Merge tag 'char-misc-5.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc

Pull char/misc driver updates from Greg KH:
 "Here is the big set of char/misc and other driver patches for 5.5-rc1

  Loads of different things in here, this feels like the catch-all of
  driver subsystems these days. Full details are in the shortlog, but
  nothing major overall, just lots of driver updates and additions.

  All of these have been in linux-next for a while with no reported
  issues"

* tag 'char-misc-5.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc: (198 commits)
  char: Fix Kconfig indentation, continued
  habanalabs: add more protection of device during reset
  habanalabs: flush EQ workers in hard reset
  habanalabs: make the reset code more consistent
  habanalabs: expose reset counters via existing INFO IOCTL
  habanalabs: make code more concise
  habanalabs: use defines for F/W files
  habanalabs: remove prints on successful device initialization
  habanalabs: remove unnecessary checks
  habanalabs: invalidate MMU cache only once
  habanalabs: skip VA block list update in reset flow
  habanalabs: optimize MMU unmap
  habanalabs: prevent read/write from/to the device during hard reset
  habanalabs: split MMU properties to PCI/DRAM
  habanalabs: re-factor MMU masks and documentation
  habanalabs: type specific MMU cache invalidation
  habanalabs: re-factor memory module code
  habanalabs: export uapi defines to user-space
  habanalabs: don't print error when queues are full
  habanalabs: increase max jobs number to 512
  ...

157 files changed, 10169 insertions, 1674 deletions

diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 265d9dd46a5e..a606262da9d6 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -65,6 +65,7 @@
 #include <linux/ratelimit.h>
 #include <linux/syscalls.h>
 #include <linux/task_work.h>
+#include <linux/sizes.h>
 
 #include <uapi/linux/android/binder.h>
 #include <uapi/linux/android/binderfs.h>
@@ -92,11 +93,6 @@ static atomic_t binder_last_id;
 static int proc_show(struct seq_file *m, void *unused);
 DEFINE_SHOW_ATTRIBUTE(proc);
 
-/* This is only defined in include/asm-arm/sizes.h */
-#ifndef SZ_1K
-#define SZ_1K                               0x400
-#endif
-
 #define FORBIDDEN_MMAP_FLAGS                (VM_WRITE)
 
 enum {
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index eb76a823fbb2..2d8b9b91dee0 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -268,7 +268,6 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 			alloc->pages_high = index + 1;
 
 		trace_binder_alloc_page_end(alloc, index);
-		/* vm_insert_page does not seem to increment the refcount */
 	}
 	if (mm) {
 		up_read(&mm->mmap_sem);
@@ -277,8 +276,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 	return 0;
 
 free_range:
-	for (page_addr = end - PAGE_SIZE; page_addr >= start;
-	     page_addr -= PAGE_SIZE) {
+	for (page_addr = end - PAGE_SIZE; 1; page_addr -= PAGE_SIZE) {
 		bool ret;
 		size_t index;
 
@@ -291,6 +289,8 @@ free_range:
 		WARN_ON(!ret);
 
 		trace_binder_free_lru_end(alloc, index);
+		if (page_addr == start)
+			break;
 		continue;
 
 err_vm_insert_page_failed:
@@ -298,7 +298,8 @@ err_vm_insert_page_failed:
 		page->page_ptr = NULL;
 err_alloc_page_failed:
 err_page_ptr_cleared:
-		;
+		if (page_addr == start)
+			break;
 	}
 err_no_vma:
 	if (mm) {
@@ -681,17 +682,17 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 	struct binder_buffer *buffer;
 
 	mutex_lock(&binder_alloc_mmap_lock);
-	if (alloc->buffer) {
+	if (alloc->buffer_size) {
 		ret = -EBUSY;
 		failure_string = "already mapped";
 		goto err_already_mapped;
 	}
+	alloc->buffer_size = min_t(unsigned long, vma->vm_end - vma->vm_start,
+				   SZ_4M);
+	mutex_unlock(&binder_alloc_mmap_lock);
 
 	alloc->buffer = (void __user *)vma->vm_start;
-	mutex_unlock(&binder_alloc_mmap_lock);
 
-	alloc->buffer_size = min_t(unsigned long, vma->vm_end - vma->vm_start,
-				   SZ_4M);
 	alloc->pages = kcalloc(alloc->buffer_size / PAGE_SIZE,
 			       sizeof(alloc->pages[0]),
 			       GFP_KERNEL);
@@ -722,8 +723,9 @@ err_alloc_buf_struct_failed:
 	kfree(alloc->pages);
 	alloc->pages = NULL;
 err_alloc_pages_failed:
-	mutex_lock(&binder_alloc_mmap_lock);
 	alloc->buffer = NULL;
+	mutex_lock(&binder_alloc_mmap_lock);
+	alloc->buffer_size = 0;
 err_already_mapped:
 	mutex_unlock(&binder_alloc_mmap_lock);
 	binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
@@ -841,14 +843,20 @@ void binder_alloc_print_pages(struct seq_file *m,
 	int free = 0;
 
 	mutex_lock(&alloc->mutex);
-	for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
-		page = &alloc->pages[i];
-		if (!page->page_ptr)
-			free++;
-		else if (list_empty(&page->lru))
-			active++;
-		else
-			lru++;
+	/*
+	 * Make sure the binder_alloc is fully initialized, otherwise we might
+	 * read inconsistent state.
+	 */
+	if (binder_alloc_get_vma(alloc) != NULL) {
+		for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
+			page = &alloc->pages[i];
+			if (!page->page_ptr)
+				free++;
+			else if (list_empty(&page->lru))
+				active++;
+			else
+				lru++;
+		}
 	}
 	mutex_unlock(&alloc->mutex);
 	seq_printf(m, "  pages: %d:%d:%d\n", active, lru, free);
diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
index df0fc997dc3e..26956c006987 100644
--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@@ -439,8 +439,8 @@ config RAW_DRIVER
 	  Once bound, I/O against /dev/raw/rawN uses efficient zero-copy I/O.
 	  See the raw(8) manpage for more details.
 
-          Applications should preferably open the device (eg /dev/hda1)
-          with the O_DIRECT flag.
+	  Applications should preferably open the device (eg /dev/hda1)
+	  with the O_DIRECT flag.
 
 config MAX_RAW_DEVS
 	int "Maximum number of RAW devices to support (1-65536)"
@@ -559,4 +559,4 @@ config RANDOM_TRUST_BOOTLOADER
 	device randomness. Say Y here to assume the entropy provided by the
 	booloader is trustworthy so it will be added to the kernel's entropy
 	pool. Otherwise, say N here so it will be regarded as device input that
-	only mixes the entropy pool.
\ No newline at end of file
+	only mixes the entropy pool.
diff --git a/drivers/char/agp/Kconfig b/drivers/char/agp/Kconfig
index 812d6aa6e013..bc54235a7022 100644
--- a/drivers/char/agp/Kconfig
+++ b/drivers/char/agp/Kconfig
@@ -63,7 +63,7 @@ config AGP_AMD64
 	  This option gives you AGP support for the GLX component of
 	  X using the on-CPU northbridge of the AMD Athlon64/Opteron CPUs.
 	  You still need an external AGP bridge like the AMD 8151, VIA
-          K8T400M, SiS755. It may also support other AGP bridges when loaded
+	  K8T400M, SiS755. It may also support other AGP bridges when loaded
 	  with agp_try_unsupported=1.
 
 config AGP_INTEL
diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig
index 3daae8ddd511..8486c29d8324 100644
--- a/drivers/char/hw_random/Kconfig
+++ b/drivers/char/hw_random/Kconfig
@@ -386,17 +386,17 @@ config HW_RANDOM_MESON
 	  If unsure, say Y.
 
 config HW_RANDOM_CAVIUM
-       tristate "Cavium ThunderX Random Number Generator support"
-       depends on HW_RANDOM && PCI && (ARM64 || (COMPILE_TEST && 64BIT))
-       default HW_RANDOM
-       ---help---
-         This driver provides kernel-side support for the Random Number
-         Generator hardware found on Cavium SoCs.
+	tristate "Cavium ThunderX Random Number Generator support"
+	depends on HW_RANDOM && PCI && (ARM64 || (COMPILE_TEST && 64BIT))
+	default HW_RANDOM
+	---help---
+	  This driver provides kernel-side support for the Random Number
+	  Generator hardware found on Cavium SoCs.
 
-         To compile this driver as a module, choose M here: the
-         module will be called cavium_rng.
+	  To compile this driver as a module, choose M here: the
+	  module will be called cavium_rng.
 
-         If unsure, say Y.
+	  If unsure, say Y.
 
 config HW_RANDOM_MTK
 	tristate "Mediatek Random Number Generator support"
diff --git a/drivers/char/ipmi/Kconfig b/drivers/char/ipmi/Kconfig
index 4bad0614109b..7dc2c3ec4051 100644
--- a/drivers/char/ipmi/Kconfig
+++ b/drivers/char/ipmi/Kconfig
@@ -4,38 +4,38 @@
 #
 
 menuconfig IPMI_HANDLER
-       tristate 'IPMI top-level message handler'
-       depends on HAS_IOMEM
-       select IPMI_DMI_DECODE if DMI
-       help
-         This enables the central IPMI message handler, required for IPMI
-	 to work.
+	tristate 'IPMI top-level message handler'
+	depends on HAS_IOMEM
+	select IPMI_DMI_DECODE if DMI
+	help
+	  This enables the central IPMI message handler, required for IPMI
+	  to work.
 
-         IPMI is a standard for managing sensors (temperature,
-         voltage, etc.) in a system.
+	  IPMI is a standard for managing sensors (temperature,
+	  voltage, etc.) in a system.
 
-         See <file:Documentation/IPMI.txt> for more details on the driver.
+	  See <file:Documentation/IPMI.txt> for more details on the driver.
 
-	 If unsure, say N.
+	  If unsure, say N.
 
 config IPMI_DMI_DECODE
-       select IPMI_PLAT_DATA
-       bool
+	select IPMI_PLAT_DATA
+	bool
 
 config IPMI_PLAT_DATA
-       bool
+	bool
 
 if IPMI_HANDLER
 
 config IPMI_PANIC_EVENT
-       bool 'Generate a panic event to all BMCs on a panic'
-       help
-	 When a panic occurs, this will cause the IPMI message handler to,
-	 by default, generate an IPMI event describing the panic to each
-	 interface registered with the message handler.  This is always
-	 available, the module parameter for ipmi_msghandler named
-	 panic_op can be set to "event" to chose this value, this config
-	 simply causes the default value to be set to "event".
+	bool 'Generate a panic event to all BMCs on a panic'
+	help
+	  When a panic occurs, this will cause the IPMI message handler to,
+	  by default, generate an IPMI event describing the panic to each
+	  interface registered with the message handler.  This is always
+	  available, the module parameter for ipmi_msghandler named
+	  panic_op can be set to "event" to chose this value, this config
+	  simply causes the default value to be set to "event".
 
 config IPMI_PANIC_STRING
 	bool 'Generate OEM events containing the panic string'
@@ -54,43 +54,43 @@ config IPMI_PANIC_STRING
 	  causes the default value to be set to "string".
 
 config IPMI_DEVICE_INTERFACE
-       tristate 'Device interface for IPMI'
-       help
-         This provides an IOCTL interface to the IPMI message handler so
-	 userland processes may use IPMI.  It supports poll() and select().
+	tristate 'Device interface for IPMI'
+	help
+	  This provides an IOCTL interface to the IPMI message handler so
+	  userland processes may use IPMI.  It supports poll() and select().
 
 config IPMI_SI
-       tristate 'IPMI System Interface handler'
-       select IPMI_PLAT_DATA
-       help
-         Provides a driver for System Interfaces (KCS, SMIC, BT).
-	 Currently, only KCS and SMIC are supported.  If
-	 you are using IPMI, you should probably say "y" here.
+	tristate 'IPMI System Interface handler'
+	select IPMI_PLAT_DATA
+	help
+	  Provides a driver for System Interfaces (KCS, SMIC, BT).
+	  Currently, only KCS and SMIC are supported.  If
+	  you are using IPMI, you should probably say "y" here.
 
 config IPMI_SSIF
-       tristate 'IPMI SMBus handler (SSIF)'
-       select I2C
-       help
-         Provides a driver for a SMBus interface to a BMC, meaning that you
-	 have a driver that must be accessed over an I2C bus instead of a
-	 standard interface.  This module requires I2C support.
+	tristate 'IPMI SMBus handler (SSIF)'
+	select I2C
+	help
+	  Provides a driver for a SMBus interface to a BMC, meaning that you
+	  have a driver that must be accessed over an I2C bus instead of a
+	  standard interface.  This module requires I2C support.
 
 config IPMI_POWERNV
-       depends on PPC_POWERNV
-       tristate 'POWERNV (OPAL firmware) IPMI interface'
-       help
-         Provides a driver for OPAL firmware-based IPMI interfaces.
+	depends on PPC_POWERNV
+	tristate 'POWERNV (OPAL firmware) IPMI interface'
+	help
+	  Provides a driver for OPAL firmware-based IPMI interfaces.
 
 config IPMI_WATCHDOG
-       tristate 'IPMI Watchdog Timer'
-       help
-         This enables the IPMI watchdog timer.
+	tristate 'IPMI Watchdog Timer'
+	help
+	  This enables the IPMI watchdog timer.
 
 config IPMI_POWEROFF
-       tristate 'IPMI Poweroff'
-       help
-         This enables a function to power off the system with IPMI if
-	 the IPMI management controller is capable of this.
+	tristate 'IPMI Poweroff'
+	help
+	  This enables a function to power off the system with IPMI if
+	  the IPMI management controller is capable of this.
 
 endif # IPMI_HANDLER
 
@@ -126,7 +126,7 @@ config NPCM7XX_KCS_IPMI_BMC
 
 config ASPEED_BT_IPMI_BMC
 	depends on ARCH_ASPEED || COMPILE_TEST
-       depends on REGMAP && REGMAP_MMIO && MFD_SYSCON
+	depends on REGMAP && REGMAP_MMIO && MFD_SYSCON
 	tristate "BT IPMI bmc driver"
 	help
 	  Provides a driver for the BT (Block Transfer) IPMI interface
diff --git a/drivers/char/lp.c b/drivers/char/lp.c
index 7c9269e3477a..bd95aba1f9fe 100644
--- a/drivers/char/lp.c
+++ b/drivers/char/lp.c
@@ -713,6 +713,10 @@ static int lp_set_timeout64(unsigned int minor, void __user *arg)
 	if (copy_from_user(karg, arg, sizeof(karg)))
 		return -EFAULT;
 
+	/* sparc64 suseconds_t is 32-bit only */
+	if (IS_ENABLED(CONFIG_SPARC64) && !in_compat_syscall())
+		karg[1] >>= 32;
+
 	return lp_set_timeout(minor, karg[0], karg[1]);
 }
 
diff --git a/drivers/char/ppdev.c b/drivers/char/ppdev.c
index c86f18aa8985..34bb88fe0b0a 100644
--- a/drivers/char/ppdev.c
+++ b/drivers/char/ppdev.c
@@ -619,20 +619,27 @@ static int pp_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		if (copy_from_user(time32, argp, sizeof(time32)))
 			return -EFAULT;
 
+		if ((time32[0] < 0) || (time32[1] < 0))
+			return -EINVAL;
+
 		return pp_set_timeout(pp->pdev, time32[0], time32[1]);
 
 	case PPSETTIME64:
 		if (copy_from_user(time64, argp, sizeof(time64)))
 			return -EFAULT;
 
+		if ((time64[0] < 0) || (time64[1] < 0))
+			return -EINVAL;
+
+		if (IS_ENABLED(CONFIG_SPARC64) && !in_compat_syscall())
+			time64[1] >>= 32;
+
 		return pp_set_timeout(pp->pdev, time64[0], time64[1]);
 
 	case PPGETTIME32:
 		jiffies_to_timespec64(pp->pdev->timeout, &ts);
 		time32[0] = ts.tv_sec;
 		time32[1] = ts.tv_nsec / NSEC_PER_USEC;
-		if ((time32[0] < 0) || (time32[1] < 0))
-			return -EINVAL;
 
 		if (copy_to_user(argp, time32, sizeof(time32)))
 			return -EFAULT;
@@ -643,8 +650,9 @@ static int pp_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		jiffies_to_timespec64(pp->pdev->timeout, &ts);
 		time64[0] = ts.tv_sec;
 		time64[1] = ts.tv_nsec / NSEC_PER_USEC;
-		if ((time64[0] < 0) || (time64[1] < 0))
-			return -EINVAL;
+
+		if (IS_ENABLED(CONFIG_SPARC64) && !in_compat_syscall())
+			time64[1] <<= 32;
 
 		if (copy_to_user(argp, time64, sizeof(time64)))
 			return -EFAULT;
diff --git a/drivers/char/xillybus/xillybus_of.c b/drivers/char/xillybus/xillybus_of.c
index bfafd8f5e826..96b6de8a30e5 100644
--- a/drivers/char/xillybus/xillybus_of.c
+++ b/drivers/char/xillybus/xillybus_of.c
@@ -116,7 +116,6 @@ static int xilly_drv_probe(struct platform_device *op)
 	struct xilly_endpoint *endpoint;
 	int rc;
 	int irq;
-	struct resource *res;
 	struct xilly_endpoint_hardware *ephw = &of_hw;
 
 	if (of_property_read_bool(dev->of_node, "dma-coherent"))
@@ -129,9 +128,7 @@ static int xilly_drv_probe(struct platform_device *op)
 
 	dev_set_drvdata(dev, endpoint);
 
-	res = platform_get_resource(op, IORESOURCE_MEM, 0);
-	endpoint->registers = devm_ioremap_resource(dev, res);
-
+	endpoint->registers = devm_platform_ioremap_resource(op, 0);
 	if (IS_ERR(endpoint->registers))
 		return PTR_ERR(endpoint->registers);
 
diff --git a/drivers/extcon/extcon-intel-cht-wc.c b/drivers/extcon/extcon-intel-cht-wc.c
index 9d32150e68db..771f6f4cf92e 100644
--- a/drivers/extcon/extcon-intel-cht-wc.c
+++ b/drivers/extcon/extcon-intel-cht-wc.c
@@ -338,6 +338,7 @@ static int cht_wc_extcon_probe(struct platform_device *pdev)
 	struct intel_soc_pmic *pmic = dev_get_drvdata(pdev->dev.parent);
 	struct cht_wc_extcon_data *ext;
 	unsigned long mask = ~(CHT_WC_PWRSRC_VBUS | CHT_WC_PWRSRC_USBID_MASK);
+	int pwrsrc_sts, id;
 	int irq, ret;
 
 	irq = platform_get_irq(pdev, 0);
@@ -387,8 +388,19 @@ static int cht_wc_extcon_probe(struct platform_device *pdev)
 		goto disable_sw_control;
 	}
 
-	/* Route D+ and D- to PMIC for initial charger detection */
-	cht_wc_extcon_set_phymux(ext, MUX_SEL_PMIC);
+	ret = regmap_read(ext->regmap, CHT_WC_PWRSRC_STS, &pwrsrc_sts);
+	if (ret) {
+		dev_err(ext->dev, "Error reading pwrsrc status: %d\n", ret);
+		goto disable_sw_control;
+	}
+
+	/*
+	 * If no USB host or device connected, route D+ and D- to PMIC for
+	 * initial charger detection
+	 */
+	id = cht_wc_extcon_get_id(ext, pwrsrc_sts);
+	if (id != INTEL_USB_ID_GND)
+		cht_wc_extcon_set_phymux(ext, MUX_SEL_PMIC);
 
 	/* Get initial state */
 	cht_wc_extcon_pwrsrc_event(ext);
diff --git a/drivers/extcon/extcon-sm5502.c b/drivers/extcon/extcon-sm5502.c
index dc43847ad2b0..bcf65aaca5d2 100644
--- a/drivers/extcon/extcon-sm5502.c
+++ b/drivers/extcon/extcon-sm5502.c
@@ -65,6 +65,10 @@ struct sm5502_muic_info {
 /* Default value of SM5502 register to bring up MUIC device. */
 static struct reg_data sm5502_reg_data[] = {
 	{
+		.reg = SM5502_REG_RESET,
+		.val = SM5502_REG_RESET_MASK,
+		.invert = true,
+	}, {
 		.reg = SM5502_REG_CONTROL,
 		.val = SM5502_REG_CONTROL_MASK_INT_MASK,
 		.invert = false,
@@ -272,7 +276,7 @@ static int sm5502_muic_set_path(struct sm5502_muic_info *info,
 /* Return cable type of attached or detached accessories */
 static unsigned int sm5502_muic_get_cable_type(struct sm5502_muic_info *info)
 {
-	unsigned int cable_type = -1, adc, dev_type1;
+	unsigned int cable_type, adc, dev_type1;
 	int ret;
 
 	/* Read ADC value according to external cable or button */
diff --git a/drivers/extcon/extcon-sm5502.h b/drivers/extcon/extcon-sm5502.h
index 9dbb634d213b..ce1f1ec310c4 100644
--- a/drivers/extcon/extcon-sm5502.h
+++ b/drivers/extcon/extcon-sm5502.h
@@ -237,6 +237,8 @@ enum sm5502_reg {
 #define DM_DP_SWITCH_UART			((DM_DP_CON_SWITCH_UART <<SM5502_REG_MANUAL_SW1_DP_SHIFT) \
 						| (DM_DP_CON_SWITCH_UART <<SM5502_REG_MANUAL_SW1_DM_SHIFT))
 
+#define SM5502_REG_RESET_MASK			(0x1)
+
 /* SM5502 Interrupts */
 enum sm5502_irq {
 	/* INT1 */
diff --git a/drivers/firmware/stratix10-rsu.c b/drivers/firmware/stratix10-rsu.c
index bb008c019920..f8533338b018 100644
--- a/drivers/firmware/stratix10-rsu.c
+++ b/drivers/firmware/stratix10-rsu.c
@@ -20,7 +20,6 @@
 #define RSU_VERSION_MASK		GENMASK_ULL(63, 32)
 #define RSU_ERROR_LOCATION_MASK		GENMASK_ULL(31, 0)
 #define RSU_ERROR_DETAIL_MASK		GENMASK_ULL(63, 32)
-#define RSU_FW_VERSION_MASK		GENMASK_ULL(15, 0)
 
 #define RSU_TIMEOUT	(msecs_to_jiffies(SVC_RSU_REQUEST_TIMEOUT_MS))
 
@@ -109,9 +108,12 @@ static void rsu_command_callback(struct stratix10_svc_client *client,
 {
 	struct stratix10_rsu_priv *priv = client->priv;
 
-	if (data->status != BIT(SVC_STATUS_RSU_OK))
-		dev_err(client->dev, "RSU returned status is %i\n",
-			data->status);
+	if (data->status == BIT(SVC_STATUS_RSU_NO_SUPPORT))
+		dev_warn(client->dev, "Secure FW doesn't support notify\n");
+	else if (data->status == BIT(SVC_STATUS_RSU_ERROR))
+		dev_err(client->dev, "Failure, returned status is %lu\n",
+			BIT(data->status));
+
 	complete(&priv->completion);
 }
 
@@ -133,9 +135,11 @@ static void rsu_retry_callback(struct stratix10_svc_client *client,
 
 	if (data->status == BIT(SVC_STATUS_RSU_OK))
 		priv->retry_counter = *counter;
+	else if (data->status == BIT(SVC_STATUS_RSU_NO_SUPPORT))
+		dev_warn(client->dev, "Secure FW doesn't support retry\n");
 	else
-		dev_err(client->dev, "Failed to get retry counter %i\n",
-			data->status);
+		dev_err(client->dev, "Failed to get retry counter %lu\n",
+			BIT(data->status));
 
 	complete(&priv->completion);
 }
@@ -333,15 +337,10 @@ static ssize_t notify_store(struct device *dev,
 		return ret;
 	}
 
-	/* only 19.3 or late version FW supports retry counter feature */
-	if (FIELD_GET(RSU_FW_VERSION_MASK, priv->status.version)) {
-		ret = rsu_send_msg(priv, COMMAND_RSU_RETRY,
-				   0, rsu_retry_callback);
-		if (ret) {
-			dev_err(dev,
-				"Error, getting RSU retry %i\n", ret);
-			return ret;
-		}
+	ret = rsu_send_msg(priv, COMMAND_RSU_RETRY, 0, rsu_retry_callback);
+	if (ret) {
+		dev_err(dev, "Error, getting RSU retry %i\n", ret);
+		return ret;
 	}
 
 	return count;
@@ -413,15 +412,10 @@ static int stratix10_rsu_probe(struct platform_device *pdev)
 		stratix10_svc_free_channel(priv->chan);
 	}
 
-	/* only 19.3 or late version FW supports retry counter feature */
-	if (FIELD_GET(RSU_FW_VERSION_MASK, priv->status.version)) {
-		ret = rsu_send_msg(priv, COMMAND_RSU_RETRY, 0,
-				   rsu_retry_callback);
-		if (ret) {
-			dev_err(dev,
-				"Error, getting RSU retry %i\n", ret);
-			stratix10_svc_free_channel(priv->chan);
-		}
+	ret = rsu_send_msg(priv, COMMAND_RSU_RETRY, 0, rsu_retry_callback);
+	if (ret) {
+		dev_err(dev, "Error, getting RSU retry %i\n", ret);
+		stratix10_svc_free_channel(priv->chan);
 	}
 
 	return ret;
diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c
index b485321189e1..c6c31402848d 100644
--- a/drivers/firmware/stratix10-svc.c
+++ b/drivers/firmware/stratix10-svc.c
@@ -493,8 +493,24 @@ static int svc_normal_to_secure_thread(void *data)
 			pdata->chan->scl->receive_cb(pdata->chan->scl, cbdata);
 			break;
 		default:
-			pr_warn("it shouldn't happen\n");
+			pr_warn("Secure firmware doesn't support...\n");
+
+			/*
+			 * be compatible with older version firmware which
+			 * doesn't support RSU notify or retry
+			 */
+			if ((pdata->command == COMMAND_RSU_RETRY) ||
+				(pdata->command == COMMAND_RSU_NOTIFY)) {
+				cbdata->status =
+					BIT(SVC_STATUS_RSU_NO_SUPPORT);
+				cbdata->kaddr1 = NULL;
+				cbdata->kaddr2 = NULL;
+				cbdata->kaddr3 = NULL;
+				pdata->chan->scl->receive_cb(
+					pdata->chan->scl, cbdata);
+			}
 			break;
+
 		}
 	};
 
diff --git a/drivers/fpga/Kconfig b/drivers/fpga/Kconfig
index 73c779e920ed..72380e1d31c7 100644
--- a/drivers/fpga/Kconfig
+++ b/drivers/fpga/Kconfig
@@ -156,7 +156,7 @@ config FPGA_DFL
 
 config FPGA_DFL_FME
 	tristate "FPGA DFL FME Driver"
-	depends on FPGA_DFL
+	depends on FPGA_DFL && HWMON
 	help
 	  The FPGA Management Engine (FME) is a feature device implemented
 	  under Device Feature List (DFL) framework. Select this option to
diff --git a/drivers/fpga/dfl-fme-main.c b/drivers/fpga/dfl-fme-main.c
index 4d78e182878f..7c930e6b314d 100644
--- a/drivers/fpga/dfl-fme-main.c
+++ b/drivers/fpga/dfl-fme-main.c
@@ -14,6 +14,8 @@
  *   Henry Mitchel <henry.mitchel@intel.com>
  */
 
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/uaccess.h>
@@ -181,6 +183,381 @@ static const struct dfl_feature_ops fme_hdr_ops = {
 	.ioctl = fme_hdr_ioctl,
 };
 
+#define FME_THERM_THRESHOLD	0x8
+#define TEMP_THRESHOLD1		GENMASK_ULL(6, 0)
+#define TEMP_THRESHOLD1_EN	BIT_ULL(7)
+#define TEMP_THRESHOLD2		GENMASK_ULL(14, 8)
+#define TEMP_THRESHOLD2_EN	BIT_ULL(15)
+#define TRIP_THRESHOLD		GENMASK_ULL(30, 24)
+#define TEMP_THRESHOLD1_STATUS	BIT_ULL(32)		/* threshold1 reached */
+#define TEMP_THRESHOLD2_STATUS	BIT_ULL(33)		/* threshold2 reached */
+/* threshold1 policy: 0 - AP2 (90% throttle) / 1 - AP1 (50% throttle) */
+#define TEMP_THRESHOLD1_POLICY	BIT_ULL(44)
+
+#define FME_THERM_RDSENSOR_FMT1	0x10
+#define FPGA_TEMPERATURE	GENMASK_ULL(6, 0)
+
+#define FME_THERM_CAP		0x20
+#define THERM_NO_THROTTLE	BIT_ULL(0)
+
+#define MD_PRE_DEG
+
+static bool fme_thermal_throttle_support(void __iomem *base)
+{
+	u64 v = readq(base + FME_THERM_CAP);
+
+	return FIELD_GET(THERM_NO_THROTTLE, v) ? false : true;
+}
+
+static umode_t thermal_hwmon_attrs_visible(const void *drvdata,
+					   enum hwmon_sensor_types type,
+					   u32 attr, int channel)
+{
+	const struct dfl_feature *feature = drvdata;
+
+	/* temperature is always supported, and check hardware cap for others */
+	if (attr == hwmon_temp_input)
+		return 0444;
+
+	return fme_thermal_throttle_support(feature->ioaddr) ? 0444 : 0;
+}
+
+static int thermal_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
+			      u32 attr, int channel, long *val)
+{
+	struct dfl_feature *feature = dev_get_drvdata(dev);
+	u64 v;
+
+	switch (attr) {
+	case hwmon_temp_input:
+		v = readq(feature->ioaddr + FME_THERM_RDSENSOR_FMT1);
+		*val = (long)(FIELD_GET(FPGA_TEMPERATURE, v) * 1000);
+		break;
+	case hwmon_temp_max:
+		v = readq(feature->ioaddr + FME_THERM_THRESHOLD);
+		*val = (long)(FIELD_GET(TEMP_THRESHOLD1, v) * 1000);
+		break;
+	case hwmon_temp_crit:
+		v = readq(feature->ioaddr + FME_THERM_THRESHOLD);
+		*val = (long)(FIELD_GET(TEMP_THRESHOLD2, v) * 1000);
+		break;
+	case hwmon_temp_emergency:
+		v = readq(feature->ioaddr + FME_THERM_THRESHOLD);
+		*val = (long)(FIELD_GET(TRIP_THRESHOLD, v) * 1000);
+		break;
+	case hwmon_temp_max_alarm:
+		v = readq(feature->ioaddr + FME_THERM_THRESHOLD);
+		*val = (long)FIELD_GET(TEMP_THRESHOLD1_STATUS, v);
+		break;
+	case hwmon_temp_crit_alarm:
+		v = readq(feature->ioaddr + FME_THERM_THRESHOLD);
+		*val = (long)FIELD_GET(TEMP_THRESHOLD2_STATUS, v);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static const struct hwmon_ops thermal_hwmon_ops = {
+	.is_visible = thermal_hwmon_attrs_visible,
+	.read = thermal_hwmon_read,
+};
+
+static const struct hwmon_channel_info *thermal_hwmon_info[] = {
+	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_EMERGENCY |
+				 HWMON_T_MAX   | HWMON_T_MAX_ALARM |
+				 HWMON_T_CRIT  | HWMON_T_CRIT_ALARM),
+	NULL
+};
+
+static const struct hwmon_chip_info thermal_hwmon_chip_info = {
+	.ops = &thermal_hwmon_ops,
+	.info = thermal_hwmon_info,
+};
+
+static ssize_t temp1_max_policy_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	struct dfl_feature *feature = dev_get_drvdata(dev);
+	u64 v;
+
+	v = readq(feature->ioaddr + FME_THERM_THRESHOLD);
+
+	return sprintf(buf, "%u\n",
+		       (unsigned int)FIELD_GET(TEMP_THRESHOLD1_POLICY, v));
+}
+
+static DEVICE_ATTR_RO(temp1_max_policy);
+
+static struct attribute *thermal_extra_attrs[] = {
+	&dev_attr_temp1_max_policy.attr,
+	NULL,
+};
+
+static umode_t thermal_extra_attrs_visible(struct kobject *kobj,
+					   struct attribute *attr, int index)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct dfl_feature *feature = dev_get_drvdata(dev);
+
+	return fme_thermal_throttle_support(feature->ioaddr) ? attr->mode : 0;
+}
+
+static const struct attribute_group thermal_extra_group = {
+	.attrs		= thermal_extra_attrs,
+	.is_visible	= thermal_extra_attrs_visible,
+};
+__ATTRIBUTE_GROUPS(thermal_extra);
+
+static int fme_thermal_mgmt_init(struct platform_device *pdev,
+				 struct dfl_feature *feature)
+{
+	struct device *hwmon;
+
+	/*
+	 * create hwmon to allow userspace monitoring temperature and other
+	 * threshold information.
+	 *
+	 * temp1_input      -> FPGA device temperature
+	 * temp1_max        -> hardware threshold 1 -> 50% or 90% throttling
+	 * temp1_crit       -> hardware threshold 2 -> 100% throttling
+	 * temp1_emergency  -> hardware trip_threshold to shutdown FPGA
+	 * temp1_max_alarm  -> hardware threshold 1 alarm
+	 * temp1_crit_alarm -> hardware threshold 2 alarm
+	 *
+	 * create device specific sysfs interfaces, e.g. read temp1_max_policy
+	 * to understand the actual hardware throttling action (50% vs 90%).
+	 *
+	 * If hardware doesn't support automatic throttling per thresholds,
+	 * then all above sysfs interfaces are not visible except temp1_input
+	 * for temperature.
+	 */
+	hwmon = devm_hwmon_device_register_with_info(&pdev->dev,
+						     "dfl_fme_thermal", feature,
+						     &thermal_hwmon_chip_info,
+						     thermal_extra_groups);
+	if (IS_ERR(hwmon)) {
+		dev_err(&pdev->dev, "Fail to register thermal hwmon\n");
+		return PTR_ERR(hwmon);
+	}
+
+	return 0;
+}
+
+static const struct dfl_feature_id fme_thermal_mgmt_id_table[] = {
+	{.id = FME_FEATURE_ID_THERMAL_MGMT,},
+	{0,}
+};
+
+static const struct dfl_feature_ops fme_thermal_mgmt_ops = {
+	.init = fme_thermal_mgmt_init,
+};
+
+#define FME_PWR_STATUS		0x8
+#define FME_LATENCY_TOLERANCE	BIT_ULL(18)
+#define PWR_CONSUMED		GENMASK_ULL(17, 0)
+
+#define FME_PWR_THRESHOLD	0x10
+#define PWR_THRESHOLD1		GENMASK_ULL(6, 0)	/* in Watts */
+#define PWR_THRESHOLD2		GENMASK_ULL(14, 8)	/* in Watts */
+#define PWR_THRESHOLD_MAX	0x7f			/* in Watts */
+#define PWR_THRESHOLD1_STATUS	BIT_ULL(16)
+#define PWR_THRESHOLD2_STATUS	BIT_ULL(17)
+
+#define FME_PWR_XEON_LIMIT	0x18
+#define XEON_PWR_LIMIT		GENMASK_ULL(14, 0)	/* in 0.1 Watts */
+#define XEON_PWR_EN		BIT_ULL(15)
+#define FME_PWR_FPGA_LIMIT	0x20
+#define FPGA_PWR_LIMIT		GENMASK_ULL(14, 0)	/* in 0.1 Watts */
+#define FPGA_PWR_EN		BIT_ULL(15)
+
+static int power_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
+			    u32 attr, int channel, long *val)
+{
+	struct dfl_feature *feature = dev_get_drvdata(dev);
+	u64 v;
+
+	switch (attr) {
+	case hwmon_power_input:
+		v = readq(feature->ioaddr + FME_PWR_STATUS);
+		*val = (long)(FIELD_GET(PWR_CONSUMED, v) * 1000000);
+		break;
+	case hwmon_power_max:
+		v = readq(feature->ioaddr + FME_PWR_THRESHOLD);
+		*val = (long)(FIELD_GET(PWR_THRESHOLD1, v) * 1000000);
+		break;
+	case hwmon_power_crit:
+		v = readq(feature->ioaddr + FME_PWR_THRESHOLD);
+		*val = (long)(FIELD_GET(PWR_THRESHOLD2, v) * 1000000);
+		break;
+	case hwmon_power_max_alarm:
+		v = readq(feature->ioaddr + FME_PWR_THRESHOLD);
+		*val = (long)FIELD_GET(PWR_THRESHOLD1_STATUS, v);
+		break;
+	case hwmon_power_crit_alarm:
+		v = readq(feature->ioaddr + FME_PWR_THRESHOLD);
+		*val = (long)FIELD_GET(PWR_THRESHOLD2_STATUS, v);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int power_hwmon_write(struct device *dev, enum hwmon_sensor_types type,
+			     u32 attr, int channel, long val)
+{
+	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev->parent);
+	struct dfl_feature *feature = dev_get_drvdata(dev);
+	int ret = 0;
+	u64 v;
+
+	val = clamp_val(val / 1000000, 0, PWR_THRESHOLD_MAX);
+
+	mutex_lock(&pdata->lock);
+
+	switch (attr) {
+	case hwmon_power_max:
+		v = readq(feature->ioaddr + FME_PWR_THRESHOLD);
+		v &= ~PWR_THRESHOLD1;
+		v |= FIELD_PREP(PWR_THRESHOLD1, val);
+		writeq(v, feature->ioaddr + FME_PWR_THRESHOLD);
+		break;
+	case hwmon_power_crit:
+		v = readq(feature->ioaddr + FME_PWR_THRESHOLD);
+		v &= ~PWR_THRESHOLD2;
+		v |= FIELD_PREP(PWR_THRESHOLD2, val);
+		writeq(v, feature->ioaddr + FME_PWR_THRESHOLD);
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+		break;
+	}
+
+	mutex_unlock(&pdata->lock);
+
+	return ret;
+}
+
+static umode_t power_hwmon_attrs_visible(const void *drvdata,
+					 enum hwmon_sensor_types type,
+					 u32 attr, int channel)
+{
+	switch (attr) {
+	case hwmon_power_input:
+	case hwmon_power_max_alarm:
+	case hwmon_power_crit_alarm:
+		return 0444;
+	case hwmon_power_max:
+	case hwmon_power_crit:
+		return 0644;
+	}
+
+	return 0;
+}
+
+static const struct hwmon_ops power_hwmon_ops = {
+	.is_visible = power_hwmon_attrs_visible,
+	.read = power_hwmon_read,
+	.write = power_hwmon_write,
+};
+
+static const struct hwmon_channel_info *power_hwmon_info[] = {
+	HWMON_CHANNEL_INFO(power, HWMON_P_INPUT |
+				  HWMON_P_MAX   | HWMON_P_MAX_ALARM |
+				  HWMON_P_CRIT  | HWMON_P_CRIT_ALARM),
+	NULL
+};
+
+static const struct hwmon_chip_info power_hwmon_chip_info = {
+	.ops = &power_hwmon_ops,
+	.info = power_hwmon_info,
+};
+
+static ssize_t power1_xeon_limit_show(struct device *dev,
+				      struct device_attribute *attr, char *buf)
+{
+	struct dfl_feature *feature = dev_get_drvdata(dev);
+	u16 xeon_limit = 0;
+	u64 v;
+
+	v = readq(feature->ioaddr + FME_PWR_XEON_LIMIT);
+
+	if (FIELD_GET(XEON_PWR_EN, v))
+		xeon_limit = FIELD_GET(XEON_PWR_LIMIT, v);
+
+	return sprintf(buf, "%u\n", xeon_limit * 100000);
+}
+
+static ssize_t power1_fpga_limit_show(struct device *dev,
+				      struct device_attribute *attr, char *buf)
+{
+	struct dfl_feature *feature = dev_get_drvdata(dev);
+	u16 fpga_limit = 0;
+	u64 v;
+
+	v = readq(feature->ioaddr + FME_PWR_FPGA_LIMIT);
+
+	if (FIELD_GET(FPGA_PWR_EN, v))
+		fpga_limit = FIELD_GET(FPGA_PWR_LIMIT, v);
+
+	return sprintf(buf, "%u\n", fpga_limit * 100000);
+}
+
+static ssize_t power1_ltr_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct dfl_feature *feature = dev_get_drvdata(dev);
+	u64 v;
+
+	v = readq(feature->ioaddr + FME_PWR_STATUS);
+
+	return sprintf(buf, "%u\n",
+		       (unsigned int)FIELD_GET(FME_LATENCY_TOLERANCE, v));
+}
+
+static DEVICE_ATTR_RO(power1_xeon_limit);
+static DEVICE_ATTR_RO(power1_fpga_limit);
+static DEVICE_ATTR_RO(power1_ltr);
+
+static struct attribute *power_extra_attrs[] = {
+	&dev_attr_power1_xeon_limit.attr,
+	&dev_attr_power1_fpga_limit.attr,
+	&dev_attr_power1_ltr.attr,
+	NULL
+};
+
+ATTRIBUTE_GROUPS(power_extra);
+
+static int fme_power_mgmt_init(struct platform_device *pdev,
+			       struct dfl_feature *feature)
+{
+	struct device *hwmon;
+
+	hwmon = devm_hwmon_device_register_with_info(&pdev->dev,
+						     "dfl_fme_power", feature,
+						     &power_hwmon_chip_info,
+						     power_extra_groups);
+	if (IS_ERR(hwmon)) {
+		dev_err(&pdev->dev, "Fail to register power hwmon\n");
+		return PTR_ERR(hwmon);
+	}
+
+	return 0;
+}
+
+static const struct dfl_feature_id fme_power_mgmt_id_table[] = {
+	{.id = FME_FEATURE_ID_POWER_MGMT,},
+	{0,}
+};
+
+static const struct dfl_feature_ops fme_power_mgmt_ops = {
+	.init = fme_power_mgmt_init,
+};
+
 static struct dfl_feature_driver fme_feature_drvs[] = {
 	{
 		.id_table = fme_hdr_id_table,
@@ -195,6 +572,14 @@ static struct dfl_feature_driver fme_feature_drvs[] = {
 		.ops = &fme_global_err_ops,
 	},
 	{
+		.id_table = fme_thermal_mgmt_id_table,
+		.ops = &fme_thermal_mgmt_ops,
+	},
+	{
+		.id_table = fme_power_mgmt_id_table,
+		.ops = &fme_power_mgmt_ops,
+	},
+	{
 		.ops = NULL,
 	},
 };
diff --git a/drivers/fpga/zynq-fpga.c b/drivers/fpga/zynq-fpga.c
index 31ef38e38537..ee7765049607 100644
--- a/drivers/fpga/zynq-fpga.c
+++ b/drivers/fpga/zynq-fpga.c
@@ -578,10 +578,8 @@ static int zynq_fpga_probe(struct platform_device *pdev)
 	init_completion(&priv->dma_done);
 
 	priv->irq = platform_get_irq(pdev, 0);
-	if (priv->irq < 0) {
-		dev_err(dev, "No IRQ available\n");
+	if (priv->irq < 0)
 		return priv->irq;
-	}
 
 	priv->clk = devm_clk_get(dev, "ref_clk");
 	if (IS_ERR(priv->clk)) {
diff --git a/drivers/fsi/Kconfig b/drivers/fsi/Kconfig
index c612db7a914a..92ce6d85802c 100644
--- a/drivers/fsi/Kconfig
+++ b/drivers/fsi/Kconfig
@@ -53,6 +53,14 @@ config FSI_MASTER_AST_CF
 	lines driven by the internal ColdFire coprocessor. This requires
 	the corresponding machine specific ColdFire firmware to be available.
 
+config FSI_MASTER_ASPEED
+	tristate "FSI ASPEED master"
+	help
+	 This option enables a FSI master that is present behind an OPB bridge
+	 in the AST2600.
+
+	 Enable it for your BMC kernel in an OpenPower or IBM Power system.
+
 config FSI_SCOM
 	tristate "SCOM FSI client device driver"
 	---help---
diff --git a/drivers/fsi/Makefile b/drivers/fsi/Makefile
index e4a2ff043c32..da218a1ad8e1 100644
--- a/drivers/fsi/Makefile
+++ b/drivers/fsi/Makefile
@@ -2,6 +2,7 @@
 
 obj-$(CONFIG_FSI) += fsi-core.o
 obj-$(CONFIG_FSI_MASTER_HUB) += fsi-master-hub.o
+obj-$(CONFIG_FSI_MASTER_ASPEED) += fsi-master-aspeed.o
 obj-$(CONFIG_FSI_MASTER_GPIO) += fsi-master-gpio.o
 obj-$(CONFIG_FSI_MASTER_AST_CF) += fsi-master-ast-cf.o
 obj-$(CONFIG_FSI_SCOM) += fsi-scom.o
diff --git a/drivers/fsi/fsi-core.c b/drivers/fsi/fsi-core.c
index 1f76740f33b6..8244da8a7241 100644
--- a/drivers/fsi/fsi-core.c
+++ b/drivers/fsi/fsi-core.c
@@ -544,6 +544,31 @@ static int fsi_slave_scan(struct fsi_slave *slave)
 	return 0;
 }
 
+static unsigned long aligned_access_size(size_t offset, size_t count)
+{
+	unsigned long offset_unit, count_unit;
+
+	/* Criteria:
+	 *
+	 * 1. Access size must be less than or equal to the maximum access
+	 *    width or the highest power-of-two factor of offset
+	 * 2. Access size must be less than or equal to the amount specified by
+	 *    count
+	 *
+	 * The access width is optimal if we can calculate 1 to be strictly
+	 * equal while still satisfying 2.
+	 */
+
+	/* Find 1 by the bottom bit of offset (with a 4 byte access cap) */
+	offset_unit = BIT(__builtin_ctzl(offset | 4));
+
+	/* Find 2 by the top bit of count */
+	count_unit = BIT(8 * sizeof(unsigned long) - 1 - __builtin_clzl(count));
+
+	/* Constrain the maximum access width to the minimum of both criteria */
+	return BIT(__builtin_ctzl(offset_unit | count_unit));
+}
+
 static ssize_t fsi_slave_sysfs_raw_read(struct file *file,
 		struct kobject *kobj, struct bin_attribute *attr, char *buf,
 		loff_t off, size_t count)
@@ -559,8 +584,7 @@ static ssize_t fsi_slave_sysfs_raw_read(struct file *file,
 		return -EINVAL;
 
 	for (total_len = 0; total_len < count; total_len += read_len) {
-		read_len = min_t(size_t, count, 4);
-		read_len -= off & 0x3;
+		read_len = aligned_access_size(off, count - total_len);
 
 		rc = fsi_slave_read(slave, off, buf + total_len, read_len);
 		if (rc)
@@ -587,8 +611,7 @@ static ssize_t fsi_slave_sysfs_raw_write(struct file *file,
 		return -EINVAL;
 
 	for (total_len = 0; total_len < count; total_len += write_len) {
-		write_len = min_t(size_t, count, 4);
-		write_len -= off & 0x3;
+		write_len = aligned_access_size(off, count - total_len);
 
 		rc = fsi_slave_write(slave, off, buf + total_len, write_len);
 		if (rc)
@@ -1241,6 +1264,19 @@ static ssize_t master_break_store(struct device *dev,
 
 static DEVICE_ATTR(break, 0200, NULL, master_break_store);
 
+static struct attribute *master_attrs[] = {
+	&dev_attr_break.attr,
+	&dev_attr_rescan.attr,
+	NULL
+};
+
+ATTRIBUTE_GROUPS(master);
+
+static struct class fsi_master_class = {
+	.name = "fsi-master",
+	.dev_groups = master_groups,
+};
+
 int fsi_master_register(struct fsi_master *master)
 {
 	int rc;
@@ -1249,6 +1285,7 @@ int fsi_master_register(struct fsi_master *master)
 	mutex_init(&master->scan_lock);
 	master->idx = ida_simple_get(&master_ida, 0, INT_MAX, GFP_KERNEL);
 	dev_set_name(&master->dev, "fsi%d", master->idx);
+	master->dev.class = &fsi_master_class;
 
 	rc = device_register(&master->dev);
 	if (rc) {
@@ -1256,20 +1293,6 @@ int fsi_master_register(struct fsi_master *master)
 		return rc;
 	}
 
-	rc = device_create_file(&master->dev, &dev_attr_rescan);
-	if (rc) {
-		device_del(&master->dev);
-		ida_simple_remove(&master_ida, master->idx);
-		return rc;
-	}
-
-	rc = device_create_file(&master->dev, &dev_attr_break);
-	if (rc) {
-		device_del(&master->dev);
-		ida_simple_remove(&master_ida, master->idx);
-		return rc;
-	}
-
 	np = dev_of_node(&master->dev);
 	if (!of_property_read_bool(np, "no-scan-on-init")) {
 		mutex_lock(&master->scan_lock);
@@ -1350,8 +1373,15 @@ static int __init fsi_init(void)
 	rc = bus_register(&fsi_bus_type);
 	if (rc)
 		goto fail_bus;
+
+	rc = class_register(&fsi_master_class);
+	if (rc)
+		goto fail_class;
+
 	return 0;
 
+ fail_class:
+	bus_unregister(&fsi_bus_type);
  fail_bus:
 	unregister_chrdev_region(fsi_base_dev, FSI_CHAR_MAX_DEVICES);
 	return rc;
@@ -1360,6 +1390,7 @@ postcore_initcall(fsi_init);
 
 static void fsi_exit(void)
 {
+	class_unregister(&fsi_master_class);
 	bus_unregister(&fsi_bus_type);
 	unregister_chrdev_region(fsi_base_dev, FSI_CHAR_MAX_DEVICES);
 	ida_destroy(&fsi_minor_ida);
diff --git a/drivers/fsi/fsi-master-aspeed.c b/drivers/fsi/fsi-master-aspeed.c
new file mode 100644
index 000000000000..f49742b310c2
--- /dev/null
+++ b/drivers/fsi/fsi-master-aspeed.c
@@ -0,0 +1,544 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+// Copyright (C) IBM Corporation 2018
+// FSI master driver for AST2600
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/fsi.h>
+#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/iopoll.h>
+
+#include "fsi-master.h"
+
+struct fsi_master_aspeed {
+	struct fsi_master	master;
+	struct device		*dev;
+	void __iomem		*base;
+	struct clk		*clk;
+};
+
+#define to_fsi_master_aspeed(m) \
+	container_of(m, struct fsi_master_aspeed, master)
+
+/* Control register (size 0x400) */
+static const u32 ctrl_base = 0x80000000;
+
+static const u32 fsi_base = 0xa0000000;
+
+#define OPB_FSI_VER	0x00
+#define OPB_TRIGGER	0x04
+#define OPB_CTRL_BASE	0x08
+#define OPB_FSI_BASE	0x0c
+#define OPB_CLK_SYNC	0x3c
+#define OPB_IRQ_CLEAR	0x40
+#define OPB_IRQ_MASK	0x44
+#define OPB_IRQ_STATUS	0x48
+
+#define OPB0_SELECT	0x10
+#define OPB0_RW		0x14
+#define OPB0_XFER_SIZE	0x18
+#define OPB0_FSI_ADDR	0x1c
+#define OPB0_FSI_DATA_W	0x20
+#define OPB0_STATUS	0x80
+#define OPB0_FSI_DATA_R	0x84
+
+#define OPB0_WRITE_ORDER1	0x4c
+#define OPB0_WRITE_ORDER2	0x50
+#define OPB1_WRITE_ORDER1	0x54
+#define OPB1_WRITE_ORDER2	0x58
+#define OPB0_READ_ORDER1	0x5c
+#define OPB1_READ_ORDER2	0x60
+
+#define OPB_RETRY_COUNTER	0x64
+
+/* OPBn_STATUS */
+#define STATUS_HALFWORD_ACK	BIT(0)
+#define STATUS_FULLWORD_ACK	BIT(1)
+#define STATUS_ERR_ACK		BIT(2)
+#define STATUS_RETRY		BIT(3)
+#define STATUS_TIMEOUT		BIT(4)
+
+/* OPB_IRQ_MASK */
+#define OPB1_XFER_ACK_EN BIT(17)
+#define OPB0_XFER_ACK_EN BIT(16)
+
+/* OPB_RW */
+#define CMD_READ	BIT(0)
+#define CMD_WRITE	0
+
+/* OPBx_XFER_SIZE */
+#define XFER_FULLWORD	(BIT(1) | BIT(0))
+#define XFER_HALFWORD	(BIT(0))
+#define XFER_BYTE	(0)
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/fsi_master_aspeed.h>
+
+#define FSI_LINK_ENABLE_SETUP_TIME	10	/* in mS */
+
+#define DEFAULT_DIVISOR			14
+#define OPB_POLL_TIMEOUT		10000
+
+static int __opb_write(struct fsi_master_aspeed *aspeed, u32 addr,
+		       u32 val, u32 transfer_size)
+{
+	void __iomem *base = aspeed->base;
+	u32 reg, status;
+	int ret;
+
+	writel(CMD_WRITE, base + OPB0_RW);
+	writel(transfer_size, base + OPB0_XFER_SIZE);
+	writel(addr, base + OPB0_FSI_ADDR);
+	writel(val, base + OPB0_FSI_DATA_W);
+	writel(0x1, base + OPB_IRQ_CLEAR);
+	writel(0x1, base + OPB_TRIGGER);
+
+	ret = readl_poll_timeout(base + OPB_IRQ_STATUS, reg,
+				(reg & OPB0_XFER_ACK_EN) != 0,
+				0, OPB_POLL_TIMEOUT);
+
+	status = readl(base + OPB0_STATUS);
+
+	trace_fsi_master_aspeed_opb_write(addr, val, transfer_size, status, reg);
+
+	/* Return error when poll timed out */
+	if (ret)
+		return ret;
+
+	/* Command failed, master will reset */
+	if (status & STATUS_ERR_ACK)
+		return -EIO;
+
+	return 0;
+}
+
+static int opb_writeb(struct fsi_master_aspeed *aspeed, u32 addr, u8 val)
+{
+	return __opb_write(aspeed, addr, val, XFER_BYTE);
+}
+
+static int opb_writew(struct fsi_master_aspeed *aspeed, u32 addr, __be16 val)
+{
+	return __opb_write(aspeed, addr, (__force u16)val, XFER_HALFWORD);
+}
+
+static int opb_writel(struct fsi_master_aspeed *aspeed, u32 addr, __be32 val)
+{
+	return __opb_write(aspeed, addr, (__force u32)val, XFER_FULLWORD);
+}
+
+static int __opb_read(struct fsi_master_aspeed *aspeed, uint32_t addr,
+		      u32 transfer_size, void *out)
+{
+	void __iomem *base = aspeed->base;
+	u32 result, reg;
+	int status, ret;
+
+	writel(CMD_READ, base + OPB0_RW);
+	writel(transfer_size, base + OPB0_XFER_SIZE);
+	writel(addr, base + OPB0_FSI_ADDR);
+	writel(0x1, base + OPB_IRQ_CLEAR);
+	writel(0x1, base + OPB_TRIGGER);
+
+	ret = readl_poll_timeout(base + OPB_IRQ_STATUS, reg,
+			   (reg & OPB0_XFER_ACK_EN) != 0,
+			   0, OPB_POLL_TIMEOUT);
+
+	status = readl(base + OPB0_STATUS);
+
+	result = readl(base + OPB0_FSI_DATA_R);
+
+	trace_fsi_master_aspeed_opb_read(addr, transfer_size, result,
+			readl(base + OPB0_STATUS),
+			reg);
+
+	/* Return error when poll timed out */
+	if (ret)
+		return ret;
+
+	/* Command failed, master will reset */
+	if (status & STATUS_ERR_ACK)
+		return -EIO;
+
+	if (out) {
+		switch (transfer_size) {
+		case XFER_BYTE:
+			*(u8 *)out = result;
+			break;
+		case XFER_HALFWORD:
+			*(u16 *)out = result;
+			break;
+		case XFER_FULLWORD:
+			*(u32 *)out = result;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+	}
+
+	return 0;
+}
+
+static int opb_readl(struct fsi_master_aspeed *aspeed, uint32_t addr, __be32 *out)
+{
+	return __opb_read(aspeed, addr, XFER_FULLWORD, out);
+}
+
+static int opb_readw(struct fsi_master_aspeed *aspeed, uint32_t addr, __be16 *out)
+{
+	return __opb_read(aspeed, addr, XFER_HALFWORD, (void *)out);
+}
+
+static int opb_readb(struct fsi_master_aspeed *aspeed, uint32_t addr, u8 *out)
+{
+	return __opb_read(aspeed, addr, XFER_BYTE, (void *)out);
+}
+
+static int check_errors(struct fsi_master_aspeed *aspeed, int err)
+{
+	int ret;
+
+	if (trace_fsi_master_aspeed_opb_error_enabled()) {
+		__be32 mresp0, mstap0, mesrb0;
+
+		opb_readl(aspeed, ctrl_base + FSI_MRESP0, &mresp0);
+		opb_readl(aspeed, ctrl_base + FSI_MSTAP0, &mstap0);
+		opb_readl(aspeed, ctrl_base + FSI_MESRB0, &mesrb0);
+
+		trace_fsi_master_aspeed_opb_error(
+				be32_to_cpu(mresp0),
+				be32_to_cpu(mstap0),
+				be32_to_cpu(mesrb0));
+	}
+
+	if (err == -EIO) {
+		/* Check MAEB (0x70) ? */
+
+		/* Then clear errors in master */
+		ret = opb_writel(aspeed, ctrl_base + FSI_MRESP0,
+				cpu_to_be32(FSI_MRESP_RST_ALL_MASTER));
+		if (ret) {
+			/* TODO: log? return different code? */
+			return ret;
+		}
+		/* TODO: confirm that 0x70 was okay */
+	}
+
+	/* This will pass through timeout errors */
+	return err;
+}
+
+static int aspeed_master_read(struct fsi_master *master, int link,
+			uint8_t id, uint32_t addr, void *val, size_t size)
+{
+	struct fsi_master_aspeed *aspeed = to_fsi_master_aspeed(master);
+	int ret;
+
+	if (id != 0)
+		return -EINVAL;
+
+	addr += link * FSI_HUB_LINK_SIZE;
+
+	switch (size) {
+	case 1:
+		ret = opb_readb(aspeed, fsi_base + addr, val);
+		break;
+	case 2:
+		ret = opb_readw(aspeed, fsi_base + addr, val);
+		break;
+	case 4:
+		ret = opb_readl(aspeed, fsi_base + addr, val);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ret = check_errors(aspeed, ret);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int aspeed_master_write(struct fsi_master *master, int link,
+			uint8_t id, uint32_t addr, const void *val, size_t size)
+{
+	struct fsi_master_aspeed *aspeed = to_fsi_master_aspeed(master);
+	int ret;
+
+	if (id != 0)
+		return -EINVAL;
+
+	addr += link * FSI_HUB_LINK_SIZE;
+
+	switch (size) {
+	case 1:
+		ret = opb_writeb(aspeed, fsi_base + addr, *(u8 *)val);
+		break;
+	case 2:
+		ret = opb_writew(aspeed, fsi_base + addr, *(__be16 *)val);
+		break;
+	case 4:
+		ret = opb_writel(aspeed, fsi_base + addr, *(__be32 *)val);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ret = check_errors(aspeed, ret);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int aspeed_master_link_enable(struct fsi_master *master, int link)
+{
+	struct fsi_master_aspeed *aspeed = to_fsi_master_aspeed(master);
+	int idx, bit, ret;
+	__be32 reg, result;
+
+	idx = link / 32;
+	bit = link % 32;
+
+	reg = cpu_to_be32(0x80000000 >> bit);
+
+	ret = opb_writel(aspeed, ctrl_base + FSI_MSENP0 + (4 * idx), reg);
+	if (ret)
+		return ret;
+
+	mdelay(FSI_LINK_ENABLE_SETUP_TIME);
+
+	ret = opb_readl(aspeed, ctrl_base + FSI_MENP0 + (4 * idx), &result);
+	if (ret)
+		return ret;
+
+	if (result != reg) {
+		dev_err(aspeed->dev, "%s failed: %08x\n", __func__, result);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int aspeed_master_term(struct fsi_master *master, int link, uint8_t id)
+{
+	uint32_t addr;
+	__be32 cmd;
+
+	addr = 0x4;
+	cmd = cpu_to_be32(0xecc00000);
+
+	return aspeed_master_write(master, link, id, addr, &cmd, 4);
+}
+
+static int aspeed_master_break(struct fsi_master *master, int link)
+{
+	uint32_t addr;
+	__be32 cmd;
+
+	addr = 0x0;
+	cmd = cpu_to_be32(0xc0de0000);
+
+	return aspeed_master_write(master, link, 0, addr, &cmd, 4);
+}
+
+static void aspeed_master_release(struct device *dev)
+{
+	struct fsi_master_aspeed *aspeed =
+		to_fsi_master_aspeed(dev_to_fsi_master(dev));
+
+	kfree(aspeed);
+}
+
+/* mmode encoders */
+static inline u32 fsi_mmode_crs0(u32 x)
+{
+	return (x & FSI_MMODE_CRS0MASK) << FSI_MMODE_CRS0SHFT;
+}
+
+static inline u32 fsi_mmode_crs1(u32 x)
+{
+	return (x & FSI_MMODE_CRS1MASK) << FSI_MMODE_CRS1SHFT;
+}
+
+static int aspeed_master_init(struct fsi_master_aspeed *aspeed)
+{
+	__be32 reg;
+
+	reg = cpu_to_be32(FSI_MRESP_RST_ALL_MASTER | FSI_MRESP_RST_ALL_LINK
+			| FSI_MRESP_RST_MCR | FSI_MRESP_RST_PYE);
+	opb_writel(aspeed, ctrl_base + FSI_MRESP0, reg);
+
+	/* Initialize the MFSI (hub master) engine */
+	reg = cpu_to_be32(FSI_MRESP_RST_ALL_MASTER | FSI_MRESP_RST_ALL_LINK
+			| FSI_MRESP_RST_MCR | FSI_MRESP_RST_PYE);
+	opb_writel(aspeed, ctrl_base + FSI_MRESP0, reg);
+
+	reg = cpu_to_be32(FSI_MECTRL_EOAE | FSI_MECTRL_P8_AUTO_TERM);
+	opb_writel(aspeed, ctrl_base + FSI_MECTRL, reg);
+
+	reg = cpu_to_be32(FSI_MMODE_ECRC | FSI_MMODE_EPC | FSI_MMODE_RELA
+			| fsi_mmode_crs0(DEFAULT_DIVISOR)
+			| fsi_mmode_crs1(DEFAULT_DIVISOR)
+			| FSI_MMODE_P8_TO_LSB);
+	opb_writel(aspeed, ctrl_base + FSI_MMODE, reg);
+
+	reg = cpu_to_be32(0xffff0000);
+	opb_writel(aspeed, ctrl_base + FSI_MDLYR, reg);
+
+	reg = cpu_to_be32(~0);
+	opb_writel(aspeed, ctrl_base + FSI_MSENP0, reg);
+
+	/* Leave enabled long enough for master logic to set up */
+	mdelay(FSI_LINK_ENABLE_SETUP_TIME);
+
+	opb_writel(aspeed, ctrl_base + FSI_MCENP0, reg);
+
+	opb_readl(aspeed, ctrl_base + FSI_MAEB, NULL);
+
+	reg = cpu_to_be32(FSI_MRESP_RST_ALL_MASTER | FSI_MRESP_RST_ALL_LINK);
+	opb_writel(aspeed, ctrl_base + FSI_MRESP0, reg);
+
+	opb_readl(aspeed, ctrl_base + FSI_MLEVP0, NULL);
+
+	/* Reset the master bridge */
+	reg = cpu_to_be32(FSI_MRESB_RST_GEN);
+	opb_writel(aspeed, ctrl_base + FSI_MRESB0, reg);
+
+	reg = cpu_to_be32(FSI_MRESB_RST_ERR);
+	opb_writel(aspeed, ctrl_base + FSI_MRESB0, reg);
+
+	return 0;
+}
+
+static int fsi_master_aspeed_probe(struct platform_device *pdev)
+{
+	struct fsi_master_aspeed *aspeed;
+	struct resource *res;
+	int rc, links, reg;
+	__be32 raw;
+
+	aspeed = devm_kzalloc(&pdev->dev, sizeof(*aspeed), GFP_KERNEL);
+	if (!aspeed)
+		return -ENOMEM;
+
+	aspeed->dev = &pdev->dev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	aspeed->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(aspeed->base))
+		return PTR_ERR(aspeed->base);
+
+	aspeed->clk = devm_clk_get(aspeed->dev, NULL);
+	if (IS_ERR(aspeed->clk)) {
+		dev_err(aspeed->dev, "couldn't get clock\n");
+		return PTR_ERR(aspeed->clk);
+	}
+	rc = clk_prepare_enable(aspeed->clk);
+	if (rc) {
+		dev_err(aspeed->dev, "couldn't enable clock\n");
+		return rc;
+	}
+
+	writel(0x1, aspeed->base + OPB_CLK_SYNC);
+	writel(OPB1_XFER_ACK_EN | OPB0_XFER_ACK_EN,
+			aspeed->base + OPB_IRQ_MASK);
+
+	/* TODO: determine an appropriate value */
+	writel(0x10, aspeed->base + OPB_RETRY_COUNTER);
+
+	writel(ctrl_base, aspeed->base + OPB_CTRL_BASE);
+	writel(fsi_base, aspeed->base + OPB_FSI_BASE);
+
+	/* Set read data order */
+	writel(0x00030b1b, aspeed->base + OPB0_READ_ORDER1);
+
+	/* Set write data order */
+	writel(0x0011101b, aspeed->base + OPB0_WRITE_ORDER1);
+	writel(0x0c330f3f, aspeed->base + OPB0_WRITE_ORDER2);
+
+	/*
+	 * Select OPB0 for all operations.
+	 * Will need to be reworked when enabling DMA or anything that uses
+	 * OPB1.
+	 */
+	writel(0x1, aspeed->base + OPB0_SELECT);
+
+	rc = opb_readl(aspeed, ctrl_base + FSI_MVER, &raw);
+	if (rc) {
+		dev_err(&pdev->dev, "failed to read hub version\n");
+		return rc;
+	}
+
+	reg = be32_to_cpu(raw);
+	links = (reg >> 8) & 0xff;
+	dev_info(&pdev->dev, "hub version %08x (%d links)\n", reg, links);
+
+	aspeed->master.dev.parent = &pdev->dev;
+	aspeed->master.dev.release = aspeed_master_release;
+	aspeed->master.dev.of_node = of_node_get(dev_of_node(&pdev->dev));
+
+	aspeed->master.n_links = links;
+	aspeed->master.read = aspeed_master_read;
+	aspeed->master.write = aspeed_master_write;
+	aspeed->master.send_break = aspeed_master_break;
+	aspeed->master.term = aspeed_master_term;
+	aspeed->master.link_enable = aspeed_master_link_enable;
+
+	dev_set_drvdata(&pdev->dev, aspeed);
+
+	aspeed_master_init(aspeed);
+
+	rc = fsi_master_register(&aspeed->master);
+	if (rc)
+		goto err_release;
+
+	/* At this point, fsi_master_register performs the device_initialize(),
+	 * and holds the sole reference on master.dev. This means the device
+	 * will be freed (via ->release) during any subsequent call to
+	 * fsi_master_unregister.  We add our own reference to it here, so we
+	 * can perform cleanup (in _remove()) without it being freed before
+	 * we're ready.
+	 */
+	get_device(&aspeed->master.dev);
+	return 0;
+
+err_release:
+	clk_disable_unprepare(aspeed->clk);
+	return rc;
+}
+
+static int fsi_master_aspeed_remove(struct platform_device *pdev)
+{
+	struct fsi_master_aspeed *aspeed = platform_get_drvdata(pdev);
+
+	fsi_master_unregister(&aspeed->master);
+	clk_disable_unprepare(aspeed->clk);
+
+	return 0;
+}
+
+static const struct of_device_id fsi_master_aspeed_match[] = {
+	{ .compatible = "aspeed,ast2600-fsi-master" },
+	{ },
+};
+
+static struct platform_driver fsi_master_aspeed_driver = {
+	.driver = {
+		.name		= "fsi-master-aspeed",
+		.of_match_table	= fsi_master_aspeed_match,
+	},
+	.probe	= fsi_master_aspeed_probe,
+	.remove = fsi_master_aspeed_remove,
+};
+
+module_platform_driver(fsi_master_aspeed_driver);
+MODULE_LICENSE("GPL");
diff --git a/drivers/fsi/fsi-master-hub.c b/drivers/fsi/fsi-master-hub.c
index f158b1a88286..def35cf92571 100644
--- a/drivers/fsi/fsi-master-hub.c
+++ b/drivers/fsi/fsi-master-hub.c
@@ -13,53 +13,7 @@
 
 #include "fsi-master.h"
 
-/* Control Registers */
-#define FSI_MMODE		0x0		/* R/W: mode */
-#define FSI_MDLYR		0x4		/* R/W: delay */
-#define FSI_MCRSP		0x8		/* R/W: clock rate */
-#define FSI_MENP0		0x10		/* R/W: enable */
-#define FSI_MLEVP0		0x18		/* R: plug detect */
-#define FSI_MSENP0		0x18		/* S: Set enable */
-#define FSI_MCENP0		0x20		/* C: Clear enable */
-#define FSI_MAEB		0x70		/* R: Error address */
-#define FSI_MVER		0x74		/* R: master version/type */
-#define FSI_MRESP0		0xd0		/* W: Port reset */
-#define FSI_MESRB0		0x1d0		/* R: Master error status */
-#define FSI_MRESB0		0x1d0		/* W: Reset bridge */
-#define FSI_MECTRL		0x2e0		/* W: Error control */
-
-/* MMODE: Mode control */
-#define FSI_MMODE_EIP		0x80000000	/* Enable interrupt polling */
-#define FSI_MMODE_ECRC		0x40000000	/* Enable error recovery */
-#define FSI_MMODE_EPC		0x10000000	/* Enable parity checking */
-#define FSI_MMODE_P8_TO_LSB	0x00000010	/* Timeout value LSB */
-						/*   MSB=1, LSB=0 is 0.8 ms */
-						/*   MSB=0, LSB=1 is 0.9 ms */
-#define FSI_MMODE_CRS0SHFT	18		/* Clk rate selection 0 shift */
-#define FSI_MMODE_CRS0MASK	0x3ff		/* Clk rate selection 0 mask */
-#define FSI_MMODE_CRS1SHFT	8		/* Clk rate selection 1 shift */
-#define FSI_MMODE_CRS1MASK	0x3ff		/* Clk rate selection 1 mask */
-
-/* MRESB: Reset brindge */
-#define FSI_MRESB_RST_GEN	0x80000000	/* General reset */
-#define FSI_MRESB_RST_ERR	0x40000000	/* Error Reset */
-
-/* MRESB: Reset port */
-#define FSI_MRESP_RST_ALL_MASTER 0x20000000	/* Reset all FSI masters */
-#define FSI_MRESP_RST_ALL_LINK	0x10000000	/* Reset all FSI port contr. */
-#define FSI_MRESP_RST_MCR	0x08000000	/* Reset FSI master reg. */
-#define FSI_MRESP_RST_PYE	0x04000000	/* Reset FSI parity error */
-#define FSI_MRESP_RST_ALL	0xfc000000	/* Reset any error */
-
-/* MECTRL: Error control */
-#define FSI_MECTRL_EOAE		0x8000		/* Enable machine check when */
-						/* master 0 in error */
-#define FSI_MECTRL_P8_AUTO_TERM	0x4000		/* Auto terminate */
-
 #define FSI_ENGID_HUB_MASTER		0x1c
-#define FSI_HUB_LINK_OFFSET		0x80000
-#define FSI_HUB_LINK_SIZE		0x80000
-#define FSI_HUB_MASTER_MAX_LINKS	8
 
 #define FSI_LINK_ENABLE_SETUP_TIME	10	/* in mS */
 
diff --git a/drivers/fsi/fsi-master.h b/drivers/fsi/fsi-master.h
index c7174237e864..6e8d4d4d5149 100644
--- a/drivers/fsi/fsi-master.h
+++ b/drivers/fsi/fsi-master.h
@@ -12,6 +12,71 @@
 #include <linux/device.h>
 #include <linux/mutex.h>
 
+/*
+ * Master registers
+ *
+ * These are used by hardware masters, such as the one in the FSP2, AST2600 and
+ * the hub master in POWER processors.
+ */
+
+/* Control Registers */
+#define FSI_MMODE		0x0		/* R/W: mode */
+#define FSI_MDLYR		0x4		/* R/W: delay */
+#define FSI_MCRSP		0x8		/* R/W: clock rate */
+#define FSI_MENP0		0x10		/* R/W: enable */
+#define FSI_MLEVP0		0x18		/* R: plug detect */
+#define FSI_MSENP0		0x18		/* S: Set enable */
+#define FSI_MCENP0		0x20		/* C: Clear enable */
+#define FSI_MAEB		0x70		/* R: Error address */
+#define FSI_MVER		0x74		/* R: master version/type */
+#define FSI_MSTAP0		0xd0		/* R: Port status */
+#define FSI_MRESP0		0xd0		/* W: Port reset */
+#define FSI_MESRB0		0x1d0		/* R: Master error status */
+#define FSI_MRESB0		0x1d0		/* W: Reset bridge */
+#define FSI_MSCSB0		0x1d4		/* R: Master sub command stack */
+#define FSI_MATRB0		0x1d8		/* R: Master address trace */
+#define FSI_MDTRB0		0x1dc		/* R: Master data trace */
+#define FSI_MECTRL		0x2e0		/* W: Error control */
+
+/* MMODE: Mode control */
+#define FSI_MMODE_EIP		0x80000000	/* Enable interrupt polling */
+#define FSI_MMODE_ECRC		0x40000000	/* Enable error recovery */
+#define FSI_MMODE_RELA		0x20000000	/* Enable relative address commands */
+#define FSI_MMODE_EPC		0x10000000	/* Enable parity checking */
+#define FSI_MMODE_P8_TO_LSB	0x00000010	/* Timeout value LSB */
+						/*   MSB=1, LSB=0 is 0.8 ms */
+						/*   MSB=0, LSB=1 is 0.9 ms */
+#define FSI_MMODE_CRS0SHFT	18		/* Clk rate selection 0 shift */
+#define FSI_MMODE_CRS0MASK	0x3ff		/* Clk rate selection 0 mask */
+#define FSI_MMODE_CRS1SHFT	8		/* Clk rate selection 1 shift */
+#define FSI_MMODE_CRS1MASK	0x3ff		/* Clk rate selection 1 mask */
+
+/* MRESB: Reset brindge */
+#define FSI_MRESB_RST_GEN	0x80000000	/* General reset */
+#define FSI_MRESB_RST_ERR	0x40000000	/* Error Reset */
+
+/* MRESP: Reset port */
+#define FSI_MRESP_RST_ALL_MASTER 0x20000000	/* Reset all FSI masters */
+#define FSI_MRESP_RST_ALL_LINK	0x10000000	/* Reset all FSI port contr. */
+#define FSI_MRESP_RST_MCR	0x08000000	/* Reset FSI master reg. */
+#define FSI_MRESP_RST_PYE	0x04000000	/* Reset FSI parity error */
+#define FSI_MRESP_RST_ALL	0xfc000000	/* Reset any error */
+
+/* MECTRL: Error control */
+#define FSI_MECTRL_EOAE		0x8000		/* Enable machine check when */
+						/* master 0 in error */
+#define FSI_MECTRL_P8_AUTO_TERM	0x4000		/* Auto terminate */
+
+#define FSI_HUB_LINK_OFFSET		0x80000
+#define FSI_HUB_LINK_SIZE		0x80000
+#define FSI_HUB_MASTER_MAX_LINKS	8
+
+/*
+ * Protocol definitions
+ *
+ * These are used by low level masters that bit-bang out the protocol
+ */
+
 /* Various protocol delays */
 #define	FSI_ECHO_DELAY_CLOCKS	16	/* Number clocks for echo delay */
 #define	FSI_SEND_DELAY_CLOCKS	16	/* Number clocks for send delay */
@@ -47,6 +112,12 @@
 /* fsi-master definition and flags */
 #define FSI_MASTER_FLAG_SWCLOCK		0x1
 
+/*
+ * Structures and function prototypes
+ *
+ * These are common to all masters
+ */
+
 struct fsi_master {
 	struct device	dev;
 	int		idx;
diff --git a/drivers/gpio/gpio-menz127.c b/drivers/gpio/gpio-menz127.c
index 70fdb42a8e88..1e21c661d79d 100644
--- a/drivers/gpio/gpio-menz127.c
+++ b/drivers/gpio/gpio-menz127.c
@@ -211,3 +211,4 @@ MODULE_AUTHOR("Andreas Werner <andreas.werner@men.de>");
 MODULE_DESCRIPTION("MEN 16z127 GPIO Controller");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("mcb:16z127");
+MODULE_IMPORT_NS(MCB);
diff --git a/drivers/greybus/connection.c b/drivers/greybus/connection.c
index fc8f57f97ce6..e3799a53a193 100644
--- a/drivers/greybus/connection.c
+++ b/drivers/greybus/connection.c
@@ -361,9 +361,6 @@ static int gb_connection_hd_cport_quiesce(struct gb_connection *connection)
 	if (connection->mode_switch)
 		peer_space += sizeof(struct gb_operation_msg_hdr);
 
-	if (!hd->driver->cport_quiesce)
-		return 0;
-
 	ret = hd->driver->cport_quiesce(hd, connection->hd_cport_id,
 					peer_space,
 					GB_CONNECTION_CPORT_QUIESCE_TIMEOUT);
diff --git a/drivers/hwtracing/coresight/Kconfig b/drivers/hwtracing/coresight/Kconfig
index 7a9f5fb08330..6ff30e25af55 100644
--- a/drivers/hwtracing/coresight/Kconfig
+++ b/drivers/hwtracing/coresight/Kconfig
@@ -4,6 +4,7 @@
 #
 menuconfig CORESIGHT
 	bool "CoreSight Tracing Support"
+	depends on ARM || ARM64
 	depends on OF || ACPI
 	select ARM_AMBA
 	select PERF_EVENTS
diff --git a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c
index 219c10eb752c..ce41482431f9 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c
@@ -217,6 +217,7 @@ static ssize_t reset_store(struct device *dev,
 
 	/* No start-stop filtering for ViewInst */
 	config->vissctlr = 0x0;
+	config->vipcssctlr = 0x0;
 
 	/* Disable seq events */
 	for (i = 0; i < drvdata->nrseqstate-1; i++)
@@ -238,6 +239,7 @@ static ssize_t reset_store(struct device *dev,
 	for (i = 0; i < drvdata->nr_resource; i++)
 		config->res_ctrl[i] = 0x0;
 
+	config->ss_idx = 0x0;
 	for (i = 0; i < drvdata->nr_ss_cmp; i++) {
 		config->ss_ctrl[i] = 0x0;
 		config->ss_pe_cmp[i] = 0x0;
@@ -296,8 +298,6 @@ static ssize_t mode_store(struct device *dev,
 
 	spin_lock(&drvdata->spinlock);
 	config->mode = val & ETMv4_MODE_ALL;
-	etm4_set_mode_exclude(drvdata,
-			      config->mode & ETM_MODE_EXCLUDE ? true : false);
 
 	if (drvdata->instrp0 == true) {
 		/* start by clearing instruction P0 field */
@@ -652,10 +652,13 @@ static ssize_t cyc_threshold_store(struct device *dev,
 
 	if (kstrtoul(buf, 16, &val))
 		return -EINVAL;
+
+	/* mask off max threshold before checking min value */
+	val &= ETM_CYC_THRESHOLD_MASK;
 	if (val < drvdata->ccitmin)
 		return -EINVAL;
 
-	config->ccctlr = val & ETM_CYC_THRESHOLD_MASK;
+	config->ccctlr = val;
 	return size;
 }
 static DEVICE_ATTR_RW(cyc_threshold);
@@ -686,14 +689,16 @@ static ssize_t bb_ctrl_store(struct device *dev,
 		return -EINVAL;
 	if (!drvdata->nr_addr_cmp)
 		return -EINVAL;
+
 	/*
-	 * Bit[7:0] selects which address range comparator is used for
-	 * branch broadcast control.
+	 * Bit[8] controls include(1) / exclude(0), bits[0-7] select
+	 * individual range comparators. If include then at least 1
+	 * range must be selected.
 	 */
-	if (BMVAL(val, 0, 7) > drvdata->nr_addr_cmp)
+	if ((val & BIT(8)) && (BMVAL(val, 0, 7) == 0))
 		return -EINVAL;
 
-	config->bb_ctrl = val;
+	config->bb_ctrl = val & GENMASK(8, 0);
 	return size;
 }
 static DEVICE_ATTR_RW(bb_ctrl);
@@ -738,7 +743,7 @@ static ssize_t s_exlevel_vinst_show(struct device *dev,
 	struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent);
 	struct etmv4_config *config = &drvdata->config;
 
-	val = BMVAL(config->vinst_ctrl, 16, 19);
+	val = (config->vinst_ctrl & ETM_EXLEVEL_S_VICTLR_MASK) >> 16;
 	return scnprintf(buf, PAGE_SIZE, "%#lx\n", val);
 }
 
@@ -754,8 +759,8 @@ static ssize_t s_exlevel_vinst_store(struct device *dev,
 		return -EINVAL;
 
 	spin_lock(&drvdata->spinlock);
-	/* clear all EXLEVEL_S bits (bit[18] is never implemented) */
-	config->vinst_ctrl &= ~(BIT(16) | BIT(17) | BIT(19));
+	/* clear all EXLEVEL_S bits  */
+	config->vinst_ctrl &= ~(ETM_EXLEVEL_S_VICTLR_MASK);
 	/* enable instruction tracing for corresponding exception level */
 	val &= drvdata->s_ex_level;
 	config->vinst_ctrl |= (val << 16);
@@ -773,7 +778,7 @@ static ssize_t ns_exlevel_vinst_show(struct device *dev,
 	struct etmv4_config *config = &drvdata->config;
 
 	/* EXLEVEL_NS, bits[23:20] */
-	val = BMVAL(config->vinst_ctrl, 20, 23);
+	val = (config->vinst_ctrl & ETM_EXLEVEL_NS_VICTLR_MASK) >> 20;
 	return scnprintf(buf, PAGE_SIZE, "%#lx\n", val);
 }
 
@@ -789,8 +794,8 @@ static ssize_t ns_exlevel_vinst_store(struct device *dev,
 		return -EINVAL;
 
 	spin_lock(&drvdata->spinlock);
-	/* clear EXLEVEL_NS bits (bit[23] is never implemented */
-	config->vinst_ctrl &= ~(BIT(20) | BIT(21) | BIT(22));
+	/* clear EXLEVEL_NS bits  */
+	config->vinst_ctrl &= ~(ETM_EXLEVEL_NS_VICTLR_MASK);
 	/* enable instruction tracing for corresponding exception level */
 	val &= drvdata->ns_ex_level;
 	config->vinst_ctrl |= (val << 20);
@@ -966,8 +971,12 @@ static ssize_t addr_range_store(struct device *dev,
 	unsigned long val1, val2;
 	struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent);
 	struct etmv4_config *config = &drvdata->config;
+	int elements, exclude;
+
+	elements = sscanf(buf, "%lx %lx %x", &val1, &val2, &exclude);
 
-	if (sscanf(buf, "%lx %lx", &val1, &val2) != 2)
+	/*  exclude is optional, but need at least two parameter */
+	if (elements < 2)
 		return -EINVAL;
 	/* lower address comparator cannot have a higher address value */
 	if (val1 > val2)
@@ -995,9 +1004,11 @@ static ssize_t addr_range_store(struct device *dev,
 	/*
 	 * Program include or exclude control bits for vinst or vdata
 	 * whenever we change addr comparators to ETM_ADDR_TYPE_RANGE
+	 * use supplied value, or default to bit set in 'mode'
 	 */
-	etm4_set_mode_exclude(drvdata,
-			      config->mode & ETM_MODE_EXCLUDE ? true : false);
+	if (elements != 3)
+		exclude = config->mode & ETM_MODE_EXCLUDE;
+	etm4_set_mode_exclude(drvdata, exclude ? true : false);
 
 	spin_unlock(&drvdata->spinlock);
 	return size;
@@ -1054,8 +1065,6 @@ static ssize_t addr_start_store(struct device *dev,
 	config->addr_val[idx] = (u64)val;
 	config->addr_type[idx] = ETM_ADDR_TYPE_START;
 	config->vissctlr |= BIT(idx);
-	/* SSSTATUS, bit[9] - turn on start/stop logic */
-	config->vinst_ctrl |= BIT(9);
 	spin_unlock(&drvdata->spinlock);
 	return size;
 }
@@ -1111,8 +1120,6 @@ static ssize_t addr_stop_store(struct device *dev,
 	config->addr_val[idx] = (u64)val;
 	config->addr_type[idx] = ETM_ADDR_TYPE_STOP;
 	config->vissctlr |= BIT(idx + 16);
-	/* SSSTATUS, bit[9] - turn on start/stop logic */
-	config->vinst_ctrl |= BIT(9);
 	spin_unlock(&drvdata->spinlock);
 	return size;
 }
@@ -1228,6 +1235,131 @@ static ssize_t addr_context_store(struct device *dev,
 }
 static DEVICE_ATTR_RW(addr_context);
 
+static ssize_t addr_exlevel_s_ns_show(struct device *dev,
+				      struct device_attribute *attr,
+				      char *buf)
+{
+	u8 idx;
+	unsigned long val;
+	struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etmv4_config *config = &drvdata->config;
+
+	spin_lock(&drvdata->spinlock);
+	idx = config->addr_idx;
+	val = BMVAL(config->addr_acc[idx], 8, 14);
+	spin_unlock(&drvdata->spinlock);
+	return scnprintf(buf, PAGE_SIZE, "%#lx\n", val);
+}
+
+static ssize_t addr_exlevel_s_ns_store(struct device *dev,
+				       struct device_attribute *attr,
+				       const char *buf, size_t size)
+{
+	u8 idx;
+	unsigned long val;
+	struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etmv4_config *config = &drvdata->config;
+
+	if (kstrtoul(buf, 0, &val))
+		return -EINVAL;
+
+	if (val & ~((GENMASK(14, 8) >> 8)))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	idx = config->addr_idx;
+	/* clear Exlevel_ns & Exlevel_s bits[14:12, 11:8], bit[15] is res0 */
+	config->addr_acc[idx] &= ~(GENMASK(14, 8));
+	config->addr_acc[idx] |= (val << 8);
+	spin_unlock(&drvdata->spinlock);
+	return size;
+}
+static DEVICE_ATTR_RW(addr_exlevel_s_ns);
+
+static const char * const addr_type_names[] = {
+	"unused",
+	"single",
+	"range",
+	"start",
+	"stop"
+};
+
+static ssize_t addr_cmp_view_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	u8 idx, addr_type;
+	unsigned long addr_v, addr_v2, addr_ctrl;
+	struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etmv4_config *config = &drvdata->config;
+	int size = 0;
+	bool exclude = false;
+
+	spin_lock(&drvdata->spinlock);
+	idx = config->addr_idx;
+	addr_v = config->addr_val[idx];
+	addr_ctrl = config->addr_acc[idx];
+	addr_type = config->addr_type[idx];
+	if (addr_type == ETM_ADDR_TYPE_RANGE) {
+		if (idx & 0x1) {
+			idx -= 1;
+			addr_v2 = addr_v;
+			addr_v = config->addr_val[idx];
+		} else {
+			addr_v2 = config->addr_val[idx + 1];
+		}
+		exclude = config->viiectlr & BIT(idx / 2 + 16);
+	}
+	spin_unlock(&drvdata->spinlock);
+	if (addr_type) {
+		size = scnprintf(buf, PAGE_SIZE, "addr_cmp[%i] %s %#lx", idx,
+				 addr_type_names[addr_type], addr_v);
+		if (addr_type == ETM_ADDR_TYPE_RANGE) {
+			size += scnprintf(buf + size, PAGE_SIZE - size,
+					  " %#lx %s", addr_v2,
+					  exclude ? "exclude" : "include");
+		}
+		size += scnprintf(buf + size, PAGE_SIZE - size,
+				  " ctrl(%#lx)\n", addr_ctrl);
+	} else {
+		size = scnprintf(buf, PAGE_SIZE, "addr_cmp[%i] unused\n", idx);
+	}
+	return size;
+}
+static DEVICE_ATTR_RO(addr_cmp_view);
+
+static ssize_t vinst_pe_cmp_start_stop_show(struct device *dev,
+					    struct device_attribute *attr,
+					    char *buf)
+{
+	unsigned long val;
+	struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etmv4_config *config = &drvdata->config;
+
+	if (!drvdata->nr_pe_cmp)
+		return -EINVAL;
+	val = config->vipcssctlr;
+	return scnprintf(buf, PAGE_SIZE, "%#lx\n", val);
+}
+static ssize_t vinst_pe_cmp_start_stop_store(struct device *dev,
+					     struct device_attribute *attr,
+					     const char *buf, size_t size)
+{
+	unsigned long val;
+	struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etmv4_config *config = &drvdata->config;
+
+	if (kstrtoul(buf, 16, &val))
+		return -EINVAL;
+	if (!drvdata->nr_pe_cmp)
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	config->vipcssctlr = val;
+	spin_unlock(&drvdata->spinlock);
+	return size;
+}
+static DEVICE_ATTR_RW(vinst_pe_cmp_start_stop);
+
 static ssize_t seq_idx_show(struct device *dev,
 			    struct device_attribute *attr,
 			    char *buf)
@@ -1324,8 +1456,8 @@ static ssize_t seq_event_store(struct device *dev,
 
 	spin_lock(&drvdata->spinlock);
 	idx = config->seq_idx;
-	/* RST, bits[7:0] */
-	config->seq_ctrl[idx] = val & 0xFF;
+	/* Seq control has two masks B[15:8] F[7:0] */
+	config->seq_ctrl[idx] = val & 0xFFFF;
 	spin_unlock(&drvdata->spinlock);
 	return size;
 }
@@ -1580,12 +1712,129 @@ static ssize_t res_ctrl_store(struct device *dev,
 	if (idx % 2 != 0)
 		/* PAIRINV, bit[21] */
 		val &= ~BIT(21);
-	config->res_ctrl[idx] = val;
+	config->res_ctrl[idx] = val & GENMASK(21, 0);
 	spin_unlock(&drvdata->spinlock);
 	return size;
 }
 static DEVICE_ATTR_RW(res_ctrl);
 
+static ssize_t sshot_idx_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etmv4_config *config = &drvdata->config;
+
+	val = config->ss_idx;
+	return scnprintf(buf, PAGE_SIZE, "%#lx\n", val);
+}
+
+static ssize_t sshot_idx_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t size)
+{
+	unsigned long val;
+	struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etmv4_config *config = &drvdata->config;
+
+	if (kstrtoul(buf, 16, &val))
+		return -EINVAL;
+	if (val >= drvdata->nr_ss_cmp)
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	config->ss_idx = val;
+	spin_unlock(&drvdata->spinlock);
+	return size;
+}
+static DEVICE_ATTR_RW(sshot_idx);
+
+static ssize_t sshot_ctrl_show(struct device *dev,
+			       struct device_attribute *attr,
+			       char *buf)
+{
+	unsigned long val;
+	struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etmv4_config *config = &drvdata->config;
+
+	spin_lock(&drvdata->spinlock);
+	val = config->ss_ctrl[config->ss_idx];
+	spin_unlock(&drvdata->spinlock);
+	return scnprintf(buf, PAGE_SIZE, "%#lx\n", val);
+}
+
+static ssize_t sshot_ctrl_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t size)
+{
+	u8 idx;
+	unsigned long val;
+	struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etmv4_config *config = &drvdata->config;
+
+	if (kstrtoul(buf, 16, &val))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	idx = config->ss_idx;
+	config->ss_ctrl[idx] = val & GENMASK(24, 0);
+	/* must clear bit 31 in related status register on programming */
+	config->ss_status[idx] &= ~BIT(31);
+	spin_unlock(&drvdata->spinlock);
+	return size;
+}
+static DEVICE_ATTR_RW(sshot_ctrl);
+
+static ssize_t sshot_status_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etmv4_config *config = &drvdata->config;
+
+	spin_lock(&drvdata->spinlock);
+	val = config->ss_status[config->ss_idx];
+	spin_unlock(&drvdata->spinlock);
+	return scnprintf(buf, PAGE_SIZE, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(sshot_status);
+
+static ssize_t sshot_pe_ctrl_show(struct device *dev,
+				  struct device_attribute *attr,
+				  char *buf)
+{
+	unsigned long val;
+	struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etmv4_config *config = &drvdata->config;
+
+	spin_lock(&drvdata->spinlock);
+	val = config->ss_pe_cmp[config->ss_idx];
+	spin_unlock(&drvdata->spinlock);
+	return scnprintf(buf, PAGE_SIZE, "%#lx\n", val);
+}
+
+static ssize_t sshot_pe_ctrl_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t size)
+{
+	u8 idx;
+	unsigned long val;
+	struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	struct etmv4_config *config = &drvdata->config;
+
+	if (kstrtoul(buf, 16, &val))
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	idx = config->ss_idx;
+	config->ss_pe_cmp[idx] = val & GENMASK(7, 0);
+	/* must clear bit 31 in related status register on programming */
+	config->ss_status[idx] &= ~BIT(31);
+	spin_unlock(&drvdata->spinlock);
+	return size;
+}
+static DEVICE_ATTR_RW(sshot_pe_ctrl);
+
 static ssize_t ctxid_idx_show(struct device *dev,
 			      struct device_attribute *attr,
 			      char *buf)
@@ -1714,6 +1963,7 @@ static ssize_t ctxid_masks_store(struct device *dev,
 	unsigned long val1, val2, mask;
 	struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent);
 	struct etmv4_config *config = &drvdata->config;
+	int nr_inputs;
 
 	/*
 	 * Don't use contextID tracing if coming from a PID namespace.  See
@@ -1729,7 +1979,9 @@ static ssize_t ctxid_masks_store(struct device *dev,
 	 */
 	if (!drvdata->ctxid_size || !drvdata->numcidc)
 		return -EINVAL;
-	if (sscanf(buf, "%lx %lx", &val1, &val2) != 2)
+	/* one mask if <= 4 comparators, two for up to 8 */
+	nr_inputs = sscanf(buf, "%lx %lx", &val1, &val2);
+	if ((drvdata->numcidc > 4) && (nr_inputs != 2))
 		return -EINVAL;
 
 	spin_lock(&drvdata->spinlock);
@@ -1903,6 +2155,7 @@ static ssize_t vmid_masks_store(struct device *dev,
 	unsigned long val1, val2, mask;
 	struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent);
 	struct etmv4_config *config = &drvdata->config;
+	int nr_inputs;
 
 	/*
 	 * only implemented when vmid tracing is enabled, i.e. at least one
@@ -1910,7 +2163,9 @@ static ssize_t vmid_masks_store(struct device *dev,
 	 */
 	if (!drvdata->vmid_size || !drvdata->numvmidc)
 		return -EINVAL;
-	if (sscanf(buf, "%lx %lx", &val1, &val2) != 2)
+	/* one mask if <= 4 comparators, two for up to 8 */
+	nr_inputs = sscanf(buf, "%lx %lx", &val1, &val2);
+	if ((drvdata->numvmidc > 4) && (nr_inputs != 2))
 		return -EINVAL;
 
 	spin_lock(&drvdata->spinlock);
@@ -2033,6 +2288,13 @@ static struct attribute *coresight_etmv4_attrs[] = {
 	&dev_attr_addr_stop.attr,
 	&dev_attr_addr_ctxtype.attr,
 	&dev_attr_addr_context.attr,
+	&dev_attr_addr_exlevel_s_ns.attr,
+	&dev_attr_addr_cmp_view.attr,
+	&dev_attr_vinst_pe_cmp_start_stop.attr,
+	&dev_attr_sshot_idx.attr,
+	&dev_attr_sshot_ctrl.attr,
+	&dev_attr_sshot_pe_ctrl.attr,
+	&dev_attr_sshot_status.attr,
 	&dev_attr_seq_idx.attr,
 	&dev_attr_seq_state.attr,
 	&dev_attr_seq_event.attr,
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c
index a128b5063f46..dc3f507e7562 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -18,6 +18,7 @@
 #include <linux/stat.h>
 #include <linux/clk.h>
 #include <linux/cpu.h>
+#include <linux/cpu_pm.h>
 #include <linux/coresight.h>
 #include <linux/coresight-pmu.h>
 #include <linux/pm_wakeup.h>
@@ -26,6 +27,7 @@
 #include <linux/uaccess.h>
 #include <linux/perf_event.h>
 #include <linux/pm_runtime.h>
+#include <linux/property.h>
 #include <asm/sections.h>
 #include <asm/local.h>
 #include <asm/virt.h>
@@ -37,6 +39,15 @@ static int boot_enable;
 module_param(boot_enable, int, 0444);
 MODULE_PARM_DESC(boot_enable, "Enable tracing on boot");
 
