt = zcrypt_msgtype6_modexpo_crt,
@@ -1136,6 +1138,7 @@ static struct zcrypt_ops zcrypt_msgtype6_ops = {
 
 static struct zcrypt_ops zcrypt_msgtype6_ep11_ops = {
 	.owner = THIS_MODULE,
+	.name = MSGTYPE06_NAME,
 	.variant = MSGTYPE06_VARIANT_EP11,
 	.rsa_modexpo = NULL,
 	.rsa_modexpo_crt = NULL,
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 37dce2380a52..c1fe0d2f90ca 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -194,6 +194,7 @@ config CHR_DEV_SCH
 config SCSI_ENCLOSURE
 	tristate "SCSI Enclosure Support"
 	depends on SCSI && ENCLOSURE_SERVICES
+	depends on m || SCSI_SAS_ATTRS != m
 	help
 	  Enclosures are devices sitting on or in SCSI backplanes that
 	  manage devices.  If you have a disk cage, the chances are that
@@ -364,6 +365,7 @@ config SCSI_HPSA
 	tristate "HP Smart Array SCSI driver"
 	depends on PCI && SCSI
 	select CHECK_SIGNATURE
+	select SCSI_SAS_ATTRS
 	help
 	  This driver supports HP Smart Array Controllers (circa 2009).
 	  It is a SCSI alternative to the cciss driver, which is a block
@@ -500,6 +502,7 @@ config SCSI_ADVANSYS
 	tristate "AdvanSys SCSI support"
 	depends on SCSI
 	depends on ISA || EISA || PCI
+	depends on ISA_DMA_API || !ISA
 	help
 	  This is a driver for all SCSI host adapters manufactured by
 	  AdvanSys. It is documented in the kernel source in
diff --git a/drivers/scsi/advansys.c b/drivers/scsi/advansys.c
index 519f9a4b3dad..febbd83e2ecd 100644
--- a/drivers/scsi/advansys.c
+++ b/drivers/scsi/advansys.c
@@ -7803,7 +7803,7 @@ adv_build_req(struct asc_board *boardp, struct scsi_cmnd *scp,
 		return ASC_BUSY;
 	}
 	scsiqp->sense_addr = cpu_to_le32(sense_addr);
-	scsiqp->sense_len = cpu_to_le32(SCSI_SENSE_BUFFERSIZE);
+	scsiqp->sense_len = SCSI_SENSE_BUFFERSIZE;
 
 	/* Build ADV_SCSI_REQ_Q */
 
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 323982fd00c3..82ac1cd818ac 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -333,6 +333,17 @@ static void scsi_host_dev_release(struct device *dev)
 		kfree(queuedata);
 	}
 
+	if (shost->shost_state == SHOST_CREATED) {
+		/*
+		 * Free the shost_dev device name here if scsi_host_alloc()
+		 * and scsi_host_put() have been called but neither
+		 * scsi_host_add() nor scsi_host_remove() has been called.
+		 * This avoids that the memory allocated for the shost_dev
+		 * name is leaked.
+		 */
+		kfree(dev_name(&shost->shost_dev));
+	}
+
 	scsi_destroy_command_freelist(shost);
 	if (shost_use_blk_mq(shost)) {
 		if (shost->tag_set.tags)
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 17a39761b05d..38ce0e308fbe 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -8764,7 +8764,7 @@ static void hpsa_disable_rld_caching(struct ctlr_info *h)
 	if ((rc != 0)  || (c->err_info->CommandStatus != 0))
 		goto errout;
 
-	if (*options && HPSA_DIAG_OPTS_DISABLE_RLD_CACHING)
+	if (*options & HPSA_DIAG_OPTS_DISABLE_RLD_CACHING)
 		goto out;
 
 errout:
diff --git a/drivers/scsi/mpt3sas/Kconfig b/drivers/scsi/mpt3sas/Kconfig
index 29061467cc17..b736dbc80485 100644
--- a/drivers/scsi/mpt3sas/Kconfig
+++ b/drivers/scsi/mpt3sas/Kconfig
@@ -71,3 +71,12 @@ config SCSI_MPT3SAS_MAX_SGE
 	MAX_PHYS_SEGMENTS in most kernels.  However in SuSE kernels this
 	can be 256. However, it may decreased down to 16.  Decreasing this
 	parameter will reduce memory requirements on a per controller instance.
+
+config SCSI_MPT2SAS
+	tristate "Legacy MPT2SAS config option"
+	default n
+	select SCSI_MPT3SAS
+	depends on PCI && SCSI
+	---help---
+	Dummy config option for backwards compatiblity: configure the MPT3SAS
+	driver instead.
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index d95206b7e116..9ab77b06434d 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -3905,8 +3905,7 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 	 * We do not expose raid functionality to upper layer for warpdrive.
 	 */
 	if (!ioc->is_warpdrive && !scsih_is_raid(&scmd->device->sdev_gendev)
-	    && (sas_device_priv_data->flags & MPT_DEVICE_TLR_ON) &&
-	    scmd->cmd_len != 32)
+	    && sas_is_tlr_enabled(scmd->device) && scmd->cmd_len != 32)
 		mpi_control |= MPI2_SCSIIO_CONTROL_TLR_ON;
 
 	smid = mpt3sas_base_get_smid_scsiio(ioc, ioc->scsi_io_cb_idx, scmd);
diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c
index 6110ef3bfa92..c7c250519c4b 100644
--- a/drivers/scsi/mvsas/mv_init.c
+++ b/drivers/scsi/mvsas/mv_init.c
@@ -760,7 +760,7 @@ mvs_store_interrupt_coalescing(struct device *cdev,
 			struct device_attribute *attr,
 			const char *buffer, size_t size)
 {
-	int val = 0;
+	unsigned int val = 0;
 	struct mvs_info *mvi = NULL;
 	struct Scsi_Host *shost = class_to_shost(cdev);
 	struct sas_ha_struct *sha = SHOST_TO_SAS_HA(shost);
@@ -768,7 +768,7 @@ mvs_store_interrupt_coalescing(struct device *cdev,
 	if (buffer == NULL)
 		return size;
 
-	if (sscanf(buffer, "%d", &val) != 1)
+	if (sscanf(buffer, "%u", &val) != 1)
 		return -EINVAL;
 
 	if (val >= 0x10000) {
diff --git a/drivers/scsi/qla2xxx/qla_nx.c b/drivers/scsi/qla2xxx/qla_nx.c
index eb0cc5475c45..b6b4cfdd7620 100644
--- a/drivers/scsi/qla2xxx/qla_nx.c
+++ b/drivers/scsi/qla2xxx/qla_nx.c
@@ -433,7 +433,7 @@ qla82xx_pci_get_crb_addr_2M(struct qla_hw_data *ha, ulong off_in,
 	if (off_in < QLA82XX_PCI_CRBSPACE)
 		return -1;
 
-	*off_out = (void __iomem *)(off_in - QLA82XX_PCI_CRBSPACE);
+	off_in -= QLA82XX_PCI_CRBSPACE;
 
 	/* Try direct map */
 	m = &crb_128M_2M_map[CRB_BLK(off_in)].sub_block[CRB_SUBBLK(off_in)];
@@ -443,6 +443,7 @@ qla82xx_pci_get_crb_addr_2M(struct qla_hw_data *ha, ulong off_in,
 		return 0;
 	}
 	/* Not in direct map, use crb window */
+	*off_out = (void __iomem *)off_in;
 	return 1;
 }
 
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 3ba2e9564b9a..81af294f15a7 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -902,7 +902,7 @@ static ssize_t tcm_qla2xxx_tpg_fabric_prot_type_show(struct config_item *item,
 	return sprintf(page, "%d\n", tpg->tpg_attrib.fabric_prot_type);
 }
 
-CONFIGFS_ATTR_WO(tcm_qla2xxx_tpg_, enable);
+CONFIGFS_ATTR(tcm_qla2xxx_tpg_, enable);
 CONFIGFS_ATTR_RO(tcm_qla2xxx_tpg_, dynamic_sessions);
 CONFIGFS_ATTR(tcm_qla2xxx_tpg_, fabric_prot_type);
 
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 237b691c8e0a..f3d69a98c725 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -465,8 +465,9 @@ static const struct opcode_info_t opcode_info_arr[SDEB_I_LAST_ELEMENT + 1] = {
 	     0} },
 	{0, 0, 0, F_INV_OP | FF_RESPOND, NULL, NULL, /* MAINT OUT */
 	    {0,  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} },
-	{0, 0, 0, F_INV_OP | FF_RESPOND, NULL, NULL, /* VERIFY */
-	    {0,  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} },
+	{0, 0x2f, 0, F_D_OUT_MAYBE | FF_DIRECT_IO, NULL, NULL, /* VERIFY(10) */
+	    {10,  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xc7,
+	     0, 0, 0, 0, 0, 0} },
 	{1, 0x7f, 0x9, F_SA_HIGH | F_D_IN | FF_DIRECT_IO, resp_read_dt0,
 	    vl_iarr, {32,  0xc7, 0, 0, 0, 0, 0x1f, 0x18, 0x0, 0x9, 0xfe, 0,
 		      0xff, 0xff, 0xff, 0xff} },/* VARIABLE LENGTH, READ(32) */
@@ -477,8 +478,8 @@ static const struct opcode_info_t opcode_info_arr[SDEB_I_LAST_ELEMENT + 1] = {
 	    {10,  0x13, 0xff, 0xff, 0, 0, 0, 0xff, 0xff, 0xc7, 0, 0, 0, 0, 0,
 	     0} },
 /* 20 */
-	{0, 0, 0, F_INV_OP | FF_RESPOND, NULL, NULL, /* ALLOW REMOVAL */
-	    {0,  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} },
+	{0, 0x1e, 0, 0, NULL, NULL, /* ALLOW REMOVAL */
+	    {6,  0, 0, 0, 0x3, 0xc7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} },
 	{0, 0x1, 0, 0, resp_start_stop, NULL, /* REWIND ?? */
 	    {6,  0x1, 0, 0, 0, 0xc7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} },
 	{0, 0, 0, F_INV_OP | FF_RESPOND, NULL, NULL, /* ATA_PT */
diff --git a/drivers/scsi/scsi_pm.c b/drivers/scsi/scsi_pm.c
index e4b799837948..459abe1dcc87 100644
--- a/drivers/scsi/scsi_pm.c
+++ b/drivers/scsi/scsi_pm.c
@@ -219,13 +219,13 @@ static int sdev_runtime_suspend(struct device *dev)
 	struct scsi_device *sdev = to_scsi_device(dev);
 	int err = 0;
 
-	if (pm && pm->runtime_suspend) {
-		err = blk_pre_runtime_suspend(sdev->request_queue);
-		if (err)
-			return err;
+	err = blk_pre_runtime_suspend(sdev->request_queue);
+	if (err)
+		return err;
+	if (pm && pm->runtime_suspend)
 		err = pm->runtime_suspend(dev);
-		blk_post_runtime_suspend(sdev->request_queue, err);
-	}
+	blk_post_runtime_suspend(sdev->request_queue, err);
+
 	return err;
 }
 
@@ -248,11 +248,11 @@ static int sdev_runtime_resume(struct device *dev)
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
 	int err = 0;
 
-	if (pm && pm->runtime_resume) {
-		blk_pre_runtime_resume(sdev->request_queue);
+	blk_pre_runtime_resume(sdev->request_queue);
+	if (pm && pm->runtime_resume)
 		err = pm->runtime_resume(dev);
-		blk_post_runtime_resume(sdev->request_queue, err);
-	}
+	blk_post_runtime_resume(sdev->request_queue, err);
+
 	return err;
 }
 
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index a1c195d71fd1..6a820668d442 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -702,9 +702,12 @@ static int scsi_probe_lun(struct scsi_device *sdev, unsigned char *inq_result,
 	 * strings.
 	 */
 	if (sdev->inquiry_len < 36) {
-		sdev_printk(KERN_INFO, sdev,
-			    "scsi scan: INQUIRY result too short (%d),"
-			    " using 36\n", sdev->inquiry_len);
+		if (!sdev->host->short_inquiry) {
+			shost_printk(KERN_INFO, sdev->host,
+				    "scsi scan: INQUIRY result too short (%d),"
+				    " using 36\n", sdev->inquiry_len);
+			sdev->host->short_inquiry = 1;
+		}
 		sdev->inquiry_len = 36;
 	}
 
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index ef360533790d..4f18a851e2c7 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -1182,6 +1182,14 @@ void __scsi_remove_device(struct scsi_device *sdev)
 {
 	struct device *dev = &sdev->sdev_gendev;
 
+	/*
+	 * This cleanup path is not reentrant and while it is impossible
+	 * to get a new reference with scsi_device_get() someone can still
+	 * hold a previously acquired one.
+	 */
+	if (sdev->sdev_state == SDEV_DEL)
+		return;
+
 	if (sdev->is_visible) {
 		if (scsi_device_set_state(sdev, SDEV_CANCEL) != 0)
 			return;
@@ -1190,7 +1198,9 @@ void __scsi_remove_device(struct scsi_device *sdev)
 		device_unregister(&sdev->sdev_dev);
 		transport_remove_device(dev);
 		scsi_dh_remove_device(sdev);
-	}
+		device_del(dev);
+	} else
+		put_device(&sdev->sdev_dev);
 
 	/*
 	 * Stop accepting new requests and wait until all queuecommand() and
@@ -1201,16 +1211,6 @@ void __scsi_remove_device(struct scsi_device *sdev)
 	blk_cleanup_queue(sdev->request_queue);
 	cancel_work_sync(&sdev->requeue_work);
 
-	/*
-	 * Remove the device after blk_cleanup_queue() has been called such
-	 * a possible bdi_register() call with the same name occurs after
-	 * blk_cleanup_queue() has called bdi_destroy().
-	 */
-	if (sdev->is_visible)
-		device_del(dev);
-	else
-		put_device(&sdev->sdev_dev);
-
 	if (sdev->host->hostt->slave_destroy)
 		sdev->host->hostt->slave_destroy(sdev);
 	transport_destroy_device(dev);
diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index 30d26e345dcc..80520e2f0fa2 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -341,6 +341,22 @@ static int do_sas_phy_delete(struct device *dev, void *data)
 }
 
 /**
+ * is_sas_attached - check if device is SAS attached
+ * @sdev: scsi device to check
+ *
+ * returns true if the device is SAS attached
+ */
+int is_sas_attached(struct scsi_device *sdev)
+{
+	struct Scsi_Host *shost = sdev->host;
+
+	return shost->transportt->host_attrs.ac.class ==
+		&sas_host_class.class;
+}
+EXPORT_SYMBOL(is_sas_attached);
+
+
+/**
  * sas_remove_children  -  tear down a devices SAS data structures
  * @dev:	device belonging to the sas object
  *
@@ -367,6 +383,20 @@ void sas_remove_host(struct Scsi_Host *shost)
 EXPORT_SYMBOL(sas_remove_host);
 
 /**
+ * sas_get_address - return the SAS address of the device
+ * @sdev: scsi device
+ *
+ * Returns the SAS address of the scsi device
+ */
+u64 sas_get_address(struct scsi_device *sdev)
+{
+	struct sas_end_device *rdev = sas_sdev_to_rdev(sdev);
+
+	return rdev->rphy.identify.sas_address;
+}
+EXPORT_SYMBOL(sas_get_address);
+
+/**
  * sas_tlr_supported - checking TLR bit in vpd 0x90
  * @sdev: scsi device struct
  *
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 54519804c46a..3d22fc3e3c1a 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -638,11 +638,24 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 	unsigned int max_blocks = 0;
 
 	q->limits.discard_zeroes_data = 0;
-	q->limits.discard_alignment = sdkp->unmap_alignment *
-		logical_block_size;
-	q->limits.discard_granularity =
-		max(sdkp->physical_block_size,
-		    sdkp->unmap_granularity * logical_block_size);
+
+	/*
+	 * When LBPRZ is reported, discard alignment and granularity
+	 * must be fixed to the logical block size. Otherwise the block
+	 * layer will drop misaligned portions of the request which can
+	 * lead to data corruption. If LBPRZ is not set, we honor the
+	 * device preference.
+	 */
+	if (sdkp->lbprz) {
+		q->limits.discard_alignment = 0;
+		q->limits.discard_granularity = 1;
+	} else {
+		q->limits.discard_alignment = sdkp->unmap_alignment *
+			logical_block_size;
+		q->limits.discard_granularity =
+			max(sdkp->physical_block_size,
+			    sdkp->unmap_granularity * logical_block_size);
+	}
 
 	sdkp->provisioning_mode = mode;
 
@@ -2321,11 +2334,8 @@ got_data:
 		}
 	}
 
-	if (sdkp->capacity > 0xffffffff) {
+	if (sdkp->capacity > 0xffffffff)
 		sdp->use_16_for_rw = 1;
-		sdkp->max_xfer_blocks = SD_MAX_XFER_BLOCKS;
-	} else
-		sdkp->max_xfer_blocks = SD_DEF_XFER_BLOCKS;
 
 	/* Rescale capacity to 512-byte units */
 	if (sector_size == 4096)
@@ -2642,7 +2652,6 @@ static void sd_read_block_limits(struct scsi_disk *sdkp)
 {
 	unsigned int sector_sz = sdkp->device->sector_size;
 	const int vpd_len = 64;
-	u32 max_xfer_length;
 	unsigned char *buffer = kmalloc(vpd_len, GFP_KERNEL);
 
 	if (!buffer ||
@@ -2650,14 +2659,11 @@ static void sd_read_block_limits(struct scsi_disk *sdkp)
 	    scsi_get_vpd_page(sdkp->device, 0xb0, buffer, vpd_len))
 		goto out;
 
-	max_xfer_length = get_unaligned_be32(&buffer[8]);
-	if (max_xfer_length)
-		sdkp->max_xfer_blocks = max_xfer_length;
-
 	blk_queue_io_min(sdkp->disk->queue,
 			 get_unaligned_be16(&buffer[6]) * sector_sz);
-	blk_queue_io_opt(sdkp->disk->queue,
-			 get_unaligned_be32(&buffer[12]) * sector_sz);
+
+	sdkp->max_xfer_blocks = get_unaligned_be32(&buffer[8]);
+	sdkp->opt_xfer_blocks = get_unaligned_be32(&buffer[12]);
 
 	if (buffer[3] == 0x3c) {
 		unsigned int lba_count, desc_count;
@@ -2806,6 +2812,11 @@ static int sd_try_extended_inquiry(struct scsi_device *sdp)
 	return 0;
 }
 
