Merge tag 'misc-habanalabs-next-2022-02-28' of https://git.kernel.org/pub/scm/linux/kernel/git/ogabbay/linux into char-misc-next

Oded writes:

This tag contains habanalabs driver changes for v5.18:

- Add new feature of recording time-stamp when a completion
  queue counter reaches a target value as determined by the
  userspace application. This is used by the graph compiler
  to accurately measure the time it takes for certain workloads
  to execute, which helps to fine-tune future compilations.

- Add two new attributes to sysfs that expose the VRM and
  f/w OS version

- Add a delay to the reset path that allows the driver to
  receive and handle additional events from the f/w before
  doing the reset. This can help when debugging why a reset
  event was received from the f/w.

- Re-factor some of the sysfs code in the driver. Mainly,
  move functions from hwmgr.c to more relevant files and
  totally remove hwmgr.c file.

- Fix multiple bugs such as races, use-after-free, ignoring
  error codes, etc.

- As usual, multiple minor changes and small fixes.

* tag 'misc-habanalabs-next-2022-02-28' of https://git.kernel.org/pub/scm/linux/kernel/git/ogabbay/linux: (50 commits)
  habanalabs: remove deprecated firmware states
  habanalabs: add an option to delay a device reset
  habanalabs: Add check for pci_enable_device
  habanalabs: Fix reset upon device release bug
  habanalabs: make sure device mem alloc is page aligned
  habanalabs/gaudi: add missing handling of NIC related events
  habanalabs/gaudi: handle axi errors from NIC engines
  habanalabs: allow user to set allocation page size
  habanalabs: use kernel-doc for memory ioctl documentation
  habanalabs: avoid using an uninitialized variable
  habanalabs: set max power on device init per ASIC
  habanalabs: use proper max_power variable for device utilization
  habanalabs: enable stop-on-error debugfs setting per ASIC
  habanalabs: change function to static
  habanalabs: add missing include of vmalloc.h
  habanalabs: fix use-after-free bug
  habanalabs: rephrase error messages in PCI initialization
  habanalabs: fix spelling mistake
  habanalabs: Timestamps buffers registration
  habanalabs: fix race when waiting on encaps signal
  ...

24 files changed, 1393 insertions, 844 deletions

diff --git a/drivers/misc/habanalabs/common/Makefile b/drivers/misc/habanalabs/common/Makefile
index 82c3824cad00..6ebe3c7001ff 100644
--- a/drivers/misc/habanalabs/common/Makefile
+++ b/drivers/misc/habanalabs/common/Makefile
@@ -11,4 +11,4 @@ HL_COMMON_FILES := common/habanalabs_drv.o common/device.o common/context.o \
 		common/command_buffer.o common/hw_queue.o common/irq.o \
 		common/sysfs.o common/hwmon.o common/memory.o \
 		common/command_submission.o common/firmware_if.o \
-		common/state_dump.o common/hwmgr.o
+		common/state_dump.o
diff --git a/drivers/misc/habanalabs/common/command_buffer.c b/drivers/misc/habanalabs/common/command_buffer.c
index 3c0ae07a2d80..a507110f6443 100644
--- a/drivers/misc/habanalabs/common/command_buffer.c
+++ b/drivers/misc/habanalabs/common/command_buffer.c
@@ -424,8 +424,8 @@ int hl_cb_ioctl(struct hl_fpriv *hpriv, void *data)
 {
 	union hl_cb_args *args = data;
 	struct hl_device *hdev = hpriv->hdev;
+	u64 handle = 0, device_va = 0;
 	enum hl_device_status status;
-	u64 handle = 0, device_va;
 	u32 usage_cnt = 0;
 	int rc;
 
@@ -464,6 +464,8 @@ int hl_cb_ioctl(struct hl_fpriv *hpriv, void *data)
 				args->in.flags,
 				&usage_cnt,
 				&device_va);
+		if (rc)
+			break;
 
 		memset(&args->out, 0, sizeof(args->out));
 
diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c
index 0a4ef13d9ac4..d93ef9f1c45c 100644
--- a/drivers/misc/habanalabs/common/command_submission.c
+++ b/drivers/misc/habanalabs/common/command_submission.c
@@ -14,6 +14,8 @@
 #define HL_CS_FLAGS_TYPE_MASK	(HL_CS_FLAGS_SIGNAL | HL_CS_FLAGS_WAIT | \
 				HL_CS_FLAGS_COLLECTIVE_WAIT)
 
+#define MAX_TS_ITER_NUM 10
+
 /**
  * enum hl_cs_wait_status - cs wait status
  * @CS_WAIT_STATUS_BUSY: cs was not completed yet
@@ -919,18 +921,21 @@ static void cs_rollback(struct hl_device *hdev, struct hl_cs *cs)
 		complete_job(hdev, job);
 }
 
-void hl_cs_rollback_all(struct hl_device *hdev)
+void hl_cs_rollback_all(struct hl_device *hdev, bool skip_wq_flush)
 {
 	int i;
 	struct hl_cs *cs, *tmp;
 
-	flush_workqueue(hdev->sob_reset_wq);
+	if (!skip_wq_flush) {
+		flush_workqueue(hdev->ts_free_obj_wq);
 
-	/* flush all completions before iterating over the CS mirror list in
-	 * order to avoid a race with the release functions
-	 */
-	for (i = 0 ; i < hdev->asic_prop.completion_queues_count ; i++)
-		flush_workqueue(hdev->cq_wq[i]);
+		/* flush all completions before iterating over the CS mirror list in
+		 * order to avoid a race with the release functions
+		 */
+		for (i = 0 ; i < hdev->asic_prop.completion_queues_count ; i++)
+			flush_workqueue(hdev->cq_wq[i]);
+
+	}
 
 	/* Make sure we don't have leftovers in the CS mirror list */
 	list_for_each_entry_safe(cs, tmp, &hdev->cs_mirror_list, mirror_node) {
@@ -948,13 +953,19 @@ void hl_cs_rollback_all(struct hl_device *hdev)
 static void
 wake_pending_user_interrupt_threads(struct hl_user_interrupt *interrupt)
 {
-	struct hl_user_pending_interrupt *pend;
+	struct hl_user_pending_interrupt *pend, *temp;
 	unsigned long flags;
 
 	spin_lock_irqsave(&interrupt->wait_list_lock, flags);
-	list_for_each_entry(pend, &interrupt->wait_list_head, wait_list_node) {
-		pend->fence.error = -EIO;
-		complete_all(&pend->fence.completion);
+	list_for_each_entry_safe(pend, temp, &interrupt->wait_list_head, wait_list_node) {
+		if (pend->ts_reg_info.ts_buff) {
+			list_del(&pend->wait_list_node);
+			hl_ts_put(pend->ts_reg_info.ts_buff);
+			hl_cb_put(pend->ts_reg_info.cq_cb);
+		} else {
+			pend->fence.error = -EIO;
+			complete_all(&pend->fence.completion);
+		}
 	}
 	spin_unlock_irqrestore(&interrupt->wait_list_lock, flags);
 }
@@ -2063,13 +2074,16 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type,
 			idp = &ctx->sig_mgr.handles;
 			idr_for_each_entry(idp, encaps_sig_hdl, id) {
 				if (encaps_sig_hdl->cs_seq == signal_seq) {
-					handle_found = true;
-					/* get refcount to protect removing
-					 * this handle from idr, needed when
-					 * multiple wait cs are used with offset
+					/* get refcount to protect removing this handle from idr,
+					 * needed when multiple wait cs are used with offset
 					 * to wait on reserved encaps signals.
+					 * Since kref_put of this handle is executed outside the
+					 * current lock, it is possible that the handle refcount
+					 * is 0 but it yet to be removed from the list. In this
+					 * case need to consider the handle as not valid.
 					 */
-					kref_get(&encaps_sig_hdl->refcount);
+					if (kref_get_unless_zero(&encaps_sig_hdl->refcount))
+						handle_found = true;
 					break;
 				}
 			}
@@ -2739,7 +2753,7 @@ static int hl_multi_cs_wait_ioctl(struct hl_fpriv *hpriv, void *data)
 		mcs_data.update_ts = false;
 		rc = hl_cs_poll_fences(&mcs_data, mcs_compl);
 
-		if (mcs_data.completion_bitmap)
+		if (rc || mcs_data.completion_bitmap)
 			break;
 
 		/*
@@ -2854,64 +2868,174 @@ static int hl_cs_wait_ioctl(struct hl_fpriv *hpriv, void *data)
 	return 0;
 }
 
+static int ts_buff_get_kernel_ts_record(struct hl_ts_buff *ts_buff,
+					struct hl_cb *cq_cb,
+					u64 ts_offset, u64 cq_offset, u64 target_value,
+					spinlock_t *wait_list_lock,
+					struct hl_user_pending_interrupt **pend)
+{
+	struct hl_user_pending_interrupt *requested_offset_record =
+				(struct hl_user_pending_interrupt *)ts_buff->kernel_buff_address +
+				ts_offset;
+	struct hl_user_pending_interrupt *cb_last =
+			(struct hl_user_pending_interrupt *)ts_buff->kernel_buff_address +
+			(ts_buff->kernel_buff_size / sizeof(struct hl_user_pending_interrupt));
+	unsigned long flags, iter_counter = 0;
+	u64 current_cq_counter;
+
+	/* Validate ts_offset not exceeding last max */
+	if (requested_offset_record > cb_last) {
+		dev_err(ts_buff->hdev->dev, "Ts offset exceeds max CB offset(0x%llx)\n",
+								(u64)(uintptr_t)cb_last);
+		return -EINVAL;
+	}
+
+start_over:
+	spin_lock_irqsave(wait_list_lock, flags);
+
+	/* Unregister only if we didn't reach the target value
+	 * since in this case there will be no handling in irq context
+	 * and then it's safe to delete the node out of the interrupt list
+	 * then re-use it on other interrupt
+	 */
+	if (requested_offset_record->ts_reg_info.in_use) {
+		current_cq_counter = *requested_offset_record->cq_kernel_addr;
+		if (current_cq_counter < requested_offset_record->cq_target_value) {
+			list_del(&requested_offset_record->wait_list_node);
+			spin_unlock_irqrestore(wait_list_lock, flags);
+
+			hl_ts_put(requested_offset_record->ts_reg_info.ts_buff);
+			hl_cb_put(requested_offset_record->ts_reg_info.cq_cb);
+
+			dev_dbg(ts_buff->hdev->dev, "ts node removed from interrupt list now can re-use\n");
+		} else {
+			dev_dbg(ts_buff->hdev->dev, "ts node in middle of irq handling\n");
+
+			/* irq handling in the middle give it time to finish */
+			spin_unlock_irqrestore(wait_list_lock, flags);
+			usleep_range(1, 10);
+			if (++iter_counter == MAX_TS_ITER_NUM) {
+				dev_err(ts_buff->hdev->dev, "handling registration interrupt took too long!!\n");
+				return -EINVAL;
+			}
+
+			goto start_over;
+		}
+	} else {
+		spin_unlock_irqrestore(wait_list_lock, flags);
+	}
+
+	/* Fill up the new registration node info */
+	requested_offset_record->ts_reg_info.in_use = 1;
+	requested_offset_record->ts_reg_info.ts_buff = ts_buff;
+	requested_offset_record->ts_reg_info.cq_cb = cq_cb;
+	requested_offset_record->ts_reg_info.timestamp_kernel_addr =
+			(u64 *) ts_buff->user_buff_address + ts_offset;
+	requested_offset_record->cq_kernel_addr =
+			(u64 *) cq_cb->kernel_address + cq_offset;
+	requested_offset_record->cq_target_value = target_value;
+
+	*pend = requested_offset_record;
+
+	dev_dbg(ts_buff->hdev->dev, "Found available node in TS kernel CB(0x%llx)\n",
+						(u64)(uintptr_t)requested_offset_record);
+	return 0;
+}
+
 static int _hl_interrupt_wait_ioctl(struct hl_device *hdev, struct hl_ctx *ctx,
-				struct hl_cb_mgr *cb_mgr, u64 timeout_us,
-				u64 cq_counters_handle,	u64 cq_counters_offset,
+				struct hl_cb_mgr *cb_mgr, struct hl_ts_mgr *ts_mgr,
+				u64 timeout_us, u64 cq_counters_handle,	u64 cq_counters_offset,
 				u64 target_value, struct hl_user_interrupt *interrupt,
-				u32 *status,
-				u64 *timestamp)
+				bool register_ts_record, u64 ts_handle, u64 ts_offset,
+				u32 *status, u64 *timestamp)
 {
+	u32 cq_patched_handle, ts_patched_handle;
 	struct hl_user_pending_interrupt *pend;
+	struct hl_ts_buff *ts_buff;
+	struct hl_cb *cq_cb;
 	unsigned long timeout, flags;
 	long completion_rc;
-	struct hl_cb *cb;
 	int rc = 0;
-	u32 handle;
 
 	timeout = hl_usecs64_to_jiffies(timeout_us);
 
 	hl_ctx_get(hdev, ctx);
 
-	cq_counters_handle >>= PAGE_SHIFT;
-	handle = (u32) cq_counters_handle;
-
-	cb = hl_cb_get(hdev, cb_mgr, handle);
-	if (!cb) {
-		hl_ctx_put(ctx);
-		return -EINVAL;
+	cq_patched_handle = lower_32_bits(cq_counters_handle >> PAGE_SHIFT);
+	cq_cb = hl_cb_get(hdev, cb_mgr, cq_patched_handle);
+	if (!cq_cb) {
+		rc = -EINVAL;
+		goto put_ctx;
 	}
 
-	pend = kzalloc(sizeof(*pend), GFP_KERNEL);
-	if (!pend) {
-		hl_cb_put(cb);
-		hl_ctx_put(ctx);
-		return -ENOMEM;
-	}
+	if (register_ts_record) {
+		dev_dbg(hdev->dev, "Timestamp registration: interrupt id: %u, ts offset: %llu, cq_offset: %llu\n",
+					interrupt->interrupt_id, ts_offset, cq_counters_offset);
 
-	hl_fence_init(&pend->fence, ULONG_MAX);
+		ts_patched_handle = lower_32_bits(ts_handle >> PAGE_SHIFT);
+		ts_buff = hl_ts_get(hdev, ts_mgr, ts_patched_handle);
+		if (!ts_buff) {
+			rc = -EINVAL;
+			goto put_cq_cb;
+		}
 
-	pend->cq_kernel_addr = (u64 *) cb->kernel_address + cq_counters_offset;
-	pend->cq_target_value = target_value;
+		/* Find first available record */
+		rc = ts_buff_get_kernel_ts_record(ts_buff, cq_cb, ts_offset,
+						cq_counters_offset, target_value,
+						&interrupt->wait_list_lock, &pend);
+		if (rc)
+			goto put_ts_buff;
+	} else {
+		pend = kzalloc(sizeof(*pend), GFP_KERNEL);
+		if (!pend) {
+			rc = -ENOMEM;
+			goto put_cq_cb;
+		}
+		hl_fence_init(&pend->fence, ULONG_MAX);
+		pend->cq_kernel_addr = (u64 *) cq_cb->kernel_address + cq_counters_offset;
+		pend->cq_target_value = target_value;
+	}
+
+	spin_lock_irqsave(&interrupt->wait_list_lock, flags);
 
 	/* We check for completion value as interrupt could have been received
 	 * before we added the node to the wait list
 	 */
 	if (*pend->cq_kernel_addr >= target_value) {
+		if (register_ts_record)
+			pend->ts_reg_info.in_use = 0;
+		spin_unlock_irqrestore(&interrupt->wait_list_lock, flags);
+
 		*status = HL_WAIT_CS_STATUS_COMPLETED;
-		/* There was no interrupt, we assume the completion is now. */
-		pend->fence.timestamp = ktime_get();
-	}
 