+#define PARAM_PM_SAVE_FIRMWARE	  0 /* save self-hosted state as per firmware */
+#define PARAM_PM_SAVE_NEVER	  1 /* never save any state */
+#define PARAM_PM_SAVE_SELF_HOSTED 2 /* save self-hosted state only */
+
+static int pm_save_enable = PARAM_PM_SAVE_FIRMWARE;
+module_param(pm_save_enable, int, 0444);
+MODULE_PARM_DESC(pm_save_enable,
+	"Save/restore state on power down: 1 = never, 2 = self-hosted");
+
 /* The number of ETMv4 currently registered */
 static int etm4_count;
 static struct etmv4_drvdata *etmdrvdata[NR_CPUS];
@@ -54,6 +65,14 @@ static void etm4_os_unlock(struct etmv4_drvdata *drvdata)
 	isb();
 }
 
+static void etm4_os_lock(struct etmv4_drvdata *drvdata)
+{
+	/* Writing 0x1 to TRCOSLAR locks the trace registers */
+	writel_relaxed(0x1, drvdata->base + TRCOSLAR);
+	drvdata->os_unlock = false;
+	isb();
+}
+
 static bool etm4_arch_supported(u8 arch)
 {
 	/* Mask out the minor version number */
@@ -149,6 +168,9 @@ static int etm4_enable_hw(struct etmv4_drvdata *drvdata)
 			       drvdata->base + TRCRSCTLRn(i));
 
 	for (i = 0; i < drvdata->nr_ss_cmp; i++) {
+		/* always clear status bit on restart if using single-shot */
+		if (config->ss_ctrl[i] || config->ss_pe_cmp[i])
+			config->ss_status[i] &= ~BIT(31);
 		writel_relaxed(config->ss_ctrl[i],
 			       drvdata->base + TRCSSCCRn(i));
 		writel_relaxed(config->ss_status[i],
@@ -448,6 +470,9 @@ static void etm4_disable_hw(void *info)
 {
 	u32 control;
 	struct etmv4_drvdata *drvdata = info;
+	struct etmv4_config *config = &drvdata->config;
+	struct device *etm_dev = &drvdata->csdev->dev;
+	int i;
 
 	CS_UNLOCK(drvdata->base);
 
@@ -470,6 +495,18 @@ static void etm4_disable_hw(void *info)
 	isb();
 	writel_relaxed(control, drvdata->base + TRCPRGCTLR);
 
+	/* wait for TRCSTATR.PMSTABLE to go to '1' */
+	if (coresight_timeout(drvdata->base, TRCSTATR,
+			      TRCSTATR_PMSTABLE_BIT, 1))
+		dev_err(etm_dev,
+			"timeout while waiting for PM stable Trace Status\n");
+
+	/* read the status of the single shot comparators */
+	for (i = 0; i < drvdata->nr_ss_cmp; i++) {
+		config->ss_status[i] =
+			readl_relaxed(drvdata->base + TRCSSCSRn(i));
+	}
+
 	coresight_disclaim_device_unlocked(drvdata->base);
 
 	CS_LOCK(drvdata->base);
@@ -576,6 +613,7 @@ static void etm4_init_arch_data(void *info)
 	u32 etmidr4;
 	u32 etmidr5;
 	struct etmv4_drvdata *drvdata = info;
+	int i;
 
 	/* Make sure all registers are accessible */
 	etm4_os_unlock(drvdata);
@@ -629,6 +667,7 @@ static void etm4_init_arch_data(void *info)
 	 * TRCARCHMAJ, bits[11:8] architecture major versin number
 	 */
 	drvdata->arch = BMVAL(etmidr1, 4, 11);
+	drvdata->config.arch = drvdata->arch;
 
 	/* maximum size of resources */
 	etmidr2 = readl_relaxed(drvdata->base + TRCIDR2);
@@ -698,9 +737,14 @@ static void etm4_init_arch_data(void *info)
 	drvdata->nr_resource = BMVAL(etmidr4, 16, 19) + 1;
 	/*
 	 * NUMSSCC, bits[23:20] the number of single-shot
-	 * comparator control for tracing
+	 * comparator control for tracing. Read any status regs as these
+	 * also contain RO capability data.
 	 */
 	drvdata->nr_ss_cmp = BMVAL(etmidr4, 20, 23);
+	for (i = 0; i < drvdata->nr_ss_cmp; i++) {
+		drvdata->config.ss_status[i] =
+			readl_relaxed(drvdata->base + TRCSSCSRn(i));
+	}
 	/* NUMCIDC, bits[27:24] number of Context ID comparators for tracing */
 	drvdata->numcidc = BMVAL(etmidr4, 24, 27);
 	/* NUMVMIDC, bits[31:28] number of VMID comparators for tracing */
@@ -780,6 +824,7 @@ static u64 etm4_get_ns_access_type(struct etmv4_config *config)
 static u64 etm4_get_access_type(struct etmv4_config *config)
 {
 	u64 access_type = etm4_get_ns_access_type(config);
+	u64 s_hyp = (config->arch & 0x0f) >= 0x4 ? ETM_EXLEVEL_S_HYP : 0;
 
 	/*
 	 * EXLEVEL_S, bits[11:8], don't trace anything happening
@@ -787,7 +832,8 @@ static u64 etm4_get_access_type(struct etmv4_config *config)
 	 */
 	access_type |= (ETM_EXLEVEL_S_APP	|
 			ETM_EXLEVEL_S_OS	|
-			ETM_EXLEVEL_S_HYP);
+			s_hyp			|
+			ETM_EXLEVEL_S_MON);
 
 	return access_type;
 }
@@ -865,6 +911,7 @@ static void etm4_set_default_filter(struct etmv4_config *config)
 	 * in the started state
 	 */
 	config->vinst_ctrl |= BIT(9);
+	config->mode |= ETM_MODE_VIEWINST_STARTSTOP;
 
 	/* No start-stop filtering for ViewInst */
 	config->vissctlr = 0x0;
@@ -1085,6 +1132,288 @@ static void etm4_init_trace_id(struct etmv4_drvdata *drvdata)
 	drvdata->trcid = coresight_get_trace_id(drvdata->cpu);
 }
 
+#ifdef CONFIG_CPU_PM
+static int etm4_cpu_save(struct etmv4_drvdata *drvdata)
+{
+	int i, ret = 0;
+	struct etmv4_save_state *state;
+	struct device *etm_dev = &drvdata->csdev->dev;
+
+	/*
+	 * As recommended by 3.4.1 ("The procedure when powering down the PE")
+	 * of ARM IHI 0064D
+	 */
+	dsb(sy);
+	isb();
+
+	CS_UNLOCK(drvdata->base);
+
+	/* Lock the OS lock to disable trace and external debugger access */
+	etm4_os_lock(drvdata);
+
+	/* wait for TRCSTATR.PMSTABLE to go up */
+	if (coresight_timeout(drvdata->base, TRCSTATR,
+			      TRCSTATR_PMSTABLE_BIT, 1)) {
+		dev_err(etm_dev,
+			"timeout while waiting for PM Stable Status\n");
+		etm4_os_unlock(drvdata);
+		ret = -EBUSY;
+		goto out;
+	}
+
+	state = drvdata->save_state;
+
+	state->trcprgctlr = readl(drvdata->base + TRCPRGCTLR);
+	state->trcprocselr = readl(drvdata->base + TRCPROCSELR);
+	state->trcconfigr = readl(drvdata->base + TRCCONFIGR);
+	state->trcauxctlr = readl(drvdata->base + TRCAUXCTLR);
+	state->trceventctl0r = readl(drvdata->base + TRCEVENTCTL0R);
+	state->trceventctl1r = readl(drvdata->base + TRCEVENTCTL1R);
+	state->trcstallctlr = readl(drvdata->base + TRCSTALLCTLR);
+	state->trctsctlr = readl(drvdata->base + TRCTSCTLR);
+	state->trcsyncpr = readl(drvdata->base + TRCSYNCPR);
+	state->trcccctlr = readl(drvdata->base + TRCCCCTLR);
+	state->trcbbctlr = readl(drvdata->base + TRCBBCTLR);
+	state->trctraceidr = readl(drvdata->base + TRCTRACEIDR);
+	state->trcqctlr = readl(drvdata->base + TRCQCTLR);
+
+	state->trcvictlr = readl(drvdata->base + TRCVICTLR);
+	state->trcviiectlr = readl(drvdata->base + TRCVIIECTLR);
+	state->trcvissctlr = readl(drvdata->base + TRCVISSCTLR);
+	state->trcvipcssctlr = readl(drvdata->base + TRCVIPCSSCTLR);
+	state->trcvdctlr = readl(drvdata->base + TRCVDCTLR);
+	state->trcvdsacctlr = readl(drvdata->base + TRCVDSACCTLR);
+	state->trcvdarcctlr = readl(drvdata->base + TRCVDARCCTLR);
+
+	for (i = 0; i < drvdata->nrseqstate; i++)
+		state->trcseqevr[i] = readl(drvdata->base + TRCSEQEVRn(i));
+
+	state->trcseqrstevr = readl(drvdata->base + TRCSEQRSTEVR);
+	state->trcseqstr = readl(drvdata->base + TRCSEQSTR);
+	state->trcextinselr = readl(drvdata->base + TRCEXTINSELR);
+
+	for (i = 0; i < drvdata->nr_cntr; i++) {
+		state->trccntrldvr[i] = readl(drvdata->base + TRCCNTRLDVRn(i));
+		state->trccntctlr[i] = readl(drvdata->base + TRCCNTCTLRn(i));
+		state->trccntvr[i] = readl(drvdata->base + TRCCNTVRn(i));
+	}
+
+	for (i = 0; i < drvdata->nr_resource * 2; i++)
+		state->trcrsctlr[i] = readl(drvdata->base + TRCRSCTLRn(i));
+
+	for (i = 0; i < drvdata->nr_ss_cmp; i++) {
+		state->trcssccr[i] = readl(drvdata->base + TRCSSCCRn(i));
+		state->trcsscsr[i] = readl(drvdata->base + TRCSSCSRn(i));
+		state->trcsspcicr[i] = readl(drvdata->base + TRCSSPCICRn(i));
+	}
+
+	for (i = 0; i < drvdata->nr_addr_cmp * 2; i++) {
+		state->trcacvr[i] = readl(drvdata->base + TRCACVRn(i));
+		state->trcacatr[i] = readl(drvdata->base + TRCACATRn(i));
+	}
+
+	/*
+	 * Data trace stream is architecturally prohibited for A profile cores
+	 * so we don't save (or later restore) trcdvcvr and trcdvcmr - As per
+	 * section 1.3.4 ("Possible functional configurations of an ETMv4 trace
+	 * unit") of ARM IHI 0064D.
+	 */
+
+	for (i = 0; i < drvdata->numcidc; i++)
+		state->trccidcvr[i] = readl(drvdata->base + TRCCIDCVRn(i));
+
+	for (i = 0; i < drvdata->numvmidc; i++)
+		state->trcvmidcvr[i] = readl(drvdata->base + TRCVMIDCVRn(i));
+
+	state->trccidcctlr0 = readl(drvdata->base + TRCCIDCCTLR0);
+	state->trccidcctlr1 = readl(drvdata->base + TRCCIDCCTLR1);
+
+	state->trcvmidcctlr0 = readl(drvdata->base + TRCVMIDCCTLR0);
+	state->trcvmidcctlr0 = readl(drvdata->base + TRCVMIDCCTLR1);
+
+	state->trcclaimset = readl(drvdata->base + TRCCLAIMCLR);
+
+	state->trcpdcr = readl(drvdata->base + TRCPDCR);
+
+	/* wait for TRCSTATR.IDLE to go up */
+	if (coresight_timeout(drvdata->base, TRCSTATR, TRCSTATR_IDLE_BIT, 1)) {
+		dev_err(etm_dev,
+			"timeout while waiting for Idle Trace Status\n");
+		etm4_os_unlock(drvdata);
+		ret = -EBUSY;
+		goto out;
+	}
+
+	drvdata->state_needs_restore = true;
+
+	/*
+	 * Power can be removed from the trace unit now. We do this to
+	 * potentially save power on systems that respect the TRCPDCR_PU
+	 * despite requesting software to save/restore state.
+	 */
+	writel_relaxed((state->trcpdcr & ~TRCPDCR_PU),
+			drvdata->base + TRCPDCR);
+
+out:
+	CS_LOCK(drvdata->base);
+	return ret;
+}
+
+static void etm4_cpu_restore(struct etmv4_drvdata *drvdata)
+{
+	int i;
+	struct etmv4_save_state *state = drvdata->save_state;
+
+	CS_UNLOCK(drvdata->base);
+
+	writel_relaxed(state->trcclaimset, drvdata->base + TRCCLAIMSET);
+
+	writel_relaxed(state->trcprgctlr, drvdata->base + TRCPRGCTLR);
+	writel_relaxed(state->trcprocselr, drvdata->base + TRCPROCSELR);
+	writel_relaxed(state->trcconfigr, drvdata->base + TRCCONFIGR);
+	writel_relaxed(state->trcauxctlr, drvdata->base + TRCAUXCTLR);
+	writel_relaxed(state->trceventctl0r, drvdata->base + TRCEVENTCTL0R);
+	writel_relaxed(state->trceventctl1r, drvdata->base + TRCEVENTCTL1R);
+	writel_relaxed(state->trcstallctlr, drvdata->base + TRCSTALLCTLR);
+	writel_relaxed(state->trctsctlr, drvdata->base + TRCTSCTLR);
+	writel_relaxed(state->trcsyncpr, drvdata->base + TRCSYNCPR);
+	writel_relaxed(state->trcccctlr, drvdata->base + TRCCCCTLR);
+	writel_relaxed(state->trcbbctlr, drvdata->base + TRCBBCTLR);
+	writel_relaxed(state->trctraceidr, drvdata->base + TRCTRACEIDR);
+	writel_relaxed(state->trcqctlr, drvdata->base + TRCQCTLR);
+
+	writel_relaxed(state->trcvictlr, drvdata->base + TRCVICTLR);
+	writel_relaxed(state->trcviiectlr, drvdata->base + TRCVIIECTLR);
+	writel_relaxed(state->trcvissctlr, drvdata->base + TRCVISSCTLR);
+	writel_relaxed(state->trcvipcssctlr, drvdata->base + TRCVIPCSSCTLR);
+	writel_relaxed(state->trcvdctlr, drvdata->base + TRCVDCTLR);
+	writel_relaxed(state->trcvdsacctlr, drvdata->base + TRCVDSACCTLR);
+	writel_relaxed(state->trcvdarcctlr, drvdata->base + TRCVDARCCTLR);
+
+	for (i = 0; i < drvdata->nrseqstate; i++)
+		writel_relaxed(state->trcseqevr[i],
+			       drvdata->base + TRCSEQEVRn(i));
+
+	writel_relaxed(state->trcseqrstevr, drvdata->base + TRCSEQRSTEVR);
+	writel_relaxed(state->trcseqstr, drvdata->base + TRCSEQSTR);
+	writel_relaxed(state->trcextinselr, drvdata->base + TRCEXTINSELR);
+
+	for (i = 0; i < drvdata->nr_cntr; i++) {
+		writel_relaxed(state->trccntrldvr[i],
+			       drvdata->base + TRCCNTRLDVRn(i));
+		writel_relaxed(state->trccntctlr[i],
+			       drvdata->base + TRCCNTCTLRn(i));
+		writel_relaxed(state->trccntvr[i],
+			       drvdata->base + TRCCNTVRn(i));
+	}
+
+	for (i = 0; i < drvdata->nr_resource * 2; i++)
+		writel_relaxed(state->trcrsctlr[i],
+			       drvdata->base + TRCRSCTLRn(i));
+
+	for (i = 0; i < drvdata->nr_ss_cmp; i++) {
+		writel_relaxed(state->trcssccr[i],
+			       drvdata->base + TRCSSCCRn(i));
+		writel_relaxed(state->trcsscsr[i],
+			       drvdata->base + TRCSSCSRn(i));
+		writel_relaxed(state->trcsspcicr[i],
+			       drvdata->base + TRCSSPCICRn(i));
+	}
+
+	for (i = 0; i < drvdata->nr_addr_cmp * 2; i++) {
+		writel_relaxed(state->trcacvr[i],
+			       drvdata->base + TRCACVRn(i));
+		writel_relaxed(state->trcacatr[i],
+			       drvdata->base + TRCACATRn(i));
+	}
+
+	for (i = 0; i < drvdata->numcidc; i++)
+		writel_relaxed(state->trccidcvr[i],
+			       drvdata->base + TRCCIDCVRn(i));
+
+	for (i = 0; i < drvdata->numvmidc; i++)
+		writel_relaxed(state->trcvmidcvr[i],
+			       drvdata->base + TRCVMIDCVRn(i));
+
+	writel_relaxed(state->trccidcctlr0, drvdata->base + TRCCIDCCTLR0);
+	writel_relaxed(state->trccidcctlr1, drvdata->base + TRCCIDCCTLR1);
+
+	writel_relaxed(state->trcvmidcctlr0, drvdata->base + TRCVMIDCCTLR0);
+	writel_relaxed(state->trcvmidcctlr0, drvdata->base + TRCVMIDCCTLR1);
+
+	writel_relaxed(state->trcclaimset, drvdata->base + TRCCLAIMSET);
+
+	writel_relaxed(state->trcpdcr, drvdata->base + TRCPDCR);
+
+	drvdata->state_needs_restore = false;
+
+	/*
+	 * As recommended by section 4.3.7 ("Synchronization when using the
+	 * memory-mapped interface") of ARM IHI 0064D
+	 */
+	dsb(sy);
+	isb();
+
+	/* Unlock the OS lock to re-enable trace and external debug access */
+	etm4_os_unlock(drvdata);
+	CS_LOCK(drvdata->base);
+}
+
+static int etm4_cpu_pm_notify(struct notifier_block *nb, unsigned long cmd,
+			      void *v)
+{
+	struct etmv4_drvdata *drvdata;
+	unsigned int cpu = smp_processor_id();
+
+	if (!etmdrvdata[cpu])
+		return NOTIFY_OK;
+
+	drvdata = etmdrvdata[cpu];
+
+	if (!drvdata->save_state)
+		return NOTIFY_OK;
+
+	if (WARN_ON_ONCE(drvdata->cpu != cpu))
+		return NOTIFY_BAD;
+
+	switch (cmd) {
+	case CPU_PM_ENTER:
+		/* save the state if self-hosted coresight is in use */
+		if (local_read(&drvdata->mode))
+			if (etm4_cpu_save(drvdata))
+				return NOTIFY_BAD;
+		break;
+	case CPU_PM_EXIT:
+		/* fallthrough */
+	case CPU_PM_ENTER_FAILED:
+		if (drvdata->state_needs_restore)
+			etm4_cpu_restore(drvdata);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block etm4_cpu_pm_nb = {
+	.notifier_call = etm4_cpu_pm_notify,
+};
+
+static int etm4_cpu_pm_register(void)
+{
+	return cpu_pm_register_notifier(&etm4_cpu_pm_nb);
+}
+
+static void etm4_cpu_pm_unregister(void)
+{
+	cpu_pm_unregister_notifier(&etm4_cpu_pm_nb);
+}
+#else
+static int etm4_cpu_pm_register(void) { return 0; }
+static void etm4_cpu_pm_unregister(void) { }
+#endif
+
 static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 {
 	int ret;
@@ -1101,6 +1430,17 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 
 	dev_set_drvdata(dev, drvdata);
 
+	if (pm_save_enable == PARAM_PM_SAVE_FIRMWARE)
+		pm_save_enable = coresight_loses_context_with_cpu(dev) ?
+			       PARAM_PM_SAVE_SELF_HOSTED : PARAM_PM_SAVE_NEVER;
+
+	if (pm_save_enable != PARAM_PM_SAVE_NEVER) {
+		drvdata->save_state = devm_kmalloc(dev,
+				sizeof(struct etmv4_save_state), GFP_KERNEL);
+		if (!drvdata->save_state)
+			return -ENOMEM;
+	}
+
 	/* Validity for the resource is already checked by the AMBA core */
 	base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(base))
@@ -1135,6 +1475,10 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 		if (ret < 0)
 			goto err_arch_supported;
 		hp_online = ret;
+
+		ret = etm4_cpu_pm_register();
+		if (ret)
+			goto err_arch_supported;
 	}
 
 	cpus_read_unlock();
@@ -1185,6 +1529,8 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 
 err_arch_supported:
 	if (--etm4_count == 0) {
+		etm4_cpu_pm_unregister();
+
 		cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING);
 		if (hp_online)
 			cpuhp_remove_state_nocalls(hp_online);
@@ -1211,6 +1557,7 @@ static const struct amba_id etm4_ids[] = {
 	CS_AMBA_UCI_ID(0x000f0211, uci_id_etm4),/* Qualcomm Kryo */
 	CS_AMBA_ID(0x000bb802),			/* Qualcomm Kryo 385 Cortex-A55 */
 	CS_AMBA_ID(0x000bb803),			/* Qualcomm Kryo 385 Cortex-A75 */
+	CS_AMBA_UCI_ID(0x000cc0af, uci_id_etm4),/* Marvell ThunderX2 */
 	{},
 };
 
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h
index 4523f10ddd0f..4a695bf90582 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.h
+++ b/drivers/hwtracing/coresight/coresight-etm4x.h
@@ -175,22 +175,28 @@
 					 ETM_MODE_EXCL_USER)
 
 #define TRCSTATR_IDLE_BIT		0
+#define TRCSTATR_PMSTABLE_BIT		1
 #define ETM_DEFAULT_ADDR_COMP		0
 
 /* PowerDown Control Register bits */
 #define TRCPDCR_PU			BIT(3)
 
-/* secure state access levels */
+/* secure state access levels - TRCACATRn */
 #define ETM_EXLEVEL_S_APP		BIT(8)
 #define ETM_EXLEVEL_S_OS		BIT(9)
-#define ETM_EXLEVEL_S_NA		BIT(10)
-#define ETM_EXLEVEL_S_HYP		BIT(11)
-/* non-secure state access levels */
+#define ETM_EXLEVEL_S_HYP		BIT(10)
+#define ETM_EXLEVEL_S_MON		BIT(11)
+/* non-secure state access levels - TRCACATRn */
 #define ETM_EXLEVEL_NS_APP		BIT(12)
 #define ETM_EXLEVEL_NS_OS		BIT(13)
 #define ETM_EXLEVEL_NS_HYP		BIT(14)
 #define ETM_EXLEVEL_NS_NA		BIT(15)
 
+/* secure / non secure masks - TRCVICTLR, IDR3 */
+#define ETM_EXLEVEL_S_VICTLR_MASK	GENMASK(19, 16)
+/* NS MON (EL3) mode never implemented */
+#define ETM_EXLEVEL_NS_VICTLR_MASK	GENMASK(22, 20)
+
 /**
  * struct etmv4_config - configuration information related to an ETMv4
  * @mode:	Controls various modes supported by this ETM.
@@ -221,6 +227,7 @@
  * @cntr_val:	Sets or returns the value for a counter.
  * @res_idx:	Resource index selector.
  * @res_ctrl:	Controls the selection of the resources in the trace unit.
+ * @ss_idx:	Single-shot index selector.
  * @ss_ctrl:	Controls the corresponding single-shot comparator resource.
  * @ss_status:	The status of the corresponding single-shot comparator.
  * @ss_pe_cmp:	Selects the PE comparator inputs for Single-shot control.
@@ -237,6 +244,7 @@
  * @vmid_mask0:	VM ID comparator mask for comparator 0-3.
  * @vmid_mask1:	VM ID comparator mask for comparator 4-7.
  * @ext_inp:	External input selection.
+ * @arch:	ETM architecture version (for arch dependent config).
  */
 struct etmv4_config {
 	u32				mode;
@@ -263,6 +271,7 @@ struct etmv4_config {
 	u32				cntr_val[ETMv4_MAX_CNTR];
 	u8				res_idx;
 	u32				res_ctrl[ETM_MAX_RES_SEL];
+	u8				ss_idx;
 	u32				ss_ctrl[ETM_MAX_SS_CMP];
 	u32				ss_status[ETM_MAX_SS_CMP];
 	u32				ss_pe_cmp[ETM_MAX_SS_CMP];
@@ -279,6 +288,66 @@ struct etmv4_config {
 	u32				vmid_mask0;
 	u32				vmid_mask1;
 	u32				ext_inp;
+	u8				arch;
+};
+
+/**
+ * struct etm4_save_state - state to be preserved when ETM is without power
+ */
+struct etmv4_save_state {
+	u32	trcprgctlr;
+	u32	trcprocselr;
+	u32	trcconfigr;
+	u32	trcauxctlr;
+	u32	trceventctl0r;
+	u32	trceventctl1r;
+	u32	trcstallctlr;
+	u32	trctsctlr;
+	u32	trcsyncpr;
+	u32	trcccctlr;
+	u32	trcbbctlr;
+	u32	trctraceidr;
+	u32	trcqctlr;
+
+	u32	trcvictlr;
+	u32	trcviiectlr;
+	u32	trcvissctlr;
+	u32	trcvipcssctlr;
+	u32	trcvdctlr;
+	u32	trcvdsacctlr;
+	u32	trcvdarcctlr;
+
+	u32	trcseqevr[ETM_MAX_SEQ_STATES];
+	u32	trcseqrstevr;
+	u32	trcseqstr;
+	u32	trcextinselr;
+	u32	trccntrldvr[ETMv4_MAX_CNTR];
+	u32	trccntctlr[ETMv4_MAX_CNTR];
+	u32	trccntvr[ETMv4_MAX_CNTR];
+
+	u32	trcrsctlr[ETM_MAX_RES_SEL * 2];
+
+	u32	trcssccr[ETM_MAX_SS_CMP];
+	u32	trcsscsr[ETM_MAX_SS_CMP];
+	u32	trcsspcicr[ETM_MAX_SS_CMP];
+
+	u64	trcacvr[ETM_MAX_SINGLE_ADDR_CMP];
+	u64	trcacatr[ETM_MAX_SINGLE_ADDR_CMP];
+	u64	trccidcvr[ETMv4_MAX_CTXID_CMP];
+	u32	trcvmidcvr[ETM_MAX_VMID_CMP];
+	u32	trccidcctlr0;
+	u32	trccidcctlr1;
+	u32	trcvmidcctlr0;
+	u32	trcvmidcctlr1;
+
+	u32	trcclaimset;
+
+	u32	cntr_val[ETMv4_MAX_CNTR];
+	u32	seq_state;
+	u32	vinst_ctrl;
+	u32	ss_status[ETM_MAX_SS_CMP];
+
+	u32	trcpdcr;
 };
 
 /**
@@ -336,6 +405,8 @@ struct etmv4_config {
  * @atbtrig:	If the implementation can support ATB triggers
  * @lpoverride:	If the implementation can support low-power state over.
  * @config:	structure holding configuration parameters.
+ * @save_state:	State to be preserved across power loss
+ * @state_needs_restore: True when there is context to restore after PM exit
  */
 struct etmv4_drvdata {
 	void __iomem			*base;
@@ -381,6 +452,8 @@ struct etmv4_drvdata {
 	bool				atbtrig;
 	bool				lpoverride;
 	struct etmv4_config		config;
+	struct etmv4_save_state		*save_state;
+	bool				state_needs_restore;
 };
 
 /* Address comparator access types */
diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c
index 05f7896c3a01..900690a9f7f0 100644
--- a/drivers/hwtracing/coresight/coresight-funnel.c
+++ b/drivers/hwtracing/coresight/coresight-funnel.c
@@ -38,12 +38,14 @@ DEFINE_CORESIGHT_DEVLIST(funnel_devs, "funnel");
  * @atclk:	optional clock for the core parts of the funnel.
  * @csdev:	component vitals needed by the framework.
  * @priority:	port selection order.
+ * @spinlock:	serialize enable/disable operations.
  */
 struct funnel_drvdata {
 	void __iomem		*base;
 	struct clk		*atclk;
 	struct coresight_device	*csdev;
 	unsigned long		priority;
+	spinlock_t		spinlock;
 };
 
 static int dynamic_funnel_enable_hw(struct funnel_drvdata *drvdata, int port)
@@ -76,11 +78,21 @@ static int funnel_enable(struct coresight_device *csdev, int inport,
 {
 	int rc = 0;
 	struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
-
-	if (drvdata->base)
-		rc = dynamic_funnel_enable_hw(drvdata, inport);
-
+	unsigned long flags;
+	bool first_enable = false;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (atomic_read(&csdev->refcnt[inport]) == 0) {
+		if (drvdata->base)
+			rc = dynamic_funnel_enable_hw(drvdata, inport);
+		if (!rc)
+			first_enable = true;
+	}
 	if (!rc)
+		atomic_inc(&csdev->refcnt[inport]);
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	if (first_enable)
 		dev_dbg(&csdev->dev, "FUNNEL inport %d enabled\n", inport);
 	return rc;
 }
@@ -107,11 +119,19 @@ static void funnel_disable(struct coresight_device *csdev, int inport,
 			   int outport)
 {
 	struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	unsigned long flags;
+	bool last_disable = false;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (atomic_dec_return(&csdev->refcnt[inport]) == 0) {
+		if (drvdata->base)
+			dynamic_funnel_disable_hw(drvdata, inport);
+		last_disable = true;
+	}
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
-	if (drvdata->base)
-		dynamic_funnel_disable_hw(drvdata, inport);
-
-	dev_dbg(&csdev->dev, "FUNNEL inport %d disabled\n", inport);
+	if (last_disable)
+		dev_dbg(&csdev->dev, "FUNNEL inport %d disabled\n", inport);
 }
 
 static const struct coresight_ops_link funnel_link_ops = {
@@ -233,6 +253,7 @@ static int funnel_probe(struct device *dev, struct resource *res)
 	}
 	dev->platform_data = pdata;
 
+	spin_lock_init(&drvdata->spinlock);
 	desc.type = CORESIGHT_DEV_TYPE_LINK;
 	desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_MERG;
 	desc.ops = &funnel_cs_ops;
diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c
index b29ba640eb25..e7dc1c31d20d 100644
--- a/drivers/hwtracing/coresight/coresight-replicator.c
+++ b/drivers/hwtracing/coresight/coresight-replicator.c
@@ -31,11 +31,13 @@ DEFINE_CORESIGHT_DEVLIST(replicator_devs, "replicator");
  *		whether this one is programmable or not.
  * @atclk:	optional clock for the core parts of the replicator.
  * @csdev:	component vitals needed by the framework
+ * @spinlock:	serialize enable/disable operations.
  */
 struct replicator_drvdata {
 	void __iomem		*base;
 	struct clk		*atclk;
 	struct coresight_device	*csdev;
+	spinlock_t		spinlock;
 };
 
 static void dynamic_replicator_reset(struct replicator_drvdata *drvdata)
@@ -97,10 +99,22 @@ static int replicator_enable(struct coresight_device *csdev, int inport,
 {
 	int rc = 0;
 	struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
-
-	if (drvdata->base)
-		rc = dynamic_replicator_enable(drvdata, inport, outport);
+	unsigned long flags;
+	bool first_enable = false;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (atomic_read(&csdev->refcnt[outport]) == 0) {
+		if (drvdata->base)
+			rc = dynamic_replicator_enable(drvdata, inport,
+						       outport);
+		if (!rc)
+			first_enable = true;
+	}
 	if (!rc)
+		atomic_inc(&csdev->refcnt[outport]);
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	if (first_enable)
 		dev_dbg(&csdev->dev, "REPLICATOR enabled\n");
 	return rc;
 }
@@ -137,10 +151,19 @@ static void replicator_disable(struct coresight_device *csdev, int inport,
 			       int outport)
 {
 	struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	unsigned long flags;
+	bool last_disable = false;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (atomic_dec_return(&csdev->refcnt[outport]) == 0) {
+		if (drvdata->base)
+			dynamic_replicator_disable(drvdata, inport, outport);
+		last_disable = true;
+	}
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
-	if (drvdata->base)
-		dynamic_replicator_disable(drvdata, inport, outport);
-	dev_dbg(&csdev->dev, "REPLICATOR disabled\n");
+	if (last_disable)
+		dev_dbg(&csdev->dev, "REPLICATOR disabled\n");
 }
 
 static const struct coresight_ops_link replicator_link_ops = {
@@ -225,6 +248,7 @@ static int replicator_probe(struct device *dev, struct resource *res)
 	}
 	dev->platform_data = pdata;
 
+	spin_lock_init(&drvdata->spinlock);
 	desc.type = CORESIGHT_DEV_TYPE_LINK;
 	desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_SPLIT;
 	desc.ops = &replicator_cs_ops;
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c
index 807416b75ecc..d0cc3985b72a 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etf.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c
@@ -334,9 +334,10 @@ static int tmc_disable_etf_sink(struct coresight_device *csdev)
 static int tmc_enable_etf_link(struct coresight_device *csdev,
 			       int inport, int outport)
 {
-	int ret;
+	int ret = 0;
 	unsigned long flags;
 	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	bool first_enable = false;
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
 	if (drvdata->reading) {
@@ -344,12 +345,18 @@ static int tmc_enable_etf_link(struct coresight_device *csdev,
 		return -EBUSY;
 	}
 
-	ret = tmc_etf_enable_hw(drvdata);
+	if (atomic_read(&csdev->refcnt[0]) == 0) {
+		ret = tmc_etf_enable_hw(drvdata);
+		if (!ret) {
+			drvdata->mode = CS_MODE_SYSFS;
+			first_enable = true;
+		}
+	}
 	if (!ret)
-		drvdata->mode = CS_MODE_SYSFS;
+		atomic_inc(&csdev->refcnt[0]);
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
-	if (!ret)
+	if (first_enable)
 		dev_dbg(&csdev->dev, "TMC-ETF enabled\n");
 	return ret;
 }
@@ -359,6 +366,7 @@ static void tmc_disable_etf_link(struct coresight_device *csdev,
 {
 	unsigned long flags;
 	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	bool last_disable = false;
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
 	if (drvdata->reading) {
@@ -366,11 +374,15 @@ static void tmc_disable_etf_link(struct coresight_device *csdev,
 		return;
 	}
 
-	tmc_etf_disable_hw(drvdata);
-	drvdata->mode = CS_MODE_DISABLED;
+	if (atomic_dec_return(&csdev->refcnt[0]) == 0) {
+		tmc_etf_disable_hw(drvdata);
+		drvdata->mode = CS_MODE_DISABLED;
+		last_disable = true;
+	}
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
-	dev_dbg(&csdev->dev, "TMC-ETF disabled\n");
+	if (last_disable)
+		dev_dbg(&csdev->dev, "TMC-ETF disabled\n");
 }
 
 static void *tmc_alloc_etf_buffer(struct coresight_device *csdev,
diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c
index 6453c67a4d01..ef20f74c85fa 100644
--- a/drivers/hwtracing/coresight/coresight.c
+++ b/drivers/hwtracing/coresight/coresight.c
@@ -253,9 +253,9 @@ static int coresight_enable_link(struct coresight_device *csdev,
 				 struct coresight_device *parent,
 				 struct coresight_device *child)
 {
-	int ret;
+	int ret = 0;
 	int link_subtype;
-	int refport, inport, outport;
+	int inport, outport;
 
 	if (!parent || !child)
 		return -EINVAL;
@@ -264,29 +264,17 @@ static int coresight_enable_link(struct coresight_device *csdev,
 	outport = coresight_find_link_outport(csdev, child);
 	link_subtype = csdev->subtype.link_subtype;
 
-	if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG)
-		refport = inport;
-	else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT)
-		refport = outport;
-	else
-		refport = 0;
-
-	if (refport < 0)
-		return refport;
-
-	if (atomic_inc_return(&csdev->refcnt[refport]) == 1) {
-		if (link_ops(csdev)->enable) {
-			ret = link_ops(csdev)->enable(csdev, inport, outport);
-			if (ret) {
-				atomic_dec(&csdev->refcnt[refport]);
-				return ret;
-			}
-		}
-	}
+	if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG && inport < 0)
+		return inport;
+	if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT && outport < 0)
+		return outport;
 
-	csdev->enable = true;
+	if (link_ops(csdev)->enable)
+		ret = link_ops(csdev)->enable(csdev, inport, outport);
+	if (!ret)
+		csdev->enable = true;
 
-	return 0;
+	return ret;
 }
 
 static void coresight_disable_link(struct coresight_device *csdev,
@@ -295,7 +283,7 @@ static void coresight_disable_link(struct coresight_device *csdev,
 {
 	int i, nr_conns;
 	int link_subtype;
-	int refport, inport, outport;
+	int inport, outport;
 
 	if (!parent || !child)
 		return;
@@ -305,20 +293,15 @@ static void coresight_disable_link(struct coresight_device *csdev,
 	link_subtype = csdev->subtype.link_subtype;
 
 	if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG) {
-		refport = inport;
 		nr_conns = csdev->pdata->nr_inport;
 	} else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT) {
-		refport = outport;
 		nr_conns = csdev->pdata->nr_outport;
 	} else {
-		refport = 0;
 		nr_conns = 1;
 	}
 
-	if (atomic_dec_return(&csdev->refcnt[refport]) == 0) {
-		if (link_ops(csdev)->disable)
-			link_ops(csdev)->disable(csdev, inport, outport);
-	}
+	if (link_ops(csdev)->disable)
+		link_ops(csdev)->disable(csdev, inport, outport);
 
 	for (i = 0; i < nr_conns; i++)
 		if (atomic_read(&csdev->refcnt[i]) != 0)
@@ -1308,6 +1291,12 @@ static inline int coresight_search_device_idx(struct coresight_dev_list *dict,
 	return -ENOENT;
 }
 
+bool coresight_loses_context_with_cpu(struct device *dev)
+{
+	return fwnode_property_present(dev_fwnode(dev),
+				       "arm,coresight-loses-context-with-cpu");
+}
+
 /*
  * coresight_alloc_device_name - Get an index for a given device in the
  * device index list specific to a driver. An index is allocated for a
diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c
index d5c1821b31c6..0dfd97bbde9e 100644
--- a/drivers/hwtracing/intel_th/core.c
+++ b/drivers/hwtracing/intel_th/core.c
@@ -649,10 +649,8 @@ intel_th_subdevice_alloc(struct intel_th *th,
 	}
 
 	err = intel_th_device_add_resources(thdev, res, subdev->nres);
-	if (err) {
-		put_device(&thdev->dev);
+	if (err)
 		goto fail_put_device;
-	}
 
 	if (subdev->type == INTEL_TH_OUTPUT) {
 		if (subdev->mknode)
@@ -667,10 +665,8 @@ intel_th_subdevice_alloc(struct intel_th *th,
 	}
 
 	err = device_add(&thdev->dev);
-	if (err) {
-		put_device(&thdev->dev);
+	if (err)
 		goto fail_free_res;
-	}
 
 	/* need switch driver to be loaded to enumerate the rest */
 	if (subdev->type == INTEL_TH_SWITCH && !req) {
diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index 03ca5b1bef9f..ebf3e30e989a 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -210,6 +210,16 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
 	{
+		/* Ice Lake CPU */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x8a29),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
+	{
+		/* Tiger Lake CPU */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x9a33),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
+	{
 		/* Tiger Lake PCH */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa0a6),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
diff --git a/drivers/hwtracing/stm/policy.c b/drivers/hwtracing/stm/policy.c
index 4b9e44b227d8..4f932a419752 100644
--- a/drivers/hwtracing/stm/policy.c
+++ b/drivers/hwtracing/stm/policy.c
@@ -345,7 +345,11 @@ void stp_policy_unbind(struct stp_policy *policy)
 	stm->policy = NULL;
 	policy->stm = NULL;
 
+	/*
+	 * Drop the reference on the protocol driver and lose the link.
+	 */
 	stm_put_protocol(stm->pdrv);
+	stm->pdrv = NULL;
 	stm_put_device(stm);
 }
 
diff --git a/drivers/iio/adc/men_z188_adc.c b/drivers/iio/adc/men_z188_adc.c
index 3b2fbb7ce431..196c8226381e 100644
--- a/drivers/iio/adc/men_z188_adc.c
+++ b/drivers/iio/adc/men_z188_adc.c
@@ -167,3 +167,4 @@ MODULE_AUTHOR("Johannes Thumshirn <johannes.thumshirn@men.de>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("IIO ADC driver for MEN 16z188 ADC Core");
 MODULE_ALIAS("mcb:16z188");
+MODULE_IMPORT_NS(MCB);
diff --git a/drivers/interconnect/qcom/Kconfig b/drivers/interconnect/qcom/Kconfig
index 6ab4012a059a..c49afbea3458 100644
--- a/drivers/interconnect/qcom/Kconfig
+++ b/drivers/interconnect/qcom/Kconfig
@@ -5,6 +5,15 @@ config INTERCONNECT_QCOM
 	help
 	  Support for Qualcomm's Network-on-Chip interconnect hardware.
 
+config INTERCONNECT_QCOM_MSM8974
+       tristate "Qualcomm MSM8974 interconnect driver"
+       depends on INTERCONNECT_QCOM
+       depends on QCOM_SMD_RPM
+       select INTERCONNECT_QCOM_SMD_RPM
+       help
+         This is a driver for the Qualcomm Network-on-Chip on msm8974-based
+         platforms.
+
 config INTERCONNECT_QCOM_QCS404
 	tristate "Qualcomm QCS404 interconnect driver"
 	depends on INTERCONNECT_QCOM
diff --git a/drivers/interconnect/qcom/Makefile b/drivers/interconnect/qcom/Makefile
index 67dafb783dec..9adf9e380545 100644
--- a/drivers/interconnect/qcom/Makefile
+++ b/drivers/interconnect/qcom/Makefile
@@ -1,9 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0
 
+qnoc-msm8974-objs			:= msm8974.o
 qnoc-qcs404-objs			:= qcs404.o
 qnoc-sdm845-objs			:= sdm845.o
 icc-smd-rpm-objs			:= smd-rpm.o
 
+obj-$(CONFIG_INTERCONNECT_QCOM_MSM8974) += qnoc-msm8974.o
 obj-$(CONFIG_INTERCONNECT_QCOM_QCS404) += qnoc-qcs404.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SDM845) += qnoc-sdm845.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SMD_RPM) += icc-smd-rpm.o
diff --git a/drivers/interconnect/qcom/msm8974.c b/drivers/interconnect/qcom/msm8974.c
new file mode 100644
index 000000000000..ce599a0c83d9
--- /dev/null
+++ b/drivers/interconnect/qcom/msm8974.c
@@ -0,0 +1,784 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Brian Masney <masneyb@onstation.org>
+ *
+ * Based on MSM bus code from downstream MSM kernel sources.
+ * Copyright (c) 2012-2013 The Linux Foundation. All rights reserved.
+ *
+ * Based on qcs404.c
+ * Copyright (C) 2019 Linaro Ltd
+ *
+ * Here's a rough representation that shows the various buses that form the
+ * Network On Chip (NOC) for the msm8974:
+ *
+ *                         Multimedia Subsystem (MMSS)
+ *         |----------+-----------------------------------+-----------|
+ *                    |                                   |
+ *                    |                                   |
+ *        Config      |                     Bus Interface | Memory Controller
+ *       |------------+-+-----------|        |------------+-+-----------|
+ *                      |                                   |
+ *                      |                                   |
+ *                      |             System                |
+ *     |--------------+-+---------------------------------+-+-------------|
+ *                    |                                   |
+ *                    |                                   |
+ *        Peripheral  |                           On Chip | Memory (OCMEM)
+ *       |------------+-------------|        |------------+-------------|
+ */
+
+#include <dt-bindings/interconnect/qcom,msm8974.h>
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/interconnect-provider.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "smd-rpm.h"
+
+enum {
+	MSM8974_BIMC_MAS_AMPSS_M0 = 1,
+	MSM8974_BIMC_MAS_AMPSS_M1,
+	MSM8974_BIMC_MAS_MSS_PROC,
+	MSM8974_BIMC_TO_MNOC,
+	MSM8974_BIMC_TO_SNOC,
+	MSM8974_BIMC_SLV_EBI_CH0,
+	MSM8974_BIMC_SLV_AMPSS_L2,
+	MSM8974_CNOC_MAS_RPM_INST,
+	MSM8974_CNOC_MAS_RPM_DATA,
+	MSM8974_CNOC_MAS_RPM_SYS,
+	MSM8974_CNOC_MAS_DEHR,
+	MSM8974_CNOC_MAS_QDSS_DAP,
+	MSM8974_CNOC_MAS_SPDM,
+	MSM8974_CNOC_MAS_TIC,
+	MSM8974_CNOC_SLV_CLK_CTL,
+	MSM8974_CNOC_SLV_CNOC_MSS,
+	MSM8974_CNOC_SLV_SECURITY,
+	MSM8974_CNOC_SLV_TCSR,
+	MSM8974_CNOC_SLV_TLMM,
+	MSM8974_CNOC_SLV_CRYPTO_0_CFG,
+	MSM8974_CNOC_SLV_CRYPTO_1_CFG,
+	MSM8974_CNOC_SLV_IMEM_CFG,
+	MSM8974_CNOC_SLV_MESSAGE_RAM,
+	MSM8974_CNOC_SLV_BIMC_CFG,
+	MSM8974_CNOC_SLV_BOOT_ROM,
+	MSM8974_CNOC_SLV_PMIC_ARB,
+	MSM8974_CNOC_SLV_SPDM_WRAPPER,
+	MSM8974_CNOC_SLV_DEHR_CFG,
+	MSM8974_CNOC_SLV_MPM,
+	MSM8974_CNOC_SLV_QDSS_CFG,
+	MSM8974_CNOC_SLV_RBCPR_CFG,
+	MSM8974_CNOC_SLV_RBCPR_QDSS_APU_CFG,
+	MSM8974_CNOC_TO_SNOC,
+	MSM8974_CNOC_SLV_CNOC_ONOC_CFG,
+	MSM8974_CNOC_SLV_CNOC_MNOC_MMSS_CFG,
+	MSM8974_CNOC_SLV_CNOC_MNOC_CFG,
+	MSM8974_CNOC_SLV_PNOC_CFG,
+	MSM8974_CNOC_SLV_SNOC_MPU_CFG,
+	MSM8974_CNOC_SLV_SNOC_CFG,
+	MSM8974_CNOC_SLV_EBI1_DLL_CFG,
+	MSM8974_CNOC_SLV_PHY_APU_CFG,
+	MSM8974_CNOC_SLV_EBI1_PHY_CFG,
+	MSM8974_CNOC_SLV_RPM,
+	MSM8974_CNOC_SLV_SERVICE_CNOC,
+	MSM8974_MNOC_MAS_GRAPHICS_3D,
+	MSM8974_MNOC_MAS_JPEG,
+	MSM8974_MNOC_MAS_MDP_PORT0,
+	MSM8974_MNOC_MAS_VIDEO_P0,
+	MSM8974_MNOC_MAS_VIDEO_P1,
+	MSM8974_MNOC_MAS_VFE,
+	MSM8974_MNOC_TO_CNOC,
+	MSM8974_MNOC_TO_BIMC,
+	MSM8974_MNOC_SLV_CAMERA_CFG,
+	MSM8974_MNOC_SLV_DISPLAY_CFG,
+	MSM8974_MNOC_SLV_OCMEM_CFG,
+	MSM8974_MNOC_SLV_CPR_CFG,
+	MSM8974_MNOC_SLV_CPR_XPU_CFG,
+	MSM8974_MNOC_SLV_MISC_CFG,
+	MSM8974_MNOC_SLV_MISC_XPU_CFG,
+	MSM8974_MNOC_SLV_VENUS_CFG,
+	MSM8974_MNOC_SLV_GRAPHICS_3D_CFG,
+	MSM8974_MNOC_SLV_MMSS_CLK_CFG,
+	MSM8974_MNOC_SLV_MMSS_CLK_XPU_CFG,
+	MSM8974_MNOC_SLV_MNOC_MPU_CFG,
+	MSM8974_MNOC_SLV_ONOC_MPU_CFG,
+	MSM8974_MNOC_SLV_SERVICE_MNOC,
+	MSM8974_OCMEM_NOC_TO_OCMEM_VNOC,
+	MSM8974_OCMEM_MAS_JPEG_OCMEM,
+	MSM8974_OCMEM_MAS_MDP_OCMEM,
+	MSM8974_OCMEM_MAS_VIDEO_P0_OCMEM,
+	MSM8974_OCMEM_MAS_VIDEO_P1_OCMEM,
+	MSM8974_OCMEM_MAS_VFE_OCMEM,
+	MSM8974_OCMEM_MAS_CNOC_ONOC_CFG,
+	MSM8974_OCMEM_SLV_SERVICE_ONOC,
+	MSM8974_OCMEM_VNOC_TO_SNOC,
+	MSM8974_OCMEM_VNOC_TO_OCMEM_NOC,
+	MSM8974_OCMEM_VNOC_MAS_GFX3D,
+	MSM8974_OCMEM_SLV_OCMEM,
+	MSM8974_PNOC_MAS_PNOC_CFG,
+	MSM8974_PNOC_MAS_SDCC_1,
+	MSM8974_PNOC_MAS_SDCC_3,
+	MSM8974_PNOC_MAS_SDCC_4,
+	MSM8974_PNOC_MAS_SDCC_2,
+	MSM8974_PNOC_MAS_TSIF,
+	MSM8974_PNOC_MAS_BAM_DMA,
+	MSM8974_PNOC_MAS_BLSP_2,
+	MSM8974_PNOC_MAS_USB_HSIC,
+	MSM8974_PNOC_MAS_BLSP_1,
+	MSM8974_PNOC_MAS_USB_HS,
+	MSM8974_PNOC_TO_SNOC,
+	MSM8974_PNOC_SLV_SDCC_1,
+	MSM8974_PNOC_SLV_SDCC_3,
+	MSM8974_PNOC_SLV_SDCC_2,
+	MSM8974_PNOC_SLV_SDCC_4,
+	MSM8974_PNOC_SLV_TSIF,
+	MSM8974_PNOC_SLV_BAM_DMA,
+	MSM8974_PNOC_SLV_BLSP_2,
+	MSM8974_PNOC_SLV_USB_HSIC,
+	MSM8974_PNOC_SLV_BLSP_1,
+	MSM8974_PNOC_SLV_USB_HS,
+	MSM8974_PNOC_SLV_PDM,
+	MSM8974_PNOC_SLV_PERIPH_APU_CFG,
+	MSM8974_PNOC_SLV_PNOC_MPU_CFG,
+	MSM8974_PNOC_SLV_PRNG,
+	MSM8974_PNOC_SLV_SERVICE_PNOC,
+	MSM8974_SNOC_MAS_LPASS_AHB,
+	MSM8974_SNOC_MAS_QDSS_BAM,
+	MSM8974_SNOC_MAS_SNOC_CFG,
+	MSM8974_SNOC_TO_BIMC,
+	MSM8974_SNOC_TO_CNOC,
+	MSM8974_SNOC_TO_PNOC,
+	MSM8974_SNOC_TO_OCMEM_VNOC,
+	MSM8974_SNOC_MAS_CRYPTO_CORE0,
+	MSM8974_SNOC_MAS_CRYPTO_CORE1,
+	MSM8974_SNOC_MAS_LPASS_PROC,
+	MSM8974_SNOC_MAS_MSS,
+	MSM8974_SNOC_MAS_MSS_NAV,
+	MSM8974_SNOC_MAS_OCMEM_DMA,
+	MSM8974_SNOC_MAS_WCSS,
+	MSM8974_SNOC_MAS_QDSS_ETR,
+	MSM8974_SNOC_MAS_USB3,
+	MSM8974_SNOC_SLV_AMPSS,
+	MSM8974_SNOC_SLV_LPASS,
+	MSM8974_SNOC_SLV_USB3,
+	MSM8974_SNOC_SLV_WCSS,
+	MSM8974_SNOC_SLV_OCIMEM,
+	MSM8974_SNOC_SLV_SNOC_OCMEM,
+	MSM8974_SNOC_SLV_SERVICE_SNOC,
+	MSM8974_SNOC_SLV_QDSS_STM,
+};
+
+#define RPM_BUS_MASTER_REQ	0x73616d62
+#define RPM_BUS_SLAVE_REQ	0x766c7362
+
+#define to_msm8974_icc_provider(_provider) \
+	container_of(_provider, struct msm8974_icc_provider, provider)
+
+static const struct clk_bulk_data msm8974_icc_bus_clocks[] = {
+	{ .id = "bus" },
+	{ .id = "bus_a" },
+};
+
+/**
+ * struct msm8974_icc_provider - Qualcomm specific interconnect provider
+ * @provider: generic interconnect provider
+ * @bus_clks: the clk_bulk_data table of bus clocks
+ * @num_clks: the total number of clk_bulk_data entries
+ */
+struct msm8974_icc_provider {
+	struct icc_provider provider;
+	struct clk_bulk_data *bus_clks;
+	int num_clks;
+};
+
+#define MSM8974_ICC_MAX_LINKS	3
+
+/**
+ * struct msm8974_icc_node - Qualcomm specific interconnect nodes
+ * @name: the node name used in debugfs
+ * @id: a unique node identifier
+ * @links: an array of nodes where we can go next while traversing
+ * @num_links: the total number of @links
+ * @buswidth: width of the interconnect between a node and the bus (bytes)
+ * @mas_rpm_id:	RPM ID for devices that are bus masters
+ * @slv_rpm_id:	RPM ID for devices that are bus slaves
+ * @rate: current bus clock rate in Hz
+ */
+struct msm8974_icc_node {
+	unsigned char *name;
+	u16 id;
+	u16 links[MSM8974_ICC_MAX_LINKS];
+	u16 num_links;
+	u16 buswidth;
+	int mas_rpm_id;
+	int slv_rpm_id;
+	u64 rate;
+};
+
+struct msm8974_icc_desc {
+	struct msm8974_icc_node **nodes;
+	size_t num_nodes;
+};
+
+#define DEFINE_QNODE(_name, _id, _buswidth, _mas_rpm_id, _slv_rpm_id,	\
+		     ...)						\
+		static struct msm8974_icc_node _name = {		\
+		.name = #_name,						\
+		.id = _id,						\
+		.buswidth = _buswidth,					\
+		.mas_rpm_id = _mas_rpm_id,				\
+		.slv_rpm_id = _slv_rpm_id,				\
+		.num_links = ARRAY_SIZE(((int[]){ __VA_ARGS__ })),	\
+		.links = { __VA_ARGS__ },				\
+	}
+
+DEFINE_QNODE(mas_ampss_m0, MSM8974_BIMC_MAS_AMPSS_M0, 8, 0, -1);
+DEFINE_QNODE(mas_ampss_m1, MSM8974_BIMC_MAS_AMPSS_M1, 8, 0, -1);
+DEFINE_QNODE(mas_mss_proc, MSM8974_BIMC_MAS_MSS_PROC, 8, 1, -1);
+DEFINE_QNODE(bimc_to_mnoc, MSM8974_BIMC_TO_MNOC, 8, 2, -1, MSM8974_BIMC_SLV_EBI_CH0);
+DEFINE_QNODE(bimc_to_snoc, MSM8974_BIMC_TO_SNOC, 8, 3, 2, MSM8974_SNOC_TO_BIMC, MSM8974_BIMC_SLV_EBI_CH0, MSM8974_BIMC_MAS_AMPSS_M0);
+DEFINE_QNODE(slv_ebi_ch0, MSM8974_BIMC_SLV_EBI_CH0, 8, -1, 0);
+DEFINE_QNODE(slv_ampss_l2, MSM8974_BIMC_SLV_AMPSS_L2, 8, -1, 1);
+
+static struct msm8974_icc_node *msm8974_bimc_nodes[] = {
+	[BIMC_MAS_AMPSS_M0] = &mas_ampss_m0,
+	[BIMC_MAS_AMPSS_M1] = &mas_ampss_m1,
+	[BIMC_MAS_MSS_PROC] = &mas_mss_proc,
+	[BIMC_TO_MNOC] = &bimc_to_mnoc,
+	[BIMC_TO_SNOC] = &bimc_to_snoc,
+	[BIMC_SLV_EBI_CH0] = &slv_ebi_ch0,
+	[BIMC_SLV_AMPSS_L2] = &slv_ampss_l2,
+};
+
+static struct msm8974_icc_desc msm8974_bimc = {
+	.nodes = msm8974_bimc_nodes,
+	.num_nodes = ARRAY_SIZE(msm8974_bimc_nodes),
+};
+
+DEFINE_QNODE(mas_rpm_inst, MSM8974_CNOC_MAS_RPM_INST, 8, 45, -1);
+DEFINE_QNODE(mas_rpm_data, MSM8974_CNOC_MAS_RPM_DATA, 8, 46, -1);
+DEFINE_QNODE(mas_rpm_sys, MSM8974_CNOC_MAS_RPM_SYS, 8, 47, -1);
+DEFINE_QNODE(mas_dehr, MSM8974_CNOC_MAS_DEHR, 8, 48, -1);
+DEFINE_QNODE(mas_qdss_dap, MSM8974_CNOC_MAS_QDSS_DAP, 8, 49, -1);
+DEFINE_QNODE(mas_spdm, MSM8974_CNOC_MAS_SPDM, 8, 50, -1);
+DEFINE_QNODE(mas_tic, MSM8974_CNOC_MAS_TIC, 8, 51, -1);
+DEFINE_QNODE(slv_clk_ctl, MSM8974_CNOC_SLV_CLK_CTL, 8, -1, 47);
+DEFINE_QNODE(slv_cnoc_mss, MSM8974_CNOC_SLV_CNOC_MSS, 8, -1, 48);
+DEFINE_QNODE(slv_security, MSM8974_CNOC_SLV_SECURITY, 8, -1, 49);
+DEFINE_QNODE(slv_tcsr, MSM8974_CNOC_SLV_TCSR, 8, -1, 50);
+DEFINE_QNODE(slv_tlmm, MSM8974_CNOC_SLV_TLMM, 8, -1, 51);
+DEFINE_QNODE(slv_crypto_0_cfg, MSM8974_CNOC_SLV_CRYPTO_0_CFG, 8, -1, 52);
+DEFINE_QNODE(slv_crypto_1_cfg, MSM8974_CNOC_SLV_CRYPTO_1_CFG, 8, -1, 53);
+DEFINE_QNODE(slv_imem_cfg, MSM8974_CNOC_SLV_IMEM_CFG, 8, -1, 54);
+DEFINE_QNODE(slv_message_ram, MSM8974_CNOC_SLV_MESSAGE_RAM, 8, -1, 55);
+DEFINE_QNODE(slv_bimc_cfg, MSM8974_CNOC_SLV_BIMC_CFG, 8, -1, 56);
+DEFINE_QNODE(slv_boot_rom, MSM8974_CNOC_SLV_BOOT_ROM, 8, -1, 57);
+DEFINE_QNODE(slv_pmic_arb, MSM8974_CNOC_SLV_PMIC_ARB, 8, -1, 59);
+DEFINE_QNODE(slv_spdm_wrapper, MSM8974_CNOC_SLV_SPDM_WRAPPER, 8, -1, 60);
+DEFINE_QNODE(slv_dehr_cfg, MSM8974_CNOC_SLV_DEHR_CFG, 8, -1, 61);
+DEFINE_QNODE(slv_mpm, MSM8974_CNOC_SLV_MPM, 8, -1, 62);
+DEFINE_QNODE(slv_qdss_cfg, MSM8974_CNOC_SLV_QDSS_CFG, 8, -1, 63);
+DEFINE_QNODE(slv_rbcpr_cfg, MSM8974_CNOC_SLV_RBCPR_CFG, 8, -1, 64);
+DEFINE_QNODE(slv_rbcpr_qdss_apu_cfg, MSM8974_CNOC_SLV_RBCPR_QDSS_APU_CFG, 8, -1, 65);
+DEFINE_QNODE(cnoc_to_snoc, MSM8974_CNOC_TO_SNOC, 8, 52, 75);
+DEFINE_QNODE(slv_cnoc_onoc_cfg, MSM8974_CNOC_SLV_CNOC_ONOC_CFG, 8, -1, 68);
+DEFINE_QNODE(slv_cnoc_mnoc_mmss_cfg, MSM8974_CNOC_SLV_CNOC_MNOC_MMSS_CFG, 8, -1, 58);
+DEFINE_QNODE(slv_cnoc_mnoc_cfg, MSM8974_CNOC_SLV_CNOC_MNOC_CFG, 8, -1, 66);
+DEFINE_QNODE(slv_pnoc_cfg, MSM8974_CNOC_SLV_PNOC_CFG, 8, -1, 69);
+DEFINE_QNODE(slv_snoc_mpu_cfg, MSM8974_CNOC_SLV_SNOC_MPU_CFG, 8, -1, 67);
+DEFINE_QNODE(slv_snoc_cfg, MSM8974_CNOC_SLV_SNOC_CFG, 8, -1, 70);
+DEFINE_QNODE(slv_ebi1_dll_cfg, MSM8974_CNOC_SLV_EBI1_DLL_CFG, 8, -1, 71);
+DEFINE_QNODE(slv_phy_apu_cfg, MSM8974_CNOC_SLV_PHY_APU_CFG, 8, -1, 72);
+DEFINE_QNODE(slv_ebi1_phy_cfg, MSM8974_CNOC_SLV_EBI1_PHY_CFG, 8, -1, 73);
+DEFINE_QNODE(slv_rpm, MSM8974_CNOC_SLV_RPM, 8, -1, 74);
+DEFINE_QNODE(slv_service_cnoc, MSM8974_CNOC_SLV_SERVICE_CNOC, 8, -1, 76);
+
+static struct msm8974_icc_node *msm8974_cnoc_nodes[] = {
+	[CNOC_MAS_RPM_INST] = &mas_rpm_inst,
+	[CNOC_MAS_RPM_DATA] = &mas_rpm_data,
+	[CNOC_MAS_RPM_SYS] = &mas_rpm_sys,
+	[CNOC_MAS_DEHR] = &mas_dehr,
+	[CNOC_MAS_QDSS_DAP] = &mas_qdss_dap,
+	[CNOC_MAS_SPDM] = &mas_spdm,
+	[CNOC_MAS_TIC] = &mas_tic,
+	[CNOC_SLV_CLK_CTL] = &slv_clk_ctl,
+	[CNOC_SLV_CNOC_MSS] = &slv_cnoc_mss,
+	[CNOC_SLV_SECURITY] = &slv_security,
+	[CNOC_SLV_TCSR] = &slv_tcsr,
+	[CNOC_SLV_TLMM] = &slv_tlmm,
+	[CNOC_SLV_CRYPTO_0_CFG] = &slv_crypto_0_cfg,
+	[CNOC_SLV_CRYPTO_1_CFG] = &slv_crypto_1_cfg,
+	[CNOC_SLV_IMEM_CFG] = &slv_imem_cfg,
+	[CNOC_SLV_MESSAGE_RAM] = &slv_message_ram,
+	[CNOC_SLV_BIMC_CFG] = &slv_bimc_cfg,
+	[CNOC_SLV_BOOT_ROM] = &slv_boot_rom,
+	[CNOC_SLV_PMIC_ARB] = &slv_pmic_arb,
+	[CNOC_SLV_SPDM_WRAPPER] = &slv_spdm_wrapper,
+	[CNOC_SLV_DEHR_CFG] = &slv_dehr_cfg,
+	[CNOC_SLV_MPM] = &slv_mpm,
+	[CNOC_SLV_QDSS_CFG] = &slv_qdss_cfg,
+	[CNOC_SLV_RBCPR_CFG] = &slv_rbcpr_cfg,
+	[CNOC_SLV_RBCPR_QDSS_APU_CFG] = &slv_rbcpr_qdss_apu_cfg,
+	[CNOC_TO_SNOC] = &cnoc_to_snoc,
+	[CNOC_SLV_CNOC_ONOC_CFG] = &slv_cnoc_onoc_cfg,
+	[CNOC_SLV_CNOC_MNOC_MMSS_CFG] = &slv_cnoc_mnoc_mmss_cfg,
+	[CNOC_SLV_CNOC_MNOC_CFG] = &slv_cnoc_mnoc_cfg,
+	[CNOC_SLV_PNOC_CFG] = &slv_pnoc_cfg,
+	[CNOC_SLV_SNOC_MPU_CFG] = &slv_snoc_mpu_cfg,
+	[CNOC_SLV_SNOC_CFG] = &slv_snoc_cfg,
+	[CNOC_SLV_EBI1_DLL_CFG] = &slv_ebi1_dll_cfg,
+	[CNOC_SLV_PHY_APU_CFG] = &slv_phy_apu_cfg,
+	[CNOC_SLV_EBI1_PHY_CFG] = &slv_ebi1_phy_cfg,
+	[CNOC_SLV_RPM] = &slv_rpm,
+	[CNOC_SLV_SERVICE_CNOC] = &slv_service_cnoc,
+};
+
+static struct msm8974_icc_desc msm8974_cnoc = {
+	.nodes = msm8974_cnoc_nodes,
+	.num_nodes = ARRAY_SIZE(msm8974_cnoc_nodes),
+};
+
+DEFINE_QNODE(mas_graphics_3d, MSM8974_MNOC_MAS_GRAPHICS_3D, 16, 6, -1, MSM8974_MNOC_TO_BIMC);
+DEFINE_QNODE(mas_jpeg, MSM8974_MNOC_MAS_JPEG, 16, 7, -1, MSM8974_MNOC_TO_BIMC);
+DEFINE_QNODE(mas_mdp_port0, MSM8974_MNOC_MAS_MDP_PORT0, 16, 8, -1, MSM8974_MNOC_TO_BIMC);
+DEFINE_QNODE(mas_video_p0, MSM8974_MNOC_MAS_VIDEO_P0, 16, 9, -1);
+DEFINE_QNODE(mas_video_p1, MSM8974_MNOC_MAS_VIDEO_P1, 16, 10, -1);
+DEFINE_QNODE(mas_vfe, MSM8974_MNOC_MAS_VFE, 16, 11, -1, MSM8974_MNOC_TO_BIMC);
+DEFINE_QNODE(mnoc_to_cnoc, MSM8974_MNOC_TO_CNOC, 16, 4, -1);
+DEFINE_QNODE(mnoc_to_bimc, MSM8974_MNOC_TO_BIMC, 16, -1, 16, MSM8974_BIMC_TO_MNOC);
+DEFINE_QNODE(slv_camera_cfg, MSM8974_MNOC_SLV_CAMERA_CFG, 16, -1, 3);
+DEFINE_QNODE(slv_display_cfg, MSM8974_MNOC_SLV_DISPLAY_CFG, 16, -1, 4);
+DEFINE_QNODE(slv_ocmem_cfg, MSM8974_MNOC_SLV_OCMEM_CFG, 16, -1, 5);
+DEFINE_QNODE(slv_cpr_cfg, MSM8974_MNOC_SLV_CPR_CFG, 16, -1, 6);
+DEFINE_QNODE(slv_cpr_xpu_cfg, MSM8974_MNOC_SLV_CPR_XPU_CFG, 16, -1, 7);
+DEFINE_QNODE(slv_misc_cfg, MSM8974_MNOC_SLV_MISC_CFG, 16, -1, 8);
+DEFINE_QNODE(slv_misc_xpu_cfg, MSM8974_MNOC_SLV_MISC_XPU_CFG, 16, -1, 9);
+DEFINE_QNODE(slv_venus_cfg, MSM8974_MNOC_SLV_VENUS_CFG, 16, -1, 10);
+DEFINE_QNODE(slv_graphics_3d_cfg, MSM8974_MNOC_SLV_GRAPHICS_3D_CFG, 16, -1, 11);
+DEFINE_QNODE(slv_mmss_clk_cfg, MSM8974_MNOC_SLV_MMSS_CLK_CFG, 16, -1, 12);
+DEFINE_QNODE(slv_mmss_clk_xpu_cfg, MSM8974_MNOC_SLV_MMSS_CLK_XPU_CFG, 16, -1, 13);
+DEFINE_QNODE(slv_mnoc_mpu_cfg, MSM8974_MNOC_SLV_MNOC_MPU_CFG, 16, -1, 14);
+DEFINE_QNODE(slv_onoc_mpu_cfg, MSM8974_MNOC_SLV_ONOC_MPU_CFG, 16, -1, 15);
+DEFINE_QNODE(slv_service_mnoc, MSM8974_MNOC_SLV_SERVICE_MNOC, 16, -1, 17);
+
+static struct msm8974_icc_node *msm8974_mnoc_nodes[] = {
+	[MNOC_MAS_GRAPHICS_3D] = &mas_graphics_3d,
+	[MNOC_MAS_JPEG] = &mas_jpeg,
+	[MNOC_MAS_MDP_PORT0] = &mas_mdp_port0,
+	[MNOC_MAS_VIDEO_P0] = &mas_video_p0,
+	[MNOC_MAS_VIDEO_P1] = &mas_video_p1,
+	[MNOC_MAS_VFE] = &mas_vfe,
+	[MNOC_TO_CNOC] = &mnoc_to_cnoc,
+	[MNOC_TO_BIMC] = &mnoc_to_bimc,
+	[MNOC_SLV_CAMERA_CFG] = &slv_camera_cfg,
+	[MNOC_SLV_DISPLAY_CFG] = &slv_display_cfg,
+	[MNOC_SLV_OCMEM_CFG] = &slv_ocmem_cfg,
+	[MNOC_SLV_CPR_CFG] = &slv_cpr_cfg,
+	[MNOC_SLV_CPR_XPU_CFG] = &slv_cpr_xpu_cfg,
+	[MNOC_SLV_MISC_CFG] = &slv_misc_cfg,
+	[MNOC_SLV_MISC_XPU_CFG] = &slv_misc_xpu_cfg,
+	[MNOC_SLV_VENUS_CFG] = &slv_venus_cfg,
+	[MNOC_SLV_GRAPHICS_3D_CFG] = &slv_graphics_3d_cfg,
+	[MNOC_SLV_MMSS_CLK_CFG] = &slv_mmss_clk_cfg,
+	[MNOC_SLV_MMSS_CLK_XPU_CFG] = &slv_mmss_clk_xpu_cfg,
+	[MNOC_SLV_MNOC_MPU_CFG] = &slv_mnoc_mpu_cfg,
+	[MNOC_SLV_ONOC_MPU_CFG] = &slv_onoc_mpu_cfg,
+	[MNOC_SLV_SERVICE_MNOC] = &slv_service_mnoc,
+};
+
+static struct msm8974_icc_desc msm8974_mnoc = {
+	.nodes = msm8974_mnoc_nodes,
+	.num_nodes = ARRAY_SIZE(msm8974_mnoc_nodes),
+};
+
+DEFINE_QNODE(ocmem_noc_to_ocmem_vnoc, MSM8974_OCMEM_NOC_TO_OCMEM_VNOC, 16, 54, 78, MSM8974_OCMEM_SLV_OCMEM);
+DEFINE_QNODE(mas_jpeg_ocmem, MSM8974_OCMEM_MAS_JPEG_OCMEM, 16, 13, -1);
+DEFINE_QNODE(mas_mdp_ocmem, MSM8974_OCMEM_MAS_MDP_OCMEM, 16, 14, -1);
+DEFINE_QNODE(mas_video_p0_ocmem, MSM8974_OCMEM_MAS_VIDEO_P0_OCMEM, 16, 15, -1);
+DEFINE_QNODE(mas_video_p1_ocmem, MSM8974_OCMEM_MAS_VIDEO_P1_OCMEM, 16, 16, -1);
+DEFINE_QNODE(mas_vfe_ocmem, MSM8974_OCMEM_MAS_VFE_OCMEM, 16, 17, -1);
+DEFINE_QNODE(mas_cnoc_onoc_cfg, MSM8974_OCMEM_MAS_CNOC_ONOC_CFG, 16, 12, -1);
+DEFINE_QNODE(slv_service_onoc, MSM8974_OCMEM_SLV_SERVICE_ONOC, 16, -1, 19);
+DEFINE_QNODE(slv_ocmem, MSM8974_OCMEM_SLV_OCMEM, 16, -1, 18);
+
+/* Virtual NoC is needed for connection to OCMEM */
+DEFINE_QNODE(ocmem_vnoc_to_onoc, MSM8974_OCMEM_VNOC_TO_OCMEM_NOC, 16, 56, 79, MSM8974_OCMEM_NOC_TO_OCMEM_VNOC);
+DEFINE_QNODE(ocmem_vnoc_to_snoc, MSM8974_OCMEM_VNOC_TO_SNOC, 8, 57, 80);
+DEFINE_QNODE(mas_v_ocmem_gfx3d, MSM8974_OCMEM_VNOC_MAS_GFX3D, 8, 55, -1, MSM8974_OCMEM_VNOC_TO_OCMEM_NOC);
+
+static struct msm8974_icc_node *msm8974_onoc_nodes[] = {
+	[OCMEM_NOC_TO_OCMEM_VNOC] = &ocmem_noc_to_ocmem_vnoc,
+	[OCMEM_MAS_JPEG_OCMEM] = &mas_jpeg_ocmem,
+	[OCMEM_MAS_MDP_OCMEM] = &mas_mdp_ocmem,
+	[OCMEM_MAS_VIDEO_P0_OCMEM] = &mas_video_p0_ocmem,
+	[OCMEM_MAS_VIDEO_P1_OCMEM] = &mas_video_p1_ocmem,
+	[OCMEM_MAS_VFE_OCMEM] = &mas_vfe_ocmem,
+	[OCMEM_MAS_CNOC_ONOC_CFG] = &mas_cnoc_onoc_cfg,
+	[OCMEM_SLV_SERVICE_ONOC] = &slv_service_onoc,
+	[OCMEM_VNOC_TO_SNOC] = &ocmem_vnoc_to_snoc,
+	[OCMEM_VNOC_TO_OCMEM_NOC] = &ocmem_vnoc_to_onoc,
+	[OCMEM_VNOC_MAS_GFX3D] = &mas_v_ocmem_gfx3d,
+	[OCMEM_SLV_OCMEM] = &slv_ocmem,
+};
+
+static struct msm8974_icc_desc msm8974_onoc = {
+	.nodes = msm8974_onoc_nodes,
+	.num_nodes = ARRAY_SIZE(msm8974_onoc_nodes),
+};
+
+DEFINE_QNODE(mas_pnoc_cfg, MSM8974_PNOC_MAS_PNOC_CFG, 8, 43, -1);
+DEFINE_QNODE(mas_sdcc_1, MSM8974_PNOC_MAS_SDCC_1, 8, 33, -1, MSM8974_PNOC_TO_SNOC);
+DEFINE_QNODE(mas_sdcc_3, MSM8974_PNOC_MAS_SDCC_3, 8, 34, -1, MSM8974_PNOC_TO_SNOC);
+DEFINE_QNODE(mas_sdcc_4, MSM8974_PNOC_MAS_SDCC_4, 8, 36, -1, MSM8974_PNOC_TO_SNOC);
+DEFINE_QNODE(mas_sdcc_2, MSM8974_PNOC_MAS_SDCC_2, 8, 35, -1, MSM8974_PNOC_TO_SNOC);
+DEFINE_QNODE(mas_tsif, MSM8974_PNOC_MAS_TSIF, 8, 37, -1, MSM8974_PNOC_TO_SNOC);
+DEFINE_QNODE(mas_bam_dma, MSM8974_PNOC_MAS_BAM_DMA, 8, 38, -1);
+DEFINE_QNODE(mas_blsp_2, MSM8974_PNOC_MAS_BLSP_2, 8, 39, -1, MSM8974_PNOC_TO_SNOC);
+DEFINE_QNODE(mas_usb_hsic, MSM8974_PNOC_MAS_USB_HSIC, 8, 40, -1, MSM8974_PNOC_TO_SNOC);
+DEFINE_QNODE(mas_blsp_1, MSM8974_PNOC_MAS_BLSP_1, 8, 41, -1, MSM8974_PNOC_TO_SNOC);
+DEFINE_QNODE(mas_usb_hs, MSM8974_PNOC_MAS_USB_HS, 8, 42, -1, MSM8974_PNOC_TO_SNOC);
+DEFINE_QNODE(pnoc_to_snoc, MSM8974_PNOC_TO_SNOC, 8, 44, 45, MSM8974_SNOC_TO_PNOC, MSM8974_PNOC_SLV_PRNG);
+DEFINE_QNODE(slv_sdcc_1, MSM8974_PNOC_SLV_SDCC_1, 8, -1, 31);
+DEFINE_QNODE(slv_sdcc_3, MSM8974_PNOC_SLV_SDCC_3, 8, -1, 32);
+DEFINE_QNODE(slv_sdcc_2, MSM8974_PNOC_SLV_SDCC_2, 8, -1, 33);
+DEFINE_QNODE(slv_sdcc_4, MSM8974_PNOC_SLV_SDCC_4, 8, -1, 34);
+DEFINE_QNODE(slv_tsif, MSM8974_PNOC_SLV_TSIF, 8, -1, 35);
+DEFINE_QNODE(slv_bam_dma, MSM8974_PNOC_SLV_BAM_DMA, 8, -1, 36);
+DEFINE_QNODE(slv_blsp_2, MSM8974_PNOC_SLV_BLSP_2, 8, -1, 37);
+DEFINE_QNODE(slv_usb_hsic, MSM8974_PNOC_SLV_USB_HSIC, 8, -1, 38);
+DEFINE_QNODE(slv_blsp_1, MSM8974_PNOC_SLV_BLSP_1, 8, -1, 39);
+DEFINE_QNODE(slv_usb_hs, MSM8974_PNOC_SLV_USB_HS, 8, -1, 40);
+DEFINE_QNODE(slv_pdm, MSM8974_PNOC_SLV_PDM, 8, -1, 41);
+DEFINE_QNODE(slv_periph_apu_cfg, MSM8974_PNOC_SLV_PERIPH_APU_CFG, 8, -1, 42);
+DEFINE_QNODE(slv_pnoc_mpu_cfg, MSM8974_PNOC_SLV_PNOC_MPU_CFG, 8, -1, 43);
+DEFINE_QNODE(slv_prng, MSM8974_PNOC_SLV_PRNG, 8, -1, 44, MSM8974_PNOC_TO_SNOC);
+DEFINE_QNODE(slv_service_pnoc, MSM8974_PNOC_SLV_SERVICE_PNOC, 8, -1, 46);
+
+static struct msm8974_icc_node *msm8974_pnoc_nodes[] = {
+	[PNOC_MAS_PNOC_CFG] = &mas_pnoc_cfg,
+	[PNOC_MAS_SDCC_1] = &mas_sdcc_1,
+	[PNOC_MAS_SDCC_3] = &mas_sdcc_3,
+	[PNOC_MAS_SDCC_4] = &mas_sdcc_4,
+	[PNOC_MAS_SDCC_2] = &mas_sdcc_2,
+	[PNOC_MAS_TSIF] = &mas_tsif,
+	[PNOC_MAS_BAM_DMA] = &mas_bam_dma,
+	[PNOC_MAS_BLSP_2] = &mas_blsp_2,
+	[PNOC_MAS_USB_HSIC] = &mas_usb_hsic,
+	[PNOC_MAS_BLSP_1] = &mas_blsp_1,
+	[PNOC_MAS_USB_HS] = &mas_usb_hs,
+	[PNOC_TO_SNOC] = &pnoc_to_snoc,
+	[PNOC_SLV_SDCC_1] = &slv_sdcc_1,
+	[PNOC_SLV_SDCC_3] = &slv_sdcc_3,
+	[PNOC_SLV_SDCC_2] = &slv_sdcc_2,
+	[PNOC_SLV_SDCC_4] = &slv_sdcc_4,
+	[PNOC_SLV_TSIF] = &slv_tsif,
+	[PNOC_SLV_BAM_DMA] = &slv_bam_dma,
+	[PNOC_SLV_BLSP_2] = &slv_blsp_2,
+	[PNOC_SLV_USB_HSIC] = &slv_usb_hsic,
+	[PNOC_SLV_BLSP_1] = &slv_blsp_1,
+	[PNOC_SLV_USB_HS] = &slv_usb_hs,
+	[PNOC_SLV_PDM] = &slv_pdm,
+	[PNOC_SLV_PERIPH_APU_CFG] = &slv_periph_apu_cfg,
+	[PNOC_SLV_PNOC_MPU_CFG] = &slv_pnoc_mpu_cfg,
+	[PNOC_SLV_PRNG] = &slv_prng,
+	[PNOC_SLV_SERVICE_PNOC] = &slv_service_pnoc,
+};
+
+static struct msm8974_icc_desc msm8974_pnoc = {
+	.nodes = msm8974_pnoc_nodes,
+	.num_nodes = ARRAY_SIZE(msm8974_pnoc_nodes),
+};
+
+DEFINE_QNODE(mas_lpass_ahb, MSM8974_SNOC_MAS_LPASS_AHB, 8, 18, -1);
+DEFINE_QNODE(mas_qdss_bam, MSM8974_SNOC_MAS_QDSS_BAM, 8, 19, -1);
+DEFINE_QNODE(mas_snoc_cfg, MSM8974_SNOC_MAS_SNOC_CFG, 8, 20, -1);
+DEFINE_QNODE(snoc_to_bimc, MSM8974_SNOC_TO_BIMC, 8, 21, 24, MSM8974_BIMC_TO_SNOC);
+DEFINE_QNODE(snoc_to_cnoc, MSM8974_SNOC_TO_CNOC, 8, 22, 25);
+DEFINE_QNODE(snoc_to_pnoc, MSM8974_SNOC_TO_PNOC, 8, 29, 28, MSM8974_PNOC_TO_SNOC);
+DEFINE_QNODE(snoc_to_ocmem_vnoc, MSM8974_SNOC_TO_OCMEM_VNOC, 8, 53, 77, MSM8974_OCMEM_VNOC_TO_OCMEM_NOC);
+DEFINE_QNODE(mas_crypto_core0, MSM8974_SNOC_MAS_CRYPTO_CORE0, 8, 23, -1, MSM8974_SNOC_TO_BIMC);
+DEFINE_QNODE(mas_crypto_core1, MSM8974_SNOC_MAS_CRYPTO_CORE1, 8, 24, -1);
+DEFINE_QNODE(mas_lpass_proc, MSM8974_SNOC_MAS_LPASS_PROC, 8, 25, -1, MSM8974_SNOC_TO_OCMEM_VNOC);
+DEFINE_QNODE(mas_mss, MSM8974_SNOC_MAS_MSS, 8, 26, -1);
+DEFINE_QNODE(mas_mss_nav, MSM8974_SNOC_MAS_MSS_NAV, 8, 27, -1);
+DEFINE_QNODE(mas_ocmem_dma, MSM8974_SNOC_MAS_OCMEM_DMA, 8, 28, -1);
+DEFINE_QNODE(mas_wcss, MSM8974_SNOC_MAS_WCSS, 8, 30, -1);
+DEFINE_QNODE(mas_qdss_etr, MSM8974_SNOC_MAS_QDSS_ETR, 8, 31, -1);
+DEFINE_QNODE(mas_usb3, MSM8974_SNOC_MAS_USB3, 8, 32, -1, MSM8974_SNOC_TO_BIMC);
+DEFINE_QNODE(slv_ampss, MSM8974_SNOC_SLV_AMPSS, 8, -1, 20);
+DEFINE_QNODE(slv_lpass, MSM8974_SNOC_SLV_LPASS, 8, -1, 21);
+DEFINE_QNODE(slv_usb3, MSM8974_SNOC_SLV_USB3, 8, -1, 22);
+DEFINE_QNODE(slv_wcss, MSM8974_SNOC_SLV_WCSS, 8, -1, 23);
+DEFINE_QNODE(slv_ocimem, MSM8974_SNOC_SLV_OCIMEM, 8, -1, 26);
+DEFINE_QNODE(slv_snoc_ocmem, MSM8974_SNOC_SLV_SNOC_OCMEM, 8, -1, 27);
+DEFINE_QNODE(slv_service_snoc, MSM8974_SNOC_SLV_SERVICE_SNOC, 8, -1, 29);
+DEFINE_QNODE(slv_qdss_stm, MSM8974_SNOC_SLV_QDSS_STM, 8, -1, 30);
+
+static struct msm8974_icc_node *msm8974_snoc_nodes[] = {
+	[SNOC_MAS_LPASS_AHB] = &mas_lpass_ahb,
+	[SNOC_MAS_QDSS_BAM] = &mas_qdss_bam,
+	[SNOC_MAS_SNOC_CFG] = &mas_snoc_cfg,
+	[SNOC_TO_BIMC] = &snoc_to_bimc,
+	[SNOC_TO_CNOC] = &snoc_to_cnoc,
+	[SNOC_TO_PNOC] = &snoc_to_pnoc,
+	[SNOC_TO_OCMEM_VNOC] = &snoc_to_ocmem_vnoc,
+	[SNOC_MAS_CRYPTO_CORE0] = &mas_crypto_core0,
+	[SNOC_MAS_CRYPTO_CORE1] = &mas_crypto_core1,
+	[SNOC_MAS_LPASS_PROC] = &mas_lpass_proc,
+	[SNOC_MAS_MSS] = &mas_mss,
+	[SNOC_MAS_MSS_NAV] = &mas_mss_nav,
+	[SNOC_MAS_OCMEM_DMA] = &mas_ocmem_dma,
+	[SNOC_MAS_WCSS] = &mas_wcss,
+	[SNOC_MAS_QDSS_ETR] = &mas_qdss_etr,
+	[SNOC_MAS_USB3] = &mas_usb3,
+	[SNOC_SLV_AMPSS] = &slv_ampss,
+	[SNOC_SLV_LPASS] = &slv_lpass,
+	[SNOC_SLV_USB3] = &slv_usb3,
+	[SNOC_SLV_WCSS] = &slv_wcss,
+	[SNOC_SLV_OCIMEM] = &slv_ocimem,
+	[SNOC_SLV_SNOC_OCMEM] = &slv_snoc_ocmem,
+	[SNOC_SLV_SERVICE_SNOC] = &slv_service_snoc,
+	[SNOC_SLV_QDSS_STM] = &slv_qdss_stm,
+};
+
+static struct msm8974_icc_desc msm8974_snoc = {
+	.nodes = msm8974_snoc_nodes,
+	.num_nodes = ARRAY_SIZE(msm8974_snoc_nodes),
+};
+
+static int msm8974_icc_aggregate(struct icc_node *node, u32 tag, u32 avg_bw,
+				 u32 peak_bw, u32 *agg_avg, u32 *agg_peak)
+{
+	*agg_avg += avg_bw;
+	*agg_peak = max(*agg_peak, peak_bw);
+
+	return 0;
+}
+
+static void msm8974_icc_rpm_smd_send(struct device *dev, int rsc_type,
+				     char *name, int id, u64 val)
+{
+	int ret;
+
+	if (id == -1)
+		return;
+
+	/*
+	 * Setting the bandwidth requests for some nodes fails and this same
+	 * behavior occurs on the downstream MSM 3.4 kernel sources based on
+	 * errors like this in that kernel:
+	 *
+	 *   msm_rpm_get_error_from_ack(): RPM NACK Unsupported resource
+	 *   AXI: msm_bus_rpm_req(): RPM: Ack failed
+	 *   AXI: msm_bus_rpm_commit_arb(): RPM: Req fail: mas:32, bw:240000000
+	 *
+	 * Since there's no publicly available documentation for this hardware,
+	 * and the bandwidth for some nodes in the path can be set properly,
+	 * let's not return an error.
+	 */
+	ret = qcom_icc_rpm_smd_send(QCOM_SMD_RPM_ACTIVE_STATE, rsc_type, id,
+				    val);
+	if (ret)
+		dev_dbg(dev, "Cannot set bandwidth for node %s (%d): %d\n",
+			name, id, ret);
+}
+
+static int msm8974_icc_set(struct icc_node *src, struct icc_node *dst)
+{
+	struct msm8974_icc_node *src_qn, *dst_qn;
+	struct msm8974_icc_provider *qp;
+	u64 sum_bw, max_peak_bw, rate;
+	u32 agg_avg = 0, agg_peak = 0;
+	struct icc_provider *provider;
+	struct icc_node *n;
+	int ret, i;
+
+	src_qn = src->data;
+	dst_qn = dst->data;
+	provider = src->provider;
+	qp = to_msm8974_icc_provider(provider);
+
+	list_for_each_entry(n, &provider->nodes, node_list)
+		msm8974_icc_aggregate(n, 0, n->avg_bw, n->peak_bw,
+				      &agg_avg, &agg_peak);
+
+	sum_bw = icc_units_to_bps(agg_avg);
+	max_peak_bw = icc_units_to_bps(agg_peak);
+
+	/* Set bandwidth on source node */
+	msm8974_icc_rpm_smd_send(provider->dev, RPM_BUS_MASTER_REQ,
+				 src_qn->name, src_qn->mas_rpm_id, sum_bw);
+
+	msm8974_icc_rpm_smd_send(provider->dev, RPM_BUS_SLAVE_REQ,
+				 src_qn->name, src_qn->slv_rpm_id, sum_bw);
+
+	/* Set bandwidth on destination node */
+	msm8974_icc_rpm_smd_send(provider->dev, RPM_BUS_MASTER_REQ,
+				 dst_qn->name, dst_qn->mas_rpm_id, sum_bw);
+
+	msm8974_icc_rpm_smd_send(provider->dev, RPM_BUS_SLAVE_REQ,
+				 dst_qn->name, dst_qn->slv_rpm_id, sum_bw);
+
+	rate = max(sum_bw, max_peak_bw);
+
+	do_div(rate, src_qn->buswidth);
+
+	if (src_qn->rate == rate)
+		return 0;
+
+	for (i = 0; i < qp->num_clks; i++) {
+		ret = clk_set_rate(qp->bus_clks[i].clk, rate);
+		if (ret) {
+			dev_err(provider->dev, "%s clk_set_rate error: %d\n",
+				qp->bus_clks[i].id, ret);
+			ret = 0;
+		}
+	}
+
+	src_qn->rate = rate;
+
+	return 0;
+}
+
+static int msm8974_icc_probe(struct platform_device *pdev)
+{
+	const struct msm8974_icc_desc *desc;
+	struct msm8974_icc_node **qnodes;
+	struct msm8974_icc_provider *qp;
+	struct device *dev = &pdev->dev;
+	struct icc_onecell_data *data;
+	struct icc_provider *provider;
+	struct icc_node *node;
+	size_t num_nodes, i;
+	int ret;
+
+	/* wait for the RPM proxy */
+	if (!qcom_icc_rpm_smd_available())
+		return -EPROBE_DEFER;
+
+	desc = of_device_get_match_data(dev);
+	if (!desc)
+		return -EINVAL;
+
+	qnodes = desc->nodes;
+	num_nodes = desc->num_nodes;
+
+	qp = devm_kzalloc(dev, sizeof(*qp), GFP_KERNEL);
+	if (!qp)
+		return -ENOMEM;
+
+	data = devm_kzalloc(dev, struct_size(data, nodes, num_nodes),
+			    GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	qp->bus_clks = devm_kmemdup(dev, msm8974_icc_bus_clocks,
+				    sizeof(msm8974_icc_bus_clocks), GFP_KERNEL);
+	if (!qp->bus_clks)
+		return -ENOMEM;
+
+	qp->num_clks = ARRAY_SIZE(msm8974_icc_bus_clocks);
+	ret = devm_clk_bulk_get(dev, qp->num_clks, qp->bus_clks);
+	if (ret)
+		return ret;
+
+	ret = clk_bulk_prepare_enable(qp->num_clks, qp->bus_clks);
+	if (ret)
+		return ret;
+
+	provider = &qp->provider;
+	INIT_LIST_HEAD(&provider->nodes);
+	provider->dev = dev;
+	provider->set = msm8974_icc_set;
+	provider->aggregate = msm8974_icc_aggregate;
+	provider->xlate = of_icc_xlate_onecell;
+	provider->data = data;
+
+	ret = icc_provider_add(provider);
+	if (ret) {
+		dev_err(dev, "error adding interconnect provider: %d\n", ret);
+		goto err_disable_clks;
+	}
+
+	for (i = 0; i < num_nodes; i++) {
+		size_t j;
+
+		node = icc_node_create(qnodes[i]->id);
+		if (IS_ERR(node)) {
+			ret = PTR_ERR(node);
+			goto err_del_icc;
+		}
+
+		node->name = qnodes[i]->name;
+		node->data = qnodes[i];
+		icc_node_add(node, provider);
+
+		dev_dbg(dev, "registered node %s\n", node->name);
+
+		/* populate links */
+		for (j = 0; j < qnodes[i]->num_links; j++)
+			icc_link_create(node, qnodes[i]->links[j]);
+
+		data->nodes[i] = node;
+	}
+	data->num_nodes = num_nodes;
+
+	platform_set_drvdata(pdev, qp);
+
+	return 0;
+
+err_del_icc:
+	list_for_each_entry(node, &provider->nodes, node_list) {
+		icc_node_del(node);
+		icc_node_destroy(node->id);
+	}
+	icc_provider_del(provider);
+
+err_disable_clks:
+	clk_bulk_disable_unprepare(qp->num_clks, qp->bus_clks);
+
+	return ret;
+}
+
+static int msm8974_icc_remove(struct platform_device *pdev)
+{
+	struct msm8974_icc_provider *qp = platform_get_drvdata(pdev);
+	struct icc_provider *provider = &qp->provider;
+	struct icc_node *n;
+
+	list_for_each_entry(n, &provider->nodes, node_list) {
+		icc_node_del(n);
+		icc_node_destroy(n->id);
+	}
+	clk_bulk_disable_unprepare(qp->num_clks, qp->bus_clks);
+
+	return icc_provider_del(provider);
+}
+
+static const struct of_device_id msm8974_noc_of_match[] = {
+	{ .compatible = "qcom,msm8974-bimc", .data = &msm8974_bimc},
+	{ .compatible = "qcom,msm8974-cnoc", .data = &msm8974_cnoc},
+	{ .compatible = "qcom,msm8974-mmssnoc", .data = &msm8974_mnoc},
+	{ .compatible = "qcom,msm8974-ocmemnoc", .data = &msm8974_onoc},
+	{ .compatible = "qcom,msm8974-pnoc", .data = &msm8974_pnoc},
+	{ .compatible = "qcom,msm8974-snoc", .data = &msm8974_snoc},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, msm8974_noc_of_match);
+
+static struct platform_driver msm8974_noc_driver = {
+	.probe = msm8974_icc_probe,
+	.remove = msm8974_icc_remove,
+	.driver = {
+		.name = "qnoc-msm8974",
+		.of_match_table = msm8974_noc_of_match,
+	},
+};
+module_platform_driver(msm8974_noc_driver);
+MODULE_DESCRIPTION("Qualcomm MSM8974 NoC driver");
+MODULE_AUTHOR("Brian Masney <masneyb@onstation.org>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mcb/mcb-core.c b/drivers/mcb/mcb-core.c
index b72e82efaee5..38fbb3b59873 100644
--- a/drivers/mcb/mcb-core.c
+++ b/drivers/mcb/mcb-core.c
@@ -191,7 +191,7 @@ int __mcb_register_driver(struct mcb_driver *drv, struct module *owner,
 
 	return driver_register(&drv->driver);
 }
-EXPORT_SYMBOL_GPL(__mcb_register_driver);
+EXPORT_SYMBOL_NS_GPL(__mcb_register_driver, MCB);
 
 /**
  * mcb_unregister_driver() - Unregister a @mcb_driver from the system
@@ -203,7 +203,7 @@ void mcb_unregister_driver(struct mcb_driver *drv)
 {
 	driver_unregister(&drv->driver);
 }
-EXPORT_SYMBOL_GPL(mcb_unregister_driver);
+EXPORT_SYMBOL_NS_GPL(mcb_unregister_driver, MCB);
 
 static void mcb_release_dev(struct device *dev)
 {
@@ -249,7 +249,7 @@ out:
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(mcb_device_register);
+EXPORT_SYMBOL_NS_GPL(mcb_device_register, MCB);
 
 static void mcb_free_bus(struct device *dev)
 {
@@ -301,7 +301,7 @@ err_free:
 	kfree(bus);
 	return ERR_PTR(rc);
 }
-EXPORT_SYMBOL_GPL(mcb_alloc_bus);
+EXPORT_SYMBOL_NS_GPL(mcb_alloc_bus, MCB);
 
 static int __mcb_devices_unregister(struct device *dev, void *data)
 {
@@ -323,7 +323,7 @@ void mcb_release_bus(struct mcb_bus *bus)
 {
 	mcb_devices_unregister(bus);
 }
-EXPORT_SYMBOL_GPL(mcb_release_bus);
+EXPORT_SYMBOL_NS_GPL(mcb_release_bus, MCB);
 
 /**
  * mcb_bus_put() - Increment refcnt
@@ -338,7 +338,7 @@ struct mcb_bus *mcb_bus_get(struct mcb_bus *bus)
 
 	return bus;
 }
-EXPORT_SYMBOL_GPL(mcb_bus_get);
+EXPORT_SYMBOL_NS_GPL(mcb_bus_get, MCB);
 
 /**
  * mcb_bus_put() - Decrement refcnt
@@ -351,7 +351,7 @@ void mcb_bus_put(struct mcb_bus *bus)
 	if (bus)
 		put_device(&bus->dev);
 }
-EXPORT_SYMBOL_GPL(mcb_bus_put);
+EXPORT_SYMBOL_NS_GPL(mcb_bus_put, MCB);
 
 /**
  * mcb_alloc_dev() - Allocate a device
@@ -371,7 +371,7 @@ struct mcb_device *mcb_alloc_dev(struct mcb_bus *bus)
 
 	return dev;
 }
-EXPORT_SYMBOL_GPL(mcb_alloc_dev);
+EXPORT_SYMBOL_NS_GPL(mcb_alloc_dev, MCB);
 
 /**
  * mcb_free_dev() - Free @mcb_device
@@ -383,7 +383,7 @@ void mcb_free_dev(struct mcb_device *dev)
 {
 	kfree(dev);
 }
-EXPORT_SYMBOL_GPL(mcb_free_dev);
+EXPORT_SYMBOL_NS_GPL(mcb_free_dev, MCB);
 
 static int __mcb_bus_add_devices(struct device *dev, void *data)
 {
@@ -412,7 +412,7 @@ void mcb_bus_add_devices(const struct mcb_bus *bus)
 {
 	bus_for_each_dev(&mcb_bus_type, NULL, NULL, __mcb_bus_add_devices);
 }
-EXPORT_SYMBOL_GPL(mcb_bus_add_devices);
+EXPORT_SYMBOL_NS_GPL(mcb_bus_add_devices, MCB);
 
 /**
  * mcb_get_resource() - get a resource for a mcb device
@@ -428,7 +428,7 @@ struct resource *mcb_get_resource(struct mcb_device *dev, unsigned int type)
 	else
 		return NULL;
 }
-EXPORT_SYMBOL_GPL(mcb_get_resource);
+EXPORT_SYMBOL_NS_GPL(mcb_get_resource, MCB);
 
 /**
  * mcb_request_mem() - Request memory
@@ -454,7 +454,7 @@ struct resource *mcb_request_mem(struct mcb_device *dev, const char *name)
 
 	return mem;
 }
-EXPORT_SYMBOL_GPL(mcb_request_mem);
+EXPORT_SYMBOL_NS_GPL(mcb_request_mem, MCB);
 
 /**
  * mcb_release_mem() - Release memory requested by device
@@ -469,7 +469,7 @@ void mcb_release_mem(struct resource *mem)
 	size = resource_size(mem);
 	release_mem_region(mem->start, size);
 }
-EXPORT_SYMBOL_GPL(mcb_release_mem);
+EXPORT_SYMBOL_NS_GPL(mcb_release_mem, MCB);
 
 static int __mcb_get_irq(struct mcb_device *dev)
 {
@@ -495,7 +495,7 @@ int mcb_get_irq(struct mcb_device *dev)
 
 	return __mcb_get_irq(dev);
 }
-EXPORT_SYMBOL_GPL(mcb_get_irq);
+EXPORT_SYMBOL_NS_GPL(mcb_get_irq, MCB);
 
 static int mcb_init(void)
 {
diff --git a/drivers/mcb/mcb-lpc.c b/drivers/mcb/mcb-lpc.c
index 8f1bde437a7e..506676754538 100644
--- a/drivers/mcb/mcb-lpc.c
+++ b/drivers/mcb/mcb-lpc.c
@@ -168,3 +168,4 @@ module_exit(mcb_lpc_exit);
 MODULE_AUTHOR("Andreas Werner <andreas.werner@men.de>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MCB over LPC support");
+MODULE_IMPORT_NS(MCB);
diff --git a/drivers/mcb/mcb-parse.c b/drivers/mcb/mcb-parse.c
index 3b69e6aa3d88..0266bfddfbe2 100644
--- a/drivers/mcb/mcb-parse.c
+++ b/drivers/mcb/mcb-parse.c
@@ -253,4 +253,4 @@ free_header:
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(chameleon_parse_cells);
+EXPORT_SYMBOL_NS_GPL(chameleon_parse_cells, MCB);
diff --git a/drivers/mcb/mcb-pci.c b/drivers/mcb/mcb-pci.c
index 14866aa22f75..dc88232d9af8 100644
--- a/drivers/mcb/mcb-pci.c
+++ b/drivers/mcb/mcb-pci.c
@@ -131,3 +131,4 @@ module_pci_driver(mcb_pci_driver);
 MODULE_AUTHOR("Johannes Thumshirn <johannes.thumshirn@men.de>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MCB over PCI support");
+MODULE_IMPORT_NS(MCB);
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index c55b63750757..7f0d48f406e3 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -8,7 +8,6 @@ menu "Misc devices"
 config SENSORS_LIS3LV02D
 	tristate
 	depends on INPUT
-	select INPUT_POLLDEV
 
 config AD525X_DPOT
 	tristate "Analog Devices Digital Potentiometers"
@@ -326,14 +325,14 @@ config SENSORS_TSL2550
 	  will be called tsl2550.
 
 config SENSORS_BH1770
-         tristate "BH1770GLC / SFH7770 combined ALS - Proximity sensor"
-         depends on I2C
-         ---help---
-           Say Y here if you want to build a driver for BH1770GLC (ROHM) or
+	 tristate "BH1770GLC / SFH7770 combined ALS - Proximity sensor"
+	 depends on I2C
+	 ---help---
+	   Say Y here if you want to build a driver for BH1770GLC (ROHM) or
 	   SFH7770 (Osram) combined ambient light and proximity sensor chip.
 