+static inline u32 logical_to_sectors(struct scsi_device *sdev, u32 blocks)
+{
+	return blocks << (ilog2(sdev->sector_size) - 9);
+}
+
 /**
  *	sd_revalidate_disk - called the first time a new disk is seen,
  *	performs disk spin up, read_capacity, etc.
@@ -2815,8 +2826,9 @@ static int sd_revalidate_disk(struct gendisk *disk)
 {
 	struct scsi_disk *sdkp = scsi_disk(disk);
 	struct scsi_device *sdp = sdkp->device;
+	struct request_queue *q = sdkp->disk->queue;
 	unsigned char *buffer;
-	unsigned int max_xfer;
+	unsigned int dev_max, rw_max;
 
 	SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp,
 				      "sd_revalidate_disk\n"));
@@ -2864,11 +2876,26 @@ static int sd_revalidate_disk(struct gendisk *disk)
 	 */
 	sd_set_flush_flag(sdkp);
 
-	max_xfer = sdkp->max_xfer_blocks;
-	max_xfer <<= ilog2(sdp->sector_size) - 9;
+	/* Initial block count limit based on CDB TRANSFER LENGTH field size. */
+	dev_max = sdp->use_16_for_rw ? SD_MAX_XFER_BLOCKS : SD_DEF_XFER_BLOCKS;
+
+	/* Some devices report a maximum block count for READ/WRITE requests. */
+	dev_max = min_not_zero(dev_max, sdkp->max_xfer_blocks);
+	q->limits.max_dev_sectors = logical_to_sectors(sdp, dev_max);
+
+	/*
+	 * Use the device's preferred I/O size for reads and writes
+	 * unless the reported value is unreasonably large (or garbage).
+	 */
+	if (sdkp->opt_xfer_blocks && sdkp->opt_xfer_blocks <= dev_max &&
+	    sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS)
+		rw_max = q->limits.io_opt =
+			logical_to_sectors(sdp, sdkp->opt_xfer_blocks);
+	else
+		rw_max = BLK_DEF_MAX_SECTORS;
 
-	sdkp->disk->queue->limits.max_sectors =
-		min_not_zero(queue_max_hw_sectors(sdkp->disk->queue), max_xfer);
+	/* Combine with controller limits */
+	q->limits.max_sectors = min(rw_max, queue_max_hw_sectors(q));
 
 	set_capacity(disk, sdkp->capacity);
 	sd_config_write_same(sdkp);
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 63ba5ca7f9a1..5f2a84aff29f 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -67,6 +67,7 @@ struct scsi_disk {
 	atomic_t	openers;
 	sector_t	capacity;	/* size in 512-byte sectors */
 	u32		max_xfer_blocks;
+	u32		opt_xfer_blocks;
 	u32		max_ws_blocks;
 	u32		max_unmap_blocks;
 	u32		unmap_granularity;
diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c
index e234da78ce6e..53ef1cb6418e 100644
--- a/drivers/scsi/ses.c
+++ b/drivers/scsi/ses.c
@@ -34,6 +34,8 @@
 #include <scsi/scsi_driver.h>
 #include <scsi/scsi_host.h>
 
+#include <scsi/scsi_transport_sas.h>
+
 struct ses_device {
 	unsigned char *page1;
 	unsigned char *page1_types;
@@ -84,6 +86,7 @@ static void init_device_slot_control(unsigned char *dest_desc,
 static int ses_recv_diag(struct scsi_device *sdev, int page_code,
 			 void *buf, int bufflen)
 {
+	int ret;
 	unsigned char cmd[] = {
 		RECEIVE_DIAGNOSTIC,
 		1,		/* Set PCV bit */
@@ -92,9 +95,26 @@ static int ses_recv_diag(struct scsi_device *sdev, int page_code,
 		bufflen & 0xff,
 		0
 	};
+	unsigned char recv_page_code;
 
-	return scsi_execute_req(sdev, cmd, DMA_FROM_DEVICE, buf, bufflen,
+	ret =  scsi_execute_req(sdev, cmd, DMA_FROM_DEVICE, buf, bufflen,
 				NULL, SES_TIMEOUT, SES_RETRIES, NULL);
+	if (unlikely(!ret))
+		return ret;
+
+	recv_page_code = ((unsigned char *)buf)[0];
+
+	if (likely(recv_page_code == page_code))
+		return ret;
+
+	/* successful diagnostic but wrong page code.  This happens to some
+	 * USB devices, just print a message and pretend there was an error */
+
+	sdev_printk(KERN_ERR, sdev,
+		    "Wrong diagnostic page; asked for %d got %u\n",
+		    page_code, recv_page_code);
+
+	return -EINVAL;
 }
 
 static int ses_send_diag(struct scsi_device *sdev, int page_code,
@@ -541,7 +561,15 @@ static void ses_enclosure_data_process(struct enclosure_device *edev,
 			if (desc_ptr)
 				desc_ptr += len;
 
-			if (addl_desc_ptr)
+			if (addl_desc_ptr &&
+			    /* only find additional descriptions for specific devices */
+			    (type_ptr[0] == ENCLOSURE_COMPONENT_DEVICE ||
+			     type_ptr[0] == ENCLOSURE_COMPONENT_ARRAY_DEVICE ||
+			     type_ptr[0] == ENCLOSURE_COMPONENT_SAS_EXPANDER ||
+			     /* these elements are optional */
+			     type_ptr[0] == ENCLOSURE_COMPONENT_SCSI_TARGET_PORT ||
+			     type_ptr[0] == ENCLOSURE_COMPONENT_SCSI_INITIATOR_PORT ||
+			     type_ptr[0] == ENCLOSURE_COMPONENT_CONTROLLER_ELECTRONICS))
 				addl_desc_ptr += addl_desc_ptr[1] + 2;
 
 		}
@@ -553,37 +581,15 @@ static void ses_enclosure_data_process(struct enclosure_device *edev,
 static void ses_match_to_enclosure(struct enclosure_device *edev,
 				   struct scsi_device *sdev)
 {
-	unsigned char *desc;
-	unsigned char __rcu *vpd_pg83;
 	struct efd efd = {
 		.addr = 0,
 	};
 
 	ses_enclosure_data_process(edev, to_scsi_device(edev->edev.parent), 0);
 
-	rcu_read_lock();
-	vpd_pg83 = rcu_dereference(sdev->vpd_pg83);
-	if (!vpd_pg83) {
-		rcu_read_unlock();
-		return;
-	}
-
-	desc = vpd_pg83 + 4;
-	while (desc < vpd_pg83 + sdev->vpd_pg83_len) {
-		enum scsi_protocol proto = desc[0] >> 4;
-		u8 code_set = desc[0] & 0x0f;
-		u8 piv = desc[1] & 0x80;
-		u8 assoc = (desc[1] & 0x30) >> 4;
-		u8 type = desc[1] & 0x0f;
-		u8 len = desc[3];
-
-		if (piv && code_set == 1 && assoc == 1
-		    && proto == SCSI_PROTOCOL_SAS && type == 3 && len == 8)
-			efd.addr = get_unaligned_be64(&desc[4]);
+	if (is_sas_attached(sdev))
+		efd.addr = sas_get_address(sdev);
 
-		desc += len + 4;
-	}
-	rcu_read_unlock();
 	if (efd.addr) {
 		efd.dev = &sdev->sdev_gendev;
 
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index e0a1e52a04e7..2e522951b619 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -4083,6 +4083,7 @@ static int create_one_cdev(struct scsi_tape *tape, int mode, int rew)
 	}
 	cdev->owner = THIS_MODULE;
 	cdev->ops = &st_fops;
+	STm->cdevs[rew] = cdev;
 
 	error = cdev_add(cdev, cdev_devno, 1);
 	if (error) {
@@ -4091,7 +4092,6 @@ static int create_one_cdev(struct scsi_tape *tape, int mode, int rew)
 		pr_err("st%d: Device not attached.\n", dev_num);
 		goto out_free;
 	}
-	STm->cdevs[rew] = cdev;
 
 	i = mode << (4 - ST_NBR_MODE_BITS);
 	snprintf(name, 10, "%s%s%s", rew ? "n" : "",
@@ -4110,8 +4110,9 @@ static int create_one_cdev(struct scsi_tape *tape, int mode, int rew)
 	return 0;
 out_free:
 	cdev_del(STm->cdevs[rew]);
-	STm->cdevs[rew] = NULL;
 out:
+	STm->cdevs[rew] = NULL;
+	STm->devs[rew] = NULL;
 	return error;
 }
 
diff --git a/drivers/sh/pm_runtime.c b/drivers/sh/pm_runtime.c
index 25abd4eb7d10..91a003011acf 100644
--- a/drivers/sh/pm_runtime.c
+++ b/drivers/sh/pm_runtime.c
@@ -34,7 +34,7 @@ static struct pm_clk_notifier_block platform_bus_notifier = {
 
 static int __init sh_pm_runtime_init(void)
 {
-	if (IS_ENABLED(CONFIG_ARCH_SHMOBILE_MULTI)) {
+	if (IS_ENABLED(CONFIG_ARCH_SHMOBILE)) {
 		if (!of_find_compatible_node(NULL, NULL,
 					     "renesas,cpg-mstp-clocks"))
 			return 0;
diff --git a/drivers/soc/mediatek/Kconfig b/drivers/soc/mediatek/Kconfig
index 9d5068248aa0..0a4ea809a61b 100644
--- a/drivers/soc/mediatek/Kconfig
+++ b/drivers/soc/mediatek/Kconfig
@@ -23,6 +23,7 @@ config MTK_PMIC_WRAP
 config MTK_SCPSYS
 	bool "MediaTek SCPSYS Support"
 	depends on ARCH_MEDIATEK || COMPILE_TEST
+	default ARM64 && ARCH_MEDIATEK
 	select REGMAP
 	select MTK_INFRACFG
 	select PM_GENERIC_DOMAINS if PM
diff --git a/drivers/soc/ti/knav_qmss_queue.c b/drivers/soc/ti/knav_qmss_queue.c
index f3a0b6a4b54e..8c03a80b482d 100644
--- a/drivers/soc/ti/knav_qmss_queue.c
+++ b/drivers/soc/ti/knav_qmss_queue.c
@@ -1179,7 +1179,7 @@ static int knav_queue_setup_link_ram(struct knav_device *kdev)
 
 		block++;
 		if (!block->size)
-			return 0;
+			continue;
 
 		dev_dbg(kdev->dev, "linkram1: phys:%x, virt:%p, size:%x\n",
 			block->phys, block->virt, block->size);
@@ -1519,9 +1519,9 @@ static int knav_queue_load_pdsp(struct knav_device *kdev,
 
 	for (i = 0; i < ARRAY_SIZE(knav_acc_firmwares); i++) {
 		if (knav_acc_firmwares[i]) {
-			ret = request_firmware(&fw,
-					       knav_acc_firmwares[i],
-					       kdev->dev);
+			ret = request_firmware_direct(&fw,
+						      knav_acc_firmwares[i],
+						      kdev->dev);
 			if (!ret) {
 				found = true;
 				break;
diff --git a/drivers/spi/spi-bcm63xx.c b/drivers/spi/spi-bcm63xx.c
index 06858e04ec59..bf9a610e5b89 100644
--- a/drivers/spi/spi-bcm63xx.c
+++ b/drivers/spi/spi-bcm63xx.c
@@ -562,8 +562,8 @@ static int bcm63xx_spi_probe(struct platform_device *pdev)
 		goto out_clk_disable;
 	}
 
-	dev_info(dev, "at 0x%08x (irq %d, FIFOs size %d)\n",
-		 r->start, irq, bs->fifo_size);
+	dev_info(dev, "at %pr (irq %d, FIFOs size %d)\n",
+		 r, irq, bs->fifo_size);
 
 	return 0;
 
diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c
index 563954a61424..7840067062a8 100644
--- a/drivers/spi/spi-mt65xx.c
+++ b/drivers/spi/spi-mt65xx.c
@@ -410,7 +410,7 @@ static int mtk_spi_setup(struct spi_device *spi)
 	if (!spi->controller_data)
 		spi->controller_data = (void *)&mtk_default_chip_info;
 
-	if (mdata->dev_comp->need_pad_sel)
+	if (mdata->dev_comp->need_pad_sel && gpio_is_valid(spi->cs_gpio))
 		gpio_direction_output(spi->cs_gpio, !(spi->mode & SPI_CS_HIGH));
 
 	return 0;
@@ -632,13 +632,23 @@ static int mtk_spi_probe(struct platform_device *pdev)
 			goto err_put_master;
 		}
 
-		for (i = 0; i < master->num_chipselect; i++) {
-			ret = devm_gpio_request(&pdev->dev, master->cs_gpios[i],
-						dev_name(&pdev->dev));
-			if (ret) {
-				dev_err(&pdev->dev,
-					"can't get CS GPIO %i\n", i);
-				goto err_put_master;
+		if (!master->cs_gpios && master->num_chipselect > 1) {
+			dev_err(&pdev->dev,
+				"cs_gpios not specified and num_chipselect > 1\n");
+			ret = -EINVAL;
+			goto err_put_master;
+		}
+
+		if (master->cs_gpios) {
+			for (i = 0; i < master->num_chipselect; i++) {
+				ret = devm_gpio_request(&pdev->dev,
+							master->cs_gpios[i],
+							dev_name(&pdev->dev));
+				if (ret) {
+					dev_err(&pdev->dev,
+						"can't get CS GPIO %i\n", i);
+					goto err_put_master;
+				}
 			}
 		}
 	}
diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index 94af80676684..5e5fd77e2711 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -1171,19 +1171,31 @@ err_no_rxchan:
 static int pl022_dma_autoprobe(struct pl022 *pl022)
 {
 	struct device *dev = &pl022->adev->dev;
+	struct dma_chan *chan;
+	int err;
 
 	/* automatically configure DMA channels from platform, normally using DT */
-	pl022->dma_rx_channel = dma_request_slave_channel(dev, "rx");
-	if (!pl022->dma_rx_channel)
+	chan = dma_request_slave_channel_reason(dev, "rx");
+	if (IS_ERR(chan)) {
+		err = PTR_ERR(chan);
 		goto err_no_rxchan;
+	}
+
+	pl022->dma_rx_channel = chan;
 
-	pl022->dma_tx_channel = dma_request_slave_channel(dev, "tx");
-	if (!pl022->dma_tx_channel)
+	chan = dma_request_slave_channel_reason(dev, "tx");
+	if (IS_ERR(chan)) {
+		err = PTR_ERR(chan);
 		goto err_no_txchan;
+	}
+
+	pl022->dma_tx_channel = chan;
 
 	pl022->dummypage = kmalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!pl022->dummypage)
+	if (!pl022->dummypage) {
+		err = -ENOMEM;
 		goto err_no_dummypage;
+	}
 
 	return 0;
 
@@ -1194,7 +1206,7 @@ err_no_txchan:
 	dma_release_channel(pl022->dma_rx_channel);
 	pl022->dma_rx_channel = NULL;
 err_no_rxchan:
-	return -ENODEV;
+	return err;
 }
 		
 static void terminate_dma(struct pl022 *pl022)
@@ -2236,6 +2248,10 @@ static int pl022_probe(struct amba_device *adev, const struct amba_id *id)
 
 	/* Get DMA channels, try autoconfiguration first */
 	status = pl022_dma_autoprobe(pl022);
+	if (status == -EPROBE_DEFER) {
+		dev_dbg(dev, "deferring probe to get DMA channel\n");
+		goto err_no_irq;
+	}
 
 	/* If that failed, use channels from platform_info */
 	if (status == 0)
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index e2415be209d5..2b0a8ec3affb 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -376,6 +376,7 @@ static void spi_drv_shutdown(struct device *dev)
 
 /**
  * __spi_register_driver - register a SPI driver
+ * @owner: owner module of the driver to register
  * @sdrv: the driver to register
  * Context: can sleep
  *
@@ -2130,6 +2131,7 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message)
 	 * Set transfer tx_nbits and rx_nbits as single transfer default
 	 * (SPI_NBITS_SINGLE) if it is not set for this transfer.
 	 */
+	message->frame_length = 0;
 	list_for_each_entry(xfer, &message->transfers, transfer_list) {
 		message->frame_length += xfer->len;
 		if (!xfer->bits_per_word)
diff --git a/drivers/staging/iio/Kconfig b/drivers/staging/iio/Kconfig
index 6d5b38d69578..9d7f0004d2d7 100644
--- a/drivers/staging/iio/Kconfig
+++ b/drivers/staging/iio/Kconfig
@@ -18,7 +18,8 @@ source "drivers/staging/iio/resolver/Kconfig"
 source "drivers/staging/iio/trigger/Kconfig"
 
 config IIO_DUMMY_EVGEN
-       tristate
+	tristate
+	select IRQ_WORK
 
 config IIO_SIMPLE_DUMMY
        tristate "An example driver with no hardware requirements"
diff --git a/drivers/staging/iio/adc/lpc32xx_adc.c b/drivers/staging/iio/adc/lpc32xx_adc.c
index d11c54b72186..b51f237cd817 100644
--- a/drivers/staging/iio/adc/lpc32xx_adc.c
+++ b/drivers/staging/iio/adc/lpc32xx_adc.c
@@ -76,7 +76,7 @@ static int lpc32xx_read_raw(struct iio_dev *indio_dev,
 
 	if (mask == IIO_CHAN_INFO_RAW) {
 		mutex_lock(&indio_dev->mlock);
-		clk_enable(info->clk);
+		clk_prepare_enable(info->clk);
 		/* Measurement setup */
 		__raw_writel(AD_INTERNAL | (chan->address) | AD_REFp | AD_REFm,
 			     LPC32XX_ADC_SELECT(info->adc_base));
@@ -84,7 +84,7 @@ static int lpc32xx_read_raw(struct iio_dev *indio_dev,
 		__raw_writel(AD_PDN_CTRL | AD_STROBE,
 			     LPC32XX_ADC_CTRL(info->adc_base));
 		wait_for_completion(&info->completion); /* set by ISR */
-		clk_disable(info->clk);
+		clk_disable_unprepare(info->clk);
 		*val = info->value;
 		mutex_unlock(&indio_dev->mlock);
 
diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_ioctl.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_ioctl.h
index f5d741f25ffd..485ab2670918 100644
--- a/drivers/staging/lustre/include/linux/libcfs/libcfs_ioctl.h
+++ b/drivers/staging/lustre/include/linux/libcfs/libcfs_ioctl.h
@@ -110,7 +110,6 @@ struct libcfs_ioctl_handler {
 #define IOC_LIBCFS_CLEAR_DEBUG	     _IOWR('e', 31, long)
 #define IOC_LIBCFS_MARK_DEBUG	      _IOWR('e', 32, long)
 #define IOC_LIBCFS_MEMHOG		  _IOWR('e', 36, long)
-#define IOC_LIBCFS_PING_TEST	       _IOWR('e', 37, long)
 /* lnet ioctls */
 #define IOC_LIBCFS_GET_NI		  _IOWR('e', 50, long)
 #define IOC_LIBCFS_FAIL_NID		_IOWR('e', 51, long)
diff --git a/drivers/staging/lustre/lustre/libcfs/module.c b/drivers/staging/lustre/lustre/libcfs/module.c
index 07a68594c279..e7c2b26156b9 100644
--- a/drivers/staging/lustre/lustre/libcfs/module.c
+++ b/drivers/staging/lustre/lustre/libcfs/module.c
@@ -274,23 +274,6 @@ static int libcfs_ioctl_int(struct cfs_psdev_file *pfile, unsigned long cmd,
 		}
 		break;
 