-	if (!timeout_us || (*status == HL_WAIT_CS_STATUS_COMPLETED))
+		if (register_ts_record) {
+			*pend->ts_reg_info.timestamp_kernel_addr = ktime_get_ns();
+			goto put_ts_buff;
+		} else {
+			pend->fence.timestamp = ktime_get();
+			goto set_timestamp;
+		}
+	} else if (!timeout_us) {
+		spin_unlock_irqrestore(&interrupt->wait_list_lock, flags);
+		*status = HL_WAIT_CS_STATUS_BUSY;
+		pend->fence.timestamp = ktime_get();
 		goto set_timestamp;
+	}
 
 	/* Add pending user interrupt to relevant list for the interrupt
-	 * handler to monitor
+	 * handler to monitor.
+	 * Note that we cannot have sorted list by target value,
+	 * in order to shorten the list pass loop, since
+	 * same list could have nodes for different cq counter handle.
 	 */
-	spin_lock_irqsave(&interrupt->wait_list_lock, flags);
 	list_add_tail(&pend->wait_list_node, &interrupt->wait_list_head);
 	spin_unlock_irqrestore(&interrupt->wait_list_lock, flags);
 
+	if (register_ts_record) {
+		rc = *status = HL_WAIT_CS_STATUS_COMPLETED;
+		goto ts_registration_exit;
+	}
+
 	/* Wait for interrupt handler to signal completion */
 	completion_rc = wait_for_completion_interruptible_timeout(&pend->fence.completion,
 								timeout);
@@ -2932,23 +3056,41 @@ static int _hl_interrupt_wait_ioctl(struct hl_device *hdev, struct hl_ctx *ctx,
 				rc = -EIO;
 				*status = HL_WAIT_CS_STATUS_ABORTED;
 			} else {
-				dev_err_ratelimited(hdev->dev, "Waiting for interrupt ID %d timedout\n",
-						interrupt->interrupt_id);
-				rc = -ETIMEDOUT;
+				/* The wait has timed-out. We don't know anything beyond that
+				 * because the workload wasn't submitted through the driver.
+				 * Therefore, from driver's perspective, the workload is still
+				 * executing.
+				 */
+				rc = 0;
+				*status = HL_WAIT_CS_STATUS_BUSY;
 			}
-			*status = HL_WAIT_CS_STATUS_BUSY;
 		}
 	}
 
+	/*
+	 * We keep removing the node from list here, and not at the irq handler
+	 * for completion timeout case. and if it's a registration
+	 * for ts record, the node will be deleted in the irq handler after
+	 * we reach the target value.
+	 */
 	spin_lock_irqsave(&interrupt->wait_list_lock, flags);
 	list_del(&pend->wait_list_node);
 	spin_unlock_irqrestore(&interrupt->wait_list_lock, flags);
 
 set_timestamp:
 	*timestamp = ktime_to_ns(pend->fence.timestamp);
-
 	kfree(pend);
-	hl_cb_put(cb);
+	hl_cb_put(cq_cb);
+ts_registration_exit:
+	hl_ctx_put(ctx);
+
+	return rc;
+
+put_ts_buff:
+	hl_ts_put(ts_buff);
+put_cq_cb:
+	hl_cb_put(cq_cb);
+put_ctx:
 	hl_ctx_put(ctx);
 
 	return rc;
@@ -3049,6 +3191,12 @@ wait_again:
 			interrupt->interrupt_id);
 		rc = -EINTR;
 	} else {
+		/* The wait has timed-out. We don't know anything beyond that
+		 * because the workload wasn't submitted through the driver.
+		 * Therefore, from driver's perspective, the workload is still
+		 * executing.
+		 */
+		rc = 0;
 		*status = HL_WAIT_CS_STATUS_BUSY;
 	}
 
@@ -3101,23 +3249,20 @@ static int hl_interrupt_wait_ioctl(struct hl_fpriv *hpriv, void *data)
 		interrupt = &hdev->user_interrupt[interrupt_id - first_interrupt];
 
 	if (args->in.flags & HL_WAIT_CS_FLAGS_INTERRUPT_KERNEL_CQ)
-		rc = _hl_interrupt_wait_ioctl(hdev, hpriv->ctx, &hpriv->cb_mgr,
+		rc = _hl_interrupt_wait_ioctl(hdev, hpriv->ctx, &hpriv->cb_mgr, &hpriv->ts_mem_mgr,
 				args->in.interrupt_timeout_us, args->in.cq_counters_handle,
 				args->in.cq_counters_offset,
-				args->in.target, interrupt, &status,
-				&timestamp);
+				args->in.target, interrupt,
+				!!(args->in.flags & HL_WAIT_CS_FLAGS_REGISTER_INTERRUPT),
+				args->in.timestamp_handle, args->in.timestamp_offset,
+				&status, &timestamp);
 	else
 		rc = _hl_interrupt_wait_ioctl_user_addr(hdev, hpriv->ctx,
 				args->in.interrupt_timeout_us, args->in.addr,
 				args->in.target, interrupt, &status,
 				&timestamp);
-	if (rc) {
-		if (rc != -EINTR)
-			dev_err_ratelimited(hdev->dev,
-				"interrupt_wait_ioctl failed (%d)\n", rc);
-
+	if (rc)
 		return rc;
-	}
 
 	memset(args, 0, sizeof(*args));
 	args->out.status = status;
diff --git a/drivers/misc/habanalabs/common/debugfs.c b/drivers/misc/habanalabs/common/debugfs.c
index fc084ee5106e..f18495545854 100644
--- a/drivers/misc/habanalabs/common/debugfs.c
+++ b/drivers/misc/habanalabs/common/debugfs.c
@@ -890,6 +890,8 @@ static ssize_t hl_set_power_state(struct file *f, const char __user *buf,
 		pci_set_power_state(hdev->pdev, PCI_D0);
 		pci_restore_state(hdev->pdev);
 		rc = pci_enable_device(hdev->pdev);
+		if (rc < 0)
+			return rc;
 	} else if (value == 2) {
 		pci_save_state(hdev->pdev);
 		pci_disable_device(hdev->pdev);
@@ -1054,42 +1056,12 @@ static ssize_t hl_device_write(struct file *f, const char __user *buf,
 static ssize_t hl_clk_gate_read(struct file *f, char __user *buf,
 					size_t count, loff_t *ppos)
 {
-	struct hl_dbg_device_entry *entry = file_inode(f)->i_private;
-	struct hl_device *hdev = entry->hdev;
-	char tmp_buf[200];
-	ssize_t rc;
-
-	if (*ppos)
-		return 0;
-
-	sprintf(tmp_buf, "0x%llx\n", hdev->clock_gating_mask);
-	rc = simple_read_from_buffer(buf, count, ppos, tmp_buf,
-			strlen(tmp_buf) + 1);
-
-	return rc;
+	return 0;
 }
 
 static ssize_t hl_clk_gate_write(struct file *f, const char __user *buf,
 				     size_t count, loff_t *ppos)
 {
-	struct hl_dbg_device_entry *entry = file_inode(f)->i_private;
-	struct hl_device *hdev = entry->hdev;
-	u64 value;
-	ssize_t rc;
-
-	if (hdev->reset_info.in_reset) {
-		dev_warn_ratelimited(hdev->dev,
-				"Can't change clock gating during reset\n");
-		return 0;
-	}
-
-	rc = kstrtoull_from_user(buf, count, 16, &value);
-	if (rc)
-		return rc;
-
-	hdev->clock_gating_mask = value;
-	hdev->asic_funcs->set_clock_gating(hdev);
-
 	return count;
 }
 
@@ -1101,6 +1073,9 @@ static ssize_t hl_stop_on_err_read(struct file *f, char __user *buf,
 	char tmp_buf[200];
 	ssize_t rc;
 
+	if (!hdev->asic_prop.configurable_stop_on_err)
+		return -EOPNOTSUPP;
+
 	if (*ppos)
 		return 0;
 
@@ -1119,6 +1094,9 @@ static ssize_t hl_stop_on_err_write(struct file *f, const char __user *buf,
 	u32 value;
 	ssize_t rc;
 
+	if (!hdev->asic_prop.configurable_stop_on_err)
+		return -EOPNOTSUPP;
+
 	if (hdev->reset_info.in_reset) {
 		dev_warn_ratelimited(hdev->dev,
 				"Can't change stop on error during reset\n");
diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c
index 733338ab6f1d..dc9341a64541 100644
--- a/drivers/misc/habanalabs/common/device.c
+++ b/drivers/misc/habanalabs/common/device.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 /*
- * Copyright 2016-2021 HabanaLabs, Ltd.
+ * Copyright 2016-2022 HabanaLabs, Ltd.
  * All Rights Reserved.
  */
 
@@ -13,6 +13,8 @@
 #include <linux/pci.h>
 #include <linux/hwmon.h>
 
+#define HL_RESET_DELAY_USEC		10000	/* 10ms */
+
 enum hl_device_status hl_device_status(struct hl_device *hdev)
 {
 	enum hl_device_status status;
@@ -145,6 +147,7 @@ static int hl_device_release(struct inode *inode, struct file *filp)
 	hl_release_pending_user_interrupts(hpriv->hdev);
 
 	hl_cb_mgr_fini(hdev, &hpriv->cb_mgr);
+	hl_ts_mgr_fini(hpriv->hdev, &hpriv->ts_mem_mgr);
 	hl_ctx_mgr_fini(hdev, &hpriv->ctx_mgr);
 
 	if (!hl_hpriv_put(hpriv))
@@ -209,6 +212,9 @@ static int hl_mmap(struct file *filp, struct vm_area_struct *vma)
 
 	case HL_MMAP_TYPE_BLOCK:
 		return hl_hw_block_mmap(hpriv, vma);
+
+	case HL_MMAP_TYPE_TS_BUFF:
+		return hl_ts_mmap(hpriv, vma);
 	}
 
 	return -EINVAL;
@@ -410,10 +416,10 @@ static int device_early_init(struct hl_device *hdev)
 		goto free_cq_wq;
 	}
 
-	hdev->sob_reset_wq = alloc_workqueue("hl-sob-reset", WQ_UNBOUND, 0);
-	if (!hdev->sob_reset_wq) {
+	hdev->ts_free_obj_wq = alloc_workqueue("hl-ts-free-obj", WQ_UNBOUND, 0);
+	if (!hdev->ts_free_obj_wq) {
 		dev_err(hdev->dev,
-			"Failed to allocate SOB reset workqueue\n");
+			"Failed to allocate Timestamp registration free workqueue\n");
 		rc = -ENOMEM;
 		goto free_eq_wq;
 	}
@@ -422,7 +428,7 @@ static int device_early_init(struct hl_device *hdev)
 					GFP_KERNEL);
 	if (!hdev->hl_chip_info) {
 		rc = -ENOMEM;
-		goto free_sob_reset_wq;
+		goto free_ts_free_wq;
 	}
 
 	rc = hl_mmu_if_set_funcs(hdev);
@@ -461,8 +467,8 @@ free_cb_mgr:
 	hl_cb_mgr_fini(hdev, &hdev->kernel_cb_mgr);
 free_chip_info:
 	kfree(hdev->hl_chip_info);
-free_sob_reset_wq:
-	destroy_workqueue(hdev->sob_reset_wq);
+free_ts_free_wq:
+	destroy_workqueue(hdev->ts_free_obj_wq);
 free_eq_wq:
 	destroy_workqueue(hdev->eq_wq);
 free_cq_wq:
@@ -501,7 +507,7 @@ static void device_early_fini(struct hl_device *hdev)
 
 	kfree(hdev->hl_chip_info);
 
-	destroy_workqueue(hdev->sob_reset_wq);
+	destroy_workqueue(hdev->ts_free_obj_wq);
 	destroy_workqueue(hdev->eq_wq);
 	destroy_workqueue(hdev->device_reset_work.wq);
 
@@ -610,7 +616,7 @@ int hl_device_utilization(struct hl_device *hdev, u32 *utilization)
 	u64 max_power, curr_power, dc_power, dividend;
 	int rc;
 
-	max_power = hdev->asic_prop.max_power_default;
+	max_power = hdev->max_power;
 	dc_power = hdev->asic_prop.dc_power_default;
 	rc = hl_fw_cpucp_power_get(hdev, &curr_power);
 
@@ -644,9 +650,6 @@ int hl_device_set_debug_mode(struct hl_device *hdev, struct hl_ctx *ctx, bool en
 
 		hdev->in_debug = 0;
 
-		if (!hdev->reset_info.hard_reset_pending)
-			hdev->asic_funcs->set_clock_gating(hdev);
-
 		goto out;
 	}
 
@@ -657,7 +660,6 @@ int hl_device_set_debug_mode(struct hl_device *hdev, struct hl_ctx *ctx, bool en
 		goto out;
 	}
 
-	hdev->asic_funcs->disable_clock_gating(hdev);
 	hdev->in_debug = 1;
 
 out:
@@ -685,7 +687,8 @@ static void take_release_locks(struct hl_device *hdev)
 	mutex_unlock(&hdev->fpriv_ctrl_list_lock);
 }
 
-static void cleanup_resources(struct hl_device *hdev, bool hard_reset, bool fw_reset)
+static void cleanup_resources(struct hl_device *hdev, bool hard_reset, bool fw_reset,
+				bool skip_wq_flush)
 {
 	if (hard_reset)
 		device_late_fini(hdev);
@@ -698,7 +701,7 @@ static void cleanup_resources(struct hl_device *hdev, bool hard_reset, bool fw_r
 	hdev->asic_funcs->halt_engines(hdev, hard_reset, fw_reset);
 
 	/* Go over all the queues, release all CS and their jobs */
-	hl_cs_rollback_all(hdev);
+	hl_cs_rollback_all(hdev, skip_wq_flush);
 
 	/* Release all pending user interrupts, each pending user interrupt
 	 * holds a reference to user context
@@ -978,7 +981,8 @@ static void handle_reset_trigger(struct hl_device *hdev, u32 flags)
 int hl_device_reset(struct hl_device *hdev, u32 flags)
 {
 	bool hard_reset, from_hard_reset_thread, fw_reset, hard_instead_soft = false,
-			reset_upon_device_release = false, schedule_hard_reset = false;
+			reset_upon_device_release = false, schedule_hard_reset = false,
+			skip_wq_flush, delay_reset;
 	u64 idle_mask[HL_BUSY_ENGINES_MASK_EXT_SIZE] = {0};
 	struct hl_ctx *ctx;
 	int i, rc;
@@ -991,6 +995,8 @@ int hl_device_reset(struct hl_device *hdev, u32 flags)
 	hard_reset = !!(flags & HL_DRV_RESET_HARD);
 	from_hard_reset_thread = !!(flags & HL_DRV_RESET_FROM_RESET_THR);
 	fw_reset = !!(flags & HL_DRV_RESET_BYPASS_REQ_TO_FW);
+	skip_wq_flush = !!(flags & HL_DRV_RESET_DEV_RELEASE);
+	delay_reset = !!(flags & HL_DRV_RESET_DELAY);
 
 	if (!hard_reset && !hdev->asic_prop.supports_soft_reset) {
 		hard_instead_soft = true;
@@ -1040,6 +1046,9 @@ do_reset:
 		hdev->reset_info.in_reset = 1;
 		spin_unlock(&hdev->reset_info.lock);
 
