Merge tag 'char-misc-5.3-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 "large" pull request for char and misc and other assorted
  smaller driver subsystems for 5.3-rc1.

  It seems that this tree is becoming the funnel point of lots of
  smaller driver subsystems, which is fine for me, but that's why it is
  getting larger over time and does not just contain stuff under
  drivers/char/ and drivers/misc.

  Lots of small updates all over the place here from different driver
  subsystems:
   - habana driver updates
   - coresight driver updates
   - documentation file movements and updates
   - Android binder fixes and updates
   - extcon driver updates
   - google firmware driver updates
   - fsi driver updates
   - smaller misc and char driver updates
   - soundwire driver updates
   - nvmem driver updates
   - w1 driver fixes

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

* tag 'char-misc-5.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc: (188 commits)
  coresight: Do not default to CPU0 for missing CPU phandle
  dt-bindings: coresight: Change CPU phandle to required property
  ocxl: Allow contexts to be attached with a NULL mm
  fsi: sbefifo: Don't fail operations when in SBE IPL state
  coresight: tmc: Smatch: Fix potential NULL pointer dereference
  coresight: etm3x: Smatch: Fix potential NULL pointer dereference
  coresight: Potential uninitialized variable in probe()
  coresight: etb10: Do not call smp_processor_id from preemptible
  coresight: tmc-etf: Do not call smp_processor_id from preemptible
  coresight: tmc-etr: alloc_perf_buf: Do not call smp_processor_id from preemptible
  coresight: tmc-etr: Do not call smp_processor_id() from preemptible
  docs: misc-devices: convert files without extension to ReST
  fpga: dfl: fme: align PR buffer size per PR datawidth
  fpga: dfl: fme: remove copy_to_user() in ioctl for PR
  fpga: dfl-fme-mgr: fix FME_PR_INTFC_ID register address.
  intel_th: msu: Start read iterator from a non-empty window
  intel_th: msu: Split sgt array and pointer in multiwindow mode
  intel_th: msu: Support multipage blocks
  intel_th: pci: Add Ice Lake NNPI support
  intel_th: msu: Fix single mode with disabled IOMMU
  ...

122 files changed, 4767 insertions, 2246 deletions

diff --git a/drivers/acpi/acpi_amba.c b/drivers/acpi/acpi_amba.c
index 8159f0a669b8..49b781a9cd97 100644
--- a/drivers/acpi/acpi_amba.c
+++ b/drivers/acpi/acpi_amba.c
@@ -21,6 +21,15 @@
 
 static const struct acpi_device_id amba_id_list[] = {
 	{"ARMH0061", 0}, /* PL061 GPIO Device */
+	{"ARMHC500", 0}, /* ARM CoreSight ETM4x */
+	{"ARMHC501", 0}, /* ARM CoreSight ETR */
+	{"ARMHC502", 0}, /* ARM CoreSight STM */
+	{"ARMHC503", 0}, /* ARM CoreSight Debug */
+	{"ARMHC979", 0}, /* ARM CoreSight TPIU */
+	{"ARMHC97C", 0}, /* ARM CoreSight SoC-400 TMC, SoC-600 ETF/ETB */
+	{"ARMHC98D", 0}, /* ARM CoreSight Dynamic Replicator */
+	{"ARMHC9CA", 0}, /* ARM CoreSight CATU */
+	{"ARMHC9FF", 0}, /* ARM CoreSight Dynamic Funnel */
 	{"", 0},
 };
 
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index bc26b5511f0a..38a59a630cd4 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -2059,10 +2059,9 @@ static size_t binder_get_object(struct binder_proc *proc,
 
 	read_size = min_t(size_t, sizeof(*object), buffer->data_size - offset);
 	if (offset > buffer->data_size || read_size < sizeof(*hdr) ||
-	    !IS_ALIGNED(offset, sizeof(u32)))
+	    binder_alloc_copy_from_buffer(&proc->alloc, object, buffer,
+					  offset, read_size))
 		return 0;
-	binder_alloc_copy_from_buffer(&proc->alloc, object, buffer,
-				      offset, read_size);
 
 	/* Ok, now see if we read a complete object. */
 	hdr = &object->hdr;
@@ -2131,8 +2130,10 @@ static struct binder_buffer_object *binder_validate_ptr(
 		return NULL;
 
 	buffer_offset = start_offset + sizeof(binder_size_t) * index;
-	binder_alloc_copy_from_buffer(&proc->alloc, &object_offset,
-				      b, buffer_offset, sizeof(object_offset));
+	if (binder_alloc_copy_from_buffer(&proc->alloc, &object_offset,
+					  b, buffer_offset,
+					  sizeof(object_offset)))
+		return NULL;
 	object_size = binder_get_object(proc, b, object_offset, object);
 	if (!object_size || object->hdr.type != BINDER_TYPE_PTR)
 		return NULL;
@@ -2212,10 +2213,12 @@ static bool binder_validate_fixup(struct binder_proc *proc,
 			return false;
 		last_min_offset = last_bbo->parent_offset + sizeof(uintptr_t);
 		buffer_offset = objects_start_offset +
-			sizeof(binder_size_t) * last_bbo->parent,
-		binder_alloc_copy_from_buffer(&proc->alloc, &last_obj_offset,
-					      b, buffer_offset,
-					      sizeof(last_obj_offset));
+			sizeof(binder_size_t) * last_bbo->parent;
+		if (binder_alloc_copy_from_buffer(&proc->alloc,
+						  &last_obj_offset,
+						  b, buffer_offset,
+						  sizeof(last_obj_offset)))
+			return false;
 	}
 	return (fixup_offset >= last_min_offset);
 }
@@ -2301,15 +2304,15 @@ static void binder_transaction_buffer_release(struct binder_proc *proc,
 	for (buffer_offset = off_start_offset; buffer_offset < off_end_offset;
 	     buffer_offset += sizeof(binder_size_t)) {
 		struct binder_object_header *hdr;
-		size_t object_size;
+		size_t object_size = 0;
 		struct binder_object object;
 		binder_size_t object_offset;
 
-		binder_alloc_copy_from_buffer(&proc->alloc, &object_offset,
-					      buffer, buffer_offset,
-					      sizeof(object_offset));
-		object_size = binder_get_object(proc, buffer,
-						object_offset, &object);
+		if (!binder_alloc_copy_from_buffer(&proc->alloc, &object_offset,
+						   buffer, buffer_offset,
+						   sizeof(object_offset)))
+			object_size = binder_get_object(proc, buffer,
+							object_offset, &object);
 		if (object_size == 0) {
 			pr_err("transaction release %d bad object at offset %lld, size %zd\n",
 			       debug_id, (u64)object_offset, buffer->data_size);
@@ -2432,15 +2435,16 @@ static void binder_transaction_buffer_release(struct binder_proc *proc,
 			for (fd_index = 0; fd_index < fda->num_fds;
 			     fd_index++) {
 				u32 fd;
+				int err;
 				binder_size_t offset = fda_offset +
 					fd_index * sizeof(fd);
 
-				binder_alloc_copy_from_buffer(&proc->alloc,
-							      &fd,
-							      buffer,
-							      offset,
-							      sizeof(fd));
-				binder_deferred_fd_close(fd);
+				err = binder_alloc_copy_from_buffer(
+						&proc->alloc, &fd, buffer,
+						offset, sizeof(fd));
+				WARN_ON(err);
+				if (!err)
+					binder_deferred_fd_close(fd);
 			}
 		} break;
 		default:
@@ -2683,11 +2687,12 @@ static int binder_translate_fd_array(struct binder_fd_array_object *fda,
 		int ret;
 		binder_size_t offset = fda_offset + fdi * sizeof(fd);
 
-		binder_alloc_copy_from_buffer(&target_proc->alloc,
-					      &fd, t->buffer,
-					      offset, sizeof(fd));
-		ret = binder_translate_fd(fd, offset, t, thread,
-					  in_reply_to);
+		ret = binder_alloc_copy_from_buffer(&target_proc->alloc,
+						    &fd, t->buffer,
+						    offset, sizeof(fd));
+		if (!ret)
+			ret = binder_translate_fd(fd, offset, t, thread,
+						  in_reply_to);
 		if (ret < 0)
 			return ret;
 	}
@@ -2740,8 +2745,12 @@ static int binder_fixup_parent(struct binder_transaction *t,
 	}
 	buffer_offset = bp->parent_offset +
 			(uintptr_t)parent->buffer - (uintptr_t)b->user_data;
-	binder_alloc_copy_to_buffer(&target_proc->alloc, b, buffer_offset,
-				    &bp->buffer, sizeof(bp->buffer));
+	if (binder_alloc_copy_to_buffer(&target_proc->alloc, b, buffer_offset,
+					&bp->buffer, sizeof(bp->buffer))) {
+		binder_user_error("%d:%d got transaction with invalid parent offset\n",
+				  proc->pid, thread->pid);
+		return -EINVAL;
+	}
 
 	return 0;
 }
@@ -3160,15 +3169,20 @@ static void binder_transaction(struct binder_proc *proc,
 		goto err_binder_alloc_buf_failed;
 	}
 	if (secctx) {
+		int err;
 		size_t buf_offset = ALIGN(tr->data_size, sizeof(void *)) +
 				    ALIGN(tr->offsets_size, sizeof(void *)) +
 				    ALIGN(extra_buffers_size, sizeof(void *)) -
 				    ALIGN(secctx_sz, sizeof(u64));
 
 		t->security_ctx = (uintptr_t)t->buffer->user_data + buf_offset;
-		binder_alloc_copy_to_buffer(&target_proc->alloc,
-					    t->buffer, buf_offset,
-					    secctx, secctx_sz);
+		err = binder_alloc_copy_to_buffer(&target_proc->alloc,
+						  t->buffer, buf_offset,
+						  secctx, secctx_sz);
+		if (err) {
+			t->security_ctx = 0;
+			WARN_ON(1);
+		}
 		security_release_secctx(secctx, secctx_sz);
 		secctx = NULL;
 	}
@@ -3234,11 +3248,16 @@ static void binder_transaction(struct binder_proc *proc,
 		struct binder_object object;
 		binder_size_t object_offset;
 
-		binder_alloc_copy_from_buffer(&target_proc->alloc,
-					      &object_offset,
-					      t->buffer,
-					      buffer_offset,
-					      sizeof(object_offset));
+		if (binder_alloc_copy_from_buffer(&target_proc->alloc,
+						  &object_offset,
+						  t->buffer,
+						  buffer_offset,
+						  sizeof(object_offset))) {
+			return_error = BR_FAILED_REPLY;
+			return_error_param = -EINVAL;
+			return_error_line = __LINE__;
+			goto err_bad_offset;
+		}
 		object_size = binder_get_object(target_proc, t->buffer,
 						object_offset, &object);
 		if (object_size == 0 || object_offset < off_min) {
@@ -3262,15 +3281,17 @@ static void binder_transaction(struct binder_proc *proc,
 
 			fp = to_flat_binder_object(hdr);
 			ret = binder_translate_binder(fp, t, thread);
-			if (ret < 0) {
+
+			if (ret < 0 ||
+			    binder_alloc_copy_to_buffer(&target_proc->alloc,
+							t->buffer,
+							object_offset,
+							fp, sizeof(*fp))) {
 				return_error = BR_FAILED_REPLY;
 				return_error_param = ret;
 				return_error_line = __LINE__;
 				goto err_translate_failed;
 			}
-			binder_alloc_copy_to_buffer(&target_proc->alloc,
-						    t->buffer, object_offset,
-						    fp, sizeof(*fp));
 		} break;
 		case BINDER_TYPE_HANDLE:
 		case BINDER_TYPE_WEAK_HANDLE: {
@@ -3278,15 +3299,16 @@ static void binder_transaction(struct binder_proc *proc,
 
 			fp = to_flat_binder_object(hdr);
 			ret = binder_translate_handle(fp, t, thread);
-			if (ret < 0) {
+			if (ret < 0 ||
+			    binder_alloc_copy_to_buffer(&target_proc->alloc,
+							t->buffer,
+							object_offset,
+							fp, sizeof(*fp))) {
 				return_error = BR_FAILED_REPLY;
 				return_error_param = ret;
 				return_error_line = __LINE__;
 				goto err_translate_failed;
 			}
-			binder_alloc_copy_to_buffer(&target_proc->alloc,
-						    t->buffer, object_offset,
-						    fp, sizeof(*fp));
 		} break;
 
 		case BINDER_TYPE_FD: {
@@ -3296,16 +3318,17 @@ static void binder_transaction(struct binder_proc *proc,
 			int ret = binder_translate_fd(fp->fd, fd_offset, t,
 						      thread, in_reply_to);
 
-			if (ret < 0) {
+			fp->pad_binder = 0;
+			if (ret < 0 ||
+			    binder_alloc_copy_to_buffer(&target_proc->alloc,
+							t->buffer,
+							object_offset,
+							fp, sizeof(*fp))) {
 				return_error = BR_FAILED_REPLY;
 				return_error_param = ret;
 				return_error_line = __LINE__;
 				goto err_translate_failed;
 			}
-			fp->pad_binder = 0;
-			binder_alloc_copy_to_buffer(&target_proc->alloc,
-						    t->buffer, object_offset,
-						    fp, sizeof(*fp));
 		} break;
 		case BINDER_TYPE_FDA: {
 			struct binder_object ptr_object;
@@ -3393,15 +3416,16 @@ static void binder_transaction(struct binder_proc *proc,
 						  num_valid,
 						  last_fixup_obj_off,
 						  last_fixup_min_off);
-			if (ret < 0) {
+			if (ret < 0 ||
+			    binder_alloc_copy_to_buffer(&target_proc->alloc,
+							t->buffer,
+							object_offset,
+							bp, sizeof(*bp))) {
 				return_error = BR_FAILED_REPLY;
 				return_error_param = ret;
 				return_error_line = __LINE__;
 				goto err_translate_failed;
 			}
-			binder_alloc_copy_to_buffer(&target_proc->alloc,
-						    t->buffer, object_offset,
-						    bp, sizeof(*bp));
 			last_fixup_obj_off = object_offset;
 			last_fixup_min_off = 0;
 		} break;
@@ -4140,20 +4164,27 @@ static int binder_apply_fd_fixups(struct binder_proc *proc,
 		trace_binder_transaction_fd_recv(t, fd, fixup->offset);
 		fd_install(fd, fixup->file);
 		fixup->file = NULL;
-		binder_alloc_copy_to_buffer(&proc->alloc, t->buffer,
-					    fixup->offset, &fd,
-					    sizeof(u32));
+		if (binder_alloc_copy_to_buffer(&proc->alloc, t->buffer,
+						fixup->offset, &fd,
+						sizeof(u32))) {
+			ret = -EINVAL;
+			break;
+		}
 	}
 	list_for_each_entry_safe(fixup, tmp, &t->fd_fixups, fixup_entry) {
 		if (fixup->file) {
 			fput(fixup->file);
 		} else if (ret) {
 			u32 fd;
-
-			binder_alloc_copy_from_buffer(&proc->alloc, &fd,
-						      t->buffer, fixup->offset,
-						      sizeof(fd));
-			binder_deferred_fd_close(fd);
+			int err;
+
+			err = binder_alloc_copy_from_buffer(&proc->alloc, &fd,
+							    t->buffer,
+							    fixup->offset,
+							    sizeof(fd));
+			WARN_ON(err);
+			if (!err)
+				binder_deferred_fd_close(fd);
 		}
 		list_del(&fixup->fixup_entry);
 		kfree(fixup);
@@ -4268,6 +4299,8 @@ retry:
 		case BINDER_WORK_TRANSACTION_COMPLETE: {
 			binder_inner_proc_unlock(proc);
 			cmd = BR_TRANSACTION_COMPLETE;
+			kfree(w);
+			binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE);
 			if (put_user(cmd, (uint32_t __user *)ptr))
 				return -EFAULT;
 			ptr += sizeof(uint32_t);
@@ -4276,8 +4309,6 @@ retry:
 			binder_debug(BINDER_DEBUG_TRANSACTION_COMPLETE,
 				     "%d:%d BR_TRANSACTION_COMPLETE\n",
 				     proc->pid, thread->pid);
-			kfree(w);
-			binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE);
 		} break;
 		case BINDER_WORK_NODE: {
 			struct binder_node *node = container_of(w, struct binder_node, work);
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index ce5603c2291c..6d79a1b0d446 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -1119,15 +1119,16 @@ binder_alloc_copy_user_to_buffer(struct binder_alloc *alloc,
 	return 0;
 }
 
-static void binder_alloc_do_buffer_copy(struct binder_alloc *alloc,
-					bool to_buffer,
-					struct binder_buffer *buffer,
-					binder_size_t buffer_offset,
-					void *ptr,
-					size_t bytes)
+static int binder_alloc_do_buffer_copy(struct binder_alloc *alloc,
+				       bool to_buffer,
+				       struct binder_buffer *buffer,
+				       binder_size_t buffer_offset,
+				       void *ptr,
+				       size_t bytes)
 {
 	/* All copies must be 32-bit aligned and 32-bit size */
-	BUG_ON(!check_buffer(alloc, buffer, buffer_offset, bytes));
+	if (!check_buffer(alloc, buffer, buffer_offset, bytes))
+		return -EINVAL;
 
 	while (bytes) {
 		unsigned long size;
@@ -1155,25 +1156,26 @@ static void binder_alloc_do_buffer_copy(struct binder_alloc *alloc,
 		ptr = ptr + size;
 		buffer_offset += size;
 	}
+	return 0;
 }
 
-void binder_alloc_copy_to_buffer(struct binder_alloc *alloc,
-				 struct binder_buffer *buffer,
-				 binder_size_t buffer_offset,
-				 void *src,
-				 size_t bytes)
+int binder_alloc_copy_to_buffer(struct binder_alloc *alloc,
+				struct binder_buffer *buffer,
+				binder_size_t buffer_offset,
+				void *src,
+				size_t bytes)
 {
-	binder_alloc_do_buffer_copy(alloc, true, buffer, buffer_offset,
-				    src, bytes);
+	return binder_alloc_do_buffer_copy(alloc, true, buffer, buffer_offset,
+					   src, bytes);
 }
 
-void binder_alloc_copy_from_buffer(struct binder_alloc *alloc,
-				   void *dest,
-				   struct binder_buffer *buffer,
-				   binder_size_t buffer_offset,
-				   size_t bytes)
+int binder_alloc_copy_from_buffer(struct binder_alloc *alloc,
+				  void *dest,
+				  struct binder_buffer *buffer,
+				  binder_size_t buffer_offset,
+				  size_t bytes)
 {
-	binder_alloc_do_buffer_copy(alloc, false, buffer, buffer_offset,
-				    dest, bytes);
+	return binder_alloc_do_buffer_copy(alloc, false, buffer, buffer_offset,
+					   dest, bytes);
 }
 
diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h
index 71bfa95f8e09..db9c1b984695 100644
--- a/drivers/android/binder_alloc.h
+++ b/drivers/android/binder_alloc.h
@@ -159,17 +159,17 @@ binder_alloc_copy_user_to_buffer(struct binder_alloc *alloc,
 				 const void __user *from,
 				 size_t bytes);
 
-void binder_alloc_copy_to_buffer(struct binder_alloc *alloc,
-				 struct binder_buffer *buffer,
-				 binder_size_t buffer_offset,
-				 void *src,
-				 size_t bytes);
-
-void binder_alloc_copy_from_buffer(struct binder_alloc *alloc,
-				   void *dest,
-				   struct binder_buffer *buffer,
-				   binder_size_t buffer_offset,
-				   size_t bytes);
+int binder_alloc_copy_to_buffer(struct binder_alloc *alloc,
+				struct binder_buffer *buffer,
+				binder_size_t buffer_offset,
+				void *src,
+				size_t bytes);
+
+int binder_alloc_copy_from_buffer(struct binder_alloc *alloc,
+				  void *dest,
+				  struct binder_buffer *buffer,
+				  binder_size_t buffer_offset,
+				  size_t bytes);
 
 #endif /* _LINUX_BINDER_ALLOC_H */
 
diff --git a/drivers/char/bsr.c b/drivers/char/bsr.c
index 167e7370d43a..e5e5333f302d 100644
--- a/drivers/char/bsr.c
+++ b/drivers/char/bsr.c
@@ -134,7 +134,7 @@ static int bsr_mmap(struct file *filp, struct vm_area_struct *vma)
 	return 0;
 }
 
-static int bsr_open(struct inode * inode, struct file * filp)
+static int bsr_open(struct inode *inode, struct file *filp)
 {
 	struct cdev *cdev = inode->i_cdev;
 	struct bsr_dev *dev = container_of(cdev, struct bsr_dev, bsr_cdev);
@@ -309,7 +309,8 @@ static int __init bsr_init(void)
 		goto out_err_2;
 	}
 
-	if ((ret = bsr_create_devs(np)) < 0) {
+	ret = bsr_create_devs(np);
+	if (ret < 0) {
 		np = NULL;
 		goto out_err_3;
 	}
diff --git a/drivers/char/misc.c b/drivers/char/misc.c
index 53cfe574d8d4..f6a147427029 100644
--- a/drivers/char/misc.c
+++ b/drivers/char/misc.c
@@ -226,6 +226,7 @@ int misc_register(struct miscdevice *misc)
 	mutex_unlock(&misc_mtx);
 	return err;
 }
+EXPORT_SYMBOL(misc_register);
 
 /**
  *	misc_deregister - unregister a miscellaneous device
@@ -249,8 +250,6 @@ void misc_deregister(struct miscdevice *misc)
 		clear_bit(i, misc_minors);
 	mutex_unlock(&misc_mtx);
 }
-
-EXPORT_SYMBOL(misc_register);
 EXPORT_SYMBOL(misc_deregister);
 
 static char *misc_devnode(struct device *dev, umode_t *mode)
diff --git a/drivers/counter/104-quad-8.c b/drivers/counter/104-quad-8.c
index 4fa2931dcb7b..00b113f4b958 100644
--- a/drivers/counter/104-quad-8.c
+++ b/drivers/counter/104-quad-8.c
@@ -833,7 +833,7 @@ static int quad8_action_get(struct counter_device *counter,
 	return 0;
 }
 
-const struct counter_ops quad8_ops = {
+static const struct counter_ops quad8_ops = {
 	.signal_read = quad8_signal_read,
 	.count_read = quad8_count_read,
 	.count_write = quad8_count_write,
diff --git a/drivers/extcon/Kconfig b/drivers/extcon/Kconfig
index 6f5af4196b8d..fa1804460e8c 100644
--- a/drivers/extcon/Kconfig
+++ b/drivers/extcon/Kconfig
@@ -37,6 +37,18 @@ config EXTCON_AXP288
 	  Say Y here to enable support for USB peripheral detection
 	  and USB MUX switching by X-Power AXP288 PMIC.
 
+config EXTCON_FSA9480
+	tristate "FSA9480 EXTCON Support"
+	depends on INPUT && I2C
+	select IRQ_DOMAIN
+	select REGMAP_I2C
+	help
+	  If you say yes here you get support for the Fairchild Semiconductor
+	  FSA9480 microUSB switch and accessory detector chip. The FSA9480 is a USB
+	  port accessory detector and switch. The FSA9480 is fully controlled using
+	  I2C and enables USB data, stereo and mono audio, video, microphone
+	  and UART data to use a common connector port.
+
 config EXTCON_GPIO
 	tristate "GPIO extcon support"
 	depends on GPIOLIB || COMPILE_TEST
diff --git a/drivers/extcon/Makefile b/drivers/extcon/Makefile
index d3941a735df3..52096fd8a216 100644
--- a/drivers/extcon/Makefile
+++ b/drivers/extcon/Makefile
@@ -8,6 +8,7 @@ extcon-core-objs		+= extcon.o devres.o
 obj-$(CONFIG_EXTCON_ADC_JACK)	+= extcon-adc-jack.o
 obj-$(CONFIG_EXTCON_ARIZONA)	+= extcon-arizona.o
 obj-$(CONFIG_EXTCON_AXP288)	+= extcon-axp288.o
+obj-$(CONFIG_EXTCON_FSA9480)	+= extcon-fsa9480.o
 obj-$(CONFIG_EXTCON_GPIO)	+= extcon-gpio.o
 obj-$(CONFIG_EXTCON_INTEL_INT3496) += extcon-intel-int3496.o
 obj-$(CONFIG_EXTCON_INTEL_CHT_WC) += extcon-intel-cht-wc.o
diff --git a/drivers/extcon/extcon-arizona.c b/drivers/extcon/extcon-arizona.c
index bb6434726c7a..7e9f4c9ee87d 100644
--- a/drivers/extcon/extcon-arizona.c
+++ b/drivers/extcon/extcon-arizona.c
@@ -326,10 +326,12 @@ static void arizona_start_mic(struct arizona_extcon_info *info)
 
 	arizona_extcon_pulse_micbias(info);
 
-	regmap_update_bits_check(arizona->regmap, ARIZONA_MIC_DETECT_1,
-				 ARIZONA_MICD_ENA, ARIZONA_MICD_ENA,
-				 &change);
-	if (!change) {
+	ret = regmap_update_bits_check(arizona->regmap, ARIZONA_MIC_DETECT_1,
+				       ARIZONA_MICD_ENA, ARIZONA_MICD_ENA,
+				       &change);
+	if (ret < 0) {
+		dev_err(arizona->dev, "Failed to enable micd: %d\n", ret);
+	} else if (!change) {
 		regulator_disable(info->micvdd);
 		pm_runtime_put_autosuspend(info->dev);
 	}
@@ -341,12 +343,14 @@ static void arizona_stop_mic(struct arizona_extcon_info *info)
 	const char *widget = arizona_extcon_get_micbias(info);
 	struct snd_soc_dapm_context *dapm = arizona->dapm;
 	struct snd_soc_component *component = snd_soc_dapm_to_component(dapm);
-	bool change;
+	bool change = false;
 	int ret;
 
-	regmap_update_bits_check(arizona->regmap, ARIZONA_MIC_DETECT_1,
-				 ARIZONA_MICD_ENA, 0,
-				 &change);
+	ret = regmap_update_bits_check(arizona->regmap, ARIZONA_MIC_DETECT_1,
+				       ARIZONA_MICD_ENA, 0,
+				       &change);
+	if (ret < 0)
+		dev_err(arizona->dev, "Failed to disable micd: %d\n", ret);
 
 	ret = snd_soc_component_disable_pin(component, widget);
 	if (ret != 0)
@@ -1718,12 +1722,15 @@ static int arizona_extcon_remove(struct platform_device *pdev)
 	struct arizona *arizona = info->arizona;
 	int jack_irq_rise, jack_irq_fall;
 	bool change;
+	int ret;
 
-	regmap_update_bits_check(arizona->regmap, ARIZONA_MIC_DETECT_1,
-				 ARIZONA_MICD_ENA, 0,
-				 &change);
-
-	if (change) {
+	ret = regmap_update_bits_check(arizona->regmap, ARIZONA_MIC_DETECT_1,
+				       ARIZONA_MICD_ENA, 0,
+				       &change);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to disable micd on remove: %d\n",
+			ret);
+	} else if (change) {
 		regulator_disable(info->micvdd);
 		pm_runtime_put(info->dev);
 	}
diff --git a/drivers/extcon/extcon-fsa9480.c b/drivers/extcon/extcon-fsa9480.c
new file mode 100644
index 000000000000..350fb34abfa0
--- /dev/null
+++ b/drivers/extcon/extcon-fsa9480.c
@@ -0,0 +1,395 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * extcon-fsa9480.c - Fairchild Semiconductor FSA9480 extcon driver
+ *
+ * Copyright (c) 2019 Tomasz Figa <tomasz.figa@gmail.com>
+ *
+ * Loosely based on old fsa9480 misc-device driver.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/i2c.h>
+#include <linux/slab.h>
+#include <linux/bitops.h>
+#include <linux/interrupt.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/kobject.h>
+#include <linux/extcon-provider.h>
+#include <linux/irqdomain.h>
+#include <linux/regmap.h>
+
+/* FSA9480 I2C registers */
+#define FSA9480_REG_DEVID               0x01
+#define FSA9480_REG_CTRL                0x02
+#define FSA9480_REG_INT1                0x03
+#define FSA9480_REG_INT2                0x04
+#define FSA9480_REG_INT1_MASK           0x05
+#define FSA9480_REG_INT2_MASK           0x06
+#define FSA9480_REG_ADC                 0x07
+#define FSA9480_REG_TIMING1             0x08
+#define FSA9480_REG_TIMING2             0x09
+#define FSA9480_REG_DEV_T1              0x0a
+#define FSA9480_REG_DEV_T2              0x0b
+#define FSA9480_REG_BTN1                0x0c
+#define FSA9480_REG_BTN2                0x0d
+#define FSA9480_REG_CK                  0x0e
+#define FSA9480_REG_CK_INT1             0x0f
+#define FSA9480_REG_CK_INT2             0x10
+#define FSA9480_REG_CK_INTMASK1         0x11
+#define FSA9480_REG_CK_INTMASK2         0x12
+#define FSA9480_REG_MANSW1              0x13
+#define FSA9480_REG_MANSW2              0x14
+#define FSA9480_REG_END                 0x15
+
+/* Control */
+#define CON_SWITCH_OPEN         (1 << 4)
+#define CON_RAW_DATA            (1 << 3)
+#define CON_MANUAL_SW           (1 << 2)
+#define CON_WAIT                (1 << 1)
+#define CON_INT_MASK            (1 << 0)
+#define CON_MASK                (CON_SWITCH_OPEN | CON_RAW_DATA | \
+				 CON_MANUAL_SW | CON_WAIT)
+
+/* Device Type 1 */
+#define DEV_USB_OTG             7
+#define DEV_DEDICATED_CHG       6
+#define DEV_USB_CHG             5
+#define DEV_CAR_KIT             4
+#define DEV_UART                3
+#define DEV_USB                 2
+#define DEV_AUDIO_2             1
+#define DEV_AUDIO_1             0
+
+#define DEV_T1_USB_MASK         (DEV_USB_OTG | DEV_USB)
+#define DEV_T1_UART_MASK        (DEV_UART)
+#define DEV_T1_CHARGER_MASK     (DEV_DEDICATED_CHG | DEV_USB_CHG)
+
+/* Device Type 2 */
+#define DEV_AV                  14
+#define DEV_TTY                 13
+#define DEV_PPD                 12
+#define DEV_JIG_UART_OFF        11
+#define DEV_JIG_UART_ON         10
+#define DEV_JIG_USB_OFF         9
+#define DEV_JIG_USB_ON          8
+
+#define DEV_T2_USB_MASK         (DEV_JIG_USB_OFF | DEV_JIG_USB_ON)
+#define DEV_T2_UART_MASK        (DEV_JIG_UART_OFF | DEV_JIG_UART_ON)
+#define DEV_T2_JIG_MASK         (DEV_JIG_USB_OFF | DEV_JIG_USB_ON | \
+				 DEV_JIG_UART_OFF | DEV_JIG_UART_ON)
+
+/*
+ * Manual Switch
+ * D- [7:5] / D+ [4:2]
+ * 000: Open all / 001: USB / 010: AUDIO / 011: UART / 100: V_AUDIO
+ */
+#define SW_VAUDIO               ((4 << 5) | (4 << 2))
+#define SW_UART                 ((3 << 5) | (3 << 2))
+#define SW_AUDIO                ((2 << 5) | (2 << 2))
+#define SW_DHOST                ((1 << 5) | (1 << 2))
+#define SW_AUTO                 ((0 << 5) | (0 << 2))
+
+/* Interrupt 1 */
+#define INT1_MASK               (0xff << 0)
+#define INT_DETACH              (1 << 1)
+#define INT_ATTACH              (1 << 0)
+
+/* Interrupt 2 mask */
+#define INT2_MASK               (0x1f << 0)
+
+/* Timing Set 1 */
+#define TIMING1_ADC_500MS       (0x6 << 0)
+
+struct fsa9480_usbsw {
+	struct device *dev;
+	struct regmap *regmap;
+	struct extcon_dev *edev;
+	u16 cable;
+};
+
+static const unsigned int fsa9480_extcon_cable[] = {
+	EXTCON_USB_HOST,
+	EXTCON_USB,
+	EXTCON_CHG_USB_DCP,
+	EXTCON_CHG_USB_SDP,
+	EXTCON_CHG_USB_ACA,
+	EXTCON_JACK_LINE_OUT,
+	EXTCON_JACK_VIDEO_OUT,
+	EXTCON_JIG,
+
+	EXTCON_NONE,
+};
+
+static const u64 cable_types[] = {
+	[DEV_USB_OTG] = BIT_ULL(EXTCON_USB_HOST),
+	[DEV_DEDICATED_CHG] = BIT_ULL(EXTCON_USB) | BIT_ULL(EXTCON_CHG_USB_DCP),
+	[DEV_USB_CHG] = BIT_ULL(EXTCON_USB) | BIT_ULL(EXTCON_CHG_USB_SDP),
+	[DEV_CAR_KIT] = BIT_ULL(EXTCON_USB) | BIT_ULL(EXTCON_CHG_USB_SDP)
+			| BIT_ULL(EXTCON_JACK_LINE_OUT),
+	[DEV_UART] = BIT_ULL(EXTCON_JIG),
+	[DEV_USB] = BIT_ULL(EXTCON_USB) | BIT_ULL(EXTCON_CHG_USB_SDP),
+	[DEV_AUDIO_2] = BIT_ULL(EXTCON_JACK_LINE_OUT),
+	[DEV_AUDIO_1] = BIT_ULL(EXTCON_JACK_LINE_OUT),
+	[DEV_AV] = BIT_ULL(EXTCON_JACK_LINE_OUT)
+		   | BIT_ULL(EXTCON_JACK_VIDEO_OUT),
+	[DEV_TTY] = BIT_ULL(EXTCON_JIG),
+	[DEV_PPD] = BIT_ULL(EXTCON_JACK_LINE_OUT) | BIT_ULL(EXTCON_CHG_USB_ACA),
+	[DEV_JIG_UART_OFF] = BIT_ULL(EXTCON_JIG),
+	[DEV_JIG_UART_ON] = BIT_ULL(EXTCON_JIG),
+	[DEV_JIG_USB_OFF] = BIT_ULL(EXTCON_USB) | BIT_ULL(EXTCON_JIG),
+	[DEV_JIG_USB_ON] = BIT_ULL(EXTCON_USB) | BIT_ULL(EXTCON_JIG),
+};
+
+/* Define regmap configuration of FSA9480 for I2C communication  */
+static bool fsa9480_volatile_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case FSA9480_REG_INT1_MASK:
+		return true;
+	default:
+		break;
+	}
+	return false;
+}
+
+static const struct regmap_config fsa9480_regmap_config = {
+	.reg_bits	= 8,
+	.val_bits	= 8,
+	.volatile_reg	= fsa9480_volatile_reg,
+	.max_register	= FSA9480_REG_END,
+};
+
+static int fsa9480_write_reg(struct fsa9480_usbsw *usbsw, int reg, int value)
+{
+	int ret;
+
+	ret = regmap_write(usbsw->regmap, reg, value);
+	if (ret < 0)
+		dev_err(usbsw->dev, "%s: err %d\n", __func__, ret);
+
+	return ret;
+}
+
+static int fsa9480_read_reg(struct fsa9480_usbsw *usbsw, int reg)
+{
+	int ret, val;
+
+	ret = regmap_read(usbsw->regmap, reg, &val);
+	if (ret < 0) {
+		dev_err(usbsw->dev, "%s: err %d\n", __func__, ret);
+		return ret;
+	}
+
+	return val;
+}
+
+static int fsa9480_read_irq(struct fsa9480_usbsw *usbsw, int *value)
+{
+	u8 regs[2];
+	int ret;
+
+	ret = regmap_bulk_read(usbsw->regmap, FSA9480_REG_INT1, regs, 2);
+	if (ret < 0)
+		dev_err(usbsw->dev, "%s: err %d\n", __func__, ret);
+
+	*value = regs[1] << 8 | regs[0];
+	return ret;
+}
+
+static void fsa9480_handle_change(struct fsa9480_usbsw *usbsw,
+				  u16 mask, bool attached)
+{
+	while (mask) {
+		int dev = fls64(mask) - 1;
+		u64 cables = cable_types[dev];
+
+		while (cables) {
+			int cable = fls64(cables) - 1;
+
+			extcon_set_state_sync(usbsw->edev, cable, attached);
+			cables &= ~BIT_ULL(cable);
+		}
+
+		mask &= ~BIT_ULL(dev);
+	}
+}
+
+static void fsa9480_detect_dev(struct fsa9480_usbsw *usbsw)
+{
+	int val1, val2;
+	u16 val;
+
+	val1 = fsa9480_read_reg(usbsw, FSA9480_REG_DEV_T1);
+	val2 = fsa9480_read_reg(usbsw, FSA9480_REG_DEV_T2);
+	if (val1 < 0 || val2 < 0) {
+		dev_err(usbsw->dev, "%s: failed to read registers", __func__);
+		return;
+	}
+	val = val2 << 8 | val1;
+
+	dev_info(usbsw->dev, "dev1: 0x%x, dev2: 0x%x\n", val1, val2);
+
+	/* handle detached cables first */
+	fsa9480_handle_change(usbsw, usbsw->cable & ~val, false);
+
+	/* then handle attached ones */
+	fsa9480_handle_change(usbsw, val & ~usbsw->cable, true);
+
+	usbsw->cable = val;
+}
+
+static irqreturn_t fsa9480_irq_handler(int irq, void *data)
+{
+	struct fsa9480_usbsw *usbsw = data;
+	int intr = 0;
+
+	/* clear interrupt */
+	fsa9480_read_irq(usbsw, &intr);
+	if (!intr)
+		return IRQ_NONE;
+
+	/* device detection */
+	fsa9480_detect_dev(usbsw);
+
+	return IRQ_HANDLED;
+}
+
+static int fsa9480_probe(struct i2c_client *client,
+			 const struct i2c_device_id *id)
+{
+	struct fsa9480_usbsw *info;
+	int ret;
+
+	if (!client->irq) {
+		dev_err(&client->dev, "no interrupt provided\n");
+		return -EINVAL;
+	}
+
+	info = devm_kzalloc(&client->dev, sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+	info->dev = &client->dev;
+
+	i2c_set_clientdata(client, info);
+
+	/* External connector */
+	info->edev = devm_extcon_dev_allocate(info->dev,
+					      fsa9480_extcon_cable);
+	if (IS_ERR(info->edev)) {
+		dev_err(info->dev, "failed to allocate memory for extcon\n");
+		ret = -ENOMEM;
+		return ret;
+	}
+
+	ret = devm_extcon_dev_register(info->dev, info->edev);
+	if (ret) {
+		dev_err(info->dev, "failed to register extcon device\n");
+		return ret;
+	}
+
+	info->regmap = devm_regmap_init_i2c(client, &fsa9480_regmap_config);
+	if (IS_ERR(info->regmap)) {
+		ret = PTR_ERR(info->regmap);
+		dev_err(info->dev, "failed to allocate register map: %d\n",
+			ret);
+		return ret;
+	}
+
+	/* ADC Detect Time: 500ms */
+	fsa9480_write_reg(info, FSA9480_REG_TIMING1, TIMING1_ADC_500MS);
+
+	/* configure automatic switching */
+	fsa9480_write_reg(info, FSA9480_REG_CTRL, CON_MASK);
+
+	/* unmask interrupt (attach/detach only) */
+	fsa9480_write_reg(info, FSA9480_REG_INT1_MASK,
+			  INT1_MASK & ~(INT_ATTACH | INT_DETACH));
+	fsa9480_write_reg(info, FSA9480_REG_INT2_MASK, INT2_MASK);
+
+	ret = devm_request_threaded_irq(info->dev, client->irq, NULL,
+					fsa9480_irq_handler,
+					IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+					"fsa9480", info);
+	if (ret) {
+		dev_err(info->dev, "failed to request IRQ\n");
+		return ret;
+	}
+
+	device_init_wakeup(info->dev, true);
+	fsa9480_detect_dev(info);
+
+	return 0;
+}
+
+static int fsa9480_remove(struct i2c_client *client)
+{
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int fsa9480_suspend(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+
+	if (device_may_wakeup(&client->dev) && client->irq)
+		enable_irq_wake(client->irq);
+
+	return 0;
+}
+
+static int fsa9480_resume(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+
+	if (device_may_wakeup(&client->dev) && client->irq)
+		disable_irq_wake(client->irq);
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops fsa9480_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(fsa9480_suspend, fsa9480_resume)
+};
+
+static const struct i2c_device_id fsa9480_id[] = {
+	{ "fsa9480", 0 },
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, fsa9480_id);
+
+static const struct of_device_id fsa9480_of_match[] = {
+	{ .compatible = "fcs,fsa9480", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, fsa9480_of_match);
+
+static struct i2c_driver fsa9480_i2c_driver = {
+	.driver			= {
+		.name		= "fsa9480",
+		.pm		= &fsa9480_pm_ops,
+		.of_match_table = fsa9480_of_match,
+	},
+	.probe			= fsa9480_probe,
+	.remove			= fsa9480_remove,
+	.id_table		= fsa9480_id,
+};
+
+static int __init fsa9480_module_init(void)
+{
+	return i2c_add_driver(&fsa9480_i2c_driver);
+}
+subsys_initcall(fsa9480_module_init);
+
+static void __exit fsa9480_module_exit(void)
+{
+	i2c_del_driver(&fsa9480_i2c_driver);
+}
+module_exit(fsa9480_module_exit);
+
+MODULE_DESCRIPTION("Fairchild Semiconductor FSA9480 extcon driver");
+MODULE_AUTHOR("Tomasz Figa <tomasz.figa@gmail.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/firmware/google/coreboot_table.h b/drivers/firmware/google/coreboot_table.h
index 1f63b3034b17..7b7b4a6eedda 100644
--- a/drivers/firmware/google/coreboot_table.h
+++ b/drivers/firmware/google/coreboot_table.h
@@ -12,7 +12,7 @@
 #ifndef __COREBOOT_TABLE_H
 #define __COREBOOT_TABLE_H
 
-#include <linux/io.h>
+#include <linux/device.h>
 
 /* Coreboot table header structure */
 struct coreboot_table_header {
@@ -83,4 +83,13 @@ int coreboot_driver_register(struct coreboot_driver *driver);
 /* Unregister a driver that uses the data from a coreboot table. */
 void coreboot_driver_unregister(struct coreboot_driver *driver);
 
+/* module_coreboot_driver() - Helper macro for drivers that don't do
+ * anything special in module init/exit.  This eliminates a lot of
+ * boilerplate.  Each module may only use this macro once, and
+ * calling it replaces module_init() and module_exit()
+ */
+#define module_coreboot_driver(__coreboot_driver) \
+	module_driver(__coreboot_driver, coreboot_driver_register, \
+			coreboot_driver_unregister)
+
 #endif /* __COREBOOT_TABLE_H */
diff --git a/drivers/firmware/google/framebuffer-coreboot.c b/drivers/firmware/google/framebuffer-coreboot.c
index 7e67b651e4ac..916f26adc595 100644
--- a/drivers/firmware/google/framebuffer-coreboot.c
+++ b/drivers/firmware/google/framebuffer-coreboot.c
@@ -89,19 +89,7 @@ static struct coreboot_driver framebuffer_driver = {
 	},
 	.tag = CB_TAG_FRAMEBUFFER,
 };
-
-static int __init coreboot_framebuffer_init(void)
-{
-	return coreboot_driver_register(&framebuffer_driver);
-}
-
-static void coreboot_framebuffer_exit(void)
-{
-	coreboot_driver_unregister(&framebuffer_driver);
-}
-
-module_init(coreboot_framebuffer_init);
-module_exit(coreboot_framebuffer_exit);
+module_coreboot_driver(framebuffer_driver);
 
 MODULE_AUTHOR("Samuel Holland <samuel@sholland.org>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/firmware/google/memconsole-coreboot.c b/drivers/firmware/google/memconsole-coreboot.c
index ac90e8536565..fd7f0fbec07e 100644
--- a/drivers/firmware/google/memconsole-coreboot.c
+++ b/drivers/firmware/google/memconsole-coreboot.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/device.h>
+#include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 
@@ -26,7 +27,7 @@ struct cbmem_cons {
 #define CURSOR_MASK ((1 << 28) - 1)
 #define OVERFLOW (1 << 31)
 
-static struct cbmem_cons __iomem *cbmem_console;
+static struct cbmem_cons *cbmem_console;
 static u32 cbmem_console_size;
 
 /*
@@ -67,7 +68,7 @@ static ssize_t memconsole_coreboot_read(char *buf, loff_t pos, size_t count)
 
 static int memconsole_probe(struct coreboot_device *dev)
 {
-	struct cbmem_cons __iomem *tmp_cbmc;
+	struct cbmem_cons *tmp_cbmc;
 
 	tmp_cbmc = memremap(dev->cbmem_ref.cbmem_addr,
 			    sizeof(*tmp_cbmc), MEMREMAP_WB);
@@ -77,13 +78,13 @@ static int memconsole_probe(struct coreboot_device *dev)
 
 	/* Read size only once to prevent overrun attack through /dev/mem. */
 	cbmem_console_size = tmp_cbmc->size_dont_access_after_boot;
-	cbmem_console = memremap(dev->cbmem_ref.cbmem_addr,
+	cbmem_console = devm_memremap(&dev->dev, dev->cbmem_ref.cbmem_addr,
 				 cbmem_console_size + sizeof(*cbmem_console),
 				 MEMREMAP_WB);
 	memunmap(tmp_cbmc);
 
-	if (!cbmem_console)
-		return -ENOMEM;
+	if (IS_ERR(cbmem_console))
+		return PTR_ERR(cbmem_console);
 
 	memconsole_setup(memconsole_coreboot_read);
 
@@ -94,9 +95,6 @@ static int memconsole_remove(struct coreboot_device *dev)
 {
 	memconsole_exit();
 
-	if (cbmem_console)
-		memunmap(cbmem_console);
-
 	return 0;
 }
 
@@ -108,19 +106,7 @@ static struct coreboot_driver memconsole_driver = {
 	},
 	.tag = CB_TAG_CBMEM_CONSOLE,
 };
-
-static void coreboot_memconsole_exit(void)
-{
-	coreboot_driver_unregister(&memconsole_driver);
-}
-
-static int __init coreboot_memconsole_init(void)
-{
-	return coreboot_driver_register(&memconsole_driver);
-}
-
-module_exit(coreboot_memconsole_exit);
-module_init(coreboot_memconsole_init);
+module_coreboot_driver(memconsole_driver);
 
 MODULE_AUTHOR("Google, Inc.");
 MODULE_LICENSE("GPL");
diff --git a/drivers/firmware/google/memconsole.c b/drivers/firmware/google/memconsole.c
index fe5aa740c34d..44d314ad69e4 100644
--- a/drivers/firmware/google/memconsole.c
+++ b/drivers/firmware/google/memconsole.c
@@ -7,21 +7,22 @@
  * Copyright 2017 Google Inc.
  */
 
-#include <linux/init.h>
 #include <linux/sysfs.h>
 #include <linux/kobject.h>
 #include <linux/module.h>
 
 #include "memconsole.h"
 
-static ssize_t (*memconsole_read_func)(char *, loff_t, size_t);
-
 static ssize_t memconsole_read(struct file *filp, struct kobject *kobp,
 			       struct bin_attribute *bin_attr, char *buf,
 			       loff_t pos, size_t count)
 {
+	ssize_t (*memconsole_read_func)(char *, loff_t, size_t);
+
+	memconsole_read_func = bin_attr->private;
 	if (WARN_ON_ONCE(!memconsole_read_func))
 		return -EIO;
+
 	return memconsole_read_func(buf, pos, count);
 }
 
@@ -32,7 +33,7 @@ static struct bin_attribute memconsole_bin_attr = {
 
 void memconsole_setup(ssize_t (*read_func)(char *, loff_t, size_t))
 {
-	memconsole_read_func = read_func;
+	memconsole_bin_attr.private = read_func;
 }
 EXPORT_SYMBOL(memconsole_setup);
 
diff --git a/drivers/firmware/google/vpd.c b/drivers/firmware/google/vpd.c
index fd5212c395c0..0739f3b70347 100644
--- a/drivers/firmware/google/vpd.c
+++ b/drivers/firmware/google/vpd.c
@@ -316,19 +316,7 @@ static struct coreboot_driver vpd_driver = {
 	},
 	.tag = CB_TAG_VPD,
 };
-
-static int __init coreboot_vpd_init(void)
-{
-	return coreboot_driver_register(&vpd_driver);
-}
-
-static void __exit coreboot_vpd_exit(void)
-{
-	coreboot_driver_unregister(&vpd_driver);
-}
-
-module_init(coreboot_vpd_init);
-module_exit(coreboot_vpd_exit);
+module_coreboot_driver(vpd_driver);
 
 MODULE_AUTHOR("Google, Inc.");
 MODULE_LICENSE("GPL");
diff --git a/drivers/firmware/google/vpd_decode.c b/drivers/firmware/google/vpd_decode.c
index c62fa7063a7c..92e3258552fc 100644
--- a/drivers/firmware/google/vpd_decode.c
+++ b/drivers/firmware/google/vpd_decode.c
@@ -7,8 +7,6 @@
  * Copyright 2017 Google Inc.
  */
 
-#include <linux/export.h>
-
 #include "vpd_decode.h"
 
 static int vpd_decode_len(const s32 max_len, const u8 *in,
diff --git a/drivers/fpga/Kconfig b/drivers/fpga/Kconfig
index 8072c195d831..474f304ec109 100644
--- a/drivers/fpga/Kconfig
+++ b/drivers/fpga/Kconfig
@@ -26,9 +26,9 @@ config FPGA_MGR_SOCFPGA_A10
 	  FPGA manager driver support for Altera Arria10 SoCFPGA.
 
 config ALTERA_PR_IP_CORE
-        tristate "Altera Partial Reconfiguration IP Core"
-        help
-          Core driver support for Altera Partial Reconfiguration IP component
+	tristate "Altera Partial Reconfiguration IP Core"
+	help
+	  Core driver support for Altera Partial Reconfiguration IP component
 
 config ALTERA_PR_IP_CORE_PLAT
 	tristate "Platform support of Altera Partial Reconfiguration IP Core"
diff --git a/drivers/fpga/dfl-fme-mgr.c b/drivers/fpga/dfl-fme-mgr.c
index 76f37709dd1a..b3f7eee3c93f 100644
--- a/drivers/fpga/dfl-fme-mgr.c
+++ b/drivers/fpga/dfl-fme-mgr.c
@@ -30,8 +30,8 @@
 #define FME_PR_STS		0x10
 #define FME_PR_DATA		0x18
 #define FME_PR_ERR		0x20
-#define FME_PR_INTFC_ID_H	0xA8
-#define FME_PR_INTFC_ID_L	0xB0
+#define FME_PR_INTFC_ID_L	0xA8
+#define FME_PR_INTFC_ID_H	0xB0
 
 /* FME PR Control Register Bitfield */
 #define FME_PR_CTRL_PR_RST	BIT_ULL(0)  /* Reset PR engine */
diff --git a/drivers/fpga/dfl-fme-pr.c b/drivers/fpga/dfl-fme-pr.c
index d9ca9554844a..3c71dc3faaf5 100644
--- a/drivers/fpga/dfl-fme-pr.c
+++ b/drivers/fpga/dfl-fme-pr.c
@@ -74,6 +74,7 @@ static int fme_pr(struct platform_device *pdev, unsigned long arg)
 	struct dfl_fme *fme;
 	unsigned long minsz;
 	void *buf = NULL;
+	size_t length;
 	int ret = 0;
 	u64 v;
 
@@ -85,9 +86,6 @@ static int fme_pr(struct platform_device *pdev, unsigned long arg)
 	if (port_pr.argsz < minsz || port_pr.flags)
 		return -EINVAL;
 
-	if (!IS_ALIGNED(port_pr.buffer_size, 4))
-		return -EINVAL;
-
 	/* get fme header region */
 	fme_hdr = dfl_get_feature_ioaddr_by_id(&pdev->dev,
 					       FME_FEATURE_ID_HEADER);
@@ -103,7 +101,13 @@ static int fme_pr(struct platform_device *pdev, unsigned long arg)
 		       port_pr.buffer_size))
 		return -EFAULT;
 
-	buf = vmalloc(port_pr.buffer_size);
+	/*
+	 * align PR buffer per PR bandwidth, as HW ignores the extra padding
+	 * data automatically.
+	 */
+	length = ALIGN(port_pr.buffer_size, 4);
+
+	buf = vmalloc(length);
 	if (!buf)
 		return -ENOMEM;
 
@@ -140,7 +144,7 @@ static int fme_pr(struct platform_device *pdev, unsigned long arg)
 	fpga_image_info_free(region->info);
 
 	info->buf = buf;
-	info->count = port_pr.buffer_size;
+	info->count = length;
 	info->region_id = port_pr.port_id;
 	region->info = info;
 
@@ -159,9 +163,6 @@ unlock_exit:
 	mutex_unlock(&pdata->lock);
 free_exit:
 	vfree(buf);
-	if (copy_to_user((void __user *)arg, &port_pr, minsz))
-		return -EFAULT;
-
 	return ret;
 }
 
diff --git a/drivers/fsi/cf-fsi-fw.h b/drivers/fsi/cf-fsi-fw.h
index 712df0461911..1118eaf7ee39 100644
--- a/drivers/fsi/cf-fsi-fw.h
+++ b/drivers/fsi/cf-fsi-fw.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: GPL-2.0+ */
 #ifndef __CF_FSI_FW_H
 #define __CF_FSI_FW_H
 
diff --git a/drivers/fsi/fsi-core.c b/drivers/fsi/fsi-core.c
index 1d83f3ba478b..1f76740f33b6 100644
--- a/drivers/fsi/fsi-core.c
+++ b/drivers/fsi/fsi-core.c
@@ -1029,6 +1029,14 @@ static int fsi_slave_init(struct fsi_master *master, int link, uint8_t id)
 
 	}
 
+	rc = fsi_slave_set_smode(slave);
+	if (rc) {
+		dev_warn(&master->dev,
+				"can't set smode on slave:%02x:%02x %d\n",
+				link, id, rc);
+		goto err_free;
+	}
+
 	/* Allocate a minor in the FSI space */
 	rc = __fsi_get_new_minor(slave, fsi_dev_cfam, &slave->dev.devt,
 				 &slave->cdev_idx);
@@ -1040,17 +1048,14 @@ static int fsi_slave_init(struct fsi_master *master, int link, uint8_t id)
 	rc = cdev_device_add(&slave->cdev, &slave->dev);
 	if (rc) {
 		dev_err(&slave->dev, "Error %d creating slave device\n", rc);
-		goto err_free;
+		goto err_free_ida;
 	}
 
-	rc = fsi_slave_set_smode(slave);
-	if (rc) {
-		dev_warn(&master->dev,
-				"can't set smode on slave:%02x:%02x %d\n",
-				link, id, rc);
-		kfree(slave);
-		return -ENODEV;
-	}
+	/* Now that we have the cdev registered with the core, any fatal
+	 * failures beyond this point will need to clean up through
+	 * cdev_device_del(). Fortunately though, nothing past here is fatal.
+	 */
+
 	if (master->link_config)
 		master->link_config(master, link,
 				    slave->t_send_delay,
@@ -1067,10 +1072,13 @@ static int fsi_slave_init(struct fsi_master *master, int link, uint8_t id)
 		dev_dbg(&master->dev, "failed during slave scan with: %d\n",
 				rc);
 
-	return rc;
+	return 0;
 
- err_free:
-	put_device(&slave->dev);
+err_free_ida:
+	fsi_free_minor(slave->dev.devt);
+err_free:
+	of_node_put(slave->dev.of_node);
+	kfree(slave);
 	return rc;
 }
 
diff --git a/drivers/fsi/fsi-occ.c b/drivers/fsi/fsi-occ.c
index a2301cea1cbb..7da9c81759ac 100644
--- a/drivers/fsi/fsi-occ.c
+++ b/drivers/fsi/fsi-occ.c
@@ -412,6 +412,7 @@ int fsi_occ_submit(struct device *dev, const void *request, size_t req_len,
 		msecs_to_jiffies(OCC_CMD_IN_PRG_WAIT_MS);
 	struct occ *occ = dev_get_drvdata(dev);
 	struct occ_response *resp = response;
+	u8 seq_no;
 	u16 resp_data_length;
 	unsigned long start;
 	int rc;
@@ -426,6 +427,8 @@ int fsi_occ_submit(struct device *dev, const void *request, size_t req_len,
 
 	mutex_lock(&occ->occ_lock);
 
+	/* Extract the seq_no from the command (first byte) */
+	seq_no = *(const u8 *)request;
 	rc = occ_putsram(occ, OCC_SRAM_CMD_ADDR, request, req_len);
 	if (rc)
 		goto done;
@@ -441,11 +444,17 @@ int fsi_occ_submit(struct device *dev, const void *request, size_t req_len,
 		if (rc)
 			goto done;
 
-		if (resp->return_status == OCC_RESP_CMD_IN_PRG) {
+		if (resp->return_status == OCC_RESP_CMD_IN_PRG ||
+		    resp->seq_no != seq_no) {
 			rc = -ETIMEDOUT;
 
-			if (time_after(jiffies, start + timeout))
-				break;
+			if (time_after(jiffies, start + timeout)) {
+				dev_err(occ->dev, "resp timeout status=%02x "
+					"resp seq_no=%d our seq_no=%d\n",
+					resp->return_status, resp->seq_no,
+					seq_no);
+				goto done;
+			}
 
 			set_current_state(TASK_UNINTERRUPTIBLE);
 			schedule_timeout(wait_time);
diff --git a/drivers/fsi/fsi-sbefifo.c b/drivers/fsi/fsi-sbefifo.c
index d92f5b87c251..f54df9ebc8b3 100644
--- a/drivers/fsi/fsi-sbefifo.c
+++ b/drivers/fsi/fsi-sbefifo.c
@@ -289,11 +289,11 @@ static int sbefifo_check_sbe_state(struct sbefifo *sbefifo)
 	switch ((sbm & CFAM_SBM_SBE_STATE_MASK) >> CFAM_SBM_SBE_STATE_SHIFT) {
 	case SBE_STATE_UNKNOWN:
 		return -ESHUTDOWN;
+	case SBE_STATE_DMT:
+		return -EBUSY;
 	case SBE_STATE_IPLING:
 	case SBE_STATE_ISTEP:
 	case SBE_STATE_MPIPL:
-	case SBE_STATE_DMT:
-		return -EBUSY;
 	case SBE_STATE_RUNTIME:
 	case SBE_STATE_DUMP: /* Not sure about that one */
 		break;
diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c
index d593517af5c2..a7d2b16dd702 100644
--- a/drivers/hwmon/occ/common.c
+++ b/drivers/hwmon/occ/common.c
@@ -124,12 +124,12 @@ struct extended_sensor {
 static int occ_poll(struct occ *occ)
 {
 	int rc;
-	u16 checksum = occ->poll_cmd_data + 1;
+	u16 checksum = occ->poll_cmd_data + occ->seq_no + 1;
 	u8 cmd[8];
 	struct occ_poll_response_header *header;
 