-	case IOC_LIBCFS_PING_TEST: {
-		extern void (kping_client)(struct libcfs_ioctl_data *);
-		void (*ping)(struct libcfs_ioctl_data *);
-
-		CDEBUG(D_IOCTL, "doing %d pings to nid %s (%s)\n",
-		       data->ioc_count, libcfs_nid2str(data->ioc_nid),
-		       libcfs_nid2str(data->ioc_nid));
-		ping = symbol_get(kping_client);
-		if (!ping)
-			CERROR("symbol_get failed\n");
-		else {
-			ping(data);
-			symbol_put(kping_client);
-		}
-		return 0;
-	}
-
 	default: {
 		struct libcfs_ioctl_handler *hand;
 
diff --git a/drivers/staging/wilc1000/coreconfigurator.c b/drivers/staging/wilc1000/coreconfigurator.c
index e10c6ffa698a..9568bdb6319b 100644
--- a/drivers/staging/wilc1000/coreconfigurator.c
+++ b/drivers/staging/wilc1000/coreconfigurator.c
@@ -13,12 +13,8 @@
 #include "wilc_wlan.h"
 #include <linux/errno.h>
 #include <linux/slab.h>
-#include <linux/etherdevice.h>
 #define TAG_PARAM_OFFSET	(MAC_HDR_LEN + TIME_STAMP_LEN + \
 							BEACON_INTERVAL_LEN + CAP_INFO_LEN)
-#define ADDR1 4
-#define ADDR2 10
-#define ADDR3 16
 
 /* Basic Frame Type Codes (2-bit) */
 enum basic_frame_type {
@@ -175,32 +171,38 @@ static inline u8 get_from_ds(u8 *header)
 	return ((header[1] & 0x02) >> 1);
 }
 
+/* This function extracts the MAC Address in 'address1' field of the MAC     */
+/* header and updates the MAC Address in the allocated 'addr' variable.      */
+static inline void get_address1(u8 *pu8msa, u8 *addr)
+{
+	memcpy(addr, pu8msa + 4, 6);
+}
+
+/* This function extracts the MAC Address in 'address2' field of the MAC     */
+/* header and updates the MAC Address in the allocated 'addr' variable.      */
+static inline void get_address2(u8 *pu8msa, u8 *addr)
+{
+	memcpy(addr, pu8msa + 10, 6);
+}
+
+/* This function extracts the MAC Address in 'address3' field of the MAC     */
+/* header and updates the MAC Address in the allocated 'addr' variable.      */
+static inline void get_address3(u8 *pu8msa, u8 *addr)
+{
+	memcpy(addr, pu8msa + 16, 6);
+}
+
 /* This function extracts the BSSID from the incoming WLAN packet based on   */
-/* the 'from ds' bit, and updates the MAC Address in the allocated 'data'    */
+/* the 'from ds' bit, and updates the MAC Address in the allocated 'addr'    */
 /* variable.                                                                 */
 static inline void get_BSSID(u8 *data, u8 *bssid)
 {
 	if (get_from_ds(data) == 1)
-		/*
-		 * Extract the MAC Address in 'address2' field of the MAC
-		 * header and update the MAC Address in the allocated 'data'
-		 *  variable.
-		 */
-		ether_addr_copy(data, bssid + ADDR2);
+		get_address2(data, bssid);
 	else if (get_to_ds(data) == 1)
-		/*
-		 * Extract the MAC Address in 'address1' field of the MAC
-		 * header and update the MAC Address in the allocated 'data'
-		 * variable.
-		 */
-		ether_addr_copy(data, bssid + ADDR1);
+		get_address1(data, bssid);
 	else
-		/*
-		 * Extract the MAC Address in 'address3' field of the MAC
-		 * header and update the MAC Address in the allocated 'data'
-		 * variable.
-		 */
-		ether_addr_copy(data, bssid + ADDR3);
+		get_address3(data, bssid);
 }
 
 /* This function extracts the SSID from a beacon/probe response frame        */
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 342a07c58d89..72204fbf2bb1 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -4074,6 +4074,17 @@ reject:
 	return iscsit_add_reject(conn, ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf);
 }
 
+static bool iscsi_target_check_conn_state(struct iscsi_conn *conn)
+{
+	bool ret;
+
+	spin_lock_bh(&conn->state_lock);
+	ret = (conn->conn_state != TARG_CONN_STATE_LOGGED_IN);
+	spin_unlock_bh(&conn->state_lock);
+
+	return ret;
+}
+
 int iscsi_target_rx_thread(void *arg)
 {
 	int ret, rc;
@@ -4091,7 +4102,7 @@ int iscsi_target_rx_thread(void *arg)
 	 * incoming iscsi/tcp socket I/O, and/or failing the connection.
 	 */
 	rc = wait_for_completion_interruptible(&conn->rx_login_comp);
-	if (rc < 0)
+	if (rc < 0 || iscsi_target_check_conn_state(conn))
 		return 0;
 
 	if (conn->conn_transport->transport_type == ISCSI_INFINIBAND) {
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index 5c964c09c89f..9fc9117d0f22 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -388,6 +388,7 @@ err:
 	if (login->login_complete) {
 		if (conn->rx_thread && conn->rx_thread_active) {
 			send_sig(SIGINT, conn->rx_thread, 1);
+			complete(&conn->rx_login_comp);
 			kthread_stop(conn->rx_thread);
 		}
 		if (conn->tx_thread && conn->tx_thread_active) {
diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c
index 51d1734d5390..2cbea2af7cd0 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.c
+++ b/drivers/target/iscsi/iscsi_target_parameters.c
@@ -208,7 +208,7 @@ int iscsi_create_default_params(struct iscsi_param_list **param_list_ptr)
 	if (!pl) {
 		pr_err("Unable to allocate memory for"
 				" struct iscsi_param_list.\n");
-		return -1 ;
+		return -ENOMEM;
 	}
 	INIT_LIST_HEAD(&pl->param_list);
 	INIT_LIST_HEAD(&pl->extra_response_list);
@@ -578,7 +578,7 @@ int iscsi_copy_param_list(
 	param_list = kzalloc(sizeof(struct iscsi_param_list), GFP_KERNEL);
 	if (!param_list) {
 		pr_err("Unable to allocate memory for struct iscsi_param_list.\n");
-		return -1;
+		return -ENOMEM;
 	}
 	INIT_LIST_HEAD(&param_list->param_list);
 	INIT_LIST_HEAD(&param_list->extra_response_list);
@@ -629,7 +629,7 @@ int iscsi_copy_param_list(
 
 err_out:
 	iscsi_release_param_list(param_list);
-	return -1;
+	return -ENOMEM;
 }
 
 static void iscsi_release_extra_responses(struct iscsi_param_list *param_list)
@@ -729,7 +729,7 @@ static int iscsi_add_notunderstood_response(
 	if (!extra_response) {
 		pr_err("Unable to allocate memory for"
 			" struct iscsi_extra_response.\n");
-		return -1;
+		return -ENOMEM;
 	}
 	INIT_LIST_HEAD(&extra_response->er_list);
 
@@ -1370,7 +1370,7 @@ int iscsi_decode_text_input(
 	tmpbuf = kzalloc(length + 1, GFP_KERNEL);
 	if (!tmpbuf) {
 		pr_err("Unable to allocate %u + 1 bytes for tmpbuf.\n", length);
-		return -1;
+		return -ENOMEM;
 	}
 
 	memcpy(tmpbuf, textbuf, length);
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 0b4b2a67d9f9..98698d875742 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -371,7 +371,8 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *o
 	return 0;
 }
 
-static sense_reason_t xdreadwrite_callback(struct se_cmd *cmd, bool success)
+static sense_reason_t xdreadwrite_callback(struct se_cmd *cmd, bool success,
+					   int *post_ret)
 {
 	unsigned char *buf, *addr;
 	struct scatterlist *sg;
@@ -437,7 +438,8 @@ sbc_execute_rw(struct se_cmd *cmd)
 			       cmd->data_direction);
 }
 
-static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success)
+static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success,
+					     int *post_ret)
 {
 	struct se_device *dev = cmd->se_dev;
 
@@ -447,8 +449,10 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success)
 	 * sent to the backend driver.
 	 */
 	spin_lock_irq(&cmd->t_state_lock);
-	if ((cmd->transport_state & CMD_T_SENT) && !cmd->scsi_status)
+	if ((cmd->transport_state & CMD_T_SENT) && !cmd->scsi_status) {
 		cmd->se_cmd_flags |= SCF_COMPARE_AND_WRITE_POST;
+		*post_ret = 1;
+	}
 	spin_unlock_irq(&cmd->t_state_lock);
 
 	/*
@@ -460,7 +464,8 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success)
 	return TCM_NO_SENSE;
 }
 
-static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool success)
+static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool success,
+						 int *post_ret)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct scatterlist *write_sg = NULL, *sg;
@@ -556,11 +561,11 @@ static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool succes
 
 		if (block_size < PAGE_SIZE) {
 			sg_set_page(&write_sg[i], m.page, block_size,
-				    block_size);
+				    m.piter.sg->offset + block_size);
 		} else {
 			sg_miter_next(&m);
 			sg_set_page(&write_sg[i], m.page, block_size,
-				    0);
+				    m.piter.sg->offset);
 		}
 		len -= block_size;
 		i++;
diff --git a/drivers/target/target_core_stat.c b/drivers/target/target_core_stat.c
index 273c72b2b83d..81a6b3e07687 100644
--- a/drivers/target/target_core_stat.c
+++ b/drivers/target/target_core_stat.c
@@ -246,7 +246,7 @@ static ssize_t target_stat_lu_prod_show(struct config_item *item, char *page)
 	char str[sizeof(dev->t10_wwn.model)+1];
 
 	/* scsiLuProductId */
-	for (i = 0; i < sizeof(dev->t10_wwn.vendor); i++)
+	for (i = 0; i < sizeof(dev->t10_wwn.model); i++)
 		str[i] = ISPRINT(dev->t10_wwn.model[i]) ?
 			dev->t10_wwn.model[i] : ' ';
 	str[i] = '\0';
diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index 5b2820312310..28fb3016370f 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -130,6 +130,9 @@ void core_tmr_abort_task(
 		if (tmr->ref_task_tag != ref_tag)
 			continue;
 
+		if (!kref_get_unless_zero(&se_cmd->cmd_kref))
+			continue;
+
 		printk("ABORT_TASK: Found referenced %s task_tag: %llu\n",
 			se_cmd->se_tfo->get_fabric_name(), ref_tag);
 
@@ -139,13 +142,15 @@ void core_tmr_abort_task(
 			       " skipping\n", ref_tag);
 			spin_unlock(&se_cmd->t_state_lock);
 			spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
+
+			target_put_sess_cmd(se_cmd);
+
 			goto out;
 		}
 		se_cmd->transport_state |= CMD_T_ABORTED;
 		spin_unlock(&se_cmd->t_state_lock);
 
 		list_del_init(&se_cmd->se_cmd_list);
-		kref_get(&se_cmd->cmd_kref);
 		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 
 		cancel_work_sync(&se_cmd->work);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 5bacc7b5ed6d..4fdcee2006d1 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -1658,7 +1658,7 @@ bool target_stop_cmd(struct se_cmd *cmd, unsigned long *flags)
 void transport_generic_request_failure(struct se_cmd *cmd,
 		sense_reason_t sense_reason)
 {
-	int ret = 0;
+	int ret = 0, post_ret = 0;
 
 	pr_debug("-----[ Storage Engine Exception for cmd: %p ITT: 0x%08llx"
 		" CDB: 0x%02x\n", cmd, cmd->tag, cmd->t_task_cdb[0]);
@@ -1680,7 +1680,7 @@ void transport_generic_request_failure(struct se_cmd *cmd,
 	 */
 	if ((cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) &&
 	     cmd->transport_complete_callback)
-		cmd->transport_complete_callback(cmd, false);
+		cmd->transport_complete_callback(cmd, false, &post_ret);
 
 	switch (sense_reason) {
 	case TCM_NON_EXISTENT_LUN:
@@ -2068,11 +2068,13 @@ static void target_complete_ok_work(struct work_struct *work)
 	 */
 	if (cmd->transport_complete_callback) {
 		sense_reason_t rc;
+		bool caw = (cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE);
+		bool zero_dl = !(cmd->data_length);
+		int post_ret = 0;
 
-		rc = cmd->transport_complete_callback(cmd, true);
-		if (!rc && !(cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE_POST)) {
-			if ((cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) &&
-			    !cmd->data_length)
+		rc = cmd->transport_complete_callback(cmd, true, &post_ret);
+		if (!rc && !post_ret) {
+			if (caw && zero_dl)
 				goto queue_rsp;
 
 			return;
@@ -2507,23 +2509,24 @@ out:
 EXPORT_SYMBOL(target_get_sess_cmd);
 
 static void target_release_cmd_kref(struct kref *kref)
-		__releases(&se_cmd->se_sess->sess_cmd_lock)
 {
 	struct se_cmd *se_cmd = container_of(kref, struct se_cmd, cmd_kref);
 	struct se_session *se_sess = se_cmd->se_sess;
+	unsigned long flags;
 
+	spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
 	if (list_empty(&se_cmd->se_cmd_list)) {
-		spin_unlock(&se_sess->sess_cmd_lock);
+		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 		se_cmd->se_tfo->release_cmd(se_cmd);
 		return;
 	}
 	if (se_sess->sess_tearing_down && se_cmd->cmd_wait_set) {
-		spin_unlock(&se_sess->sess_cmd_lock);
+		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 		complete(&se_cmd->cmd_wait_comp);
 		return;
 	}
 	list_del(&se_cmd->se_cmd_list);
-	spin_unlock(&se_sess->sess_cmd_lock);
+	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 
 	se_cmd->se_tfo->release_cmd(se_cmd);
 }
@@ -2539,8 +2542,7 @@ int target_put_sess_cmd(struct se_cmd *se_cmd)
 		se_cmd->se_tfo->release_cmd(se_cmd);
 		return 1;
 	}
-	return kref_put_spinlock_irqsave(&se_cmd->cmd_kref, target_release_cmd_kref,
-			&se_sess->sess_cmd_lock);
+	return kref_put(&se_cmd->cmd_kref, target_release_cmd_kref);
 }
 EXPORT_SYMBOL(target_put_sess_cmd);
 
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 937cebf76633..5e6d6cb348fc 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -638,7 +638,7 @@ static int tcmu_check_expired_cmd(int id, void *p, void *data)
 	if (test_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags))
 		return 0;
 
-	if (!time_after(cmd->deadline, jiffies))
+	if (!time_after(jiffies, cmd->deadline))
 		return 0;
 
 	set_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags);
@@ -1101,8 +1101,6 @@ tcmu_parse_cdb(struct se_cmd *cmd)
 
 static const struct target_backend_ops tcmu_ops = {
 	.name			= "user",
-	.inquiry_prod		= "USER",
-	.inquiry_rev		= TCMU_VERSION,
 	.owner			= THIS_MODULE,
 	.transport_flags	= TRANSPORT_FLAG_PASSTHROUGH,
 	.attach_hba		= tcmu_attach_hba,
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index c463c89b90ef..8cc4ac64a91c 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -382,7 +382,7 @@ endmenu
 
 config QCOM_SPMI_TEMP_ALARM
 	tristate "Qualcomm SPMI PMIC Temperature Alarm"
-	depends on OF && (SPMI || COMPILE_TEST) && IIO
+	depends on OF && SPMI && IIO
 	select REGMAP_SPMI
 	help
 	  This enables a thermal sysfs driver for Qualcomm plug-and-play (QPNP)
diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c
index c8fe3cac2e0e..c5547bd711db 100644
--- a/drivers/thermal/imx_thermal.c
+++ b/drivers/thermal/imx_thermal.c
@@ -55,6 +55,7 @@
 #define TEMPSENSE2_PANIC_VALUE_SHIFT	16
 #define TEMPSENSE2_PANIC_VALUE_MASK	0xfff0000
 
+#define OCOTP_MEM0			0x0480
 #define OCOTP_ANA1			0x04e0
 
 /* The driver supports 1 passive trip point and 1 critical trip point */
@@ -64,12 +65,6 @@ enum imx_thermal_trip {
 	IMX_TRIP_NUM,
 };
 
-/*
- * It defines the temperature in millicelsius for passive trip point
- * that will trigger cooling action when crossed.
- */
-#define IMX_TEMP_PASSIVE		85000
-
 #define IMX_POLLING_DELAY		2000 /* millisecond */
 #define IMX_PASSIVE_DELAY		1000
 
@@ -100,12 +95,14 @@ struct imx_thermal_data {
 	u32 c1, c2; /* See formula in imx_get_sensor_data() */
 	int temp_passive;
 	int temp_critical;
+	int temp_max;
 	int alarm_temp;
 	int last_temp;
 	bool irq_enabled;
 	int irq;
 	struct clk *thermal_clk;
 	const struct thermal_soc_data *socdata;
+	const char *temp_grade;
 };
 
 static void imx_set_panic_temp(struct imx_thermal_data *data,
@@ -285,10 +282,12 @@ static int imx_set_trip_temp(struct thermal_zone_device *tz, int trip,
 {
 	struct imx_thermal_data *data = tz->devdata;
 
+	/* do not allow changing critical threshold */
 	if (trip == IMX_TRIP_CRITICAL)
 		return -EPERM;
 