+		if (delay_reset)
+			usleep_range(HL_RESET_DELAY_USEC, HL_RESET_DELAY_USEC << 1);
+
 		handle_reset_trigger(hdev, flags);
 
 		/* This still allows the completion of some KDMA ops */
@@ -1076,7 +1085,7 @@ again:
 		return 0;
 	}
 
-	cleanup_resources(hdev, hard_reset, fw_reset);
+	cleanup_resources(hdev, hard_reset, fw_reset, skip_wq_flush);
 
 kill_processes:
 	if (hard_reset) {
@@ -1232,7 +1241,7 @@ kill_processes:
 			goto out_err;
 		}
 
-		hl_set_max_power(hdev);
+		hl_fw_set_max_power(hdev);
 	} else {
 		rc = hdev->asic_funcs->non_hard_reset_late_init(hdev);
 		if (rc) {
@@ -1297,11 +1306,14 @@ out_err:
 		hdev->reset_info.hard_reset_cnt++;
 	} else if (reset_upon_device_release) {
 		dev_err(hdev->dev, "Failed to reset device after user release\n");
+		flags |= HL_DRV_RESET_HARD;
+		flags &= ~HL_DRV_RESET_DEV_RELEASE;
 		hard_reset = true;
 		goto again;
 	} else {
 		dev_err(hdev->dev, "Failed to do soft-reset\n");
 		hdev->reset_info.soft_reset_cnt++;
+		flags |= HL_DRV_RESET_HARD;
 		hard_reset = true;
 		goto again;
 	}
@@ -1538,7 +1550,8 @@ int hl_device_init(struct hl_device *hdev, struct class *hclass)
 	/* Need to call this again because the max power might change,
 	 * depending on card type for certain ASICs
 	 */
-	hl_set_max_power(hdev);
+	if (hdev->asic_prop.set_max_power_on_device_init)
+		hl_fw_set_max_power(hdev);
 
 	/*
 	 * hl_hwmon_init() must be called after device_late_init(), because only
@@ -1682,7 +1695,7 @@ void hl_device_fini(struct hl_device *hdev)
 
 	hl_hwmon_fini(hdev);
 
-	cleanup_resources(hdev, true, false);
+	cleanup_resources(hdev, true, false, false);
 
 	/* Kill processes here after CS rollback. This is because the process
 	 * can't really exit until all its CSs are done, which is what we
diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
index 6775c5c3166b..3262126cc7ca 100644
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 /*
- * Copyright 2016-2021 HabanaLabs, Ltd.
+ * Copyright 2016-2022 HabanaLabs, Ltd.
  * All Rights Reserved.
  */
 
@@ -214,7 +214,7 @@ int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
 	dma_addr_t pkt_dma_addr;
 	struct hl_bd *sent_bd;
 	u32 tmp, expected_ack_val, pi;
-	int rc = 0;
+	int rc;
 
 	pkt = hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev, len,
 								&pkt_dma_addr);
@@ -228,8 +228,11 @@ int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
 
 	mutex_lock(&hdev->send_cpu_message_lock);
 
-	if (hdev->disabled)
+	/* CPU-CP messages can be sent during soft-reset */
+	if (hdev->disabled && !hdev->reset_info.is_in_soft_reset) {
+		rc = 0;
 		goto out;
+	}
 
 	if (hdev->device_cpu_disabled) {
 		rc = -EIO;
@@ -958,15 +961,17 @@ int hl_fw_cpucp_pll_info_get(struct hl_device *hdev, u32 pll_index,
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
 			HL_CPUCP_INFO_TIMEOUT_USEC, &result);
-	if (rc)
+	if (rc) {
 		dev_err(hdev->dev, "Failed to read PLL info, error %d\n", rc);
+		return rc;
+	}
 
 	pll_freq_arr[0] = FIELD_GET(CPUCP_PKT_RES_PLL_OUT0_MASK, result);
 	pll_freq_arr[1] = FIELD_GET(CPUCP_PKT_RES_PLL_OUT1_MASK, result);
 	pll_freq_arr[2] = FIELD_GET(CPUCP_PKT_RES_PLL_OUT2_MASK, result);
 	pll_freq_arr[3] = FIELD_GET(CPUCP_PKT_RES_PLL_OUT3_MASK, result);
 
-	return rc;
+	return 0;
 }
 
 int hl_fw_cpucp_power_get(struct hl_device *hdev, u64 *power)
@@ -1202,8 +1207,6 @@ static int hl_fw_read_preboot_caps(struct hl_device *hdev,
 		hdev,
 		cpu_boot_status_reg,
 		status,
-		(status == CPU_BOOT_STATUS_IN_UBOOT) ||
-		(status == CPU_BOOT_STATUS_DRAM_RDY) ||
 		(status == CPU_BOOT_STATUS_NIC_FW_RDY) ||
 		(status == CPU_BOOT_STATUS_READY_TO_BOOT) ||
 		(status == CPU_BOOT_STATUS_WAITING_FOR_BOOT_FIT),
@@ -2682,3 +2685,138 @@ int hl_fw_init_cpu(struct hl_device *hdev)
 			hl_fw_dynamic_init_cpu(hdev, fw_loader) :
 			hl_fw_static_init_cpu(hdev, fw_loader);
 }
+
+void hl_fw_set_pll_profile(struct hl_device *hdev)
+{
+	hl_fw_set_frequency(hdev, hdev->asic_prop.clk_pll_index,
+				hdev->asic_prop.max_freq_value);
+}
+
+int hl_fw_get_clk_rate(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk)
+{
+	long value;
+
+	if (!hl_device_operational(hdev, NULL))
+		return -ENODEV;
+
+	if (!hdev->pdev) {
+		*cur_clk = 0;
+		*max_clk = 0;
+		return 0;
+	}
+
+	value = hl_fw_get_frequency(hdev, hdev->asic_prop.clk_pll_index, false);
+
+	if (value < 0) {
+		dev_err(hdev->dev, "Failed to retrieve device max clock %ld\n", value);
+		return value;
+	}
+
+	*max_clk = (value / 1000 / 1000);
+
+	value = hl_fw_get_frequency(hdev, hdev->asic_prop.clk_pll_index, true);
+
+	if (value < 0) {
+		dev_err(hdev->dev, "Failed to retrieve device current clock %ld\n", value);
+		return value;
+	}
+
+	*cur_clk = (value / 1000 / 1000);
+
+	return 0;
+}
+
+long hl_fw_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr)
+{
+	struct cpucp_packet pkt;
+	u32 used_pll_idx;
+	u64 result;
+	int rc;
+
+	rc = get_used_pll_index(hdev, pll_index, &used_pll_idx);
+	if (rc)
+		return rc;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	if (curr)
+		pkt.ctl = cpu_to_le32(CPUCP_PACKET_FREQUENCY_CURR_GET <<
+						CPUCP_PKT_CTL_OPCODE_SHIFT);
+	else
+		pkt.ctl = cpu_to_le32(CPUCP_PACKET_FREQUENCY_GET << CPUCP_PKT_CTL_OPCODE_SHIFT);
+
+	pkt.pll_index = cpu_to_le32((u32)used_pll_idx);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, &result);
+
+	if (rc) {
+		dev_err(hdev->dev, "Failed to get frequency of PLL %d, error %d\n",
+			used_pll_idx, rc);
+		return rc;
+	}
+
+	return (long) result;
+}
+
+void hl_fw_set_frequency(struct hl_device *hdev, u32 pll_index, u64 freq)
+{
+	struct cpucp_packet pkt;
+	u32 used_pll_idx;
+	int rc;
+
+	rc = get_used_pll_index(hdev, pll_index, &used_pll_idx);
+	if (rc)
+		return;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_FREQUENCY_SET << CPUCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.pll_index = cpu_to_le32((u32)used_pll_idx);
+	pkt.value = cpu_to_le64(freq);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, NULL);
+
+	if (rc)
+		dev_err(hdev->dev, "Failed to set frequency to PLL %d, error %d\n",
+			used_pll_idx, rc);
+}
+
+long hl_fw_get_max_power(struct hl_device *hdev)
+{
+	struct cpucp_packet pkt;
+	u64 result;
+	int rc;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_MAX_POWER_GET << CPUCP_PKT_CTL_OPCODE_SHIFT);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, &result);
+
+	if (rc) {
+		dev_err(hdev->dev, "Failed to get max power, error %d\n", rc);
+		return rc;
+	}
+
+	return result;
+}
+
+void hl_fw_set_max_power(struct hl_device *hdev)
+{
+	struct cpucp_packet pkt;
+	int rc;
+
+	/* TODO: remove this after simulator supports this packet */
+	if (!hdev->pdev)
+		return;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_MAX_POWER_SET << CPUCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.value = cpu_to_le64(hdev->max_power);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, NULL);
+
+	if (rc)
+		dev_err(hdev->dev, "Failed to set max power, error %d\n", rc);
+}
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index cb710fd478b6..1edaf6ab67bd 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0
  *
- * Copyright 2016-2021 HabanaLabs, Ltd.
+ * Copyright 2016-2022 HabanaLabs, Ltd.
  * All Rights Reserved.
  *
  */
@@ -31,14 +31,15 @@
 #define HL_NAME				"habanalabs"
 
 /* Use upper bits of mmap offset to store habana driver specific information.
- * bits[63:61] - Encode mmap type
+ * bits[63:59] - Encode mmap type
  * bits[45:0]  - mmap offset value
  *
  * NOTE: struct vm_area_struct.vm_pgoff uses offset in pages. Hence, these
  *  defines are w.r.t to PAGE_SIZE
  */
-#define HL_MMAP_TYPE_SHIFT		(61 - PAGE_SHIFT)
-#define HL_MMAP_TYPE_MASK		(0x7ull << HL_MMAP_TYPE_SHIFT)
+#define HL_MMAP_TYPE_SHIFT		(59 - PAGE_SHIFT)
+#define HL_MMAP_TYPE_MASK		(0x1full << HL_MMAP_TYPE_SHIFT)
+#define HL_MMAP_TYPE_TS_BUFF		(0x10ull << HL_MMAP_TYPE_SHIFT)
 #define HL_MMAP_TYPE_BLOCK		(0x4ull << HL_MMAP_TYPE_SHIFT)
 #define HL_MMAP_TYPE_CB			(0x2ull << HL_MMAP_TYPE_SHIFT)
 
@@ -141,6 +142,9 @@ enum hl_mmu_page_table_location {
  *
  * - HL_DRV_RESET_FW_FATAL_ERR
  *       Set if reset is due to a fatal error from FW
+ *
+ * - HL_DRV_RESET_DELAY
+ *       Set if a delay should be added before the reset
  */
 
 #define HL_DRV_RESET_HARD		(1 << 0)
@@ -150,6 +154,7 @@ enum hl_mmu_page_table_location {
 #define HL_DRV_RESET_DEV_RELEASE	(1 << 4)
 #define HL_DRV_RESET_BYPASS_REQ_TO_FW	(1 << 5)
 #define HL_DRV_RESET_FW_FATAL_ERR	(1 << 6)
+#define HL_DRV_RESET_DELAY		(1 << 7)
 
 #define HL_MAX_SOBS_PER_MONITOR	8
 
@@ -402,8 +407,11 @@ enum hl_device_hw_state {
  * @hop4_mask: mask to get the PTE address in hop 4.
  * @hop5_mask: mask to get the PTE address in hop 5.
  * @last_mask: mask to get the bit indicating this is the last hop.
+ * @pgt_size: size for page tables.
  * @page_size: default page size used to allocate memory.
  * @num_hops: The amount of hops supported by the translation table.
+ * @hop_table_size: HOP table size.
+ * @hop0_tables_total_size: total size for all HOP0 tables.
  * @host_resident: Should the MMU page table reside in host memory or in the
  *                 device DRAM.
  */
@@ -423,8 +431,11 @@ struct hl_mmu_properties {
 	u64	hop4_mask;
 	u64	hop5_mask;
 	u64	last_mask;
+	u64	pgt_size;
 	u32	page_size;
 	u32	num_hops;
+	u32	hop_table_size;
+	u32	hop0_tables_total_size;
 	u8	host_resident;
 };
 
@@ -554,6 +565,9 @@ struct hl_hints_range {
  *                              use-case of doing soft-reset in training (due
  *                              to the fact that training runs on multiple
  *                              devices)
+ * @configurable_stop_on_err: is stop-on-error option configurable via debugfs.
+ * @set_max_power_on_device_init: true if need to set max power in F/W on device init.
+ * @supports_user_set_page_size: true if user can set the allocation page size.
  */
 struct asic_fixed_properties {
 	struct hw_queue_properties	*hw_queues_props;
@@ -637,6 +651,9 @@ struct asic_fixed_properties {
 	u8				use_get_power_for_reset_history;
 	u8				supports_soft_reset;
 	u8				allow_inference_soft_reset;
+	u8				configurable_stop_on_err;
+	u8				set_max_power_on_device_init;
+	u8				supports_user_set_page_size;
 };
 
 /**
@@ -704,6 +721,40 @@ struct hl_cb_mgr {
 };
 
 /**
+ * struct hl_ts_mgr - describes the timestamp registration memory manager.
+ * @ts_lock: protects ts_handles.
+ * @ts_handles: an idr to hold all ts bufferes handles.
+ */
+struct hl_ts_mgr {
+	spinlock_t		ts_lock;
+	struct idr		ts_handles;
+};
+
+/**
+ * struct hl_ts_buff - describes a timestamp buffer.
+ * @refcount: reference counter for usage of the buffer.
+ * @hdev: pointer to device this buffer belongs to.
+ * @mmap: true if the buff is currently mapped to user.
+ * @kernel_buff_address: Holds the internal buffer's kernel virtual address.
+ * @user_buff_address: Holds the user buffer's kernel virtual address.
+ * @id: the buffer ID.
+ * @mmap_size: Holds the buffer size that was mmaped.
+ * @kernel_buff_size: Holds the internal kernel buffer size.
+ * @user_buff_size: Holds the user buffer size.
+ */
+struct hl_ts_buff {
+	struct kref		refcount;
+	struct hl_device	*hdev;
+	atomic_t		mmap;
+	void			*kernel_buff_address;
+	void			*user_buff_address;
+	u32			id;
+	u32			mmap_size;
+	u32			kernel_buff_size;
+	u32			user_buff_size;
+};
+
+/**
  * struct hl_cb - describes a Command Buffer.
  * @refcount: reference counter for usage of the CB.
  * @hdev: pointer to device this CB belongs to.
@@ -881,8 +932,53 @@ struct hl_user_interrupt {
 };
 