 	/* big endian */
-	cmd[0] = 0;			/* sequence number */
+	cmd[0] = occ->seq_no++;		/* sequence number */
 	cmd[1] = 0;			/* cmd type */
 	cmd[2] = 0;			/* data length msb */
 	cmd[3] = 1;			/* data length lsb */
diff --git a/drivers/hwmon/occ/common.h b/drivers/hwmon/occ/common.h
index fc13f3c73c47..67e6968b8978 100644
--- a/drivers/hwmon/occ/common.h
+++ b/drivers/hwmon/occ/common.h
@@ -95,6 +95,7 @@ struct occ {
 	struct occ_sensors sensors;
 
 	int powr_sample_time_us;	/* average power sample time */
+	u8 seq_no;
 	u8 poll_cmd_data;		/* to perform OCC poll command */
 	int (*send_cmd)(struct occ *occ, u8 *cmd);
 
diff --git a/drivers/hwtracing/coresight/Kconfig b/drivers/hwtracing/coresight/Kconfig
index 5487d4a1abc2..14638db4991d 100644
--- a/drivers/hwtracing/coresight/Kconfig
+++ b/drivers/hwtracing/coresight/Kconfig
@@ -4,6 +4,7 @@
 #
 menuconfig CORESIGHT
 	bool "CoreSight Tracing Support"
+	depends on OF || ACPI
 	select ARM_AMBA
 	select PERF_EVENTS
 	help
diff --git a/drivers/hwtracing/coresight/Makefile b/drivers/hwtracing/coresight/Makefile
index 3b435aa42af5..3c0ac421e211 100644
--- a/drivers/hwtracing/coresight/Makefile
+++ b/drivers/hwtracing/coresight/Makefile
@@ -2,8 +2,7 @@
 #
 # Makefile for CoreSight drivers.
 #
-obj-$(CONFIG_CORESIGHT) += coresight.o coresight-etm-perf.o
-obj-$(CONFIG_OF) += of_coresight.o
+obj-$(CONFIG_CORESIGHT) += coresight.o coresight-etm-perf.o coresight-platform.o
 obj-$(CONFIG_CORESIGHT_LINK_AND_SINK_TMC) += coresight-tmc.o \
 					     coresight-tmc-etf.o \
 					     coresight-tmc-etr.o
diff --git a/drivers/hwtracing/coresight/coresight-catu.c b/drivers/hwtracing/coresight/coresight-catu.c
index 4ea68a3522e9..16ebf38a9f66 100644
--- a/drivers/hwtracing/coresight/coresight-catu.c
+++ b/drivers/hwtracing/coresight/coresight-catu.c
@@ -28,6 +28,8 @@
 #define catu_dbg(x, ...) do {} while (0)
 #endif
 
+DEFINE_CORESIGHT_DEVLIST(catu_devs, "catu");
+
 struct catu_etr_buf {
 	struct tmc_sg_table *catu_table;
 	dma_addr_t sladdr;
@@ -328,19 +330,18 @@ static int catu_alloc_etr_buf(struct tmc_drvdata *tmc_drvdata,
 			      struct etr_buf *etr_buf, int node, void **pages)
 {
 	struct coresight_device *csdev;
-	struct device *catu_dev;
 	struct tmc_sg_table *catu_table;
 	struct catu_etr_buf *catu_buf;
 
 	csdev = tmc_etr_get_catu_device(tmc_drvdata);
 	if (!csdev)
 		return -ENODEV;
-	catu_dev = csdev->dev.parent;
 	catu_buf = kzalloc(sizeof(*catu_buf), GFP_KERNEL);
 	if (!catu_buf)
 		return -ENOMEM;
 
-	catu_table = catu_init_sg_table(catu_dev, node, etr_buf->size, pages);
+	catu_table = catu_init_sg_table(&csdev->dev, node,
+					etr_buf->size, pages);
 	if (IS_ERR(catu_table)) {
 		kfree(catu_buf);
 		return PTR_ERR(catu_table);
@@ -409,13 +410,14 @@ static int catu_enable_hw(struct catu_drvdata *drvdata, void *data)
 	int rc;
 	u32 control, mode;
 	struct etr_buf *etr_buf = data;
+	struct device *dev = &drvdata->csdev->dev;
 
 	if (catu_wait_for_ready(drvdata))
-		dev_warn(drvdata->dev, "Timeout while waiting for READY\n");
+		dev_warn(dev, "Timeout while waiting for READY\n");
 
 	control = catu_read_control(drvdata);
 	if (control & BIT(CATU_CONTROL_ENABLE)) {
-		dev_warn(drvdata->dev, "CATU is already enabled\n");
+		dev_warn(dev, "CATU is already enabled\n");
 		return -EBUSY;
 	}
 
@@ -441,7 +443,7 @@ static int catu_enable_hw(struct catu_drvdata *drvdata, void *data)
 	catu_write_irqen(drvdata, 0);
 	catu_write_mode(drvdata, mode);
 	catu_write_control(drvdata, control);
-	dev_dbg(drvdata->dev, "Enabled in %s mode\n",
+	dev_dbg(dev, "Enabled in %s mode\n",
 		(mode == CATU_MODE_PASS_THROUGH) ?
 		"Pass through" :
 		"Translate");
@@ -462,15 +464,16 @@ static int catu_enable(struct coresight_device *csdev, void *data)
 static int catu_disable_hw(struct catu_drvdata *drvdata)
 {
 	int rc = 0;
+	struct device *dev = &drvdata->csdev->dev;
 
 	catu_write_control(drvdata, 0);
 	coresight_disclaim_device_unlocked(drvdata->base);
 	if (catu_wait_for_ready(drvdata)) {
-		dev_info(drvdata->dev, "Timeout while waiting for READY\n");
+		dev_info(dev, "Timeout while waiting for READY\n");
 		rc = -EAGAIN;
 	}
 
-	dev_dbg(drvdata->dev, "Disabled\n");
+	dev_dbg(dev, "Disabled\n");
 	return rc;
 }
 
@@ -502,17 +505,11 @@ static int catu_probe(struct amba_device *adev, const struct amba_id *id)
 	struct coresight_desc catu_desc;
 	struct coresight_platform_data *pdata = NULL;
 	struct device *dev = &adev->dev;
-	struct device_node *np = dev->of_node;
 	void __iomem *base;
 
-	if (np) {
-		pdata = of_get_coresight_platform_data(dev, np);
-		if (IS_ERR(pdata)) {
-			ret = PTR_ERR(pdata);
-			goto out;
-		}
-		dev->platform_data = pdata;
-	}
+	catu_desc.name = coresight_alloc_device_name(&catu_devs, dev);
+	if (!catu_desc.name)
+		return -ENOMEM;
 
 	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
 	if (!drvdata) {
@@ -520,7 +517,6 @@ static int catu_probe(struct amba_device *adev, const struct amba_id *id)
 		goto out;
 	}
 
-	drvdata->dev = dev;
 	dev_set_drvdata(dev, drvdata);
 	base = devm_ioremap_resource(dev, &adev->res);
 	if (IS_ERR(base)) {
@@ -547,6 +543,13 @@ static int catu_probe(struct amba_device *adev, const struct amba_id *id)
 	if (ret)
 		goto out;
 
+	pdata = coresight_get_platform_data(dev);
+	if (IS_ERR(pdata)) {
+		ret = PTR_ERR(pdata);
+		goto out;
+	}
+	dev->platform_data = pdata;
+
 	drvdata->base = base;
 	catu_desc.pdata = pdata;
 	catu_desc.dev = dev;
@@ -554,6 +557,7 @@ static int catu_probe(struct amba_device *adev, const struct amba_id *id)
 	catu_desc.type = CORESIGHT_DEV_TYPE_HELPER;
 	catu_desc.subtype.helper_subtype = CORESIGHT_DEV_SUBTYPE_HELPER_CATU;
 	catu_desc.ops = &catu_ops;
+
 	drvdata->csdev = coresight_register(&catu_desc);
 	if (IS_ERR(drvdata->csdev))
 		ret = PTR_ERR(drvdata->csdev);
diff --git a/drivers/hwtracing/coresight/coresight-catu.h b/drivers/hwtracing/coresight/coresight-catu.h
index 1d2ad183fd92..80ceee3c739c 100644
--- a/drivers/hwtracing/coresight/coresight-catu.h
+++ b/drivers/hwtracing/coresight/coresight-catu.h
@@ -61,7 +61,6 @@
 #define CATU_IRQEN_OFF		0x0
 
 struct catu_drvdata {
-	struct device *dev;
 	void __iomem *base;
 	struct coresight_device *csdev;
 	int irq;
diff --git a/drivers/hwtracing/coresight/coresight-cpu-debug.c b/drivers/hwtracing/coresight/coresight-cpu-debug.c
index e8819d750938..58bfd6319f65 100644
--- a/drivers/hwtracing/coresight/coresight-cpu-debug.c
+++ b/drivers/hwtracing/coresight/coresight-cpu-debug.c
@@ -572,14 +572,16 @@ static int debug_probe(struct amba_device *adev, const struct amba_id *id)
 	struct device *dev = &adev->dev;
 	struct debug_drvdata *drvdata;
 	struct resource *res = &adev->res;
-	struct device_node *np = adev->dev.of_node;
 	int ret;
 
 	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
 	if (!drvdata)
 		return -ENOMEM;
 
-	drvdata->cpu = np ? of_coresight_get_cpu(np) : 0;
+	drvdata->cpu = coresight_get_cpu(dev);
+	if (drvdata->cpu < 0)
+		return drvdata->cpu;
+
 	if (per_cpu(debug_drvdata, drvdata->cpu)) {
 		dev_err(dev, "CPU%d drvdata has already been initialized\n",
 			drvdata->cpu);
diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c
index 4ee4c80a4354..3810290e6d07 100644
--- a/drivers/hwtracing/coresight/coresight-etb10.c
+++ b/drivers/hwtracing/coresight/coresight-etb10.c
@@ -63,10 +63,11 @@
 #define ETB_FFSR_BIT		1
 #define ETB_FRAME_SIZE_WORDS	4
 
+DEFINE_CORESIGHT_DEVLIST(etb_devs, "etb");
+
 /**
  * struct etb_drvdata - specifics associated to an ETB component
  * @base:	memory mapped base address for this component.
- * @dev:	the device entity associated to this component.
  * @atclk:	optional clock for the core parts of the ETB.
  * @csdev:	component vitals needed by the framework.
  * @miscdev:	specifics to handle "/dev/xyz.etb" entry.
@@ -81,7 +82,6 @@
  */
 struct etb_drvdata {
 	void __iomem		*base;
-	struct device		*dev;
 	struct clk		*atclk;
 	struct coresight_device	*csdev;
 	struct miscdevice	miscdev;
@@ -227,7 +227,6 @@ out:
 static int etb_enable(struct coresight_device *csdev, u32 mode, void *data)
 {
 	int ret;
-	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
 	switch (mode) {
 	case CS_MODE_SYSFS:
@@ -244,13 +243,14 @@ static int etb_enable(struct coresight_device *csdev, u32 mode, void *data)
 	if (ret)
 		return ret;
 
-	dev_dbg(drvdata->dev, "ETB enabled\n");
+	dev_dbg(&csdev->dev, "ETB enabled\n");
 	return 0;
 }
 
 static void __etb_disable_hw(struct etb_drvdata *drvdata)
 {
 	u32 ffcr;
+	struct device *dev = &drvdata->csdev->dev;
 
 	CS_UNLOCK(drvdata->base);
 
@@ -263,7 +263,7 @@ static void __etb_disable_hw(struct etb_drvdata *drvdata)
 	writel_relaxed(ffcr, drvdata->base + ETB_FFCR);
 
 	if (coresight_timeout(drvdata->base, ETB_FFCR, ETB_FFCR_BIT, 0)) {
-		dev_err(drvdata->dev,
+		dev_err(dev,
 		"timeout while waiting for completion of Manual Flush\n");
 	}
 
@@ -271,7 +271,7 @@ static void __etb_disable_hw(struct etb_drvdata *drvdata)
 	writel_relaxed(0x0, drvdata->base + ETB_CTL_REG);
 
 	if (coresight_timeout(drvdata->base, ETB_FFSR, ETB_FFSR_BIT, 1)) {
-		dev_err(drvdata->dev,
+		dev_err(dev,
 			"timeout while waiting for Formatter to Stop\n");
 	}
 
@@ -286,6 +286,7 @@ static void etb_dump_hw(struct etb_drvdata *drvdata)
 	u32 read_data, depth;
 	u32 read_ptr, write_ptr;
 	u32 frame_off, frame_endoff;
+	struct device *dev = &drvdata->csdev->dev;
 
 	CS_UNLOCK(drvdata->base);
 
@@ -295,10 +296,10 @@ static void etb_dump_hw(struct etb_drvdata *drvdata)
 	frame_off = write_ptr % ETB_FRAME_SIZE_WORDS;
 	frame_endoff = ETB_FRAME_SIZE_WORDS - frame_off;
 	if (frame_off) {
-		dev_err(drvdata->dev,
+		dev_err(dev,
 			"write_ptr: %lu not aligned to formatter frame size\n",
 			(unsigned long)write_ptr);
-		dev_err(drvdata->dev, "frameoff: %lu, frame_endoff: %lu\n",
+		dev_err(dev, "frameoff: %lu, frame_endoff: %lu\n",
 			(unsigned long)frame_off, (unsigned long)frame_endoff);
 		write_ptr += frame_endoff;
 	}
@@ -365,7 +366,7 @@ static int etb_disable(struct coresight_device *csdev)
 	drvdata->mode = CS_MODE_DISABLED;
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
-	dev_dbg(drvdata->dev, "ETB disabled\n");
+	dev_dbg(&csdev->dev, "ETB disabled\n");
 	return 0;
 }
 
@@ -373,12 +374,10 @@ static void *etb_alloc_buffer(struct coresight_device *csdev,
 			      struct perf_event *event, void **pages,
 			      int nr_pages, bool overwrite)
 {
-	int node, cpu = event->cpu;
+	int node;
 	struct cs_buffers *buf;
 
-	if (cpu == -1)
-		cpu = smp_processor_id();
-	node = cpu_to_node(cpu);
+	node = (event->cpu == -1) ? NUMA_NO_NODE : cpu_to_node(event->cpu);
 
 	buf = kzalloc_node(sizeof(struct cs_buffers), GFP_KERNEL, node);
 	if (!buf)
@@ -460,7 +459,7 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev,
 	 * chance to fix things.
 	 */
 	if (write_ptr % ETB_FRAME_SIZE_WORDS) {
-		dev_err(drvdata->dev,
+		dev_err(&csdev->dev,
 			"write_ptr: %lu not aligned to formatter frame size\n",
 			(unsigned long)write_ptr);
 
@@ -512,7 +511,13 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev,
 		lost = true;
 	}
 
-	if (lost)
+	/*
+	 * Don't set the TRUNCATED flag in snapshot mode because 1) the
+	 * captured buffer is expected to be truncated and 2) a full buffer
+	 * prevents the event from being re-enabled by the perf core,
+	 * resulting in stale data being send to user space.
+	 */
+	if (!buf->snapshot && lost)
 		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 
 	/* finally tell HW where we want to start reading from */
@@ -548,13 +553,14 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev,
 	writel_relaxed(0x0, drvdata->base + ETB_RAM_WRITE_POINTER);
 
 	/*
-	 * In snapshot mode we have to update the handle->head to point
-	 * to the new location.
+	 * In snapshot mode we simply increment the head by the number of byte
+	 * that were written.  User space function  cs_etm_find_snapshot() will
+	 * figure out how many bytes to get from the AUX buffer based on the
+	 * position of the head.
 	 */
-	if (buf->snapshot) {
-		handle->head = (cur * PAGE_SIZE) + offset;
-		to_read = buf->nr_pages << PAGE_SHIFT;
-	}
+	if (buf->snapshot)
+		handle->head += to_read;
+
 	__etb_enable_hw(drvdata);
 	CS_LOCK(drvdata->base);
 out:
@@ -587,7 +593,7 @@ static void etb_dump(struct etb_drvdata *drvdata)
 	}
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
-	dev_dbg(drvdata->dev, "ETB dumped\n");
+	dev_dbg(&drvdata->csdev->dev, "ETB dumped\n");
 }
 
 static int etb_open(struct inode *inode, struct file *file)
@@ -598,7 +604,7 @@ static int etb_open(struct inode *inode, struct file *file)
 	if (local_cmpxchg(&drvdata->reading, 0, 1))
 		return -EBUSY;
 
-	dev_dbg(drvdata->dev, "%s: successfully opened\n", __func__);
+	dev_dbg(&drvdata->csdev->dev, "%s: successfully opened\n", __func__);
 	return 0;
 }
 
@@ -608,6 +614,7 @@ static ssize_t etb_read(struct file *file, char __user *data,
 	u32 depth;
 	struct etb_drvdata *drvdata = container_of(file->private_data,
 						   struct etb_drvdata, miscdev);
+	struct device *dev = &drvdata->csdev->dev;
 
 	etb_dump(drvdata);
 
@@ -616,13 +623,14 @@ static ssize_t etb_read(struct file *file, char __user *data,
 		len = depth * 4 - *ppos;
 
 	if (copy_to_user(data, drvdata->buf + *ppos, len)) {
-		dev_dbg(drvdata->dev, "%s: copy_to_user failed\n", __func__);
+		dev_dbg(dev,
+			"%s: copy_to_user failed\n", __func__);
 		return -EFAULT;
 	}
 
 	*ppos += len;
 
-	dev_dbg(drvdata->dev, "%s: %zu bytes copied, %d bytes left\n",
+	dev_dbg(dev, "%s: %zu bytes copied, %d bytes left\n",
 		__func__, len, (int)(depth * 4 - *ppos));
 	return len;
 }
@@ -633,7 +641,7 @@ static int etb_release(struct inode *inode, struct file *file)
 						   struct etb_drvdata, miscdev);
 	local_set(&drvdata->reading, 0);
 
-	dev_dbg(drvdata->dev, "%s: released\n", __func__);
+	dev_dbg(&drvdata->csdev->dev, "%s: released\n", __func__);
 	return 0;
 }
 
@@ -724,20 +732,15 @@ static int etb_probe(struct amba_device *adev, const struct amba_id *id)
 	struct etb_drvdata *drvdata;
 	struct resource *res = &adev->res;
 	struct coresight_desc desc = { 0 };
-	struct device_node *np = adev->dev.of_node;
 
-	if (np) {
-		pdata = of_get_coresight_platform_data(dev, np);
-		if (IS_ERR(pdata))
-			return PTR_ERR(pdata);
-		adev->dev.platform_data = pdata;
-	}
+	desc.name = coresight_alloc_device_name(&etb_devs, dev);
+	if (!desc.name)
+		return -ENOMEM;
 
 	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
 	if (!drvdata)
 		return -ENOMEM;
 
-	drvdata->dev = &adev->dev;
 	drvdata->atclk = devm_clk_get(&adev->dev, "atclk"); /* optional */
 	if (!IS_ERR(drvdata->atclk)) {
 		ret = clk_prepare_enable(drvdata->atclk);
@@ -768,6 +771,11 @@ static int etb_probe(struct amba_device *adev, const struct amba_id *id)
 	/* This device is not associated with a session */
 	drvdata->pid = -1;
 
+	pdata = coresight_get_platform_data(dev);
+	if (IS_ERR(pdata))
+		return PTR_ERR(pdata);
+	adev->dev.platform_data = pdata;
+
 	desc.type = CORESIGHT_DEV_TYPE_SINK;
 	desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER;
 	desc.ops = &etb_cs_ops;
@@ -778,7 +786,7 @@ static int etb_probe(struct amba_device *adev, const struct amba_id *id)
 	if (IS_ERR(drvdata->csdev))
 		return PTR_ERR(drvdata->csdev);
 
-	drvdata->miscdev.name = pdata->name;
+	drvdata->miscdev.name = desc.name;
 	drvdata->miscdev.minor = MISC_DYNAMIC_MINOR;
 	drvdata->miscdev.fops = &etb_fops;
 	ret = misc_register(&drvdata->miscdev);
diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c
index 3c6294432748..5c1ca0df5cb0 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.c
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.c
@@ -523,7 +523,7 @@ int etm_perf_add_symlink_sink(struct coresight_device *csdev)
 	unsigned long hash;
 	const char *name;
 	struct device *pmu_dev = etm_pmu.dev;
-	struct device *pdev = csdev->dev.parent;
+	struct device *dev = &csdev->dev;
 	struct dev_ext_attribute *ea;
 
 	if (csdev->type != CORESIGHT_DEV_TYPE_SINK &&
@@ -536,15 +536,15 @@ int etm_perf_add_symlink_sink(struct coresight_device *csdev)
 	if (!etm_perf_up)
 		return -EPROBE_DEFER;
 
-	ea = devm_kzalloc(pdev, sizeof(*ea), GFP_KERNEL);
+	ea = devm_kzalloc(dev, sizeof(*ea), GFP_KERNEL);
 	if (!ea)
 		return -ENOMEM;
 
-	name = dev_name(pdev);
+	name = dev_name(dev);
 	/* See function coresight_get_sink_by_id() to know where this is used */
 	hash = hashlen_hash(hashlen_string(NULL, name));
 
-	ea->attr.attr.name = devm_kstrdup(pdev, name, GFP_KERNEL);
+	ea->attr.attr.name = devm_kstrdup(dev, name, GFP_KERNEL);
 	if (!ea->attr.attr.name)
 		return -ENOMEM;
 
diff --git a/drivers/hwtracing/coresight/coresight-etm.h b/drivers/hwtracing/coresight/coresight-etm.h
index 79e1ad860d8a..f3ab96eaf44e 100644
--- a/drivers/hwtracing/coresight/coresight-etm.h
+++ b/drivers/hwtracing/coresight/coresight-etm.h
@@ -208,7 +208,6 @@ struct etm_config {
 /**
  * struct etm_drvdata - specifics associated to an ETM component
  * @base:	memory mapped base address for this component.
- * @dev:	the device entity associated to this component.
  * @atclk:	optional clock for the core parts of the ETM.
  * @csdev:	component vitals needed by the framework.
  * @spinlock:	only one at a time pls.
@@ -232,7 +231,6 @@ struct etm_config {
  */
 struct etm_drvdata {
 	void __iomem			*base;
-	struct device			*dev;
 	struct clk			*atclk;
 	struct coresight_device		*csdev;
 	spinlock_t			spinlock;
@@ -260,7 +258,7 @@ static inline void etm_writel(struct etm_drvdata *drvdata,
 {
 	if (drvdata->use_cp14) {
 		if (etm_writel_cp14(off, val)) {
-			dev_err(drvdata->dev,
+			dev_err(&drvdata->csdev->dev,
 				"invalid CP14 access to ETM reg: %#x", off);
 		}
 	} else {
@@ -274,7 +272,7 @@ static inline unsigned int etm_readl(struct etm_drvdata *drvdata, u32 off)
 
 	if (drvdata->use_cp14) {
 		if (etm_readl_cp14(off, &val)) {
-			dev_err(drvdata->dev,
+			dev_err(&drvdata->csdev->dev,
 				"invalid CP14 access to ETM reg: %#x", off);
 		}
 	} else {
diff --git a/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c b/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c
index 75487b3fad86..e8c7649f123e 100644
--- a/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c
+++ b/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c
@@ -48,7 +48,7 @@ static ssize_t etmsr_show(struct device *dev,
 	unsigned long flags, val;
 	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
 
-	pm_runtime_get_sync(drvdata->dev);
+	pm_runtime_get_sync(dev->parent);
 	spin_lock_irqsave(&drvdata->spinlock, flags);
 	CS_UNLOCK(drvdata->base);
 
@@ -56,7 +56,7 @@ static ssize_t etmsr_show(struct device *dev,
 
 	CS_LOCK(drvdata->base);
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
-	pm_runtime_put(drvdata->dev);
+	pm_runtime_put(dev->parent);
 
 	return sprintf(buf, "%#lx\n", val);
 }
@@ -131,7 +131,7 @@ static ssize_t mode_store(struct device *dev,
 
 	if (config->mode & ETM_MODE_STALL) {
 		if (!(drvdata->etmccr & ETMCCR_FIFOFULL)) {
-			dev_warn(drvdata->dev, "stall mode not supported\n");
+			dev_warn(dev, "stall mode not supported\n");
 			ret = -EINVAL;
 			goto err_unlock;
 		}
@@ -141,7 +141,7 @@ static ssize_t mode_store(struct device *dev,
 
 	if (config->mode & ETM_MODE_TIMESTAMP) {
 		if (!(drvdata->etmccer & ETMCCER_TIMESTAMP)) {
-			dev_warn(drvdata->dev, "timestamp not supported\n");
+			dev_warn(dev, "timestamp not supported\n");
 			ret = -EINVAL;
 			goto err_unlock;
 		}
@@ -945,7 +945,7 @@ static ssize_t seq_curr_state_show(struct device *dev,
 		goto out;
 	}
 
-	pm_runtime_get_sync(drvdata->dev);
+	pm_runtime_get_sync(dev->parent);
 	spin_lock_irqsave(&drvdata->spinlock, flags);
 
 	CS_UNLOCK(drvdata->base);
@@ -953,7 +953,7 @@ static ssize_t seq_curr_state_show(struct device *dev,
 	CS_LOCK(drvdata->base);
 
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
-	pm_runtime_put(drvdata->dev);
+	pm_runtime_put(dev->parent);
 out:
 	return sprintf(buf, "%#lx\n", val);
 }
diff --git a/drivers/hwtracing/coresight/coresight-etm3x.c b/drivers/hwtracing/coresight/coresight-etm3x.c
index be302ec5f66b..e2cb6873c3f2 100644
--- a/drivers/hwtracing/coresight/coresight-etm3x.c
+++ b/drivers/hwtracing/coresight/coresight-etm3x.c
@@ -165,7 +165,7 @@ static void etm_set_prog(struct etm_drvdata *drvdata)
 	 */
 	isb();
 	if (coresight_timeout_etm(drvdata, ETMSR, ETMSR_PROG_BIT, 1)) {
-		dev_err(drvdata->dev,
+		dev_err(&drvdata->csdev->dev,
 			"%s: timeout observed when probing at offset %#x\n",
 			__func__, ETMSR);
 	}
@@ -184,7 +184,7 @@ static void etm_clr_prog(struct etm_drvdata *drvdata)
 	 */
 	isb();
 	if (coresight_timeout_etm(drvdata, ETMSR, ETMSR_PROG_BIT, 0)) {
-		dev_err(drvdata->dev,
+		dev_err(&drvdata->csdev->dev,
 			"%s: timeout observed when probing at offset %#x\n",
 			__func__, ETMSR);
 	}
@@ -425,7 +425,7 @@ static int etm_enable_hw(struct etm_drvdata *drvdata)
 done:
 	CS_LOCK(drvdata->base);
 
-	dev_dbg(drvdata->dev, "cpu: %d enable smp call done: %d\n",
+	dev_dbg(&drvdata->csdev->dev, "cpu: %d enable smp call done: %d\n",
 		drvdata->cpu, rc);
 	return rc;
 }
@@ -455,14 +455,16 @@ int etm_get_trace_id(struct etm_drvdata *drvdata)
 {
 	unsigned long flags;
 	int trace_id = -1;
+	struct device *etm_dev;
 
 	if (!drvdata)
 		goto out;
 
+	etm_dev = drvdata->csdev->dev.parent;
 	if (!local_read(&drvdata->mode))
 		return drvdata->traceid;
 
-	pm_runtime_get_sync(drvdata->dev);
+	pm_runtime_get_sync(etm_dev);
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
 
@@ -471,7 +473,7 @@ int etm_get_trace_id(struct etm_drvdata *drvdata)
 	CS_LOCK(drvdata->base);
 
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
-	pm_runtime_put(drvdata->dev);
+	pm_runtime_put(etm_dev);
 
 out:
 	return trace_id;
@@ -526,7 +528,7 @@ static int etm_enable_sysfs(struct coresight_device *csdev)
 	spin_unlock(&drvdata->spinlock);
 
 	if (!ret)
-		dev_dbg(drvdata->dev, "ETM tracing enabled\n");
+		dev_dbg(&csdev->dev, "ETM tracing enabled\n");
 	return ret;
 }
 
@@ -581,7 +583,8 @@ static void etm_disable_hw(void *info)
 
 	CS_LOCK(drvdata->base);
 
-	dev_dbg(drvdata->dev, "cpu: %d disable smp call done\n", drvdata->cpu);
+	dev_dbg(&drvdata->csdev->dev,
+		"cpu: %d disable smp call done\n", drvdata->cpu);
 }
 
 static void etm_disable_perf(struct coresight_device *csdev)
@@ -628,7 +631,7 @@ static void etm_disable_sysfs(struct coresight_device *csdev)
 	spin_unlock(&drvdata->spinlock);
 	cpus_read_unlock();
 
-	dev_dbg(drvdata->dev, "ETM tracing disabled\n");
+	dev_dbg(&csdev->dev, "ETM tracing disabled\n");
 }
 
 static void etm_disable(struct coresight_device *csdev,
@@ -788,22 +791,12 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id)
 	struct etm_drvdata *drvdata;
 	struct resource *res = &adev->res;
 	struct coresight_desc desc = { 0 };
-	struct device_node *np = adev->dev.of_node;
 
 	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
 	if (!drvdata)
 		return -ENOMEM;
 
-	if (np) {
-		pdata = of_get_coresight_platform_data(dev, np);
-		if (IS_ERR(pdata))
-			return PTR_ERR(pdata);
-
-		adev->dev.platform_data = pdata;
-		drvdata->use_cp14 = of_property_read_bool(np, "arm,cp14");
-	}
-
-	drvdata->dev = &adev->dev;
+	drvdata->use_cp14 = fwnode_property_read_bool(dev->fwnode, "arm,cp14");
 	dev_set_drvdata(dev, drvdata);
 
 	/* Validity for the resource is already checked by the AMBA core */
@@ -822,7 +815,13 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id)
 			return ret;
 	}
 
-	drvdata->cpu = pdata ? pdata->cpu : 0;
+	drvdata->cpu = coresight_get_cpu(dev);
+	if (drvdata->cpu < 0)
+		return drvdata->cpu;
+
+	desc.name  = devm_kasprintf(dev, GFP_KERNEL, "etm%d", drvdata->cpu);
+	if (!desc.name)
+		return -ENOMEM;
 
 	cpus_read_lock();
 	etmdrvdata[drvdata->cpu] = drvdata;
@@ -852,6 +851,13 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id)
 	etm_init_trace_id(drvdata);
 	etm_set_default(&drvdata->config);
 
+	pdata = coresight_get_platform_data(dev);
+	if (IS_ERR(pdata)) {
+		ret = PTR_ERR(pdata);
+		goto err_arch_supported;
+	}
+	adev->dev.platform_data = pdata;
+
 	desc.type = CORESIGHT_DEV_TYPE_SOURCE;
 	desc.subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_PROC;
 	desc.ops = &etm_cs_ops;
@@ -871,7 +877,8 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id)
 	}
 
 	pm_runtime_put(&adev->dev);
-	dev_info(dev, "%s initialized\n", (char *)coresight_get_uci_data(id));
+	dev_info(&drvdata->csdev->dev,
+		 "%s initialized\n", (char *)coresight_get_uci_data(id));
 	if (boot_enable) {
 		coresight_enable(drvdata->csdev);
 		drvdata->boot_enable = true;
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c
index 8bb0092c7ec2..7bcac8896fc1 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -88,6 +88,7 @@ static int etm4_enable_hw(struct etmv4_drvdata *drvdata)
 {
 	int i, rc;
 	struct etmv4_config *config = &drvdata->config;
+	struct device *etm_dev = &drvdata->csdev->dev;
 
 	CS_UNLOCK(drvdata->base);
 
@@ -102,7 +103,7 @@ static int etm4_enable_hw(struct etmv4_drvdata *drvdata)
 
 	/* wait for TRCSTATR.IDLE to go up */
 	if (coresight_timeout(drvdata->base, TRCSTATR, TRCSTATR_IDLE_BIT, 1))
-		dev_err(drvdata->dev,
+		dev_err(etm_dev,
 			"timeout while waiting for Idle Trace Status\n");
 
 	writel_relaxed(config->pe_sel, drvdata->base + TRCPROCSELR);
@@ -184,13 +185,13 @@ static int etm4_enable_hw(struct etmv4_drvdata *drvdata)
 
 	/* wait for TRCSTATR.IDLE to go back down to '0' */
 	if (coresight_timeout(drvdata->base, TRCSTATR, TRCSTATR_IDLE_BIT, 0))
-		dev_err(drvdata->dev,
+		dev_err(etm_dev,
 			"timeout while waiting for Idle Trace Status\n");
 
 done:
 	CS_LOCK(drvdata->base);
 
-	dev_dbg(drvdata->dev, "cpu: %d enable smp call done: %d\n",
+	dev_dbg(etm_dev, "cpu: %d enable smp call done: %d\n",
 		drvdata->cpu, rc);
 	return rc;
 }
@@ -400,7 +401,7 @@ static int etm4_enable_sysfs(struct coresight_device *csdev)
 	spin_unlock(&drvdata->spinlock);
 
 	if (!ret)
-		dev_dbg(drvdata->dev, "ETM tracing enabled\n");
+		dev_dbg(&csdev->dev, "ETM tracing enabled\n");
 	return ret;
 }
 
@@ -461,7 +462,8 @@ static void etm4_disable_hw(void *info)
 
 	CS_LOCK(drvdata->base);
 
-	dev_dbg(drvdata->dev, "cpu: %d disable smp call done\n", drvdata->cpu);
+	dev_dbg(&drvdata->csdev->dev,
+		"cpu: %d disable smp call done\n", drvdata->cpu);
 }
 
 static int etm4_disable_perf(struct coresight_device *csdev,
@@ -511,7 +513,7 @@ static void etm4_disable_sysfs(struct coresight_device *csdev)
 	spin_unlock(&drvdata->spinlock);
 	cpus_read_unlock();
 
-	dev_dbg(drvdata->dev, "ETM tracing disabled\n");
+	dev_dbg(&csdev->dev, "ETM tracing disabled\n");
 }
 
 static void etm4_disable(struct coresight_device *csdev,
@@ -1082,20 +1084,11 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 	struct etmv4_drvdata *drvdata;
 	struct resource *res = &adev->res;
 	struct coresight_desc desc = { 0 };
-	struct device_node *np = adev->dev.of_node;
 
 	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
 	if (!drvdata)
 		return -ENOMEM;
 
-	if (np) {
-		pdata = of_get_coresight_platform_data(dev, np);
-		if (IS_ERR(pdata))
-			return PTR_ERR(pdata);
-		adev->dev.platform_data = pdata;
-	}
-
-	drvdata->dev = &adev->dev;
 	dev_set_drvdata(dev, drvdata);
 
 	/* Validity for the resource is already checked by the AMBA core */
@@ -1107,7 +1100,13 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 
 	spin_lock_init(&drvdata->spinlock);
 
-	drvdata->cpu = pdata ? pdata->cpu : 0;
+	drvdata->cpu = coresight_get_cpu(dev);
+	if (drvdata->cpu < 0)
+		return drvdata->cpu;
+
+	desc.name = devm_kasprintf(dev, GFP_KERNEL, "etm%d", drvdata->cpu);
+	if (!desc.name)
+		return -ENOMEM;
 
 	cpus_read_lock();
 	etmdrvdata[drvdata->cpu] = drvdata;
@@ -1138,6 +1137,13 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 	etm4_init_trace_id(drvdata);
 	etm4_set_default(&drvdata->config);
 
+	pdata = coresight_get_platform_data(dev);
+	if (IS_ERR(pdata)) {
+		ret = PTR_ERR(pdata);
+		goto err_arch_supported;
+	}
+	adev->dev.platform_data = pdata;
+
 	desc.type = CORESIGHT_DEV_TYPE_SOURCE;
 	desc.subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_PROC;
 	desc.ops = &etm4_cs_ops;
@@ -1157,7 +1163,7 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 	}
 
 	pm_runtime_put(&adev->dev);
-	dev_info(dev, "CPU%d: ETM v%d.%d initialized\n",
+	dev_info(&drvdata->csdev->dev, "CPU%d: ETM v%d.%d initialized\n",
 		 drvdata->cpu, drvdata->arch >> 4, drvdata->arch & 0xf);
 
 	if (boot_enable) {
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h
index 52786e9d8926..4523f10ddd0f 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.h
+++ b/drivers/hwtracing/coresight/coresight-etm4x.h
@@ -284,7 +284,6 @@ struct etmv4_config {
 /**
  * struct etm4_drvdata - specifics associated to an ETM component
  * @base:       Memory mapped base address for this component.
- * @dev:        The device entity associated to this component.
  * @csdev:      Component vitals needed by the framework.
  * @spinlock:   Only one at a time pls.
  * @mode:	This tracer's mode, i.e sysFS, Perf or disabled.
@@ -340,7 +339,6 @@ struct etmv4_config {
  */
 struct etmv4_drvdata {
 	void __iomem			*base;
-	struct device			*dev;
 	struct coresight_device		*csdev;
 	spinlock_t			spinlock;
 	local_t				mode;
diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c
index 16b0c0e1e43a..fa97cb9ab4f9 100644
--- a/drivers/hwtracing/coresight/coresight-funnel.c
+++ b/drivers/hwtracing/coresight/coresight-funnel.c
@@ -29,17 +29,17 @@
 #define FUNNEL_HOLDTIME		(0x7 << FUNNEL_HOLDTIME_SHFT)
 #define FUNNEL_ENSx_MASK	0xff
 
+DEFINE_CORESIGHT_DEVLIST(funnel_devs, "funnel");
+
 /**
  * struct funnel_drvdata - specifics associated to a funnel component
  * @base:	memory mapped base address for this component.
- * @dev:	the device entity associated to this component.
  * @atclk:	optional clock for the core parts of the funnel.
  * @csdev:	component vitals needed by the framework.
  * @priority:	port selection order.
  */
 struct funnel_drvdata {
 	void __iomem		*base;
-	struct device		*dev;
 	struct clk		*atclk;
 	struct coresight_device	*csdev;
 	unsigned long		priority;
@@ -80,7 +80,7 @@ static int funnel_enable(struct coresight_device *csdev, int inport,
 		rc = dynamic_funnel_enable_hw(drvdata, inport);
 
 	if (!rc)
-		dev_dbg(drvdata->dev, "FUNNEL inport %d enabled\n", inport);
+		dev_dbg(&csdev->dev, "FUNNEL inport %d enabled\n", inport);
 	return rc;
 }
 
@@ -110,7 +110,7 @@ static void funnel_disable(struct coresight_device *csdev, int inport,
 	if (drvdata->base)
 		dynamic_funnel_disable_hw(drvdata, inport);
 
-	dev_dbg(drvdata->dev, "FUNNEL inport %d disabled\n", inport);
+	dev_dbg(&csdev->dev, "FUNNEL inport %d disabled\n", inport);
 }
 
 static const struct coresight_ops_link funnel_link_ops = {
@@ -165,11 +165,11 @@ static ssize_t funnel_ctrl_show(struct device *dev,
 	u32 val;
 	struct funnel_drvdata *drvdata = dev_get_drvdata(dev->parent);
 
-	pm_runtime_get_sync(drvdata->dev);
+	pm_runtime_get_sync(dev->parent);
 
 	val = get_funnel_ctrl_hw(drvdata);
 
-	pm_runtime_put(drvdata->dev);
+	pm_runtime_put(dev->parent);
 
 	return sprintf(buf, "%#x\n", val);
 }
@@ -189,23 +189,19 @@ static int funnel_probe(struct device *dev, struct resource *res)
 	struct coresight_platform_data *pdata = NULL;
 	struct funnel_drvdata *drvdata;
 	struct coresight_desc desc = { 0 };
-	struct device_node *np = dev->of_node;
-
-	if (np) {
-		pdata = of_get_coresight_platform_data(dev, np);
-		if (IS_ERR(pdata))
-			return PTR_ERR(pdata);
-		dev->platform_data = pdata;
-	}
 
-	if (of_device_is_compatible(np, "arm,coresight-funnel"))
+	if (is_of_node(dev_fwnode(dev)) &&
+	    of_device_is_compatible(dev->of_node, "arm,coresight-funnel"))
 		pr_warn_once("Uses OBSOLETE CoreSight funnel binding\n");
 
+	desc.name = coresight_alloc_device_name(&funnel_devs, dev);
+	if (!desc.name)
+		return -ENOMEM;
+
 	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
 	if (!drvdata)
 		return -ENOMEM;
 
-	drvdata->dev = dev;
 	drvdata->atclk = devm_clk_get(dev, "atclk"); /* optional */
 	if (!IS_ERR(drvdata->atclk)) {
 		ret = clk_prepare_enable(drvdata->atclk);
@@ -229,6 +225,13 @@ static int funnel_probe(struct device *dev, struct resource *res)
 
 	dev_set_drvdata(dev, drvdata);
 
+	pdata = coresight_get_platform_data(dev);
+	if (IS_ERR(pdata)) {
+		ret = PTR_ERR(pdata);
+		goto out_disable_clk;
+	}
+	dev->platform_data = pdata;
+
 	desc.type = CORESIGHT_DEV_TYPE_LINK;
 	desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_MERG;
 	desc.ops = &funnel_cs_ops;
@@ -241,6 +244,7 @@ static int funnel_probe(struct device *dev, struct resource *res)
 	}
 
 	pm_runtime_put(dev);
+	ret = 0;
 
 out_disable_clk:
 	if (ret && !IS_ERR_OR_NULL(drvdata->atclk))
diff --git a/drivers/hwtracing/coresight/coresight-platform.c b/drivers/hwtracing/coresight/coresight-platform.c
new file mode 100644
index 000000000000..cf580ffbc27c
--- /dev/null
+++ b/drivers/hwtracing/coresight/coresight-platform.c
@@ -0,0 +1,815 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/acpi.h>
+#include <linux/types.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_graph.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/amba/bus.h>
+#include <linux/coresight.h>
+#include <linux/cpumask.h>
+#include <asm/smp_plat.h>
+
+#include "coresight-priv.h"
+/*
+ * coresight_alloc_conns: Allocate connections record for each output
+ * port from the device.
+ */
+static int coresight_alloc_conns(struct device *dev,
+				 struct coresight_platform_data *pdata)
+{
+	if (pdata->nr_outport) {
+		pdata->conns = devm_kzalloc(dev, pdata->nr_outport *
+					    sizeof(*pdata->conns),
+					    GFP_KERNEL);
+		if (!pdata->conns)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+int coresight_device_fwnode_match(struct device *dev, void *fwnode)
+{
+	return dev_fwnode(dev) == fwnode;
+}
+
+static struct device *
+coresight_find_device_by_fwnode(struct fwnode_handle *fwnode)
+{
+	struct device *dev = NULL;
+
+	/*
+	 * If we have a non-configurable replicator, it will be found on the
+	 * platform bus.
+	 */
+	dev = bus_find_device(&platform_bus_type, NULL,
+			      fwnode, coresight_device_fwnode_match);
+	if (dev)
+		return dev;
+
+	/*
+	 * We have a configurable component - circle through the AMBA bus
+	 * looking for the device that matches the endpoint node.
+	 */
+	return bus_find_device(&amba_bustype, NULL,
+			       fwnode, coresight_device_fwnode_match);
+}
+
+#ifdef CONFIG_OF
+static inline bool of_coresight_legacy_ep_is_input(struct device_node *ep)
+{
+	return of_property_read_bool(ep, "slave-mode");
+}
+
+static void of_coresight_get_ports_legacy(const struct device_node *node,
+					  int *nr_inport, int *nr_outport)
+{
+	struct device_node *ep = NULL;
+	int in = 0, out = 0;
+
+	do {
+		ep = of_graph_get_next_endpoint(node, ep);
+		if (!ep)
+			break;
+
+		if (of_coresight_legacy_ep_is_input(ep))
+			in++;
+		else
+			out++;
+
+	} while (ep);
+
+	*nr_inport = in;
+	*nr_outport = out;
+}
+
+static struct device_node *of_coresight_get_port_parent(struct device_node *ep)
+{
+	struct device_node *parent = of_graph_get_port_parent(ep);
+
+	/*
+	 * Skip one-level up to the real device node, if we
+	 * are using the new bindings.
+	 */
+	if (of_node_name_eq(parent, "in-ports") ||
+	    of_node_name_eq(parent, "out-ports"))
+		parent = of_get_next_parent(parent);
+
+	return parent;
+}
+
+static inline struct device_node *
+of_coresight_get_input_ports_node(const struct device_node *node)
+{
+	return of_get_child_by_name(node, "in-ports");
+}
+
+static inline struct device_node *
+of_coresight_get_output_ports_node(const struct device_node *node)
+{
+	return of_get_child_by_name(node, "out-ports");
+}
+
+static inline int
+of_coresight_count_ports(struct device_node *port_parent)
+{
+	int i = 0;
+	struct device_node *ep = NULL;
+
+	while ((ep = of_graph_get_next_endpoint(port_parent, ep)))
+		i++;
+	return i;
+}
+
+static void of_coresight_get_ports(const struct device_node *node,
+				   int *nr_inport, int *nr_outport)
+{
+	struct device_node *input_ports = NULL, *output_ports = NULL;
+
+	input_ports = of_coresight_get_input_ports_node(node);
+	output_ports = of_coresight_get_output_ports_node(node);
+
+	if (input_ports || output_ports) {
+		if (input_ports) {
+			*nr_inport = of_coresight_count_ports(input_ports);
+			of_node_put(input_ports);
+		}
+		if (output_ports) {
+			*nr_outport = of_coresight_count_ports(output_ports);
+			of_node_put(output_ports);
+		}
+	} else {
+		/* Fall back to legacy DT bindings parsing */
+		of_coresight_get_ports_legacy(node, nr_inport, nr_outport);
+	}
+}
+
+static int of_coresight_get_cpu(struct device *dev)
+{
+	int cpu;
+	struct device_node *dn;
+
+	if (!dev->of_node)
+		return -ENODEV;
+
+	dn = of_parse_phandle(dev->of_node, "cpu", 0);
+	if (!dn)
+		return -ENODEV;
+
+	cpu = of_cpu_node_to_id(dn);
+	of_node_put(dn);
+
+	return cpu;
+}
+
+/*
+ * of_coresight_parse_endpoint : Parse the given output endpoint @ep
+ * and fill the connection information in @conn
+ *
+ * Parses the local port, remote device name and the remote port.
+ *
+ * Returns :
+ *	 1	- If the parsing is successful and a connection record
+ *		  was created for an output connection.
+ *	 0	- If the parsing completed without any fatal errors.
+ *	-Errno	- Fatal error, abort the scanning.
+ */
+static int of_coresight_parse_endpoint(struct device *dev,
+				       struct device_node *ep,
+				       struct coresight_connection *conn)
+{
+	int ret = 0;
+	struct of_endpoint endpoint, rendpoint;
+	struct device_node *rparent = NULL;
+	struct device_node *rep = NULL;
+	struct device *rdev = NULL;
+	struct fwnode_handle *rdev_fwnode;
+
+	do {
+		/* Parse the local port details */
+		if (of_graph_parse_endpoint(ep, &endpoint))
+			break;
+		/*
+		 * Get a handle on the remote endpoint and the device it is
+		 * attached to.
+		 */
+		rep = of_graph_get_remote_endpoint(ep);
+		if (!rep)
+			break;
+		rparent = of_coresight_get_port_parent(rep);
+		if (!rparent)
+			break;
+		if (of_graph_parse_endpoint(rep, &rendpoint))
+			break;
+
+		rdev_fwnode = of_fwnode_handle(rparent);
+		/* If the remote device is not available, defer probing */
+		rdev = coresight_find_device_by_fwnode(rdev_fwnode);
+		if (!rdev) {
+			ret = -EPROBE_DEFER;
+			break;
+		}
+
+		conn->outport = endpoint.port;
+		/*
+		 * Hold the refcount to the target device. This could be
+		 * released via:
+		 * 1) coresight_release_platform_data() if the probe fails or
+		 *    this device is unregistered.
+		 * 2) While removing the target device via
+		 *    coresight_remove_match()
+		 */
+		conn->child_fwnode = fwnode_handle_get(rdev_fwnode);
+		conn->child_port = rendpoint.port;
+		/* Connection record updated */
+		ret = 1;
+	} while (0);
+
+	of_node_put(rparent);
+	of_node_put(rep);
+	put_device(rdev);
+
+	return ret;
+}
+
+static int of_get_coresight_platform_data(struct device *dev,
+					  struct coresight_platform_data *pdata)
+{
+	int ret = 0;
+	struct coresight_connection *conn;
+	struct device_node *ep = NULL;
+	const struct device_node *parent = NULL;
+	bool legacy_binding = false;
+	struct device_node *node = dev->of_node;
+
+	/* Get the number of input and output port for this component */
+	of_coresight_get_ports(node, &pdata->nr_inport, &pdata->nr_outport);
+
+	/* If there are no output connections, we are done */
+	if (!pdata->nr_outport)
+		return 0;
+
+	ret = coresight_alloc_conns(dev, pdata);
+	if (ret)
+		return ret;
+
+	parent = of_coresight_get_output_ports_node(node);
+	/*
+	 * If the DT uses obsoleted bindings, the ports are listed
+	 * under the device and we need to filter out the input
+	 * ports.
+	 */
+	if (!parent) {
+		legacy_binding = true;
+		parent = node;
+		dev_warn_once(dev, "Uses obsolete Coresight DT bindings\n");
+	}
+
+	conn = pdata->conns;
+
+	/* Iterate through each output port to discover topology */
+	while ((ep = of_graph_get_next_endpoint(parent, ep))) {
+		/*
+		 * Legacy binding mixes input/output ports under the
+		 * same parent. So, skip the input ports if we are dealing
+		 * with legacy binding, as they processed with their
+		 * connected output ports.
+		 */
+		if (legacy_binding && of_coresight_legacy_ep_is_input(ep))
+			continue;
+
+		ret = of_coresight_parse_endpoint(dev, ep, conn);
+		switch (ret) {
+		case 1:
+			conn++;		/* Fall through */
+		case 0:
+			break;
+		default:
+			return ret;
+		}
+	}
+
+	return 0;
+}
+#else
+static inline int
+of_get_coresight_platform_data(struct device *dev,
+			       struct coresight_platform_data *pdata)
+{
+	return -ENOENT;
+}
+
+static inline int of_coresight_get_cpu(struct device *dev)
+{
+	return -ENODEV;
+}
+#endif
+
+#ifdef CONFIG_ACPI
+
+#include <acpi/actypes.h>
+#include <acpi/processor.h>
+
+/* ACPI Graph _DSD UUID : "ab02a46b-74c7-45a2-bd68-f7d344ef2153" */
+static const guid_t acpi_graph_uuid = GUID_INIT(0xab02a46b, 0x74c7, 0x45a2,
+						0xbd, 0x68, 0xf7, 0xd3,
+						0x44, 0xef, 0x21, 0x53);
+/* Coresight ACPI Graph UUID : "3ecbc8b6-1d0e-4fb3-8107-e627f805c6cd" */
+static const guid_t coresight_graph_uuid = GUID_INIT(0x3ecbc8b6, 0x1d0e, 0x4fb3,
+						     0x81, 0x07, 0xe6, 0x27,
+						     0xf8, 0x05, 0xc6, 0xcd);
+#define ACPI_CORESIGHT_LINK_SLAVE	0
+#define ACPI_CORESIGHT_LINK_MASTER	1
+
+static inline bool is_acpi_guid(const union acpi_object *obj)
+{
+	return (obj->type == ACPI_TYPE_BUFFER) && (obj->buffer.length == 16);
+}
+
+/*
+ * acpi_guid_matches	- Checks if the given object is a GUID object and
+ * that it matches the supplied the GUID.
+ */
+static inline bool acpi_guid_matches(const union acpi_object *obj,
+				   const guid_t *guid)
+{
+	return is_acpi_guid(obj) &&
+	       guid_equal((guid_t *)obj->buffer.pointer, guid);
+}
+
+static inline bool is_acpi_dsd_graph_guid(const union acpi_object *obj)
+{
+	return acpi_guid_matches(obj, &acpi_graph_uuid);
+}
+
+static inline bool is_acpi_coresight_graph_guid(const union acpi_object *obj)
+{
+	return acpi_guid_matches(obj, &coresight_graph_uuid);
+}
+
+static inline bool is_acpi_coresight_graph(const union acpi_object *obj)
+{
+	const union acpi_object *graphid, *guid, *links;
+
+	if (obj->type != ACPI_TYPE_PACKAGE ||
+	    obj->package.count < 3)
+		return false;
+
+	graphid = &obj->package.elements[0];
+	guid = &obj->package.elements[1];
+	links = &obj->package.elements[2];
+
+	if (graphid->type != ACPI_TYPE_INTEGER ||
+	    links->type != ACPI_TYPE_INTEGER)
+		return false;
+
+	return is_acpi_coresight_graph_guid(guid);
+}
+
+/*
+ * acpi_validate_dsd_graph	- Make sure the given _DSD graph conforms
+ * to the ACPI _DSD Graph specification.
+ *
+ * ACPI Devices Graph property has the following format:
+ *  {
+ *	Revision	- Integer, must be 0
+ *	NumberOfGraphs	- Integer, N indicating the following list.
+ *	Graph[1],
+ *	 ...
+ *	Graph[N]
+ *  }
+ *
+ * And each Graph entry has the following format:
+ *  {
+ *	GraphID		- Integer, identifying a graph the device belongs to.
+ *	UUID		- UUID identifying the specification that governs
+ *			  this graph. (e.g, see is_acpi_coresight_graph())
+ *	NumberOfLinks	- Number "N" of connections on this node of the graph.
+ *	Links[1]
+ *	...
+ *	Links[N]
+ *  }
+ *
+ * Where each "Links" entry has the following format:
+ *
+ * {
+ *	SourcePortAddress	- Integer
+ *	DestinationPortAddress	- Integer
+ *	DestinationDeviceName	- Reference to another device
+ *	( --- CoreSight specific extensions below ---)
+ *	DirectionOfFlow		- Integer 1 for output(master)
+ *				  0 for input(slave)
+ * }
+ *
+ * e.g:
+ * For a Funnel device
+ *
+ * Device(MFUN) {
+ *   ...
+ *
+ *   Name (_DSD, Package() {
+ *	// DSD Package contains tuples of {  Proeprty_Type_UUID, Package() }
+ *	ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"), //Std. Property UUID
+ *	Package() {
+ *		Package(2) { "property-name", <property-value> }
+ *	},
+ *
+ *	ToUUID("ab02a46b-74c7-45a2-bd68-f7d344ef2153"), // ACPI Graph UUID
+ *	Package() {
+ *	  0,		// Revision
+ *	  1,		// NumberOfGraphs.
+ *	  Package() {	// Graph[0] Package
+ *	     1,		// GraphID
+ *	     // Coresight Graph UUID
+ *	     ToUUID("3ecbc8b6-1d0e-4fb3-8107-e627f805c6cd"),
+ *	     3,		// NumberOfLinks aka ports
+ *	     // Link[0]: Output_0 -> Replicator:Input_0
+ *	     Package () { 0, 0, \_SB_.RPL0, 1 },
+ *	     // Link[1]: Input_0 <- Cluster0_Funnel0:Output_0
+ *	     Package () { 0, 0, \_SB_.CLU0.FUN0, 0 },
+ *	     // Link[2]: Input_1 <- Cluster1_Funnel0:Output_0
+ *	      Package () { 1, 0, \_SB_.CLU1.FUN0, 0 },
+ *	  }	// End of Graph[0] Package
+ *
+ *	}, // End of ACPI Graph Property
+ *  })
+ */
+static inline bool acpi_validate_dsd_graph(const union acpi_object *graph)
+{
+	int i, n;
+	const union acpi_object *rev, *nr_graphs;
+
+	/* The graph must contain at least the Revision and Number of Graphs */
+	if (graph->package.count < 2)
+		return false;
+
+	rev = &graph->package.elements[0];
+	nr_graphs = &graph->package.elements[1];
+
+	if (rev->type != ACPI_TYPE_INTEGER ||
+	    nr_graphs->type != ACPI_TYPE_INTEGER)
+		return false;
+
+	/* We only support revision 0 */
+	if (rev->integer.value != 0)
+		return false;
+
+	n = nr_graphs->integer.value;
+	/* CoreSight devices are only part of a single Graph */
+	if (n != 1)
+		return false;
+
+	/* Make sure the ACPI graph package has right number of elements */
+	if (graph->package.count != (n + 2))
+		return false;
+
+	/*
+	 * Each entry must be a graph package with at least 3 members :
+	 * { GraphID, UUID, NumberOfLinks(n), Links[.],... }
+	 */
+	for (i = 2; i < n + 2; i++) {
+		const union acpi_object *obj = &graph->package.elements[i];
+
+		if (obj->type != ACPI_TYPE_PACKAGE ||
+		    obj->package.count < 3)
+			return false;
+	}
+
+	return true;
+}
+
+/* acpi_get_dsd_graph	- Find the _DSD Graph property for the given device. */
+const union acpi_object *
+acpi_get_dsd_graph(struct acpi_device *adev)
+{
+	int i;
+	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER };
+	acpi_status status;
+	const union acpi_object *dsd;
+
+	status = acpi_evaluate_object_typed(adev->handle, "_DSD", NULL,
+					    &buf, ACPI_TYPE_PACKAGE);
+	if (ACPI_FAILURE(status))
+		return NULL;
+
+	dsd = buf.pointer;
+
+	/*
+	 * _DSD property consists tuples { Prop_UUID, Package() }
+	 * Iterate through all the packages and find the Graph.
+	 */
+	for (i = 0; i + 1 < dsd->package.count; i += 2) {
+		const union acpi_object *guid, *package;
+
+		guid = &dsd->package.elements[i];
+		package = &dsd->package.elements[i + 1];
+
+		/* All _DSD elements must have a UUID and a Package */
+		if (!is_acpi_guid(guid) || package->type != ACPI_TYPE_PACKAGE)
+			break;
+		/* Skip the non-Graph _DSD packages */
+		if (!is_acpi_dsd_graph_guid(guid))
+			continue;
+		if (acpi_validate_dsd_graph(package))
+			return package;
+		/* Invalid graph format, continue */
+		dev_warn(&adev->dev, "Invalid Graph _DSD property\n");
+	}
+
+	return NULL;
+}
+
+static inline bool
+acpi_validate_coresight_graph(const union acpi_object *cs_graph)
+{
+	int nlinks;
+
+	nlinks = cs_graph->package.elements[2].integer.value;
+	/*
+	 * Graph must have the following fields :
+	 * { GraphID, GraphUUID, NumberOfLinks, Links... }
+	 */
+	if (cs_graph->package.count != (nlinks + 3))
+		return false;
+	/* The links are validated in acpi_coresight_parse_link() */
+	return true;
+}
+
+/*
+ * acpi_get_coresight_graph	- Parse the device _DSD tables and find
+ * the Graph property matching the CoreSight Graphs.
+ *
+ * Returns the pointer to the CoreSight Graph Package when found. Otherwise
+ * returns NULL.
+ */
+const union acpi_object *
+acpi_get_coresight_graph(struct acpi_device *adev)
+{
+	const union acpi_object *graph_list, *graph;
+	int i, nr_graphs;
+
+	graph_list = acpi_get_dsd_graph(adev);
+	if (!graph_list)
+		return graph_list;
+
+	nr_graphs = graph_list->package.elements[1].integer.value;
+
+	for (i = 2; i < nr_graphs + 2; i++) {
+		graph = &graph_list->package.elements[i];
+		if (!is_acpi_coresight_graph(graph))
+			continue;
+		if (acpi_validate_coresight_graph(graph))
+			return graph;
+		/* Invalid graph format */
+		break;
+	}
+
+	return NULL;
+}
+
+/*
+ * acpi_coresight_parse_link	- Parse the given Graph connection
+ * of the device and populate the coresight_connection for an output
+ * connection.
+ *
+ * CoreSight Graph specification mandates that the direction of the data
+ * flow must be specified in the link. i.e,
+ *
+ *	SourcePortAddress,	// Integer
+ *	DestinationPortAddress,	// Integer
+ *	DestinationDeviceName,	// Reference to another device
+ *	DirectionOfFlow,	// 1 for output(master), 0 for input(slave)
+ *
+ * Returns the direction of the data flow [ Input(slave) or Output(master) ]
+ * upon success.
+ * Returns an negative error number otherwise.
+ */
+static int acpi_coresight_parse_link(struct acpi_device *adev,
+				     const union acpi_object *link,
+				     struct coresight_connection *conn)
+{
+	int rc, dir;
+	const union acpi_object *fields;
+	struct acpi_device *r_adev;
+	struct device *rdev;
+
+	if (link->type != ACPI_TYPE_PACKAGE ||
+	    link->package.count != 4)
+		return -EINVAL;
+
+	fields = link->package.elements;
+
+	if (fields[0].type != ACPI_TYPE_INTEGER ||
+	    fields[1].type != ACPI_TYPE_INTEGER ||
+	    fields[2].type != ACPI_TYPE_LOCAL_REFERENCE ||
+	    fields[3].type != ACPI_TYPE_INTEGER)
+		return -EINVAL;
+
+	rc = acpi_bus_get_device(fields[2].reference.handle, &r_adev);
+	if (rc)
+		return rc;
+
+	dir = fields[3].integer.value;
+	if (dir == ACPI_CORESIGHT_LINK_MASTER) {
+		conn->outport = fields[0].integer.value;
+		conn->child_port = fields[1].integer.value;
+		rdev = coresight_find_device_by_fwnode(&r_adev->fwnode);
+		if (!rdev)
+			return -EPROBE_DEFER;
+		/*
+		 * Hold the refcount to the target device. This could be
+		 * released via:
+		 * 1) coresight_release_platform_data() if the probe fails or
+		 *    this device is unregistered.
+		 * 2) While removing the target device via
+		 *    coresight_remove_match().
+		 */
+		conn->child_fwnode = fwnode_handle_get(&r_adev->fwnode);
+	}
+
+	return dir;
+}
+
+/*
+ * acpi_coresight_parse_graph	- Parse the _DSD CoreSight graph
+ * connection information and populate the supplied coresight_platform_data
+ * instance.
+ */
+static int acpi_coresight_parse_graph(struct acpi_device *adev,
+				      struct coresight_platform_data *pdata)
+{
+	int rc, i, nlinks;
+	const union acpi_object *graph;
+	struct coresight_connection *conns, *ptr;
+
+	pdata->nr_inport = pdata->nr_outport = 0;
+	graph = acpi_get_coresight_graph(adev);
+	if (!graph)
+		return -ENOENT;
+
+	nlinks = graph->package.elements[2].integer.value;
+	if (!nlinks)
+		return 0;
+
+	/*
+	 * To avoid scanning the table twice (once for finding the number of
+	 * output links and then later for parsing the output links),
+	 * cache the links information in one go and then later copy
+	 * it to the pdata.
+	 */
+	conns = devm_kcalloc(&adev->dev, nlinks, sizeof(*conns), GFP_KERNEL);
+	if (!conns)
+		return -ENOMEM;
+	ptr = conns;
+	for (i = 0; i < nlinks; i++) {
+		const union acpi_object *link = &graph->package.elements[3 + i];
+		int dir;
+
+		dir = acpi_coresight_parse_link(adev, link, ptr);
+		if (dir < 0)
+			return dir;
+
+		if (dir == ACPI_CORESIGHT_LINK_MASTER) {
+			pdata->nr_outport++;
+			ptr++;
+		} else {
+			pdata->nr_inport++;
+		}
+	}
+
+	rc = coresight_alloc_conns(&adev->dev, pdata);
+	if (rc)
+		return rc;
+
+	/* Copy the connection information to the final location */
+	for (i = 0; i < pdata->nr_outport; i++)
+		pdata->conns[i] = conns[i];
+
+	devm_kfree(&adev->dev, conns);
+	return 0;
+}
+
+/*
+ * acpi_handle_to_logical_cpuid - Map a given acpi_handle to the
+ * logical CPU id of the corresponding CPU device.
+ *
+ * Returns the logical CPU id when found. Otherwise returns >= nr_cpus_id.
+ */
+static int
+acpi_handle_to_logical_cpuid(acpi_handle handle)
+{
+	int i;
+	struct acpi_processor *pr;
+
+	for_each_possible_cpu(i) {
+		pr = per_cpu(processors, i);
+		if (pr && pr->handle == handle)
+			break;
+	}
+
+	return i;
+}
+
+/*
+ * acpi_coresigh_get_cpu - Find the logical CPU id of the CPU associated
+ * with this coresight device. With ACPI bindings, the CoreSight components
+ * are listed as child device of the associated CPU.
+ *
+ * Returns the logical CPU id when found. Otherwise returns 0.
+ */
+static int acpi_coresight_get_cpu(struct device *dev)
+{
+	int cpu;
+	acpi_handle cpu_handle;
+	acpi_status status;
+	struct acpi_device *adev = ACPI_COMPANION(dev);
+
+	if (!adev)
+		return -ENODEV;
+	status = acpi_get_parent(adev->handle, &cpu_handle);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	cpu = acpi_handle_to_logical_cpuid(cpu_handle);
+	if (cpu >= nr_cpu_ids)
+		return -ENODEV;
+	return cpu;
+}
+
+static int
+acpi_get_coresight_platform_data(struct device *dev,
+				 struct coresight_platform_data *pdata)
+{
+	struct acpi_device *adev;
+
+	adev = ACPI_COMPANION(dev);
+	if (!adev)
+		return -EINVAL;
+
+	return acpi_coresight_parse_graph(adev, pdata);
+}
+
+#else
+
+static inline int
+acpi_get_coresight_platform_data(struct device *dev,
+				 struct coresight_platform_data *pdata)
+{
+	return -ENOENT;
+}
+
+static inline int acpi_coresight_get_cpu(struct device *dev)
+{
+	return -ENODEV;
+}
+#endif
+
+int coresight_get_cpu(struct device *dev)
+{
+	if (is_of_node(dev->fwnode))
+		return of_coresight_get_cpu(dev);
+	else if (is_acpi_device_node(dev->fwnode))
+		return acpi_coresight_get_cpu(dev);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(coresight_get_cpu);
+
+struct coresight_platform_data *
+coresight_get_platform_data(struct device *dev)
+{
+	int ret = -ENOENT;
+	struct coresight_platform_data *pdata = NULL;
+	struct fwnode_handle *fwnode = dev_fwnode(dev);
+
+	if (IS_ERR_OR_NULL(fwnode))
+		goto error;
+
+	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	if (is_of_node(fwnode))
+		ret = of_get_coresight_platform_data(dev, pdata);
+	else if (is_acpi_device_node(fwnode))
+		ret = acpi_get_coresight_platform_data(dev, pdata);
+
+	if (!ret)
+		return pdata;
+error:
+	if (!IS_ERR_OR_NULL(pdata))
+		/* Cleanup the connection information */
+		coresight_release_platform_data(pdata);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(coresight_get_platform_data);
diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h
index e0684d06e9ee..8b07fe55395a 100644
--- a/drivers/hwtracing/coresight/coresight-priv.h
+++ b/drivers/hwtracing/coresight/coresight-priv.h
@@ -200,4 +200,8 @@ static inline void *coresight_get_uci_data(const struct amba_id *id)
 	return 0;
 }
 