-	if (temp < 0 || temp > IMX_TEMP_PASSIVE)
+	/* do not allow passive to be set higher than critical */
+	if (temp < 0 || temp > data->temp_critical)
 		return -EINVAL;
 
 	data->temp_passive = temp;
@@ -404,17 +403,39 @@ static int imx_get_sensor_data(struct platform_device *pdev)
 	data->c1 = temp64;
 	data->c2 = n1 * data->c1 + 1000 * t1;
 
-	/*
-	 * Set the default passive cooling trip point,
-	 * can be changed from userspace.
-	 */
-	data->temp_passive = IMX_TEMP_PASSIVE;
+	/* use OTP for thermal grade */
+	ret = regmap_read(map, OCOTP_MEM0, &val);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to read temp grade: %d\n", ret);
+		return ret;
+	}
+
+	/* The maximum die temp is specified by the Temperature Grade */
+	switch ((val >> 6) & 0x3) {
+	case 0: /* Commercial (0 to 95C) */
+		data->temp_grade = "Commercial";
+		data->temp_max = 95000;
+		break;
+	case 1: /* Extended Commercial (-20 to 105C) */
+		data->temp_grade = "Extended Commercial";
+		data->temp_max = 105000;
+		break;
+	case 2: /* Industrial (-40 to 105C) */
+		data->temp_grade = "Industrial";
+		data->temp_max = 105000;
+		break;
+	case 3: /* Automotive (-40 to 125C) */
+		data->temp_grade = "Automotive";
+		data->temp_max = 125000;
+		break;
+	}
 
 	/*
-	 * The maximum die temperature set to 20 C higher than
-	 * IMX_TEMP_PASSIVE.
+	 * Set the critical trip point at 5C under max
+	 * Set the passive trip point at 10C under max (can change via sysfs)
 	 */
-	data->temp_critical = 1000 * 20 + data->temp_passive;
+	data->temp_critical = data->temp_max - (1000 * 5);
+	data->temp_passive = data->temp_max - (1000 * 10);
 
 	return 0;
 }
@@ -551,6 +572,11 @@ static int imx_thermal_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	dev_info(&pdev->dev, "%s CPU temperature grade - max:%dC"
+		 " critical:%dC passive:%dC\n", data->temp_grade,
+		 data->temp_max / 1000, data->temp_critical / 1000,
+		 data->temp_passive / 1000);
+
 	/* Enable measurements at ~ 10 Hz */
 	regmap_write(map, TEMPSENSE1 + REG_CLR, TEMPSENSE1_MEASURE_FREQ);
 	measure_freq = DIV_ROUND_UP(32768, 10); /* 10 Hz */
diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c
index 42b7d4253b94..be4eedcb839a 100644
--- a/drivers/thermal/of-thermal.c
+++ b/drivers/thermal/of-thermal.c
@@ -964,7 +964,7 @@ void of_thermal_destroy_zones(void)
 
 	np = of_find_node_by_name(NULL, "thermal-zones");
 	if (!np) {
-		pr_err("unable to find thermal zones\n");
+		pr_debug("unable to find thermal zones\n");
 		return;
 	}
 
diff --git a/drivers/thermal/power_allocator.c b/drivers/thermal/power_allocator.c
index f0fbea386869..1246aa6fcab0 100644
--- a/drivers/thermal/power_allocator.c
+++ b/drivers/thermal/power_allocator.c
@@ -174,7 +174,6 @@ static void estimate_pid_constants(struct thermal_zone_device *tz,
 /**
  * pid_controller() - PID controller
  * @tz:	thermal zone we are operating in
- * @current_temp:	the current temperature in millicelsius
  * @control_temp:	the target temperature in millicelsius
  * @max_allocatable_power:	maximum allocatable power for this thermal zone
  *
@@ -191,7 +190,6 @@ static void estimate_pid_constants(struct thermal_zone_device *tz,
  * Return: The power budget for the next period.
  */
 static u32 pid_controller(struct thermal_zone_device *tz,
-			  int current_temp,
 			  int control_temp,
 			  u32 max_allocatable_power)
 {
@@ -211,7 +209,7 @@ static u32 pid_controller(struct thermal_zone_device *tz,
 				       true);
 	}
 
-	err = control_temp - current_temp;
+	err = control_temp - tz->temperature;
 	err = int_to_frac(err);
 
 	/* Calculate the proportional term */
@@ -332,7 +330,6 @@ static void divvy_up_power(u32 *req_power, u32 *max_power, int num_actors,
 }
 
 static int allocate_power(struct thermal_zone_device *tz,
-			  int current_temp,
 			  int control_temp)
 {
 	struct thermal_instance *instance;
@@ -418,8 +415,7 @@ static int allocate_power(struct thermal_zone_device *tz,
 		i++;
 	}
 
-	power_range = pid_controller(tz, current_temp, control_temp,
-				     max_allocatable_power);
+	power_range = pid_controller(tz, control_temp, max_allocatable_power);
 
 	divvy_up_power(weighted_req_power, max_power, num_actors,
 		       total_weighted_req_power, power_range, granted_power,
@@ -444,8 +440,8 @@ static int allocate_power(struct thermal_zone_device *tz,
 	trace_thermal_power_allocator(tz, req_power, total_req_power,
 				      granted_power, total_granted_power,
 				      num_actors, power_range,
-				      max_allocatable_power, current_temp,
-				      control_temp - current_temp);
+				      max_allocatable_power, tz->temperature,
+				      control_temp - tz->temperature);
 
 	kfree(req_power);
 unlock:
@@ -612,7 +608,7 @@ static void power_allocator_unbind(struct thermal_zone_device *tz)
 static int power_allocator_throttle(struct thermal_zone_device *tz, int trip)
 {
 	int ret;
-	int switch_on_temp, control_temp, current_temp;
+	int switch_on_temp, control_temp;
 	struct power_allocator_params *params = tz->governor_data;
 
 	/*
@@ -622,15 +618,9 @@ static int power_allocator_throttle(struct thermal_zone_device *tz, int trip)
 	if (trip != params->trip_max_desired_temperature)
 		return 0;
 
-	ret = thermal_zone_get_temp(tz, &current_temp);
-	if (ret) {
-		dev_warn(&tz->device, "Failed to get temperature: %d\n", ret);
-		return ret;
-	}
-
 	ret = tz->ops->get_trip_temp(tz, params->trip_switch_on,
 				     &switch_on_temp);
-	if (!ret && (current_temp < switch_on_temp)) {
+	if (!ret && (tz->temperature < switch_on_temp)) {
 		tz->passive = 0;
 		reset_pid_controller(params);
 		allow_maximum_power(tz);
@@ -648,7 +638,7 @@ static int power_allocator_throttle(struct thermal_zone_device *tz, int trip)
 		return ret;
 	}
 
-	return allocate_power(tz, current_temp, control_temp);
+	return allocate_power(tz, control_temp);
 }
 
 static struct thermal_governor thermal_gov_power_allocator = {
diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c
index 5d4ae7d705e0..13d01edc7a04 100644
--- a/drivers/thermal/rcar_thermal.c
+++ b/drivers/thermal/rcar_thermal.c
@@ -361,6 +361,24 @@ static irqreturn_t rcar_thermal_irq(int irq, void *data)
 /*
  *		platform functions
  */
+static int rcar_thermal_remove(struct platform_device *pdev)
+{
+	struct rcar_thermal_common *common = platform_get_drvdata(pdev);
+	struct device *dev = &pdev->dev;
+	struct rcar_thermal_priv *priv;
+
+	rcar_thermal_for_each_priv(priv, common) {
+		if (rcar_has_irq_support(priv))
+			rcar_thermal_irq_disable(priv);
+		thermal_zone_device_unregister(priv->zone);
+	}
+
+	pm_runtime_put(dev);
+	pm_runtime_disable(dev);
+
+	return 0;
+}
+
 static int rcar_thermal_probe(struct platform_device *pdev)
 {
 	struct rcar_thermal_common *common;
@@ -377,6 +395,8 @@ static int rcar_thermal_probe(struct platform_device *pdev)
 	if (!common)
 		return -ENOMEM;
 
+	platform_set_drvdata(pdev, common);
+
 	INIT_LIST_HEAD(&common->head);
 	spin_lock_init(&common->lock);
 	common->dev = dev;
@@ -454,43 +474,16 @@ static int rcar_thermal_probe(struct platform_device *pdev)
 		rcar_thermal_common_write(common, ENR, enr_bits);
 	}
 
-	platform_set_drvdata(pdev, common);
-
 	dev_info(dev, "%d sensor probed\n", i);
 
 	return 0;
 
 error_unregister:
-	rcar_thermal_for_each_priv(priv, common) {
-		if (rcar_has_irq_support(priv))
-			rcar_thermal_irq_disable(priv);
-		thermal_zone_device_unregister(priv->zone);
-	}
-
-	pm_runtime_put(dev);
-	pm_runtime_disable(dev);
+	rcar_thermal_remove(pdev);
 
 	return ret;
 }
 
-static int rcar_thermal_remove(struct platform_device *pdev)
-{
-	struct rcar_thermal_common *common = platform_get_drvdata(pdev);
-	struct device *dev = &pdev->dev;
-	struct rcar_thermal_priv *priv;
-
-	rcar_thermal_for_each_priv(priv, common) {
-		if (rcar_has_irq_support(priv))
-			rcar_thermal_irq_disable(priv);
-		thermal_zone_device_unregister(priv->zone);
-	}
-
-	pm_runtime_put(dev);
-	pm_runtime_disable(dev);
-
-	return 0;
-}
-
 static const struct of_device_id rcar_thermal_dt_ids[] = {
 	{ .compatible = "renesas,rcar-thermal", },
 	{},
diff --git a/drivers/thermal/rockchip_thermal.c b/drivers/thermal/rockchip_thermal.c
index 9787e8aa509f..e845841ab036 100644
--- a/drivers/thermal/rockchip_thermal.c
+++ b/drivers/thermal/rockchip_thermal.c
@@ -1,6 +1,9 @@
 /*
  * Copyright (c) 2014, Fuzhou Rockchip Electronics Co., Ltd
  *
+ * Copyright (c) 2015, Fuzhou Rockchip Electronics Co., Ltd
+ * Caesar Wang <wxt@rock-chips.com>
+ *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
  * version 2, as published by the Free Software Foundation.
@@ -45,17 +48,50 @@ enum tshut_polarity {
 };
 
 /**
- * The system has three Temperature Sensors.  channel 0 is reserved,
- * channel 1 is for CPU, and channel 2 is for GPU.
+ * The system has two Temperature Sensors.
+ * sensor0 is for CPU, and sensor1 is for GPU.
  */
 enum sensor_id {
-	SENSOR_CPU = 1,
+	SENSOR_CPU = 0,
 	SENSOR_GPU,
 };
 
+/**
+* The conversion table has the adc value and temperature.
+* ADC_DECREMENT is the adc value decremnet.(e.g. v2_code_table)
+* ADC_INCREMNET is the adc value incremnet.(e.g. v3_code_table)
+*/
+enum adc_sort_mode {
+	ADC_DECREMENT = 0,
+	ADC_INCREMENT,
+};
+
+/**
+ * The max sensors is two in rockchip SoCs.
+ * Two sensors: CPU and GPU sensor.
+ */
+#define SOC_MAX_SENSORS	2
+
+struct chip_tsadc_table {
+	const struct tsadc_table *id;
+
+	/* the array table size*/
+	unsigned int length;
+
+	/* that analogic mask data */
+	u32 data_mask;
+
+	/* the sort mode is adc value that increment or decrement in table */
+	enum adc_sort_mode mode;
+};
+
 struct rockchip_tsadc_chip {
+	/* The sensor id of chip correspond to the ADC channel */
+	int chn_id[SOC_MAX_SENSORS];
+	int chn_num;
+
 	/* The hardware-controlled tshut property */
-	long tshut_temp;
+	int tshut_temp;
 	enum tshut_mode tshut_mode;
 	enum tshut_polarity tshut_polarity;
 
@@ -65,37 +101,40 @@ struct rockchip_tsadc_chip {
 	void (*control)(void __iomem *reg, bool on);
 
 	/* Per-sensor methods */
-	int (*get_temp)(int chn, void __iomem *reg, int *temp);
-	void (*set_tshut_temp)(int chn, void __iomem *reg, long temp);
+	int (*get_temp)(struct chip_tsadc_table table,
+			int chn, void __iomem *reg, int *temp);
+	void (*set_tshut_temp)(struct chip_tsadc_table table,
+			       int chn, void __iomem *reg, int temp);
 	void (*set_tshut_mode)(int chn, void __iomem *reg, enum tshut_mode m);
+
+	/* Per-table methods */
+	struct chip_tsadc_table table;
 };
 
 struct rockchip_thermal_sensor {
 	struct rockchip_thermal_data *thermal;
 	struct thermal_zone_device *tzd;
-	enum sensor_id id;
+	int id;
 };
 
-#define NUM_SENSORS	2 /* Ignore unused sensor 0 */
-
 struct rockchip_thermal_data {
 	const struct rockchip_tsadc_chip *chip;
 	struct platform_device *pdev;
 	struct reset_control *reset;
 
-	struct rockchip_thermal_sensor sensors[NUM_SENSORS];
+	struct rockchip_thermal_sensor sensors[SOC_MAX_SENSORS];
 
 	struct clk *clk;
 	struct clk *pclk;
 
 	void __iomem *regs;
 
-	long tshut_temp;
+	int tshut_temp;
 	enum tshut_mode tshut_mode;
 	enum tshut_polarity tshut_polarity;
 };
 
-/* TSADC V2 Sensor info define: */
+/* TSADC Sensor info define: */
 #define TSADCV2_AUTO_CON			0x04
 #define TSADCV2_INT_EN				0x08
 #define TSADCV2_INT_PD				0x0c
@@ -117,6 +156,8 @@ struct rockchip_thermal_data {
 #define TSADCV2_INT_PD_CLEAR_MASK		~BIT(8)
 
 #define TSADCV2_DATA_MASK			0xfff
+#define TSADCV3_DATA_MASK			0x3ff
+
 #define TSADCV2_HIGHT_INT_DEBOUNCE_COUNT	4
 #define TSADCV2_HIGHT_TSHUT_DEBOUNCE_COUNT	4
 #define TSADCV2_AUTO_PERIOD_TIME		250 /* msec */
@@ -124,7 +165,7 @@ struct rockchip_thermal_data {
 
 struct tsadc_table {
 	u32 code;
-	long temp;
+	int temp;
 };
 
 static const struct tsadc_table v2_code_table[] = {
@@ -165,21 +206,61 @@ static const struct tsadc_table v2_code_table[] = {
 	{3421, 125000},
 };
 
-static u32 rk_tsadcv2_temp_to_code(long temp)
+static const struct tsadc_table v3_code_table[] = {
+	{0, -40000},
+	{106, -40000},
+	{108, -35000},
+	{110, -30000},
+	{112, -25000},
+	{114, -20000},
+	{116, -15000},
+	{118, -10000},
+	{120, -5000},
+	{122, 0},
+	{124, 5000},
+	{126, 10000},
+	{128, 15000},
+	{130, 20000},
+	{132, 25000},
+	{134, 30000},
+	{136, 35000},
+	{138, 40000},
+	{140, 45000},
+	{142, 50000},
+	{144, 55000},
+	{146, 60000},
+	{148, 65000},
+	{150, 70000},
+	{152, 75000},
+	{154, 80000},
+	{156, 85000},
+	{158, 90000},
+	{160, 95000},
+	{162, 100000},
+	{163, 105000},
+	{165, 110000},
+	{167, 115000},
+	{169, 120000},
+	{171, 125000},
+	{TSADCV3_DATA_MASK, 125000},
+};
+
+static u32 rk_tsadcv2_temp_to_code(struct chip_tsadc_table table,
+				   int temp)
 {
 	int high, low, mid;
 
 	low = 0;
-	high = ARRAY_SIZE(v2_code_table) - 1;
+	high = table.length - 1;
 	mid = (high + low) / 2;
 
-	if (temp < v2_code_table[low].temp || temp > v2_code_table[high].temp)
+	if (temp < table.id[low].temp || temp > table.id[high].temp)
 		return 0;
 
 	while (low <= high) {
-		if (temp == v2_code_table[mid].temp)
-			return v2_code_table[mid].code;
-		else if (temp < v2_code_table[mid].temp)
+		if (temp == table.id[mid].temp)
+			return table.id[mid].code;
+		else if (temp < table.id[mid].temp)
 			high = mid - 1;
 		else
 			low = mid + 1;
@@ -189,29 +270,54 @@ static u32 rk_tsadcv2_temp_to_code(long temp)
 	return 0;
 }
 
-static int rk_tsadcv2_code_to_temp(u32 code, int *temp)
+static int rk_tsadcv2_code_to_temp(struct chip_tsadc_table table, u32 code,
+				   int *temp)
 {
 	unsigned int low = 1;
-	unsigned int high = ARRAY_SIZE(v2_code_table) - 1;
+	unsigned int high = table.length - 1;
 	unsigned int mid = (low + high) / 2;
 	unsigned int num;
 	unsigned long denom;
 
-	BUILD_BUG_ON(ARRAY_SIZE(v2_code_table) < 2);
-
-	code &= TSADCV2_DATA_MASK;
-	if (code < v2_code_table[high].code)
-		return -EAGAIN;		/* Incorrect reading */
-
-	while (low <= high) {
-		if (code >= v2_code_table[mid].code &&
-		    code < v2_code_table[mid - 1].code)
-			break;
-		else if (code < v2_code_table[mid].code)
-			low = mid + 1;
-		else
-			high = mid - 1;
-		mid = (low + high) / 2;
+	WARN_ON(table.length < 2);
+
+	switch (table.mode) {
+	case ADC_DECREMENT:
+		code &= table.data_mask;
+		if (code < table.id[high].code)
+			return -EAGAIN;		/* Incorrect reading */
+
+		while (low <= high) {
+			if (code >= table.id[mid].code &&
+			    code < table.id[mid - 1].code)
+				break;
+			else if (code < table.id[mid].code)
+				low = mid + 1;
+			else
+				high = mid - 1;
+
+			mid = (low + high) / 2;
+		}
+		break;
+	case ADC_INCREMENT:
+		code &= table.data_mask;
+		if (code < table.id[low].code)
+			return -EAGAIN;		/* Incorrect reading */
+
+		while (low <= high) {
+			if (code >= table.id[mid - 1].code &&
+			    code < table.id[mid].code)
+				break;
+			else if (code > table.id[mid].code)
+				low = mid + 1;
+			else
+				high = mid - 1;
+
+			mid = (low + high) / 2;
+		}
+		break;
+	default:
+		pr_err("Invalid the conversion table\n");
 	}
 