-           To compile this driver as a module, choose M here: the
-           module will be called bh1770glc. If unsure, say N here.
+	   To compile this driver as a module, choose M here: the
+	   module will be called bh1770glc. If unsure, say N here.
 
 config SENSORS_APDS990X
 	 tristate "APDS990X combined als and proximity sensors"
@@ -438,8 +437,8 @@ config PCI_ENDPOINT_TEST
 	select CRC32
 	tristate "PCI Endpoint Test driver"
 	---help---
-           Enable this configuration option to enable the host side test driver
-           for PCI Endpoint.
+	   Enable this configuration option to enable the host side test driver
+	   for PCI Endpoint.
 
 config XILINX_SDFEC
 	tristate "Xilinx SDFEC 16"
diff --git a/drivers/misc/atmel_tclib.c b/drivers/misc/atmel_tclib.c
index 08b5b639d77f..7de7840f613c 100644
--- a/drivers/misc/atmel_tclib.c
+++ b/drivers/misc/atmel_tclib.c
@@ -109,7 +109,6 @@ static int __init tc_probe(struct platform_device *pdev)
 	struct atmel_tc *tc;
 	struct clk	*clk;
 	int		irq;
-	struct resource	*r;
 	unsigned int	i;
 
 	if (of_get_child_count(pdev->dev.of_node))
@@ -133,8 +132,7 @@ static int __init tc_probe(struct platform_device *pdev)
 	if (IS_ERR(tc->slow_clk))
 		return PTR_ERR(tc->slow_clk);
 
-	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	tc->regs = devm_ioremap_resource(&pdev->dev, r);
+	tc->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(tc->regs))
 		return PTR_ERR(tc->regs);
 
diff --git a/drivers/misc/cardreader/Makefile b/drivers/misc/cardreader/Makefile
index d9bff5a2217e..1f56267ed2f4 100644
--- a/drivers/misc/cardreader/Makefile
+++ b/drivers/misc/cardreader/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_MISC_ALCOR_PCI)	+= alcor_pci.o
 obj-$(CONFIG_MISC_RTSX_PCI)	+= rtsx_pci.o
-rtsx_pci-objs := rtsx_pcr.o rts5209.o rts5229.o rtl8411.o rts5227.o rts5249.o rts5260.o
+rtsx_pci-objs := rtsx_pcr.o rts5209.o rts5229.o rtl8411.o rts5227.o rts5249.o rts5260.o rts5261.o
 obj-$(CONFIG_MISC_RTSX_USB)	+= rtsx_usb.o
diff --git a/drivers/misc/cardreader/rts5260.c b/drivers/misc/cardreader/rts5260.c
index 40a6d199f2ea..4214f02a17fd 100644
--- a/drivers/misc/cardreader/rts5260.c
+++ b/drivers/misc/cardreader/rts5260.c
@@ -191,7 +191,6 @@ static int sd_set_sample_push_timing_sd30(struct rtsx_pcr *pcr)
 
 static int rts5260_card_power_on(struct rtsx_pcr *pcr, int card)
 {
-	int err = 0;
 	struct rtsx_cr_option *option = &pcr->option;
 
 	if (option->ocp_en)
@@ -231,7 +230,7 @@ static int rts5260_card_power_on(struct rtsx_pcr *pcr, int card)
 
 	rtsx_pci_write_register(pcr, REG_PRE_RW_MODE, EN_INFINITE_MODE, 0);
 
-	return err;
+	return 0;
 }
 
 static int rts5260_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage)
diff --git a/drivers/misc/cardreader/rts5261.c b/drivers/misc/cardreader/rts5261.c
new file mode 100644
index 000000000000..32dcec2e9dfd
--- /dev/null
+++ b/drivers/misc/cardreader/rts5261.c
@@ -0,0 +1,792 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2018-2019 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * Author:
+ *   Rui FENG <rui_feng@realsil.com.cn>
+ *   Wei WANG <wei_wang@realsil.com.cn>
+ */
+
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/rtsx_pci.h>
+
+#include "rts5261.h"
+#include "rtsx_pcr.h"
+
+static u8 rts5261_get_ic_version(struct rtsx_pcr *pcr)
+{
+	u8 val;
+
+	rtsx_pci_read_register(pcr, DUMMY_REG_RESET_0, &val);
+	return val & IC_VERSION_MASK;
+}
+
+static void rts5261_fill_driving(struct rtsx_pcr *pcr, u8 voltage)
+{
+	u8 driving_3v3[4][3] = {
+		{0x13, 0x13, 0x13},
+		{0x96, 0x96, 0x96},
+		{0x7F, 0x7F, 0x7F},
+		{0x96, 0x96, 0x96},
+	};
+	u8 driving_1v8[4][3] = {
+		{0x99, 0x99, 0x99},
+		{0x3A, 0x3A, 0x3A},
+		{0xE6, 0xE6, 0xE6},
+		{0xB3, 0xB3, 0xB3},
+	};
+	u8 (*driving)[3], drive_sel;
+
+	if (voltage == OUTPUT_3V3) {
+		driving = driving_3v3;
+		drive_sel = pcr->sd30_drive_sel_3v3;
+	} else {
+		driving = driving_1v8;
+		drive_sel = pcr->sd30_drive_sel_1v8;
+	}
+
+	rtsx_pci_write_register(pcr, SD30_CLK_DRIVE_SEL,
+			 0xFF, driving[drive_sel][0]);
+
+	rtsx_pci_write_register(pcr, SD30_CMD_DRIVE_SEL,
+			 0xFF, driving[drive_sel][1]);
+
+	rtsx_pci_write_register(pcr, SD30_DAT_DRIVE_SEL,
+			 0xFF, driving[drive_sel][2]);
+}
+
+static void rtsx5261_fetch_vendor_settings(struct rtsx_pcr *pcr)
+{
+	u32 reg;
+	/* 0x814~0x817 */
+	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG2, &reg);
+	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG2, reg);
+
+	if (!rts5261_vendor_setting_valid(reg)) {
+		pcr_dbg(pcr, "skip fetch vendor setting\n");
+		return;
+	}
+
+	pcr->card_drive_sel &= 0x3F;
+	pcr->card_drive_sel |= rts5261_reg_to_card_drive_sel(reg);
+
+	if (rts5261_reg_check_reverse_socket(reg))
+		pcr->flags |= PCR_REVERSE_SOCKET;
+
+	/* 0x724~0x727 */
+	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG1, &reg);
+	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG1, reg);
+
+	pcr->aspm_en = rts5261_reg_to_aspm(reg);
+	pcr->sd30_drive_sel_1v8 = rts5261_reg_to_sd30_drive_sel_1v8(reg);
+	pcr->sd30_drive_sel_3v3 = rts5261_reg_to_sd30_drive_sel_3v3(reg);
+}
+
+static void rts5261_force_power_down(struct rtsx_pcr *pcr, u8 pm_state)
+{
+	/* Set relink_time to 0 */
+	rtsx_pci_write_register(pcr, AUTOLOAD_CFG_BASE + 1, MASK_8_BIT_DEF, 0);
+	rtsx_pci_write_register(pcr, AUTOLOAD_CFG_BASE + 2, MASK_8_BIT_DEF, 0);
+	rtsx_pci_write_register(pcr, AUTOLOAD_CFG_BASE + 3,
+				RELINK_TIME_MASK, 0);
+
+	if (pm_state == HOST_ENTER_S3)
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3,
+					D3_DELINK_MODE_EN, D3_DELINK_MODE_EN);
+
+	rtsx_pci_write_register(pcr, RTS5261_REG_FPDCTL,
+		SSC_POWER_DOWN, SSC_POWER_DOWN);
+}
+
+static int rts5261_enable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, OLT_LED_CTL,
+		LED_SHINE_MASK, LED_SHINE_EN);
+}
+
+static int rts5261_disable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, OLT_LED_CTL,
+		LED_SHINE_MASK, LED_SHINE_DISABLE);
+}
+
+static int rts5261_turn_on_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, GPIO_CTL,
+		0x02, 0x02);
+}
+
+static int rts5261_turn_off_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, GPIO_CTL,
+		0x02, 0x00);
+}
+
+/* SD Pull Control Enable:
+ *     SD_DAT[3:0] ==> pull up
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull up
+ *     SD_CMD      ==> pull up
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rts5261_sd_pull_ctl_enable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0xAA),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xE9),
+	0,
+};
+
+/* SD Pull Control Disable:
+ *     SD_DAT[3:0] ==> pull down
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull down
+ *     SD_CMD      ==> pull down
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rts5261_sd_pull_ctl_disable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xD5),
+	0,
+};
+
+static int rts5261_sd_set_sample_push_timing_sd30(struct rtsx_pcr *pcr)
+{
+	rtsx_pci_write_register(pcr, SD_CFG1, SD_MODE_SELECT_MASK
+		| SD_ASYNC_FIFO_NOT_RST, SD_30_MODE | SD_ASYNC_FIFO_NOT_RST);
+	rtsx_pci_write_register(pcr, CLK_CTL, CLK_LOW_FREQ, CLK_LOW_FREQ);
+	rtsx_pci_write_register(pcr, CARD_CLK_SOURCE, 0xFF,
+			CRC_VAR_CLK0 | SD30_FIX_CLK | SAMPLE_VAR_CLK1);
+	rtsx_pci_write_register(pcr, CLK_CTL, CLK_LOW_FREQ, 0);
+
+	return 0;
+}
+
+static int rts5261_card_power_on(struct rtsx_pcr *pcr, int card)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+
+	if (option->ocp_en)
+		rtsx_pci_enable_ocp(pcr);
+
+
+	rtsx_pci_write_register(pcr, RTS5261_LDO1_CFG1,
+			RTS5261_LDO1_TUNE_MASK, RTS5261_LDO1_33);
+	rtsx_pci_write_register(pcr, RTS5261_LDO1233318_POW_CTL,
+			RTS5261_LDO1_POWERON, RTS5261_LDO1_POWERON);
+
+	rtsx_pci_write_register(pcr, RTS5261_LDO1233318_POW_CTL,
+			RTS5261_LDO3318_POWERON, RTS5261_LDO3318_POWERON);
+
+	msleep(20);
+
+	rtsx_pci_write_register(pcr, CARD_OE, SD_OUTPUT_EN, SD_OUTPUT_EN);
+
+	/* Initialize SD_CFG1 register */
+	rtsx_pci_write_register(pcr, SD_CFG1, 0xFF,
+			SD_CLK_DIVIDE_128 | SD_20_MODE | SD_BUS_WIDTH_1BIT);
+
+	rtsx_pci_write_register(pcr, SD_SAMPLE_POINT_CTL,
+			0xFF, SD20_RX_POS_EDGE);
+	rtsx_pci_write_register(pcr, SD_PUSH_POINT_CTL, 0xFF, 0);
+	rtsx_pci_write_register(pcr, CARD_STOP, SD_STOP | SD_CLR_ERR,
+			SD_STOP | SD_CLR_ERR);
+
+	/* Reset SD_CFG3 register */
+	rtsx_pci_write_register(pcr, SD_CFG3, SD30_CLK_END_EN, 0);
+	rtsx_pci_write_register(pcr, REG_SD_STOP_SDCLK_CFG,
+			SD30_CLK_STOP_CFG_EN | SD30_CLK_STOP_CFG1 |
+			SD30_CLK_STOP_CFG0, 0);
+
+	if (pcr->extra_caps & EXTRA_CAPS_SD_SDR50 ||
+	    pcr->extra_caps & EXTRA_CAPS_SD_SDR104)
+		rts5261_sd_set_sample_push_timing_sd30(pcr);
+
+	return 0;
+}
+
+static int rts5261_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage)
+{
+	int err;
+	u16 val = 0;
+
+	rtsx_pci_write_register(pcr, RTS5261_CARD_PWR_CTL,
+			RTS5261_PUPDC, RTS5261_PUPDC);
+
+	switch (voltage) {
+	case OUTPUT_3V3:
+		rtsx_pci_read_phy_register(pcr, PHY_TUNE, &val);
+		val |= PHY_TUNE_SDBUS_33;
+		err = rtsx_pci_write_phy_register(pcr, PHY_TUNE, val);
+		if (err < 0)
+			return err;
+
+		rtsx_pci_write_register(pcr, RTS5261_DV3318_CFG,
+				RTS5261_DV3318_TUNE_MASK, RTS5261_DV3318_33);
+		rtsx_pci_write_register(pcr, SD_PAD_CTL,
+				SD_IO_USING_1V8, 0);
+		break;
+	case OUTPUT_1V8:
+		rtsx_pci_read_phy_register(pcr, PHY_TUNE, &val);
+		val &= ~PHY_TUNE_SDBUS_33;
+		err = rtsx_pci_write_phy_register(pcr, PHY_TUNE, val);
+		if (err < 0)
+			return err;
+
+		rtsx_pci_write_register(pcr, RTS5261_DV3318_CFG,
+				RTS5261_DV3318_TUNE_MASK, RTS5261_DV3318_18);
+		rtsx_pci_write_register(pcr, SD_PAD_CTL,
+				SD_IO_USING_1V8, SD_IO_USING_1V8);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* set pad drive */
+	rts5261_fill_driving(pcr, voltage);
+
+	return 0;
+}
+
+static void rts5261_stop_cmd(struct rtsx_pcr *pcr)
+{
+	rtsx_pci_writel(pcr, RTSX_HCBCTLR, STOP_CMD);
+	rtsx_pci_writel(pcr, RTSX_HDBCTLR, STOP_DMA);
+	rtsx_pci_write_register(pcr, RTS5260_DMA_RST_CTL_0,
+				RTS5260_DMA_RST | RTS5260_ADMA3_RST,
+				RTS5260_DMA_RST | RTS5260_ADMA3_RST);
+	rtsx_pci_write_register(pcr, RBCTL, RB_FLUSH, RB_FLUSH);
+}
+
+static void rts5261_card_before_power_off(struct rtsx_pcr *pcr)
+{
+	rts5261_stop_cmd(pcr);
+	rts5261_switch_output_voltage(pcr, OUTPUT_3V3);
+
+}
+
+static void rts5261_enable_ocp(struct rtsx_pcr *pcr)
+{
+	u8 val = 0;
+
+	val = SD_OCP_INT_EN | SD_DETECT_EN;
+	rtsx_pci_write_register(pcr, REG_OCPCTL, 0xFF, val);
+
+}
+
+static void rts5261_disable_ocp(struct rtsx_pcr *pcr)
+{
+	u8 mask = 0;
+
+	mask = SD_OCP_INT_EN | SD_DETECT_EN;
+	rtsx_pci_write_register(pcr, REG_OCPCTL, mask, 0);
+	rtsx_pci_write_register(pcr, RTS5261_LDO1_CFG0,
+			RTS5261_LDO1_OCP_EN | RTS5261_LDO1_OCP_LMT_EN, 0);
+
+}
+
+static int rts5261_card_power_off(struct rtsx_pcr *pcr, int card)
+{
+	int err = 0;
+
+	rts5261_card_before_power_off(pcr);
+	err = rtsx_pci_write_register(pcr, RTS5261_LDO1233318_POW_CTL,
+				RTS5261_LDO_POWERON_MASK, 0);
+
+	if (pcr->option.ocp_en)
+		rtsx_pci_disable_ocp(pcr);
+
+	return err;
+}
+
+static void rts5261_init_ocp(struct rtsx_pcr *pcr)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+
+	if (option->ocp_en) {
+		u8 mask, val;
+
+		rtsx_pci_write_register(pcr, RTS5261_LDO1_CFG0,
+			RTS5261_LDO1_OCP_EN | RTS5261_LDO1_OCP_LMT_EN,
+			RTS5261_LDO1_OCP_EN | RTS5261_LDO1_OCP_LMT_EN);
+
+		rtsx_pci_write_register(pcr, RTS5261_LDO1_CFG0,
+			RTS5261_LDO1_OCP_THD_MASK, option->sd_800mA_ocp_thd);
+
+		rtsx_pci_write_register(pcr, RTS5261_LDO1_CFG0,
+			RTS5261_LDO1_OCP_LMT_THD_MASK,
+			RTS5261_LDO1_LMT_THD_2000);
+
+		mask = SD_OCP_GLITCH_MASK;
+		val = pcr->hw_param.ocp_glitch;
+		rtsx_pci_write_register(pcr, REG_OCPGLITCH, mask, val);
+
+		rts5261_enable_ocp(pcr);
+	} else {
+		rtsx_pci_write_register(pcr, RTS5261_LDO1_CFG0,
+			RTS5261_LDO1_OCP_EN | RTS5261_LDO1_OCP_LMT_EN, 0);
+	}
+}
+
+static void rts5261_clear_ocpstat(struct rtsx_pcr *pcr)
+{
+	u8 mask = 0;
+	u8 val = 0;
+
+	mask = SD_OCP_INT_CLR | SD_OC_CLR;
+	val = SD_OCP_INT_CLR | SD_OC_CLR;
+
+	rtsx_pci_write_register(pcr, REG_OCPCTL, mask, val);
+
+	udelay(10);
+	rtsx_pci_write_register(pcr, REG_OCPCTL, mask, 0);
+
+}
+
+static void rts5261_process_ocp(struct rtsx_pcr *pcr)
+{
+	if (!pcr->option.ocp_en)
+		return;
+
+	rtsx_pci_get_ocpstat(pcr, &pcr->ocp_stat);
+
+	if (pcr->ocp_stat & (SD_OC_NOW | SD_OC_EVER)) {
+		rts5261_card_power_off(pcr, RTSX_SD_CARD);
+		rtsx_pci_write_register(pcr, CARD_OE, SD_OUTPUT_EN, 0);
+		rts5261_clear_ocpstat(pcr);
+		pcr->ocp_stat = 0;
+	}
+
+}
+
+static int rts5261_init_from_hw(struct rtsx_pcr *pcr)
+{
+	int retval;
+	u32 lval, i;
+	u8 valid, efuse_valid, tmp;
+
+	rtsx_pci_write_register(pcr, RTS5261_REG_PME_FORCE_CTL,
+		REG_EFUSE_POR | REG_EFUSE_POWER_MASK,
+		REG_EFUSE_POR | REG_EFUSE_POWERON);
+	udelay(1);
+	rtsx_pci_write_register(pcr, RTS5261_EFUSE_ADDR,
+		RTS5261_EFUSE_ADDR_MASK, 0x00);
+	rtsx_pci_write_register(pcr, RTS5261_EFUSE_CTL,
+		RTS5261_EFUSE_ENABLE | RTS5261_EFUSE_MODE_MASK,
+		RTS5261_EFUSE_ENABLE);
+
+	/* Wait transfer end */
+	for (i = 0; i < MAX_RW_REG_CNT; i++) {
+		rtsx_pci_read_register(pcr, RTS5261_EFUSE_CTL, &tmp);
+		if ((tmp & 0x80) == 0)
+			break;
+	}
+	rtsx_pci_read_register(pcr, RTS5261_EFUSE_READ_DATA, &tmp);
+	efuse_valid = ((tmp & 0x0C) >> 2);
+	pcr_dbg(pcr, "Load efuse valid: 0x%x\n", efuse_valid);
+
+	if (efuse_valid == 0) {
+		retval = rtsx_pci_read_config_dword(pcr,
+			PCR_SETTING_REG2, &lval);
+		if (retval != 0)
+			pcr_dbg(pcr, "read 0x814 DW fail\n");
+		pcr_dbg(pcr, "DW from 0x814: 0x%x\n", lval);
+		/* 0x816 */
+		valid = (u8)((lval >> 16) & 0x03);
+		pcr_dbg(pcr, "0x816: %d\n", valid);
+	}
+	rtsx_pci_write_register(pcr, RTS5261_REG_PME_FORCE_CTL,
+		REG_EFUSE_POR, 0);
+	pcr_dbg(pcr, "Disable efuse por!\n");
+
+	rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG2, &lval);
+	lval = lval & 0x00FFFFFF;
+	retval = rtsx_pci_write_config_dword(pcr, PCR_SETTING_REG2, lval);
+	if (retval != 0)
+		pcr_dbg(pcr, "write config fail\n");
+
+	return retval;
+}
+
+static void rts5261_init_from_cfg(struct rtsx_pcr *pcr)
+{
+	u32 lval;
+	struct rtsx_cr_option *option = &pcr->option;
+
+	rtsx_pci_read_config_dword(pcr, PCR_ASPM_SETTING_REG1, &lval);
+
+	if (lval & ASPM_L1_1_EN_MASK)
+		rtsx_set_dev_flag(pcr, ASPM_L1_1_EN);
+	else
+		rtsx_clear_dev_flag(pcr, ASPM_L1_1_EN);
+
+	if (lval & ASPM_L1_2_EN_MASK)
+		rtsx_set_dev_flag(pcr, ASPM_L1_2_EN);
+	else
+		rtsx_clear_dev_flag(pcr, ASPM_L1_2_EN);
+
+	if (lval & PM_L1_1_EN_MASK)
+		rtsx_set_dev_flag(pcr, PM_L1_1_EN);
+	else
+		rtsx_clear_dev_flag(pcr, PM_L1_1_EN);
+
+	if (lval & PM_L1_2_EN_MASK)
+		rtsx_set_dev_flag(pcr, PM_L1_2_EN);
+	else
+		rtsx_clear_dev_flag(pcr, PM_L1_2_EN);
+
+	rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0xFF, 0);
+	if (option->ltr_en) {
+		u16 val;
+
+		pcie_capability_read_word(pcr->pci, PCI_EXP_DEVCTL2, &val);
+		if (val & PCI_EXP_DEVCTL2_LTR_EN) {
+			option->ltr_enabled = true;
+			option->ltr_active = true;
+			rtsx_set_ltr_latency(pcr, option->ltr_active_latency);
+		} else {
+			option->ltr_enabled = false;
+		}
+	}
+
+	if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN
+				| PM_L1_1_EN | PM_L1_2_EN))
+		option->force_clkreq_0 = false;
+	else
+		option->force_clkreq_0 = true;
+}
+
+static int rts5261_extra_init_hw(struct rtsx_pcr *pcr)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+
+	rtsx_pci_write_register(pcr, RTS5261_AUTOLOAD_CFG1,
+			CD_RESUME_EN_MASK, CD_RESUME_EN_MASK);
+
+	rts5261_init_from_cfg(pcr);
+	rts5261_init_from_hw(pcr);
+
+	/* power off efuse */
+	rtsx_pci_write_register(pcr, RTS5261_REG_PME_FORCE_CTL,
+			REG_EFUSE_POWER_MASK, REG_EFUSE_POWEROFF);
+	rtsx_pci_write_register(pcr, L1SUB_CONFIG1,
+			AUX_CLK_ACTIVE_SEL_MASK, MAC_CKSW_DONE);
+	rtsx_pci_write_register(pcr, L1SUB_CONFIG3, 0xFF, 0);
+
+	rtsx_pci_write_register(pcr, RTS5261_AUTOLOAD_CFG4,
+			RTS5261_AUX_CLK_16M_EN, 0);
+
+	/* Release PRSNT# */
+	rtsx_pci_write_register(pcr, RTS5261_AUTOLOAD_CFG4,
+			RTS5261_FORCE_PRSNT_LOW, 0);
+	rtsx_pci_write_register(pcr, FUNC_FORCE_CTL,
+			FUNC_FORCE_UPME_XMT_DBG, FUNC_FORCE_UPME_XMT_DBG);
+
+	rtsx_pci_write_register(pcr, PCLK_CTL,
+			PCLK_MODE_SEL, PCLK_MODE_SEL);
+
+	rtsx_pci_write_register(pcr, PM_EVENT_DEBUG, PME_DEBUG_0, PME_DEBUG_0);
+	rtsx_pci_write_register(pcr, PM_CLK_FORCE_CTL, CLK_PM_EN, CLK_PM_EN);
+
+	/* LED shine disabled, set initial shine cycle period */
+	rtsx_pci_write_register(pcr, OLT_LED_CTL, 0x0F, 0x02);
+
+	/* Configure driving */
+	rts5261_fill_driving(pcr, OUTPUT_3V3);
+
+	/*
+	 * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced
+	 * to drive low, and we forcibly request clock.
+	 */
+	if (option->force_clkreq_0)
+		rtsx_pci_write_register(pcr, PETXCFG,
+				 FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW);
+	else
+		rtsx_pci_write_register(pcr, PETXCFG,
+				 FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH);
+
+	rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x10, 0x00);
+	rtsx_pci_write_register(pcr, RTS5261_REG_PME_FORCE_CTL,
+			FORCE_PM_CONTROL | FORCE_PM_VALUE, FORCE_PM_CONTROL);
+
+	/* Clear Enter RTD3_cold Information*/
+	rtsx_pci_write_register(pcr, RTS5261_FW_CTL,
+		RTS5261_INFORM_RTD3_COLD, 0);
+
+	return 0;
+}
+
+static void rts5261_enable_aspm(struct rtsx_pcr *pcr, bool enable)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+	u8 val = 0;
+
+	if (pcr->aspm_enabled == enable)
+		return;
+
+	if (option->dev_aspm_mode == DEV_ASPM_DYNAMIC) {
+		val = pcr->aspm_en;
+		rtsx_pci_update_cfg_byte(pcr, pcr->pcie_cap + PCI_EXP_LNKCTL,
+					 ASPM_MASK_NEG, val);
+	} else if (option->dev_aspm_mode == DEV_ASPM_BACKDOOR) {
+		u8 mask = FORCE_ASPM_VAL_MASK | FORCE_ASPM_CTL0;
+
+		val = FORCE_ASPM_CTL0;
+		val |= (pcr->aspm_en & 0x02);
+		rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, mask, val);
+		val = pcr->aspm_en;
+		rtsx_pci_update_cfg_byte(pcr, pcr->pcie_cap + PCI_EXP_LNKCTL,
+					 ASPM_MASK_NEG, val);
+	}
+	pcr->aspm_enabled = enable;
+
+}
+
+static void rts5261_disable_aspm(struct rtsx_pcr *pcr, bool enable)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+	u8 val = 0;
+
+	if (pcr->aspm_enabled == enable)
+		return;
+
+	if (option->dev_aspm_mode == DEV_ASPM_DYNAMIC) {
+		val = 0;
+		rtsx_pci_update_cfg_byte(pcr, pcr->pcie_cap + PCI_EXP_LNKCTL,
+					 ASPM_MASK_NEG, val);
+	} else if (option->dev_aspm_mode == DEV_ASPM_BACKDOOR) {
+		u8 mask = FORCE_ASPM_VAL_MASK | FORCE_ASPM_CTL0;
+
+		val = 0;
+		rtsx_pci_update_cfg_byte(pcr, pcr->pcie_cap + PCI_EXP_LNKCTL,
+					 ASPM_MASK_NEG, val);
+		val = FORCE_ASPM_CTL0;
+		rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, mask, val);
+	}
+	rtsx_pci_write_register(pcr, SD_CFG1, SD_ASYNC_FIFO_NOT_RST, 0);
+	udelay(10);
+	pcr->aspm_enabled = enable;
+}
+
+static void rts5261_set_aspm(struct rtsx_pcr *pcr, bool enable)
+{
+	if (enable)
+		rts5261_enable_aspm(pcr, true);
+	else
+		rts5261_disable_aspm(pcr, false);
+}
+
+static void rts5261_set_l1off_cfg_sub_d0(struct rtsx_pcr *pcr, int active)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+	int aspm_L1_1, aspm_L1_2;
+	u8 val = 0;
+
+	aspm_L1_1 = rtsx_check_dev_flag(pcr, ASPM_L1_1_EN);
+	aspm_L1_2 = rtsx_check_dev_flag(pcr, ASPM_L1_2_EN);
+
+	if (active) {
+		/* run, latency: 60us */
+		if (aspm_L1_1)
+			val = option->ltr_l1off_snooze_sspwrgate;
+	} else {
+		/* l1off, latency: 300us */
+		if (aspm_L1_2)
+			val = option->ltr_l1off_sspwrgate;
+	}
+
+	rtsx_set_l1off_sub(pcr, val);
+}
+
+static const struct pcr_ops rts5261_pcr_ops = {
+	.fetch_vendor_settings = rtsx5261_fetch_vendor_settings,
+	.turn_on_led = rts5261_turn_on_led,
+	.turn_off_led = rts5261_turn_off_led,
+	.extra_init_hw = rts5261_extra_init_hw,
+	.enable_auto_blink = rts5261_enable_auto_blink,
+	.disable_auto_blink = rts5261_disable_auto_blink,
+	.card_power_on = rts5261_card_power_on,
+	.card_power_off = rts5261_card_power_off,
+	.switch_output_voltage = rts5261_switch_output_voltage,
+	.force_power_down = rts5261_force_power_down,
+	.stop_cmd = rts5261_stop_cmd,
+	.set_aspm = rts5261_set_aspm,
+	.set_l1off_cfg_sub_d0 = rts5261_set_l1off_cfg_sub_d0,
+	.enable_ocp = rts5261_enable_ocp,
+	.disable_ocp = rts5261_disable_ocp,
+	.init_ocp = rts5261_init_ocp,
+	.process_ocp = rts5261_process_ocp,
+	.clear_ocpstat = rts5261_clear_ocpstat,
+};
+
+static inline u8 double_ssc_depth(u8 depth)
+{
+	return ((depth > 1) ? (depth - 1) : depth);
+}
+
+int rts5261_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
+		u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk)
+{
+	int err, clk;
+	u8 n, clk_divider, mcu_cnt, div;
+	static const u8 depth[] = {
+		[RTSX_SSC_DEPTH_4M] = RTS5261_SSC_DEPTH_4M,
+		[RTSX_SSC_DEPTH_2M] = RTS5261_SSC_DEPTH_2M,
+		[RTSX_SSC_DEPTH_1M] = RTS5261_SSC_DEPTH_1M,
+		[RTSX_SSC_DEPTH_500K] = RTS5261_SSC_DEPTH_512K,
+	};
+
+	if (initial_mode) {
+		/* We use 250k(around) here, in initial stage */
+		clk_divider = SD_CLK_DIVIDE_128;
+		card_clock = 30000000;
+	} else {
+		clk_divider = SD_CLK_DIVIDE_0;
+	}
+	err = rtsx_pci_write_register(pcr, SD_CFG1,
+			SD_CLK_DIVIDE_MASK, clk_divider);
+	if (err < 0)
+		return err;
+
+	card_clock /= 1000000;
+	pcr_dbg(pcr, "Switch card clock to %dMHz\n", card_clock);
+
+	clk = card_clock;
+	if (!initial_mode && double_clk)
+		clk = card_clock * 2;
+	pcr_dbg(pcr, "Internal SSC clock: %dMHz (cur_clock = %d)\n",
+		clk, pcr->cur_clock);
+
+	if (clk == pcr->cur_clock)
+		return 0;
+
+	if (pcr->ops->conv_clk_and_div_n)
+		n = (u8)pcr->ops->conv_clk_and_div_n(clk, CLK_TO_DIV_N);
+	else
+		n = (u8)(clk - 4);
+	if ((clk <= 4) || (n > 396))
+		return -EINVAL;
+
+	mcu_cnt = (u8)(125/clk + 3);
+	if (mcu_cnt > 15)
+		mcu_cnt = 15;
+
+	div = CLK_DIV_1;
+	while ((n < MIN_DIV_N_PCR - 4) && (div < CLK_DIV_8)) {
+		if (pcr->ops->conv_clk_and_div_n) {
+			int dbl_clk = pcr->ops->conv_clk_and_div_n(n,
+					DIV_N_TO_CLK) * 2;
+			n = (u8)pcr->ops->conv_clk_and_div_n(dbl_clk,
+					CLK_TO_DIV_N);
+		} else {
+			n = (n + 4) * 2 - 4;
+		}
+		div++;
+	}
+
+	n = (n / 2);
+	pcr_dbg(pcr, "n = %d, div = %d\n", n, div);
+
+	ssc_depth = depth[ssc_depth];
+	if (double_clk)
+		ssc_depth = double_ssc_depth(ssc_depth);
+
+	if (ssc_depth) {
+		if (div == CLK_DIV_2) {
+			if (ssc_depth > 1)
+				ssc_depth -= 1;
+			else
+				ssc_depth = RTS5261_SSC_DEPTH_8M;
+		} else if (div == CLK_DIV_4) {
+			if (ssc_depth > 2)
+				ssc_depth -= 2;
+			else
+				ssc_depth = RTS5261_SSC_DEPTH_8M;
+		} else if (div == CLK_DIV_8) {
+			if (ssc_depth > 3)
+				ssc_depth -= 3;
+			else
+				ssc_depth = RTS5261_SSC_DEPTH_8M;
+		}
+	} else {
+		ssc_depth = 0;
+	}
+	pcr_dbg(pcr, "ssc_depth = %d\n", ssc_depth);
+
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_CTL,
+				CLK_LOW_FREQ, CLK_LOW_FREQ);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_DIV,
+			0xFF, (div << 4) | mcu_cnt);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, 0);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2,
+			SSC_DEPTH_MASK, ssc_depth);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_DIV_N_0, 0xFF, n);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, SSC_RSTB);
+	if (vpclk) {
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK0_CTL,
+				PHASE_NOT_RESET, 0);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK1_CTL,
+				PHASE_NOT_RESET, 0);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK0_CTL,
+				PHASE_NOT_RESET, PHASE_NOT_RESET);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK1_CTL,
+				PHASE_NOT_RESET, PHASE_NOT_RESET);
+	}
+
+	err = rtsx_pci_send_cmd(pcr, 2000);
+	if (err < 0)
+		return err;
+
+	/* Wait SSC clock stable */
+	udelay(SSC_CLOCK_STABLE_WAIT);
+	err = rtsx_pci_write_register(pcr, CLK_CTL, CLK_LOW_FREQ, 0);
+	if (err < 0)
+		return err;
+
+	pcr->cur_clock = clk;
+	return 0;
+
+}
+
+void rts5261_init_params(struct rtsx_pcr *pcr)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+	struct rtsx_hw_param *hw_param = &pcr->hw_param;
+
+	pcr->extra_caps = EXTRA_CAPS_SD_SDR50 | EXTRA_CAPS_SD_SDR104;
+	pcr->num_slots = 1;
+	pcr->ops = &rts5261_pcr_ops;
+
+	pcr->flags = 0;
+	pcr->card_drive_sel = RTSX_CARD_DRIVE_DEFAULT;
+	pcr->sd30_drive_sel_1v8 = CFG_DRIVER_TYPE_B;
+	pcr->sd30_drive_sel_3v3 = CFG_DRIVER_TYPE_B;
+	pcr->aspm_en = ASPM_L1_EN;
+	pcr->tx_initial_phase = SET_CLOCK_PHASE(20, 27, 16);
+	pcr->rx_initial_phase = SET_CLOCK_PHASE(24, 6, 5);
+
+	pcr->ic_version = rts5261_get_ic_version(pcr);
+	pcr->sd_pull_ctl_enable_tbl = rts5261_sd_pull_ctl_enable_tbl;
+	pcr->sd_pull_ctl_disable_tbl = rts5261_sd_pull_ctl_disable_tbl;
+
+	pcr->reg_pm_ctrl3 = RTS5261_AUTOLOAD_CFG3;
+
+	option->dev_flags = (LTR_L1SS_PWR_GATE_CHECK_CARD_EN
+				| LTR_L1SS_PWR_GATE_EN);
+	option->ltr_en = true;
+
+	/* init latency of active, idle, L1OFF to 60us, 300us, 3ms */
+	option->ltr_active_latency = LTR_ACTIVE_LATENCY_DEF;
+	option->ltr_idle_latency = LTR_IDLE_LATENCY_DEF;
+	option->ltr_l1off_latency = LTR_L1OFF_LATENCY_DEF;
+	option->l1_snooze_delay = L1_SNOOZE_DELAY_DEF;
+	option->ltr_l1off_sspwrgate = 0x7F;
+	option->ltr_l1off_snooze_sspwrgate = 0x78;
+	option->dev_aspm_mode = DEV_ASPM_DYNAMIC;
+
+	option->ocp_en = 1;
+	hw_param->interrupt_en |= SD_OC_INT_EN;
+	hw_param->ocp_glitch =  SD_OCP_GLITCH_800U;
+	option->sd_800mA_ocp_thd =  RTS5261_LDO1_OCP_THD_1040;
+}
diff --git a/drivers/misc/cardreader/rts5261.h b/drivers/misc/cardreader/rts5261.h
new file mode 100644
index 000000000000..ebfdd236a553
--- /dev/null
+++ b/drivers/misc/cardreader/rts5261.h
@@ -0,0 +1,233 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2018-2019 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * Author:
+ *   Rui FENG <rui_feng@realsil.com.cn>
+ *   Wei WANG <wei_wang@realsil.com.cn>
+ */
+#ifndef RTS5261_H
+#define RTS5261_H
+
+/*New add*/
+#define rts5261_vendor_setting_valid(reg)	((reg) & 0x010000)
+#define rts5261_reg_to_aspm(reg)		(((reg) >> 28) ^ 0x03)
+#define rts5261_reg_check_reverse_socket(reg)	((reg) & 0x04)
+#define rts5261_reg_to_card_drive_sel(reg)	((((reg) >> 6) & 0x01) << 6)
+#define rts5261_reg_to_sd30_drive_sel_1v8(reg)	(((reg) >> 22) ^ 0x03)
+#define rts5261_reg_to_sd30_drive_sel_3v3(reg)	(((reg) >> 16) ^ 0x03)
+
+
+#define RTS5261_AUTOLOAD_CFG0		0xFF7B
+#define RTS5261_AUTOLOAD_CFG1		0xFF7C
+#define RTS5261_AUTOLOAD_CFG2		0xFF7D
+#define RTS5261_AUTOLOAD_CFG3		0xFF7E
+#define RTS5261_AUTOLOAD_CFG4		0xFF7F
+#define RTS5261_FORCE_PRSNT_LOW		(1 << 6)
+#define RTS5261_AUX_CLK_16M_EN		(1 << 5)
+
+#define RTS5261_REG_VREF		0xFE97
+#define RTS5261_PWD_SUSPND_EN		(1 << 4)
+
+#define RTS5261_PAD_H3L1		0xFF79
+#define PAD_GPIO_H3L1			(1 << 3)
+
+/* SSC_CTL2 0xFC12 */
+#define RTS5261_SSC_DEPTH_MASK		0x07
+#define RTS5261_SSC_DEPTH_DISALBE	0x00
+#define RTS5261_SSC_DEPTH_8M		0x01
+#define RTS5261_SSC_DEPTH_4M		0x02
+#define RTS5261_SSC_DEPTH_2M		0x03
+#define RTS5261_SSC_DEPTH_1M		0x04
+#define RTS5261_SSC_DEPTH_512K		0x05
+#define RTS5261_SSC_DEPTH_256K		0x06
+#define RTS5261_SSC_DEPTH_128K		0x07
+
+/* efuse control register*/
+#define RTS5261_EFUSE_CTL		0xFC30
+#define RTS5261_EFUSE_ENABLE		0x80
+/* EFUSE_MODE: 0=READ 1=PROGRAM */
+#define RTS5261_EFUSE_MODE_MASK		0x40
+#define RTS5261_EFUSE_PROGRAM		0x40
+
+#define RTS5261_EFUSE_ADDR		0xFC31
+#define	RTS5261_EFUSE_ADDR_MASK		0x3F
+
+#define RTS5261_EFUSE_WRITE_DATA	0xFC32
+#define RTS5261_EFUSE_READ_DATA		0xFC34
+
+/* DMACTL 0xFE2C */
+#define RTS5261_DMA_PACK_SIZE_MASK	0xF0
+
+/* FW config info register */
+#define RTS5261_FW_CFG_INFO0		0xFF50
+#define RTS5261_FW_EXPRESS_TEST_MASK	(0x01<<0)
+#define RTS5261_FW_EA_MODE_MASK		(0x01<<5)
+
+/* FW config register */
+#define RTS5261_FW_CFG0			0xFF54
+#define RTS5261_FW_ENTER_EXPRESS	(0x01<<0)
+
+#define RTS5261_FW_CFG1			0xFF55
+#define RTS5261_SYS_CLK_SEL_MCU_CLK	(0x01<<7)
+#define RTS5261_CRC_CLK_SEL_MCU_CLK	(0x01<<6)
+#define RTS5261_FAKE_MCU_CLOCK_GATING	(0x01<<5)
+/*MCU_bus_mode_sel: 0=real 8051 1=fake mcu*/
+#define RTS5261_MCU_BUS_SEL_MASK	(0x01<<4)
+/*MCU_clock_sel:VerA 00=aux16M 01=aux400K 1x=REFCLK100M*/
+/*MCU_clock_sel:VerB 00=aux400K 01=aux16M 10=REFCLK100M*/
+#define RTS5261_MCU_CLOCK_SEL_MASK	(0x03<<2)
+#define RTS5261_MCU_CLOCK_SEL_16M	(0x01<<2)
+#define RTS5261_MCU_CLOCK_GATING	(0x01<<1)
+#define RTS5261_DRIVER_ENABLE_FW	(0x01<<0)
+
+/* FW status register */
+#define RTS5261_FW_STATUS		0xFF56
+#define RTS5261_EXPRESS_LINK_FAIL_MASK	(0x01<<7)
+
+/* FW control register */
+#define RTS5261_FW_CTL			0xFF5F
+#define RTS5261_INFORM_RTD3_COLD	(0x01<<5)
+
+#define RTS5261_REG_FPDCTL		0xFF60
+
+#define RTS5261_REG_LDO12_CFG		0xFF6E
+#define RTS5261_LDO12_VO_TUNE_MASK	(0x07<<1)
+#define RTS5261_LDO12_115		(0x03<<1)
+#define RTS5261_LDO12_120		(0x04<<1)
+#define RTS5261_LDO12_125		(0x05<<1)
+#define RTS5261_LDO12_130		(0x06<<1)
+#define RTS5261_LDO12_135		(0x07<<1)
+
+/* LDO control register */
+#define RTS5261_CARD_PWR_CTL		0xFD50
+#define RTS5261_SD_CLK_ISO		(0x01<<7)
+#define RTS5261_PAD_SD_DAT_FW_CTRL	(0x01<<6)
+#define RTS5261_PUPDC			(0x01<<5)
+#define RTS5261_SD_CMD_ISO		(0x01<<4)
+#define RTS5261_SD_DAT_ISO_MASK		(0x0F<<0)
+
+#define RTS5261_LDO1233318_POW_CTL	0xFF70
+#define RTS5261_LDO3318_POWERON		(0x01<<3)
+#define RTS5261_LDO3_POWERON		(0x01<<2)
+#define RTS5261_LDO2_POWERON		(0x01<<1)
+#define RTS5261_LDO1_POWERON		(0x01<<0)
+#define RTS5261_LDO_POWERON_MASK	(0x0F<<0)
+
+#define RTS5261_DV3318_CFG		0xFF71
+#define RTS5261_DV3318_TUNE_MASK	(0x07<<4)
+#define RTS5261_DV3318_18		(0x02<<4)
+#define RTS5261_DV3318_19		(0x04<<4)
+#define RTS5261_DV3318_33		(0x07<<4)
+
+#define RTS5261_LDO1_CFG0		0xFF72
+#define RTS5261_LDO1_OCP_THD_MASK	(0x07<<5)
+#define RTS5261_LDO1_OCP_EN		(0x01<<4)
+#define RTS5261_LDO1_OCP_LMT_THD_MASK	(0x03<<2)
+#define RTS5261_LDO1_OCP_LMT_EN		(0x01<<1)
+
+/* CRD6603-433 190319 request changed */
+#define RTS5261_LDO1_OCP_THD_740	(0x00<<5)
+#define RTS5261_LDO1_OCP_THD_800	(0x01<<5)
+#define RTS5261_LDO1_OCP_THD_860	(0x02<<5)
+#define RTS5261_LDO1_OCP_THD_920	(0x03<<5)
+#define RTS5261_LDO1_OCP_THD_980	(0x04<<5)
+#define RTS5261_LDO1_OCP_THD_1040	(0x05<<5)
+#define RTS5261_LDO1_OCP_THD_1100	(0x06<<5)
+#define RTS5261_LDO1_OCP_THD_1160	(0x07<<5)
+
+#define RTS5261_LDO1_LMT_THD_450	(0x00<<2)
+#define RTS5261_LDO1_LMT_THD_1000	(0x01<<2)
+#define RTS5261_LDO1_LMT_THD_1500	(0x02<<2)
+#define RTS5261_LDO1_LMT_THD_2000	(0x03<<2)
+
+#define RTS5261_LDO1_CFG1		0xFF73
+#define RTS5261_LDO1_TUNE_MASK		(0x07<<1)
+#define RTS5261_LDO1_18			(0x05<<1)
+#define RTS5261_LDO1_33			(0x07<<1)
+#define RTS5261_LDO1_PWD_MASK		(0x01<<0)
+
+#define RTS5261_LDO2_CFG0		0xFF74
+#define RTS5261_LDO2_OCP_THD_MASK	(0x07<<5)
+#define RTS5261_LDO2_OCP_EN		(0x01<<4)
+#define RTS5261_LDO2_OCP_LMT_THD_MASK	(0x03<<2)
+#define RTS5261_LDO2_OCP_LMT_EN		(0x01<<1)
+
+#define RTS5261_LDO2_OCP_THD_620	(0x00<<5)
+#define RTS5261_LDO2_OCP_THD_650	(0x01<<5)
+#define RTS5261_LDO2_OCP_THD_680	(0x02<<5)
+#define RTS5261_LDO2_OCP_THD_720	(0x03<<5)
+#define RTS5261_LDO2_OCP_THD_750	(0x04<<5)
+#define RTS5261_LDO2_OCP_THD_780	(0x05<<5)
+#define RTS5261_LDO2_OCP_THD_810	(0x06<<5)
+#define RTS5261_LDO2_OCP_THD_840	(0x07<<5)
+
+#define RTS5261_LDO2_CFG1		0xFF75
+#define RTS5261_LDO2_TUNE_MASK		(0x07<<1)
+#define RTS5261_LDO2_18			(0x05<<1)
+#define RTS5261_LDO2_33			(0x07<<1)
+#define RTS5261_LDO2_PWD_MASK		(0x01<<0)
+
+#define RTS5261_LDO3_CFG0		0xFF76
+#define RTS5261_LDO3_OCP_THD_MASK	(0x07<<5)
+#define RTS5261_LDO3_OCP_EN		(0x01<<4)
+#define RTS5261_LDO3_OCP_LMT_THD_MASK	(0x03<<2)
+#define RTS5261_LDO3_OCP_LMT_EN		(0x01<<1)
+
+#define RTS5261_LDO3_OCP_THD_620	(0x00<<5)
+#define RTS5261_LDO3_OCP_THD_650	(0x01<<5)
+#define RTS5261_LDO3_OCP_THD_680	(0x02<<5)
+#define RTS5261_LDO3_OCP_THD_720	(0x03<<5)
+#define RTS5261_LDO3_OCP_THD_750	(0x04<<5)
+#define RTS5261_LDO3_OCP_THD_780	(0x05<<5)
+#define RTS5261_LDO3_OCP_THD_810	(0x06<<5)
+#define RTS5261_LDO3_OCP_THD_840	(0x07<<5)
+
+#define RTS5261_LDO3_CFG1		0xFF77
+#define RTS5261_LDO3_TUNE_MASK		(0x07<<1)
+#define RTS5261_LDO3_18			(0x05<<1)
+#define RTS5261_LDO3_33			(0x07<<1)
+#define RTS5261_LDO3_PWD_MASK		(0x01<<0)
+
+#define RTS5261_REG_PME_FORCE_CTL	0xFF78
+#define FORCE_PM_CONTROL		0x20
+#define FORCE_PM_VALUE			0x10
+#define REG_EFUSE_BYPASS		0x08
+#define REG_EFUSE_POR			0x04
+#define REG_EFUSE_POWER_MASK		0x03
+#define REG_EFUSE_POWERON		0x03
+#define REG_EFUSE_POWEROFF		0x00
+
+
+/* Single LUN, support SD/SD EXPRESS */
+#define DEFAULT_SINGLE		0
+#define SD_LUN			1
+#define SD_EXPRESS_LUN		2
+
+/* For Change_FPGA_SSCClock Function */
+#define MULTIPLY_BY_1    0x00
+#define MULTIPLY_BY_2    0x01
+#define MULTIPLY_BY_3    0x02
+#define MULTIPLY_BY_4    0x03
+#define MULTIPLY_BY_5    0x04
+#define MULTIPLY_BY_6    0x05
+#define MULTIPLY_BY_7    0x06
+#define MULTIPLY_BY_8    0x07
+#define MULTIPLY_BY_9    0x08
+#define MULTIPLY_BY_10   0x09
+
+#define DIVIDE_BY_2      0x01
+#define DIVIDE_BY_3      0x02
+#define DIVIDE_BY_4      0x03
+#define DIVIDE_BY_5      0x04
+#define DIVIDE_BY_6      0x05
+#define DIVIDE_BY_7      0x06
+#define DIVIDE_BY_8      0x07
+#define DIVIDE_BY_9      0x08
+#define DIVIDE_BY_10     0x09
+
+int rts5261_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
+		u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk);
+
+#endif /* RTS5261_H */
diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c
index b4a66b64f742..fd7b2167103d 100644
--- a/drivers/misc/cardreader/rtsx_pcr.c
+++ b/drivers/misc/cardreader/rtsx_pcr.c
@@ -22,6 +22,7 @@
 #include <asm/unaligned.h>
 
 #include "rtsx_pcr.h"
+#include "rts5261.h"
 
 static bool msi_en = true;
 module_param(msi_en, bool, S_IRUGO | S_IWUSR);
@@ -34,9 +35,6 @@ static struct mfd_cell rtsx_pcr_cells[] = {
 	[RTSX_SD_CARD] = {
 		.name = DRV_NAME_RTSX_PCI_SDMMC,
 	},
-	[RTSX_MS_CARD] = {
-		.name = DRV_NAME_RTSX_PCI_MS,
-	},
 };
 
 static const struct pci_device_id rtsx_pci_ids[] = {
@@ -51,6 +49,7 @@ static const struct pci_device_id rtsx_pci_ids[] = {
 	{ PCI_DEVICE(0x10EC, 0x524A), PCI_CLASS_OTHERS << 16, 0xFF0000 },
 	{ PCI_DEVICE(0x10EC, 0x525A), PCI_CLASS_OTHERS << 16, 0xFF0000 },
 	{ PCI_DEVICE(0x10EC, 0x5260), PCI_CLASS_OTHERS << 16, 0xFF0000 },
+	{ PCI_DEVICE(0x10EC, 0x5261), PCI_CLASS_OTHERS << 16, 0xFF0000 },
 	{ 0, }
 };
 
@@ -438,8 +437,16 @@ static void rtsx_pci_add_sg_tbl(struct rtsx_pcr *pcr,
 
 	if (end)
 		option |= RTSX_SG_END;
-	val = ((u64)addr << 32) | ((u64)len << 12) | option;
 
+	if (PCI_PID(pcr) == PID_5261) {
+		if (len > 0xFFFF)
+			val = ((u64)addr << 32) | (((u64)len & 0xFFFF) << 16)
+				| (((u64)len >> 16) << 6) | option;
+		else
+			val = ((u64)addr << 32) | ((u64)len << 16) | option;
+	} else {
+		val = ((u64)addr << 32) | ((u64)len << 12) | option;
+	}
 	put_unaligned_le64(val, ptr);
 	pcr->sgi++;
 }
@@ -684,7 +691,6 @@ int rtsx_pci_card_pull_ctl_disable(struct rtsx_pcr *pcr, int card)
 	else
 		return -EINVAL;
 
-
 	return rtsx_pci_set_pull_ctl(pcr, tbl);
 }
 EXPORT_SYMBOL_GPL(rtsx_pci_card_pull_ctl_disable);
@@ -735,6 +741,10 @@ int rtsx_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
 		[RTSX_SSC_DEPTH_250K] = SSC_DEPTH_250K,
 	};
 
+	if (PCI_PID(pcr) == PID_5261)
+		return rts5261_pci_switch_clock(pcr, card_clock,
+				ssc_depth, initial_mode, double_clk, vpclk);
+
 	if (initial_mode) {
 		/* We use 250k(around) here, in initial stage */
 		clk_divider = SD_CLK_DIVIDE_128;
@@ -1253,7 +1263,15 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
 	rtsx_pci_enable_bus_int(pcr);
 
 	/* Power on SSC */
-	err = rtsx_pci_write_register(pcr, FPDCTL, SSC_POWER_DOWN, 0);
+	if (PCI_PID(pcr) == PID_5261) {
+		/* Gating real mcu clock */
+		err = rtsx_pci_write_register(pcr, RTS5261_FW_CFG1,
+			RTS5261_MCU_CLOCK_GATING, 0);
+		err = rtsx_pci_write_register(pcr, RTS5261_REG_FPDCTL,
+			SSC_POWER_DOWN, 0);
+	} else {
+		err = rtsx_pci_write_register(pcr, FPDCTL, SSC_POWER_DOWN, 0);
+	}
 	if (err < 0)
 		return err;
 
@@ -1283,7 +1301,12 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
 	/* Enable SSC Clock */
 	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1,
 			0xFF, SSC_8X_EN | SSC_SEL_4M);
-	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2, 0xFF, 0x12);
+	if (PCI_PID(pcr) == PID_5261)
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2, 0xFF,
+			RTS5261_SSC_DEPTH_2M);
+	else
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2, 0xFF, 0x12);
+
 	/* Disable cd_pwr_save */
 	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CHANGE_LINK_STATE, 0x16, 0x10);
 	/* Clear Link Ready Interrupt */
@@ -1314,6 +1337,7 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr)
 	case PID_524A:
 	case PID_525A:
 	case PID_5260:
+	case PID_5261:
 		rtsx_pci_write_register(pcr, PM_CLK_FORCE_CTL, 1, 1);
 		break;
 	default:
@@ -1393,9 +1417,14 @@ static int rtsx_pci_init_chip(struct rtsx_pcr *pcr)
 	case 0x5286:
 		rtl8402_init_params(pcr);
 		break;
+
 	case 0x5260:
 		rts5260_init_params(pcr);
 		break;
+
+	case 0x5261:
+		rts5261_init_params(pcr);
+		break;
 	}
 
 	pcr_dbg(pcr, "PID: 0x%04x, IC version: 0x%02x\n",
diff --git a/drivers/misc/cardreader/rtsx_pcr.h b/drivers/misc/cardreader/rtsx_pcr.h
index 98f729263dc1..ed391df52f4f 100644
--- a/drivers/misc/cardreader/rtsx_pcr.h
+++ b/drivers/misc/cardreader/rtsx_pcr.h
@@ -53,6 +53,7 @@ void rts524a_init_params(struct rtsx_pcr *pcr);
 void rts525a_init_params(struct rtsx_pcr *pcr);
 void rtl8411b_init_params(struct rtsx_pcr *pcr);
 void rts5260_init_params(struct rtsx_pcr *pcr);
+void rts5261_init_params(struct rtsx_pcr *pcr);
 
 static inline u8 map_sd_drive(int idx)
 {
diff --git a/drivers/misc/eeprom/eeprom.c b/drivers/misc/eeprom/eeprom.c
index 2cfe3d4ae144..226b5efa6a77 100644
--- a/drivers/misc/eeprom/eeprom.c
+++ b/drivers/misc/eeprom/eeprom.c
@@ -175,6 +175,10 @@ static int eeprom_probe(struct i2c_client *client,
 		}
 	}
 
+	/* Let the users know they are using deprecated driver */
+	dev_notice(&client->dev,
+		   "eeprom driver is deprecated, please use at24 instead\n");
+
 	/* create the sysfs eeprom file */
 	return sysfs_create_bin_file(&client->dev.kobj, &eeprom_attr);
 }
diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 1b1a794d639d..ae4ee27a63c4 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -32,8 +32,9 @@
 #define FASTRPC_CTX_MAX (256)
 #define FASTRPC_INIT_HANDLE	1
 #define FASTRPC_CTXID_MASK (0xFF0)
-#define INIT_FILELEN_MAX (64 * 1024 * 1024)
+#define INIT_FILELEN_MAX (2 * 1024 * 1024)
 #define FASTRPC_DEVICE_NAME	"fastrpc"
+#define ADSP_MMAP_ADD_PAGES 0x1000
 
 /* Retrives number of input buffers from the scalars parameter */
 #define REMOTE_SCALARS_INBUFS(sc)	(((sc) >> 16) & 0x0ff)
@@ -66,6 +67,8 @@
 /* Remote Method id table */
 #define FASTRPC_RMID_INIT_ATTACH	0
 #define FASTRPC_RMID_INIT_RELEASE	1
+#define FASTRPC_RMID_INIT_MMAP		4
+#define FASTRPC_RMID_INIT_MUNMAP	5
 #define FASTRPC_RMID_INIT_CREATE	6
 #define FASTRPC_RMID_INIT_CREATE_ATTR	7
 #define FASTRPC_RMID_INIT_CREATE_STATIC	8
@@ -89,6 +92,23 @@ struct fastrpc_remote_arg {
 	u64 len;
 };
 
+struct fastrpc_mmap_rsp_msg {
+	u64 vaddr;
+};
+
+struct fastrpc_mmap_req_msg {
+	s32 pgid;
+	u32 flags;
+	u64 vaddr;
+	s32 num;
+};
+
+struct fastrpc_munmap_req_msg {
+	s32 pgid;
+	u64 vaddr;
+	u64 size;
+};
+
 struct fastrpc_msg {
 	int pid;		/* process group id */
 	int tid;		/* thread id */
@@ -123,6 +143,9 @@ struct fastrpc_buf {
 	/* Lock for dma buf attachments */
 	struct mutex lock;
 	struct list_head attachments;
+	/* mmap support */
+	struct list_head node; /* list of user requested mmaps */
+	uintptr_t raddr;
 };
 
 struct fastrpc_dma_buf_attachment {
@@ -192,6 +215,7 @@ struct fastrpc_user {
 	struct list_head user;
 	struct list_head maps;
 	struct list_head pending;
+	struct list_head mmaps;
 
 	struct fastrpc_channel_ctx *cctx;
 	struct fastrpc_session_ctx *sctx;
@@ -269,6 +293,7 @@ static int fastrpc_buf_alloc(struct fastrpc_user *fl, struct device *dev,
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&buf->attachments);
+	INIT_LIST_HEAD(&buf->node);
 	mutex_init(&buf->lock);
 
 	buf->fl = fl;
@@ -276,6 +301,7 @@ static int fastrpc_buf_alloc(struct fastrpc_user *fl, struct device *dev,
 	buf->phys = 0;
 	buf->size = size;
 	buf->dev = dev;
+	buf->raddr = 0;
 
 	buf->virt = dma_alloc_coherent(dev, buf->size, (dma_addr_t *)&buf->phys,
 				       GFP_KERNEL);
@@ -934,8 +960,13 @@ static int fastrpc_internal_invoke(struct fastrpc_user *fl,  u32 kernel,
 	if (err)
 		goto bail;
 
-	/* Wait for remote dsp to respond or time out */
-	err = wait_for_completion_interruptible(&ctx->work);
+	if (kernel) {
+		if (!wait_for_completion_timeout(&ctx->work, 10 * HZ))
+			err = -ETIMEDOUT;
+	} else {
+		err = wait_for_completion_interruptible(&ctx->work);
+	}
+
 	if (err)
 		goto bail;
 
@@ -954,12 +985,13 @@ static int fastrpc_internal_invoke(struct fastrpc_user *fl,  u32 kernel,
 	}
 
 bail:
-	/* We are done with this compute context, remove it from pending list */
-	spin_lock(&fl->lock);
-	list_del(&ctx->node);
-	spin_unlock(&fl->lock);
-	fastrpc_context_put(ctx);
-
+	if (err != -ERESTARTSYS && err != -ETIMEDOUT) {
+		/* We are done with this compute context */
+		spin_lock(&fl->lock);
+		list_del(&ctx->node);
+		spin_unlock(&fl->lock);
+		fastrpc_context_put(ctx);
+	}
 	if (err)
 		dev_dbg(fl->sctx->dev, "Error: Invoke Failed %d\n", err);
 
@@ -1131,6 +1163,7 @@ static int fastrpc_device_release(struct inode *inode, struct file *file)
 	struct fastrpc_channel_ctx *cctx = fl->cctx;
 	struct fastrpc_invoke_ctx *ctx, *n;
 	struct fastrpc_map *map, *m;
+	struct fastrpc_buf *buf, *b;
 	unsigned long flags;
 
 	fastrpc_release_current_dsp_process(fl);
@@ -1152,6 +1185,11 @@ static int fastrpc_device_release(struct inode *inode, struct file *file)
 		fastrpc_map_put(map);
 	}
 
+	list_for_each_entry_safe(buf, b, &fl->mmaps, node) {
+		list_del(&buf->node);
+		fastrpc_buf_free(buf);
+	}
+
 	fastrpc_session_free(cctx, fl->sctx);
 	fastrpc_channel_ctx_put(cctx);
 
@@ -1180,6 +1218,7 @@ static int fastrpc_device_open(struct inode *inode, struct file *filp)
 	mutex_init(&fl->mutex);
 	INIT_LIST_HEAD(&fl->pending);
 	INIT_LIST_HEAD(&fl->maps);
+	INIT_LIST_HEAD(&fl->mmaps);
 	INIT_LIST_HEAD(&fl->user);
 	fl->tgid = current->tgid;
 	fl->cctx = cctx;
@@ -1285,6 +1324,148 @@ static int fastrpc_invoke(struct fastrpc_user *fl, char __user *argp)
 	return err;
 }
 
+static int fastrpc_req_munmap_impl(struct fastrpc_user *fl,
+				   struct fastrpc_req_munmap *req)
+{
+	struct fastrpc_invoke_args args[1] = { [0] = { 0 } };
+	struct fastrpc_buf *buf, *b;
+	struct fastrpc_munmap_req_msg req_msg;
+	struct device *dev = fl->sctx->dev;
+	int err;
+	u32 sc;
+
+	spin_lock(&fl->lock);
+	list_for_each_entry_safe(buf, b, &fl->mmaps, node) {
+		if ((buf->raddr == req->vaddrout) && (buf->size == req->size))
+			break;
+		buf = NULL;
+	}
+	spin_unlock(&fl->lock);
+
+	if (!buf) {
+		dev_err(dev, "mmap not in list\n");
+		return -EINVAL;
+	}
+
+	req_msg.pgid = fl->tgid;
+	req_msg.size = buf->size;
+	req_msg.vaddr = buf->raddr;
+
+	args[0].ptr = (u64) (uintptr_t) &req_msg;
+	args[0].length = sizeof(req_msg);
+
+	sc = FASTRPC_SCALARS(FASTRPC_RMID_INIT_MUNMAP, 1, 0);
+	err = fastrpc_internal_invoke(fl, true, FASTRPC_INIT_HANDLE, sc,
+				      &args[0]);
+	if (!err) {
+		dev_dbg(dev, "unmmap\tpt 0x%09lx OK\n", buf->raddr);
+		spin_lock(&fl->lock);
+		list_del(&buf->node);
+		spin_unlock(&fl->lock);
+		fastrpc_buf_free(buf);
+	} else {
+		dev_err(dev, "unmmap\tpt 0x%09lx ERROR\n", buf->raddr);
+	}
+
+	return err;
+}
+
+static int fastrpc_req_munmap(struct fastrpc_user *fl, char __user *argp)
+{
+	struct fastrpc_req_munmap req;
+
+	if (copy_from_user(&req, argp, sizeof(req)))
+		return -EFAULT;
+
+	return fastrpc_req_munmap_impl(fl, &req);
+}
+
+static int fastrpc_req_mmap(struct fastrpc_user *fl, char __user *argp)
+{
+	struct fastrpc_invoke_args args[3] = { [0 ... 2] = { 0 } };
+	struct fastrpc_buf *buf = NULL;
+	struct fastrpc_mmap_req_msg req_msg;
+	struct fastrpc_mmap_rsp_msg rsp_msg;
+	struct fastrpc_req_munmap req_unmap;
+	struct fastrpc_phy_page pages;
+	struct fastrpc_req_mmap req;
+	struct device *dev = fl->sctx->dev;
+	int err;
+	u32 sc;
+
+	if (copy_from_user(&req, argp, sizeof(req)))
+		return -EFAULT;
+
+	if (req.flags != ADSP_MMAP_ADD_PAGES) {
+		dev_err(dev, "flag not supported 0x%x\n", req.flags);
+		return -EINVAL;
+	}
+
+	if (req.vaddrin) {
+		dev_err(dev, "adding user allocated pages is not supported\n");
+		return -EINVAL;
+	}
+
+	err = fastrpc_buf_alloc(fl, fl->sctx->dev, req.size, &buf);
+	if (err) {
+		dev_err(dev, "failed to allocate buffer\n");
+		return err;
+	}
+
+	req_msg.pgid = fl->tgid;
+	req_msg.flags = req.flags;
+	req_msg.vaddr = req.vaddrin;
+	req_msg.num = sizeof(pages);
+
+	args[0].ptr = (u64) (uintptr_t) &req_msg;
+	args[0].length = sizeof(req_msg);
+
+	pages.addr = buf->phys;
+	pages.size = buf->size;
+
+	args[1].ptr = (u64) (uintptr_t) &pages;
+	args[1].length = sizeof(pages);
+
+	args[2].ptr = (u64) (uintptr_t) &rsp_msg;
+	args[2].length = sizeof(rsp_msg);
+
+	sc = FASTRPC_SCALARS(FASTRPC_RMID_INIT_MMAP, 2, 1);
+	err = fastrpc_internal_invoke(fl, true, FASTRPC_INIT_HANDLE, sc,
+				      &args[0]);
+	if (err) {
+		dev_err(dev, "mmap error (len 0x%08llx)\n", buf->size);
+		goto err_invoke;
+	}
+
+	/* update the buffer to be able to deallocate the memory on the DSP */
+	buf->raddr = (uintptr_t) rsp_msg.vaddr;
+
+	/* let the client know the address to use */
+	req.vaddrout = rsp_msg.vaddr;
+
+	spin_lock(&fl->lock);
+	list_add_tail(&buf->node, &fl->mmaps);
+	spin_unlock(&fl->lock);
+
+	if (copy_to_user((void __user *)argp, &req, sizeof(req))) {
+		/* unmap the memory and release the buffer */
+		req_unmap.vaddrout = buf->raddr;
+		req_unmap.size = buf->size;
+		fastrpc_req_munmap_impl(fl, &req_unmap);
+		return -EFAULT;
+	}
+
+	dev_dbg(dev, "mmap\t\tpt 0x%09lx OK [len 0x%08llx]\n",
+		buf->raddr, buf->size);
+
+	return 0;
+
+err_invoke:
+	fastrpc_buf_free(buf);
+
+	return err;
+}
+
 static long fastrpc_device_ioctl(struct file *file, unsigned int cmd,
 				 unsigned long arg)
 {
@@ -1305,6 +1486,12 @@ static long fastrpc_device_ioctl(struct file *file, unsigned int cmd,
 	case FASTRPC_IOCTL_ALLOC_DMA_BUFF:
 		err = fastrpc_dmabuf_alloc(fl, argp);
 		break;
+	case FASTRPC_IOCTL_MMAP:
+		err = fastrpc_req_mmap(fl, argp);
+		break;
+	case FASTRPC_IOCTL_MUNMAP:
+		err = fastrpc_req_munmap(fl, argp);
+		break;
 	default:
 		err = -ENOTTY;
 		break;
@@ -1430,8 +1617,8 @@ static int fastrpc_rpmsg_probe(struct rpmsg_device *rpdev)
 		return -ENOMEM;
 
 	data->miscdev.minor = MISC_DYNAMIC_MINOR;
-	data->miscdev.name = kasprintf(GFP_KERNEL, "fastrpc-%s",
-				domains[domain_id]);
+	data->miscdev.name = devm_kasprintf(rdev, GFP_KERNEL, "fastrpc-%s",
+					    domains[domain_id]);
 	data->miscdev.fops = &fastrpc_fops;
 	err = misc_register(&data->miscdev);
 	if (err)
diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c
index a9ac045dcfde..8850f475a413 100644
--- a/drivers/misc/habanalabs/command_submission.c
+++ b/drivers/misc/habanalabs/command_submission.c
@@ -65,6 +65,18 @@ static void cs_put(struct hl_cs *cs)
 	kref_put(&cs->refcount, cs_do_release);
 }
 
+static bool is_cb_patched(struct hl_device *hdev, struct hl_cs_job *job)
+{
+	/*
+	 * Patched CB is created for external queues jobs, and for H/W queues
+	 * jobs if the user CB was allocated by driver and MMU is disabled.
+	 */
+	return (job->queue_type == QUEUE_TYPE_EXT ||
+			(job->queue_type == QUEUE_TYPE_HW &&
+					job->is_kernel_allocated_cb &&
+					!hdev->mmu_enable));
+}
+
 /*
  * cs_parser - parse the user command submission
  *
@@ -91,11 +103,13 @@ static int cs_parser(struct hl_fpriv *hpriv, struct hl_cs_job *job)
 	parser.patched_cb = NULL;
 	parser.user_cb = job->user_cb;
 	parser.user_cb_size = job->user_cb_size;
-	parser.ext_queue = job->ext_queue;
+	parser.queue_type = job->queue_type;
+	parser.is_kernel_allocated_cb = job->is_kernel_allocated_cb;
 	job->patched_cb = NULL;
 
 	rc = hdev->asic_funcs->cs_parser(hdev, &parser);
-	if (job->ext_queue) {
+
+	if (is_cb_patched(hdev, job)) {
 		if (!rc) {
 			job->patched_cb = parser.patched_cb;
 			job->job_cb_size = parser.patched_cb_size;
@@ -124,7 +138,7 @@ static void free_job(struct hl_device *hdev, struct hl_cs_job *job)
 {
 	struct hl_cs *cs = job->cs;
 
-	if (job->ext_queue) {
+	if (is_cb_patched(hdev, job)) {
 		hl_userptr_delete_list(hdev, &job->userptr_list);
 
 		/*
@@ -140,6 +154,19 @@ static void free_job(struct hl_device *hdev, struct hl_cs_job *job)
 		}
 	}
 
+	/* For H/W queue jobs, if a user CB was allocated by driver and MMU is
+	 * enabled, the user CB isn't released in cs_parser() and thus should be
+	 * released here.
+	 */
+	if (job->queue_type == QUEUE_TYPE_HW &&
+			job->is_kernel_allocated_cb && hdev->mmu_enable) {
+		spin_lock(&job->user_cb->lock);
+		job->user_cb->cs_cnt--;
+		spin_unlock(&job->user_cb->lock);
+
+		hl_cb_put(job->user_cb);
+	}
+
 	/*
 	 * This is the only place where there can be multiple threads
 	 * modifying the list at the same time
@@ -150,7 +177,8 @@ static void free_job(struct hl_device *hdev, struct hl_cs_job *job)
 
 	hl_debugfs_remove_job(hdev, job);
 
-	if (job->ext_queue)
+	if (job->queue_type == QUEUE_TYPE_EXT ||
+			job->queue_type == QUEUE_TYPE_HW)
 		cs_put(cs);
 
 	kfree(job);
@@ -387,18 +415,13 @@ static void job_wq_completion(struct work_struct *work)
 	free_job(hdev, job);
 }
 
-static struct hl_cb *validate_queue_index(struct hl_device *hdev,
-					struct hl_cb_mgr *cb_mgr,
-					struct hl_cs_chunk *chunk,
-					bool *ext_queue)
+static int validate_queue_index(struct hl_device *hdev,
+				struct hl_cs_chunk *chunk,
+				enum hl_queue_type *queue_type,
+				bool *is_kernel_allocated_cb)
 {
 	struct asic_fixed_properties *asic = &hdev->asic_prop;
 	struct hw_queue_properties *hw_queue_prop;
-	u32 cb_handle;
-	struct hl_cb *cb;
-
-	/* Assume external queue */
-	*ext_queue = true;
 
 	hw_queue_prop = &asic->hw_queues_props[chunk->queue_index];
 
@@ -406,20 +429,29 @@ static struct hl_cb *validate_queue_index(struct hl_device *hdev,
 			(hw_queue_prop->type == QUEUE_TYPE_NA)) {
 		dev_err(hdev->dev, "Queue index %d is invalid\n",
 			chunk->queue_index);
-		return NULL;
+		return -EINVAL;
 	}
 
 	if (hw_queue_prop->driver_only) {
 		dev_err(hdev->dev,
 			"Queue index %d is restricted for the kernel driver\n",
 			chunk->queue_index);
-		return NULL;
-	} else if (hw_queue_prop->type == QUEUE_TYPE_INT) {
-		*ext_queue = false;
-		return (struct hl_cb *) (uintptr_t) chunk->cb_handle;
+		return -EINVAL;
 	}
 
-	/* Retrieve CB object */
+	*queue_type = hw_queue_prop->type;
+	*is_kernel_allocated_cb = !!hw_queue_prop->requires_kernel_cb;
+
+	return 0;
+}
+
+static struct hl_cb *get_cb_from_cs_chunk(struct hl_device *hdev,
+					struct hl_cb_mgr *cb_mgr,
+					struct hl_cs_chunk *chunk)
+{
+	struct hl_cb *cb;
+	u32 cb_handle;
+
 	cb_handle = (u32) (chunk->cb_handle >> PAGE_SHIFT);
 
 	cb = hl_cb_get(hdev, cb_mgr, cb_handle);
@@ -444,7 +476,8 @@ release_cb:
 	return NULL;
 }
 
-struct hl_cs_job *hl_cs_allocate_job(struct hl_device *hdev, bool ext_queue)
+struct hl_cs_job *hl_cs_allocate_job(struct hl_device *hdev,
+		enum hl_queue_type queue_type, bool is_kernel_allocated_cb)
 {
 	struct hl_cs_job *job;
 
@@ -452,12 +485,14 @@ struct hl_cs_job *hl_cs_allocate_job(struct hl_device *hdev, bool ext_queue)
 	if (!job)
 		return NULL;
 
-	job->ext_queue = ext_queue;
+	job->queue_type = queue_type;
+	job->is_kernel_allocated_cb = is_kernel_allocated_cb;
 
-	if (job->ext_queue) {
+	if (is_cb_patched(hdev, job))
 		INIT_LIST_HEAD(&job->userptr_list);
+
+	if (job->queue_type == QUEUE_TYPE_EXT)
 		INIT_WORK(&job->finish_work, job_wq_completion);
-	}
 
 	return job;
 }
@@ -470,7 +505,7 @@ static int _hl_cs_ioctl(struct hl_fpriv *hpriv, void __user *chunks,
 	struct hl_cs_job *job;
 	struct hl_cs *cs;
 	struct hl_cb *cb;
-	bool ext_queue_present = false;
+	bool int_queues_only = true;
 	u32 size_to_copy;
 	int rc, i, parse_cnt;
 
@@ -514,23 +549,33 @@ static int _hl_cs_ioctl(struct hl_fpriv *hpriv, void __user *chunks,
 	/* Validate ALL the CS chunks before submitting the CS */
 	for (i = 0, parse_cnt = 0 ; i < num_chunks ; i++, parse_cnt++) {
 		struct hl_cs_chunk *chunk = &cs_chunk_array[i];
-		bool ext_queue;
+		enum hl_queue_type queue_type;
+		bool is_kernel_allocated_cb;
+
+		rc = validate_queue_index(hdev, chunk, &queue_type,
+						&is_kernel_allocated_cb);
+		if (rc)
+			goto free_cs_object;
 
-		cb = validate_queue_index(hdev, &hpriv->cb_mgr, chunk,
-					&ext_queue);
-		if (ext_queue) {
-			ext_queue_present = true;
+		if (is_kernel_allocated_cb) {
+			cb = get_cb_from_cs_chunk(hdev, &hpriv->cb_mgr, chunk);
 			if (!cb) {
 				rc = -EINVAL;
 				goto free_cs_object;
 			}
+		} else {
+			cb = (struct hl_cb *) (uintptr_t) chunk->cb_handle;
 		}
 
-		job = hl_cs_allocate_job(hdev, ext_queue);
+		if (queue_type == QUEUE_TYPE_EXT || queue_type == QUEUE_TYPE_HW)
+			int_queues_only = false;
+
+		job = hl_cs_allocate_job(hdev, queue_type,
+						is_kernel_allocated_cb);
 		if (!job) {
 			dev_err(hdev->dev, "Failed to allocate a new job\n");
 			rc = -ENOMEM;
-			if (ext_queue)
+			if (is_kernel_allocated_cb)
 				goto release_cb;
 			else
 				goto free_cs_object;
@@ -540,7 +585,7 @@ static int _hl_cs_ioctl(struct hl_fpriv *hpriv, void __user *chunks,
 		job->cs = cs;
 		job->user_cb = cb;
 		job->user_cb_size = chunk->cb_size;
-		if (job->ext_queue)
+		if (is_kernel_allocated_cb)
 			job->job_cb_size = cb->size;
 		else
 			job->job_cb_size = chunk->cb_size;
@@ -553,10 +598,11 @@ static int _hl_cs_ioctl(struct hl_fpriv *hpriv, void __user *chunks,
 		/*
 		 * Increment CS reference. When CS reference is 0, CS is
 		 * done and can be signaled to user and free all its resources
-		 * Only increment for JOB on external queues, because only
-		 * for those JOBs we get completion
+		 * Only increment for JOB on external or H/W queues, because
+		 * only for those JOBs we get completion
 		 */
-		if (job->ext_queue)
+		if (job->queue_type == QUEUE_TYPE_EXT ||
+				job->queue_type == QUEUE_TYPE_HW)
 			cs_get(cs);
 
 		hl_debugfs_add_job(hdev, job);
@@ -570,9 +616,9 @@ static int _hl_cs_ioctl(struct hl_fpriv *hpriv, void __user *chunks,
 		}
 	}
 
-	if (!ext_queue_present) {
+	if (int_queues_only) {
 		dev_err(hdev->dev,
-			"Reject CS %d.%llu because no external queues jobs\n",
+			"Reject CS %d.%llu because only internal queues jobs are present\n",
 			cs->ctx->asid, cs->sequence);
 		rc = -EINVAL;
 		goto free_cs_object;
@@ -580,9 +626,10 @@ static int _hl_cs_ioctl(struct hl_fpriv *hpriv, void __user *chunks,
 
 	rc = hl_hw_queue_schedule_cs(cs);
 	if (rc) {
-		dev_err(hdev->dev,
-			"Failed to submit CS %d.%llu to H/W queues, error %d\n",
-			cs->ctx->asid, cs->sequence, rc);
+		if (rc != -EAGAIN)
+			dev_err(hdev->dev,
+				"Failed to submit CS %d.%llu to H/W queues, error %d\n",
+				cs->ctx->asid, cs->sequence, rc);
 		goto free_cs_object;
 	}
 
diff --git a/drivers/misc/habanalabs/debugfs.c b/drivers/misc/habanalabs/debugfs.c
index 87f37ac31ccd..20413e350343 100644
--- a/drivers/misc/habanalabs/debugfs.c
+++ b/drivers/misc/habanalabs/debugfs.c
@@ -307,45 +307,57 @@ static inline u64 get_hop0_addr(struct hl_ctx *ctx)
 			(ctx->asid * ctx->hdev->asic_prop.mmu_hop_table_size);
 }
 
-static inline u64 get_hop0_pte_addr(struct hl_ctx *ctx, u64 hop_addr,
-		u64 virt_addr)
+static inline u64 get_hopN_pte_addr(struct hl_ctx *ctx, u64 hop_addr,
+					u64 virt_addr, u64 mask, u64 shift)
 {
 	return hop_addr + ctx->hdev->asic_prop.mmu_pte_size *
-			((virt_addr & HOP0_MASK) >> HOP0_SHIFT);
+			((virt_addr & mask) >> shift);
 }
 
-static inline u64 get_hop1_pte_addr(struct hl_ctx *ctx, u64 hop_addr,
-		u64 virt_addr)
+static inline u64 get_hop0_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_specs,
+					u64 hop_addr, u64 vaddr)
 {
-	return hop_addr + ctx->hdev->asic_prop.mmu_pte_size *
-			((virt_addr & HOP1_MASK) >> HOP1_SHIFT);
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_specs->hop0_mask,
+					mmu_specs->hop0_shift);
 }
 
-static inline u64 get_hop2_pte_addr(struct hl_ctx *ctx, u64 hop_addr,
-		u64 virt_addr)
+static inline u64 get_hop1_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_specs,
+					u64 hop_addr, u64 vaddr)
 {
-	return hop_addr + ctx->hdev->asic_prop.mmu_pte_size *
-			((virt_addr & HOP2_MASK) >> HOP2_SHIFT);
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_specs->hop1_mask,
+					mmu_specs->hop1_shift);
 }
 
-static inline u64 get_hop3_pte_addr(struct hl_ctx *ctx, u64 hop_addr,
-		u64 virt_addr)
+static inline u64 get_hop2_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_specs,
+					u64 hop_addr, u64 vaddr)
 {
-	return hop_addr + ctx->hdev->asic_prop.mmu_pte_size *
-			((virt_addr & HOP3_MASK) >> HOP3_SHIFT);
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_specs->hop2_mask,
+					mmu_specs->hop2_shift);
 }
 
-static inline u64 get_hop4_pte_addr(struct hl_ctx *ctx, u64 hop_addr,
-		u64 virt_addr)
+static inline u64 get_hop3_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_specs,
+					u64 hop_addr, u64 vaddr)
 {
-	return hop_addr + ctx->hdev->asic_prop.mmu_pte_size *
-			((virt_addr & HOP4_MASK) >> HOP4_SHIFT);
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_specs->hop3_mask,
+					mmu_specs->hop3_shift);
+}
+
+static inline u64 get_hop4_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_specs,
+					u64 hop_addr, u64 vaddr)
+{
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_specs->hop4_mask,
+					mmu_specs->hop4_shift);
 }
 
 static inline u64 get_next_hop_addr(u64 curr_pte)
 {
 	if (curr_pte & PAGE_PRESENT_MASK)
-		return curr_pte & PHYS_ADDR_MASK;
+		return curr_pte & HOP_PHYS_ADDR_MASK;
 	else
 		return ULLONG_MAX;
 }
@@ -355,7 +367,10 @@ static int mmu_show(struct seq_file *s, void *data)
 	struct hl_debugfs_entry *entry = s->private;
 	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
 	struct hl_device *hdev = dev_entry->hdev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct hl_mmu_properties *mmu_prop;
 	struct hl_ctx *ctx;
+	bool is_dram_addr;
 
 	u64 hop0_addr = 0, hop0_pte_addr = 0, hop0_pte = 0,
 		hop1_addr = 0, hop1_pte_addr = 0, hop1_pte = 0,
@@ -377,33 +392,39 @@ static int mmu_show(struct seq_file *s, void *data)
 		return 0;
 	}
 
+	is_dram_addr = hl_mem_area_inside_range(virt_addr, prop->dmmu.page_size,
+				prop->va_space_dram_start_address,
+				prop->va_space_dram_end_address);
+
+	mmu_prop = is_dram_addr ? &prop->dmmu : &prop->pmmu;
+
 	mutex_lock(&ctx->mmu_lock);
 
 	/* the following lookup is copied from unmap() in mmu.c */
 
 	hop0_addr = get_hop0_addr(ctx);
-	hop0_pte_addr = get_hop0_pte_addr(ctx, hop0_addr, virt_addr);
+	hop0_pte_addr = get_hop0_pte_addr(ctx, mmu_prop, hop0_addr, virt_addr);
 	hop0_pte = hdev->asic_funcs->read_pte(hdev, hop0_pte_addr);
 	hop1_addr = get_next_hop_addr(hop0_pte);
 
 	if (hop1_addr == ULLONG_MAX)
 		goto not_mapped;
 
-	hop1_pte_addr = get_hop1_pte_addr(ctx, hop1_addr, virt_addr);
+	hop1_pte_addr = get_hop1_pte_addr(ctx, mmu_prop, hop1_addr, virt_addr);
 	hop1_pte = hdev->asic_funcs->read_pte(hdev, hop1_pte_addr);
 	hop2_addr = get_next_hop_addr(hop1_pte);
 
 	if (hop2_addr == ULLONG_MAX)
 		goto not_mapped;
 
-	hop2_pte_addr = get_hop2_pte_addr(ctx, hop2_addr, virt_addr);
+	hop2_pte_addr = get_hop2_pte_addr(ctx, mmu_prop, hop2_addr, virt_addr);
 	hop2_pte = hdev->asic_funcs->read_pte(hdev, hop2_pte_addr);
 	hop3_addr = get_next_hop_addr(hop2_pte);
 
 	if (hop3_addr == ULLONG_MAX)
 		goto not_mapped;
 
-	hop3_pte_addr = get_hop3_pte_addr(ctx, hop3_addr, virt_addr);
+	hop3_pte_addr = get_hop3_pte_addr(ctx, mmu_prop, hop3_addr, virt_addr);
 	hop3_pte = hdev->asic_funcs->read_pte(hdev, hop3_pte_addr);
 
 	if (!(hop3_pte & LAST_MASK)) {
@@ -412,7 +433,8 @@ static int mmu_show(struct seq_file *s, void *data)
 		if (hop4_addr == ULLONG_MAX)
 			goto not_mapped;
 
-		hop4_pte_addr = get_hop4_pte_addr(ctx, hop4_addr, virt_addr);
+		hop4_pte_addr = get_hop4_pte_addr(ctx, mmu_prop, hop4_addr,
+							virt_addr);
 		hop4_pte = hdev->asic_funcs->read_pte(hdev, hop4_pte_addr);
 		if (!(hop4_pte & PAGE_PRESENT_MASK))
 			goto not_mapped;
@@ -506,6 +528,12 @@ static int engines_show(struct seq_file *s, void *data)
 	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
 	struct hl_device *hdev = dev_entry->hdev;
 
+	if (atomic_read(&hdev->in_reset)) {
+		dev_warn_ratelimited(hdev->dev,
+				"Can't check device idle during reset\n");
+		return 0;
+	}
+
 	hdev->asic_funcs->is_device_idle(hdev, NULL, s);
 
 	return 0;
@@ -534,41 +562,50 @@ static int device_va_to_pa(struct hl_device *hdev, u64 virt_addr,
 				u64 *phys_addr)
 {
 	struct hl_ctx *ctx = hdev->compute_ctx;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct hl_mmu_properties *mmu_prop;
 	u64 hop_addr, hop_pte_addr, hop_pte;
-	u64 offset_mask = HOP4_MASK | OFFSET_MASK;
+	u64 offset_mask = HOP4_MASK | FLAGS_MASK;
 	int rc = 0;
+	bool is_dram_addr;
 
 	if (!ctx) {
 		dev_err(hdev->dev, "no ctx available\n");
 		return -EINVAL;
 	}
 
+	is_dram_addr = hl_mem_area_inside_range(virt_addr, prop->dmmu.page_size,
+				prop->va_space_dram_start_address,
+				prop->va_space_dram_end_address);
+
+	mmu_prop = is_dram_addr ? &prop->dmmu : &prop->pmmu;
+
 	mutex_lock(&ctx->mmu_lock);
 
 	/* hop 0 */
 	hop_addr = get_hop0_addr(ctx);
-	hop_pte_addr = get_hop0_pte_addr(ctx, hop_addr, virt_addr);
+	hop_pte_addr = get_hop0_pte_addr(ctx, mmu_prop, hop_addr, virt_addr);
 	hop_pte = hdev->asic_funcs->read_pte(hdev, hop_pte_addr);
 
 	/* hop 1 */
 	hop_addr = get_next_hop_addr(hop_pte);
 	if (hop_addr == ULLONG_MAX)
 		goto not_mapped;
-	hop_pte_addr = get_hop1_pte_addr(ctx, hop_addr, virt_addr);
+	hop_pte_addr = get_hop1_pte_addr(ctx, mmu_prop, hop_addr, virt_addr);
 	hop_pte = hdev->asic_funcs->read_pte(hdev, hop_pte_addr);
 
 	/* hop 2 */
 	hop_addr = get_next_hop_addr(hop_pte);
 	if (hop_addr == ULLONG_MAX)
 		goto not_mapped;
-	hop_pte_addr = get_hop2_pte_addr(ctx, hop_addr, virt_addr);
+	hop_pte_addr = get_hop2_pte_addr(ctx, mmu_prop, hop_addr, virt_addr);
 	hop_pte = hdev->asic_funcs->read_pte(hdev, hop_pte_addr);
 
 	/* hop 3 */
 	hop_addr = get_next_hop_addr(hop_pte);
 	if (hop_addr == ULLONG_MAX)
 		goto not_mapped;
-	hop_pte_addr = get_hop3_pte_addr(ctx, hop_addr, virt_addr);
+	hop_pte_addr = get_hop3_pte_addr(ctx, mmu_prop, hop_addr, virt_addr);
 	hop_pte = hdev->asic_funcs->read_pte(hdev, hop_pte_addr);
 
 	if (!(hop_pte & LAST_MASK)) {
@@ -576,10 +613,11 @@ static int device_va_to_pa(struct hl_device *hdev, u64 virt_addr,
 		hop_addr = get_next_hop_addr(hop_pte);
 		if (hop_addr == ULLONG_MAX)
 			goto not_mapped;
-		hop_pte_addr = get_hop4_pte_addr(ctx, hop_addr, virt_addr);
+		hop_pte_addr = get_hop4_pte_addr(ctx, mmu_prop, hop_addr,
+							virt_addr);
 		hop_pte = hdev->asic_funcs->read_pte(hdev, hop_pte_addr);
 
-		offset_mask = OFFSET_MASK;
+		offset_mask = FLAGS_MASK;
 	}
 
 	if (!(hop_pte & PAGE_PRESENT_MASK))
@@ -608,6 +646,11 @@ static ssize_t hl_data_read32(struct file *f, char __user *buf,
 	u32 val;
 	ssize_t rc;
 
+	if (atomic_read(&hdev->in_reset)) {
+		dev_warn_ratelimited(hdev->dev, "Can't read during reset\n");
+		return 0;
+	}
+
 	if (*ppos)
 		return 0;
 
@@ -637,6 +680,11 @@ static ssize_t hl_data_write32(struct file *f, const char __user *buf,
 	u32 value;
 	ssize_t rc;
 