+void coresight_release_platform_data(struct coresight_platform_data *pdata);
+
+int coresight_device_fwnode_match(struct device *dev, void *fwnode);
+
 #endif
diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c
index 8c9ce74498e1..b7d6d59d56db 100644
--- a/drivers/hwtracing/coresight/coresight-replicator.c
+++ b/drivers/hwtracing/coresight/coresight-replicator.c
@@ -5,6 +5,7 @@
  * Description: CoreSight Replicator driver
  */
 
+#include <linux/acpi.h>
 #include <linux/amba/bus.h>
 #include <linux/kernel.h>
 #include <linux/device.h>
@@ -22,17 +23,17 @@
 #define REPLICATOR_IDFILTER0		0x000
 #define REPLICATOR_IDFILTER1		0x004
 
+DEFINE_CORESIGHT_DEVLIST(replicator_devs, "replicator");
+
 /**
  * struct replicator_drvdata - specifics associated to a replicator component
  * @base:	memory mapped base address for this component. Also indicates
  *		whether this one is programmable or not.
- * @dev:	the device entity associated with this component
  * @atclk:	optional clock for the core parts of the replicator.
  * @csdev:	component vitals needed by the framework
  */
 struct replicator_drvdata {
 	void __iomem		*base;
-	struct device		*dev;
 	struct clk		*atclk;
 	struct coresight_device	*csdev;
 };
@@ -100,7 +101,7 @@ static int replicator_enable(struct coresight_device *csdev, int inport,
 	if (drvdata->base)
 		rc = dynamic_replicator_enable(drvdata, inport, outport);
 	if (!rc)
-		dev_dbg(drvdata->dev, "REPLICATOR enabled\n");
+		dev_dbg(&csdev->dev, "REPLICATOR enabled\n");
 	return rc;
 }
 
@@ -139,7 +140,7 @@ static void replicator_disable(struct coresight_device *csdev, int inport,
 
 	if (drvdata->base)
 		dynamic_replicator_disable(drvdata, inport, outport);
-	dev_dbg(drvdata->dev, "REPLICATOR disabled\n");
+	dev_dbg(&csdev->dev, "REPLICATOR disabled\n");
 }
 
 static const struct coresight_ops_link replicator_link_ops = {
@@ -179,24 +180,20 @@ static int replicator_probe(struct device *dev, struct resource *res)
 	struct coresight_platform_data *pdata = NULL;
 	struct replicator_drvdata *drvdata;
 	struct coresight_desc desc = { 0 };
-	struct device_node *np = dev->of_node;
 	void __iomem *base;
 
-	if (np) {
-		pdata = of_get_coresight_platform_data(dev, np);
-		if (IS_ERR(pdata))
-			return PTR_ERR(pdata);
-		dev->platform_data = pdata;
-	}
-
-	if (of_device_is_compatible(np, "arm,coresight-replicator"))
+	if (is_of_node(dev_fwnode(dev)) &&
+	    of_device_is_compatible(dev->of_node, "arm,coresight-replicator"))
 		pr_warn_once("Uses OBSOLETE CoreSight replicator binding\n");
 
+	desc.name = coresight_alloc_device_name(&replicator_devs, dev);
+	if (!desc.name)
+		return -ENOMEM;
+
 	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
 	if (!drvdata)
 		return -ENOMEM;
 
-	drvdata->dev = dev;
 	drvdata->atclk = devm_clk_get(dev, "atclk"); /* optional */
 	if (!IS_ERR(drvdata->atclk)) {
 		ret = clk_prepare_enable(drvdata->atclk);
@@ -220,11 +217,19 @@ static int replicator_probe(struct device *dev, struct resource *res)
 
 	dev_set_drvdata(dev, drvdata);
 
+	pdata = coresight_get_platform_data(dev);
+	if (IS_ERR(pdata)) {
+		ret = PTR_ERR(pdata);
+		goto out_disable_clk;
+	}
+	dev->platform_data = pdata;
+
 	desc.type = CORESIGHT_DEV_TYPE_LINK;
 	desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_SPLIT;
 	desc.ops = &replicator_cs_ops;
 	desc.pdata = dev->platform_data;
 	desc.dev = dev;
+
 	drvdata->csdev = coresight_register(&desc);
 	if (IS_ERR(drvdata->csdev)) {
 		ret = PTR_ERR(drvdata->csdev);
@@ -292,11 +297,19 @@ static const struct of_device_id static_replicator_match[] = {
 	{}
 };
 
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id static_replicator_acpi_ids[] = {
+	{"ARMHC985", 0}, /* ARM CoreSight Static Replicator */
+	{}
+};
+#endif
+
 static struct platform_driver static_replicator_driver = {
 	.probe          = static_replicator_probe,
 	.driver         = {
 		.name   = "coresight-static-replicator",
-		.of_match_table = static_replicator_match,
+		.of_match_table = of_match_ptr(static_replicator_match),
+		.acpi_match_table = ACPI_PTR(static_replicator_acpi_ids),
 		.pm	= &replicator_dev_pm_ops,
 		.suppress_bind_attrs = true,
 	},
diff --git a/drivers/hwtracing/coresight/coresight-stm.c b/drivers/hwtracing/coresight/coresight-stm.c
index 9f8a844ed7aa..b908ca104645 100644
--- a/drivers/hwtracing/coresight/coresight-stm.c
+++ b/drivers/hwtracing/coresight/coresight-stm.c
@@ -16,6 +16,7 @@
  * (C) 2015-2016 Chunyan Zhang <zhang.chunyan@linaro.org>
  */
 #include <asm/local.h>
+#include <linux/acpi.h>
 #include <linux/amba/bus.h>
 #include <linux/bitmap.h>
 #include <linux/clk.h>
@@ -107,10 +108,11 @@ struct channel_space {
 	unsigned long		*guaranteed;
 };
 
+DEFINE_CORESIGHT_DEVLIST(stm_devs, "stm");
+
 /**
  * struct stm_drvdata - specifics associated to an STM component
  * @base:		memory mapped base address for this component.
- * @dev:		the device entity associated to this component.
  * @atclk:		optional clock for the core parts of the STM.
  * @csdev:		component vitals needed by the framework.
  * @spinlock:		only one at a time pls.
@@ -128,7 +130,6 @@ struct channel_space {
  */
 struct stm_drvdata {
 	void __iomem		*base;
-	struct device		*dev;
 	struct clk		*atclk;
 	struct coresight_device	*csdev;
 	spinlock_t		spinlock;
@@ -205,13 +206,13 @@ static int stm_enable(struct coresight_device *csdev,
 	if (val)
 		return -EBUSY;
 
-	pm_runtime_get_sync(drvdata->dev);
+	pm_runtime_get_sync(csdev->dev.parent);
 
 	spin_lock(&drvdata->spinlock);
 	stm_enable_hw(drvdata);
 	spin_unlock(&drvdata->spinlock);
 
-	dev_dbg(drvdata->dev, "STM tracing enabled\n");
+	dev_dbg(&csdev->dev, "STM tracing enabled\n");
 	return 0;
 }
 
@@ -271,10 +272,10 @@ static void stm_disable(struct coresight_device *csdev,
 		/* Wait until the engine has completely stopped */
 		coresight_timeout(drvdata->base, STMTCSR, STMTCSR_BUSY_BIT, 0);
 
-		pm_runtime_put(drvdata->dev);
+		pm_runtime_put(csdev->dev.parent);
 
 		local_set(&drvdata->mode, CS_MODE_DISABLED);
-		dev_dbg(drvdata->dev, "STM tracing disabled\n");
+		dev_dbg(&csdev->dev, "STM tracing disabled\n");
 	}
 }
 
@@ -685,14 +686,15 @@ static const struct attribute_group *coresight_stm_groups[] = {
 	NULL,
 };
 
-static int stm_get_resource_byname(struct device_node *np,
-				   char *ch_base, struct resource *res)
+#ifdef CONFIG_OF
+static int of_stm_get_stimulus_area(struct device *dev, struct resource *res)
 {
 	const char *name = NULL;
 	int index = 0, found = 0;
+	struct device_node *np = dev->of_node;
 
 	while (!of_property_read_string_index(np, "reg-names", index, &name)) {
-		if (strcmp(ch_base, name)) {
+		if (strcmp("stm-stimulus-base", name)) {
 			index++;
 			continue;
 		}
@@ -707,6 +709,70 @@ static int stm_get_resource_byname(struct device_node *np,
 
 	return of_address_to_resource(np, index, res);
 }
+#else
+static inline int of_stm_get_stimulus_area(struct device *dev,
+					   struct resource *res)
+{
+	return -ENOENT;
+}
+#endif
+
+#ifdef CONFIG_ACPI
+static int acpi_stm_get_stimulus_area(struct device *dev, struct resource *res)
+{
+	int rc;
+	bool found_base = false;
+	struct resource_entry *rent;
+	LIST_HEAD(res_list);
+
+	struct acpi_device *adev = ACPI_COMPANION(dev);
+
+	if (!adev)
+		return -ENODEV;
+	rc = acpi_dev_get_resources(adev, &res_list, NULL, NULL);
+	if (rc < 0)
+		return rc;
+
+	/*
+	 * The stimulus base for STM device must be listed as the second memory
+	 * resource, followed by the programming base address as described in
+	 * "Section 2.3 Resources" in ACPI for CoreSightTM 1.0 Platform Design
+	 * document (DEN0067).
+	 */
+	rc = -ENOENT;
+	list_for_each_entry(rent, &res_list, node) {
+		if (resource_type(rent->res) != IORESOURCE_MEM)
+			continue;
+		if (found_base) {
+			*res = *rent->res;
+			rc = 0;
+			break;
+		}
+
+		found_base = true;
+	}
+
+	acpi_dev_free_resource_list(&res_list);
+	return rc;
+}
+#else
+static inline int acpi_stm_get_stimulus_area(struct device *dev,
+					     struct resource *res)
+{
+	return -ENOENT;
+}
+#endif
+
+static int stm_get_stimulus_area(struct device *dev, struct resource *res)
+{
+	struct fwnode_handle *fwnode = dev_fwnode(dev);
+
+	if (is_of_node(fwnode))
+		return of_stm_get_stimulus_area(dev, res);
+	else if (is_acpi_node(fwnode))
+		return acpi_stm_get_stimulus_area(dev, res);
+	return -ENOENT;
+}
 
 static u32 stm_fundamental_data_size(struct stm_drvdata *drvdata)
 {
@@ -763,9 +829,10 @@ static void stm_init_default_data(struct stm_drvdata *drvdata)
 	bitmap_clear(drvdata->chs.guaranteed, 0, drvdata->numsp);
 }
 
-static void stm_init_generic_data(struct stm_drvdata *drvdata)
+static void stm_init_generic_data(struct stm_drvdata *drvdata,
+				  const char *name)
 {
-	drvdata->stm.name = dev_name(drvdata->dev);
+	drvdata->stm.name = name;
 
 	/*
 	 * MasterIDs are assigned at HW design phase. As such the core is
@@ -795,19 +862,15 @@ static int stm_probe(struct amba_device *adev, const struct amba_id *id)
 	struct resource ch_res;
 	size_t bitmap_size;
 	struct coresight_desc desc = { 0 };
-	struct device_node *np = adev->dev.of_node;
 
-	if (np) {
-		pdata = of_get_coresight_platform_data(dev, np);
-		if (IS_ERR(pdata))
-			return PTR_ERR(pdata);
-		adev->dev.platform_data = pdata;
-	}
+	desc.name = coresight_alloc_device_name(&stm_devs, dev);
+	if (!desc.name)
+		return -ENOMEM;
+
 	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
 	if (!drvdata)
 		return -ENOMEM;
 
-	drvdata->dev = &adev->dev;
 	drvdata->atclk = devm_clk_get(&adev->dev, "atclk"); /* optional */
 	if (!IS_ERR(drvdata->atclk)) {
 		ret = clk_prepare_enable(drvdata->atclk);
@@ -821,7 +884,7 @@ static int stm_probe(struct amba_device *adev, const struct amba_id *id)
 		return PTR_ERR(base);
 	drvdata->base = base;
 
-	ret = stm_get_resource_byname(np, "stm-stimulus-base", &ch_res);
+	ret = stm_get_stimulus_area(dev, &ch_res);
 	if (ret)
 		return ret;
 	drvdata->chs.phys = ch_res.start;
@@ -848,14 +911,22 @@ static int stm_probe(struct amba_device *adev, const struct amba_id *id)
 	spin_lock_init(&drvdata->spinlock);
 
 	stm_init_default_data(drvdata);
-	stm_init_generic_data(drvdata);
+	stm_init_generic_data(drvdata, desc.name);
 
 	if (stm_register_device(dev, &drvdata->stm, THIS_MODULE)) {
 		dev_info(dev,
-			 "stm_register_device failed, probing deferred\n");
+			 "%s : stm_register_device failed, probing deferred\n",
+			 desc.name);
 		return -EPROBE_DEFER;
 	}
 
+	pdata = coresight_get_platform_data(dev);
+	if (IS_ERR(pdata)) {
+		ret = PTR_ERR(pdata);
+		goto stm_unregister;
+	}
+	adev->dev.platform_data = pdata;
+
 	desc.type = CORESIGHT_DEV_TYPE_SOURCE;
 	desc.subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE;
 	desc.ops = &stm_cs_ops;
@@ -870,7 +941,8 @@ static int stm_probe(struct amba_device *adev, const struct amba_id *id)
 
 	pm_runtime_put(&adev->dev);
 
-	dev_info(dev, "%s initialized\n", (char *)coresight_get_uci_data(id));
+	dev_info(&drvdata->csdev->dev, "%s initialized\n",
+		 (char *)coresight_get_uci_data(id));
 	return 0;
 
 stm_unregister:
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c
index 2527b5d3b65e..23b7ff00af5c 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etf.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c
@@ -280,7 +280,6 @@ static int tmc_enable_etf_sink(struct coresight_device *csdev,
 			       u32 mode, void *data)
 {
 	int ret;
-	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
 	switch (mode) {
 	case CS_MODE_SYSFS:
@@ -298,7 +297,7 @@ static int tmc_enable_etf_sink(struct coresight_device *csdev,
 	if (ret)
 		return ret;
 
-	dev_dbg(drvdata->dev, "TMC-ETB/ETF enabled\n");
+	dev_dbg(&csdev->dev, "TMC-ETB/ETF enabled\n");
 	return 0;
 }
 
@@ -328,7 +327,7 @@ static int tmc_disable_etf_sink(struct coresight_device *csdev)
 
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
-	dev_dbg(drvdata->dev, "TMC-ETB/ETF disabled\n");
+	dev_dbg(&csdev->dev, "TMC-ETB/ETF disabled\n");
 	return 0;
 }
 
@@ -351,7 +350,7 @@ static int tmc_enable_etf_link(struct coresight_device *csdev,
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
 	if (!ret)
-		dev_dbg(drvdata->dev, "TMC-ETF enabled\n");
+		dev_dbg(&csdev->dev, "TMC-ETF enabled\n");
 	return ret;
 }
 
@@ -371,19 +370,17 @@ static void tmc_disable_etf_link(struct coresight_device *csdev,
 	drvdata->mode = CS_MODE_DISABLED;
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
-	dev_dbg(drvdata->dev, "TMC-ETF disabled\n");
+	dev_dbg(&csdev->dev, "TMC-ETF disabled\n");
 }
 
 static void *tmc_alloc_etf_buffer(struct coresight_device *csdev,
 				  struct perf_event *event, void **pages,
 				  int nr_pages, bool overwrite)
 {
-	int node, cpu = event->cpu;
+	int node;
 	struct cs_buffers *buf;
 
-	if (cpu == -1)
-		cpu = smp_processor_id();
-	node = cpu_to_node(cpu);
+	node = (event->cpu == -1) ? NUMA_NO_NODE : cpu_to_node(event->cpu);
 
 	/* Allocate memory structure for interaction with Perf */
 	buf = kzalloc_node(sizeof(struct cs_buffers), GFP_KERNEL, node);
@@ -477,9 +474,11 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev,
 	/*
 	 * The TMC RAM buffer may be bigger than the space available in the
 	 * perf ring buffer (handle->size).  If so advance the RRP so that we
-	 * get the latest trace data.
+	 * get the latest trace data.  In snapshot mode none of that matters
+	 * since we are expected to clobber stale data in favour of the latest
+	 * traces.
 	 */
-	if (to_read > handle->size) {
+	if (!buf->snapshot && to_read > handle->size) {
 		u32 mask = 0;
 
 		/*
@@ -516,7 +515,13 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev,
 		lost = true;
 	}
 
-	if (lost)
+	/*
+	 * Don't set the TRUNCATED flag in snapshot mode because 1) the
+	 * captured buffer is expected to be truncated and 2) a full buffer
+	 * prevents the event from being re-enabled by the perf core,
+	 * resulting in stale data being send to user space.
+	 */
+	if (!buf->snapshot && lost)
 		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 
 	cur = buf->cur;
@@ -542,11 +547,15 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev,
 		}
 	}
 
-	/* In snapshot mode we have to update the head */
-	if (buf->snapshot) {
-		handle->head = (cur * PAGE_SIZE) + offset;
-		to_read = buf->nr_pages << PAGE_SHIFT;
-	}
+	/*
+	 * In snapshot mode we simply increment the head by the number of byte
+	 * that were written.  User space function  cs_etm_find_snapshot() will
+	 * figure out how many bytes to get from the AUX buffer based on the
+	 * position of the head.
+	 */
+	if (buf->snapshot)
+		handle->head += to_read;
+
 	CS_LOCK(drvdata->base);
 out:
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c
index df6e4b0b84e9..17006705287a 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etr.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c
@@ -162,10 +162,11 @@ static void tmc_pages_free(struct tmc_pages *tmc_pages,
 			   struct device *dev, enum dma_data_direction dir)
 {
 	int i;
+	struct device *real_dev = dev->parent;
 
 	for (i = 0; i < tmc_pages->nr_pages; i++) {
 		if (tmc_pages->daddrs && tmc_pages->daddrs[i])
-			dma_unmap_page(dev, tmc_pages->daddrs[i],
+			dma_unmap_page(real_dev, tmc_pages->daddrs[i],
 					 PAGE_SIZE, dir);
 		if (tmc_pages->pages && tmc_pages->pages[i])
 			__free_page(tmc_pages->pages[i]);
@@ -193,6 +194,7 @@ static int tmc_pages_alloc(struct tmc_pages *tmc_pages,
 	int i, nr_pages;
 	dma_addr_t paddr;
 	struct page *page;
+	struct device *real_dev = dev->parent;
 
 	nr_pages = tmc_pages->nr_pages;
 	tmc_pages->daddrs = kcalloc(nr_pages, sizeof(*tmc_pages->daddrs),
@@ -216,8 +218,8 @@ static int tmc_pages_alloc(struct tmc_pages *tmc_pages,
 			page = alloc_pages_node(node,
 						GFP_KERNEL | __GFP_ZERO, 0);
 		}
-		paddr = dma_map_page(dev, page, 0, PAGE_SIZE, dir);
-		if (dma_mapping_error(dev, paddr))
+		paddr = dma_map_page(real_dev, page, 0, PAGE_SIZE, dir);
+		if (dma_mapping_error(real_dev, paddr))
 			goto err;
 		tmc_pages->daddrs[i] = paddr;
 		tmc_pages->pages[i] = page;
@@ -304,7 +306,7 @@ static int tmc_alloc_data_pages(struct tmc_sg_table *sg_table, void **pages)
  * and data buffers. TMC writes to the data buffers and reads from the SG
  * Table pages.
  *
- * @dev		- Device to which page should be DMA mapped.
+ * @dev		- Coresight device to which page should be DMA mapped.
  * @node	- Numa node for mem allocations
  * @nr_tpages	- Number of pages for the table entries.
  * @nr_dpages	- Number of pages for Data buffer.
@@ -348,13 +350,13 @@ void tmc_sg_table_sync_data_range(struct tmc_sg_table *table,
 {
 	int i, index, start;
 	int npages = DIV_ROUND_UP(size, PAGE_SIZE);
-	struct device *dev = table->dev;
+	struct device *real_dev = table->dev->parent;
 	struct tmc_pages *data = &table->data_pages;
 
 	start = offset >> PAGE_SHIFT;
 	for (i = start; i < (start + npages); i++) {
 		index = i % data->nr_pages;
-		dma_sync_single_for_cpu(dev, data->daddrs[index],
+		dma_sync_single_for_cpu(real_dev, data->daddrs[index],
 					PAGE_SIZE, DMA_FROM_DEVICE);
 	}
 }
@@ -363,11 +365,11 @@ void tmc_sg_table_sync_data_range(struct tmc_sg_table *table,
 void tmc_sg_table_sync_table(struct tmc_sg_table *sg_table)
 {
 	int i;
-	struct device *dev = sg_table->dev;
+	struct device *real_dev = sg_table->dev->parent;
 	struct tmc_pages *table_pages = &sg_table->table_pages;
 
 	for (i = 0; i < table_pages->nr_pages; i++)
-		dma_sync_single_for_device(dev, table_pages->daddrs[i],
+		dma_sync_single_for_device(real_dev, table_pages->daddrs[i],
 					   PAGE_SIZE, DMA_TO_DEVICE);
 }
 
@@ -590,6 +592,7 @@ static int tmc_etr_alloc_flat_buf(struct tmc_drvdata *drvdata,
 				  void **pages)
 {
 	struct etr_flat_buf *flat_buf;
+	struct device *real_dev = drvdata->csdev->dev.parent;
 
 	/* We cannot reuse existing pages for flat buf */
 	if (pages)
@@ -599,7 +602,7 @@ static int tmc_etr_alloc_flat_buf(struct tmc_drvdata *drvdata,
 	if (!flat_buf)
 		return -ENOMEM;
 
-	flat_buf->vaddr = dma_alloc_coherent(drvdata->dev, etr_buf->size,
+	flat_buf->vaddr = dma_alloc_coherent(real_dev, etr_buf->size,
 					     &flat_buf->daddr, GFP_KERNEL);
 	if (!flat_buf->vaddr) {
 		kfree(flat_buf);
@@ -607,7 +610,7 @@ static int tmc_etr_alloc_flat_buf(struct tmc_drvdata *drvdata,
 	}
 
 	flat_buf->size = etr_buf->size;
-	flat_buf->dev = drvdata->dev;
+	flat_buf->dev = &drvdata->csdev->dev;
 	etr_buf->hwaddr = flat_buf->daddr;
 	etr_buf->mode = ETR_MODE_FLAT;
 	etr_buf->private = flat_buf;
@@ -618,9 +621,12 @@ static void tmc_etr_free_flat_buf(struct etr_buf *etr_buf)
 {
 	struct etr_flat_buf *flat_buf = etr_buf->private;
 
-	if (flat_buf && flat_buf->daddr)
-		dma_free_coherent(flat_buf->dev, flat_buf->size,
+	if (flat_buf && flat_buf->daddr) {
+		struct device *real_dev = flat_buf->dev->parent;
+
+		dma_free_coherent(real_dev, flat_buf->size,
 				  flat_buf->vaddr, flat_buf->daddr);
+	}
 	kfree(flat_buf);
 }
 
@@ -666,8 +672,9 @@ static int tmc_etr_alloc_sg_buf(struct tmc_drvdata *drvdata,
 				void **pages)
 {
 	struct etr_sg_table *etr_table;
+	struct device *dev = &drvdata->csdev->dev;
 
-	etr_table = tmc_init_etr_sg_table(drvdata->dev, node,
+	etr_table = tmc_init_etr_sg_table(dev, node,
 					  etr_buf->size, pages);
 	if (IS_ERR(etr_table))
 		return -ENOMEM;
@@ -751,8 +758,8 @@ tmc_etr_get_catu_device(struct tmc_drvdata *drvdata)
 	if (!IS_ENABLED(CONFIG_CORESIGHT_CATU))
 		return NULL;
 
-	for (i = 0; i < etr->nr_outport; i++) {
-		tmp = etr->conns[i].child_dev;
+	for (i = 0; i < etr->pdata->nr_outport; i++) {
+		tmp = etr->pdata->conns[i].child_dev;
 		if (tmp && coresight_is_catu_device(tmp))
 			return tmp;
 	}
@@ -823,9 +830,10 @@ static struct etr_buf *tmc_alloc_etr_buf(struct tmc_drvdata *drvdata,
 	bool has_etr_sg, has_iommu;
 	bool has_sg, has_catu;
 	struct etr_buf *etr_buf;
+	struct device *dev = &drvdata->csdev->dev;
 
 	has_etr_sg = tmc_etr_has_cap(drvdata, TMC_ETR_SG);
-	has_iommu = iommu_get_domain_for_dev(drvdata->dev);
+	has_iommu = iommu_get_domain_for_dev(dev->parent);
 	has_catu = !!tmc_etr_get_catu_device(drvdata);
 
 	has_sg = has_catu || has_etr_sg;
@@ -863,7 +871,7 @@ static struct etr_buf *tmc_alloc_etr_buf(struct tmc_drvdata *drvdata,
 		return ERR_PTR(rc);
 	}
 
-	dev_dbg(drvdata->dev, "allocated buffer of size %ldKB in mode %d\n",
+	dev_dbg(dev, "allocated buffer of size %ldKB in mode %d\n",
 		(unsigned long)size >> 10, etr_buf->mode);
 	return etr_buf;
 }
@@ -1162,7 +1170,7 @@ out:
 		tmc_etr_free_sysfs_buf(free_buf);
 
 	if (!ret)
-		dev_dbg(drvdata->dev, "TMC-ETR enabled\n");
+		dev_dbg(&csdev->dev, "TMC-ETR enabled\n");
 
 	return ret;
 }
@@ -1178,14 +1186,11 @@ static struct etr_buf *
 alloc_etr_buf(struct tmc_drvdata *drvdata, struct perf_event *event,
 	      int nr_pages, void **pages, bool snapshot)
 {
-	int node, cpu = event->cpu;
+	int node;
 	struct etr_buf *etr_buf;
 	unsigned long size;
 
-	if (cpu == -1)
-		cpu = smp_processor_id();
-	node = cpu_to_node(cpu);
-
+	node = (event->cpu == -1) ? NUMA_NO_NODE : cpu_to_node(event->cpu);
 	/*
 	 * Try to match the perf ring buffer size if it is larger
 	 * than the size requested via sysfs.
@@ -1317,13 +1322,11 @@ static struct etr_perf_buffer *
 tmc_etr_setup_perf_buf(struct tmc_drvdata *drvdata, struct perf_event *event,
 		       int nr_pages, void **pages, bool snapshot)
 {
-	int node, cpu = event->cpu;
+	int node;
 	struct etr_buf *etr_buf;
 	struct etr_perf_buffer *etr_perf;
 
-	if (cpu == -1)
-		cpu = smp_processor_id();
-	node = cpu_to_node(cpu);
+	node = (event->cpu == -1) ? NUMA_NO_NODE : cpu_to_node(event->cpu);
 
 	etr_perf = kzalloc_node(sizeof(*etr_perf), GFP_KERNEL, node);
 	if (!etr_perf)
@@ -1358,7 +1361,7 @@ static void *tmc_alloc_etr_buffer(struct coresight_device *csdev,
 	etr_perf = tmc_etr_setup_perf_buf(drvdata, event,
 					  nr_pages, pages, snapshot);
 	if (IS_ERR(etr_perf)) {
-		dev_dbg(drvdata->dev, "Unable to allocate ETR buffer\n");
+		dev_dbg(&csdev->dev, "Unable to allocate ETR buffer\n");
 		return NULL;
 	}
 
@@ -1501,18 +1504,23 @@ tmc_update_etr_buffer(struct coresight_device *csdev,
 	tmc_etr_sync_perf_buffer(etr_perf);
 
 	/*
-	 * Update handle->head in snapshot mode. Also update the size to the
-	 * hardware buffer size if there was an overflow.
+	 * In snapshot mode we simply increment the head by the number of byte
+	 * that were written.  User space function  cs_etm_find_snapshot() will
+	 * figure out how many bytes to get from the AUX buffer based on the
+	 * position of the head.
 	 */
-	if (etr_perf->snapshot) {
+	if (etr_perf->snapshot)
 		handle->head += size;
-		if (etr_buf->full)
-			size = etr_buf->size;
-	}
 
 	lost |= etr_buf->full;
 out:
-	if (lost)
+	/*
+	 * Don't set the TRUNCATED flag in snapshot mode because 1) the
+	 * captured buffer is expected to be truncated and 2) a full buffer
+	 * prevents the event from being re-enabled by the perf core,
+	 * resulting in stale data being send to user space.
+	 */
+	if (!etr_perf->snapshot && lost)
 		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 	return size;
 }
@@ -1612,7 +1620,7 @@ static int tmc_disable_etr_sink(struct coresight_device *csdev)
 
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
-	dev_dbg(drvdata->dev, "TMC-ETR disabled\n");
+	dev_dbg(&csdev->dev, "TMC-ETR disabled\n");
 	return 0;
 }
 
diff --git a/drivers/hwtracing/coresight/coresight-tmc.c b/drivers/hwtracing/coresight/coresight-tmc.c
index 3f718729d741..be37aff573b4 100644
--- a/drivers/hwtracing/coresight/coresight-tmc.c
+++ b/drivers/hwtracing/coresight/coresight-tmc.c
@@ -27,12 +27,16 @@
 #include "coresight-priv.h"
 #include "coresight-tmc.h"
 
+DEFINE_CORESIGHT_DEVLIST(etb_devs, "tmc_etb");
+DEFINE_CORESIGHT_DEVLIST(etf_devs, "tmc_etf");
+DEFINE_CORESIGHT_DEVLIST(etr_devs, "tmc_etr");
+
 void tmc_wait_for_tmcready(struct tmc_drvdata *drvdata)
 {
 	/* Ensure formatter, unformatter and hardware fifo are empty */
 	if (coresight_timeout(drvdata->base,
 			      TMC_STS, TMC_STS_TMCREADY_BIT, 1)) {
-		dev_err(drvdata->dev,
+		dev_err(&drvdata->csdev->dev,
 			"timeout while waiting for TMC to be Ready\n");
 	}
 }
@@ -49,7 +53,7 @@ void tmc_flush_and_stop(struct tmc_drvdata *drvdata)
 	/* Ensure flush completes */
 	if (coresight_timeout(drvdata->base,
 			      TMC_FFCR, TMC_FFCR_FLUSHMAN_BIT, 0)) {
-		dev_err(drvdata->dev,
+		dev_err(&drvdata->csdev->dev,
 		"timeout while waiting for completion of Manual Flush\n");
 	}
 
@@ -83,7 +87,7 @@ static int tmc_read_prepare(struct tmc_drvdata *drvdata)
 	}
 
 	if (!ret)
-		dev_dbg(drvdata->dev, "TMC read start\n");
+		dev_dbg(&drvdata->csdev->dev, "TMC read start\n");
 
 	return ret;
 }
@@ -105,7 +109,7 @@ static int tmc_read_unprepare(struct tmc_drvdata *drvdata)
 	}
 
 	if (!ret)
-		dev_dbg(drvdata->dev, "TMC read end\n");
+		dev_dbg(&drvdata->csdev->dev, "TMC read end\n");
 
 	return ret;
 }
@@ -122,7 +126,7 @@ static int tmc_open(struct inode *inode, struct file *file)
 
 	nonseekable_open(inode, file);
 
-	dev_dbg(drvdata->dev, "%s: successfully opened\n", __func__);
+	dev_dbg(&drvdata->csdev->dev, "%s: successfully opened\n", __func__);
 	return 0;
 }
 
@@ -152,12 +156,13 @@ static ssize_t tmc_read(struct file *file, char __user *data, size_t len,
 		return 0;
 
 	if (copy_to_user(data, bufp, actual)) {
-		dev_dbg(drvdata->dev, "%s: copy_to_user failed\n", __func__);
+		dev_dbg(&drvdata->csdev->dev,
+			"%s: copy_to_user failed\n", __func__);
 		return -EFAULT;
 	}
 
 	*ppos += actual;
-	dev_dbg(drvdata->dev, "%zu bytes copied\n", actual);
+	dev_dbg(&drvdata->csdev->dev, "%zu bytes copied\n", actual);
 
 	return actual;
 }
@@ -172,7 +177,7 @@ static int tmc_release(struct inode *inode, struct file *file)
 	if (ret)
 		return ret;
 
-	dev_dbg(drvdata->dev, "%s: released\n", __func__);
+	dev_dbg(&drvdata->csdev->dev, "%s: released\n", __func__);
 	return 0;
 }
 
@@ -332,24 +337,22 @@ const struct attribute_group *coresight_tmc_groups[] = {
 	NULL,
 };
 
-static inline bool tmc_etr_can_use_sg(struct tmc_drvdata *drvdata)
+static inline bool tmc_etr_can_use_sg(struct device *dev)
 {
-	return fwnode_property_present(drvdata->dev->fwnode,
-				       "arm,scatter-gather");
+	return fwnode_property_present(dev->fwnode, "arm,scatter-gather");
 }
 
 /* Detect and initialise the capabilities of a TMC ETR */
-static int tmc_etr_setup_caps(struct tmc_drvdata *drvdata,
-			     u32 devid, void *dev_caps)
+static int tmc_etr_setup_caps(struct device *parent, u32 devid, void *dev_caps)
 {
 	int rc;
-
 	u32 dma_mask = 0;
+	struct tmc_drvdata *drvdata = dev_get_drvdata(parent);
 
 	/* Set the unadvertised capabilities */
 	tmc_etr_init_caps(drvdata, (u32)(unsigned long)dev_caps);
 
-	if (!(devid & TMC_DEVID_NOSCAT) && tmc_etr_can_use_sg(drvdata))
+	if (!(devid & TMC_DEVID_NOSCAT) && tmc_etr_can_use_sg(parent))
 		tmc_etr_set_cap(drvdata, TMC_ETR_SG);
 
 	/* Check if the AXI address width is available */
@@ -367,18 +370,27 @@ static int tmc_etr_setup_caps(struct tmc_drvdata *drvdata,
 	case 44:
 	case 48:
 	case 52:
-		dev_info(drvdata->dev, "Detected dma mask %dbits\n", dma_mask);
+		dev_info(parent, "Detected dma mask %dbits\n", dma_mask);
 		break;
 	default:
 		dma_mask = 40;
 	}
 
-	rc = dma_set_mask_and_coherent(drvdata->dev, DMA_BIT_MASK(dma_mask));
+	rc = dma_set_mask_and_coherent(parent, DMA_BIT_MASK(dma_mask));
 	if (rc)
-		dev_err(drvdata->dev, "Failed to setup DMA mask: %d\n", rc);
+		dev_err(parent, "Failed to setup DMA mask: %d\n", rc);
 	return rc;
 }
 
+static u32 tmc_etr_get_default_buffer_size(struct device *dev)
+{
+	u32 size;
+
+	if (fwnode_property_read_u32(dev->fwnode, "arm,buffer-size", &size))
+		size = SZ_1M;
+	return size;
+}
+
 static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
 {
 	int ret = 0;
@@ -389,23 +401,13 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
 	struct tmc_drvdata *drvdata;
 	struct resource *res = &adev->res;
 	struct coresight_desc desc = { 0 };
-	struct device_node *np = adev->dev.of_node;
-
-	if (np) {
-		pdata = of_get_coresight_platform_data(dev, np);
-		if (IS_ERR(pdata)) {
-			ret = PTR_ERR(pdata);
-			goto out;
-		}
-		adev->dev.platform_data = pdata;
-	}
+	struct coresight_dev_list *dev_list = NULL;
 
 	ret = -ENOMEM;
 	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
 	if (!drvdata)
 		goto out;
 
-	drvdata->dev = &adev->dev;
 	dev_set_drvdata(dev, drvdata);
 
 	/* Validity for the resource is already checked by the AMBA core */
@@ -425,18 +427,11 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
 	/* This device is not associated with a session */
 	drvdata->pid = -1;
 
-	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
-		if (np)
-			ret = of_property_read_u32(np,
-						   "arm,buffer-size",
-						   &drvdata->size);
-		if (ret)
-			drvdata->size = SZ_1M;
-	} else {
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR)
+		drvdata->size = tmc_etr_get_default_buffer_size(dev);
+	else
 		drvdata->size = readl_relaxed(drvdata->base + TMC_RSZ) * 4;
-	}
 
-	desc.pdata = pdata;
 	desc.dev = dev;
 	desc.groups = coresight_tmc_groups;
 
@@ -445,36 +440,53 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
 		desc.type = CORESIGHT_DEV_TYPE_SINK;
 		desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER;
 		desc.ops = &tmc_etb_cs_ops;
+		dev_list = &etb_devs;
 		break;
 	case TMC_CONFIG_TYPE_ETR:
 		desc.type = CORESIGHT_DEV_TYPE_SINK;
 		desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER;
 		desc.ops = &tmc_etr_cs_ops;
-		ret = tmc_etr_setup_caps(drvdata, devid,
+		ret = tmc_etr_setup_caps(dev, devid,
 					 coresight_get_uci_data(id));
 		if (ret)
 			goto out;
 		idr_init(&drvdata->idr);
 		mutex_init(&drvdata->idr_mutex);
+		dev_list = &etr_devs;
 		break;
 	case TMC_CONFIG_TYPE_ETF:
 		desc.type = CORESIGHT_DEV_TYPE_LINKSINK;
 		desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_FIFO;
 		desc.ops = &tmc_etf_cs_ops;
+		dev_list = &etf_devs;
 		break;
 	default:
-		pr_err("%s: Unsupported TMC config\n", pdata->name);
+		pr_err("%s: Unsupported TMC config\n", desc.name);
 		ret = -EINVAL;
 		goto out;
 	}
 
+	desc.name = coresight_alloc_device_name(dev_list, dev);
+	if (!desc.name) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	pdata = coresight_get_platform_data(dev);
+	if (IS_ERR(pdata)) {
+		ret = PTR_ERR(pdata);
+		goto out;
+	}
+	adev->dev.platform_data = pdata;
+	desc.pdata = pdata;
+
 	drvdata->csdev = coresight_register(&desc);
 	if (IS_ERR(drvdata->csdev)) {
 		ret = PTR_ERR(drvdata->csdev);
 		goto out;
 	}
 
-	drvdata->miscdev.name = pdata->name;
+	drvdata->miscdev.name = desc.name;
 	drvdata->miscdev.minor = MISC_DYNAMIC_MINOR;
 	drvdata->miscdev.fops = &tmc_fops;
 	ret = misc_register(&drvdata->miscdev);
diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h
index 503f1b3a3741..1ed50411cc3c 100644
--- a/drivers/hwtracing/coresight/coresight-tmc.h
+++ b/drivers/hwtracing/coresight/coresight-tmc.h
@@ -161,7 +161,6 @@ struct etr_buf {
 /**
  * struct tmc_drvdata - specifics associated to an TMC component
  * @base:	memory mapped base address for this component.
- * @dev:	the device entity associated to this component.
  * @csdev:	component vitals needed by the framework.
  * @miscdev:	specifics to handle "/dev/xyz.tmc" entry.
  * @spinlock:	only one at a time pls.
@@ -184,7 +183,6 @@ struct etr_buf {
  */
 struct tmc_drvdata {
 	void __iomem		*base;
-	struct device		*dev;
 	struct coresight_device	*csdev;
 	struct miscdevice	miscdev;
 	spinlock_t		spinlock;
diff --git a/drivers/hwtracing/coresight/coresight-tpiu.c b/drivers/hwtracing/coresight/coresight-tpiu.c
index 63d9af31f57f..f8583e4032a6 100644
--- a/drivers/hwtracing/coresight/coresight-tpiu.c
+++ b/drivers/hwtracing/coresight/coresight-tpiu.c
@@ -47,15 +47,15 @@
 #define FFCR_FON_MAN		BIT(6)
 #define FFCR_STOP_FI		BIT(12)
 
+DEFINE_CORESIGHT_DEVLIST(tpiu_devs, "tpiu");
+
 /**
  * @base:	memory mapped base address for this component.
- * @dev:	the device entity associated to this component.
  * @atclk:	optional clock for the core parts of the TPIU.
  * @csdev:	component vitals needed by the framework.
  */
 struct tpiu_drvdata {
 	void __iomem		*base;
-	struct device		*dev;
 	struct clk		*atclk;
 	struct coresight_device	*csdev;
 };
@@ -75,7 +75,7 @@ static int tpiu_enable(struct coresight_device *csdev, u32 mode, void *__unused)
 
 	tpiu_enable_hw(drvdata);
 	atomic_inc(csdev->refcnt);
-	dev_dbg(drvdata->dev, "TPIU enabled\n");
+	dev_dbg(&csdev->dev, "TPIU enabled\n");
 	return 0;
 }
 
@@ -104,7 +104,7 @@ static int tpiu_disable(struct coresight_device *csdev)
 
 	tpiu_disable_hw(drvdata);
 
-	dev_dbg(drvdata->dev, "TPIU disabled\n");
+	dev_dbg(&csdev->dev, "TPIU disabled\n");
 	return 0;
 }
 
@@ -126,20 +126,15 @@ static int tpiu_probe(struct amba_device *adev, const struct amba_id *id)
 	struct tpiu_drvdata *drvdata;
 	struct resource *res = &adev->res;
 	struct coresight_desc desc = { 0 };
-	struct device_node *np = adev->dev.of_node;
 
-	if (np) {
-		pdata = of_get_coresight_platform_data(dev, np);
-		if (IS_ERR(pdata))
-			return PTR_ERR(pdata);
-		adev->dev.platform_data = pdata;
-	}
+	desc.name = coresight_alloc_device_name(&tpiu_devs, dev);
+	if (!desc.name)
+		return -ENOMEM;
 
 	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
 	if (!drvdata)
 		return -ENOMEM;
 
-	drvdata->dev = &adev->dev;
 	drvdata->atclk = devm_clk_get(&adev->dev, "atclk"); /* optional */
 	if (!IS_ERR(drvdata->atclk)) {
 		ret = clk_prepare_enable(drvdata->atclk);
@@ -158,6 +153,11 @@ static int tpiu_probe(struct amba_device *adev, const struct amba_id *id)
 	/* Disable tpiu to support older devices */
 	tpiu_disable_hw(drvdata);
 
+	pdata = coresight_get_platform_data(dev);
+	if (IS_ERR(pdata))
+		return PTR_ERR(pdata);
+	dev->platform_data = pdata;
+
 	desc.type = CORESIGHT_DEV_TYPE_SINK;
 	desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_PORT;
 	desc.ops = &tpiu_cs_ops;
diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c
index 4b130281236a..86d1fc2c1bd4 100644
--- a/drivers/hwtracing/coresight/coresight.c
+++ b/drivers/hwtracing/coresight/coresight.c
@@ -100,8 +100,8 @@ static int coresight_find_link_inport(struct coresight_device *csdev,
 	int i;
 	struct coresight_connection *conn;
 
-	for (i = 0; i < parent->nr_outport; i++) {
-		conn = &parent->conns[i];
+	for (i = 0; i < parent->pdata->nr_outport; i++) {
+		conn = &parent->pdata->conns[i];
 		if (conn->child_dev == csdev)
 			return conn->child_port;
 	}
@@ -118,8 +118,8 @@ static int coresight_find_link_outport(struct coresight_device *csdev,
 	int i;
 	struct coresight_connection *conn;
 
-	for (i = 0; i < csdev->nr_outport; i++) {
-		conn = &csdev->conns[i];
+	for (i = 0; i < csdev->pdata->nr_outport; i++) {
+		conn = &csdev->pdata->conns[i];
 		if (conn->child_dev == child)
 			return conn->outport;
 	}
@@ -306,10 +306,10 @@ static void coresight_disable_link(struct coresight_device *csdev,
 
 	if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG) {
 		refport = inport;
-		nr_conns = csdev->nr_inport;
+		nr_conns = csdev->pdata->nr_inport;
 	} else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT) {
 		refport = outport;
-		nr_conns = csdev->nr_outport;
+		nr_conns = csdev->pdata->nr_outport;
 	} else {
 		refport = 0;
 		nr_conns = 1;
@@ -595,9 +595,10 @@ static void coresight_grab_device(struct coresight_device *csdev)
 {
 	int i;
 
-	for (i = 0; i < csdev->nr_outport; i++) {
-		struct coresight_device *child = csdev->conns[i].child_dev;
+	for (i = 0; i < csdev->pdata->nr_outport; i++) {
+		struct coresight_device *child;
 
+		child  = csdev->pdata->conns[i].child_dev;
 		if (child && child->type == CORESIGHT_DEV_TYPE_HELPER)
 			pm_runtime_get_sync(child->dev.parent);
 	}
@@ -613,9 +614,10 @@ static void coresight_drop_device(struct coresight_device *csdev)
 	int i;
 
 	pm_runtime_put(csdev->dev.parent);
-	for (i = 0; i < csdev->nr_outport; i++) {
-		struct coresight_device *child = csdev->conns[i].child_dev;
+	for (i = 0; i < csdev->pdata->nr_outport; i++) {
+		struct coresight_device *child;
 
+		child  = csdev->pdata->conns[i].child_dev;
 		if (child && child->type == CORESIGHT_DEV_TYPE_HELPER)
 			pm_runtime_put(child->dev.parent);
 	}
@@ -645,9 +647,10 @@ static int _coresight_build_path(struct coresight_device *csdev,
 		goto out;
 
 	/* Not a sink - recursively explore each port found on this element */
-	for (i = 0; i < csdev->nr_outport; i++) {
-		struct coresight_device *child_dev = csdev->conns[i].child_dev;
+	for (i = 0; i < csdev->pdata->nr_outport; i++) {
+		struct coresight_device *child_dev;
 
+		child_dev = csdev->pdata->conns[i].child_dev;
 		if (child_dev &&
 		    _coresight_build_path(child_dev, sink, path) == 0) {
 			found = true;
@@ -975,6 +978,7 @@ static void coresight_device_release(struct device *dev)
 {
 	struct coresight_device *csdev = to_coresight_device(dev);
 
+	fwnode_handle_put(csdev->dev.fwnode);
 	kfree(csdev->refcnt);
 	kfree(csdev);
 }
@@ -1000,19 +1004,17 @@ static int coresight_orphan_match(struct device *dev, void *data)
 	 * Circle throuch all the connection of that component.  If we find
 	 * an orphan connection whose name matches @csdev, link it.
 	 */
-	for (i = 0; i < i_csdev->nr_outport; i++) {
-		conn = &i_csdev->conns[i];
+	for (i = 0; i < i_csdev->pdata->nr_outport; i++) {
+		conn = &i_csdev->pdata->conns[i];
 
 		/* We have found at least one orphan connection */
 		if (conn->child_dev == NULL) {
 			/* Does it match this newly added device? */
-			if (conn->child_name &&
-			    !strcmp(dev_name(&csdev->dev), conn->child_name)) {
+			if (conn->child_fwnode == csdev->dev.fwnode)
 				conn->child_dev = csdev;
-			} else {
+			else
 				/* This component still has an orphan */
 				still_orphan = true;
-			}
 		}
 	}
 
@@ -1040,13 +1042,13 @@ static void coresight_fixup_device_conns(struct coresight_device *csdev)
 {
 	int i;
 
-	for (i = 0; i < csdev->nr_outport; i++) {
-		struct coresight_connection *conn = &csdev->conns[i];
+	for (i = 0; i < csdev->pdata->nr_outport; i++) {
+		struct coresight_connection *conn = &csdev->pdata->conns[i];
 		struct device *dev = NULL;
 
-		if (conn->child_name)
-			dev = bus_find_device_by_name(&coresight_bustype, NULL,
-						      conn->child_name);
+		dev = bus_find_device(&coresight_bustype, NULL,
+				      (void *)conn->child_fwnode,
+				      coresight_device_fwnode_match);
 		if (dev) {
 			conn->child_dev = to_coresight_device(dev);
 			/* and put reference from 'bus_find_device()' */
@@ -1075,15 +1077,21 @@ static int coresight_remove_match(struct device *dev, void *data)
 	 * Circle throuch all the connection of that component.  If we find
 	 * a connection whose name matches @csdev, remove it.
 	 */
-	for (i = 0; i < iterator->nr_outport; i++) {
-		conn = &iterator->conns[i];
+	for (i = 0; i < iterator->pdata->nr_outport; i++) {
+		conn = &iterator->pdata->conns[i];
 
 		if (conn->child_dev == NULL)
 			continue;
 
-		if (!strcmp(dev_name(&csdev->dev), conn->child_name)) {
+		if (csdev->dev.fwnode == conn->child_fwnode) {
 			iterator->orphan = true;
 			conn->child_dev = NULL;
+			/*
+			 * Drop the reference to the handle for the remote
+			 * device acquired in parsing the connections from
+			 * platform data.
+			 */
+			fwnode_handle_put(conn->child_fwnode);
 			/* No need to continue */
 			break;
 		}
@@ -1096,10 +1104,21 @@ static int coresight_remove_match(struct device *dev, void *data)
 	return 0;
 }
 
+/*
+ * coresight_remove_conns - Remove references to this given devices
+ * from the connections of other devices.
+ */
 static void coresight_remove_conns(struct coresight_device *csdev)
 {
-	bus_for_each_dev(&coresight_bustype, NULL,
-			 csdev, coresight_remove_match);
+	/*
+	 * Another device will point to this device only if there is
+	 * an output port connected to this one. i.e, if the device
+	 * doesn't have at least one input port, there is no point
+	 * in searching all the devices.
+	 */
+	if (csdev->pdata->nr_inport)
+		bus_for_each_dev(&coresight_bustype, NULL,
+				 csdev, coresight_remove_match);
 }
 
 /**
@@ -1152,6 +1171,22 @@ static int __init coresight_init(void)
 }
 postcore_initcall(coresight_init);
 
+/*
+ * coresight_release_platform_data: Release references to the devices connected
+ * to the output port of this device.
+ */
+void coresight_release_platform_data(struct coresight_platform_data *pdata)
+{
+	int i;
+
+	for (i = 0; i < pdata->nr_outport; i++) {
+		if (pdata->conns[i].child_fwnode) {
+			fwnode_handle_put(pdata->conns[i].child_fwnode);
+			pdata->conns[i].child_fwnode = NULL;
+		}
+	}
+}
+
 struct coresight_device *coresight_register(struct coresight_desc *desc)
 {
 	int ret;
@@ -1184,10 +1219,7 @@ struct coresight_device *coresight_register(struct coresight_desc *desc)
 
 	csdev->refcnt = refcnts;
 