 	/*
@@ -220,24 +326,28 @@ static int rk_tsadcv2_code_to_temp(u32 code, int *temp)
 	 * temperature between 2 table entries is linear and interpolate
 	 * to produce less granular result.
 	 */
-	num = v2_code_table[mid].temp - v2_code_table[mid - 1].temp;
-	num *= v2_code_table[mid - 1].code - code;
-	denom = v2_code_table[mid - 1].code - v2_code_table[mid].code;
-	*temp = v2_code_table[mid - 1].temp + (num / denom);
+	num = table.id[mid].temp - v2_code_table[mid - 1].temp;
+	num *= abs(table.id[mid - 1].code - code);
+	denom = abs(table.id[mid - 1].code - table.id[mid].code);
+	*temp = table.id[mid - 1].temp + (num / denom);
 
 	return 0;
 }
 
 /**
- * rk_tsadcv2_initialize - initialize TASDC Controller
- * (1) Set TSADCV2_AUTO_PERIOD, configure the interleave between
- * every two accessing of TSADC in normal operation.
- * (2) Set TSADCV2_AUTO_PERIOD_HT, configure the interleave between
- * every two accessing of TSADC after the temperature is higher
- * than COM_SHUT or COM_INT.
- * (3) Set TSADCV2_HIGH_INT_DEBOUNCE and TSADC_HIGHT_TSHUT_DEBOUNCE,
- * if the temperature is higher than COMP_INT or COMP_SHUT for
- * "debounce" times, TSADC controller will generate interrupt or TSHUT.
+ * rk_tsadcv2_initialize - initialize TASDC Controller.
+ *
+ * (1) Set TSADC_V2_AUTO_PERIOD:
+ *     Configure the interleave between every two accessing of
+ *     TSADC in normal operation.
+ *
+ * (2) Set TSADCV2_AUTO_PERIOD_HT:
+ *     Configure the interleave between every two accessing of
+ *     TSADC after the temperature is higher than COM_SHUT or COM_INT.
+ *
+ * (3) Set TSADCV2_HIGH_INT_DEBOUNCE and TSADC_HIGHT_TSHUT_DEBOUNCE:
+ *     If the temperature is higher than COMP_INT or COMP_SHUT for
+ *     "debounce" times, TSADC controller will generate interrupt or TSHUT.
  */
 static void rk_tsadcv2_initialize(void __iomem *regs,
 				  enum tshut_polarity tshut_polarity)
@@ -279,20 +389,22 @@ static void rk_tsadcv2_control(void __iomem *regs, bool enable)
 	writel_relaxed(val, regs + TSADCV2_AUTO_CON);
 }
 
-static int rk_tsadcv2_get_temp(int chn, void __iomem *regs, int *temp)
+static int rk_tsadcv2_get_temp(struct chip_tsadc_table table,
+			       int chn, void __iomem *regs, int *temp)
 {
 	u32 val;
 
 	val = readl_relaxed(regs + TSADCV2_DATA(chn));
 
-	return rk_tsadcv2_code_to_temp(val, temp);
+	return rk_tsadcv2_code_to_temp(table, val, temp);
 }
 
-static void rk_tsadcv2_tshut_temp(int chn, void __iomem *regs, long temp)
+static void rk_tsadcv2_tshut_temp(struct chip_tsadc_table table,
+				  int chn, void __iomem *regs, int temp)
 {
 	u32 tshut_value, val;
 
-	tshut_value = rk_tsadcv2_temp_to_code(temp);
+	tshut_value = rk_tsadcv2_temp_to_code(table, temp);
 	writel_relaxed(tshut_value, regs + TSADCV2_COMP_SHUT(chn));
 
 	/* TSHUT will be valid */
@@ -318,6 +430,10 @@ static void rk_tsadcv2_tshut_mode(int chn, void __iomem *regs,
 }
 
 static const struct rockchip_tsadc_chip rk3288_tsadc_data = {
+	.chn_id[SENSOR_CPU] = 1, /* cpu sensor is channel 1 */
+	.chn_id[SENSOR_GPU] = 2, /* gpu sensor is channel 2 */
+	.chn_num = 2, /* two channels for tsadc */
+
 	.tshut_mode = TSHUT_MODE_GPIO, /* default TSHUT via GPIO give PMIC */
 	.tshut_polarity = TSHUT_LOW_ACTIVE, /* default TSHUT LOW ACTIVE */
 	.tshut_temp = 95000,
@@ -328,6 +444,37 @@ static const struct rockchip_tsadc_chip rk3288_tsadc_data = {
 	.get_temp = rk_tsadcv2_get_temp,
 	.set_tshut_temp = rk_tsadcv2_tshut_temp,
 	.set_tshut_mode = rk_tsadcv2_tshut_mode,
+
+	.table = {
+		.id = v2_code_table,
+		.length = ARRAY_SIZE(v2_code_table),
+		.data_mask = TSADCV2_DATA_MASK,
+		.mode = ADC_DECREMENT,
+	},
+};
+
+static const struct rockchip_tsadc_chip rk3368_tsadc_data = {
+	.chn_id[SENSOR_CPU] = 0, /* cpu sensor is channel 0 */
+	.chn_id[SENSOR_GPU] = 1, /* gpu sensor is channel 1 */
+	.chn_num = 2, /* two channels for tsadc */
+
+	.tshut_mode = TSHUT_MODE_GPIO, /* default TSHUT via GPIO give PMIC */
+	.tshut_polarity = TSHUT_LOW_ACTIVE, /* default TSHUT LOW ACTIVE */
+	.tshut_temp = 95000,
+
+	.initialize = rk_tsadcv2_initialize,
+	.irq_ack = rk_tsadcv2_irq_ack,
+	.control = rk_tsadcv2_control,
+	.get_temp = rk_tsadcv2_get_temp,
+	.set_tshut_temp = rk_tsadcv2_tshut_temp,
+	.set_tshut_mode = rk_tsadcv2_tshut_mode,
+
+	.table = {
+		.id = v3_code_table,
+		.length = ARRAY_SIZE(v3_code_table),
+		.data_mask = TSADCV3_DATA_MASK,
+		.mode = ADC_INCREMENT,
+	},
 };
 
 static const struct of_device_id of_rockchip_thermal_match[] = {
@@ -335,6 +482,10 @@ static const struct of_device_id of_rockchip_thermal_match[] = {
 		.compatible = "rockchip,rk3288-tsadc",
 		.data = (void *)&rk3288_tsadc_data,
 	},
+	{
+		.compatible = "rockchip,rk3368-tsadc",
+		.data = (void *)&rk3368_tsadc_data,
+	},
 	{ /* end */ },
 };
 MODULE_DEVICE_TABLE(of, of_rockchip_thermal_match);
@@ -357,7 +508,7 @@ static irqreturn_t rockchip_thermal_alarm_irq_thread(int irq, void *dev)
 
 	thermal->chip->irq_ack(thermal->regs);
 
-	for (i = 0; i < ARRAY_SIZE(thermal->sensors); i++)
+	for (i = 0; i < thermal->chip->chn_num; i++)
 		thermal_zone_device_update(thermal->sensors[i].tzd);
 
 	return IRQ_HANDLED;
@@ -370,7 +521,8 @@ static int rockchip_thermal_get_temp(void *_sensor, int *out_temp)
 	const struct rockchip_tsadc_chip *tsadc = sensor->thermal->chip;
 	int retval;
 
-	retval = tsadc->get_temp(sensor->id, thermal->regs, out_temp);
+	retval = tsadc->get_temp(tsadc->table,
+				 sensor->id, thermal->regs, out_temp);
 	dev_dbg(&thermal->pdev->dev, "sensor %d - temp: %d, retval: %d\n",
 		sensor->id, *out_temp, retval);
 
@@ -389,7 +541,7 @@ static int rockchip_configure_from_dt(struct device *dev,
 
 	if (of_property_read_u32(np, "rockchip,hw-tshut-temp", &shut_temp)) {
 		dev_warn(dev,
-			 "Missing tshut temp property, using default %ld\n",
+			 "Missing tshut temp property, using default %d\n",
 			 thermal->chip->tshut_temp);
 		thermal->tshut_temp = thermal->chip->tshut_temp;
 	} else {
@@ -397,7 +549,7 @@ static int rockchip_configure_from_dt(struct device *dev,
 	}
 
 	if (thermal->tshut_temp > INT_MAX) {
-		dev_err(dev, "Invalid tshut temperature specified: %ld\n",
+		dev_err(dev, "Invalid tshut temperature specified: %d\n",
 			thermal->tshut_temp);
 		return -ERANGE;
 	}
@@ -442,13 +594,14 @@ static int
 rockchip_thermal_register_sensor(struct platform_device *pdev,
 				 struct rockchip_thermal_data *thermal,
 				 struct rockchip_thermal_sensor *sensor,
-				 enum sensor_id id)
+				 int id)
 {
 	const struct rockchip_tsadc_chip *tsadc = thermal->chip;
 	int error;
 
 	tsadc->set_tshut_mode(id, thermal->regs, thermal->tshut_mode);
-	tsadc->set_tshut_temp(id, thermal->regs, thermal->tshut_temp);
+	tsadc->set_tshut_temp(tsadc->table, id, thermal->regs,
+			      thermal->tshut_temp);
 
 	sensor->thermal = thermal;
 	sensor->id = id;
@@ -481,7 +634,7 @@ static int rockchip_thermal_probe(struct platform_device *pdev)
 	const struct of_device_id *match;
 	struct resource *res;
 	int irq;
-	int i;
+	int i, j;
 	int error;
 
 	match = of_match_node(of_rockchip_thermal_match, np);
@@ -556,22 +709,19 @@ static int rockchip_thermal_probe(struct platform_device *pdev)
 
 	thermal->chip->initialize(thermal->regs, thermal->tshut_polarity);
 
-	error = rockchip_thermal_register_sensor(pdev, thermal,
-						 &thermal->sensors[0],
-						 SENSOR_CPU);
-	if (error) {
-		dev_err(&pdev->dev,
-			"failed to register CPU thermal sensor: %d\n", error);
-		goto err_disable_pclk;
-	}
-
-	error = rockchip_thermal_register_sensor(pdev, thermal,
-						 &thermal->sensors[1],
-						 SENSOR_GPU);
-	if (error) {
-		dev_err(&pdev->dev,
-			"failed to register GPU thermal sensor: %d\n", error);
-		goto err_unregister_cpu_sensor;
+	for (i = 0; i < thermal->chip->chn_num; i++) {
+		error = rockchip_thermal_register_sensor(pdev, thermal,
+						&thermal->sensors[i],
+						thermal->chip->chn_id[i]);
+		if (error) {
+			dev_err(&pdev->dev,
+				"failed to register sensor[%d] : error = %d\n",
+				i, error);
+			for (j = 0; j < i; j++)
+				thermal_zone_of_sensor_unregister(&pdev->dev,
+						thermal->sensors[j].tzd);
+			goto err_disable_pclk;
+		}
 	}
 
 	error = devm_request_threaded_irq(&pdev->dev, irq, NULL,
@@ -581,22 +731,23 @@ static int rockchip_thermal_probe(struct platform_device *pdev)
 	if (error) {
 		dev_err(&pdev->dev,
 			"failed to request tsadc irq: %d\n", error);
-		goto err_unregister_gpu_sensor;
+		goto err_unregister_sensor;
 	}
 
 	thermal->chip->control(thermal->regs, true);
 
-	for (i = 0; i < ARRAY_SIZE(thermal->sensors); i++)
+	for (i = 0; i < thermal->chip->chn_num; i++)
 		rockchip_thermal_toggle_sensor(&thermal->sensors[i], true);
 
 	platform_set_drvdata(pdev, thermal);
 
 	return 0;
 
-err_unregister_gpu_sensor:
-	thermal_zone_of_sensor_unregister(&pdev->dev, thermal->sensors[1].tzd);
-err_unregister_cpu_sensor:
-	thermal_zone_of_sensor_unregister(&pdev->dev, thermal->sensors[0].tzd);
+err_unregister_sensor:
+	while (i--)
+		thermal_zone_of_sensor_unregister(&pdev->dev,
+						  thermal->sensors[i].tzd);
+
 err_disable_pclk:
 	clk_disable_unprepare(thermal->pclk);
 err_disable_clk:
@@ -610,7 +761,7 @@ static int rockchip_thermal_remove(struct platform_device *pdev)
 	struct rockchip_thermal_data *thermal = platform_get_drvdata(pdev);
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(thermal->sensors); i++) {
+	for (i = 0; i < thermal->chip->chn_num; i++) {
 		struct rockchip_thermal_sensor *sensor = &thermal->sensors[i];
 
 		rockchip_thermal_toggle_sensor(sensor, false);
@@ -631,7 +782,7 @@ static int __maybe_unused rockchip_thermal_suspend(struct device *dev)
 	struct rockchip_thermal_data *thermal = platform_get_drvdata(pdev);
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(thermal->sensors); i++)
+	for (i = 0; i < thermal->chip->chn_num; i++)
 		rockchip_thermal_toggle_sensor(&thermal->sensors[i], false);
 
 	thermal->chip->control(thermal->regs, false);
@@ -663,18 +814,19 @@ static int __maybe_unused rockchip_thermal_resume(struct device *dev)
 
 	thermal->chip->initialize(thermal->regs, thermal->tshut_polarity);
 
-	for (i = 0; i < ARRAY_SIZE(thermal->sensors); i++) {
-		enum sensor_id id = thermal->sensors[i].id;
+	for (i = 0; i < thermal->chip->chn_num; i++) {
+		int id = thermal->sensors[i].id;
 
 		thermal->chip->set_tshut_mode(id, thermal->regs,
 					      thermal->tshut_mode);
-		thermal->chip->set_tshut_temp(id, thermal->regs,
+		thermal->chip->set_tshut_temp(thermal->chip->table,
+					      id, thermal->regs,
 					      thermal->tshut_temp);
 	}
 
 	thermal->chip->control(thermal->regs, true);
 
-	for (i = 0; i < ARRAY_SIZE(thermal->sensors); i++)
+	for (i = 0; i < thermal->chip->chn_num; i++)
 		rockchip_thermal_toggle_sensor(&thermal->sensors[i], true);
 
 	pinctrl_pm_select_default_state(dev);
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index 13844261cd5f..ed776149261e 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -169,7 +169,7 @@ static inline int tty_copy_to_user(struct tty_struct *tty,
 {
 	struct n_tty_data *ldata = tty->disc_data;
 
-	tty_audit_add_data(tty, to, n, ldata->icanon);
+	tty_audit_add_data(tty, from, n, ldata->icanon);
 	return copy_to_user(to, from, n);
 }
 
diff --git a/drivers/tty/serial/8250/8250_fsl.c b/drivers/tty/serial/8250/8250_fsl.c
index c0533a57ec53..910bfee5a88b 100644
--- a/drivers/tty/serial/8250/8250_fsl.c
+++ b/drivers/tty/serial/8250/8250_fsl.c
@@ -60,3 +60,4 @@ int fsl8250_handle_irq(struct uart_port *port)
 	spin_unlock_irqrestore(&up->port.lock, flags);
 	return 1;
 }
+EXPORT_SYMBOL_GPL(fsl8250_handle_irq);
diff --git a/drivers/tty/serial/8250/Kconfig b/drivers/tty/serial/8250/Kconfig
index e6f5e12a2d83..6412f1455beb 100644
--- a/drivers/tty/serial/8250/Kconfig
+++ b/drivers/tty/serial/8250/Kconfig
@@ -373,6 +373,7 @@ config SERIAL_8250_MID
 	depends on SERIAL_8250 && PCI
 	select HSU_DMA if SERIAL_8250_DMA
 	select HSU_DMA_PCI if X86_INTEL_MID
+	select RATIONAL
 	help
 	  Selecting this option will enable handling of the extra features
 	  present on the UART found on Intel Medfield SOC and various other
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 1aec4404062d..f38beb28e7ae 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -1539,7 +1539,6 @@ config SERIAL_FSL_LPUART
 	tristate "Freescale lpuart serial port support"
 	depends on HAS_DMA
 	select SERIAL_CORE
-	select SERIAL_EARLYCON
 	help
 	  Support for the on-chip lpuart on some Freescale SOCs.
 