+	if (atomic_read(&hdev->in_reset)) {
+		dev_warn_ratelimited(hdev->dev, "Can't write during reset\n");
+		return 0;
+	}
+
 	rc = kstrtouint_from_user(buf, count, 16, &value);
 	if (rc)
 		return rc;
diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c
index 459fee70a597..b155e9549076 100644
--- a/drivers/misc/habanalabs/device.c
+++ b/drivers/misc/habanalabs/device.c
@@ -42,12 +42,10 @@ static void hpriv_release(struct kref *ref)
 {
 	struct hl_fpriv *hpriv;
 	struct hl_device *hdev;
-	struct hl_ctx *ctx;
 
 	hpriv = container_of(ref, struct hl_fpriv, refcount);
 
 	hdev = hpriv->hdev;
-	ctx = hpriv->ctx;
 
 	put_pid(hpriv->taskpid);
 
@@ -889,13 +887,19 @@ again:
 	/* Go over all the queues, release all CS and their jobs */
 	hl_cs_rollback_all(hdev);
 
-	/* Kill processes here after CS rollback. This is because the process
-	 * can't really exit until all its CSs are done, which is what we
-	 * do in cs rollback
-	 */
-	if (from_hard_reset_thread)
+	if (hard_reset) {
+		/* Kill processes here after CS rollback. This is because the
+		 * process can't really exit until all its CSs are done, which
+		 * is what we do in cs rollback
+		 */
 		device_kill_open_processes(hdev);
 
+		/* Flush the Event queue workers to make sure no other thread is
+		 * reading or writing to registers during the reset
+		 */
+		flush_workqueue(hdev->eq_wq);
+	}
+
 	/* Release kernel context */
 	if ((hard_reset) && (hl_ctx_put(hdev->kernel_ctx) == 1))
 		hdev->kernel_ctx = NULL;
diff --git a/drivers/misc/habanalabs/firmware_if.c b/drivers/misc/habanalabs/firmware_if.c
index ea2ca67fbfbf..f5bd03171dac 100644
--- a/drivers/misc/habanalabs/firmware_if.c
+++ b/drivers/misc/habanalabs/firmware_if.c
@@ -143,10 +143,7 @@ int hl_fw_test_cpu_queue(struct hl_device *hdev)
 			sizeof(test_pkt), HL_DEVICE_TIMEOUT_USEC, &result);
 
 	if (!rc) {
-		if (result == ARMCP_PACKET_FENCE_VAL)
-			dev_info(hdev->dev,
-				"queue test on CPU queue succeeded\n");
-		else
+		if (result != ARMCP_PACKET_FENCE_VAL)
 			dev_err(hdev->dev,
 				"CPU queue test failed (0x%08lX)\n", result);
 	} else {
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index 6fba14b81f90..c8d16aa4382c 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -72,6 +72,9 @@
  *
  */
 
+#define GOYA_UBOOT_FW_FILE	"habanalabs/goya/goya-u-boot.bin"
+#define GOYA_LINUX_FW_FILE	"habanalabs/goya/goya-fit.itb"
+
 #define GOYA_MMU_REGS_NUM		63
 
 #define GOYA_DMA_POOL_BLK_SIZE		0x100		/* 256 bytes */
@@ -337,17 +340,20 @@ void goya_get_fixed_properties(struct hl_device *hdev)
 	for (i = 0 ; i < NUMBER_OF_EXT_HW_QUEUES ; i++) {
 		prop->hw_queues_props[i].type = QUEUE_TYPE_EXT;
 		prop->hw_queues_props[i].driver_only = 0;
+		prop->hw_queues_props[i].requires_kernel_cb = 1;
 	}
 
 	for (; i < NUMBER_OF_EXT_HW_QUEUES + NUMBER_OF_CPU_HW_QUEUES ; i++) {
 		prop->hw_queues_props[i].type = QUEUE_TYPE_CPU;
 		prop->hw_queues_props[i].driver_only = 1;
+		prop->hw_queues_props[i].requires_kernel_cb = 0;
 	}
 
 	for (; i < NUMBER_OF_EXT_HW_QUEUES + NUMBER_OF_CPU_HW_QUEUES +
 			NUMBER_OF_INT_HW_QUEUES; i++) {
 		prop->hw_queues_props[i].type = QUEUE_TYPE_INT;
 		prop->hw_queues_props[i].driver_only = 0;
+		prop->hw_queues_props[i].requires_kernel_cb = 0;
 	}
 
 	for (; i < HL_MAX_QUEUES; i++)
@@ -377,6 +383,23 @@ void goya_get_fixed_properties(struct hl_device *hdev)
 	prop->mmu_hop0_tables_total_size = HOP0_TABLES_TOTAL_SIZE;
 	prop->dram_page_size = PAGE_SIZE_2MB;
 
+	prop->dmmu.hop0_shift = HOP0_SHIFT;
+	prop->dmmu.hop1_shift = HOP1_SHIFT;
+	prop->dmmu.hop2_shift = HOP2_SHIFT;
+	prop->dmmu.hop3_shift = HOP3_SHIFT;
+	prop->dmmu.hop4_shift = HOP4_SHIFT;
+	prop->dmmu.hop0_mask = HOP0_MASK;
+	prop->dmmu.hop1_mask = HOP1_MASK;
+	prop->dmmu.hop2_mask = HOP2_MASK;
+	prop->dmmu.hop3_mask = HOP3_MASK;
+	prop->dmmu.hop4_mask = HOP4_MASK;
+	prop->dmmu.huge_page_size = PAGE_SIZE_2MB;
+
+	/* No difference between PMMU and DMMU except of page size */
+	memcpy(&prop->pmmu, &prop->dmmu, sizeof(prop->dmmu));
+	prop->dmmu.page_size = PAGE_SIZE_2MB;
+	prop->pmmu.page_size = PAGE_SIZE_4KB;
+
 	prop->va_space_host_start_address = VA_HOST_SPACE_START;
 	prop->va_space_host_end_address = VA_HOST_SPACE_END;
 	prop->va_space_dram_start_address = VA_DDR_SPACE_START;
@@ -393,6 +416,9 @@ void goya_get_fixed_properties(struct hl_device *hdev)
 	prop->tpc_enabled_mask = TPC_ENABLED_MASK;
 	prop->pcie_dbi_base_address = mmPCIE_DBI_BASE;
 	prop->pcie_aux_dbi_reg_addr = CFG_BASE + mmPCIE_AUX_DBI;
+
+	strncpy(prop->armcp_info.card_name, GOYA_DEFAULT_CARD_NAME,
+		CARD_NAME_MAX_LEN);
 }
 
 /*
@@ -1454,6 +1480,9 @@ static void goya_init_golden_registers(struct hl_device *hdev)
 				1 << TPC0_NRTR_SCRAMB_EN_VAL_SHIFT);
 		WREG32(mmTPC0_NRTR_NON_LIN_SCRAMB + offset,
 				1 << TPC0_NRTR_NON_LIN_SCRAMB_EN_SHIFT);
+
+		WREG32_FIELD(TPC0_CFG_MSS_CONFIG, offset,
+				ICACHE_FETCH_LINE_NUM, 2);
 	}
 
 	WREG32(mmDMA_NRTR_SCRAMB_EN, 1 << DMA_NRTR_SCRAMB_EN_VAL_SHIFT);
@@ -1533,7 +1562,6 @@ static void goya_init_mme_cmdq(struct hl_device *hdev)
 	u32 mtr_base_lo, mtr_base_hi;
 	u32 so_base_lo, so_base_hi;
 	u32 gic_base_lo, gic_base_hi;
-	u64 qman_base_addr;
 
 	mtr_base_lo = lower_32_bits(CFG_BASE + mmSYNC_MNGR_MON_PAY_ADDRL_0);
 	mtr_base_hi = upper_32_bits(CFG_BASE + mmSYNC_MNGR_MON_PAY_ADDRL_0);
@@ -1545,9 +1573,6 @@ static void goya_init_mme_cmdq(struct hl_device *hdev)
 	gic_base_hi =
 		upper_32_bits(CFG_BASE + mmGIC_DISTRIBUTOR__5_GICD_SETSPI_NSR);
 
-	qman_base_addr = hdev->asic_prop.sram_base_address +
-				MME_QMAN_BASE_OFFSET;
-
 	WREG32(mmMME_CMDQ_CP_MSG_BASE0_ADDR_LO, mtr_base_lo);
 	WREG32(mmMME_CMDQ_CP_MSG_BASE0_ADDR_HI, mtr_base_hi);
 	WREG32(mmMME_CMDQ_CP_MSG_BASE1_ADDR_LO,	so_base_lo);
@@ -2141,13 +2166,11 @@ static void goya_halt_engines(struct hl_device *hdev, bool hard_reset)
  */
 static int goya_push_uboot_to_device(struct hl_device *hdev)
 {
-	char fw_name[200];
 	void __iomem *dst;
 
-	snprintf(fw_name, sizeof(fw_name), "habanalabs/goya/goya-u-boot.bin");
 	dst = hdev->pcie_bar[SRAM_CFG_BAR_ID] + UBOOT_FW_OFFSET;
 
-	return hl_fw_push_fw_to_device(hdev, fw_name, dst);
+	return hl_fw_push_fw_to_device(hdev, GOYA_UBOOT_FW_FILE, dst);
 }
 
 /*
@@ -2160,13 +2183,11 @@ static int goya_push_uboot_to_device(struct hl_device *hdev)
  */
 static int goya_push_linux_to_device(struct hl_device *hdev)
 {
-	char fw_name[200];
 	void __iomem *dst;
 
-	snprintf(fw_name, sizeof(fw_name), "habanalabs/goya/goya-fit.itb");
 	dst = hdev->pcie_bar[DDR_BAR_ID] + LINUX_FW_OFFSET;
 
-	return hl_fw_push_fw_to_device(hdev, fw_name, dst);
+	return hl_fw_push_fw_to_device(hdev, GOYA_LINUX_FW_FILE, dst);
 }
 
 static int goya_pldm_init_cpu(struct hl_device *hdev)
@@ -2291,6 +2312,10 @@ static int goya_init_cpu(struct hl_device *hdev, u32 cpu_timeout)
 		10000,
 		cpu_timeout);
 
+	/* Read U-Boot version now in case we will later fail */
+	goya_read_device_fw_version(hdev, FW_COMP_UBOOT);
+	goya_read_device_fw_version(hdev, FW_COMP_PREBOOT);
+
 	if (rc) {
 		dev_err(hdev->dev, "Error in ARM u-boot!");
 		switch (status) {
@@ -2328,6 +2353,11 @@ static int goya_init_cpu(struct hl_device *hdev, u32 cpu_timeout)
 				"ARM status %d - u-boot stopped by user\n",
 				status);
 			break;
+		case CPU_BOOT_STATUS_TS_INIT_FAIL:
+			dev_err(hdev->dev,
+				"ARM status %d - Thermal Sensor initialization failed\n",
+				status);
+			break;
 		default:
 			dev_err(hdev->dev,
 				"ARM status %d - Invalid status code\n",
@@ -2337,10 +2367,6 @@ static int goya_init_cpu(struct hl_device *hdev, u32 cpu_timeout)
 		return -EIO;
 	}
 
-	/* Read U-Boot version now in case we will later fail */
-	goya_read_device_fw_version(hdev, FW_COMP_UBOOT);
-	goya_read_device_fw_version(hdev, FW_COMP_PREBOOT);
-
 	if (!hdev->fw_loading) {
 		dev_info(hdev->dev, "Skip loading FW\n");
 		goto out;
@@ -2453,7 +2479,8 @@ int goya_mmu_init(struct hl_device *hdev)
 	WREG32_AND(mmSTLB_STLB_FEATURE_EN,
 			(~STLB_STLB_FEATURE_EN_FOLLOWER_EN_MASK));
 
-	hdev->asic_funcs->mmu_invalidate_cache(hdev, true);
+	hdev->asic_funcs->mmu_invalidate_cache(hdev, true,
+					VM_TYPE_USERPTR | VM_TYPE_PHYS_PACK);
 
 	WREG32(mmMMU_MMU_ENABLE, 1);
 	WREG32(mmMMU_SPI_MASK, 0xF);
@@ -2978,9 +3005,6 @@ int goya_test_queue(struct hl_device *hdev, u32 hw_queue_id)
 			"H/W queue %d test failed (scratch(0x%08llX) == 0x%08X)\n",
 			hw_queue_id, (unsigned long long) fence_dma_addr, tmp);
 		rc = -EIO;
-	} else {
-		dev_info(hdev->dev, "queue test on H/W queue %d succeeded\n",
-			hw_queue_id);
 	}
 
 free_pkt:
@@ -3925,7 +3949,7 @@ static int goya_parse_cb_no_ext_queue(struct hl_device *hdev,
 		return 0;
 
 	dev_err(hdev->dev,
-		"Internal CB address %px + 0x%x is not in SRAM nor in DRAM\n",
+		"Internal CB address 0x%px + 0x%x is not in SRAM nor in DRAM\n",
 		parser->user_cb, parser->user_cb_size);
 
 	return -EFAULT;
@@ -3935,7 +3959,7 @@ int goya_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser)
 {
 	struct goya_device *goya = hdev->asic_specific;
 
-	if (!parser->ext_queue)
+	if (parser->queue_type == QUEUE_TYPE_INT)
 		return goya_parse_cb_no_ext_queue(hdev, parser);
 
 	if (goya->hw_cap_initialized & HW_CAP_MMU)
@@ -4606,7 +4630,7 @@ static int goya_memset_device_memory(struct hl_device *hdev, u64 addr, u64 size,
 		lin_dma_pkt++;
 	} while (--lin_dma_pkts_cnt);
 
-	job = hl_cs_allocate_job(hdev, true);
+	job = hl_cs_allocate_job(hdev, QUEUE_TYPE_EXT, true);
 	if (!job) {
 		dev_err(hdev->dev, "Failed to allocate a new job\n");
 		rc = -ENOMEM;
@@ -4835,13 +4859,15 @@ static void goya_mmu_prepare(struct hl_device *hdev, u32 asid)
 		goya_mmu_prepare_reg(hdev, goya_mmu_regs[i], asid);
 }
 
-static void goya_mmu_invalidate_cache(struct hl_device *hdev, bool is_hard)
+static void goya_mmu_invalidate_cache(struct hl_device *hdev, bool is_hard,
+					u32 flags)
 {
 	struct goya_device *goya = hdev->asic_specific;
 	u32 status, timeout_usec;
 	int rc;
 
-	if (!(goya->hw_cap_initialized & HW_CAP_MMU))
+	if (!(goya->hw_cap_initialized & HW_CAP_MMU) ||
+		hdev->hard_reset_pending)
 		return;
 
 	/* no need in L1 only invalidation in Goya */
@@ -4880,7 +4906,8 @@ static void goya_mmu_invalidate_cache_range(struct hl_device *hdev,
 	u32 status, timeout_usec, inv_data, pi;
 	int rc;
 
-	if (!(goya->hw_cap_initialized & HW_CAP_MMU))
+	if (!(goya->hw_cap_initialized & HW_CAP_MMU) ||
+		hdev->hard_reset_pending)
 		return;
 
 	/* no need in L1 only invalidation in Goya */
@@ -5137,7 +5164,8 @@ static const struct hl_asic_funcs goya_funcs = {
 	.init_iatu = goya_init_iatu,
 	.rreg = hl_rreg,
 	.wreg = hl_wreg,
-	.halt_coresight = goya_halt_coresight
+	.halt_coresight = goya_halt_coresight,
+	.get_clk_rate = goya_get_clk_rate
 };
 
 /*
diff --git a/drivers/misc/habanalabs/goya/goyaP.h b/drivers/misc/habanalabs/goya/goyaP.h
index 89b6574f8e4f..c3230cb6e25c 100644
--- a/drivers/misc/habanalabs/goya/goyaP.h
+++ b/drivers/misc/habanalabs/goya/goyaP.h
@@ -233,4 +233,6 @@ void goya_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size,
 					void *vaddr);
 void goya_mmu_remove_device_cpu_mappings(struct hl_device *hdev);
 
+int goya_get_clk_rate(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk);
+
 #endif /* GOYAP_H_ */
diff --git a/drivers/misc/habanalabs/goya/goya_coresight.c b/drivers/misc/habanalabs/goya/goya_coresight.c
index b4d406af1bed..c1ee6e2b5dff 100644
--- a/drivers/misc/habanalabs/goya/goya_coresight.c
+++ b/drivers/misc/habanalabs/goya/goya_coresight.c
@@ -8,6 +8,7 @@
 #include "goyaP.h"
 #include "include/goya/goya_coresight.h"
 #include "include/goya/asic_reg/goya_regs.h"
+#include "include/goya/asic_reg/goya_masks.h"
 
 #include <uapi/misc/habanalabs.h>
 
@@ -377,33 +378,32 @@ static int goya_config_etr(struct hl_device *hdev,
 		struct hl_debug_params *params)
 {
 	struct hl_debug_params_etr *input;
-	u64 base_reg = mmPSOC_ETR_BASE - CFG_BASE;
 	u32 val;
 	int rc;
 
-	WREG32(base_reg + 0xFB0, CORESIGHT_UNLOCK);
+	WREG32(mmPSOC_ETR_LAR, CORESIGHT_UNLOCK);
 
-	val = RREG32(base_reg + 0x304);
+	val = RREG32(mmPSOC_ETR_FFCR);
 	val |= 0x1000;
-	WREG32(base_reg + 0x304, val);
+	WREG32(mmPSOC_ETR_FFCR, val);
 	val |= 0x40;
-	WREG32(base_reg + 0x304, val);
+	WREG32(mmPSOC_ETR_FFCR, val);
 
-	rc = goya_coresight_timeout(hdev, base_reg + 0x304, 6, false);
+	rc = goya_coresight_timeout(hdev, mmPSOC_ETR_FFCR, 6, false);
 	if (rc) {
 		dev_err(hdev->dev, "Failed to %s ETR on timeout, error %d\n",
 				params->enable ? "enable" : "disable", rc);
 		return rc;
 	}
 
-	rc = goya_coresight_timeout(hdev, base_reg + 0xC, 2, true);
+	rc = goya_coresight_timeout(hdev, mmPSOC_ETR_STS, 2, true);
 	if (rc) {
 		dev_err(hdev->dev, "Failed to %s ETR on timeout, error %d\n",
 				params->enable ? "enable" : "disable", rc);
 		return rc;
 	}
 
-	WREG32(base_reg + 0x20, 0);
+	WREG32(mmPSOC_ETR_CTL, 0);
 
 	if (params->enable) {
 		input = params->input;
@@ -423,25 +423,26 @@ static int goya_config_etr(struct hl_device *hdev,
 			return -EINVAL;
 		}
 
-		WREG32(base_reg + 0x34, 0x3FFC);
-		WREG32(base_reg + 0x4, input->buffer_size);
-		WREG32(base_reg + 0x28, input->sink_mode);
-		WREG32(base_reg + 0x110, 0x700);
-		WREG32(base_reg + 0x118,
+		WREG32(mmPSOC_ETR_BUFWM, 0x3FFC);
+		WREG32(mmPSOC_ETR_RSZ, input->buffer_size);
+		WREG32(mmPSOC_ETR_MODE, input->sink_mode);
+		WREG32(mmPSOC_ETR_AXICTL,
+				0x700 | PSOC_ETR_AXICTL_PROTCTRLBIT1_SHIFT);
+		WREG32(mmPSOC_ETR_DBALO,
 				lower_32_bits(input->buffer_address));
-		WREG32(base_reg + 0x11C,
+		WREG32(mmPSOC_ETR_DBAHI,
 				upper_32_bits(input->buffer_address));
-		WREG32(base_reg + 0x304, 3);
-		WREG32(base_reg + 0x308, 0xA);
-		WREG32(base_reg + 0x20, 1);
+		WREG32(mmPSOC_ETR_FFCR, 3);
+		WREG32(mmPSOC_ETR_PSCR, 0xA);
+		WREG32(mmPSOC_ETR_CTL, 1);
 	} else {
-		WREG32(base_reg + 0x34, 0);
-		WREG32(base_reg + 0x4, 0x400);
-		WREG32(base_reg + 0x118, 0);
-		WREG32(base_reg + 0x11C, 0);
-		WREG32(base_reg + 0x308, 0);
-		WREG32(base_reg + 0x28, 0);
-		WREG32(base_reg + 0x304, 0);
+		WREG32(mmPSOC_ETR_BUFWM, 0);
+		WREG32(mmPSOC_ETR_RSZ, 0x400);
+		WREG32(mmPSOC_ETR_DBALO, 0);
+		WREG32(mmPSOC_ETR_DBAHI, 0);
+		WREG32(mmPSOC_ETR_PSCR, 0);
+		WREG32(mmPSOC_ETR_MODE, 0);
+		WREG32(mmPSOC_ETR_FFCR, 0);
 
 		if (params->output_size >= sizeof(u64)) {
 			u32 rwp, rwphi;
@@ -451,8 +452,8 @@ static int goya_config_etr(struct hl_device *hdev,
 			 * the buffer is set in the RWP register (lower 32
 			 * bits), and in the RWPHI register (upper 8 bits).
 			 */
-			rwp = RREG32(base_reg + 0x18);
-			rwphi = RREG32(base_reg + 0x3c) & 0xff;
+			rwp = RREG32(mmPSOC_ETR_RWP);
+			rwphi = RREG32(mmPSOC_ETR_RWPHI) & 0xff;
 			*(u64 *) params->output = ((u64) rwphi << 32) | rwp;
 		}
 	}
diff --git a/drivers/misc/habanalabs/goya/goya_hwmgr.c b/drivers/misc/habanalabs/goya/goya_hwmgr.c
index a2a700c3d597..b2ebc01e27f4 100644
--- a/drivers/misc/habanalabs/goya/goya_hwmgr.c
+++ b/drivers/misc/habanalabs/goya/goya_hwmgr.c
@@ -32,6 +32,37 @@ void goya_set_pll_profile(struct hl_device *hdev, enum hl_pll_frequency freq)
 	}
 }
 
+int goya_get_clk_rate(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk)
+{
+	long value;
+
+	if (hl_device_disabled_or_in_reset(hdev))
+		return -ENODEV;
+
+	value = hl_get_frequency(hdev, MME_PLL, false);
+
+	if (value < 0) {
+		dev_err(hdev->dev, "Failed to retrieve device max clock %ld\n",
+			value);
+		return value;
+	}
+
+	*max_clk = (value / 1000 / 1000);
+
+	value = hl_get_frequency(hdev, MME_PLL, true);
+
+	if (value < 0) {
+		dev_err(hdev->dev,
+			"Failed to retrieve device current clock %ld\n",
+			value);
+		return value;
+	}
+
+	*cur_clk = (value / 1000 / 1000);
+
+	return 0;
+}
+
 static ssize_t mme_clk_show(struct device *dev, struct device_attribute *attr,
 				char *buf)
 {
diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h
index 75862be53c60..00c949f4ccd1 100644
--- a/drivers/misc/habanalabs/habanalabs.h
+++ b/drivers/misc/habanalabs/habanalabs.h
@@ -40,8 +40,6 @@
 
 #define HL_MAX_QUEUES			128
 
-#define HL_MAX_JOBS_PER_CS		64
-
 /* MUST BE POWER OF 2 and larger than 1 */
 #define HL_MAX_PENDING_CS		64
 
@@ -85,12 +83,15 @@ struct hl_fpriv;
  * @QUEUE_TYPE_INT: internal queue that performs DMA inside the device's
  *			memories and/or operates the compute engines.
  * @QUEUE_TYPE_CPU: S/W queue for communication with the device's CPU.
+ * @QUEUE_TYPE_HW: queue of DMA and compute engines jobs, for which completion
+ *                 notifications are sent by H/W.
  */
 enum hl_queue_type {
 	QUEUE_TYPE_NA,
 	QUEUE_TYPE_EXT,
 	QUEUE_TYPE_INT,
-	QUEUE_TYPE_CPU
+	QUEUE_TYPE_CPU,
+	QUEUE_TYPE_HW
 };
 
 /**
@@ -98,10 +99,13 @@ enum hl_queue_type {
  * @type: queue type.
  * @driver_only: true if only the driver is allowed to send a job to this queue,
  *               false otherwise.
+ * @requires_kernel_cb: true if a CB handle must be provided for jobs on this
+ *                      queue, false otherwise (a CB address must be provided).
  */
 struct hw_queue_properties {
 	enum hl_queue_type	type;
 	u8			driver_only;
+	u8			requires_kernel_cb;
 };
 
 /**
@@ -110,8 +114,8 @@ struct hw_queue_properties {
  * @VM_TYPE_PHYS_PACK: mapping of DRAM memory to device virtual address.
  */
 enum vm_type_t {
-	VM_TYPE_USERPTR,
-	VM_TYPE_PHYS_PACK
+	VM_TYPE_USERPTR = 0x1,
+	VM_TYPE_PHYS_PACK = 0x2
 };
 
 /**
@@ -127,12 +131,44 @@ enum hl_device_hw_state {
 };
 
 /**
+ * struct hl_mmu_properties - ASIC specific MMU address translation properties.
+ * @hop0_shift: shift of hop 0 mask.
+ * @hop1_shift: shift of hop 1 mask.
+ * @hop2_shift: shift of hop 2 mask.
+ * @hop3_shift: shift of hop 3 mask.
+ * @hop4_shift: shift of hop 4 mask.
+ * @hop0_mask: mask to get the PTE address in hop 0.
+ * @hop1_mask: mask to get the PTE address in hop 1.
+ * @hop2_mask: mask to get the PTE address in hop 2.
+ * @hop3_mask: mask to get the PTE address in hop 3.
+ * @hop4_mask: mask to get the PTE address in hop 4.
+ * @page_size: default page size used to allocate memory.
+ * @huge_page_size: page size used to allocate memory with huge pages.
+ */
+struct hl_mmu_properties {
+	u64	hop0_shift;
+	u64	hop1_shift;
+	u64	hop2_shift;
+	u64	hop3_shift;
+	u64	hop4_shift;
+	u64	hop0_mask;
+	u64	hop1_mask;
+	u64	hop2_mask;
+	u64	hop3_mask;
+	u64	hop4_mask;
+	u32	page_size;
+	u32	huge_page_size;
+};
+
+/**
  * struct asic_fixed_properties - ASIC specific immutable properties.
  * @hw_queues_props: H/W queues properties.
  * @armcp_info: received various information from ArmCP regarding the H/W, e.g.
  *		available sensors.
  * @uboot_ver: F/W U-boot version.
  * @preboot_ver: F/W Preboot version.
+ * @dmmu: DRAM MMU address translation properties.
+ * @pmmu: PCI (host) MMU address translation properties.
  * @sram_base_address: SRAM physical start address.
  * @sram_end_address: SRAM physical end address.
  * @sram_user_base_address - SRAM physical start address for user access.
@@ -169,53 +205,55 @@ enum hl_device_hw_state {
  * @psoc_pci_pll_nf: PCI PLL NF value.
  * @psoc_pci_pll_od: PCI PLL OD value.
  * @psoc_pci_pll_div_factor: PCI PLL DIV FACTOR 1 value.
- * @completion_queues_count: number of completion queues.
  * @high_pll: high PLL frequency used by the device.
  * @cb_pool_cb_cnt: number of CBs in the CB pool.
  * @cb_pool_cb_size: size of each CB in the CB pool.
  * @tpc_enabled_mask: which TPCs are enabled.
+ * @completion_queues_count: number of completion queues.
  */
 struct asic_fixed_properties {
 	struct hw_queue_properties	hw_queues_props[HL_MAX_QUEUES];
-	struct armcp_info	armcp_info;
-	char			uboot_ver[VERSION_MAX_LEN];
-	char			preboot_ver[VERSION_MAX_LEN];
-	u64			sram_base_address;
-	u64			sram_end_address;
-	u64			sram_user_base_address;
-	u64			dram_base_address;
-	u64			dram_end_address;
-	u64			dram_user_base_address;
-	u64			dram_size;
-	u64			dram_pci_bar_size;
-	u64			max_power_default;
-	u64			va_space_host_start_address;
-	u64			va_space_host_end_address;
-	u64			va_space_dram_start_address;
-	u64			va_space_dram_end_address;
-	u64			dram_size_for_default_page_mapping;
-	u64			pcie_dbi_base_address;
-	u64			pcie_aux_dbi_reg_addr;
-	u64			mmu_pgt_addr;
-	u64			mmu_dram_default_page_addr;
-	u32			mmu_pgt_size;
-	u32			mmu_pte_size;
-	u32			mmu_hop_table_size;
-	u32			mmu_hop0_tables_total_size;
-	u32			dram_page_size;
-	u32			cfg_size;
-	u32			sram_size;
-	u32			max_asid;
-	u32			num_of_events;
-	u32			psoc_pci_pll_nr;
-	u32			psoc_pci_pll_nf;
-	u32			psoc_pci_pll_od;
-	u32			psoc_pci_pll_div_factor;
-	u32			high_pll;
-	u32			cb_pool_cb_cnt;
-	u32			cb_pool_cb_size;
-	u8			completion_queues_count;
-	u8			tpc_enabled_mask;
+	struct armcp_info		armcp_info;
+	char				uboot_ver[VERSION_MAX_LEN];
+	char				preboot_ver[VERSION_MAX_LEN];
+	struct hl_mmu_properties	dmmu;
+	struct hl_mmu_properties	pmmu;
+	u64				sram_base_address;
+	u64				sram_end_address;
+	u64				sram_user_base_address;
+	u64				dram_base_address;
+	u64				dram_end_address;
+	u64				dram_user_base_address;
+	u64				dram_size;
+	u64				dram_pci_bar_size;
+	u64				max_power_default;
+	u64				va_space_host_start_address;
+	u64				va_space_host_end_address;
+	u64				va_space_dram_start_address;
+	u64				va_space_dram_end_address;
+	u64				dram_size_for_default_page_mapping;
+	u64				pcie_dbi_base_address;
+	u64				pcie_aux_dbi_reg_addr;
+	u64				mmu_pgt_addr;
+	u64				mmu_dram_default_page_addr;
+	u32				mmu_pgt_size;
+	u32				mmu_pte_size;
+	u32				mmu_hop_table_size;
+	u32				mmu_hop0_tables_total_size;
+	u32				dram_page_size;
+	u32				cfg_size;
+	u32				sram_size;
+	u32				max_asid;
+	u32				num_of_events;
+	u32				psoc_pci_pll_nr;
+	u32				psoc_pci_pll_nf;
+	u32				psoc_pci_pll_od;
+	u32				psoc_pci_pll_div_factor;
+	u32				high_pll;
+	u32				cb_pool_cb_cnt;
+	u32				cb_pool_cb_size;
+	u8				tpc_enabled_mask;
+	u8				completion_queues_count;
 };
 
 /**
@@ -236,8 +274,6 @@ struct hl_dma_fence {
  * Command Buffers
  */
 
-#define HL_MAX_CB_SIZE		0x200000	/* 2MB */
-
 /**
  * struct hl_cb_mgr - describes a Command Buffer Manager.
  * @cb_lock: protects cb_handles.
@@ -481,8 +517,8 @@ enum hl_pll_frequency {
  * @get_events_stat: retrieve event queue entries histogram.
  * @read_pte: read MMU page table entry from DRAM.
  * @write_pte: write MMU page table entry to DRAM.
- * @mmu_invalidate_cache: flush MMU STLB cache, either with soft (L1 only) or
- *                        hard (L0 & L1) flush.
+ * @mmu_invalidate_cache: flush MMU STLB host/DRAM cache, either with soft
+ *                        (L1 only) or hard (L0 & L1) flush.
  * @mmu_invalidate_cache_range: flush specific MMU STLB cache lines with
  *                              ASID-VA-size mask.
  * @send_heartbeat: send is-alive packet to ArmCP and verify response.
@@ -502,6 +538,7 @@ enum hl_pll_frequency {
  * @rreg: Read a register. Needed for simulator support.
  * @wreg: Write a register. Needed for simulator support.
  * @halt_coresight: stop the ETF and ETR traces.
+ * @get_clk_rate: Retrieve the ASIC current and maximum clock rate in MHz
  */
 struct hl_asic_funcs {
 	int (*early_init)(struct hl_device *hdev);
@@ -562,7 +599,8 @@ struct hl_asic_funcs {
 				u32 *size);
 	u64 (*read_pte)(struct hl_device *hdev, u64 addr);
 	void (*write_pte)(struct hl_device *hdev, u64 addr, u64 val);
-	void (*mmu_invalidate_cache)(struct hl_device *hdev, bool is_hard);
+	void (*mmu_invalidate_cache)(struct hl_device *hdev, bool is_hard,
+					u32 flags);
 	void (*mmu_invalidate_cache_range)(struct hl_device *hdev, bool is_hard,
 			u32 asid, u64 va, u64 size);
 	int (*send_heartbeat)(struct hl_device *hdev);
@@ -584,6 +622,7 @@ struct hl_asic_funcs {
 	u32 (*rreg)(struct hl_device *hdev, u32 reg);
 	void (*wreg)(struct hl_device *hdev, u32 reg, u32 val);
 	void (*halt_coresight)(struct hl_device *hdev);
+	int (*get_clk_rate)(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk);
 };
 
 
@@ -688,7 +727,7 @@ struct hl_ctx_mgr {
  * @sgt: pointer to the scatter-gather table that holds the pages.
  * @dir: for DMA unmapping, the direction must be supplied, so save it.
  * @debugfs_list: node in debugfs list of command submissions.
- * @addr: user-space virtual pointer to the start of the memory area.
+ * @addr: user-space virtual address of the start of the memory area.
  * @size: size of the memory area to pin & map.
  * @dma_mapped: true if the SG was mapped to DMA addresses, false otherwise.
  */
@@ -752,11 +791,14 @@ struct hl_cs {
  * @userptr_list: linked-list of userptr mappings that belong to this job and
  *			wait for completion.
  * @debugfs_list: node in debugfs list of command submission jobs.
+ * @queue_type: the type of the H/W queue this job is submitted to.
  * @id: the id of this job inside a CS.
  * @hw_queue_id: the id of the H/W queue this job is submitted to.
  * @user_cb_size: the actual size of the CB we got from the user.
  * @job_cb_size: the actual size of the CB that we put on the queue.
- * @ext_queue: whether the job is for external queue or internal queue.
+ * @is_kernel_allocated_cb: true if the CB handle we got from the user holds a
+ *                          handle to a kernel-allocated CB object, false
+ *                          otherwise (SRAM/DRAM/host address).
  */
 struct hl_cs_job {
 	struct list_head	cs_node;
@@ -766,39 +808,44 @@ struct hl_cs_job {
 	struct work_struct	finish_work;
 	struct list_head	userptr_list;
 	struct list_head	debugfs_list;
+	enum hl_queue_type	queue_type;
 	u32			id;
 	u32			hw_queue_id;
 	u32			user_cb_size;
 	u32			job_cb_size;
-	u8			ext_queue;
+	u8			is_kernel_allocated_cb;
 };
 
 /**
- * struct hl_cs_parser - command submission paerser properties.
+ * struct hl_cs_parser - command submission parser properties.
  * @user_cb: the CB we got from the user.
  * @patched_cb: in case of patching, this is internal CB which is submitted on
  *		the queue instead of the CB we got from the IOCTL.
  * @job_userptr_list: linked-list of userptr mappings that belong to the related
  *			job and wait for completion.
  * @cs_sequence: the sequence number of the related CS.
+ * @queue_type: the type of the H/W queue this job is submitted to.
  * @ctx_id: the ID of the context the related CS belongs to.
  * @hw_queue_id: the id of the H/W queue this job is submitted to.
  * @user_cb_size: the actual size of the CB we got from the user.
  * @patched_cb_size: the size of the CB after parsing.
- * @ext_queue: whether the job is for external queue or internal queue.
  * @job_id: the id of the related job inside the related CS.
+ * @is_kernel_allocated_cb: true if the CB handle we got from the user holds a
+ *                          handle to a kernel-allocated CB object, false
+ *                          otherwise (SRAM/DRAM/host address).
  */
 struct hl_cs_parser {
 	struct hl_cb		*user_cb;
 	struct hl_cb		*patched_cb;
 	struct list_head	*job_userptr_list;
 	u64			cs_sequence;
+	enum hl_queue_type	queue_type;
 	u32			ctx_id;
 	u32			hw_queue_id;
 	u32			user_cb_size;
 	u32			patched_cb_size;
-	u8			ext_queue;
 	u8			job_id;
+	u8			is_kernel_allocated_cb;
 };
 
 
@@ -1048,9 +1095,10 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val);
 
 #define REG_FIELD_SHIFT(reg, field) reg##_##field##_SHIFT
 #define REG_FIELD_MASK(reg, field) reg##_##field##_MASK
-#define WREG32_FIELD(reg, field, val)	\
-	WREG32(mm##reg, (RREG32(mm##reg) & ~REG_FIELD_MASK(reg, field)) | \
-			(val) << REG_FIELD_SHIFT(reg, field))
+#define WREG32_FIELD(reg, offset, field, val)	\
+	WREG32(mm##reg + offset, (RREG32(mm##reg + offset) & \
+				~REG_FIELD_MASK(reg, field)) | \
+				(val) << REG_FIELD_SHIFT(reg, field))
 
 /* Timeout should be longer when working with simulator but cap the
  * increased timeout to some maximum
@@ -1501,7 +1549,8 @@ int hl_cb_pool_init(struct hl_device *hdev);
 int hl_cb_pool_fini(struct hl_device *hdev);
 
 void hl_cs_rollback_all(struct hl_device *hdev);
-struct hl_cs_job *hl_cs_allocate_job(struct hl_device *hdev, bool ext_queue);
+struct hl_cs_job *hl_cs_allocate_job(struct hl_device *hdev,
+		enum hl_queue_type queue_type, bool is_kernel_allocated_cb);
 
 void goya_set_asic_funcs(struct hl_device *hdev);
 
@@ -1513,7 +1562,7 @@ void hl_vm_fini(struct hl_device *hdev);
 
 int hl_pin_host_memory(struct hl_device *hdev, u64 addr, u64 size,
 			struct hl_userptr *userptr);
-int hl_unpin_host_memory(struct hl_device *hdev, struct hl_userptr *userptr);
+void hl_unpin_host_memory(struct hl_device *hdev, struct hl_userptr *userptr);
 void hl_userptr_delete_list(struct hl_device *hdev,
 				struct list_head *userptr_list);
 bool hl_userptr_is_pinned(struct hl_device *hdev, u64 addr, u32 size,
diff --git a/drivers/misc/habanalabs/habanalabs_ioctl.c b/drivers/misc/habanalabs/habanalabs_ioctl.c
index 66d9c710073c..6474b868ef27 100644
--- a/drivers/misc/habanalabs/habanalabs_ioctl.c
+++ b/drivers/misc/habanalabs/habanalabs_ioctl.c
@@ -60,11 +60,16 @@ static int hw_ip_info(struct hl_device *hdev, struct hl_info_args *args)
 	hw_ip.tpc_enabled_mask = prop->tpc_enabled_mask;
 	hw_ip.sram_size = prop->sram_size - sram_kmd_size;
 	hw_ip.dram_size = prop->dram_size - dram_kmd_size;
-	if (hw_ip.dram_size > 0)
+	if (hw_ip.dram_size > PAGE_SIZE)
 		hw_ip.dram_enabled = 1;
 	hw_ip.num_of_events = prop->num_of_events;
-	memcpy(hw_ip.armcp_version,
-		prop->armcp_info.armcp_version, VERSION_MAX_LEN);
+
+	memcpy(hw_ip.armcp_version, prop->armcp_info.armcp_version,
+		min(VERSION_MAX_LEN, HL_INFO_VERSION_MAX_LEN));
+
+	memcpy(hw_ip.card_name, prop->armcp_info.card_name,
+		min(CARD_NAME_MAX_LEN, HL_INFO_CARD_NAME_MAX_LEN));
+
 	hw_ip.armcp_cpld_version = le32_to_cpu(prop->armcp_info.cpld_version);
 	hw_ip.psoc_pci_pll_nr = prop->psoc_pci_pll_nr;
 	hw_ip.psoc_pci_pll_nf = prop->psoc_pci_pll_nf;
@@ -179,17 +184,14 @@ static int debug_coresight(struct hl_device *hdev, struct hl_debug_args *args)
 		goto out;
 	}
 
-	if (output) {
-		if (copy_to_user((void __user *) (uintptr_t) args->output_ptr,
-					output,
-					args->output_size)) {
-			dev_err(hdev->dev,
-				"copy to user failed in debug ioctl\n");
-			rc = -EFAULT;
-			goto out;
-		}
+	if (output && copy_to_user((void __user *) (uintptr_t) args->output_ptr,
+					output, args->output_size)) {
+		dev_err(hdev->dev, "copy to user failed in debug ioctl\n");
+		rc = -EFAULT;
+		goto out;
 	}
 
+
 out:
 	kfree(params);
 	kfree(output);
@@ -221,6 +223,41 @@ static int device_utilization(struct hl_device *hdev, struct hl_info_args *args)
 		min((size_t) max_size, sizeof(device_util))) ? -EFAULT : 0;
 }
 
+static int get_clk_rate(struct hl_device *hdev, struct hl_info_args *args)
+{
+	struct hl_info_clk_rate clk_rate = {0};
+	u32 max_size = args->return_size;
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+	int rc;
+
+	if ((!max_size) || (!out))
+		return -EINVAL;
+
+	rc = hdev->asic_funcs->get_clk_rate(hdev, &clk_rate.cur_clk_rate_mhz,
+						&clk_rate.max_clk_rate_mhz);
+	if (rc)
+		return rc;
+
+	return copy_to_user(out, &clk_rate,
+		min((size_t) max_size, sizeof(clk_rate))) ? -EFAULT : 0;
+}
+
+static int get_reset_count(struct hl_device *hdev, struct hl_info_args *args)
+{
+	struct hl_info_reset_count reset_count = {0};
+	u32 max_size = args->return_size;
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+
+	if ((!max_size) || (!out))
+		return -EINVAL;
+
+	reset_count.hard_reset_cnt = hdev->hard_reset_cnt;
+	reset_count.soft_reset_cnt = hdev->soft_reset_cnt;
+
+	return copy_to_user(out, &reset_count,
+		min((size_t) max_size, sizeof(reset_count))) ? -EFAULT : 0;
+}
+
 static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
 				struct device *dev)
 {
@@ -239,6 +276,9 @@ static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
 	case HL_INFO_DEVICE_STATUS:
 		return device_status_info(hdev, args);
 
+	case HL_INFO_RESET_COUNT:
+		return get_reset_count(hdev, args);
+
 	default:
 		break;
 	}
@@ -271,6 +311,10 @@ static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
 		rc = hw_events_info(hdev, true, args);
 		break;
 
+	case HL_INFO_CLK_RATE:
+		rc = get_clk_rate(hdev, args);
+		break;
+
 	default:
 		dev_err(dev, "Invalid request %d\n", args->op);
 		rc = -ENOTTY;
@@ -406,9 +450,8 @@ static long _hl_ioctl(struct file *filep, unsigned int cmd, unsigned long arg,
 
 	retcode = func(hpriv, kdata);
 
-	if (cmd & IOC_OUT)
-		if (copy_to_user((void __user *)arg, kdata, usize))
-			retcode = -EFAULT;
+	if ((cmd & IOC_OUT) && copy_to_user((void __user *)arg, kdata, usize))
+		retcode = -EFAULT;
 
 out_err:
 	if (retcode)
diff --git a/drivers/misc/habanalabs/hw_queue.c b/drivers/misc/habanalabs/hw_queue.c
index 55b383b2a116..91579dde9262 100644
--- a/drivers/misc/habanalabs/hw_queue.c
+++ b/drivers/misc/habanalabs/hw_queue.c
@@ -58,8 +58,8 @@ out:
 }
 
 /*
- * ext_queue_submit_bd - Submit a buffer descriptor to an external queue
- *
+ * ext_and_hw_queue_submit_bd() - Submit a buffer descriptor to an external or a
+ *                                H/W queue.
  * @hdev: pointer to habanalabs device structure
  * @q: pointer to habanalabs queue structure
  * @ctl: BD's control word
@@ -73,8 +73,8 @@ out:
  * This function must be called when the scheduler mutex is taken
  *
  */
-static void ext_queue_submit_bd(struct hl_device *hdev, struct hl_hw_queue *q,
-				u32 ctl, u32 len, u64 ptr)
+static void ext_and_hw_queue_submit_bd(struct hl_device *hdev,
+			struct hl_hw_queue *q, u32 ctl, u32 len, u64 ptr)
 {
 	struct hl_bd *bd;
 
@@ -174,6 +174,45 @@ static int int_queue_sanity_checks(struct hl_device *hdev,
 }
 
 /*
+ * hw_queue_sanity_checks() - Perform some sanity checks on a H/W queue.
+ * @hdev: Pointer to hl_device structure.
+ * @q: Pointer to hl_hw_queue structure.
+ * @num_of_entries: How many entries to check for space.
+ *
+ * Perform the following:
+ * - Make sure we have enough space in the completion queue.
+ *   This check also ensures that there is enough space in the h/w queue, as
+ *   both queues are of the same size.
+ * - Reserve space in the completion queue (needs to be reversed if there
+ *   is a failure down the road before the actual submission of work).
+ *
+ * Both operations are done using the "free_slots_cnt" field of the completion
+ * queue. The CI counters of the queue and the completion queue are not
+ * needed/used for the H/W queue type.
+ */
+static int hw_queue_sanity_checks(struct hl_device *hdev, struct hl_hw_queue *q,
+					int num_of_entries)
+{
+	atomic_t *free_slots =
+			&hdev->completion_queue[q->hw_queue_id].free_slots_cnt;
+
+	/*
+	 * Check we have enough space in the completion queue.
+	 * Add -1 to counter (decrement) unless counter was already 0.
+	 * In that case, CQ is full so we can't submit a new CB.
+	 * atomic_add_unless will return 0 if counter was already 0.
+	 */
+	if (atomic_add_negative(num_of_entries * -1, free_slots)) {
+		dev_dbg(hdev->dev, "No space for %d entries on CQ %d\n",
+			num_of_entries, q->hw_queue_id);
+		atomic_add(num_of_entries, free_slots);
+		return -EAGAIN;
+	}
+
+	return 0;
+}
+
+/*
  * hl_hw_queue_send_cb_no_cmpl - send a single CB (not a JOB) without completion
  *
  * @hdev: pointer to hl_device structure
@@ -188,7 +227,7 @@ int hl_hw_queue_send_cb_no_cmpl(struct hl_device *hdev, u32 hw_queue_id,
 				u32 cb_size, u64 cb_ptr)
 {
 	struct hl_hw_queue *q = &hdev->kernel_queues[hw_queue_id];
-	int rc;
+	int rc = 0;
 
 	/*
 	 * The CPU queue is a synchronous queue with an effective depth of
@@ -206,11 +245,18 @@ int hl_hw_queue_send_cb_no_cmpl(struct hl_device *hdev, u32 hw_queue_id,
 		goto out;
 	}
 
-	rc = ext_queue_sanity_checks(hdev, q, 1, false);
-	if (rc)
-		goto out;
+	/*
+	 * hl_hw_queue_send_cb_no_cmpl() is called for queues of a H/W queue
+	 * type only on init phase, when the queues are empty and being tested,
+	 * so there is no need for sanity checks.
+	 */
+	if (q->queue_type != QUEUE_TYPE_HW) {
+		rc = ext_queue_sanity_checks(hdev, q, 1, false);
+		if (rc)
+			goto out;
+	}
 
-	ext_queue_submit_bd(hdev, q, 0, cb_size, cb_ptr);
+	ext_and_hw_queue_submit_bd(hdev, q, 0, cb_size, cb_ptr);
 
 out:
 	if (q->queue_type != QUEUE_TYPE_CPU)
@@ -220,14 +266,14 @@ out:
 }
 
 /*
- * ext_hw_queue_schedule_job - submit an JOB to an external queue
+ * ext_queue_schedule_job - submit a JOB to an external queue
  *
  * @job: pointer to the job that needs to be submitted to the queue
  *
  * This function must be called when the scheduler mutex is taken
  *
  */
-static void ext_hw_queue_schedule_job(struct hl_cs_job *job)
+static void ext_queue_schedule_job(struct hl_cs_job *job)
 {
 	struct hl_device *hdev = job->cs->ctx->hdev;
 	struct hl_hw_queue *q = &hdev->kernel_queues[job->hw_queue_id];
@@ -260,7 +306,7 @@ static void ext_hw_queue_schedule_job(struct hl_cs_job *job)
 	 * H/W queues is done under the scheduler mutex
 	 *
 	 * No need to check if CQ is full because it was already
-	 * checked in hl_queue_sanity_checks
+	 * checked in ext_queue_sanity_checks
 	 */
 	cq = &hdev->completion_queue[q->hw_queue_id];
 	cq_addr = cq->bus_address + cq->pi * sizeof(struct hl_cq_entry);
@@ -274,18 +320,18 @@ static void ext_hw_queue_schedule_job(struct hl_cs_job *job)
 
 	cq->pi = hl_cq_inc_ptr(cq->pi);
 
-	ext_queue_submit_bd(hdev, q, ctl, len, ptr);
+	ext_and_hw_queue_submit_bd(hdev, q, ctl, len, ptr);
 }
 
 /*
- * int_hw_queue_schedule_job - submit an JOB to an internal queue
+ * int_queue_schedule_job - submit a JOB to an internal queue
  *
  * @job: pointer to the job that needs to be submitted to the queue
  *
  * This function must be called when the scheduler mutex is taken
  *
  */
-static void int_hw_queue_schedule_job(struct hl_cs_job *job)
+static void int_queue_schedule_job(struct hl_cs_job *job)
 {
 	struct hl_device *hdev = job->cs->ctx->hdev;
 	struct hl_hw_queue *q = &hdev->kernel_queues[job->hw_queue_id];
@@ -308,6 +354,60 @@ static void int_hw_queue_schedule_job(struct hl_cs_job *job)
 }
 
 /*
+ * hw_queue_schedule_job - submit a JOB to a H/W queue
+ *
+ * @job: pointer to the job that needs to be submitted to the queue
+ *
+ * This function must be called when the scheduler mutex is taken
+ *
+ */
+static void hw_queue_schedule_job(struct hl_cs_job *job)
+{
+	struct hl_device *hdev = job->cs->ctx->hdev;
+	struct hl_hw_queue *q = &hdev->kernel_queues[job->hw_queue_id];
+	struct hl_cq *cq;
+	u64 ptr;
+	u32 offset, ctl, len;
+
+	/*
+	 * Upon PQE completion, COMP_DATA is used as the write data to the
+	 * completion queue (QMAN HBW message), and COMP_OFFSET is used as the
+	 * write address offset in the SM block (QMAN LBW message).
+	 * The write address offset is calculated as "COMP_OFFSET << 2".
+	 */
+	offset = job->cs->sequence & (HL_MAX_PENDING_CS - 1);
+	ctl = ((offset << BD_CTL_COMP_OFFSET_SHIFT) & BD_CTL_COMP_OFFSET_MASK) |
+		((q->pi << BD_CTL_COMP_DATA_SHIFT) & BD_CTL_COMP_DATA_MASK);
+
+	len = job->job_cb_size;
+
+	/*
+	 * A patched CB is created only if a user CB was allocated by driver and
+	 * MMU is disabled. If MMU is enabled, the user CB should be used
+	 * instead. If the user CB wasn't allocated by driver, assume that it
+	 * holds an address.
+	 */
+	if (job->patched_cb)
+		ptr = job->patched_cb->bus_address;
+	else if (job->is_kernel_allocated_cb)
+		ptr = job->user_cb->bus_address;
+	else
+		ptr = (u64) (uintptr_t) job->user_cb;
+
+	/*
+	 * No need to protect pi_offset because scheduling to the
+	 * H/W queues is done under the scheduler mutex
+	 *
+	 * No need to check if CQ is full because it was already
+	 * checked in hw_queue_sanity_checks
+	 */
+	cq = &hdev->completion_queue[q->hw_queue_id];
+	cq->pi = hl_cq_inc_ptr(cq->pi);
+
+	ext_and_hw_queue_submit_bd(hdev, q, ctl, len, ptr);
+}
+
+/*
  * hl_hw_queue_schedule_cs - schedule a command submission
  *
  * @job        : pointer to the CS
@@ -330,23 +430,34 @@ int hl_hw_queue_schedule_cs(struct hl_cs *cs)
 	}
 
 	q = &hdev->kernel_queues[0];
-	/* This loop assumes all external queues are consecutive */
 	for (i = 0, cq_cnt = 0 ; i < HL_MAX_QUEUES ; i++, q++) {
-		if (q->queue_type == QUEUE_TYPE_EXT) {
-			if (cs->jobs_in_queue_cnt[i]) {
+		if (cs->jobs_in_queue_cnt[i]) {
+			switch (q->queue_type) {
+			case QUEUE_TYPE_EXT:
 				rc = ext_queue_sanity_checks(hdev, q,
-					cs->jobs_in_queue_cnt[i], true);
-				if (rc)
-					goto unroll_cq_resv;
-				cq_cnt++;
-			}
-		} else if (q->queue_type == QUEUE_TYPE_INT) {
-			if (cs->jobs_in_queue_cnt[i]) {
+						cs->jobs_in_queue_cnt[i], true);
+				break;
+			case QUEUE_TYPE_INT:
 				rc = int_queue_sanity_checks(hdev, q,
-					cs->jobs_in_queue_cnt[i]);
-				if (rc)
-					goto unroll_cq_resv;
+						cs->jobs_in_queue_cnt[i]);
+				break;
+			case QUEUE_TYPE_HW:
+				rc = hw_queue_sanity_checks(hdev, q,
+						cs->jobs_in_queue_cnt[i]);
+				break;
+			default:
+				dev_err(hdev->dev, "Queue type %d is invalid\n",
+					q->queue_type);
+				rc = -EINVAL;
+				break;
 			}
+
+			if (rc)
+				goto unroll_cq_resv;
+
+			if (q->queue_type == QUEUE_TYPE_EXT ||
+					q->queue_type == QUEUE_TYPE_HW)
+				cq_cnt++;
 		}
 	}
 
@@ -373,21 +484,30 @@ int hl_hw_queue_schedule_cs(struct hl_cs *cs)
 	}
 
 	list_for_each_entry_safe(job, tmp, &cs->job_list, cs_node)
-		if (job->ext_queue)
-			ext_hw_queue_schedule_job(job);
-		else
-			int_hw_queue_schedule_job(job);
+		switch (job->queue_type) {
+		case QUEUE_TYPE_EXT:
+			ext_queue_schedule_job(job);
+			break;
+		case QUEUE_TYPE_INT:
+			int_queue_schedule_job(job);
+			break;
+		case QUEUE_TYPE_HW:
+			hw_queue_schedule_job(job);
+			break;
+		default:
+			break;
+		}
 
 	cs->submitted = true;
 
 	goto out;
 
 unroll_cq_resv:
-	/* This loop assumes all external queues are consecutive */
 	q = &hdev->kernel_queues[0];
 	for (i = 0 ; (i < HL_MAX_QUEUES) && (cq_cnt > 0) ; i++, q++) {
-		if ((q->queue_type == QUEUE_TYPE_EXT) &&
-				(cs->jobs_in_queue_cnt[i])) {
+		if ((q->queue_type == QUEUE_TYPE_EXT ||
+				q->queue_type == QUEUE_TYPE_HW) &&
+				cs->jobs_in_queue_cnt[i]) {
 			atomic_t *free_slots =
 				&hdev->completion_queue[i].free_slots_cnt;
 			atomic_add(cs->jobs_in_queue_cnt[i], free_slots);
@@ -414,8 +534,8 @@ void hl_hw_queue_inc_ci_kernel(struct hl_device *hdev, u32 hw_queue_id)
 	q->ci = hl_queue_inc_ptr(q->ci);
 }
 
-static int ext_and_cpu_hw_queue_init(struct hl_device *hdev,
-				struct hl_hw_queue *q, bool is_cpu_queue)
+static int ext_and_cpu_queue_init(struct hl_device *hdev, struct hl_hw_queue *q,
+					bool is_cpu_queue)
 {
 	void *p;
 	int rc;
@@ -465,7 +585,7 @@ free_queue:
 	return rc;
 }
 
-static int int_hw_queue_init(struct hl_device *hdev, struct hl_hw_queue *q)
+static int int_queue_init(struct hl_device *hdev, struct hl_hw_queue *q)
 {
 	void *p;
 
@@ -485,18 +605,38 @@ static int int_hw_queue_init(struct hl_device *hdev, struct hl_hw_queue *q)
 	return 0;
 }
 
-static int cpu_hw_queue_init(struct hl_device *hdev, struct hl_hw_queue *q)
+static int cpu_queue_init(struct hl_device *hdev, struct hl_hw_queue *q)
+{
+	return ext_and_cpu_queue_init(hdev, q, true);
+}
+
+static int ext_queue_init(struct hl_device *hdev, struct hl_hw_queue *q)
 {
-	return ext_and_cpu_hw_queue_init(hdev, q, true);
+	return ext_and_cpu_queue_init(hdev, q, false);
 }
 
-static int ext_hw_queue_init(struct hl_device *hdev, struct hl_hw_queue *q)
+static int hw_queue_init(struct hl_device *hdev, struct hl_hw_queue *q)
 {
-	return ext_and_cpu_hw_queue_init(hdev, q, false);
+	void *p;
+
+	p = hdev->asic_funcs->asic_dma_alloc_coherent(hdev,
+						HL_QUEUE_SIZE_IN_BYTES,
+						&q->bus_address,
+						GFP_KERNEL | __GFP_ZERO);
+	if (!p)
+		return -ENOMEM;
+
+	q->kernel_address = (u64) (uintptr_t) p;
+
+	/* Make sure read/write pointers are initialized to start of queue */
+	q->ci = 0;
+	q->pi = 0;
+
+	return 0;
 }
 
 /*
- * hw_queue_init - main initialization function for H/W queue object
+ * queue_init - main initialization function for H/W queue object
  *
  * @hdev: pointer to hl_device device structure
  * @q: pointer to hl_hw_queue queue structure
@@ -505,7 +645,7 @@ static int ext_hw_queue_init(struct hl_device *hdev, struct hl_hw_queue *q)
  * Allocate dma-able memory for the queue and initialize fields
  * Returns 0 on success
  */
-static int hw_queue_init(struct hl_device *hdev, struct hl_hw_queue *q,
+static int queue_init(struct hl_device *hdev, struct hl_hw_queue *q,
 			u32 hw_queue_id)
 {
 	int rc;
@@ -516,21 +656,20 @@ static int hw_queue_init(struct hl_device *hdev, struct hl_hw_queue *q,
 
 	switch (q->queue_type) {
 	case QUEUE_TYPE_EXT:
-		rc = ext_hw_queue_init(hdev, q);
+		rc = ext_queue_init(hdev, q);
 		break;
-
 	case QUEUE_TYPE_INT:
-		rc = int_hw_queue_init(hdev, q);
+		rc = int_queue_init(hdev, q);
 		break;
-
 	case QUEUE_TYPE_CPU:
-		rc = cpu_hw_queue_init(hdev, q);
+		rc = cpu_queue_init(hdev, q);
+		break;
+	case QUEUE_TYPE_HW:
+		rc = hw_queue_init(hdev, q);
 		break;
-
 	case QUEUE_TYPE_NA:
 		q->valid = 0;
 		return 0;
-
 	default:
 		dev_crit(hdev->dev, "wrong queue type %d during init\n",
 			q->queue_type);
@@ -554,7 +693,7 @@ static int hw_queue_init(struct hl_device *hdev, struct hl_hw_queue *q,
  *
  * Free the queue memory
  */
-static void hw_queue_fini(struct hl_device *hdev, struct hl_hw_queue *q)
+static void queue_fini(struct hl_device *hdev, struct hl_hw_queue *q)
 {
 	if (!q->valid)
 		return;
@@ -612,7 +751,7 @@ int hl_hw_queues_create(struct hl_device *hdev)
 			i < HL_MAX_QUEUES ; i++, q_ready_cnt++, q++) {
 
 		q->queue_type = asic->hw_queues_props[i].type;
-		rc = hw_queue_init(hdev, q, i);
+		rc = queue_init(hdev, q, i);
 		if (rc) {
 			dev_err(hdev->dev,
 				"failed to initialize queue %d\n", i);
@@ -624,7 +763,7 @@ int hl_hw_queues_create(struct hl_device *hdev)
 
 release_queues:
 	for (i = 0, q = hdev->kernel_queues ; i < q_ready_cnt ; i++, q++)
-		hw_queue_fini(hdev, q);
+		queue_fini(hdev, q);
 
 	kfree(hdev->kernel_queues);
 
@@ -637,7 +776,7 @@ void hl_hw_queues_destroy(struct hl_device *hdev)
 	int i;
 
 	for (i = 0, q = hdev->kernel_queues ; i < HL_MAX_QUEUES ; i++, q++)
-		hw_queue_fini(hdev, q);
+		queue_fini(hdev, q);
 
 	kfree(hdev->kernel_queues);
 }
diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/goya_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/goya_masks.h
index 8618891d5afa..3c44ef3a23ed 100644
--- a/drivers/misc/habanalabs/include/goya/asic_reg/goya_masks.h
+++ b/drivers/misc/habanalabs/include/goya/asic_reg/goya_masks.h
@@ -260,4 +260,6 @@
 #define DMA_QM_3_GLBL_CFG1_DMA_STOP_SHIFT DMA_QM_0_GLBL_CFG1_DMA_STOP_SHIFT
 #define DMA_QM_4_GLBL_CFG1_DMA_STOP_SHIFT DMA_QM_0_GLBL_CFG1_DMA_STOP_SHIFT
 
+#define PSOC_ETR_AXICTL_PROTCTRLBIT1_SHIFT                           1
+
 #endif /* ASIC_REG_GOYA_MASKS_H_ */
diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/goya_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/goya_regs.h
index 19b0f0ef1d0b..fce490e6a231 100644
--- a/drivers/misc/habanalabs/include/goya/asic_reg/goya_regs.h
+++ b/drivers/misc/habanalabs/include/goya/asic_reg/goya_regs.h
@@ -84,6 +84,7 @@
 #include "tpc6_rtr_regs.h"
 #include "tpc7_nrtr_regs.h"
 #include "tpc0_eml_cfg_regs.h"
+#include "psoc_etr_regs.h"
 
 #include "psoc_global_conf_masks.h"
 #include "dma_macro_masks.h"
diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/psoc_etr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/psoc_etr_regs.h
new file mode 100644
index 000000000000..b7c33e025db5
--- /dev/null
+++ b/drivers/misc/habanalabs/include/goya/asic_reg/psoc_etr_regs.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright 2016-2018 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ *
+ */
+
+/************************************
+ ** This is an auto-generated file **
+ **       DO NOT EDIT BELOW        **
+ ************************************/
+
+#ifndef ASIC_REG_PSOC_ETR_REGS_H_
+#define ASIC_REG_PSOC_ETR_REGS_H_
+
+/*
+ *****************************************
+ *   PSOC_ETR (Prototype: ETR)
+ *****************************************
+ */
+
+#define mmPSOC_ETR_RSZ                                               0x2C43004
+
+#define mmPSOC_ETR_STS                                               0x2C4300C
+
+#define mmPSOC_ETR_RRD                                               0x2C43010
+
+#define mmPSOC_ETR_RRP                                               0x2C43014
+
+#define mmPSOC_ETR_RWP                                               0x2C43018
+
+#define mmPSOC_ETR_TRG                                               0x2C4301C
+
+#define mmPSOC_ETR_CTL                                               0x2C43020
+
+#define mmPSOC_ETR_RWD                                               0x2C43024
+
+#define mmPSOC_ETR_MODE                                              0x2C43028
+
+#define mmPSOC_ETR_LBUFLEVEL                                         0x2C4302C
+
+#define mmPSOC_ETR_CBUFLEVEL                                         0x2C43030
+
+#define mmPSOC_ETR_BUFWM                                             0x2C43034
+
+#define mmPSOC_ETR_RRPHI                                             0x2C43038
+
+#define mmPSOC_ETR_RWPHI                                             0x2C4303C
+
+#define mmPSOC_ETR_AXICTL                                            0x2C43110
+
+#define mmPSOC_ETR_DBALO                                             0x2C43118
+
+#define mmPSOC_ETR_DBAHI                                             0x2C4311C
+
+#define mmPSOC_ETR_FFSR                                              0x2C43300
+
+#define mmPSOC_ETR_FFCR                                              0x2C43304
+
+#define mmPSOC_ETR_PSCR                                              0x2C43308
+
+#define mmPSOC_ETR_ITMISCOP0                                         0x2C43EE0
+
+#define mmPSOC_ETR_ITTRFLIN                                          0x2C43EE8
+
+#define mmPSOC_ETR_ITATBDATA0                                        0x2C43EEC
+
+#define mmPSOC_ETR_ITATBCTR2                                         0x2C43EF0
+
+#define mmPSOC_ETR_ITATBCTR1                                         0x2C43EF4
+
+#define mmPSOC_ETR_ITATBCTR0                                         0x2C43EF8
+
+#define mmPSOC_ETR_ITCTRL                                            0x2C43F00
+
+#define mmPSOC_ETR_CLAIMSET                                          0x2C43FA0
+
+#define mmPSOC_ETR_CLAIMCLR                                          0x2C43FA4
+
+#define mmPSOC_ETR_LAR                                               0x2C43FB0
+
+#define mmPSOC_ETR_LSR                                               0x2C43FB4
+
+#define mmPSOC_ETR_AUTHSTATUS                                        0x2C43FB8
+
+#define mmPSOC_ETR_DEVID                                             0x2C43FC8
+
+#define mmPSOC_ETR_DEVTYPE                                           0x2C43FCC
+
+#define mmPSOC_ETR_PERIPHID4                                         0x2C43FD0
+
+#define mmPSOC_ETR_PERIPHID5                                         0x2C43FD4
+
+#define mmPSOC_ETR_PERIPHID6                                         0x2C43FD8
+
+#define mmPSOC_ETR_PERIPHID7                                         0x2C43FDC
+
+#define mmPSOC_ETR_PERIPHID0                                         0x2C43FE0
+
+#define mmPSOC_ETR_PERIPHID1                                         0x2C43FE4
+
+#define mmPSOC_ETR_PERIPHID2                                         0x2C43FE8
+
+#define mmPSOC_ETR_PERIPHID3                                         0x2C43FEC
+
+#define mmPSOC_ETR_COMPID0                                           0x2C43FF0
+
+#define mmPSOC_ETR_COMPID1                                           0x2C43FF4
+
+#define mmPSOC_ETR_COMPID2                                           0x2C43FF8
+
+#define mmPSOC_ETR_COMPID3                                           0x2C43FFC
+
+#endif /* ASIC_REG_PSOC_ETR_REGS_H_ */
diff --git a/drivers/misc/habanalabs/include/hl_boot_if.h b/drivers/misc/habanalabs/include/hl_boot_if.h
index 4cd04c090285..2853a2de8cf6 100644
--- a/drivers/misc/habanalabs/include/hl_boot_if.h
+++ b/drivers/misc/habanalabs/include/hl_boot_if.h
@@ -20,6 +20,8 @@ enum cpu_boot_status {
 	CPU_BOOT_STATUS_DRAM_INIT_FAIL,
 	CPU_BOOT_STATUS_FIT_CORRUPTED,
 	CPU_BOOT_STATUS_UBOOT_NOT_READY,
+	CPU_BOOT_STATUS_RESERVED,
+	CPU_BOOT_STATUS_TS_INIT_FAIL,
 };
 
 enum kmd_msg {
diff --git a/drivers/misc/habanalabs/include/hw_ip/mmu/mmu_general.h b/drivers/misc/habanalabs/include/hw_ip/mmu/mmu_general.h
index 71ea3c3e8ba3..a6851a9d3f03 100644
--- a/drivers/misc/habanalabs/include/hw_ip/mmu/mmu_general.h
+++ b/drivers/misc/habanalabs/include/hw_ip/mmu/mmu_general.h
@@ -12,18 +12,16 @@
 #define PAGE_SHIFT_2MB			21
 #define PAGE_SIZE_2MB			(_AC(1, UL) << PAGE_SHIFT_2MB)
 #define PAGE_SIZE_4KB			(_AC(1, UL) << PAGE_SHIFT_4KB)
-#define PAGE_MASK_2MB			(~(PAGE_SIZE_2MB - 1))
 
 #define PAGE_PRESENT_MASK		0x0000000000001ull
 #define SWAP_OUT_MASK			0x0000000000004ull
 #define LAST_MASK			0x0000000000800ull
-#define PHYS_ADDR_MASK			0xFFFFFFFFFFFFF000ull
 #define HOP0_MASK			0x3000000000000ull
 #define HOP1_MASK			0x0FF8000000000ull
 #define HOP2_MASK			0x0007FC0000000ull
 #define HOP3_MASK			0x000003FE00000ull
 #define HOP4_MASK			0x00000001FF000ull
-#define OFFSET_MASK			0x0000000000FFFull
+#define FLAGS_MASK			0x0000000000FFFull
 
 #define HOP0_SHIFT			48
 #define HOP1_SHIFT			39
@@ -31,8 +29,7 @@
 #define HOP3_SHIFT			21
 #define HOP4_SHIFT			12
 
-#define PTE_PHYS_ADDR_SHIFT		12
-#define PTE_PHYS_ADDR_MASK		~OFFSET_MASK
+#define HOP_PHYS_ADDR_MASK		(~FLAGS_MASK)
 
 #define HL_PTE_SIZE			sizeof(u64)
 #define HOP_TABLE_SIZE			PAGE_SIZE_4KB
diff --git a/drivers/misc/habanalabs/include/qman_if.h b/drivers/misc/habanalabs/include/qman_if.h
index bf59bbe27fdc..0fdb49188ed7 100644
--- a/drivers/misc/habanalabs/include/qman_if.h
+++ b/drivers/misc/habanalabs/include/qman_if.h
@@ -23,6 +23,8 @@ struct hl_bd {
 #define HL_BD_SIZE			sizeof(struct hl_bd)
 
 /*
+ * S/W CTL FIELDS.
+ *
  * BD_CTL_REPEAT_VALID tells the CP whether the repeat field in the BD CTL is
  * valid. 1 means the repeat field is valid, 0 means not-valid,
  * i.e. repeat == 1
@@ -34,6 +36,16 @@ struct hl_bd {
 #define BD_CTL_SHADOW_INDEX_MASK	0x00000FFF
 
 /*
+ * H/W CTL FIELDS
+ */
+
+#define BD_CTL_COMP_OFFSET_SHIFT	16
+#define BD_CTL_COMP_OFFSET_MASK		0x00FF0000
+
+#define BD_CTL_COMP_DATA_SHIFT		0
+#define BD_CTL_COMP_DATA_MASK		0x0000FFFF
+
+/*
  * COMPLETION QUEUE
  */
 
diff --git a/drivers/misc/habanalabs/memory.c b/drivers/misc/habanalabs/memory.c
index 365fb0cb8dff..6c72cb4eff54 100644
--- a/drivers/misc/habanalabs/memory.c
+++ b/drivers/misc/habanalabs/memory.c
@@ -13,7 +13,6 @@
 #include <linux/slab.h>
 #include <linux/genalloc.h>
 
-#define PGS_IN_2MB_PAGE	(PAGE_SIZE_2MB >> PAGE_SHIFT)
 #define HL_MMU_DEBUG	0
 
 /*
@@ -159,20 +158,19 @@ pages_pack_err:
 }
 
 /*
- * get_userptr_from_host_va - initialize userptr structure from given host
- *                            virtual address
- *
- * @hdev                : habanalabs device structure
- * @args                : parameters containing the virtual address and size
- * @p_userptr           : pointer to result userptr structure
+ * dma_map_host_va - DMA mapping of the given host virtual address.
+ * @hdev: habanalabs device structure
+ * @addr: the host virtual address of the memory area
+ * @size: the size of the memory area
+ * @p_userptr: pointer to result userptr structure
  *
  * This function does the following:
  * - Allocate userptr structure
  * - Pin the given host memory using the userptr structure
  * - Perform DMA mapping to have the DMA addresses of the pages
  */
-static int get_userptr_from_host_va(struct hl_device *hdev,
-		struct hl_mem_in *args, struct hl_userptr **p_userptr)
+static int dma_map_host_va(struct hl_device *hdev, u64 addr, u64 size,
+				struct hl_userptr **p_userptr)
 {
 	struct hl_userptr *userptr;
 	int rc;
@@ -183,8 +181,7 @@ static int get_userptr_from_host_va(struct hl_device *hdev,
 		goto userptr_err;
 	}
 
-	rc = hl_pin_host_memory(hdev, args->map_host.host_virt_addr,
-			args->map_host.mem_size, userptr);
+	rc = hl_pin_host_memory(hdev, addr, size, userptr);
 	if (rc) {
 		dev_err(hdev->dev, "Failed to pin host memory\n");
 		goto pin_err;
@@ -215,16 +212,16 @@ userptr_err:
 }
 
 /*
- * free_userptr - free userptr structure
- *
- * @hdev                : habanalabs device structure
- * @userptr             : userptr to free
+ * dma_unmap_host_va - DMA unmapping of the given host virtual address.
+ * @hdev: habanalabs device structure
+ * @userptr: userptr to free
  *
  * This function does the following:
  * - Unpins the physical pages
  * - Frees the userptr structure
  */
-static void free_userptr(struct hl_device *hdev, struct hl_userptr *userptr)
+static void dma_unmap_host_va(struct hl_device *hdev,
+				struct hl_userptr *userptr)
 {
 	hl_unpin_host_memory(hdev, userptr);
 	kfree(userptr);
@@ -253,10 +250,9 @@ static void dram_pg_pool_do_release(struct kref *ref)
 }
 
 /*
- * free_phys_pg_pack   - free physical page pack
- *
- * @hdev               : habanalabs device structure
- * @phys_pg_pack       : physical page pack to free
+ * free_phys_pg_pack - free physical page pack
+ * @hdev: habanalabs device structure
+ * @phys_pg_pack: physical page pack to free
  *
  * This function does the following:
  * - For DRAM memory only, iterate over the pack and free each physical block
@@ -264,7 +260,7 @@ static void dram_pg_pool_do_release(struct kref *ref)
  * - Free the hl_vm_phys_pg_pack structure
  */
 static void free_phys_pg_pack(struct hl_device *hdev,
-		struct hl_vm_phys_pg_pack *phys_pg_pack)
+				struct hl_vm_phys_pg_pack *phys_pg_pack)
 {
 	struct hl_vm *vm = &hdev->vm;
 	u64 i;
@@ -519,8 +515,8 @@ static inline int add_va_block(struct hl_device *hdev,
  * - Return the start address of the virtual block
  */
 static u64 get_va_block(struct hl_device *hdev,
-		struct hl_va_range *va_range, u64 size, u64 hint_addr,
-		bool is_userptr)
+			struct hl_va_range *va_range, u64 size, u64 hint_addr,
+			bool is_userptr)
 {
 	struct hl_vm_va_block *va_block, *new_va_block = NULL;
 	u64 valid_start, valid_size, prev_start, prev_end, page_mask,
@@ -528,18 +524,17 @@ static u64 get_va_block(struct hl_device *hdev,
 	u32 page_size;
 	bool add_prev = false;
 
-	if (is_userptr) {
+	if (is_userptr)
 		/*
 		 * We cannot know if the user allocated memory with huge pages
 		 * or not, hence we continue with the biggest possible
 		 * granularity.
 		 */
-		page_size = PAGE_SIZE_2MB;
-		page_mask = PAGE_MASK_2MB;
-	} else {
-		page_size = hdev->asic_prop.dram_page_size;
-		page_mask = ~((u64)page_size - 1);
-	}
+		page_size = hdev->asic_prop.pmmu.huge_page_size;
+	else
+		page_size = hdev->asic_prop.dmmu.page_size;
+
+	page_mask = ~((u64)page_size - 1);
 
 	mutex_lock(&va_range->lock);
 
@@ -549,7 +544,6 @@ static u64 get_va_block(struct hl_device *hdev,
 		/* calc the first possible aligned addr */
 		valid_start = va_block->start;
 
-
 		if (valid_start & (page_size - 1)) {
 			valid_start &= page_mask;
 			valid_start += page_size;
@@ -561,7 +555,6 @@ static u64 get_va_block(struct hl_device *hdev,
 
 		if (valid_size >= size &&
 			(!new_va_block || valid_size < res_valid_size)) {
-
 			new_va_block = va_block;
 			res_valid_start = valid_start;
 			res_valid_size = valid_size;
@@ -631,11 +624,10 @@ static u32 get_sg_info(struct scatterlist *sg, dma_addr_t *dma_addr)
 
 /*
  * init_phys_pg_pack_from_userptr - initialize physical page pack from host
- *                                   memory
- *
- * @ctx                : current context
- * @userptr            : userptr to initialize from
- * @pphys_pg_pack      : res pointer
+ *                                  memory
+ * @ctx: current context
+ * @userptr: userptr to initialize from
+ * @pphys_pg_pack: result pointer
  *
  * This function does the following:
  * - Pin the physical pages related to the given virtual block
@@ -643,16 +635,19 @@ static u32 get_sg_info(struct scatterlist *sg, dma_addr_t *dma_addr)
  *   virtual block
  */
 static int init_phys_pg_pack_from_userptr(struct hl_ctx *ctx,
-		struct hl_userptr *userptr,
-		struct hl_vm_phys_pg_pack **pphys_pg_pack)
+				struct hl_userptr *userptr,
+				struct hl_vm_phys_pg_pack **pphys_pg_pack)
 {
+	struct hl_mmu_properties *mmu_prop = &ctx->hdev->asic_prop.pmmu;
 	struct hl_vm_phys_pg_pack *phys_pg_pack;
 	struct scatterlist *sg;
 	dma_addr_t dma_addr;
 	u64 page_mask, total_npages;
-	u32 npages, page_size = PAGE_SIZE;
+	u32 npages, page_size = PAGE_SIZE,
+		huge_page_size = mmu_prop->huge_page_size;
 	bool first = true, is_huge_page_opt = true;
 	int rc, i, j;
+	u32 pgs_in_huge_page = huge_page_size >> __ffs(page_size);
 
 	phys_pg_pack = kzalloc(sizeof(*phys_pg_pack), GFP_KERNEL);
 	if (!phys_pg_pack)
@@ -675,14 +670,14 @@ static int init_phys_pg_pack_from_userptr(struct hl_ctx *ctx,
 
 		total_npages += npages;
 
-		if ((npages % PGS_IN_2MB_PAGE) ||
-					(dma_addr & (PAGE_SIZE_2MB - 1)))
+		if ((npages % pgs_in_huge_page) ||
+					(dma_addr & (huge_page_size - 1)))
 			is_huge_page_opt = false;
 	}
 
 	if (is_huge_page_opt) {
-		page_size = PAGE_SIZE_2MB;
-		total_npages /= PGS_IN_2MB_PAGE;
+		page_size = huge_page_size;
+		do_div(total_npages, pgs_in_huge_page);
 	}
 
 	page_mask = ~(((u64) page_size) - 1);
@@ -714,7 +709,7 @@ static int init_phys_pg_pack_from_userptr(struct hl_ctx *ctx,
 			dma_addr += page_size;
 
 			if (is_huge_page_opt)
-				npages -= PGS_IN_2MB_PAGE;
+				npages -= pgs_in_huge_page;
 			else
 				npages--;
 		}
@@ -731,19 +726,18 @@ page_pack_arr_mem_err:
 }
 
 /*
- * map_phys_page_pack - maps the physical page pack
- *
- * @ctx                : current context
- * @vaddr              : start address of the virtual area to map from
- * @phys_pg_pack       : the pack of physical pages to map to
+ * map_phys_pg_pack - maps the physical page pack.
+ * @ctx: current context
+ * @vaddr: start address of the virtual area to map from
+ * @phys_pg_pack: the pack of physical pages to map to
  *
  * This function does the following:
  * - Maps each chunk of virtual memory to matching physical chunk
  * - Stores number of successful mappings in the given argument
- * - Returns 0 on success, error code otherwise.
+ * - Returns 0 on success, error code otherwise
  */
-static int map_phys_page_pack(struct hl_ctx *ctx, u64 vaddr,
-		struct hl_vm_phys_pg_pack *phys_pg_pack)
+static int map_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr,
+				struct hl_vm_phys_pg_pack *phys_pg_pack)
 {
 	struct hl_device *hdev = ctx->hdev;
 	u64 next_vaddr = vaddr, paddr, mapped_pg_cnt = 0, i;
@@ -783,6 +777,36 @@ err:
 	return rc;
 }
 
+/*
+ * unmap_phys_pg_pack - unmaps the physical page pack
+ * @ctx: current context
+ * @vaddr: start address of the virtual area to unmap
+ * @phys_pg_pack: the pack of physical pages to unmap
+ */
+static void unmap_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr,
+				struct hl_vm_phys_pg_pack *phys_pg_pack)
+{
+	struct hl_device *hdev = ctx->hdev;
+	u64 next_vaddr, i;
+	u32 page_size;
+
+	page_size = phys_pg_pack->page_size;
+	next_vaddr = vaddr;
+
+	for (i = 0 ; i < phys_pg_pack->npages ; i++, next_vaddr += page_size) {
+		if (hl_mmu_unmap(ctx, next_vaddr, page_size))
+			dev_warn_ratelimited(hdev->dev,
+			"unmap failed for vaddr: 0x%llx\n", next_vaddr);
+
+		/*
+		 * unmapping on Palladium can be really long, so avoid a CPU
+		 * soft lockup bug by sleeping a little between unmapping pages
+		 */
+		if (hdev->pldm)
+			usleep_range(500, 1000);
+	}
+}
+
 static int get_paddr_from_handle(struct hl_ctx *ctx, struct hl_mem_in *args,
 				u64 *paddr)
 {
@@ -839,7 +863,10 @@ static int map_device_va(struct hl_ctx *ctx, struct hl_mem_in *args,
 	*device_addr = 0;
 
 	if (is_userptr) {
-		rc = get_userptr_from_host_va(hdev, args, &userptr);
+		u64 addr = args->map_host.host_virt_addr,
+			size = args->map_host.mem_size;
+
+		rc = dma_map_host_va(hdev, addr, size, &userptr);
 		if (rc) {
 			dev_err(hdev->dev, "failed to get userptr from va\n");
 			return rc;
@@ -850,7 +877,7 @@ static int map_device_va(struct hl_ctx *ctx, struct hl_mem_in *args,
 		if (rc) {
 			dev_err(hdev->dev,
 				"unable to init page pack for vaddr 0x%llx\n",
-				args->map_host.host_virt_addr);
+				addr);
 			goto init_page_pack_err;
 		}
 
@@ -909,7 +936,7 @@ static int map_device_va(struct hl_ctx *ctx, struct hl_mem_in *args,
 
 	mutex_lock(&ctx->mmu_lock);
 
-	rc = map_phys_page_pack(ctx, ret_vaddr, phys_pg_pack);
+	rc = map_phys_pg_pack(ctx, ret_vaddr, phys_pg_pack);
 	if (rc) {
 		mutex_unlock(&ctx->mmu_lock);
 		dev_err(hdev->dev, "mapping page pack failed for handle %u\n",
@@ -917,7 +944,7 @@ static int map_device_va(struct hl_ctx *ctx, struct hl_mem_in *args,
 		goto map_err;
 	}
 
-	hdev->asic_funcs->mmu_invalidate_cache(hdev, false);
+	hdev->asic_funcs->mmu_invalidate_cache(hdev, false, *vm_type);
 
 	mutex_unlock(&ctx->mmu_lock);
 
@@ -955,7 +982,7 @@ shared_err:
 		free_phys_pg_pack(hdev, phys_pg_pack);
 init_page_pack_err:
 	if (is_userptr)
-		free_userptr(hdev, userptr);
+		dma_unmap_host_va(hdev, userptr);
 
 	return rc;
 }
@@ -965,20 +992,20 @@ init_page_pack_err:
  *
  * @ctx                 : current context
  * @vaddr               : device virtual address to unmap
+ * @ctx_free            : true if in context free flow, false otherwise.
  *
  * This function does the following:
  * - Unmap the physical pages related to the given virtual address
  * - return the device virtual block to the virtual block list
  */
-static int unmap_device_va(struct hl_ctx *ctx, u64 vaddr)
+static int unmap_device_va(struct hl_ctx *ctx, u64 vaddr, bool ctx_free)
 {
 	struct hl_device *hdev = ctx->hdev;
 	struct hl_vm_phys_pg_pack *phys_pg_pack = NULL;
 	struct hl_vm_hash_node *hnode = NULL;
 	struct hl_userptr *userptr = NULL;
+	struct hl_va_range *va_range;
 	enum vm_type_t *vm_type;
-	u64 next_vaddr, i;
-	u32 page_size;
 	bool is_userptr;
 	int rc;
 
@@ -1003,9 +1030,10 @@ static int unmap_device_va(struct hl_ctx *ctx, u64 vaddr)
 
 	if (*vm_type == VM_TYPE_USERPTR) {
 		is_userptr = true;
+		va_range = &ctx->host_va_range;
 		userptr = hnode->ptr;
 		rc = init_phys_pg_pack_from_userptr(ctx, userptr,
-				&phys_pg_pack);
+							&phys_pg_pack);
 		if (rc) {
 			dev_err(hdev->dev,
 				"unable to init page pack for vaddr 0x%llx\n",
@@ -1014,6 +1042,7 @@ static int unmap_device_va(struct hl_ctx *ctx, u64 vaddr)
 		}
 	} else if (*vm_type == VM_TYPE_PHYS_PACK) {
 		is_userptr = false;
+		va_range = &ctx->dram_va_range;
 		phys_pg_pack = hnode->ptr;
 	} else {
 		dev_warn(hdev->dev,
@@ -1029,42 +1058,41 @@ static int unmap_device_va(struct hl_ctx *ctx, u64 vaddr)
 		goto mapping_cnt_err;
 	}
 
-	page_size = phys_pg_pack->page_size;
-	vaddr &= ~(((u64) page_size) - 1);
-
-	next_vaddr = vaddr;
+	vaddr &= ~(((u64) phys_pg_pack->page_size) - 1);
 
 	mutex_lock(&ctx->mmu_lock);
 
-	for (i = 0 ; i < phys_pg_pack->npages ; i++, next_vaddr += page_size) {
-		if (hl_mmu_unmap(ctx, next_vaddr, page_size))
-			dev_warn_ratelimited(hdev->dev,
-			"unmap failed for vaddr: 0x%llx\n", next_vaddr);
-
-		/* unmapping on Palladium can be really long, so avoid a CPU
-		 * soft lockup bug by sleeping a little between unmapping pages
-		 */
-		if (hdev->pldm)
-			usleep_range(500, 1000);
-	}
+	unmap_phys_pg_pack(ctx, vaddr, phys_pg_pack);
 
-	hdev->asic_funcs->mmu_invalidate_cache(hdev, true);
+	/*
+	 * During context free this function is called in a loop to clean all
+	 * the context mappings. Hence the cache invalidation can be called once
+	 * at the loop end rather than for each iteration
+	 */
+	if (!ctx_free)
+		hdev->asic_funcs->mmu_invalidate_cache(hdev, true, *vm_type);
 
 	mutex_unlock(&ctx->mmu_lock);
 
-	if (add_va_block(hdev,
-			is_userptr ? &ctx->host_va_range : &ctx->dram_va_range,
-			vaddr,
-			vaddr + phys_pg_pack->total_size - 1))
-		dev_warn(hdev->dev, "add va block failed for vaddr: 0x%llx\n",
-				vaddr);
+	/*
+	 * No point in maintaining the free VA block list if the context is
+	 * closing as the list will be freed anyway
+	 */
+	if (!ctx_free) {
+		rc = add_va_block(hdev, va_range, vaddr,
+					vaddr + phys_pg_pack->total_size - 1);
+		if (rc)
+			dev_warn(hdev->dev,
+					"add va block failed for vaddr: 0x%llx\n",
+					vaddr);
+	}
 
 	atomic_dec(&phys_pg_pack->mapping_cnt);
 	kfree(hnode);
 
 	if (is_userptr) {
 		free_phys_pg_pack(hdev, phys_pg_pack);
-		free_userptr(hdev, userptr);
+		dma_unmap_host_va(hdev, userptr);
 	}
 
 	return 0;
@@ -1189,8 +1217,8 @@ int hl_mem_ioctl(struct hl_fpriv *hpriv, void *data)
 		break;
 
 	case HL_MEM_OP_UNMAP:
-		rc = unmap_device_va(ctx,
-				args->in.unmap.device_virt_addr);
+		rc = unmap_device_va(ctx, args->in.unmap.device_virt_addr,
+					false);
 		break;
 
 	default:
@@ -1203,20 +1231,72 @@ out:
 	return rc;
 }
 
+static int get_user_memory(struct hl_device *hdev, u64 addr, u64 size,
+				u32 npages, u64 start, u32 offset,
+				struct hl_userptr *userptr)
+{
+	int rc;
+
+	if (!access_ok((void __user *) (uintptr_t) addr, size)) {
+		dev_err(hdev->dev, "user pointer is invalid - 0x%llx\n", addr);
+		return -EFAULT;
+	}
+
+	userptr->vec = frame_vector_create(npages);
+	if (!userptr->vec) {
+		dev_err(hdev->dev, "Failed to create frame vector\n");
+		return -ENOMEM;
+	}
+
+	rc = get_vaddr_frames(start, npages, FOLL_FORCE | FOLL_WRITE,
+				userptr->vec);
+
+	if (rc != npages) {
+		dev_err(hdev->dev,
+			"Failed to map host memory, user ptr probably wrong\n");
+		if (rc < 0)
+			goto destroy_framevec;
+		rc = -EFAULT;
+		goto put_framevec;
+	}
+
+	if (frame_vector_to_pages(userptr->vec) < 0) {
+		dev_err(hdev->dev,
+			"Failed to translate frame vector to pages\n");
+		rc = -EFAULT;
+		goto put_framevec;
+	}
+
+	rc = sg_alloc_table_from_pages(userptr->sgt,
+					frame_vector_pages(userptr->vec),
+					npages, offset, size, GFP_ATOMIC);
+	if (rc < 0) {
+		dev_err(hdev->dev, "failed to create SG table from pages\n");
+		goto put_framevec;
+	}
+
+	return 0;
+
+put_framevec:
+	put_vaddr_frames(userptr->vec);
+destroy_framevec:
+	frame_vector_destroy(userptr->vec);
+	return rc;
+}
+
 /*
- * hl_pin_host_memory - pins a chunk of host memory
- *
- * @hdev                : pointer to the habanalabs device structure
- * @addr                : the user-space virtual address of the memory area
- * @size                : the size of the memory area
- * @userptr	        : pointer to hl_userptr structure
+ * hl_pin_host_memory - pins a chunk of host memory.
+ * @hdev: pointer to the habanalabs device structure
+ * @addr: the host virtual address of the memory area
+ * @size: the size of the memory area
+ * @userptr: pointer to hl_userptr structure
  *
  * This function does the following:
  * - Pins the physical pages
- * - Create a SG list from those pages
+ * - Create an SG list from those pages
  */
 int hl_pin_host_memory(struct hl_device *hdev, u64 addr, u64 size,
-			struct hl_userptr *userptr)
+					struct hl_userptr *userptr)
 {
 	u64 start, end;
 	u32 npages, offset;
@@ -1227,11 +1307,6 @@ int hl_pin_host_memory(struct hl_device *hdev, u64 addr, u64 size,
 		return -EINVAL;
 	}
 
-	if (!access_ok((void __user *) (uintptr_t) addr, size)) {
-		dev_err(hdev->dev, "user pointer is invalid - 0x%llx\n", addr);
-		return -EFAULT;
-	}
-
 	/*
 	 * If the combination of the address and size requested for this memory
 	 * region causes an integer overflow, return error.
@@ -1244,6 +1319,14 @@ int hl_pin_host_memory(struct hl_device *hdev, u64 addr, u64 size,
 		return -EINVAL;
 	}
 
+	/*
+	 * This function can be called also from data path, hence use atomic
+	 * always as it is not a big allocation.
+	 */
+	userptr->sgt = kzalloc(sizeof(*userptr->sgt), GFP_ATOMIC);
+	if (!userptr->sgt)
+		return -ENOMEM;
+
 	start = addr & PAGE_MASK;
 	offset = addr & ~PAGE_MASK;
 	end = PAGE_ALIGN(addr + size);
@@ -1254,42 +1337,12 @@ int hl_pin_host_memory(struct hl_device *hdev, u64 addr, u64 size,
 	userptr->dma_mapped = false;
 	INIT_LIST_HEAD(&userptr->job_node);
 
-	userptr->vec = frame_vector_create(npages);
-	if (!userptr->vec) {
-		dev_err(hdev->dev, "Failed to create frame vector\n");
-		return -ENOMEM;
-	}
-
-	rc = get_vaddr_frames(start, npages, FOLL_FORCE | FOLL_WRITE,
-				userptr->vec);
-
-	if (rc != npages) {
-		dev_err(hdev->dev,
-			"Failed to map host memory, user ptr probably wrong\n");
-		if (rc < 0)
-			goto destroy_framevec;
-		rc = -EFAULT;
-		goto put_framevec;
-	}
-
-	if (frame_vector_to_pages(userptr->vec) < 0) {
+	rc = get_user_memory(hdev, addr, size, npages, start, offset,
+				userptr);
+	if (rc) {
 		dev_err(hdev->dev,
-			"Failed to translate frame vector to pages\n");
-		rc = -EFAULT;
-		goto put_framevec;
-	}
-
-	userptr->sgt = kzalloc(sizeof(*userptr->sgt), GFP_ATOMIC);
-	if (!userptr->sgt) {
-		rc = -ENOMEM;
-		goto put_framevec;
-	}
-
-	rc = sg_alloc_table_from_pages(userptr->sgt,
-					frame_vector_pages(userptr->vec),
-					npages, offset, size, GFP_ATOMIC);
-	if (rc < 0) {
-		dev_err(hdev->dev, "failed to create SG table from pages\n");
+			"failed to get user memory for address 0x%llx\n",
+			addr);
 		goto free_sgt;
 	}
 
@@ -1299,34 +1352,28 @@ int hl_pin_host_memory(struct hl_device *hdev, u64 addr, u64 size,
 
 free_sgt:
 	kfree(userptr->sgt);
-put_framevec:
-	put_vaddr_frames(userptr->vec);
-destroy_framevec:
-	frame_vector_destroy(userptr->vec);
 	return rc;
 }
 
 /*
- * hl_unpin_host_memory - unpins a chunk of host memory
- *
- * @hdev                : pointer to the habanalabs device structure
- * @userptr             : pointer to hl_userptr structure
+ * hl_unpin_host_memory - unpins a chunk of host memory.
+ * @hdev: pointer to the habanalabs device structure
+ * @userptr: pointer to hl_userptr structure
  *
  * This function does the following:
  * - Unpins the physical pages related to the host memory
  * - Free the SG list
  */
-int hl_unpin_host_memory(struct hl_device *hdev, struct hl_userptr *userptr)
+void hl_unpin_host_memory(struct hl_device *hdev, struct hl_userptr *userptr)
 {
 	struct page **pages;
 
 	hl_debugfs_remove_userptr(hdev, userptr);
 
 	if (userptr->dma_mapped)
-		hdev->asic_funcs->hl_dma_unmap_sg(hdev,
-				userptr->sgt->sgl,
-				userptr->sgt->nents,
-				userptr->dir);
+		hdev->asic_funcs->hl_dma_unmap_sg(hdev, userptr->sgt->sgl,
+							userptr->sgt->nents,
+							userptr->dir);
 
 	pages = frame_vector_pages(userptr->vec);
 	if (!IS_ERR(pages)) {
@@ -1342,8 +1389,6 @@ int hl_unpin_host_memory(struct hl_device *hdev, struct hl_userptr *userptr)
 
 	sg_free_table(userptr->sgt);
 	kfree(userptr->sgt);
-
-	return 0;
 }
 
 /*
@@ -1542,43 +1587,16 @@ int hl_vm_ctx_init(struct hl_ctx *ctx)
  * @hdev                : pointer to the habanalabs structure
  * va_range             : pointer to virtual addresses range
  *
- * This function initializes the following:
- * - Checks that the given range contains the whole initial range
+ * This function does the following:
  * - Frees the virtual addresses block list and its lock
  */
 static void hl_va_range_fini(struct hl_device *hdev,
 		struct hl_va_range *va_range)
 {
-	struct hl_vm_va_block *va_block;
-
-	if (list_empty(&va_range->list)) {
-		dev_warn(hdev->dev,
-				"va list should not be empty on cleanup!\n");
-		goto out;
-	}
-
-	if (!list_is_singular(&va_range->list)) {
-		dev_warn(hdev->dev,
-			"va list should not contain multiple blocks on cleanup!\n");
-		goto free_va_list;
-	}
-
-	va_block = list_first_entry(&va_range->list, typeof(*va_block), node);
-
-	if (va_block->start != va_range->start_addr ||
-		va_block->end != va_range->end_addr) {
-		dev_warn(hdev->dev,
-			"wrong va block on cleanup, from 0x%llx to 0x%llx\n",
-				va_block->start, va_block->end);
-		goto free_va_list;
-	}
-
-free_va_list:
 	mutex_lock(&va_range->lock);
 	clear_va_list_locked(hdev, &va_range->list);
 	mutex_unlock(&va_range->lock);
 