 /**
+ * struct timestamp_reg_free_node - holds the timestamp registration free objects node
+ * @free_objects_node: node in the list free_obj_jobs
+ * @cq_cb: pointer to cq command buffer to be freed
+ * @ts_buff: pointer to timestamp buffer to be freed
+ */
+struct timestamp_reg_free_node {
+	struct list_head	free_objects_node;
+	struct hl_cb		*cq_cb;
+	struct hl_ts_buff	*ts_buff;
+};
+
+/* struct timestamp_reg_work_obj - holds the timestamp registration free objects job
+ * the job will be to pass over the free_obj_jobs list and put refcount to objects
+ * in each node of the list
+ * @free_obj: workqueue object to free timestamp registration node objects
+ * @hdev: pointer to the device structure
+ * @free_obj_head: list of free jobs nodes (node type timestamp_reg_free_node)
+ */
+struct timestamp_reg_work_obj {
+	struct work_struct	free_obj;
+	struct hl_device	*hdev;
+	struct list_head	*free_obj_head;
+};
+
+/* struct timestamp_reg_info - holds the timestamp registration related data.
+ * @ts_buff: pointer to the timestamp buffer which include both user/kernel buffers.
+ *           relevant only when doing timestamps records registration.
+ * @cq_cb: pointer to CQ counter CB.
+ * @timestamp_kernel_addr: timestamp handle address, where to set timestamp
+ *                         relevant only when doing timestamps records
+ *                         registration.
+ * @in_use: indicates if the node already in use. relevant only when doing
+ *          timestamps records registration, since in this case the driver
+ *          will have it's own buffer which serve as a records pool instead of
+ *          allocating records dynamically.
+ */
+struct timestamp_reg_info {
+	struct hl_ts_buff	*ts_buff;
+	struct hl_cb		*cq_cb;
+	u64			*timestamp_kernel_addr;
+	u8			in_use;
+};
+
+/**
  * struct hl_user_pending_interrupt - holds a context to a user thread
  *                                    pending on an interrupt
+ * @ts_reg_info: holds the timestamps registration nodes info
  * @wait_list_node: node in the list of user threads pending on an interrupt
  * @fence: hl fence object for interrupt completion
  * @cq_target_value: CQ target value
@@ -890,10 +986,11 @@ struct hl_user_interrupt {
  *                  handler for taget value comparison
  */
 struct hl_user_pending_interrupt {
-	struct list_head	wait_list_node;
-	struct hl_fence		fence;
-	u64			cq_target_value;
-	u64			*cq_kernel_addr;
+	struct timestamp_reg_info	ts_reg_info;
+	struct list_head		wait_list_node;
+	struct hl_fence			fence;
+	u64				cq_target_value;
+	u64				*cq_kernel_addr;
 };
 
 /**
@@ -1155,7 +1252,6 @@ struct fw_load_mgr {
  *                    internal memory via DMA engine.
  * @add_device_attr: add ASIC specific device attributes.
  * @handle_eqe: handle event queue entry (IRQ) from CPU-CP.
- * @set_pll_profile: change PLL profile (manual/automatic).
  * @get_events_stat: retrieve event queue entries histogram.
  * @read_pte: read MMU page table entry from DRAM.
  * @write_pte: write MMU page table entry to DRAM.
@@ -1164,9 +1260,6 @@ struct fw_load_mgr {
  * @mmu_invalidate_cache_range: flush specific MMU STLB cache lines with
  *                              ASID-VA-size mask.
  * @send_heartbeat: send is-alive packet to CPU-CP and verify response.
- * @set_clock_gating: enable/disable clock gating per engine according to
- *                    clock gating mask in hdev
- * @disable_clock_gating: disable clock gating completely
  * @debug_coresight: perform certain actions on Coresight for debugging.
  * @is_device_idle: return true if device is idle, false otherwise.
  * @non_hard_reset_late_init: perform certain actions needed after a reset which is not hard-reset
@@ -1187,7 +1280,6 @@ struct fw_load_mgr {
  * @halt_coresight: stop the ETF and ETR traces.
  * @ctx_init: context dependent initialization.
  * @ctx_fini: context dependent cleanup.
- * @get_clk_rate: Retrieve the ASIC current and maximum clock rate in MHz
  * @get_queue_id_for_cq: Get the H/W queue id related to the given CQ index.
  * @load_firmware_to_device: load the firmware to the device's memory
  * @load_boot_fit_to_device: load boot fit to device's memory
@@ -1225,6 +1317,8 @@ struct fw_load_mgr {
  * @get_sob_addr: get SOB base address offset.
  * @set_pci_memory_regions: setting properties of PCI memory regions
  * @get_stream_master_qid_arr: get pointer to stream masters QID array
+ * @is_valid_dram_page_size: return true if page size is supported in device
+ *                           memory allocation, otherwise false.
  */
 struct hl_asic_funcs {
 	int (*early_init)(struct hl_device *hdev);
@@ -1285,12 +1379,10 @@ struct hl_asic_funcs {
 				bool user_address, u64 val);
 	int (*debugfs_read_dma)(struct hl_device *hdev, u64 addr, u32 size,
 				void *blob_addr);
-	void (*add_device_attr)(struct hl_device *hdev,
-				struct attribute_group *dev_attr_grp);
+	void (*add_device_attr)(struct hl_device *hdev, struct attribute_group *dev_clk_attr_grp,
+				struct attribute_group *dev_vrm_attr_grp);
 	void (*handle_eqe)(struct hl_device *hdev,
 				struct hl_eq_entry *eq_entry);
-	void (*set_pll_profile)(struct hl_device *hdev,
-			enum hl_pll_frequency freq);
 	void* (*get_events_stat)(struct hl_device *hdev, bool aggregate,
 				u32 *size);
 	u64 (*read_pte)(struct hl_device *hdev, u64 addr);
@@ -1300,8 +1392,6 @@ struct hl_asic_funcs {
 	int (*mmu_invalidate_cache_range)(struct hl_device *hdev, bool is_hard,
 				u32 flags, u32 asid, u64 va, u64 size);
 	int (*send_heartbeat)(struct hl_device *hdev);
-	void (*set_clock_gating)(struct hl_device *hdev);
-	void (*disable_clock_gating)(struct hl_device *hdev);
 	int (*debug_coresight)(struct hl_device *hdev, struct hl_ctx *ctx, void *data);
 	bool (*is_device_idle)(struct hl_device *hdev, u64 *mask_arr,
 					u8 mask_len, struct seq_file *s);
@@ -1320,7 +1410,6 @@ struct hl_asic_funcs {
 	void (*halt_coresight)(struct hl_device *hdev, struct hl_ctx *ctx);
 	int (*ctx_init)(struct hl_ctx *ctx);
 	void (*ctx_fini)(struct hl_ctx *ctx);
-	int (*get_clk_rate)(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk);
 	u32 (*get_queue_id_for_cq)(struct hl_device *hdev, u32 cq_idx);
 	int (*load_firmware_to_device)(struct hl_device *hdev);
 	int (*load_boot_fit_to_device)(struct hl_device *hdev);
@@ -1355,6 +1444,7 @@ struct hl_asic_funcs {
 	u32 (*get_sob_addr)(struct hl_device *hdev, u32 sob_id);
 	void (*set_pci_memory_regions)(struct hl_device *hdev);
 	u32* (*get_stream_master_qid_arr)(void);
+	bool (*is_valid_dram_page_size)(u32 page_size);
 };
 
 
@@ -1742,6 +1832,8 @@ struct hl_vm_hw_block_list_node {
  * @pages: the physical page array.
  * @npages: num physical pages in the pack.
  * @total_size: total size of all the pages in this list.
+ * @node: used to attach to deletion list that is used when all the allocations are cleared
+ *        at the teardown of the context.
  * @mapping_cnt: number of shared mappings.
  * @exporting_cnt: number of dma-buf exporting.
  * @asid: the context related to this list.
@@ -1757,6 +1849,7 @@ struct hl_vm_phys_pg_pack {
 	u64			*pages;
 	u64			npages;
 	u64			total_size;
+	struct list_head	node;
 	atomic_t		mapping_cnt;
 	u32			exporting_cnt;
 	u32			asid;
@@ -1834,6 +1927,7 @@ struct hl_debug_params {
  * @ctx: current executing context. TODO: remove for multiple ctx per process
  * @ctx_mgr: context manager to handle multiple context for this FD.
  * @cb_mgr: command buffer manager to handle multiple buffers for this FD.
+ * @ts_mem_mgr: timestamp registration manager for alloc/free/map timestamp buffers.
  * @debugfs_list: list of relevant ASIC debugfs.
  * @dev_node: node in the device list of file private data
  * @refcount: number of related contexts.
@@ -1846,6 +1940,7 @@ struct hl_fpriv {
 	struct hl_ctx		*ctx;
 	struct hl_ctx_mgr	ctx_mgr;
 	struct hl_cb_mgr	cb_mgr;
+	struct hl_ts_mgr	ts_mem_mgr;
 	struct list_head	debugfs_list;
 	struct list_head	dev_node;
 	struct kref		refcount;
@@ -2518,7 +2613,7 @@ struct hl_reset_info {
  * @cq_wq: work queues of completion queues for executing work in process
  *         context.
  * @eq_wq: work queue of event queue for executing work in process context.
- * @sob_reset_wq: work queue for sob reset executions.
+ * @ts_free_obj_wq: work queue for timestamp registration objects release.
  * @kernel_ctx: Kernel driver context structure.
  * @kernel_queues: array of hl_hw_queue.
  * @cs_mirror_list: CS mirror list for TDR.
@@ -2569,9 +2664,6 @@ struct hl_reset_info {
  * @max_power: the max power of the device, as configured by the sysadmin. This
  *             value is saved so in case of hard-reset, the driver will restore
  *             this value and update the F/W after the re-initialization
- * @clock_gating_mask: is clock gating enabled. bitmask that represents the
- *                     different engines. See debugfs-driver-habanalabs for
- *                     details.
  * @boot_error_status_mask: contains a mask of the device boot error status.
  *                          Each bit represents a different error, according to
  *                          the defines in hl_boot_if.h. If the bit is cleared,
@@ -2611,8 +2703,6 @@ struct hl_reset_info {
  * @in_debug: whether the device is in a state where the profiling/tracing infrastructure
  *            can be used. This indication is needed because in some ASICs we need to do
  *            specific operations to enable that infrastructure.
- * @power9_64bit_dma_enable: true to enable 64-bit DMA mask support. Relevant
- *                           only to POWER9 machines.
  * @cdev_sysfs_created: were char devices and sysfs nodes created.
  * @stop_on_err: true if engines should stop on error.
  * @supports_sync_stream: is sync stream supported.
@@ -2651,7 +2741,7 @@ struct hl_device {
 	struct hl_user_interrupt	common_user_interrupt;
 	struct workqueue_struct		**cq_wq;
 	struct workqueue_struct		*eq_wq;
-	struct workqueue_struct		*sob_reset_wq;
+	struct workqueue_struct		*ts_free_obj_wq;
 	struct hl_ctx			*kernel_ctx;
 	struct hl_hw_queue		*kernel_queues;
 	struct list_head		cs_mirror_list;
@@ -2710,7 +2800,6 @@ struct hl_device {
 	atomic64_t			dram_used_mem;
 	u64				timeout_jiffies;
 	u64				max_power;
-	u64				clock_gating_mask;
 	u64				boot_error_status_mask;
 	u64				dram_pci_bar_start;
 	u64				last_successful_open_jif;
@@ -2736,7 +2825,6 @@ struct hl_device {
 	u8				device_cpu_disabled;
 	u8				dma_mask;
 	u8				in_debug;
-	u8				power9_64bit_dma_enable;
 	u8				cdev_sysfs_created;
 	u8				stop_on_err;
 	u8				supports_sync_stream;
@@ -2970,7 +3058,7 @@ int hl_cb_pool_fini(struct hl_device *hdev);
 int hl_cb_va_pool_init(struct hl_ctx *ctx);
 void hl_cb_va_pool_fini(struct hl_ctx *ctx);
 
-void hl_cs_rollback_all(struct hl_device *hdev);
+void hl_cs_rollback_all(struct hl_device *hdev, bool skip_wq_flush);
 struct hl_cs_job *hl_cs_allocate_job(struct hl_device *hdev,
 		enum hl_queue_type queue_type, bool is_kernel_allocated_cb);
 void hl_sob_reset_error(struct kref *ref);
@@ -3024,6 +3112,9 @@ int hl_mmu_unmap_contiguous(struct hl_ctx *ctx, u64 virt_addr, u32 size);
 int hl_mmu_invalidate_cache(struct hl_device *hdev, bool is_hard, u32 flags);
 int hl_mmu_invalidate_cache_range(struct hl_device *hdev, bool is_hard,
 					u32 flags, u32 asid, u64 va, u64 size);
+u64 hl_mmu_get_next_hop_addr(struct hl_ctx *ctx, u64 curr_pte);
+u64 hl_mmu_get_hop_pte_phys_addr(struct hl_ctx *ctx, struct hl_mmu_properties *mmu_prop,
+					u8 hop_idx, u64 hop_addr, u64 virt_addr);
 void hl_mmu_swap_out(struct hl_ctx *ctx);
 void hl_mmu_swap_in(struct hl_ctx *ctx);
 int hl_mmu_if_set_funcs(struct hl_device *hdev);
@@ -3094,39 +3185,26 @@ enum pci_region hl_get_pci_memory_region(struct hl_device *hdev, u64 addr);
 int hl_pci_init(struct hl_device *hdev);
 void hl_pci_fini(struct hl_device *hdev);
 
-long hl_get_frequency(struct hl_device *hdev, u32 pll_index,
-								bool curr);
-void hl_set_frequency(struct hl_device *hdev, u32 pll_index,
-								u64 freq);
-int hl_get_temperature(struct hl_device *hdev,
-		       int sensor_index, u32 attr, long *value);
-int hl_set_temperature(struct hl_device *hdev,
-		       int sensor_index, u32 attr, long value);
-int hl_get_voltage(struct hl_device *hdev,
-		   int sensor_index, u32 attr, long *value);
-int hl_get_current(struct hl_device *hdev,
-		   int sensor_index, u32 attr, long *value);
-int hl_get_fan_speed(struct hl_device *hdev,
-		     int sensor_index, u32 attr, long *value);
-int hl_get_pwm_info(struct hl_device *hdev,
-		    int sensor_index, u32 attr, long *value);
-void hl_set_pwm_info(struct hl_device *hdev, int sensor_index, u32 attr,
-			long value);
-u64 hl_get_max_power(struct hl_device *hdev);
-void hl_set_max_power(struct hl_device *hdev);
-int hl_set_voltage(struct hl_device *hdev,
-			int sensor_index, u32 attr, long value);
-int hl_set_current(struct hl_device *hdev,
-			int sensor_index, u32 attr, long value);
-int hl_set_power(struct hl_device *hdev,
-			int sensor_index, u32 attr, long value);
-int hl_get_power(struct hl_device *hdev,
-			int sensor_index, u32 attr, long *value);
-int hl_get_clk_rate(struct hl_device *hdev,
-			u32 *cur_clk, u32 *max_clk);
-void hl_set_pll_profile(struct hl_device *hdev, enum hl_pll_frequency freq);
-void hl_add_device_attr(struct hl_device *hdev,
-			struct attribute_group *dev_attr_grp);
+long hl_fw_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr);
+void hl_fw_set_frequency(struct hl_device *hdev, u32 pll_index, u64 freq);
+int hl_get_temperature(struct hl_device *hdev, int sensor_index, u32 attr, long *value);
+int hl_set_temperature(struct hl_device *hdev, int sensor_index, u32 attr, long value);
+int hl_get_voltage(struct hl_device *hdev, int sensor_index, u32 attr, long *value);
+int hl_get_current(struct hl_device *hdev, int sensor_index, u32 attr, long *value);
+int hl_get_fan_speed(struct hl_device *hdev, int sensor_index, u32 attr, long *value);
+int hl_get_pwm_info(struct hl_device *hdev, int sensor_index, u32 attr, long *value);
+void hl_set_pwm_info(struct hl_device *hdev, int sensor_index, u32 attr, long value);
+long hl_fw_get_max_power(struct hl_device *hdev);
+void hl_fw_set_max_power(struct hl_device *hdev);
+int hl_set_voltage(struct hl_device *hdev, int sensor_index, u32 attr, long value);
+int hl_set_current(struct hl_device *hdev, int sensor_index, u32 attr, long value);
+int hl_set_power(struct hl_device *hdev, int sensor_index, u32 attr, long value);
+int hl_get_power(struct hl_device *hdev, int sensor_index, u32 attr, long *value);
+int hl_fw_get_clk_rate(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk);
+void hl_fw_set_pll_profile(struct hl_device *hdev);
+void hl_sysfs_add_dev_clk_attr(struct hl_device *hdev, struct attribute_group *dev_clk_attr_grp);
+void hl_sysfs_add_dev_vrm_attr(struct hl_device *hdev, struct attribute_group *dev_vrm_attr_grp);
+
 void hw_sob_get(struct hl_hw_sob *hw_sob);
 void hw_sob_put(struct hl_hw_sob *hw_sob);
 void hl_encaps_handle_do_release(struct kref *ref);
@@ -3146,6 +3224,11 @@ __printf(4, 5) int hl_snprintf_resize(char **buf, size_t *size, size_t *offset,
 					const char *format, ...);
 char *hl_format_as_binary(char *buf, size_t buf_len, u32 n);
 const char *hl_sync_engine_to_string(enum hl_sync_engine_type engine_type);
+void hl_ts_mgr_init(struct hl_ts_mgr *mgr);
+void hl_ts_mgr_fini(struct hl_device *hdev, struct hl_ts_mgr *mgr);
+int hl_ts_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma);
+struct hl_ts_buff *hl_ts_get(struct hl_device *hdev, struct hl_ts_mgr *mgr, u32 handle);
+void hl_ts_put(struct hl_ts_buff *buff);
 