-	csdev->nr_inport = desc->pdata->nr_inport;
-	csdev->nr_outport = desc->pdata->nr_outport;
-
-	csdev->conns = desc->pdata->conns;
+	csdev->pdata = desc->pdata;
 
 	csdev->type = desc->type;
 	csdev->subtype = desc->subtype;
@@ -1199,7 +1231,12 @@ struct coresight_device *coresight_register(struct coresight_desc *desc)
 	csdev->dev.parent = desc->dev;
 	csdev->dev.release = coresight_device_release;
 	csdev->dev.bus = &coresight_bustype;
-	dev_set_name(&csdev->dev, "%s", desc->pdata->name);
+	/*
+	 * Hold the reference to our parent device. This will be
+	 * dropped only in coresight_device_release().
+	 */
+	csdev->dev.fwnode = fwnode_handle_get(dev_fwnode(desc->dev));
+	dev_set_name(&csdev->dev, "%s", desc->name);
 
 	ret = device_register(&csdev->dev);
 	if (ret) {
@@ -1239,6 +1276,8 @@ struct coresight_device *coresight_register(struct coresight_desc *desc)
 err_free_csdev:
 	kfree(csdev);
 err_out:
+	/* Cleanup the connection information */
+	coresight_release_platform_data(desc->pdata);
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(coresight_register);
@@ -1248,6 +1287,65 @@ void coresight_unregister(struct coresight_device *csdev)
 	etm_perf_del_symlink_sink(csdev);
 	/* Remove references of that device in the topology */
 	coresight_remove_conns(csdev);
+	coresight_release_platform_data(csdev->pdata);
 	device_unregister(&csdev->dev);
 }
 EXPORT_SYMBOL_GPL(coresight_unregister);
+
+
+/*
+ * coresight_search_device_idx - Search the fwnode handle of a device
+ * in the given dev_idx list. Must be called with the coresight_mutex held.
+ *
+ * Returns the index of the entry, when found. Otherwise, -ENOENT.
+ */
+static inline int coresight_search_device_idx(struct coresight_dev_list *dict,
+					      struct fwnode_handle *fwnode)
+{
+	int i;
+
+	for (i = 0; i < dict->nr_idx; i++)
+		if (dict->fwnode_list[i] == fwnode)
+			return i;
+	return -ENOENT;
+}
+
+/*
+ * 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
+ * device and is tracked with the fwnode_handle to prevent allocating
+ * duplicate indices for the same device (e.g, if we defer probing of
+ * a device due to dependencies), in case the index is requested again.
+ */
+char *coresight_alloc_device_name(struct coresight_dev_list *dict,
+				  struct device *dev)
+{
+	int idx;
+	char *name = NULL;
+	struct fwnode_handle **list;
+
+	mutex_lock(&coresight_mutex);
+
+	idx = coresight_search_device_idx(dict, dev_fwnode(dev));
+	if (idx < 0) {
+		/* Make space for the new entry */
+		idx = dict->nr_idx;
+		list = krealloc(dict->fwnode_list,
+				(idx + 1) * sizeof(*dict->fwnode_list),
+				GFP_KERNEL);
+		if (ZERO_OR_NULL_PTR(list)) {
+			idx = -ENOMEM;
+			goto done;
+		}
+
+		list[idx] = dev_fwnode(dev);
+		dict->fwnode_list = list;
+		dict->nr_idx = idx + 1;
+	}
+
+	name = devm_kasprintf(dev, GFP_KERNEL, "%s%d", dict->pfx, idx);
+done:
+	mutex_unlock(&coresight_mutex);
+	return name;
+}
+EXPORT_SYMBOL_GPL(coresight_alloc_device_name);
diff --git a/drivers/hwtracing/coresight/of_coresight.c b/drivers/hwtracing/coresight/of_coresight.c
deleted file mode 100644
index 7045930fc958..000000000000
--- a/drivers/hwtracing/coresight/of_coresight.c
+++ /dev/null
@@ -1,297 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (c) 2012, The Linux Foundation. All rights reserved.
- */
-
-#include <linux/types.h>
-#include <linux/err.h>
-#include <linux/slab.h>
-#include <linux/clk.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_graph.h>
-#include <linux/of_platform.h>
-#include <linux/platform_device.h>
-#include <linux/amba/bus.h>
-#include <linux/coresight.h>
-#include <linux/cpumask.h>
-#include <asm/smp_plat.h>
-
-
-static int of_dev_node_match(struct device *dev, void *data)
-{
-	return dev->of_node == data;
-}
-
-static struct device *
-of_coresight_get_endpoint_device(struct device_node *endpoint)
-{
-	struct device *dev = NULL;
-
-	/*
-	 * If we have a non-configurable replicator, it will be found on the
-	 * platform bus.
-	 */
-	dev = bus_find_device(&platform_bus_type, NULL,
-			      endpoint, of_dev_node_match);
-	if (dev)
-		return dev;
-
-	/*
-	 * We have a configurable component - circle through the AMBA bus
-	 * looking for the device that matches the endpoint node.
-	 */
-	return bus_find_device(&amba_bustype, NULL,
-			       endpoint, of_dev_node_match);
-}
-
-static inline bool of_coresight_legacy_ep_is_input(struct device_node *ep)
-{
-	return of_property_read_bool(ep, "slave-mode");
-}
-
-static void of_coresight_get_ports_legacy(const struct device_node *node,
-					  int *nr_inport, int *nr_outport)
-{
-	struct device_node *ep = NULL;
-	int in = 0, out = 0;
-
-	do {
-		ep = of_graph_get_next_endpoint(node, ep);
-		if (!ep)
-			break;
-
-		if (of_coresight_legacy_ep_is_input(ep))
-			in++;
-		else
-			out++;
-
-	} while (ep);
-
-	*nr_inport = in;
-	*nr_outport = out;
-}
-
-static struct device_node *of_coresight_get_port_parent(struct device_node *ep)
-{
-	struct device_node *parent = of_graph_get_port_parent(ep);
-
-	/*
-	 * Skip one-level up to the real device node, if we
-	 * are using the new bindings.
-	 */
-	if (of_node_name_eq(parent, "in-ports") ||
-	    of_node_name_eq(parent, "out-ports"))
-		parent = of_get_next_parent(parent);
-
-	return parent;
-}
-
-static inline struct device_node *
-of_coresight_get_input_ports_node(const struct device_node *node)
-{
-	return of_get_child_by_name(node, "in-ports");
-}
-
-static inline struct device_node *
-of_coresight_get_output_ports_node(const struct device_node *node)
-{
-	return of_get_child_by_name(node, "out-ports");
-}
-
-static inline int
-of_coresight_count_ports(struct device_node *port_parent)
-{
-	int i = 0;
-	struct device_node *ep = NULL;
-
-	while ((ep = of_graph_get_next_endpoint(port_parent, ep)))
-		i++;
-	return i;
-}
-
-static void of_coresight_get_ports(const struct device_node *node,
-				   int *nr_inport, int *nr_outport)
-{
-	struct device_node *input_ports = NULL, *output_ports = NULL;
-
-	input_ports = of_coresight_get_input_ports_node(node);
-	output_ports = of_coresight_get_output_ports_node(node);
-
-	if (input_ports || output_ports) {
-		if (input_ports) {
-			*nr_inport = of_coresight_count_ports(input_ports);
-			of_node_put(input_ports);
-		}
-		if (output_ports) {
-			*nr_outport = of_coresight_count_ports(output_ports);
-			of_node_put(output_ports);
-		}
-	} else {
-		/* Fall back to legacy DT bindings parsing */
-		of_coresight_get_ports_legacy(node, nr_inport, nr_outport);
-	}
-}
-
-static int of_coresight_alloc_memory(struct device *dev,
-			struct coresight_platform_data *pdata)
-{
-	if (pdata->nr_outport) {
-		pdata->conns = devm_kzalloc(dev, pdata->nr_outport *
-					    sizeof(*pdata->conns),
-					    GFP_KERNEL);
-		if (!pdata->conns)
-			return -ENOMEM;
-	}
-
-	return 0;
-}
-
-int of_coresight_get_cpu(const struct device_node *node)
-{
-	int cpu;
-	struct device_node *dn;
-
-	dn = of_parse_phandle(node, "cpu", 0);
-	/* Affinity defaults to CPU0 */
-	if (!dn)
-		return 0;
-	cpu = of_cpu_node_to_id(dn);
-	of_node_put(dn);
-
-	/* Affinity to CPU0 if no cpu nodes are found */
-	return (cpu < 0) ? 0 : cpu;
-}
-EXPORT_SYMBOL_GPL(of_coresight_get_cpu);
-
-/*
- * of_coresight_parse_endpoint : Parse the given output endpoint @ep
- * and fill the connection information in @conn
- *
- * Parses the local port, remote device name and the remote port.
- *
- * Returns :
- *	 1	- If the parsing is successful and a connection record
- *		  was created for an output connection.
- *	 0	- If the parsing completed without any fatal errors.
- *	-Errno	- Fatal error, abort the scanning.
- */
-static int of_coresight_parse_endpoint(struct device *dev,
-				       struct device_node *ep,
-				       struct coresight_connection *conn)
-{
-	int ret = 0;
-	struct of_endpoint endpoint, rendpoint;
-	struct device_node *rparent = NULL;
-	struct device_node *rep = NULL;
-	struct device *rdev = NULL;
-
-	do {
-		/* Parse the local port details */
-		if (of_graph_parse_endpoint(ep, &endpoint))
-			break;
-		/*
-		 * Get a handle on the remote endpoint and the device it is
-		 * attached to.
-		 */
-		rep = of_graph_get_remote_endpoint(ep);
-		if (!rep)
-			break;
-		rparent = of_coresight_get_port_parent(rep);
-		if (!rparent)
-			break;
-		if (of_graph_parse_endpoint(rep, &rendpoint))
-			break;
-
-		/* If the remote device is not available, defer probing */
-		rdev = of_coresight_get_endpoint_device(rparent);
-		if (!rdev) {
-			ret = -EPROBE_DEFER;
-			break;
-		}
-
-		conn->outport = endpoint.port;
-		conn->child_name = devm_kstrdup(dev,
-						dev_name(rdev),
-						GFP_KERNEL);
-		conn->child_port = rendpoint.port;
-		/* Connection record updated */
-		ret = 1;
-	} while (0);
-
-	of_node_put(rparent);
-	of_node_put(rep);
-	put_device(rdev);
-
-	return ret;
-}
-
-struct coresight_platform_data *
-of_get_coresight_platform_data(struct device *dev,
-			       const struct device_node *node)
-{
-	int ret = 0;
-	struct coresight_platform_data *pdata;
-	struct coresight_connection *conn;
-	struct device_node *ep = NULL;
-	const struct device_node *parent = NULL;
-	bool legacy_binding = false;
-
-	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
-	if (!pdata)
-		return ERR_PTR(-ENOMEM);
-
-	/* Use device name as sysfs handle */
-	pdata->name = dev_name(dev);
-	pdata->cpu = of_coresight_get_cpu(node);
-
-	/* Get the number of input and output port for this component */
-	of_coresight_get_ports(node, &pdata->nr_inport, &pdata->nr_outport);
-
-	/* If there are no output connections, we are done */
-	if (!pdata->nr_outport)
-		return pdata;
-
-	ret = of_coresight_alloc_memory(dev, pdata);
-	if (ret)
-		return ERR_PTR(ret);
-
-	parent = of_coresight_get_output_ports_node(node);
-	/*
-	 * If the DT uses obsoleted bindings, the ports are listed
-	 * under the device and we need to filter out the input
-	 * ports.
-	 */
-	if (!parent) {
-		legacy_binding = true;
-		parent = node;
-		dev_warn_once(dev, "Uses obsolete Coresight DT bindings\n");
-	}
-
-	conn = pdata->conns;
-
-	/* Iterate through each output port to discover topology */
-	while ((ep = of_graph_get_next_endpoint(parent, ep))) {
-		/*
-		 * Legacy binding mixes input/output ports under the
-		 * same parent. So, skip the input ports if we are dealing
-		 * with legacy binding, as they processed with their
-		 * connected output ports.
-		 */
-		if (legacy_binding && of_coresight_legacy_ep_is_input(ep))
-			continue;
-
-		ret = of_coresight_parse_endpoint(dev, ep, conn);
-		switch (ret) {
-		case 1:
-			conn++;		/* Fall through */
-		case 0:
-			break;
-		default:
-			return ERR_PTR(ret);
-		}
-	}
-
-	return pdata;
-}
-EXPORT_SYMBOL_GPL(of_get_coresight_platform_data);
diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index 81bb54fa3ce8..8ab28e5fb366 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -33,14 +33,18 @@
  * @entry:	window list linkage (msc::win_list)
  * @pgoff:	page offset into the buffer that this window starts at
  * @nr_blocks:	number of blocks (pages) in this window
+ * @nr_segs:	number of segments in this window (<= @nr_blocks)
+ * @_sgt:	array of block descriptors
  * @sgt:	array of block descriptors
  */
 struct msc_window {
 	struct list_head	entry;
 	unsigned long		pgoff;
 	unsigned int		nr_blocks;
+	unsigned int		nr_segs;
 	struct msc		*msc;
-	struct sg_table		sgt;
+	struct sg_table		_sgt;
+	struct sg_table		*sgt;
 };
 
 /**
@@ -138,13 +142,19 @@ static inline bool msc_block_is_empty(struct msc_block_desc *bdesc)
 static inline struct msc_block_desc *
 msc_win_block(struct msc_window *win, unsigned int block)
 {
-	return sg_virt(&win->sgt.sgl[block]);
+	return sg_virt(&win->sgt->sgl[block]);
+}
+
+static inline size_t
+msc_win_actual_bsz(struct msc_window *win, unsigned int block)
+{
+	return win->sgt->sgl[block].length;
 }
 
 static inline dma_addr_t
 msc_win_baddr(struct msc_window *win, unsigned int block)
 {
-	return sg_dma_address(&win->sgt.sgl[block]);
+	return sg_dma_address(&win->sgt->sgl[block]);
 }
 
 static inline unsigned long
@@ -179,17 +189,18 @@ static struct msc_window *msc_next_window(struct msc_window *win)
 }
 
 /**
- * msc_oldest_window() - locate the window with oldest data
+ * msc_find_window() - find a window matching a given sg_table
  * @msc:	MSC device
+ * @sgt:	SG table of the window
+ * @nonempty:	skip over empty windows
  *
- * This should only be used in multiblock mode. Caller should hold the
- * msc::user_count reference.
- *
- * Return:	the oldest window with valid data
+ * Return:	MSC window structure pointer or NULL if the window
+ *		could not be found.
  */
-static struct msc_window *msc_oldest_window(struct msc *msc)
+static struct msc_window *
+msc_find_window(struct msc *msc, struct sg_table *sgt, bool nonempty)
 {
-	struct msc_window *win, *next = msc_next_window(msc->cur_win);
+	struct msc_window *win;
 	unsigned int found = 0;
 
 	if (list_empty(&msc->win_list))
@@ -201,17 +212,40 @@ static struct msc_window *msc_oldest_window(struct msc *msc)
 	 * something like 2, in which case we're good
 	 */
 	list_for_each_entry(win, &msc->win_list, entry) {
-		if (win == next)
+		if (win->sgt == sgt)
 			found++;
 
 		/* skip the empty ones */
-		if (msc_block_is_empty(msc_win_block(win, 0)))
+		if (nonempty && msc_block_is_empty(msc_win_block(win, 0)))
 			continue;
 
 		if (found)
 			return win;
 	}
 
+	return NULL;
+}
+
+/**
+ * msc_oldest_window() - locate the window with oldest data
+ * @msc:	MSC device
+ *
+ * This should only be used in multiblock mode. Caller should hold the
+ * msc::user_count reference.
+ *
+ * Return:	the oldest window with valid data
+ */
+static struct msc_window *msc_oldest_window(struct msc *msc)
+{
+	struct msc_window *win;
+
+	if (list_empty(&msc->win_list))
+		return NULL;
+
+	win = msc_find_window(msc, msc_next_window(msc->cur_win)->sgt, true);
+	if (win)
+		return win;
+
 	return list_first_entry(&msc->win_list, struct msc_window, entry);
 }
 
@@ -234,7 +268,7 @@ static unsigned int msc_win_oldest_block(struct msc_window *win)
 	 * with wrapping, last written block contains both the newest and the
 	 * oldest data for this window.
 	 */
-	for (blk = 0; blk < win->nr_blocks; blk++) {
+	for (blk = 0; blk < win->nr_segs; blk++) {
 		bdesc = msc_win_block(win, blk);
 
 		if (msc_block_last_written(bdesc))
@@ -366,7 +400,7 @@ static int msc_iter_block_advance(struct msc_iter *iter)
 		return msc_iter_win_advance(iter);
 
 	/* block advance */
-	if (++iter->block == iter->win->nr_blocks)
+	if (++iter->block == iter->win->nr_segs)
 		iter->block = 0;
 
 	/* no wrapping, sanity check in case there is no last written block */
@@ -478,7 +512,7 @@ static void msc_buffer_clear_hw_header(struct msc *msc)
 		size_t hw_sz = sizeof(struct msc_block_desc) -
 			offsetof(struct msc_block_desc, hw_tag);
 
-		for (blk = 0; blk < win->nr_blocks; blk++) {
+		for (blk = 0; blk < win->nr_segs; blk++) {
 			struct msc_block_desc *bdesc = msc_win_block(win, blk);
 
 			memset(&bdesc->hw_tag, 0, hw_sz);
@@ -667,7 +701,7 @@ static int msc_buffer_contig_alloc(struct msc *msc, unsigned long size)
 		goto err_out;
 
 	ret = -ENOMEM;
-	page = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
+	page = alloc_pages(GFP_KERNEL | __GFP_ZERO | GFP_DMA32, order);
 	if (!page)
 		goto err_free_sgt;
 
@@ -734,17 +768,17 @@ static struct page *msc_buffer_contig_get_page(struct msc *msc,
 }
 
 static int __msc_buffer_win_alloc(struct msc_window *win,
-				  unsigned int nr_blocks)
+				  unsigned int nr_segs)
 {
 	struct scatterlist *sg_ptr;
 	void *block;
 	int i, ret;
 
-	ret = sg_alloc_table(&win->sgt, nr_blocks, GFP_KERNEL);
+	ret = sg_alloc_table(win->sgt, nr_segs, GFP_KERNEL);
 	if (ret)
 		return -ENOMEM;
 
-	for_each_sg(win->sgt.sgl, sg_ptr, nr_blocks, i) {
+	for_each_sg(win->sgt->sgl, sg_ptr, nr_segs, i) {
 		block = dma_alloc_coherent(msc_dev(win->msc)->parent->parent,
 					  PAGE_SIZE, &sg_dma_address(sg_ptr),
 					  GFP_KERNEL);
@@ -754,7 +788,7 @@ static int __msc_buffer_win_alloc(struct msc_window *win,
 		sg_set_buf(sg_ptr, block, PAGE_SIZE);
 	}
 
-	return nr_blocks;
+	return nr_segs;
 
 err_nomem:
 	for (i--; i >= 0; i--)
@@ -762,11 +796,35 @@ err_nomem:
 				  msc_win_block(win, i),
 				  msc_win_baddr(win, i));
 
-	sg_free_table(&win->sgt);
+	sg_free_table(win->sgt);
 
 	return -ENOMEM;
 }
 
+#ifdef CONFIG_X86
+static void msc_buffer_set_uc(struct msc_window *win, unsigned int nr_segs)
+{
+	int i;
+
+	for (i = 0; i < nr_segs; i++)
+		/* Set the page as uncached */
+		set_memory_uc((unsigned long)msc_win_block(win, i), 1);
+}
+
+static void msc_buffer_set_wb(struct msc_window *win)
+{
+	int i;
+
+	for (i = 0; i < win->nr_segs; i++)
+		/* Reset the page to write-back */
+		set_memory_wb((unsigned long)msc_win_block(win, i), 1);
+}
+#else /* !X86 */
+static inline void
+msc_buffer_set_uc(struct msc_window *win, unsigned int nr_segs) {}
+static inline void msc_buffer_set_wb(struct msc_window *win) {}
+#endif /* CONFIG_X86 */
+
 /**
  * msc_buffer_win_alloc() - alloc a window for a multiblock mode
  * @msc:	MSC device
@@ -780,7 +838,7 @@ err_nomem:
 static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks)
 {
 	struct msc_window *win;
-	int ret = -ENOMEM, i;
+	int ret = -ENOMEM;
 
 	if (!nr_blocks)
 		return 0;
@@ -797,13 +855,13 @@ static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks)
 		return -ENOMEM;
 
 	win->msc = msc;
+	win->sgt = &win->_sgt;
 
 	if (!list_empty(&msc->win_list)) {
 		struct msc_window *prev = list_last_entry(&msc->win_list,
 							  struct msc_window,
 							  entry);
 
-		/* This works as long as blocks are page-sized */
 		win->pgoff = prev->pgoff + prev->nr_blocks;
 	}
 
@@ -811,13 +869,10 @@ static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks)
 	if (ret < 0)
 		goto err_nomem;
 
-#ifdef CONFIG_X86
-	for (i = 0; i < ret; i++)
-		/* Set the page as uncached */
-		set_memory_uc((unsigned long)msc_win_block(win, i), 1);
-#endif
+	msc_buffer_set_uc(win, ret);
 
-	win->nr_blocks = ret;
+	win->nr_segs = ret;
+	win->nr_blocks = nr_blocks;
 
 	if (list_empty(&msc->win_list)) {
 		msc->base = msc_win_block(win, 0);
@@ -840,14 +895,14 @@ static void __msc_buffer_win_free(struct msc *msc, struct msc_window *win)
 {
 	int i;
 
-	for (i = 0; i < win->nr_blocks; i++) {
-		struct page *page = sg_page(&win->sgt.sgl[i]);
+	for (i = 0; i < win->nr_segs; i++) {
+		struct page *page = sg_page(&win->sgt->sgl[i]);
 
 		page->mapping = NULL;
 		dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE,
 				  msc_win_block(win, i), msc_win_baddr(win, i));
 	}
-	sg_free_table(&win->sgt);
+	sg_free_table(win->sgt);
 }
 
 /**
@@ -860,8 +915,6 @@ static void __msc_buffer_win_free(struct msc *msc, struct msc_window *win)
  */
 static void msc_buffer_win_free(struct msc *msc, struct msc_window *win)
 {
-	int i;
-
 	msc->nr_pages -= win->nr_blocks;
 
 	list_del(&win->entry);
@@ -870,11 +923,7 @@ static void msc_buffer_win_free(struct msc *msc, struct msc_window *win)
 		msc->base_addr = 0;
 	}
 
-#ifdef CONFIG_X86
-	for (i = 0; i < win->nr_blocks; i++)
-		/* Reset the page to write-back */
-		set_memory_wb((unsigned long)msc_win_block(win, i), 1);
-#endif
+	msc_buffer_set_wb(win);
 
 	__msc_buffer_win_free(msc, win);
 
@@ -909,7 +958,7 @@ static void msc_buffer_relink(struct msc *msc)
 			next_win = list_next_entry(win, entry);
 		}
 
-		for (blk = 0; blk < win->nr_blocks; blk++) {
+		for (blk = 0; blk < win->nr_segs; blk++) {
 			struct msc_block_desc *bdesc = msc_win_block(win, blk);
 
 			memset(bdesc, 0, sizeof(*bdesc));
@@ -920,7 +969,7 @@ static void msc_buffer_relink(struct msc *msc)
 			 * Similarly to last window, last block should point
 			 * to the first one.
 			 */
-			if (blk == win->nr_blocks - 1) {
+			if (blk == win->nr_segs - 1) {
 				sw_tag |= MSC_SW_TAG_LASTBLK;
 				bdesc->next_blk = msc_win_bpfn(win, 0);
 			} else {
@@ -928,7 +977,7 @@ static void msc_buffer_relink(struct msc *msc)
 			}
 
 			bdesc->sw_tag = sw_tag;
-			bdesc->block_sz = PAGE_SIZE / 64;
+			bdesc->block_sz = msc_win_actual_bsz(win, blk) / 64;
 		}
 	}
 
@@ -1087,6 +1136,7 @@ static int msc_buffer_free_unless_used(struct msc *msc)
 static struct page *msc_buffer_get_page(struct msc *msc, unsigned long pgoff)
 {
 	struct msc_window *win;
+	unsigned int blk;
 
 	if (msc->mode == MSC_MODE_SINGLE)
 		return msc_buffer_contig_get_page(msc, pgoff);
@@ -1099,7 +1149,18 @@ static struct page *msc_buffer_get_page(struct msc *msc, unsigned long pgoff)
 
 found:
 	pgoff -= win->pgoff;
-	return sg_page(&win->sgt.sgl[pgoff]);
+
+	for (blk = 0; blk < win->nr_segs; blk++) {
+		struct page *page = sg_page(&win->sgt->sgl[blk]);
+		size_t pgsz = PFN_DOWN(msc_win_actual_bsz(win, blk));
+
+		if (pgoff < pgsz)
+			return page + pgoff;
+
+		pgoff -= pgsz;
+	}
+
+	return NULL;
 }
 
 /**
@@ -1386,10 +1447,9 @@ static int intel_th_msc_init(struct msc *msc)
 
 static void msc_win_switch(struct msc *msc)
 {
-	struct msc_window *last, *first;
+	struct msc_window *first;
 
 	first = list_first_entry(&msc->win_list, struct msc_window, entry);
-	last = list_last_entry(&msc->win_list, struct msc_window, entry);
 
 	if (msc_is_last_win(msc->cur_win))
 		msc->cur_win = first;
diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index f1228708f2a2..c0378c3de9a4 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -194,6 +194,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x02a6),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
+	{
+		/* Ice Lake NNPI */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x45c5),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
 	{ 0 },
 };
 
diff --git a/drivers/memory/Kconfig b/drivers/memory/Kconfig
index 392ad4f5c570..dbdee02bb592 100644
--- a/drivers/memory/Kconfig
+++ b/drivers/memory/Kconfig
@@ -123,7 +123,7 @@ config FSL_IFC
 config JZ4780_NEMC
 	bool "Ingenic JZ4780 SoC NEMC driver"
 	default y
-	depends on MACH_JZ4780 || COMPILE_TEST
+	depends on MIPS || COMPILE_TEST
 	depends on HAS_IOMEM && OF
 	help
 	  This driver is for the NAND/External Memory Controller (NEMC) in
diff --git a/drivers/memory/jz4780-nemc.c b/drivers/memory/jz4780-nemc.c
index 698da973de35..2a3f7ef1c8c4 100644
--- a/drivers/memory/jz4780-nemc.c
+++ b/drivers/memory/jz4780-nemc.c
@@ -41,9 +41,14 @@
 #define NEMC_NFCSR_NFCEn(n)	BIT((((n) - 1) << 1) + 1)
 #define NEMC_NFCSR_TNFEn(n)	BIT(16 + (n) - 1)
 
+struct jz_soc_info {
+	u8 tas_tah_cycles_max;
+};
+
 struct jz4780_nemc {
 	spinlock_t lock;
 	struct device *dev;
+	const struct jz_soc_info *soc_info;
 	void __iomem *base;
 	struct clk *clk;
 	uint32_t clk_period;
@@ -158,7 +163,7 @@ static bool jz4780_nemc_configure_bank(struct jz4780_nemc *nemc,
 	 * Conversion of tBP and tAW cycle counts to values supported by the
 	 * hardware (round up to the next supported value).
 	 */
-	static const uint32_t convert_tBP_tAW[] = {
+	static const u8 convert_tBP_tAW[] = {
 		0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10,
 
 		/* 11 - 12 -> 12 cycles */
@@ -199,7 +204,7 @@ static bool jz4780_nemc_configure_bank(struct jz4780_nemc *nemc,
 	if (of_property_read_u32(node, "ingenic,nemc-tAS", &val) == 0) {
 		smcr &= ~NEMC_SMCR_TAS_MASK;
 		cycles = jz4780_nemc_ns_to_cycles(nemc, val);
-		if (cycles > 15) {
+		if (cycles > nemc->soc_info->tas_tah_cycles_max) {
 			dev_err(nemc->dev, "tAS %u is too high (%u cycles)\n",
 				val, cycles);
 			return false;
@@ -211,7 +216,7 @@ static bool jz4780_nemc_configure_bank(struct jz4780_nemc *nemc,
 	if (of_property_read_u32(node, "ingenic,nemc-tAH", &val) == 0) {
 		smcr &= ~NEMC_SMCR_TAH_MASK;
 		cycles = jz4780_nemc_ns_to_cycles(nemc, val);
-		if (cycles > 15) {
+		if (cycles > nemc->soc_info->tas_tah_cycles_max) {
 			dev_err(nemc->dev, "tAH %u is too high (%u cycles)\n",
 				val, cycles);
 			return false;
@@ -275,6 +280,10 @@ static int jz4780_nemc_probe(struct platform_device *pdev)
 	if (!nemc)
 		return -ENOMEM;
 
+	nemc->soc_info = device_get_match_data(dev);
+	if (!nemc->soc_info)
+		return -EINVAL;
+
 	spin_lock_init(&nemc->lock);
 	nemc->dev = dev;
 
@@ -367,8 +376,17 @@ static int jz4780_nemc_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct jz_soc_info jz4740_soc_info = {
+	.tas_tah_cycles_max = 7,
+};
+
+static const struct jz_soc_info jz4780_soc_info = {
+	.tas_tah_cycles_max = 15,
+};
+
 static const struct of_device_id jz4780_nemc_dt_match[] = {
-	{ .compatible = "ingenic,jz4780-nemc" },
+	{ .compatible = "ingenic,jz4740-nemc", .data = &jz4740_soc_info, },
+	{ .compatible = "ingenic,jz4780-nemc", .data = &jz4780_soc_info, },
 	{},
 };
 
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 85fc77148d19..6abfc8e92fcc 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -9,7 +9,6 @@ config SENSORS_LIS3LV02D
 	tristate
 	depends on INPUT
 	select INPUT_POLLDEV
-	default n
 
 config AD525X_DPOT
 	tristate "Analog Devices Digital Potentiometers"
@@ -62,7 +61,6 @@ config ATMEL_TCLIB
 
 config DUMMY_IRQ
 	tristate "Dummy IRQ handler"
-	default n
 	---help---
 	  This module accepts a single 'irq' parameter, which it should register for.
 	  The sole purpose of this module is to help with debugging of systems on
@@ -118,7 +116,6 @@ config PHANTOM
 config INTEL_MID_PTI
 	tristate "Parallel Trace Interface for MIPI P1149.7 cJTAG standard"
 	depends on PCI && TTY && (X86_INTEL_MID || COMPILE_TEST)
-	default n
 	help
 	  The PTI (Parallel Trace Interface) driver directs
 	  trace data routed from various parts in the system out
@@ -194,7 +191,6 @@ config ATMEL_SSC
 
 config ENCLOSURE_SERVICES
 	tristate "Enclosure Services"
-	default n
 	help
 	  Provides support for intelligent enclosures (bays which
 	  contain storage devices).  You also need either a host
@@ -218,7 +214,6 @@ config SGI_XP
 config CS5535_MFGPT
 	tristate "CS5535/CS5536 Geode Multi-Function General Purpose Timer (MFGPT) support"
 	depends on MFD_CS5535
-	default n
 	help
 	  This driver provides access to MFGPT functionality for other
 	  drivers that need timers.  MFGPTs are available in the CS5535 and
@@ -251,7 +246,6 @@ config CS5535_CLOCK_EVENT_SRC
 config HP_ILO
 	tristate "Channel interface driver for the HP iLO processor"
 	depends on PCI
-	default n
 	help
 	  The channel interface driver allows applications to communicate
 	  with iLO management processors present on HP ProLiant servers.
@@ -286,7 +280,6 @@ config QCOM_FASTRPC
 config SGI_GRU
 	tristate "SGI GRU driver"
 	depends on X86_UV && SMP
-	default n
 	select MMU_NOTIFIER
 	---help---
 	The GRU is a hardware resource located in the system chipset. The GRU
@@ -301,7 +294,6 @@ config SGI_GRU
 config SGI_GRU_DEBUG
 	bool  "SGI GRU driver debug"
 	depends on SGI_GRU
-	default n
 	---help---
 	This option enables additional debugging code for the SGI GRU driver.
 	If you are unsure, say N.
@@ -359,7 +351,6 @@ config SENSORS_BH1770
 config SENSORS_APDS990X
 	 tristate "APDS990X combined als and proximity sensors"
 	 depends on I2C
-	 default n
 	 ---help---
 	   Say Y here if you want to build a driver for Avago APDS990x
 	   combined ambient light and proximity sensor chip.
@@ -387,7 +378,6 @@ config DS1682
 config SPEAR13XX_PCIE_GADGET
 	bool "PCIe gadget support for SPEAr13XX platform"
 	depends on ARCH_SPEAR13XX && BROKEN
-	default n
 	help
 	 This option enables gadget support for PCIe controller. If
 	 board file defines any controller as PCIe endpoint then a sysfs
@@ -397,6 +387,7 @@ config SPEAR13XX_PCIE_GADGET
 config VMWARE_BALLOON
 	tristate "VMware Balloon Driver"
 	depends on VMWARE_VMCI && X86 && HYPERVISOR_GUEST
+	select MEMORY_BALLOON
 	help
 	  This is VMware physical memory management driver which acts
 	  like a "balloon" that can be inflated to reclaim physical pages
@@ -431,15 +422,6 @@ config PCH_PHUB
 	  To compile this driver as a module, choose M here: the module will
 	  be called pch_phub.
 
-config USB_SWITCH_FSA9480
-	tristate "FSA9480 USB Switch"
-	depends on I2C
-	help
-	  The FSA9480 is a USB port accessory detector and switch.
-	  The FSA9480 is fully controlled using I2C and enables USB data,
-	  stereo and mono audio, video, microphone and UART data to use
-	  a common connector port.
-
 config LATTICE_ECP3_CONFIG
 	tristate "Lattice ECP3 FPGA bitstream configuration via SPI"
 	depends on SPI && SYSFS
@@ -481,6 +463,18 @@ config PCI_ENDPOINT_TEST
            Enable this configuration option to enable the host side test driver
            for PCI Endpoint.
 
+config XILINX_SDFEC
+	tristate "Xilinx SDFEC 16"
+	help
+	  This option enables support for the Xilinx SDFEC (Soft Decision
+	  Forward Error Correction) driver. This enables a char driver
+	  for the SDFEC.
+
+	  You may select this driver if your design instantiates the
+	  SDFEC(16nm) hardened block. To compile this as a module choose M.
+
+	  If unsure, say N.
+
 config MISC_RTSX
 	tristate
 	default MISC_RTSX_PCI || MISC_RTSX_USB
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index b9affcdaa3d6..abd8ae249746 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -42,7 +42,6 @@ obj-$(CONFIG_VMWARE_BALLOON)	+= vmw_balloon.o
 obj-$(CONFIG_PCH_PHUB)		+= pch_phub.o
 obj-y				+= ti-st/
 obj-y				+= lis3lv02d/
-obj-$(CONFIG_USB_SWITCH_FSA9480) += fsa9480.o
 obj-$(CONFIG_ALTERA_STAPL)	+=altera-stapl/
 obj-$(CONFIG_INTEL_MEI)		+= mei/
 obj-$(CONFIG_VMWARE_VMCI)	+= vmw_vmci/
@@ -59,3 +58,4 @@ obj-$(CONFIG_OCXL)		+= ocxl/
 obj-y				+= cardreader/
 obj-$(CONFIG_PVPANIC)   	+= pvpanic.o
 obj-$(CONFIG_HABANA_AI)		+= habanalabs/
+obj-$(CONFIG_XILINX_SDFEC)	+= xilinx_sdfec.o
diff --git a/drivers/misc/altera-stapl/Kconfig b/drivers/misc/altera-stapl/Kconfig
index b34863544365..6c4c6575ec31 100644
--- a/drivers/misc/altera-stapl/Kconfig
+++ b/drivers/misc/altera-stapl/Kconfig
@@ -5,6 +5,5 @@ comment "Altera FPGA firmware download module (requires I2C)"
 config ALTERA_STAPL
 	tristate "Altera FPGA firmware download module"
 	depends on I2C
-	default n
 	help
 	  An Altera FPGA module. Say Y when you want to support this tool.
diff --git a/drivers/misc/c2port/Kconfig b/drivers/misc/c2port/Kconfig
index 192e25094bd4..e20516ffd91e 100644
--- a/drivers/misc/c2port/Kconfig
+++ b/drivers/misc/c2port/Kconfig
@@ -5,7 +5,6 @@
 
 menuconfig C2PORT
 	tristate "Silicon Labs C2 port support"
-	default n
 	help
 	  This option enables support for Silicon Labs C2 port used to
 	  program Silicon micro controller chips (and other 8051 compatible).
@@ -24,7 +23,6 @@ if C2PORT
 config C2PORT_DURAMAR_2150
 	tristate "C2 port support for Eurotech's Duramar 2150"
 	depends on X86
-	default n
 	help
 	  This option enables C2 support for the Eurotech's Duramar 2150
 	  on board micro controller.
diff --git a/drivers/misc/cb710/Kconfig b/drivers/misc/cb710/Kconfig
index 3c7356d55423..a696d7509024 100644
--- a/drivers/misc/cb710/Kconfig
+++ b/drivers/misc/cb710/Kconfig
@@ -15,7 +15,6 @@ config CB710_CORE
 config CB710_DEBUG
 	bool "Enable driver debugging"
 	depends on CB710_CORE != n
-	default n
 	help
 	  This is an option for use by developers; most people should
 	  say N here.  This adds a lot of debugging output to dmesg.
diff --git a/drivers/misc/cxl/Kconfig b/drivers/misc/cxl/Kconfig
index f1d9a843e361..39eec9031487 100644
--- a/drivers/misc/cxl/Kconfig
+++ b/drivers/misc/cxl/Kconfig
@@ -5,16 +5,13 @@
 
 config CXL_BASE
 	bool
-	default n
 	select PPC_COPRO_BASE
 
 config CXL_AFU_DRIVER_OPS
 	bool
-	default n
 
 config CXL_LIB
 	bool
-	default n
 
 config CXL
 	tristate "Support for IBM Coherent Accelerators (CXL)"
diff --git a/drivers/misc/echo/Kconfig b/drivers/misc/echo/Kconfig
index 39656413e70d..be70b263e271 100644
--- a/drivers/misc/echo/Kconfig
+++ b/drivers/misc/echo/Kconfig
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config ECHO
 	tristate "Line Echo Canceller support"
-	default n
 	---help---
 	  This driver provides line echo cancelling support for mISDN and
 	  Zaptel drivers.
diff --git a/drivers/misc/eeprom/ee1004.c b/drivers/misc/eeprom/ee1004.c
index be3263df278a..6f00c33cfe22 100644
--- a/drivers/misc/eeprom/ee1004.c
+++ b/drivers/misc/eeprom/ee1004.c
@@ -2,7 +2,7 @@
 /*
  * ee1004 - driver for DDR4 SPD EEPROMs
  *
- * Copyright (C) 2017 Jean Delvare
+ * Copyright (C) 2017-2019 Jean Delvare
  *
  * Based on the at24 driver:
  * Copyright (C) 2005-2007 David Brownell
@@ -53,6 +53,24 @@ MODULE_DEVICE_TABLE(i2c, ee1004_ids);
 
 /*-------------------------------------------------------------------------*/
 
+static int ee1004_get_current_page(void)
+{
+	int err;
+
+	err = i2c_smbus_read_byte(ee1004_set_page[0]);
+	if (err == -ENXIO) {
+		/* Nack means page 1 is selected */
+		return 1;
+	}
+	if (err < 0) {
+		/* Anything else is a real error, bail out */
+		return err;
+	}
+
+	/* Ack means page 0 is selected, returned value meaningless */
+	return 0;
+}
+
 static ssize_t ee1004_eeprom_read(struct i2c_client *client, char *buf,
 				  unsigned int offset, size_t count)
 {
@@ -102,6 +120,16 @@ static ssize_t ee1004_read(struct file *filp, struct kobject *kobj,
 			/* Data is ignored */
 			status = i2c_smbus_write_byte(ee1004_set_page[page],
 						      0x00);
+			if (status == -ENXIO) {
+				/*
+				 * Don't give up just yet. Some memory
+				 * modules will select the page but not
+				 * ack the command. Check which page is
+				 * selected now.
+				 */
+				if (ee1004_get_current_page() == page)
+					status = 0;
+			}
 			if (status < 0) {
 				dev_err(dev, "Failed to select page %d (%d)\n",
 					page, status);
@@ -186,17 +214,10 @@ static int ee1004_probe(struct i2c_client *client,
 	}
 
 	/* Remember current page to avoid unneeded page select */
-	err = i2c_smbus_read_byte(ee1004_set_page[0]);
-	if (err == -ENXIO) {
-		/* Nack means page 1 is selected */
-		ee1004_current_page = 1;
-	} else if (err < 0) {
-		/* Anything else is a real error, bail out */
+	err = ee1004_get_current_page();
+	if (err < 0)
 		goto err_clients;
-	} else {
-		/* Ack means page 0 is selected, returned value meaningless */
-		ee1004_current_page = 0;
-	}
+	ee1004_current_page = err;
 	dev_dbg(&client->dev, "Currently selected page: %d\n",
 		ee1004_current_page);
 	mutex_unlock(&ee1004_bus_lock);
diff --git a/drivers/misc/eeprom/idt_89hpesx.c b/drivers/misc/eeprom/idt_89hpesx.c
index 8a4659518c33..81c70e5bc168 100644
--- a/drivers/misc/eeprom/idt_89hpesx.c
+++ b/drivers/misc/eeprom/idt_89hpesx.c
@@ -115,7 +115,6 @@ static struct dentry *csr_dbgdir;
  * @client:	i2c client used to perform IO operations
  *
  * @ee_file:	EEPROM read/write sysfs-file
- * @csr_file:	CSR read/write debugfs-node
  */
 struct idt_smb_seq;
 struct idt_89hpesx_dev {
@@ -137,7 +136,6 @@ struct idt_89hpesx_dev {
 
 	struct bin_attribute *ee_file;
 	struct dentry *csr_dir;
-	struct dentry *csr_file;
 };
 
 /*
@@ -1378,8 +1376,8 @@ static void idt_create_dbgfs_files(struct idt_89hpesx_dev *pdev)
 	pdev->csr_dir = debugfs_create_dir(fname, csr_dbgdir);
 
 	/* Create Debugfs file for CSR read/write operations */
-	pdev->csr_file = debugfs_create_file(cli->name, 0600,
-		pdev->csr_dir, pdev, &csr_dbgfs_ops);
+	debugfs_create_file(cli->name, 0600, pdev->csr_dir, pdev,
+			    &csr_dbgfs_ops);
 }
 
 /*
diff --git a/drivers/misc/fsa9480.c b/drivers/misc/fsa9480.c
deleted file mode 100644
index fab02f2da077..000000000000
--- a/drivers/misc/fsa9480.c
+++ /dev/null
@@ -1,547 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * fsa9480.c - FSA9480 micro USB switch device driver
- *
- * Copyright (C) 2010 Samsung Electronics
- * Minkyu Kang <mk7.kang@samsung.com>
- * Wonguk Jeong <wonguk.jeong@samsung.com>
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/err.h>
-#include <linux/i2c.h>
-#include <linux/platform_data/fsa9480.h>
-#include <linux/irq.h>
-#include <linux/interrupt.h>
-#include <linux/workqueue.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-#include <linux/pm_runtime.h>
-
-/* FSA9480 I2C registers */
-#define FSA9480_REG_DEVID		0x01
-#define FSA9480_REG_CTRL		0x02
-#define FSA9480_REG_INT1		0x03
-#define FSA9480_REG_INT2		0x04
-#define FSA9480_REG_INT1_MASK		0x05
-#define FSA9480_REG_INT2_MASK		0x06
-#define FSA9480_REG_ADC			0x07
-#define FSA9480_REG_TIMING1		0x08
-#define FSA9480_REG_TIMING2		0x09
-#define FSA9480_REG_DEV_T1		0x0a
-#define FSA9480_REG_DEV_T2		0x0b
-#define FSA9480_REG_BTN1		0x0c
-#define FSA9480_REG_BTN2		0x0d
-#define FSA9480_REG_CK			0x0e
-#define FSA9480_REG_CK_INT1		0x0f
-#define FSA9480_REG_CK_INT2		0x10
-#define FSA9480_REG_CK_INTMASK1		0x11
-#define FSA9480_REG_CK_INTMASK2		0x12
-#define FSA9480_REG_MANSW1		0x13
-#define FSA9480_REG_MANSW2		0x14
-
-/* Control */
-#define CON_SWITCH_OPEN		(1 << 4)
-#define CON_RAW_DATA		(1 << 3)
-#define CON_MANUAL_SW		(1 << 2)
-#define CON_WAIT		(1 << 1)
-#define CON_INT_MASK		(1 << 0)
-#define CON_MASK		(CON_SWITCH_OPEN | CON_RAW_DATA | \
-				CON_MANUAL_SW | CON_WAIT)
-
-/* Device Type 1 */
-#define DEV_USB_OTG		(1 << 7)
-#define DEV_DEDICATED_CHG	(1 << 6)
-#define DEV_USB_CHG		(1 << 5)
-#define DEV_CAR_KIT		(1 << 4)
-#define DEV_UART		(1 << 3)
-#define DEV_USB			(1 << 2)
-#define DEV_AUDIO_2		(1 << 1)
-#define DEV_AUDIO_1		(1 << 0)
-
-#define DEV_T1_USB_MASK		(DEV_USB_OTG | DEV_USB)
-#define DEV_T1_UART_MASK	(DEV_UART)
-#define DEV_T1_CHARGER_MASK	(DEV_DEDICATED_CHG | DEV_USB_CHG)
-
-/* Device Type 2 */
-#define DEV_AV			(1 << 6)
-#define DEV_TTY			(1 << 5)
-#define DEV_PPD			(1 << 4)
-#define DEV_JIG_UART_OFF	(1 << 3)
-#define DEV_JIG_UART_ON		(1 << 2)
-#define DEV_JIG_USB_OFF		(1 << 1)
-#define DEV_JIG_USB_ON		(1 << 0)
-
-#define DEV_T2_USB_MASK		(DEV_JIG_USB_OFF | DEV_JIG_USB_ON)
-#define DEV_T2_UART_MASK	(DEV_JIG_UART_OFF | DEV_JIG_UART_ON)
-#define DEV_T2_JIG_MASK		(DEV_JIG_USB_OFF | DEV_JIG_USB_ON | \
-				DEV_JIG_UART_OFF | DEV_JIG_UART_ON)
-
-/*
- * Manual Switch
- * D- [7:5] / D+ [4:2]
- * 000: Open all / 001: USB / 010: AUDIO / 011: UART / 100: V_AUDIO
- */
-#define SW_VAUDIO		((4 << 5) | (4 << 2))
-#define SW_UART			((3 << 5) | (3 << 2))
-#define SW_AUDIO		((2 << 5) | (2 << 2))
-#define SW_DHOST		((1 << 5) | (1 << 2))
-#define SW_AUTO			((0 << 5) | (0 << 2))
-
-/* Interrupt 1 */
-#define INT_DETACH		(1 << 1)
-#define INT_ATTACH		(1 << 0)
-
-struct fsa9480_usbsw {
-	struct i2c_client		*client;
-	struct fsa9480_platform_data	*pdata;
-	int				dev1;
-	int				dev2;
-	int				mansw;
-};
-
-static struct fsa9480_usbsw *chip;
-
-static int fsa9480_write_reg(struct i2c_client *client,
-		int reg, int value)
-{
-	int ret;
-
-	ret = i2c_smbus_write_byte_data(client, reg, value);
-
-	if (ret < 0)
-		dev_err(&client->dev, "%s: err %d\n", __func__, ret);
-
-	return ret;
-}
-
-static int fsa9480_read_reg(struct i2c_client *client, int reg)
-{
-	int ret;
-
-	ret = i2c_smbus_read_byte_data(client, reg);
-
-	if (ret < 0)
-		dev_err(&client->dev, "%s: err %d\n", __func__, ret);
-
-	return ret;
-}
-
-static int fsa9480_read_irq(struct i2c_client *client, int *value)
-{
-	int ret;
-
-	ret = i2c_smbus_read_i2c_block_data(client,
-			FSA9480_REG_INT1, 2, (u8 *)value);
-	*value &= 0xffff;
-
-	if (ret < 0)
-		dev_err(&client->dev, "%s: err %d\n", __func__, ret);
-
-	return ret;
-}
-
-static void fsa9480_set_switch(const char *buf)
-{
-	struct fsa9480_usbsw *usbsw = chip;
-	struct i2c_client *client = usbsw->client;
-	unsigned int value;
-	unsigned int path = 0;
-
-	value = fsa9480_read_reg(client, FSA9480_REG_CTRL);
-
-	if (!strncmp(buf, "VAUDIO", 6)) {
-		path = SW_VAUDIO;
-		value &= ~CON_MANUAL_SW;
-	} else if (!strncmp(buf, "UART", 4)) {
-		path = SW_UART;
-		value &= ~CON_MANUAL_SW;
-	} else if (!strncmp(buf, "AUDIO", 5)) {
-		path = SW_AUDIO;
-		value &= ~CON_MANUAL_SW;
-	} else if (!strncmp(buf, "DHOST", 5)) {
-		path = SW_DHOST;
-		value &= ~CON_MANUAL_SW;
-	} else if (!strncmp(buf, "AUTO", 4)) {
-		path = SW_AUTO;
-		value |= CON_MANUAL_SW;
-	} else {
-		printk(KERN_ERR "Wrong command\n");
-		return;
-	}
-
-	usbsw->mansw = path;
-	fsa9480_write_reg(client, FSA9480_REG_MANSW1, path);
-	fsa9480_write_reg(client, FSA9480_REG_CTRL, value);
-}
-
-static ssize_t fsa9480_get_switch(char *buf)
-{
-	struct fsa9480_usbsw *usbsw = chip;
-	struct i2c_client *client = usbsw->client;
-	unsigned int value;
-
-	value = fsa9480_read_reg(client, FSA9480_REG_MANSW1);
-
-	if (value == SW_VAUDIO)
-		return sprintf(buf, "VAUDIO\n");
-	else if (value == SW_UART)
-		return sprintf(buf, "UART\n");
-	else if (value == SW_AUDIO)
-		return sprintf(buf, "AUDIO\n");
-	else if (value == SW_DHOST)
-		return sprintf(buf, "DHOST\n");
-	else if (value == SW_AUTO)
-		return sprintf(buf, "AUTO\n");
-	else
-		return sprintf(buf, "%x", value);
-}
-
-static ssize_t fsa9480_show_device(struct device *dev,
-				   struct device_attribute *attr,
-				   char *buf)
-{
-	struct fsa9480_usbsw *usbsw = dev_get_drvdata(dev);
-	struct i2c_client *client = usbsw->client;
-	int dev1, dev2;
-
-	dev1 = fsa9480_read_reg(client, FSA9480_REG_DEV_T1);
-	dev2 = fsa9480_read_reg(client, FSA9480_REG_DEV_T2);
-
-	if (!dev1 && !dev2)
-		return sprintf(buf, "NONE\n");
-
-	/* USB */
-	if (dev1 & DEV_T1_USB_MASK || dev2 & DEV_T2_USB_MASK)
-		return sprintf(buf, "USB\n");
-
-	/* UART */
-	if (dev1 & DEV_T1_UART_MASK || dev2 & DEV_T2_UART_MASK)
-		return sprintf(buf, "UART\n");
-
-	/* CHARGER */
-	if (dev1 & DEV_T1_CHARGER_MASK)
-		return sprintf(buf, "CHARGER\n");
-
-	/* JIG */
-	if (dev2 & DEV_T2_JIG_MASK)
-		return sprintf(buf, "JIG\n");
-
-	return sprintf(buf, "UNKNOWN\n");
-}
-
-static ssize_t fsa9480_show_manualsw(struct device *dev,
-		struct device_attribute *attr, char *buf)
-{
-	return fsa9480_get_switch(buf);
-
-}
-
-static ssize_t fsa9480_set_manualsw(struct device *dev,
-				    struct device_attribute *attr,
-				    const char *buf, size_t count)
-{
-	fsa9480_set_switch(buf);
-
-	return count;
-}
-
-static DEVICE_ATTR(device, S_IRUGO, fsa9480_show_device, NULL);
-static DEVICE_ATTR(switch, S_IRUGO | S_IWUSR,
-		fsa9480_show_manualsw, fsa9480_set_manualsw);
-
-static struct attribute *fsa9480_attributes[] = {
-	&dev_attr_device.attr,
-	&dev_attr_switch.attr,
-	NULL
-};
-
-static const struct attribute_group fsa9480_group = {
-	.attrs = fsa9480_attributes,
-};
-
-static void fsa9480_detect_dev(struct fsa9480_usbsw *usbsw, int intr)
-{
-	int val1, val2, ctrl;
-	struct fsa9480_platform_data *pdata = usbsw->pdata;
-	struct i2c_client *client = usbsw->client;
-
-	val1 = fsa9480_read_reg(client, FSA9480_REG_DEV_T1);
-	val2 = fsa9480_read_reg(client, FSA9480_REG_DEV_T2);
-	ctrl = fsa9480_read_reg(client, FSA9480_REG_CTRL);
-
-	dev_info(&client->dev, "intr: 0x%x, dev1: 0x%x, dev2: 0x%x\n",
-			intr, val1, val2);
-
-	if (!intr)
-		goto out;
-
-	if (intr & INT_ATTACH) {	/* Attached */
-		/* USB */
-		if (val1 & DEV_T1_USB_MASK || val2 & DEV_T2_USB_MASK) {
-			if (pdata->usb_cb)
-				pdata->usb_cb(FSA9480_ATTACHED);
-
-			if (usbsw->mansw) {
-				fsa9480_write_reg(client,
-					FSA9480_REG_MANSW1, usbsw->mansw);
-			}
-		}
-
-		/* UART */
-		if (val1 & DEV_T1_UART_MASK || val2 & DEV_T2_UART_MASK) {
-			if (pdata->uart_cb)
-				pdata->uart_cb(FSA9480_ATTACHED);
-
-			if (!(ctrl & CON_MANUAL_SW)) {
-				fsa9480_write_reg(client,
-					FSA9480_REG_MANSW1, SW_UART);
-			}
-		}
-
-		/* CHARGER */
-		if (val1 & DEV_T1_CHARGER_MASK) {
-			if (pdata->charger_cb)
-				pdata->charger_cb(FSA9480_ATTACHED);
-		}
-
-		/* JIG */
-		if (val2 & DEV_T2_JIG_MASK) {
-			if (pdata->jig_cb)
-				pdata->jig_cb(FSA9480_ATTACHED);
-		}
-	} else if (intr & INT_DETACH) {	/* Detached */
-		/* USB */
-		if (usbsw->dev1 & DEV_T1_USB_MASK ||
-			usbsw->dev2 & DEV_T2_USB_MASK) {
-			if (pdata->usb_cb)
-				pdata->usb_cb(FSA9480_DETACHED);
-		}
-
-		/* UART */
-		if (usbsw->dev1 & DEV_T1_UART_MASK ||
-			usbsw->dev2 & DEV_T2_UART_MASK) {
-			if (pdata->uart_cb)
-				pdata->uart_cb(FSA9480_DETACHED);
-		}
-
-		/* CHARGER */
-		if (usbsw->dev1 & DEV_T1_CHARGER_MASK) {
-			if (pdata->charger_cb)
-				pdata->charger_cb(FSA9480_DETACHED);
-		}
-
-		/* JIG */
-		if (usbsw->dev2 & DEV_T2_JIG_MASK) {
-			if (pdata->jig_cb)
-				pdata->jig_cb(FSA9480_DETACHED);
-		}
-	}
-
-	usbsw->dev1 = val1;
-	usbsw->dev2 = val2;
-
-out:
-	ctrl &= ~CON_INT_MASK;
-	fsa9480_write_reg(client, FSA9480_REG_CTRL, ctrl);
-}
-
-static irqreturn_t fsa9480_irq_handler(int irq, void *data)
-{
-	struct fsa9480_usbsw *usbsw = data;
-	struct i2c_client *client = usbsw->client;
-	int intr;
-
-	/* clear interrupt */
-	fsa9480_read_irq(client, &intr);
-
-	/* device detection */
-	fsa9480_detect_dev(usbsw, intr);
-
-	return IRQ_HANDLED;
-}
-
-static int fsa9480_irq_init(struct fsa9480_usbsw *usbsw)
-{
-	struct fsa9480_platform_data *pdata = usbsw->pdata;
-	struct i2c_client *client = usbsw->client;
-	int ret;
-	int intr;
-	unsigned int ctrl = CON_MASK;
-
-	/* clear interrupt */
-	fsa9480_read_irq(client, &intr);
-
-	/* unmask interrupt (attach/detach only) */
-	fsa9480_write_reg(client, FSA9480_REG_INT1_MASK, 0xfc);
-	fsa9480_write_reg(client, FSA9480_REG_INT2_MASK, 0x1f);
-
-	usbsw->mansw = fsa9480_read_reg(client, FSA9480_REG_MANSW1);
-
-	if (usbsw->mansw)
-		ctrl &= ~CON_MANUAL_SW;	/* Manual Switching Mode */
-
-	fsa9480_write_reg(client, FSA9480_REG_CTRL, ctrl);
-
-	if (pdata && pdata->cfg_gpio)
-		pdata->cfg_gpio();
-
-	if (client->irq) {
-		ret = request_threaded_irq(client->irq, NULL,
-				fsa9480_irq_handler,
-				IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
-				"fsa9480 micro USB", usbsw);
-		if (ret) {
-			dev_err(&client->dev, "failed to request IRQ\n");
-			return ret;
-		}
-
-		if (pdata)
-			device_init_wakeup(&client->dev, pdata->wakeup);
-	}
-
-	return 0;
-}
-
-static int fsa9480_probe(struct i2c_client *client,
-			 const struct i2c_device_id *id)
-{
-	struct i2c_adapter *adapter = to_i2c_adapter(client->dev.parent);
-	struct fsa9480_usbsw *usbsw;
-	int ret = 0;
-
-	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA))
-		return -EIO;
-
-	usbsw = kzalloc(sizeof(struct fsa9480_usbsw), GFP_KERNEL);
-	if (!usbsw) {
-		dev_err(&client->dev, "failed to allocate driver data\n");
-		return -ENOMEM;
-	}
-
-	usbsw->client = client;
-	usbsw->pdata = client->dev.platform_data;
-
-	chip = usbsw;
-
-	i2c_set_clientdata(client, usbsw);
-
-	ret = fsa9480_irq_init(usbsw);
-	if (ret)
-		goto fail1;
-
-	ret = sysfs_create_group(&client->dev.kobj, &fsa9480_group);
-	if (ret) {
-		dev_err(&client->dev,
-				"failed to create fsa9480 attribute group\n");
-		goto fail2;
-	}
-
-	/* ADC Detect Time: 500ms */
-	fsa9480_write_reg(client, FSA9480_REG_TIMING1, 0x6);
-
-	if (chip->pdata->reset_cb)
-		chip->pdata->reset_cb();
-
-	/* device detection */
-	fsa9480_detect_dev(usbsw, INT_ATTACH);
-
-	pm_runtime_set_active(&client->dev);
-
-	return 0;
-
-fail2:
-	if (client->irq)
-		free_irq(client->irq, usbsw);
-fail1:
-	kfree(usbsw);
-	return ret;
-}
-
-static int fsa9480_remove(struct i2c_client *client)
-{
-	struct fsa9480_usbsw *usbsw = i2c_get_clientdata(client);
-
-	if (client->irq)
-		free_irq(client->irq, usbsw);
-
-	sysfs_remove_group(&client->dev.kobj, &fsa9480_group);
-	device_init_wakeup(&client->dev, 0);
-	kfree(usbsw);
-	return 0;
-}
-
-#ifdef CONFIG_PM_SLEEP
-
-static int fsa9480_suspend(struct device *dev)
-{
-	struct i2c_client *client = to_i2c_client(dev);
-	struct fsa9480_usbsw *usbsw = i2c_get_clientdata(client);
-	struct fsa9480_platform_data *pdata = usbsw->pdata;
-
-	if (device_may_wakeup(&client->dev) && client->irq)
-		enable_irq_wake(client->irq);
-
-	if (pdata->usb_power)
-		pdata->usb_power(0);
-
-	return 0;
-}
-
-static int fsa9480_resume(struct device *dev)
-{
-	struct i2c_client *client = to_i2c_client(dev);
-	struct fsa9480_usbsw *usbsw = i2c_get_clientdata(client);
-	int dev1, dev2;
-
-	if (device_may_wakeup(&client->dev) && client->irq)
-		disable_irq_wake(client->irq);
-
-	/*
-	 * Clear Pending interrupt. Note that detect_dev does what
-	 * the interrupt handler does. So, we don't miss pending and
-	 * we reenable interrupt if there is one.
-	 */
-	fsa9480_read_reg(client, FSA9480_REG_INT1);
-	fsa9480_read_reg(client, FSA9480_REG_INT2);
-
-	dev1 = fsa9480_read_reg(client, FSA9480_REG_DEV_T1);
-	dev2 = fsa9480_read_reg(client, FSA9480_REG_DEV_T2);
-
-	/* device detection */
-	fsa9480_detect_dev(usbsw, (dev1 || dev2) ? INT_ATTACH : INT_DETACH);
-
-	return 0;
-}
-
-static SIMPLE_DEV_PM_OPS(fsa9480_pm_ops, fsa9480_suspend, fsa9480_resume);
-#define FSA9480_PM_OPS (&fsa9480_pm_ops)
-
-#else
-
-#define FSA9480_PM_OPS NULL
-
-#endif /* CONFIG_PM_SLEEP */
-
-static const struct i2c_device_id fsa9480_id[] = {
-	{"fsa9480", 0},
-	{}
-};
-MODULE_DEVICE_TABLE(i2c, fsa9480_id);
-
-static struct i2c_driver fsa9480_i2c_driver = {
-	.driver = {
-		.name = "fsa9480",
-		.pm = FSA9480_PM_OPS,
-	},
-	.probe = fsa9480_probe,
-	.remove = fsa9480_remove,
-	.id_table = fsa9480_id,
-};
-
-module_i2c_driver(fsa9480_i2c_driver);
-
-MODULE_AUTHOR("Minkyu Kang <mk7.kang@samsung.com>");
-MODULE_DESCRIPTION("FSA9480 USB Switch driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/misc/genwqe/Kconfig b/drivers/misc/genwqe/Kconfig
index a8a608713d26..97f64bcf9fe0 100644
--- a/drivers/misc/genwqe/Kconfig
+++ b/drivers/misc/genwqe/Kconfig
@@ -7,7 +7,6 @@ menuconfig GENWQE
 	tristate "GenWQE PCIe Accelerator"
 	depends on PCI && 64BIT
 	select CRC_ITU_T
-	default n
 	help
 	  Enables PCIe card driver for IBM GenWQE accelerators.
 	  The user-space interface is described in
diff --git a/drivers/misc/habanalabs/asid.c b/drivers/misc/habanalabs/asid.c
index f54e7971a762..2c01461701a3 100644
--- a/drivers/misc/habanalabs/asid.c
+++ b/drivers/misc/habanalabs/asid.c
@@ -18,7 +18,7 @@ int hl_asid_init(struct hl_device *hdev)
 
 	mutex_init(&hdev->asid_mutex);
 