-out:
 	mutex_destroy(&va_range->lock);
 }
 
@@ -1613,21 +1631,31 @@ void hl_vm_ctx_fini(struct hl_ctx *ctx)
 
 	hl_debugfs_remove_ctx_mem_hash(hdev, ctx);
 
-	if (!hash_empty(ctx->mem_hash))
-		dev_notice(hdev->dev, "ctx is freed while it has va in use\n");
+	/*
+	 * Clearly something went wrong on hard reset so no point in printing
+	 * another side effect error
+	 */
+	if (!hdev->hard_reset_pending && !hash_empty(ctx->mem_hash))
+		dev_notice(hdev->dev,
+				"ctx %d is freed while it has va in use\n",
+				ctx->asid);
 
 	hash_for_each_safe(ctx->mem_hash, i, tmp_node, hnode, node) {
 		dev_dbg(hdev->dev,
 			"hl_mem_hash_node of vaddr 0x%llx of asid %d is still alive\n",
 			hnode->vaddr, ctx->asid);
-		unmap_device_va(ctx, hnode->vaddr);
+		unmap_device_va(ctx, hnode->vaddr, true);
 	}
 
+	/* invalidate the cache once after the unmapping loop */
+	hdev->asic_funcs->mmu_invalidate_cache(hdev, true, VM_TYPE_USERPTR);
+	hdev->asic_funcs->mmu_invalidate_cache(hdev, true, VM_TYPE_PHYS_PACK);
+
 	spin_lock(&vm->idr_lock);
 	idr_for_each_entry(&vm->phys_pg_pack_handles, phys_pg_list, i)
 		if (phys_pg_list->asid == ctx->asid) {
 			dev_dbg(hdev->dev,
-				"page list 0x%p of asid %d is still alive\n",
+				"page list 0x%px of asid %d is still alive\n",
 				phys_pg_list, ctx->asid);
 			atomic64_sub(phys_pg_list->total_size,
 					&hdev->dram_used_mem);
diff --git a/drivers/misc/habanalabs/mmu.c b/drivers/misc/habanalabs/mmu.c
index 176c315836f1..6262b26e2086 100644
--- a/drivers/misc/habanalabs/mmu.c
+++ b/drivers/misc/habanalabs/mmu.c
@@ -25,10 +25,9 @@ static struct pgt_info *get_pgt_info(struct hl_ctx *ctx, u64 hop_addr)
 	return pgt_info;
 }
 
-static void free_hop(struct hl_ctx *ctx, u64 hop_addr)
+static void _free_hop(struct hl_ctx *ctx, struct pgt_info *pgt_info)
 {
 	struct hl_device *hdev = ctx->hdev;
-	struct pgt_info *pgt_info = get_pgt_info(ctx, hop_addr);
 
 	gen_pool_free(hdev->mmu_pgt_pool, pgt_info->phys_addr,
 			hdev->asic_prop.mmu_hop_table_size);
@@ -37,6 +36,13 @@ static void free_hop(struct hl_ctx *ctx, u64 hop_addr)
 	kfree(pgt_info);
 }
 
+static void free_hop(struct hl_ctx *ctx, u64 hop_addr)
+{
+	struct pgt_info *pgt_info = get_pgt_info(ctx, hop_addr);
+
+	_free_hop(ctx, pgt_info);
+}
+
 static u64 alloc_hop(struct hl_ctx *ctx)
 {
 	struct hl_device *hdev = ctx->hdev;
@@ -105,8 +111,8 @@ static inline void write_pte(struct hl_ctx *ctx, u64 shadow_pte_addr, u64 val)
 	 * clear the 12 LSBs and translate the shadow hop to its associated
 	 * physical hop, and add back the original 12 LSBs.
 	 */
-	u64 phys_val = get_phys_addr(ctx, val & PTE_PHYS_ADDR_MASK) |
-				(val & OFFSET_MASK);
+	u64 phys_val = get_phys_addr(ctx, val & HOP_PHYS_ADDR_MASK) |
+				(val & FLAGS_MASK);
 
 	ctx->hdev->asic_funcs->write_pte(ctx->hdev,
 					get_phys_addr(ctx, shadow_pte_addr),
@@ -159,7 +165,7 @@ static inline int put_pte(struct hl_ctx *ctx, u64 hop_addr)
 	 */
 	num_of_ptes_left = pgt_info->num_of_ptes;
 	if (!num_of_ptes_left)
-		free_hop(ctx, hop_addr);
+		_free_hop(ctx, pgt_info);
 
 	return num_of_ptes_left;
 }
@@ -171,35 +177,50 @@ static inline u64 get_hopN_pte_addr(struct hl_ctx *ctx, u64 hop_addr,
 			((virt_addr & mask) >> shift);
 }
 
-static inline u64 get_hop0_pte_addr(struct hl_ctx *ctx, u64 hop_addr, u64 vaddr)
+static inline u64 get_hop0_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_prop,
+					u64 hop_addr, u64 vaddr)
 {
-	return get_hopN_pte_addr(ctx, hop_addr, vaddr, HOP0_MASK, HOP0_SHIFT);
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_prop->hop0_mask,
+					mmu_prop->hop0_shift);
 }
 
-static inline u64 get_hop1_pte_addr(struct hl_ctx *ctx, u64 hop_addr, u64 vaddr)
+static inline u64 get_hop1_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_prop,
+					u64 hop_addr, u64 vaddr)
 {
-	return get_hopN_pte_addr(ctx, hop_addr, vaddr, HOP1_MASK, HOP1_SHIFT);
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_prop->hop1_mask,
+					mmu_prop->hop1_shift);
 }
 
-static inline u64 get_hop2_pte_addr(struct hl_ctx *ctx, u64 hop_addr, u64 vaddr)
+static inline u64 get_hop2_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_prop,
+					u64 hop_addr, u64 vaddr)
 {
-	return get_hopN_pte_addr(ctx, hop_addr, vaddr, HOP2_MASK, HOP2_SHIFT);
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_prop->hop2_mask,
+					mmu_prop->hop2_shift);
 }
 
-static inline u64 get_hop3_pte_addr(struct hl_ctx *ctx, u64 hop_addr, u64 vaddr)
+static inline u64 get_hop3_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_prop,
+					u64 hop_addr, u64 vaddr)
 {
-	return get_hopN_pte_addr(ctx, hop_addr, vaddr, HOP3_MASK, HOP3_SHIFT);
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_prop->hop3_mask,
+					mmu_prop->hop3_shift);
 }
 
-static inline u64 get_hop4_pte_addr(struct hl_ctx *ctx, u64 hop_addr, u64 vaddr)
+static inline u64 get_hop4_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_prop,
+					u64 hop_addr, u64 vaddr)
 {
-	return get_hopN_pte_addr(ctx, hop_addr, vaddr, HOP4_MASK, HOP4_SHIFT);
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_prop->hop4_mask,
+					mmu_prop->hop4_shift);
 }
 
 static inline u64 get_next_hop_addr(struct hl_ctx *ctx, u64 curr_pte)
 {
 	if (curr_pte & PAGE_PRESENT_MASK)
-		return curr_pte & PHYS_ADDR_MASK;
+		return curr_pte & HOP_PHYS_ADDR_MASK;
 	else
 		return ULLONG_MAX;
 }
@@ -288,23 +309,23 @@ static int dram_default_mapping_init(struct hl_ctx *ctx)
 	}
 
 	/* need only pte 0 in hops 0 and 1 */
-	pte_val = (hop1_addr & PTE_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
+	pte_val = (hop1_addr & HOP_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
 	write_pte(ctx, hop0_addr, pte_val);
 
-	pte_val = (hop2_addr & PTE_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
+	pte_val = (hop2_addr & HOP_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
 	write_pte(ctx, hop1_addr, pte_val);
 	get_pte(ctx, hop1_addr);
 
 	hop2_pte_addr = hop2_addr;
 	for (i = 0 ; i < num_of_hop3 ; i++) {
-		pte_val = (ctx->dram_default_hops[i] & PTE_PHYS_ADDR_MASK) |
+		pte_val = (ctx->dram_default_hops[i] & HOP_PHYS_ADDR_MASK) |
 				PAGE_PRESENT_MASK;
 		write_pte(ctx, hop2_pte_addr, pte_val);
 		get_pte(ctx, hop2_addr);
 		hop2_pte_addr += HL_PTE_SIZE;
 	}
 
-	pte_val = (prop->mmu_dram_default_page_addr & PTE_PHYS_ADDR_MASK) |
+	pte_val = (prop->mmu_dram_default_page_addr & HOP_PHYS_ADDR_MASK) |
 			LAST_MASK | PAGE_PRESENT_MASK;
 
 	for (i = 0 ; i < num_of_hop3 ; i++) {
@@ -400,8 +421,6 @@ int hl_mmu_init(struct hl_device *hdev)
 	if (!hdev->mmu_enable)
 		return 0;
 
-	/* MMU H/W init was already done in device hw_init() */
-
 	hdev->mmu_pgt_pool =
 			gen_pool_create(__ffs(prop->mmu_hop_table_size), -1);
 
@@ -427,6 +446,8 @@ int hl_mmu_init(struct hl_device *hdev)
 		goto err_pool_add;
 	}
 
+	/* MMU H/W init will be done in device hw_init() */
+
 	return 0;
 
 err_pool_add:
@@ -450,10 +471,10 @@ void hl_mmu_fini(struct hl_device *hdev)
 	if (!hdev->mmu_enable)
 		return;
 
+	/* MMU H/W fini was already done in device hw_fini() */
+
 	kvfree(hdev->mmu_shadow_hop0);
 	gen_pool_destroy(hdev->mmu_pgt_pool);
-
-	/* MMU H/W fini will be done in device hw_fini() */
 }
 
 /**
@@ -501,36 +522,36 @@ void hl_mmu_ctx_fini(struct hl_ctx *ctx)
 	dram_default_mapping_fini(ctx);
 
 	if (!hash_empty(ctx->mmu_shadow_hash))
-		dev_err(hdev->dev, "ctx is freed while it has pgts in use\n");
+		dev_err(hdev->dev, "ctx %d is freed while it has pgts in use\n",
+			ctx->asid);
 
 	hash_for_each_safe(ctx->mmu_shadow_hash, i, tmp, pgt_info, node) {
-		dev_err(hdev->dev,
+		dev_err_ratelimited(hdev->dev,
 			"pgt_info of addr 0x%llx of asid %d was not destroyed, num_ptes: %d\n",
 			pgt_info->phys_addr, ctx->asid, pgt_info->num_of_ptes);
-		free_hop(ctx, pgt_info->shadow_addr);
+		_free_hop(ctx, pgt_info);
 	}
 
 	mutex_destroy(&ctx->mmu_lock);
 }
 
-static int _hl_mmu_unmap(struct hl_ctx *ctx, u64 virt_addr)
+static int _hl_mmu_unmap(struct hl_ctx *ctx, u64 virt_addr, bool is_dram_addr)
 {
 	struct hl_device *hdev = ctx->hdev;
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct hl_mmu_properties *mmu_prop;
 	u64 hop0_addr = 0, hop0_pte_addr = 0,
 		hop1_addr = 0, hop1_pte_addr = 0,
 		hop2_addr = 0, hop2_pte_addr = 0,
 		hop3_addr = 0, hop3_pte_addr = 0,
 		hop4_addr = 0, hop4_pte_addr = 0,
 		curr_pte;
-	bool is_dram_addr, is_huge, clear_hop3 = true;
+	bool is_huge, clear_hop3 = true;
 
-	is_dram_addr = hl_mem_area_inside_range(virt_addr, PAGE_SIZE_2MB,
-				prop->va_space_dram_start_address,
-				prop->va_space_dram_end_address);
+	mmu_prop = is_dram_addr ? &prop->dmmu : &prop->pmmu;
 
 	hop0_addr = get_hop0_addr(ctx);
-	hop0_pte_addr = get_hop0_pte_addr(ctx, hop0_addr, virt_addr);
+	hop0_pte_addr = get_hop0_pte_addr(ctx, mmu_prop, hop0_addr, virt_addr);
 
 	curr_pte = *(u64 *) (uintptr_t) hop0_pte_addr;
 
@@ -539,7 +560,7 @@ static int _hl_mmu_unmap(struct hl_ctx *ctx, u64 virt_addr)
 	if (hop1_addr == ULLONG_MAX)
 		goto not_mapped;
 
-	hop1_pte_addr = get_hop1_pte_addr(ctx, hop1_addr, virt_addr);
+	hop1_pte_addr = get_hop1_pte_addr(ctx, mmu_prop, hop1_addr, virt_addr);
 
 	curr_pte = *(u64 *) (uintptr_t) hop1_pte_addr;
 
@@ -548,7 +569,7 @@ static int _hl_mmu_unmap(struct hl_ctx *ctx, u64 virt_addr)
 	if (hop2_addr == ULLONG_MAX)
 		goto not_mapped;
 
-	hop2_pte_addr = get_hop2_pte_addr(ctx, hop2_addr, virt_addr);
+	hop2_pte_addr = get_hop2_pte_addr(ctx, mmu_prop, hop2_addr, virt_addr);
 
 	curr_pte = *(u64 *) (uintptr_t) hop2_pte_addr;
 
@@ -557,7 +578,7 @@ static int _hl_mmu_unmap(struct hl_ctx *ctx, u64 virt_addr)
 	if (hop3_addr == ULLONG_MAX)
 		goto not_mapped;
 
-	hop3_pte_addr = get_hop3_pte_addr(ctx, hop3_addr, virt_addr);
+	hop3_pte_addr = get_hop3_pte_addr(ctx, mmu_prop, hop3_addr, virt_addr);
 
 	curr_pte = *(u64 *) (uintptr_t) hop3_pte_addr;
 
@@ -575,7 +596,8 @@ static int _hl_mmu_unmap(struct hl_ctx *ctx, u64 virt_addr)
 		if (hop4_addr == ULLONG_MAX)
 			goto not_mapped;
 
-		hop4_pte_addr = get_hop4_pte_addr(ctx, hop4_addr, virt_addr);
+		hop4_pte_addr = get_hop4_pte_addr(ctx, mmu_prop, hop4_addr,
+							virt_addr);
 
 		curr_pte = *(u64 *) (uintptr_t) hop4_pte_addr;
 
@@ -584,7 +606,7 @@ static int _hl_mmu_unmap(struct hl_ctx *ctx, u64 virt_addr)
 
 	if (hdev->dram_default_page_mapping && is_dram_addr) {
 		u64 default_pte = (prop->mmu_dram_default_page_addr &
-				PTE_PHYS_ADDR_MASK) | LAST_MASK |
+				HOP_PHYS_ADDR_MASK) | LAST_MASK |
 					PAGE_PRESENT_MASK;
 		if (curr_pte == default_pte) {
 			dev_err(hdev->dev,
@@ -667,25 +689,36 @@ not_mapped:
 int hl_mmu_unmap(struct hl_ctx *ctx, u64 virt_addr, u32 page_size)
 {
 	struct hl_device *hdev = ctx->hdev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct hl_mmu_properties *mmu_prop;
 	u64 real_virt_addr;
 	u32 real_page_size, npages;
 	int i, rc;
+	bool is_dram_addr;
 
 	if (!hdev->mmu_enable)
 		return 0;
 
+	is_dram_addr = hl_mem_area_inside_range(virt_addr, prop->dmmu.page_size,
+				prop->va_space_dram_start_address,
+				prop->va_space_dram_end_address);
+
+	mmu_prop = is_dram_addr ? &prop->dmmu : &prop->pmmu;
+
 	/*
-	 * The H/W handles mapping of 4KB/2MB page. Hence if the host page size
-	 * is bigger, we break it to sub-pages and unmap them separately.
+	 * The H/W handles mapping of specific page sizes. Hence if the page
+	 * size is bigger, we break it to sub-pages and unmap them separately.
 	 */
-	if ((page_size % PAGE_SIZE_2MB) == 0) {
-		real_page_size = PAGE_SIZE_2MB;
-	} else if ((page_size % PAGE_SIZE_4KB) == 0) {
-		real_page_size = PAGE_SIZE_4KB;
+	if ((page_size % mmu_prop->huge_page_size) == 0) {
+		real_page_size = mmu_prop->huge_page_size;
+	} else if ((page_size % mmu_prop->page_size) == 0) {
+		real_page_size = mmu_prop->page_size;
 	} else {
 		dev_err(hdev->dev,
-			"page size of %u is not 4KB nor 2MB aligned, can't unmap\n",
-				page_size);
+			"page size of %u is not %uKB nor %uMB aligned, can't unmap\n",
+			page_size,
+			mmu_prop->page_size >> 10,
+			mmu_prop->huge_page_size >> 20);
 
 		return -EFAULT;
 	}
@@ -694,7 +727,7 @@ int hl_mmu_unmap(struct hl_ctx *ctx, u64 virt_addr, u32 page_size)
 	real_virt_addr = virt_addr;
 
 	for (i = 0 ; i < npages ; i++) {
-		rc = _hl_mmu_unmap(ctx, real_virt_addr);
+		rc = _hl_mmu_unmap(ctx, real_virt_addr, is_dram_addr);
 		if (rc)
 			return rc;
 
@@ -705,10 +738,11 @@ int hl_mmu_unmap(struct hl_ctx *ctx, u64 virt_addr, u32 page_size)
 }
 
 static int _hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr,
-		u32 page_size)
+			u32 page_size, bool is_dram_addr)
 {
 	struct hl_device *hdev = ctx->hdev;
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct hl_mmu_properties *mmu_prop;
 	u64 hop0_addr = 0, hop0_pte_addr = 0,
 		hop1_addr = 0, hop1_pte_addr = 0,
 		hop2_addr = 0, hop2_pte_addr = 0,
@@ -716,21 +750,19 @@ static int _hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr,
 		hop4_addr = 0, hop4_pte_addr = 0,
 		curr_pte = 0;
 	bool hop1_new = false, hop2_new = false, hop3_new = false,
-		hop4_new = false, is_huge, is_dram_addr;
+		hop4_new = false, is_huge;
 	int rc = -ENOMEM;
 
+	mmu_prop = is_dram_addr ? &prop->dmmu : &prop->pmmu;
+
 	/*
-	 * This mapping function can map a 4KB/2MB page. For 2MB page there are
-	 * only 3 hops rather than 4. Currently the DRAM allocation uses 2MB
-	 * pages only but user memory could have been allocated with one of the
-	 * two page sizes. Since this is a common code for all the three cases,
-	 * we need this hugs page check.
+	 * This mapping function can map a page or a huge page. For huge page
+	 * there are only 3 hops rather than 4. Currently the DRAM allocation
+	 * uses huge pages only but user memory could have been allocated with
+	 * one of the two page sizes. Since this is a common code for all the
+	 * three cases, we need this hugs page check.
 	 */
-	is_huge = page_size == PAGE_SIZE_2MB;
-
-	is_dram_addr = hl_mem_area_inside_range(virt_addr, page_size,
-				prop->va_space_dram_start_address,
-				prop->va_space_dram_end_address);
+	is_huge = page_size == mmu_prop->huge_page_size;
 
 	if (is_dram_addr && !is_huge) {
 		dev_err(hdev->dev, "DRAM mapping should use huge pages only\n");
@@ -738,28 +770,28 @@ static int _hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr,
 	}
 
 	hop0_addr = get_hop0_addr(ctx);
-	hop0_pte_addr = get_hop0_pte_addr(ctx, hop0_addr, virt_addr);
+	hop0_pte_addr = get_hop0_pte_addr(ctx, mmu_prop, hop0_addr, virt_addr);
 	curr_pte = *(u64 *) (uintptr_t) hop0_pte_addr;
 
 	hop1_addr = get_alloc_next_hop_addr(ctx, curr_pte, &hop1_new);
 	if (hop1_addr == ULLONG_MAX)
 		goto err;
 
-	hop1_pte_addr = get_hop1_pte_addr(ctx, hop1_addr, virt_addr);
+	hop1_pte_addr = get_hop1_pte_addr(ctx, mmu_prop, hop1_addr, virt_addr);
 	curr_pte = *(u64 *) (uintptr_t) hop1_pte_addr;
 
 	hop2_addr = get_alloc_next_hop_addr(ctx, curr_pte, &hop2_new);
 	if (hop2_addr == ULLONG_MAX)
 		goto err;
 
-	hop2_pte_addr = get_hop2_pte_addr(ctx, hop2_addr, virt_addr);
+	hop2_pte_addr = get_hop2_pte_addr(ctx, mmu_prop, hop2_addr, virt_addr);
 	curr_pte = *(u64 *) (uintptr_t) hop2_pte_addr;
 
 	hop3_addr = get_alloc_next_hop_addr(ctx, curr_pte, &hop3_new);
 	if (hop3_addr == ULLONG_MAX)
 		goto err;
 
-	hop3_pte_addr = get_hop3_pte_addr(ctx, hop3_addr, virt_addr);
+	hop3_pte_addr = get_hop3_pte_addr(ctx, mmu_prop, hop3_addr, virt_addr);
 	curr_pte = *(u64 *) (uintptr_t) hop3_pte_addr;
 
 	if (!is_huge) {
@@ -767,13 +799,14 @@ static int _hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr,
 		if (hop4_addr == ULLONG_MAX)
 			goto err;
 
-		hop4_pte_addr = get_hop4_pte_addr(ctx, hop4_addr, virt_addr);
+		hop4_pte_addr = get_hop4_pte_addr(ctx, mmu_prop, hop4_addr,
+							virt_addr);
 		curr_pte = *(u64 *) (uintptr_t) hop4_pte_addr;
 	}
 
 	if (hdev->dram_default_page_mapping && is_dram_addr) {
 		u64 default_pte = (prop->mmu_dram_default_page_addr &
-					PTE_PHYS_ADDR_MASK) | LAST_MASK |
+					HOP_PHYS_ADDR_MASK) | LAST_MASK |
 						PAGE_PRESENT_MASK;
 
 		if (curr_pte != default_pte) {
@@ -813,7 +846,7 @@ static int _hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr,
 		goto err;
 	}
 
-	curr_pte = (phys_addr & PTE_PHYS_ADDR_MASK) | LAST_MASK
+	curr_pte = (phys_addr & HOP_PHYS_ADDR_MASK) | LAST_MASK
 			| PAGE_PRESENT_MASK;
 
 	if (is_huge)
@@ -823,25 +856,25 @@ static int _hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr,
 
 	if (hop1_new) {
 		curr_pte =
-			(hop1_addr & PTE_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
+			(hop1_addr & HOP_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
 		write_pte(ctx, hop0_pte_addr, curr_pte);
 	}
 	if (hop2_new) {
 		curr_pte =
-			(hop2_addr & PTE_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
+			(hop2_addr & HOP_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
 		write_pte(ctx, hop1_pte_addr, curr_pte);
 		get_pte(ctx, hop1_addr);
 	}
 	if (hop3_new) {
 		curr_pte =
-			(hop3_addr & PTE_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
+			(hop3_addr & HOP_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
 		write_pte(ctx, hop2_pte_addr, curr_pte);
 		get_pte(ctx, hop2_addr);
 	}
 
 	if (!is_huge) {
 		if (hop4_new) {
-			curr_pte = (hop4_addr & PTE_PHYS_ADDR_MASK) |
+			curr_pte = (hop4_addr & HOP_PHYS_ADDR_MASK) |
 					PAGE_PRESENT_MASK;
 			write_pte(ctx, hop3_pte_addr, curr_pte);
 			get_pte(ctx, hop3_addr);
@@ -890,25 +923,36 @@ err:
 int hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, u32 page_size)
 {
 	struct hl_device *hdev = ctx->hdev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct hl_mmu_properties *mmu_prop;
 	u64 real_virt_addr, real_phys_addr;
 	u32 real_page_size, npages;
 	int i, rc, mapped_cnt = 0;
+	bool is_dram_addr;
 
 	if (!hdev->mmu_enable)
 		return 0;
 
+	is_dram_addr = hl_mem_area_inside_range(virt_addr, prop->dmmu.page_size,
+				prop->va_space_dram_start_address,
+				prop->va_space_dram_end_address);
+
+	mmu_prop = is_dram_addr ? &prop->dmmu : &prop->pmmu;
+
 	/*
-	 * The H/W handles mapping of 4KB/2MB page. Hence if the host page size
-	 * is bigger, we break it to sub-pages and map them separately.
+	 * The H/W handles mapping of specific page sizes. Hence if the page
+	 * size is bigger, we break it to sub-pages and map them separately.
 	 */
-	if ((page_size % PAGE_SIZE_2MB) == 0) {
-		real_page_size = PAGE_SIZE_2MB;
-	} else if ((page_size % PAGE_SIZE_4KB) == 0) {
-		real_page_size = PAGE_SIZE_4KB;
+	if ((page_size % mmu_prop->huge_page_size) == 0) {
+		real_page_size = mmu_prop->huge_page_size;
+	} else if ((page_size % mmu_prop->page_size) == 0) {
+		real_page_size = mmu_prop->page_size;
 	} else {
 		dev_err(hdev->dev,
-			"page size of %u is not 4KB nor 2MB aligned, can't map\n",
-				page_size);
+			"page size of %u is not %dKB nor %dMB aligned, can't unmap\n",
+			page_size,
+			mmu_prop->page_size >> 10,
+			mmu_prop->huge_page_size >> 20);
 
 		return -EFAULT;
 	}
@@ -923,7 +967,7 @@ int hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, u32 page_size)
 
 	for (i = 0 ; i < npages ; i++) {
 		rc = _hl_mmu_map(ctx, real_virt_addr, real_phys_addr,
-				real_page_size);
+				real_page_size, is_dram_addr);
 		if (rc)
 			goto err;
 
@@ -937,7 +981,7 @@ int hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, u32 page_size)
 err:
 	real_virt_addr = virt_addr;
 	for (i = 0 ; i < mapped_cnt ; i++) {
-		if (_hl_mmu_unmap(ctx, real_virt_addr))
+		if (_hl_mmu_unmap(ctx, real_virt_addr, is_dram_addr))
 			dev_warn_ratelimited(hdev->dev,
 				"failed to unmap va: 0x%llx\n", real_virt_addr);
 
diff --git a/drivers/misc/hpilo.h b/drivers/misc/hpilo.h
index 94dfb9e40e29..1aa433a7f66c 100644
--- a/drivers/misc/hpilo.h
+++ b/drivers/misc/hpilo.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * linux/drivers/char/hpilo.h
  *
diff --git a/drivers/misc/ibmvmc.h b/drivers/misc/ibmvmc.h
index e140ada8fe2c..0e1756fffeae 100644
--- a/drivers/misc/ibmvmc.h
+++ b/drivers/misc/ibmvmc.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0+
- *
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
  * linux/drivers/misc/ibmvmc.h
  *
  * IBM Power Systems Virtual Management Channel Support.
diff --git a/drivers/misc/lis3lv02d/lis3lv02d.c b/drivers/misc/lis3lv02d/lis3lv02d.c
index 057d7bbde402..dd65cedf3b12 100644
--- a/drivers/misc/lis3lv02d/lis3lv02d.c
+++ b/drivers/misc/lis3lv02d/lis3lv02d.c
@@ -16,7 +16,7 @@
 #include <linux/types.h>
 #include <linux/platform_device.h>
 #include <linux/interrupt.h>
-#include <linux/input-polldev.h>
+#include <linux/input.h>
 #include <linux/delay.h>
 #include <linux/wait.h>
 #include <linux/poll.h>
@@ -434,23 +434,23 @@ int lis3lv02d_poweron(struct lis3lv02d *lis3)
 EXPORT_SYMBOL_GPL(lis3lv02d_poweron);
 
 
-static void lis3lv02d_joystick_poll(struct input_polled_dev *pidev)
+static void lis3lv02d_joystick_poll(struct input_dev *input)
 {
-	struct lis3lv02d *lis3 = pidev->private;
+	struct lis3lv02d *lis3 = input_get_drvdata(input);
 	int x, y, z;
 
 	mutex_lock(&lis3->mutex);
 	lis3lv02d_get_xyz(lis3, &x, &y, &z);
-	input_report_abs(pidev->input, ABS_X, x);
-	input_report_abs(pidev->input, ABS_Y, y);
-	input_report_abs(pidev->input, ABS_Z, z);
-	input_sync(pidev->input);
+	input_report_abs(input, ABS_X, x);
+	input_report_abs(input, ABS_Y, y);
+	input_report_abs(input, ABS_Z, z);
+	input_sync(input);
 	mutex_unlock(&lis3->mutex);
 }
 
-static void lis3lv02d_joystick_open(struct input_polled_dev *pidev)
+static int lis3lv02d_joystick_open(struct input_dev *input)
 {
-	struct lis3lv02d *lis3 = pidev->private;
+	struct lis3lv02d *lis3 = input_get_drvdata(input);
 
 	if (lis3->pm_dev)
 		pm_runtime_get_sync(lis3->pm_dev);
@@ -461,12 +461,14 @@ static void lis3lv02d_joystick_open(struct input_polled_dev *pidev)
 	 * Update coordinates for the case where poll interval is 0 and
 	 * the chip in running purely under interrupt control
 	 */
-	lis3lv02d_joystick_poll(pidev);
+	lis3lv02d_joystick_poll(input);
+
+	return 0;
 }
 
-static void lis3lv02d_joystick_close(struct input_polled_dev *pidev)
+static void lis3lv02d_joystick_close(struct input_dev *input)
 {
-	struct lis3lv02d *lis3 = pidev->private;
+	struct lis3lv02d *lis3 = input_get_drvdata(input);
 
 	atomic_set(&lis3->wake_thread, 0);
 	if (lis3->pm_dev)
@@ -497,7 +499,7 @@ out:
 
 static void lis302dl_interrupt_handle_click(struct lis3lv02d *lis3)
 {
-	struct input_dev *dev = lis3->idev->input;
+	struct input_dev *dev = lis3->idev;
 	u8 click_src;
 
 	mutex_lock(&lis3->mutex);
@@ -677,26 +679,19 @@ int lis3lv02d_joystick_enable(struct lis3lv02d *lis3)
 	if (lis3->idev)
 		return -EINVAL;
 
-	lis3->idev = input_allocate_polled_device();
-	if (!lis3->idev)
+	input_dev = input_allocate_device();
+	if (!input_dev)
 		return -ENOMEM;
 
-	lis3->idev->poll = lis3lv02d_joystick_poll;
-	lis3->idev->open = lis3lv02d_joystick_open;
-	lis3->idev->close = lis3lv02d_joystick_close;
-	lis3->idev->poll_interval = MDPS_POLL_INTERVAL;
-	lis3->idev->poll_interval_min = MDPS_POLL_MIN;
-	lis3->idev->poll_interval_max = MDPS_POLL_MAX;
-	lis3->idev->private = lis3;
-	input_dev = lis3->idev->input;
-
 	input_dev->name       = "ST LIS3LV02DL Accelerometer";
 	input_dev->phys       = DRIVER_NAME "/input0";
 	input_dev->id.bustype = BUS_HOST;
 	input_dev->id.vendor  = 0;
 	input_dev->dev.parent = &lis3->pdev->dev;
 
-	set_bit(EV_ABS, input_dev->evbit);
+	input_dev->open = lis3lv02d_joystick_open;
+	input_dev->close = lis3lv02d_joystick_close;
+
 	max_val = (lis3->mdps_max_val * lis3->scale) / LIS3_ACCURACY;
 	if (lis3->whoami == WAI_12B) {
 		fuzz = LIS3_DEFAULT_FUZZ_12B;
@@ -712,17 +707,32 @@ int lis3lv02d_joystick_enable(struct lis3lv02d *lis3)
 	input_set_abs_params(input_dev, ABS_Y, -max_val, max_val, fuzz, flat);
 	input_set_abs_params(input_dev, ABS_Z, -max_val, max_val, fuzz, flat);
 
+	input_set_drvdata(input_dev, lis3);
+	lis3->idev = input_dev;
+
+	err = input_setup_polling(input_dev, lis3lv02d_joystick_poll);
+	if (err)
+		goto err_free_input;
+
+	input_set_poll_interval(input_dev, MDPS_POLL_INTERVAL);
+	input_set_min_poll_interval(input_dev, MDPS_POLL_MIN);
+	input_set_max_poll_interval(input_dev, MDPS_POLL_MAX);
+
 	lis3->mapped_btns[0] = lis3lv02d_get_axis(abs(lis3->ac.x), btns);
 	lis3->mapped_btns[1] = lis3lv02d_get_axis(abs(lis3->ac.y), btns);
 	lis3->mapped_btns[2] = lis3lv02d_get_axis(abs(lis3->ac.z), btns);
 
-	err = input_register_polled_device(lis3->idev);
-	if (err) {
-		input_free_polled_device(lis3->idev);
-		lis3->idev = NULL;
-	}
+	err = input_register_device(lis3->idev);
+	if (err)
+		goto err_free_input;
 
+	return 0;
+
+err_free_input:
+	input_free_device(input_dev);
+	lis3->idev = NULL;
 	return err;
+
 }
 EXPORT_SYMBOL_GPL(lis3lv02d_joystick_enable);
 
@@ -738,8 +748,7 @@ void lis3lv02d_joystick_disable(struct lis3lv02d *lis3)
 
 	if (lis3->irq)
 		misc_deregister(&lis3->miscdev);
-	input_unregister_polled_device(lis3->idev);
-	input_free_polled_device(lis3->idev);
+	input_unregister_device(lis3->idev);
 	lis3->idev = NULL;
 }
 EXPORT_SYMBOL_GPL(lis3lv02d_joystick_disable);
@@ -895,10 +904,9 @@ static void lis3lv02d_8b_configure(struct lis3lv02d *lis3,
 			(p->click_thresh_y << 4));
 
 		if (lis3->idev) {
-			struct input_dev *input_dev = lis3->idev->input;
-			input_set_capability(input_dev, EV_KEY, BTN_X);
-			input_set_capability(input_dev, EV_KEY, BTN_Y);
-			input_set_capability(input_dev, EV_KEY, BTN_Z);
+			input_set_capability(lis3->idev, EV_KEY, BTN_X);
+			input_set_capability(lis3->idev, EV_KEY, BTN_Y);
+			input_set_capability(lis3->idev, EV_KEY, BTN_Z);
 		}
 	}
 
diff --git a/drivers/misc/lis3lv02d/lis3lv02d.h b/drivers/misc/lis3lv02d/lis3lv02d.h
index 1b0c99883c57..c394c0b08519 100644
--- a/drivers/misc/lis3lv02d/lis3lv02d.h
+++ b/drivers/misc/lis3lv02d/lis3lv02d.h
@@ -6,7 +6,7 @@
  *  Copyright (C) 2008-2009 Eric Piel
  */
 #include <linux/platform_device.h>
-#include <linux/input-polldev.h>
+#include <linux/input.h>
 #include <linux/regulator/consumer.h>
 #include <linux/miscdevice.h>
 
@@ -281,7 +281,7 @@ struct lis3lv02d {
 					* (1/1000th of earth gravity)
 					*/
 
-	struct input_polled_dev	*idev;     /* input device */
+	struct input_dev	*idev;     /* input device */
 	struct platform_device	*pdev;     /* platform device */
 	struct regulator_bulk_data regulators[2];
 	atomic_t		count;     /* interrupt count after last read */
diff --git a/drivers/misc/mei/bus-fixup.c b/drivers/misc/mei/bus-fixup.c
index 0a2b99e1af45..9ad9c01ddf41 100644
--- a/drivers/misc/mei/bus-fixup.c
+++ b/drivers/misc/mei/bus-fixup.c
@@ -46,8 +46,6 @@ static const uuid_le mei_nfc_info_guid = MEI_UUID_NFC_INFO;
  */
 static void number_of_connections(struct mei_cl_device *cldev)
 {
-	dev_dbg(&cldev->dev, "running hook %s\n", __func__);
-
 	if (cldev->me_cl->props.max_number_of_connections > 1)
 		cldev->do_match = 0;
 }
@@ -59,8 +57,6 @@ static void number_of_connections(struct mei_cl_device *cldev)
  */
 static void blacklist(struct mei_cl_device *cldev)
 {
-	dev_dbg(&cldev->dev, "running hook %s\n", __func__);
-
 	cldev->do_match = 0;
 }
 
@@ -71,8 +67,6 @@ static void blacklist(struct mei_cl_device *cldev)
  */
 static void whitelist(struct mei_cl_device *cldev)
 {
-	dev_dbg(&cldev->dev, "running hook %s\n", __func__);
-
 	cldev->do_match = 1;
 }
 
@@ -256,7 +250,6 @@ static void mei_wd(struct mei_cl_device *cldev)
 {
 	struct pci_dev *pdev = to_pci_dev(cldev->dev.parent);
 
-	dev_dbg(&cldev->dev, "running hook %s\n", __func__);
 	if (pdev->device == MEI_DEV_ID_WPT_LP ||
 	    pdev->device == MEI_DEV_ID_SPT ||
 	    pdev->device == MEI_DEV_ID_SPT_H)
@@ -410,8 +403,6 @@ static void mei_nfc(struct mei_cl_device *cldev)
 
 	bus = cldev->bus;
 
-	dev_dbg(&cldev->dev, "running hook %s\n", __func__);
-
 	mutex_lock(&bus->device_lock);
 	/* we need to connect to INFO GUID */
 	cl = mei_cl_alloc_linked(bus);
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index 985bd4fd3328..a0a495c95e3c 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -791,11 +791,44 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *a,
 }
 static DEVICE_ATTR_RO(modalias);
 
+static ssize_t max_conn_show(struct device *dev, struct device_attribute *a,
+			     char *buf)
+{
+	struct mei_cl_device *cldev = to_mei_cl_device(dev);
+	u8 maxconn = mei_me_cl_max_conn(cldev->me_cl);
+
+	return scnprintf(buf, PAGE_SIZE, "%d", maxconn);
+}
+static DEVICE_ATTR_RO(max_conn);
+
+static ssize_t fixed_show(struct device *dev, struct device_attribute *a,
+			  char *buf)
+{
+	struct mei_cl_device *cldev = to_mei_cl_device(dev);
+	u8 fixed = mei_me_cl_fixed(cldev->me_cl);
+
+	return scnprintf(buf, PAGE_SIZE, "%d", fixed);
+}
+static DEVICE_ATTR_RO(fixed);
+
+static ssize_t max_len_show(struct device *dev, struct device_attribute *a,
+			    char *buf)
+{
+	struct mei_cl_device *cldev = to_mei_cl_device(dev);
+	u32 maxlen = mei_me_cl_max_len(cldev->me_cl);
+
+	return scnprintf(buf, PAGE_SIZE, "%u", maxlen);
+}
+static DEVICE_ATTR_RO(max_len);
+
 static struct attribute *mei_cldev_attrs[] = {
 	&dev_attr_name.attr,
 	&dev_attr_uuid.attr,
 	&dev_attr_version.attr,
 	&dev_attr_modalias.attr,
+	&dev_attr_max_conn.attr,
+	&dev_attr_fixed.attr,
+	&dev_attr_max_len.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(mei_cldev);
@@ -873,15 +906,16 @@ static const struct device_type mei_cl_device_type = {
 
 /**
  * mei_cl_bus_set_name - set device name for me client device
+ *  <controller>-<client device>
+ *  Example: 0000:00:16.0-55213584-9a29-4916-badf-0fb7ed682aeb
  *
  * @cldev: me client device
  */
 static inline void mei_cl_bus_set_name(struct mei_cl_device *cldev)
 {
-	dev_set_name(&cldev->dev, "mei:%s:%pUl:%02X",
-		     cldev->name,
-		     mei_me_cl_uuid(cldev->me_cl),
-		     mei_me_cl_ver(cldev->me_cl));
+	dev_set_name(&cldev->dev, "%s-%pUl",
+		     dev_name(cldev->bus->dev),
+		     mei_me_cl_uuid(cldev->me_cl));
 }
 
 /**
diff --git a/drivers/misc/mei/client.h b/drivers/misc/mei/client.h
index c1f9e810cf81..2f8954def591 100644
--- a/drivers/misc/mei/client.h
+++ b/drivers/misc/mei/client.h
@@ -69,6 +69,42 @@ static inline u8 mei_me_cl_ver(const struct mei_me_client *me_cl)
 	return me_cl->props.protocol_version;
 }
 
+/**
+ * mei_me_cl_max_conn - return me client max number of connections
+ *
+ * @me_cl: me client
+ *
+ * Return: me client max number of connections
+ */
+static inline u8 mei_me_cl_max_conn(const struct mei_me_client *me_cl)
+{
+	return me_cl->props.max_number_of_connections;
+}
+
+/**
+ * mei_me_cl_fixed - return me client fixed address, if any
+ *
+ * @me_cl: me client
+ *
+ * Return: me client fixed address
+ */
+static inline u8 mei_me_cl_fixed(const struct mei_me_client *me_cl)
+{
+	return me_cl->props.fixed_address;
+}
+
+/**
+ * mei_me_cl_max_len - return me client max msg length
+ *
+ * @me_cl: me client
+ *
+ * Return: me client max msg length
+ */
+static inline u32 mei_me_cl_max_len(const struct mei_me_client *me_cl)
+{
+	return me_cl->props.max_msg_length;
+}
+
 /*
  * MEI IO Functions
  */
diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index c09f8bb49495..7cd67fb2365d 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -81,6 +81,7 @@
 
 #define MEI_DEV_ID_CMP_LP     0x02e0  /* Comet Point LP */
 #define MEI_DEV_ID_CMP_LP_3   0x02e4  /* Comet Point LP 3 (iTouch) */
+#define MEI_DEV_ID_CMP_V      0xA3BA  /* Comet Point Lake V */
 
 #define MEI_DEV_ID_ICP_LP     0x34E0  /* Ice Lake Point LP */
 
@@ -162,7 +163,8 @@ access to ME_CBD */
 #define ME_IS_HRA         0x00000002
 /* ME Interrupt Enable HRA - host read only access to ME_IE */
 #define ME_IE_HRA         0x00000001
-
+/* TRC control shadow register */
+#define ME_TRC            0x00000030
 
 /* H_HPG_CSR register bits */
 #define H_HPG_CSR_PGIHEXR 0x00000001
diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c
index c4f6991d3028..668418d7ea77 100644
--- a/drivers/misc/mei/hw-me.c
+++ b/drivers/misc/mei/hw-me.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (c) 2003-2018, Intel Corporation. All rights reserved.
+ * Copyright (c) 2003-2019, Intel Corporation. All rights reserved.
  * Intel Management Engine Interface (Intel MEI) Linux driver
  */
 
@@ -173,6 +173,27 @@ static inline void mei_me_d0i3c_write(struct mei_device *dev, u32 reg)
 }
 
 /**
+ * mei_me_trc_status - read trc status register
+ *
+ * @dev: mei device
+ * @trc: trc status register value
+ *
+ * Return: 0 on success, error otherwise
+ */
+static int mei_me_trc_status(struct mei_device *dev, u32 *trc)
+{
+	struct mei_me_hw *hw = to_me_hw(dev);
+
+	if (!hw->cfg->hw_trc_supported)
+		return -EOPNOTSUPP;
+
+	*trc = mei_me_reg_read(hw, ME_TRC);
+	trace_mei_reg_read(dev->dev, "ME_TRC", ME_TRC, *trc);
+
+	return 0;
+}
+
+/**
  * mei_me_fw_status - read fw status register from pci config space
  *
  * @dev: mei device
@@ -183,20 +204,19 @@ static inline void mei_me_d0i3c_write(struct mei_device *dev, u32 reg)
 static int mei_me_fw_status(struct mei_device *dev,
 			    struct mei_fw_status *fw_status)
 {
-	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	struct mei_me_hw *hw = to_me_hw(dev);
 	const struct mei_fw_status *fw_src = &hw->cfg->fw_status;
 	int ret;
 	int i;
 
-	if (!fw_status)
+	if (!fw_status || !hw->read_fws)
 		return -EINVAL;
 
 	fw_status->count = fw_src->count;
 	for (i = 0; i < fw_src->count && i < MEI_FW_STATUS_MAX; i++) {
-		ret = pci_read_config_dword(pdev, fw_src->status[i],
-					    &fw_status->status[i]);
-		trace_mei_pci_cfg_read(dev->dev, "PCI_CFG_HSF_X",
+		ret = hw->read_fws(dev, fw_src->status[i],
+				   &fw_status->status[i]);
+		trace_mei_pci_cfg_read(dev->dev, "PCI_CFG_HFS_X",
 				       fw_src->status[i],
 				       fw_status->status[i]);
 		if (ret)
@@ -210,19 +230,26 @@ static int mei_me_fw_status(struct mei_device *dev,
  * mei_me_hw_config - configure hw dependent settings
  *
  * @dev: mei device
+ *
+ * Return:
+ *  * -EINVAL when read_fws is not set
+ *  * 0 on success
+ *
  */
-static void mei_me_hw_config(struct mei_device *dev)
+static int mei_me_hw_config(struct mei_device *dev)
 {
-	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	struct mei_me_hw *hw = to_me_hw(dev);
 	u32 hcsr, reg;
 
+	if (WARN_ON(!hw->read_fws))
+		return -EINVAL;
+
 	/* Doesn't change in runtime */
 	hcsr = mei_hcsr_read(dev);
 	hw->hbuf_depth = (hcsr & H_CBD) >> 24;
 
 	reg = 0;
-	pci_read_config_dword(pdev, PCI_CFG_HFS_1, &reg);
+	hw->read_fws(dev, PCI_CFG_HFS_1, &reg);
 	trace_mei_pci_cfg_read(dev->dev, "PCI_CFG_HFS_1", PCI_CFG_HFS_1, reg);
 	hw->d0i3_supported =
 		((reg & PCI_CFG_HFS_1_D0I3_MSK) == PCI_CFG_HFS_1_D0I3_MSK);
@@ -233,6 +260,8 @@ static void mei_me_hw_config(struct mei_device *dev)
 		if (reg & H_D0I3C_I3)
 			hw->pg_state = MEI_PG_ON;
 	}
+
+	return 0;
 }
 
 /**
@@ -269,7 +298,7 @@ static inline void me_intr_disable(struct mei_device *dev, u32 hcsr)
 }
 
 /**
- * mei_me_intr_clear - clear and stop interrupts
+ * me_intr_clear - clear and stop interrupts
  *
  * @dev: the device structure
  * @hcsr: supplied hcsr register value
@@ -323,9 +352,9 @@ static void mei_me_intr_disable(struct mei_device *dev)
  */
 static void mei_me_synchronize_irq(struct mei_device *dev)
 {
-	struct pci_dev *pdev = to_pci_dev(dev->dev);
+	struct mei_me_hw *hw = to_me_hw(dev);
 
-	synchronize_irq(pdev->irq);
+	synchronize_irq(hw->irq);
 }
 
 /**
@@ -1294,6 +1323,7 @@ end:
 
 static const struct mei_hw_ops mei_me_hw_ops = {
 
+	.trc_status = mei_me_trc_status,
 	.fw_status = mei_me_fw_status,
 	.pg_state  = mei_me_pg_state,
 
@@ -1384,6 +1414,9 @@ static bool mei_me_fw_type_sps(struct pci_dev *pdev)
 	.dma_size[DMA_DSCR_DEVICE] = SZ_128K, \
 	.dma_size[DMA_DSCR_CTRL] = PAGE_SIZE
 
+#define MEI_CFG_TRC \
+	.hw_trc_supported = 1
+
 /* ICH Legacy devices */
 static const struct mei_cfg mei_me_ich_cfg = {
 	MEI_CFG_ICH_HFS,
@@ -1432,6 +1465,14 @@ static const struct mei_cfg mei_me_pch12_cfg = {
 	MEI_CFG_DMA_128,
 };
 
+/* Tiger Lake and newer devices */
+static const struct mei_cfg mei_me_pch15_cfg = {
+	MEI_CFG_PCH8_HFS,
+	MEI_CFG_FW_VER_SUPP,
+	MEI_CFG_DMA_128,
+	MEI_CFG_TRC,
+};
+
 /*
  * mei_cfg_list - A list of platform platform specific configurations.
  * Note: has to be synchronized with  enum mei_cfg_idx.
@@ -1446,6 +1487,7 @@ static const struct mei_cfg *const mei_cfg_list[] = {
 	[MEI_ME_PCH8_CFG] = &mei_me_pch8_cfg,
 	[MEI_ME_PCH8_SPS_CFG] = &mei_me_pch8_sps_cfg,
 	[MEI_ME_PCH12_CFG] = &mei_me_pch12_cfg,
+	[MEI_ME_PCH15_CFG] = &mei_me_pch15_cfg,
 };
 
 const struct mei_cfg *mei_me_get_cfg(kernel_ulong_t idx)
@@ -1461,19 +1503,19 @@ const struct mei_cfg *mei_me_get_cfg(kernel_ulong_t idx)
 /**
  * mei_me_dev_init - allocates and initializes the mei device structure
  *
- * @pdev: The pci device structure
+ * @parent: device associated with physical device (pci/platform)
  * @cfg: per device generation config
  *
  * Return: The mei_device pointer on success, NULL on failure.
  */
-struct mei_device *mei_me_dev_init(struct pci_dev *pdev,
+struct mei_device *mei_me_dev_init(struct device *parent,
 				   const struct mei_cfg *cfg)
 {
 	struct mei_device *dev;
 	struct mei_me_hw *hw;
 	int i;
 
-	dev = devm_kzalloc(&pdev->dev, sizeof(struct mei_device) +
+	dev = devm_kzalloc(parent, sizeof(struct mei_device) +
 			   sizeof(struct mei_me_hw), GFP_KERNEL);
 	if (!dev)
 		return NULL;
@@ -1483,7 +1525,7 @@ struct mei_device *mei_me_dev_init(struct pci_dev *pdev,
 	for (i = 0; i < DMA_DSCR_NUM; i++)
 		dev->dr_dscr[i].size = cfg->dma_size[i];
 
-	mei_device_init(dev, &pdev->dev, &mei_me_hw_ops);
+	mei_device_init(dev, parent, &mei_me_hw_ops);
 	hw->cfg = cfg;
 
 	dev->fw_f_fw_ver_supported = cfg->fw_ver_supported;
diff --git a/drivers/misc/mei/hw-me.h b/drivers/misc/mei/hw-me.h
index 1d8794828cbc..4a8d4dcd5a91 100644
--- a/drivers/misc/mei/hw-me.h
+++ b/drivers/misc/mei/hw-me.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
- * Copyright (c) 2012-2018, Intel Corporation. All rights reserved.
+ * Copyright (c) 2012-2019, Intel Corporation. All rights reserved.
  * Intel Management Engine Interface (Intel MEI) Linux driver
  */
 
@@ -21,12 +21,14 @@
  * @quirk_probe: device exclusion quirk
  * @dma_size: device DMA buffers size
  * @fw_ver_supported: is fw version retrievable from FW
+ * @hw_trc_supported: does the hw support trc register
  */
 struct mei_cfg {
 	const struct mei_fw_status fw_status;
 	bool (*quirk_probe)(struct pci_dev *pdev);
 	size_t dma_size[DMA_DSCR_NUM];
 	u32 fw_ver_supported:1;
+	u32 hw_trc_supported:1;
 };
 
 
@@ -42,16 +44,20 @@ struct mei_cfg {
  *
  * @cfg: per device generation config and ops
  * @mem_addr: io memory address
+ * @irq: irq number
  * @pg_state: power gating state
  * @d0i3_supported: di03 support
  * @hbuf_depth: depth of hardware host/write buffer in slots
+ * @read_fws: read FW status register handler
  */
 struct mei_me_hw {
 	const struct mei_cfg *cfg;
 	void __iomem *mem_addr;
+	int irq;
 	enum mei_pg_state pg_state;
 	bool d0i3_supported;
 	u8 hbuf_depth;
+	int (*read_fws)(const struct mei_device *dev, int where, u32 *val);
 };
 
 #define to_me_hw(dev) (struct mei_me_hw *)((dev)->hw)
@@ -74,6 +80,7 @@ struct mei_me_hw {
  *                         servers platforms with quirk for
  *                         SPS firmware exclusion.
  * @MEI_ME_PCH12_CFG:      Platform Controller Hub Gen12 and newer
+ * @MEI_ME_PCH15_CFG:      Platform Controller Hub Gen15 and newer
  * @MEI_ME_NUM_CFG:        Upper Sentinel.
  */
 enum mei_cfg_idx {
@@ -86,12 +93,13 @@ enum mei_cfg_idx {
 	MEI_ME_PCH8_CFG,
 	MEI_ME_PCH8_SPS_CFG,
 	MEI_ME_PCH12_CFG,
+	MEI_ME_PCH15_CFG,
 	MEI_ME_NUM_CFG,
 };
 
 const struct mei_cfg *mei_me_get_cfg(kernel_ulong_t idx);
 
-struct mei_device *mei_me_dev_init(struct pci_dev *pdev,
+struct mei_device *mei_me_dev_init(struct device *parent,
 				   const struct mei_cfg *cfg);
 
 int mei_me_pg_enter_sync(struct mei_device *dev);
diff --git a/drivers/misc/mei/hw-txe.c b/drivers/misc/mei/hw-txe.c
index 5e58656b8e19..785b260b3ae9 100644
--- a/drivers/misc/mei/hw-txe.c
+++ b/drivers/misc/mei/hw-txe.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (c) 2013-2014, Intel Corporation. All rights reserved.
+ * Copyright (c) 2013-2019, Intel Corporation. All rights reserved.
  * Intel Management Engine Interface (Intel MEI) Linux driver
  */
 
@@ -660,14 +660,16 @@ static int mei_txe_fw_status(struct mei_device *dev,
 }
 
 /**
- *  mei_txe_hw_config - configure hardware at the start of the devices
+ * mei_txe_hw_config - configure hardware at the start of the devices
  *
  * @dev: the device structure
  *
  * Configure hardware at the start of the device should be done only
  *   once at the device probe time
+ *
+ * Return: always 0
  */
-static void mei_txe_hw_config(struct mei_device *dev)
+static int mei_txe_hw_config(struct mei_device *dev)
 {
 
 	struct mei_txe_hw *hw = to_txe_hw(dev);
@@ -677,6 +679,8 @@ static void mei_txe_hw_config(struct mei_device *dev)
 
 	dev_dbg(dev->dev, "aliveness_resp = 0x%08x, readiness = 0x%08x.\n",
 		hw->aliveness, hw->readiness);
+
+	return 0;
 }
 
 /**
diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c
index b9fef773e71b..bcee77768b91 100644
--- a/drivers/misc/mei/init.c
+++ b/drivers/misc/mei/init.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (c) 2012-2018, Intel Corporation. All rights reserved.
+ * Copyright (c) 2012-2019, Intel Corporation. All rights reserved.
  * Intel Management Engine Interface (Intel MEI) Linux driver
  */
 
@@ -190,7 +190,9 @@ int mei_start(struct mei_device *dev)
 	/* acknowledge interrupt and stop interrupts */
 	mei_clear_interrupts(dev);
 
-	mei_hw_config(dev);
+	ret = mei_hw_config(dev);
+	if (ret)
+		goto err;
 
 	dev_dbg(dev->dev, "reset in start the mei device.\n");
 
diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c
index 7310b476323c..4ef6e37caafc 100644
--- a/drivers/misc/mei/main.c
+++ b/drivers/misc/mei/main.c
@@ -701,6 +701,29 @@ static int mei_fasync(int fd, struct file *file, int band)
 }
 
 /**
+ * trc_show - mei device trc attribute show method
+ *
+ * @device: device pointer
+ * @attr: attribute pointer
+ * @buf:  char out buffer
+ *
+ * Return: number of the bytes printed into buf or error
+ */
+static ssize_t trc_show(struct device *device,
+			struct device_attribute *attr, char *buf)
+{
+	struct mei_device *dev = dev_get_drvdata(device);
+	u32 trc;
+	int ret;
+
+	ret = mei_trc_status(dev, &trc);
+	if (ret)
+		return ret;
+	return sprintf(buf, "%08X\n", trc);
+}
+static DEVICE_ATTR_RO(trc);
+
+/**
  * fw_status_show - mei device fw_status attribute show method
  *
  * @device: device pointer
@@ -887,6 +910,7 @@ static struct attribute *mei_attrs[] = {
 	&dev_attr_tx_queue_limit.attr,
 	&dev_attr_fw_ver.attr,
 	&dev_attr_dev_state.attr,
+	&dev_attr_trc.attr,
 	NULL
 };
 ATTRIBUTE_GROUPS(mei);
diff --git a/drivers/misc/mei/mei_dev.h b/drivers/misc/mei/mei_dev.h
index 0f2141178299..76f8ff5ff974 100644
--- a/drivers/misc/mei/mei_dev.h
+++ b/drivers/misc/mei/mei_dev.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
- * Copyright (c) 2003-2018, Intel Corporation. All rights reserved.
+ * Copyright (c) 2003-2019, Intel Corporation. All rights reserved.
  * Intel Management Engine Interface (Intel MEI) Linux driver
  */
 
@@ -260,6 +260,7 @@ struct mei_cl {
  * @hw_config        : configure hw
  *
  * @fw_status        : get fw status registers
+ * @trc_status       : get trc status register
  * @pg_state         : power gating state of the device
  * @pg_in_transition : is device now in pg transition
  * @pg_is_enabled    : is power gating enabled
@@ -287,9 +288,11 @@ struct mei_hw_ops {
 	bool (*hw_is_ready)(struct mei_device *dev);
 	int (*hw_reset)(struct mei_device *dev, bool enable);
 	int (*hw_start)(struct mei_device *dev);
-	void (*hw_config)(struct mei_device *dev);
+	int (*hw_config)(struct mei_device *dev);
 
 	int (*fw_status)(struct mei_device *dev, struct mei_fw_status *fw_sts);
+	int (*trc_status)(struct mei_device *dev, u32 *trc);
+
 	enum mei_pg_state (*pg_state)(struct mei_device *dev);
 	bool (*pg_in_transition)(struct mei_device *dev);
 	bool (*pg_is_enabled)(struct mei_device *dev);
@@ -614,9 +617,9 @@ void mei_irq_compl_handler(struct mei_device *dev, struct list_head *cmpl_list);
  */
 
 
-static inline void mei_hw_config(struct mei_device *dev)
+static inline int mei_hw_config(struct mei_device *dev)
 {
-	dev->ops->hw_config(dev);
+	return dev->ops->hw_config(dev);
 }
 
 static inline enum mei_pg_state mei_pg_state(struct mei_device *dev)
@@ -711,6 +714,13 @@ static inline int mei_count_full_read_slots(struct mei_device *dev)
 	return dev->ops->rdbuf_full_slots(dev);
 }
 
+static inline int mei_trc_status(struct mei_device *dev, u32 *trc)
+{
+	if (dev->ops->trc_status)
+		return dev->ops->trc_status(dev, trc);
+	return -EOPNOTSUPP;
+}
+
 static inline int mei_fw_status(struct mei_device *dev,
 				struct mei_fw_status *fw_status)
 {
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index 3dca63eddaa0..c845b7e40f26 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -98,12 +98,13 @@ static const struct pci_device_id mei_me_pci_tbl[] = {
 
 	{MEI_PCI_DEVICE(MEI_DEV_ID_CMP_LP, MEI_ME_PCH12_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_CMP_LP_3, MEI_ME_PCH8_CFG)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_CMP_V, MEI_ME_PCH12_CFG)},
 
 	{MEI_PCI_DEVICE(MEI_DEV_ID_ICP_LP, MEI_ME_PCH12_CFG)},
 
-	{MEI_PCI_DEVICE(MEI_DEV_ID_TGP_LP, MEI_ME_PCH12_CFG)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_TGP_LP, MEI_ME_PCH15_CFG)},
 
-	{MEI_PCI_DEVICE(MEI_DEV_ID_MCC, MEI_ME_PCH12_CFG)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_MCC, MEI_ME_PCH15_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_MCC_4, MEI_ME_PCH8_CFG)},
 
 	/* required last entry */
@@ -120,6 +121,13 @@ static inline void mei_me_set_pm_domain(struct mei_device *dev) {}
 static inline void mei_me_unset_pm_domain(struct mei_device *dev) {}
 #endif /* CONFIG_PM */
 
+static int mei_me_read_fws(const struct mei_device *dev, int where, u32 *val)
+{
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
+
+	return pci_read_config_dword(pdev, where, val);
+}
+
 /**
  * mei_me_quirk_probe - probe for devices that doesn't valid ME interface
  *
@@ -191,13 +199,15 @@ static int mei_me_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	/* allocates and initializes the mei dev structure */
-	dev = mei_me_dev_init(pdev, cfg);
+	dev = mei_me_dev_init(&pdev->dev, cfg);
 	if (!dev) {
 		err = -ENOMEM;
 		goto end;
 	}
 	hw = to_me_hw(dev);
 	hw->mem_addr = pcim_iomap_table(pdev)[0];
+	hw->irq = pdev->irq;
+	hw->read_fws = mei_me_read_fws;
 
 	pci_enable_msi(pdev);
 
diff --git a/drivers/misc/mic/Kconfig b/drivers/misc/mic/Kconfig
index 948f45bbf135..b6841ba6d922 100644
--- a/drivers/misc/mic/Kconfig
+++ b/drivers/misc/mic/Kconfig
@@ -1,8 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 menu "Intel MIC & related support"
 
-comment "Intel MIC Bus Driver"
-
 config INTEL_MIC_BUS
 	tristate "Intel MIC Bus Driver"
 	depends on 64BIT && PCI && X86
@@ -18,8 +16,6 @@ config INTEL_MIC_BUS
 	  OS and tools for MIC to use with this driver are available from
 	  <http://software.intel.com/en-us/mic-developer>.
 
-comment "SCIF Bus Driver"
-
 config SCIF_BUS
 	tristate "SCIF Bus Driver"
 	depends on 64BIT && PCI && X86
@@ -35,8 +31,6 @@ config SCIF_BUS
 	  OS and tools for MIC to use with this driver are available from
 	  <http://software.intel.com/en-us/mic-developer>.
 
-comment "VOP Bus Driver"
-
 config VOP_BUS
 	tristate "VOP Bus Driver"
 	help
@@ -51,8 +45,6 @@ config VOP_BUS
 	  OS and tools for MIC to use with this driver are available from
 	  <http://software.intel.com/en-us/mic-developer>.
 
-comment "Intel MIC Host Driver"
-
 config INTEL_MIC_HOST
 	tristate "Intel MIC Host Driver"
 	depends on 64BIT && PCI && X86
@@ -71,8 +63,6 @@ config INTEL_MIC_HOST
 	  OS and tools for MIC to use with this driver are available from
 	  <http://software.intel.com/en-us/mic-developer>.
 
-comment "Intel MIC Card Driver"
-
 config INTEL_MIC_CARD
 	tristate "Intel MIC Card Driver"
 	depends on 64BIT && X86
@@ -90,8 +80,6 @@ config INTEL_MIC_CARD
 	  For more information see
 	  <http://software.intel.com/en-us/mic-developer>.
 
-comment "SCIF Driver"
-
 config SCIF
 	tristate "SCIF Driver"
 	depends on 64BIT && PCI && X86 && SCIF_BUS && IOMMU_SUPPORT
@@ -110,8 +98,6 @@ config SCIF
 	  OS and tools for MIC to use with this driver are available from
 	  <http://software.intel.com/en-us/mic-developer>.
 
-comment "Intel MIC Coprocessor State Management (COSM) Drivers"
-
 config MIC_COSM
 	tristate "Intel MIC Coprocessor State Management (COSM) Drivers"
 	depends on 64BIT && PCI && X86 && SCIF
@@ -128,8 +114,6 @@ config MIC_COSM
 	  OS and tools for MIC to use with this driver are available from
 	  <http://software.intel.com/en-us/mic-developer>.
 
-comment "VOP Driver"
-
 config VOP
 	tristate "VOP Driver"
 	depends on VOP_BUS
diff --git a/drivers/misc/ocxl/ocxl_internal.h b/drivers/misc/ocxl/ocxl_internal.h
index 97415afd79f3..345bf843a38e 100644
--- a/drivers/misc/ocxl/ocxl_internal.h
+++ b/drivers/misc/ocxl/ocxl_internal.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: GPL-2.0+ */
 // Copyright 2017 IBM Corp.
 #ifndef _OCXL_INTERNAL_H_
 #define _OCXL_INTERNAL_H_
diff --git a/drivers/misc/ocxl/trace.h b/drivers/misc/ocxl/trace.h
index 024f417e7e01..17e21cb2addd 100644
--- a/drivers/misc/ocxl/trace.h
+++ b/drivers/misc/ocxl/trace.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: GPL-2.0+ */
 // Copyright 2017 IBM Corp.
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM ocxl
diff --git a/drivers/misc/sgi-gru/gruprocfs.c b/drivers/misc/sgi-gru/gruprocfs.c
index 3a8d76d1ccae..2817f4751306 100644
--- a/drivers/misc/sgi-gru/gruprocfs.c
+++ b/drivers/misc/sgi-gru/gruprocfs.c
@@ -119,7 +119,7 @@ static int mcs_statistics_show(struct seq_file *s, void *p)
 		"cch_interrupt_sync", "cch_deallocate", "tfh_write_only",
 		"tfh_write_restart", "tgh_invalidate"};
 
-	seq_printf(s, "%-20s%12s%12s%12s\n", "#id", "count", "aver-clks", "max-clks");
+	seq_puts(s, "#id                        count   aver-clks    max-clks\n");
 	for (op = 0; op < mcsop_last; op++) {
 		count = atomic_long_read(&mcs_op_statistics[op].count);
 		total = atomic_long_read(&mcs_op_statistics[op].total);
@@ -165,8 +165,7 @@ static int cch_seq_show(struct seq_file *file, void *data)
 	const char *mode[] = { "??", "UPM", "INTR", "OS_POLL" };
 
 	if (gid == 0)
-		seq_printf(file, "#%5s%5s%6s%7s%9s%6s%8s%8s\n", "gid", "bid",
-			   "ctx#", "asid", "pid", "cbrs", "dsbytes", "mode");
+		seq_puts(file, "#  gid  bid  ctx#   asid      pid  cbrs dsbytes    mode\n");
 	if (gru)
 		for (i = 0; i < GRU_NUM_CCH; i++) {
 			ts = gru->gs_gts[i];
@@ -191,10 +190,8 @@ static int gru_seq_show(struct seq_file *file, void *data)
 	struct gru_state *gru = GID_TO_GRU(gid);
 
 	if (gid == 0) {
-		seq_printf(file, "#%5s%5s%7s%6s%6s%8s%6s%6s\n", "gid", "nid",
-			   "ctx", "cbr", "dsr", "ctx", "cbr", "dsr");
-		seq_printf(file, "#%5s%5s%7s%6s%6s%8s%6s%6s\n", "", "", "busy",
-			   "busy", "busy", "free", "free", "free");
+		seq_puts(file, "#  gid  nid    ctx   cbr   dsr     ctx   cbr   dsr\n");
+		seq_puts(file, "#             busy  busy  busy    free  free  free\n");
 	}
 	if (gru) {
 		ctxfree = GRU_NUM_CCH - gru->gs_active_contexts;
diff --git a/drivers/misc/ti-st/st_core.c b/drivers/misc/ti-st/st_core.c
index 7d9e23aa0b92..2ae9948a91e1 100644
--- a/drivers/misc/ti-st/st_core.c
+++ b/drivers/misc/ti-st/st_core.c
@@ -708,7 +708,6 @@ EXPORT_SYMBOL_GPL(st_unregister);
  */
 static int st_tty_open(struct tty_struct *tty)
 {
-	int err = 0;
 	struct st_data_s *st_gdata;
 	pr_info("%s ", __func__);
 
@@ -731,7 +730,8 @@ static int st_tty_open(struct tty_struct *tty)
 	 */
 	st_kim_complete(st_gdata->kim_data);
 	pr_debug("done %s", __func__);
-	return err;
+
+	return 0;
 }
 
 static void st_tty_close(struct tty_struct *tty)
diff --git a/drivers/nvmem/Kconfig b/drivers/nvmem/Kconfig
index c2ec750cae6e..73567e922491 100644
--- a/drivers/nvmem/Kconfig
+++ b/drivers/nvmem/Kconfig
@@ -50,6 +50,7 @@ config NVMEM_IMX_OCOTP
 config NVMEM_IMX_OCOTP_SCU
 	tristate "i.MX8 SCU On-Chip OTP Controller support"
 	depends on IMX_SCU
+	depends on HAVE_ARM_SMCCC
 	help
 	  This is a driver for the SCU On-Chip OTP Controller (OCOTP)
 	  available on i.MX8 SoCs.
@@ -119,6 +120,17 @@ config ROCKCHIP_EFUSE
 	  This driver can also be built as a module. If so, the module
 	  will be called nvmem_rockchip_efuse.
 
+config ROCKCHIP_OTP
+	tristate "Rockchip OTP controller support"
+	depends on ARCH_ROCKCHIP || COMPILE_TEST
+	depends on HAS_IOMEM
+	help
+	  This is a simple drive to dump specified values of Rockchip SoC
+	  from otp, such as cpu-leakage.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called nvmem_rockchip_otp.
+
 config NVMEM_BCM_OCOTP
 	tristate "Broadcom On-Chip OTP Controller support"
 	depends on ARCH_BCM_IPROC || COMPILE_TEST
@@ -230,4 +242,15 @@ config NVMEM_ZYNQMP
 
 	  If sure, say yes. If unsure, say no.
 
+config SPRD_EFUSE
+	tristate "Spreadtrum SoC eFuse Support"
+	depends on ARCH_SPRD || COMPILE_TEST
+	depends on HAS_IOMEM
+	help
+	  This is a simple driver to dump specified values of Spreadtrum
+	  SoCs from eFuse.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called nvmem-sprd-efuse.
+
 endif
diff --git a/drivers/nvmem/Makefile b/drivers/nvmem/Makefile
index e5c153d99a67..9e667823edb3 100644
--- a/drivers/nvmem/Makefile
+++ b/drivers/nvmem/Makefile
@@ -30,6 +30,8 @@ obj-$(CONFIG_QCOM_QFPROM)	+= nvmem_qfprom.o
 nvmem_qfprom-y			:= qfprom.o
 obj-$(CONFIG_ROCKCHIP_EFUSE)	+= nvmem_rockchip_efuse.o
 nvmem_rockchip_efuse-y		:= rockchip-efuse.o
+obj-$(CONFIG_ROCKCHIP_OTP)	+= nvmem-rockchip-otp.o
+nvmem-rockchip-otp-y		:= rockchip-otp.o
 obj-$(CONFIG_NVMEM_SUNXI_SID)	+= nvmem_sunxi_sid.o
 nvmem_stm32_romem-y 		:= stm32-romem.o
 obj-$(CONFIG_NVMEM_STM32_ROMEM) += nvmem_stm32_romem.o
@@ -50,3 +52,5 @@ obj-$(CONFIG_SC27XX_EFUSE)	+= nvmem-sc27xx-efuse.o
 nvmem-sc27xx-efuse-y		:= sc27xx-efuse.o
 obj-$(CONFIG_NVMEM_ZYNQMP)	+= nvmem_zynqmp_nvmem.o
 nvmem_zynqmp_nvmem-y		:= zynqmp_nvmem.o
+obj-$(CONFIG_SPRD_EFUSE)	+= nvmem_sprd_efuse.o
+nvmem_sprd_efuse-y		:= sprd-efuse.o
diff --git a/drivers/nvmem/imx-ocotp-scu.c b/drivers/nvmem/imx-ocotp-scu.c
index 61a17f943f47..03f1ab23ad51 100644
--- a/drivers/nvmem/imx-ocotp-scu.c
+++ b/drivers/nvmem/imx-ocotp-scu.c
@@ -7,6 +7,7 @@
  * Peng Fan <peng.fan@nxp.com>
  */
 
+#include <linux/arm-smccc.h>
 #include <linux/firmware/imx/sci.h>
 #include <linux/module.h>
 #include <linux/nvmem-provider.h>
@@ -14,14 +15,28 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 
+#define IMX_SIP_OTP			0xC200000A
+#define IMX_SIP_OTP_WRITE		0x2
+
 enum ocotp_devtype {
 	IMX8QXP,
 	IMX8QM,
 };
 
+#define ECC_REGION	BIT(0)
+#define HOLE_REGION	BIT(1)
+
+struct ocotp_region {
+	u32 start;
+	u32 end;
+	u32 flag;
+};
+
 struct ocotp_devtype_data {
 	int devtype;
 	int nregs;
+	u32 num_region;
+	struct ocotp_region region[];
 };
 
 struct ocotp_priv {
@@ -35,16 +50,63 @@ struct imx_sc_msg_misc_fuse_read {
 	u32 word;
 } __packed;
 
+static DEFINE_MUTEX(scu_ocotp_mutex);
+
 static struct ocotp_devtype_data imx8qxp_data = {
 	.devtype = IMX8QXP,
 	.nregs = 800,
+	.num_region = 3,
+	.region = {
+		{0x10, 0x10f, ECC_REGION},
+		{0x110, 0x21F, HOLE_REGION},
+		{0x220, 0x31F, ECC_REGION},
+	},
 };
 
 static struct ocotp_devtype_data imx8qm_data = {
 	.devtype = IMX8QM,
 	.nregs = 800,
+	.num_region = 2,
+	.region = {
+		{0x10, 0x10f, ECC_REGION},
+		{0x1a0, 0x1ff, ECC_REGION},
+	},
 };
 
+static bool in_hole(void *context, u32 index)
+{
+	struct ocotp_priv *priv = context;
+	const struct ocotp_devtype_data *data = priv->data;
+	int i;
+
+	for (i = 0; i < data->num_region; i++) {
+		if (data->region[i].flag & HOLE_REGION) {
+			if ((index >= data->region[i].start) &&
+			    (index <= data->region[i].end))
+				return true;
+		}
+	}
+
+	return false;
+}
+
+static bool in_ecc(void *context, u32 index)
+{
+	struct ocotp_priv *priv = context;
+	const struct ocotp_devtype_data *data = priv->data;
+	int i;
+
+	for (i = 0; i < data->num_region; i++) {
+		if (data->region[i].flag & ECC_REGION) {
+			if ((index >= data->region[i].start) &&
+			    (index <= data->region[i].end))
+				return true;
+		}
+	}
+
+	return false;
+}
+
 static int imx_sc_misc_otp_fuse_read(struct imx_sc_ipc *ipc, u32 word,
 				     u32 *val)
 {
@@ -88,18 +150,19 @@ static int imx_scu_ocotp_read(void *context, unsigned int offset,
 	if (!p)
 		return -ENOMEM;
 
+	mutex_lock(&scu_ocotp_mutex);
+
 	buf = p;
 
 	for (i = index; i < (index + count); i++) {
-		if (priv->data->devtype == IMX8QXP) {
-			if ((i > 271) && (i < 544)) {
-				*buf++ = 0;
-				continue;
-			}
+		if (in_hole(context, i)) {
+			*buf++ = 0;
+			continue;
 		}
 
 		ret = imx_sc_misc_otp_fuse_read(priv->nvmem_ipc, i, buf);
 		if (ret) {
+			mutex_unlock(&scu_ocotp_mutex);
 			kfree(p);
 			return ret;
 		}
@@ -108,18 +171,63 @@ static int imx_scu_ocotp_read(void *context, unsigned int offset,
 
 	memcpy(val, (u8 *)p + offset % 4, bytes);
 
+	mutex_unlock(&scu_ocotp_mutex);
+
 	kfree(p);
 
 	return 0;
 }
 
+static int imx_scu_ocotp_write(void *context, unsigned int offset,
+			       void *val, size_t bytes)
+{
+	struct ocotp_priv *priv = context;
+	struct arm_smccc_res res;
+	u32 *buf = val;
+	u32 tmp;
+	u32 index;
+	int ret;
+
+	/* allow only writing one complete OTP word at a time */
+	if ((bytes != 4) || (offset % 4))
+		return -EINVAL;
+
+	index = offset >> 2;
+
+	if (in_hole(context, index))
+		return -EINVAL;
+
+	if (in_ecc(context, index)) {
+		pr_warn("ECC region, only program once\n");
+		mutex_lock(&scu_ocotp_mutex);
+		ret = imx_sc_misc_otp_fuse_read(priv->nvmem_ipc, index, &tmp);
+		mutex_unlock(&scu_ocotp_mutex);
+		if (ret)
+			return ret;
+		if (tmp) {
+			pr_warn("ECC region, already has value: %x\n", tmp);
+			return -EIO;
+		}
+	}
+
+	mutex_lock(&scu_ocotp_mutex);
+
+	arm_smccc_smc(IMX_SIP_OTP, IMX_SIP_OTP_WRITE, index, *buf,
+		      0, 0, 0, 0, &res);
+
+	mutex_unlock(&scu_ocotp_mutex);
+
+	return res.a0;
+}
+
 static struct nvmem_config imx_scu_ocotp_nvmem_config = {
 	.name = "imx-scu-ocotp",
-	.read_only = true,
+	.read_only = false,
 	.word_size = 4,
 	.stride = 1,
 	.owner = THIS_MODULE,
 	.reg_read = imx_scu_ocotp_read,
+	.reg_write = imx_scu_ocotp_write,
 };
 
 static const struct of_device_id imx_scu_ocotp_dt_ids[] = {
diff --git a/drivers/nvmem/imx-ocotp.c b/drivers/nvmem/imx-ocotp.c
index dff2f3c357f5..fc40555ca4cd 100644
--- a/drivers/nvmem/imx-ocotp.c
+++ b/drivers/nvmem/imx-ocotp.c
@@ -521,6 +521,10 @@ static int imx_ocotp_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->clk))
 		return PTR_ERR(priv->clk);
 
+	clk_prepare_enable(priv->clk);
+	imx_ocotp_clr_err_if_set(priv->base);
+	clk_disable_unprepare(priv->clk);
+
 	priv->params = of_device_get_match_data(&pdev->dev);
 	imx_ocotp_nvmem_config.size = 4 * priv->params->nregs;
 	imx_ocotp_nvmem_config.dev = dev;
diff --git a/drivers/nvmem/rockchip-otp.c b/drivers/nvmem/rockchip-otp.c
new file mode 100644
index 000000000000..9f53bcce2f87
--- /dev/null
+++ b/drivers/nvmem/rockchip-otp.c
@@ -0,0 +1,268 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Rockchip OTP Driver
+ *
+ * Copyright (c) 2018 Rockchip Electronics Co. Ltd.
+ * Author: Finley Xiao <finley.xiao@rock-chips.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/nvmem-provider.h>
+#include <linux/reset.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+
+/* OTP Register Offsets */
+#define OTPC_SBPI_CTRL			0x0020
+#define OTPC_SBPI_CMD_VALID_PRE		0x0024
+#define OTPC_SBPI_CS_VALID_PRE		0x0028
+#define OTPC_SBPI_STATUS		0x002C
+#define OTPC_USER_CTRL			0x0100
+#define OTPC_USER_ADDR			0x0104
+#define OTPC_USER_ENABLE		0x0108
+#define OTPC_USER_Q			0x0124
+#define OTPC_INT_STATUS			0x0304
+#define OTPC_SBPI_CMD0_OFFSET		0x1000
+#define OTPC_SBPI_CMD1_OFFSET		0x1004
+
+/* OTP Register bits and masks */
+#define OTPC_USER_ADDR_MASK		GENMASK(31, 16)
+#define OTPC_USE_USER			BIT(0)
+#define OTPC_USE_USER_MASK		GENMASK(16, 16)
+#define OTPC_USER_FSM_ENABLE		BIT(0)
+#define OTPC_USER_FSM_ENABLE_MASK	GENMASK(16, 16)
+#define OTPC_SBPI_DONE			BIT(1)
+#define OTPC_USER_DONE			BIT(2)
+
+#define SBPI_DAP_ADDR			0x02
+#define SBPI_DAP_ADDR_SHIFT		8
+#define SBPI_DAP_ADDR_MASK		GENMASK(31, 24)
+#define SBPI_CMD_VALID_MASK		GENMASK(31, 16)
+#define SBPI_DAP_CMD_WRF		0xC0
+#define SBPI_DAP_REG_ECC		0x3A
+#define SBPI_ECC_ENABLE			0x00
+#define SBPI_ECC_DISABLE		0x09
+#define SBPI_ENABLE			BIT(0)
+#define SBPI_ENABLE_MASK		GENMASK(16, 16)
+
+#define OTPC_TIMEOUT			10000
+
+struct rockchip_otp {
+	struct device *dev;
+	void __iomem *base;
+	struct clk_bulk_data	*clks;
+	int num_clks;
+	struct reset_control *rst;
+};
+
+/* list of required clocks */
+static const char * const rockchip_otp_clocks[] = {
+	"otp", "apb_pclk", "phy",
+};
+
+struct rockchip_data {
+	int size;
+};
+
+static int rockchip_otp_reset(struct rockchip_otp *otp)
+{
+	int ret;
+
+	ret = reset_control_assert(otp->rst);
+	if (ret) {
+		dev_err(otp->dev, "failed to assert otp phy %d\n", ret);
+		return ret;
+	}
+
+	udelay(2);
+
+	ret = reset_control_deassert(otp->rst);
+	if (ret) {
+		dev_err(otp->dev, "failed to deassert otp phy %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int rockchip_otp_wait_status(struct rockchip_otp *otp, u32 flag)
+{
+	u32 status = 0;
+	int ret;
+
+	ret = readl_poll_timeout_atomic(otp->base + OTPC_INT_STATUS, status,
+					(status & flag), 1, OTPC_TIMEOUT);
+	if (ret)
+		return ret;
+
+	/* clean int status */
+	writel(flag, otp->base + OTPC_INT_STATUS);
+
+	return 0;
+}
+
+static int rockchip_otp_ecc_enable(struct rockchip_otp *otp, bool enable)
+{
+	int ret = 0;
+
+	writel(SBPI_DAP_ADDR_MASK | (SBPI_DAP_ADDR << SBPI_DAP_ADDR_SHIFT),
+	       otp->base + OTPC_SBPI_CTRL);
+
+	writel(SBPI_CMD_VALID_MASK | 0x1, otp->base + OTPC_SBPI_CMD_VALID_PRE);
+	writel(SBPI_DAP_CMD_WRF | SBPI_DAP_REG_ECC,
+	       otp->base + OTPC_SBPI_CMD0_OFFSET);
+	if (enable)
+		writel(SBPI_ECC_ENABLE, otp->base + OTPC_SBPI_CMD1_OFFSET);
+	else
+		writel(SBPI_ECC_DISABLE, otp->base + OTPC_SBPI_CMD1_OFFSET);
+
+	writel(SBPI_ENABLE_MASK | SBPI_ENABLE, otp->base + OTPC_SBPI_CTRL);
+
+	ret = rockchip_otp_wait_status(otp, OTPC_SBPI_DONE);
+	if (ret < 0)
+		dev_err(otp->dev, "timeout during ecc_enable\n");
+
+	return ret;
+}
+
+static int rockchip_otp_read(void *context, unsigned int offset,
+			     void *val, size_t bytes)
+{
+	struct rockchip_otp *otp = context;
+	u8 *buf = val;
+	int ret = 0;
+
+	ret = clk_bulk_prepare_enable(otp->num_clks, otp->clks);
+	if (ret < 0) {
+		dev_err(otp->dev, "failed to prepare/enable clks\n");
+		return ret;
+	}
+
+	ret = rockchip_otp_reset(otp);
+	if (ret) {
+		dev_err(otp->dev, "failed to reset otp phy\n");
+		goto disable_clks;
+	}
+
+	ret = rockchip_otp_ecc_enable(otp, false);
+	if (ret < 0) {
+		dev_err(otp->dev, "rockchip_otp_ecc_enable err\n");
+		goto disable_clks;
+	}
+
+	writel(OTPC_USE_USER | OTPC_USE_USER_MASK, otp->base + OTPC_USER_CTRL);
+	udelay(5);
+	while (bytes--) {
+		writel(offset++ | OTPC_USER_ADDR_MASK,
+		       otp->base + OTPC_USER_ADDR);
+		writel(OTPC_USER_FSM_ENABLE | OTPC_USER_FSM_ENABLE_MASK,
+		       otp->base + OTPC_USER_ENABLE);
+		ret = rockchip_otp_wait_status(otp, OTPC_USER_DONE);
+		if (ret < 0) {
+			dev_err(otp->dev, "timeout during read setup\n");
+			goto read_end;
+		}
+		*buf++ = readb(otp->base + OTPC_USER_Q);
+	}
+
+read_end:
+	writel(0x0 | OTPC_USE_USER_MASK, otp->base + OTPC_USER_CTRL);
+disable_clks:
+	clk_bulk_disable_unprepare(otp->num_clks, otp->clks);
+
+	return ret;
+}
+
+static struct nvmem_config otp_config = {
+	.name = "rockchip-otp",
+	.owner = THIS_MODULE,
+	.read_only = true,
+	.stride = 1,
+	.word_size = 1,
+	.reg_read = rockchip_otp_read,
+};
+
+static const struct rockchip_data px30_data = {
+	.size = 0x40,
+};
+
+static const struct of_device_id rockchip_otp_match[] = {
+	{
+		.compatible = "rockchip,px30-otp",
+		.data = (void *)&px30_data,
+	},
+	{
+		.compatible = "rockchip,rk3308-otp",
+		.data = (void *)&px30_data,
+	},
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, rockchip_otp_match);
+
+static int rockchip_otp_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct rockchip_otp *otp;
+	const struct rockchip_data *data;
+	struct nvmem_device *nvmem;
+	int ret, i;
+
+	data = of_device_get_match_data(dev);
+	if (!data) {
+		dev_err(dev, "failed to get match data\n");
+		return -EINVAL;
+	}
+
+	otp = devm_kzalloc(&pdev->dev, sizeof(struct rockchip_otp),
+			   GFP_KERNEL);
+	if (!otp)
+		return -ENOMEM;
+
+	otp->dev = dev;
+	otp->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(otp->base))
+		return PTR_ERR(otp->base);
+
+	otp->num_clks = ARRAY_SIZE(rockchip_otp_clocks);
+	otp->clks = devm_kcalloc(dev, otp->num_clks,
+				     sizeof(*otp->clks), GFP_KERNEL);
+	if (!otp->clks)
+		return -ENOMEM;
+
+	for (i = 0; i < otp->num_clks; ++i)
+		otp->clks[i].id = rockchip_otp_clocks[i];
+
+	ret = devm_clk_bulk_get(dev, otp->num_clks, otp->clks);
+	if (ret)
+		return ret;
+
+	otp->rst = devm_reset_control_get(dev, "phy");
+	if (IS_ERR(otp->rst))
+		return PTR_ERR(otp->rst);
+
+	otp_config.size = data->size;
+	otp_config.priv = otp;
+	otp_config.dev = dev;
+	nvmem = devm_nvmem_register(dev, &otp_config);
+
+	return PTR_ERR_OR_ZERO(nvmem);
+}
+
+static struct platform_driver rockchip_otp_driver = {
+	.probe = rockchip_otp_probe,
+	.driver = {
+		.name = "rockchip-otp",
+		.of_match_table = rockchip_otp_match,
+	},
+};
+
+module_platform_driver(rockchip_otp_driver);
+MODULE_DESCRIPTION("Rockchip OTP driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvmem/sc27xx-efuse.c b/drivers/nvmem/sc27xx-efuse.c
index c6ee21018d80..ab5e7e0bc3d8 100644
--- a/drivers/nvmem/sc27xx-efuse.c
+++ b/drivers/nvmem/sc27xx-efuse.c
@@ -211,7 +211,7 @@ static int sc27xx_efuse_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	efuse->hwlock = hwspin_lock_request_specific(ret);
+	efuse->hwlock = devm_hwspin_lock_request_specific(&pdev->dev, ret);
 	if (!efuse->hwlock) {
 		dev_err(&pdev->dev, "failed to request hwspinlock\n");
 		return -ENXIO;
@@ -219,7 +219,6 @@ static int sc27xx_efuse_probe(struct platform_device *pdev)
 
 	mutex_init(&efuse->mutex);
 	efuse->dev = &pdev->dev;
-	platform_set_drvdata(pdev, efuse);
 
 	econfig.stride = 1;
 	econfig.word_size = 1;
@@ -232,21 +231,12 @@ static int sc27xx_efuse_probe(struct platform_device *pdev)
 	nvmem = devm_nvmem_register(&pdev->dev, &econfig);
 	if (IS_ERR(nvmem)) {
 		dev_err(&pdev->dev, "failed to register nvmem config\n");
-		hwspin_lock_free(efuse->hwlock);
 		return PTR_ERR(nvmem);
 	}
 
 	return 0;
 }
 
-static int sc27xx_efuse_remove(struct platform_device *pdev)
-{
-	struct sc27xx_efuse *efuse = platform_get_drvdata(pdev);
-
-	hwspin_lock_free(efuse->hwlock);
-	return 0;
-}
-
 static const struct of_device_id sc27xx_efuse_of_match[] = {
 	{ .compatible = "sprd,sc2731-efuse" },
 	{ }
@@ -254,7 +244,6 @@ static const struct of_device_id sc27xx_efuse_of_match[] = {
 
 static struct platform_driver sc27xx_efuse_driver = {
 	.probe = sc27xx_efuse_probe,
-	.remove = sc27xx_efuse_remove,
 	.driver = {
 		.name = "sc27xx-efuse",
 		.of_match_table = sc27xx_efuse_of_match,
diff --git a/drivers/nvmem/sprd-efuse.c b/drivers/nvmem/sprd-efuse.c
new file mode 100644
index 000000000000..2f1e0fbd1901
--- /dev/null
+++ b/drivers/nvmem/sprd-efuse.c
@@ -0,0 +1,424 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2019 Spreadtrum Communications Inc.
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/hwspinlock.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/nvmem-provider.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+
+#define SPRD_EFUSE_ENABLE		0x20
+#define SPRD_EFUSE_ERR_FLAG		0x24
+#define SPRD_EFUSE_ERR_CLR		0x28
+#define SPRD_EFUSE_MAGIC_NUM		0x2c
+#define SPRD_EFUSE_FW_CFG		0x50
+#define SPRD_EFUSE_PW_SWT		0x54
+#define SPRD_EFUSE_MEM(val)		(0x1000 + ((val) << 2))
+
+#define SPRD_EFUSE_VDD_EN		BIT(0)
+#define SPRD_EFUSE_AUTO_CHECK_EN	BIT(1)
+#define SPRD_EFUSE_DOUBLE_EN		BIT(2)
+#define SPRD_EFUSE_MARGIN_RD_EN		BIT(3)
+#define SPRD_EFUSE_LOCK_WR_EN		BIT(4)
+
+#define SPRD_EFUSE_ERR_CLR_MASK		GENMASK(13, 0)
+
+#define SPRD_EFUSE_ENK1_ON		BIT(0)
+#define SPRD_EFUSE_ENK2_ON		BIT(1)
+#define SPRD_EFUSE_PROG_EN		BIT(2)
+
+#define SPRD_EFUSE_MAGIC_NUMBER		0x8810
+
+/* Block width (bytes) definitions */
+#define SPRD_EFUSE_BLOCK_WIDTH		4
+
+/*
+ * The Spreadtrum AP efuse contains 2 parts: normal efuse and secure efuse,
+ * and we can only access the normal efuse in kernel. So define the normal
+ * block offset index and normal block numbers.
+ */
+#define SPRD_EFUSE_NORMAL_BLOCK_NUMS	24
+#define SPRD_EFUSE_NORMAL_BLOCK_OFFSET	72
+
+/* Timeout (ms) for the trylock of hardware spinlocks */
+#define SPRD_EFUSE_HWLOCK_TIMEOUT	5000
+
+/*
+ * Since different Spreadtrum SoC chip can have different normal block numbers
+ * and offset. And some SoC can support block double feature, which means
+ * when reading or writing data to efuse memory, the controller can save double
+ * data in case one data become incorrect after a long period.
+ *
+ * Thus we should save them in the device data structure.
+ */
+struct sprd_efuse_variant_data {
+	u32 blk_nums;
+	u32 blk_offset;
+	bool blk_double;
+};
+
+struct sprd_efuse {
+	struct device *dev;
+	struct clk *clk;
+	struct hwspinlock *hwlock;
+	struct mutex mutex;
+	void __iomem *base;
+	const struct sprd_efuse_variant_data *data;
+};
+
+static const struct sprd_efuse_variant_data ums312_data = {
+	.blk_nums = SPRD_EFUSE_NORMAL_BLOCK_NUMS,
+	.blk_offset = SPRD_EFUSE_NORMAL_BLOCK_OFFSET,
+	.blk_double = false,
+};
+
+/*
+ * On Spreadtrum platform, we have multi-subsystems will access the unique
+ * efuse controller, so we need one hardware spinlock to synchronize between
+ * the multiple subsystems.
+ */
+static int sprd_efuse_lock(struct sprd_efuse *efuse)
+{
+	int ret;
+
+	mutex_lock(&efuse->mutex);
+
+	ret = hwspin_lock_timeout_raw(efuse->hwlock,
+				      SPRD_EFUSE_HWLOCK_TIMEOUT);
+	if (ret) {
+		dev_err(efuse->dev, "timeout get the hwspinlock\n");
+		mutex_unlock(&efuse->mutex);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void sprd_efuse_unlock(struct sprd_efuse *efuse)
+{
+	hwspin_unlock_raw(efuse->hwlock);
+	mutex_unlock(&efuse->mutex);
+}
+
+static void sprd_efuse_set_prog_power(struct sprd_efuse *efuse, bool en)
+{
+	u32 val = readl(efuse->base + SPRD_EFUSE_PW_SWT);
+
+	if (en)
+		val &= ~SPRD_EFUSE_ENK2_ON;
+	else
+		val &= ~SPRD_EFUSE_ENK1_ON;
+
+	writel(val, efuse->base + SPRD_EFUSE_PW_SWT);
+
+	/* Open or close efuse power need wait 1000us to make power stable. */
+	usleep_range(1000, 1200);
+
+	if (en)
+		val |= SPRD_EFUSE_ENK1_ON;
+	else
+		val |= SPRD_EFUSE_ENK2_ON;
+
+	writel(val, efuse->base + SPRD_EFUSE_PW_SWT);
+
+	/* Open or close efuse power need wait 1000us to make power stable. */
+	usleep_range(1000, 1200);
+}
+
+static void sprd_efuse_set_read_power(struct sprd_efuse *efuse, bool en)
+{
+	u32 val = readl(efuse->base + SPRD_EFUSE_ENABLE);
+
+	if (en)
+		val |= SPRD_EFUSE_VDD_EN;
+	else
+		val &= ~SPRD_EFUSE_VDD_EN;
+
+	writel(val, efuse->base + SPRD_EFUSE_ENABLE);
+
+	/* Open or close efuse power need wait 1000us to make power stable. */
+	usleep_range(1000, 1200);
+}
+
+static void sprd_efuse_set_prog_lock(struct sprd_efuse *efuse, bool en)
+{
+	u32 val = readl(efuse->base + SPRD_EFUSE_ENABLE);
+
+	if (en)
+		val |= SPRD_EFUSE_LOCK_WR_EN;
+	else
+		val &= ~SPRD_EFUSE_LOCK_WR_EN;
+
+	writel(val, efuse->base + SPRD_EFUSE_ENABLE);
+}
+
+static void sprd_efuse_set_auto_check(struct sprd_efuse *efuse, bool en)
+{
+	u32 val = readl(efuse->base + SPRD_EFUSE_ENABLE);
+
+	if (en)
+		val |= SPRD_EFUSE_AUTO_CHECK_EN;
+	else
+		val &= ~SPRD_EFUSE_AUTO_CHECK_EN;
+
+	writel(val, efuse->base + SPRD_EFUSE_ENABLE);
+}
+
+static void sprd_efuse_set_data_double(struct sprd_efuse *efuse, bool en)
+{
+	u32 val = readl(efuse->base + SPRD_EFUSE_ENABLE);
+
+	if (en)
+		val |= SPRD_EFUSE_DOUBLE_EN;
+	else
+		val &= ~SPRD_EFUSE_DOUBLE_EN;
+
+	writel(val, efuse->base + SPRD_EFUSE_ENABLE);
+}
+
+static void sprd_efuse_set_prog_en(struct sprd_efuse *efuse, bool en)
+{
+	u32 val = readl(efuse->base + SPRD_EFUSE_PW_SWT);
+
+	if (en)
+		val |= SPRD_EFUSE_PROG_EN;
+	else
+		val &= ~SPRD_EFUSE_PROG_EN;
+
+	writel(val, efuse->base + SPRD_EFUSE_PW_SWT);
+}
+
+static int sprd_efuse_raw_prog(struct sprd_efuse *efuse, u32 blk, bool doub,
+			       bool lock, u32 *data)
+{
+	u32 status;
+	int ret = 0;
+
+	/*
+	 * We need set the correct magic number before writing the efuse to
+	 * allow programming, and block other programming until we clear the
+	 * magic number.
+	 */
+	writel(SPRD_EFUSE_MAGIC_NUMBER,
+	       efuse->base + SPRD_EFUSE_MAGIC_NUM);
+
+	/*
+	 * Power on the efuse, enable programme and enable double data
+	 * if asked.
+	 */
+	sprd_efuse_set_prog_power(efuse, true);
+	sprd_efuse_set_prog_en(efuse, true);
+	sprd_efuse_set_data_double(efuse, doub);
+
+	/*
+	 * Enable the auto-check function to validate if the programming is
+	 * successful.
+	 */
+	sprd_efuse_set_auto_check(efuse, true);
+
+	writel(*data, efuse->base + SPRD_EFUSE_MEM(blk));
+
+	/* Disable auto-check and data double after programming */
+	sprd_efuse_set_auto_check(efuse, false);
+	sprd_efuse_set_data_double(efuse, false);
+
+	/*
+	 * Check the efuse error status, if the programming is successful,
+	 * we should lock this efuse block to avoid programming again.
+	 */
+	status = readl(efuse->base + SPRD_EFUSE_ERR_FLAG);
+	if (status) {
+		dev_err(efuse->dev,
+			"write error status %d of block %d\n", ret, blk);
+
+		writel(SPRD_EFUSE_ERR_CLR_MASK,
+		       efuse->base + SPRD_EFUSE_ERR_CLR);
+		ret = -EBUSY;
+	} else {
+		sprd_efuse_set_prog_lock(efuse, lock);
+		writel(*data, efuse->base + SPRD_EFUSE_MEM(blk));
+		sprd_efuse_set_prog_lock(efuse, false);
+	}
+
+	sprd_efuse_set_prog_power(efuse, false);
+	writel(0, efuse->base + SPRD_EFUSE_MAGIC_NUM);
+
+	return ret;
+}
+
+static int sprd_efuse_raw_read(struct sprd_efuse *efuse, int blk, u32 *val,
+			       bool doub)
+{
+	u32 status;
+
+	/*
+	 * Need power on the efuse before reading data from efuse, and will
+	 * power off the efuse after reading process.
+	 */
+	sprd_efuse_set_read_power(efuse, true);
+
+	/* Enable double data if asked */
+	sprd_efuse_set_data_double(efuse, doub);
+
+	/* Start to read data from efuse block */
+	*val = readl(efuse->base + SPRD_EFUSE_MEM(blk));
+
+	/* Disable double data */
+	sprd_efuse_set_data_double(efuse, false);
+
+	/* Power off the efuse */
+	sprd_efuse_set_read_power(efuse, false);
+
+	/*
+	 * Check the efuse error status and clear them if there are some
+	 * errors occurred.
+	 */
+	status = readl(efuse->base + SPRD_EFUSE_ERR_FLAG);
+	if (status) {
+		dev_err(efuse->dev,
+			"read error status %d of block %d\n", status, blk);
+
+		writel(SPRD_EFUSE_ERR_CLR_MASK,
+		       efuse->base + SPRD_EFUSE_ERR_CLR);
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+static int sprd_efuse_read(void *context, u32 offset, void *val, size_t bytes)
+{
+	struct sprd_efuse *efuse = context;
+	bool blk_double = efuse->data->blk_double;
+	u32 index = offset / SPRD_EFUSE_BLOCK_WIDTH + efuse->data->blk_offset;
+	u32 blk_offset = (offset % SPRD_EFUSE_BLOCK_WIDTH) * BITS_PER_BYTE;
+	u32 data;
+	int ret;
+
+	ret = sprd_efuse_lock(efuse);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(efuse->clk);
+	if (ret)
+		goto unlock;
+
+	ret = sprd_efuse_raw_read(efuse, index, &data, blk_double);
+	if (!ret) {
+		data >>= blk_offset;
+		memcpy(val, &data, bytes);
+	}
+
+	clk_disable_unprepare(efuse->clk);
+
+unlock:
+	sprd_efuse_unlock(efuse);
+	return ret;
+}
+
+static int sprd_efuse_write(void *context, u32 offset, void *val, size_t bytes)
+{
+	struct sprd_efuse *efuse = context;
+	int ret;
+
+	ret = sprd_efuse_lock(efuse);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(efuse->clk);
+	if (ret)
+		goto unlock;
+
+	ret = sprd_efuse_raw_prog(efuse, offset, false, false, val);
+
+	clk_disable_unprepare(efuse->clk);
+
+unlock:
+	sprd_efuse_unlock(efuse);
+	return ret;
+}
+
+static int sprd_efuse_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct nvmem_device *nvmem;
+	struct nvmem_config econfig = { };
+	struct sprd_efuse *efuse;
+	const struct sprd_efuse_variant_data *pdata;
+	int ret;
+
+	pdata = of_device_get_match_data(&pdev->dev);
+	if (!pdata) {
+		dev_err(&pdev->dev, "No matching driver data found\n");
+		return -EINVAL;
+	}
+
+	efuse = devm_kzalloc(&pdev->dev, sizeof(*efuse), GFP_KERNEL);
+	if (!efuse)
+		return -ENOMEM;
+
+	efuse->base = devm_platform_ioremap_resource(pdev, 0);
+	if (!efuse->base)
+		return -ENOMEM;
+
+	ret = of_hwspin_lock_get_id(np, 0);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to get hwlock id\n");
+		return ret;
+	}
+
+	efuse->hwlock = devm_hwspin_lock_request_specific(&pdev->dev, ret);
+	if (!efuse->hwlock) {
+		dev_err(&pdev->dev, "failed to request hwlock\n");
+		return -ENXIO;
+	}
+
+	efuse->clk = devm_clk_get(&pdev->dev, "enable");
+	if (IS_ERR(efuse->clk)) {
+		dev_err(&pdev->dev, "failed to get enable clock\n");
+		return PTR_ERR(efuse->clk);
+	}
+
+	mutex_init(&efuse->mutex);
+	efuse->dev = &pdev->dev;
+	efuse->data = pdata;
+
+	econfig.stride = 1;
+	econfig.word_size = 1;
+	econfig.read_only = false;
+	econfig.name = "sprd-efuse";
+	econfig.size = efuse->data->blk_nums * SPRD_EFUSE_BLOCK_WIDTH;
+	econfig.reg_read = sprd_efuse_read;
+	econfig.reg_write = sprd_efuse_write;
+	econfig.priv = efuse;
+	econfig.dev = &pdev->dev;
+	nvmem = devm_nvmem_register(&pdev->dev, &econfig);
+	if (IS_ERR(nvmem)) {
+		dev_err(&pdev->dev, "failed to register nvmem\n");
+		return PTR_ERR(nvmem);
+	}
+
+	return 0;
+}
+
+static const struct of_device_id sprd_efuse_of_match[] = {
+	{ .compatible = "sprd,ums312-efuse", .data = &ums312_data },
+	{ }
+};
+
+static struct platform_driver sprd_efuse_driver = {
+	.probe = sprd_efuse_probe,
+	.driver = {
+		.name = "sprd-efuse",
+		.of_match_table = sprd_efuse_of_match,
+	},
+};
+
+module_platform_driver(sprd_efuse_driver);
+
+MODULE_AUTHOR("Freeman Liu <freeman.liu@spreadtrum.com>");
+MODULE_DESCRIPTION("Spreadtrum AP efuse driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/parport/daisy.c b/drivers/parport/daisy.c
index 5484a46dafda..3b00e2c8e2e9 100644
--- a/drivers/parport/daisy.c
+++ b/drivers/parport/daisy.c
@@ -45,6 +45,7 @@ static struct daisydev {
 static DEFINE_SPINLOCK(topology_lock);
 
 static int numdevs;
+static bool daisy_init_done;
 
 /* Forward-declaration of lower-level functions. */
 static int mux_present(struct parport *port);
@@ -87,6 +88,24 @@ static struct parport *clone_parport(struct parport *real, int muxport)
 	return extra;
 }
 
+static int daisy_drv_probe(struct pardevice *par_dev)
+{
+	struct device_driver *drv = par_dev->dev.driver;
+
+	if (strcmp(drv->name, "daisy_drv"))
+		return -ENODEV;
+	if (strcmp(par_dev->name, daisy_dev_name))
+		return -ENODEV;
+
+	return 0;
+}
+
+static struct parport_driver daisy_driver = {
+	.name = "daisy_drv",
+	.probe = daisy_drv_probe,
+	.devmodel = true,
+};
+
 /* Discover the IEEE1284.3 topology on a port -- muxes and daisy chains.
  * Return value is number of devices actually detected. */
 int parport_daisy_init(struct parport *port)
@@ -98,6 +117,23 @@ int parport_daisy_init(struct parport *port)
 	int i;
 	int last_try = 0;
 
+	if (!daisy_init_done) {
+		/*
+		 * flag should be marked true first as
+		 * parport_register_driver() might try to load the low
+		 * level driver which will lead to announcing new ports
+		 * and which will again come back here at
+		 * parport_daisy_init()
+		 */
+		daisy_init_done = true;
+		i = parport_register_driver(&daisy_driver);
+		if (i) {
+			pr_err("daisy registration failed\n");
+			daisy_init_done = false;
+			return i;
+		}
+	}
+
 again:
 	/* Because this is called before any other devices exist,
 	 * we don't have to claim exclusive access.  */
@@ -213,10 +249,12 @@ void parport_daisy_fini(struct parport *port)
 struct pardevice *parport_open(int devnum, const char *name)
 {
 	struct daisydev *p = topology;
+	struct pardev_cb par_cb;
 	struct parport *port;
 	struct pardevice *dev;
 	int daisy;
 
+	memset(&par_cb, 0, sizeof(par_cb));
 	spin_lock(&topology_lock);
 	while (p && p->devnum != devnum)
 		p = p->next;
@@ -230,7 +268,7 @@ struct pardevice *parport_open(int devnum, const char *name)
 	port = parport_get_port(p->port);
 	spin_unlock(&topology_lock);
 
-	dev = parport_register_device(port, name, NULL, NULL, NULL, 0, NULL);
+	dev = parport_register_dev_model(port, name, &par_cb, devnum);
 	parport_put_port(port);
 	if (!dev)
 		return NULL;
diff --git a/drivers/parport/probe.c b/drivers/parport/probe.c
index e035174ba205..e5e6a463a941 100644
--- a/drivers/parport/probe.c
+++ b/drivers/parport/probe.c
@@ -257,7 +257,7 @@ static ssize_t parport_read_device_id (struct parport *port, char *buffer,
 ssize_t parport_device_id (int devnum, char *buffer, size_t count)
 {
 	ssize_t retval = -ENXIO;
-	struct pardevice *dev = parport_open (devnum, "Device ID probe");
+	struct pardevice *dev = parport_open(devnum, daisy_dev_name);
 	if (!dev)
 		return -ENXIO;
 
diff --git a/drivers/parport/share.c b/drivers/parport/share.c
index 7b4ee33c1935..d6920ebeabcd 100644
--- a/drivers/parport/share.c
+++ b/drivers/parport/share.c
@@ -230,6 +230,18 @@ static int port_check(struct device *dev, void *dev_drv)
 	return 0;
 }
 
+/*
+ * Iterates through all the devices connected to the bus and return 1
+ * if the device is a parallel port.
+ */
+
+static int port_detect(struct device *dev, void *dev_drv)
+{
+	if (is_parport(dev))
+		return 1;
+	return 0;
+}
+
 /**
  *	parport_register_driver - register a parallel port device driver
  *	@drv: structure describing the driver
@@ -266,9 +278,6 @@ static int port_check(struct device *dev, void *dev_drv)
 int __parport_register_driver(struct parport_driver *drv, struct module *owner,
 			      const char *mod_name)
 {
-	if (list_empty(&portlist))
-		get_lowlevel_driver();
-
 	if (drv->devmodel) {
 		/* using device model */
 		int ret;
@@ -282,6 +291,15 @@ int __parport_register_driver(struct parport_driver *drv, struct module *owner,
 		if (ret)
 			return ret;
 
+		/*
+		 * check if bus has any parallel port registered, if
+		 * none is found then load the lowlevel driver.
+		 */
+		ret = bus_for_each_dev(&parport_bus_type, NULL, NULL,
+				       port_detect);
+		if (!ret)
+			get_lowlevel_driver();
+
 		mutex_lock(&registration_lock);
 		if (drv->match_port)
 			bus_for_each_dev(&parport_bus_type, NULL, drv,
@@ -292,6 +310,8 @@ int __parport_register_driver(struct parport_driver *drv, struct module *owner,
 
 		drv->devmodel = false;
 
+		if (list_empty(&portlist))
+			get_lowlevel_driver();
 		mutex_lock(&registration_lock);
 		list_for_each_entry(port, &portlist, list)
 			drv->attach(port);
diff --git a/drivers/phy/allwinner/Kconfig b/drivers/phy/allwinner/Kconfig
index 215425296c77..3dab79e9d52b 100644
--- a/drivers/phy/allwinner/Kconfig
+++ b/drivers/phy/allwinner/Kconfig
@@ -45,3 +45,14 @@ config PHY_SUN9I_USB
 	  sun9i SoCs.
 