@@ -1547,6 +1546,7 @@ config SERIAL_FSL_LPUART_CONSOLE
 	bool "Console on Freescale lpuart serial port"
 	depends on SERIAL_FSL_LPUART=y
 	select SERIAL_CORE_CONSOLE
+	select SERIAL_EARLYCON
 	help
 	  If you have enabled the lpuart serial port on the Freescale SoCs,
 	  you can make it the console by answering Y to this option.
diff --git a/drivers/tty/serial/bcm63xx_uart.c b/drivers/tty/serial/bcm63xx_uart.c
index 681e0f3d5e0e..a1c0a89d9c7f 100644
--- a/drivers/tty/serial/bcm63xx_uart.c
+++ b/drivers/tty/serial/bcm63xx_uart.c
@@ -474,7 +474,7 @@ static int bcm_uart_startup(struct uart_port *port)
 
 	/* register irq and enable rx interrupts */
 	ret = request_irq(port->irq, bcm_uart_interrupt, 0,
-			  bcm_uart_type(port), port);
+			  dev_name(port->dev), port);
 	if (ret)
 		return ret;
 	bcm_uart_writel(port, UART_RX_INT_MASK, UART_IR_REG);
diff --git a/drivers/tty/serial/etraxfs-uart.c b/drivers/tty/serial/etraxfs-uart.c
index 6813e316e9ff..2f80bc7e44fb 100644
--- a/drivers/tty/serial/etraxfs-uart.c
+++ b/drivers/tty/serial/etraxfs-uart.c
@@ -894,7 +894,7 @@ static int etraxfs_uart_probe(struct platform_device *pdev)
 	up->regi_ser = of_iomap(np, 0);
 	up->port.dev = &pdev->dev;
 
-	up->gpios = mctrl_gpio_init(&pdev->dev, 0);
+	up->gpios = mctrl_gpio_init_noauto(&pdev->dev, 0);
 	if (IS_ERR(up->gpios))
 		return PTR_ERR(up->gpios);
 
diff --git a/drivers/tty/tty_audit.c b/drivers/tty/tty_audit.c
index 90ca082935f6..3d245cd3d8e6 100644
--- a/drivers/tty/tty_audit.c
+++ b/drivers/tty/tty_audit.c
@@ -265,7 +265,7 @@ static struct tty_audit_buf *tty_audit_buf_get(struct tty_struct *tty,
  *
  *	Audit @data of @size from @tty, if necessary.
  */
-void tty_audit_add_data(struct tty_struct *tty, unsigned char *data,
+void tty_audit_add_data(struct tty_struct *tty, const void *data,
 			size_t size, unsigned icanon)
 {
 	struct tty_audit_buf *buf;
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 0c41dbcb90b8..bcc8e1e8bb72 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -1282,18 +1282,22 @@ int tty_send_xchar(struct tty_struct *tty, char ch)
 	int	was_stopped = tty->stopped;
 
 	if (tty->ops->send_xchar) {
+		down_read(&tty->termios_rwsem);
 		tty->ops->send_xchar(tty, ch);
+		up_read(&tty->termios_rwsem);
 		return 0;
 	}
 
 	if (tty_write_lock(tty, 0) < 0)
 		return -ERESTARTSYS;
 
+	down_read(&tty->termios_rwsem);
 	if (was_stopped)
 		start_tty(tty);
 	tty->ops->write(tty, &ch, 1);
 	if (was_stopped)
 		stop_tty(tty);
+	up_read(&tty->termios_rwsem);
 	tty_write_unlock(tty);
 	return 0;
 }
diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c
index 9c5aebfe7053..1445dd39aa62 100644
--- a/drivers/tty/tty_ioctl.c
+++ b/drivers/tty/tty_ioctl.c
@@ -1147,16 +1147,12 @@ int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file,
 			spin_unlock_irq(&tty->flow_lock);
 			break;
 		case TCIOFF:
-			down_read(&tty->termios_rwsem);
 			if (STOP_CHAR(tty) != __DISABLED_CHAR)
 				retval = tty_send_xchar(tty, STOP_CHAR(tty));
-			up_read(&tty->termios_rwsem);
 			break;
 		case TCION:
-			down_read(&tty->termios_rwsem);
 			if (START_CHAR(tty) != __DISABLED_CHAR)
 				retval = tty_send_xchar(tty, START_CHAR(tty));
-			up_read(&tty->termios_rwsem);
 			break;
 		default:
 			return -EINVAL;
diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c
index 5af8f1874c1a..629e3c865072 100644
--- a/drivers/tty/tty_ldisc.c
+++ b/drivers/tty/tty_ldisc.c
@@ -592,7 +592,7 @@ int tty_set_ldisc(struct tty_struct *tty, int ldisc)
 
 	/* Restart the work queue in case no characters kick it off. Safe if
 	   already running */
-	schedule_work(&tty->port->buf.work);
+	tty_buffer_restart_work(tty->port);
 
 	tty_unlock(tty);
 	return retval;
diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index 6ccbf60cdd5c..5a048b7b92e8 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -84,6 +84,12 @@ struct ci_hdrc_imx_data {
 	struct imx_usbmisc_data *usbmisc_data;
 	bool supports_runtime_pm;
 	bool in_lpm;
+	/* SoC before i.mx6 (except imx23/imx28) needs three clks */
+	bool need_three_clks;
+	struct clk *clk_ipg;
+	struct clk *clk_ahb;
+	struct clk *clk_per;
+	/* --------------------------------- */
 };
 
 /* Common functions shared by usbmisc drivers */
@@ -135,6 +141,102 @@ static struct imx_usbmisc_data *usbmisc_get_init_data(struct device *dev)
 }
 
 /* End of common functions shared by usbmisc drivers*/
+static int imx_get_clks(struct device *dev)
+{
+	struct ci_hdrc_imx_data *data = dev_get_drvdata(dev);
+	int ret = 0;
+
+	data->clk_ipg = devm_clk_get(dev, "ipg");
+	if (IS_ERR(data->clk_ipg)) {
+		/* If the platform only needs one clocks */
+		data->clk = devm_clk_get(dev, NULL);
+		if (IS_ERR(data->clk)) {
+			ret = PTR_ERR(data->clk);
+			dev_err(dev,
+				"Failed to get clks, err=%ld,%ld\n",
+				PTR_ERR(data->clk), PTR_ERR(data->clk_ipg));
+			return ret;
+		}
+		return ret;
+	}
+
+	data->clk_ahb = devm_clk_get(dev, "ahb");
+	if (IS_ERR(data->clk_ahb)) {
+		ret = PTR_ERR(data->clk_ahb);
+		dev_err(dev,
+			"Failed to get ahb clock, err=%d\n", ret);
+		return ret;
+	}
+
+	data->clk_per = devm_clk_get(dev, "per");
+	if (IS_ERR(data->clk_per)) {
+		ret = PTR_ERR(data->clk_per);
+		dev_err(dev,
+			"Failed to get per clock, err=%d\n", ret);
+		return ret;
+	}
+
+	data->need_three_clks = true;
+	return ret;
+}
+
+static int imx_prepare_enable_clks(struct device *dev)
+{
+	struct ci_hdrc_imx_data *data = dev_get_drvdata(dev);
+	int ret = 0;
+
+	if (data->need_three_clks) {
+		ret = clk_prepare_enable(data->clk_ipg);
+		if (ret) {
+			dev_err(dev,
+				"Failed to prepare/enable ipg clk, err=%d\n",
+				ret);
+			return ret;
+		}
+
+		ret = clk_prepare_enable(data->clk_ahb);
+		if (ret) {
+			dev_err(dev,
+				"Failed to prepare/enable ahb clk, err=%d\n",
+				ret);
+			clk_disable_unprepare(data->clk_ipg);
+			return ret;
+		}
+
+		ret = clk_prepare_enable(data->clk_per);
+		if (ret) {
+			dev_err(dev,
+				"Failed to prepare/enable per clk, err=%d\n",
+				ret);
+			clk_disable_unprepare(data->clk_ahb);
+			clk_disable_unprepare(data->clk_ipg);
+			return ret;
+		}
+	} else {
+		ret = clk_prepare_enable(data->clk);
+		if (ret) {
+			dev_err(dev,
+				"Failed to prepare/enable clk, err=%d\n",
+				ret);
+			return ret;
+		}
+	}
+
+	return ret;
+}
+
+static void imx_disable_unprepare_clks(struct device *dev)
+{
+	struct ci_hdrc_imx_data *data = dev_get_drvdata(dev);
+
+	if (data->need_three_clks) {
+		clk_disable_unprepare(data->clk_per);
+		clk_disable_unprepare(data->clk_ahb);
+		clk_disable_unprepare(data->clk_ipg);
+	} else {
+		clk_disable_unprepare(data->clk);
+	}
+}
 
 static int ci_hdrc_imx_probe(struct platform_device *pdev)
 {
@@ -145,31 +247,31 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 		.flags		= CI_HDRC_SET_NON_ZERO_TTHA,
 	};
 	int ret;
-	const struct of_device_id *of_id =
-			of_match_device(ci_hdrc_imx_dt_ids, &pdev->dev);
-	const struct ci_hdrc_imx_platform_flag *imx_platform_flag = of_id->data;
+	const struct of_device_id *of_id;
+	const struct ci_hdrc_imx_platform_flag *imx_platform_flag;
+
+	of_id = of_match_device(ci_hdrc_imx_dt_ids, &pdev->dev);
+	if (!of_id)
+		return -ENODEV;
+
+	imx_platform_flag = of_id->data;
 
 	data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
+	platform_set_drvdata(pdev, data);
 	data->usbmisc_data = usbmisc_get_init_data(&pdev->dev);
 	if (IS_ERR(data->usbmisc_data))
 		return PTR_ERR(data->usbmisc_data);
 
-	data->clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(data->clk)) {
-		dev_err(&pdev->dev,
-			"Failed to get clock, err=%ld\n", PTR_ERR(data->clk));
-		return PTR_ERR(data->clk);
-	}
+	ret = imx_get_clks(&pdev->dev);
+	if (ret)
+		return ret;
 
-	ret = clk_prepare_enable(data->clk);
-	if (ret) {
-		dev_err(&pdev->dev,
-			"Failed to prepare or enable clock, err=%d\n", ret);
+	ret = imx_prepare_enable_clks(&pdev->dev);
+	if (ret)
 		return ret;
-	}
 
 	data->phy = devm_usb_get_phy_by_phandle(&pdev->dev, "fsl,usbphy", 0);
 	if (IS_ERR(data->phy)) {
@@ -212,8 +314,6 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 		goto disable_device;
 	}
 
-	platform_set_drvdata(pdev, data);
-
 	if (data->supports_runtime_pm) {
 		pm_runtime_set_active(&pdev->dev);
 		pm_runtime_enable(&pdev->dev);
@@ -226,7 +326,7 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 disable_device:
 	ci_hdrc_remove_device(data->ci_pdev);
 err_clk:
-	clk_disable_unprepare(data->clk);
+	imx_disable_unprepare_clks(&pdev->dev);
 	return ret;
 }
 
@@ -240,7 +340,7 @@ static int ci_hdrc_imx_remove(struct platform_device *pdev)
 		pm_runtime_put_noidle(&pdev->dev);
 	}
 	ci_hdrc_remove_device(data->ci_pdev);
-	clk_disable_unprepare(data->clk);
+	imx_disable_unprepare_clks(&pdev->dev);
 
 	return 0;
 }
@@ -252,7 +352,7 @@ static int imx_controller_suspend(struct device *dev)
 
 	dev_dbg(dev, "at %s\n", __func__);
 
-	clk_disable_unprepare(data->clk);
+	imx_disable_unprepare_clks(dev);
 	data->in_lpm = true;
 
 	return 0;
@@ -270,7 +370,7 @@ static int imx_controller_resume(struct device *dev)
 		return 0;
 	}
 
-	ret = clk_prepare_enable(data->clk);
+	ret = imx_prepare_enable_clks(dev);
 	if (ret)
 		return ret;
 
@@ -285,7 +385,7 @@ static int imx_controller_resume(struct device *dev)
 	return 0;
 
 clk_disable:
-	clk_disable_unprepare(data->clk);
+	imx_disable_unprepare_clks(dev);
 	return ret;
 }
 
diff --git a/drivers/usb/chipidea/debug.c b/drivers/usb/chipidea/debug.c
index 080b7be3daf0..58c8485a0715 100644
--- a/drivers/usb/chipidea/debug.c
+++ b/drivers/usb/chipidea/debug.c
@@ -322,8 +322,10 @@ static ssize_t ci_role_write(struct file *file, const char __user *ubuf,
 		return -EINVAL;
 
 	pm_runtime_get_sync(ci->dev);
+	disable_irq(ci->irq);
 	ci_role_stop(ci);
 	ret = ci_role_start(ci, role);
+	enable_irq(ci->irq);
 	pm_runtime_put_sync(ci->dev);
 
 	return ret ? ret : count;
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index 8223fe73ea85..391a1225b0ba 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -1751,6 +1751,22 @@ static int ci_udc_start(struct usb_gadget *gadget,
 	return retval;
 }
 
+static void ci_udc_stop_for_otg_fsm(struct ci_hdrc *ci)
+{
+	if (!ci_otg_is_fsm_mode(ci))
+		return;
+
+	mutex_lock(&ci->fsm.lock);
+	if (ci->fsm.otg->state == OTG_STATE_A_PERIPHERAL) {
+		ci->fsm.a_bidl_adis_tmout = 1;
+		ci_hdrc_otg_fsm_start(ci);
+	} else if (ci->fsm.otg->state == OTG_STATE_B_PERIPHERAL) {
+		ci->fsm.protocol = PROTO_UNDEF;
+		ci->fsm.otg->state = OTG_STATE_UNDEFINED;
+	}
+	mutex_unlock(&ci->fsm.lock);
+}
+
 /**
  * ci_udc_stop: unregister a gadget driver
  */
@@ -1775,6 +1791,7 @@ static int ci_udc_stop(struct usb_gadget *gadget)
 	ci->driver = NULL;
 	spin_unlock_irqrestore(&ci->lock, flags);
 
+	ci_udc_stop_for_otg_fsm(ci);
 	return 0;
 }
 
diff --git a/drivers/usb/chipidea/usbmisc_imx.c b/drivers/usb/chipidea/usbmisc_imx.c
index fcea4eb36eee..ab8b027e8cc8 100644
--- a/drivers/usb/chipidea/usbmisc_imx.c
+++ b/drivers/usb/chipidea/usbmisc_imx.c
@@ -500,7 +500,11 @@ static int usbmisc_imx_probe(struct platform_device *pdev)
 {
 	struct resource	*res;
 	struct imx_usbmisc *data;
-	struct of_device_id *tmp_dev;
+	const struct of_device_id *of_id;
+
+	of_id = of_match_device(usbmisc_imx_dt_ids, &pdev->dev);
+	if (!of_id)
+		return -ENODEV;
 
 	data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
@@ -513,9 +517,7 @@ static int usbmisc_imx_probe(struct platform_device *pdev)
 	if (IS_ERR(data->base))
 		return PTR_ERR(data->base);
 
-	tmp_dev = (struct of_device_id *)
-		of_match_device(usbmisc_imx_dt_ids, &pdev->dev);
-	data->ops = (const struct usbmisc_ops *)tmp_dev->data;
+	data->ops = (const struct usbmisc_ops *)of_id->data;
 	platform_set_drvdata(pdev, data);
 
 	return 0;
diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c
index 433bbc34a8a4..071964c7847f 100644
--- a/drivers/usb/class/usblp.c
+++ b/drivers/usb/class/usblp.c
@@ -884,11 +884,11 @@ static int usblp_wwait(struct usblp *usblp, int nonblock)
 
 	add_wait_queue(&usblp->wwait, &waita);
 	for (;;) {
-		set_current_state(TASK_INTERRUPTIBLE);
 		if (mutex_lock_interruptible(&usblp->mut)) {
 			rc = -EINTR;
 			break;
 		}
+		set_current_state(TASK_INTERRUPTIBLE);
 		rc = usblp_wtest(usblp, nonblock);
 		mutex_unlock(&usblp->mut);
 		if (rc <= 0)
diff --git a/drivers/usb/core/Kconfig b/drivers/usb/core/Kconfig
index a99c89e78126..dd280108758f 100644
--- a/drivers/usb/core/Kconfig
+++ b/drivers/usb/core/Kconfig
@@ -77,8 +77,7 @@ config USB_OTG_BLACKLIST_HUB
 
 config USB_OTG_FSM
 	tristate "USB 2.0 OTG FSM implementation"
-	depends on USB
-	select USB_OTG
+	depends on USB && USB_OTG
 	select USB_PHY
 	help
 	  Implements OTG Finite State Machine as specified in On-The-Go
diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c
index e79baf73c234..571c21727ff9 100644
--- a/drivers/usb/dwc2/hcd.c
+++ b/drivers/usb/dwc2/hcd.c
@@ -324,12 +324,13 @@ void dwc2_hcd_disconnect(struct dwc2_hsotg *hsotg)
  */
 static void dwc2_hcd_rem_wakeup(struct dwc2_hsotg *hsotg)
 {
-	if (hsotg->lx_state == DWC2_L2) {
+	if (hsotg->bus_suspended) {
 		hsotg->flags.b.port_suspend_change = 1;
 		usb_hcd_resume_root_hub(hsotg->priv);
-	} else {
-		hsotg->flags.b.port_l1_change = 1;
 	}
+
+	if (hsotg->lx_state == DWC2_L1)
+		hsotg->flags.b.port_l1_change = 1;
 }
 
 /**
@@ -1428,8 +1429,8 @@ static void dwc2_wakeup_detected(unsigned long data)
 	dev_dbg(hsotg->dev, "Clear Resume: HPRT0=%0x\n",
 		dwc2_readl(hsotg->regs + HPRT0));
 
-	hsotg->bus_suspended = 0;
 	dwc2_hcd_rem_wakeup(hsotg);
+	hsotg->bus_suspended = 0;
 
 	/* Change to L0 state */
 	hsotg->lx_state = DWC2_L0;
diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c
index 5859b0fa19ee..e61d773cf65e 100644
--- a/drivers/usb/dwc2/platform.c
+++ b/drivers/usb/dwc2/platform.c
@@ -108,7 +108,8 @@ static const struct dwc2_core_params params_rk3066 = {
 	.host_ls_low_power_phy_clk	= -1,
 	.ts_dline			= -1,
 	.reload_ctl			= -1,
-	.ahbcfg				= 0x7, /* INCR16 */
+	.ahbcfg				= GAHBCFG_HBSTLEN_INCR16 <<
+					  GAHBCFG_HBSTLEN_SHIFT,
 	.uframe_sched			= -1,
 	.external_id_pin_ctl		= -1,
 	.hibernation			= -1,
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 77a622cb48ab..009d83048c8c 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -34,6 +34,8 @@
 #define PCI_DEVICE_ID_INTEL_BSW			0x22b7
 #define PCI_DEVICE_ID_INTEL_SPTLP		0x9d30
 #define PCI_DEVICE_ID_INTEL_SPTH		0xa130
+#define PCI_DEVICE_ID_INTEL_BXT			0x0aaa
+#define PCI_DEVICE_ID_INTEL_APL			0x5aaa
 
 static const struct acpi_gpio_params reset_gpios = { 0, 0, false };
 static const struct acpi_gpio_params cs_gpios = { 1, 0, false };
@@ -210,6 +212,8 @@ static const struct pci_device_id dwc3_pci_id_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MRFLD), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SPTLP), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SPTH), },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BXT), },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_APL), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_NL_USB), },
 	{  }	/* Terminating Entry */
 };
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 55ba447fdf8b..e24a01cc98df 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -2744,12 +2744,34 @@ int dwc3_gadget_init(struct dwc3 *dwc)
 	}
 
 	dwc->gadget.ops			= &dwc3_gadget_ops;
-	dwc->gadget.max_speed		= USB_SPEED_SUPER;
 	dwc->gadget.speed		= USB_SPEED_UNKNOWN;
 	dwc->gadget.sg_supported	= true;
 	dwc->gadget.name		= "dwc3-gadget";
 