-	/* ASID 0 is reserved for KMD */
+	/* ASID 0 is reserved for KMD and device CPU */
 	set_bit(0, hdev->asid_bitmap);
 
 	return 0;
diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c
index 6fe785e26859..6ad83d5ef4b0 100644
--- a/drivers/misc/habanalabs/command_submission.c
+++ b/drivers/misc/habanalabs/command_submission.c
@@ -682,14 +682,12 @@ int hl_cs_ioctl(struct hl_fpriv *hpriv, void *data)
 		u32 tmp;
 
 		rc = hl_poll_timeout_memory(hdev,
-			(u64) (uintptr_t) &ctx->thread_ctx_switch_wait_token,
-			jiffies_to_usecs(hdev->timeout_jiffies),
-			&tmp);
+			&ctx->thread_ctx_switch_wait_token, tmp, (tmp == 1),
+			100, jiffies_to_usecs(hdev->timeout_jiffies));
 
-		if (rc || !tmp) {
+		if (rc == -ETIMEDOUT) {
 			dev_err(hdev->dev,
-				"context switch phase didn't finish in time\n");
-			rc = -ETIMEDOUT;
+				"context switch phase timeout (%d)\n", tmp);
 			goto out;
 		}
 	}
diff --git a/drivers/misc/habanalabs/context.c b/drivers/misc/habanalabs/context.c
index f4c92f110a72..8682590e3f6e 100644
--- a/drivers/misc/habanalabs/context.c
+++ b/drivers/misc/habanalabs/context.c
@@ -31,9 +31,13 @@ static void hl_ctx_fini(struct hl_ctx *ctx)
 		 * Coresight might be still working by accessing addresses
 		 * related to the stopped engines. Hence stop it explicitly.
 		 */
-		hdev->asic_funcs->halt_coresight(hdev);
+		if (hdev->in_debug)
+			hl_device_set_debug_mode(hdev, false);
+
 		hl_vm_ctx_fini(ctx);
 		hl_asid_free(hdev, ctx->asid);
+	} else {
+		hl_mmu_ctx_fini(ctx);
 	}
 }
 
@@ -117,6 +121,11 @@ int hl_ctx_init(struct hl_device *hdev, struct hl_ctx *ctx, bool is_kernel_ctx)
 
 	if (is_kernel_ctx) {
 		ctx->asid = HL_KERNEL_ASID_ID; /* KMD gets ASID 0 */
+		rc = hl_mmu_ctx_init(ctx);
+		if (rc) {
+			dev_err(hdev->dev, "Failed to init mmu ctx module\n");
+			goto mem_ctx_err;
+		}
 	} else {
 		ctx->asid = hl_asid_alloc(hdev);
 		if (!ctx->asid) {
diff --git a/drivers/misc/habanalabs/debugfs.c b/drivers/misc/habanalabs/debugfs.c
index ba418aaa404c..18e499c900c7 100644
--- a/drivers/misc/habanalabs/debugfs.c
+++ b/drivers/misc/habanalabs/debugfs.c
@@ -355,7 +355,7 @@ 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 hl_ctx *ctx = hdev->user_ctx;
+	struct hl_ctx *ctx;
 
 	u64 hop0_addr = 0, hop0_pte_addr = 0, hop0_pte = 0,
 		hop1_addr = 0, hop1_pte_addr = 0, hop1_pte = 0,
@@ -367,6 +367,11 @@ static int mmu_show(struct seq_file *s, void *data)
 	if (!hdev->mmu_enable)
 		return 0;
 
+	if (dev_entry->mmu_asid == HL_KERNEL_ASID_ID)
+		ctx = hdev->kernel_ctx;
+	else
+		ctx = hdev->user_ctx;
+
 	if (!ctx) {
 		dev_err(hdev->dev, "no ctx available\n");
 		return 0;
@@ -495,6 +500,36 @@ err:
 	return -EINVAL;
 }
 
+static int engines_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;
+
+	hdev->asic_funcs->is_device_idle(hdev, NULL, s);
+
+	return 0;
+}
+
+static bool hl_is_device_va(struct hl_device *hdev, u64 addr)
+{
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+
+	if (!hdev->mmu_enable)
+		goto out;
+
+	if (hdev->dram_supports_virtual_memory &&
+			addr >= prop->va_space_dram_start_address &&
+			addr < prop->va_space_dram_end_address)
+		return true;
+
+	if (addr >= prop->va_space_host_start_address &&
+			addr < prop->va_space_host_end_address)
+		return true;
+out:
+	return false;
+}
+
 static int device_va_to_pa(struct hl_device *hdev, u64 virt_addr,
 				u64 *phys_addr)
 {
@@ -568,7 +603,6 @@ static ssize_t hl_data_read32(struct file *f, char __user *buf,
 {
 	struct hl_dbg_device_entry *entry = file_inode(f)->i_private;
 	struct hl_device *hdev = entry->hdev;
-	struct asic_fixed_properties *prop = &hdev->asic_prop;
 	char tmp_buf[32];
 	u64 addr = entry->addr;
 	u32 val;
@@ -577,11 +611,8 @@ static ssize_t hl_data_read32(struct file *f, char __user *buf,
 	if (*ppos)
 		return 0;
 
-	if (addr >= prop->va_space_dram_start_address &&
-			addr < prop->va_space_dram_end_address &&
-			hdev->mmu_enable &&
-			hdev->dram_supports_virtual_memory) {
-		rc = device_va_to_pa(hdev, entry->addr, &addr);
+	if (hl_is_device_va(hdev, addr)) {
+		rc = device_va_to_pa(hdev, addr, &addr);
 		if (rc)
 			return rc;
 	}
@@ -602,7 +633,6 @@ static ssize_t hl_data_write32(struct file *f, const char __user *buf,
 {
 	struct hl_dbg_device_entry *entry = file_inode(f)->i_private;
 	struct hl_device *hdev = entry->hdev;
-	struct asic_fixed_properties *prop = &hdev->asic_prop;
 	u64 addr = entry->addr;
 	u32 value;
 	ssize_t rc;
@@ -611,11 +641,8 @@ static ssize_t hl_data_write32(struct file *f, const char __user *buf,
 	if (rc)
 		return rc;
 
-	if (addr >= prop->va_space_dram_start_address &&
-			addr < prop->va_space_dram_end_address &&
-			hdev->mmu_enable &&
-			hdev->dram_supports_virtual_memory) {
-		rc = device_va_to_pa(hdev, entry->addr, &addr);
+	if (hl_is_device_va(hdev, addr)) {
+		rc = device_va_to_pa(hdev, addr, &addr);
 		if (rc)
 			return rc;
 	}
@@ -877,6 +904,7 @@ static const struct hl_info_list hl_debugfs_list[] = {
 	{"userptr", userptr_show, NULL},
 	{"vm", vm_show, NULL},
 	{"mmu", mmu_show, mmu_write},
+	{"engines", engines_show, NULL}
 };
 
 static int hl_debugfs_open(struct inode *inode, struct file *file)
diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c
index 0b19d3eefb98..0c4894dd9c02 100644
--- a/drivers/misc/habanalabs/device.c
+++ b/drivers/misc/habanalabs/device.c
@@ -231,6 +231,7 @@ static int device_early_init(struct hl_device *hdev)
 
 	mutex_init(&hdev->fd_open_cnt_lock);
 	mutex_init(&hdev->send_cpu_message_lock);
+	mutex_init(&hdev->debug_lock);
 	mutex_init(&hdev->mmu_cache_lock);
 	INIT_LIST_HEAD(&hdev->hw_queues_mirror_list);
 	spin_lock_init(&hdev->hw_queues_mirror_lock);
@@ -262,6 +263,7 @@ early_fini:
 static void device_early_fini(struct hl_device *hdev)
 {
 	mutex_destroy(&hdev->mmu_cache_lock);
+	mutex_destroy(&hdev->debug_lock);
 	mutex_destroy(&hdev->send_cpu_message_lock);
 
 	hl_cb_mgr_fini(hdev, &hdev->kernel_cb_mgr);
@@ -324,7 +326,15 @@ static int device_late_init(struct hl_device *hdev)
 {
 	int rc;
 
-	INIT_DELAYED_WORK(&hdev->work_freq, set_freq_to_low_job);
+	if (hdev->asic_funcs->late_init) {
+		rc = hdev->asic_funcs->late_init(hdev);
+		if (rc) {
+			dev_err(hdev->dev,
+				"failed late initialization for the H/W\n");
+			return rc;
+		}
+	}
+
 	hdev->high_pll = hdev->asic_prop.high_pll;
 
 	/* force setting to low frequency */
@@ -335,17 +345,9 @@ static int device_late_init(struct hl_device *hdev)
 	else
 		hdev->asic_funcs->set_pll_profile(hdev, PLL_LAST);
 
-	if (hdev->asic_funcs->late_init) {
-		rc = hdev->asic_funcs->late_init(hdev);
-		if (rc) {
-			dev_err(hdev->dev,
-				"failed late initialization for the H/W\n");
-			return rc;
-		}
-	}
-
+	INIT_DELAYED_WORK(&hdev->work_freq, set_freq_to_low_job);
 	schedule_delayed_work(&hdev->work_freq,
-			usecs_to_jiffies(HL_PLL_LOW_JOB_FREQ_USEC));
+	usecs_to_jiffies(HL_PLL_LOW_JOB_FREQ_USEC));
 
 	if (hdev->heartbeat) {
 		INIT_DELAYED_WORK(&hdev->work_heartbeat, hl_device_heartbeat);
@@ -420,6 +422,52 @@ int hl_device_set_frequency(struct hl_device *hdev, enum hl_pll_frequency freq)
 	return 1;
 }
 
+int hl_device_set_debug_mode(struct hl_device *hdev, bool enable)
+{
+	int rc = 0;
+
+	mutex_lock(&hdev->debug_lock);
+
+	if (!enable) {
+		if (!hdev->in_debug) {
+			dev_err(hdev->dev,
+				"Failed to disable debug mode because device was not in debug mode\n");
+			rc = -EFAULT;
+			goto out;
+		}
+
+		hdev->asic_funcs->halt_coresight(hdev);
+		hdev->in_debug = 0;
+
+		goto out;
+	}
+
+	if (hdev->in_debug) {
+		dev_err(hdev->dev,
+			"Failed to enable debug mode because device is already in debug mode\n");
+		rc = -EFAULT;
+		goto out;
+	}
+
+	mutex_lock(&hdev->fd_open_cnt_lock);
+
+	if (atomic_read(&hdev->fd_open_cnt) > 1) {
+		dev_err(hdev->dev,
+			"Failed to enable debug mode. More then a single user is using the device\n");
+		rc = -EPERM;
+		goto unlock_fd_open_lock;
+	}
+
+	hdev->in_debug = 1;
+
+unlock_fd_open_lock:
+	mutex_unlock(&hdev->fd_open_cnt_lock);
+out:
+	mutex_unlock(&hdev->debug_lock);
+
+	return rc;
+}
+
 /*
  * hl_device_suspend - initiate device suspend
  *
@@ -647,13 +695,6 @@ again:
 
 		hdev->hard_reset_pending = true;
 
-		if (!hdev->pdev) {
-			dev_err(hdev->dev,
-				"Reset action is NOT supported in simulator\n");
-			rc = -EINVAL;
-			goto out_err;
-		}
-
 		device_reset_work = kzalloc(sizeof(*device_reset_work),
 						GFP_ATOMIC);
 		if (!device_reset_work) {
@@ -704,6 +745,7 @@ again:
 
 	if (hard_reset) {
 		hl_vm_fini(hdev);
+		hl_mmu_fini(hdev);
 		hl_eq_reset(hdev, &hdev->event_queue);
 	}
 
@@ -731,6 +773,13 @@ again:
 			goto out_err;
 		}
 
+		rc = hl_mmu_init(hdev);
+		if (rc) {
+			dev_err(hdev->dev,
+				"Failed to initialize MMU S/W after hard reset\n");
+			goto out_err;
+		}
+
 		/* Allocate the kernel context */
 		hdev->kernel_ctx = kzalloc(sizeof(*hdev->kernel_ctx),
 						GFP_KERNEL);
@@ -902,11 +951,18 @@ int hl_device_init(struct hl_device *hdev, struct class *hclass)
 		goto cq_fini;
 	}
 
+	/* MMU S/W must be initialized before kernel context is created */
+	rc = hl_mmu_init(hdev);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to initialize MMU S/W structures\n");
+		goto eq_fini;
+	}
+
 	/* Allocate the kernel context */
 	hdev->kernel_ctx = kzalloc(sizeof(*hdev->kernel_ctx), GFP_KERNEL);
 	if (!hdev->kernel_ctx) {
 		rc = -ENOMEM;
-		goto eq_fini;
+		goto mmu_fini;
 	}
 
 	hdev->user_ctx = NULL;
@@ -954,8 +1010,6 @@ int hl_device_init(struct hl_device *hdev, struct class *hclass)
 		goto out_disabled;
 	}
 
-	/* After test_queues, KMD can start sending messages to device CPU */
-
 	rc = device_late_init(hdev);
 	if (rc) {
 		dev_err(hdev->dev, "Failed late initialization\n");
@@ -1001,6 +1055,8 @@ release_ctx:
 			"kernel ctx is still alive on initialization failure\n");
 free_ctx:
 	kfree(hdev->kernel_ctx);
+mmu_fini:
+	hl_mmu_fini(hdev);
 eq_fini:
 	hl_eq_fini(hdev, &hdev->event_queue);
 cq_fini:
@@ -1105,6 +1161,8 @@ void hl_device_fini(struct hl_device *hdev)
 
 	hl_vm_fini(hdev);
 
+	hl_mmu_fini(hdev);
+
 	hl_eq_fini(hdev, &hdev->event_queue);
 
 	for (i = 0 ; i < hdev->asic_prop.completion_queues_count ; i++)
@@ -1126,95 +1184,6 @@ void hl_device_fini(struct hl_device *hdev)
 }
 
 /*
- * hl_poll_timeout_memory - Periodically poll a host memory address
- *                              until it is not zero or a timeout occurs
- * @hdev: pointer to habanalabs device structure
- * @addr: Address to poll
- * @timeout_us: timeout in us
- * @val: Variable to read the value into
- *
- * Returns 0 on success and -ETIMEDOUT upon a timeout. In either
- * case, the last read value at @addr is stored in @val. Must not
- * be called from atomic context if sleep_us or timeout_us are used.
- *
- * The function sleeps for 100us with timeout value of
- * timeout_us
- */
-int hl_poll_timeout_memory(struct hl_device *hdev, u64 addr,
-				u32 timeout_us, u32 *val)
-{
-	/*
-	 * address in this function points always to a memory location in the
-	 * host's (server's) memory. That location is updated asynchronously
-	 * either by the direct access of the device or by another core
-	 */
-	u32 *paddr = (u32 *) (uintptr_t) addr;
-	ktime_t timeout;
-
-	/* timeout should be longer when working with simulator */
-	if (!hdev->pdev)
-		timeout_us *= 10;
-
-	timeout = ktime_add_us(ktime_get(), timeout_us);
-
-	might_sleep();
-
-	for (;;) {
-		/*
-		 * Flush CPU read/write buffers to make sure we read updates
-		 * done by other cores or by the device
-		 */
-		mb();
-		*val = *paddr;
-		if (*val)
-			break;
-		if (ktime_compare(ktime_get(), timeout) > 0) {
-			*val = *paddr;
-			break;
-		}
-		usleep_range((100 >> 2) + 1, 100);
-	}
-
-	return *val ? 0 : -ETIMEDOUT;
-}
-
-/*
- * hl_poll_timeout_devicememory - Periodically poll a device memory address
- *                                until it is not zero or a timeout occurs
- * @hdev: pointer to habanalabs device structure
- * @addr: Device address to poll
- * @timeout_us: timeout in us
- * @val: Variable to read the value into
- *
- * Returns 0 on success and -ETIMEDOUT upon a timeout. In either
- * case, the last read value at @addr is stored in @val. Must not
- * be called from atomic context if sleep_us or timeout_us are used.
- *
- * The function sleeps for 100us with timeout value of
- * timeout_us
- */
-int hl_poll_timeout_device_memory(struct hl_device *hdev, void __iomem *addr,
-				u32 timeout_us, u32 *val)
-{
-	ktime_t timeout = ktime_add_us(ktime_get(), timeout_us);
-
-	might_sleep();
-
-	for (;;) {
-		*val = readl(addr);
-		if (*val)
-			break;
-		if (ktime_compare(ktime_get(), timeout) > 0) {
-			*val = readl(addr);
-			break;
-		}
-		usleep_range((100 >> 2) + 1, 100);
-	}
-
-	return *val ? 0 : -ETIMEDOUT;
-}
-
-/*
  * MMIO register access helper functions.
  */
 
diff --git a/drivers/misc/habanalabs/firmware_if.c b/drivers/misc/habanalabs/firmware_if.c
index eda5d7fcb79f..cc8168bacb24 100644
--- a/drivers/misc/habanalabs/firmware_if.c
+++ b/drivers/misc/habanalabs/firmware_if.c
@@ -29,13 +29,13 @@ int hl_fw_push_fw_to_device(struct hl_device *hdev, const char *fw_name,
 
 	rc = request_firmware(&fw, fw_name, hdev->dev);
 	if (rc) {
-		dev_err(hdev->dev, "Failed to request %s\n", fw_name);
+		dev_err(hdev->dev, "Firmware file %s is not found!\n", fw_name);
 		goto out;
 	}
 
 	fw_size = fw->size;
 	if ((fw_size % 4) != 0) {
-		dev_err(hdev->dev, "illegal %s firmware size %zu\n",
+		dev_err(hdev->dev, "Illegal %s firmware size %zu\n",
 			fw_name, fw_size);
 		rc = -EINVAL;
 		goto out;
@@ -85,12 +85,6 @@ int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
 	u32 tmp;
 	int rc = 0;
 
-	if (len > HL_CPU_CB_SIZE) {
-		dev_err(hdev->dev, "Invalid CPU message size of %d bytes\n",
-			len);
-		return -ENOMEM;
-	}
-
 	pkt = hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev, len,
 								&pkt_dma_addr);
 	if (!pkt) {
@@ -117,33 +111,28 @@ int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
 		goto out;
 	}
 
-	rc = hl_poll_timeout_memory(hdev, (u64) (uintptr_t) &pkt->fence,
-					timeout, &tmp);
+	rc = hl_poll_timeout_memory(hdev, &pkt->fence, tmp,
+				(tmp == ARMCP_PACKET_FENCE_VAL), 1000, timeout);
 
 	hl_hw_queue_inc_ci_kernel(hdev, hw_queue_id);
 
 	if (rc == -ETIMEDOUT) {
-		dev_err(hdev->dev, "Timeout while waiting for device CPU\n");
+		dev_err(hdev->dev, "Device CPU packet timeout (0x%x)\n", tmp);
 		hdev->device_cpu_disabled = true;
 		goto out;
 	}
 
-	if (tmp == ARMCP_PACKET_FENCE_VAL) {
-		u32 ctl = le32_to_cpu(pkt->ctl);
+	tmp = le32_to_cpu(pkt->ctl);
 
-		rc = (ctl & ARMCP_PKT_CTL_RC_MASK) >> ARMCP_PKT_CTL_RC_SHIFT;
-		if (rc) {
-			dev_err(hdev->dev,
-				"F/W ERROR %d for CPU packet %d\n",
-				rc, (ctl & ARMCP_PKT_CTL_OPCODE_MASK)
+	rc = (tmp & ARMCP_PKT_CTL_RC_MASK) >> ARMCP_PKT_CTL_RC_SHIFT;
+	if (rc) {
+		dev_err(hdev->dev, "F/W ERROR %d for CPU packet %d\n",
+			rc,
+			(tmp & ARMCP_PKT_CTL_OPCODE_MASK)
 						>> ARMCP_PKT_CTL_OPCODE_SHIFT);
-			rc = -EINVAL;
-		} else if (result) {
-			*result = (long) le64_to_cpu(pkt->result);
-		}
-	} else {
-		dev_err(hdev->dev, "CPU packet wrong fence value\n");
-		rc = -EINVAL;
+		rc = -EIO;
+	} else if (result) {
+		*result = (long) le64_to_cpu(pkt->result);
 	}
 
 out:
@@ -186,9 +175,6 @@ void *hl_fw_cpu_accessible_dma_pool_alloc(struct hl_device *hdev, size_t size,
 {
 	u64 kernel_addr;
 
-	/* roundup to HL_CPU_PKT_SIZE */
-	size = (size + (HL_CPU_PKT_SIZE - 1)) & HL_CPU_PKT_MASK;
-
 	kernel_addr = gen_pool_alloc(hdev->cpu_accessible_dma_pool, size);
 
 	*dma_handle = hdev->cpu_accessible_dma_address +
@@ -200,9 +186,6 @@ void *hl_fw_cpu_accessible_dma_pool_alloc(struct hl_device *hdev, size_t size,
 void hl_fw_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size,
 					void *vaddr)
 {
-	/* roundup to HL_CPU_PKT_SIZE */
-	size = (size + (HL_CPU_PKT_SIZE - 1)) & HL_CPU_PKT_MASK;
-
 	gen_pool_free(hdev->cpu_accessible_dma_pool, (u64) (uintptr_t) vaddr,
 			size);
 }
@@ -256,7 +239,7 @@ int hl_fw_armcp_info_get(struct hl_device *hdev)
 					HL_ARMCP_INFO_TIMEOUT_USEC, &result);
 	if (rc) {
 		dev_err(hdev->dev,
-			"Failed to send armcp info pkt, error %d\n", rc);
+			"Failed to send ArmCP info pkt, error %d\n", rc);
 		goto out;
 	}
 
@@ -291,7 +274,7 @@ int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size)
 					max_size, &eeprom_info_dma_addr);
 	if (!eeprom_info_cpu_addr) {
 		dev_err(hdev->dev,
-			"Failed to allocate DMA memory for EEPROM info packet\n");
+			"Failed to allocate DMA memory for ArmCP EEPROM packet\n");
 		return -ENOMEM;
 	}
 
@@ -307,7 +290,7 @@ int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size)
 
 	if (rc) {
 		dev_err(hdev->dev,
-			"Failed to send armcp EEPROM pkt, error %d\n", rc);
+			"Failed to send ArmCP EEPROM packet, error %d\n", rc);
 		goto out;
 	}
 
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index 02d116b01a1a..75294ec65257 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -14,6 +14,8 @@
 #include <linux/genalloc.h>
 #include <linux/hwmon.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/iommu.h>
+#include <linux/seq_file.h>
 
 /*
  * GOYA security scheme:
@@ -89,6 +91,30 @@
 #define GOYA_CB_POOL_CB_CNT		512
 #define GOYA_CB_POOL_CB_SIZE		0x20000		/* 128KB */
 
+#define IS_QM_IDLE(engine, qm_glbl_sts0) \
+	(((qm_glbl_sts0) & engine##_QM_IDLE_MASK) == engine##_QM_IDLE_MASK)
+#define IS_DMA_QM_IDLE(qm_glbl_sts0)	IS_QM_IDLE(DMA, qm_glbl_sts0)
+#define IS_TPC_QM_IDLE(qm_glbl_sts0)	IS_QM_IDLE(TPC, qm_glbl_sts0)
+#define IS_MME_QM_IDLE(qm_glbl_sts0)	IS_QM_IDLE(MME, qm_glbl_sts0)
+
+#define IS_CMDQ_IDLE(engine, cmdq_glbl_sts0) \
+	(((cmdq_glbl_sts0) & engine##_CMDQ_IDLE_MASK) == \
+			engine##_CMDQ_IDLE_MASK)
+#define IS_TPC_CMDQ_IDLE(cmdq_glbl_sts0) \
+	IS_CMDQ_IDLE(TPC, cmdq_glbl_sts0)
+#define IS_MME_CMDQ_IDLE(cmdq_glbl_sts0) \
+	IS_CMDQ_IDLE(MME, cmdq_glbl_sts0)
+
+#define IS_DMA_IDLE(dma_core_sts0) \
+	!((dma_core_sts0) & DMA_CH_0_STS0_DMA_BUSY_MASK)
+
+#define IS_TPC_IDLE(tpc_cfg_sts) \
+	(((tpc_cfg_sts) & TPC_CFG_IDLE_MASK) == TPC_CFG_IDLE_MASK)
+
+#define IS_MME_IDLE(mme_arch_sts) \
+	(((mme_arch_sts) & MME_ARCH_IDLE_MASK) == MME_ARCH_IDLE_MASK)
+
+
 static const char goya_irq_name[GOYA_MSIX_ENTRIES][GOYA_MAX_STRING_LEN] = {
 		"goya cq 0", "goya cq 1", "goya cq 2", "goya cq 3",
 		"goya cq 4", "goya cpu eq"
@@ -297,6 +323,11 @@ static u32 goya_all_events[] = {
 	GOYA_ASYNC_EVENT_ID_DMA_BM_CH4
 };
 
+static int goya_mmu_clear_pgt_range(struct hl_device *hdev);
+static int goya_mmu_set_dram_default_page(struct hl_device *hdev);
+static int goya_mmu_add_mappings_for_device_cpu(struct hl_device *hdev);
+static void goya_mmu_prepare(struct hl_device *hdev, u32 asid);
+
 void goya_get_fixed_properties(struct hl_device *hdev)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
@@ -467,7 +498,7 @@ static int goya_early_init(struct hl_device *hdev)
 
 	prop->dram_pci_bar_size = pci_resource_len(pdev, DDR_BAR_ID);
 
-	rc = hl_pci_init(hdev, 39);
+	rc = hl_pci_init(hdev, 48);
 	if (rc)
 		return rc;
 
@@ -539,9 +570,36 @@ int goya_late_init(struct hl_device *hdev)
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
 	int rc;
 
+	goya_fetch_psoc_frequency(hdev);
+
+	rc = goya_mmu_clear_pgt_range(hdev);
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to clear MMU page tables range %d\n", rc);
+		return rc;
+	}
+
+	rc = goya_mmu_set_dram_default_page(hdev);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to set DRAM default page %d\n", rc);
+		return rc;
+	}
+
+	rc = goya_mmu_add_mappings_for_device_cpu(hdev);
+	if (rc)
+		return rc;
+
+	rc = goya_init_cpu_queues(hdev);
+	if (rc)
+		return rc;
+
+	rc = goya_test_cpu_queue(hdev);
+	if (rc)
+		return rc;
+
 	rc = goya_armcp_info_get(hdev);
 	if (rc) {
-		dev_err(hdev->dev, "Failed to get armcp info\n");
+		dev_err(hdev->dev, "Failed to get armcp info %d\n", rc);
 		return rc;
 	}
 
@@ -553,33 +611,15 @@ int goya_late_init(struct hl_device *hdev)
 
 	rc = hl_fw_send_pci_access_msg(hdev, ARMCP_PACKET_ENABLE_PCI_ACCESS);
 	if (rc) {
-		dev_err(hdev->dev, "Failed to enable PCI access from CPU\n");
+		dev_err(hdev->dev,
+			"Failed to enable PCI access from CPU %d\n", rc);
 		return rc;
 	}
 
 	WREG32(mmGIC_DISTRIBUTOR__5_GICD_SETSPI_NSR,
 			GOYA_ASYNC_EVENT_ID_INTS_REGISTER);
 
-	goya_fetch_psoc_frequency(hdev);
-
-	rc = goya_mmu_clear_pgt_range(hdev);
-	if (rc) {
-		dev_err(hdev->dev, "Failed to clear MMU page tables range\n");
-		goto disable_pci_access;
-	}
-
-	rc = goya_mmu_set_dram_default_page(hdev);
-	if (rc) {
-		dev_err(hdev->dev, "Failed to set DRAM default page\n");
-		goto disable_pci_access;
-	}
-
 	return 0;
-
-disable_pci_access:
-	hl_fw_send_pci_access_msg(hdev, ARMCP_PACKET_DISABLE_PCI_ACCESS);
-
-	return rc;
 }
 
 /*
@@ -655,7 +695,10 @@ static int goya_sw_init(struct hl_device *hdev)
 		goto free_dma_pool;
 	}
 
-	hdev->cpu_accessible_dma_pool = gen_pool_create(HL_CPU_PKT_SHIFT, -1);
+	dev_dbg(hdev->dev, "cpu accessible memory at bus address 0x%llx\n",
+		hdev->cpu_accessible_dma_address);
+
+	hdev->cpu_accessible_dma_pool = gen_pool_create(ilog2(32), -1);
 	if (!hdev->cpu_accessible_dma_pool) {
 		dev_err(hdev->dev,
 			"Failed to create CPU accessible DMA pool\n");
@@ -786,7 +829,6 @@ static void goya_init_dma_ch(struct hl_device *hdev, int dma_id)
 	else
 		sob_addr = CFG_BASE + mmSYNC_MNGR_SOB_OBJ_1007;
 
-	WREG32(mmDMA_CH_0_WR_COMP_ADDR_LO + reg_off, lower_32_bits(sob_addr));
 	WREG32(mmDMA_CH_0_WR_COMP_ADDR_HI + reg_off, upper_32_bits(sob_addr));
 	WREG32(mmDMA_CH_0_WR_COMP_WDATA + reg_off, 0x80000001);
 }
@@ -973,9 +1015,9 @@ int goya_init_cpu_queues(struct hl_device *hdev)
 	WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_3, upper_32_bits(eq->bus_address));
 
 	WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_8,
-			lower_32_bits(hdev->cpu_accessible_dma_address));
+			lower_32_bits(VA_CPU_ACCESSIBLE_MEM_ADDR));
 	WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_9,
-			upper_32_bits(hdev->cpu_accessible_dma_address));
+			upper_32_bits(VA_CPU_ACCESSIBLE_MEM_ADDR));
 
 	WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_5, HL_QUEUE_SIZE_IN_BYTES);
 	WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_4, HL_EQ_SIZE_IN_BYTES);
@@ -1001,7 +1043,7 @@ int goya_init_cpu_queues(struct hl_device *hdev)
 
 	if (err) {
 		dev_err(hdev->dev,
-			"Failed to communicate with ARM CPU (ArmCP timeout)\n");
+			"Failed to setup communication with device CPU\n");
 		return -EIO;
 	}
 
@@ -2061,10 +2103,12 @@ static void goya_halt_engines(struct hl_device *hdev, bool hard_reset)
 	goya_disable_external_queues(hdev);
 	goya_disable_internal_queues(hdev);
 
-	if (hard_reset)
+	if (hard_reset) {
 		goya_disable_msix(hdev);
-	else
+		goya_mmu_remove_device_cpu_mappings(hdev);
+	} else {
 		goya_sync_irqs(hdev);
+	}
 }
 
 /*
@@ -2277,14 +2321,14 @@ static int goya_init_cpu(struct hl_device *hdev, u32 cpu_timeout)
 	goya_read_device_fw_version(hdev, FW_COMP_UBOOT);
 	goya_read_device_fw_version(hdev, FW_COMP_PREBOOT);
 
-	if (status == CPU_BOOT_STATUS_SRAM_AVAIL)
-		goto out;
-
 	if (!hdev->fw_loading) {
 		dev_info(hdev->dev, "Skip loading FW\n");
 		goto out;
 	}
 
+	if (status == CPU_BOOT_STATUS_SRAM_AVAIL)
+		goto out;
+
 	rc = goya_push_linux_to_device(hdev);
 	if (rc)
 		return rc;
@@ -2466,34 +2510,11 @@ static int goya_hw_init(struct hl_device *hdev)
 	if (rc)
 		goto disable_queues;
 
-	rc = goya_init_cpu_queues(hdev);
-	if (rc) {
-		dev_err(hdev->dev, "failed to initialize CPU H/W queues %d\n",
-			rc);
-		goto disable_msix;
-	}
-
-	/*
-	 * Check if we managed to set the DMA mask to more then 32 bits. If so,
-	 * let's try to increase it again because in Goya we set the initial
-	 * dma mask to less then 39 bits so that the allocation of the memory
-	 * area for the device's cpu will be under 39 bits
-	 */
-	if (hdev->dma_mask > 32) {
-		rc = hl_pci_set_dma_mask(hdev, 48);
-		if (rc)
-			goto disable_pci_access;
-	}
-
 	/* Perform read from the device to flush all MSI-X configuration */
 	val = RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG);
 
 	return 0;
 
-disable_pci_access:
-	hl_fw_send_pci_access_msg(hdev, ARMCP_PACKET_DISABLE_PCI_ACCESS);
-disable_msix:
-	goya_disable_msix(hdev);
 disable_queues:
 	goya_disable_internal_queues(hdev);
 	goya_disable_external_queues(hdev);
@@ -2629,7 +2650,6 @@ static int goya_cb_mmap(struct hl_device *hdev, struct vm_area_struct *vma,
 void goya_ring_doorbell(struct hl_device *hdev, u32 hw_queue_id, u32 pi)
 {
 	u32 db_reg_offset, db_value;
-	bool invalid_queue = false;
 
 	switch (hw_queue_id) {
 	case GOYA_QUEUE_ID_DMA_0:
@@ -2653,10 +2673,7 @@ void goya_ring_doorbell(struct hl_device *hdev, u32 hw_queue_id, u32 pi)
 		break;
 
 	case GOYA_QUEUE_ID_CPU_PQ:
-		if (hdev->cpu_queues_enable)
-			db_reg_offset = mmCPU_IF_PF_PQ_PI;
-		else
-			invalid_queue = true;
+		db_reg_offset = mmCPU_IF_PF_PQ_PI;
 		break;
 
 	case GOYA_QUEUE_ID_MME:
@@ -2696,12 +2713,8 @@ void goya_ring_doorbell(struct hl_device *hdev, u32 hw_queue_id, u32 pi)
 		break;
 
 	default:
-		invalid_queue = true;
-	}
-
-	if (invalid_queue) {
 		/* Should never get here */
-		dev_err(hdev->dev, "h/w queue %d is invalid. Can't set pi\n",
+		dev_err(hdev->dev, "H/W queue %d is invalid. Can't set pi\n",
 			hw_queue_id);
 		return;
 	}
@@ -2808,7 +2821,6 @@ static int goya_send_job_on_qman0(struct hl_device *hdev, struct hl_cs_job *job)
 	dma_addr_t fence_dma_addr;
 	struct hl_cb *cb;
 	u32 tmp, timeout;
-	char buf[16] = {};
 	int rc;
 
 	if (hdev->pldm)
@@ -2816,10 +2828,9 @@ static int goya_send_job_on_qman0(struct hl_device *hdev, struct hl_cs_job *job)
 	else
 		timeout = HL_DEVICE_TIMEOUT_USEC;
 
-	if (!hdev->asic_funcs->is_device_idle(hdev, buf, sizeof(buf))) {
+	if (!hdev->asic_funcs->is_device_idle(hdev, NULL, NULL)) {
 		dev_err_ratelimited(hdev->dev,
-			"Can't send KMD job on QMAN0 because %s is busy\n",
-			buf);
+			"Can't send KMD job on QMAN0 because the device is not idle\n");
 		return -EBUSY;
 	}
 
@@ -2831,16 +2842,8 @@ static int goya_send_job_on_qman0(struct hl_device *hdev, struct hl_cs_job *job)
 		return -ENOMEM;
 	}
 
-	*fence_ptr = 0;
-
 	goya_qman0_set_security(hdev, true);
 
-	/*
-	 * goya cs parser saves space for 2xpacket_msg_prot at end of CB. For
-	 * synchronized kernel jobs we only need space for 1 packet_msg_prot
-	 */
-	job->job_cb_size -= sizeof(struct packet_msg_prot);
-
 	cb = job->patched_cb;
 
 	fence_pkt = (struct packet_msg_prot *) (uintptr_t) (cb->kernel_address +
@@ -2860,14 +2863,14 @@ static int goya_send_job_on_qman0(struct hl_device *hdev, struct hl_cs_job *job)
 		goto free_fence_ptr;
 	}
 
-	rc = hl_poll_timeout_memory(hdev, (u64) (uintptr_t) fence_ptr, timeout,
-					&tmp);
+	rc = hl_poll_timeout_memory(hdev, fence_ptr, tmp,
+				(tmp == GOYA_QMAN0_FENCE_VAL), 1000, timeout);
 
 	hl_hw_queue_inc_ci_kernel(hdev, GOYA_QUEUE_ID_DMA_0);
 
-	if ((rc) || (tmp != GOYA_QMAN0_FENCE_VAL)) {
-		dev_err(hdev->dev, "QMAN0 Job hasn't finished in time\n");
-		rc = -ETIMEDOUT;
+	if (rc == -ETIMEDOUT) {
+		dev_err(hdev->dev, "QMAN0 Job timeout (0x%x)\n", tmp);
+		goto free_fence_ptr;
 	}
 
 free_fence_ptr:
@@ -2941,20 +2944,19 @@ int goya_test_queue(struct hl_device *hdev, u32 hw_queue_id)
 		goto free_pkt;
 	}
 
-	rc = hl_poll_timeout_memory(hdev, (u64) (uintptr_t) fence_ptr,
-					GOYA_TEST_QUEUE_WAIT_USEC, &tmp);
+	rc = hl_poll_timeout_memory(hdev, fence_ptr, tmp, (tmp == fence_val),
+					1000, GOYA_TEST_QUEUE_WAIT_USEC);
 
 	hl_hw_queue_inc_ci_kernel(hdev, hw_queue_id);
 
-	if ((!rc) && (tmp == fence_val)) {
-		dev_info(hdev->dev,
-			"queue test on H/W queue %d succeeded\n",
-			hw_queue_id);
-	} else {
+	if (rc == -ETIMEDOUT) {
 		dev_err(hdev->dev,
 			"H/W queue %d test failed (scratch(0x%08llX) == 0x%08X)\n",
 			hw_queue_id, (unsigned long long) fence_dma_addr, tmp);
-		rc = -EINVAL;
+		rc = -EIO;
+	} else {
+		dev_info(hdev->dev, "queue test on H/W queue %d succeeded\n",
+			hw_queue_id);
 	}
 
 free_pkt:
@@ -2990,12 +2992,6 @@ int goya_test_queues(struct hl_device *hdev)
 			ret_val = -EINVAL;
 	}
 
-	if (hdev->cpu_queues_enable) {
-		rc = goya_test_cpu_queue(hdev);
-		if (rc)
-			ret_val = -EINVAL;
-	}
-
 	return ret_val;
 }
 
@@ -3028,7 +3024,13 @@ static void goya_dma_pool_free(struct hl_device *hdev, void *vaddr,
 void *goya_cpu_accessible_dma_pool_alloc(struct hl_device *hdev, size_t size,
 					dma_addr_t *dma_handle)
 {
-	return hl_fw_cpu_accessible_dma_pool_alloc(hdev, size, dma_handle);
+	void *vaddr;
+
+	vaddr = hl_fw_cpu_accessible_dma_pool_alloc(hdev, size, dma_handle);
+	*dma_handle = (*dma_handle) - hdev->cpu_accessible_dma_address +
+			VA_CPU_ACCESSIBLE_MEM_ADDR;
+
+	return vaddr;
 }
 
 void goya_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size,
@@ -3907,8 +3909,8 @@ int goya_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser)
 		return goya_parse_cb_no_mmu(hdev, parser);
 }
 
-void goya_add_end_of_cb_packets(u64 kernel_address, u32 len, u64 cq_addr,
-				u32 cq_val, u32 msix_vec)
+void goya_add_end_of_cb_packets(struct hl_device *hdev, u64 kernel_address,
+				u32 len, u64 cq_addr, u32 cq_val, u32 msix_vec)
 {
 	struct packet_msg_prot *cq_pkt;
 	u32 tmp;
@@ -3939,6 +3941,11 @@ void goya_update_eq_ci(struct hl_device *hdev, u32 val)
 
 void goya_restore_phase_topology(struct hl_device *hdev)
 {
+
+}
+
+static void goya_clear_sm_regs(struct hl_device *hdev)
+{
 	int i, num_of_sob_in_longs, num_of_mon_in_longs;
 
 	num_of_sob_in_longs =
@@ -3958,10 +3965,11 @@ void goya_restore_phase_topology(struct hl_device *hdev)
 }
 
 /*
- * goya_debugfs_read32 - read a 32bit value from a given device address
+ * goya_debugfs_read32 - read a 32bit value from a given device or a host mapped
+ *                       address.
  *
  * @hdev:	pointer to hl_device structure
- * @addr:	address in device
+ * @addr:	device or host mapped address
  * @val:	returned value
  *
  * In case of DDR address that is not mapped into the default aperture that
@@ -4002,6 +4010,10 @@ static int goya_debugfs_read32(struct hl_device *hdev, u64 addr, u32 *val)
 		}
 		if (ddr_bar_addr == U64_MAX)
 			rc = -EIO;
+
+	} else if (addr >= HOST_PHYS_BASE && !iommu_present(&pci_bus_type)) {
+		*val = *(u32 *) phys_to_virt(addr - HOST_PHYS_BASE);
+
 	} else {
 		rc = -EFAULT;
 	}
@@ -4010,10 +4022,11 @@ static int goya_debugfs_read32(struct hl_device *hdev, u64 addr, u32 *val)
 }
 
 /*
- * goya_debugfs_write32 - write a 32bit value to a given device address
+ * goya_debugfs_write32 - write a 32bit value to a given device or a host mapped
+ *                        address.
  *
  * @hdev:	pointer to hl_device structure
- * @addr:	address in device
+ * @addr:	device or host mapped address
  * @val:	returned value
  *
  * In case of DDR address that is not mapped into the default aperture that
@@ -4054,6 +4067,10 @@ static int goya_debugfs_write32(struct hl_device *hdev, u64 addr, u32 val)
 		}
 		if (ddr_bar_addr == U64_MAX)
 			rc = -EIO;
+
+	} else if (addr >= HOST_PHYS_BASE && !iommu_present(&pci_bus_type)) {
+		*(u32 *) phys_to_virt(addr - HOST_PHYS_BASE) = val;
+
 	} else {
 		rc = -EFAULT;
 	}
@@ -4086,6 +4103,47 @@ static void goya_write_pte(struct hl_device *hdev, u64 addr, u64 val)
 static const char *_goya_get_event_desc(u16 event_type)
 {
 	switch (event_type) {
+	case GOYA_ASYNC_EVENT_ID_PCIE_IF:
+		return "PCIe_if";
+	case GOYA_ASYNC_EVENT_ID_TPC0_ECC:
+	case GOYA_ASYNC_EVENT_ID_TPC1_ECC:
+	case GOYA_ASYNC_EVENT_ID_TPC2_ECC:
+	case GOYA_ASYNC_EVENT_ID_TPC3_ECC:
+	case GOYA_ASYNC_EVENT_ID_TPC4_ECC:
+	case GOYA_ASYNC_EVENT_ID_TPC5_ECC:
+	case GOYA_ASYNC_EVENT_ID_TPC6_ECC:
+	case GOYA_ASYNC_EVENT_ID_TPC7_ECC:
+		return "TPC%d_ecc";
+	case GOYA_ASYNC_EVENT_ID_MME_ECC:
+		return "MME_ecc";
+	case GOYA_ASYNC_EVENT_ID_MME_ECC_EXT:
+		return "MME_ecc_ext";
+	case GOYA_ASYNC_EVENT_ID_MMU_ECC:
+		return "MMU_ecc";
+	case GOYA_ASYNC_EVENT_ID_DMA_MACRO:
+		return "DMA_macro";
+	case GOYA_ASYNC_EVENT_ID_DMA_ECC:
+		return "DMA_ecc";
+	case GOYA_ASYNC_EVENT_ID_CPU_IF_ECC:
+		return "CPU_if_ecc";
+	case GOYA_ASYNC_EVENT_ID_PSOC_MEM:
+		return "PSOC_mem";
+	case GOYA_ASYNC_EVENT_ID_PSOC_CORESIGHT:
+		return "PSOC_coresight";
+	case GOYA_ASYNC_EVENT_ID_SRAM0 ... GOYA_ASYNC_EVENT_ID_SRAM29:
+		return "SRAM%d";
+	case GOYA_ASYNC_EVENT_ID_GIC500:
+		return "GIC500";
+	case GOYA_ASYNC_EVENT_ID_PLL0 ... GOYA_ASYNC_EVENT_ID_PLL6:
+		return "PLL%d";
+	case GOYA_ASYNC_EVENT_ID_AXI_ECC:
+		return "AXI_ecc";
+	case GOYA_ASYNC_EVENT_ID_L2_RAM_ECC:
+		return "L2_ram_ecc";
+	case GOYA_ASYNC_EVENT_ID_PSOC_GPIO_05_SW_RESET:
+		return "PSOC_gpio_05_sw_reset";
+	case GOYA_ASYNC_EVENT_ID_PSOC_GPIO_10_VRHOT_ICRIT:
+		return "PSOC_gpio_10_vrhot_icrit";
 	case GOYA_ASYNC_EVENT_ID_PCIE_DEC:
 		return "PCIe_dec";
 	case GOYA_ASYNC_EVENT_ID_TPC0_DEC:
@@ -4128,6 +4186,17 @@ static const char *_goya_get_event_desc(u16 event_type)
 		return "DMA%d_qm";
 	case GOYA_ASYNC_EVENT_ID_DMA0_CH ... GOYA_ASYNC_EVENT_ID_DMA4_CH:
 		return "DMA%d_ch";
+	case GOYA_ASYNC_EVENT_ID_TPC0_BMON_SPMU:
+	case GOYA_ASYNC_EVENT_ID_TPC1_BMON_SPMU:
+	case GOYA_ASYNC_EVENT_ID_TPC2_BMON_SPMU:
+	case GOYA_ASYNC_EVENT_ID_TPC3_BMON_SPMU:
+	case GOYA_ASYNC_EVENT_ID_TPC4_BMON_SPMU:
+	case GOYA_ASYNC_EVENT_ID_TPC5_BMON_SPMU:
+	case GOYA_ASYNC_EVENT_ID_TPC6_BMON_SPMU:
+	case GOYA_ASYNC_EVENT_ID_TPC7_BMON_SPMU:
+		return "TPC%d_bmon_spmu";
+	case GOYA_ASYNC_EVENT_ID_DMA_BM_CH0 ... GOYA_ASYNC_EVENT_ID_DMA_BM_CH4:
+		return "DMA_bm_ch%d";
 	default:
 		return "N/A";
 	}
@@ -4138,6 +4207,25 @@ static void goya_get_event_desc(u16 event_type, char *desc, size_t size)
 	u8 index;
 
 	switch (event_type) {
+	case GOYA_ASYNC_EVENT_ID_TPC0_ECC:
+	case GOYA_ASYNC_EVENT_ID_TPC1_ECC:
+	case GOYA_ASYNC_EVENT_ID_TPC2_ECC:
+	case GOYA_ASYNC_EVENT_ID_TPC3_ECC:
+	case GOYA_ASYNC_EVENT_ID_TPC4_ECC:
+	case GOYA_ASYNC_EVENT_ID_TPC5_ECC:
+	case GOYA_ASYNC_EVENT_ID_TPC6_ECC:
+	case GOYA_ASYNC_EVENT_ID_TPC7_ECC:
+		index = (event_type - GOYA_ASYNC_EVENT_ID_TPC0_ECC) / 3;
+		snprintf(desc, size, _goya_get_event_desc(event_type), index);
+		break;
+	case GOYA_ASYNC_EVENT_ID_SRAM0 ... GOYA_ASYNC_EVENT_ID_SRAM29:
+		index = event_type - GOYA_ASYNC_EVENT_ID_SRAM0;
+		snprintf(desc, size, _goya_get_event_desc(event_type), index);
+		break;
+	case GOYA_ASYNC_EVENT_ID_PLL0 ... GOYA_ASYNC_EVENT_ID_PLL6:
+		index = event_type - GOYA_ASYNC_EVENT_ID_PLL0;
+		snprintf(desc, size, _goya_get_event_desc(event_type), index);
+		break;
 	case GOYA_ASYNC_EVENT_ID_TPC0_DEC:
 	case GOYA_ASYNC_EVENT_ID_TPC1_DEC:
 	case GOYA_ASYNC_EVENT_ID_TPC2_DEC:
@@ -4176,6 +4264,21 @@ static void goya_get_event_desc(u16 event_type, char *desc, size_t size)
 		index = event_type - GOYA_ASYNC_EVENT_ID_DMA0_CH;
 		snprintf(desc, size, _goya_get_event_desc(event_type), index);
 		break;
+	case GOYA_ASYNC_EVENT_ID_TPC0_BMON_SPMU:
+	case GOYA_ASYNC_EVENT_ID_TPC1_BMON_SPMU:
+	case GOYA_ASYNC_EVENT_ID_TPC2_BMON_SPMU:
+	case GOYA_ASYNC_EVENT_ID_TPC3_BMON_SPMU:
+	case GOYA_ASYNC_EVENT_ID_TPC4_BMON_SPMU:
+	case GOYA_ASYNC_EVENT_ID_TPC5_BMON_SPMU:
+	case GOYA_ASYNC_EVENT_ID_TPC6_BMON_SPMU:
+	case GOYA_ASYNC_EVENT_ID_TPC7_BMON_SPMU:
+		index = (event_type - GOYA_ASYNC_EVENT_ID_TPC0_BMON_SPMU) / 10;
+		snprintf(desc, size, _goya_get_event_desc(event_type), index);
+		break;
+	case GOYA_ASYNC_EVENT_ID_DMA_BM_CH0 ... GOYA_ASYNC_EVENT_ID_DMA_BM_CH4:
+		index = event_type - GOYA_ASYNC_EVENT_ID_DMA_BM_CH0;
+		snprintf(desc, size, _goya_get_event_desc(event_type), index);
+		break;
 	default:
 		snprintf(desc, size, _goya_get_event_desc(event_type));
 		break;
@@ -4226,7 +4329,8 @@ static void goya_print_mmu_error_info(struct hl_device *hdev)
 	}
 }
 
-static void goya_print_irq_info(struct hl_device *hdev, u16 event_type)
+static void goya_print_irq_info(struct hl_device *hdev, u16 event_type,
+				bool razwi)
 {
 	char desc[20] = "";
 
@@ -4234,8 +4338,10 @@ static void goya_print_irq_info(struct hl_device *hdev, u16 event_type)
 	dev_err(hdev->dev, "Received H/W interrupt %d [\"%s\"]\n",
 		event_type, desc);
 
-	goya_print_razwi_info(hdev);
-	goya_print_mmu_error_info(hdev);
+	if (razwi) {
+		goya_print_razwi_info(hdev);
+		goya_print_mmu_error_info(hdev);
+	}
 }
 
 static int goya_unmask_irq_arr(struct hl_device *hdev, u32 *irq_arr,
@@ -4339,19 +4445,12 @@ void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry)
 	case GOYA_ASYNC_EVENT_ID_PSOC_CORESIGHT:
 	case GOYA_ASYNC_EVENT_ID_SRAM0 ... GOYA_ASYNC_EVENT_ID_SRAM29:
 	case GOYA_ASYNC_EVENT_ID_GIC500:
-	case GOYA_ASYNC_EVENT_ID_PLL0:
-	case GOYA_ASYNC_EVENT_ID_PLL1:
-	case GOYA_ASYNC_EVENT_ID_PLL3:
-	case GOYA_ASYNC_EVENT_ID_PLL4:
-	case GOYA_ASYNC_EVENT_ID_PLL5:
-	case GOYA_ASYNC_EVENT_ID_PLL6:
+	case GOYA_ASYNC_EVENT_ID_PLL0 ... GOYA_ASYNC_EVENT_ID_PLL6:
 	case GOYA_ASYNC_EVENT_ID_AXI_ECC:
 	case GOYA_ASYNC_EVENT_ID_L2_RAM_ECC:
 	case GOYA_ASYNC_EVENT_ID_PSOC_GPIO_05_SW_RESET:
 	case GOYA_ASYNC_EVENT_ID_PSOC_GPIO_10_VRHOT_ICRIT:
-		dev_err(hdev->dev,
-			"Received H/W interrupt %d, reset the chip\n",
-			event_type);
+		goya_print_irq_info(hdev, event_type, false);
 		hl_device_reset(hdev, true, false);
 		break;
 
@@ -4382,7 +4481,7 @@ void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry)
 	case GOYA_ASYNC_EVENT_ID_MME_CMDQ:
 	case GOYA_ASYNC_EVENT_ID_DMA0_QM ... GOYA_ASYNC_EVENT_ID_DMA4_QM:
 	case GOYA_ASYNC_EVENT_ID_DMA0_CH ... GOYA_ASYNC_EVENT_ID_DMA4_CH:
-		goya_print_irq_info(hdev, event_type);
+		goya_print_irq_info(hdev, event_type, true);
 		goya_unmask_irq(hdev, event_type);
 		break;
 
@@ -4394,12 +4493,9 @@ void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry)
 	case GOYA_ASYNC_EVENT_ID_TPC5_BMON_SPMU:
 	case GOYA_ASYNC_EVENT_ID_TPC6_BMON_SPMU:
 	case GOYA_ASYNC_EVENT_ID_TPC7_BMON_SPMU:
-	case GOYA_ASYNC_EVENT_ID_DMA_BM_CH0:
-	case GOYA_ASYNC_EVENT_ID_DMA_BM_CH1:
-	case GOYA_ASYNC_EVENT_ID_DMA_BM_CH2:
-	case GOYA_ASYNC_EVENT_ID_DMA_BM_CH3:
-	case GOYA_ASYNC_EVENT_ID_DMA_BM_CH4:
-		dev_info(hdev->dev, "Received H/W interrupt %d\n", event_type);
+	case GOYA_ASYNC_EVENT_ID_DMA_BM_CH0 ... GOYA_ASYNC_EVENT_ID_DMA_BM_CH4:
+		goya_print_irq_info(hdev, event_type, false);
+		goya_unmask_irq(hdev, event_type);
 		break;
 
 	default:
@@ -4418,36 +4514,47 @@ void *goya_get_events_stat(struct hl_device *hdev, u32 *size)
 	return goya->events_stat;
 }
 
-static int goya_memset_device_memory(struct hl_device *hdev, u64 addr, u32 size,
+static int goya_memset_device_memory(struct hl_device *hdev, u64 addr, u64 size,
 				u64 val, bool is_dram)
 {
 	struct packet_lin_dma *lin_dma_pkt;
 	struct hl_cs_job *job;
 	u32 cb_size, ctl;
 	struct hl_cb *cb;
-	int rc;
+	int rc, lin_dma_pkts_cnt;
 
-	cb = hl_cb_kernel_create(hdev, PAGE_SIZE);
+	lin_dma_pkts_cnt = DIV_ROUND_UP_ULL(size, SZ_2G);
+	cb_size = lin_dma_pkts_cnt * sizeof(struct packet_lin_dma) +
+						sizeof(struct packet_msg_prot);
+	cb = hl_cb_kernel_create(hdev, cb_size);
 	if (!cb)
-		return -EFAULT;
+		return -ENOMEM;
 
 	lin_dma_pkt = (struct packet_lin_dma *) (uintptr_t) cb->kernel_address;
 
-	memset(lin_dma_pkt, 0, sizeof(*lin_dma_pkt));
-	cb_size = sizeof(*lin_dma_pkt);
-
-	ctl = ((PACKET_LIN_DMA << GOYA_PKT_CTL_OPCODE_SHIFT) |
-			(1 << GOYA_PKT_LIN_DMA_CTL_MEMSET_SHIFT) |
-			(1 << GOYA_PKT_LIN_DMA_CTL_WO_SHIFT) |
-			(1 << GOYA_PKT_CTL_RB_SHIFT) |
-			(1 << GOYA_PKT_CTL_MB_SHIFT));
-	ctl |= (is_dram ? DMA_HOST_TO_DRAM : DMA_HOST_TO_SRAM) <<
-			GOYA_PKT_LIN_DMA_CTL_DMA_DIR_SHIFT;
-	lin_dma_pkt->ctl = cpu_to_le32(ctl);
+	do {
+		memset(lin_dma_pkt, 0, sizeof(*lin_dma_pkt));
+
+		ctl = ((PACKET_LIN_DMA << GOYA_PKT_CTL_OPCODE_SHIFT) |
+				(1 << GOYA_PKT_LIN_DMA_CTL_MEMSET_SHIFT) |
+				(1 << GOYA_PKT_LIN_DMA_CTL_WO_SHIFT) |
+				(1 << GOYA_PKT_CTL_RB_SHIFT) |
+				(1 << GOYA_PKT_CTL_MB_SHIFT));
+		ctl |= (is_dram ? DMA_HOST_TO_DRAM : DMA_HOST_TO_SRAM) <<
+				GOYA_PKT_LIN_DMA_CTL_DMA_DIR_SHIFT;
+		lin_dma_pkt->ctl = cpu_to_le32(ctl);
+
+		lin_dma_pkt->src_addr = cpu_to_le64(val);
+		lin_dma_pkt->dst_addr = cpu_to_le64(addr);
+		if (lin_dma_pkts_cnt > 1)
+			lin_dma_pkt->tsize = cpu_to_le32(SZ_2G);
+		else
+			lin_dma_pkt->tsize = cpu_to_le32(size);
 
-	lin_dma_pkt->src_addr = cpu_to_le64(val);
-	lin_dma_pkt->dst_addr = cpu_to_le64(addr);
-	lin_dma_pkt->tsize = cpu_to_le32(size);
+		size -= SZ_2G;
+		addr += SZ_2G;
+		lin_dma_pkt++;
+	} while (--lin_dma_pkts_cnt);
 
 	job = hl_cs_allocate_job(hdev, true);
 	if (!job) {
@@ -4462,8 +4569,7 @@ static int goya_memset_device_memory(struct hl_device *hdev, u64 addr, u32 size,
 	job->user_cb_size = cb_size;
 	job->hw_queue_id = GOYA_QUEUE_ID_DMA_0;
 	job->patched_cb = job->user_cb;
-	job->job_cb_size = job->user_cb_size +
-			sizeof(struct packet_msg_prot) * 2;
+	job->job_cb_size = job->user_cb_size;
 
 	hl_debugfs_add_job(hdev, job);
 
@@ -4485,10 +4591,12 @@ release_cb:
 int goya_context_switch(struct hl_device *hdev, u32 asid)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
-	u64 addr = prop->sram_base_address;
+	u64 addr = prop->sram_base_address, sob_addr;
 	u32 size = hdev->pldm ? 0x10000 : prop->sram_size;
 	u64 val = 0x7777777777777777ull;
-	int rc;
+	int rc, dma_id;
+	u32 channel_off = mmDMA_CH_1_WR_COMP_ADDR_LO -
+					mmDMA_CH_0_WR_COMP_ADDR_LO;
 
 	rc = goya_memset_device_memory(hdev, addr, size, val, false);
 	if (rc) {
@@ -4496,13 +4604,27 @@ int goya_context_switch(struct hl_device *hdev, u32 asid)
 		return rc;
 	}
 
+	/* we need to reset registers that the user is allowed to change */
+	sob_addr = CFG_BASE + mmSYNC_MNGR_SOB_OBJ_1007;
+	WREG32(mmDMA_CH_0_WR_COMP_ADDR_LO, lower_32_bits(sob_addr));
+
+	for (dma_id = 1 ; dma_id < NUMBER_OF_EXT_HW_QUEUES ; dma_id++) {
+		sob_addr = CFG_BASE + mmSYNC_MNGR_SOB_OBJ_1000 +
+							(dma_id - 1) * 4;
+		WREG32(mmDMA_CH_0_WR_COMP_ADDR_LO + channel_off * dma_id,
+						lower_32_bits(sob_addr));
+	}
+
 	WREG32(mmTPC_PLL_CLK_RLX_0, 0x200020);
+
 	goya_mmu_prepare(hdev, asid);
 