 	  This driver controls each individual USB 2 host PHY.
+
+config PHY_SUN50I_USB3
+	tristate "Allwinner H6 SoC USB3 PHY driver"
+	depends on ARCH_SUNXI && HAS_IOMEM && OF
+	depends on RESET_CONTROLLER
+	select GENERIC_PHY
+	help
+	  Enable this to support the USB3.0-capable transceiver that is
+	  part of Allwinner H6 SoC.
+
+	  This driver controls each individual USB 2+3 host PHY combo.
diff --git a/drivers/phy/allwinner/Makefile b/drivers/phy/allwinner/Makefile
index 799a65c0b58d..bd74901a1255 100644
--- a/drivers/phy/allwinner/Makefile
+++ b/drivers/phy/allwinner/Makefile
@@ -2,3 +2,4 @@
 obj-$(CONFIG_PHY_SUN4I_USB)		+= phy-sun4i-usb.o
 obj-$(CONFIG_PHY_SUN6I_MIPI_DPHY)	+= phy-sun6i-mipi-dphy.o
 obj-$(CONFIG_PHY_SUN9I_USB)		+= phy-sun9i-usb.o
+obj-$(CONFIG_PHY_SUN50I_USB3)		+= phy-sun50i-usb3.o
diff --git a/drivers/phy/allwinner/phy-sun50i-usb3.c b/drivers/phy/allwinner/phy-sun50i-usb3.c
new file mode 100644
index 000000000000..1169f3e83a6f
--- /dev/null
+++ b/drivers/phy/allwinner/phy-sun50i-usb3.c
@@ -0,0 +1,190 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Allwinner sun50i(H6) USB 3.0 phy driver
+ *
+ * Copyright (C) 2017 Icenowy Zheng <icenowy@aosc.io>
+ *
+ * Based on phy-sun9i-usb.c, which is:
+ *
+ * Copyright (C) 2014-2015 Chen-Yu Tsai <wens@csie.org>
+ *
+ * Based on code from Allwinner BSP, which is:
+ *
+ * Copyright (c) 2010-2015 Allwinner Technology Co., Ltd.
+ */
+
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/phy/phy.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+
+/* Interface Status and Control Registers */
+#define SUNXI_ISCR			0x00
+#define SUNXI_PIPE_CLOCK_CONTROL	0x14
+#define SUNXI_PHY_TUNE_LOW		0x18
+#define SUNXI_PHY_TUNE_HIGH		0x1c
+#define SUNXI_PHY_EXTERNAL_CONTROL	0x20
+
+/* USB2.0 Interface Status and Control Register */
+#define SUNXI_ISCR_FORCE_VBUS		(3 << 12)
+
+/* PIPE Clock Control Register */
+#define SUNXI_PCC_PIPE_CLK_OPEN		(1 << 6)
+
+/* PHY External Control Register */
+#define SUNXI_PEC_EXTERN_VBUS		(3 << 1)
+#define SUNXI_PEC_SSC_EN		(1 << 24)
+#define SUNXI_PEC_REF_SSP_EN		(1 << 26)
+
+/* PHY Tune High Register */
+#define SUNXI_TX_DEEMPH_3P5DB(n)	((n) << 19)
+#define SUNXI_TX_DEEMPH_3P5DB_MASK	GENMASK(24, 19)
+#define SUNXI_TX_DEEMPH_6DB(n)		((n) << 13)
+#define SUNXI_TX_DEEMPH_6GB_MASK	GENMASK(18, 13)
+#define SUNXI_TX_SWING_FULL(n)		((n) << 6)
+#define SUNXI_TX_SWING_FULL_MASK	GENMASK(12, 6)
+#define SUNXI_LOS_BIAS(n)		((n) << 3)
+#define SUNXI_LOS_BIAS_MASK		GENMASK(5, 3)
+#define SUNXI_TXVBOOSTLVL(n)		((n) << 0)
+#define SUNXI_TXVBOOSTLVL_MASK		GENMASK(0, 2)
+
+struct sun50i_usb3_phy {
+	struct phy *phy;
+	void __iomem *regs;
+	struct reset_control *reset;
+	struct clk *clk;
+};
+
+static void sun50i_usb3_phy_open(struct sun50i_usb3_phy *phy)
+{
+	u32 val;
+
+	val = readl(phy->regs + SUNXI_PHY_EXTERNAL_CONTROL);
+	val |= SUNXI_PEC_EXTERN_VBUS;
+	val |= SUNXI_PEC_SSC_EN | SUNXI_PEC_REF_SSP_EN;
+	writel(val, phy->regs + SUNXI_PHY_EXTERNAL_CONTROL);
+
+	val = readl(phy->regs + SUNXI_PIPE_CLOCK_CONTROL);
+	val |= SUNXI_PCC_PIPE_CLK_OPEN;
+	writel(val, phy->regs + SUNXI_PIPE_CLOCK_CONTROL);
+
+	val = readl(phy->regs + SUNXI_ISCR);
+	val |= SUNXI_ISCR_FORCE_VBUS;
+	writel(val, phy->regs + SUNXI_ISCR);
+
+	/*
+	 * All the magic numbers written to the PHY_TUNE_{LOW_HIGH}
+	 * registers are directly taken from the BSP USB3 driver from
+	 * Allwiner.
+	 */
+	writel(0x0047fc87, phy->regs + SUNXI_PHY_TUNE_LOW);
+
+	val = readl(phy->regs + SUNXI_PHY_TUNE_HIGH);
+	val &= ~(SUNXI_TXVBOOSTLVL_MASK | SUNXI_LOS_BIAS_MASK |
+		 SUNXI_TX_SWING_FULL_MASK | SUNXI_TX_DEEMPH_6GB_MASK |
+		 SUNXI_TX_DEEMPH_3P5DB_MASK);
+	val |= SUNXI_TXVBOOSTLVL(0x7);
+	val |= SUNXI_LOS_BIAS(0x7);
+	val |= SUNXI_TX_SWING_FULL(0x55);
+	val |= SUNXI_TX_DEEMPH_6DB(0x20);
+	val |= SUNXI_TX_DEEMPH_3P5DB(0x15);
+	writel(val, phy->regs + SUNXI_PHY_TUNE_HIGH);
+}
+
+static int sun50i_usb3_phy_init(struct phy *_phy)
+{
+	struct sun50i_usb3_phy *phy = phy_get_drvdata(_phy);
+	int ret;
+
+	ret = clk_prepare_enable(phy->clk);
+	if (ret)
+		return ret;
+
+	ret = reset_control_deassert(phy->reset);
+	if (ret) {
+		clk_disable_unprepare(phy->clk);
+		return ret;
+	}
+
+	sun50i_usb3_phy_open(phy);
+	return 0;
+}
+
+static int sun50i_usb3_phy_exit(struct phy *_phy)
+{
+	struct sun50i_usb3_phy *phy = phy_get_drvdata(_phy);
+
+	reset_control_assert(phy->reset);
+	clk_disable_unprepare(phy->clk);
+
+	return 0;
+}
+
+static const struct phy_ops sun50i_usb3_phy_ops = {
+	.init		= sun50i_usb3_phy_init,
+	.exit		= sun50i_usb3_phy_exit,
+	.owner		= THIS_MODULE,
+};
+
+static int sun50i_usb3_phy_probe(struct platform_device *pdev)
+{
+	struct sun50i_usb3_phy *phy;
+	struct device *dev = &pdev->dev;
+	struct phy_provider *phy_provider;
+	struct resource *res;
+
+	phy = devm_kzalloc(dev, sizeof(*phy), GFP_KERNEL);
+	if (!phy)
+		return -ENOMEM;
+
+	phy->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(phy->clk)) {
+		if (PTR_ERR(phy->clk) != -EPROBE_DEFER)
+			dev_err(dev, "failed to get phy clock\n");
+		return PTR_ERR(phy->clk);
+	}
+
+	phy->reset = devm_reset_control_get(dev, NULL);
+	if (IS_ERR(phy->reset)) {
+		dev_err(dev, "failed to get reset control\n");
+		return PTR_ERR(phy->reset);
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	phy->regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(phy->regs))
+		return PTR_ERR(phy->regs);
+
+	phy->phy = devm_phy_create(dev, NULL, &sun50i_usb3_phy_ops);
+	if (IS_ERR(phy->phy)) {
+		dev_err(dev, "failed to create PHY\n");
+		return PTR_ERR(phy->phy);
+	}
+
+	phy_set_drvdata(phy->phy, phy);
+	phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate);
+
+	return PTR_ERR_OR_ZERO(phy_provider);
+}
+
+static const struct of_device_id sun50i_usb3_phy_of_match[] = {
+	{ .compatible = "allwinner,sun50i-h6-usb3-phy" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, sun50i_usb3_phy_of_match);
+
+static struct platform_driver sun50i_usb3_phy_driver = {
+	.probe	= sun50i_usb3_phy_probe,
+	.driver = {
+		.of_match_table	= sun50i_usb3_phy_of_match,
+		.name  = "sun50i-usb3-phy",
+	}
+};
+module_platform_driver(sun50i_usb3_phy_driver);
+
+MODULE_DESCRIPTION("Allwinner H6 USB 3.0 phy driver");
+MODULE_AUTHOR("Icenowy Zheng <icenowy@aosc.io>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/phy/broadcom/phy-brcm-usb-init.c b/drivers/phy/broadcom/phy-brcm-usb-init.c
index 3c53625f8bc2..91b5b09589d6 100644
--- a/drivers/phy/broadcom/phy-brcm-usb-init.c
+++ b/drivers/phy/broadcom/phy-brcm-usb-init.c
@@ -126,8 +126,8 @@ enum {
 	USB_CTRL_SELECTOR_COUNT,
 };
 
-#define USB_CTRL_REG(base, reg)	((void *)base + USB_CTRL_##reg)
-#define USB_XHCI_EC_REG(base, reg) ((void *)base + USB_XHCI_EC_##reg)
+#define USB_CTRL_REG(base, reg)	((void __iomem *)base + USB_CTRL_##reg)
+#define USB_XHCI_EC_REG(base, reg) ((void __iomem *)base + USB_XHCI_EC_##reg)
 #define USB_CTRL_MASK(reg, field) \
 	USB_CTRL_##reg##_##field##_MASK
 #define USB_CTRL_MASK_FAMILY(params, reg, field)			\
@@ -416,7 +416,7 @@ void usb_ctrl_unset_family(struct brcm_usb_init_params *params,
 			   u32 reg_offset, u32 field)
 {
 	u32 mask;
-	void *reg;
+	void __iomem *reg;
 
 	mask = params->usb_reg_bits_map[field];
 	reg = params->ctrl_regs + reg_offset;
@@ -428,7 +428,7 @@ void usb_ctrl_set_family(struct brcm_usb_init_params *params,
 			 u32 reg_offset, u32 field)
 {
 	u32 mask;
-	void *reg;
+	void __iomem *reg;
 
 	mask = params->usb_reg_bits_map[field];
 	reg = params->ctrl_regs + reg_offset;
@@ -707,7 +707,7 @@ static void brcmusb_usb3_otp_fix(struct brcm_usb_init_params *params)
 	void __iomem *xhci_ec_base = params->xhci_ec_regs;
 	u32 val;
 
-	if (params->family_id != 0x74371000 || xhci_ec_base == 0)
+	if (params->family_id != 0x74371000 || !xhci_ec_base)
 		return;
 	brcmusb_writel(0xa20c, USB_XHCI_EC_REG(xhci_ec_base, IRAADR));
 	val = brcmusb_readl(USB_XHCI_EC_REG(xhci_ec_base, IRADAT));
diff --git a/drivers/phy/hisilicon/phy-hisi-inno-usb2.c b/drivers/phy/hisilicon/phy-hisi-inno-usb2.c
index 9b16f13b5ab2..34a6a9a1ceb2 100644
--- a/drivers/phy/hisilicon/phy-hisi-inno-usb2.c
+++ b/drivers/phy/hisilicon/phy-hisi-inno-usb2.c
@@ -114,7 +114,6 @@ static int hisi_inno_phy_probe(struct platform_device *pdev)
 	struct hisi_inno_phy_priv *priv;
 	struct phy_provider *provider;
 	struct device_node *child;
-	struct resource *res;
 	int i = 0;
 	int ret;
 
@@ -122,8 +121,7 @@ static int hisi_inno_phy_probe(struct platform_device *pdev)
 	if (!priv)
 		return -ENOMEM;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	priv->mmio = devm_ioremap_resource(dev, res);
+	priv->mmio = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(priv->mmio)) {
 		ret = PTR_ERR(priv->mmio);
 		return ret;
diff --git a/drivers/phy/hisilicon/phy-histb-combphy.c b/drivers/phy/hisilicon/phy-histb-combphy.c
index 62d10ef20296..f1cb3e4d2add 100644
--- a/drivers/phy/hisilicon/phy-histb-combphy.c
+++ b/drivers/phy/hisilicon/phy-histb-combphy.c
@@ -195,7 +195,6 @@ static int histb_combphy_probe(struct platform_device *pdev)
 	struct histb_combphy_priv *priv;
 	struct device_node *np = dev->of_node;
 	struct histb_combphy_mode *mode;
-	struct resource *res;
 	u32 vals[3];
 	int ret;
 
@@ -203,8 +202,7 @@ static int histb_combphy_probe(struct platform_device *pdev)
 	if (!priv)
 		return -ENOMEM;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	priv->mmio = devm_ioremap_resource(dev, res);
+	priv->mmio = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(priv->mmio)) {
 		ret = PTR_ERR(priv->mmio);
 		return ret;
diff --git a/drivers/phy/lantiq/phy-lantiq-vrx200-pcie.c b/drivers/phy/lantiq/phy-lantiq-vrx200-pcie.c
index 544d64a84cc0..6e457967653e 100644
--- a/drivers/phy/lantiq/phy-lantiq-vrx200-pcie.c
+++ b/drivers/phy/lantiq/phy-lantiq-vrx200-pcie.c
@@ -323,7 +323,8 @@ static int ltq_vrx200_pcie_phy_power_on(struct phy *phy)
 		goto err_disable_pdi_clk;
 
 	/* Check if we are in "startup ready" status */
-	if (ltq_vrx200_pcie_phy_wait_for_pll(phy) != 0)
+	ret = ltq_vrx200_pcie_phy_wait_for_pll(phy);
+	if (ret)
 		goto err_disable_phy_clk;
 
 	ltq_vrx200_pcie_phy_apply_workarounds(phy);
diff --git a/drivers/phy/marvell/phy-mvebu-a3700-utmi.c b/drivers/phy/marvell/phy-mvebu-a3700-utmi.c
index ded900b06f5a..23bc3bf5c4c0 100644
--- a/drivers/phy/marvell/phy-mvebu-a3700-utmi.c
+++ b/drivers/phy/marvell/phy-mvebu-a3700-utmi.c
@@ -216,20 +216,13 @@ static int mvebu_a3700_utmi_phy_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct mvebu_a3700_utmi *utmi;
 	struct phy_provider *provider;
-	struct resource *res;
 
 	utmi = devm_kzalloc(dev, sizeof(*utmi), GFP_KERNEL);
 	if (!utmi)
 		return -ENOMEM;
 
 	/* Get UTMI memory region */
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(dev, "Missing UTMI PHY memory resource\n");
-		return -ENODEV;
-	}
-
-	utmi->regs = devm_ioremap_resource(dev, res);
+	utmi->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(utmi->regs))
 		return PTR_ERR(utmi->regs);
 
diff --git a/drivers/phy/phy-xgene.c b/drivers/phy/phy-xgene.c
index 3c9189473407..7a33ec12f71b 100644
--- a/drivers/phy/phy-xgene.c
+++ b/drivers/phy/phy-xgene.c
@@ -1342,7 +1342,7 @@ static int xgene_phy_hw_initialize(struct xgene_phy_ctx *ctx,
 static void xgene_phy_force_lat_summer_cal(struct xgene_phy_ctx *ctx, int lane)
 {
 	int i;
-	struct {
+	static const struct {
 		u32 reg;
 		u32 val;
 	} serdes_reg[] = {
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.c b/drivers/phy/qualcomm/phy-qcom-qmp.c
index 39e8deb8001e..091e20303a14 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp.c
@@ -165,6 +165,11 @@ static const unsigned int sdm845_ufsphy_regs_layout[] = {
 	[QPHY_PCS_READY_STATUS]		= 0x160,
 };
 
+static const unsigned int sm8150_ufsphy_regs_layout[] = {
+	[QPHY_START_CTRL]		= 0x00,
+	[QPHY_PCS_READY_STATUS]		= 0x180,
+};
+
 static const struct qmp_phy_init_tbl msm8996_pcie_serdes_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_COM_BIAS_EN_CLKBUFLR_EN, 0x1c),
 	QMP_PHY_INIT_CFG(QSERDES_COM_CLK_ENABLE1, 0x10),
@@ -879,6 +884,93 @@ static const struct qmp_phy_init_tbl msm8998_usb3_pcs_tbl[] = {
 	QMP_PHY_INIT_CFG(QPHY_V3_PCS_RXEQTRAINING_RUN_TIME, 0x13),
 };
 
+static const struct qmp_phy_init_tbl sm8150_ufsphy_serdes_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_POWER_DOWN_CONTROL, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_SYSCLK_EN_SEL, 0xd9),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_HSCLK_SEL, 0x11),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_HSCLK_HS_SWITCH_SEL, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_LOCK_CMP_EN, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_VCO_TUNE_MAP, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_PLL_IVCO, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_VCO_TUNE_INITVAL2, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_BIN_VCOCAL_HSCLK_SEL, 0x11),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_DEC_START_MODE0, 0x82),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_CP_CTRL_MODE0, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_PLL_RCTRL_MODE0, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_PLL_CCTRL_MODE0, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_LOCK_CMP1_MODE0, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_LOCK_CMP2_MODE0, 0x0c),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0xac),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x1e),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_DEC_START_MODE1, 0x98),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_CP_CTRL_MODE1, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_PLL_RCTRL_MODE1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_PLL_CCTRL_MODE1, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_LOCK_CMP1_MODE1, 0x32),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_LOCK_CMP2_MODE1, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_BIN_VCOCAL_CMP_CODE1_MODE1, 0xdd),
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_BIN_VCOCAL_CMP_CODE2_MODE1, 0x23),
+
+	/* Rate B */
+	QMP_PHY_INIT_CFG(QSERDES_V4_COM_VCO_TUNE_MAP, 0x06),
+};
+
+static const struct qmp_phy_init_tbl sm8150_ufsphy_tx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V4_TX_PWM_GEAR_1_DIVIDER_BAND0_1, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V4_TX_PWM_GEAR_2_DIVIDER_BAND0_1, 0x03),
+	QMP_PHY_INIT_CFG(QSERDES_V4_TX_PWM_GEAR_3_DIVIDER_BAND0_1, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V4_TX_PWM_GEAR_4_DIVIDER_BAND0_1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V4_TX_LANE_MODE_1, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_V4_TX_TRAN_DRVR_EMP_EN, 0x0c),
+};
+
+static const struct qmp_phy_init_tbl sm8150_ufsphy_rx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_SIGDET_LVL, 0x24),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_SIGDET_CNTRL, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_SIGDET_DEGLITCH_CNTRL, 0x1e),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_BAND, 0x18),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_UCDR_FASTLOCK_FO_GAIN, 0x0a),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x4b),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_UCDR_PI_CONTROLS, 0xf1),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_UCDR_FASTLOCK_COUNT_LOW, 0x80),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_UCDR_PI_CTRL2, 0x80),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_UCDR_FO_GAIN, 0x0c),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_UCDR_SO_GAIN, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_TERM_BW, 0x1b),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_EQU_ADAPTOR_CNTRL2, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_EQU_ADAPTOR_CNTRL3, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_EQU_ADAPTOR_CNTRL4, 0x1d),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_OFFSET_ADAPTOR_CNTRL2, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_IDAC_MEASURE_TIME, 0x10),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_IDAC_TSETTLE_LOW, 0xc0),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_IDAC_TSETTLE_HIGH, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_00_LOW, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_00_HIGH, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_00_HIGH2, 0xf6),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_00_HIGH3, 0x3b),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_00_HIGH4, 0x3d),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_01_LOW, 0xe0),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_01_HIGH, 0xc8),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_01_HIGH2, 0xc8),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_01_HIGH3, 0x3b),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_01_HIGH4, 0xb1),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_10_LOW, 0xe0),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_10_HIGH, 0xc8),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_10_HIGH2, 0xc8),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_10_HIGH3, 0x3b),
+	QMP_PHY_INIT_CFG(QSERDES_V4_RX_RX_MODE_10_HIGH4, 0xb1),
+
+};
+
+static const struct qmp_phy_init_tbl sm8150_ufsphy_pcs_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V4_RX_SIGDET_CTRL2, 0x6d),
+	QMP_PHY_INIT_CFG(QPHY_V4_TX_LARGE_AMP_DRV_LVL, 0x0a),
+	QMP_PHY_INIT_CFG(QPHY_V4_TX_SMALL_AMP_DRV_LVL, 0x02),
+	QMP_PHY_INIT_CFG(QPHY_V4_TX_MID_TERM_CTRL1, 0x43),
+	QMP_PHY_INIT_CFG(QPHY_V4_DEBUG_BUS_CLKSEL, 0x1f),
+	QMP_PHY_INIT_CFG(QPHY_V4_RX_MIN_HIBERN8_TIME, 0xff),
+	QMP_PHY_INIT_CFG(QPHY_V4_MULTI_LANE_CTRL1, 0x02),
+};
 
 /* struct qmp_phy_cfg - per-PHY initialization config */
 struct qmp_phy_cfg {
@@ -1276,6 +1368,31 @@ static const struct qmp_phy_cfg msm8998_usb3phy_cfg = {
 	.is_dual_lane_phy       = true,
 };
 
+static const struct qmp_phy_cfg sm8150_ufsphy_cfg = {
+	.type			= PHY_TYPE_UFS,
+	.nlanes			= 2,
+
+	.serdes_tbl		= sm8150_ufsphy_serdes_tbl,
+	.serdes_tbl_num		= ARRAY_SIZE(sm8150_ufsphy_serdes_tbl),
+	.tx_tbl			= sm8150_ufsphy_tx_tbl,
+	.tx_tbl_num		= ARRAY_SIZE(sm8150_ufsphy_tx_tbl),
+	.rx_tbl			= sm8150_ufsphy_rx_tbl,
+	.rx_tbl_num		= ARRAY_SIZE(sm8150_ufsphy_rx_tbl),
+	.pcs_tbl		= sm8150_ufsphy_pcs_tbl,
+	.pcs_tbl_num		= ARRAY_SIZE(sm8150_ufsphy_pcs_tbl),
+	.clk_list		= sdm845_ufs_phy_clk_l,
+	.num_clks		= ARRAY_SIZE(sdm845_ufs_phy_clk_l),
+	.vreg_list		= qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(qmp_phy_vreg_l),
+	.regs			= sm8150_ufsphy_regs_layout,
+
+	.start_ctrl		= SERDES_START,
+	.pwrdn_ctrl		= SW_PWRDN,
+
+	.is_dual_lane_phy	= true,
+	.no_pcs_sw_reset	= true,
+};
+
 static void qcom_qmp_phy_configure(void __iomem *base,
 				   const unsigned int *regs,
 				   const struct qmp_phy_init_tbl tbl[],
@@ -1998,6 +2115,9 @@ static const struct of_device_id qcom_qmp_phy_of_match_table[] = {
 	}, {
 		.compatible = "qcom,msm8998-qmp-usb3-phy",
 		.data = &msm8998_usb3phy_cfg,
+	}, {
+		.compatible = "qcom,sm8150-qmp-ufs-phy",
+		.data = &sm8150_ufsphy_cfg,
 	},
 	{ },
 };
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.h b/drivers/phy/qualcomm/phy-qcom-qmp.h
index 335ea5d7ef40..ab6ff9b45a32 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp.h
@@ -313,4 +313,100 @@
 #define QPHY_V3_PCS_MISC_OSC_DTCT_MODE2_CONFIG4		0x5c
 #define QPHY_V3_PCS_MISC_OSC_DTCT_MODE2_CONFIG5		0x60
 
+/* Only for QMP V4 PHY - QSERDES COM registers */
+#define QSERDES_V4_COM_PLL_IVCO				0x058
+#define QSERDES_V4_COM_CMN_IPTRIM			0x060
+#define QSERDES_V4_COM_CP_CTRL_MODE0			0x074
+#define QSERDES_V4_COM_CP_CTRL_MODE1			0x078
+#define QSERDES_V4_COM_PLL_RCTRL_MODE0			0x07c
+#define QSERDES_V4_COM_PLL_RCTRL_MODE1			0x080
+#define QSERDES_V4_COM_PLL_CCTRL_MODE0			0x084
+#define QSERDES_V4_COM_PLL_CCTRL_MODE1			0x088
+#define QSERDES_V4_COM_SYSCLK_EN_SEL			0x094
+#define QSERDES_V4_COM_LOCK_CMP_EN			0x0a4
+#define QSERDES_V4_COM_LOCK_CMP1_MODE0			0x0ac
+#define QSERDES_V4_COM_LOCK_CMP2_MODE0			0x0b0
+#define QSERDES_V4_COM_LOCK_CMP1_MODE1			0x0b4
+#define QSERDES_V4_COM_DEC_START_MODE0			0x0bc
+#define QSERDES_V4_COM_LOCK_CMP2_MODE1			0x0b8
+#define QSERDES_V4_COM_DEC_START_MODE1			0x0c4
+#define QSERDES_V4_COM_VCO_TUNE_MAP			0x10c
+#define QSERDES_V4_COM_VCO_TUNE_INITVAL2		0x124
+#define QSERDES_V4_COM_HSCLK_SEL			0x158
+#define QSERDES_V4_COM_HSCLK_HS_SWITCH_SEL		0x15c
+#define QSERDES_V4_COM_BIN_VCOCAL_CMP_CODE1_MODE0	0x1ac
+#define QSERDES_V4_COM_BIN_VCOCAL_CMP_CODE2_MODE0	0x1b0
+#define QSERDES_V4_COM_BIN_VCOCAL_CMP_CODE1_MODE1	0x1b4
+#define QSERDES_V4_COM_BIN_VCOCAL_HSCLK_SEL		0x1bc
+#define QSERDES_V4_COM_BIN_VCOCAL_CMP_CODE2_MODE1	0x1b8
+
+/* Only for QMP V4 PHY - TX registers */
+#define QSERDES_V4_TX_LANE_MODE_1			0x84
+#define QSERDES_V4_TX_PWM_GEAR_1_DIVIDER_BAND0_1	0xd8
+#define QSERDES_V4_TX_PWM_GEAR_2_DIVIDER_BAND0_1	0xdC
+#define QSERDES_V4_TX_PWM_GEAR_3_DIVIDER_BAND0_1	0xe0
+#define QSERDES_V4_TX_PWM_GEAR_4_DIVIDER_BAND0_1	0xe4
+#define QSERDES_V4_TX_TRAN_DRVR_EMP_EN			0xb8
+
+/* Only for QMP V4 PHY - RX registers */
+#define QSERDES_V4_RX_UCDR_FO_GAIN			0x008
+#define QSERDES_V4_RX_UCDR_SO_GAIN			0x014
+#define QSERDES_V4_RX_UCDR_FASTLOCK_FO_GAIN		0x030
+#define QSERDES_V4_RX_UCDR_SO_SATURATION_AND_ENABLE	0x034
+#define QSERDES_V4_RX_UCDR_FASTLOCK_COUNT_LOW		0x03c
+#define QSERDES_V4_RX_UCDR_PI_CONTROLS			0x044
+#define QSERDES_V4_RX_UCDR_PI_CTRL2			0x048
+#define QSERDES_V4_RX_AC_JTAG_ENABLE			0x068
+#define QSERDES_V4_RX_AC_JTAG_MODE			0x078
+#define QSERDES_V4_RX_RX_TERM_BW			0x080
+#define QSERDES_V4_RX_RX_EQU_ADAPTOR_CNTRL2		0x0ec
+#define QSERDES_V4_RX_RX_EQU_ADAPTOR_CNTRL3		0x0f0
+#define QSERDES_V4_RX_RX_EQU_ADAPTOR_CNTRL4		0x0f4
+#define QSERDES_V4_RX_RX_IDAC_TSETTLE_LOW		0x0f8
+#define QSERDES_V4_RX_RX_IDAC_TSETTLE_HIGH		0x0fc
+#define QSERDES_V4_RX_RX_IDAC_MEASURE_TIME		0x100
+#define QSERDES_V4_RX_RX_OFFSET_ADAPTOR_CNTRL2		0x114
+#define QSERDES_V4_RX_SIGDET_CNTRL			0x11c
+#define QSERDES_V4_RX_SIGDET_LVL			0x120
+#define QSERDES_V4_RX_SIGDET_DEGLITCH_CNTRL		0x124
+#define QSERDES_V4_RX_RX_BAND				0x128
+#define QSERDES_V4_RX_RX_MODE_00_LOW			0x170
+#define QSERDES_V4_RX_RX_MODE_00_HIGH			0x174
+#define QSERDES_V4_RX_RX_MODE_00_HIGH2			0x178
+#define QSERDES_V4_RX_RX_MODE_00_HIGH3			0x17c
+#define QSERDES_V4_RX_RX_MODE_00_HIGH4			0x180
+#define QSERDES_V4_RX_RX_MODE_01_LOW			0x184
+#define QSERDES_V4_RX_RX_MODE_01_HIGH			0x188
+#define QSERDES_V4_RX_RX_MODE_01_HIGH2			0x18c
+#define QSERDES_V4_RX_RX_MODE_01_HIGH3			0x190
+#define QSERDES_V4_RX_RX_MODE_01_HIGH4			0x194
+#define QSERDES_V4_RX_RX_MODE_10_LOW			0x198
+#define QSERDES_V4_RX_RX_MODE_10_HIGH			0x19c
+#define QSERDES_V4_RX_RX_MODE_10_HIGH2			0x1a0
+#define QSERDES_V4_RX_RX_MODE_10_HIGH3			0x1a4
+#define QSERDES_V4_RX_RX_MODE_10_HIGH4			0x1a8
+#define QSERDES_V4_RX_DCC_CTRL1				0x1bc
+
+/* Only for QMP V4 PHY - PCS registers */
+#define QPHY_V4_PHY_START				0x000
+#define QPHY_V4_POWER_DOWN_CONTROL			0x004
+#define QPHY_V4_SW_RESET				0x008
+#define QPHY_V4_TIMER_20US_CORECLK_STEPS_MSB		0x00c
+#define QPHY_V4_TIMER_20US_CORECLK_STEPS_LSB		0x010
+#define QPHY_V4_PLL_CNTL				0x02c
+#define QPHY_V4_TX_LARGE_AMP_DRV_LVL			0x030
+#define QPHY_V4_TX_SMALL_AMP_DRV_LVL			0x038
+#define QPHY_V4_BIST_FIXED_PAT_CTRL			0x060
+#define QPHY_V4_TX_HSGEAR_CAPABILITY			0x074
+#define QPHY_V4_RX_HSGEAR_CAPABILITY			0x0b4
+#define QPHY_V4_DEBUG_BUS_CLKSEL			0x124
+#define QPHY_V4_LINECFG_DISABLE				0x148
+#define QPHY_V4_RX_MIN_HIBERN8_TIME			0x150
+#define QPHY_V4_RX_SIGDET_CTRL2				0x158
+#define QPHY_V4_TX_PWM_GEAR_BAND			0x160
+#define QPHY_V4_TX_HS_GEAR_BAND				0x168
+#define QPHY_V4_PCS_READY_STATUS			0x180
+#define QPHY_V4_TX_MID_TERM_CTRL1			0x1d8
+#define QPHY_V4_MULTI_LANE_CTRL1			0x1e0
+
 #endif
diff --git a/drivers/phy/qualcomm/phy-qcom-usb-hs.c b/drivers/phy/qualcomm/phy-qcom-usb-hs.c
index b163b3a1558d..61054272a7c8 100644
--- a/drivers/phy/qualcomm/phy-qcom-usb-hs.c
+++ b/drivers/phy/qualcomm/phy-qcom-usb-hs.c
@@ -158,8 +158,8 @@ static int qcom_usb_hs_phy_power_on(struct phy *phy)
 		/* setup initial state */
 		qcom_usb_hs_phy_vbus_notifier(&uphy->vbus_notify, state,
 					      uphy->vbus_edev);
-		ret = devm_extcon_register_notifier(&ulpi->dev, uphy->vbus_edev,
-				EXTCON_USB, &uphy->vbus_notify);
+		ret = extcon_register_notifier(uphy->vbus_edev, EXTCON_USB,
+					       &uphy->vbus_notify);
 		if (ret)
 			goto err_ulpi;
 	}
@@ -180,6 +180,9 @@ static int qcom_usb_hs_phy_power_off(struct phy *phy)
 {
 	struct qcom_usb_hs_phy *uphy = phy_get_drvdata(phy);
 
+	if (uphy->vbus_edev)
+		extcon_unregister_notifier(uphy->vbus_edev, EXTCON_USB,
+					   &uphy->vbus_notify);
 	regulator_disable(uphy->v3p3);
 	regulator_disable(uphy->v1p8);
 	clk_disable_unprepare(uphy->sleep_clk);
diff --git a/drivers/phy/renesas/phy-rcar-gen2.c b/drivers/phy/renesas/phy-rcar-gen2.c
index 2926e4937301..2e279ac0fa4d 100644
--- a/drivers/phy/renesas/phy-rcar-gen2.c
+++ b/drivers/phy/renesas/phy-rcar-gen2.c
@@ -71,6 +71,7 @@ struct rcar_gen2_phy_driver {
 struct rcar_gen2_phy_data {
 	const struct phy_ops *gen2_phy_ops;
 	const u32 (*select_value)[PHYS_PER_CHANNEL];
+	const u32 num_channels;
 };
 
 static int rcar_gen2_phy_init(struct phy *p)
@@ -271,11 +272,13 @@ static const u32 usb20_select_value[][PHYS_PER_CHANNEL] = {
 static const struct rcar_gen2_phy_data rcar_gen2_usb_phy_data = {
 	.gen2_phy_ops = &rcar_gen2_phy_ops,
 	.select_value = pci_select_value,
+	.num_channels = ARRAY_SIZE(pci_select_value),
 };
 
 static const struct rcar_gen2_phy_data rz_g1c_usb_phy_data = {
 	.gen2_phy_ops = &rz_g1c_phy_ops,
 	.select_value = usb20_select_value,
+	.num_channels = ARRAY_SIZE(usb20_select_value),
 };
 
 static const struct of_device_id rcar_gen2_phy_match_table[] = {
@@ -389,7 +392,7 @@ static int rcar_gen2_phy_probe(struct platform_device *pdev)
 		channel->selected_phy = -1;
 
 		error = of_property_read_u32(np, "reg", &channel_num);
-		if (error || channel_num > 2) {
+		if (error || channel_num >= data->num_channels) {
 			dev_err(dev, "Invalid \"reg\" property\n");
 			of_node_put(np);
 			return error;
diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
index 49ec67d46ccc..bfb22f868857 100644
--- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c
+++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
@@ -21,6 +21,7 @@
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
+#include <linux/string.h>
 #include <linux/usb/of.h>
 #include <linux/workqueue.h>
 
@@ -320,9 +321,9 @@ static ssize_t role_store(struct device *dev, struct device_attribute *attr,
 	if (!ch->is_otg_channel || !rcar_gen3_is_any_rphy_initialized(ch))
 		return -EIO;
 
-	if (!strncmp(buf, "host", strlen("host")))
+	if (sysfs_streq(buf, "host"))
 		new_mode = PHY_MODE_USB_HOST;
-	else if (!strncmp(buf, "peripheral", strlen("peripheral")))
+	else if (sysfs_streq(buf, "peripheral"))
 		new_mode = PHY_MODE_USB_DEVICE;
 	else
 		return -EINVAL;
diff --git a/drivers/phy/rockchip/Kconfig b/drivers/phy/rockchip/Kconfig
index c454c90cd99e..dbd2de4d28b1 100644
--- a/drivers/phy/rockchip/Kconfig
+++ b/drivers/phy/rockchip/Kconfig
@@ -35,6 +35,14 @@ config PHY_ROCKCHIP_INNO_USB2
 	help
 	  Support for Rockchip USB2.0 PHY with Innosilicon IP block.
 
+config PHY_ROCKCHIP_INNO_DSIDPHY
+	tristate "Rockchip Innosilicon MIPI/LVDS/TTL PHY driver"
+	depends on (ARCH_ROCKCHIP || COMPILE_TEST) && OF
+	select GENERIC_PHY
+	help
+	  Enable this to support the Rockchip MIPI/LVDS/TTL PHY with
+	  Innosilicon IP block.
+
 config PHY_ROCKCHIP_PCIE
 	tristate "Rockchip PCIe PHY Driver"
 	depends on (ARCH_ROCKCHIP && OF) || COMPILE_TEST
diff --git a/drivers/phy/rockchip/Makefile b/drivers/phy/rockchip/Makefile
index fd21cbaf40dd..9f59a81e4e0d 100644
--- a/drivers/phy/rockchip/Makefile
+++ b/drivers/phy/rockchip/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_PHY_ROCKCHIP_DP)		+= phy-rockchip-dp.o
 obj-$(CONFIG_PHY_ROCKCHIP_EMMC)		+= phy-rockchip-emmc.o
+obj-$(CONFIG_PHY_ROCKCHIP_INNO_DSIDPHY)	+= phy-rockchip-inno-dsidphy.o
 obj-$(CONFIG_PHY_ROCKCHIP_INNO_HDMI)	+= phy-rockchip-inno-hdmi.o
 obj-$(CONFIG_PHY_ROCKCHIP_INNO_USB2)	+= phy-rockchip-inno-usb2.o
 obj-$(CONFIG_PHY_ROCKCHIP_PCIE)		+= phy-rockchip-pcie.o
diff --git a/drivers/phy/rockchip/phy-rockchip-inno-dsidphy.c b/drivers/phy/rockchip/phy-rockchip-inno-dsidphy.c
new file mode 100644
index 000000000000..fc729ecd3fe9
--- /dev/null
+++ b/drivers/phy/rockchip/phy-rockchip-inno-dsidphy.c
@@ -0,0 +1,805 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 Rockchip Electronics Co. Ltd.
+ *
+ * Author: Wyon Bi <bivvy.bi@rock-chips.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/clk.h>
+#include <linux/iopoll.h>
+#include <linux/clk-provider.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+#include <linux/phy/phy.h>
+#include <linux/pm_runtime.h>
+#include <linux/mfd/syscon.h>
+
+#define PSEC_PER_SEC	1000000000000LL
+
+#define UPDATE(x, h, l)	(((x) << (l)) & GENMASK((h), (l)))
+
+/*
+ * The offset address[7:0] is distributed two parts, one from the bit7 to bit5
+ * is the first address, the other from the bit4 to bit0 is the second address.
+ * when you configure the registers, you must set both of them. The Clock Lane
+ * and Data Lane use the same registers with the same second address, but the
+ * first address is different.
+ */
+#define FIRST_ADDRESS(x)		(((x) & 0x7) << 5)
+#define SECOND_ADDRESS(x)		(((x) & 0x1f) << 0)
+#define PHY_REG(first, second)		(FIRST_ADDRESS(first) | \
+					 SECOND_ADDRESS(second))
+
+/* Analog Register Part: reg00 */
+#define BANDGAP_POWER_MASK			BIT(7)
+#define BANDGAP_POWER_DOWN			BIT(7)
+#define BANDGAP_POWER_ON			0
+#define LANE_EN_MASK				GENMASK(6, 2)
+#define LANE_EN_CK				BIT(6)
+#define LANE_EN_3				BIT(5)
+#define LANE_EN_2				BIT(4)
+#define LANE_EN_1				BIT(3)
+#define LANE_EN_0				BIT(2)
+#define POWER_WORK_MASK				GENMASK(1, 0)
+#define POWER_WORK_ENABLE			UPDATE(1, 1, 0)
+#define POWER_WORK_DISABLE			UPDATE(2, 1, 0)
+/* Analog Register Part: reg01 */
+#define REG_SYNCRST_MASK			BIT(2)
+#define REG_SYNCRST_RESET			BIT(2)
+#define REG_SYNCRST_NORMAL			0
+#define REG_LDOPD_MASK				BIT(1)
+#define REG_LDOPD_POWER_DOWN			BIT(1)
+#define REG_LDOPD_POWER_ON			0
+#define REG_PLLPD_MASK				BIT(0)
+#define REG_PLLPD_POWER_DOWN			BIT(0)
+#define REG_PLLPD_POWER_ON			0
+/* Analog Register Part: reg03 */
+#define REG_FBDIV_HI_MASK			BIT(5)
+#define REG_FBDIV_HI(x)				UPDATE((x >> 8), 5, 5)
+#define REG_PREDIV_MASK				GENMASK(4, 0)
+#define REG_PREDIV(x)				UPDATE(x, 4, 0)
+/* Analog Register Part: reg04 */
+#define REG_FBDIV_LO_MASK			GENMASK(7, 0)
+#define REG_FBDIV_LO(x)				UPDATE(x, 7, 0)
+/* Analog Register Part: reg05 */
+#define SAMPLE_CLOCK_PHASE_MASK			GENMASK(6, 4)
+#define SAMPLE_CLOCK_PHASE(x)			UPDATE(x, 6, 4)
+#define CLOCK_LANE_SKEW_PHASE_MASK		GENMASK(2, 0)
+#define CLOCK_LANE_SKEW_PHASE(x)		UPDATE(x, 2, 0)
+/* Analog Register Part: reg06 */
+#define DATA_LANE_3_SKEW_PHASE_MASK		GENMASK(6, 4)
+#define DATA_LANE_3_SKEW_PHASE(x)		UPDATE(x, 6, 4)
+#define DATA_LANE_2_SKEW_PHASE_MASK		GENMASK(2, 0)
+#define DATA_LANE_2_SKEW_PHASE(x)		UPDATE(x, 2, 0)
+/* Analog Register Part: reg07 */
+#define DATA_LANE_1_SKEW_PHASE_MASK		GENMASK(6, 4)
+#define DATA_LANE_1_SKEW_PHASE(x)		UPDATE(x, 6, 4)
+#define DATA_LANE_0_SKEW_PHASE_MASK		GENMASK(2, 0)
+#define DATA_LANE_0_SKEW_PHASE(x)		UPDATE(x, 2, 0)
+/* Analog Register Part: reg08 */
+#define SAMPLE_CLOCK_DIRECTION_MASK		BIT(4)
+#define SAMPLE_CLOCK_DIRECTION_REVERSE		BIT(4)
+#define SAMPLE_CLOCK_DIRECTION_FORWARD		0
+/* Digital Register Part: reg00 */
+#define REG_DIG_RSTN_MASK			BIT(0)
+#define REG_DIG_RSTN_NORMAL			BIT(0)
+#define REG_DIG_RSTN_RESET			0
+/* Digital Register Part: reg01 */
+#define INVERT_TXCLKESC_MASK			BIT(1)
+#define INVERT_TXCLKESC_ENABLE			BIT(1)
+#define INVERT_TXCLKESC_DISABLE			0
+#define INVERT_TXBYTECLKHS_MASK			BIT(0)
+#define INVERT_TXBYTECLKHS_ENABLE		BIT(0)
+#define INVERT_TXBYTECLKHS_DISABLE		0
+/* Clock/Data0/Data1/Data2/Data3 Lane Register Part: reg05 */
+#define T_LPX_CNT_MASK				GENMASK(5, 0)
+#define T_LPX_CNT(x)				UPDATE(x, 5, 0)
+/* Clock/Data0/Data1/Data2/Data3 Lane Register Part: reg06 */
+#define T_HS_PREPARE_CNT_MASK			GENMASK(6, 0)
+#define T_HS_PREPARE_CNT(x)			UPDATE(x, 6, 0)
+/* Clock/Data0/Data1/Data2/Data3 Lane Register Part: reg07 */
+#define T_HS_ZERO_CNT_MASK			GENMASK(5, 0)
+#define T_HS_ZERO_CNT(x)			UPDATE(x, 5, 0)
+/* Clock/Data0/Data1/Data2/Data3 Lane Register Part: reg08 */
+#define T_HS_TRAIL_CNT_MASK			GENMASK(6, 0)
+#define T_HS_TRAIL_CNT(x)			UPDATE(x, 6, 0)
+/* Clock/Data0/Data1/Data2/Data3 Lane Register Part: reg09 */
+#define T_HS_EXIT_CNT_MASK			GENMASK(4, 0)
+#define T_HS_EXIT_CNT(x)			UPDATE(x, 4, 0)
+/* Clock/Data0/Data1/Data2/Data3 Lane Register Part: reg0a */
+#define T_CLK_POST_CNT_MASK			GENMASK(3, 0)
+#define T_CLK_POST_CNT(x)			UPDATE(x, 3, 0)
+/* Clock/Data0/Data1/Data2/Data3 Lane Register Part: reg0c */
+#define LPDT_TX_PPI_SYNC_MASK			BIT(2)
+#define LPDT_TX_PPI_SYNC_ENABLE			BIT(2)
+#define LPDT_TX_PPI_SYNC_DISABLE		0
+#define T_WAKEUP_CNT_HI_MASK			GENMASK(1, 0)
+#define T_WAKEUP_CNT_HI(x)			UPDATE(x, 1, 0)
+/* Clock/Data0/Data1/Data2/Data3 Lane Register Part: reg0d */
+#define T_WAKEUP_CNT_LO_MASK			GENMASK(7, 0)
+#define T_WAKEUP_CNT_LO(x)			UPDATE(x, 7, 0)
+/* Clock/Data0/Data1/Data2/Data3 Lane Register Part: reg0e */
+#define T_CLK_PRE_CNT_MASK			GENMASK(3, 0)
+#define T_CLK_PRE_CNT(x)			UPDATE(x, 3, 0)
+/* Clock/Data0/Data1/Data2/Data3 Lane Register Part: reg10 */
+#define T_TA_GO_CNT_MASK			GENMASK(5, 0)
+#define T_TA_GO_CNT(x)				UPDATE(x, 5, 0)
+/* Clock/Data0/Data1/Data2/Data3 Lane Register Part: reg11 */
+#define T_TA_SURE_CNT_MASK			GENMASK(5, 0)
+#define T_TA_SURE_CNT(x)			UPDATE(x, 5, 0)
+/* Clock/Data0/Data1/Data2/Data3 Lane Register Part: reg12 */
+#define T_TA_WAIT_CNT_MASK			GENMASK(5, 0)
+#define T_TA_WAIT_CNT(x)			UPDATE(x, 5, 0)
+/* LVDS Register Part: reg00 */
+#define LVDS_DIGITAL_INTERNAL_RESET_MASK	BIT(2)
+#define LVDS_DIGITAL_INTERNAL_RESET_DISABLE	BIT(2)
+#define LVDS_DIGITAL_INTERNAL_RESET_ENABLE	0
+/* LVDS Register Part: reg01 */
+#define LVDS_DIGITAL_INTERNAL_ENABLE_MASK	BIT(7)
+#define LVDS_DIGITAL_INTERNAL_ENABLE		BIT(7)
+#define LVDS_DIGITAL_INTERNAL_DISABLE		0
+/* LVDS Register Part: reg03 */
+#define MODE_ENABLE_MASK			GENMASK(2, 0)
+#define TTL_MODE_ENABLE				BIT(2)
+#define LVDS_MODE_ENABLE			BIT(1)
+#define MIPI_MODE_ENABLE			BIT(0)
+/* LVDS Register Part: reg0b */
+#define LVDS_LANE_EN_MASK			GENMASK(7, 3)
+#define LVDS_DATA_LANE0_EN			BIT(7)
+#define LVDS_DATA_LANE1_EN			BIT(6)
+#define LVDS_DATA_LANE2_EN			BIT(5)
+#define LVDS_DATA_LANE3_EN			BIT(4)
+#define LVDS_CLK_LANE_EN			BIT(3)
+#define LVDS_PLL_POWER_MASK			BIT(2)
+#define LVDS_PLL_POWER_OFF			BIT(2)
+#define LVDS_PLL_POWER_ON			0
+#define LVDS_BANDGAP_POWER_MASK			BIT(0)
+#define LVDS_BANDGAP_POWER_DOWN			BIT(0)
+#define LVDS_BANDGAP_POWER_ON			0
+
+#define DSI_PHY_RSTZ		0xa0
+#define PHY_ENABLECLK		BIT(2)
+#define DSI_PHY_STATUS		0xb0
+#define PHY_LOCK		BIT(0)
+
+struct mipi_dphy_timing {
+	unsigned int clkmiss;
+	unsigned int clkpost;
+	unsigned int clkpre;
+	unsigned int clkprepare;
+	unsigned int clksettle;
+	unsigned int clktermen;
+	unsigned int clktrail;
+	unsigned int clkzero;
+	unsigned int dtermen;
+	unsigned int eot;
+	unsigned int hsexit;
+	unsigned int hsprepare;
+	unsigned int hszero;
+	unsigned int hssettle;
+	unsigned int hsskip;
+	unsigned int hstrail;
+	unsigned int init;
+	unsigned int lpx;
+	unsigned int taget;
+	unsigned int tago;
+	unsigned int tasure;
+	unsigned int wakeup;
+};
+
+struct inno_dsidphy {
+	struct device *dev;
+	struct clk *ref_clk;
+	struct clk *pclk_phy;
+	struct clk *pclk_host;
+	void __iomem *phy_base;
+	void __iomem *host_base;
+	struct reset_control *rst;
+	enum phy_mode mode;
+
+	struct {
+		struct clk_hw hw;
+		u8 prediv;
+		u16 fbdiv;
+		unsigned long rate;
+	} pll;
+};
+
+enum {
+	REGISTER_PART_ANALOG,
+	REGISTER_PART_DIGITAL,
+	REGISTER_PART_CLOCK_LANE,
+	REGISTER_PART_DATA0_LANE,
+	REGISTER_PART_DATA1_LANE,
+	REGISTER_PART_DATA2_LANE,
+	REGISTER_PART_DATA3_LANE,
+	REGISTER_PART_LVDS,
+};
+
+static inline struct inno_dsidphy *hw_to_inno(struct clk_hw *hw)
+{
+	return container_of(hw, struct inno_dsidphy, pll.hw);
+}
+
+static void phy_update_bits(struct inno_dsidphy *inno,
+			    u8 first, u8 second, u8 mask, u8 val)
+{
+	u32 reg = PHY_REG(first, second) << 2;
+	unsigned int tmp, orig;
+
+	orig = readl(inno->phy_base + reg);
+	tmp = orig & ~mask;
+	tmp |= val & mask;
+	writel(tmp, inno->phy_base + reg);
+}
+
+static void mipi_dphy_timing_get_default(struct mipi_dphy_timing *timing,
+					 unsigned long period)
+{
+	/* Global Operation Timing Parameters */
+	timing->clkmiss = 0;
+	timing->clkpost = 70000 + 52 * period;
+	timing->clkpre = 8 * period;
+	timing->clkprepare = 65000;
+	timing->clksettle = 95000;
+	timing->clktermen = 0;
+	timing->clktrail = 80000;
+	timing->clkzero = 260000;
+	timing->dtermen = 0;
+	timing->eot = 0;
+	timing->hsexit = 120000;
+	timing->hsprepare = 65000 + 4 * period;
+	timing->hszero = 145000 + 6 * period;
+	timing->hssettle = 85000 + 6 * period;
+	timing->hsskip = 40000;
+	timing->hstrail = max(8 * period, 60000 + 4 * period);
+	timing->init = 100000000;
+	timing->lpx = 60000;
+	timing->taget = 5 * timing->lpx;
+	timing->tago = 4 * timing->lpx;
+	timing->tasure = 2 * timing->lpx;
+	timing->wakeup = 1000000000;
+}
+
+static void inno_dsidphy_mipi_mode_enable(struct inno_dsidphy *inno)
+{
+	struct mipi_dphy_timing gotp;
+	const struct {
+		unsigned long rate;
+		u8 hs_prepare;
+		u8 clk_lane_hs_zero;
+		u8 data_lane_hs_zero;
+		u8 hs_trail;
+	} timings[] = {
+		{ 110000000, 0x20, 0x16, 0x02, 0x22},
+		{ 150000000, 0x06, 0x16, 0x03, 0x45},
+		{ 200000000, 0x18, 0x17, 0x04, 0x0b},
+		{ 250000000, 0x05, 0x17, 0x05, 0x16},
+		{ 300000000, 0x51, 0x18, 0x06, 0x2c},
+		{ 400000000, 0x64, 0x19, 0x07, 0x33},
+		{ 500000000, 0x20, 0x1b, 0x07, 0x4e},
+		{ 600000000, 0x6a, 0x1d, 0x08, 0x3a},
+		{ 700000000, 0x3e, 0x1e, 0x08, 0x6a},
+		{ 800000000, 0x21, 0x1f, 0x09, 0x29},
+		{1000000000, 0x09, 0x20, 0x09, 0x27},
+	};
+	u32 t_txbyteclkhs, t_txclkesc, ui;
+	u32 txbyteclkhs, txclkesc, esc_clk_div;
+	u32 hs_exit, clk_post, clk_pre, wakeup, lpx, ta_go, ta_sure, ta_wait;
+	u32 hs_prepare, hs_trail, hs_zero, clk_lane_hs_zero, data_lane_hs_zero;
+	unsigned int i;
+
+	/* Select MIPI mode */
+	phy_update_bits(inno, REGISTER_PART_LVDS, 0x03,
+			MODE_ENABLE_MASK, MIPI_MODE_ENABLE);
+	/* Configure PLL */
+	phy_update_bits(inno, REGISTER_PART_ANALOG, 0x03,
+			REG_PREDIV_MASK, REG_PREDIV(inno->pll.prediv));
+	phy_update_bits(inno, REGISTER_PART_ANALOG, 0x03,
+			REG_FBDIV_HI_MASK, REG_FBDIV_HI(inno->pll.fbdiv));
+	phy_update_bits(inno, REGISTER_PART_ANALOG, 0x04,
+			REG_FBDIV_LO_MASK, REG_FBDIV_LO(inno->pll.fbdiv));
+	/* Enable PLL and LDO */
+	phy_update_bits(inno, REGISTER_PART_ANALOG, 0x01,
+			REG_LDOPD_MASK | REG_PLLPD_MASK,
+			REG_LDOPD_POWER_ON | REG_PLLPD_POWER_ON);
+	/* Reset analog */
+	phy_update_bits(inno, REGISTER_PART_ANALOG, 0x01,
+			REG_SYNCRST_MASK, REG_SYNCRST_RESET);
+	udelay(1);
+	phy_update_bits(inno, REGISTER_PART_ANALOG, 0x01,
+			REG_SYNCRST_MASK, REG_SYNCRST_NORMAL);
+	/* Reset digital */
+	phy_update_bits(inno, REGISTER_PART_DIGITAL, 0x00,
+			REG_DIG_RSTN_MASK, REG_DIG_RSTN_RESET);
+	udelay(1);
+	phy_update_bits(inno, REGISTER_PART_DIGITAL, 0x00,
+			REG_DIG_RSTN_MASK, REG_DIG_RSTN_NORMAL);
+
+	txbyteclkhs = inno->pll.rate / 8;
+	t_txbyteclkhs = div_u64(PSEC_PER_SEC, txbyteclkhs);
+
+	esc_clk_div = DIV_ROUND_UP(txbyteclkhs, 20000000);
+	txclkesc = txbyteclkhs / esc_clk_div;
+	t_txclkesc = div_u64(PSEC_PER_SEC, txclkesc);
+
+	ui = div_u64(PSEC_PER_SEC, inno->pll.rate);
+
+	memset(&gotp, 0, sizeof(gotp));
+	mipi_dphy_timing_get_default(&gotp, ui);
+
+	/*
+	 * The value of counter for HS Ths-exit
+	 * Ths-exit = Tpin_txbyteclkhs * value
+	 */
+	hs_exit = DIV_ROUND_UP(gotp.hsexit, t_txbyteclkhs);
+	/*
+	 * The value of counter for HS Tclk-post
+	 * Tclk-post = Tpin_txbyteclkhs * value
+	 */
+	clk_post = DIV_ROUND_UP(gotp.clkpost, t_txbyteclkhs);
+	/*
+	 * The value of counter for HS Tclk-pre
+	 * Tclk-pre = Tpin_txbyteclkhs * value
+	 */
+	clk_pre = DIV_ROUND_UP(gotp.clkpre, t_txbyteclkhs);
+
+	/*
+	 * The value of counter for HS Tlpx Time
+	 * Tlpx = Tpin_txbyteclkhs * (2 + value)
+	 */
+	lpx = DIV_ROUND_UP(gotp.lpx, t_txbyteclkhs);
+	if (lpx >= 2)
+		lpx -= 2;
+
+	/*
+	 * The value of counter for HS Tta-go
+	 * Tta-go for turnaround
+	 * Tta-go = Ttxclkesc * value
+	 */
+	ta_go = DIV_ROUND_UP(gotp.tago, t_txclkesc);
+	/*
+	 * The value of counter for HS Tta-sure
+	 * Tta-sure for turnaround
+	 * Tta-sure = Ttxclkesc * value
+	 */
+	ta_sure = DIV_ROUND_UP(gotp.tasure, t_txclkesc);
+	/*
+	 * The value of counter for HS Tta-wait
+	 * Tta-wait for turnaround
+	 * Tta-wait = Ttxclkesc * value
+	 */
+	ta_wait = DIV_ROUND_UP(gotp.taget, t_txclkesc);
+
+	for (i = 0; i < ARRAY_SIZE(timings); i++)
+		if (inno->pll.rate <= timings[i].rate)
+			break;
+
+	if (i == ARRAY_SIZE(timings))
+		--i;
+
+	hs_prepare = timings[i].hs_prepare;
+	hs_trail = timings[i].hs_trail;
+	clk_lane_hs_zero = timings[i].clk_lane_hs_zero;
+	data_lane_hs_zero = timings[i].data_lane_hs_zero;
+	wakeup = 0x3ff;
+
+	for (i = REGISTER_PART_CLOCK_LANE; i <= REGISTER_PART_DATA3_LANE; i++) {
+		if (i == REGISTER_PART_CLOCK_LANE)
+			hs_zero = clk_lane_hs_zero;
+		else
+			hs_zero = data_lane_hs_zero;
+
+		phy_update_bits(inno, i, 0x05, T_LPX_CNT_MASK,
+				T_LPX_CNT(lpx));
+		phy_update_bits(inno, i, 0x06, T_HS_PREPARE_CNT_MASK,
+				T_HS_PREPARE_CNT(hs_prepare));
+		phy_update_bits(inno, i, 0x07, T_HS_ZERO_CNT_MASK,
+				T_HS_ZERO_CNT(hs_zero));
+		phy_update_bits(inno, i, 0x08, T_HS_TRAIL_CNT_MASK,
+				T_HS_TRAIL_CNT(hs_trail));
+		phy_update_bits(inno, i, 0x09, T_HS_EXIT_CNT_MASK,
+				T_HS_EXIT_CNT(hs_exit));
+		phy_update_bits(inno, i, 0x0a, T_CLK_POST_CNT_MASK,
+				T_CLK_POST_CNT(clk_post));
+		phy_update_bits(inno, i, 0x0e, T_CLK_PRE_CNT_MASK,
+				T_CLK_PRE_CNT(clk_pre));
+		phy_update_bits(inno, i, 0x0c, T_WAKEUP_CNT_HI_MASK,
+				T_WAKEUP_CNT_HI(wakeup >> 8));
+		phy_update_bits(inno, i, 0x0d, T_WAKEUP_CNT_LO_MASK,
+				T_WAKEUP_CNT_LO(wakeup));
+		phy_update_bits(inno, i, 0x10, T_TA_GO_CNT_MASK,
+				T_TA_GO_CNT(ta_go));
+		phy_update_bits(inno, i, 0x11, T_TA_SURE_CNT_MASK,
+				T_TA_SURE_CNT(ta_sure));
+		phy_update_bits(inno, i, 0x12, T_TA_WAIT_CNT_MASK,
+				T_TA_WAIT_CNT(ta_wait));
+	}
+
+	/* Enable all lanes on analog part */
+	phy_update_bits(inno, REGISTER_PART_ANALOG, 0x00,
+			LANE_EN_MASK, LANE_EN_CK | LANE_EN_3 | LANE_EN_2 |
+			LANE_EN_1 | LANE_EN_0);
+}
+
+static void inno_dsidphy_lvds_mode_enable(struct inno_dsidphy *inno)
+{
+	u8 prediv = 2;
+	u16 fbdiv = 28;
+
+	/* Sample clock reverse direction */
+	phy_update_bits(inno, REGISTER_PART_ANALOG, 0x08,
+			SAMPLE_CLOCK_DIRECTION_MASK,
+			SAMPLE_CLOCK_DIRECTION_REVERSE);
+
+	/* Select LVDS mode */
+	phy_update_bits(inno, REGISTER_PART_LVDS, 0x03,
+			MODE_ENABLE_MASK, LVDS_MODE_ENABLE);
+	/* Configure PLL */
+	phy_update_bits(inno, REGISTER_PART_ANALOG, 0x03,
+			REG_PREDIV_MASK, REG_PREDIV(prediv));
+	phy_update_bits(inno, REGISTER_PART_ANALOG, 0x03,
+			REG_FBDIV_HI_MASK, REG_FBDIV_HI(fbdiv));
+	phy_update_bits(inno, REGISTER_PART_ANALOG, 0x04,
+			REG_FBDIV_LO_MASK, REG_FBDIV_LO(fbdiv));
+	phy_update_bits(inno, REGISTER_PART_LVDS, 0x08, 0xff, 0xfc);
+	/* Enable PLL and Bandgap */
+	phy_update_bits(inno, REGISTER_PART_LVDS, 0x0b,
+			LVDS_PLL_POWER_MASK | LVDS_BANDGAP_POWER_MASK,
+			LVDS_PLL_POWER_ON | LVDS_BANDGAP_POWER_ON);
+
+	msleep(20);
+
+	/* Reset LVDS digital logic */
+	phy_update_bits(inno, REGISTER_PART_LVDS, 0x00,
+			LVDS_DIGITAL_INTERNAL_RESET_MASK,
+			LVDS_DIGITAL_INTERNAL_RESET_ENABLE);
+	udelay(1);
+	phy_update_bits(inno, REGISTER_PART_LVDS, 0x00,
+			LVDS_DIGITAL_INTERNAL_RESET_MASK,
+			LVDS_DIGITAL_INTERNAL_RESET_DISABLE);
+	/* Enable LVDS digital logic */
+	phy_update_bits(inno, REGISTER_PART_LVDS, 0x01,
+			LVDS_DIGITAL_INTERNAL_ENABLE_MASK,
+			LVDS_DIGITAL_INTERNAL_ENABLE);
+	/* Enable LVDS analog driver */
+	phy_update_bits(inno, REGISTER_PART_LVDS, 0x0b,
+			LVDS_LANE_EN_MASK, LVDS_CLK_LANE_EN |
+			LVDS_DATA_LANE0_EN | LVDS_DATA_LANE1_EN |
+			LVDS_DATA_LANE2_EN | LVDS_DATA_LANE3_EN);
+}
+
+static int inno_dsidphy_power_on(struct phy *phy)
+{
+	struct inno_dsidphy *inno = phy_get_drvdata(phy);
+
+	clk_prepare_enable(inno->pclk_phy);
+	pm_runtime_get_sync(inno->dev);
+
+	/* Bandgap power on */
+	phy_update_bits(inno, REGISTER_PART_ANALOG, 0x00,
+			BANDGAP_POWER_MASK, BANDGAP_POWER_ON);
+	/* Enable power work */
+	phy_update_bits(inno, REGISTER_PART_ANALOG, 0x00,
+			POWER_WORK_MASK, POWER_WORK_ENABLE);
+
+	switch (inno->mode) {
+	case PHY_MODE_MIPI_DPHY:
+		inno_dsidphy_mipi_mode_enable(inno);
+		break;
+	case PHY_MODE_LVDS:
+		inno_dsidphy_lvds_mode_enable(inno);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int inno_dsidphy_power_off(struct phy *phy)
+{
+	struct inno_dsidphy *inno = phy_get_drvdata(phy);
+
+	phy_update_bits(inno, REGISTER_PART_ANALOG, 0x00, LANE_EN_MASK, 0);
+	phy_update_bits(inno, REGISTER_PART_ANALOG, 0x01,
+			REG_LDOPD_MASK | REG_PLLPD_MASK,
+			REG_LDOPD_POWER_DOWN | REG_PLLPD_POWER_DOWN);
+	phy_update_bits(inno, REGISTER_PART_ANALOG, 0x00,
+			POWER_WORK_MASK, POWER_WORK_DISABLE);
+	phy_update_bits(inno, REGISTER_PART_ANALOG, 0x00,
+			BANDGAP_POWER_MASK, BANDGAP_POWER_DOWN);
+
+	phy_update_bits(inno, REGISTER_PART_LVDS, 0x0b, LVDS_LANE_EN_MASK, 0);
+	phy_update_bits(inno, REGISTER_PART_LVDS, 0x01,
+			LVDS_DIGITAL_INTERNAL_ENABLE_MASK,
+			LVDS_DIGITAL_INTERNAL_DISABLE);
+	phy_update_bits(inno, REGISTER_PART_LVDS, 0x0b,
+			LVDS_PLL_POWER_MASK | LVDS_BANDGAP_POWER_MASK,
+			LVDS_PLL_POWER_OFF | LVDS_BANDGAP_POWER_DOWN);
+
+	pm_runtime_put(inno->dev);
+	clk_disable_unprepare(inno->pclk_phy);
+
+	return 0;
+}
+
+static int inno_dsidphy_set_mode(struct phy *phy, enum phy_mode mode,
+				   int submode)
+{
+	struct inno_dsidphy *inno = phy_get_drvdata(phy);
+
+	switch (mode) {
+	case PHY_MODE_MIPI_DPHY:
+	case PHY_MODE_LVDS:
+		inno->mode = mode;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct phy_ops inno_dsidphy_ops = {
+	.set_mode = inno_dsidphy_set_mode,
+	.power_on = inno_dsidphy_power_on,
+	.power_off = inno_dsidphy_power_off,
+	.owner = THIS_MODULE,
+};
+
+static unsigned long inno_dsidphy_pll_round_rate(struct inno_dsidphy *inno,
+						   unsigned long prate,
+						   unsigned long rate,
+						   u8 *prediv, u16 *fbdiv)
+{
+	unsigned long best_freq = 0;
+	unsigned long fref, fout;
+	u8 min_prediv, max_prediv;
+	u8 _prediv, best_prediv = 1;
+	u16 _fbdiv, best_fbdiv = 1;
+	u32 min_delta = UINT_MAX;
+
+	/*
+	 * The PLL output frequency can be calculated using a simple formula:
+	 * PLL_Output_Frequency = (FREF / PREDIV * FBDIV) / 2
+	 * PLL_Output_Frequency: it is equal to DDR-Clock-Frequency * 2
+	 */
+	fref = prate / 2;
+	if (rate > 1000000000UL)
+		fout = 1000000000UL;
+	else
+		fout = rate;
+
+	/* 5Mhz < Fref / prediv < 40MHz */
+	min_prediv = DIV_ROUND_UP(fref, 40000000);
+	max_prediv = fref / 5000000;
+
+	for (_prediv = min_prediv; _prediv <= max_prediv; _prediv++) {
+		u64 tmp;
+		u32 delta;
+
+		tmp = (u64)fout * _prediv;
+		do_div(tmp, fref);
+		_fbdiv = tmp;
+
+		/*
+		 * The possible settings of feedback divider are
+		 * 12, 13, 14, 16, ~ 511
+		 */
+		if (_fbdiv == 15)
+			continue;
+
+		if (_fbdiv < 12 || _fbdiv > 511)
+			continue;
+
+		tmp = (u64)_fbdiv * fref;
+		do_div(tmp, _prediv);
+
+		delta = abs(fout - tmp);
+		if (!delta) {
+			best_prediv = _prediv;
+			best_fbdiv = _fbdiv;
+			best_freq = tmp;
+			break;
+		} else if (delta < min_delta) {
+			best_prediv = _prediv;
+			best_fbdiv = _fbdiv;
+			best_freq = tmp;
+			min_delta = delta;
+		}
+	}
+
+	if (best_freq) {
+		*prediv = best_prediv;
+		*fbdiv = best_fbdiv;
+	}
+
+	return best_freq;
+}
+
+static long inno_dsidphy_pll_clk_round_rate(struct clk_hw *hw,
+					      unsigned long rate,
+					      unsigned long *prate)
+{
+	struct inno_dsidphy *inno = hw_to_inno(hw);
+	unsigned long fout;
+	u16 fbdiv = 1;
+	u8 prediv = 1;
+
+	fout = inno_dsidphy_pll_round_rate(inno, *prate, rate,
+					     &prediv, &fbdiv);
+
+	return fout;
+}
+
+static int inno_dsidphy_pll_clk_set_rate(struct clk_hw *hw,
+					   unsigned long rate,
+					   unsigned long parent_rate)
+{
+	struct inno_dsidphy *inno = hw_to_inno(hw);
+	unsigned long fout;
+	u16 fbdiv = 1;
+	u8 prediv = 1;
+
+	fout = inno_dsidphy_pll_round_rate(inno, parent_rate, rate,
+					     &prediv, &fbdiv);
+
+	dev_dbg(inno->dev, "fin=%lu, fout=%lu, prediv=%u, fbdiv=%u\n",
+		parent_rate, fout, prediv, fbdiv);
+
+	inno->pll.prediv = prediv;
+	inno->pll.fbdiv = fbdiv;
+	inno->pll.rate = fout;
+
+	return 0;
+}
+
+static unsigned long
+inno_dsidphy_pll_clk_recalc_rate(struct clk_hw *hw, unsigned long prate)
+{
+	struct inno_dsidphy *inno = hw_to_inno(hw);
+
+	/* PLL_Output_Frequency = (FREF / PREDIV * FBDIV) / 2 */
+	return (prate / inno->pll.prediv * inno->pll.fbdiv) / 2;
+}
+
+static const struct clk_ops inno_dsidphy_pll_clk_ops = {
+	.round_rate = inno_dsidphy_pll_clk_round_rate,
+	.set_rate = inno_dsidphy_pll_clk_set_rate,
+	.recalc_rate = inno_dsidphy_pll_clk_recalc_rate,
+};
+
+static int inno_dsidphy_pll_register(struct inno_dsidphy *inno)
+{
+	struct device *dev = inno->dev;
+	struct clk *clk;
+	const char *parent_name;
+	struct clk_init_data init;
+	int ret;
+
+	parent_name = __clk_get_name(inno->ref_clk);
+
+	init.name = "mipi_dphy_pll";
+	ret = of_property_read_string(dev->of_node, "clock-output-names",
+				      &init.name);
+	if (ret < 0)
+		dev_dbg(dev, "phy should set clock-output-names property\n");
+
+	init.ops = &inno_dsidphy_pll_clk_ops;
+	init.parent_names = &parent_name;
+	init.num_parents = 1;
+	init.flags = 0;
+
+	inno->pll.hw.init = &init;
+	clk = devm_clk_register(dev, &inno->pll.hw);
+	if (IS_ERR(clk)) {
+		ret = PTR_ERR(clk);
+		dev_err(dev, "failed to register PLL: %d\n", ret);
+		return ret;
+	}
+
+	return devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get,
+					   &inno->pll.hw);
+}
+
+static int inno_dsidphy_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct inno_dsidphy *inno;
+	struct phy_provider *phy_provider;
+	struct phy *phy;
+	int ret;
+
+	inno = devm_kzalloc(dev, sizeof(*inno), GFP_KERNEL);
+	if (!inno)
+		return -ENOMEM;
+
+	inno->dev = dev;
+	platform_set_drvdata(pdev, inno);
+
+	inno->phy_base = devm_platform_ioremap_resource(pdev, 0);
+	if (!inno->phy_base)
+		return -ENOMEM;
+
+	inno->ref_clk = devm_clk_get(dev, "ref");
+	if (IS_ERR(inno->ref_clk)) {
+		ret = PTR_ERR(inno->ref_clk);
+		dev_err(dev, "failed to get ref clock: %d\n", ret);
+		return ret;
+	}
+
+	inno->pclk_phy = devm_clk_get(dev, "pclk");
+	if (IS_ERR(inno->pclk_phy)) {
+		ret = PTR_ERR(inno->pclk_phy);
+		dev_err(dev, "failed to get phy pclk: %d\n", ret);
+		return ret;
+	}
+
+	inno->rst = devm_reset_control_get(dev, "apb");
+	if (IS_ERR(inno->rst)) {
+		ret = PTR_ERR(inno->rst);
+		dev_err(dev, "failed to get system reset control: %d\n", ret);
+		return ret;
+	}
+
+	phy = devm_phy_create(dev, NULL, &inno_dsidphy_ops);
+	if (IS_ERR(phy)) {
+		ret = PTR_ERR(phy);
+		dev_err(dev, "failed to create phy: %d\n", ret);
+		return ret;
+	}
+
+	phy_set_drvdata(phy, inno);
+
+	phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate);
+	if (IS_ERR(phy_provider)) {
+		ret = PTR_ERR(phy_provider);
+		dev_err(dev, "failed to register phy provider: %d\n", ret);
+		return ret;
+	}
+
+	ret = inno_dsidphy_pll_register(inno);
+	if (ret)
+		return ret;
+
+	pm_runtime_enable(dev);
+
+	return 0;
+}
+
+static int inno_dsidphy_remove(struct platform_device *pdev)
+{
+	struct inno_dsidphy *inno = platform_get_drvdata(pdev);
+
+	pm_runtime_disable(inno->dev);
+
+	return 0;
+}
+
+static const struct of_device_id inno_dsidphy_of_match[] = {
+	{ .compatible = "rockchip,px30-dsi-dphy", },
+	{ .compatible = "rockchip,rk3128-dsi-dphy", },
+	{ .compatible = "rockchip,rk3368-dsi-dphy", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, inno_dsidphy_of_match);
+
+static struct platform_driver inno_dsidphy_driver = {
+	.driver = {
+		.name = "inno-dsidphy",
+		.of_match_table	= of_match_ptr(inno_dsidphy_of_match),
+	},
+	.probe = inno_dsidphy_probe,
+	.remove = inno_dsidphy_remove,
+};
+module_platform_driver(inno_dsidphy_driver);
+
+MODULE_AUTHOR("Wyon Bi <bivvy.bi@rock-chips.com>");
+MODULE_DESCRIPTION("Innosilicon MIPI/LVDS/TTL Video Combo PHY driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
index eae865ff312c..680cc0c8825c 100644
--- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
+++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
@@ -1423,6 +1423,7 @@ static const struct rockchip_usb2phy_cfg rv1108_phy_cfgs[] = {
 };
 
 static const struct of_device_id rockchip_usb2phy_dt_match[] = {
+	{ .compatible = "rockchip,px30-usb2phy", .data = &rk3328_phy_cfgs },
 	{ .compatible = "rockchip,rk3228-usb2phy", .data = &rk3228_phy_cfgs },
 	{ .compatible = "rockchip,rk3328-usb2phy", .data = &rk3328_phy_cfgs },
 	{ .compatible = "rockchip,rk3366-usb2phy", .data = &rk3366_phy_cfgs },
diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c
index 6f3afaf9398f..84c27394c181 100644
--- a/drivers/phy/tegra/xusb-tegra186.c
+++ b/drivers/phy/tegra/xusb-tegra186.c
@@ -857,9 +857,32 @@ static void tegra186_xusb_padctl_remove(struct tegra_xusb_padctl *padctl)
 {
 }
 
+static int tegra186_xusb_padctl_vbus_override(struct tegra_xusb_padctl *padctl,
+					       bool status)
+{
+	u32 value;
+
+	dev_dbg(padctl->dev, "%s vbus override\n", status ? "set" : "clear");
+
+	value = padctl_readl(padctl, USB2_VBUS_ID);
+
+	if (status) {
+		value |= VBUS_OVERRIDE;
+		value &= ~ID_OVERRIDE(~0);
+		value |= ID_OVERRIDE_FLOATING;
+	} else {
+		value &= ~VBUS_OVERRIDE;
+	}
+
+	padctl_writel(padctl, value, USB2_VBUS_ID);
+
+	return 0;
+}
+
 static const struct tegra_xusb_padctl_ops tegra186_xusb_padctl_ops = {
 	.probe = tegra186_xusb_padctl_probe,
 	.remove = tegra186_xusb_padctl_remove,
+	.vbus_override = tegra186_xusb_padctl_vbus_override,
 };
 
 static const char * const tegra186_xusb_padctl_supply_names[] = {
diff --git a/drivers/phy/tegra/xusb-tegra210.c b/drivers/phy/tegra/xusb-tegra210.c
index 0c0df6897a3b..394913bb2f20 100644
--- a/drivers/phy/tegra/xusb-tegra210.c
+++ b/drivers/phy/tegra/xusb-tegra210.c
@@ -39,7 +39,10 @@
 #define XUSB_PADCTL_USB2_PAD_MUX_USB2_BIAS_PAD_XUSB 0x1
 
 #define XUSB_PADCTL_USB2_PORT_CAP 0x008
+#define XUSB_PADCTL_USB2_PORT_CAP_PORTX_CAP_DISABLED(x) (0x0 << ((x) * 4))
 #define XUSB_PADCTL_USB2_PORT_CAP_PORTX_CAP_HOST(x) (0x1 << ((x) * 4))
+#define XUSB_PADCTL_USB2_PORT_CAP_PORTX_CAP_DEVICE(x) (0x2 << ((x) * 4))
+#define XUSB_PADCTL_USB2_PORT_CAP_PORTX_CAP_OTG(x) (0x3 << ((x) * 4))
 #define XUSB_PADCTL_USB2_PORT_CAP_PORTX_CAP_MASK(x) (0x3 << ((x) * 4))
 
 #define XUSB_PADCTL_SS_PORT_MAP 0x014
@@ -47,6 +50,7 @@
 #define XUSB_PADCTL_SS_PORT_MAP_PORTX_MAP_SHIFT(x) ((x) * 5)
 #define XUSB_PADCTL_SS_PORT_MAP_PORTX_MAP_MASK(x) (0x7 << ((x) * 5))
 #define XUSB_PADCTL_SS_PORT_MAP_PORTX_MAP(x, v) (((v) & 0x7) << ((x) * 5))
+#define XUSB_PADCTL_SS_PORT_MAP_PORT_DISABLED 0x7
 
 #define XUSB_PADCTL_ELPG_PROGRAM1 0x024
 #define XUSB_PADCTL_ELPG_PROGRAM1_AUX_MUX_LP0_VCORE_DOWN (1 << 31)
@@ -61,9 +65,14 @@
 #define XUSB_PADCTL_USB3_PAD_MUX_PCIE_IDDQ_DISABLE(x) (1 << (1 + (x)))
 #define XUSB_PADCTL_USB3_PAD_MUX_SATA_IDDQ_DISABLE(x) (1 << (8 + (x)))
 
+#define XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPADX_CTL0(x) (0x080 + (x) * 0x40)
+#define XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL0_ZIP (1 << 18)
+#define XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL0_ZIN (1 << 22)
+
 #define XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPADX_CTL1(x) (0x084 + (x) * 0x40)
 #define XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL1_VREG_LEV_SHIFT 7
 #define XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL1_VREG_LEV_MASK 0x3
+#define XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL1_VREG_LEV_VAL 0x1
 #define XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL1_VREG_FIX18 (1 << 6)
 
 #define XUSB_PADCTL_USB2_OTG_PADX_CTL0(x) (0x088 + (x) * 0x40)
@@ -222,6 +231,12 @@
 #define XUSB_PADCTL_UPHY_USB3_PADX_ECTL6(x) (0xa74 + (x) * 0x40)
 #define XUSB_PADCTL_UPHY_USB3_PAD_ECTL6_RX_EQ_CTRL_H_VAL 0xfcf01368
 
+#define XUSB_PADCTL_USB2_VBUS_ID 0xc60
+#define XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_VBUS_ON (1 << 14)
+#define XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_SHIFT 18
+#define XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_MASK 0xf
+#define XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_FLOATING 8
+
 struct tegra210_xusb_fuse_calibration {
 	u32 hs_curr_level[4];
 	u32 hs_term_range_adj;
@@ -940,6 +955,34 @@ static int tegra210_usb2_phy_power_on(struct phy *phy)
 
 	priv = to_tegra210_xusb_padctl(padctl);
 
+	if (port->usb3_port_fake != -1) {
+		value = padctl_readl(padctl, XUSB_PADCTL_SS_PORT_MAP);
+		value &= ~XUSB_PADCTL_SS_PORT_MAP_PORTX_MAP_MASK(
+					port->usb3_port_fake);
+		value |= XUSB_PADCTL_SS_PORT_MAP_PORTX_MAP(
+					port->usb3_port_fake, index);
+		padctl_writel(padctl, value, XUSB_PADCTL_SS_PORT_MAP);
+
+		value = padctl_readl(padctl, XUSB_PADCTL_ELPG_PROGRAM1);
+		value &= ~XUSB_PADCTL_ELPG_PROGRAM1_SSPX_ELPG_VCORE_DOWN(
+					port->usb3_port_fake);
+		padctl_writel(padctl, value, XUSB_PADCTL_ELPG_PROGRAM1);
+
+		usleep_range(100, 200);
+
+		value = padctl_readl(padctl, XUSB_PADCTL_ELPG_PROGRAM1);
+		value &= ~XUSB_PADCTL_ELPG_PROGRAM1_SSPX_ELPG_CLAMP_EN_EARLY(
+					port->usb3_port_fake);
+		padctl_writel(padctl, value, XUSB_PADCTL_ELPG_PROGRAM1);
+
+		usleep_range(100, 200);
+
+		value = padctl_readl(padctl, XUSB_PADCTL_ELPG_PROGRAM1);
+		value &= ~XUSB_PADCTL_ELPG_PROGRAM1_SSPX_ELPG_CLAMP_EN(
+					port->usb3_port_fake);
+		padctl_writel(padctl, value, XUSB_PADCTL_ELPG_PROGRAM1);
+	}
+
 	value = padctl_readl(padctl, XUSB_PADCTL_USB2_BIAS_PAD_CTL0);
 	value &= ~((XUSB_PADCTL_USB2_BIAS_PAD_CTL0_HS_SQUELCH_LEVEL_MASK <<
 		    XUSB_PADCTL_USB2_BIAS_PAD_CTL0_HS_SQUELCH_LEVEL_SHIFT) |
@@ -957,7 +1000,14 @@ static int tegra210_usb2_phy_power_on(struct phy *phy)
 
 	value = padctl_readl(padctl, XUSB_PADCTL_USB2_PORT_CAP);
 	value &= ~XUSB_PADCTL_USB2_PORT_CAP_PORTX_CAP_MASK(index);
-	value |= XUSB_PADCTL_USB2_PORT_CAP_PORTX_CAP_HOST(index);
+	if (port->mode == USB_DR_MODE_UNKNOWN)
+		value |= XUSB_PADCTL_USB2_PORT_CAP_PORTX_CAP_DISABLED(index);
+	else if (port->mode == USB_DR_MODE_PERIPHERAL)
+		value |= XUSB_PADCTL_USB2_PORT_CAP_PORTX_CAP_DEVICE(index);
+	else if (port->mode == USB_DR_MODE_HOST)
+		value |= XUSB_PADCTL_USB2_PORT_CAP_PORTX_CAP_HOST(index);
+	else if (port->mode == USB_DR_MODE_OTG)
+		value |= XUSB_PADCTL_USB2_PORT_CAP_PORTX_CAP_OTG(index);
 	padctl_writel(padctl, value, XUSB_PADCTL_USB2_PORT_CAP);
 
 	value = padctl_readl(padctl, XUSB_PADCTL_USB2_OTG_PADX_CTL0(index));
@@ -989,7 +1039,12 @@ static int tegra210_usb2_phy_power_on(struct phy *phy)
 			     XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPADX_CTL1(index));
 	value &= ~(XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL1_VREG_LEV_MASK <<
 		   XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL1_VREG_LEV_SHIFT);
-	value |= XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL1_VREG_FIX18;
+	if (port->mode == USB_DR_MODE_HOST)
+		value |= XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL1_VREG_FIX18;
+	else
+		value |=
+		      XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL1_VREG_LEV_VAL <<
+		      XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL1_VREG_LEV_SHIFT;
 	padctl_writel(padctl, value,
 		      XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPADX_CTL1(index));
 