 #ifdef CONFIG_DEBUG_FS
 
diff --git a/drivers/misc/habanalabs/common/habanalabs_drv.c b/drivers/misc/habanalabs/common/habanalabs_drv.c
index 690b763c7a95..ca404ed9d9a7 100644
--- a/drivers/misc/habanalabs/common/habanalabs_drv.c
+++ b/drivers/misc/habanalabs/common/habanalabs_drv.c
@@ -140,6 +140,7 @@ int hl_device_open(struct inode *inode, struct file *filp)
 
 	hl_cb_mgr_init(&hpriv->cb_mgr);
 	hl_ctx_mgr_init(&hpriv->ctx_mgr);
+	hl_ts_mgr_init(&hpriv->ts_mem_mgr);
 
 	hpriv->taskpid = get_task_pid(current, PIDTYPE_PID);
 
@@ -184,6 +185,7 @@ int hl_device_open(struct inode *inode, struct file *filp)
 out_err:
 	mutex_unlock(&hdev->fpriv_list_lock);
 	hl_cb_mgr_fini(hpriv->hdev, &hpriv->cb_mgr);
+	hl_ts_mgr_fini(hpriv->hdev, &hpriv->ts_mem_mgr);
 	hl_ctx_mgr_fini(hpriv->hdev, &hpriv->ctx_mgr);
 	filp->private_data = NULL;
 	mutex_destroy(&hpriv->restore_phase_mutex);
@@ -256,7 +258,6 @@ static void set_driver_behavior_per_device(struct hl_device *hdev)
 	hdev->cpu_queues_enable = 1;
 	hdev->heartbeat = 1;
 	hdev->mmu_enable = 1;
-	hdev->clock_gating_mask = ULONG_MAX;
 	hdev->sram_scrambler_enable = 1;
 	hdev->dram_scrambler_enable = 1;
 	hdev->bmc_enable = 1;
diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
index 3ba3a8ffda3e..c13a3c2a7013 100644
--- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 /*
- * Copyright 2016-2019 HabanaLabs, Ltd.
+ * Copyright 2016-2022 HabanaLabs, Ltd.
  * All Rights Reserved.
  */
 
@@ -92,8 +92,8 @@ static int hw_ip_info(struct hl_device *hdev, struct hl_info_args *args)
 	hw_ip.psoc_pci_pll_od = prop->psoc_pci_pll_od;
 	hw_ip.psoc_pci_pll_div_factor = prop->psoc_pci_pll_div_factor;
 
-	hw_ip.first_available_interrupt_id =
-			prop->first_available_user_msix_interrupt;
+	hw_ip.first_available_interrupt_id = prop->first_available_user_msix_interrupt;
+	hw_ip.number_of_user_interrupts = prop->user_interrupt_count;
 	hw_ip.server_type = prop->server_type;
 
 	return copy_to_user(out, &hw_ip,
@@ -251,13 +251,12 @@ static int get_clk_rate(struct hl_device *hdev, struct hl_info_args *args)
 	if ((!max_size) || (!out))
 		return -EINVAL;
 
-	rc = hdev->asic_funcs->get_clk_rate(hdev, &clk_rate.cur_clk_rate_mhz,
-						&clk_rate.max_clk_rate_mhz);
+	rc = hl_fw_get_clk_rate(hdev, &clk_rate.cur_clk_rate_mhz, &clk_rate.max_clk_rate_mhz);
 	if (rc)
 		return rc;
 
-	return copy_to_user(out, &clk_rate,
-		min((size_t) max_size, sizeof(clk_rate))) ? -EFAULT : 0;
+	return copy_to_user(out, &clk_rate, min_t(size_t, max_size, sizeof(clk_rate)))
+										? -EFAULT : 0;
 }
 
 static int get_reset_count(struct hl_device *hdev, struct hl_info_args *args)
diff --git a/drivers/misc/habanalabs/common/hwmgr.c b/drivers/misc/habanalabs/common/hwmgr.c
deleted file mode 100644
index 5451019f143f..000000000000
--- a/drivers/misc/habanalabs/common/hwmgr.c
+++ /dev/null
@@ -1,117 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-/*
- * Copyright 2019-2021 HabanaLabs, Ltd.
- * All Rights Reserved.
- */
-
-#include "habanalabs.h"
-
-void hl_set_pll_profile(struct hl_device *hdev, enum hl_pll_frequency freq)
-{
-	hl_set_frequency(hdev, hdev->asic_prop.clk_pll_index,
-			hdev->asic_prop.max_freq_value);
-}
-
-int hl_get_clk_rate(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk)
-{
-	long value;
-
-	if (!hl_device_operational(hdev, NULL))
-		return -ENODEV;
-
-	value = hl_get_frequency(hdev, hdev->asic_prop.clk_pll_index, false);
-
-	if (value < 0) {
-		dev_err(hdev->dev, "Failed to retrieve device max clock %ld\n",
-			value);
-		return value;
-	}
-
-	*max_clk = (value / 1000 / 1000);
-
-	value = hl_get_frequency(hdev, hdev->asic_prop.clk_pll_index, true);
-
-	if (value < 0) {
-		dev_err(hdev->dev,
-			"Failed to retrieve device current clock %ld\n",
-			value);
-		return value;
-	}
-
-	*cur_clk = (value / 1000 / 1000);
-
-	return 0;
-}
-
-static ssize_t clk_max_freq_mhz_show(struct device *dev,
-		struct device_attribute *attr, char *buf)
-{
-	struct hl_device *hdev = dev_get_drvdata(dev);
-	long value;
-
-	if (!hl_device_operational(hdev, NULL))
-		return -ENODEV;
-
-	value = hl_get_frequency(hdev, hdev->asic_prop.clk_pll_index, false);
-
-	hdev->asic_prop.max_freq_value = value;
-
-	return sprintf(buf, "%lu\n", (value / 1000 / 1000));
-}
-
-static ssize_t clk_max_freq_mhz_store(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
-{
-	struct hl_device *hdev = dev_get_drvdata(dev);
-	int rc;
-	u64 value;
-
-	if (!hl_device_operational(hdev, NULL)) {
-		count = -ENODEV;
-		goto fail;
-	}
-
-	rc = kstrtoull(buf, 0, &value);
-	if (rc) {
-		count = -EINVAL;
-		goto fail;
-	}
-
-	hdev->asic_prop.max_freq_value = value * 1000 * 1000;
-
-	hl_set_frequency(hdev, hdev->asic_prop.clk_pll_index,
-			hdev->asic_prop.max_freq_value);
-
-fail:
-	return count;
-}
-
-static ssize_t clk_cur_freq_mhz_show(struct device *dev,
-		struct device_attribute *attr, char *buf)
-{
-	struct hl_device *hdev = dev_get_drvdata(dev);
-	long value;
-
-	if (!hl_device_operational(hdev, NULL))
-		return -ENODEV;
-
-	value = hl_get_frequency(hdev, hdev->asic_prop.clk_pll_index, true);
-
-	return sprintf(buf, "%lu\n", (value / 1000 / 1000));
-}
-
-static DEVICE_ATTR_RW(clk_max_freq_mhz);
-static DEVICE_ATTR_RO(clk_cur_freq_mhz);
-
-static struct attribute *hl_dev_attrs[] = {
-	&dev_attr_clk_max_freq_mhz.attr,
-	&dev_attr_clk_cur_freq_mhz.attr,
-	NULL,
-};
-
-void hl_add_device_attr(struct hl_device *hdev,
-			struct attribute_group *dev_attr_grp)
-{
-	dev_attr_grp->attrs = hl_dev_attrs;
-}
diff --git a/drivers/misc/habanalabs/common/irq.c b/drivers/misc/habanalabs/common/irq.c
index 1b6bdc900c26..e2bc128f2291 100644
--- a/drivers/misc/habanalabs/common/irq.c
+++ b/drivers/misc/habanalabs/common/irq.c
@@ -137,22 +137,137 @@ irqreturn_t hl_irq_handler_cq(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
+/*
+ * hl_ts_free_objects - handler of the free objects workqueue.
+ * This function should put refcount to objects that the registration node
+ * took refcount to them.
+ * @work: workqueue object pointer
+ */
+static void hl_ts_free_objects(struct work_struct *work)
+{
+	struct timestamp_reg_work_obj *job =
+			container_of(work, struct timestamp_reg_work_obj, free_obj);
+	struct timestamp_reg_free_node *free_obj, *temp_free_obj;
+	struct list_head *free_list_head = job->free_obj_head;
+	struct hl_device *hdev = job->hdev;
+
+	list_for_each_entry_safe(free_obj, temp_free_obj, free_list_head, free_objects_node) {
+		dev_dbg(hdev->dev, "About to put refcount to ts_buff (%p) cq_cb(%p)\n",
+					free_obj->ts_buff,
+					free_obj->cq_cb);
+
+		hl_ts_put(free_obj->ts_buff);
+		hl_cb_put(free_obj->cq_cb);
+		kfree(free_obj);
+	}
+
+	kfree(free_list_head);
+	kfree(job);
+}
+
+/*
+ * This function called with spin_lock of wait_list_lock taken
+ * This function will set timestamp and delete the registration node from the
+ * wait_list_lock.
+ * and since we're protected with spin_lock here, so we cannot just put the refcount
+ * for the objects here, since the release function may be called and it's also a long
+ * logic (which might sleep also) that cannot be handled in irq context.
+ * so here we'll be filling a list with nodes of "put" jobs and then will send this
+ * list to a dedicated workqueue to do the actual put.
+ */
+static int handle_registration_node(struct hl_device *hdev, struct hl_user_pending_interrupt *pend,
+						struct list_head **free_list)
+{
+	struct timestamp_reg_free_node *free_node;
+	u64 timestamp;
+
+	if (!(*free_list)) {
+		/* Alloc/Init the timestamp registration free objects list */
+		*free_list = kmalloc(sizeof(struct list_head), GFP_ATOMIC);
+		if (!(*free_list))
+			return -ENOMEM;
+
+		INIT_LIST_HEAD(*free_list);
+	}
+
+	free_node = kmalloc(sizeof(*free_node), GFP_ATOMIC);
+	if (!free_node)
+		return -ENOMEM;
+
+	timestamp = ktime_get_ns();
+
+	*pend->ts_reg_info.timestamp_kernel_addr = timestamp;
+
+	dev_dbg(hdev->dev, "Timestamp is set to ts cb address (%p), ts: 0x%llx\n",
+			pend->ts_reg_info.timestamp_kernel_addr,
+			*(u64 *)pend->ts_reg_info.timestamp_kernel_addr);
+
+	list_del(&pend->wait_list_node);
+
+	/* Mark kernel CB node as free */
+	pend->ts_reg_info.in_use = 0;
+
+	/* Putting the refcount for ts_buff and cq_cb objects will be handled
+	 * in workqueue context, just add job to free_list.
+	 */
+	free_node->ts_buff = pend->ts_reg_info.ts_buff;
+	free_node->cq_cb = pend->ts_reg_info.cq_cb;
+	list_add(&free_node->free_objects_node, *free_list);
+
+	return 0;
+}
+
 static void handle_user_cq(struct hl_device *hdev,
 			struct hl_user_interrupt *user_cq)
 {
-	struct hl_user_pending_interrupt *pend;
+	struct hl_user_pending_interrupt *pend, *temp_pend;
+	struct list_head *ts_reg_free_list_head = NULL;
+	struct timestamp_reg_work_obj *job;
+	bool reg_node_handle_fail = false;
 	ktime_t now = ktime_get();
+	int rc;
+
+	/* For registration nodes:
+	 * As part of handling the registration nodes, we should put refcount to
+	 * some objects. the problem is that we cannot do that under spinlock
+	 * or in irq handler context at all (since release functions are long and
+	 * might sleep), so we will need to handle that part in workqueue context.
+	 * To avoid handling kmalloc failure which compels us rolling back actions
+	 * and move nodes hanged on the free list back to the interrupt wait list
+	 * we always alloc the job of the WQ at the beginning.
+	 */
+	job = kmalloc(sizeof(*job), GFP_ATOMIC);
+	if (!job)
+		return;
 
 	spin_lock(&user_cq->wait_list_lock);
-	list_for_each_entry(pend, &user_cq->wait_list_head, wait_list_node) {
-		if ((pend->cq_kernel_addr &&
-				*(pend->cq_kernel_addr) >= pend->cq_target_value) ||
+	list_for_each_entry_safe(pend, temp_pend, &user_cq->wait_list_head, wait_list_node) {
+		if ((pend->cq_kernel_addr && *(pend->cq_kernel_addr) >= pend->cq_target_value) ||
 				!pend->cq_kernel_addr) {
-			pend->fence.timestamp = now;
-			complete_all(&pend->fence.completion);
+			if (pend->ts_reg_info.ts_buff) {
+				if (!reg_node_handle_fail) {
+					rc = handle_registration_node(hdev, pend,
+									&ts_reg_free_list_head);
+					if (rc)
+						reg_node_handle_fail = true;
+				}
+			} else {
+				/* Handle wait target value node */
+				pend->fence.timestamp = now;
+				complete_all(&pend->fence.completion);
+			}
 		}
 	}
 	spin_unlock(&user_cq->wait_list_lock);
+
+	if (ts_reg_free_list_head) {
+		INIT_WORK(&job->free_obj, hl_ts_free_objects);
+		job->free_obj_head = ts_reg_free_list_head;
+		job->hdev = hdev;
+		queue_work(hdev->ts_free_obj_wq, &job->free_obj);
+	} else {
+		kfree(job);
+	}
 }
 
 /**
diff --git a/drivers/misc/habanalabs/common/memory.c b/drivers/misc/habanalabs/common/memory.c
index c1eefaebacb6..e008d82e4ba3 100644
--- a/drivers/misc/habanalabs/common/memory.c
+++ b/drivers/misc/habanalabs/common/memory.c
@@ -11,6 +11,7 @@
 
 #include <linux/uaccess.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <linux/pci-p2pdma.h>
 
 MODULE_IMPORT_NS(DMA_BUF);
@@ -20,6 +21,34 @@ MODULE_IMPORT_NS(DMA_BUF);
 /* use small pages for supporting non-pow2 (32M/40M/48M) DRAM phys page sizes */
 #define DRAM_POOL_PAGE_SIZE SZ_8M
 