 	/*
+	 * FIXME We might be setting max_speed to <SUPER, however versions
+	 * <2.20a of dwc3 have an issue with metastability (documented
+	 * elsewhere in this driver) which tells us we can't set max speed to
+	 * anything lower than SUPER.
+	 *
+	 * Because gadget.max_speed is only used by composite.c and function
+	 * drivers (i.e. it won't go into dwc3's registers) we are allowing this
+	 * to happen so we avoid sending SuperSpeed Capability descriptor
+	 * together with our BOS descriptor as that could confuse host into
+	 * thinking we can handle super speed.
+	 *
+	 * Note that, in fact, we won't even support GetBOS requests when speed
+	 * is less than super speed because we don't have means, yet, to tell
+	 * composite.c that we are USB 2.0 + LPM ECN.
+	 */
+	if (dwc->revision < DWC3_REVISION_220A)
+		dwc3_trace(trace_dwc3_gadget,
+				"Changing max_speed on rev %08x\n",
+				dwc->revision);
+
+	dwc->gadget.max_speed		= dwc->maximum_speed;
+
+	/*
 	 * Per databook, DWC3 needs buffer size to be aligned to MaxPacketSize
 	 * on ep out.
 	 */
diff --git a/drivers/usb/gadget/function/f_loopback.c b/drivers/usb/gadget/function/f_loopback.c
index 23933bdf2d9d..ddc3aad886b7 100644
--- a/drivers/usb/gadget/function/f_loopback.c
+++ b/drivers/usb/gadget/function/f_loopback.c
@@ -329,7 +329,7 @@ static int alloc_requests(struct usb_composite_dev *cdev,
 	for (i = 0; i < loop->qlen && result == 0; i++) {
 		result = -ENOMEM;
 
-		in_req = usb_ep_alloc_request(loop->in_ep, GFP_KERNEL);
+		in_req = usb_ep_alloc_request(loop->in_ep, GFP_ATOMIC);
 		if (!in_req)
 			goto fail;
 
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index f0f2b066ac08..f92f5aff0dd5 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -1633,7 +1633,7 @@ static irqreturn_t usba_udc_irq(int irq, void *devid)
 	spin_lock(&udc->lock);
 
 	int_enb = usba_int_enb_get(udc);
-	status = usba_readl(udc, INT_STA) & int_enb;
+	status = usba_readl(udc, INT_STA) & (int_enb | USBA_HIGH_SPEED);
 	DBG(DBG_INT, "irq, status=%#08x\n", status);
 
 	if (status & USBA_DET_SUSPEND) {
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 5d2d7e954bd4..0230965fb78c 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -782,12 +782,15 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd,
 			status |= USB_PORT_STAT_SUSPEND;
 		}
 	}
-	if ((raw_port_status & PORT_PLS_MASK) == XDEV_U0
-			&& (raw_port_status & PORT_POWER)
-			&& (bus_state->suspended_ports & (1 << wIndex))) {
-		bus_state->suspended_ports &= ~(1 << wIndex);
-		if (hcd->speed < HCD_USB3)
-			bus_state->port_c_suspend |= 1 << wIndex;
+	if ((raw_port_status & PORT_PLS_MASK) == XDEV_U0 &&
+	    (raw_port_status & PORT_POWER)) {
+		if (bus_state->suspended_ports & (1 << wIndex)) {
+			bus_state->suspended_ports &= ~(1 << wIndex);
+			if (hcd->speed < HCD_USB3)
+				bus_state->port_c_suspend |= 1 << wIndex;
+		}
+		bus_state->resume_done[wIndex] = 0;
+		clear_bit(wIndex, &bus_state->resuming_ports);
 	}
 	if (raw_port_status & PORT_CONNECT) {
 		status |= USB_PORT_STAT_CONNECTION;
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index fa836251ca21..6c5e8133cf87 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -3896,28 +3896,6 @@ cleanup:
 	return ret;
 }
 
-static int ep_ring_is_processing(struct xhci_hcd *xhci,
-		int slot_id, unsigned int ep_index)
-{
-	struct xhci_virt_device *xdev;
-	struct xhci_ring *ep_ring;
-	struct xhci_ep_ctx *ep_ctx;
-	struct xhci_virt_ep *xep;
-	dma_addr_t hw_deq;
-
-	xdev = xhci->devs[slot_id];
-	xep = &xhci->devs[slot_id]->eps[ep_index];
-	ep_ring = xep->ring;
-	ep_ctx = xhci_get_ep_ctx(xhci, xdev->out_ctx, ep_index);
-
-	if ((le32_to_cpu(ep_ctx->ep_info) & EP_STATE_MASK) != EP_STATE_RUNNING)
-		return 0;
-
-	hw_deq = le64_to_cpu(ep_ctx->deq) & ~EP_CTX_CYCLE_MASK;
-	return (hw_deq !=
-		xhci_trb_virt_to_dma(ep_ring->enq_seg, ep_ring->enqueue));
-}
-
 /*
  * Check transfer ring to guarantee there is enough room for the urb.
  * Update ISO URB start_frame and interval.
@@ -3983,10 +3961,12 @@ int xhci_queue_isoc_tx_prepare(struct xhci_hcd *xhci, gfp_t mem_flags,
 	}
 
 	/* Calculate the start frame and put it in urb->start_frame. */
-	if (HCC_CFC(xhci->hcc_params) &&
-			ep_ring_is_processing(xhci, slot_id, ep_index)) {
-		urb->start_frame = xep->next_frame_id;
-		goto skip_start_over;
+	if (HCC_CFC(xhci->hcc_params) && !list_empty(&ep_ring->td_list)) {
+		if ((le32_to_cpu(ep_ctx->ep_info) & EP_STATE_MASK) ==
+				EP_STATE_RUNNING) {
+			urb->start_frame = xep->next_frame_id;
+			goto skip_start_over;
+		}
 	}
 
 	start_frame = readl(&xhci->run_regs->microframe_index);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 6e7dc6f93978..dfa44d3e8eee 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -175,6 +175,16 @@ int xhci_reset(struct xhci_hcd *xhci)
 	command |= CMD_RESET;
 	writel(command, &xhci->op_regs->command);
 
+	/* Existing Intel xHCI controllers require a delay of 1 mS,
+	 * after setting the CMD_RESET bit, and before accessing any
+	 * HC registers. This allows the HC to complete the
+	 * reset operation and be ready for HC register access.
+	 * Without this delay, the subsequent HC register access,
+	 * may result in a system hang very rarely.
+	 */
+	if (xhci->quirks & XHCI_INTEL_HOST)
+		udelay(1000);
+
 	ret = xhci_handshake(&xhci->op_regs->command,
 			CMD_RESET, 0, 10 * 1000 * 1000);
 	if (ret)
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index ba13529cbd52..18cfc0a361cb 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -132,7 +132,7 @@ static inline struct musb *dev_to_musb(struct device *dev)
 /*-------------------------------------------------------------------------*/
 
 #ifndef CONFIG_BLACKFIN
-static int musb_ulpi_read(struct usb_phy *phy, u32 offset)
+static int musb_ulpi_read(struct usb_phy *phy, u32 reg)
 {
 	void __iomem *addr = phy->io_priv;
 	int	i = 0;
@@ -151,7 +151,7 @@ static int musb_ulpi_read(struct usb_phy *phy, u32 offset)
 	 * ULPICarKitControlDisableUTMI after clearing POWER_SUSPENDM.
 	 */
 
-	musb_writeb(addr, MUSB_ULPI_REG_ADDR, (u8)offset);
+	musb_writeb(addr, MUSB_ULPI_REG_ADDR, (u8)reg);
 	musb_writeb(addr, MUSB_ULPI_REG_CONTROL,
 			MUSB_ULPI_REG_REQ | MUSB_ULPI_RDN_WR);
 
@@ -176,7 +176,7 @@ out:
 	return ret;
 }
 
-static int musb_ulpi_write(struct usb_phy *phy, u32 offset, u32 data)
+static int musb_ulpi_write(struct usb_phy *phy, u32 val, u32 reg)
 {
 	void __iomem *addr = phy->io_priv;
 	int	i = 0;
@@ -191,8 +191,8 @@ static int musb_ulpi_write(struct usb_phy *phy, u32 offset, u32 data)
 	power &= ~MUSB_POWER_SUSPENDM;
 	musb_writeb(addr, MUSB_POWER, power);
 
-	musb_writeb(addr, MUSB_ULPI_REG_ADDR, (u8)offset);
-	musb_writeb(addr, MUSB_ULPI_REG_DATA, (u8)data);
+	musb_writeb(addr, MUSB_ULPI_REG_ADDR, (u8)reg);
+	musb_writeb(addr, MUSB_ULPI_REG_DATA, (u8)val);
 	musb_writeb(addr, MUSB_ULPI_REG_CONTROL, MUSB_ULPI_REG_REQ);
 
 	while (!(musb_readb(addr, MUSB_ULPI_REG_CONTROL)
@@ -1668,7 +1668,7 @@ EXPORT_SYMBOL_GPL(musb_interrupt);
 static bool use_dma = 1;
 
 /* "modprobe ... use_dma=0" etc */
-module_param(use_dma, bool, 0);
+module_param(use_dma, bool, 0644);
 MODULE_PARM_DESC(use_dma, "enable/disable use of DMA");
 
 void musb_dma_completion(struct musb *musb, u8 epnum, u8 transmit)
diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index 26c65e66cc0f..795a45b1b25b 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -112,22 +112,32 @@ static void musb_h_tx_flush_fifo(struct musb_hw_ep *ep)
 	struct musb	*musb = ep->musb;
 	void __iomem	*epio = ep->regs;
 	u16		csr;
-	u16		lastcsr = 0;
 	int		retries = 1000;
 
 	csr = musb_readw(epio, MUSB_TXCSR);
 	while (csr & MUSB_TXCSR_FIFONOTEMPTY) {
-		if (csr != lastcsr)
-			dev_dbg(musb->controller, "Host TX FIFONOTEMPTY csr: %02x\n", csr);
-		lastcsr = csr;
 		csr |= MUSB_TXCSR_FLUSHFIFO | MUSB_TXCSR_TXPKTRDY;
 		musb_writew(epio, MUSB_TXCSR, csr);
 		csr = musb_readw(epio, MUSB_TXCSR);
-		if (WARN(retries-- < 1,
+
+		/*
+		 * FIXME: sometimes the tx fifo flush failed, it has been
+		 * observed during device disconnect on AM335x.
+		 *
+		 * To reproduce the issue, ensure tx urb(s) are queued when
+		 * unplug the usb device which is connected to AM335x usb
+		 * host port.
+		 *
+		 * I found using a usb-ethernet device and running iperf
+		 * (client on AM335x) has very high chance to trigger it.
+		 *
+		 * Better to turn on dev_dbg() in musb_cleanup_urb() with
+		 * CPPI enabled to see the issue when aborting the tx channel.
+		 */
+		if (dev_WARN_ONCE(musb->controller, retries-- < 1,
 				"Could not flush host TX%d fifo: csr: %04x\n",
 				ep->epnum, csr))
 			return;
-		mdelay(1);
 	}
 }
 
diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig
index 173132416170..22e8ecb6bfbd 100644
--- a/drivers/usb/phy/Kconfig
+++ b/drivers/usb/phy/Kconfig
@@ -21,7 +21,6 @@ config AB8500_USB
 config FSL_USB2_OTG
 	bool "Freescale USB OTG Transceiver Driver"
 	depends on USB_EHCI_FSL && USB_FSL_USB2 && USB_OTG_FSM && PM
-	select USB_OTG
 	select USB_PHY
 	help
 	  Enable this to support Freescale USB OTG transceiver.
@@ -168,8 +167,7 @@ config USB_QCOM_8X16_PHY
 
 config USB_MV_OTG
 	tristate "Marvell USB OTG support"
-	depends on USB_EHCI_MV && USB_MV_UDC && PM
-	select USB_OTG
+	depends on USB_EHCI_MV && USB_MV_UDC && PM && USB_OTG
 	select USB_PHY
 	help
 	  Say Y here if you want to build Marvell USB OTG transciever
diff --git a/drivers/usb/phy/phy-mxs-usb.c b/drivers/usb/phy/phy-mxs-usb.c
index 4d863ebc117c..b7536af777ab 100644
--- a/drivers/usb/phy/phy-mxs-usb.c
+++ b/drivers/usb/phy/phy-mxs-usb.c
@@ -452,10 +452,13 @@ static int mxs_phy_probe(struct platform_device *pdev)
 	struct clk *clk;
 	struct mxs_phy *mxs_phy;
 	int ret;
-	const struct of_device_id *of_id =
-			of_match_device(mxs_phy_dt_ids, &pdev->dev);
+	const struct of_device_id *of_id;
 	struct device_node *np = pdev->dev.of_node;
 
+	of_id = of_match_device(mxs_phy_dt_ids, &pdev->dev);
+	if (!of_id)
+		return -ENODEV;
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(base))
diff --git a/drivers/usb/phy/phy-omap-otg.c b/drivers/usb/phy/phy-omap-otg.c
index 1270906ccb95..c4bf2de6d14e 100644
--- a/drivers/usb/phy/phy-omap-otg.c
+++ b/drivers/usb/phy/phy-omap-otg.c
@@ -105,7 +105,6 @@ static int omap_otg_probe(struct platform_device *pdev)
 	extcon = extcon_get_extcon_dev(config->extcon);
 	if (!extcon)
 		return -EPROBE_DEFER;
-	otg_dev->extcon = extcon;
 
 	otg_dev = devm_kzalloc(&pdev->dev, sizeof(*otg_dev), GFP_KERNEL);
 	if (!otg_dev)
@@ -115,6 +114,7 @@ static int omap_otg_probe(struct platform_device *pdev)
 	if (IS_ERR(otg_dev->base))
 		return PTR_ERR(otg_dev->base);
 
+	otg_dev->extcon = extcon;
 	otg_dev->id_nb.notifier_call = omap_otg_id_notifier;
 	otg_dev->vbus_nb.notifier_call = omap_otg_vbus_notifier;
 
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 685fef71d3d1..f2280606b73c 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -161,6 +161,7 @@ static void option_instat_callback(struct urb *urb);
 #define NOVATELWIRELESS_PRODUCT_HSPA_EMBEDDED_HIGHSPEED	0x9001
 #define NOVATELWIRELESS_PRODUCT_E362		0x9010
 #define NOVATELWIRELESS_PRODUCT_E371		0x9011
+#define NOVATELWIRELESS_PRODUCT_U620L		0x9022
 #define NOVATELWIRELESS_PRODUCT_G2		0xA010
 #define NOVATELWIRELESS_PRODUCT_MC551		0xB001
 
@@ -354,6 +355,7 @@ static void option_instat_callback(struct urb *urb);
 /* This is the 4G XS Stick W14 a.k.a. Mobilcom Debitel Surf-Stick *
  * It seems to contain a Qualcomm QSC6240/6290 chipset            */
 #define FOUR_G_SYSTEMS_PRODUCT_W14		0x9603
+#define FOUR_G_SYSTEMS_PRODUCT_W100		0x9b01
 
 /* iBall 3.5G connect wireless modem */
 #define IBALL_3_5G_CONNECT			0x9605
@@ -519,6 +521,11 @@ static const struct option_blacklist_info four_g_w14_blacklist = {
 	.sendsetup = BIT(0) | BIT(1),
 };
 
+static const struct option_blacklist_info four_g_w100_blacklist = {
+	.sendsetup = BIT(1) | BIT(2),
+	.reserved = BIT(3),
+};
+
 static const struct option_blacklist_info alcatel_x200_blacklist = {
 	.sendsetup = BIT(0) | BIT(1),
 	.reserved = BIT(4),
@@ -1052,6 +1059,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_MC551, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_E362, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_E371, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_U620L, 0xff, 0x00, 0x00) },
 
 	{ USB_DEVICE(AMOI_VENDOR_ID, AMOI_PRODUCT_H01) },
 	{ USB_DEVICE(AMOI_VENDOR_ID, AMOI_PRODUCT_H01A) },
@@ -1641,6 +1649,9 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(LONGCHEER_VENDOR_ID, FOUR_G_SYSTEMS_PRODUCT_W14),
   	  .driver_info = (kernel_ulong_t)&four_g_w14_blacklist
   	},
+	{ USB_DEVICE(LONGCHEER_VENDOR_ID, FOUR_G_SYSTEMS_PRODUCT_W100),
+	  .driver_info = (kernel_ulong_t)&four_g_w100_blacklist
+	},
 	{ USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, SPEEDUP_PRODUCT_SU9800, 0xff) },
 	{ USB_DEVICE(LONGCHEER_VENDOR_ID, ZOOM_PRODUCT_4597) },
 	{ USB_DEVICE(LONGCHEER_VENDOR_ID, IBALL_3_5G_CONNECT) },
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index 5022fcfa0260..9919d2a9faf2 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -22,6 +22,8 @@
 #define DRIVER_AUTHOR "Qualcomm Inc"
 #define DRIVER_DESC "Qualcomm USB Serial driver"
 
+#define QUECTEL_EC20_PID	0x9215
+
 /* standard device layouts supported by this driver */
 enum qcserial_layouts {
 	QCSERIAL_G2K = 0,	/* Gobi 2000 */
@@ -171,6 +173,38 @@ static const struct usb_device_id id_table[] = {
 };
 MODULE_DEVICE_TABLE(usb, id_table);
 
+static int handle_quectel_ec20(struct device *dev, int ifnum)
+{
+	int altsetting = 0;
+
+	/*
+	 * Quectel EC20 Mini PCIe LTE module layout:
+	 * 0: DM/DIAG (use libqcdm from ModemManager for communication)
+	 * 1: NMEA
+	 * 2: AT-capable modem port
+	 * 3: Modem interface
+	 * 4: NDIS
+	 */
+	switch (ifnum) {
+	case 0:
+		dev_dbg(dev, "Quectel EC20 DM/DIAG interface found\n");
+		break;
+	case 1:
+		dev_dbg(dev, "Quectel EC20 NMEA GPS interface found\n");
+		break;
+	case 2:
+	case 3:
+		dev_dbg(dev, "Quectel EC20 Modem port found\n");
+		break;
+	case 4:
+		/* Don't claim the QMI/net interface */
+		altsetting = -1;
+		break;
+	}
+
+	return altsetting;
+}
+
 static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id)
 {
 	struct usb_host_interface *intf = serial->interface->cur_altsetting;
@@ -181,6 +215,10 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id)
 	int altsetting = -1;
 	bool sendsetup = false;
 