@@ -1062,6 +1117,32 @@ static int tegra210_usb2_phy_power_off(struct phy *phy)
 
 	mutex_lock(&padctl->lock);
 
+	if (port->usb3_port_fake != -1) {
+		value = padctl_readl(padctl, XUSB_PADCTL_ELPG_PROGRAM1);
+		value |= XUSB_PADCTL_ELPG_PROGRAM1_SSPX_ELPG_CLAMP_EN_EARLY(
+					port->usb3_port_fake);
+		padctl_writel(padctl, value, XUSB_PADCTL_ELPG_PROGRAM1);
+
+		usleep_range(100, 200);
+
+		value = padctl_readl(padctl, XUSB_PADCTL_ELPG_PROGRAM1);
+		value |= XUSB_PADCTL_ELPG_PROGRAM1_SSPX_ELPG_CLAMP_EN(
+					port->usb3_port_fake);
+		padctl_writel(padctl, value, XUSB_PADCTL_ELPG_PROGRAM1);
+
+		usleep_range(250, 350);
+
+		value = padctl_readl(padctl, XUSB_PADCTL_ELPG_PROGRAM1);
+		value |= XUSB_PADCTL_ELPG_PROGRAM1_SSPX_ELPG_VCORE_DOWN(
+					port->usb3_port_fake);
+		padctl_writel(padctl, value, XUSB_PADCTL_ELPG_PROGRAM1);
+
+		value = padctl_readl(padctl, XUSB_PADCTL_SS_PORT_MAP);
+		value |= XUSB_PADCTL_SS_PORT_MAP_PORTX_MAP(port->usb3_port_fake,
+					XUSB_PADCTL_SS_PORT_MAP_PORT_DISABLED);
+		padctl_writel(padctl, value, XUSB_PADCTL_SS_PORT_MAP);
+	}
+
 	if (WARN_ON(pad->enable == 0))
 		goto out;
 
@@ -1225,13 +1306,10 @@ static int tegra210_hsic_phy_power_on(struct phy *phy)
 	struct tegra_xusb_hsic_lane *hsic = to_hsic_lane(lane);
 	struct tegra_xusb_hsic_pad *pad = to_hsic_pad(lane->pad);
 	struct tegra_xusb_padctl *padctl = lane->pad->padctl;
-	struct tegra210_xusb_padctl *priv;
 	unsigned int index = lane->index;
 	u32 value;
 	int err;
 
-	priv = to_tegra210_xusb_padctl(padctl);
-
 	err = regulator_enable(pad->supply);
 	if (err)
 		return err;
@@ -1945,6 +2023,52 @@ static const struct tegra_xusb_port_ops tegra210_usb3_port_ops = {
 	.map = tegra210_usb3_port_map,
 };
 
+static int tegra210_xusb_padctl_vbus_override(struct tegra_xusb_padctl *padctl,
+					      bool status)
+{
+	u32 value;
+
+	dev_dbg(padctl->dev, "%s vbus override\n", status ? "set" : "clear");
+
+	value = padctl_readl(padctl, XUSB_PADCTL_USB2_VBUS_ID);
+
+	if (status) {
+		value |= XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_VBUS_ON;
+		value &= ~(XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_MASK <<
+			   XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_SHIFT);
+		value |= XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_FLOATING <<
+			 XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_SHIFT;
+	} else {
+		value &= ~XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_VBUS_ON;
+	}
+
+	padctl_writel(padctl, value, XUSB_PADCTL_USB2_VBUS_ID);
+
+	return 0;
+}
+
+static int tegra210_utmi_port_reset(struct phy *phy)
+{
+	struct tegra_xusb_padctl *padctl;
+	struct tegra_xusb_lane *lane;
+	u32 value;
+
+	lane = phy_get_drvdata(phy);
+	padctl = lane->pad->padctl;
+
+	value = padctl_readl(padctl,
+		     XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPADX_CTL0(lane->index));
+
+	if ((value & XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL0_ZIP) ||
+	    (value & XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL0_ZIN)) {
+		tegra210_xusb_padctl_vbus_override(padctl, false);
+		tegra210_xusb_padctl_vbus_override(padctl, true);
+		return 1;
+	}
+
+	return 0;
+}
+
 static int
 tegra210_xusb_read_fuse_calibration(struct tegra210_xusb_fuse_calibration *fuse)
 {
@@ -2007,6 +2131,8 @@ static const struct tegra_xusb_padctl_ops tegra210_xusb_padctl_ops = {
 	.remove = tegra210_xusb_padctl_remove,
 	.usb3_set_lfps_detect = tegra210_usb3_set_lfps_detect,
 	.hsic_set_idle = tegra210_hsic_set_idle,
+	.vbus_override = tegra210_xusb_padctl_vbus_override,
+	.utmi_port_reset = tegra210_utmi_port_reset,
 };
 
 static const char * const tegra210_xusb_padctl_supply_names[] = {
@@ -2036,6 +2162,7 @@ const struct tegra_xusb_padctl_soc tegra210_xusb_padctl_soc = {
 	.ops = &tegra210_xusb_padctl_ops,
 	.supply_names = tegra210_xusb_padctl_supply_names,
 	.num_supplies = ARRAY_SIZE(tegra210_xusb_padctl_supply_names),
+	.need_fake_usb3_port = true,
 };
 EXPORT_SYMBOL_GPL(tegra210_xusb_padctl_soc);
 
diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c
index 2ea8497af82a..f98ec3922c02 100644
--- a/drivers/phy/tegra/xusb.c
+++ b/drivers/phy/tegra/xusb.c
@@ -800,9 +800,62 @@ static void __tegra_xusb_remove_ports(struct tegra_xusb_padctl *padctl)
 	}
 }
 
+static int tegra_xusb_find_unused_usb3_port(struct tegra_xusb_padctl *padctl)
+{
+	struct device_node *np;
+	unsigned int i;
+
+	for (i = 0; i < padctl->soc->ports.usb3.count; i++) {
+		np = tegra_xusb_find_port_node(padctl, "usb3", i);
+		if (!np || !of_device_is_available(np))
+			return i;
+	}
+
+	return -ENODEV;
+}
+
+static bool tegra_xusb_port_is_companion(struct tegra_xusb_usb2_port *usb2)
+{
+	unsigned int i;
+	struct tegra_xusb_usb3_port *usb3;
+	struct tegra_xusb_padctl *padctl = usb2->base.padctl;
+
+	for (i = 0; i < padctl->soc->ports.usb3.count; i++) {
+		usb3 = tegra_xusb_find_usb3_port(padctl, i);
+		if (usb3 && usb3->port == usb2->base.index)
+			return true;
+	}
+
+	return false;
+}
+
+static int tegra_xusb_update_usb3_fake_port(struct tegra_xusb_usb2_port *usb2)
+{
+	int fake;
+
+	/* Disable usb3_port_fake usage by default and assign if needed */
+	usb2->usb3_port_fake = -1;
+
+	if ((usb2->mode == USB_DR_MODE_OTG ||
+	     usb2->mode == USB_DR_MODE_PERIPHERAL) &&
+		!tegra_xusb_port_is_companion(usb2)) {
+		fake = tegra_xusb_find_unused_usb3_port(usb2->base.padctl);
+		if (fake < 0) {
+			dev_err(&usb2->base.dev, "no unused USB3 ports available\n");
+			return -ENODEV;
+		}
+
+		dev_dbg(&usb2->base.dev, "Found unused usb3 port: %d\n", fake);
+		usb2->usb3_port_fake = fake;
+	}
+
+	return 0;
+}
+
 static int tegra_xusb_setup_ports(struct tegra_xusb_padctl *padctl)
 {
 	struct tegra_xusb_port *port;
+	struct tegra_xusb_usb2_port *usb2;
 	unsigned int i;
 	int err = 0;
 
@@ -832,6 +885,18 @@ static int tegra_xusb_setup_ports(struct tegra_xusb_padctl *padctl)
 			goto remove_ports;
 	}
 
+	if (padctl->soc->need_fake_usb3_port) {
+		for (i = 0; i < padctl->soc->ports.usb2.count; i++) {
+			usb2 = tegra_xusb_find_usb2_port(padctl, i);
+			if (!usb2)
+				continue;
+
+			err = tegra_xusb_update_usb3_fake_port(usb2);
+			if (err < 0)
+				goto remove_ports;
+		}
+	}
+
 	list_for_each_entry(port, &padctl->ports, list) {
 		err = port->ops->enable(port);
 		if (err < 0)
@@ -862,7 +927,6 @@ static int tegra_xusb_padctl_probe(struct platform_device *pdev)
 	struct tegra_xusb_padctl *padctl;
 	const struct of_device_id *match;
 	struct resource *res;
-	unsigned int i;
 	int err;
 
 	/* for backwards compatibility with old device trees */
@@ -907,8 +971,9 @@ static int tegra_xusb_padctl_probe(struct platform_device *pdev)
 		goto remove;
 	}
 
-	for (i = 0; i < padctl->soc->num_supplies; i++)
-		padctl->supplies[i].supply = padctl->soc->supply_names[i];
+	regulator_bulk_set_supply_names(padctl->supplies,
+					padctl->soc->supply_names,
+					padctl->soc->num_supplies);
 
 	err = devm_regulator_bulk_get(&pdev->dev, padctl->soc->num_supplies,
 				      padctl->supplies);
@@ -1056,6 +1121,28 @@ int tegra_xusb_padctl_usb3_set_lfps_detect(struct tegra_xusb_padctl *padctl,
 }
 EXPORT_SYMBOL_GPL(tegra_xusb_padctl_usb3_set_lfps_detect);
 
+int tegra_xusb_padctl_set_vbus_override(struct tegra_xusb_padctl *padctl,
+							bool val)
+{
+	if (padctl->soc->ops->vbus_override)
+		return padctl->soc->ops->vbus_override(padctl, val);
+
+	return -ENOTSUPP;
+}
+EXPORT_SYMBOL_GPL(tegra_xusb_padctl_set_vbus_override);
+
+int tegra_phy_xusb_utmi_port_reset(struct phy *phy)
+{
+	struct tegra_xusb_lane *lane = phy_get_drvdata(phy);
+	struct tegra_xusb_padctl *padctl = lane->pad->padctl;
+
+	if (padctl->soc->ops->utmi_port_reset)
+		return padctl->soc->ops->utmi_port_reset(phy);
+
+	return -ENOTSUPP;
+}
+EXPORT_SYMBOL_GPL(tegra_phy_xusb_utmi_port_reset);
+
 MODULE_AUTHOR("Thierry Reding <treding@nvidia.com>");
 MODULE_DESCRIPTION("Tegra XUSB Pad Controller driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/phy/tegra/xusb.h b/drivers/phy/tegra/xusb.h
index 093076ca27fd..da94fcce6307 100644
--- a/drivers/phy/tegra/xusb.h
+++ b/drivers/phy/tegra/xusb.h
@@ -291,6 +291,7 @@ struct tegra_xusb_usb2_port {
 	struct regulator *supply;
 	enum usb_dr_mode mode;
 	bool internal;
+	int usb3_port_fake;
 };
 
 static inline struct tegra_xusb_usb2_port *
@@ -372,6 +373,8 @@ struct tegra_xusb_padctl_ops {
 			     unsigned int index, bool idle);
 	int (*usb3_set_lfps_detect)(struct tegra_xusb_padctl *padctl,
 				    unsigned int index, bool enable);
+	int (*vbus_override)(struct tegra_xusb_padctl *padctl, bool set);
+	int (*utmi_port_reset)(struct phy *phy);
 };
 
 struct tegra_xusb_padctl_soc {
@@ -389,6 +392,7 @@ struct tegra_xusb_padctl_soc {
 
 	const char * const *supply_names;
 	unsigned int num_supplies;
+	bool need_fake_usb3_port;
 };
 
 struct tegra_xusb_padctl {
diff --git a/drivers/phy/ti/phy-dm816x-usb.c b/drivers/phy/ti/phy-dm816x-usb.c
index cbcce7cf0028..26f194779064 100644
--- a/drivers/phy/ti/phy-dm816x-usb.c
+++ b/drivers/phy/ti/phy-dm816x-usb.c
@@ -189,7 +189,6 @@ static int dm816x_usb_phy_probe(struct platform_device *pdev)
 	struct phy_provider *phy_provider;
 	struct usb_otg *otg;
 	const struct of_device_id *of_id;
-	const struct usb_phy_data *phy_data;
 	int error;
 
 	of_id = of_match_device(of_match_ptr(dm816x_usb_phy_id_table),
@@ -220,8 +219,6 @@ static int dm816x_usb_phy_probe(struct platform_device *pdev)
 	if (phy->usbphy_ctrl == 0x2c)
 		phy->instance = 1;
 
-	phy_data = of_id->data;
-
 	otg = devm_kzalloc(&pdev->dev, sizeof(*otg), GFP_KERNEL);
 	if (!otg)
 		return -ENOMEM;
diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c
index a52c5bb35033..a28bd15297f5 100644
--- a/drivers/phy/ti/phy-gmii-sel.c
+++ b/drivers/phy/ti/phy-gmii-sel.c
@@ -69,11 +69,11 @@ static int phy_gmii_sel_mode(struct phy *phy, enum phy_mode mode, int submode)
 		break;
 
 	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
 		gmii_sel_mode = AM33XX_GMII_SEL_MODE_RGMII;
 		break;
 
 	case PHY_INTERFACE_MODE_RGMII_ID:
-	case PHY_INTERFACE_MODE_RGMII_RXID:
 	case PHY_INTERFACE_MODE_RGMII_TXID:
 		gmii_sel_mode = AM33XX_GMII_SEL_MODE_RGMII;
 		rgmii_id = 1;
diff --git a/drivers/platform/goldfish/Kconfig b/drivers/platform/goldfish/Kconfig
index 77b35df3a801..f3d09b1631e3 100644
--- a/drivers/platform/goldfish/Kconfig
+++ b/drivers/platform/goldfish/Kconfig
@@ -1,8 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 menuconfig GOLDFISH
 	bool "Platform support for Goldfish virtual devices"
-	depends on X86_32 || X86_64 || ARM || ARM64 || MIPS
-	depends on HAS_IOMEM
+	depends on HAS_IOMEM && HAS_DMA
 	help
 	  Say Y here to get to see options for the Goldfish virtual platform.
 	  This option alone does not add any kernel code.
diff --git a/drivers/soundwire/Kconfig b/drivers/soundwire/Kconfig
index c8c80df090d1..c725d0a8b288 100644
--- a/drivers/soundwire/Kconfig
+++ b/drivers/soundwire/Kconfig
@@ -24,7 +24,7 @@ config SOUNDWIRE_CADENCE
 config SOUNDWIRE_INTEL
 	tristate "Intel SoundWire Master driver"
 	select SOUNDWIRE_CADENCE
-	depends on X86 && ACPI && SND_SOC
+	depends on ACPI && SND_SOC
 	help
 	  SoundWire Intel Master driver.
 	  If you have an Intel platform which has a SoundWire Master then
diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index fc53dbe57f85..be5d437058ed 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -422,10 +422,11 @@ static struct sdw_slave *sdw_get_slave(struct sdw_bus *bus, int i)
 
 static int sdw_compare_devid(struct sdw_slave *slave, struct sdw_slave_id id)
 {
-	if (slave->id.unique_id != id.unique_id ||
-	    slave->id.mfg_id != id.mfg_id ||
+	if (slave->id.mfg_id != id.mfg_id ||
 	    slave->id.part_id != id.part_id ||
-	    slave->id.class_id != id.class_id)
+	    slave->id.class_id != id.class_id ||
+	    (slave->id.unique_id != SDW_IGNORED_UNIQUE_ID &&
+	     slave->id.unique_id != id.unique_id))
 		return -ENODEV;
 
 	return 0;
diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c
index 502ed4ec8f07..fed21e2b2277 100644
--- a/drivers/soundwire/cadence_master.c
+++ b/drivers/soundwire/cadence_master.c
@@ -183,9 +183,6 @@ MODULE_PARM_DESC(cdns_mcp_int_mask, "Cadence MCP IntMask");
 #define CDNS_DEFAULT_SSP_INTERVAL		0x18
 #define CDNS_TX_TIMEOUT				2000
 
-#define CDNS_PCM_PDI_OFFSET			0x2
-#define CDNS_PDM_PDI_OFFSET			0x6
-
 #define CDNS_SCP_RX_FIFOLEVEL			0x2
 
 /*
@@ -232,6 +229,22 @@ static int cdns_clear_bit(struct sdw_cdns *cdns, int offset, u32 value)
 }
 
 /*
+ * all changes to the MCP_CONFIG, MCP_CONTROL, MCP_CMDCTRL and MCP_PHYCTRL
+ * need to be confirmed with a write to MCP_CONFIG_UPDATE
+ */
+static int cdns_update_config(struct sdw_cdns *cdns)
+{
+	int ret;
+
+	ret = cdns_clear_bit(cdns, CDNS_MCP_CONFIG_UPDATE,
+			     CDNS_MCP_CONFIG_UPDATE_BIT);
+	if (ret < 0)
+		dev_err(cdns->dev, "Config update timedout\n");
+
+	return ret;
+}
+
+/*
  * debugfs
  */
 #ifdef CONFIG_DEBUG_FS
@@ -279,11 +292,7 @@ static int cdns_reg_show(struct seq_file *s, void *data)
 	ret += scnprintf(buf + ret, RD_BUF - ret,
 			 "\nDPn B0 Registers\n");
 
-	/*
-	 * in sdw_cdns_pdi_init() we filter out the Bulk PDIs,
-	 * so the indices need to be corrected again
-	 */
-	num_ports = cdns->num_ports + CDNS_PCM_PDI_OFFSET;
+	num_ports = cdns->num_ports;
 
 	for (i = 0; i < num_ports; i++) {
 		ret += scnprintf(buf + ret, RD_BUF - ret,
@@ -324,6 +333,26 @@ static int cdns_reg_show(struct seq_file *s, void *data)
 }
 DEFINE_SHOW_ATTRIBUTE(cdns_reg);
 
+static int cdns_hw_reset(void *data, u64 value)
+{
+	struct sdw_cdns *cdns = data;
+	int ret;
+
+	if (value != 1)
+		return -EINVAL;
+
+	/* Userspace changed the hardware state behind the kernel's back */
+	add_taint(TAINT_USER, LOCKDEP_STILL_OK);
+
+	ret = sdw_cdns_exit_reset(cdns);
+
+	dev_dbg(cdns->dev, "link hw_reset done: %d\n", ret);
+
+	return ret;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(cdns_hw_reset_fops, NULL, cdns_hw_reset, "%llu\n");
+
 /**
  * sdw_cdns_debugfs_init() - Cadence debugfs init
  * @cdns: Cadence instance
@@ -332,6 +361,9 @@ DEFINE_SHOW_ATTRIBUTE(cdns_reg);
 void sdw_cdns_debugfs_init(struct sdw_cdns *cdns, struct dentry *root)
 {
 	debugfs_create_file("cdns-registers", 0400, root, cdns, &cdns_reg_fops);
+
+	debugfs_create_file("cdns-hw-reset", 0200, root, cdns,
+			    &cdns_hw_reset_fops);
 }
 EXPORT_SYMBOL_GPL(sdw_cdns_debugfs_init);
 
@@ -752,14 +784,48 @@ EXPORT_SYMBOL(sdw_cdns_thread);
 /*
  * init routines
  */
-static int _cdns_enable_interrupt(struct sdw_cdns *cdns)
+
+/**
+ * sdw_cdns_exit_reset() - Program reset parameters and start bus operations
+ * @cdns: Cadence instance
+ */
+int sdw_cdns_exit_reset(struct sdw_cdns *cdns)
 {
-	u32 mask;
+	/* program maximum length reset to be safe */
+	cdns_updatel(cdns, CDNS_MCP_CONTROL,
+		     CDNS_MCP_CONTROL_RST_DELAY,
+		     CDNS_MCP_CONTROL_RST_DELAY);
+
+	/* use hardware generated reset */
+	cdns_updatel(cdns, CDNS_MCP_CONTROL,
+		     CDNS_MCP_CONTROL_HW_RST,
+		     CDNS_MCP_CONTROL_HW_RST);
+
+	/* enable bus operations with clock and data */
+	cdns_updatel(cdns, CDNS_MCP_CONFIG,
+		     CDNS_MCP_CONFIG_OP,
+		     CDNS_MCP_CONFIG_OP_NORMAL);
+
+	/* commit changes */
+	return cdns_update_config(cdns);
+}
+EXPORT_SYMBOL(sdw_cdns_exit_reset);
 
-	cdns_writel(cdns, CDNS_MCP_SLAVE_INTMASK0,
-		    CDNS_MCP_SLAVE_INTMASK0_MASK);
-	cdns_writel(cdns, CDNS_MCP_SLAVE_INTMASK1,
-		    CDNS_MCP_SLAVE_INTMASK1_MASK);
+/**
+ * sdw_cdns_enable_interrupt() - Enable SDW interrupts and update config
+ * @cdns: Cadence instance
+ */
+int sdw_cdns_enable_interrupt(struct sdw_cdns *cdns, bool state)
+{
+	u32 slave_intmask0 = 0;
+	u32 slave_intmask1 = 0;
+	u32 mask = 0;
+
+	if (!state)
+		goto update_masks;
+
+	slave_intmask0 = CDNS_MCP_SLAVE_INTMASK0_MASK;
+	slave_intmask1 = CDNS_MCP_SLAVE_INTMASK1_MASK;
 
 	/* enable detection of all slave state changes */
 	mask = CDNS_MCP_INT_SLAVE_MASK;
@@ -782,26 +848,13 @@ static int _cdns_enable_interrupt(struct sdw_cdns *cdns)
 	if (interrupt_mask) /* parameter override */
 		mask = interrupt_mask;
 
+update_masks:
+	cdns_writel(cdns, CDNS_MCP_SLAVE_INTMASK0, slave_intmask0);
+	cdns_writel(cdns, CDNS_MCP_SLAVE_INTMASK1, slave_intmask1);
 	cdns_writel(cdns, CDNS_MCP_INTMASK, mask);
 
-	return 0;
-}
-
-/**
- * sdw_cdns_enable_interrupt() - Enable SDW interrupts and update config
- * @cdns: Cadence instance
- */
-int sdw_cdns_enable_interrupt(struct sdw_cdns *cdns)
-{
-	int ret;
-
-	_cdns_enable_interrupt(cdns);
-	ret = cdns_clear_bit(cdns, CDNS_MCP_CONFIG_UPDATE,
-			     CDNS_MCP_CONFIG_UPDATE_BIT);
-	if (ret < 0)
-		dev_err(cdns->dev, "Config update timedout\n");
-
-	return ret;
+	/* commit changes */
+	return cdns_update_config(cdns);
 }
 EXPORT_SYMBOL(sdw_cdns_enable_interrupt);
 
@@ -821,7 +874,6 @@ static int cdns_allocate_pdi(struct sdw_cdns *cdns,
 
 	for (i = 0; i < num; i++) {
 		pdi[i].num = i + pdi_offset;
-		pdi[i].assigned = false;
 	}
 
 	*stream = pdi;
@@ -838,7 +890,8 @@ int sdw_cdns_pdi_init(struct sdw_cdns *cdns,
 		      struct sdw_cdns_stream_config config)
 {
 	struct sdw_cdns_streams *stream;
-	int offset, i, ret;
+	int offset;
+	int ret;
 
 	cdns->pcm.num_bd = config.pcm_bd;
 	cdns->pcm.num_in = config.pcm_in;
@@ -850,11 +903,8 @@ int sdw_cdns_pdi_init(struct sdw_cdns *cdns,
 	/* Allocate PDIs for PCMs */
 	stream = &cdns->pcm;
 
-	/* First two PDIs are reserved for bulk transfers */
-	if (stream->num_bd < CDNS_PCM_PDI_OFFSET)
-		return -EINVAL;
-	stream->num_bd -= CDNS_PCM_PDI_OFFSET;
-	offset = CDNS_PCM_PDI_OFFSET;
+	/* we allocate PDI0 and PDI1 which are used for Bulk */
+	offset = 0;
 
 	ret = cdns_allocate_pdi(cdns, &stream->bd,
 				stream->num_bd, offset);
@@ -881,7 +931,6 @@ int sdw_cdns_pdi_init(struct sdw_cdns *cdns,
 
 	/* Allocate PDIs for PDMs */
 	stream = &cdns->pdm;
-	offset = CDNS_PDM_PDI_OFFSET;
 	ret = cdns_allocate_pdi(cdns, &stream->bd,
 				stream->num_bd, offset);
 	if (ret)
@@ -898,6 +947,9 @@ int sdw_cdns_pdi_init(struct sdw_cdns *cdns,
 
 	ret = cdns_allocate_pdi(cdns, &stream->out,
 				stream->num_out, offset);
+
+	offset += stream->num_out;
+
 	if (ret)
 		return ret;
 
@@ -905,18 +957,6 @@ int sdw_cdns_pdi_init(struct sdw_cdns *cdns,
 	stream->num_pdi = stream->num_bd + stream->num_in + stream->num_out;
 	cdns->num_ports += stream->num_pdi;
 
-	cdns->ports = devm_kcalloc(cdns->dev, cdns->num_ports,
-				   sizeof(*cdns->ports), GFP_KERNEL);
-	if (!cdns->ports) {
-		ret = -ENOMEM;
-		return ret;
-	}
-
-	for (i = 0; i < cdns->num_ports; i++) {
-		cdns->ports[i].assigned = false;
-		cdns->ports[i].num = i + 1; /* Port 0 reserved for bulk */
-	}
-
 	return 0;
 }
 EXPORT_SYMBOL(sdw_cdns_pdi_init);
@@ -939,7 +979,7 @@ static u32 cdns_set_initial_frame_shape(int n_rows, int n_cols)
  * sdw_cdns_init() - Cadence initialization
  * @cdns: Cadence instance
  */
-int sdw_cdns_init(struct sdw_cdns *cdns)
+int sdw_cdns_init(struct sdw_cdns *cdns, bool clock_stop_exit)
 {
 	struct sdw_bus *bus = &cdns->bus;
 	struct sdw_master_prop *prop = &bus->prop;
@@ -947,12 +987,13 @@ int sdw_cdns_init(struct sdw_cdns *cdns)
 	int divider;
 	int ret;
 
-	/* Exit clock stop */
-	ret = cdns_clear_bit(cdns, CDNS_MCP_CONTROL,
-			     CDNS_MCP_CONTROL_CLK_STOP_CLR);
-	if (ret < 0) {
-		dev_err(cdns->dev, "Couldn't exit from clock stop\n");
-		return ret;
+	if (clock_stop_exit) {
+		ret = cdns_clear_bit(cdns, CDNS_MCP_CONTROL,
+				     CDNS_MCP_CONTROL_CLK_STOP_CLR);
+		if (ret < 0) {
+			dev_err(cdns->dev, "Couldn't exit from clock stop\n");
+			return ret;
+		}
 	}
 
 	/* Set clock divider */
@@ -975,6 +1016,10 @@ int sdw_cdns_init(struct sdw_cdns *cdns)
 	cdns_writel(cdns, CDNS_MCP_SSP_CTRL0, CDNS_DEFAULT_SSP_INTERVAL);
 	cdns_writel(cdns, CDNS_MCP_SSP_CTRL1, CDNS_DEFAULT_SSP_INTERVAL);
 
+	/* flush command FIFOs */
+	cdns_updatel(cdns, CDNS_MCP_CONTROL, CDNS_MCP_CONTROL_CMD_RST,
+		     CDNS_MCP_CONTROL_CMD_RST);
+
 	/* Set cmd accept mode */
 	cdns_updatel(cdns, CDNS_MCP_CONTROL, CDNS_MCP_CONTROL_CMD_ACCEPT,
 		     CDNS_MCP_CONTROL_CMD_ACCEPT);
@@ -997,13 +1042,10 @@ int sdw_cdns_init(struct sdw_cdns *cdns)
 	/* Set cmd mode for Tx and Rx cmds */
 	val &= ~CDNS_MCP_CONFIG_CMD;
 
-	/* Set operation to normal */
-	val &= ~CDNS_MCP_CONFIG_OP;
-	val |= CDNS_MCP_CONFIG_OP_NORMAL;
-
 	cdns_writel(cdns, CDNS_MCP_CONFIG, val);
 
-	return 0;
+	/* commit changes */
+	return cdns_update_config(cdns);
 }
 EXPORT_SYMBOL(sdw_cdns_init);
 
@@ -1185,20 +1227,20 @@ EXPORT_SYMBOL(cdns_set_sdw_stream);
  * @num: Number of PDIs
  * @pdi: PDI instances
  *
- * Find and return a free PDI for a given PDI array
+ * Find a PDI for a given PDI array. The PDI num and dai_id are
+ * expected to match, return NULL otherwise.
  */
 static struct sdw_cdns_pdi *cdns_find_pdi(struct sdw_cdns *cdns,
+					  unsigned int offset,
 					  unsigned int num,
-					  struct sdw_cdns_pdi *pdi)
+					  struct sdw_cdns_pdi *pdi,
+					  int dai_id)
 {
 	int i;
 
-	for (i = 0; i < num; i++) {
-		if (pdi[i].assigned)
-			continue;
-		pdi[i].assigned = true;
-		return &pdi[i];
-	}
+	for (i = offset; i < offset + num; i++)
+		if (pdi[i].num == dai_id)
+			return &pdi[i];
 
 	return NULL;
 }
@@ -1207,13 +1249,11 @@ static struct sdw_cdns_pdi *cdns_find_pdi(struct sdw_cdns *cdns,
  * sdw_cdns_config_stream: Configure a stream
  *
  * @cdns: Cadence instance
- * @port: Cadence data port
  * @ch: Channel count
  * @dir: Data direction
  * @pdi: PDI to be used
  */
 void sdw_cdns_config_stream(struct sdw_cdns *cdns,
-			    struct sdw_cdns_port *port,
 			    u32 ch, u32 dir, struct sdw_cdns_pdi *pdi)
 {
 	u32 offset, val = 0;
@@ -1221,113 +1261,51 @@ void sdw_cdns_config_stream(struct sdw_cdns *cdns,
 	if (dir == SDW_DATA_DIR_RX)
 		val = CDNS_PORTCTRL_DIRN;
 
-	offset = CDNS_PORTCTRL + port->num * CDNS_PORT_OFFSET;
+	offset = CDNS_PORTCTRL + pdi->num * CDNS_PORT_OFFSET;
 	cdns_updatel(cdns, offset, CDNS_PORTCTRL_DIRN, val);
 
-	val = port->num;
+	val = pdi->num;
 	val |= ((1 << ch) - 1) << SDW_REG_SHIFT(CDNS_PDI_CONFIG_CHANNEL);
 	cdns_writel(cdns, CDNS_PDI_CONFIG(pdi->num), val);
 }
 EXPORT_SYMBOL(sdw_cdns_config_stream);
 
 /**
- * cdns_get_num_pdi() - Get number of PDIs required
- *
- * @cdns: Cadence instance
- * @pdi: PDI to be used
- * @num: Number of PDIs
- * @ch_count: Channel count
- */
-static int cdns_get_num_pdi(struct sdw_cdns *cdns,
-			    struct sdw_cdns_pdi *pdi,
-			    unsigned int num, u32 ch_count)
-{
-	int i, pdis = 0;
-
-	for (i = 0; i < num; i++) {
-		if (pdi[i].assigned)
-			continue;
-
-		if (pdi[i].ch_count < ch_count)
-			ch_count -= pdi[i].ch_count;
-		else
-			ch_count = 0;
-
-		pdis++;
-
-		if (!ch_count)
-			break;
-	}
-
-	if (ch_count)
-		return 0;
-
-	return pdis;
-}
-
-/**
- * sdw_cdns_get_stream() - Get stream information
- *
- * @cdns: Cadence instance
- * @stream: Stream to be allocated
- * @ch: Channel count
- * @dir: Data direction
- */
-int sdw_cdns_get_stream(struct sdw_cdns *cdns,
-			struct sdw_cdns_streams *stream,
-			u32 ch, u32 dir)
-{
-	int pdis = 0;
-
-	if (dir == SDW_DATA_DIR_RX)
-		pdis = cdns_get_num_pdi(cdns, stream->in, stream->num_in, ch);
-	else
-		pdis = cdns_get_num_pdi(cdns, stream->out, stream->num_out, ch);
-
-	/* check if we found PDI, else find in bi-directional */
-	if (!pdis)
-		pdis = cdns_get_num_pdi(cdns, stream->bd, stream->num_bd, ch);
-
-	return pdis;
-}
-EXPORT_SYMBOL(sdw_cdns_get_stream);
-
-/**
- * sdw_cdns_alloc_stream() - Allocate a stream
+ * sdw_cdns_alloc_pdi() - Allocate a PDI
  *
  * @cdns: Cadence instance
  * @stream: Stream to be allocated
- * @port: Cadence data port
  * @ch: Channel count
  * @dir: Data direction
  */
-int sdw_cdns_alloc_stream(struct sdw_cdns *cdns,
-			  struct sdw_cdns_streams *stream,
-			  struct sdw_cdns_port *port, u32 ch, u32 dir)
+struct sdw_cdns_pdi *sdw_cdns_alloc_pdi(struct sdw_cdns *cdns,
+					struct sdw_cdns_streams *stream,
+					u32 ch, u32 dir, int dai_id)
 {
 	struct sdw_cdns_pdi *pdi = NULL;
 
 	if (dir == SDW_DATA_DIR_RX)
-		pdi = cdns_find_pdi(cdns, stream->num_in, stream->in);
+		pdi = cdns_find_pdi(cdns, 0, stream->num_in, stream->in,
+				    dai_id);
 	else
-		pdi = cdns_find_pdi(cdns, stream->num_out, stream->out);
+		pdi = cdns_find_pdi(cdns, 0, stream->num_out, stream->out,
+				    dai_id);
 
 	/* check if we found a PDI, else find in bi-directional */
 	if (!pdi)
-		pdi = cdns_find_pdi(cdns, stream->num_bd, stream->bd);
-
-	if (!pdi)
-		return -EIO;
-
-	port->pdi = pdi;
-	pdi->l_ch_num = 0;
-	pdi->h_ch_num = ch - 1;
-	pdi->dir = dir;
-	pdi->ch_count = ch;
+		pdi = cdns_find_pdi(cdns, 2, stream->num_bd, stream->bd,
+				    dai_id);
+
+	if (pdi) {
+		pdi->l_ch_num = 0;
+		pdi->h_ch_num = ch - 1;
+		pdi->dir = dir;
+		pdi->ch_count = ch;
+	}
 
-	return 0;
+	return pdi;
 }
-EXPORT_SYMBOL(sdw_cdns_alloc_stream);
+EXPORT_SYMBOL(sdw_cdns_alloc_pdi);
 
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_DESCRIPTION("Cadence Soundwire Library");
diff --git a/drivers/soundwire/cadence_master.h b/drivers/soundwire/cadence_master.h
index 0b72b7094735..001457cbe5ad 100644
--- a/drivers/soundwire/cadence_master.h
+++ b/drivers/soundwire/cadence_master.h
@@ -8,7 +8,6 @@
 /**
  * struct sdw_cdns_pdi: PDI (Physical Data Interface) instance
  *
- * @assigned: pdi assigned
  * @num: pdi number
  * @intel_alh_id: link identifier
  * @l_ch_num: low channel for PDI
@@ -18,7 +17,6 @@
  * @type: stream type, PDM or PCM
  */
 struct sdw_cdns_pdi {
-	bool assigned;
 	int num;
 	int intel_alh_id;
 	int l_ch_num;
@@ -29,23 +27,6 @@ struct sdw_cdns_pdi {
 };
 
 /**
- * struct sdw_cdns_port: Cadence port structure
- *
- * @num: port number
- * @assigned: port assigned
- * @ch: channel count
- * @direction: data port direction
- * @pdi: pdi for this port
- */
-struct sdw_cdns_port {
-	unsigned int num;
-	bool assigned;
-	unsigned int ch;
-	enum sdw_data_direction direction;
-	struct sdw_cdns_pdi *pdi;
-};
-
-/**
  * struct sdw_cdns_streams: Cadence stream data structure
  *
  * @num_bd: number of bidirectional streams
@@ -95,8 +76,8 @@ struct sdw_cdns_stream_config {
  * struct sdw_cdns_dma_data: Cadence DMA data
  *
  * @name: SoundWire stream name
- * @nr_ports: Number of ports
- * @port: Ports
+ * @stream: stream runtime
+ * @pdi: PDI used for this dai
  * @bus: Bus handle
  * @stream_type: Stream type
  * @link_id: Master link id
@@ -104,8 +85,7 @@ struct sdw_cdns_stream_config {
 struct sdw_cdns_dma_data {
 	char *name;
 	struct sdw_stream_runtime *stream;
-	int nr_ports;
-	struct sdw_cdns_port **port;
+	struct sdw_cdns_pdi *pdi;
 	struct sdw_bus *bus;
 	enum sdw_stream_type stream_type;
 	int link_id;
@@ -158,10 +138,11 @@ extern struct sdw_master_ops sdw_cdns_master_ops;
 irqreturn_t sdw_cdns_irq(int irq, void *dev_id);
 irqreturn_t sdw_cdns_thread(int irq, void *dev_id);
 
-int sdw_cdns_init(struct sdw_cdns *cdns);
+int sdw_cdns_init(struct sdw_cdns *cdns, bool clock_stop_exit);
 int sdw_cdns_pdi_init(struct sdw_cdns *cdns,
 		      struct sdw_cdns_stream_config config);
-int sdw_cdns_enable_interrupt(struct sdw_cdns *cdns);
+int sdw_cdns_exit_reset(struct sdw_cdns *cdns);
+int sdw_cdns_enable_interrupt(struct sdw_cdns *cdns, bool state);
 
 #ifdef CONFIG_DEBUG_FS
 void sdw_cdns_debugfs_init(struct sdw_cdns *cdns, struct dentry *root);
@@ -170,10 +151,10 @@ void sdw_cdns_debugfs_init(struct sdw_cdns *cdns, struct dentry *root);
 int sdw_cdns_get_stream(struct sdw_cdns *cdns,
 			struct sdw_cdns_streams *stream,
 			u32 ch, u32 dir);
-int sdw_cdns_alloc_stream(struct sdw_cdns *cdns,
-			  struct sdw_cdns_streams *stream,
-			  struct sdw_cdns_port *port, u32 ch, u32 dir);
-void sdw_cdns_config_stream(struct sdw_cdns *cdns, struct sdw_cdns_port *port,
+struct sdw_cdns_pdi *sdw_cdns_alloc_pdi(struct sdw_cdns *cdns,
+					struct sdw_cdns_streams *stream,
+					u32 ch, u32 dir, int dai_id);
+void sdw_cdns_config_stream(struct sdw_cdns *cdns,
 			    u32 ch, u32 dir, struct sdw_cdns_pdi *pdi);
 
 int sdw_cdns_pcm_set_stream(struct snd_soc_dai *dai,
diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c
index 13c54eac0cc3..99dc61021211 100644
--- a/drivers/soundwire/intel.c
+++ b/drivers/soundwire/intel.c
@@ -10,6 +10,7 @@
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
+#include <linux/io.h>
 #include <linux/platform_device.h>
 #include <sound/pcm_params.h>
 #include <sound/soc.h>
@@ -479,7 +480,10 @@ intel_pdi_shim_configure(struct sdw_intel *sdw, struct sdw_cdns_pdi *pdi)
 	unsigned int link_id = sdw->instance;
 	int pdi_conf = 0;
 
-	pdi->intel_alh_id = (link_id * 16) + pdi->num + 5;
+	/* the Bulk and PCM streams are not contiguous */
+	pdi->intel_alh_id = (link_id * 16) + pdi->num + 3;
+	if (pdi->num >= 2)
+		pdi->intel_alh_id += 2;
 
 	/*
 	 * Program stream parameters to stream SHIM register
@@ -508,7 +512,10 @@ intel_pdi_alh_configure(struct sdw_intel *sdw, struct sdw_cdns_pdi *pdi)
 	unsigned int link_id = sdw->instance;
 	unsigned int conf;
 
-	pdi->intel_alh_id = (link_id * 16) + pdi->num + 5;
+	/* the Bulk and PCM streams are not contiguous */
+	pdi->intel_alh_id = (link_id * 16) + pdi->num + 3;
+	if (pdi->num >= 2)
+		pdi->intel_alh_id += 2;
 
 	/* Program Stream config ALH register */
 	conf = intel_readl(alh, SDW_ALH_STRMZCFG(pdi->intel_alh_id));
@@ -603,66 +610,6 @@ static int intel_post_bank_switch(struct sdw_bus *bus)
  * DAI routines
  */
 
-static struct sdw_cdns_port *intel_alloc_port(struct sdw_intel *sdw,
-					      u32 ch, u32 dir, bool pcm)
-{
-	struct sdw_cdns *cdns = &sdw->cdns;
-	struct sdw_cdns_port *port = NULL;
-	int i, ret = 0;
-
-	for (i = 0; i < cdns->num_ports; i++) {
-		if (cdns->ports[i].assigned)
-			continue;
-
-		port = &cdns->ports[i];
-		port->assigned = true;
-		port->direction = dir;
-		port->ch = ch;
-		break;
-	}
-
-	if (!port) {
-		dev_err(cdns->dev, "Unable to find a free port\n");
-		return NULL;
-	}
-
-	if (pcm) {
-		ret = sdw_cdns_alloc_stream(cdns, &cdns->pcm, port, ch, dir);
-		if (ret)
-			goto out;
-
-		intel_pdi_shim_configure(sdw, port->pdi);
-		sdw_cdns_config_stream(cdns, port, ch, dir, port->pdi);
-
-		intel_pdi_alh_configure(sdw, port->pdi);
-
-	} else {
-		ret = sdw_cdns_alloc_stream(cdns, &cdns->pdm, port, ch, dir);
-	}
-
-out:
-	if (ret) {
-		port->assigned = false;
-		port = NULL;
-	}
-
-	return port;
-}
-
-static void intel_port_cleanup(struct sdw_cdns_dma_data *dma)
-{
-	int i;
-
-	for (i = 0; i < dma->nr_ports; i++) {
-		if (dma->port[i]) {
-			dma->port[i]->pdi->assigned = false;
-			dma->port[i]->pdi = NULL;
-			dma->port[i]->assigned = false;
-			dma->port[i] = NULL;
-		}
-	}
-}
-
 static int intel_hw_params(struct snd_pcm_substream *substream,
 			   struct snd_pcm_hw_params *params,
 			   struct snd_soc_dai *dai)
@@ -670,9 +617,11 @@ static int intel_hw_params(struct snd_pcm_substream *substream,
 	struct sdw_cdns *cdns = snd_soc_dai_get_drvdata(dai);
 	struct sdw_intel *sdw = cdns_to_intel(cdns);
 	struct sdw_cdns_dma_data *dma;
+	struct sdw_cdns_pdi *pdi;
 	struct sdw_stream_config sconfig;
 	struct sdw_port_config *pconfig;
-	int ret, i, ch, dir;
+	int ch, dir;
+	int ret;
 	bool pcm = true;
 
 	dma = snd_soc_dai_get_dma_data(dai, substream);
@@ -685,38 +634,30 @@ static int intel_hw_params(struct snd_pcm_substream *substream,
 	else
 		dir = SDW_DATA_DIR_TX;
 
-	if (dma->stream_type == SDW_STREAM_PDM) {
-		/* TODO: Check whether PDM decimator is already in use */
-		dma->nr_ports = sdw_cdns_get_stream(cdns, &cdns->pdm, ch, dir);
+	if (dma->stream_type == SDW_STREAM_PDM)
 		pcm = false;
-	} else {
-		dma->nr_ports = sdw_cdns_get_stream(cdns, &cdns->pcm, ch, dir);
-	}
 
-	if (!dma->nr_ports) {
-		dev_err(dai->dev, "ports/resources not available\n");
-		return -EINVAL;
+	if (pcm)
+		pdi = sdw_cdns_alloc_pdi(cdns, &cdns->pcm, ch, dir, dai->id);
+	else
+		pdi = sdw_cdns_alloc_pdi(cdns, &cdns->pdm, ch, dir, dai->id);
+
+	if (!pdi) {
+		ret = -EINVAL;
+		goto error;
 	}
 
-	dma->port = kcalloc(dma->nr_ports, sizeof(*dma->port), GFP_KERNEL);
-	if (!dma->port)
-		return -ENOMEM;
+	/* do run-time configurations for SHIM, ALH and PDI/PORT */
+	intel_pdi_shim_configure(sdw, pdi);
+	intel_pdi_alh_configure(sdw, pdi);
+	sdw_cdns_config_stream(cdns, ch, dir, pdi);
 
-	for (i = 0; i < dma->nr_ports; i++) {
-		dma->port[i] = intel_alloc_port(sdw, ch, dir, pcm);
-		if (!dma->port[i]) {
-			ret = -EINVAL;
-			goto port_error;
-		}
-	}
 
 	/* Inform DSP about PDI stream number */
-	for (i = 0; i < dma->nr_ports; i++) {
-		ret = intel_config_stream(sdw, substream, dai, params,
-					  dma->port[i]->pdi->intel_alh_id);
-		if (ret)
-			goto port_error;
-	}
+	ret = intel_config_stream(sdw, substream, dai, params,
+				  pdi->intel_alh_id);
+	if (ret)
+		goto error;
 
 	sconfig.direction = dir;
 	sconfig.ch_count = ch;
@@ -731,32 +672,22 @@ static int intel_hw_params(struct snd_pcm_substream *substream,
 	}
 
 	/* Port configuration */
-	pconfig = kcalloc(dma->nr_ports, sizeof(*pconfig), GFP_KERNEL);
+	pconfig = kcalloc(1, sizeof(*pconfig), GFP_KERNEL);
 	if (!pconfig) {
 		ret =  -ENOMEM;
-		goto port_error;
+		goto error;
 	}
 
-	for (i = 0; i < dma->nr_ports; i++) {
-		pconfig[i].num = dma->port[i]->num;
-		pconfig[i].ch_mask = (1 << ch) - 1;
-	}
+	pconfig->num = pdi->num;
+	pconfig->ch_mask = (1 << ch) - 1;
 
 	ret = sdw_stream_add_master(&cdns->bus, &sconfig,
-				    pconfig, dma->nr_ports, dma->stream);
-	if (ret) {
+				    pconfig, 1, dma->stream);
+	if (ret)
 		dev_err(cdns->dev, "add master to stream failed:%d\n", ret);
-		goto stream_error;
-	}
 
 	kfree(pconfig);
-	return ret;
-
-stream_error:
-	kfree(pconfig);
-port_error:
-	intel_port_cleanup(dma);
-	kfree(dma->port);
+error:
 	return ret;
 }
 
@@ -776,8 +707,6 @@ intel_hw_free(struct snd_pcm_substream *substream, struct snd_soc_dai *dai)
 		dev_err(dai->dev, "remove master from stream %s failed: %d\n",
 			dma->stream->name, ret);
 
-	intel_port_cleanup(dma);
-	kfree(dma->port);
 	return ret;
 }
 
@@ -842,14 +771,6 @@ static int intel_create_dai(struct sdw_cdns *cdns,
 			return -ENOMEM;
 
 		if (type == INTEL_PDI_BD || type == INTEL_PDI_OUT) {
-			dais[i].playback.stream_name =
-				kasprintf(GFP_KERNEL, "SDW%d Tx%d",
-					  cdns->instance, i);
-			if (!dais[i].playback.stream_name) {
-				kfree(dais[i].name);
-				return -ENOMEM;
-			}
-
 			dais[i].playback.channels_min = 1;
 			dais[i].playback.channels_max = max_ch;
 			dais[i].playback.rates = SNDRV_PCM_RATE_48000;
@@ -857,23 +778,12 @@ static int intel_create_dai(struct sdw_cdns *cdns,
 		}
 
 		if (type == INTEL_PDI_BD || type == INTEL_PDI_IN) {
-			dais[i].capture.stream_name =
-				kasprintf(GFP_KERNEL, "SDW%d Rx%d",
-					  cdns->instance, i);
-			if (!dais[i].capture.stream_name) {
-				kfree(dais[i].name);
-				kfree(dais[i].playback.stream_name);
-				return -ENOMEM;
-			}
-
 			dais[i].capture.channels_min = 1;
 			dais[i].capture.channels_max = max_ch;
 			dais[i].capture.rates = SNDRV_PCM_RATE_48000;
 			dais[i].capture.formats = SNDRV_PCM_FMTBIT_S16_LE;
 		}
 
-		dais[i].id = SDW_DAI_ID_RANGE_START + i;
-
 		if (pcm)
 			dais[i].ops = &intel_pcm_dai_ops;
 		else
@@ -993,6 +903,15 @@ static struct sdw_master_ops sdw_intel_ops = {
 	.post_bank_switch = intel_post_bank_switch,
 };
 
+static int intel_init(struct sdw_intel *sdw)
+{
+	/* Initialize shim and controller */
+	intel_link_power_up(sdw);
+	intel_shim_init(sdw);
+
+	return sdw_cdns_init(&sdw->cdns, false);
+}
+
 /*
  * probe and init
  */
@@ -1026,7 +945,7 @@ static int intel_probe(struct platform_device *pdev)
 	ret = sdw_add_bus_master(&sdw->cdns.bus);
 	if (ret) {
 		dev_err(&pdev->dev, "sdw_add_bus_master fail: %d\n", ret);
-		goto err_master_reg;
+		return ret;
 	}
 
 	if (sdw->cdns.bus.prop.hw_disabled) {
@@ -1035,16 +954,11 @@ static int intel_probe(struct platform_device *pdev)
 		return 0;
 	}
 
-	/* Initialize shim and controller */
-	intel_link_power_up(sdw);
-	intel_shim_init(sdw);
-
-	ret = sdw_cdns_init(&sdw->cdns);
+	/* Initialize shim, controller and Cadence IP */
+	ret = intel_init(sdw);
 	if (ret)
 		goto err_init;
 
-	ret = sdw_cdns_enable_interrupt(&sdw->cdns);
-
 	/* Read the PDI config and initialize cadence PDI */
 	intel_pdi_init(sdw, &config);
 	ret = sdw_cdns_pdi_init(&sdw->cdns, config);
@@ -1062,23 +976,35 @@ static int intel_probe(struct platform_device *pdev)
 		goto err_init;
 	}
 
+	ret = sdw_cdns_enable_interrupt(&sdw->cdns, true);
+	if (ret < 0) {
+		dev_err(sdw->cdns.dev, "cannot enable interrupts\n");
+		goto err_init;
+	}
+
+	ret = sdw_cdns_exit_reset(&sdw->cdns);
+	if (ret < 0) {
+		dev_err(sdw->cdns.dev, "unable to exit bus reset sequence\n");
+		goto err_interrupt;
+	}
+
 	/* Register DAIs */
 	ret = intel_register_dai(sdw);
 	if (ret) {
 		dev_err(sdw->cdns.dev, "DAI registration failed: %d\n", ret);
 		snd_soc_unregister_component(sdw->cdns.dev);
-		goto err_dai;
+		goto err_interrupt;
 	}
 
 	intel_debugfs_init(sdw);
 
 	return 0;
 
-err_dai:
+err_interrupt:
+	sdw_cdns_enable_interrupt(&sdw->cdns, false);
 	free_irq(sdw->res->irq, sdw);
 err_init:
 	sdw_delete_bus_master(&sdw->cdns.bus);
-err_master_reg:
 	return ret;
 }
 
@@ -1090,6 +1016,7 @@ static int intel_remove(struct platform_device *pdev)
 
 	if (!sdw->cdns.bus.prop.hw_disabled) {
 		intel_debugfs_exit(sdw);
+		sdw_cdns_enable_interrupt(&sdw->cdns, false);
 		free_irq(sdw->res->irq, sdw);
 		snd_soc_unregister_component(sdw->cdns.dev);
 	}
diff --git a/drivers/soundwire/intel_init.c b/drivers/soundwire/intel_init.c
index b74c2f144962..2a2b4d8df462 100644
--- a/drivers/soundwire/intel_init.c
+++ b/drivers/soundwire/intel_init.c
@@ -9,6 +9,7 @@
 
 #include <linux/acpi.h>
 #include <linux/export.h>
+#include <linux/io.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/soundwire/sdw_intel.h>
diff --git a/drivers/soundwire/slave.c b/drivers/soundwire/slave.c
index 6473fa602f82..19919975bb6d 100644
--- a/drivers/soundwire/slave.c
+++ b/drivers/soundwire/slave.c
@@ -29,10 +29,17 @@ static int sdw_slave_add(struct sdw_bus *bus,
 	slave->dev.parent = bus->dev;
 	slave->dev.fwnode = fwnode;
 
-	/* name shall be sdw:link:mfg:part:class:unique */
-	dev_set_name(&slave->dev, "sdw:%x:%x:%x:%x:%x",
-		     bus->link_id, id->mfg_id, id->part_id,
-		     id->class_id, id->unique_id);
+	if (id->unique_id == SDW_IGNORED_UNIQUE_ID) {
+		/* name shall be sdw:link:mfg:part:class */
+		dev_set_name(&slave->dev, "sdw:%x:%x:%x:%x",
+			     bus->link_id, id->mfg_id, id->part_id,
+			     id->class_id);
+	} else {
+		/* name shall be sdw:link:mfg:part:class:unique */
+		dev_set_name(&slave->dev, "sdw:%x:%x:%x:%x:%x",
+			     bus->link_id, id->mfg_id, id->part_id,
+			     id->class_id, id->unique_id);
+	}
 
 	slave->dev.release = sdw_slave_release;
 	slave->dev.bus = &sdw_bus_type;
@@ -64,6 +71,36 @@ static int sdw_slave_add(struct sdw_bus *bus,
 }
 
 #if IS_ENABLED(CONFIG_ACPI)
+
+static bool find_slave(struct sdw_bus *bus,
+		       struct acpi_device *adev,
+		       struct sdw_slave_id *id)
+{
+	unsigned long long addr;
+	unsigned int link_id;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(adev->handle,
+				       METHOD_NAME__ADR, NULL, &addr);
+
+	if (ACPI_FAILURE(status)) {
+		dev_err(bus->dev, "_ADR resolution failed: %x\n",
+			status);
+		return false;
+	}
+
+	/* Extract link id from ADR, Bit 51 to 48 (included) */
+	link_id = (addr >> 48) & GENMASK(3, 0);
+
+	/* Check for link_id match */
+	if (link_id != bus->link_id)
+		return false;
+
+	sdw_extract_slave_id(bus, addr, id);
+
+	return true;
+}
+
 /*
  * sdw_acpi_find_slaves() - Find Slave devices in Master ACPI node
  * @bus: SDW bus instance
@@ -73,6 +110,7 @@ static int sdw_slave_add(struct sdw_bus *bus,
 int sdw_acpi_find_slaves(struct sdw_bus *bus)
 {
 	struct acpi_device *adev, *parent;
+	struct acpi_device *adev2, *parent2;
 
 	parent = ACPI_COMPANION(bus->dev);
 	if (!parent) {
@@ -81,28 +119,46 @@ int sdw_acpi_find_slaves(struct sdw_bus *bus)
 	}
 
 	list_for_each_entry(adev, &parent->children, node) {
-		unsigned long long addr;
 		struct sdw_slave_id id;
-		unsigned int link_id;
-		acpi_status status;
+		struct sdw_slave_id id2;
+		bool ignore_unique_id = true;
 
-		status = acpi_evaluate_integer(adev->handle,
-					       METHOD_NAME__ADR, NULL, &addr);
+		if (!find_slave(bus, adev, &id))
+			continue;
 
-		if (ACPI_FAILURE(status)) {
-			dev_err(bus->dev, "_ADR resolution failed: %x\n",
-				status);
-			return status;
+		/* brute-force O(N^2) search for duplicates */
+		parent2 = parent;
+		list_for_each_entry(adev2, &parent2->children, node) {
+
+			if (adev == adev2)
+				continue;
+
+			if (!find_slave(bus, adev2, &id2))
+				continue;
+
+			if (id.sdw_version != id2.sdw_version ||
+			    id.mfg_id != id2.mfg_id ||
+			    id.part_id != id2.part_id ||
+			    id.class_id != id2.class_id)
+				continue;
+
+			if (id.unique_id != id2.unique_id) {
+				dev_dbg(bus->dev,
+					"Valid unique IDs %x %x for Slave mfg %x part %d\n",
+					id.unique_id, id2.unique_id,
+					id.mfg_id, id.part_id);
+				ignore_unique_id = false;
+			} else {
+				dev_err(bus->dev,
+					"Invalid unique IDs %x %x for Slave mfg %x part %d\n",
+					id.unique_id, id2.unique_id,
+					id.mfg_id, id.part_id);
+				return -ENODEV;
+			}
 		}
 
-		/* Extract link id from ADR, Bit 51 to 48 (included) */
-		link_id = (addr >> 48) & GENMASK(3, 0);
-
-		/* Check for link_id match */
-		if (link_id != bus->link_id)
-			continue;
-
-		sdw_extract_slave_id(bus, addr, &id);
+		if (ignore_unique_id)
+			id.unique_id = SDW_IGNORED_UNIQUE_ID;
 
 		/*
 		 * don't error check for sdw_slave_add as we want to continue
diff --git a/drivers/thunderbolt/cap.c b/drivers/thunderbolt/cap.c
index 8bf8e031f0bc..fdd77bb4628d 100644
--- a/drivers/thunderbolt/cap.c
+++ b/drivers/thunderbolt/cap.c
@@ -33,9 +33,9 @@ static int tb_port_enable_tmu(struct tb_port *port, bool enable)
 	 * Legacy devices need to have TMU access enabled before port
 	 * space can be fully accessed.
 	 */
-	if (tb_switch_is_lr(sw))
+	if (tb_switch_is_light_ridge(sw))
 		offset = 0x26;
-	else if (tb_switch_is_er(sw))
+	else if (tb_switch_is_eagle_ridge(sw))
 		offset = 0x2a;
 	else
 		return 0;
@@ -60,7 +60,7 @@ static void tb_port_dummy_read(struct tb_port *port)
 	 * reading stale data on next read perform one dummy read after
 	 * port capabilities are walked.
 	 */
-	if (tb_switch_is_lr(port->sw)) {
+	if (tb_switch_is_light_ridge(port->sw)) {
 		u32 dummy;
 
 		tb_port_read(port, &dummy, TB_CFG_PORT, 0, 1);
diff --git a/drivers/thunderbolt/ctl.c b/drivers/thunderbolt/ctl.c
index 2ec1af8f7968..d97813e80e5f 100644
--- a/drivers/thunderbolt/ctl.c
+++ b/drivers/thunderbolt/ctl.c
@@ -962,8 +962,8 @@ int tb_cfg_read(struct tb_ctl *ctl, void *buffer, u64 route, u32 port,
 		return tb_cfg_get_error(ctl, space, &res);
 
 	case -ETIMEDOUT:
-		tb_ctl_warn(ctl, "timeout reading config space %u from %#x\n",
-			    space, offset);
+		tb_ctl_warn(ctl, "%llx: timeout reading config space %u from %#x\n",
+			    route, space, offset);
 		break;
 
 	default:
@@ -988,8 +988,8 @@ int tb_cfg_write(struct tb_ctl *ctl, const void *buffer, u64 route, u32 port,
 		return tb_cfg_get_error(ctl, space, &res);
 
 	case -ETIMEDOUT:
-		tb_ctl_warn(ctl, "timeout writing config space %u to %#x\n",
-			    space, offset);
+		tb_ctl_warn(ctl, "%llx: timeout writing config space %u to %#x\n",
+			    route, space, offset);
 		break;
 
 	default:
diff --git a/drivers/thunderbolt/eeprom.c b/drivers/thunderbolt/eeprom.c
index ee5196479854..8dd7de0cc826 100644
--- a/drivers/thunderbolt/eeprom.c
+++ b/drivers/thunderbolt/eeprom.c
@@ -514,17 +514,6 @@ int tb_drom_read(struct tb_switch *sw)
 		 * no entries). Hardcode the configuration here.
 		 */
 		tb_drom_read_uid_only(sw, &sw->uid);
-
-		sw->ports[1].link_nr = 0;
-		sw->ports[2].link_nr = 1;
-		sw->ports[1].dual_link_port = &sw->ports[2];
-		sw->ports[2].dual_link_port = &sw->ports[1];
-
-		sw->ports[3].link_nr = 0;
-		sw->ports[4].link_nr = 1;
-		sw->ports[3].dual_link_port = &sw->ports[4];
-		sw->ports[4].dual_link_port = &sw->ports[3];
-
 		return 0;
 	}
 
diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c
index 245588f691e7..13e88109742e 100644
--- a/drivers/thunderbolt/icm.c
+++ b/drivers/thunderbolt/icm.c
@@ -11,6 +11,7 @@
 
 #include <linux/delay.h>
 #include <linux/mutex.h>
+#include <linux/moduleparam.h>
 #include <linux/pci.h>
 #include <linux/pm_runtime.h>
 #include <linux/platform_data/x86/apple.h>
@@ -43,6 +44,10 @@
 #define ICM_APPROVE_TIMEOUT		10000	/* ms */
 #define ICM_MAX_LINK			4
 
+static bool start_icm;
+module_param(start_icm, bool, 0444);
+MODULE_PARM_DESC(start_icm, "start ICM firmware if it is not running (default: false)");
+
 /**
  * struct icm - Internal connection manager private data
  * @request_lock: Makes sure only one message is send to ICM at time
@@ -147,6 +152,17 @@ static const struct intel_vss *parse_intel_vss(const void *ep_name, size_t size)
 	return NULL;
 }
 
+static bool intel_vss_is_rtd3(const void *ep_name, size_t size)
+{
+	const struct intel_vss *vss;
+
+	vss = parse_intel_vss(ep_name, size);
+	if (vss)
+		return !!(vss->flags & INTEL_VSS_FLAGS_RTD3);
+
+	return false;
+}
+
 static inline struct tb *icm_to_tb(struct icm *icm)
 {
 	return ((void *)icm - sizeof(struct tb));
@@ -339,6 +355,14 @@ static void icm_veto_end(struct tb *tb)
 	}
 }
 
+static bool icm_firmware_running(const struct tb_nhi *nhi)
+{
+	u32 val;
+
+	val = ioread32(nhi->iobase + REG_FW_STS);
+	return !!(val & REG_FW_STS_ICM_EN);
+}
+
 static bool icm_fr_is_supported(struct tb *tb)
 {
 	return !x86_apple_machine;
@@ -562,58 +586,42 @@ static int icm_fr_disconnect_xdomain_paths(struct tb *tb, struct tb_xdomain *xd)
 	return 0;
 }
 
-static struct tb_switch *add_switch(struct tb_switch *parent_sw, u64 route,
-				    const uuid_t *uuid, const u8 *ep_name,
-				    size_t ep_name_size, u8 connection_id,
-				    u8 connection_key, u8 link, u8 depth,
-				    enum tb_security_level security_level,
-				    bool authorized, bool boot)
+static struct tb_switch *alloc_switch(struct tb_switch *parent_sw, u64 route,
+				      const uuid_t *uuid)
 {
-	const struct intel_vss *vss;
+	struct tb *tb = parent_sw->tb;
 	struct tb_switch *sw;
-	int ret;
-
-	pm_runtime_get_sync(&parent_sw->dev);
 
-	sw = tb_switch_alloc(parent_sw->tb, &parent_sw->dev, route);
-	if (IS_ERR(sw))
-		goto out;
+	sw = tb_switch_alloc(tb, &parent_sw->dev, route);
+	if (IS_ERR(sw)) {
+		tb_warn(tb, "failed to allocate switch at %llx\n", route);
+		return sw;
+	}
 
 	sw->uuid = kmemdup(uuid, sizeof(*uuid), GFP_KERNEL);
 	if (!sw->uuid) {
-		tb_sw_warn(sw, "cannot allocate memory for switch\n");
 		tb_switch_put(sw);
-		goto out;
+		return ERR_PTR(-ENOMEM);
 	}
-	sw->connection_id = connection_id;
-	sw->connection_key = connection_key;
-	sw->link = link;
-	sw->depth = depth;
-	sw->authorized = authorized;
-	sw->security_level = security_level;
-	sw->boot = boot;
+
 	init_completion(&sw->rpm_complete);
+	return sw;
+}
 
-	vss = parse_intel_vss(ep_name, ep_name_size);
-	if (vss)
-		sw->rpm = !!(vss->flags & INTEL_VSS_FLAGS_RTD3);
+static int add_switch(struct tb_switch *parent_sw, struct tb_switch *sw)
+{
+	u64 route = tb_route(sw);
+	int ret;
 
 	/* Link the two switches now */
 	tb_port_at(route, parent_sw)->remote = tb_upstream_port(sw);
 	tb_upstream_port(sw)->remote = tb_port_at(route, parent_sw);
 
 	ret = tb_switch_add(sw);
-	if (ret) {
+	if (ret)
 		tb_port_at(tb_route(sw), parent_sw)->remote = NULL;
-		tb_switch_put(sw);
-		sw = ERR_PTR(ret);
-	}
-
-out:
-	pm_runtime_mark_last_busy(&parent_sw->dev);
-	pm_runtime_put_autosuspend(&parent_sw->dev);
 
-	return sw;
+	return ret;
 }
 
 static void update_switch(struct tb_switch *parent_sw, struct tb_switch *sw,
@@ -697,11 +705,11 @@ icm_fr_device_connected(struct tb *tb, const struct icm_pkg_header *hdr)
 		(const struct icm_fr_event_device_connected *)hdr;
 	enum tb_security_level security_level;
 	struct tb_switch *sw, *parent_sw;
+	bool boot, dual_lane, speed_gen3;
 	struct icm *icm = tb_priv(tb);
 	bool authorized = false;
 	struct tb_xdomain *xd;
 	u8 link, depth;
-	bool boot;
 	u64 route;
 	int ret;
 
@@ -714,6 +722,8 @@ icm_fr_device_connected(struct tb *tb, const struct icm_pkg_header *hdr)
 	security_level = (pkg->hdr.flags & ICM_FLAGS_SLEVEL_MASK) >>
 			 ICM_FLAGS_SLEVEL_SHIFT;
 	boot = pkg->link_info & ICM_LINK_INFO_BOOT;
+	dual_lane = pkg->hdr.flags & ICM_FLAGS_DUAL_LANE;
+	speed_gen3 = pkg->hdr.flags & ICM_FLAGS_SPEED_GEN3;
 
 	if (pkg->link_info & ICM_LINK_INFO_REJECTED) {
 		tb_info(tb, "switch at %u.%u was rejected by ICM firmware because topology limit exceeded\n",
@@ -811,10 +821,27 @@ icm_fr_device_connected(struct tb *tb, const struct icm_pkg_header *hdr)
 		return;
 	}
 
-	add_switch(parent_sw, route, &pkg->ep_uuid, (const u8 *)pkg->ep_name,
-		   sizeof(pkg->ep_name), pkg->connection_id,
-		   pkg->connection_key, link, depth, security_level,
-		   authorized, boot);
+	pm_runtime_get_sync(&parent_sw->dev);
+
+	sw = alloc_switch(parent_sw, route, &pkg->ep_uuid);
+	if (!IS_ERR(sw)) {
+		sw->connection_id = pkg->connection_id;
+		sw->connection_key = pkg->connection_key;
+		sw->link = link;
+		sw->depth = depth;
+		sw->authorized = authorized;
+		sw->security_level = security_level;
+		sw->boot = boot;
+		sw->link_speed = speed_gen3 ? 20 : 10;
+		sw->link_width = dual_lane ? 2 : 1;
+		sw->rpm = intel_vss_is_rtd3(pkg->ep_name, sizeof(pkg->ep_name));
+
+		if (add_switch(parent_sw, sw))
+			tb_switch_put(sw);
+	}
+
+	pm_runtime_mark_last_busy(&parent_sw->dev);
+	pm_runtime_put_autosuspend(&parent_sw->dev);
 
 	tb_switch_put(parent_sw);
 }
@@ -1142,10 +1169,10 @@ __icm_tr_device_connected(struct tb *tb, const struct icm_pkg_header *hdr,
 {
 	const struct icm_tr_event_device_connected *pkg =
 		(const struct icm_tr_event_device_connected *)hdr;
+	bool authorized, boot, dual_lane, speed_gen3;
 	enum tb_security_level security_level;
 	struct tb_switch *sw, *parent_sw;
 	struct tb_xdomain *xd;
-	bool authorized, boot;
 	u64 route;
 
 	icm_postpone_rescan(tb);
@@ -1163,6 +1190,8 @@ __icm_tr_device_connected(struct tb *tb, const struct icm_pkg_header *hdr,
 	security_level = (pkg->hdr.flags & ICM_FLAGS_SLEVEL_MASK) >>
 			 ICM_FLAGS_SLEVEL_SHIFT;
 	boot = pkg->link_info & ICM_LINK_INFO_BOOT;
+	dual_lane = pkg->hdr.flags & ICM_FLAGS_DUAL_LANE;
+	speed_gen3 = pkg->hdr.flags & ICM_FLAGS_SPEED_GEN3;
 
 	if (pkg->link_info & ICM_LINK_INFO_REJECTED) {
 		tb_info(tb, "switch at %llx was rejected by ICM firmware because topology limit exceeded\n",
@@ -1205,11 +1234,27 @@ __icm_tr_device_connected(struct tb *tb, const struct icm_pkg_header *hdr,
 		return;
 	}
 
-	sw = add_switch(parent_sw, route, &pkg->ep_uuid, (const u8 *)pkg->ep_name,
-			sizeof(pkg->ep_name), pkg->connection_id, 0, 0, 0,
-			security_level, authorized, boot);
-	if (!IS_ERR(sw) && force_rtd3)
-		sw->rpm = true;
+	pm_runtime_get_sync(&parent_sw->dev);
+
+	sw = alloc_switch(parent_sw, route, &pkg->ep_uuid);
+	if (!IS_ERR(sw)) {
+		sw->connection_id = pkg->connection_id;
+		sw->authorized = authorized;
+		sw->security_level = security_level;
+		sw->boot = boot;
+		sw->link_speed = speed_gen3 ? 20 : 10;
+		sw->link_width = dual_lane ? 2 : 1;
+		sw->rpm = force_rtd3;
+		if (!sw->rpm)
+			sw->rpm = intel_vss_is_rtd3(pkg->ep_name,
+						    sizeof(pkg->ep_name));
+
+		if (add_switch(parent_sw, sw))
+			tb_switch_put(sw);
+	}
+
+	pm_runtime_mark_last_busy(&parent_sw->dev);
+	pm_runtime_put_autosuspend(&parent_sw->dev);
 
 	tb_switch_put(parent_sw);
 }
@@ -1349,9 +1394,12 @@ static bool icm_ar_is_supported(struct tb *tb)
 	/*
 	 * Starting from Alpine Ridge we can use ICM on Apple machines
 	 * as well. We just need to reset and re-enable it first.
+	 * However, only start it if explicitly asked by the user.
 	 */
-	if (!x86_apple_machine)
+	if (icm_firmware_running(tb->nhi))
 		return true;
+	if (!start_icm)
+		return false;
 
 	/*
 	 * Find the upstream PCIe port in case we need to do reset
@@ -1704,8 +1752,7 @@ static int icm_firmware_start(struct tb *tb, struct tb_nhi *nhi)
 	u32 val;
 
 	/* Check if the ICM firmware is already running */
-	val = ioread32(nhi->iobase + REG_FW_STS);
-	if (val & REG_FW_STS_ICM_EN)
+	if (icm_firmware_running(nhi))
 		return 0;
 
 	dev_dbg(&nhi->pdev->dev, "starting ICM firmware\n");
@@ -1893,14 +1940,12 @@ static int icm_suspend(struct tb *tb)
  */
 static void icm_unplug_children(struct tb_switch *sw)
 {
-	unsigned int i;
+	struct tb_port *port;
 
 	if (tb_route(sw))
 		sw->is_unplugged = true;
 
-	for (i = 1; i <= sw->config.max_port_number; i++) {
-		struct tb_port *port = &sw->ports[i];
-
+	tb_switch_for_each_port(sw, port) {
 		if (port->xdomain)
 			port->xdomain->is_unplugged = true;
 		else if (tb_port_has_remote(port))
@@ -1936,11 +1981,9 @@ static void remove_unplugged_switch(struct tb_switch *sw)
 
 static void icm_free_unplugged_children(struct tb_switch *sw)
 {
-	unsigned int i;
-
-	for (i = 1; i <= sw->config.max_port_number; i++) {
-		struct tb_port *port = &sw->ports[i];
+	struct tb_port *port;
 
+	tb_switch_for_each_port(sw, port) {
 		if (port->xdomain && port->xdomain->is_unplugged) {
 			tb_xdomain_remove(port->xdomain);
 			port->xdomain = NULL;
@@ -2216,7 +2259,7 @@ struct tb *icm_probe(struct tb_nhi *nhi)
 
 	case PCI_DEVICE_ID_INTEL_ICL_NHI0:
 	case PCI_DEVICE_ID_INTEL_ICL_NHI1:
-		icm->is_supported = icm_ar_is_supported;
+		icm->is_supported = icm_fr_is_supported;
 		icm->driver_ready = icm_icl_driver_ready;
 		icm->set_uuid = icm_icl_set_uuid;
 		icm->device_connected = icm_icl_device_connected;
diff --git a/drivers/thunderbolt/lc.c b/drivers/thunderbolt/lc.c
index ae1e92611c3e..bd44d50246d2 100644
--- a/drivers/thunderbolt/lc.c
+++ b/drivers/thunderbolt/lc.c
@@ -94,7 +94,7 @@ int tb_lc_configure_link(struct tb_switch *sw)
 	struct tb_port *up, *down;
 	int ret;
 
-	if (!sw->config.enabled || !tb_route(sw))
+	if (!tb_route(sw) || tb_switch_is_icm(sw))
 		return 0;
 
 	up = tb_upstream_port(sw);
@@ -124,7 +124,7 @@ void tb_lc_unconfigure_link(struct tb_switch *sw)
 {
 	struct tb_port *up, *down;
 
-	if (sw->is_unplugged || !sw->config.enabled || !tb_route(sw))
+	if (sw->is_unplugged || !tb_route(sw) || tb_switch_is_icm(sw))
 		return;
 
 	up = tb_upstream_port(sw);
@@ -177,3 +177,192 @@ int tb_lc_set_sleep(struct tb_switch *sw)
 
 	return 0;
 }
+
+/**
+ * tb_lc_lane_bonding_possible() - Is lane bonding possible towards switch
+ * @sw: Switch to check
+ *
+ * Checks whether conditions for lane bonding from parent to @sw are
+ * possible.
+ */
+bool tb_lc_lane_bonding_possible(struct tb_switch *sw)
+{
+	struct tb_port *up;
+	int cap, ret;
+	u32 val;
+
+	if (sw->generation < 2)
+		return false;
+
+	up = tb_upstream_port(sw);
+	cap = find_port_lc_cap(up);
+	if (cap < 0)
+		return false;
+
+	ret = tb_sw_read(sw, &val, TB_CFG_SWITCH, cap + TB_LC_PORT_ATTR, 1);
+	if (ret)
+		return false;
+
+	return !!(val & TB_LC_PORT_ATTR_BE);
+}
+
+static int tb_lc_dp_sink_from_port(const struct tb_switch *sw,
+				   struct tb_port *in)
+{
+	struct tb_port *port;
+
+	/* The first DP IN port is sink 0 and second is sink 1 */
+	tb_switch_for_each_port(sw, port) {
+		if (tb_port_is_dpin(port))
+			return in != port;
+	}
+
+	return -EINVAL;
+}
+
+static int tb_lc_dp_sink_available(struct tb_switch *sw, int sink)
+{
+	u32 val, alloc;
+	int ret;
+
+	ret = tb_sw_read(sw, &val, TB_CFG_SWITCH,
+			 sw->cap_lc + TB_LC_SNK_ALLOCATION, 1);
+	if (ret)
+		return ret;
+
+	/*
+	 * Sink is available for CM/SW to use if the allocation valie is
+	 * either 0 or 1.
+	 */
+	if (!sink) {
+		alloc = val & TB_LC_SNK_ALLOCATION_SNK0_MASK;
+		if (!alloc || alloc == TB_LC_SNK_ALLOCATION_SNK0_CM)
+			return 0;
+	} else {
+		alloc = (val & TB_LC_SNK_ALLOCATION_SNK1_MASK) >>
+			TB_LC_SNK_ALLOCATION_SNK1_SHIFT;
+		if (!alloc || alloc == TB_LC_SNK_ALLOCATION_SNK1_CM)
+			return 0;
+	}
+
+	return -EBUSY;
+}
+
+/**
+ * tb_lc_dp_sink_query() - Is DP sink available for DP IN port
+ * @sw: Switch whose DP sink is queried
+ * @in: DP IN port to check
+ *
+ * Queries through LC SNK_ALLOCATION registers whether DP sink is available
+ * for the given DP IN port or not.
+ */
+bool tb_lc_dp_sink_query(struct tb_switch *sw, struct tb_port *in)
+{
+	int sink;
+
+	/*
+	 * For older generations sink is always available as there is no
+	 * allocation mechanism.
+	 */
+	if (sw->generation < 3)
+		return true;
+
+	sink = tb_lc_dp_sink_from_port(sw, in);
+	if (sink < 0)
+		return false;
+
+	return !tb_lc_dp_sink_available(sw, sink);
+}
+
+/**
+ * tb_lc_dp_sink_alloc() - Allocate DP sink
+ * @sw: Switch whose DP sink is allocated
+ * @in: DP IN port the DP sink is allocated for
+ *
+ * Allocate DP sink for @in via LC SNK_ALLOCATION registers. If the
+ * resource is available and allocation is successful returns %0. In all
+ * other cases returs negative errno. In particular %-EBUSY is returned if
+ * the resource was not available.
+ */
+int tb_lc_dp_sink_alloc(struct tb_switch *sw, struct tb_port *in)
+{
+	int ret, sink;
+	u32 val;
+
+	if (sw->generation < 3)
+		return 0;
+
+	sink = tb_lc_dp_sink_from_port(sw, in);
+	if (sink < 0)
+		return sink;
+
+	ret = tb_lc_dp_sink_available(sw, sink);
+	if (ret)
+		return ret;
+
+	ret = tb_sw_read(sw, &val, TB_CFG_SWITCH,
+			 sw->cap_lc + TB_LC_SNK_ALLOCATION, 1);
+	if (ret)
+		return ret;
+
+	if (!sink) {
+		val &= ~TB_LC_SNK_ALLOCATION_SNK0_MASK;
+		val |= TB_LC_SNK_ALLOCATION_SNK0_CM;
+	} else {
+		val &= ~TB_LC_SNK_ALLOCATION_SNK1_MASK;
+		val |= TB_LC_SNK_ALLOCATION_SNK1_CM <<
+			TB_LC_SNK_ALLOCATION_SNK1_SHIFT;
+	}
+
+	ret = tb_sw_write(sw, &val, TB_CFG_SWITCH,
+			  sw->cap_lc + TB_LC_SNK_ALLOCATION, 1);
+
+	if (ret)
+		return ret;
+
+	tb_port_dbg(in, "sink %d allocated\n", sink);
+	return 0;
+}
+
+/**
+ * tb_lc_dp_sink_dealloc() - De-allocate DP sink
+ * @sw: Switch whose DP sink is de-allocated
+ * @in: DP IN port whose DP sink is de-allocated
+ *
+ * De-allocate DP sink from @in using LC SNK_ALLOCATION registers.
+ */
+int tb_lc_dp_sink_dealloc(struct tb_switch *sw, struct tb_port *in)
+{
+	int ret, sink;
+	u32 val;
+
+	if (sw->generation < 3)
+		return 0;
+
+	sink = tb_lc_dp_sink_from_port(sw, in);
+	if (sink < 0)
+		return sink;
+
+	/* Needs to be owned by CM/SW */
+	ret = tb_lc_dp_sink_available(sw, sink);
+	if (ret)
+		return ret;
+
+	ret = tb_sw_read(sw, &val, TB_CFG_SWITCH,
+			 sw->cap_lc + TB_LC_SNK_ALLOCATION, 1);
+	if (ret)
+		return ret;
+
+	if (!sink)
+		val &= ~TB_LC_SNK_ALLOCATION_SNK0_MASK;
+	else
+		val &= ~TB_LC_SNK_ALLOCATION_SNK1_MASK;
+
+	ret = tb_sw_write(sw, &val, TB_CFG_SWITCH,
+			  sw->cap_lc + TB_LC_SNK_ALLOCATION, 1);
+	if (ret)
+		return ret;
+
+	tb_port_dbg(in, "sink %d de-allocated\n", sink);
+	return 0;
+}
diff --git a/drivers/thunderbolt/path.c b/drivers/thunderbolt/path.c
index afe5f8391ebf..ad58559ea88e 100644
--- a/drivers/thunderbolt/path.c
+++ b/drivers/thunderbolt/path.c
@@ -220,7 +220,8 @@ err:
  * Creates path between two ports starting with given @src_hopid. Reserves
  * HopIDs for each port (they can be different from @src_hopid depending on
  * how many HopIDs each port already have reserved). If there are dual
- * links on the path, prioritizes using @link_nr.
+ * links on the path, prioritizes using @link_nr but takes into account
+ * that the lanes may be bonded.
  *
  * Return: Returns a tb_path on success or NULL on failure.
  */
@@ -259,7 +260,9 @@ struct tb_path *tb_path_alloc(struct tb *tb, struct tb_port *src, int src_hopid,
 		if (!in_port)
 			goto err;
 
-		if (in_port->dual_link_port && in_port->link_nr != link_nr)
+		/* When lanes are bonded primary link must be used */
+		if (!in_port->bonded && in_port->dual_link_port &&
+		    in_port->link_nr != link_nr)
 			in_port = in_port->dual_link_port;
 
 		ret = tb_port_alloc_in_hopid(in_port, in_hopid, in_hopid);
@@ -271,8 +274,27 @@ struct tb_path *tb_path_alloc(struct tb *tb, struct tb_port *src, int src_hopid,
 		if (!out_port)
 			goto err;
 
-		if (out_port->dual_link_port && out_port->link_nr != link_nr)
-			out_port = out_port->dual_link_port;
+		/*
+		 * Pick up right port when going from non-bonded to
+		 * bonded or from bonded to non-bonded.
+		 */
+		if (out_port->dual_link_port) {
+			if (!in_port->bonded && out_port->bonded &&
+			    out_port->link_nr) {
+				/*
+				 * Use primary link when going from
+				 * non-bonded to bonded.
+				 */
+				out_port = out_port->dual_link_port;
+			} else if (!out_port->bonded &&
+				   out_port->link_nr != link_nr) {
+				/*
+				 * If out port is not bonded follow
+				 * link_nr.
+				 */
+				out_port = out_port->dual_link_port;
+			}
+		}
 
 		if (i == num_hops - 1)
 			ret = tb_port_alloc_out_hopid(out_port, dst_hopid,
@@ -535,3 +557,25 @@ bool tb_path_is_invalid(struct tb_path *path)
 	}
 	return false;
 }
+
+/**
+ * tb_path_switch_on_path() - Does the path go through certain switch
+ * @path: Path to check
+ * @sw: Switch to check
+ *
+ * Goes over all hops on path and checks if @sw is any of them.
+ * Direction does not matter.
+ */
+bool tb_path_switch_on_path(const struct tb_path *path,
+			    const struct tb_switch *sw)
+{
+	int i;
+
+	for (i = 0; i < path->path_length; i++) {
+		if (path->hops[i].in_port->sw == sw ||
+		    path->hops[i].out_port->sw == sw)
+			return true;
+	}
+
+	return false;
+}
diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index 5ea8db667e83..ca86a8e09c77 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -168,7 +168,7 @@ static int nvm_validate_and_write(struct tb_switch *sw)
 
 static int nvm_authenticate_host(struct tb_switch *sw)
 {
-	int ret;
+	int ret = 0;
 
 	/*
 	 * Root switch NVM upgrade requires that we disconnect the
@@ -176,6 +176,8 @@ static int nvm_authenticate_host(struct tb_switch *sw)
 	 * already).
 	 */
 	if (!sw->safe_mode) {
+		u32 status;
+
 		ret = tb_domain_disconnect_all_paths(sw->tb);
 		if (ret)
 			return ret;
@@ -184,7 +186,16 @@ static int nvm_authenticate_host(struct tb_switch *sw)
 		 * everything goes well so getting timeout is expected.
 		 */
 		ret = dma_port_flash_update_auth(sw->dma_port);
-		return ret == -ETIMEDOUT ? 0 : ret;
+		if (!ret || ret == -ETIMEDOUT)
+			return 0;
+
+		/*
+		 * Any error from update auth operation requires power
+		 * cycling of the host router.
+		 */
+		tb_sw_warn(sw, "failed to authenticate NVM, power cycling\n");
+		if (dma_port_flash_update_auth_status(sw->dma_port, &status) > 0)
+			nvm_set_auth_status(sw, status);
 	}
 
 	/*
@@ -192,7 +203,7 @@ static int nvm_authenticate_host(struct tb_switch *sw)
 	 * switch.
 	 */
 	dma_port_power_cycle(sw->dma_port);
-	return 0;
+	return ret;
 }
 
 static int nvm_authenticate_device(struct tb_switch *sw)
@@ -200,8 +211,16 @@ static int nvm_authenticate_device(struct tb_switch *sw)
 	int ret, retries = 10;
 
 	ret = dma_port_flash_update_auth(sw->dma_port);
-	if (ret && ret != -ETIMEDOUT)
+	switch (ret) {
+	case 0:
+	case -ETIMEDOUT:
+	case -EACCES:
+	case -EINVAL:
+		/* Power cycle is required */
+		break;
+	default:
 		return ret;
+	}
 
 	/*
 	 * Poll here for the authentication status. It takes some time
@@ -553,17 +572,17 @@ int tb_port_add_nfc_credits(struct tb_port *port, int credits)
 	if (credits == 0 || port->sw->is_unplugged)
 		return 0;
 
-	nfc_credits = port->config.nfc_credits & TB_PORT_NFC_CREDITS_MASK;
+	nfc_credits = port->config.nfc_credits & ADP_CS_4_NFC_BUFFERS_MASK;
 	nfc_credits += credits;
 
-	tb_port_dbg(port, "adding %d NFC credits to %lu",
-		    credits, port->config.nfc_credits & TB_PORT_NFC_CREDITS_MASK);
+	tb_port_dbg(port, "adding %d NFC credits to %lu", credits,
+		    port->config.nfc_credits & ADP_CS_4_NFC_BUFFERS_MASK);
 
-	port->config.nfc_credits &= ~TB_PORT_NFC_CREDITS_MASK;
+	port->config.nfc_credits &= ~ADP_CS_4_NFC_BUFFERS_MASK;
 	port->config.nfc_credits |= nfc_credits;
 
 	return tb_port_write(port, &port->config.nfc_credits,
-			     TB_CFG_PORT, 4, 1);
+			     TB_CFG_PORT, ADP_CS_4, 1);
 }
 
 /**
@@ -578,14 +597,14 @@ int tb_port_set_initial_credits(struct tb_port *port, u32 credits)
 	u32 data;
 	int ret;
 
-	ret = tb_port_read(port, &data, TB_CFG_PORT, 5, 1);
+	ret = tb_port_read(port, &data, TB_CFG_PORT, ADP_CS_5, 1);
 	if (ret)
 		return ret;
 
-	data &= ~TB_PORT_LCA_MASK;
-	data |= (credits << TB_PORT_LCA_SHIFT) & TB_PORT_LCA_MASK;
+	data &= ~ADP_CS_5_LCA_MASK;
+	data |= (credits << ADP_CS_5_LCA_SHIFT) & ADP_CS_5_LCA_MASK;
 
-	return tb_port_write(port, &data, TB_CFG_PORT, 5, 1);
+	return tb_port_write(port, &data, TB_CFG_PORT, ADP_CS_5, 1);
 }
 
 /**
@@ -645,6 +664,7 @@ static int tb_init_port(struct tb_port *port)
 		ida_init(&port->out_hopids);
 	}
 
+	INIT_LIST_HEAD(&port->list);
 	return 0;
 
 }
@@ -775,6 +795,132 @@ struct tb_port *tb_next_port_on_path(struct tb_port *start, struct tb_port *end,
 	return next;
 }
 
+static int tb_port_get_link_speed(struct tb_port *port)
+{
+	u32 val, speed;
+	int ret;
+
+	if (!port->cap_phy)
+		return -EINVAL;
+
+	ret = tb_port_read(port, &val, TB_CFG_PORT,
+			   port->cap_phy + LANE_ADP_CS_1, 1);
+	if (ret)
+		return ret;
+
+	speed = (val & LANE_ADP_CS_1_CURRENT_SPEED_MASK) >>
+		LANE_ADP_CS_1_CURRENT_SPEED_SHIFT;
+	return speed == LANE_ADP_CS_1_CURRENT_SPEED_GEN3 ? 20 : 10;
+}
+
+static int tb_port_get_link_width(struct tb_port *port)
+{
+	u32 val;
+	int ret;
+
+	if (!port->cap_phy)
+		return -EINVAL;
+
+	ret = tb_port_read(port, &val, TB_CFG_PORT,
+			   port->cap_phy + LANE_ADP_CS_1, 1);
+	if (ret)
+		return ret;
+
+	return (val & LANE_ADP_CS_1_CURRENT_WIDTH_MASK) >>
+		LANE_ADP_CS_1_CURRENT_WIDTH_SHIFT;
+}
+
+static bool tb_port_is_width_supported(struct tb_port *port, int width)
+{
+	u32 phy, widths;
+	int ret;
+
+	if (!port->cap_phy)
+		return false;
+
+	ret = tb_port_read(port, &phy, TB_CFG_PORT,
+			   port->cap_phy + LANE_ADP_CS_0, 1);
+	if (ret)
+		return ret;
+
+	widths = (phy & LANE_ADP_CS_0_SUPPORTED_WIDTH_MASK) >>
+		LANE_ADP_CS_0_SUPPORTED_WIDTH_SHIFT;
+
+	return !!(widths & width);
+}
+
+static int tb_port_set_link_width(struct tb_port *port, unsigned int width)
+{
+	u32 val;
+	int ret;
+
+	if (!port->cap_phy)
+		return -EINVAL;
+
+	ret = tb_port_read(port, &val, TB_CFG_PORT,
+			   port->cap_phy + LANE_ADP_CS_1, 1);
+	if (ret)
+		return ret;
+
+	val &= ~LANE_ADP_CS_1_TARGET_WIDTH_MASK;
+	switch (width) {
+	case 1:
+		val |= LANE_ADP_CS_1_TARGET_WIDTH_SINGLE <<
+			LANE_ADP_CS_1_TARGET_WIDTH_SHIFT;
+		break;
+	case 2:
+		val |= LANE_ADP_CS_1_TARGET_WIDTH_DUAL <<
+			LANE_ADP_CS_1_TARGET_WIDTH_SHIFT;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	val |= LANE_ADP_CS_1_LB;
+
+	return tb_port_write(port, &val, TB_CFG_PORT,
+			     port->cap_phy + LANE_ADP_CS_1, 1);
+}
+
+static int tb_port_lane_bonding_enable(struct tb_port *port)
+{
+	int ret;
+
+	/*
+	 * Enable lane bonding for both links if not already enabled by
+	 * for example the boot firmware.
+	 */
+	ret = tb_port_get_link_width(port);
+	if (ret == 1) {
+		ret = tb_port_set_link_width(port, 2);
+		if (ret)
+			return ret;
+	}
+
+	ret = tb_port_get_link_width(port->dual_link_port);
+	if (ret == 1) {
+		ret = tb_port_set_link_width(port->dual_link_port, 2);
+		if (ret) {
+			tb_port_set_link_width(port, 1);
+			return ret;
+		}
+	}
+
+	port->bonded = true;
+	port->dual_link_port->bonded = true;
+
+	return 0;
+}
+
+static void tb_port_lane_bonding_disable(struct tb_port *port)
+{
+	port->dual_link_port->bonded = false;
+	port->bonded = false;
+
+	tb_port_set_link_width(port->dual_link_port, 1);
+	tb_port_set_link_width(port, 1);
+}
+
 /**
  * tb_port_is_enabled() - Is the adapter port enabled
  * @port: Port to check
@@ -803,10 +949,11 @@ bool tb_pci_port_is_enabled(struct tb_port *port)
 {
 	u32 data;
 
-	if (tb_port_read(port, &data, TB_CFG_PORT, port->cap_adap, 1))
+	if (tb_port_read(port, &data, TB_CFG_PORT,
+			 port->cap_adap + ADP_PCIE_CS_0, 1))
 		return false;
 
-	return !!(data & TB_PCI_EN);
+	return !!(data & ADP_PCIE_CS_0_PE);
 }
 
 /**
@@ -816,10 +963,11 @@ bool tb_pci_port_is_enabled(struct tb_port *port)
  */
 int tb_pci_port_enable(struct tb_port *port, bool enable)
 {
-	u32 word = enable ? TB_PCI_EN : 0x0;
+	u32 word = enable ? ADP_PCIE_CS_0_PE : 0x0;
 	if (!port->cap_adap)
 		return -ENXIO;
-	return tb_port_write(port, &word, TB_CFG_PORT, port->cap_adap, 1);
+	return tb_port_write(port, &word, TB_CFG_PORT,
+			     port->cap_adap + ADP_PCIE_CS_0, 1);
 }
 
 /**
@@ -833,11 +981,12 @@ int tb_dp_port_hpd_is_active(struct tb_port *port)
 	u32 data;
 	int ret;
 
-	ret = tb_port_read(port, &data, TB_CFG_PORT, port->cap_adap + 2, 1);
+	ret = tb_port_read(port, &data, TB_CFG_PORT,
+			   port->cap_adap + ADP_DP_CS_2, 1);
 	if (ret)
 		return ret;
 
-	return !!(data & TB_DP_HDP);
+	return !!(data & ADP_DP_CS_2_HDP);
 }
 
 /**
@@ -851,12 +1000,14 @@ int tb_dp_port_hpd_clear(struct tb_port *port)
 	u32 data;
 	int ret;
 
-	ret = tb_port_read(port, &data, TB_CFG_PORT, port->cap_adap + 3, 1);
+	ret = tb_port_read(port, &data, TB_CFG_PORT,
+			   port->cap_adap + ADP_DP_CS_3, 1);
 	if (ret)
 		return ret;
 
-	data |= TB_DP_HPDC;
-	return tb_port_write(port, &data, TB_CFG_PORT, port->cap_adap + 3, 1);
+	data |= ADP_DP_CS_3_HDPC;
+	return tb_port_write(port, &data, TB_CFG_PORT,
+			     port->cap_adap + ADP_DP_CS_3, 1);
 }
 
 /**
@@ -874,20 +1025,23 @@ int tb_dp_port_set_hops(struct tb_port *port, unsigned int video,
 	u32 data[2];
 	int ret;
 
-	ret = tb_port_read(port, data, TB_CFG_PORT, port->cap_adap,
-			   ARRAY_SIZE(data));
+	ret = tb_port_read(port, data, TB_CFG_PORT,
+			   port->cap_adap + ADP_DP_CS_0, ARRAY_SIZE(data));
 	if (ret)
 		return ret;
 