+static int allocate_timestamps_buffers(struct hl_fpriv *hpriv,
+			struct hl_mem_in *args, u64 *handle);
+
+static int set_alloc_page_size(struct hl_device *hdev, struct hl_mem_in *args, u32 *page_size)
+{
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	u32 psize;
+
+	/*
+	 * for ASIC that supports setting the allocation page size by user we will address
+	 * user's choice only if it is not 0 (as 0 means taking the default page size)
+	 */
+	if (prop->supports_user_set_page_size && args->alloc.page_size) {
+		psize = args->alloc.page_size;
+
+		if (!hdev->asic_funcs->is_valid_dram_page_size(psize)) {
+			dev_err(hdev->dev, "user page size (%#x) is not valid\n", psize);
+			return -EINVAL;
+		}
+	} else {
+		psize = hdev->asic_prop.dram_page_size;
+	}
+
+	*page_size = psize;
+
+	return 0;
+}
+
 /*
  * The va ranges in context object contain a list with the available chunks of
  * device virtual memory.
@@ -61,11 +90,15 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args,
 	struct hl_vm_phys_pg_pack *phys_pg_pack;
 	u64 paddr = 0, total_size, num_pgs, i;
 	u32 num_curr_pgs, page_size;
-	int handle, rc;
 	bool contiguous;
+	int handle, rc;
 
 	num_curr_pgs = 0;
-	page_size = hdev->asic_prop.dram_page_size;
+
+	rc = set_alloc_page_size(hdev, args, &page_size);
+	if (rc)
+		return rc;
+
 	num_pgs = DIV_ROUND_UP_ULL(args->alloc.mem_size, page_size);
 	total_size = num_pgs * page_size;
 
@@ -77,7 +110,11 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args,
 	contiguous = args->flags & HL_MEM_CONTIGUOUS;
 
 	if (contiguous) {
-		paddr = (u64) gen_pool_alloc(vm->dram_pg_pool, total_size);
+		if (is_power_of_2(page_size))
+			paddr = (u64) (uintptr_t) gen_pool_dma_alloc_align(vm->dram_pg_pool,
+								total_size, NULL, page_size);
+		else
+			paddr = (u64) (uintptr_t) gen_pool_alloc(vm->dram_pg_pool, total_size);
 		if (!paddr) {
 			dev_err(hdev->dev,
 				"failed to allocate %llu contiguous pages with total size of %llu\n",
@@ -111,9 +148,14 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args,
 			phys_pg_pack->pages[i] = paddr + i * page_size;
 	} else {
 		for (i = 0 ; i < num_pgs ; i++) {
-			phys_pg_pack->pages[i] = (u64) gen_pool_alloc(
-							vm->dram_pg_pool,
-							page_size);
+			if (is_power_of_2(page_size))
+				phys_pg_pack->pages[i] =
+						(u64) gen_pool_dma_alloc_align(vm->dram_pg_pool,
+										page_size, NULL,
+										page_size);
+			else
+				phys_pg_pack->pages[i] = (u64) gen_pool_alloc(vm->dram_pg_pool,
+										page_size);
 			if (!phys_pg_pack->pages[i]) {
 				dev_err(hdev->dev,
 					"Failed to allocate device memory (out of memory)\n");
@@ -652,7 +694,7 @@ static u64 get_va_block(struct hl_device *hdev,
 			continue;
 
 		/*
-		 * In case hint address is 0, and arc_hints_range_reservation
+		 * In case hint address is 0, and hints_range_reservation
 		 * property enabled, then avoid allocating va blocks from the
 		 * range reserved for hint addresses
 		 */
@@ -1967,16 +2009,15 @@ err_dec_exporting_cnt:
 static int mem_ioctl_no_mmu(struct hl_fpriv *hpriv, union hl_mem_args *args)
 {
 	struct hl_device *hdev = hpriv->hdev;
-	struct hl_ctx *ctx = hpriv->ctx;
 	u64 block_handle, device_addr = 0;
+	struct hl_ctx *ctx = hpriv->ctx;
 	u32 handle = 0, block_size;
-	int rc, dmabuf_fd = -EBADF;
+	int rc;
 
 	switch (args->in.op) {
 	case HL_MEM_OP_ALLOC:
 		if (args->in.alloc.mem_size == 0) {
-			dev_err(hdev->dev,
-				"alloc size must be larger than 0\n");
+			dev_err(hdev->dev, "alloc size must be larger than 0\n");
 			rc = -EINVAL;
 			goto out;
 		}
@@ -1997,15 +2038,14 @@ static int mem_ioctl_no_mmu(struct hl_fpriv *hpriv, union hl_mem_args *args)
 
 	case HL_MEM_OP_MAP:
 		if (args->in.flags & HL_MEM_USERPTR) {
-			device_addr = args->in.map_host.host_virt_addr;
-			rc = 0;
+			dev_err(hdev->dev, "Failed to map host memory when MMU is disabled\n");
+			rc = -EPERM;
 		} else {
-			rc = get_paddr_from_handle(ctx, &args->in,
-							&device_addr);
+			rc = get_paddr_from_handle(ctx, &args->in, &device_addr);
+			memset(args, 0, sizeof(*args));
+			args->out.device_virt_addr = device_addr;
 		}
 
-		memset(args, 0, sizeof(*args));
-		args->out.device_virt_addr = device_addr;
 		break;
 
 	case HL_MEM_OP_UNMAP:
@@ -2013,22 +2053,19 @@ static int mem_ioctl_no_mmu(struct hl_fpriv *hpriv, union hl_mem_args *args)
 		break;
 
 	case HL_MEM_OP_MAP_BLOCK:
-		rc = map_block(hdev, args->in.map_block.block_addr,
-				&block_handle, &block_size);
+		rc = map_block(hdev, args->in.map_block.block_addr, &block_handle, &block_size);
 		args->out.block_handle = block_handle;
 		args->out.block_size = block_size;
 		break;
 
 	case HL_MEM_OP_EXPORT_DMABUF_FD:
-		rc = export_dmabuf_from_addr(ctx,
-				args->in.export_dmabuf_fd.handle,
-				args->in.export_dmabuf_fd.mem_size,
-				args->in.flags,
-				&dmabuf_fd);
-		memset(args, 0, sizeof(*args));
-		args->out.fd = dmabuf_fd;
+		dev_err(hdev->dev, "Failed to export dma-buf object when MMU is disabled\n");
+		rc = -EPERM;
 		break;
 
+	case HL_MEM_OP_TS_ALLOC:
+		rc = allocate_timestamps_buffers(hpriv, &args->in, &args->out.handle);
+		break;
 	default:
 		dev_err(hdev->dev, "Unknown opcode for memory IOCTL\n");
 		rc = -EINVAL;
@@ -2039,6 +2076,258 @@ out:
 	return rc;
 }
 
+static void ts_buff_release(struct kref *ref)
+{
+	struct hl_ts_buff *buff;
+
+	buff = container_of(ref, struct hl_ts_buff, refcount);
+
+	vfree(buff->kernel_buff_address);
+	vfree(buff->user_buff_address);
+	kfree(buff);
+}
+
+struct hl_ts_buff *hl_ts_get(struct hl_device *hdev, struct hl_ts_mgr *mgr,
+					u32 handle)
+{
+	struct hl_ts_buff *buff;
+
+	spin_lock(&mgr->ts_lock);
+	buff = idr_find(&mgr->ts_handles, handle);
+	if (!buff) {
+		spin_unlock(&mgr->ts_lock);
+		dev_warn(hdev->dev,
+			"TS buff get failed, no match to handle 0x%x\n", handle);
+		return NULL;
+	}
+	kref_get(&buff->refcount);
+	spin_unlock(&mgr->ts_lock);
+
+	return buff;
+}
+
+void hl_ts_put(struct hl_ts_buff *buff)
+{
+	kref_put(&buff->refcount, ts_buff_release);
+}
+
+static void buff_vm_close(struct vm_area_struct *vma)
+{
+	struct hl_ts_buff *buff = (struct hl_ts_buff *) vma->vm_private_data;
+	long new_mmap_size;
+
+	new_mmap_size = buff->mmap_size - (vma->vm_end - vma->vm_start);
+
+	if (new_mmap_size > 0) {
+		buff->mmap_size = new_mmap_size;
+		return;
+	}
+
+	atomic_set(&buff->mmap, 0);
+	hl_ts_put(buff);
+	vma->vm_private_data = NULL;
+}
+
+static const struct vm_operations_struct ts_buff_vm_ops = {
+	.close = buff_vm_close
+};
+
+int hl_ts_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma)
+{
+	struct hl_device *hdev = hpriv->hdev;
+	struct hl_ts_buff *buff;
+	u32 handle, user_buff_size;
+	int rc;
+
+	/* We use the page offset to hold the idr and thus we need to clear
+	 * it before doing the mmap itself
+	 */
+	handle = vma->vm_pgoff;
+	vma->vm_pgoff = 0;
+
+	buff = hl_ts_get(hdev, &hpriv->ts_mem_mgr, handle);
+	if (!buff) {
+		dev_err(hdev->dev,
+			"TS buff mmap failed, no match to handle 0x%x\n", handle);
+		return -EINVAL;
+	}
+
+	/* Validation check */
+	user_buff_size = vma->vm_end - vma->vm_start;
+	if (user_buff_size != ALIGN(buff->user_buff_size, PAGE_SIZE)) {
+		dev_err(hdev->dev,
+			"TS buff mmap failed, mmap size 0x%x != 0x%x buff size\n",
+			user_buff_size, ALIGN(buff->user_buff_size, PAGE_SIZE));
+		rc = -EINVAL;
+		goto put_buff;
+	}
+
+#ifdef _HAS_TYPE_ARG_IN_ACCESS_OK
+	if (!access_ok(VERIFY_WRITE,
+		(void __user *) (uintptr_t) vma->vm_start, user_buff_size)) {
+#else
+	if (!access_ok((void __user *) (uintptr_t) vma->vm_start,
+						user_buff_size)) {
+#endif
+		dev_err(hdev->dev,
+			"user pointer is invalid - 0x%lx\n",
+			vma->vm_start);
+
+		rc = -EINVAL;
+		goto put_buff;
+	}
+
+	if (atomic_cmpxchg(&buff->mmap, 0, 1)) {
+		dev_err(hdev->dev, "TS buff memory mmap failed, already mmaped to user\n");
+		rc = -EINVAL;
+		goto put_buff;
+	}
+
+	vma->vm_ops = &ts_buff_vm_ops;
+	vma->vm_private_data = buff;
+	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP | VM_DONTCOPY | VM_NORESERVE;
+	rc = remap_vmalloc_range(vma, buff->user_buff_address, 0);
+	if (rc) {
+		atomic_set(&buff->mmap, 0);
+		goto put_buff;
+	}
+
+	buff->mmap_size = buff->user_buff_size;
+	vma->vm_pgoff = handle;
+
+	return 0;
+
+put_buff:
+	hl_ts_put(buff);
+	return rc;
+}
+
+void hl_ts_mgr_init(struct hl_ts_mgr *mgr)
+{
+	spin_lock_init(&mgr->ts_lock);
+	idr_init(&mgr->ts_handles);
+}
+
+void hl_ts_mgr_fini(struct hl_device *hdev, struct hl_ts_mgr *mgr)
+{
+	struct hl_ts_buff *buff;
+	struct idr *idp;
+	u32 id;
+
+	idp = &mgr->ts_handles;
+
+	idr_for_each_entry(idp, buff, id) {
+		if (kref_put(&buff->refcount, ts_buff_release) != 1)
+			dev_err(hdev->dev, "TS buff handle %d for CTX is still alive\n",
+							id);
+	}
+
+	idr_destroy(&mgr->ts_handles);
+}
+
+static struct hl_ts_buff *hl_ts_alloc_buff(struct hl_device *hdev, u32 num_elements)
+{
+	struct hl_ts_buff *ts_buff = NULL;
+	u32 size;
+	void *p;
+
+	ts_buff = kzalloc(sizeof(*ts_buff), GFP_KERNEL);
+	if (!ts_buff)
+		return NULL;
+
+	/* Allocate the user buffer */
+	size = num_elements * sizeof(u64);
+	p = vmalloc_user(size);
+	if (!p)
+		goto free_mem;
+
+	ts_buff->user_buff_address = p;
+	ts_buff->user_buff_size = size;
+
+	/* Allocate the internal kernel buffer */
+	size = num_elements * sizeof(struct hl_user_pending_interrupt);
+	p = vmalloc(size);
+	if (!p)
+		goto free_user_buff;
+
+	ts_buff->kernel_buff_address = p;
+	ts_buff->kernel_buff_size = size;
+
+	return ts_buff;
+
+free_user_buff:
+	vfree(ts_buff->user_buff_address);
+free_mem:
+	kfree(ts_buff);
+	return NULL;
+}
+
+/**
+ * allocate_timestamps_buffers() - allocate timestamps buffers
+ * This function will allocate ts buffer that will later on be mapped to the user
+ * in order to be able to read the timestamp.
+ * in additon it'll allocate an extra buffer for registration management.
+ * since we cannot fail during registration for out-of-memory situation, so
+ * we'll prepare a pool which will be used as user interrupt nodes and instead
+ * of dynamically allocating nodes while registration we'll pick the node from
+ * this pool. in addtion it'll add node to the mapping hash which will be used
+ * to map user ts buffer to the internal kernel ts buffer.
+ * @hpriv: pointer to the private data of the fd
+ * @args: ioctl input
+ * @handle: user timestamp buffer handle as an output
+ */
+static int allocate_timestamps_buffers(struct hl_fpriv *hpriv, struct hl_mem_in *args, u64 *handle)
+{
+	struct hl_ts_mgr *ts_mgr = &hpriv->ts_mem_mgr;
+	struct hl_device *hdev = hpriv->hdev;
+	struct hl_ts_buff *ts_buff;
+	int rc = 0;
+
+	if (args->num_of_elements > TS_MAX_ELEMENTS_NUM) {
+		dev_err(hdev->dev, "Num of elements exceeds Max allowed number (0x%x > 0x%x)\n",
+				args->num_of_elements, TS_MAX_ELEMENTS_NUM);
+		return -EINVAL;
+	}
+
+	/* Allocate ts buffer object
+	 * This object will contain two buffers one that will be mapped to the user
+	 * and another internal buffer for the driver use only, which won't be mapped
+	 * to the user.
+	 */
+	ts_buff = hl_ts_alloc_buff(hdev, args->num_of_elements);
+	if (!ts_buff) {
+		rc = -ENOMEM;
+		goto out_err;
+	}
+
+	spin_lock(&ts_mgr->ts_lock);
+	rc = idr_alloc(&ts_mgr->ts_handles, ts_buff, 1, 0, GFP_ATOMIC);
+	spin_unlock(&ts_mgr->ts_lock);
+	if (rc < 0) {
+		dev_err(hdev->dev, "Failed to allocate IDR for a new ts buffer\n");
+		goto release_ts_buff;
+	}
+
+	ts_buff->id = rc;
+	ts_buff->hdev = hdev;
+
+	kref_init(&ts_buff->refcount);
+
+	/* idr is 32-bit so we can safely OR it with a mask that is above 32 bit */
+	*handle = (u64) ts_buff->id | HL_MMAP_TYPE_TS_BUFF;
+	*handle <<= PAGE_SHIFT;
+
+	dev_dbg(hdev->dev, "Created ts buff object handle(%u)\n", ts_buff->id);
+
+	return 0;
+
+release_ts_buff:
+	kref_put(&ts_buff->refcount, ts_buff_release);
+out_err:
+	*handle = 0;
+	return rc;
+}
+
 int hl_mem_ioctl(struct hl_fpriv *hpriv, void *data)
 {
 	enum hl_device_status status;
@@ -2154,6 +2443,9 @@ int hl_mem_ioctl(struct hl_fpriv *hpriv, void *data)
 		args->out.fd = dmabuf_fd;
 		break;
 