+	goya_clear_sm_regs(hdev);
+
 	return 0;
 }
 
-int goya_mmu_clear_pgt_range(struct hl_device *hdev)
+static int goya_mmu_clear_pgt_range(struct hl_device *hdev)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
 	struct goya_device *goya = hdev->asic_specific;
@@ -4516,7 +4638,7 @@ int goya_mmu_clear_pgt_range(struct hl_device *hdev)
 	return goya_memset_device_memory(hdev, addr, size, 0, true);
 }
 
-int goya_mmu_set_dram_default_page(struct hl_device *hdev)
+static int goya_mmu_set_dram_default_page(struct hl_device *hdev)
 {
 	struct goya_device *goya = hdev->asic_specific;
 	u64 addr = hdev->asic_prop.mmu_dram_default_page_addr;
@@ -4529,7 +4651,123 @@ int goya_mmu_set_dram_default_page(struct hl_device *hdev)
 	return goya_memset_device_memory(hdev, addr, size, val, true);
 }
 
-void goya_mmu_prepare(struct hl_device *hdev, u32 asid)
+static int goya_mmu_add_mappings_for_device_cpu(struct hl_device *hdev)
+{
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct goya_device *goya = hdev->asic_specific;
+	s64 off, cpu_off;
+	int rc;
+
+	if (!(goya->hw_cap_initialized & HW_CAP_MMU))
+		return 0;
+
+	for (off = 0 ; off < CPU_FW_IMAGE_SIZE ; off += PAGE_SIZE_2MB) {
+		rc = hl_mmu_map(hdev->kernel_ctx, prop->dram_base_address + off,
+				prop->dram_base_address + off, PAGE_SIZE_2MB);
+		if (rc) {
+			dev_err(hdev->dev, "Map failed for address 0x%llx\n",
+				prop->dram_base_address + off);
+			goto unmap;
+		}
+	}
+
+	if (!(hdev->cpu_accessible_dma_address & (PAGE_SIZE_2MB - 1))) {
+		rc = hl_mmu_map(hdev->kernel_ctx, VA_CPU_ACCESSIBLE_MEM_ADDR,
+			hdev->cpu_accessible_dma_address, PAGE_SIZE_2MB);
+
+		if (rc) {
+			dev_err(hdev->dev,
+				"Map failed for CPU accessible memory\n");
+			off -= PAGE_SIZE_2MB;
+			goto unmap;
+		}
+	} else {
+		for (cpu_off = 0 ; cpu_off < SZ_2M ; cpu_off += PAGE_SIZE_4KB) {
+			rc = hl_mmu_map(hdev->kernel_ctx,
+				VA_CPU_ACCESSIBLE_MEM_ADDR + cpu_off,
+				hdev->cpu_accessible_dma_address + cpu_off,
+				PAGE_SIZE_4KB);
+			if (rc) {
+				dev_err(hdev->dev,
+					"Map failed for CPU accessible memory\n");
+				cpu_off -= PAGE_SIZE_4KB;
+				goto unmap_cpu;
+			}
+		}
+	}
+
+	goya_mmu_prepare_reg(hdev, mmCPU_IF_ARUSER_OVR, HL_KERNEL_ASID_ID);
+	goya_mmu_prepare_reg(hdev, mmCPU_IF_AWUSER_OVR, HL_KERNEL_ASID_ID);
+	WREG32(mmCPU_IF_ARUSER_OVR_EN, 0x7FF);
+	WREG32(mmCPU_IF_AWUSER_OVR_EN, 0x7FF);
+
+	/* Make sure configuration is flushed to device */
+	RREG32(mmCPU_IF_AWUSER_OVR_EN);
+
+	goya->device_cpu_mmu_mappings_done = true;
+
+	return 0;
+
+unmap_cpu:
+	for (; cpu_off >= 0 ; cpu_off -= PAGE_SIZE_4KB)
+		if (hl_mmu_unmap(hdev->kernel_ctx,
+				VA_CPU_ACCESSIBLE_MEM_ADDR + cpu_off,
+				PAGE_SIZE_4KB))
+			dev_warn_ratelimited(hdev->dev,
+				"failed to unmap address 0x%llx\n",
+				VA_CPU_ACCESSIBLE_MEM_ADDR + cpu_off);
+unmap:
+	for (; off >= 0 ; off -= PAGE_SIZE_2MB)
+		if (hl_mmu_unmap(hdev->kernel_ctx,
+				prop->dram_base_address + off, PAGE_SIZE_2MB))
+			dev_warn_ratelimited(hdev->dev,
+				"failed to unmap address 0x%llx\n",
+				prop->dram_base_address + off);
+
+	return rc;
+}
+
+void goya_mmu_remove_device_cpu_mappings(struct hl_device *hdev)
+{
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct goya_device *goya = hdev->asic_specific;
+	u32 off, cpu_off;
+
+	if (!(goya->hw_cap_initialized & HW_CAP_MMU))
+		return;
+
+	if (!goya->device_cpu_mmu_mappings_done)
+		return;
+
+	WREG32(mmCPU_IF_ARUSER_OVR_EN, 0);
+	WREG32(mmCPU_IF_AWUSER_OVR_EN, 0);
+
+	if (!(hdev->cpu_accessible_dma_address & (PAGE_SIZE_2MB - 1))) {
+		if (hl_mmu_unmap(hdev->kernel_ctx, VA_CPU_ACCESSIBLE_MEM_ADDR,
+				PAGE_SIZE_2MB))
+			dev_warn(hdev->dev,
+				"Failed to unmap CPU accessible memory\n");
+	} else {
+		for (cpu_off = 0 ; cpu_off < SZ_2M ; cpu_off += PAGE_SIZE_4KB)
+			if (hl_mmu_unmap(hdev->kernel_ctx,
+					VA_CPU_ACCESSIBLE_MEM_ADDR + cpu_off,
+					PAGE_SIZE_4KB))
+				dev_warn_ratelimited(hdev->dev,
+					"failed to unmap address 0x%llx\n",
+					VA_CPU_ACCESSIBLE_MEM_ADDR + cpu_off);
+	}
+
+	for (off = 0 ; off < CPU_FW_IMAGE_SIZE ; off += PAGE_SIZE_2MB)
+		if (hl_mmu_unmap(hdev->kernel_ctx,
+				prop->dram_base_address + off, PAGE_SIZE_2MB))
+			dev_warn_ratelimited(hdev->dev,
+					"Failed to unmap address 0x%llx\n",
+					prop->dram_base_address + off);
+
+	goya->device_cpu_mmu_mappings_done = false;
+}
+
+static void goya_mmu_prepare(struct hl_device *hdev, u32 asid)
 {
 	struct goya_device *goya = hdev->asic_specific;
 	int i;
@@ -4676,57 +4914,82 @@ int goya_armcp_info_get(struct hl_device *hdev)
 	return 0;
 }
 
-static bool goya_is_device_idle(struct hl_device *hdev, char *buf, size_t size)
+static bool goya_is_device_idle(struct hl_device *hdev, u32 *mask,
+				struct seq_file *s)
 {
-	u64 offset, dma_qm_reg, tpc_qm_reg, tpc_cmdq_reg, tpc_cfg_reg;
+	const char *fmt = "%-5d%-9s%#-14x%#-16x%#x\n";
+	const char *dma_fmt = "%-5d%-9s%#-14x%#x\n";
+	u32 qm_glbl_sts0, cmdq_glbl_sts0, dma_core_sts0, tpc_cfg_sts,
+		mme_arch_sts;
+	bool is_idle = true, is_eng_idle;
+	u64 offset;
 	int i;
 
+	if (s)
+		seq_puts(s, "\nDMA  is_idle  QM_GLBL_STS0  DMA_CORE_STS0\n"
+				"---  -------  ------------  -------------\n");
+
 	offset = mmDMA_QM_1_GLBL_STS0 - mmDMA_QM_0_GLBL_STS0;
 
 	for (i = 0 ; i < DMA_MAX_NUM ; i++) {
-		dma_qm_reg = mmDMA_QM_0_GLBL_STS0 + i * offset;
+		qm_glbl_sts0 = RREG32(mmDMA_QM_0_GLBL_STS0 + i * offset);
+		dma_core_sts0 = RREG32(mmDMA_CH_0_STS0 + i * offset);
+		is_eng_idle = IS_DMA_QM_IDLE(qm_glbl_sts0) &&
+				IS_DMA_IDLE(dma_core_sts0);
+		is_idle &= is_eng_idle;
 
-		if ((RREG32(dma_qm_reg) & DMA_QM_IDLE_MASK) !=
-				DMA_QM_IDLE_MASK)
-			return HL_ENG_BUSY(buf, size, "DMA%d_QM", i);
+		if (mask)
+			*mask |= !is_eng_idle << (GOYA_ENGINE_ID_DMA_0 + i);
+		if (s)
+			seq_printf(s, dma_fmt, i, is_eng_idle ? "Y" : "N",
+					qm_glbl_sts0, dma_core_sts0);
 	}
 
+	if (s)
+		seq_puts(s,
+			"\nTPC  is_idle  QM_GLBL_STS0  CMDQ_GLBL_STS0  CFG_STATUS\n"
+			"---  -------  ------------  --------------  ----------\n");
+
 	offset = mmTPC1_QM_GLBL_STS0 - mmTPC0_QM_GLBL_STS0;
 
 	for (i = 0 ; i < TPC_MAX_NUM ; i++) {
-		tpc_qm_reg = mmTPC0_QM_GLBL_STS0 + i * offset;
-		tpc_cmdq_reg = mmTPC0_CMDQ_GLBL_STS0 + i * offset;
-		tpc_cfg_reg = mmTPC0_CFG_STATUS + i * offset;
-
-		if ((RREG32(tpc_qm_reg) & TPC_QM_IDLE_MASK) !=
-				TPC_QM_IDLE_MASK)
-			return HL_ENG_BUSY(buf, size, "TPC%d_QM", i);
-
-		if ((RREG32(tpc_cmdq_reg) & TPC_CMDQ_IDLE_MASK) !=
-				TPC_CMDQ_IDLE_MASK)
-			return HL_ENG_BUSY(buf, size, "TPC%d_CMDQ", i);
-
-		if ((RREG32(tpc_cfg_reg) & TPC_CFG_IDLE_MASK) !=
-				TPC_CFG_IDLE_MASK)
-			return HL_ENG_BUSY(buf, size, "TPC%d_CFG", i);
-	}
-
-	if ((RREG32(mmMME_QM_GLBL_STS0) & MME_QM_IDLE_MASK) !=
-			MME_QM_IDLE_MASK)
-		return HL_ENG_BUSY(buf, size, "MME_QM");
-
-	if ((RREG32(mmMME_CMDQ_GLBL_STS0) & MME_CMDQ_IDLE_MASK) !=
-			MME_CMDQ_IDLE_MASK)
-		return HL_ENG_BUSY(buf, size, "MME_CMDQ");
-
-	if ((RREG32(mmMME_ARCH_STATUS) & MME_ARCH_IDLE_MASK) !=
-			MME_ARCH_IDLE_MASK)
-		return HL_ENG_BUSY(buf, size, "MME_ARCH");
-
-	if (RREG32(mmMME_SHADOW_0_STATUS) & MME_SHADOW_IDLE_MASK)
-		return HL_ENG_BUSY(buf, size, "MME");
-
-	return true;
+		qm_glbl_sts0 = RREG32(mmTPC0_QM_GLBL_STS0 + i * offset);
+		cmdq_glbl_sts0 = RREG32(mmTPC0_CMDQ_GLBL_STS0 + i * offset);
+		tpc_cfg_sts = RREG32(mmTPC0_CFG_STATUS + i * offset);
+		is_eng_idle = IS_TPC_QM_IDLE(qm_glbl_sts0) &&
+				IS_TPC_CMDQ_IDLE(cmdq_glbl_sts0) &&
+				IS_TPC_IDLE(tpc_cfg_sts);
+		is_idle &= is_eng_idle;
+
+		if (mask)
+			*mask |= !is_eng_idle << (GOYA_ENGINE_ID_TPC_0 + i);
+		if (s)
+			seq_printf(s, fmt, i, is_eng_idle ? "Y" : "N",
+				qm_glbl_sts0, cmdq_glbl_sts0, tpc_cfg_sts);
+	}
+
+	if (s)
+		seq_puts(s,
+			"\nMME  is_idle  QM_GLBL_STS0  CMDQ_GLBL_STS0  ARCH_STATUS\n"
+			"---  -------  ------------  --------------  -----------\n");
+
+	qm_glbl_sts0 = RREG32(mmMME_QM_GLBL_STS0);
+	cmdq_glbl_sts0 = RREG32(mmMME_CMDQ_GLBL_STS0);
+	mme_arch_sts = RREG32(mmMME_ARCH_STATUS);
+	is_eng_idle = IS_MME_QM_IDLE(qm_glbl_sts0) &&
+			IS_MME_CMDQ_IDLE(cmdq_glbl_sts0) &&
+			IS_MME_IDLE(mme_arch_sts);
+	is_idle &= is_eng_idle;
+
+	if (mask)
+		*mask |= !is_eng_idle << GOYA_ENGINE_ID_MME_0;
+	if (s) {
+		seq_printf(s, fmt, 0, is_eng_idle ? "Y" : "N", qm_glbl_sts0,
+				cmdq_glbl_sts0, mme_arch_sts);
+		seq_puts(s, "\n");
+	}
+
+	return is_idle;
 }
 
 static void goya_hw_queues_lock(struct hl_device *hdev)
diff --git a/drivers/misc/habanalabs/goya/goyaP.h b/drivers/misc/habanalabs/goya/goyaP.h
index c83cab0d641e..f8c611883dc1 100644
--- a/drivers/misc/habanalabs/goya/goyaP.h
+++ b/drivers/misc/habanalabs/goya/goyaP.h
@@ -126,6 +126,12 @@
 #define VA_DDR_SPACE_SIZE	(VA_DDR_SPACE_END - \
 					VA_DDR_SPACE_START)	/* 128GB */
 
+#if (HL_CPU_ACCESSIBLE_MEM_SIZE != SZ_2M)
+#error "HL_CPU_ACCESSIBLE_MEM_SIZE must be exactly 2MB to enable MMU mapping"
+#endif
+
+#define VA_CPU_ACCESSIBLE_MEM_ADDR	0x8000000000ull
+
 #define DMA_MAX_TRANSFER_SIZE	U32_MAX
 
 #define HW_CAP_PLL		0x00000001
@@ -157,6 +163,7 @@ struct goya_device {
 	u64		ddr_bar_cur_addr;
 	u32		events_stat[GOYA_ASYNC_EVENT_ID_SIZE];
 	u32		hw_cap_initialized;
+	u8		device_cpu_mmu_mappings_done;
 };
 
 void goya_get_fixed_properties(struct hl_device *hdev);
@@ -204,18 +211,14 @@ int goya_armcp_info_get(struct hl_device *hdev);
 int goya_debug_coresight(struct hl_device *hdev, void *data);
 void goya_halt_coresight(struct hl_device *hdev);
 
-void goya_mmu_prepare(struct hl_device *hdev, u32 asid);
-int goya_mmu_clear_pgt_range(struct hl_device *hdev);
-int goya_mmu_set_dram_default_page(struct hl_device *hdev);
-
 int goya_suspend(struct hl_device *hdev);
 int goya_resume(struct hl_device *hdev);
 
 void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry);
 void *goya_get_events_stat(struct hl_device *hdev, u32 *size);
 
-void goya_add_end_of_cb_packets(u64 kernel_address, u32 len, u64 cq_addr,
-				u32 cq_val, u32 msix_vec);
+void goya_add_end_of_cb_packets(struct hl_device *hdev, u64 kernel_address,
+				u32 len, u64 cq_addr, u32 cq_val, u32 msix_vec);
 int goya_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser);
 void *goya_get_int_queue_base(struct hl_device *hdev, u32 queue_id,
 				dma_addr_t *dma_handle,	u16 *queue_len);
@@ -225,5 +228,6 @@ void *goya_cpu_accessible_dma_pool_alloc(struct hl_device *hdev, size_t size,
 					dma_addr_t *dma_handle);
 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);
 
 #endif /* GOYAP_H_ */
diff --git a/drivers/misc/habanalabs/goya/goya_security.c b/drivers/misc/habanalabs/goya/goya_security.c
index d95d1b2f860d..d6ec12b3e692 100644
--- a/drivers/misc/habanalabs/goya/goya_security.c
+++ b/drivers/misc/habanalabs/goya/goya_security.c
@@ -677,6 +677,17 @@ static void goya_init_tpc_protection_bits(struct hl_device *hdev)
 	goya_pb_set_block(hdev, mmTPC0_RD_REGULATOR_BASE);
 	goya_pb_set_block(hdev, mmTPC0_WR_REGULATOR_BASE);
 
+	pb_addr = (mmTPC0_CFG_SEMAPHORE & ~0xFFF) + PROT_BITS_OFFS;
+	word_offset = ((mmTPC0_CFG_SEMAPHORE & PROT_BITS_OFFS) >> 7) << 2;
+
+	mask = 1 << ((mmTPC0_CFG_SEMAPHORE & 0x7F) >> 2);
+	mask |= 1 << ((mmTPC0_CFG_VFLAGS & 0x7F) >> 2);
+	mask |= 1 << ((mmTPC0_CFG_SFLAGS & 0x7F) >> 2);
+	mask |= 1 << ((mmTPC0_CFG_LFSR_POLYNOM & 0x7F) >> 2);
+	mask |= 1 << ((mmTPC0_CFG_STATUS & 0x7F) >> 2);
+
+	WREG32(pb_addr + word_offset, ~mask);
+
 	pb_addr = (mmTPC0_CFG_CFG_BASE_ADDRESS_HIGH & ~0xFFF) + PROT_BITS_OFFS;
 	word_offset = ((mmTPC0_CFG_CFG_BASE_ADDRESS_HIGH &
 			PROT_BITS_OFFS) >> 7) << 2;
@@ -684,6 +695,11 @@ static void goya_init_tpc_protection_bits(struct hl_device *hdev)
 	mask |= 1 << ((mmTPC0_CFG_CFG_SUBTRACT_VALUE & 0x7F) >> 2);
 	mask |= 1 << ((mmTPC0_CFG_SM_BASE_ADDRESS_LOW & 0x7F) >> 2);
 	mask |= 1 << ((mmTPC0_CFG_SM_BASE_ADDRESS_HIGH & 0x7F) >> 2);
+	mask |= 1 << ((mmTPC0_CFG_CFG_SUBTRACT_VALUE & 0x7F) >> 2);
+	mask |= 1 << ((mmTPC0_CFG_TPC_STALL & 0x7F) >> 2);
+	mask |= 1 << ((mmTPC0_CFG_MSS_CONFIG & 0x7F) >> 2);
+	mask |= 1 << ((mmTPC0_CFG_TPC_INTR_CAUSE & 0x7F) >> 2);
+	mask |= 1 << ((mmTPC0_CFG_TPC_INTR_MASK & 0x7F) >> 2);
 
 	WREG32(pb_addr + word_offset, ~mask);
 
diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h
index adef7d9d7488..10da9940ee0d 100644
--- a/drivers/misc/habanalabs/habanalabs.h
+++ b/drivers/misc/habanalabs/habanalabs.h
@@ -34,6 +34,8 @@
 #define HL_ARMCP_INFO_TIMEOUT_USEC	10000000 /* 10s */
 #define HL_ARMCP_EEPROM_TIMEOUT_USEC	10000000 /* 10s */
 
+#define HL_PCI_ELBI_TIMEOUT_MSEC	10 /* 10ms */
+
 #define HL_MAX_QUEUES			128
 
 #define HL_MAX_JOBS_PER_CS		64
@@ -123,7 +125,7 @@ enum hl_device_hw_state {
 /**
  * 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.
+ * @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.
@@ -318,18 +320,8 @@ struct hl_cs_job;
 #define HL_EQ_LENGTH			64
 #define HL_EQ_SIZE_IN_BYTES		(HL_EQ_LENGTH * HL_EQ_ENTRY_SIZE)
 
-#define HL_CPU_PKT_SHIFT		5
-#define HL_CPU_PKT_SIZE			(1 << HL_CPU_PKT_SHIFT)
-#define HL_CPU_PKT_MASK			(~((1 << HL_CPU_PKT_SHIFT) - 1))
-#define HL_CPU_MAX_PKTS_IN_CB		32
-#define HL_CPU_CB_SIZE			(HL_CPU_PKT_SIZE * \
-					 HL_CPU_MAX_PKTS_IN_CB)
-#define HL_CPU_CB_QUEUE_SIZE		(HL_QUEUE_LENGTH * HL_CPU_CB_SIZE)
-
-/* KMD <-> ArmCP shared memory size (EQ + PQ + CPU CB queue) */
-#define HL_CPU_ACCESSIBLE_MEM_SIZE	(HL_EQ_SIZE_IN_BYTES + \
-					 HL_QUEUE_SIZE_IN_BYTES + \
-					 HL_CPU_CB_QUEUE_SIZE)
+/* KMD <-> ArmCP shared memory size */
+#define HL_CPU_ACCESSIBLE_MEM_SIZE	SZ_2M
 
 /**
  * struct hl_hw_queue - describes a H/W transport queue.
@@ -543,8 +535,9 @@ struct hl_asic_funcs {
 				enum dma_data_direction dir);
 	u32 (*get_dma_desc_list_size)(struct hl_device *hdev,
 					struct sg_table *sgt);
-	void (*add_end_of_cb_packets)(u64 kernel_address, u32 len, u64 cq_addr,
-					u32 cq_val, u32 msix_num);
+	void (*add_end_of_cb_packets)(struct hl_device *hdev,
+					u64 kernel_address, u32 len,
+					u64 cq_addr, u32 cq_val, u32 msix_num);
 	void (*update_eq_ci)(struct hl_device *hdev, u32 val);
 	int (*context_switch)(struct hl_device *hdev, u32 asid);
 	void (*restore_phase_topology)(struct hl_device *hdev);
@@ -564,7 +557,8 @@ struct hl_asic_funcs {
 			u32 asid, u64 va, u64 size);
 	int (*send_heartbeat)(struct hl_device *hdev);
 	int (*debug_coresight)(struct hl_device *hdev, void *data);
-	bool (*is_device_idle)(struct hl_device *hdev, char *buf, size_t size);
+	bool (*is_device_idle)(struct hl_device *hdev, u32 *mask,
+				struct seq_file *s);
 	int (*soft_reset_late_init)(struct hl_device *hdev);
 	void (*hw_queues_lock)(struct hl_device *hdev);
 	void (*hw_queues_unlock)(struct hl_device *hdev);
@@ -1065,12 +1059,59 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val);
 	(cond) ? 0 : -ETIMEDOUT; \
 })
 
+/*
+ * address in this macro points always to a memory location in the
+ * host's (server's) memory. That location is updated asynchronously
+ * either by the direct access of the device or by another core
+ */
+#define hl_poll_timeout_memory(hdev, addr, val, cond, sleep_us, timeout_us) \
+({ \
+	ktime_t __timeout; \
+	/* timeout should be longer when working with simulator */ \
+	if (hdev->pdev) \
+		__timeout = ktime_add_us(ktime_get(), timeout_us); \
+	else \
+		__timeout = ktime_add_us(ktime_get(), (timeout_us * 10)); \
+	might_sleep_if(sleep_us); \
+	for (;;) { \
+		/* Verify we read updates done by other cores or by device */ \
+		mb(); \
+		(val) = *((u32 *) (uintptr_t) (addr)); \
+		if (cond) \
+			break; \
+		if (timeout_us && ktime_compare(ktime_get(), __timeout) > 0) { \
+			(val) = *((u32 *) (uintptr_t) (addr)); \
+			break; \
+		} \
+		if (sleep_us) \
+			usleep_range((sleep_us >> 2) + 1, sleep_us); \
+	} \
+	(cond) ? 0 : -ETIMEDOUT; \
+})
 
-#define HL_ENG_BUSY(buf, size, fmt, ...) ({ \
-		if (buf) \
-			snprintf(buf, size, fmt, ##__VA_ARGS__); \
-		false; \
-	})
+#define hl_poll_timeout_device_memory(hdev, addr, val, cond, sleep_us, \
+					timeout_us) \
+({ \
+	ktime_t __timeout; \
+	/* timeout should be longer when working with simulator */ \
+	if (hdev->pdev) \
+		__timeout = ktime_add_us(ktime_get(), timeout_us); \
+	else \
+		__timeout = ktime_add_us(ktime_get(), (timeout_us * 10)); \
+	might_sleep_if(sleep_us); \
+	for (;;) { \
+		(val) = readl(addr); \
+		if (cond) \
+			break; \
+		if (timeout_us && ktime_compare(ktime_get(), __timeout) > 0) { \
+			(val) = readl(addr); \
+			break; \
+		} \
+		if (sleep_us) \
+			usleep_range((sleep_us >> 2) + 1, sleep_us); \
+	} \
+	(cond) ? 0 : -ETIMEDOUT; \
+})
 
 struct hwmon_chip_info;
 
@@ -1117,6 +1158,7 @@ struct hl_device_reset_work {
  *                    lock here so we can flush user processes which are opening
  *                    the device while we are trying to hard reset it
  * @send_cpu_message_lock: enforces only one message in KMD <-> ArmCP queue.
+ * @debug_lock: protects critical section of setting debug mode for device
  * @asic_prop: ASIC specific immutable properties.
  * @asic_funcs: ASIC specific functions.
  * @asic_specific: ASIC specific information to use only from ASIC files.
@@ -1159,6 +1201,8 @@ struct hl_device_reset_work {
  * @mmu_enable: is MMU enabled.
  * @device_cpu_disabled: is the device CPU disabled (due to timeouts)
  * @dma_mask: the dma mask that was set for this device
+ * @in_debug: is device under debug. This, together with fd_open_cnt, enforces
+ *            that only a single user is configuring the debug infrastructure.
  */
 struct hl_device {
 	struct pci_dev			*pdev;
@@ -1188,6 +1232,7 @@ struct hl_device {
 	/* TODO: remove fd_open_cnt_lock for multiple process support */
 	struct mutex			fd_open_cnt_lock;
 	struct mutex			send_cpu_message_lock;
+	struct mutex			debug_lock;
 	struct asic_fixed_properties	asic_prop;
 	const struct hl_asic_funcs	*asic_funcs;
 	void				*asic_specific;
@@ -1230,6 +1275,7 @@ struct hl_device {
 	u8				init_done;
 	u8				device_cpu_disabled;
 	u8				dma_mask;
+	u8				in_debug;
 
 	/* Parameters for bring-up */
 	u8				mmu_enable;
@@ -1325,13 +1371,10 @@ static inline bool hl_mem_area_crosses_range(u64 address, u32 size,
 int hl_device_open(struct inode *inode, struct file *filp);
 bool hl_device_disabled_or_in_reset(struct hl_device *hdev);
 enum hl_device_status hl_device_status(struct hl_device *hdev);
+int hl_device_set_debug_mode(struct hl_device *hdev, bool enable);
 int create_hdev(struct hl_device **dev, struct pci_dev *pdev,
 		enum hl_asic_type asic_type, int minor);
 void destroy_hdev(struct hl_device *hdev);
-int hl_poll_timeout_memory(struct hl_device *hdev, u64 addr, u32 timeout_us,
-				u32 *val);
-int hl_poll_timeout_device_memory(struct hl_device *hdev, void __iomem *addr,
-				u32 timeout_us, u32 *val);
 int hl_hw_queues_create(struct hl_device *hdev);
 void hl_hw_queues_destroy(struct hl_device *hdev);
 int hl_hw_queue_send_cb_no_cmpl(struct hl_device *hdev, u32 hw_queue_id,
diff --git a/drivers/misc/habanalabs/habanalabs_drv.c b/drivers/misc/habanalabs/habanalabs_drv.c
index 5f4d155be767..6f6dbe93f1df 100644
--- a/drivers/misc/habanalabs/habanalabs_drv.c
+++ b/drivers/misc/habanalabs/habanalabs_drv.c
@@ -105,9 +105,17 @@ int hl_device_open(struct inode *inode, struct file *filp)
 		return -EPERM;
 	}
 
+	if (hdev->in_debug) {
+		dev_err_ratelimited(hdev->dev,
+			"Can't open %s because it is being debugged by another user\n",
+			dev_name(hdev->dev));
+		mutex_unlock(&hdev->fd_open_cnt_lock);
+		return -EPERM;
+	}
+
 	if (atomic_read(&hdev->fd_open_cnt)) {
 		dev_info_ratelimited(hdev->dev,
-			"Device %s is already attached to application\n",
+			"Can't open %s because another user is working on it\n",
 			dev_name(hdev->dev));
 		mutex_unlock(&hdev->fd_open_cnt_lock);
 		return -EBUSY;
@@ -164,6 +172,17 @@ close_device:
 	return rc;
 }
 
+static void set_driver_behavior_per_device(struct hl_device *hdev)
+{
+	hdev->mmu_enable = 1;
+	hdev->cpu_enable = 1;
+	hdev->fw_loading = 1;
+	hdev->cpu_queues_enable = 1;
+	hdev->heartbeat = 1;
+
+	hdev->reset_pcilink = 0;
+}
+
 /*
  * create_hdev - create habanalabs device instance
  *
@@ -188,29 +207,25 @@ int create_hdev(struct hl_device **dev, struct pci_dev *pdev,
 	if (!hdev)
 		return -ENOMEM;
 
+	/* First, we must find out which ASIC are we handling. This is needed
+	 * to configure the behavior of the driver (kernel parameters)
+	 */
+	if (pdev) {
+		hdev->asic_type = get_asic_type(pdev->device);
+		if (hdev->asic_type == ASIC_INVALID) {
+			dev_err(&pdev->dev, "Unsupported ASIC\n");
+			rc = -ENODEV;
+			goto free_hdev;
+		}
+	} else {
+		hdev->asic_type = asic_type;
+	}
+
 	hdev->major = hl_major;
 	hdev->reset_on_lockup = reset_on_lockup;
-
-	/* Parameters for bring-up - set them to defaults */
-	hdev->mmu_enable = 1;
-	hdev->cpu_enable = 1;
-	hdev->reset_pcilink = 0;
-	hdev->cpu_queues_enable = 1;
-	hdev->fw_loading = 1;
 	hdev->pldm = 0;
-	hdev->heartbeat = 1;
-
-	/* If CPU is disabled, no point in loading FW */
-	if (!hdev->cpu_enable)
-		hdev->fw_loading = 0;
 
-	/* If we don't load FW, no need to initialize CPU queues */
-	if (!hdev->fw_loading)
-		hdev->cpu_queues_enable = 0;
-
-	/* If CPU queues not enabled, no way to do heartbeat */
-	if (!hdev->cpu_queues_enable)
-		hdev->heartbeat = 0;
+	set_driver_behavior_per_device(hdev);
 
 	if (timeout_locked)
 		hdev->timeout_jiffies = msecs_to_jiffies(timeout_locked * 1000);
@@ -220,17 +235,6 @@ int create_hdev(struct hl_device **dev, struct pci_dev *pdev,
 	hdev->disabled = true;
 	hdev->pdev = pdev; /* can be NULL in case of simulator device */
 
-	if (pdev) {
-		hdev->asic_type = get_asic_type(pdev->device);
-		if (hdev->asic_type == ASIC_INVALID) {
-			dev_err(&pdev->dev, "Unsupported ASIC\n");
-			rc = -ENODEV;
-			goto free_hdev;
-		}
-	} else {
-		hdev->asic_type = asic_type;
-	}
-
 	/* Set default DMA mask to 32 bits */
 	hdev->dma_mask = 32;
 
diff --git a/drivers/misc/habanalabs/habanalabs_ioctl.c b/drivers/misc/habanalabs/habanalabs_ioctl.c
index b7a0eecf6b6c..07127576b3e8 100644
--- a/drivers/misc/habanalabs/habanalabs_ioctl.c
+++ b/drivers/misc/habanalabs/habanalabs_ioctl.c
@@ -119,7 +119,8 @@ static int hw_idle(struct hl_device *hdev, struct hl_info_args *args)
 	if ((!max_size) || (!out))
 		return -EINVAL;
 
-	hw_idle.is_idle = hdev->asic_funcs->is_device_idle(hdev, NULL, 0);
+	hw_idle.is_idle = hdev->asic_funcs->is_device_idle(hdev,
+					&hw_idle.busy_engines_mask, NULL);
 
 	return copy_to_user(out, &hw_idle,
 		min((size_t) max_size, sizeof(hw_idle))) ? -EFAULT : 0;
@@ -254,10 +255,18 @@ static int hl_debug_ioctl(struct hl_fpriv *hpriv, void *data)
 	case HL_DEBUG_OP_BMON:
 	case HL_DEBUG_OP_SPMU:
 	case HL_DEBUG_OP_TIMESTAMP:
+		if (!hdev->in_debug) {
+			dev_err_ratelimited(hdev->dev,
+				"Rejecting debug configuration request because device not in debug mode\n");
+			return -EFAULT;
+		}
 		args->input_size =
 			min(args->input_size, hl_debug_struct_size[args->op]);
 		rc = debug_coresight(hdev, args);
 		break;
+	case HL_DEBUG_OP_SET_MODE:
+		rc = hl_device_set_debug_mode(hdev, (bool) args->enable);
+		break;
 	default:
 		dev_err(hdev->dev, "Invalid request %d\n", args->op);
 		rc = -ENOTTY;
diff --git a/drivers/misc/habanalabs/hw_queue.c b/drivers/misc/habanalabs/hw_queue.c
index 2894d8975933..e3b5517897ea 100644
--- a/drivers/misc/habanalabs/hw_queue.c
+++ b/drivers/misc/habanalabs/hw_queue.c
@@ -265,7 +265,7 @@ static void ext_hw_queue_schedule_job(struct hl_cs_job *job)
 	cq = &hdev->completion_queue[q->hw_queue_id];
 	cq_addr = cq->bus_address + cq->pi * sizeof(struct hl_cq_entry);
 
-	hdev->asic_funcs->add_end_of_cb_packets(cb->kernel_address, len,
+	hdev->asic_funcs->add_end_of_cb_packets(hdev, cb->kernel_address, len,
 						cq_addr,
 						__le32_to_cpu(cq_pkt.data),
 						q->hw_queue_id);
diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_0_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_0_masks.h
new file mode 100644
index 000000000000..028143408401
--- /dev/null
+++ b/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_0_masks.h
@@ -0,0 +1,418 @@
+/* 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_DMA_CH_0_MASKS_H_
+#define ASIC_REG_DMA_CH_0_MASKS_H_
+
+/*
+ *****************************************
+ *   DMA_CH_0 (Prototype: DMA_CH)
+ *****************************************
+ */
+
+/* DMA_CH_0_CFG0 */
+#define DMA_CH_0_CFG0_RD_MAX_OUTSTAND_SHIFT                          0
+#define DMA_CH_0_CFG0_RD_MAX_OUTSTAND_MASK                           0x3FF
+#define DMA_CH_0_CFG0_WR_MAX_OUTSTAND_SHIFT                          16
+#define DMA_CH_0_CFG0_WR_MAX_OUTSTAND_MASK                           0xFFF0000
+
+/* DMA_CH_0_CFG1 */
+#define DMA_CH_0_CFG1_RD_BUF_MAX_SIZE_SHIFT                          0
+#define DMA_CH_0_CFG1_RD_BUF_MAX_SIZE_MASK                           0x3FF
+
+/* DMA_CH_0_ERRMSG_ADDR_LO */
+#define DMA_CH_0_ERRMSG_ADDR_LO_VAL_SHIFT                            0
+#define DMA_CH_0_ERRMSG_ADDR_LO_VAL_MASK                             0xFFFFFFFF
+
+/* DMA_CH_0_ERRMSG_ADDR_HI */
+#define DMA_CH_0_ERRMSG_ADDR_HI_VAL_SHIFT                            0
+#define DMA_CH_0_ERRMSG_ADDR_HI_VAL_MASK                             0xFFFFFFFF
+
+/* DMA_CH_0_ERRMSG_WDATA */
+#define DMA_CH_0_ERRMSG_WDATA_VAL_SHIFT                              0
+#define DMA_CH_0_ERRMSG_WDATA_VAL_MASK                               0xFFFFFFFF
+
+/* DMA_CH_0_RD_COMP_ADDR_LO */
+#define DMA_CH_0_RD_COMP_ADDR_LO_VAL_SHIFT                           0
+#define DMA_CH_0_RD_COMP_ADDR_LO_VAL_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_RD_COMP_ADDR_HI */
+#define DMA_CH_0_RD_COMP_ADDR_HI_VAL_SHIFT                           0
+#define DMA_CH_0_RD_COMP_ADDR_HI_VAL_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_RD_COMP_WDATA */
+#define DMA_CH_0_RD_COMP_WDATA_VAL_SHIFT                             0
+#define DMA_CH_0_RD_COMP_WDATA_VAL_MASK                              0xFFFFFFFF
+
+/* DMA_CH_0_WR_COMP_ADDR_LO */
+#define DMA_CH_0_WR_COMP_ADDR_LO_VAL_SHIFT                           0
+#define DMA_CH_0_WR_COMP_ADDR_LO_VAL_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_WR_COMP_ADDR_HI */
+#define DMA_CH_0_WR_COMP_ADDR_HI_VAL_SHIFT                           0
+#define DMA_CH_0_WR_COMP_ADDR_HI_VAL_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_WR_COMP_WDATA */
+#define DMA_CH_0_WR_COMP_WDATA_VAL_SHIFT                             0
+#define DMA_CH_0_WR_COMP_WDATA_VAL_MASK                              0xFFFFFFFF
+
+/* DMA_CH_0_LDMA_SRC_ADDR_LO */
+#define DMA_CH_0_LDMA_SRC_ADDR_LO_VAL_SHIFT                          0
+#define DMA_CH_0_LDMA_SRC_ADDR_LO_VAL_MASK                           0xFFFFFFFF
+
+/* DMA_CH_0_LDMA_SRC_ADDR_HI */
+#define DMA_CH_0_LDMA_SRC_ADDR_HI_VAL_SHIFT                          0
+#define DMA_CH_0_LDMA_SRC_ADDR_HI_VAL_MASK                           0xFFFFFFFF
+
+/* DMA_CH_0_LDMA_DST_ADDR_LO */
+#define DMA_CH_0_LDMA_DST_ADDR_LO_VAL_SHIFT                          0
+#define DMA_CH_0_LDMA_DST_ADDR_LO_VAL_MASK                           0xFFFFFFFF
+
+/* DMA_CH_0_LDMA_DST_ADDR_HI */
+#define DMA_CH_0_LDMA_DST_ADDR_HI_VAL_SHIFT                          0
+#define DMA_CH_0_LDMA_DST_ADDR_HI_VAL_MASK                           0xFFFFFFFF
+
+/* DMA_CH_0_LDMA_TSIZE */
+#define DMA_CH_0_LDMA_TSIZE_VAL_SHIFT                                0
+#define DMA_CH_0_LDMA_TSIZE_VAL_MASK                                 0xFFFFFFFF
+
+/* DMA_CH_0_COMIT_TRANSFER */
+#define DMA_CH_0_COMIT_TRANSFER_PCI_UPS_WKORDR_SHIFT                 0
+#define DMA_CH_0_COMIT_TRANSFER_PCI_UPS_WKORDR_MASK                  0x1
+#define DMA_CH_0_COMIT_TRANSFER_RD_COMP_EN_SHIFT                     1
+#define DMA_CH_0_COMIT_TRANSFER_RD_COMP_EN_MASK                      0x2
+#define DMA_CH_0_COMIT_TRANSFER_WR_COMP_EN_SHIFT                     2
+#define DMA_CH_0_COMIT_TRANSFER_WR_COMP_EN_MASK                      0x4
+#define DMA_CH_0_COMIT_TRANSFER_NOSNOOP_SHIFT                        3
+#define DMA_CH_0_COMIT_TRANSFER_NOSNOOP_MASK                         0x8
+#define DMA_CH_0_COMIT_TRANSFER_SRC_ADDR_INC_DIS_SHIFT               4
+#define DMA_CH_0_COMIT_TRANSFER_SRC_ADDR_INC_DIS_MASK                0x10
+#define DMA_CH_0_COMIT_TRANSFER_DST_ADDR_INC_DIS_SHIFT               5
+#define DMA_CH_0_COMIT_TRANSFER_DST_ADDR_INC_DIS_MASK                0x20
+#define DMA_CH_0_COMIT_TRANSFER_MEM_SET_SHIFT                        6
+#define DMA_CH_0_COMIT_TRANSFER_MEM_SET_MASK                         0x40
+#define DMA_CH_0_COMIT_TRANSFER_MOD_TENSOR_SHIFT                     15
+#define DMA_CH_0_COMIT_TRANSFER_MOD_TENSOR_MASK                      0x8000
+#define DMA_CH_0_COMIT_TRANSFER_CTL_SHIFT                            16
+#define DMA_CH_0_COMIT_TRANSFER_CTL_MASK                             0xFFFF0000
+
+/* DMA_CH_0_STS0 */
+#define DMA_CH_0_STS0_DMA_BUSY_SHIFT                                 0
+#define DMA_CH_0_STS0_DMA_BUSY_MASK                                  0x1
+#define DMA_CH_0_STS0_RD_STS_CTX_FULL_SHIFT                          1
+#define DMA_CH_0_STS0_RD_STS_CTX_FULL_MASK                           0x2
+#define DMA_CH_0_STS0_WR_STS_CTX_FULL_SHIFT                          2
+#define DMA_CH_0_STS0_WR_STS_CTX_FULL_MASK                           0x4
+
+/* DMA_CH_0_STS1 */
+#define DMA_CH_0_STS1_RD_STS_CTX_CNT_SHIFT                           0
+#define DMA_CH_0_STS1_RD_STS_CTX_CNT_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_STS2 */
+#define DMA_CH_0_STS2_WR_STS_CTX_CNT_SHIFT                           0
+#define DMA_CH_0_STS2_WR_STS_CTX_CNT_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_STS3 */
+#define DMA_CH_0_STS3_RD_STS_TRN_CNT_SHIFT                           0
+#define DMA_CH_0_STS3_RD_STS_TRN_CNT_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_STS4 */
+#define DMA_CH_0_STS4_WR_STS_TRN_CNT_SHIFT                           0
+#define DMA_CH_0_STS4_WR_STS_TRN_CNT_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_SRC_ADDR_LO_STS */
+#define DMA_CH_0_SRC_ADDR_LO_STS_VAL_SHIFT                           0
+#define DMA_CH_0_SRC_ADDR_LO_STS_VAL_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_SRC_ADDR_HI_STS */
+#define DMA_CH_0_SRC_ADDR_HI_STS_VAL_SHIFT                           0
+#define DMA_CH_0_SRC_ADDR_HI_STS_VAL_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_SRC_TSIZE_STS */
+#define DMA_CH_0_SRC_TSIZE_STS_VAL_SHIFT                             0
+#define DMA_CH_0_SRC_TSIZE_STS_VAL_MASK                              0xFFFFFFFF
+
+/* DMA_CH_0_DST_ADDR_LO_STS */
+#define DMA_CH_0_DST_ADDR_LO_STS_VAL_SHIFT                           0
+#define DMA_CH_0_DST_ADDR_LO_STS_VAL_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_DST_ADDR_HI_STS */
+#define DMA_CH_0_DST_ADDR_HI_STS_VAL_SHIFT                           0
+#define DMA_CH_0_DST_ADDR_HI_STS_VAL_MASK                            0xFFFFFFFF
+
+/* DMA_CH_0_DST_TSIZE_STS */
+#define DMA_CH_0_DST_TSIZE_STS_VAL_SHIFT                             0
+#define DMA_CH_0_DST_TSIZE_STS_VAL_MASK                              0xFFFFFFFF
+
+/* DMA_CH_0_RD_RATE_LIM_EN */
+#define DMA_CH_0_RD_RATE_LIM_EN_VAL_SHIFT                            0
+#define DMA_CH_0_RD_RATE_LIM_EN_VAL_MASK                             0x1
+
+/* DMA_CH_0_RD_RATE_LIM_RST_TOKEN */
+#define DMA_CH_0_RD_RATE_LIM_RST_TOKEN_VAL_SHIFT                     0
+#define DMA_CH_0_RD_RATE_LIM_RST_TOKEN_VAL_MASK                      0xFFFF
+
+/* DMA_CH_0_RD_RATE_LIM_SAT */
+#define DMA_CH_0_RD_RATE_LIM_SAT_VAL_SHIFT                           0
+#define DMA_CH_0_RD_RATE_LIM_SAT_VAL_MASK                            0xFFFF
+
+/* DMA_CH_0_RD_RATE_LIM_TOUT */
+#define DMA_CH_0_RD_RATE_LIM_TOUT_VAL_SHIFT                          0
+#define DMA_CH_0_RD_RATE_LIM_TOUT_VAL_MASK                           0x7FFFFFFF
+
+/* DMA_CH_0_WR_RATE_LIM_EN */
+#define DMA_CH_0_WR_RATE_LIM_EN_VAL_SHIFT                            0
+#define DMA_CH_0_WR_RATE_LIM_EN_VAL_MASK                             0x1
+
+/* DMA_CH_0_WR_RATE_LIM_RST_TOKEN */
+#define DMA_CH_0_WR_RATE_LIM_RST_TOKEN_VAL_SHIFT                     0
+#define DMA_CH_0_WR_RATE_LIM_RST_TOKEN_VAL_MASK                      0xFFFF
+
+/* DMA_CH_0_WR_RATE_LIM_SAT */
+#define DMA_CH_0_WR_RATE_LIM_SAT_VAL_SHIFT                           0
+#define DMA_CH_0_WR_RATE_LIM_SAT_VAL_MASK                            0xFFFF
+
+/* DMA_CH_0_WR_RATE_LIM_TOUT */
+#define DMA_CH_0_WR_RATE_LIM_TOUT_VAL_SHIFT                          0
+#define DMA_CH_0_WR_RATE_LIM_TOUT_VAL_MASK                           0x7FFFFFFF
+
+/* DMA_CH_0_CFG2 */
+#define DMA_CH_0_CFG2_FORCE_WORD_SHIFT                               0
+#define DMA_CH_0_CFG2_FORCE_WORD_MASK                                0x1
+
+/* DMA_CH_0_TDMA_CTL */
+#define DMA_CH_0_TDMA_CTL_DTYPE_SHIFT                                0
+#define DMA_CH_0_TDMA_CTL_DTYPE_MASK                                 0x7
+
+/* DMA_CH_0_TDMA_SRC_BASE_ADDR_LO */
+#define DMA_CH_0_TDMA_SRC_BASE_ADDR_LO_VAL_SHIFT                     0
+#define DMA_CH_0_TDMA_SRC_BASE_ADDR_LO_VAL_MASK                      0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_BASE_ADDR_HI */
+#define DMA_CH_0_TDMA_SRC_BASE_ADDR_HI_VAL_SHIFT                     0
+#define DMA_CH_0_TDMA_SRC_BASE_ADDR_HI_VAL_MASK                      0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_BASE_0 */
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_0_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_0_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_SIZE_0 */
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_0_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_0_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_0 */
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_0_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_0_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_START_OFFSET_0 */
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_0_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_0_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_STRIDE_0 */
+#define DMA_CH_0_TDMA_SRC_STRIDE_0_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_SRC_STRIDE_0_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_BASE_1 */
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_1_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_1_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_SIZE_1 */
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_1_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_1_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_1 */
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_1_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_1_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_START_OFFSET_1 */
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_1_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_1_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_STRIDE_1 */
+#define DMA_CH_0_TDMA_SRC_STRIDE_1_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_SRC_STRIDE_1_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_BASE_2 */
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_2_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_2_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_SIZE_2 */
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_2_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_2_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_2 */
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_2_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_2_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_START_OFFSET_2 */
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_2_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_2_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_STRIDE_2 */
+#define DMA_CH_0_TDMA_SRC_STRIDE_2_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_SRC_STRIDE_2_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_BASE_3 */
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_3_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_3_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_SIZE_3 */
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_3_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_3_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_3 */
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_3_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_3_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_START_OFFSET_3 */
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_3_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_3_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_STRIDE_3 */
+#define DMA_CH_0_TDMA_SRC_STRIDE_3_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_SRC_STRIDE_3_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_BASE_4 */
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_4_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_BASE_4_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_ROI_SIZE_4 */
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_4_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_SRC_ROI_SIZE_4_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_4 */
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_4_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_SRC_VALID_ELEMENTS_4_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_START_OFFSET_4 */
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_4_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_SRC_START_OFFSET_4_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_SRC_STRIDE_4 */
+#define DMA_CH_0_TDMA_SRC_STRIDE_4_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_SRC_STRIDE_4_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_BASE_ADDR_LO */
+#define DMA_CH_0_TDMA_DST_BASE_ADDR_LO_VAL_SHIFT                     0
+#define DMA_CH_0_TDMA_DST_BASE_ADDR_LO_VAL_MASK                      0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_BASE_ADDR_HI */
+#define DMA_CH_0_TDMA_DST_BASE_ADDR_HI_VAL_SHIFT                     0
+#define DMA_CH_0_TDMA_DST_BASE_ADDR_HI_VAL_MASK                      0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_BASE_0 */
+#define DMA_CH_0_TDMA_DST_ROI_BASE_0_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_BASE_0_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_SIZE_0 */
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_0_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_0_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_VALID_ELEMENTS_0 */
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_0_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_0_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_START_OFFSET_0 */
+#define DMA_CH_0_TDMA_DST_START_OFFSET_0_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_DST_START_OFFSET_0_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_STRIDE_0 */
+#define DMA_CH_0_TDMA_DST_STRIDE_0_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_DST_STRIDE_0_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_BASE_1 */
+#define DMA_CH_0_TDMA_DST_ROI_BASE_1_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_BASE_1_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_SIZE_1 */
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_1_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_1_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_VALID_ELEMENTS_1 */
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_1_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_1_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_START_OFFSET_1 */
+#define DMA_CH_0_TDMA_DST_START_OFFSET_1_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_DST_START_OFFSET_1_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_STRIDE_1 */
+#define DMA_CH_0_TDMA_DST_STRIDE_1_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_DST_STRIDE_1_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_BASE_2 */
+#define DMA_CH_0_TDMA_DST_ROI_BASE_2_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_BASE_2_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_SIZE_2 */
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_2_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_2_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_VALID_ELEMENTS_2 */
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_2_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_2_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_START_OFFSET_2 */
+#define DMA_CH_0_TDMA_DST_START_OFFSET_2_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_DST_START_OFFSET_2_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_STRIDE_2 */
+#define DMA_CH_0_TDMA_DST_STRIDE_2_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_DST_STRIDE_2_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_BASE_3 */
+#define DMA_CH_0_TDMA_DST_ROI_BASE_3_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_BASE_3_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_SIZE_3 */
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_3_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_3_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_VALID_ELEMENTS_3 */
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_3_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_3_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_START_OFFSET_3 */
+#define DMA_CH_0_TDMA_DST_START_OFFSET_3_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_DST_START_OFFSET_3_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_STRIDE_3 */
+#define DMA_CH_0_TDMA_DST_STRIDE_3_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_DST_STRIDE_3_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_BASE_4 */
+#define DMA_CH_0_TDMA_DST_ROI_BASE_4_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_BASE_4_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_ROI_SIZE_4 */
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_4_VAL_SHIFT                       0
+#define DMA_CH_0_TDMA_DST_ROI_SIZE_4_VAL_MASK                        0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_VALID_ELEMENTS_4 */
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_4_VAL_SHIFT                 0
+#define DMA_CH_0_TDMA_DST_VALID_ELEMENTS_4_VAL_MASK                  0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_START_OFFSET_4 */
+#define DMA_CH_0_TDMA_DST_START_OFFSET_4_VAL_SHIFT                   0
+#define DMA_CH_0_TDMA_DST_START_OFFSET_4_VAL_MASK                    0xFFFFFFFF
+
+/* DMA_CH_0_TDMA_DST_STRIDE_4 */
+#define DMA_CH_0_TDMA_DST_STRIDE_4_VAL_SHIFT                         0
+#define DMA_CH_0_TDMA_DST_STRIDE_4_VAL_MASK                          0xFFFFFFFF
+
+/* DMA_CH_0_MEM_INIT_BUSY */
+#define DMA_CH_0_MEM_INIT_BUSY_SBC_DATA_SHIFT                        0
+#define DMA_CH_0_MEM_INIT_BUSY_SBC_DATA_MASK                         0xFF
+#define DMA_CH_0_MEM_INIT_BUSY_SBC_MD_SHIFT                          8
+#define DMA_CH_0_MEM_INIT_BUSY_SBC_MD_MASK                           0x100
+
+#endif /* ASIC_REG_DMA_CH_0_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 506e71e201e1..19b0f0ef1d0b 100644
--- a/drivers/misc/habanalabs/include/goya/asic_reg/goya_regs.h
+++ b/drivers/misc/habanalabs/include/goya/asic_reg/goya_regs.h
@@ -88,6 +88,7 @@
 #include "psoc_global_conf_masks.h"
 #include "dma_macro_masks.h"
 #include "dma_qm_0_masks.h"
+#include "dma_ch_0_masks.h"
 #include "tpc0_qm_masks.h"
 #include "tpc0_cmdq_masks.h"
 #include "mme_qm_masks.h"
diff --git a/drivers/misc/habanalabs/memory.c b/drivers/misc/habanalabs/memory.c
index 693877e37fd8..42d237cae1dc 100644
--- a/drivers/misc/habanalabs/memory.c
+++ b/drivers/misc/habanalabs/memory.c
@@ -1657,17 +1657,10 @@ int hl_vm_init(struct hl_device *hdev)
 	struct hl_vm *vm = &hdev->vm;
 	int rc;
 
-	rc = hl_mmu_init(hdev);
-	if (rc) {
-		dev_err(hdev->dev, "Failed to init MMU\n");
-		return rc;
-	}
-
 	vm->dram_pg_pool = gen_pool_create(__ffs(prop->dram_page_size), -1);
 	if (!vm->dram_pg_pool) {
 		dev_err(hdev->dev, "Failed to create dram page pool\n");
-		rc = -ENOMEM;
-		goto pool_create_err;
+		return -ENOMEM;
 	}
 
 	kref_init(&vm->dram_pg_pool_refcount);
@@ -1693,8 +1686,6 @@ int hl_vm_init(struct hl_device *hdev)
 
 pool_add_err:
 	gen_pool_destroy(vm->dram_pg_pool);
-pool_create_err:
-	hl_mmu_fini(hdev);
 
 	return rc;
 }
@@ -1724,7 +1715,5 @@ void hl_vm_fini(struct hl_device *hdev)
 		dev_warn(hdev->dev, "dram_pg_pool was not destroyed on %s\n",
 				__func__);
 
-	hl_mmu_fini(hdev);
-
 	vm->init_done = false;
 }
diff --git a/drivers/misc/habanalabs/mmu.c b/drivers/misc/habanalabs/mmu.c
index 10aee3141444..176c315836f1 100644
--- a/drivers/misc/habanalabs/mmu.c
+++ b/drivers/misc/habanalabs/mmu.c
@@ -241,8 +241,9 @@ static int dram_default_mapping_init(struct hl_ctx *ctx)
 		hop2_pte_addr, hop3_pte_addr, pte_val;
 	int rc, i, j, hop3_allocated = 0;
 
-	if (!hdev->dram_supports_virtual_memory ||
-			!hdev->dram_default_page_mapping)
+	if ((!hdev->dram_supports_virtual_memory) ||
+			(!hdev->dram_default_page_mapping) ||
+			(ctx->asid == HL_KERNEL_ASID_ID))
 		return 0;
 
 	num_of_hop3 = prop->dram_size_for_default_page_mapping;
@@ -340,8 +341,9 @@ static void dram_default_mapping_fini(struct hl_ctx *ctx)
 		hop2_pte_addr, hop3_pte_addr;
 	int i, j;
 
-	if (!hdev->dram_supports_virtual_memory ||
-			!hdev->dram_default_page_mapping)
+	if ((!hdev->dram_supports_virtual_memory) ||
+			(!hdev->dram_default_page_mapping) ||
+			(ctx->asid == HL_KERNEL_ASID_ID))
 		return;
 
 	num_of_hop3 = prop->dram_size_for_default_page_mapping;
@@ -385,12 +387,8 @@ static void dram_default_mapping_fini(struct hl_ctx *ctx)
  * @hdev: habanalabs device structure.
  *
  * This function does the following:
- * - Allocate max_asid zeroed hop0 pgts so no mapping is available.
- * - Enable MMU in H/W.
- * - Invalidate the MMU cache.
  * - Create a pool of pages for pgt_infos.
- *
- * This function depends on DMA QMAN to be working!
+ * - Create a shadow table for pgt
  *
  * Return: 0 for success, non-zero for failure.
  */
@@ -915,6 +913,10 @@ int hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, u32 page_size)
 		return -EFAULT;
 	}
 
+	WARN_ONCE((phys_addr & (real_page_size - 1)),
+		"Mapping 0x%llx with page size of 0x%x is erroneous! Address must be divisible by page size",
+		phys_addr, real_page_size);
+
 	npages = page_size / real_page_size;
 	real_virt_addr = virt_addr;
 	real_phys_addr = phys_addr;
diff --git a/drivers/misc/habanalabs/pci.c b/drivers/misc/habanalabs/pci.c
index 0e78a04d63f4..c98d88c7a5c6 100644
--- a/drivers/misc/habanalabs/pci.c
+++ b/drivers/misc/habanalabs/pci.c
@@ -10,6 +10,8 @@
 
 #include <linux/pci.h>
 
+#define HL_PLDM_PCI_ELBI_TIMEOUT_MSEC	(HL_PCI_ELBI_TIMEOUT_MSEC * 10)
+
 /**
  * hl_pci_bars_map() - Map PCI BARs.
  * @hdev: Pointer to hl_device structure.
@@ -88,8 +90,14 @@ static int hl_pci_elbi_write(struct hl_device *hdev, u64 addr, u32 data)
 {
 	struct pci_dev *pdev = hdev->pdev;
 	ktime_t timeout;
+	u64 msec;
 	u32 val;
 
+	if (hdev->pldm)
+		msec = HL_PLDM_PCI_ELBI_TIMEOUT_MSEC;
+	else
+		msec = HL_PCI_ELBI_TIMEOUT_MSEC;
+
 	/* Clear previous status */
 	pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_STS, 0);
 
@@ -98,7 +106,7 @@ static int hl_pci_elbi_write(struct hl_device *hdev, u64 addr, u32 data)
 	pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_CTRL,
 				PCI_CONFIG_ELBI_CTRL_WRITE);
 
-	timeout = ktime_add_ms(ktime_get(), 10);
+	timeout = ktime_add_ms(ktime_get(), msec);
 	for (;;) {
 		pci_read_config_dword(pdev, mmPCI_CONFIG_ELBI_STS, &val);
 		if (val & PCI_CONFIG_ELBI_STS_MASK)
diff --git a/drivers/misc/habanalabs/sysfs.c b/drivers/misc/habanalabs/sysfs.c
index c900ab15cceb..25eb46d29d88 100644
--- a/drivers/misc/habanalabs/sysfs.c
+++ b/drivers/misc/habanalabs/sysfs.c
@@ -328,10 +328,6 @@ static ssize_t pci_addr_show(struct device *dev, struct device_attribute *attr,
 {
 	struct hl_device *hdev = dev_get_drvdata(dev);
 