-	data[0] &= ~TB_DP_VIDEO_HOPID_MASK;
-	data[1] &= ~(TB_DP_AUX_RX_HOPID_MASK | TB_DP_AUX_TX_HOPID_MASK);
+	data[0] &= ~ADP_DP_CS_0_VIDEO_HOPID_MASK;
+	data[1] &= ~ADP_DP_CS_1_AUX_RX_HOPID_MASK;
+	data[1] &= ~ADP_DP_CS_1_AUX_RX_HOPID_MASK;
 
-	data[0] |= (video << TB_DP_VIDEO_HOPID_SHIFT) & TB_DP_VIDEO_HOPID_MASK;
-	data[1] |= aux_tx & TB_DP_AUX_TX_HOPID_MASK;
-	data[1] |= (aux_rx << TB_DP_AUX_RX_HOPID_SHIFT) & TB_DP_AUX_RX_HOPID_MASK;
+	data[0] |= (video << ADP_DP_CS_0_VIDEO_HOPID_SHIFT) &
+		ADP_DP_CS_0_VIDEO_HOPID_MASK;
+	data[1] |= aux_tx & ADP_DP_CS_1_AUX_TX_HOPID_MASK;
+	data[1] |= (aux_rx << ADP_DP_CS_1_AUX_RX_HOPID_SHIFT) &
+		ADP_DP_CS_1_AUX_RX_HOPID_MASK;
 
-	return tb_port_write(port, data, TB_CFG_PORT, port->cap_adap,
-			     ARRAY_SIZE(data));
+	return tb_port_write(port, data, TB_CFG_PORT,
+			     port->cap_adap + ADP_DP_CS_0, ARRAY_SIZE(data));
 }
 
 /**
@@ -898,11 +1052,11 @@ bool tb_dp_port_is_enabled(struct tb_port *port)
 {
 	u32 data[2];
 
-	if (tb_port_read(port, data, TB_CFG_PORT, port->cap_adap,
+	if (tb_port_read(port, data, TB_CFG_PORT, port->cap_adap + ADP_DP_CS_0,
 			 ARRAY_SIZE(data)))
 		return false;
 
-	return !!(data[0] & (TB_DP_VIDEO_EN | TB_DP_AUX_EN));
+	return !!(data[0] & (ADP_DP_CS_0_VE | ADP_DP_CS_0_AE));
 }
 
 /**
@@ -918,18 +1072,18 @@ int tb_dp_port_enable(struct tb_port *port, bool enable)
 	u32 data[2];
 	int ret;
 
-	ret = tb_port_read(port, data, TB_CFG_PORT, port->cap_adap,
-			   ARRAY_SIZE(data));
+	ret = tb_port_read(port, data, TB_CFG_PORT,
+			  port->cap_adap + ADP_DP_CS_0, ARRAY_SIZE(data));
 	if (ret)
 		return ret;
 
 	if (enable)
-		data[0] |= TB_DP_VIDEO_EN | TB_DP_AUX_EN;
+		data[0] |= ADP_DP_CS_0_VE | ADP_DP_CS_0_AE;
 	else
-		data[0] &= ~(TB_DP_VIDEO_EN | TB_DP_AUX_EN);
+		data[0] &= ~(ADP_DP_CS_0_VE | ADP_DP_CS_0_AE);
 
-	return tb_port_write(port, data, TB_CFG_PORT, port->cap_adap,
-			     ARRAY_SIZE(data));
+	return tb_port_write(port, data, TB_CFG_PORT,
+			     port->cap_adap + ADP_DP_CS_0, ARRAY_SIZE(data));
 }
 
 /* switch utility functions */
@@ -986,7 +1140,7 @@ static int tb_plug_events_active(struct tb_switch *sw, bool active)
 	u32 data;
 	int res;
 
-	if (!sw->config.enabled)
+	if (tb_switch_is_icm(sw))
 		return 0;
 
 	sw->config.plug_events_delay = 0xff;
@@ -1114,6 +1268,15 @@ device_name_show(struct device *dev, struct device_attribute *attr, char *buf)
 }
 static DEVICE_ATTR_RO(device_name);
 
+static ssize_t
+generation_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct tb_switch *sw = tb_to_switch(dev);
+
+	return sprintf(buf, "%u\n", sw->generation);
+}
+static DEVICE_ATTR_RO(generation);
+
 static ssize_t key_show(struct device *dev, struct device_attribute *attr,
 			char *buf)
 {
@@ -1166,6 +1329,36 @@ static ssize_t key_store(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR(key, 0600, key_show, key_store);
 
+static ssize_t speed_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	struct tb_switch *sw = tb_to_switch(dev);
+
+	return sprintf(buf, "%u.0 Gb/s\n", sw->link_speed);
+}
+
+/*
+ * Currently all lanes must run at the same speed but we expose here
+ * both directions to allow possible asymmetric links in the future.
+ */
+static DEVICE_ATTR(rx_speed, 0444, speed_show, NULL);
+static DEVICE_ATTR(tx_speed, 0444, speed_show, NULL);
+
+static ssize_t lanes_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	struct tb_switch *sw = tb_to_switch(dev);
+
+	return sprintf(buf, "%u\n", sw->link_width);
+}
+
+/*
+ * Currently link has same amount of lanes both directions (1 or 2) but
+ * expose them separately to allow possible asymmetric links in the future.
+ */
+static DEVICE_ATTR(rx_lanes, 0444, lanes_show, NULL);
+static DEVICE_ATTR(tx_lanes, 0444, lanes_show, NULL);
+
 static void nvm_authenticate_start(struct tb_switch *sw)
 {
 	struct pci_dev *root_port;
@@ -1246,8 +1439,6 @@ static ssize_t nvm_authenticate_store(struct device *dev,
 			 */
 			nvm_authenticate_start(sw);
 			ret = nvm_authenticate_host(sw);
-			if (ret)
-				nvm_authenticate_complete(sw);
 		} else {
 			ret = nvm_authenticate_device(sw);
 		}
@@ -1319,9 +1510,14 @@ static struct attribute *switch_attrs[] = {
 	&dev_attr_boot.attr,
 	&dev_attr_device.attr,
 	&dev_attr_device_name.attr,
+	&dev_attr_generation.attr,
 	&dev_attr_key.attr,
 	&dev_attr_nvm_authenticate.attr,
 	&dev_attr_nvm_version.attr,
+	&dev_attr_rx_speed.attr,
+	&dev_attr_rx_lanes.attr,
+	&dev_attr_tx_speed.attr,
+	&dev_attr_tx_lanes.attr,
 	&dev_attr_vendor.attr,
 	&dev_attr_vendor_name.attr,
 	&dev_attr_unique_id.attr,
@@ -1352,6 +1548,13 @@ static umode_t switch_attr_is_visible(struct kobject *kobj,
 		    sw->security_level == TB_SECURITY_SECURE)
 			return attr->mode;
 		return 0;
+	} else if (attr == &dev_attr_rx_speed.attr ||
+		   attr == &dev_attr_rx_lanes.attr ||
+		   attr == &dev_attr_tx_speed.attr ||
+		   attr == &dev_attr_tx_lanes.attr) {
+		if (tb_route(sw))
+			return attr->mode;
+		return 0;
 	} else if (attr == &dev_attr_nvm_authenticate.attr) {
 		if (sw->dma_port && !sw->no_nvm_upgrade)
 			return attr->mode;
@@ -1382,14 +1585,14 @@ static const struct attribute_group *switch_groups[] = {
 static void tb_switch_release(struct device *dev)
 {
 	struct tb_switch *sw = tb_to_switch(dev);
-	int i;
+	struct tb_port *port;
 
 	dma_port_free(sw->dma_port);
 
-	for (i = 1; i <= sw->config.max_port_number; i++) {
-		if (!sw->ports[i].disabled) {
-			ida_destroy(&sw->ports[i].in_hopids);
-			ida_destroy(&sw->ports[i].out_hopids);
+	tb_switch_for_each_port(sw, port) {
+		if (!port->disabled) {
+			ida_destroy(&port->in_hopids);
+			ida_destroy(&port->out_hopids);
 		}
 	}
 
@@ -1690,13 +1893,16 @@ static int tb_switch_add_dma_port(struct tb_switch *sw)
 	int ret;
 
 	switch (sw->generation) {
-	case 3:
-		break;
-
 	case 2:
 		/* Only root switch can be upgraded */
 		if (tb_route(sw))
 			return 0;
+
+		/* fallthrough */
+	case 3:
+		ret = tb_switch_set_uuid(sw);
+		if (ret)
+			return ret;
 		break;
 
 	default:
@@ -1710,7 +1916,7 @@ static int tb_switch_add_dma_port(struct tb_switch *sw)
 	}
 
 	/* Root switch DMA port requires running firmware */
-	if (!tb_route(sw) && sw->config.enabled)
+	if (!tb_route(sw) && !tb_switch_is_icm(sw))
 		return 0;
 
 	sw->dma_port = dma_port_alloc(sw);
@@ -1721,6 +1927,19 @@ static int tb_switch_add_dma_port(struct tb_switch *sw)
 		return 0;
 
 	/*
+	 * If there is status already set then authentication failed
+	 * when the dma_port_flash_update_auth() returned. Power cycling
+	 * is not needed (it was done already) so only thing we do here
+	 * is to unblock runtime PM of the root port.
+	 */
+	nvm_get_auth_status(sw, &status);
+	if (status) {
+		if (!tb_route(sw))
+			nvm_authenticate_complete(sw);
+		return 0;
+	}
+
+	/*
 	 * Check status of the previous flash authentication. If there
 	 * is one we need to power cycle the switch in any case to make
 	 * it functional again.
@@ -1735,9 +1954,6 @@ static int tb_switch_add_dma_port(struct tb_switch *sw)
 
 	if (status) {
 		tb_sw_info(sw, "switch flash authentication failed\n");
-		ret = tb_switch_set_uuid(sw);
-		if (ret)
-			return ret;
 		nvm_set_auth_status(sw, status);
 	}
 
@@ -1751,6 +1967,153 @@ static int tb_switch_add_dma_port(struct tb_switch *sw)
 	return -ESHUTDOWN;
 }
 
+static void tb_switch_default_link_ports(struct tb_switch *sw)
+{
+	int i;
+
+	for (i = 1; i <= sw->config.max_port_number; i += 2) {
+		struct tb_port *port = &sw->ports[i];
+		struct tb_port *subordinate;
+
+		if (!tb_port_is_null(port))
+			continue;
+
+		/* Check for the subordinate port */
+		if (i == sw->config.max_port_number ||
+		    !tb_port_is_null(&sw->ports[i + 1]))
+			continue;
+
+		/* Link them if not already done so (by DROM) */
+		subordinate = &sw->ports[i + 1];
+		if (!port->dual_link_port && !subordinate->dual_link_port) {
+			port->link_nr = 0;
+			port->dual_link_port = subordinate;
+			subordinate->link_nr = 1;
+			subordinate->dual_link_port = port;
+
+			tb_sw_dbg(sw, "linked ports %d <-> %d\n",
+				  port->port, subordinate->port);
+		}
+	}
+}
+
+static bool tb_switch_lane_bonding_possible(struct tb_switch *sw)
+{
+	const struct tb_port *up = tb_upstream_port(sw);
+
+	if (!up->dual_link_port || !up->dual_link_port->remote)
+		return false;
+
+	return tb_lc_lane_bonding_possible(sw);
+}
+
+static int tb_switch_update_link_attributes(struct tb_switch *sw)
+{
+	struct tb_port *up;
+	bool change = false;
+	int ret;
+
+	if (!tb_route(sw) || tb_switch_is_icm(sw))
+		return 0;
+
+	up = tb_upstream_port(sw);
+
+	ret = tb_port_get_link_speed(up);
+	if (ret < 0)
+		return ret;
+	if (sw->link_speed != ret)
+		change = true;
+	sw->link_speed = ret;
+
+	ret = tb_port_get_link_width(up);
+	if (ret < 0)
+		return ret;
+	if (sw->link_width != ret)
+		change = true;
+	sw->link_width = ret;
+
+	/* Notify userspace that there is possible link attribute change */
+	if (device_is_registered(&sw->dev) && change)
+		kobject_uevent(&sw->dev.kobj, KOBJ_CHANGE);
+
+	return 0;
+}
+
+/**
+ * tb_switch_lane_bonding_enable() - Enable lane bonding
+ * @sw: Switch to enable lane bonding
+ *
+ * Connection manager can call this function to enable lane bonding of a
+ * switch. If conditions are correct and both switches support the feature,
+ * lanes are bonded. It is safe to call this to any switch.
+ */
+int tb_switch_lane_bonding_enable(struct tb_switch *sw)
+{
+	struct tb_switch *parent = tb_to_switch(sw->dev.parent);
+	struct tb_port *up, *down;
+	u64 route = tb_route(sw);
+	int ret;
+
+	if (!route)
+		return 0;
+
+	if (!tb_switch_lane_bonding_possible(sw))
+		return 0;
+
+	up = tb_upstream_port(sw);
+	down = tb_port_at(route, parent);
+
+	if (!tb_port_is_width_supported(up, 2) ||
+	    !tb_port_is_width_supported(down, 2))
+		return 0;
+
+	ret = tb_port_lane_bonding_enable(up);
+	if (ret) {
+		tb_port_warn(up, "failed to enable lane bonding\n");
+		return ret;
+	}
+
+	ret = tb_port_lane_bonding_enable(down);
+	if (ret) {
+		tb_port_warn(down, "failed to enable lane bonding\n");
+		tb_port_lane_bonding_disable(up);
+		return ret;
+	}
+
+	tb_switch_update_link_attributes(sw);
+
+	tb_sw_dbg(sw, "lane bonding enabled\n");
+	return ret;
+}
+
+/**
+ * tb_switch_lane_bonding_disable() - Disable lane bonding
+ * @sw: Switch whose lane bonding to disable
+ *
+ * Disables lane bonding between @sw and parent. This can be called even
+ * if lanes were not bonded originally.
+ */
+void tb_switch_lane_bonding_disable(struct tb_switch *sw)
+{
+	struct tb_switch *parent = tb_to_switch(sw->dev.parent);
+	struct tb_port *up, *down;
+
+	if (!tb_route(sw))
+		return;
+
+	up = tb_upstream_port(sw);
+	if (!up->bonded)
+		return;
+
+	down = tb_port_at(tb_route(sw), parent);
+
+	tb_port_lane_bonding_disable(up);
+	tb_port_lane_bonding_disable(down);
+
+	tb_switch_update_link_attributes(sw);
+	tb_sw_dbg(sw, "lane bonding disabled\n");
+}
+
 /**
  * tb_switch_add() - Add a switch to the domain
  * @sw: Switch to add
@@ -1775,21 +2138,25 @@ int tb_switch_add(struct tb_switch *sw)
 	 * configuration based mailbox.
 	 */
 	ret = tb_switch_add_dma_port(sw);
-	if (ret)
+	if (ret) {
+		dev_err(&sw->dev, "failed to add DMA port\n");
 		return ret;
+	}
 
 	if (!sw->safe_mode) {
 		/* read drom */
 		ret = tb_drom_read(sw);
 		if (ret) {
-			tb_sw_warn(sw, "tb_eeprom_read_rom failed\n");
+			dev_err(&sw->dev, "reading DROM failed\n");
 			return ret;
 		}
 		tb_sw_dbg(sw, "uid: %#llx\n", sw->uid);
 
 		ret = tb_switch_set_uuid(sw);
-		if (ret)
+		if (ret) {
+			dev_err(&sw->dev, "failed to set UUID\n");
 			return ret;
+		}
 
 		for (i = 0; i <= sw->config.max_port_number; i++) {
 			if (sw->ports[i].disabled) {
@@ -1797,14 +2164,24 @@ int tb_switch_add(struct tb_switch *sw)
 				continue;
 			}
 			ret = tb_init_port(&sw->ports[i]);
-			if (ret)
+			if (ret) {
+				dev_err(&sw->dev, "failed to initialize port %d\n", i);
 				return ret;
+			}
 		}
+
+		tb_switch_default_link_ports(sw);
+
+		ret = tb_switch_update_link_attributes(sw);
+		if (ret)
+			return ret;
 	}
 
 	ret = device_add(&sw->dev);
-	if (ret)
+	if (ret) {
+		dev_err(&sw->dev, "failed to add device: %d\n", ret);
 		return ret;
+	}
 
 	if (tb_route(sw)) {
 		dev_info(&sw->dev, "new device found, vendor=%#x device=%#x\n",
@@ -1816,6 +2193,7 @@ int tb_switch_add(struct tb_switch *sw)
 
 	ret = tb_switch_nvm_add(sw);
 	if (ret) {
+		dev_err(&sw->dev, "failed to add NVM devices\n");
 		device_del(&sw->dev);
 		return ret;
 	}
@@ -1842,7 +2220,7 @@ int tb_switch_add(struct tb_switch *sw)
  */
 void tb_switch_remove(struct tb_switch *sw)
 {
-	int i;
+	struct tb_port *port;
 
 	if (sw->rpm) {
 		pm_runtime_get_sync(&sw->dev);
@@ -1850,13 +2228,13 @@ void tb_switch_remove(struct tb_switch *sw)
 	}
 
 	/* port 0 is the switch itself and never has a remote */
-	for (i = 1; i <= sw->config.max_port_number; i++) {
-		if (tb_port_has_remote(&sw->ports[i])) {
-			tb_switch_remove(sw->ports[i].remote->sw);
-			sw->ports[i].remote = NULL;
-		} else if (sw->ports[i].xdomain) {
-			tb_xdomain_remove(sw->ports[i].xdomain);
-			sw->ports[i].xdomain = NULL;
+	tb_switch_for_each_port(sw, port) {
+		if (tb_port_has_remote(port)) {
+			tb_switch_remove(port->remote->sw);
+			port->remote = NULL;
+		} else if (port->xdomain) {
+			tb_xdomain_remove(port->xdomain);
+			port->xdomain = NULL;
 		}
 	}
 
@@ -1876,7 +2254,8 @@ void tb_switch_remove(struct tb_switch *sw)
  */
 void tb_sw_set_unplugged(struct tb_switch *sw)
 {
-	int i;
+	struct tb_port *port;
+
 	if (sw == sw->tb->root_switch) {
 		tb_sw_WARN(sw, "cannot unplug root switch\n");
 		return;
@@ -1886,17 +2265,19 @@ void tb_sw_set_unplugged(struct tb_switch *sw)
 		return;
 	}
 	sw->is_unplugged = true;
-	for (i = 0; i <= sw->config.max_port_number; i++) {
-		if (tb_port_has_remote(&sw->ports[i]))
-			tb_sw_set_unplugged(sw->ports[i].remote->sw);
-		else if (sw->ports[i].xdomain)
-			sw->ports[i].xdomain->is_unplugged = true;
+	tb_switch_for_each_port(sw, port) {
+		if (tb_port_has_remote(port))
+			tb_sw_set_unplugged(port->remote->sw);
+		else if (port->xdomain)
+			port->xdomain->is_unplugged = true;
 	}
 }
 
 int tb_switch_resume(struct tb_switch *sw)
 {
-	int i, err;
+	struct tb_port *port;
+	int err;
+
 	tb_sw_dbg(sw, "resuming switch\n");
 
 	/*
@@ -1944,9 +2325,7 @@ int tb_switch_resume(struct tb_switch *sw)
 		return err;
 
 	/* check for surviving downstream switches */
-	for (i = 1; i <= sw->config.max_port_number; i++) {
-		struct tb_port *port = &sw->ports[i];
-
+	tb_switch_for_each_port(sw, port) {
 		if (!tb_port_has_remote(port) && !port->xdomain)
 			continue;
 
@@ -1970,19 +2349,64 @@ int tb_switch_resume(struct tb_switch *sw)
 
 void tb_switch_suspend(struct tb_switch *sw)
 {
-	int i, err;
+	struct tb_port *port;
+	int err;
+
 	err = tb_plug_events_active(sw, false);
 	if (err)
 		return;
 
-	for (i = 1; i <= sw->config.max_port_number; i++) {
-		if (tb_port_has_remote(&sw->ports[i]))
-			tb_switch_suspend(sw->ports[i].remote->sw);
+	tb_switch_for_each_port(sw, port) {
+		if (tb_port_has_remote(port))
+			tb_switch_suspend(port->remote->sw);
 	}
 
 	tb_lc_set_sleep(sw);
 }
 
+/**
+ * tb_switch_query_dp_resource() - Query availability of DP resource
+ * @sw: Switch whose DP resource is queried
+ * @in: DP IN port
+ *
+ * Queries availability of DP resource for DP tunneling using switch
+ * specific means. Returns %true if resource is available.
+ */
+bool tb_switch_query_dp_resource(struct tb_switch *sw, struct tb_port *in)
+{
+	return tb_lc_dp_sink_query(sw, in);
+}
+
+/**
+ * tb_switch_alloc_dp_resource() - Allocate available DP resource
+ * @sw: Switch whose DP resource is allocated
+ * @in: DP IN port
+ *
+ * Allocates DP resource for DP tunneling. The resource must be
+ * available for this to succeed (see tb_switch_query_dp_resource()).
+ * Returns %0 in success and negative errno otherwise.
+ */
+int tb_switch_alloc_dp_resource(struct tb_switch *sw, struct tb_port *in)
+{
+	return tb_lc_dp_sink_alloc(sw, in);
+}
+
+/**
+ * tb_switch_dealloc_dp_resource() - De-allocate DP resource
+ * @sw: Switch whose DP resource is de-allocated
+ * @in: DP IN port
+ *
+ * De-allocates DP resource that was previously allocated for DP
+ * tunneling.
+ */
+void tb_switch_dealloc_dp_resource(struct tb_switch *sw, struct tb_port *in)
+{
+	if (tb_lc_dp_sink_dealloc(sw, in)) {
+		tb_sw_warn(sw, "failed to de-allocate DP resource for port %d\n",
+			   in->port);
+	}
+}
+
 struct tb_sw_lookup {
 	struct tb *tb;
 	u8 link;
diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c
index 1f7a9e1cc09c..ea8727f769d6 100644
--- a/drivers/thunderbolt/tb.c
+++ b/drivers/thunderbolt/tb.c
@@ -9,7 +9,6 @@
 #include <linux/slab.h>
 #include <linux/errno.h>
 #include <linux/delay.h>
-#include <linux/platform_data/x86/apple.h>
 
 #include "tb.h"
 #include "tb_regs.h"
@@ -18,6 +17,7 @@
 /**
  * struct tb_cm - Simple Thunderbolt connection manager
  * @tunnel_list: List of active tunnels
+ * @dp_resources: List of available DP resources for DP tunneling
  * @hotplug_active: tb_handle_hotplug will stop progressing plug
  *		    events and exit if this is not set (it needs to
  *		    acquire the lock one more time). Used to drain wq
@@ -25,6 +25,7 @@
  */
 struct tb_cm {
 	struct list_head tunnel_list;
+	struct list_head dp_resources;
 	bool hotplug_active;
 };
 
@@ -56,17 +57,51 @@ static void tb_queue_hotplug(struct tb *tb, u64 route, u8 port, bool unplug)
 
 /* enumeration & hot plug handling */
 
+static void tb_add_dp_resources(struct tb_switch *sw)
+{
+	struct tb_cm *tcm = tb_priv(sw->tb);
+	struct tb_port *port;
+
+	tb_switch_for_each_port(sw, port) {
+		if (!tb_port_is_dpin(port))
+			continue;
+
+		if (!tb_switch_query_dp_resource(sw, port))
+			continue;
+
+		list_add_tail(&port->list, &tcm->dp_resources);
+		tb_port_dbg(port, "DP IN resource available\n");
+	}
+}
+
+static void tb_remove_dp_resources(struct tb_switch *sw)
+{
+	struct tb_cm *tcm = tb_priv(sw->tb);
+	struct tb_port *port, *tmp;
+
+	/* Clear children resources first */
+	tb_switch_for_each_port(sw, port) {
+		if (tb_port_has_remote(port))
+			tb_remove_dp_resources(port->remote->sw);
+	}
+
+	list_for_each_entry_safe(port, tmp, &tcm->dp_resources, list) {
+		if (port->sw == sw) {
+			tb_port_dbg(port, "DP OUT resource unavailable\n");
+			list_del_init(&port->list);
+		}
+	}
+}
+
 static void tb_discover_tunnels(struct tb_switch *sw)
 {
 	struct tb *tb = sw->tb;
 	struct tb_cm *tcm = tb_priv(tb);
 	struct tb_port *port;
-	int i;
 
-	for (i = 1; i <= sw->config.max_port_number; i++) {
+	tb_switch_for_each_port(sw, port) {
 		struct tb_tunnel *tunnel = NULL;
 
-		port = &sw->ports[i];
 		switch (port->config.type) {
 		case TB_TYPE_DP_HDMI_IN:
 			tunnel = tb_tunnel_discover_dp(tb, port);
@@ -95,9 +130,9 @@ static void tb_discover_tunnels(struct tb_switch *sw)
 		list_add_tail(&tunnel->list, &tcm->tunnel_list);
 	}
 
-	for (i = 1; i <= sw->config.max_port_number; i++) {
-		if (tb_port_has_remote(&sw->ports[i]))
-			tb_discover_tunnels(sw->ports[i].remote->sw);
+	tb_switch_for_each_port(sw, port) {
+		if (tb_port_has_remote(port))
+			tb_discover_tunnels(port->remote->sw);
 	}
 }
 
@@ -130,9 +165,10 @@ static void tb_scan_port(struct tb_port *port);
  */
 static void tb_scan_switch(struct tb_switch *sw)
 {
-	int i;
-	for (i = 1; i <= sw->config.max_port_number; i++)
-		tb_scan_port(&sw->ports[i]);
+	struct tb_port *port;
+
+	tb_switch_for_each_port(sw, port)
+		tb_scan_port(port);
 }
 
 /**
@@ -217,11 +253,16 @@ static void tb_scan_port(struct tb_port *port)
 		upstream_port->dual_link_port->remote = port->dual_link_port;
 	}
 
+	/* Enable lane bonding if supported */
+	if (tb_switch_lane_bonding_enable(sw))
+		tb_sw_warn(sw, "failed to enable lane bonding\n");
+
 	tb_scan_switch(sw);
 }
 
-static int tb_free_tunnel(struct tb *tb, enum tb_tunnel_type type,
-			  struct tb_port *src_port, struct tb_port *dst_port)
+static struct tb_tunnel *tb_find_tunnel(struct tb *tb, enum tb_tunnel_type type,
+					struct tb_port *src_port,
+					struct tb_port *dst_port)
 {
 	struct tb_cm *tcm = tb_priv(tb);
 	struct tb_tunnel *tunnel;
@@ -230,14 +271,32 @@ static int tb_free_tunnel(struct tb *tb, enum tb_tunnel_type type,
 		if (tunnel->type == type &&
 		    ((src_port && src_port == tunnel->src_port) ||
 		     (dst_port && dst_port == tunnel->dst_port))) {
-			tb_tunnel_deactivate(tunnel);
-			list_del(&tunnel->list);
-			tb_tunnel_free(tunnel);
-			return 0;
+			return tunnel;
 		}
 	}
 
-	return -ENODEV;
+	return NULL;
+}
+
+static void tb_deactivate_and_free_tunnel(struct tb_tunnel *tunnel)
+{
+	if (!tunnel)
+		return;
+
+	tb_tunnel_deactivate(tunnel);
+	list_del(&tunnel->list);
+
+	/*
+	 * In case of DP tunnel make sure the DP IN resource is deallocated
+	 * properly.
+	 */
+	if (tb_tunnel_is_dp(tunnel)) {
+		struct tb_port *in = tunnel->src_port;
+
+		tb_switch_dealloc_dp_resource(in->sw, in);
+	}
+
+	tb_tunnel_free(tunnel);
 }
 
 /**
@@ -250,11 +309,8 @@ static void tb_free_invalid_tunnels(struct tb *tb)
 	struct tb_tunnel *n;
 
 	list_for_each_entry_safe(tunnel, n, &tcm->tunnel_list, list) {
-		if (tb_tunnel_is_invalid(tunnel)) {
-			tb_tunnel_deactivate(tunnel);
-			list_del(&tunnel->list);
-			tb_tunnel_free(tunnel);
-		}
+		if (tb_tunnel_is_invalid(tunnel))
+			tb_deactivate_and_free_tunnel(tunnel);
 	}
 }
 
@@ -263,14 +319,15 @@ static void tb_free_invalid_tunnels(struct tb *tb)
  */
 static void tb_free_unplugged_children(struct tb_switch *sw)
 {
-	int i;
-	for (i = 1; i <= sw->config.max_port_number; i++) {
-		struct tb_port *port = &sw->ports[i];
+	struct tb_port *port;
 
+	tb_switch_for_each_port(sw, port) {
 		if (!tb_port_has_remote(port))
 			continue;
 
 		if (port->remote->sw->is_unplugged) {
+			tb_remove_dp_resources(port->remote->sw);
+			tb_switch_lane_bonding_disable(port->remote->sw);
 			tb_switch_remove(port->remote->sw);
 			port->remote = NULL;
 			if (port->dual_link_port)
@@ -289,10 +346,13 @@ static void tb_free_unplugged_children(struct tb_switch *sw)
 static struct tb_port *tb_find_port(struct tb_switch *sw,
 				    enum tb_port_type type)
 {
-	int i;
-	for (i = 1; i <= sw->config.max_port_number; i++)
-		if (sw->ports[i].config.type == type)
-			return &sw->ports[i];
+	struct tb_port *port;
+
+	tb_switch_for_each_port(sw, port) {
+		if (port->config.type == type)
+			return port;
+	}
+
 	return NULL;
 }
 
@@ -304,18 +364,18 @@ static struct tb_port *tb_find_port(struct tb_switch *sw,
 static struct tb_port *tb_find_unused_port(struct tb_switch *sw,
 					   enum tb_port_type type)
 {
-	int i;
+	struct tb_port *port;
 
-	for (i = 1; i <= sw->config.max_port_number; i++) {
-		if (tb_is_upstream_port(&sw->ports[i]))
+	tb_switch_for_each_port(sw, port) {
+		if (tb_is_upstream_port(port))
 			continue;
-		if (sw->ports[i].config.type != type)
+		if (port->config.type != type)
 			continue;
-		if (!sw->ports[i].cap_adap)
+		if (port->cap_adap)
 			continue;
-		if (tb_port_is_enabled(&sw->ports[i]))
+		if (tb_port_is_enabled(port))
 			continue;
-		return &sw->ports[i];
+		return port;
 	}
 	return NULL;
 }
@@ -336,10 +396,13 @@ static struct tb_port *tb_find_pcie_down(struct tb_switch *sw,
 		 * Hard-coded Thunderbolt port to PCIe down port mapping
 		 * per controller.
 		 */
-		if (tb_switch_is_cr(sw))
+		if (tb_switch_is_cactus_ridge(sw) ||
+		    tb_switch_is_alpine_ridge(sw))
 			index = !phy_port ? 6 : 7;
-		else if (tb_switch_is_fr(sw))
+		else if (tb_switch_is_falcon_ridge(sw))
 			index = !phy_port ? 6 : 8;
+		else if (tb_switch_is_titan_ridge(sw))
+			index = !phy_port ? 8 : 9;
 		else
 			goto out;
 
@@ -358,42 +421,162 @@ out:
 	return tb_find_unused_port(sw, TB_TYPE_PCIE_DOWN);
 }
 
-static int tb_tunnel_dp(struct tb *tb, struct tb_port *out)
+static int tb_available_bw(struct tb_cm *tcm, struct tb_port *in,
+			   struct tb_port *out)
 {
-	struct tb_cm *tcm = tb_priv(tb);
 	struct tb_switch *sw = out->sw;
 	struct tb_tunnel *tunnel;
-	struct tb_port *in;
+	int bw, available_bw = 40000;
 
-	if (tb_port_is_enabled(out))
-		return 0;
+	while (sw && sw != in->sw) {
+		bw = sw->link_speed * sw->link_width * 1000; /* Mb/s */
+		/* Leave 10% guard band */
+		bw -= bw / 10;
+
+		/*
+		 * Check for any active DP tunnels that go through this
+		 * switch and reduce their consumed bandwidth from
+		 * available.
+		 */
+		list_for_each_entry(tunnel, &tcm->tunnel_list, list) {
+			int consumed_bw;
+
+			if (!tb_tunnel_switch_on_path(tunnel, sw))
+				continue;
+
+			consumed_bw = tb_tunnel_consumed_bandwidth(tunnel);
+			if (consumed_bw < 0)
+				return consumed_bw;
+
+			bw -= consumed_bw;
+		}
 
-	do {
-		sw = tb_to_switch(sw->dev.parent);
-		if (!sw)
-			return 0;
-		in = tb_find_unused_port(sw, TB_TYPE_DP_HDMI_IN);
-	} while (!in);
+		if (bw < available_bw)
+			available_bw = bw;
 
-	tunnel = tb_tunnel_alloc_dp(tb, in, out);
+		sw = tb_switch_parent(sw);
+	}
+
+	return available_bw;
+}
+
+static void tb_tunnel_dp(struct tb *tb)
+{
+	struct tb_cm *tcm = tb_priv(tb);
+	struct tb_port *port, *in, *out;
+	struct tb_tunnel *tunnel;
+	int available_bw;
+
+	/*
+	 * Find pair of inactive DP IN and DP OUT adapters and then
+	 * establish a DP tunnel between them.
+	 */
+	tb_dbg(tb, "looking for DP IN <-> DP OUT pairs:\n");
+
+	in = NULL;
+	out = NULL;
+	list_for_each_entry(port, &tcm->dp_resources, list) {
+		if (tb_port_is_enabled(port)) {
+			tb_port_dbg(port, "in use\n");
+			continue;
+		}
+
+		tb_port_dbg(port, "available\n");
+
+		if (!in && tb_port_is_dpin(port))
+			in = port;
+		else if (!out && tb_port_is_dpout(port))
+			out = port;
+	}
+
+	if (!in) {
+		tb_dbg(tb, "no suitable DP IN adapter available, not tunneling\n");
+		return;
+	}
+	if (!out) {
+		tb_dbg(tb, "no suitable DP OUT adapter available, not tunneling\n");
+		return;
+	}
+
+	if (tb_switch_alloc_dp_resource(in->sw, in)) {
+		tb_port_dbg(in, "no resource available for DP IN, not tunneling\n");
+		return;
+	}
+
+	/* Calculate available bandwidth between in and out */
+	available_bw = tb_available_bw(tcm, in, out);
+	if (available_bw < 0) {
+		tb_warn(tb, "failed to determine available bandwidth\n");
+		return;
+	}
+
+	tb_dbg(tb, "available bandwidth for new DP tunnel %u Mb/s\n",
+	       available_bw);
+
+	tunnel = tb_tunnel_alloc_dp(tb, in, out, available_bw);
 	if (!tunnel) {
-		tb_port_dbg(out, "DP tunnel allocation failed\n");
-		return -ENOMEM;
+		tb_port_dbg(out, "could not allocate DP tunnel\n");
+		goto dealloc_dp;
 	}
 
 	if (tb_tunnel_activate(tunnel)) {
 		tb_port_info(out, "DP tunnel activation failed, aborting\n");
 		tb_tunnel_free(tunnel);
-		return -EIO;
+		goto dealloc_dp;
 	}
 
 	list_add_tail(&tunnel->list, &tcm->tunnel_list);
-	return 0;
+	return;
+
+dealloc_dp:
+	tb_switch_dealloc_dp_resource(in->sw, in);
 }
 
-static void tb_teardown_dp(struct tb *tb, struct tb_port *out)
+static void tb_dp_resource_unavailable(struct tb *tb, struct tb_port *port)
 {
-	tb_free_tunnel(tb, TB_TUNNEL_DP, NULL, out);
+	struct tb_port *in, *out;
+	struct tb_tunnel *tunnel;
+
+	if (tb_port_is_dpin(port)) {
+		tb_port_dbg(port, "DP IN resource unavailable\n");
+		in = port;
+		out = NULL;
+	} else {
+		tb_port_dbg(port, "DP OUT resource unavailable\n");
+		in = NULL;
+		out = port;
+	}
+
+	tunnel = tb_find_tunnel(tb, TB_TUNNEL_DP, in, out);
+	tb_deactivate_and_free_tunnel(tunnel);
+	list_del_init(&port->list);
+
+	/*
+	 * See if there is another DP OUT port that can be used for
+	 * to create another tunnel.
+	 */
+	tb_tunnel_dp(tb);
+}
+
+static void tb_dp_resource_available(struct tb *tb, struct tb_port *port)
+{
+	struct tb_cm *tcm = tb_priv(tb);
+	struct tb_port *p;
+
+	if (tb_port_is_enabled(port))
+		return;
+
+	list_for_each_entry(p, &tcm->dp_resources, list) {
+		if (p == port)
+			return;
+	}
+
+	tb_port_dbg(port, "DP %s resource available\n",
+		    tb_port_is_dpin(port) ? "IN" : "OUT");
+	list_add_tail(&port->list, &tcm->dp_resources);
+
+	/* Look for suitable DP IN <-> DP OUT pairs now */
+	tb_tunnel_dp(tb);
 }
 
 static int tb_tunnel_pci(struct tb *tb, struct tb_switch *sw)
@@ -468,6 +651,7 @@ static int tb_approve_xdomain_paths(struct tb *tb, struct tb_xdomain *xd)
 static void __tb_disconnect_xdomain_paths(struct tb *tb, struct tb_xdomain *xd)
 {
 	struct tb_port *dst_port;
+	struct tb_tunnel *tunnel;
 	struct tb_switch *sw;
 
 	sw = tb_to_switch(xd->dev.parent);
@@ -478,7 +662,8 @@ static void __tb_disconnect_xdomain_paths(struct tb *tb, struct tb_xdomain *xd)
 	 * case of cable disconnect) so it is fine if we cannot find it
 	 * here anymore.
 	 */
-	tb_free_tunnel(tb, TB_TUNNEL_DMA, NULL, dst_port);
+	tunnel = tb_find_tunnel(tb, TB_TUNNEL_DMA, NULL, dst_port);
+	tb_deactivate_and_free_tunnel(tunnel);
 }
 
 static int tb_disconnect_xdomain_paths(struct tb *tb, struct tb_xdomain *xd)
@@ -533,10 +718,14 @@ static void tb_handle_hotplug(struct work_struct *work)
 			tb_port_dbg(port, "switch unplugged\n");
 			tb_sw_set_unplugged(port->remote->sw);
 			tb_free_invalid_tunnels(tb);
+			tb_remove_dp_resources(port->remote->sw);
+			tb_switch_lane_bonding_disable(port->remote->sw);
 			tb_switch_remove(port->remote->sw);
 			port->remote = NULL;
 			if (port->dual_link_port)
 				port->dual_link_port->remote = NULL;
+			/* Maybe we can create another DP tunnel */
+			tb_tunnel_dp(tb);
 		} else if (port->xdomain) {
 			struct tb_xdomain *xd = tb_xdomain_get(port->xdomain);
 
@@ -553,8 +742,8 @@ static void tb_handle_hotplug(struct work_struct *work)
 			port->xdomain = NULL;
 			__tb_disconnect_xdomain_paths(tb, xd);
 			tb_xdomain_put(xd);
-		} else if (tb_port_is_dpout(port)) {
-			tb_teardown_dp(tb, port);
+		} else if (tb_port_is_dpout(port) || tb_port_is_dpin(port)) {
+			tb_dp_resource_unavailable(tb, port);
 		} else {
 			tb_port_dbg(port,
 				   "got unplug event for disconnected port, ignoring\n");
@@ -567,8 +756,8 @@ static void tb_handle_hotplug(struct work_struct *work)
 			tb_scan_port(port);
 			if (!port->remote)
 				tb_port_dbg(port, "hotplug: no switch found\n");
-		} else if (tb_port_is_dpout(port)) {
-			tb_tunnel_dp(tb, port);
+		} else if (tb_port_is_dpout(port) || tb_port_is_dpin(port)) {
+			tb_dp_resource_available(tb, port);
 		}
 	}
 
@@ -681,6 +870,8 @@ static int tb_start(struct tb *tb)
 	tb_scan_switch(tb->root_switch);
 	/* Find out tunnels created by the boot firmware */
 	tb_discover_tunnels(tb->root_switch);
+	/* Add DP IN resources for the root switch */
+	tb_add_dp_resources(tb->root_switch);
 	/* Make the discovered switches available to the userspace */
 	device_for_each_child(&tb->root_switch->dev, NULL,
 			      tb_scan_finalize_switch);
@@ -702,6 +893,21 @@ static int tb_suspend_noirq(struct tb *tb)
 	return 0;
 }
 
+static void tb_restore_children(struct tb_switch *sw)
+{
+	struct tb_port *port;
+
+	tb_switch_for_each_port(sw, port) {
+		if (!tb_port_has_remote(port))
+			continue;
+
+		if (tb_switch_lane_bonding_enable(port->remote->sw))
+			dev_warn(&sw->dev, "failed to restore lane bonding\n");
+
+		tb_restore_children(port->remote->sw);
+	}
+}
+
 static int tb_resume_noirq(struct tb *tb)
 {
 	struct tb_cm *tcm = tb_priv(tb);
@@ -715,6 +921,7 @@ static int tb_resume_noirq(struct tb *tb)
 	tb_switch_resume(tb->root_switch);
 	tb_free_invalid_tunnels(tb);
 	tb_free_unplugged_children(tb->root_switch);
+	tb_restore_children(tb->root_switch);
 	list_for_each_entry_safe(tunnel, n, &tcm->tunnel_list, list)
 		tb_tunnel_restart(tunnel);
 	if (!list_empty(&tcm->tunnel_list)) {
@@ -734,11 +941,10 @@ static int tb_resume_noirq(struct tb *tb)
 
 static int tb_free_unplugged_xdomains(struct tb_switch *sw)
 {
-	int i, ret = 0;
-
-	for (i = 1; i <= sw->config.max_port_number; i++) {
-		struct tb_port *port = &sw->ports[i];
+	struct tb_port *port;
+	int ret = 0;
 
+	tb_switch_for_each_port(sw, port) {
 		if (tb_is_upstream_port(port))
 			continue;
 		if (port->xdomain && port->xdomain->is_unplugged) {
@@ -783,9 +989,6 @@ struct tb *tb_probe(struct tb_nhi *nhi)
 	struct tb_cm *tcm;
 	struct tb *tb;
 
-	if (!x86_apple_machine)
-		return NULL;
-
 	tb = tb_domain_alloc(nhi, sizeof(*tcm));
 	if (!tb)
 		return NULL;
@@ -795,6 +998,7 @@ struct tb *tb_probe(struct tb_nhi *nhi)
 
 	tcm = tb_priv(tb);
 	INIT_LIST_HEAD(&tcm->tunnel_list);
+	INIT_LIST_HEAD(&tcm->dp_resources);
 
 	return tb;
 }
diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h
index 6407d529871d..ec851f20c571 100644
--- a/drivers/thunderbolt/tb.h
+++ b/drivers/thunderbolt/tb.h
@@ -61,6 +61,8 @@ struct tb_switch_nvm {
  * @device: Device ID of the switch
  * @vendor_name: Name of the vendor (or %NULL if not known)
  * @device_name: Name of the device (or %NULL if not known)
+ * @link_speed: Speed of the link in Gb/s
+ * @link_width: Width of the link (1 or 2)
  * @generation: Switch Thunderbolt generation
  * @cap_plug_events: Offset to the plug events capability (%0 if not found)
  * @cap_lc: Offset to the link controller capability (%0 if not found)
@@ -97,6 +99,8 @@ struct tb_switch {
 	u16 device;
 	const char *vendor_name;
 	const char *device_name;
+	unsigned int link_speed;
+	unsigned int link_width;
 	unsigned int generation;
 	int cap_plug_events;
 	int cap_lc;
@@ -127,11 +131,13 @@ struct tb_switch {
  * @cap_adap: Offset of the adapter specific capability (%0 if not present)
  * @port: Port number on switch
  * @disabled: Disabled by eeprom
+ * @bonded: true if the port is bonded (two lanes combined as one)
  * @dual_link_port: If the switch is connected using two ports, points
  *		    to the other port.
  * @link_nr: Is this primary or secondary port on the dual_link.
  * @in_hopids: Currently allocated input HopIDs
  * @out_hopids: Currently allocated output HopIDs
+ * @list: Used to link ports to DP resources list
  */
 struct tb_port {
 	struct tb_regs_port_header config;
@@ -142,10 +148,12 @@ struct tb_port {
 	int cap_adap;
 	u8 port;
 	bool disabled;
+	bool bonded;
 	struct tb_port *dual_link_port;
 	u8 link_nr:1;
 	struct ida in_hopids;
 	struct ida out_hopids;
+	struct list_head list;
 };
 
 /**
@@ -399,7 +407,7 @@ static inline int tb_sw_read(struct tb_switch *sw, void *buffer,
 			   length);
 }
 
-static inline int tb_sw_write(struct tb_switch *sw, void *buffer,
+static inline int tb_sw_write(struct tb_switch *sw, const void *buffer,
 			      enum tb_cfg_space space, u32 offset, u32 length)
 {
 	if (sw->is_unplugged)
@@ -530,6 +538,17 @@ struct tb_switch *tb_switch_find_by_link_depth(struct tb *tb, u8 link,
 struct tb_switch *tb_switch_find_by_uuid(struct tb *tb, const uuid_t *uuid);
 struct tb_switch *tb_switch_find_by_route(struct tb *tb, u64 route);
 
+/**
+ * tb_switch_for_each_port() - Iterate over each switch port
+ * @sw: Switch whose ports to iterate
+ * @p: Port used as iterator
+ *
+ * Iterates over each switch port skipping the control port (port %0).
+ */
+#define tb_switch_for_each_port(sw, p)					\
+	for ((p) = &(sw)->ports[1];					\
+	     (p) <= &(sw)->ports[(sw)->config.max_port_number]; (p)++)
+
 static inline struct tb_switch *tb_switch_get(struct tb_switch *sw)
 {
 	if (sw)
@@ -559,17 +578,17 @@ static inline struct tb_switch *tb_switch_parent(struct tb_switch *sw)
 	return tb_to_switch(sw->dev.parent);
 }
 
-static inline bool tb_switch_is_lr(const struct tb_switch *sw)
+static inline bool tb_switch_is_light_ridge(const struct tb_switch *sw)
 {
 	return sw->config.device_id == PCI_DEVICE_ID_INTEL_LIGHT_RIDGE;
 }
 
-static inline bool tb_switch_is_er(const struct tb_switch *sw)
+static inline bool tb_switch_is_eagle_ridge(const struct tb_switch *sw)
 {
 	return sw->config.device_id == PCI_DEVICE_ID_INTEL_EAGLE_RIDGE;
 }
 
-static inline bool tb_switch_is_cr(const struct tb_switch *sw)
+static inline bool tb_switch_is_cactus_ridge(const struct tb_switch *sw)
 {
 	switch (sw->config.device_id) {
 	case PCI_DEVICE_ID_INTEL_CACTUS_RIDGE_2C:
@@ -580,7 +599,7 @@ static inline bool tb_switch_is_cr(const struct tb_switch *sw)
 	}
 }
 
-static inline bool tb_switch_is_fr(const struct tb_switch *sw)
+static inline bool tb_switch_is_falcon_ridge(const struct tb_switch *sw)
 {
 	switch (sw->config.device_id) {
 	case PCI_DEVICE_ID_INTEL_FALCON_RIDGE_2C_BRIDGE:
@@ -591,6 +610,52 @@ static inline bool tb_switch_is_fr(const struct tb_switch *sw)
 	}
 }
 
+static inline bool tb_switch_is_alpine_ridge(const struct tb_switch *sw)
+{
+	switch (sw->config.device_id) {
+	case PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_2C_BRIDGE:
+	case PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_LP_BRIDGE:
+	case PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_C_4C_BRIDGE:
+	case PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_C_2C_BRIDGE:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static inline bool tb_switch_is_titan_ridge(const struct tb_switch *sw)
+{
+	switch (sw->config.device_id) {
+	case PCI_DEVICE_ID_INTEL_TITAN_RIDGE_2C_BRIDGE:
+	case PCI_DEVICE_ID_INTEL_TITAN_RIDGE_4C_BRIDGE:
+	case PCI_DEVICE_ID_INTEL_TITAN_RIDGE_DD_BRIDGE:
+		return true;
+	default:
+		return false;
+	}
+}
+
+/**
+ * tb_switch_is_icm() - Is the switch handled by ICM firmware
+ * @sw: Switch to check
+ *
+ * In case there is a need to differentiate whether ICM firmware or SW CM
+ * is handling @sw this function can be called. It is valid to call this
+ * after tb_switch_alloc() and tb_switch_configure() has been called
+ * (latter only for SW CM case).
+ */
+static inline bool tb_switch_is_icm(const struct tb_switch *sw)
+{
+	return !sw->config.enabled;
+}
+
+int tb_switch_lane_bonding_enable(struct tb_switch *sw);
+void tb_switch_lane_bonding_disable(struct tb_switch *sw);
+
+bool tb_switch_query_dp_resource(struct tb_switch *sw, struct tb_port *in);
+int tb_switch_alloc_dp_resource(struct tb_switch *sw, struct tb_port *in);
+void tb_switch_dealloc_dp_resource(struct tb_switch *sw, struct tb_port *in);
+
 int tb_wait_for_port(struct tb_port *port, bool wait_if_unplugged);
 int tb_port_add_nfc_credits(struct tb_port *port, int credits);
 int tb_port_set_initial_credits(struct tb_port *port, u32 credits);
@@ -626,6 +691,8 @@ void tb_path_free(struct tb_path *path);
 int tb_path_activate(struct tb_path *path);
 void tb_path_deactivate(struct tb_path *path);
 bool tb_path_is_invalid(struct tb_path *path);
+bool tb_path_switch_on_path(const struct tb_path *path,
+			    const struct tb_switch *sw);
 
 int tb_drom_read(struct tb_switch *sw);
 int tb_drom_read_uid_only(struct tb_switch *sw, u64 *uid);
@@ -634,6 +701,10 @@ int tb_lc_read_uuid(struct tb_switch *sw, u32 *uuid);
 int tb_lc_configure_link(struct tb_switch *sw);
 void tb_lc_unconfigure_link(struct tb_switch *sw);
 int tb_lc_set_sleep(struct tb_switch *sw);
+bool tb_lc_lane_bonding_possible(struct tb_switch *sw);
+bool tb_lc_dp_sink_query(struct tb_switch *sw, struct tb_port *in);
+int tb_lc_dp_sink_alloc(struct tb_switch *sw, struct tb_port *in);
+int tb_lc_dp_sink_dealloc(struct tb_switch *sw, struct tb_port *in);
 
 static inline int tb_route_length(u64 route)
 {
diff --git a/drivers/thunderbolt/tb_msgs.h b/drivers/thunderbolt/tb_msgs.h
index 4b641e4ee0c5..3705057723b6 100644
--- a/drivers/thunderbolt/tb_msgs.h
+++ b/drivers/thunderbolt/tb_msgs.h
@@ -122,6 +122,8 @@ struct icm_pkg_header {
 #define ICM_FLAGS_NO_KEY		BIT(1)
 #define ICM_FLAGS_SLEVEL_SHIFT		3
 #define ICM_FLAGS_SLEVEL_MASK		GENMASK(4, 3)
+#define ICM_FLAGS_DUAL_LANE		BIT(5)
+#define ICM_FLAGS_SPEED_GEN3		BIT(7)
 #define ICM_FLAGS_WRITE			BIT(7)
 
 struct icm_pkg_driver_ready {
diff --git a/drivers/thunderbolt/tb_regs.h b/drivers/thunderbolt/tb_regs.h
index deb9d4a977b9..7ee45b73c7f7 100644
--- a/drivers/thunderbolt/tb_regs.h
+++ b/drivers/thunderbolt/tb_regs.h
@@ -211,37 +211,71 @@ struct tb_regs_port_header {
 
 } __packed;
 
-/* DWORD 4 */
-#define TB_PORT_NFC_CREDITS_MASK	GENMASK(19, 0)
-#define TB_PORT_MAX_CREDITS_SHIFT	20
-#define TB_PORT_MAX_CREDITS_MASK	GENMASK(26, 20)
-/* DWORD 5 */
-#define TB_PORT_LCA_SHIFT		22
-#define TB_PORT_LCA_MASK		GENMASK(28, 22)
+/* Basic adapter configuration registers */
+#define ADP_CS_4				0x04
+#define ADP_CS_4_NFC_BUFFERS_MASK		GENMASK(9, 0)
+#define ADP_CS_4_TOTAL_BUFFERS_MASK		GENMASK(29, 20)
+#define ADP_CS_4_TOTAL_BUFFERS_SHIFT		20
+#define ADP_CS_5				0x05
+#define ADP_CS_5_LCA_MASK			GENMASK(28, 22)
+#define ADP_CS_5_LCA_SHIFT			22
+
+/* Lane adapter registers */
+#define LANE_ADP_CS_0				0x00
+#define LANE_ADP_CS_0_SUPPORTED_WIDTH_MASK	GENMASK(25, 20)
+#define LANE_ADP_CS_0_SUPPORTED_WIDTH_SHIFT	20
+#define LANE_ADP_CS_1				0x01
+#define LANE_ADP_CS_1_TARGET_WIDTH_MASK		GENMASK(9, 4)
+#define LANE_ADP_CS_1_TARGET_WIDTH_SHIFT	4
+#define LANE_ADP_CS_1_TARGET_WIDTH_SINGLE	0x1
+#define LANE_ADP_CS_1_TARGET_WIDTH_DUAL		0x3
+#define LANE_ADP_CS_1_LB			BIT(15)
+#define LANE_ADP_CS_1_CURRENT_SPEED_MASK	GENMASK(19, 16)
+#define LANE_ADP_CS_1_CURRENT_SPEED_SHIFT	16
+#define LANE_ADP_CS_1_CURRENT_SPEED_GEN2	0x8
+#define LANE_ADP_CS_1_CURRENT_SPEED_GEN3	0x4
+#define LANE_ADP_CS_1_CURRENT_WIDTH_MASK	GENMASK(25, 20)
+#define LANE_ADP_CS_1_CURRENT_WIDTH_SHIFT	20
 
 /* Display Port adapter registers */
-
-/* DWORD 0 */
-#define TB_DP_VIDEO_HOPID_SHIFT		16
-#define TB_DP_VIDEO_HOPID_MASK		GENMASK(26, 16)
-#define TB_DP_AUX_EN			BIT(30)
-#define TB_DP_VIDEO_EN			BIT(31)
-/* DWORD 1 */
-#define TB_DP_AUX_TX_HOPID_MASK		GENMASK(10, 0)
-#define TB_DP_AUX_RX_HOPID_SHIFT	11
-#define TB_DP_AUX_RX_HOPID_MASK		GENMASK(21, 11)
-/* DWORD 2 */
-#define TB_DP_HDP			BIT(6)
-/* DWORD 3 */
-#define TB_DP_HPDC			BIT(9)
-/* DWORD 4 */
-#define TB_DP_LOCAL_CAP			0x4
-/* DWORD 5 */
-#define TB_DP_REMOTE_CAP		0x5
+#define ADP_DP_CS_0				0x00
+#define ADP_DP_CS_0_VIDEO_HOPID_MASK		GENMASK(26, 16)
+#define ADP_DP_CS_0_VIDEO_HOPID_SHIFT		16
+#define ADP_DP_CS_0_AE				BIT(30)
+#define ADP_DP_CS_0_VE				BIT(31)
+#define ADP_DP_CS_1_AUX_TX_HOPID_MASK		GENMASK(10, 0)
+#define ADP_DP_CS_1_AUX_RX_HOPID_MASK		GENMASK(21, 11)
+#define ADP_DP_CS_1_AUX_RX_HOPID_SHIFT		11
+#define ADP_DP_CS_2				0x02
+#define ADP_DP_CS_2_HDP				BIT(6)
+#define ADP_DP_CS_3				0x03
+#define ADP_DP_CS_3_HDPC			BIT(9)
+#define DP_LOCAL_CAP				0x04
+#define DP_REMOTE_CAP				0x05
+#define DP_STATUS_CTRL				0x06
+#define DP_STATUS_CTRL_CMHS			BIT(25)
+#define DP_STATUS_CTRL_UF			BIT(26)
+#define DP_COMMON_CAP				0x07
+/*
+ * DP_COMMON_CAP offsets work also for DP_LOCAL_CAP and DP_REMOTE_CAP
+ * with exception of DPRX done.
+ */
+#define DP_COMMON_CAP_RATE_MASK			GENMASK(11, 8)
+#define DP_COMMON_CAP_RATE_SHIFT		8
+#define DP_COMMON_CAP_RATE_RBR			0x0
+#define DP_COMMON_CAP_RATE_HBR			0x1
+#define DP_COMMON_CAP_RATE_HBR2			0x2
+#define DP_COMMON_CAP_RATE_HBR3			0x3
+#define DP_COMMON_CAP_LANES_MASK		GENMASK(14, 12)
+#define DP_COMMON_CAP_LANES_SHIFT		12
+#define DP_COMMON_CAP_1_LANE			0x0
+#define DP_COMMON_CAP_2_LANES			0x1
+#define DP_COMMON_CAP_4_LANES			0x2
+#define DP_COMMON_CAP_DPRX_DONE			BIT(31)
 
 /* PCIe adapter registers */
-
-#define TB_PCI_EN			BIT(31)
+#define ADP_PCIE_CS_0				0x00
+#define ADP_PCIE_CS_0_PE			BIT(31)
 
 /* Hop register from TB_CFG_HOPS. 8 byte per entry. */
 struct tb_regs_hop {
@@ -278,8 +312,17 @@ struct tb_regs_hop {
 #define TB_LC_DESC_PORT_SIZE_SHIFT	16
 #define TB_LC_DESC_PORT_SIZE_MASK	GENMASK(27, 16)
 #define TB_LC_FUSE			0x03
+#define TB_LC_SNK_ALLOCATION		0x10
+#define TB_LC_SNK_ALLOCATION_SNK0_MASK	GENMASK(3, 0)
+#define TB_LC_SNK_ALLOCATION_SNK0_CM	0x1
+#define TB_LC_SNK_ALLOCATION_SNK1_SHIFT	4
+#define TB_LC_SNK_ALLOCATION_SNK1_MASK	GENMASK(7, 4)
+#define TB_LC_SNK_ALLOCATION_SNK1_CM	0x1
 
 /* Link controller registers */
+#define TB_LC_PORT_ATTR			0x8d
+#define TB_LC_PORT_ATTR_BE		BIT(12)
+
 #define TB_LC_SX_CTRL			0x96
 #define TB_LC_SX_CTRL_L1C		BIT(16)
 #define TB_LC_SX_CTRL_L2C		BIT(20)
diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c
index 5a99234826e7..0d3463c4e24a 100644
--- a/drivers/thunderbolt/tunnel.c
+++ b/drivers/thunderbolt/tunnel.c
@@ -6,6 +6,7 @@
  * Copyright (C) 2019, Intel Corporation
  */
 
+#include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/list.h>
 
@@ -90,6 +91,22 @@ static int tb_pci_activate(struct tb_tunnel *tunnel, bool activate)
 	return 0;
 }
 
+static int tb_initial_credits(const struct tb_switch *sw)
+{
+	/* If the path is complete sw is not NULL */
+	if (sw) {
+		/* More credits for faster link */
+		switch (sw->link_speed * sw->link_width) {
+		case 40:
+			return 32;
+		case 20:
+			return 24;
+		}
+	}
+
+	return 16;
+}
+
 static void tb_pci_init_path(struct tb_path *path)
 {
 	path->egress_fc_enable = TB_PATH_SOURCE | TB_PATH_INTERNAL;
@@ -101,7 +118,8 @@ static void tb_pci_init_path(struct tb_path *path)
 	path->drop_packages = 0;
 	path->nfc_credits = 0;
 	path->hops[0].initial_credits = 7;
-	path->hops[1].initial_credits = 16;
+	path->hops[1].initial_credits =
+		tb_initial_credits(path->hops[1].in_port->sw);
 }
 
 /**
@@ -225,11 +243,174 @@ struct tb_tunnel *tb_tunnel_alloc_pci(struct tb *tb, struct tb_port *up,
 	return tunnel;
 }
 
+static int tb_dp_cm_handshake(struct tb_port *in, struct tb_port *out)
+{
+	int timeout = 10;
+	u32 val;
+	int ret;
+
+	/* Both ends need to support this */
+	if (!tb_switch_is_titan_ridge(in->sw) ||
+	    !tb_switch_is_titan_ridge(out->sw))
+		return 0;
+
+	ret = tb_port_read(out, &val, TB_CFG_PORT,
+			   out->cap_adap + DP_STATUS_CTRL, 1);
+	if (ret)
+		return ret;
+
+	val |= DP_STATUS_CTRL_UF | DP_STATUS_CTRL_CMHS;
+
+	ret = tb_port_write(out, &val, TB_CFG_PORT,
+			    out->cap_adap + DP_STATUS_CTRL, 1);
+	if (ret)
+		return ret;
+
+	do {
+		ret = tb_port_read(out, &val, TB_CFG_PORT,
+				   out->cap_adap + DP_STATUS_CTRL, 1);
+		if (ret)
+			return ret;
+		if (!(val & DP_STATUS_CTRL_CMHS))
+			return 0;
+		usleep_range(10, 100);
+	} while (timeout--);
+
+	return -ETIMEDOUT;
+}
+
+static inline u32 tb_dp_cap_get_rate(u32 val)
+{
+	u32 rate = (val & DP_COMMON_CAP_RATE_MASK) >> DP_COMMON_CAP_RATE_SHIFT;
+
+	switch (rate) {
+	case DP_COMMON_CAP_RATE_RBR:
+		return 1620;
+	case DP_COMMON_CAP_RATE_HBR:
+		return 2700;
+	case DP_COMMON_CAP_RATE_HBR2:
+		return 5400;
+	case DP_COMMON_CAP_RATE_HBR3:
+		return 8100;
+	default:
+		return 0;
+	}
+}
+
+static inline u32 tb_dp_cap_set_rate(u32 val, u32 rate)
+{
+	val &= ~DP_COMMON_CAP_RATE_MASK;
+	switch (rate) {
+	default:
+		WARN(1, "invalid rate %u passed, defaulting to 1620 MB/s\n", rate);
+		/* Fallthrough */
+	case 1620:
+		val |= DP_COMMON_CAP_RATE_RBR << DP_COMMON_CAP_RATE_SHIFT;
+		break;
+	case 2700:
+		val |= DP_COMMON_CAP_RATE_HBR << DP_COMMON_CAP_RATE_SHIFT;
+		break;
+	case 5400:
+		val |= DP_COMMON_CAP_RATE_HBR2 << DP_COMMON_CAP_RATE_SHIFT;
+		break;
+	case 8100:
+		val |= DP_COMMON_CAP_RATE_HBR3 << DP_COMMON_CAP_RATE_SHIFT;
+		break;
+	}
+	return val;
+}
+
+static inline u32 tb_dp_cap_get_lanes(u32 val)
+{
+	u32 lanes = (val & DP_COMMON_CAP_LANES_MASK) >> DP_COMMON_CAP_LANES_SHIFT;
+
+	switch (lanes) {
+	case DP_COMMON_CAP_1_LANE:
+		return 1;
+	case DP_COMMON_CAP_2_LANES:
+		return 2;
+	case DP_COMMON_CAP_4_LANES:
+		return 4;
+	default:
+		return 0;
+	}
+}
+
+static inline u32 tb_dp_cap_set_lanes(u32 val, u32 lanes)
+{
+	val &= ~DP_COMMON_CAP_LANES_MASK;
+	switch (lanes) {
+	default:
+		WARN(1, "invalid number of lanes %u passed, defaulting to 1\n",
+		     lanes);
+		/* Fallthrough */
+	case 1:
+		val |= DP_COMMON_CAP_1_LANE << DP_COMMON_CAP_LANES_SHIFT;
+		break;
+	case 2:
+		val |= DP_COMMON_CAP_2_LANES << DP_COMMON_CAP_LANES_SHIFT;
+		break;
+	case 4:
+		val |= DP_COMMON_CAP_4_LANES << DP_COMMON_CAP_LANES_SHIFT;
+		break;
+	}
+	return val;
+}
+
+static unsigned int tb_dp_bandwidth(unsigned int rate, unsigned int lanes)
+{
+	/* Tunneling removes the DP 8b/10b encoding */
+	return rate * lanes * 8 / 10;
+}
+
+static int tb_dp_reduce_bandwidth(int max_bw, u32 in_rate, u32 in_lanes,
+				  u32 out_rate, u32 out_lanes, u32 *new_rate,
+				  u32 *new_lanes)
+{
+	static const u32 dp_bw[][2] = {
+		/* Mb/s, lanes */
+		{ 8100, 4 }, /* 25920 Mb/s */
+		{ 5400, 4 }, /* 17280 Mb/s */
+		{ 8100, 2 }, /* 12960 Mb/s */
+		{ 2700, 4 }, /* 8640 Mb/s */
+		{ 5400, 2 }, /* 8640 Mb/s */
+		{ 8100, 1 }, /* 6480 Mb/s */
+		{ 1620, 4 }, /* 5184 Mb/s */
+		{ 5400, 1 }, /* 4320 Mb/s */
+		{ 2700, 2 }, /* 4320 Mb/s */
+		{ 1620, 2 }, /* 2592 Mb/s */
+		{ 2700, 1 }, /* 2160 Mb/s */
+		{ 1620, 1 }, /* 1296 Mb/s */
+	};
+	unsigned int i;
+
+	/*
+	 * Find a combination that can fit into max_bw and does not
+	 * exceed the maximum rate and lanes supported by the DP OUT and
+	 * DP IN adapters.
+	 */
+	for (i = 0; i < ARRAY_SIZE(dp_bw); i++) {
+		if (dp_bw[i][0] > out_rate || dp_bw[i][1] > out_lanes)
+			continue;
+
+		if (dp_bw[i][0] > in_rate || dp_bw[i][1] > in_lanes)
+			continue;
+
+		if (tb_dp_bandwidth(dp_bw[i][0], dp_bw[i][1]) <= max_bw) {
+			*new_rate = dp_bw[i][0];
+			*new_lanes = dp_bw[i][1];
+			return 0;
+		}
+	}
+
+	return -ENOSR;
+}
+
 static int tb_dp_xchg_caps(struct tb_tunnel *tunnel)
 {
+	u32 out_dp_cap, out_rate, out_lanes, in_dp_cap, in_rate, in_lanes, bw;
 	struct tb_port *out = tunnel->dst_port;
 	struct tb_port *in = tunnel->src_port;
-	u32 in_dp_cap, out_dp_cap;
 	int ret;
 
 	/*
@@ -239,25 +420,71 @@ static int tb_dp_xchg_caps(struct tb_tunnel *tunnel)
 	if (in->sw->generation < 2 || out->sw->generation < 2)
 		return 0;
 
+	/*
+	 * Perform connection manager handshake between IN and OUT ports
+	 * before capabilities exchange can take place.
+	 */
+	ret = tb_dp_cm_handshake(in, out);
+	if (ret)
+		return ret;
+
 	/* Read both DP_LOCAL_CAP registers */
 	ret = tb_port_read(in, &in_dp_cap, TB_CFG_PORT,
-			   in->cap_adap + TB_DP_LOCAL_CAP, 1);
+			   in->cap_adap + DP_LOCAL_CAP, 1);
 	if (ret)
 		return ret;
 
 	ret = tb_port_read(out, &out_dp_cap, TB_CFG_PORT,
-			   out->cap_adap + TB_DP_LOCAL_CAP, 1);
+			   out->cap_adap + DP_LOCAL_CAP, 1);
 	if (ret)
 		return ret;
 
 	/* Write IN local caps to OUT remote caps */
 	ret = tb_port_write(out, &in_dp_cap, TB_CFG_PORT,
-			    out->cap_adap + TB_DP_REMOTE_CAP, 1);
+			    out->cap_adap + DP_REMOTE_CAP, 1);
 	if (ret)
 		return ret;
 
+	in_rate = tb_dp_cap_get_rate(in_dp_cap);
+	in_lanes = tb_dp_cap_get_lanes(in_dp_cap);
+	tb_port_dbg(in, "maximum supported bandwidth %u Mb/s x%u = %u Mb/s\n",
+		    in_rate, in_lanes, tb_dp_bandwidth(in_rate, in_lanes));
+
+	/*
+	 * If the tunnel bandwidth is limited (max_bw is set) then see
+	 * if we need to reduce bandwidth to fit there.
+	 */
+	out_rate = tb_dp_cap_get_rate(out_dp_cap);
+	out_lanes = tb_dp_cap_get_lanes(out_dp_cap);
+	bw = tb_dp_bandwidth(out_rate, out_lanes);
+	tb_port_dbg(out, "maximum supported bandwidth %u Mb/s x%u = %u Mb/s\n",
+		    out_rate, out_lanes, bw);
+
+	if (tunnel->max_bw && bw > tunnel->max_bw) {
+		u32 new_rate, new_lanes, new_bw;
+
+		ret = tb_dp_reduce_bandwidth(tunnel->max_bw, in_rate, in_lanes,
+					     out_rate, out_lanes, &new_rate,
+					     &new_lanes);
+		if (ret) {
+			tb_port_info(out, "not enough bandwidth for DP tunnel\n");
+			return ret;
+		}
+
+		new_bw = tb_dp_bandwidth(new_rate, new_lanes);
+		tb_port_dbg(out, "bandwidth reduced to %u Mb/s x%u = %u Mb/s\n",
+			    new_rate, new_lanes, new_bw);
+
+		/*
+		 * Set new rate and number of lanes before writing it to
+		 * the IN port remote caps.
+		 */
+		out_dp_cap = tb_dp_cap_set_rate(out_dp_cap, new_rate);
+		out_dp_cap = tb_dp_cap_set_lanes(out_dp_cap, new_lanes);
+	}
+
 	return tb_port_write(in, &out_dp_cap, TB_CFG_PORT,
-			     in->cap_adap + TB_DP_REMOTE_CAP, 1);
+			     in->cap_adap + DP_REMOTE_CAP, 1);
 }
 
 static int tb_dp_activate(struct tb_tunnel *tunnel, bool active)
@@ -297,6 +524,56 @@ static int tb_dp_activate(struct tb_tunnel *tunnel, bool active)
 	return 0;
 }
 
+static int tb_dp_consumed_bandwidth(struct tb_tunnel *tunnel)
+{
+	struct tb_port *in = tunnel->src_port;
+	const struct tb_switch *sw = in->sw;
+	u32 val, rate = 0, lanes = 0;
+	int ret;
+
+	if (tb_switch_is_titan_ridge(sw)) {
+		int timeout = 10;
+
+		/*
+		 * Wait for DPRX done. Normally it should be already set
+		 * for active tunnel.
+		 */
+		do {
+			ret = tb_port_read(in, &val, TB_CFG_PORT,
+					   in->cap_adap + DP_COMMON_CAP, 1);
+			if (ret)
+				return ret;
+
+			if (val & DP_COMMON_CAP_DPRX_DONE) {
+				rate = tb_dp_cap_get_rate(val);
+				lanes = tb_dp_cap_get_lanes(val);
+				break;
+			}
+			msleep(250);
+		} while (timeout--);
+
+		if (!timeout)
+			return -ETIMEDOUT;
+	} else if (sw->generation >= 2) {
+		/*
+		 * Read from the copied remote cap so that we take into
+		 * account if capabilities were reduced during exchange.
+		 */
+		ret = tb_port_read(in, &val, TB_CFG_PORT,
+				   in->cap_adap + DP_REMOTE_CAP, 1);
+		if (ret)
+			return ret;
+
+		rate = tb_dp_cap_get_rate(val);
+		lanes = tb_dp_cap_get_lanes(val);
+	} else {
+		/* No bandwidth management for legacy devices  */
+		return 0;
+	}
+
+	return tb_dp_bandwidth(rate, lanes);
+}
+
 static void tb_dp_init_aux_path(struct tb_path *path)
 {
 	int i;
@@ -324,12 +601,12 @@ static void tb_dp_init_video_path(struct tb_path *path, bool discover)
 	path->weight = 1;
 
 	if (discover) {
-		path->nfc_credits = nfc_credits & TB_PORT_NFC_CREDITS_MASK;
+		path->nfc_credits = nfc_credits & ADP_CS_4_NFC_BUFFERS_MASK;
 	} else {
 		u32 max_credits;
 
-		max_credits = (nfc_credits & TB_PORT_MAX_CREDITS_MASK) >>
-			TB_PORT_MAX_CREDITS_SHIFT;
+		max_credits = (nfc_credits & ADP_CS_4_TOTAL_BUFFERS_MASK) >>
+			ADP_CS_4_TOTAL_BUFFERS_SHIFT;
 		/* Leave some credits for AUX path */
 		path->nfc_credits = min(max_credits - 2, 12U);
 	}
@@ -361,6 +638,7 @@ struct tb_tunnel *tb_tunnel_discover_dp(struct tb *tb, struct tb_port *in)
 
 	tunnel->init = tb_dp_xchg_caps;
 	tunnel->activate = tb_dp_activate;
+	tunnel->consumed_bandwidth = tb_dp_consumed_bandwidth;
 	tunnel->src_port = in;
 
 	path = tb_path_discover(in, TB_DP_VIDEO_HOPID, NULL, -1,
@@ -419,6 +697,7 @@ err_free:
  * @tb: Pointer to the domain structure
  * @in: DP in adapter port
  * @out: DP out adapter port
+ * @max_bw: Maximum available bandwidth for the DP tunnel (%0 if not limited)
  *
  * Allocates a tunnel between @in and @out that is capable of tunneling
  * Display Port traffic.
@@ -426,7 +705,7 @@ err_free:
  * Return: Returns a tb_tunnel on success or NULL on failure.
  */
 struct tb_tunnel *tb_tunnel_alloc_dp(struct tb *tb, struct tb_port *in,
-				     struct tb_port *out)
+				     struct tb_port *out, int max_bw)
 {
 	struct tb_tunnel *tunnel;
 	struct tb_path **paths;
@@ -441,8 +720,10 @@ struct tb_tunnel *tb_tunnel_alloc_dp(struct tb *tb, struct tb_port *in,
 
 	tunnel->init = tb_dp_xchg_caps;
 	tunnel->activate = tb_dp_activate;
+	tunnel->consumed_bandwidth = tb_dp_consumed_bandwidth;
 	tunnel->src_port = in;
 	tunnel->dst_port = out;
+	tunnel->max_bw = max_bw;
 
 	paths = tunnel->paths;
 
@@ -478,8 +759,8 @@ static u32 tb_dma_credits(struct tb_port *nhi)
 {
 	u32 max_credits;
 
-	max_credits = (nhi->config.nfc_credits & TB_PORT_MAX_CREDITS_MASK) >>
-		TB_PORT_MAX_CREDITS_SHIFT;
+	max_credits = (nhi->config.nfc_credits & ADP_CS_4_TOTAL_BUFFERS_MASK) >>
+		ADP_CS_4_TOTAL_BUFFERS_SHIFT;
 	return min(max_credits, 13U);
 }
 
@@ -689,3 +970,62 @@ void tb_tunnel_deactivate(struct tb_tunnel *tunnel)
 			tb_path_deactivate(tunnel->paths[i]);
 	}
 }
+
+/**
+ * tb_tunnel_switch_on_path() - Does the tunnel go through switch
+ * @tunnel: Tunnel to check
+ * @sw: Switch to check
+ *
+ * Returns true if @tunnel goes through @sw (direction does not matter),
+ * false otherwise.
+ */
+bool tb_tunnel_switch_on_path(const struct tb_tunnel *tunnel,
+			      const struct tb_switch *sw)
+{
+	int i;
+
+	for (i = 0; i < tunnel->npaths; i++) {
+		if (!tunnel->paths[i])
+			continue;
+		if (tb_path_switch_on_path(tunnel->paths[i], sw))
+			return true;
+	}
+
+	return false;
+}
+
+static bool tb_tunnel_is_active(const struct tb_tunnel *tunnel)
+{
+	int i;
+
+	for (i = 0; i < tunnel->npaths; i++) {
+		if (!tunnel->paths[i])
+			return false;
+		if (!tunnel->paths[i]->activated)
+			return false;
+	}
+
+	return true;
+}
+
+/**
+ * tb_tunnel_consumed_bandwidth() - Return bandwidth consumed by the tunnel
+ * @tunnel: Tunnel to check
+ *
+ * Returns bandwidth currently consumed by @tunnel and %0 if the @tunnel
+ * is not active or does consume bandwidth.
+ */
+int tb_tunnel_consumed_bandwidth(struct tb_tunnel *tunnel)
+{
+	if (!tb_tunnel_is_active(tunnel))
+		return 0;
+
+	if (tunnel->consumed_bandwidth) {
+		int ret = tunnel->consumed_bandwidth(tunnel);
+
+		tb_tunnel_dbg(tunnel, "consumed bandwidth %d Mb/s\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
diff --git a/drivers/thunderbolt/tunnel.h b/drivers/thunderbolt/tunnel.h
index c68bbcd3a62c..ba888da005f5 100644
--- a/drivers/thunderbolt/tunnel.h
+++ b/drivers/thunderbolt/tunnel.h
@@ -27,8 +27,11 @@ enum tb_tunnel_type {
  * @npaths: Number of paths in @paths
  * @init: Optional tunnel specific initialization
  * @activate: Optional tunnel specific activation/deactivation
+ * @consumed_bandwidth: Return how much bandwidth the tunnel consumes
  * @list: Tunnels are linked using this field
  * @type: Type of the tunnel
+ * @max_bw: Maximum bandwidth (Mb/s) available for the tunnel (only for DP).
+ *	    Only set if the bandwidth needs to be limited.
  */
 struct tb_tunnel {
 	struct tb *tb;
@@ -38,8 +41,10 @@ struct tb_tunnel {
 	size_t npaths;
 	int (*init)(struct tb_tunnel *tunnel);
 	int (*activate)(struct tb_tunnel *tunnel, bool activate);
+	int (*consumed_bandwidth)(struct tb_tunnel *tunnel);
 	struct list_head list;
 	enum tb_tunnel_type type;
+	unsigned int max_bw;
 };
 
 struct tb_tunnel *tb_tunnel_discover_pci(struct tb *tb, struct tb_port *down);
@@ -47,7 +52,7 @@ struct tb_tunnel *tb_tunnel_alloc_pci(struct tb *tb, struct tb_port *up,
 				      struct tb_port *down);
 struct tb_tunnel *tb_tunnel_discover_dp(struct tb *tb, struct tb_port *in);
 struct tb_tunnel *tb_tunnel_alloc_dp(struct tb *tb, struct tb_port *in,
-				     struct tb_port *out);
+				     struct tb_port *out, int max_bw);
 struct tb_tunnel *tb_tunnel_alloc_dma(struct tb *tb, struct tb_port *nhi,
 				      struct tb_port *dst, int transmit_ring,
 				      int transmit_path, int receive_ring,
@@ -58,6 +63,9 @@ int tb_tunnel_activate(struct tb_tunnel *tunnel);
 int tb_tunnel_restart(struct tb_tunnel *tunnel);
 void tb_tunnel_deactivate(struct tb_tunnel *tunnel);
 bool tb_tunnel_is_invalid(struct tb_tunnel *tunnel);
+bool tb_tunnel_switch_on_path(const struct tb_tunnel *tunnel,
+			      const struct tb_switch *sw);
+int tb_tunnel_consumed_bandwidth(struct tb_tunnel *tunnel);
 
 static inline bool tb_tunnel_is_pci(const struct tb_tunnel *tunnel)
 {
diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c
index 4e17a7c7bf0a..880d784398a3 100644
--- a/drivers/thunderbolt/xdomain.c
+++ b/drivers/thunderbolt/xdomain.c
@@ -1404,10 +1404,9 @@ struct tb_xdomain_lookup {
 static struct tb_xdomain *switch_find_xdomain(struct tb_switch *sw,
 	const struct tb_xdomain_lookup *lookup)
 {
-	int i;
+	struct tb_port *port;
 
-	for (i = 1; i <= sw->config.max_port_number; i++) {
-		struct tb_port *port = &sw->ports[i];
+	tb_switch_for_each_port(sw, port) {
 		struct tb_xdomain *xd;
 
 		if (port->xdomain) {
diff --git a/drivers/tty/serial/8250/8250_men_mcb.c b/drivers/tty/serial/8250/8250_men_mcb.c
index 8df89e9cd254..e985f344b2dd 100644
--- a/drivers/tty/serial/8250/8250_men_mcb.c
+++ b/drivers/tty/serial/8250/8250_men_mcb.c
@@ -174,3 +174,4 @@ MODULE_AUTHOR("Michael Moese <michael.moese@men.de");
 MODULE_ALIAS("mcb:16z125");
 MODULE_ALIAS("mcb:16z025");
 MODULE_ALIAS("mcb:16z057");
+MODULE_IMPORT_NS(MCB);
diff --git a/drivers/tty/serial/men_z135_uart.c b/drivers/tty/serial/men_z135_uart.c
index e5d3ebab6dae..4f53a4caabf6 100644
--- a/drivers/tty/serial/men_z135_uart.c
+++ b/drivers/tty/serial/men_z135_uart.c
@@ -930,3 +930,4 @@ MODULE_AUTHOR("Johannes Thumshirn <johannes.thumshirn@men.de>");
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("MEN 16z135 High Speed UART");
 MODULE_ALIAS("mcb:16z135");
+MODULE_IMPORT_NS(MCB);
diff --git a/drivers/uio/uio_dmem_genirq.c b/drivers/uio/uio_dmem_genirq.c
index ebcf1434e296..81c88f7bbbcb 100644
--- a/drivers/uio/uio_dmem_genirq.c
+++ b/drivers/uio/uio_dmem_genirq.c
@@ -151,8 +151,6 @@ static int uio_dmem_genirq_probe(struct platform_device *pdev)
 	int i;
 
 	if (pdev->dev.of_node) {
-		int irq;
-
 		/* alloc uioinfo for one device */
 		uioinfo = kzalloc(sizeof(*uioinfo), GFP_KERNEL);
 		if (!uioinfo) {
@@ -163,13 +161,6 @@ static int uio_dmem_genirq_probe(struct platform_device *pdev)
 		uioinfo->name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%pOFn",
 					       pdev->dev.of_node);
 		uioinfo->version = "devicetree";
-
-		/* Multiple IRQs are not supported */
-		irq = platform_get_irq(pdev, 0);
-		if (irq == -ENXIO)
-			uioinfo->irq = UIO_IRQ_NONE;
-		else
-			uioinfo->irq = irq;
 	}
 
 	if (!uioinfo || !uioinfo->name || !uioinfo->version) {
@@ -199,8 +190,11 @@ static int uio_dmem_genirq_probe(struct platform_device *pdev)
 	mutex_init(&priv->alloc_lock);
 
 	if (!uioinfo->irq) {
+		/* Multiple IRQs are not supported */
 		ret = platform_get_irq(pdev, 0);
-		if (ret < 0)
+		if (ret == -ENXIO && pdev->dev.of_node)
+			ret = UIO_IRQ_NONE;
+		else if (ret < 0)
 			goto bad1;
 		uioinfo->irq = ret;
 	}
diff --git a/drivers/w1/masters/sgi_w1.c b/drivers/w1/masters/sgi_w1.c
index 1b2d96b945be..e8c7fa68d3cc 100644
--- a/drivers/w1/masters/sgi_w1.c
+++ b/drivers/w1/masters/sgi_w1.c
@@ -77,15 +77,13 @@ static int sgi_w1_probe(struct platform_device *pdev)
 {
 	struct sgi_w1_device *sdev;
 	struct sgi_w1_platform_data *pdata;
-	struct resource *res;
 
 	sdev = devm_kzalloc(&pdev->dev, sizeof(struct sgi_w1_device),
 			    GFP_KERNEL);
 	if (!sdev)
 		return -ENOMEM;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	sdev->mcr = devm_ioremap_resource(&pdev->dev, res);
+	sdev->mcr = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(sdev->mcr))
 		return PTR_ERR(sdev->mcr);
 
diff --git a/drivers/w1/slaves/Kconfig b/drivers/w1/slaves/Kconfig
index b7847636501d..687753889c34 100644
--- a/drivers/w1/slaves/Kconfig
+++ b/drivers/w1/slaves/Kconfig
@@ -74,6 +74,14 @@ config W1_SLAVE_DS2805
           organized as 7 pages of 16 bytes each with 64bit
           unique number. Requires OverDrive Speed to talk to.
 
+config W1_SLAVE_DS2430
+	tristate "256b EEPROM family support (DS2430)"
+	help
+	  Say Y here if you want to use a 1-wire 256bit EEPROM
+	  family device (DS2430).
+	  This EEPROM is organized as one page of 32 bytes for random
+	  access.
+
 config W1_SLAVE_DS2431
 	tristate "1kb EEPROM family support (DS2431)"
 	help
diff --git a/drivers/w1/slaves/Makefile b/drivers/w1/slaves/Makefile
index 8e9655eaa478..278bcf2a9bfd 100644
--- a/drivers/w1/slaves/Makefile
+++ b/drivers/w1/slaves/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_W1_SLAVE_DS2408)	+= w1_ds2408.o
 obj-$(CONFIG_W1_SLAVE_DS2413)	+= w1_ds2413.o
 obj-$(CONFIG_W1_SLAVE_DS2406)	+= w1_ds2406.o
 obj-$(CONFIG_W1_SLAVE_DS2423)	+= w1_ds2423.o
+obj-$(CONFIG_W1_SLAVE_DS2430)	+= w1_ds2430.o
 obj-$(CONFIG_W1_SLAVE_DS2431)	+= w1_ds2431.o
 obj-$(CONFIG_W1_SLAVE_DS2805)	+= w1_ds2805.o
 obj-$(CONFIG_W1_SLAVE_DS2433)	+= w1_ds2433.o
diff --git a/drivers/w1/slaves/w1_ds2430.c b/drivers/w1/slaves/w1_ds2430.c
new file mode 100644
index 000000000000..6fb0563fb2ae
--- /dev/null
+++ b/drivers/w1/slaves/w1_ds2430.c
@@ -0,0 +1,295 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * w1_ds2430.c - w1 family 14 (DS2430) driver
+ **
+ * Copyright (c) 2019 Angelo Dureghello <angelo.dureghello@timesys.com>
+ *
+ * Cloned and modified from ds2431
+ * Copyright (c) 2008 Bernhard Weirich <bernhard.weirich@riedel.net>
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/device.h>
+#include <linux/types.h>
+#include <linux/delay.h>
+
+#include <linux/w1.h>
+
+#define W1_EEPROM_DS2430	0x14
+
+#define W1_F14_EEPROM_SIZE	32
+#define W1_F14_PAGE_COUNT	1
+#define W1_F14_PAGE_BITS	5
+#define W1_F14_PAGE_SIZE	(1 << W1_F14_PAGE_BITS)
+#define W1_F14_PAGE_MASK	0x1F
+
+#define W1_F14_SCRATCH_BITS	5
+#define W1_F14_SCRATCH_SIZE	(1 << W1_F14_SCRATCH_BITS)
+#define W1_F14_SCRATCH_MASK	(W1_F14_SCRATCH_SIZE-1)
+
+#define W1_F14_READ_EEPROM	0xF0
+#define W1_F14_WRITE_SCRATCH	0x0F
+#define W1_F14_READ_SCRATCH	0xAA
+#define W1_F14_COPY_SCRATCH	0x55
+#define W1_F14_VALIDATION_KEY	0xa5
+
+#define W1_F14_TPROG_MS		11
+#define W1_F14_READ_RETRIES	10
+#define W1_F14_READ_MAXLEN	W1_F14_SCRATCH_SIZE
+
+/*
+ * Check the file size bounds and adjusts count as needed.
+ * This would not be needed if the file size didn't reset to 0 after a write.
+ */
+static inline size_t w1_f14_fix_count(loff_t off, size_t count, size_t size)
+{
+	if (off > size)
+		return 0;
+
+	if ((off + count) > size)
+		return size - off;
+
+	return count;
+}
+
+/*
+ * Read a block from W1 ROM two times and compares the results.
+ * If they are equal they are returned, otherwise the read
+ * is repeated W1_F14_READ_RETRIES times.
+ *
+ * count must not exceed W1_F14_READ_MAXLEN.
+ */
+static int w1_f14_readblock(struct w1_slave *sl, int off, int count, char *buf)
+{
+	u8 wrbuf[2];
+	u8 cmp[W1_F14_READ_MAXLEN];
+	int tries = W1_F14_READ_RETRIES;
+
+	do {
+		wrbuf[0] = W1_F14_READ_EEPROM;
+		wrbuf[1] = off & 0xff;
+
+		if (w1_reset_select_slave(sl))
+			return -1;
+
+		w1_write_block(sl->master, wrbuf, 2);
+		w1_read_block(sl->master, buf, count);
+
+		if (w1_reset_select_slave(sl))
+			return -1;
+
+		w1_write_block(sl->master, wrbuf, 2);
+		w1_read_block(sl->master, cmp, count);
+
+		if (!memcmp(cmp, buf, count))
+			return 0;
+	} while (--tries);
+
+	dev_err(&sl->dev, "proof reading failed %d times\n",
+			W1_F14_READ_RETRIES);
+
+	return -1;
+}
+
+static ssize_t eeprom_read(struct file *filp, struct kobject *kobj,
+			   struct bin_attribute *bin_attr, char *buf,
+			   loff_t off, size_t count)
+{
+	struct w1_slave *sl = kobj_to_w1_slave(kobj);
+	int todo = count;
+
+	count = w1_f14_fix_count(off, count, W1_F14_EEPROM_SIZE);
+	if (count == 0)
+		return 0;
+
+	mutex_lock(&sl->master->bus_mutex);
+
+	/* read directly from the EEPROM in chunks of W1_F14_READ_MAXLEN */
+	while (todo > 0) {
+		int block_read;
+
+		if (todo >= W1_F14_READ_MAXLEN)
+			block_read = W1_F14_READ_MAXLEN;
+		else
+			block_read = todo;
+
+		if (w1_f14_readblock(sl, off, block_read, buf) < 0)
+			count = -EIO;
+
+		todo -= W1_F14_READ_MAXLEN;
+		buf += W1_F14_READ_MAXLEN;
+		off += W1_F14_READ_MAXLEN;
+	}
+
+	mutex_unlock(&sl->master->bus_mutex);
+
+	return count;
+}
+
+/*
+ * Writes to the scratchpad and reads it back for verification.
+ * Then copies the scratchpad to EEPROM.
+ * The data must be aligned at W1_F14_SCRATCH_SIZE bytes and
+ * must be W1_F14_SCRATCH_SIZE bytes long.
+ * The master must be locked.
+ *
+ * @param sl	The slave structure
+ * @param addr	Address for the write
+ * @param len   length must be <= (W1_F14_PAGE_SIZE - (addr & W1_F14_PAGE_MASK))
+ * @param data	The data to write
+ * @return	0=Success -1=failure
+ */
+static int w1_f14_write(struct w1_slave *sl, int addr, int len, const u8 *data)
+{
+	int tries = W1_F14_READ_RETRIES;
+	u8 wrbuf[2];
+	u8 rdbuf[W1_F14_SCRATCH_SIZE + 3];
+
+retry:
+
+	/* Write the data to the scratchpad */
+	if (w1_reset_select_slave(sl))
+		return -1;
+
+	wrbuf[0] = W1_F14_WRITE_SCRATCH;
+	wrbuf[1] = addr & 0xff;
+
+	w1_write_block(sl->master, wrbuf, 2);
+	w1_write_block(sl->master, data, len);
+
+	/* Read the scratchpad and verify */
+	if (w1_reset_select_slave(sl))
+		return -1;
+
+	w1_write_8(sl->master, W1_F14_READ_SCRATCH);
+	w1_read_block(sl->master, rdbuf, len + 2);
+
+	/*
+	 * Compare what was read against the data written
+	 * Note: on read scratchpad, device returns 2 bulk 0xff bytes,
+	 * to be discarded.
+	 */
+	if ((memcmp(data, &rdbuf[2], len) != 0)) {
+
+		if (--tries)
+			goto retry;
+
+		dev_err(&sl->dev,
+			"could not write to eeprom, scratchpad compare failed %d times\n",
+			W1_F14_READ_RETRIES);
+
+		return -1;
+	}
+
+	/* Copy the scratchpad to EEPROM */
+	if (w1_reset_select_slave(sl))
+		return -1;
+
+	wrbuf[0] = W1_F14_COPY_SCRATCH;
+	wrbuf[1] = W1_F14_VALIDATION_KEY;
+	w1_write_block(sl->master, wrbuf, 2);
+
+	/* Sleep for tprog ms to wait for the write to complete */
+	msleep(W1_F14_TPROG_MS);
+
+	/* Reset the bus to wake up the EEPROM  */
+	w1_reset_bus(sl->master);
+
+	return 0;
+}
+
+static ssize_t eeprom_write(struct file *filp, struct kobject *kobj,
+			    struct bin_attribute *bin_attr, char *buf,
+			    loff_t off, size_t count)
+{
+	struct w1_slave *sl = kobj_to_w1_slave(kobj);
+	int addr, len;
+	int copy;
+
+	count = w1_f14_fix_count(off, count, W1_F14_EEPROM_SIZE);
+	if (count == 0)
+		return 0;
+
+	mutex_lock(&sl->master->bus_mutex);
+
+	/* Can only write data in blocks of the size of the scratchpad */
+	addr = off;
+	len = count;
+	while (len > 0) {
+
+		/* if len too short or addr not aligned */
+		if (len < W1_F14_SCRATCH_SIZE || addr & W1_F14_SCRATCH_MASK) {
+			char tmp[W1_F14_SCRATCH_SIZE];
+
+			/* read the block and update the parts to be written */
+			if (w1_f14_readblock(sl, addr & ~W1_F14_SCRATCH_MASK,
+					W1_F14_SCRATCH_SIZE, tmp)) {
+				count = -EIO;
+				goto out_up;
+			}
+
+			/* copy at most to the boundary of the PAGE or len */
+			copy = W1_F14_SCRATCH_SIZE -
+				(addr & W1_F14_SCRATCH_MASK);
+
+			if (copy > len)
+				copy = len;
+
+			memcpy(&tmp[addr & W1_F14_SCRATCH_MASK], buf, copy);
+			if (w1_f14_write(sl, addr & ~W1_F14_SCRATCH_MASK,
+					W1_F14_SCRATCH_SIZE, tmp) < 0) {
+				count = -EIO;
+				goto out_up;
+			}
+		} else {
+
+			copy = W1_F14_SCRATCH_SIZE;
+			if (w1_f14_write(sl, addr, copy, buf) < 0) {
+				count = -EIO;
+				goto out_up;
+			}
+		}
+		buf += copy;
+		addr += copy;
+		len -= copy;
+	}
+
+out_up:
+	mutex_unlock(&sl->master->bus_mutex);
+
+	return count;
+}
+
+static BIN_ATTR_RW(eeprom, W1_F14_EEPROM_SIZE);
+
+static struct bin_attribute *w1_f14_bin_attrs[] = {
+	&bin_attr_eeprom,
+	NULL,
+};
+
+static const struct attribute_group w1_f14_group = {
+	.bin_attrs = w1_f14_bin_attrs,
+};
+
+static const struct attribute_group *w1_f14_groups[] = {
+	&w1_f14_group,
+	NULL,
+};
+
+static struct w1_family_ops w1_f14_fops = {
+	.groups	= w1_f14_groups,
+};
+
+static struct w1_family w1_family_14 = {
+	.fid = W1_EEPROM_DS2430,
+	.fops = &w1_f14_fops,
+};
+module_w1_family(w1_family_14);
+
+MODULE_AUTHOR("Angelo Dureghello <angelo.dureghello@timesys.com>");
+MODULE_DESCRIPTION("w1 family 14 driver for DS2430, 256kb EEPROM");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("w1-family-" __stringify(W1_EEPROM_DS2430));
diff --git a/drivers/watchdog/menz69_wdt.c b/drivers/watchdog/menz69_wdt.c
index ed18238c5407..8973f98bc6a5 100644
--- a/drivers/watchdog/menz69_wdt.c
+++ b/drivers/watchdog/menz69_wdt.c
@@ -168,3 +168,4 @@ module_mcb_driver(men_z069_driver);
 MODULE_AUTHOR("Johannes Thumshirn <jth@kernel.org>");
 MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("mcb:16z069");
+MODULE_IMPORT_NS(MCB);