+	case HL_MEM_OP_TS_ALLOC:
+		rc = allocate_timestamps_buffers(hpriv, &args->in, &args->out.handle);
+		break;
 	default:
 		dev_err(hdev->dev, "Unknown opcode for memory IOCTL\n");
 		rc = -EINVAL;
@@ -2607,11 +2899,12 @@ int hl_vm_ctx_init(struct hl_ctx *ctx)
  */
 void hl_vm_ctx_fini(struct hl_ctx *ctx)
 {
+	struct hl_vm_phys_pg_pack *phys_pg_list, *tmp_phys_node;
 	struct hl_device *hdev = ctx->hdev;
-	struct hl_vm *vm = &hdev->vm;
-	struct hl_vm_phys_pg_pack *phys_pg_list;
 	struct hl_vm_hash_node *hnode;
+	struct hl_vm *vm = &hdev->vm;
 	struct hlist_node *tmp_node;
+	struct list_head free_list;
 	struct hl_mem_in args;
 	int i;
 
@@ -2644,19 +2937,24 @@ void hl_vm_ctx_fini(struct hl_ctx *ctx)
 
 	mutex_unlock(&ctx->mmu_lock);
 
+	INIT_LIST_HEAD(&free_list);
+
 	spin_lock(&vm->idr_lock);
 	idr_for_each_entry(&vm->phys_pg_pack_handles, phys_pg_list, i)
 		if (phys_pg_list->asid == ctx->asid) {
 			dev_dbg(hdev->dev,
 				"page list 0x%px of asid %d is still alive\n",
 				phys_pg_list, ctx->asid);
-			atomic64_sub(phys_pg_list->total_size,
-					&hdev->dram_used_mem);
-			free_phys_pg_pack(hdev, phys_pg_list);
+
+			atomic64_sub(phys_pg_list->total_size, &hdev->dram_used_mem);
 			idr_remove(&vm->phys_pg_pack_handles, i);
+			list_add(&phys_pg_list->node, &free_list);
 		}
 	spin_unlock(&vm->idr_lock);
 
+	list_for_each_entry_safe(phys_pg_list, tmp_phys_node, &free_list, node)
+		free_phys_pg_pack(hdev, phys_pg_list);
+
 	va_range_fini(hdev, ctx->va_range[HL_VA_RANGE_TYPE_DRAM]);
 	va_range_fini(hdev, ctx->va_range[HL_VA_RANGE_TYPE_HOST]);
 
diff --git a/drivers/misc/habanalabs/common/mmu/mmu.c b/drivers/misc/habanalabs/common/mmu/mmu.c
index 9153a1f55175..810b73421ce1 100644
--- a/drivers/misc/habanalabs/common/mmu/mmu.c
+++ b/drivers/misc/habanalabs/common/mmu/mmu.c
@@ -662,3 +662,58 @@ int hl_mmu_invalidate_cache_range(struct hl_device *hdev, bool is_hard,
 	return rc;
 }
 
+u64 hl_mmu_get_next_hop_addr(struct hl_ctx *ctx, u64 curr_pte)
+{
+	return (curr_pte & PAGE_PRESENT_MASK) ? (curr_pte & HOP_PHYS_ADDR_MASK) : ULLONG_MAX;
+}
+
+/**
+ * hl_mmu_get_hop_pte_phys_addr() - extract PTE address from HOP
+ * @ctx: pointer to the context structure to initialize.
+ * @hop_idx: HOP index.
+ * @hop_addr: HOP address.
+ * @virt_addr: virtual address fro the translation.
+ *
+ * @return the matching PTE value on success, otherwise U64_MAX.
+ */
+u64 hl_mmu_get_hop_pte_phys_addr(struct hl_ctx *ctx, struct hl_mmu_properties *mmu_prop,
+					u8 hop_idx, u64 hop_addr, u64 virt_addr)
+{
+	u64 mask, shift;
+
+	if (hop_idx >= mmu_prop->num_hops) {
+		dev_err_ratelimited(ctx->hdev->dev, "Invalid hop index %d\n", hop_idx);
+		return U64_MAX;
+	}
+
+	/* currently max number of HOPs is 6 */
+	switch (hop_idx) {
+	case 0:
+		mask = mmu_prop->hop0_mask;
+		shift = mmu_prop->hop0_shift;
+		break;
+	case 1:
+		mask = mmu_prop->hop1_mask;
+		shift = mmu_prop->hop1_shift;
+		break;
+	case 2:
+		mask = mmu_prop->hop2_mask;
+		shift = mmu_prop->hop2_shift;
+		break;
+	case 3:
+		mask = mmu_prop->hop3_mask;
+		shift = mmu_prop->hop3_shift;
+		break;
+	case 4:
+		mask = mmu_prop->hop4_mask;
+		shift = mmu_prop->hop4_shift;
+		break;
+	default:
+		mask = mmu_prop->hop5_mask;
+		shift = mmu_prop->hop5_shift;
+		break;
+	}
+
+	return hop_addr + ctx->hdev->asic_prop.mmu_pte_size * ((virt_addr & mask) >> shift);
+}
+
diff --git a/drivers/misc/habanalabs/common/mmu/mmu_v1.c b/drivers/misc/habanalabs/common/mmu/mmu_v1.c
index 6134b6ae7615..d03786d0c407 100644
--- a/drivers/misc/habanalabs/common/mmu/mmu_v1.c
+++ b/drivers/misc/habanalabs/common/mmu/mmu_v1.c
@@ -217,18 +217,10 @@ static inline u64 get_hop4_pte_addr(struct hl_ctx *ctx,
 					mmu_prop->hop4_shift);
 }
 
-static inline u64 get_next_hop_addr(struct hl_ctx *ctx, u64 curr_pte)
-{
-	if (curr_pte & PAGE_PRESENT_MASK)
-		return curr_pte & HOP_PHYS_ADDR_MASK;
-	else
-		return ULLONG_MAX;
-}
-
 static inline u64 get_alloc_next_hop_addr(struct hl_ctx *ctx, u64 curr_pte,
 						bool *is_new_hop)
 {
-	u64 hop_addr = get_next_hop_addr(ctx, curr_pte);
+	u64 hop_addr = hl_mmu_get_next_hop_addr(ctx, curr_pte);
 
 	if (hop_addr == ULLONG_MAX) {
 		hop_addr = alloc_hop(ctx);
@@ -467,7 +459,7 @@ static void hl_mmu_v1_fini(struct hl_device *hdev)
 {
 	/* MMU H/W fini was already done in device hw_fini() */
 
-	if (!ZERO_OR_NULL_PTR(hdev->mmu_priv.hr.mmu_shadow_hop0)) {
+	if (!ZERO_OR_NULL_PTR(hdev->mmu_priv.dr.mmu_shadow_hop0)) {
 		kvfree(hdev->mmu_priv.dr.mmu_shadow_hop0);
 		gen_pool_destroy(hdev->mmu_priv.dr.mmu_pgt_pool);
 
@@ -546,7 +538,7 @@ static int _hl_mmu_v1_unmap(struct hl_ctx *ctx,
 
 	curr_pte = *(u64 *) (uintptr_t) hop0_pte_addr;
 
-	hop1_addr = get_next_hop_addr(ctx, curr_pte);
+	hop1_addr = hl_mmu_get_next_hop_addr(ctx, curr_pte);
 
 	if (hop1_addr == ULLONG_MAX)
 		goto not_mapped;
@@ -555,7 +547,7 @@ static int _hl_mmu_v1_unmap(struct hl_ctx *ctx,
 
 	curr_pte = *(u64 *) (uintptr_t) hop1_pte_addr;
 
-	hop2_addr = get_next_hop_addr(ctx, curr_pte);
+	hop2_addr = hl_mmu_get_next_hop_addr(ctx, curr_pte);
 
 	if (hop2_addr == ULLONG_MAX)
 		goto not_mapped;
@@ -564,7 +556,7 @@ static int _hl_mmu_v1_unmap(struct hl_ctx *ctx,
 
 	curr_pte = *(u64 *) (uintptr_t) hop2_pte_addr;
 
-	hop3_addr = get_next_hop_addr(ctx, curr_pte);
+	hop3_addr = hl_mmu_get_next_hop_addr(ctx, curr_pte);
 
 	if (hop3_addr == ULLONG_MAX)
 		goto not_mapped;
@@ -582,7 +574,7 @@ static int _hl_mmu_v1_unmap(struct hl_ctx *ctx,
 	}
 
 	if (!is_huge) {
-		hop4_addr = get_next_hop_addr(ctx, curr_pte);
+		hop4_addr = hl_mmu_get_next_hop_addr(ctx, curr_pte);
 
 		if (hop4_addr == ULLONG_MAX)
 			goto not_mapped;
@@ -845,27 +837,6 @@ static void hl_mmu_v1_swap_in(struct hl_ctx *ctx)
 
 }
 
-static inline u64 get_hop_pte_addr(struct hl_ctx *ctx,
-				struct hl_mmu_properties *mmu_prop,
-				int hop_num, u64 hop_addr, u64 virt_addr)
-{
-	switch (hop_num) {
-	case 0:
-		return get_hop0_pte_addr(ctx, mmu_prop, hop_addr, virt_addr);
-	case 1:
-		return get_hop1_pte_addr(ctx, mmu_prop, hop_addr, virt_addr);
-	case 2:
-		return get_hop2_pte_addr(ctx, mmu_prop, hop_addr, virt_addr);
-	case 3:
-		return get_hop3_pte_addr(ctx, mmu_prop, hop_addr, virt_addr);
-	case 4:
-		return get_hop4_pte_addr(ctx, mmu_prop, hop_addr, virt_addr);
-	default:
-		break;
-	}
-	return U64_MAX;
-}
-
 static int hl_mmu_v1_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr,
 				struct hl_mmu_hop_info *hops)
 {
@@ -906,7 +877,7 @@ static int hl_mmu_v1_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr,
 
 	hops->hop_info[0].hop_addr = get_phys_hop0_addr(ctx);
 	hops->hop_info[0].hop_pte_addr =
-			get_hop_pte_addr(ctx, mmu_prop, 0,
+			hl_mmu_get_hop_pte_phys_addr(ctx, mmu_prop, 0,
 					hops->hop_info[0].hop_addr, virt_addr);
 	hops->hop_info[0].hop_pte_val =
 			hdev->asic_funcs->read_pte(hdev,
@@ -914,13 +885,13 @@ static int hl_mmu_v1_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr,
 
 	for (i = 1 ; i < used_hops ; i++) {
 		hops->hop_info[i].hop_addr =
-			get_next_hop_addr(ctx,
+			hl_mmu_get_next_hop_addr(ctx,
 					hops->hop_info[i - 1].hop_pte_val);
 		if (hops->hop_info[i].hop_addr == ULLONG_MAX)
 			return -EFAULT;
 
 		hops->hop_info[i].hop_pte_addr =
-				get_hop_pte_addr(ctx, mmu_prop, i,
+				hl_mmu_get_hop_pte_phys_addr(ctx, mmu_prop, i,
 						hops->hop_info[i].hop_addr,
 						virt_addr);
 		hops->hop_info[i].hop_pte_val =
diff --git a/drivers/misc/habanalabs/common/pci/pci.c b/drivers/misc/habanalabs/common/pci/pci.c
index 0b5366cc84fd..bb9ce22bafc4 100644
--- a/drivers/misc/habanalabs/common/pci/pci.c
+++ b/drivers/misc/habanalabs/common/pci/pci.c
@@ -338,10 +338,7 @@ int hl_pci_set_outbound_region(struct hl_device *hdev,
 				lower_32_bits(outbound_region_end_address));
 	rc |= hl_pci_iatu_write(hdev, 0x014, 0);
 
-	if ((hdev->power9_64bit_dma_enable) && (hdev->dma_mask == 64))
-		rc |= hl_pci_iatu_write(hdev, 0x018, 0x08000000);
-	else
-		rc |= hl_pci_iatu_write(hdev, 0x018, 0);
+	rc |= hl_pci_iatu_write(hdev, 0x018, 0);
 
 	rc |= hl_pci_iatu_write(hdev, 0x020,
 				upper_32_bits(outbound_region_end_address));
@@ -411,13 +408,13 @@ int hl_pci_init(struct hl_device *hdev)
 
 	rc = hdev->asic_funcs->pci_bars_map(hdev);
 	if (rc) {
-		dev_err(hdev->dev, "Failed to initialize PCI BARs\n");
+		dev_err(hdev->dev, "Failed to map PCI BAR addresses\n");
 		goto disable_device;
 	}
 
 	rc = hdev->asic_funcs->init_iatu(hdev);
 	if (rc) {
-		dev_err(hdev->dev, "Failed to initialize iATU\n");
+		dev_err(hdev->dev, "PCI controller was not initialized successfully\n");
 		goto unmap_pci_bars;
 	}
 
diff --git a/drivers/misc/habanalabs/common/sysfs.c b/drivers/misc/habanalabs/common/sysfs.c
index 45c715325e2a..9ebeb18ab85e 100644
--- a/drivers/misc/habanalabs/common/sysfs.c
+++ b/drivers/misc/habanalabs/common/sysfs.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 /*
- * Copyright 2016-2019 HabanaLabs, Ltd.
+ * Copyright 2016-2022 HabanaLabs, Ltd.
  * All Rights Reserved.
  */
 
@@ -9,105 +9,91 @@
 
 #include <linux/pci.h>
 
-long hl_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr)
+static ssize_t clk_max_freq_mhz_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	struct cpucp_packet pkt;
-	u32 used_pll_idx;
-	u64 result;
-	int rc;
-
-	rc = get_used_pll_index(hdev, pll_index, &used_pll_idx);
-	if (rc)
-		return rc;
-
-	memset(&pkt, 0, sizeof(pkt));
+	struct hl_device *hdev = dev_get_drvdata(dev);
+	long value;
 
-	if (curr)
-		pkt.ctl = cpu_to_le32(CPUCP_PACKET_FREQUENCY_CURR_GET <<
-						CPUCP_PKT_CTL_OPCODE_SHIFT);
-	else
-		pkt.ctl = cpu_to_le32(CPUCP_PACKET_FREQUENCY_GET <<
-						CPUCP_PKT_CTL_OPCODE_SHIFT);
-	pkt.pll_index = cpu_to_le32((u32)used_pll_idx);
+	if (!hl_device_operational(hdev, NULL))
+		return -ENODEV;
 
-	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-						0, &result);
+	value = hl_fw_get_frequency(hdev, hdev->asic_prop.clk_pll_index, false);
+	if (value < 0)
+		return value;
 
-	if (rc) {
-		dev_err(hdev->dev,
-			"Failed to get frequency of PLL %d, error %d\n",
-			used_pll_idx, rc);
-		return rc;
-	}
+	hdev->asic_prop.max_freq_value = value;
 
-	return (long) result;
+	return sprintf(buf, "%lu\n", (value / 1000 / 1000));
 }
 
-void hl_set_frequency(struct hl_device *hdev, u32 pll_index, u64 freq)
+static ssize_t clk_max_freq_mhz_store(struct device *dev, struct device_attribute *attr,
+					const char *buf, size_t count)
 {
-	struct cpucp_packet pkt;
-	u32 used_pll_idx;
+	struct hl_device *hdev = dev_get_drvdata(dev);
 	int rc;
+	u64 value;
 