-	/* Use dummy, fixed address for simulator */
-	if (!hdev->pdev)
-		return sprintf(buf, "0000:%02d:00.0\n", hdev->id);
-
 	return sprintf(buf, "%04x:%02x:%02x.%x\n",
 			pci_domain_nr(hdev->pdev->bus),
 			hdev->pdev->bus->number,
diff --git a/drivers/misc/isl29003.c b/drivers/misc/isl29003.c
index 3431a825f24e..c12406f610d5 100644
--- a/drivers/misc/isl29003.c
+++ b/drivers/misc/isl29003.c
@@ -3,7 +3,7 @@
  *  isl29003.c - Linux kernel module for
  * 	Intersil ISL29003 ambient light sensor
  *
- *  See file:Documentation/misc-devices/isl29003
+ *  See file:Documentation/misc-devices/isl29003.rst
  *
  *  Copyright (c) 2009 Daniel Mack <daniel@caiaq.de>
  *
@@ -377,7 +377,7 @@ static int isl29003_init_client(struct i2c_client *client)
 static int isl29003_probe(struct i2c_client *client,
 				    const struct i2c_device_id *id)
 {
-	struct i2c_adapter *adapter = to_i2c_adapter(client->dev.parent);
+	struct i2c_adapter *adapter = client->adapter;
 	struct isl29003_data *data;
 	int err = 0;
 
diff --git a/drivers/misc/lis3lv02d/Kconfig b/drivers/misc/lis3lv02d/Kconfig
index 4cfad45229c8..bb2fec4b5880 100644
--- a/drivers/misc/lis3lv02d/Kconfig
+++ b/drivers/misc/lis3lv02d/Kconfig
@@ -7,7 +7,6 @@ config SENSORS_LIS3_SPI
 	tristate "STMicroeletronics LIS3LV02Dx three-axis digital accelerometer (SPI)"
 	depends on !ACPI && SPI_MASTER && INPUT
 	select SENSORS_LIS3LV02D
-	default n
 	help
 	  This driver provides support for the LIS3LV02Dx accelerometer connected
 	  via SPI. The accelerometer data is readable via
@@ -24,7 +23,6 @@ config SENSORS_LIS3_I2C
 	tristate "STMicroeletronics LIS3LV02Dx three-axis digital accelerometer (I2C)"
 	depends on I2C && INPUT
 	select SENSORS_LIS3LV02D
-	default n
 	help
 	  This driver provides support for the LIS3LV02Dx accelerometer connected
 	  via I2C. The accelerometer data is readable via
diff --git a/drivers/misc/lkdtm/Makefile b/drivers/misc/lkdtm/Makefile
index 951c984de61a..fb10eafe9bde 100644
--- a/drivers/misc/lkdtm/Makefile
+++ b/drivers/misc/lkdtm/Makefile
@@ -15,8 +15,7 @@ KCOV_INSTRUMENT_rodata.o	:= n
 
 OBJCOPYFLAGS :=
 OBJCOPYFLAGS_rodata_objcopy.o	:= \
-			--set-section-flags .text=alloc,readonly \
-			--rename-section .text=.rodata
+			--rename-section .text=.rodata,alloc,readonly,load
 targets += rodata.o rodata_objcopy.o
 $(obj)/rodata_objcopy.o: $(obj)/rodata.o FORCE
 	$(call if_changed,objcopy)
diff --git a/drivers/misc/lkdtm/bugs.c b/drivers/misc/lkdtm/bugs.c
index d9fcfd3b5af0..1606658b9b7e 100644
--- a/drivers/misc/lkdtm/bugs.c
+++ b/drivers/misc/lkdtm/bugs.c
@@ -266,3 +266,69 @@ void lkdtm_STACK_GUARD_PAGE_TRAILING(void)
 
 	pr_err("FAIL: accessed page after stack!\n");
 }
+
+void lkdtm_UNSET_SMEP(void)
+{
+#ifdef CONFIG_X86_64
+#define MOV_CR4_DEPTH	64
+	void (*direct_write_cr4)(unsigned long val);
+	unsigned char *insn;
+	unsigned long cr4;
+	int i;
+
+	cr4 = native_read_cr4();
+
+	if ((cr4 & X86_CR4_SMEP) != X86_CR4_SMEP) {
+		pr_err("FAIL: SMEP not in use\n");
+		return;
+	}
+	cr4 &= ~(X86_CR4_SMEP);
+
+	pr_info("trying to clear SMEP normally\n");
+	native_write_cr4(cr4);
+	if (cr4 == native_read_cr4()) {
+		pr_err("FAIL: pinning SMEP failed!\n");
+		cr4 |= X86_CR4_SMEP;
+		pr_info("restoring SMEP\n");
+		native_write_cr4(cr4);
+		return;
+	}
+	pr_info("ok: SMEP did not get cleared\n");
+
+	/*
+	 * To test the post-write pinning verification we need to call
+	 * directly into the middle of native_write_cr4() where the
+	 * cr4 write happens, skipping any pinning. This searches for
+	 * the cr4 writing instruction.
+	 */
+	insn = (unsigned char *)native_write_cr4;
+	for (i = 0; i < MOV_CR4_DEPTH; i++) {
+		/* mov %rdi, %cr4 */
+		if (insn[i] == 0x0f && insn[i+1] == 0x22 && insn[i+2] == 0xe7)
+			break;
+		/* mov %rdi,%rax; mov %rax, %cr4 */
+		if (insn[i]   == 0x48 && insn[i+1] == 0x89 &&
+		    insn[i+2] == 0xf8 && insn[i+3] == 0x0f &&
+		    insn[i+4] == 0x22 && insn[i+5] == 0xe0)
+			break;
+	}
+	if (i >= MOV_CR4_DEPTH) {
+		pr_info("ok: cannot locate cr4 writing call gadget\n");
+		return;
+	}
+	direct_write_cr4 = (void *)(insn + i);
+
+	pr_info("trying to clear SMEP with call gadget\n");
+	direct_write_cr4(cr4);
+	if (native_read_cr4() & X86_CR4_SMEP) {
+		pr_info("ok: SMEP removal was reverted\n");
+	} else {
+		pr_err("FAIL: cleared SMEP not detected!\n");
+		cr4 |= X86_CR4_SMEP;
+		pr_info("restoring SMEP\n");
+		native_write_cr4(cr4);
+	}
+#else
+	pr_err("FAIL: this test is x86_64-only\n");
+#endif
+}
diff --git a/drivers/misc/lkdtm/core.c b/drivers/misc/lkdtm/core.c
index bba49abb6750..756794ac8fd8 100644
--- a/drivers/misc/lkdtm/core.c
+++ b/drivers/misc/lkdtm/core.c
@@ -114,6 +114,7 @@ static const struct crashtype crashtypes[] = {
 	CRASHTYPE(CORRUPT_USER_DS),
 	CRASHTYPE(STACK_GUARD_PAGE_LEADING),
 	CRASHTYPE(STACK_GUARD_PAGE_TRAILING),
+	CRASHTYPE(UNSET_SMEP),
 	CRASHTYPE(UNALIGNED_LOAD_STORE_WRITE),
 	CRASHTYPE(OVERWRITE_ALLOCATION),
 	CRASHTYPE(WRITE_AFTER_FREE),
diff --git a/drivers/misc/lkdtm/lkdtm.h b/drivers/misc/lkdtm/lkdtm.h
index 23dc565b4307..bbcd370786d4 100644
--- a/drivers/misc/lkdtm/lkdtm.h
+++ b/drivers/misc/lkdtm/lkdtm.h
@@ -26,6 +26,7 @@ void lkdtm_CORRUPT_LIST_DEL(void);
 void lkdtm_CORRUPT_USER_DS(void);
 void lkdtm_STACK_GUARD_PAGE_LEADING(void);
 void lkdtm_STACK_GUARD_PAGE_TRAILING(void);
+void lkdtm_UNSET_SMEP(void);
 
 /* lkdtm_heap.c */
 void lkdtm_OVERWRITE_ALLOCATION(void);
diff --git a/drivers/misc/mei/debugfs.c b/drivers/misc/mei/debugfs.c
index 0970142bcace..47cfd5005e1b 100644
--- a/drivers/misc/mei/debugfs.c
+++ b/drivers/misc/mei/debugfs.c
@@ -8,6 +8,7 @@
 #include <linux/kernel.h>
 #include <linux/device.h>
 #include <linux/debugfs.h>
+#include <linux/seq_file.h>
 
 #include <linux/mei.h>
 
@@ -15,104 +16,56 @@
 #include "client.h"
 #include "hw.h"
 
-static ssize_t mei_dbgfs_read_meclients(struct file *fp, char __user *ubuf,
-					size_t cnt, loff_t *ppos)
+static int mei_dbgfs_meclients_show(struct seq_file *m, void *unused)
 {
-	struct mei_device *dev = fp->private_data;
+	struct mei_device *dev = m->private;
 	struct mei_me_client *me_cl;
-	size_t bufsz = 1;
-	char *buf;
 	int i = 0;
-	int pos = 0;
-	int ret;
 
-#define HDR \
-"  |id|fix|         UUID                       |con|msg len|sb|refc|\n"
+	if (!dev)
+		return -ENODEV;
 
 	down_read(&dev->me_clients_rwsem);
-	list_for_each_entry(me_cl, &dev->me_clients, list)
-		bufsz++;
 
-	bufsz *= sizeof(HDR) + 1;
-	buf = kzalloc(bufsz, GFP_KERNEL);
-	if (!buf) {
-		up_read(&dev->me_clients_rwsem);
-		return -ENOMEM;
-	}
-
-	pos += scnprintf(buf + pos, bufsz - pos, HDR);
-#undef HDR
+	seq_puts(m, "  |id|fix|         UUID                       |con|msg len|sb|refc|\n");
 
 	/*  if the driver is not enabled the list won't be consistent */
 	if (dev->dev_state != MEI_DEV_ENABLED)
 		goto out;
 
 	list_for_each_entry(me_cl, &dev->me_clients, list) {
-
-		if (mei_me_cl_get(me_cl)) {
-			pos += scnprintf(buf + pos, bufsz - pos,
-				"%2d|%2d|%3d|%pUl|%3d|%7d|%2d|%4d|\n",
-				i++, me_cl->client_id,
-				me_cl->props.fixed_address,
-				&me_cl->props.protocol_name,
-				me_cl->props.max_number_of_connections,
-				me_cl->props.max_msg_length,
-				me_cl->props.single_recv_buf,
-				kref_read(&me_cl->refcnt));
-
-			mei_me_cl_put(me_cl);
-		}
+		if (!mei_me_cl_get(me_cl))
+			continue;
+
+		seq_printf(m, "%2d|%2d|%3d|%pUl|%3d|%7d|%2d|%4d|\n",
+			   i++, me_cl->client_id,
+			   me_cl->props.fixed_address,
+			   &me_cl->props.protocol_name,
+			   me_cl->props.max_number_of_connections,
+			   me_cl->props.max_msg_length,
+			   me_cl->props.single_recv_buf,
+			   kref_read(&me_cl->refcnt));
+		mei_me_cl_put(me_cl);
 	}
 
 out:
 	up_read(&dev->me_clients_rwsem);
-	ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, pos);
-	kfree(buf);
-	return ret;
+	return 0;
 }
+DEFINE_SHOW_ATTRIBUTE(mei_dbgfs_meclients);
 
-static const struct file_operations mei_dbgfs_fops_meclients = {
-	.open = simple_open,
-	.read = mei_dbgfs_read_meclients,
-	.llseek = generic_file_llseek,
-};
-
-static ssize_t mei_dbgfs_read_active(struct file *fp, char __user *ubuf,
-					size_t cnt, loff_t *ppos)
+static int mei_dbgfs_active_show(struct seq_file *m, void *unused)
 {
-	struct mei_device *dev = fp->private_data;
+	struct mei_device *dev = m->private;
 	struct mei_cl *cl;
-	size_t bufsz = 1;
-	char *buf;
 	int i = 0;
-	int pos = 0;
-	int ret;
-
-#define HDR "   |me|host|state|rd|wr|wrq\n"
 
 	if (!dev)
 		return -ENODEV;
 
 	mutex_lock(&dev->device_lock);
 
-	/*
-	 * if the driver is not enabled the list won't be consistent,
-	 * we output empty table
-	 */
-	if (dev->dev_state == MEI_DEV_ENABLED)
-		list_for_each_entry(cl, &dev->file_list, link)
-			bufsz++;
-
-	bufsz *= sizeof(HDR) + 1;
-
-	buf = kzalloc(bufsz, GFP_KERNEL);
-	if  (!buf) {
-		mutex_unlock(&dev->device_lock);
-		return -ENOMEM;
-	}
-
-	pos += scnprintf(buf + pos, bufsz - pos, HDR);
-#undef HDR
+	seq_puts(m, "   |me|host|state|rd|wr|wrq\n");
 
 	/*  if the driver is not enabled the list won't be consistent */
 	if (dev->dev_state != MEI_DEV_ENABLED)
@@ -120,76 +73,44 @@ static ssize_t mei_dbgfs_read_active(struct file *fp, char __user *ubuf,
 
 	list_for_each_entry(cl, &dev->file_list, link) {
 
-		pos += scnprintf(buf + pos, bufsz - pos,
-			"%3d|%2d|%4d|%5d|%2d|%2d|%3u\n",
-			i, mei_cl_me_id(cl), cl->host_client_id, cl->state,
-			!list_empty(&cl->rd_completed), cl->writing_state,
-			cl->tx_cb_queued);
+		seq_printf(m, "%3d|%2d|%4d|%5d|%2d|%2d|%3u\n",
+			   i, mei_cl_me_id(cl), cl->host_client_id, cl->state,
+			   !list_empty(&cl->rd_completed), cl->writing_state,
+			   cl->tx_cb_queued);
 		i++;
 	}
 out:
 	mutex_unlock(&dev->device_lock);
-	ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, pos);
-	kfree(buf);
-	return ret;
+	return 0;
 }
+DEFINE_SHOW_ATTRIBUTE(mei_dbgfs_active);
 
-static const struct file_operations mei_dbgfs_fops_active = {
-	.open = simple_open,
-	.read = mei_dbgfs_read_active,
-	.llseek = generic_file_llseek,
-};
-
-static ssize_t mei_dbgfs_read_devstate(struct file *fp, char __user *ubuf,
-					size_t cnt, loff_t *ppos)
+static int mei_dbgfs_devstate_show(struct seq_file *m, void *unused)
 {
-	struct mei_device *dev = fp->private_data;
-	const size_t bufsz = 1024;
-	char *buf = kzalloc(bufsz, GFP_KERNEL);
-	int pos = 0;
-	int ret;
-
-	if  (!buf)
-		return -ENOMEM;
+	struct mei_device *dev = m->private;
 
-	pos += scnprintf(buf + pos, bufsz - pos, "dev: %s\n",
-			mei_dev_state_str(dev->dev_state));
-	pos += scnprintf(buf + pos, bufsz - pos, "hbm: %s\n",
-			mei_hbm_state_str(dev->hbm_state));
+	seq_printf(m, "dev: %s\n", mei_dev_state_str(dev->dev_state));
+	seq_printf(m, "hbm: %s\n", mei_hbm_state_str(dev->hbm_state));
 
 	if (dev->hbm_state >= MEI_HBM_ENUM_CLIENTS &&
 	    dev->hbm_state <= MEI_HBM_STARTED) {
-		pos += scnprintf(buf + pos, bufsz - pos, "hbm features:\n");
-		pos += scnprintf(buf + pos, bufsz - pos, "\tPG: %01d\n",
-				 dev->hbm_f_pg_supported);
-		pos += scnprintf(buf + pos, bufsz - pos, "\tDC: %01d\n",
-				 dev->hbm_f_dc_supported);
-		pos += scnprintf(buf + pos, bufsz - pos, "\tIE: %01d\n",
-				 dev->hbm_f_ie_supported);
-		pos += scnprintf(buf + pos, bufsz - pos, "\tDOT: %01d\n",
-				 dev->hbm_f_dot_supported);
-		pos += scnprintf(buf + pos, bufsz - pos, "\tEV: %01d\n",
-				 dev->hbm_f_ev_supported);
-		pos += scnprintf(buf + pos, bufsz - pos, "\tFA: %01d\n",
-				 dev->hbm_f_fa_supported);
-		pos += scnprintf(buf + pos, bufsz - pos, "\tOS: %01d\n",
-				 dev->hbm_f_os_supported);
-		pos += scnprintf(buf + pos, bufsz - pos, "\tDR: %01d\n",
-				 dev->hbm_f_dr_supported);
+		seq_puts(m, "hbm features:\n");
+		seq_printf(m, "\tPG: %01d\n", dev->hbm_f_pg_supported);
+		seq_printf(m, "\tDC: %01d\n", dev->hbm_f_dc_supported);
+		seq_printf(m, "\tIE: %01d\n", dev->hbm_f_ie_supported);
+		seq_printf(m, "\tDOT: %01d\n", dev->hbm_f_dot_supported);
+		seq_printf(m, "\tEV: %01d\n", dev->hbm_f_ev_supported);
+		seq_printf(m, "\tFA: %01d\n", dev->hbm_f_fa_supported);
+		seq_printf(m, "\tOS: %01d\n", dev->hbm_f_os_supported);
+		seq_printf(m, "\tDR: %01d\n", dev->hbm_f_dr_supported);
 	}
 
-	pos += scnprintf(buf + pos, bufsz - pos, "pg:  %s, %s\n",
-			mei_pg_is_enabled(dev) ? "ENABLED" : "DISABLED",
-			mei_pg_state_str(mei_pg_state(dev)));
-	ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, pos);
-	kfree(buf);
-	return ret;
+	seq_printf(m, "pg:  %s, %s\n",
+		   mei_pg_is_enabled(dev) ? "ENABLED" : "DISABLED",
+		   mei_pg_state_str(mei_pg_state(dev)));
+	return 0;
 }
-static const struct file_operations mei_dbgfs_fops_devstate = {
-	.open = simple_open,
-	.read = mei_dbgfs_read_devstate,
-	.llseek = generic_file_llseek,
-};
+DEFINE_SHOW_ATTRIBUTE(mei_dbgfs_devstate);
 
 static ssize_t mei_dbgfs_write_allow_fa(struct file *file,
 					const char __user *user_buf,
@@ -208,7 +129,7 @@ static ssize_t mei_dbgfs_write_allow_fa(struct file *file,
 	return ret;
 }
 
-static const struct file_operations mei_dbgfs_fops_allow_fa = {
+static const struct file_operations mei_dbgfs_allow_fa_fops = {
 	.open = simple_open,
 	.read = debugfs_read_file_bool,
 	.write = mei_dbgfs_write_allow_fa,
@@ -247,26 +168,26 @@ int mei_dbgfs_register(struct mei_device *dev, const char *name)
 	dev->dbgfs_dir = dir;
 
 	f = debugfs_create_file("meclients", S_IRUSR, dir,
-				dev, &mei_dbgfs_fops_meclients);
+				dev, &mei_dbgfs_meclients_fops);
 	if (!f) {
 		dev_err(dev->dev, "meclients: registration failed\n");
 		goto err;
 	}
 	f = debugfs_create_file("active", S_IRUSR, dir,
-				dev, &mei_dbgfs_fops_active);
+				dev, &mei_dbgfs_active_fops);
 	if (!f) {
 		dev_err(dev->dev, "active: registration failed\n");
 		goto err;
 	}
 	f = debugfs_create_file("devstate", S_IRUSR, dir,
-				dev, &mei_dbgfs_fops_devstate);
+				dev, &mei_dbgfs_devstate_fops);
 	if (!f) {
 		dev_err(dev->dev, "devstate: registration failed\n");
 		goto err;
 	}
 	f = debugfs_create_file("allow_fixed_address", S_IRUSR | S_IWUSR, dir,
 				&dev->allow_fixed_address,
-				&mei_dbgfs_fops_allow_fa);
+				&mei_dbgfs_allow_fa_fops);
 	if (!f) {
 		dev_err(dev->dev, "allow_fixed_address: registration failed\n");
 		goto err;
@@ -276,4 +197,3 @@ err:
 	mei_dbgfs_deregister(dev);
 	return -ENODEV;
 }
-
diff --git a/drivers/misc/mei/hdcp/mei_hdcp.c b/drivers/misc/mei/hdcp/mei_hdcp.c
index b07000202d4a..ed816939fb32 100644
--- a/drivers/misc/mei/hdcp/mei_hdcp.c
+++ b/drivers/misc/mei/hdcp/mei_hdcp.c
@@ -2,7 +2,7 @@
 /*
  * Copyright © 2019 Intel Corporation
  *
- * Mei_hdcp.c: HDCP client driver for mei bus
+ * mei_hdcp.c: HDCP client driver for mei bus
  *
  * Author:
  * Ramalingam C <ramalingam.c@intel.com>
@@ -11,12 +11,9 @@
 /**
  * DOC: MEI_HDCP Client Driver
  *
- * This is a client driver to the mei_bus to make the HDCP2.2 services of
- * ME FW available for the interested consumers like I915.
- *
- * This module will act as a translation layer between HDCP protocol
- * implementor(I915) and ME FW by translating HDCP2.2 authentication
- * messages to ME FW command payloads and vice versa.
+ * The mei_hdcp driver acts as a translation layer between HDCP 2.2
+ * protocol  implementer (I915) and ME FW by translating HDCP2.2
+ * negotiation messages to ME FW command payloads and vice versa.
  */
 
 #include <linux/module.h>
diff --git a/drivers/misc/mic/scif/scif_main.c b/drivers/misc/mic/scif/scif_main.c
index 490e3bdc1941..e2278bf9f11d 100644
--- a/drivers/misc/mic/scif/scif_main.c
+++ b/drivers/misc/mic/scif/scif_main.c
@@ -133,6 +133,7 @@ static int scif_setup_scifdev(void)
 static void scif_destroy_scifdev(void)
 {
 	kfree(scif_dev);
+	scif_dev = NULL;
 }
 
 static int scif_probe(struct scif_hw_dev *sdev)
diff --git a/drivers/misc/ocxl/Kconfig b/drivers/misc/ocxl/Kconfig
index 7fb6d39d4c5a..1916fa65f2f2 100644
--- a/drivers/misc/ocxl/Kconfig
+++ b/drivers/misc/ocxl/Kconfig
@@ -5,7 +5,6 @@
 
 config OCXL_BASE
 	bool
-	default n
 	select PPC_COPRO_BASE
 
 config OCXL
diff --git a/drivers/misc/ocxl/context.c b/drivers/misc/ocxl/context.c
index bab9c9364184..994563a078eb 100644
--- a/drivers/misc/ocxl/context.c
+++ b/drivers/misc/ocxl/context.c
@@ -69,6 +69,7 @@ static void xsl_fault_error(void *data, u64 addr, u64 dsisr)
 int ocxl_context_attach(struct ocxl_context *ctx, u64 amr, struct mm_struct *mm)
 {
 	int rc;
+	unsigned long pidr = 0;
 
 	// Locks both status & tidr
 	mutex_lock(&ctx->status_mutex);
@@ -77,9 +78,11 @@ int ocxl_context_attach(struct ocxl_context *ctx, u64 amr, struct mm_struct *mm)
 		goto out;
 	}
 
-	rc = ocxl_link_add_pe(ctx->afu->fn->link, ctx->pasid,
-			mm->context.id, ctx->tidr, amr, mm,
-			xsl_fault_error, ctx);
+	if (mm)
+		pidr = mm->context.id;
+
+	rc = ocxl_link_add_pe(ctx->afu->fn->link, ctx->pasid, pidr, ctx->tidr,
+			      amr, mm, xsl_fault_error, ctx);
 	if (rc)
 		goto out;
 
diff --git a/drivers/misc/ocxl/link.c b/drivers/misc/ocxl/link.c
index cce5b0d64505..58d111afd9f6 100644
--- a/drivers/misc/ocxl/link.c
+++ b/drivers/misc/ocxl/link.c
@@ -224,6 +224,17 @@ static irqreturn_t xsl_fault_handler(int irq, void *data)
 		ack_irq(spa, ADDRESS_ERROR);
 		return IRQ_HANDLED;
 	}
+
+	if (!pe_data->mm) {
+		/*
+		 * translation fault from a kernel context - an OpenCAPI
+		 * device tried to access a bad kernel address
+		 */
+		rcu_read_unlock();
+		pr_warn("Unresolved OpenCAPI xsl fault in kernel context\n");
+		ack_irq(spa, ADDRESS_ERROR);
+		return IRQ_HANDLED;
+	}
 	WARN_ON(pe_data->mm->context.id != pid);
 
 	if (mmget_not_zero(pe_data->mm)) {
@@ -523,7 +534,13 @@ int ocxl_link_add_pe(void *link_handle, int pasid, u32 pidr, u32 tidr,
 	pe->amr = cpu_to_be64(amr);
 	pe->software_state = cpu_to_be32(SPA_PE_VALID);
 
-	mm_context_add_copro(mm);
+	/*
+	 * For user contexts, register a copro so that TLBIs are seen
+	 * by the nest MMU. If we have a kernel context, TLBIs are
+	 * already global.
+	 */
+	if (mm)
+		mm_context_add_copro(mm);
 	/*
 	 * Barrier is to make sure PE is visible in the SPA before it
 	 * is used by the device. It also helps with the global TLBI
@@ -546,7 +563,8 @@ int ocxl_link_add_pe(void *link_handle, int pasid, u32 pidr, u32 tidr,
 	 * have a reference on mm_users. Incrementing mm_count solves
 	 * the problem.
 	 */
-	mmgrab(mm);
+	if (mm)
+		mmgrab(mm);
 	trace_ocxl_context_add(current->pid, spa->spa_mem, pasid, pidr, tidr);
 unlock:
 	mutex_unlock(&spa->spa_lock);
@@ -652,8 +670,10 @@ int ocxl_link_remove_pe(void *link_handle, int pasid)
 	if (!pe_data) {
 		WARN(1, "Couldn't find pe data when removing PE\n");
 	} else {
-		mm_context_remove_copro(pe_data->mm);
-		mmdrop(pe_data->mm);
+		if (pe_data->mm) {
+			mm_context_remove_copro(pe_data->mm);
+			mmdrop(pe_data->mm);
+		}
 		kfree_rcu(pe_data, rcu);
 	}
 unlock:
diff --git a/drivers/misc/sgi-xp/xpc_partition.c b/drivers/misc/sgi-xp/xpc_partition.c
index 3eba1c420cc0..782ce95d3f17 100644
--- a/drivers/misc/sgi-xp/xpc_partition.c
+++ b/drivers/misc/sgi-xp/xpc_partition.c
@@ -70,7 +70,7 @@ xpc_get_rsvd_page_pa(int nasid)
 	unsigned long rp_pa = nasid;	/* seed with nasid */
 	size_t len = 0;
 	size_t buf_len = 0;
-	void *buf = buf;
+	void *buf = NULL;
 	void *buf_base = NULL;
 	enum xp_retval (*get_partition_rsvd_page_pa)
 		(void *, u64 *, unsigned long *, size_t *) =
diff --git a/drivers/misc/tsl2550.c b/drivers/misc/tsl2550.c
index 5b7afd6190fe..09db397df287 100644
--- a/drivers/misc/tsl2550.c
+++ b/drivers/misc/tsl2550.c
@@ -336,7 +336,7 @@ static struct i2c_driver tsl2550_driver;
 static int tsl2550_probe(struct i2c_client *client,
 				   const struct i2c_device_id *id)
 {
-	struct i2c_adapter *adapter = to_i2c_adapter(client->dev.parent);
+	struct i2c_adapter *adapter = client->adapter;
 	struct tsl2550_data *data;
 	int *opmode, err = 0;
 
diff --git a/drivers/misc/vmw_balloon.c b/drivers/misc/vmw_balloon.c
index ad807d5a3141..043eed845246 100644
--- a/drivers/misc/vmw_balloon.c
+++ b/drivers/misc/vmw_balloon.c
@@ -28,6 +28,8 @@
 #include <linux/rwsem.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/mount.h>
+#include <linux/balloon_compaction.h>
 #include <linux/vmw_vmci_defs.h>
 #include <linux/vmw_vmci_api.h>
 #include <asm/hypervisor.h>
@@ -38,25 +40,20 @@ MODULE_ALIAS("dmi:*:svnVMware*:*");
 MODULE_ALIAS("vmware_vmmemctl");
 MODULE_LICENSE("GPL");
 
-/*
- * Use __GFP_HIGHMEM to allow pages from HIGHMEM zone. We don't allow wait
- * (__GFP_RECLAIM) for huge page allocations. Use __GFP_NOWARN, to suppress page
- * allocation failure warnings. Disallow access to emergency low-memory pools.
- */
-#define VMW_HUGE_PAGE_ALLOC_FLAGS	(__GFP_HIGHMEM|__GFP_NOWARN|	\
-					 __GFP_NOMEMALLOC)
+static bool __read_mostly vmwballoon_shrinker_enable;
+module_param(vmwballoon_shrinker_enable, bool, 0444);
+MODULE_PARM_DESC(vmwballoon_shrinker_enable,
+	"Enable non-cooperative out-of-memory protection. Disabled by default as it may degrade performance.");
 
-/*
- * Use __GFP_HIGHMEM to allow pages from HIGHMEM zone. We allow lightweight
- * reclamation (__GFP_NORETRY). Use __GFP_NOWARN, to suppress page allocation
- * failure warnings. Disallow access to emergency low-memory pools.
- */
-#define VMW_PAGE_ALLOC_FLAGS		(__GFP_HIGHMEM|__GFP_NOWARN|	\
-					 __GFP_NOMEMALLOC|__GFP_NORETRY)
+/* Delay in seconds after shrink before inflation. */
+#define VMBALLOON_SHRINK_DELAY		(5)
 
 /* Maximum number of refused pages we accumulate during inflation cycle */
 #define VMW_BALLOON_MAX_REFUSED		16
 
+/* Magic number for the balloon mount-point */
+#define BALLOON_VMW_MAGIC		0x0ba11007
+
 /*
  * Hypervisor communication port definitions.
  */
@@ -229,29 +226,26 @@ enum vmballoon_stat_general {
 	VMW_BALLOON_STAT_TIMER,
 	VMW_BALLOON_STAT_DOORBELL,
 	VMW_BALLOON_STAT_RESET,
-	VMW_BALLOON_STAT_LAST = VMW_BALLOON_STAT_RESET
+	VMW_BALLOON_STAT_SHRINK,
+	VMW_BALLOON_STAT_SHRINK_FREE,
+	VMW_BALLOON_STAT_LAST = VMW_BALLOON_STAT_SHRINK_FREE
 };
 
 #define VMW_BALLOON_STAT_NUM		(VMW_BALLOON_STAT_LAST + 1)
 
-
 static DEFINE_STATIC_KEY_TRUE(vmw_balloon_batching);
 static DEFINE_STATIC_KEY_FALSE(balloon_stat_enabled);
 
 struct vmballoon_ctl {
 	struct list_head pages;
 	struct list_head refused_pages;
+	struct list_head prealloc_pages;
 	unsigned int n_refused_pages;
 	unsigned int n_pages;
 	enum vmballoon_page_size_type page_size;
 	enum vmballoon_op op;
 };
 
-struct vmballoon_page_size {
-	/* list of reserved physical pages */
-	struct list_head pages;
-};
-
 /**
  * struct vmballoon_batch_entry - a batch entry for lock or unlock.
  *
@@ -266,8 +260,6 @@ struct vmballoon_batch_entry {
 } __packed;
 
 struct vmballoon {
-	struct vmballoon_page_size page_sizes[VMW_BALLOON_NUM_PAGE_SIZES];
-
 	/**
 	 * @max_page_size: maximum supported page size for ballooning.
 	 *
@@ -340,6 +332,15 @@ struct vmballoon {
 	 */
 	struct page *page;
 
+	/**
+	 * @shrink_timeout: timeout until the next inflation.
+	 *
+	 * After an shrink event, indicates the time in jiffies after which
+	 * inflation is allowed again. Can be written concurrently with reads,
+	 * so must use READ_ONCE/WRITE_ONCE when accessing.
+	 */
+	unsigned long shrink_timeout;
+
 	/* statistics */
 	struct vmballoon_stats *stats;
 
@@ -348,9 +349,21 @@ struct vmballoon {
 	struct dentry *dbg_entry;
 #endif
 
+	/**
+	 * @b_dev_info: balloon device information descriptor.
+	 */
+	struct balloon_dev_info b_dev_info;
+
 	struct delayed_work dwork;
 
 	/**
+	 * @huge_pages - list of the inflated 2MB pages.
+	 *
+	 * Protected by @b_dev_info.pages_lock .
+	 */
+	struct list_head huge_pages;
+
+	/**
 	 * @vmci_doorbell.
 	 *
 	 * Protected by @conf_sem.
@@ -368,6 +381,20 @@ struct vmballoon {
 	 * Lock ordering: @conf_sem -> @comm_lock .
 	 */
 	spinlock_t comm_lock;
+
+	/**
+	 * @shrinker: shrinker interface that is used to avoid over-inflation.
+	 */
+	struct shrinker shrinker;
+
+	/**
+	 * @shrinker_registered: whether the shrinker was registered.
+	 *
+	 * The shrinker interface does not handle gracefully the removal of
+	 * shrinker that was not registered before. This indication allows to
+	 * simplify the unregistration process.
+	 */
+	bool shrinker_registered;
 };
 
 static struct vmballoon balloon;
@@ -642,15 +669,25 @@ static int vmballoon_alloc_page_list(struct vmballoon *b,
 	unsigned int i;
 
 	for (i = 0; i < req_n_pages; i++) {
-		if (ctl->page_size == VMW_BALLOON_2M_PAGE)
-			page = alloc_pages(VMW_HUGE_PAGE_ALLOC_FLAGS,
-					   VMW_BALLOON_2M_ORDER);
-		else
-			page = alloc_page(VMW_PAGE_ALLOC_FLAGS);
-
-		/* Update statistics */
-		vmballoon_stats_page_inc(b, VMW_BALLOON_PAGE_STAT_ALLOC,
-					 ctl->page_size);
+		/*
+		 * First check if we happen to have pages that were allocated
+		 * before. This happens when 2MB page rejected during inflation
+		 * by the hypervisor, and then split into 4KB pages.
+		 */
+		if (!list_empty(&ctl->prealloc_pages)) {
+			page = list_first_entry(&ctl->prealloc_pages,
+						struct page, lru);
+			list_del(&page->lru);
+		} else {
+			if (ctl->page_size == VMW_BALLOON_2M_PAGE)
+				page = alloc_pages(__GFP_HIGHMEM|__GFP_NOWARN|
+					__GFP_NOMEMALLOC, VMW_BALLOON_2M_ORDER);
+			else
+				page = balloon_page_alloc();
+
+			vmballoon_stats_page_inc(b, VMW_BALLOON_PAGE_STAT_ALLOC,
+						 ctl->page_size);
+		}
 
 		if (page) {
 			vmballoon_mark_page_offline(page, ctl->page_size);
@@ -896,7 +933,8 @@ static void vmballoon_release_page_list(struct list_head *page_list,
 		__free_pages(page, vmballoon_page_order(page_size));
 	}
 
-	*n_pages = 0;
+	if (n_pages)
+		*n_pages = 0;
 }
 
 
@@ -942,6 +980,10 @@ static int64_t vmballoon_change(struct vmballoon *b)
 	    size - target < vmballoon_page_in_frames(VMW_BALLOON_2M_PAGE))
 		return 0;
 
+	/* If an out-of-memory recently occurred, inflation is disallowed. */
+	if (target > size && time_before(jiffies, READ_ONCE(b->shrink_timeout)))
+		return 0;
+
 	return target - size;
 }
 
@@ -961,9 +1003,22 @@ static void vmballoon_enqueue_page_list(struct vmballoon *b,
 					unsigned int *n_pages,
 					enum vmballoon_page_size_type page_size)
 {
-	struct vmballoon_page_size *page_size_info = &b->page_sizes[page_size];
+	unsigned long flags;
+
+	if (page_size == VMW_BALLOON_4K_PAGE) {
+		balloon_page_list_enqueue(&b->b_dev_info, pages);
+	} else {
+		/*
+		 * Keep the huge pages in a local list which is not available
+		 * for the balloon compaction mechanism.
+		 */
+		spin_lock_irqsave(&b->b_dev_info.pages_lock, flags);
+		list_splice_init(pages, &b->huge_pages);
+		__count_vm_events(BALLOON_INFLATE, *n_pages *
+				  vmballoon_page_in_frames(VMW_BALLOON_2M_PAGE));
+		spin_unlock_irqrestore(&b->b_dev_info.pages_lock, flags);
+	}
 
-	list_splice_init(pages, &page_size_info->pages);
 	*n_pages = 0;
 }
 
@@ -986,19 +1041,58 @@ static void vmballoon_dequeue_page_list(struct vmballoon *b,
 					enum vmballoon_page_size_type page_size,
 					unsigned int n_req_pages)
 {
-	struct vmballoon_page_size *page_size_info = &b->page_sizes[page_size];
 	struct page *page, *tmp;
 	unsigned int i = 0;
+	unsigned long flags;
+
+	/* In the case of 4k pages, use the compaction infrastructure */
+	if (page_size == VMW_BALLOON_4K_PAGE) {
+		*n_pages = balloon_page_list_dequeue(&b->b_dev_info, pages,
+						     n_req_pages);
+		return;
+	}
 
-	list_for_each_entry_safe(page, tmp, &page_size_info->pages, lru) {
+	/* 2MB pages */
+	spin_lock_irqsave(&b->b_dev_info.pages_lock, flags);
+	list_for_each_entry_safe(page, tmp, &b->huge_pages, lru) {
 		list_move(&page->lru, pages);
 		if (++i == n_req_pages)
 			break;
 	}
+
+	__count_vm_events(BALLOON_DEFLATE,
+			  i * vmballoon_page_in_frames(VMW_BALLOON_2M_PAGE));
+	spin_unlock_irqrestore(&b->b_dev_info.pages_lock, flags);
 	*n_pages = i;
 }
 
 /**
+ * vmballoon_split_refused_pages() - Split the 2MB refused pages to 4k.
+ *
+ * If inflation of 2MB pages was denied by the hypervisor, it is likely to be
+ * due to one or few 4KB pages. These 2MB pages may keep being allocated and
+ * then being refused. To prevent this case, this function splits the refused
+ * pages into 4KB pages and adds them into @prealloc_pages list.
+ *
+ * @ctl: pointer for the %struct vmballoon_ctl, which defines the operation.
+ */
+static void vmballoon_split_refused_pages(struct vmballoon_ctl *ctl)
+{
+	struct page *page, *tmp;
+	unsigned int i, order;
+
+	order = vmballoon_page_order(ctl->page_size);
+
+	list_for_each_entry_safe(page, tmp, &ctl->refused_pages, lru) {
+		list_del(&page->lru);
+		split_page(page, order);
+		for (i = 0; i < (1 << order); i++)
+			list_add(&page[i].lru, &ctl->prealloc_pages);
+	}
+	ctl->n_refused_pages = 0;
+}
+
+/**
  * vmballoon_inflate() - Inflate the balloon towards its target size.
  *
  * @b: pointer to the balloon.
@@ -1009,6 +1103,7 @@ static void vmballoon_inflate(struct vmballoon *b)
 	struct vmballoon_ctl ctl = {
 		.pages = LIST_HEAD_INIT(ctl.pages),
 		.refused_pages = LIST_HEAD_INIT(ctl.refused_pages),
+		.prealloc_pages = LIST_HEAD_INIT(ctl.prealloc_pages),
 		.page_size = b->max_page_size,
 		.op = VMW_BALLOON_INFLATE
 	};
@@ -1056,10 +1151,10 @@ static void vmballoon_inflate(struct vmballoon *b)
 				break;
 
 			/*
-			 * Ignore errors from locking as we now switch to 4k
-			 * pages and we might get different errors.
+			 * Split the refused pages to 4k. This will also empty
+			 * the refused pages list.
 			 */
-			vmballoon_release_refused_pages(b, &ctl);
+			vmballoon_split_refused_pages(&ctl);
 			ctl.page_size--;
 		}
 
@@ -1073,6 +1168,8 @@ static void vmballoon_inflate(struct vmballoon *b)
 	 */
 	if (ctl.n_refused_pages != 0)
 		vmballoon_release_refused_pages(b, &ctl);
+
+	vmballoon_release_page_list(&ctl.prealloc_pages, NULL, ctl.page_size);
 }
 
 /**
@@ -1411,6 +1508,90 @@ static void vmballoon_work(struct work_struct *work)
 
 }
 
+/**
+ * vmballoon_shrinker_scan() - deflate the balloon due to memory pressure.
+ * @shrinker: pointer to the balloon shrinker.
+ * @sc: page reclaim information.
+ *
+ * Returns: number of pages that were freed during deflation.
+ */
+static unsigned long vmballoon_shrinker_scan(struct shrinker *shrinker,
+					     struct shrink_control *sc)
+{
+	struct vmballoon *b = &balloon;
+	unsigned long deflated_frames;
+
+	pr_debug("%s - size: %llu", __func__, atomic64_read(&b->size));
+
+	vmballoon_stats_gen_inc(b, VMW_BALLOON_STAT_SHRINK);
+
+	/*
+	 * If the lock is also contended for read, we cannot easily reclaim and
+	 * we bail out.
+	 */
+	if (!down_read_trylock(&b->conf_sem))
+		return 0;
+
+	deflated_frames = vmballoon_deflate(b, sc->nr_to_scan, true);
+
+	vmballoon_stats_gen_add(b, VMW_BALLOON_STAT_SHRINK_FREE,
+				deflated_frames);
+
+	/*
+	 * Delay future inflation for some time to mitigate the situations in
+	 * which balloon continuously grows and shrinks. Use WRITE_ONCE() since
+	 * the access is asynchronous.
+	 */
+	WRITE_ONCE(b->shrink_timeout, jiffies + HZ * VMBALLOON_SHRINK_DELAY);
+
+	up_read(&b->conf_sem);
+
+	return deflated_frames;
+}
+
+/**
+ * vmballoon_shrinker_count() - return the number of ballooned pages.
+ * @shrinker: pointer to the balloon shrinker.
+ * @sc: page reclaim information.
+ *
+ * Returns: number of 4k pages that are allocated for the balloon and can
+ *	    therefore be reclaimed under pressure.
+ */
+static unsigned long vmballoon_shrinker_count(struct shrinker *shrinker,
+					      struct shrink_control *sc)
+{
+	struct vmballoon *b = &balloon;
+
+	return atomic64_read(&b->size);
+}
+
+static void vmballoon_unregister_shrinker(struct vmballoon *b)
+{
+	if (b->shrinker_registered)
+		unregister_shrinker(&b->shrinker);
+	b->shrinker_registered = false;
+}
+
+static int vmballoon_register_shrinker(struct vmballoon *b)
+{
+	int r;
+
+	/* Do nothing if the shrinker is not enabled */
+	if (!vmwballoon_shrinker_enable)
+		return 0;
+
+	b->shrinker.scan_objects = vmballoon_shrinker_scan;
+	b->shrinker.count_objects = vmballoon_shrinker_count;
+	b->shrinker.seeks = DEFAULT_SEEKS;
+
+	r = register_shrinker(&b->shrinker);
+
+	if (r == 0)
+		b->shrinker_registered = true;
+
+	return r;
+}
+
 /*
  * DEBUGFS Interface
  */
@@ -1428,6 +1609,8 @@ static const char * const vmballoon_stat_names[] = {
 	[VMW_BALLOON_STAT_TIMER]		= "timer",
 	[VMW_BALLOON_STAT_DOORBELL]		= "doorbell",
 	[VMW_BALLOON_STAT_RESET]		= "reset",
+	[VMW_BALLOON_STAT_SHRINK]		= "shrink",
+	[VMW_BALLOON_STAT_SHRINK_FREE]		= "shrinkFree"
 };
 
 static int vmballoon_enable_stats(struct vmballoon *b)
@@ -1552,9 +1735,204 @@ static inline void vmballoon_debugfs_exit(struct vmballoon *b)
 
 #endif	/* CONFIG_DEBUG_FS */
 
+
+#ifdef CONFIG_BALLOON_COMPACTION
+
+static struct dentry *vmballoon_mount(struct file_system_type *fs_type,
+				      int flags, const char *dev_name,
+				      void *data)
+{
+	static const struct dentry_operations ops = {
+		.d_dname = simple_dname,
+	};
+
+	return mount_pseudo(fs_type, "balloon-vmware:", NULL, &ops,
+			    BALLOON_VMW_MAGIC);
+}
+
+static struct file_system_type vmballoon_fs = {
+	.name           = "balloon-vmware",
+	.mount          = vmballoon_mount,
+	.kill_sb        = kill_anon_super,
+};
+
+static struct vfsmount *vmballoon_mnt;
+
+/**
+ * vmballoon_migratepage() - migrates a balloon page.
+ * @b_dev_info: balloon device information descriptor.
+ * @newpage: the page to which @page should be migrated.
+ * @page: a ballooned page that should be migrated.
+ * @mode: migration mode, ignored.
+ *
+ * This function is really open-coded, but that is according to the interface
+ * that balloon_compaction provides.
+ *
+ * Return: zero on success, -EAGAIN when migration cannot be performed
+ *	   momentarily, and -EBUSY if migration failed and should be retried
+ *	   with that specific page.
+ */
+static int vmballoon_migratepage(struct balloon_dev_info *b_dev_info,
+				 struct page *newpage, struct page *page,
+				 enum migrate_mode mode)
+{
+	unsigned long status, flags;
+	struct vmballoon *b;
+	int ret;
+
+	b = container_of(b_dev_info, struct vmballoon, b_dev_info);
+
+	/*
+	 * If the semaphore is taken, there is ongoing configuration change
+	 * (i.e., balloon reset), so try again.
+	 */
+	if (!down_read_trylock(&b->conf_sem))
+		return -EAGAIN;
+
+	spin_lock(&b->comm_lock);
+	/*
+	 * We must start by deflating and not inflating, as otherwise the
+	 * hypervisor may tell us that it has enough memory and the new page is
+	 * not needed. Since the old page is isolated, we cannot use the list
+	 * interface to unlock it, as the LRU field is used for isolation.
+	 * Instead, we use the native interface directly.
+	 */
+	vmballoon_add_page(b, 0, page);
+	status = vmballoon_lock_op(b, 1, VMW_BALLOON_4K_PAGE,
+				   VMW_BALLOON_DEFLATE);
+
+	if (status == VMW_BALLOON_SUCCESS)
+		status = vmballoon_status_page(b, 0, &page);
+
+	/*
+	 * If a failure happened, let the migration mechanism know that it
+	 * should not retry.
+	 */
+	if (status != VMW_BALLOON_SUCCESS) {
+		spin_unlock(&b->comm_lock);
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+
+	/*
+	 * The page is isolated, so it is safe to delete it without holding
+	 * @pages_lock . We keep holding @comm_lock since we will need it in a
+	 * second.
+	 */
+	balloon_page_delete(page);
+
+	put_page(page);
+
+	/* Inflate */
+	vmballoon_add_page(b, 0, newpage);
+	status = vmballoon_lock_op(b, 1, VMW_BALLOON_4K_PAGE,
+				   VMW_BALLOON_INFLATE);
+
+	if (status == VMW_BALLOON_SUCCESS)
+		status = vmballoon_status_page(b, 0, &newpage);
+
+	spin_unlock(&b->comm_lock);
+
+	if (status != VMW_BALLOON_SUCCESS) {
+		/*
+		 * A failure happened. While we can deflate the page we just
+		 * inflated, this deflation can also encounter an error. Instead
+		 * we will decrease the size of the balloon to reflect the
+		 * change and report failure.
+		 */
+		atomic64_dec(&b->size);
+		ret = -EBUSY;
+	} else {
+		/*
+		 * Success. Take a reference for the page, and we will add it to
+		 * the list after acquiring the lock.
+		 */
+		get_page(newpage);
+		ret = MIGRATEPAGE_SUCCESS;
+	}
+
+	/* Update the balloon list under the @pages_lock */
+	spin_lock_irqsave(&b->b_dev_info.pages_lock, flags);
+
+	/*
+	 * On inflation success, we already took a reference for the @newpage.
+	 * If we succeed just insert it to the list and update the statistics
+	 * under the lock.
+	 */
+	if (ret == MIGRATEPAGE_SUCCESS) {
+		balloon_page_insert(&b->b_dev_info, newpage);
+		__count_vm_event(BALLOON_MIGRATE);
+	}
+
+	/*
+	 * We deflated successfully, so regardless to the inflation success, we
+	 * need to reduce the number of isolated_pages.
+	 */
+	b->b_dev_info.isolated_pages--;
+	spin_unlock_irqrestore(&b->b_dev_info.pages_lock, flags);
+
+out_unlock:
+	up_read(&b->conf_sem);
+	return ret;
+}
+
+/**
+ * vmballoon_compaction_deinit() - removes compaction related data.
+ *
+ * @b: pointer to the balloon.
+ */
+static void vmballoon_compaction_deinit(struct vmballoon *b)
+{
+	if (!IS_ERR(b->b_dev_info.inode))
+		iput(b->b_dev_info.inode);
+
+	b->b_dev_info.inode = NULL;
+	kern_unmount(vmballoon_mnt);
+	vmballoon_mnt = NULL;
+}
+
+/**
+ * vmballoon_compaction_init() - initialized compaction for the balloon.
+ *
+ * @b: pointer to the balloon.
+ *
+ * If during the initialization a failure occurred, this function does not
+ * perform cleanup. The caller must call vmballoon_compaction_deinit() in this
+ * case.
+ *
+ * Return: zero on success or error code on failure.
+ */
+static __init int vmballoon_compaction_init(struct vmballoon *b)
+{
+	vmballoon_mnt = kern_mount(&vmballoon_fs);
+	if (IS_ERR(vmballoon_mnt))
+		return PTR_ERR(vmballoon_mnt);
+
+	b->b_dev_info.migratepage = vmballoon_migratepage;
+	b->b_dev_info.inode = alloc_anon_inode(vmballoon_mnt->mnt_sb);
+
+	if (IS_ERR(b->b_dev_info.inode))
+		return PTR_ERR(b->b_dev_info.inode);
+
+	b->b_dev_info.inode->i_mapping->a_ops = &balloon_aops;
+	return 0;
+}
+
+#else /* CONFIG_BALLOON_COMPACTION */
+
+static void vmballoon_compaction_deinit(struct vmballoon *b)
+{
+}
+
+static int vmballoon_compaction_init(struct vmballoon *b)
+{
+	return 0;
+}
+
+#endif /* CONFIG_BALLOON_COMPACTION */
+
 static int __init vmballoon_init(void)
 {
-	enum vmballoon_page_size_type page_size;
 	int error;
 
 	/*
@@ -1564,17 +1942,26 @@ static int __init vmballoon_init(void)
 	if (x86_hyper_type != X86_HYPER_VMWARE)
 		return -ENODEV;
 
-	for (page_size = VMW_BALLOON_4K_PAGE;
-	     page_size <= VMW_BALLOON_LAST_SIZE; page_size++)
-		INIT_LIST_HEAD(&balloon.page_sizes[page_size].pages);
-
-
 	INIT_DELAYED_WORK(&balloon.dwork, vmballoon_work);
 
+	error = vmballoon_register_shrinker(&balloon);
+	if (error)
+		goto fail;
+
 	error = vmballoon_debugfs_init(&balloon);
 	if (error)
-		return error;
+		goto fail;
+
+	/*
+	 * Initialization of compaction must be done after the call to
+	 * balloon_devinfo_init() .
+	 */
+	balloon_devinfo_init(&balloon.b_dev_info);
+	error = vmballoon_compaction_init(&balloon);
+	if (error)
+		goto fail;
 
+	INIT_LIST_HEAD(&balloon.huge_pages);
 	spin_lock_init(&balloon.comm_lock);
 	init_rwsem(&balloon.conf_sem);
 	balloon.vmci_doorbell = VMCI_INVALID_HANDLE;
@@ -1585,6 +1972,10 @@ static int __init vmballoon_init(void)
 	queue_delayed_work(system_freezable_wq, &balloon.dwork, 0);
 
 	return 0;
+fail:
+	vmballoon_unregister_shrinker(&balloon);
+	vmballoon_compaction_deinit(&balloon);
+	return error;
 }
 
 /*
@@ -1597,6 +1988,7 @@ late_initcall(vmballoon_init);
 
 static void __exit vmballoon_exit(void)
 {
+	vmballoon_unregister_shrinker(&balloon);
 	vmballoon_vmci_cleanup(&balloon);
 	cancel_delayed_work_sync(&balloon.dwork);
 
@@ -1609,5 +2001,8 @@ static void __exit vmballoon_exit(void)
 	 */
 	vmballoon_send_start(&balloon, 0);
 	vmballoon_pop(&balloon);
+
+	/* Only once we popped the balloon, compaction can be deinit */
+	vmballoon_compaction_deinit(&balloon);
 }
 module_exit(vmballoon_exit);
diff --git a/drivers/misc/vmw_vmci/vmci_context.c b/drivers/misc/vmw_vmci/vmci_context.c
index 300ed69fe2c7..16695366ec92 100644
--- a/drivers/misc/vmw_vmci/vmci_context.c
+++ b/drivers/misc/vmw_vmci/vmci_context.c
@@ -21,6 +21,9 @@
 #include "vmci_driver.h"
 #include "vmci_event.h"
 
+/* Use a wide upper bound for the maximum contexts. */
+#define VMCI_MAX_CONTEXTS 2000
+
 /*
  * List of current VMCI contexts.  Contexts can be added by
  * vmci_ctx_create() and removed via vmci_ctx_destroy().
@@ -117,19 +120,22 @@ struct vmci_ctx *vmci_ctx_create(u32 cid, u32 priv_flags,
 	/* Initialize host-specific VMCI context. */
 	init_waitqueue_head(&context->host_context.wait_queue);
 
-	context->queue_pair_array = vmci_handle_arr_create(0);
+	context->queue_pair_array =
+		vmci_handle_arr_create(0, VMCI_MAX_GUEST_QP_COUNT);
 	if (!context->queue_pair_array) {
 		error = -ENOMEM;
 		goto err_free_ctx;
 	}
 
-	context->doorbell_array = vmci_handle_arr_create(0);
+	context->doorbell_array =
+		vmci_handle_arr_create(0, VMCI_MAX_GUEST_DOORBELL_COUNT);
 	if (!context->doorbell_array) {
 		error = -ENOMEM;
 		goto err_free_qp_array;
 	}
 
-	context->pending_doorbell_array = vmci_handle_arr_create(0);
+	context->pending_doorbell_array =
+		vmci_handle_arr_create(0, VMCI_MAX_GUEST_DOORBELL_COUNT);
 	if (!context->pending_doorbell_array) {
 		error = -ENOMEM;
 		goto err_free_db_array;
@@ -204,7 +210,7 @@ static int ctx_fire_notification(u32 context_id, u32 priv_flags)
 	 * We create an array to hold the subscribers we find when
 	 * scanning through all contexts.
 	 */
-	subscriber_array = vmci_handle_arr_create(0);
+	subscriber_array = vmci_handle_arr_create(0, VMCI_MAX_CONTEXTS);
 	if (subscriber_array == NULL)
 		return VMCI_ERROR_NO_MEM;
 
@@ -623,20 +629,26 @@ int vmci_ctx_add_notification(u32 context_id, u32 remote_cid)
 
 	spin_lock(&context->lock);
 
-	list_for_each_entry(n, &context->notifier_list, node) {
-		if (vmci_handle_is_equal(n->handle, notifier->handle)) {
-			exists = true;
-			break;
+	if (context->n_notifiers < VMCI_MAX_CONTEXTS) {
+		list_for_each_entry(n, &context->notifier_list, node) {
+			if (vmci_handle_is_equal(n->handle, notifier->handle)) {
+				exists = true;
+				break;
+			}
 		}
-	}
 
-	if (exists) {
-		kfree(notifier);
-		result = VMCI_ERROR_ALREADY_EXISTS;
+		if (exists) {
+			kfree(notifier);
+			result = VMCI_ERROR_ALREADY_EXISTS;
+		} else {
+			list_add_tail_rcu(&notifier->node,
+					  &context->notifier_list);
+			context->n_notifiers++;
+			result = VMCI_SUCCESS;
+		}
 	} else {
-		list_add_tail_rcu(&notifier->node, &context->notifier_list);
-		context->n_notifiers++;
-		result = VMCI_SUCCESS;
+		kfree(notifier);
+		result = VMCI_ERROR_NO_MEM;
 	}
 
 	spin_unlock(&context->lock);
@@ -721,8 +733,7 @@ static int vmci_ctx_get_chkpt_doorbells(struct vmci_ctx *context,
 					u32 *buf_size, void **pbuf)
 {
 	struct dbell_cpt_state *dbells;
-	size_t n_doorbells;
-	int i;
+	u32 i, n_doorbells;
 
 	n_doorbells = vmci_handle_arr_get_size(context->doorbell_array);
 	if (n_doorbells > 0) {
@@ -860,7 +871,8 @@ int vmci_ctx_rcv_notifications_get(u32 context_id,
 	spin_lock(&context->lock);
 
 	*db_handle_array = context->pending_doorbell_array;
-	context->pending_doorbell_array = vmci_handle_arr_create(0);
+	context->pending_doorbell_array =
+		vmci_handle_arr_create(0, VMCI_MAX_GUEST_DOORBELL_COUNT);
 	if (!context->pending_doorbell_array) {
 		context->pending_doorbell_array = *db_handle_array;
 		*db_handle_array = NULL;
@@ -942,12 +954,11 @@ int vmci_ctx_dbell_create(u32 context_id, struct vmci_handle handle)
 		return VMCI_ERROR_NOT_FOUND;
 
 	spin_lock(&context->lock);
-	if (!vmci_handle_arr_has_entry(context->doorbell_array, handle)) {
-		vmci_handle_arr_append_entry(&context->doorbell_array, handle);
-		result = VMCI_SUCCESS;
-	} else {
+	if (!vmci_handle_arr_has_entry(context->doorbell_array, handle))
+		result = vmci_handle_arr_append_entry(&context->doorbell_array,
+						      handle);
+	else
 		result = VMCI_ERROR_DUPLICATE_ENTRY;
-	}
 
 	spin_unlock(&context->lock);
 	vmci_ctx_put(context);
@@ -1083,15 +1094,16 @@ int vmci_ctx_notify_dbell(u32 src_cid,
 			if (!vmci_handle_arr_has_entry(
 					dst_context->pending_doorbell_array,
 					handle)) {
-				vmci_handle_arr_append_entry(
+				result = vmci_handle_arr_append_entry(
 					&dst_context->pending_doorbell_array,
 					handle);
-
-				ctx_signal_notify(dst_context);
-				wake_up(&dst_context->host_context.wait_queue);
-
+				if (result == VMCI_SUCCESS) {
+					ctx_signal_notify(dst_context);
+					wake_up(&dst_context->host_context.wait_queue);
+				}
+			} else {
+				result = VMCI_SUCCESS;
 			}
-			result = VMCI_SUCCESS;
 		}
 		spin_unlock(&dst_context->lock);
 	}
@@ -1118,13 +1130,11 @@ int vmci_ctx_qp_create(struct vmci_ctx *context, struct vmci_handle handle)
 	if (context == NULL || vmci_handle_is_invalid(handle))
 		return VMCI_ERROR_INVALID_ARGS;
 
-	if (!vmci_handle_arr_has_entry(context->queue_pair_array, handle)) {
-		vmci_handle_arr_append_entry(&context->queue_pair_array,
-					     handle);
-		result = VMCI_SUCCESS;
-	} else {
+	if (!vmci_handle_arr_has_entry(context->queue_pair_array, handle))
+		result = vmci_handle_arr_append_entry(
+			&context->queue_pair_array, handle);
+	else
 		result = VMCI_ERROR_DUPLICATE_ENTRY;
-	}
 
 	return result;
 }
diff --git a/drivers/misc/vmw_vmci/vmci_handle_array.c b/drivers/misc/vmw_vmci/vmci_handle_array.c
index c527388f5d7b..de7fee7ead1b 100644
--- a/drivers/misc/vmw_vmci/vmci_handle_array.c
+++ b/drivers/misc/vmw_vmci/vmci_handle_array.c
@@ -8,24 +8,29 @@
 #include <linux/slab.h>
 #include "vmci_handle_array.h"
 
-static size_t handle_arr_calc_size(size_t capacity)
+static size_t handle_arr_calc_size(u32 capacity)
 {
-	return sizeof(struct vmci_handle_arr) +
+	return VMCI_HANDLE_ARRAY_HEADER_SIZE +
 	    capacity * sizeof(struct vmci_handle);
 }
 