+	/* we only support vendor specific functions */
+	if (intf->desc.bInterfaceClass != USB_CLASS_VENDOR_SPEC)
+		goto done;
+
 	nintf = serial->dev->actconfig->desc.bNumInterfaces;
 	dev_dbg(dev, "Num Interfaces = %d\n", nintf);
 	ifnum = intf->desc.bInterfaceNumber;
@@ -240,6 +278,12 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id)
 			altsetting = -1;
 		break;
 	case QCSERIAL_G2K:
+		/* handle non-standard layouts */
+		if (nintf == 5 && id->idProduct == QUECTEL_EC20_PID) {
+			altsetting = handle_quectel_ec20(dev, ifnum);
+			goto done;
+		}
+
 		/*
 		 * Gobi 2K+ USB layout:
 		 * 0: QMI/net
@@ -301,29 +345,39 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id)
 		break;
 	case QCSERIAL_HWI:
 		/*
-		 * Huawei layout:
-		 * 0: AT-capable modem port
-		 * 1: DM/DIAG
-		 * 2: AT-capable modem port
-		 * 3: CCID-compatible PCSC interface
-		 * 4: QMI/net
-		 * 5: NMEA
+		 * Huawei devices map functions by subclass + protocol
+		 * instead of interface numbers. The protocol identify
+		 * a specific function, while the subclass indicate a
+		 * specific firmware source
+		 *
+		 * This is a blacklist of functions known to be
+		 * non-serial.  The rest are assumed to be serial and
+		 * will be handled by this driver
 		 */
-		switch (ifnum) {
-		case 0:
-		case 2:
-			dev_dbg(dev, "Modem port found\n");
-			break;
-		case 1:
-			dev_dbg(dev, "DM/DIAG interface found\n");
-			break;
-		case 5:
-			dev_dbg(dev, "NMEA GPS interface found\n");
-			break;
-		default:
-			/* don't claim any unsupported interface */
+		switch (intf->desc.bInterfaceProtocol) {
+			/* QMI combined (qmi_wwan) */
+		case 0x07:
+		case 0x37:
+		case 0x67:
+			/* QMI data (qmi_wwan) */
+		case 0x08:
+		case 0x38:
+		case 0x68:
+			/* QMI control (qmi_wwan) */
+		case 0x09:
+		case 0x39:
+		case 0x69:
+			/* NCM like (huawei_cdc_ncm) */
+		case 0x16:
+		case 0x46:
+		case 0x76:
 			altsetting = -1;
 			break;
+		default:
+			dev_dbg(dev, "Huawei type serial port found (%02x/%02x/%02x)\n",
+				intf->desc.bInterfaceClass,
+				intf->desc.bInterfaceSubClass,
+				intf->desc.bInterfaceProtocol);
 		}
 		break;
 	default:
diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c
index e9da41d9fe7f..2694df2f4559 100644
--- a/drivers/usb/serial/ti_usb_3410_5052.c
+++ b/drivers/usb/serial/ti_usb_3410_5052.c
@@ -159,6 +159,7 @@ static const struct usb_device_id ti_id_table_3410[] = {
 	{ USB_DEVICE(ABBOTT_VENDOR_ID, ABBOTT_STEREO_PLUG_ID) },
 	{ USB_DEVICE(ABBOTT_VENDOR_ID, ABBOTT_STRIP_PORT_ID) },
 	{ USB_DEVICE(TI_VENDOR_ID, FRI2_PRODUCT_ID) },
+	{ USB_DEVICE(HONEYWELL_VENDOR_ID, HONEYWELL_HGI80_PRODUCT_ID) },
 	{ }	/* terminator */
 };
 
@@ -191,6 +192,7 @@ static const struct usb_device_id ti_id_table_combined[] = {
 	{ USB_DEVICE(ABBOTT_VENDOR_ID, ABBOTT_PRODUCT_ID) },
 	{ USB_DEVICE(ABBOTT_VENDOR_ID, ABBOTT_STRIP_PORT_ID) },
 	{ USB_DEVICE(TI_VENDOR_ID, FRI2_PRODUCT_ID) },
+	{ USB_DEVICE(HONEYWELL_VENDOR_ID, HONEYWELL_HGI80_PRODUCT_ID) },
 	{ }	/* terminator */
 };
 
diff --git a/drivers/usb/serial/ti_usb_3410_5052.h b/drivers/usb/serial/ti_usb_3410_5052.h
index 4a2423e84d55..98f35c656c02 100644
--- a/drivers/usb/serial/ti_usb_3410_5052.h
+++ b/drivers/usb/serial/ti_usb_3410_5052.h
@@ -56,6 +56,10 @@
 #define ABBOTT_PRODUCT_ID		ABBOTT_STEREO_PLUG_ID
 #define ABBOTT_STRIP_PORT_ID		0x3420
 
+/* Honeywell vendor and product IDs */
+#define HONEYWELL_VENDOR_ID		0x10ac
+#define HONEYWELL_HGI80_PRODUCT_ID	0x0102  /* Honeywell HGI80 */
+
 /* Commands */
 #define TI_GET_VERSION			0x01
 #define TI_GET_PORT_STATUS		0x02
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 7a8a6c6952e9..1c427beffadd 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -446,7 +446,7 @@ config MAX63XX_WATCHDOG
 
 config IMX2_WDT
 	tristate "IMX2+ Watchdog"
-	depends on ARCH_MXC
+	depends on ARCH_MXC || ARCH_LAYERSCAPE
 	select REGMAP_MMIO
 	select WATCHDOG_CORE
 	help
diff --git a/drivers/watchdog/mtk_wdt.c b/drivers/watchdog/mtk_wdt.c
index 6ad9df948711..b751f43d76ed 100644
--- a/drivers/watchdog/mtk_wdt.c
+++ b/drivers/watchdog/mtk_wdt.c
@@ -123,6 +123,7 @@ static int mtk_wdt_stop(struct watchdog_device *wdt_dev)
 
 	reg = readl(wdt_base + WDT_MODE);
 	reg &= ~WDT_MODE_EN;
+	reg |= WDT_MODE_KEY;
 	iowrite32(reg, wdt_base + WDT_MODE);
 
 	return 0;
diff --git a/drivers/watchdog/omap_wdt.c b/drivers/watchdog/omap_wdt.c
index d96bee017fd3..6f17c935a6cf 100644
--- a/drivers/watchdog/omap_wdt.c
+++ b/drivers/watchdog/omap_wdt.c
@@ -205,7 +205,7 @@ static int omap_wdt_set_timeout(struct watchdog_device *wdog,
 
 static unsigned int omap_wdt_get_timeleft(struct watchdog_device *wdog)
 {
-	struct omap_wdt_dev *wdev = watchdog_get_drvdata(wdog);
+	struct omap_wdt_dev *wdev = to_omap_wdt_dev(wdog);
 	void __iomem *base = wdev->base;
 	u32 value;
 
diff --git a/drivers/watchdog/pnx4008_wdt.c b/drivers/watchdog/pnx4008_wdt.c
index 4224b3ec83a5..313cd1c6fda0 100644
--- a/drivers/watchdog/pnx4008_wdt.c
+++ b/drivers/watchdog/pnx4008_wdt.c
@@ -80,7 +80,7 @@ static unsigned int heartbeat = DEFAULT_HEARTBEAT;
 
 static DEFINE_SPINLOCK(io_lock);
 static void __iomem	*wdt_base;
-struct clk		*wdt_clk;
+static struct clk	*wdt_clk;
 
 static int pnx4008_wdt_start(struct watchdog_device *wdd)
 {
@@ -161,7 +161,7 @@ static int pnx4008_wdt_probe(struct platform_device *pdev)
 	if (IS_ERR(wdt_clk))
 		return PTR_ERR(wdt_clk);
 
-	ret = clk_enable(wdt_clk);
+	ret = clk_prepare_enable(wdt_clk);
 	if (ret)
 		return ret;
 
@@ -184,7 +184,7 @@ static int pnx4008_wdt_probe(struct platform_device *pdev)
 	return 0;
 
 disable_clk:
-	clk_disable(wdt_clk);
+	clk_disable_unprepare(wdt_clk);
 	return ret;
 }
 
@@ -192,7 +192,7 @@ static int pnx4008_wdt_remove(struct platform_device *pdev)
 {
 	watchdog_unregister_device(&pnx4008_wdd);
 
-	clk_disable(wdt_clk);
+	clk_disable_unprepare(wdt_clk);
 
 	return 0;
 }
diff --git a/drivers/watchdog/tegra_wdt.c b/drivers/watchdog/tegra_wdt.c
index 7f97cdd53f29..9ec57608da82 100644
--- a/drivers/watchdog/tegra_wdt.c
+++ b/drivers/watchdog/tegra_wdt.c
@@ -140,8 +140,10 @@ static int tegra_wdt_set_timeout(struct watchdog_device *wdd,
 {
 	wdd->timeout = timeout;
 
-	if (watchdog_active(wdd))
+	if (watchdog_active(wdd)) {
+		tegra_wdt_stop(wdd);
 		return tegra_wdt_start(wdd);
+	}
 
 	return 0;
 }
diff --git a/drivers/watchdog/w83977f_wdt.c b/drivers/watchdog/w83977f_wdt.c
index 91bf55a20024..20e2bba10400 100644
--- a/drivers/watchdog/w83977f_wdt.c
+++ b/drivers/watchdog/w83977f_wdt.c
@@ -224,7 +224,7 @@ static int wdt_keepalive(void)
 
 static int wdt_set_timeout(int t)
 {
-	int tmrval;
+	unsigned int tmrval;
 
 	/*
 	 * Convert seconds to watchdog counter time units, rounding up.
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 849500e4e14d..524c22146429 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -39,6 +39,7 @@
 #include <asm/irq.h>
 #include <asm/idle.h>
 #include <asm/io_apic.h>
+#include <asm/i8259.h>
 #include <asm/xen/pci.h>
 #endif
 #include <asm/sync_bitops.h>
@@ -420,7 +421,7 @@ static int __must_check xen_allocate_irq_gsi(unsigned gsi)
 		return xen_allocate_irq_dynamic();
 
 	/* Legacy IRQ descriptors are already allocated by the arch. */
-	if (gsi < NR_IRQS_LEGACY)
+	if (gsi < nr_legacy_irqs())
 		irq = gsi;
 	else
 		irq = irq_alloc_desc_at(gsi, -1);
@@ -446,7 +447,7 @@ static void xen_free_irq(unsigned irq)
 	kfree(info);
 
 	/* Legacy IRQ descriptors are managed by the arch. */
-	if (irq < NR_IRQS_LEGACY)
+	if (irq < nr_legacy_irqs())
 		return;
 
 	irq_free_desc(irq);
diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c
index 00f40f051d95..38272ad24551 100644
--- a/drivers/xen/evtchn.c
+++ b/drivers/xen/evtchn.c
@@ -49,6 +49,8 @@
 #include <linux/init.h>
 #include <linux/mutex.h>
 #include <linux/cpu.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
 
 #include <xen/xen.h>
 #include <xen/events.h>
@@ -58,10 +60,10 @@
 struct per_user_data {
 	struct mutex bind_mutex; /* serialize bind/unbind operations */
 	struct rb_root evtchns;
+	unsigned int nr_evtchns;
 
 	/* Notification ring, accessed via /dev/xen/evtchn. */
-#define EVTCHN_RING_SIZE     (PAGE_SIZE / sizeof(evtchn_port_t))
-#define EVTCHN_RING_MASK(_i) ((_i)&(EVTCHN_RING_SIZE-1))
+	unsigned int ring_size;
 	evtchn_port_t *ring;
 	unsigned int ring_cons, ring_prod, ring_overflow;
 	struct mutex ring_cons_mutex; /* protect against concurrent readers */
@@ -80,10 +82,41 @@ struct user_evtchn {
 	bool enabled;
 };
 
+static evtchn_port_t *evtchn_alloc_ring(unsigned int size)
+{
+	evtchn_port_t *ring;
+	size_t s = size * sizeof(*ring);
+
+	ring = kmalloc(s, GFP_KERNEL);
+	if (!ring)
+		ring = vmalloc(s);
+
+	return ring;
+}
+
+static void evtchn_free_ring(evtchn_port_t *ring)
+{
+	kvfree(ring);
+}
+
+static unsigned int evtchn_ring_offset(struct per_user_data *u,
+				       unsigned int idx)
+{
+	return idx & (u->ring_size - 1);
+}
+
+static evtchn_port_t *evtchn_ring_entry(struct per_user_data *u,
+					unsigned int idx)
+{
+	return u->ring + evtchn_ring_offset(u, idx);
+}
+
 static int add_evtchn(struct per_user_data *u, struct user_evtchn *evtchn)
 {
 	struct rb_node **new = &(u->evtchns.rb_node), *parent = NULL;
 
+	u->nr_evtchns++;
+
 	while (*new) {
 		struct user_evtchn *this;
 
@@ -107,6 +140,7 @@ static int add_evtchn(struct per_user_data *u, struct user_evtchn *evtchn)
 
 static void del_evtchn(struct per_user_data *u, struct user_evtchn *evtchn)
 {
+	u->nr_evtchns--;
 	rb_erase(&evtchn->node, &u->evtchns);
 	kfree(evtchn);
 }
@@ -144,8 +178,8 @@ static irqreturn_t evtchn_interrupt(int irq, void *data)
 
 	spin_lock(&u->ring_prod_lock);
 
-	if ((u->ring_prod - u->ring_cons) < EVTCHN_RING_SIZE) {
-		u->ring[EVTCHN_RING_MASK(u->ring_prod)] = evtchn->port;
+	if ((u->ring_prod - u->ring_cons) < u->ring_size) {
+		*evtchn_ring_entry(u, u->ring_prod) = evtchn->port;
 		wmb(); /* Ensure ring contents visible */
 		if (u->ring_cons == u->ring_prod++) {
 			wake_up_interruptible(&u->evtchn_wait);
@@ -200,10 +234,10 @@ static ssize_t evtchn_read(struct file *file, char __user *buf,
 	}
 
 	/* Byte lengths of two chunks. Chunk split (if any) is at ring wrap. */
-	if (((c ^ p) & EVTCHN_RING_SIZE) != 0) {
-		bytes1 = (EVTCHN_RING_SIZE - EVTCHN_RING_MASK(c)) *
+	if (((c ^ p) & u->ring_size) != 0) {
+		bytes1 = (u->ring_size - evtchn_ring_offset(u, c)) *
 			sizeof(evtchn_port_t);
-		bytes2 = EVTCHN_RING_MASK(p) * sizeof(evtchn_port_t);
+		bytes2 = evtchn_ring_offset(u, p) * sizeof(evtchn_port_t);
 	} else {
 		bytes1 = (p - c) * sizeof(evtchn_port_t);
 		bytes2 = 0;
@@ -219,7 +253,7 @@ static ssize_t evtchn_read(struct file *file, char __user *buf,
 
 	rc = -EFAULT;
 	rmb(); /* Ensure that we see the port before we copy it. */
-	if (copy_to_user(buf, &u->ring[EVTCHN_RING_MASK(c)], bytes1) ||
+	if (copy_to_user(buf, evtchn_ring_entry(u, c), bytes1) ||
 	    ((bytes2 != 0) &&
 	     copy_to_user(&buf[bytes1], &u->ring[0], bytes2)))
 		goto unlock_out;
@@ -278,6 +312,66 @@ static ssize_t evtchn_write(struct file *file, const char __user *buf,
 	return rc;
 }
 
+static int evtchn_resize_ring(struct per_user_data *u)
+{
+	unsigned int new_size;
+	evtchn_port_t *new_ring, *old_ring;
+	unsigned int p, c;
+
+	/*
+	 * Ensure the ring is large enough to capture all possible
+	 * events. i.e., one free slot for each bound event.
+	 */
+	if (u->nr_evtchns <= u->ring_size)
+		return 0;
+
+	if (u->ring_size == 0)
+		new_size = 64;
+	else
+		new_size = 2 * u->ring_size;
+
+	new_ring = evtchn_alloc_ring(new_size);
+	if (!new_ring)
+		return -ENOMEM;
+
+	old_ring = u->ring;
+
+	/*
+	 * Access to the ring contents is serialized by either the
+	 * prod /or/ cons lock so take both when resizing.
+	 */
+	mutex_lock(&u->ring_cons_mutex);
+	spin_lock_irq(&u->ring_prod_lock);
+
+	/*
+	 * Copy the old ring contents to the new ring.
+	 *
+	 * If the ring contents crosses the end of the current ring,
+	 * it needs to be copied in two chunks.
+	 *
+	 * +---------+    +------------------+
+	 * |34567  12| -> |       1234567    |
+	 * +-----p-c-+    +------------------+
+	 */
+	p = evtchn_ring_offset(u, u->ring_prod);
+	c = evtchn_ring_offset(u, u->ring_cons);
+	if (p < c) {
+		memcpy(new_ring + c, u->ring + c, (u->ring_size - c) * sizeof(*u->ring));
+		memcpy(new_ring + u->ring_size, u->ring, p * sizeof(*u->ring));
+	} else
+		memcpy(new_ring + c, u->ring + c, (p - c) * sizeof(*u->ring));
+
+	u->ring = new_ring;
+	u->ring_size = new_size;
+
+	spin_unlock_irq(&u->ring_prod_lock);
+	mutex_unlock(&u->ring_cons_mutex);
+
+	evtchn_free_ring(old_ring);
+
+	return 0;
+}
+
 static int evtchn_bind_to_user(struct per_user_data *u, int port)
 {
 	struct user_evtchn *evtchn;
@@ -305,6 +399,10 @@ static int evtchn_bind_to_user(struct per_user_data *u, int port)
 	if (rc < 0)
 		goto err;
 
+	rc = evtchn_resize_ring(u);
+	if (rc < 0)
+		goto err;
+
 	rc = bind_evtchn_to_irqhandler(port, evtchn_interrupt, 0,
 				       u->name, evtchn);
 	if (rc < 0)
@@ -503,13 +601,6 @@ static int evtchn_open(struct inode *inode, struct file *filp)
 
 	init_waitqueue_head(&u->evtchn_wait);
 
-	u->ring = (evtchn_port_t *)__get_free_page(GFP_KERNEL);
-	if (u->ring == NULL) {
-		kfree(u->name);
-		kfree(u);
-		return -ENOMEM;
-	}
-
 	mutex_init(&u->bind_mutex);
 	mutex_init(&u->ring_cons_mutex);
 	spin_lock_init(&u->ring_prod_lock);
@@ -532,7 +623,7 @@ static int evtchn_release(struct inode *inode, struct file *filp)
 		evtchn_unbind_from_user(u, evtchn);
 	}
 
-	free_page((unsigned long)u->ring);
+	evtchn_free_ring(u->ring);
 	kfree(u->name);
 	kfree(u);
 
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 2ea0b3b2a91d..1be5dd048622 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -804,7 +804,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 
 	vma->vm_ops = &gntdev_vmops;
 
-	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
+	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP | VM_IO;
 
 	if (use_ptemod)
 		vma->vm_flags |= VM_DONTCOPY;