-struct vmci_handle_arr *vmci_handle_arr_create(size_t capacity)
+struct vmci_handle_arr *vmci_handle_arr_create(u32 capacity, u32 max_capacity)
 {
 	struct vmci_handle_arr *array;
 
+	if (max_capacity == 0 || capacity > max_capacity)
+		return NULL;
+
 	if (capacity == 0)
-		capacity = VMCI_HANDLE_ARRAY_DEFAULT_SIZE;
+		capacity = min((u32)VMCI_HANDLE_ARRAY_DEFAULT_CAPACITY,
+			       max_capacity);
 
 	array = kmalloc(handle_arr_calc_size(capacity), GFP_ATOMIC);
 	if (!array)
 		return NULL;
 
 	array->capacity = capacity;
+	array->max_capacity = max_capacity;
 	array->size = 0;
 
 	return array;
@@ -36,27 +41,34 @@ void vmci_handle_arr_destroy(struct vmci_handle_arr *array)
 	kfree(array);
 }
 
-void vmci_handle_arr_append_entry(struct vmci_handle_arr **array_ptr,
-				  struct vmci_handle handle)
+int vmci_handle_arr_append_entry(struct vmci_handle_arr **array_ptr,
+				 struct vmci_handle handle)
 {
 	struct vmci_handle_arr *array = *array_ptr;
 
 	if (unlikely(array->size >= array->capacity)) {
 		/* reallocate. */
 		struct vmci_handle_arr *new_array;
-		size_t new_capacity = array->capacity * VMCI_ARR_CAP_MULT;
-		size_t new_size = handle_arr_calc_size(new_capacity);
+		u32 capacity_bump = min(array->max_capacity - array->capacity,
+					array->capacity);
+		size_t new_size = handle_arr_calc_size(array->capacity +
+						       capacity_bump);
+
+		if (array->size >= array->max_capacity)
+			return VMCI_ERROR_NO_MEM;
 
 		new_array = krealloc(array, new_size, GFP_ATOMIC);
 		if (!new_array)
-			return;
+			return VMCI_ERROR_NO_MEM;
 
-		new_array->capacity = new_capacity;
+		new_array->capacity += capacity_bump;
 		*array_ptr = array = new_array;
 	}
 
 	array->entries[array->size] = handle;
 	array->size++;
+
+	return VMCI_SUCCESS;
 }
 
 /*
@@ -66,7 +78,7 @@ struct vmci_handle vmci_handle_arr_remove_entry(struct vmci_handle_arr *array,
 						struct vmci_handle entry_handle)
 {
 	struct vmci_handle handle = VMCI_INVALID_HANDLE;
-	size_t i;
+	u32 i;
 
 	for (i = 0; i < array->size; i++) {
 		if (vmci_handle_is_equal(array->entries[i], entry_handle)) {
@@ -101,7 +113,7 @@ struct vmci_handle vmci_handle_arr_remove_tail(struct vmci_handle_arr *array)
  * Handle at given index, VMCI_INVALID_HANDLE if invalid index.
  */
 struct vmci_handle
-vmci_handle_arr_get_entry(const struct vmci_handle_arr *array, size_t index)
+vmci_handle_arr_get_entry(const struct vmci_handle_arr *array, u32 index)
 {
 	if (unlikely(index >= array->size))
 		return VMCI_INVALID_HANDLE;
@@ -112,7 +124,7 @@ vmci_handle_arr_get_entry(const struct vmci_handle_arr *array, size_t index)
 bool vmci_handle_arr_has_entry(const struct vmci_handle_arr *array,
 			       struct vmci_handle entry_handle)
 {
-	size_t i;
+	u32 i;
 
 	for (i = 0; i < array->size; i++)
 		if (vmci_handle_is_equal(array->entries[i], entry_handle))
diff --git a/drivers/misc/vmw_vmci/vmci_handle_array.h b/drivers/misc/vmw_vmci/vmci_handle_array.h
index bd1559a548e9..96193f85be5b 100644
--- a/drivers/misc/vmw_vmci/vmci_handle_array.h
+++ b/drivers/misc/vmw_vmci/vmci_handle_array.h
@@ -9,32 +9,41 @@
 #define _VMCI_HANDLE_ARRAY_H_
 
 #include <linux/vmw_vmci_defs.h>
+#include <linux/limits.h>
 #include <linux/types.h>
 
-#define VMCI_HANDLE_ARRAY_DEFAULT_SIZE 4
-#define VMCI_ARR_CAP_MULT 2	/* Array capacity multiplier */
-
 struct vmci_handle_arr {
-	size_t capacity;
-	size_t size;
+	u32 capacity;
+	u32 max_capacity;
+	u32 size;
+	u32 pad;
 	struct vmci_handle entries[];
 };
 
-struct vmci_handle_arr *vmci_handle_arr_create(size_t capacity);
+#define VMCI_HANDLE_ARRAY_HEADER_SIZE				\
+	offsetof(struct vmci_handle_arr, entries)
+/* Select a default capacity that results in a 64 byte sized array */
+#define VMCI_HANDLE_ARRAY_DEFAULT_CAPACITY			6
+/* Make sure that the max array size can be expressed by a u32 */
+#define VMCI_HANDLE_ARRAY_MAX_CAPACITY				\
+	((U32_MAX - VMCI_HANDLE_ARRAY_HEADER_SIZE - 1) /	\
+	sizeof(struct vmci_handle))
+
+struct vmci_handle_arr *vmci_handle_arr_create(u32 capacity, u32 max_capacity);
 void vmci_handle_arr_destroy(struct vmci_handle_arr *array);
-void vmci_handle_arr_append_entry(struct vmci_handle_arr **array_ptr,
-				  struct vmci_handle handle);
+int vmci_handle_arr_append_entry(struct vmci_handle_arr **array_ptr,
+				 struct vmci_handle handle);
 struct vmci_handle vmci_handle_arr_remove_entry(struct vmci_handle_arr *array,
 						struct vmci_handle
 						entry_handle);
 struct vmci_handle vmci_handle_arr_remove_tail(struct vmci_handle_arr *array);
 struct vmci_handle
-vmci_handle_arr_get_entry(const struct vmci_handle_arr *array, size_t index);
+vmci_handle_arr_get_entry(const struct vmci_handle_arr *array, u32 index);
 bool vmci_handle_arr_has_entry(const struct vmci_handle_arr *array,
 			       struct vmci_handle entry_handle);
 struct vmci_handle *vmci_handle_arr_get_handles(struct vmci_handle_arr *array);
 
-static inline size_t vmci_handle_arr_get_size(
+static inline u32 vmci_handle_arr_get_size(
 	const struct vmci_handle_arr *array)
 {
 	return array->size;
diff --git a/drivers/misc/xilinx_sdfec.c b/drivers/misc/xilinx_sdfec.c
new file mode 100644
index 000000000000..f257d3812110
--- /dev/null
+++ b/drivers/misc/xilinx_sdfec.c
@@ -0,0 +1,345 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Xilinx SDFEC
+ *
+ * Copyright (C) 2019 Xilinx, Inc.
+ *
+ * Description:
+ * This driver is developed for SDFEC16 (Soft Decision FEC 16nm)
+ * IP. It exposes a char device which supports file operations
+ * like  open(), close() and ioctl().
+ */
+
+#include <linux/miscdevice.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/poll.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+
+#define DEV_NAME_LEN 12
+
+static struct idr dev_idr;
+static struct mutex dev_idr_lock;
+
+/**
+ * struct xsdfec_clks - For managing SD-FEC clocks
+ * @core_clk: Main processing clock for core
+ * @axi_clk: AXI4-Lite memory-mapped clock
+ * @din_words_clk: DIN Words AXI4-Stream Slave clock
+ * @din_clk: DIN AXI4-Stream Slave clock
+ * @dout_clk: DOUT Words AXI4-Stream Slave clock
+ * @dout_words_clk: DOUT AXI4-Stream Slave clock
+ * @ctrl_clk: Control AXI4-Stream Slave clock
+ * @status_clk: Status AXI4-Stream Slave clock
+ */
+struct xsdfec_clks {
+	struct clk *core_clk;
+	struct clk *axi_clk;
+	struct clk *din_words_clk;
+	struct clk *din_clk;
+	struct clk *dout_clk;
+	struct clk *dout_words_clk;
+	struct clk *ctrl_clk;
+	struct clk *status_clk;
+};
+
+/**
+ * struct xsdfec_dev - Driver data for SDFEC
+ * @regs: device physical base address
+ * @dev: pointer to device struct
+ * @miscdev: Misc device handle
+ * @error_data_lock: Error counter and states spinlock
+ * @clks: Clocks managed by the SDFEC driver
+ * @dev_name: Device name
+ * @dev_id: Device ID
+ *
+ * This structure contains necessary state for SDFEC driver to operate
+ */
+struct xsdfec_dev {
+	void __iomem *regs;
+	struct device *dev;
+	struct miscdevice miscdev;
+	/* Spinlock to protect state_updated and stats_updated */
+	spinlock_t error_data_lock;
+	struct xsdfec_clks clks;
+	char dev_name[DEV_NAME_LEN];
+	int dev_id;
+};
+
+static const struct file_operations xsdfec_fops = {
+	.owner = THIS_MODULE,
+};
+
+static int xsdfec_clk_init(struct platform_device *pdev,
+			   struct xsdfec_clks *clks)
+{
+	int err;
+
+	clks->core_clk = devm_clk_get(&pdev->dev, "core_clk");
+	if (IS_ERR(clks->core_clk)) {
+		dev_err(&pdev->dev, "failed to get core_clk");
+		return PTR_ERR(clks->core_clk);
+	}
+
+	clks->axi_clk = devm_clk_get(&pdev->dev, "s_axi_aclk");
+	if (IS_ERR(clks->axi_clk)) {
+		dev_err(&pdev->dev, "failed to get axi_clk");
+		return PTR_ERR(clks->axi_clk);
+	}
+
+	clks->din_words_clk = devm_clk_get(&pdev->dev, "s_axis_din_words_aclk");
+	if (IS_ERR(clks->din_words_clk)) {
+		if (PTR_ERR(clks->din_words_clk) != -ENOENT) {
+			err = PTR_ERR(clks->din_words_clk);
+			return err;
+		}
+		clks->din_words_clk = NULL;
+	}
+
+	clks->din_clk = devm_clk_get(&pdev->dev, "s_axis_din_aclk");
+	if (IS_ERR(clks->din_clk)) {
+		if (PTR_ERR(clks->din_clk) != -ENOENT) {
+			err = PTR_ERR(clks->din_clk);
+			return err;
+		}
+		clks->din_clk = NULL;
+	}
+
+	clks->dout_clk = devm_clk_get(&pdev->dev, "m_axis_dout_aclk");
+	if (IS_ERR(clks->dout_clk)) {
+		if (PTR_ERR(clks->dout_clk) != -ENOENT) {
+			err = PTR_ERR(clks->dout_clk);
+			return err;
+		}
+		clks->dout_clk = NULL;
+	}
+
+	clks->dout_words_clk =
+		devm_clk_get(&pdev->dev, "s_axis_dout_words_aclk");
+	if (IS_ERR(clks->dout_words_clk)) {
+		if (PTR_ERR(clks->dout_words_clk) != -ENOENT) {
+			err = PTR_ERR(clks->dout_words_clk);
+			return err;
+		}
+		clks->dout_words_clk = NULL;
+	}
+
+	clks->ctrl_clk = devm_clk_get(&pdev->dev, "s_axis_ctrl_aclk");
+	if (IS_ERR(clks->ctrl_clk)) {
+		if (PTR_ERR(clks->ctrl_clk) != -ENOENT) {
+			err = PTR_ERR(clks->ctrl_clk);
+			return err;
+		}
+		clks->ctrl_clk = NULL;
+	}
+
+	clks->status_clk = devm_clk_get(&pdev->dev, "m_axis_status_aclk");
+	if (IS_ERR(clks->status_clk)) {
+		if (PTR_ERR(clks->status_clk) != -ENOENT) {
+			err = PTR_ERR(clks->status_clk);
+			return err;
+		}
+		clks->status_clk = NULL;
+	}
+
+	err = clk_prepare_enable(clks->core_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable core_clk (%d)", err);
+		return err;
+	}
+
+	err = clk_prepare_enable(clks->axi_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable axi_clk (%d)", err);
+		goto err_disable_core_clk;
+	}
+
+	err = clk_prepare_enable(clks->din_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable din_clk (%d)", err);
+		goto err_disable_axi_clk;
+	}
+
+	err = clk_prepare_enable(clks->din_words_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable din_words_clk (%d)", err);
+		goto err_disable_din_clk;
+	}
+
+	err = clk_prepare_enable(clks->dout_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable dout_clk (%d)", err);
+		goto err_disable_din_words_clk;
+	}
+
+	err = clk_prepare_enable(clks->dout_words_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable dout_words_clk (%d)",
+			err);
+		goto err_disable_dout_clk;
+	}
+
+	err = clk_prepare_enable(clks->ctrl_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable ctrl_clk (%d)", err);
+		goto err_disable_dout_words_clk;
+	}
+
+	err = clk_prepare_enable(clks->status_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable status_clk (%d)\n", err);
+		goto err_disable_ctrl_clk;
+	}
+
+	return err;
+
+err_disable_ctrl_clk:
+	clk_disable_unprepare(clks->ctrl_clk);
+err_disable_dout_words_clk:
+	clk_disable_unprepare(clks->dout_words_clk);
+err_disable_dout_clk:
+	clk_disable_unprepare(clks->dout_clk);
+err_disable_din_words_clk:
+	clk_disable_unprepare(clks->din_words_clk);
+err_disable_din_clk:
+	clk_disable_unprepare(clks->din_clk);
+err_disable_axi_clk:
+	clk_disable_unprepare(clks->axi_clk);
+err_disable_core_clk:
+	clk_disable_unprepare(clks->core_clk);
+
+	return err;
+}
+
+static void xsdfec_disable_all_clks(struct xsdfec_clks *clks)
+{
+	clk_disable_unprepare(clks->status_clk);
+	clk_disable_unprepare(clks->ctrl_clk);
+	clk_disable_unprepare(clks->dout_words_clk);
+	clk_disable_unprepare(clks->dout_clk);
+	clk_disable_unprepare(clks->din_words_clk);
+	clk_disable_unprepare(clks->din_clk);
+	clk_disable_unprepare(clks->core_clk);
+	clk_disable_unprepare(clks->axi_clk);
+}
+
+static void xsdfec_idr_remove(struct xsdfec_dev *xsdfec)
+{
+	mutex_lock(&dev_idr_lock);
+	idr_remove(&dev_idr, xsdfec->dev_id);
+	mutex_unlock(&dev_idr_lock);
+}
+
+static int xsdfec_probe(struct platform_device *pdev)
+{
+	struct xsdfec_dev *xsdfec;
+	struct device *dev;
+	struct resource *res;
+	int err;
+
+	xsdfec = devm_kzalloc(&pdev->dev, sizeof(*xsdfec), GFP_KERNEL);
+	if (!xsdfec)
+		return -ENOMEM;
+
+	xsdfec->dev = &pdev->dev;
+	spin_lock_init(&xsdfec->error_data_lock);
+
+	err = xsdfec_clk_init(pdev, &xsdfec->clks);
+	if (err)
+		return err;
+
+	dev = xsdfec->dev;
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	xsdfec->regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(xsdfec->regs)) {
+		err = PTR_ERR(xsdfec->regs);
+		goto err_xsdfec_dev;
+	}
+
+	/* Save driver private data */
+	platform_set_drvdata(pdev, xsdfec);
+
+	mutex_lock(&dev_idr_lock);
+	err = idr_alloc(&dev_idr, xsdfec->dev_name, 0, 0, GFP_KERNEL);
+	mutex_unlock(&dev_idr_lock);
+	if (err < 0)
+		goto err_xsdfec_dev;
+	xsdfec->dev_id = err;
+
+	snprintf(xsdfec->dev_name, DEV_NAME_LEN, "xsdfec%d", xsdfec->dev_id);
+	xsdfec->miscdev.minor = MISC_DYNAMIC_MINOR;
+	xsdfec->miscdev.name = xsdfec->dev_name;
+	xsdfec->miscdev.fops = &xsdfec_fops;
+	xsdfec->miscdev.parent = dev;
+	err = misc_register(&xsdfec->miscdev);
+	if (err) {
+		dev_err(dev, "error:%d. Unable to register device", err);
+		goto err_xsdfec_idr;
+	}
+	return 0;
+
+err_xsdfec_idr:
+	xsdfec_idr_remove(xsdfec);
+err_xsdfec_dev:
+	xsdfec_disable_all_clks(&xsdfec->clks);
+	return err;
+}
+
+static int xsdfec_remove(struct platform_device *pdev)
+{
+	struct xsdfec_dev *xsdfec;
+
+	xsdfec = platform_get_drvdata(pdev);
+	misc_deregister(&xsdfec->miscdev);
+	xsdfec_idr_remove(xsdfec);
+	xsdfec_disable_all_clks(&xsdfec->clks);
+	return 0;
+}
+
+static const struct of_device_id xsdfec_of_match[] = {
+	{
+		.compatible = "xlnx,sd-fec-1.1",
+	},
+	{ /* end of table */ }
+};
+MODULE_DEVICE_TABLE(of, xsdfec_of_match);
+
+static struct platform_driver xsdfec_driver = {
+	.driver = {
+		.name = "xilinx-sdfec",
+		.of_match_table = xsdfec_of_match,
+	},
+	.probe = xsdfec_probe,
+	.remove =  xsdfec_remove,
+};
+
+static int __init xsdfec_init(void)
+{
+	int err;
+
+	mutex_init(&dev_idr_lock);
+	idr_init(&dev_idr);
+	err = platform_driver_register(&xsdfec_driver);
+	if (err < 0) {
+		pr_err("%s Unabled to register SDFEC driver", __func__);
+		return err;
+	}
+	return 0;
+}
+
+static void __exit xsdfec_exit(void)
+{
+	platform_driver_unregister(&xsdfec_driver);
+	idr_destroy(&dev_idr);
+}
+
+module_init(xsdfec_init);
+module_exit(xsdfec_exit);
+
+MODULE_AUTHOR("Xilinx, Inc");
+MODULE_DESCRIPTION("Xilinx SD-FEC16 Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/mux/Kconfig b/drivers/mux/Kconfig
index 7659d6c5f718..e5c571fd232c 100644
--- a/drivers/mux/Kconfig
+++ b/drivers/mux/Kconfig
@@ -46,14 +46,14 @@ config MUX_GPIO
 	  be called mux-gpio.
 
 config MUX_MMIO
-	tristate "MMIO register bitfield-controlled Multiplexer"
-	depends on (OF && MFD_SYSCON) || COMPILE_TEST
+	tristate "MMIO/Regmap register bitfield-controlled Multiplexer"
+	depends on OF || COMPILE_TEST
 	help
-	  MMIO register bitfield-controlled Multiplexer controller.
+	  MMIO/Regmap register bitfield-controlled Multiplexer controller.
 
-	  The driver builds multiplexer controllers for bitfields in a syscon
-	  register. For N bit wide bitfields, there will be 2^N possible
-	  multiplexer states.
+	  The driver builds multiplexer controllers for bitfields in either
+	  a syscon register or a driver regmap register. For N bit wide
+	  bitfields, there will be 2^N possible multiplexer states.
 
 	  To compile the driver as a module, choose M here: the module will
 	  be called mux-mmio.
diff --git a/drivers/mux/mmio.c b/drivers/mux/mmio.c
index 935ac44aa209..44a7a0e885b8 100644
--- a/drivers/mux/mmio.c
+++ b/drivers/mux/mmio.c
@@ -28,6 +28,7 @@ static const struct mux_control_ops mux_mmio_ops = {
 
 static const struct of_device_id mux_mmio_dt_ids[] = {
 	{ .compatible = "mmio-mux", },
+	{ .compatible = "reg-mux", },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, mux_mmio_dt_ids);
@@ -43,7 +44,10 @@ static int mux_mmio_probe(struct platform_device *pdev)
 	int ret;
 	int i;
 
-	regmap = syscon_node_to_regmap(np->parent);
+	if (of_device_is_compatible(np, "mmio-mux"))
+		regmap = syscon_node_to_regmap(np->parent);
+	else
+		regmap = dev_get_regmap(dev->parent, NULL) ?: ERR_PTR(-ENODEV);
 	if (IS_ERR(regmap)) {
 		ret = PTR_ERR(regmap);
 		dev_err(dev, "failed to get regmap: %d\n", ret);
diff --git a/drivers/nvmem/Kconfig b/drivers/nvmem/Kconfig
index afa4335e0a20..c2ec750cae6e 100644
--- a/drivers/nvmem/Kconfig
+++ b/drivers/nvmem/Kconfig
@@ -47,6 +47,13 @@ config NVMEM_IMX_OCOTP
 	  This driver can also be built as a module. If so, the module
 	  will be called nvmem-imx-ocotp.
 
+config NVMEM_IMX_OCOTP_SCU
+	tristate "i.MX8 SCU On-Chip OTP Controller support"
+	depends on IMX_SCU
+	help
+	  This is a driver for the SCU On-Chip OTP Controller (OCOTP)
+	  available on i.MX8 SoCs.
+
 config NVMEM_LPC18XX_EEPROM
 	tristate "NXP LPC18XX EEPROM Memory Support"
 	depends on ARCH_LPC18XX || COMPILE_TEST
@@ -188,7 +195,7 @@ config MESON_MX_EFUSE
 
 config NVMEM_SNVS_LPGPR
 	tristate "Support for Low Power General Purpose Register"
-	depends on SOC_IMX6 || SOC_IMX7D || COMPILE_TEST
+	depends on ARCH_MXC || COMPILE_TEST
 	help
 	  This is a driver for Low Power General Purpose Register (LPGPR) available on
 	  i.MX6 and i.MX7 SoCs in Secure Non-Volatile Storage (SNVS) of this chip.
diff --git a/drivers/nvmem/Makefile b/drivers/nvmem/Makefile
index c1fe4768dfef..e5c153d99a67 100644
--- a/drivers/nvmem/Makefile
+++ b/drivers/nvmem/Makefile
@@ -16,6 +16,8 @@ obj-$(CONFIG_NVMEM_IMX_IIM)	+= nvmem-imx-iim.o
 nvmem-imx-iim-y			:= imx-iim.o
 obj-$(CONFIG_NVMEM_IMX_OCOTP)	+= nvmem-imx-ocotp.o
 nvmem-imx-ocotp-y		:= imx-ocotp.o
+obj-$(CONFIG_NVMEM_IMX_OCOTP_SCU)	+= nvmem-imx-ocotp-scu.o
+nvmem-imx-ocotp-scu-y		:= imx-ocotp-scu.o
 obj-$(CONFIG_NVMEM_LPC18XX_EEPROM)	+= nvmem_lpc18xx_eeprom.o
 nvmem_lpc18xx_eeprom-y	:= lpc18xx_eeprom.o
 obj-$(CONFIG_NVMEM_LPC18XX_OTP)	+= nvmem_lpc18xx_otp.o
diff --git a/drivers/nvmem/imx-ocotp-scu.c b/drivers/nvmem/imx-ocotp-scu.c
new file mode 100644
index 000000000000..d9dc482ecb2f
--- /dev/null
+++ b/drivers/nvmem/imx-ocotp-scu.c
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * i.MX8 OCOTP fusebox driver
+ *
+ * Copyright 2019 NXP
+ *
+ * Peng Fan <peng.fan@nxp.com>
+ */
+
+#include <linux/firmware/imx/sci.h>
+#include <linux/module.h>
+#include <linux/nvmem-provider.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+enum ocotp_devtype {
+	IMX8QXP,
+};
+
+struct ocotp_devtype_data {
+	int devtype;
+	int nregs;
+};
+
+struct ocotp_priv {
+	struct device *dev;
+	const struct ocotp_devtype_data *data;
+	struct imx_sc_ipc *nvmem_ipc;
+};
+
+struct imx_sc_msg_misc_fuse_read {
+	struct imx_sc_rpc_msg hdr;
+	u32 word;
+} __packed;
+
+static struct ocotp_devtype_data imx8qxp_data = {
+	.devtype = IMX8QXP,
+	.nregs = 800,
+};
+
+static int imx_sc_misc_otp_fuse_read(struct imx_sc_ipc *ipc, u32 word,
+				     u32 *val)
+{
+	struct imx_sc_msg_misc_fuse_read msg;
+	struct imx_sc_rpc_msg *hdr = &msg.hdr;
+	int ret;
+
+	hdr->ver = IMX_SC_RPC_VERSION;
+	hdr->svc = IMX_SC_RPC_SVC_MISC;
+	hdr->func = IMX_SC_MISC_FUNC_OTP_FUSE_READ;
+	hdr->size = 2;
+
+	msg.word = word;
+
+	ret = imx_scu_call_rpc(ipc, &msg, true);
+	if (ret)
+		return ret;
+
+	*val = msg.word;
+
+	return 0;
+}
+
+static int imx_scu_ocotp_read(void *context, unsigned int offset,
+			      void *val, size_t bytes)
+{
+	struct ocotp_priv *priv = context;
+	u32 count, index, num_bytes;
+	u32 *buf;
+	void *p;
+	int i, ret;
+
+	index = offset >> 2;
+	num_bytes = round_up((offset % 4) + bytes, 4);
+	count = num_bytes >> 2;
+
+	if (count > (priv->data->nregs - index))
+		count = priv->data->nregs - index;
+
+	p = kzalloc(num_bytes, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	buf = p;
+
+	for (i = index; i < (index + count); i++) {
+		if (priv->data->devtype == IMX8QXP) {
+			if ((i > 271) && (i < 544)) {
+				*buf++ = 0;
+				continue;
+			}
+		}
+
+		ret = imx_sc_misc_otp_fuse_read(priv->nvmem_ipc, i, buf);
+		if (ret) {
+			kfree(p);
+			return ret;
+		}
+		buf++;
+	}
+
+	memcpy(val, (u8 *)p + offset % 4, bytes);
+
+	kfree(p);
+
+	return 0;
+}
+
+static struct nvmem_config imx_scu_ocotp_nvmem_config = {
+	.name = "imx-scu-ocotp",
+	.read_only = true,
+	.word_size = 4,
+	.stride = 1,
+	.owner = THIS_MODULE,
+	.reg_read = imx_scu_ocotp_read,
+};
+
+static const struct of_device_id imx_scu_ocotp_dt_ids[] = {
+	{ .compatible = "fsl,imx8qxp-scu-ocotp", (void *)&imx8qxp_data },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, imx_scu_ocotp_dt_ids);
+
+static int imx_scu_ocotp_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct ocotp_priv *priv;
+	struct nvmem_device *nvmem;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	ret = imx_scu_get_handle(&priv->nvmem_ipc);
+	if (ret)
+		return ret;
+
+	priv->data = of_device_get_match_data(dev);
+	priv->dev = dev;
+	imx_scu_ocotp_nvmem_config.size = 4 * priv->data->nregs;
+	imx_scu_ocotp_nvmem_config.dev = dev;
+	imx_scu_ocotp_nvmem_config.priv = priv;
+	nvmem = devm_nvmem_register(dev, &imx_scu_ocotp_nvmem_config);
+
+	return PTR_ERR_OR_ZERO(nvmem);
+}
+
+static struct platform_driver imx_scu_ocotp_driver = {
+	.probe	= imx_scu_ocotp_probe,
+	.driver = {
+		.name	= "imx_scu_ocotp",
+		.of_match_table = imx_scu_ocotp_dt_ids,
+	},
+};
+module_platform_driver(imx_scu_ocotp_driver);
+
+MODULE_AUTHOR("Peng Fan <peng.fan@nxp.com>");
+MODULE_DESCRIPTION("i.MX8 SCU OCOTP fuse box driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/nvmem/imx-ocotp.c b/drivers/nvmem/imx-ocotp.c
index bd016b928589..42d4451e7d67 100644
--- a/drivers/nvmem/imx-ocotp.c
+++ b/drivers/nvmem/imx-ocotp.c
@@ -39,12 +39,14 @@
 #define IMX_OCOTP_ADDR_DATA2		0x0040
 #define IMX_OCOTP_ADDR_DATA3		0x0050
 
-#define IMX_OCOTP_BM_CTRL_ADDR		0x0000007F
+#define IMX_OCOTP_BM_CTRL_ADDR		0x000000FF
 #define IMX_OCOTP_BM_CTRL_BUSY		0x00000100
 #define IMX_OCOTP_BM_CTRL_ERROR		0x00000200
 #define IMX_OCOTP_BM_CTRL_REL_SHADOWS	0x00000400
 
-#define DEF_RELAX			20	/* > 16.5ns */
+#define TIMING_STROBE_PROG_US		10	/* Min time to blow a fuse */
+#define TIMING_STROBE_READ_NS		37	/* Min time before read */
+#define TIMING_RELAX_NS			17
 #define DEF_FSOURCE			1001	/* > 1000 ns */
 #define DEF_STROBE_PROG			10000	/* IPG clocks */
 #define IMX_OCOTP_WR_UNLOCK		0x3E770000
@@ -176,14 +178,41 @@ static void imx_ocotp_set_imx6_timing(struct ocotp_priv *priv)
 	 * fields with timing values to match the current frequency of the
 	 * ipg_clk. OTP writes will work at maximum bus frequencies as long
 	 * as the HW_OCOTP_TIMING parameters are set correctly.
+	 *
+	 * Note: there are minimum timings required to ensure an OTP fuse burns
+	 * correctly that are independent of the ipg_clk. Those values are not
+	 * formally documented anywhere however, working from the minimum
+	 * timings given in u-boot we can say:
+	 *
+	 * - Minimum STROBE_PROG time is 10 microseconds. Intuitively 10
+	 *   microseconds feels about right as representative of a minimum time
+	 *   to physically burn out a fuse.
+	 *
+	 * - Minimum STROBE_READ i.e. the time to wait post OTP fuse burn before
+	 *   performing another read is 37 nanoseconds
+	 *
+	 * - Minimum RELAX timing is 17 nanoseconds. This final RELAX minimum
+	 *   timing is not entirely clear the documentation says "This
+	 *   count value specifies the time to add to all default timing
+	 *   parameters other than the Tpgm and Trd. It is given in number
+	 *   of ipg_clk periods." where Tpgm and Trd refer to STROBE_PROG
+	 *   and STROBE_READ respectively. What the other timing parameters
+	 *   are though, is not specified. Experience shows a zero RELAX
+	 *   value will mess up a re-load of the shadow registers post OTP
+	 *   burn.
 	 */
 	clk_rate = clk_get_rate(priv->clk);
 
-	relax = clk_rate / (1000000000 / DEF_RELAX) - 1;
-	strobe_prog = clk_rate / (1000000000 / 10000) + 2 * (DEF_RELAX + 1) - 1;
-	strobe_read = clk_rate / (1000000000 / 40) + 2 * (DEF_RELAX + 1) - 1;
+	relax = DIV_ROUND_UP(clk_rate * TIMING_RELAX_NS, 1000000000) - 1;
+	strobe_read = DIV_ROUND_UP(clk_rate * TIMING_STROBE_READ_NS,
+				   1000000000);
+	strobe_read += 2 * (relax + 1) - 1;
+	strobe_prog = DIV_ROUND_CLOSEST(clk_rate * TIMING_STROBE_PROG_US,
+					1000000);
+	strobe_prog += 2 * (relax + 1) - 1;
 
-	timing = strobe_prog & 0x00000FFF;
+	timing = readl(priv->base + IMX_OCOTP_ADDR_TIMING) & 0x0FC00000;
+	timing |= strobe_prog & 0x00000FFF;
 	timing |= (relax       << 12) & 0x0000F000;
 	timing |= (strobe_read << 16) & 0x003F0000;
 
@@ -440,8 +469,14 @@ static const struct ocotp_params imx7ulp_params = {
 
 static const struct ocotp_params imx8mq_params = {
 	.nregs = 256,
-	.bank_address_words = 4,
-	.set_timing = imx_ocotp_set_imx7_timing,
+	.bank_address_words = 0,
+	.set_timing = imx_ocotp_set_imx6_timing,
+};
+
+static const struct ocotp_params imx8mm_params = {
+	.nregs = 256,
+	.bank_address_words = 0,
+	.set_timing = imx_ocotp_set_imx6_timing,
 };
 
 static const struct of_device_id imx_ocotp_dt_ids[] = {
@@ -454,6 +489,7 @@ static const struct of_device_id imx_ocotp_dt_ids[] = {
 	{ .compatible = "fsl,imx6sll-ocotp", .data = &imx6sll_params },
 	{ .compatible = "fsl,imx7ulp-ocotp", .data = &imx7ulp_params },
 	{ .compatible = "fsl,imx8mq-ocotp", .data = &imx8mq_params },
+	{ .compatible = "fsl,imx8mm-ocotp", .data = &imx8mm_params },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, imx_ocotp_dt_ids);
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index b7e5cee2aa26..6053d0158b3b 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -341,7 +341,7 @@ config HP_ACCEL
 
 	  Support for a led indicating disk protection will be provided as
 	  hp::hddprotect. For more information on the feature, refer to
-	  Documentation/misc-devices/lis3lv02d.
+	  Documentation/misc-devices/lis3lv02d.rst.
 
 	  To compile this driver as a module, choose M here: the module will
 	  be called hp_accel.
diff --git a/drivers/slimbus/core.c b/drivers/slimbus/core.c
index b2f07d2043eb..526e3215d8fe 100644
--- a/drivers/slimbus/core.c
+++ b/drivers/slimbus/core.c
@@ -98,11 +98,6 @@ static int slim_device_remove(struct device *dev)
 static int slim_device_uevent(struct device *dev, struct kobj_uevent_env *env)
 {
 	struct slim_device *sbdev = to_slim_device(dev);
-	int ret;
-
-	ret = of_device_uevent_modalias(dev, env);
-	if (ret != -ENODEV)
-		return ret;
 
 	return add_uevent_var(env, "MODALIAS=slim:%s", dev_name(&sbdev->dev));
 }
diff --git a/drivers/slimbus/qcom-ctrl.c b/drivers/slimbus/qcom-ctrl.c
index ad3e2e23f56e..a444badd8df5 100644
--- a/drivers/slimbus/qcom-ctrl.c
+++ b/drivers/slimbus/qcom-ctrl.c
@@ -528,10 +528,8 @@ static int qcom_slim_probe(struct platform_device *pdev)
 
 	slim_mem = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ctrl");
 	ctrl->base = devm_ioremap_resource(ctrl->dev, slim_mem);
-	if (IS_ERR(ctrl->base)) {
-		dev_err(&pdev->dev, "IOremap failed\n");
+	if (IS_ERR(ctrl->base))
 		return PTR_ERR(ctrl->base);
-	}
 
 	sctrl->set_laddr = qcom_set_laddr;
 	sctrl->xfer_msg = qcom_xfer_msg;
diff --git a/drivers/slimbus/stream.c b/drivers/slimbus/stream.c
index 2fa05324ed07..75f87b3d8b95 100644
--- a/drivers/slimbus/stream.c
+++ b/drivers/slimbus/stream.c
@@ -84,7 +84,7 @@ static const int slim_presence_rate_table[] = {
 	512000,
 };
 
-/*
+/**
  * slim_stream_allocate() - Allocate a new SLIMbus Stream
  * @dev:Slim device to be associated with
  * @name: name of the stream
@@ -189,7 +189,7 @@ static int slim_get_prate_code(int rate)
 	return -EINVAL;
 }
 
-/*
+/**
  * slim_stream_prepare() - Prepare a SLIMbus Stream
  *
  * @rt: instance of slim stream runtime to configure
@@ -336,7 +336,7 @@ static int slim_activate_channel(struct slim_stream_runtime *stream,
 	return slim_do_transfer(sdev->ctrl, &txn);
 }
 
-/*
+/**
  * slim_stream_enable() - Enable a prepared SLIMbus Stream
  *
  * @stream: instance of slim stream runtime to enable
@@ -389,7 +389,7 @@ int slim_stream_enable(struct slim_stream_runtime *stream)
 }
 EXPORT_SYMBOL_GPL(slim_stream_enable);
 
-/*
+/**
  * slim_stream_disable() - Disable a SLIMbus Stream
  *
  * @stream: instance of slim stream runtime to disable
@@ -423,7 +423,7 @@ int slim_stream_disable(struct slim_stream_runtime *stream)
 }
 EXPORT_SYMBOL_GPL(slim_stream_disable);
 
-/*
+/**
  * slim_stream_unprepare() - Un-prepare a SLIMbus Stream
  *
  * @stream: instance of slim stream runtime to unprepare
@@ -449,7 +449,7 @@ int slim_stream_unprepare(struct slim_stream_runtime *stream)
 }
 EXPORT_SYMBOL_GPL(slim_stream_unprepare);
 
-/*
+/**
  * slim_stream_free() - Free a SLIMbus Stream
  *
  * @stream: instance of slim stream runtime to free
diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index aac35fc3cf22..fe745830a261 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -87,7 +87,7 @@ int sdw_add_bus_master(struct sdw_bus *bus)
 
 	/*
 	 * Initialize clock values based on Master properties. The max
-	 * frequency is read from max_freq property. Current assumption
+	 * frequency is read from max_clk_freq property. Current assumption
 	 * is that the bus will start at highest clock frequency when
 	 * powered on.
 	 *
@@ -95,7 +95,7 @@ int sdw_add_bus_master(struct sdw_bus *bus)
 	 * to start with bank 0 (Table 40 of Spec)
 	 */
 	prop = &bus->prop;
-	bus->params.max_dr_freq = prop->max_freq * SDW_DOUBLE_RATE_FACTOR;
+	bus->params.max_dr_freq = prop->max_clk_freq * SDW_DOUBLE_RATE_FACTOR;
 	bus->params.curr_dr_freq = bus->params.max_dr_freq;
 	bus->params.curr_bank = SDW_BANK0;
 	bus->params.next_bank = SDW_BANK1;
@@ -648,7 +648,7 @@ static int sdw_initialize_slave(struct sdw_slave *slave)
 		return 0;
 
 	/* Enable DP0 interrupts */
-	val = prop->dp0_prop->device_interrupts;
+	val = prop->dp0_prop->imp_def_interrupts;
 	val |= SDW_DP0_INT_PORT_READY | SDW_DP0_INT_BRA_FAILURE;
 
 	ret = sdw_update(slave, SDW_DP0_INTMASK, val, val);
diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c
index 682789bb8ab3..ff4badc9b3de 100644
--- a/drivers/soundwire/cadence_master.c
+++ b/drivers/soundwire/cadence_master.c
@@ -9,6 +9,7 @@
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/interrupt.h>
+#include <linux/io.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
 #include <linux/soundwire/sdw_registers.h>
@@ -236,19 +237,19 @@ cdns_fill_msg_resp(struct sdw_cdns *cdns,
 	for (i = 0; i < count; i++) {
 		if (!(cdns->response_buf[i] & CDNS_MCP_RESP_ACK)) {
 			no_ack = 1;
-			dev_dbg(cdns->dev, "Msg Ack not received\n");
+			dev_dbg_ratelimited(cdns->dev, "Msg Ack not received\n");
 			if (cdns->response_buf[i] & CDNS_MCP_RESP_NACK) {
 				nack = 1;
-				dev_err(cdns->dev, "Msg NACK received\n");
+				dev_err_ratelimited(cdns->dev, "Msg NACK received\n");
 			}
 		}
 	}
 
 	if (nack) {
-		dev_err(cdns->dev, "Msg NACKed for Slave %d\n", msg->dev_num);
+		dev_err_ratelimited(cdns->dev, "Msg NACKed for Slave %d\n", msg->dev_num);
 		return SDW_CMD_FAIL;
 	} else if (no_ack) {
-		dev_dbg(cdns->dev, "Msg ignored for Slave %d\n", msg->dev_num);
+		dev_dbg_ratelimited(cdns->dev, "Msg ignored for Slave %d\n", msg->dev_num);
 		return SDW_CMD_IGNORED;
 	}
 
@@ -356,12 +357,12 @@ cdns_program_scp_addr(struct sdw_cdns *cdns, struct sdw_msg *msg)
 
 	/* For NACK, NO ack, don't return err if we are in Broadcast mode */
 	if (nack) {
-		dev_err(cdns->dev,
-			"SCP_addrpage NACKed for Slave %d\n", msg->dev_num);
+		dev_err_ratelimited(cdns->dev,
+				    "SCP_addrpage NACKed for Slave %d\n", msg->dev_num);
 		return SDW_CMD_FAIL;
 	} else if (no_ack) {
-		dev_dbg(cdns->dev,
-			"SCP_addrpage ignored for Slave %d\n", msg->dev_num);
+		dev_dbg_ratelimited(cdns->dev,
+				    "SCP_addrpage ignored for Slave %d\n", msg->dev_num);
 		return SDW_CMD_IGNORED;
 	}
 
@@ -486,7 +487,8 @@ static int cdns_update_slave_status(struct sdw_cdns *cdns,
 {
 	enum sdw_slave_status status[SDW_MAX_DEVICES + 1];
 	bool is_slave = false;
-	u64 slave, mask;
+	u64 slave;
+	u32 mask;
 	int i, set_status;
 
 	/* combine the two status */
@@ -524,9 +526,9 @@ static int cdns_update_slave_status(struct sdw_cdns *cdns,
 
 		/* first check if Slave reported multiple status */
 		if (set_status > 1) {
-			dev_warn(cdns->dev,
-				 "Slave reported multiple Status: %d\n",
-				 status[i]);
+			dev_warn_ratelimited(cdns->dev,
+					     "Slave reported multiple Status: %d\n",
+					     mask);
 			/*
 			 * TODO: we need to reread the status here by
 			 * issuing a PING cmd
@@ -612,7 +614,7 @@ irqreturn_t sdw_cdns_thread(int irq, void *dev_id)
 	struct sdw_cdns *cdns = dev_id;
 	u32 slave0, slave1;
 
-	dev_dbg(cdns->dev, "Slave status change\n");
+	dev_dbg_ratelimited(cdns->dev, "Slave status change\n");
 
 	slave0 = cdns_readl(cdns, CDNS_MCP_SLAVE_INTSTAT0);
 	slave1 = cdns_readl(cdns, CDNS_MCP_SLAVE_INTSTAT1);
@@ -716,6 +718,8 @@ int sdw_cdns_pdi_init(struct sdw_cdns *cdns,
 	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;
 
diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c
index 60293a00a14e..317873bc0555 100644
--- a/drivers/soundwire/intel.c
+++ b/drivers/soundwire/intel.c
@@ -263,6 +263,9 @@ static void intel_pdi_init(struct sdw_intel *sdw,
 	config->pcm_out = (pcm_cap & SDW_SHIM_PCMSCAP_OSS) >>
 					SDW_REG_SHIFT(SDW_SHIM_PCMSCAP_OSS);
 
+	dev_dbg(sdw->cdns.dev, "PCM cap bd:%d in:%d out:%d\n",
+		config->pcm_bd, config->pcm_in, config->pcm_out);
+
 	/* PDM Stream Capability */
 	pdm_cap = intel_readw(shim, SDW_SHIM_PDMSCAP(link_id));
 
@@ -272,6 +275,9 @@ static void intel_pdi_init(struct sdw_intel *sdw,
 					SDW_REG_SHIFT(SDW_SHIM_PDMSCAP_ISS);
 	config->pdm_out = (pdm_cap & SDW_SHIM_PDMSCAP_OSS) >>
 					SDW_REG_SHIFT(SDW_SHIM_PDMSCAP_OSS);
+
+	dev_dbg(sdw->cdns.dev, "PDM cap bd:%d in:%d out:%d\n",
+		config->pdm_bd, config->pdm_in, config->pdm_out);
 }
 
 static int
@@ -796,13 +802,14 @@ static int intel_prop_read(struct sdw_bus *bus)
 	sdw_master_read_prop(bus);
 
 	/* BIOS is not giving some values correctly. So, lets override them */
-	bus->prop.num_freq = 1;
-	bus->prop.freq = devm_kcalloc(bus->dev, bus->prop.num_freq,
-				      sizeof(*bus->prop.freq), GFP_KERNEL);
-	if (!bus->prop.freq)
+	bus->prop.num_clk_freq = 1;
+	bus->prop.clk_freq = devm_kcalloc(bus->dev, bus->prop.num_clk_freq,
+					  sizeof(*bus->prop.clk_freq),
+					  GFP_KERNEL);
+	if (!bus->prop.clk_freq)
 		return -ENOMEM;
 
-	bus->prop.freq[0] = bus->prop.max_freq;
+	bus->prop.clk_freq[0] = bus->prop.max_clk_freq;
 	bus->prop.err_threshold = 5;
 
 	return 0;
diff --git a/drivers/soundwire/intel.h b/drivers/soundwire/intel.h
index 71050e5f643d..d923b6262330 100644
--- a/drivers/soundwire/intel.h
+++ b/drivers/soundwire/intel.h
@@ -5,7 +5,7 @@
 #define __SDW_INTEL_LOCAL_H
 
 /**
- * struct sdw_intel_res - Soundwire link resources
+ * struct sdw_intel_link_res - Soundwire link resources
  * @registers: Link IO registers base
  * @shim: Audio shim pointer
  * @alh: ALH (Audio Link Hub) pointer
diff --git a/drivers/soundwire/intel_init.c b/drivers/soundwire/intel_init.c
index d3d6b54c5791..70637a0383d2 100644
--- a/drivers/soundwire/intel_init.c
+++ b/drivers/soundwire/intel_init.c
@@ -14,6 +14,7 @@
 #include <linux/soundwire/sdw_intel.h>
 #include "intel.h"
 
+#define SDW_LINK_TYPE		4 /* from Intel ACPI documentation */
 #define SDW_MAX_LINKS		4
 #define SDW_SHIM_LCAP		0x0
 #define SDW_SHIM_BASE		0x2C000
@@ -80,6 +81,7 @@ static struct sdw_intel_ctx
 
 	/* Check SNDWLCAP.LCOUNT */
 	caps = ioread32(res->mmio_base + SDW_SHIM_BASE + SDW_SHIM_LCAP);
+	caps &= GENMASK(2, 0);
 
 	/* Check HW supported vs property value and use min of two */
 	count = min_t(u8, caps, count);
@@ -89,6 +91,9 @@ static struct sdw_intel_ctx
 		dev_err(&adev->dev, "Link count %d exceeds max %d\n",
 			count, SDW_MAX_LINKS);
 		return NULL;
+	} else if (!count) {
+		dev_warn(&adev->dev, "No SoundWire links detected\n");
+		return NULL;
 	}
 
 	dev_dbg(&adev->dev, "Creating %d SDW Link devices\n", count);
@@ -150,6 +155,12 @@ static acpi_status sdw_intel_acpi_cb(acpi_handle handle, u32 level,
 {
 	struct sdw_intel_res *res = cdata;
 	struct acpi_device *adev;
+	acpi_status status;
+	u64 adr;
+
+	status = acpi_evaluate_integer(handle, METHOD_NAME__ADR, NULL, &adr);
+	if (ACPI_FAILURE(status))
+		return AE_OK; /* keep going */
 
 	if (acpi_bus_get_device(handle, &adev)) {
 		pr_err("%s: Couldn't find ACPI handle\n", __func__);
@@ -157,7 +168,19 @@ static acpi_status sdw_intel_acpi_cb(acpi_handle handle, u32 level,
 	}
 
 	res->handle = handle;
-	return AE_OK;
+
+	/*
+	 * On some Intel platforms, multiple children of the HDAS
+	 * device can be found, but only one of them is the SoundWire
+	 * controller. The SNDW device is always exposed with
+	 * Name(_ADR, 0x40000000), with bits 31..28 representing the
+	 * SoundWire link so filter accordingly
+	 */
+	if ((adr & GENMASK(31, 28)) >> 28 != SDW_LINK_TYPE)
+		return AE_OK; /* keep going */
+
+	/* device found, stop namespace walk */
+	return AE_CTRL_TERMINATE;
 }
 
 /**
diff --git a/drivers/soundwire/mipi_disco.c b/drivers/soundwire/mipi_disco.c
index c1f51d6a23d2..79fee1b21ab6 100644
--- a/drivers/soundwire/mipi_disco.c
+++ b/drivers/soundwire/mipi_disco.c
@@ -40,7 +40,7 @@ int sdw_master_read_prop(struct sdw_bus *bus)
 
 	/* Find master handle */
 	snprintf(name, sizeof(name),
-		 "mipi-sdw-master-%d-subproperties", bus->link_id);
+		 "mipi-sdw-link-%d-subproperties", bus->link_id);
 
 	link = device_get_named_child_node(bus->dev, name);
 	if (!link) {
@@ -50,39 +50,40 @@ int sdw_master_read_prop(struct sdw_bus *bus)
 
 	if (fwnode_property_read_bool(link,
 				      "mipi-sdw-clock-stop-mode0-supported"))
-		prop->clk_stop_mode = SDW_CLK_STOP_MODE0;
+		prop->clk_stop_modes |= BIT(SDW_CLK_STOP_MODE0);
 
 	if (fwnode_property_read_bool(link,
 				      "mipi-sdw-clock-stop-mode1-supported"))
-		prop->clk_stop_mode |= SDW_CLK_STOP_MODE1;
+		prop->clk_stop_modes |= BIT(SDW_CLK_STOP_MODE1);
 
 	fwnode_property_read_u32(link,
 				 "mipi-sdw-max-clock-frequency",
-				 &prop->max_freq);
+				 &prop->max_clk_freq);
 
 	nval = fwnode_property_read_u32_array(link,
 			"mipi-sdw-clock-frequencies-supported", NULL, 0);
 	if (nval > 0) {
-		prop->num_freq = nval;
-		prop->freq = devm_kcalloc(bus->dev, prop->num_freq,
-					  sizeof(*prop->freq), GFP_KERNEL);
-		if (!prop->freq)
+		prop->num_clk_freq = nval;
+		prop->clk_freq = devm_kcalloc(bus->dev, prop->num_clk_freq,
+					      sizeof(*prop->clk_freq),
+					      GFP_KERNEL);
+		if (!prop->clk_freq)
 			return -ENOMEM;
 
 		fwnode_property_read_u32_array(link,
 				"mipi-sdw-clock-frequencies-supported",
-				prop->freq, prop->num_freq);
+				prop->clk_freq, prop->num_clk_freq);
 	}
 
 	/*
 	 * Check the frequencies supported. If FW doesn't provide max
 	 * freq, then populate here by checking values.
 	 */
-	if (!prop->max_freq && prop->freq) {
-		prop->max_freq = prop->freq[0];
-		for (i = 1; i < prop->num_freq; i++) {
-			if (prop->freq[i] > prop->max_freq)
-				prop->max_freq = prop->freq[i];
+	if (!prop->max_clk_freq && prop->clk_freq) {
+		prop->max_clk_freq = prop->clk_freq[0];
+		for (i = 1; i < prop->num_clk_freq; i++) {
+			if (prop->clk_freq[i] > prop->max_clk_freq)
+				prop->max_clk_freq = prop->clk_freq[i];
 		}
 	}
 
@@ -149,13 +150,13 @@ static int sdw_slave_read_dp0(struct sdw_slave *slave,
 				dp0->words, dp0->num_words);
 	}
 
-	dp0->flow_controlled = fwnode_property_read_bool(port,
+	dp0->BRA_flow_controlled = fwnode_property_read_bool(port,
 				"mipi-sdw-bra-flow-controlled");
 
 	dp0->simple_ch_prep_sm = fwnode_property_read_bool(port,
 				"mipi-sdw-simplified-channel-prepare-sm");
 
-	dp0->device_interrupts = fwnode_property_read_bool(port,
+	dp0->imp_def_interrupts = fwnode_property_read_bool(port,
 				"mipi-sdw-imp-def-dp0-interrupts-supported");
 
 	return 0;
@@ -224,7 +225,7 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave,
 
 		fwnode_property_read_u32(node,
 				"mipi-sdw-imp-def-dpn-interrupts-supported",
-				&dpn[i].device_interrupts);
+				&dpn[i].imp_def_interrupts);
 
 		fwnode_property_read_u32(node, "mipi-sdw-min-channel-number",
 					 &dpn[i].min_ch);
diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
index 1d5294b8783b..a0476755a459 100644
--- a/drivers/soundwire/stream.c
+++ b/drivers/soundwire/stream.c
@@ -439,7 +439,7 @@ static int sdw_prep_deprep_slave_ports(struct sdw_bus *bus,
 
 	prep_ch.bank = bus->params.next_bank;
 
-	if (dpn_prop->device_interrupts || !dpn_prop->simple_ch_prep_sm)
+	if (dpn_prop->imp_def_interrupts || !dpn_prop->simple_ch_prep_sm)
 		intr = true;
 
 	/*
@@ -449,7 +449,7 @@ static int sdw_prep_deprep_slave_ports(struct sdw_bus *bus,
 	 */
 	if (prep && intr) {
 		ret = sdw_configure_dpn_intr(s_rt->slave, p_rt->num, prep,
-					     dpn_prop->device_interrupts);
+					     dpn_prop->imp_def_interrupts);
 		if (ret < 0)
 			return ret;
 	}
@@ -493,7 +493,7 @@ static int sdw_prep_deprep_slave_ports(struct sdw_bus *bus,
 	/* Disable interrupt after Port de-prepare */
 	if (!prep && intr)
 		ret = sdw_configure_dpn_intr(s_rt->slave, p_rt->num, prep,
-					     dpn_prop->device_interrupts);
+					     dpn_prop->imp_def_interrupts);
 
 	return ret;
 }
@@ -1473,7 +1473,7 @@ static int _sdw_prepare_stream(struct sdw_stream_runtime *stream)
 		memcpy(&params, &bus->params, sizeof(params));
 
 		/* TODO: Support Asynchronous mode */
-		if ((prop->max_freq % stream->params.rate) != 0) {
+		if ((prop->max_clk_freq % stream->params.rate) != 0) {
 			dev_err(bus->dev, "Async mode not supported\n");
 			return -EINVAL;
 		}
diff --git a/drivers/w1/slaves/w1_ds2413.c b/drivers/w1/slaves/w1_ds2413.c
index 5ae74d5545e6..f1fb18afbcea 100644
--- a/drivers/w1/slaves/w1_ds2413.c
+++ b/drivers/w1/slaves/w1_ds2413.c
@@ -22,12 +22,17 @@
 #define W1_F3A_FUNC_PIO_ACCESS_READ        0xF5
 #define W1_F3A_FUNC_PIO_ACCESS_WRITE       0x5A
 #define W1_F3A_SUCCESS_CONFIRM_BYTE        0xAA
+#define W1_F3A_INVALID_PIO_STATE           0xFF
 
 static ssize_t state_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);
+	unsigned int retries = W1_F3A_RETRIES;
+	ssize_t bytes_read = -EIO;
+	u8 state;
+
 	dev_dbg(&sl->dev,
 		"Reading %s kobj: %p, off: %0#10x, count: %zu, buff addr: %p",
 		bin_attr->attr.name, kobj, (unsigned int)off, count, buf);
@@ -40,22 +45,37 @@ static ssize_t state_read(struct file *filp, struct kobject *kobj,
 	mutex_lock(&sl->master->bus_mutex);
 	dev_dbg(&sl->dev, "mutex locked");
 
-	if (w1_reset_select_slave(sl)) {
-		mutex_unlock(&sl->master->bus_mutex);
-		return -EIO;
-	}
+next:
+	if (w1_reset_select_slave(sl))
+		goto out;
+
+	while (retries--) {
+		w1_write_8(sl->master, W1_F3A_FUNC_PIO_ACCESS_READ);
+
+		state = w1_read_8(sl->master);
+		if ((state & 0x0F) == ((~state >> 4) & 0x0F)) {
+			/* complement is correct */
+			*buf = state;
+			bytes_read = 1;
+			goto out;
+		} else if (state == W1_F3A_INVALID_PIO_STATE) {
+			/* slave didn't respond, try to select it again */
+			dev_warn(&sl->dev, "slave device did not respond to PIO_ACCESS_READ, " \
+					    "reselecting, retries left: %d\n", retries);
+			goto next;
+		}
 
-	w1_write_8(sl->master, W1_F3A_FUNC_PIO_ACCESS_READ);
-	*buf = w1_read_8(sl->master);
+		if (w1_reset_resume_command(sl->master))
+			goto out; /* unrecoverable error */
 
-	mutex_unlock(&sl->master->bus_mutex);
-	dev_dbg(&sl->dev, "mutex unlocked");
+		dev_warn(&sl->dev, "PIO_ACCESS_READ error, retries left: %d\n", retries);
+	}
 
-	/* check for correct complement */
-	if ((*buf & 0x0F) != ((~*buf >> 4) & 0x0F))
-		return -EIO;
-	else
-		return 1;
+out:
+	mutex_unlock(&sl->master->bus_mutex);
+	dev_dbg(&sl->dev, "%s, mutex unlocked, retries: %d\n",
+		(bytes_read > 0) ? "succeeded" : "error", retries);
+	return bytes_read;
 }
 
 static BIN_ATTR_RO(state, 1);
@@ -67,6 +87,7 @@ static ssize_t output_write(struct file *filp, struct kobject *kobj,
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
 	u8 w1_buf[3];
 	unsigned int retries = W1_F3A_RETRIES;
+	ssize_t bytes_written = -EIO;
 
 	if (count != 1 || off != 0)
 		return -EFAULT;
@@ -76,7 +97,7 @@ static ssize_t output_write(struct file *filp, struct kobject *kobj,
 	dev_dbg(&sl->dev, "mutex locked");
 
 	if (w1_reset_select_slave(sl))
-		goto error;
+		goto out;
 
 	/* according to the DS2413 datasheet the most significant 6 bits
 	   should be set to "1"s, so do it now */
@@ -89,18 +110,20 @@ static ssize_t output_write(struct file *filp, struct kobject *kobj,
 		w1_write_block(sl->master, w1_buf, 3);
 
 		if (w1_read_8(sl->master) == W1_F3A_SUCCESS_CONFIRM_BYTE) {
-			mutex_unlock(&sl->master->bus_mutex);
-			dev_dbg(&sl->dev, "mutex unlocked, retries:%d", retries);
-			return 1;
+			bytes_written = 1;
+			goto out;
 		}
 		if (w1_reset_resume_command(sl->master))
-			goto error;
+			goto out; /* unrecoverable error */
+
+		dev_warn(&sl->dev, "PIO_ACCESS_WRITE error, retries left: %d\n", retries);
 	}
 
-error:
+out:
 	mutex_unlock(&sl->master->bus_mutex);
-	dev_dbg(&sl->dev, "mutex unlocked in error, retries:%d", retries);
-	return -EIO;
+	dev_dbg(&sl->dev, "%s, mutex unlocked, retries: %d\n",
+		(bytes_written > 0) ? "succeeded" : "error", retries);
+	return bytes_written;
 }
 
 static BIN_ATTR(output, S_IRUGO | S_IWUSR | S_IWGRP, NULL, output_write, 1);
diff --git a/drivers/w1/slaves/w1_ds2805.c b/drivers/w1/slaves/w1_ds2805.c
index ee1ec9867a78..ccb753a474b1 100644
--- a/drivers/w1/slaves/w1_ds2805.c
+++ b/drivers/w1/slaves/w1_ds2805.c
@@ -286,7 +286,7 @@ static struct w1_family_ops w1_f0d_fops = {
 	.remove_slave   = w1_f0d_remove_slave,
 };
 
-static struct w1_family w1_family_2d = {
+static struct w1_family w1_family_0d = {
 	.fid = W1_EEPROM_DS2805,
 	.fops = &w1_f0d_fops,
 };
@@ -294,13 +294,13 @@ static struct w1_family w1_family_2d = {
 static int __init w1_f0d_init(void)
 {
 	pr_info("%s()\n", __func__);
-	return w1_register_family(&w1_family_2d);
+	return w1_register_family(&w1_family_0d);
 }
 
 static void __exit w1_f0d_fini(void)
 {
 	pr_info("%s()\n", __func__);
-	w1_unregister_family(&w1_family_2d);
+	w1_unregister_family(&w1_family_0d);
 }
 
 module_init(w1_f0d_init);