-	rc = get_used_pll_index(hdev, pll_index, &used_pll_idx);
-	if (rc)
-		return;
+	if (!hl_device_operational(hdev, NULL)) {
+		count = -ENODEV;
+		goto fail;
+	}
 
-	memset(&pkt, 0, sizeof(pkt));
+	rc = kstrtoull(buf, 0, &value);
+	if (rc) {
+		count = -EINVAL;
+		goto fail;
+	}
 
-	pkt.ctl = cpu_to_le32(CPUCP_PACKET_FREQUENCY_SET <<
-					CPUCP_PKT_CTL_OPCODE_SHIFT);
-	pkt.pll_index = cpu_to_le32((u32)used_pll_idx);
-	pkt.value = cpu_to_le64(freq);
+	hdev->asic_prop.max_freq_value = value * 1000 * 1000;
 
-	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-						0, NULL);
+	hl_fw_set_frequency(hdev, hdev->asic_prop.clk_pll_index, hdev->asic_prop.max_freq_value);
 
-	if (rc)
-		dev_err(hdev->dev,
-			"Failed to set frequency to PLL %d, error %d\n",
-			used_pll_idx, rc);
+fail:
+	return count;
 }
 
-u64 hl_get_max_power(struct hl_device *hdev)
+static ssize_t clk_cur_freq_mhz_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	struct cpucp_packet pkt;
-	u64 result;
-	int rc;
+	struct hl_device *hdev = dev_get_drvdata(dev);
+	long value;
 
-	memset(&pkt, 0, sizeof(pkt));
+	if (!hl_device_operational(hdev, NULL))
+		return -ENODEV;
 
-	pkt.ctl = cpu_to_le32(CPUCP_PACKET_MAX_POWER_GET <<
-				CPUCP_PKT_CTL_OPCODE_SHIFT);
+	value = hl_fw_get_frequency(hdev, hdev->asic_prop.clk_pll_index, true);
+	if (value < 0)
+		return value;
 
-	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-						0, &result);
+	return sprintf(buf, "%lu\n", (value / 1000 / 1000));
+}
 
-	if (rc) {
-		dev_err(hdev->dev, "Failed to get max power, error %d\n", rc);
-		return (u64) rc;
-	}
+static DEVICE_ATTR_RW(clk_max_freq_mhz);
+static DEVICE_ATTR_RO(clk_cur_freq_mhz);
 
-	return result;
-}
+static struct attribute *hl_dev_clk_attrs[] = {
+	&dev_attr_clk_max_freq_mhz.attr,
+	&dev_attr_clk_cur_freq_mhz.attr,
+};
 
-void hl_set_max_power(struct hl_device *hdev)
+static ssize_t vrm_ver_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	struct cpucp_packet pkt;
-	int rc;
+	struct hl_device *hdev = dev_get_drvdata(dev);
+	struct cpucp_info *cpucp_info;
 
-	memset(&pkt, 0, sizeof(pkt));
+	cpucp_info = &hdev->asic_prop.cpucp_info;
 
-	pkt.ctl = cpu_to_le32(CPUCP_PACKET_MAX_POWER_SET <<
-				CPUCP_PKT_CTL_OPCODE_SHIFT);
-	pkt.value = cpu_to_le64(hdev->max_power);
+	if (cpucp_info->infineon_second_stage_version)
+		return sprintf(buf, "%#04x %#04x\n", le32_to_cpu(cpucp_info->infineon_version),
+				le32_to_cpu(cpucp_info->infineon_second_stage_version));
+	else
+		return sprintf(buf, "%#04x\n", le32_to_cpu(cpucp_info->infineon_version));
+}
 
-	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-						0, NULL);
+static DEVICE_ATTR_RO(vrm_ver);
 
-	if (rc)
-		dev_err(hdev->dev, "Failed to set max power, error %d\n", rc);
-}
+static struct attribute *hl_dev_vrm_attrs[] = {
+	&dev_attr_vrm_ver.attr,
+};
 
 static ssize_t uboot_ver_show(struct device *dev, struct device_attribute *attr,
 				char *buf)
@@ -158,20 +144,6 @@ static ssize_t cpucp_ver_show(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%s\n", hdev->asic_prop.cpucp_info.cpucp_version);
 }
 
-static ssize_t infineon_ver_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	struct hl_device *hdev = dev_get_drvdata(dev);
-
-	if (hdev->asic_prop.cpucp_info.infineon_second_stage_version)
-		return sprintf(buf, "%#04x %#04x\n",
-			le32_to_cpu(hdev->asic_prop.cpucp_info.infineon_version),
-			le32_to_cpu(hdev->asic_prop.cpucp_info.infineon_second_stage_version));
-	else
-		return sprintf(buf, "%#04x\n",
-			le32_to_cpu(hdev->asic_prop.cpucp_info.infineon_version));
-}
-
 static ssize_t fuse_ver_show(struct device *dev, struct device_attribute *attr,
 				char *buf)
 {
@@ -188,6 +160,14 @@ static ssize_t thermal_ver_show(struct device *dev,
 	return sprintf(buf, "%s", hdev->asic_prop.cpucp_info.thermal_version);
 }
 
+static ssize_t fw_os_ver_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%s", hdev->asic_prop.cpucp_info.fw_os_version);
+}
+
 static ssize_t preboot_btl_ver_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
@@ -323,7 +303,9 @@ static ssize_t max_power_show(struct device *dev, struct device_attribute *attr,
 	if (!hl_device_operational(hdev, NULL))
 		return -ENODEV;
 
-	val = hl_get_max_power(hdev);
+	val = hl_fw_get_max_power(hdev);
+	if (val < 0)
+		return val;
 
 	return sprintf(buf, "%lu\n", val);
 }
@@ -348,7 +330,7 @@ static ssize_t max_power_store(struct device *dev,
 	}
 
 	hdev->max_power = value;
-	hl_set_max_power(hdev);
+	hl_fw_set_max_power(hdev);
 
 out:
 	return count;
@@ -394,7 +376,6 @@ static DEVICE_ATTR_RO(device_type);
 static DEVICE_ATTR_RO(fuse_ver);
 static DEVICE_ATTR_WO(hard_reset);
 static DEVICE_ATTR_RO(hard_reset_cnt);
-static DEVICE_ATTR_RO(infineon_ver);
 static DEVICE_ATTR_RW(max_power);
 static DEVICE_ATTR_RO(pci_addr);
 static DEVICE_ATTR_RO(preboot_btl_ver);
@@ -403,6 +384,7 @@ static DEVICE_ATTR_RO(soft_reset_cnt);
 static DEVICE_ATTR_RO(status);
 static DEVICE_ATTR_RO(thermal_ver);
 static DEVICE_ATTR_RO(uboot_ver);
+static DEVICE_ATTR_RO(fw_os_ver);
 
 static struct bin_attribute bin_attr_eeprom = {
 	.attr = {.name = "eeprom", .mode = (0444)},
@@ -420,13 +402,13 @@ static struct attribute *hl_dev_attrs[] = {
 	&dev_attr_fuse_ver.attr,
 	&dev_attr_hard_reset.attr,
 	&dev_attr_hard_reset_cnt.attr,
-	&dev_attr_infineon_ver.attr,
 	&dev_attr_max_power.attr,
 	&dev_attr_pci_addr.attr,
 	&dev_attr_preboot_btl_ver.attr,
 	&dev_attr_status.attr,
 	&dev_attr_thermal_ver.attr,
 	&dev_attr_uboot_ver.attr,
+	&dev_attr_fw_os_ver.attr,
 	NULL,
 };
 
@@ -441,10 +423,12 @@ static struct attribute_group hl_dev_attr_group = {
 };
 
 static struct attribute_group hl_dev_clks_attr_group;
+static struct attribute_group hl_dev_vrm_attr_group;
 
 static const struct attribute_group *hl_dev_attr_groups[] = {
 	&hl_dev_attr_group,
 	&hl_dev_clks_attr_group,
+	&hl_dev_vrm_attr_group,
 	NULL,
 };
 
@@ -463,13 +447,23 @@ static const struct attribute_group *hl_dev_inference_attr_groups[] = {
 	NULL,
 };
 
+void hl_sysfs_add_dev_clk_attr(struct hl_device *hdev, struct attribute_group *dev_clk_attr_grp)
+{
+	dev_clk_attr_grp->attrs = hl_dev_clk_attrs;
+}
+
+void hl_sysfs_add_dev_vrm_attr(struct hl_device *hdev, struct attribute_group *dev_vrm_attr_grp)
+{
+	dev_vrm_attr_grp->attrs = hl_dev_vrm_attrs;
+}
+
 int hl_sysfs_init(struct hl_device *hdev)
 {
 	int rc;
 
 	hdev->max_power = hdev->asic_prop.max_power_default;
 
-	hdev->asic_funcs->add_device_attr(hdev, &hl_dev_clks_attr_group);
+	hdev->asic_funcs->add_device_attr(hdev, &hl_dev_clks_attr_group, &hl_dev_vrm_attr_group);
 
 	rc = device_add_groups(hdev->dev, hl_dev_attr_groups);
 	if (rc) {
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 013c6da2e3ca..21c2b678ff72 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 /*
- * Copyright 2016-2021 HabanaLabs, Ltd.
+ * Copyright 2016-2022 HabanaLabs, Ltd.
  * All Rights Reserved.
  */
 
@@ -458,7 +458,6 @@ struct ecc_info_extract_params {
 	u64 block_address;
 	u32 num_memories;
 	bool derr;
-	bool disable_clock_gating;
 };
 
 static int gaudi_mmu_update_asid_hop0_addr(struct hl_device *hdev, u32 asid,
@@ -614,6 +613,9 @@ static int gaudi_set_fixed_properties(struct hl_device *hdev)
 	prop->pmmu.page_size = PAGE_SIZE_4KB;
 	prop->pmmu.num_hops = MMU_ARCH_5_HOPS;
 	prop->pmmu.last_mask = LAST_MASK;
+	/* TODO: will be duplicated until implementing per-MMU props */
+	prop->pmmu.hop_table_size = prop->mmu_hop_table_size;
+	prop->pmmu.hop0_tables_total_size = prop->mmu_hop0_tables_total_size;
 
 	/* PMMU and HPMMU are the same except of page size */
 	memcpy(&prop->pmmu_huge, &prop->pmmu, sizeof(prop->pmmu));
@@ -667,6 +669,10 @@ static int gaudi_set_fixed_properties(struct hl_device *hdev)
 
 	prop->use_get_power_for_reset_history = true;
 
+	prop->configurable_stop_on_err = true;
+
+	prop->set_max_power_on_device_init = true;
+
 	return 0;
 }
 
@@ -1636,7 +1642,7 @@ static int gaudi_late_init(struct hl_device *hdev)
 	 */
 	gaudi_mmu_prepare(hdev, 1);
 
-	hdev->asic_funcs->set_pll_profile(hdev, PLL_LAST);
+	hl_fw_set_pll_profile(hdev);
 
 	return 0;
 
@@ -1896,7 +1902,6 @@ static int gaudi_sw_init(struct hl_device *hdev)
 		goto free_cpu_accessible_dma_pool;
 
 	spin_lock_init(&gaudi->hw_queues_lock);
-	mutex_init(&gaudi->clk_gate_mutex);
 
 	hdev->supports_sync_stream = true;
 	hdev->supports_coresight = true;
@@ -1946,8 +1951,6 @@ static int gaudi_sw_fini(struct hl_device *hdev)
 
 	dma_pool_destroy(hdev->dma_pool);
 
-	mutex_destroy(&gaudi->clk_gate_mutex);
-
 	kfree(gaudi);
 
 	return 0;
@@ -3738,76 +3741,8 @@ static void gaudi_tpc_stall(struct hl_device *hdev)
 	WREG32(mmTPC7_CFG_TPC_STALL, 1 << TPC0_CFG_TPC_STALL_V_SHIFT);
 }
 
-static void gaudi_set_clock_gating(struct hl_device *hdev)
-{
-	struct gaudi_device *gaudi = hdev->asic_specific;
-	u32 qman_offset;
-	bool enable;
-	int i;
-
-	/* In case we are during debug session, don't enable the clock gate
-	 * as it may interfere
-	 */
-	if (hdev->in_debug)
-		return;
-
-	if (hdev->asic_prop.fw_security_enabled)
-		return;
-
-	for (i = GAUDI_PCI_DMA_1, qman_offset = 0 ; i < GAUDI_HBM_DMA_1 ; i++) {
-		enable = !!(hdev->clock_gating_mask &
-				(BIT_ULL(gaudi_dma_assignment[i])));
-
-		qman_offset = gaudi_dma_assignment[i] * DMA_QMAN_OFFSET;
-		WREG32(mmDMA0_QM_CGM_CFG1 + qman_offset,
-				enable ? QMAN_CGM1_PWR_GATE_EN : 0);
-		WREG32(mmDMA0_QM_CGM_CFG + qman_offset,
-				enable ? QMAN_UPPER_CP_CGM_PWR_GATE_EN : 0);
-	}
-
-	for (i = GAUDI_HBM_DMA_1 ; i < GAUDI_DMA_MAX ; i++) {
-		enable = !!(hdev->clock_gating_mask &
-				(BIT_ULL(gaudi_dma_assignment[i])));
-
-		/* GC sends work to DMA engine through Upper CP in DMA5 so
-		 * we need to not enable clock gating in that DMA
-		 */
-		if (i == GAUDI_HBM_DMA_4)
-			enable = 0;
-
-		qman_offset = gaudi_dma_assignment[i] * DMA_QMAN_OFFSET;
-		WREG32(mmDMA0_QM_CGM_CFG1 + qman_offset,
-				enable ? QMAN_CGM1_PWR_GATE_EN : 0);
-		WREG32(mmDMA0_QM_CGM_CFG + qman_offset,
-				enable ? QMAN_COMMON_CP_CGM_PWR_GATE_EN : 0);
-	}
-
-	enable = !!(hdev->clock_gating_mask & (BIT_ULL(GAUDI_ENGINE_ID_MME_0)));
-	WREG32(mmMME0_QM_CGM_CFG1, enable ? QMAN_CGM1_PWR_GATE_EN : 0);
-	WREG32(mmMME0_QM_CGM_CFG, enable ? QMAN_COMMON_CP_CGM_PWR_GATE_EN : 0);
-
-	enable = !!(hdev->clock_gating_mask & (BIT_ULL(GAUDI_ENGINE_ID_MME_2)));
-	WREG32(mmMME2_QM_CGM_CFG1, enable ? QMAN_CGM1_PWR_GATE_EN : 0);
-	WREG32(mmMME2_QM_CGM_CFG, enable ? QMAN_COMMON_CP_CGM_PWR_GATE_EN : 0);
-
-	for (i = 0, qman_offset = 0 ; i < TPC_NUMBER_OF_ENGINES ; i++) {
-		enable = !!(hdev->clock_gating_mask &
-				(BIT_ULL(GAUDI_ENGINE_ID_TPC_0 + i)));
-
-		WREG32(mmTPC0_QM_CGM_CFG1 + qman_offset,
-				enable ? QMAN_CGM1_PWR_GATE_EN : 0);
-		WREG32(mmTPC0_QM_CGM_CFG + qman_offset,
-				enable ? QMAN_COMMON_CP_CGM_PWR_GATE_EN : 0);
-
-		qman_offset += TPC_QMAN_OFFSET;
-	}
-
-	gaudi->hw_cap_initialized |= HW_CAP_CLK_GATE;
-}
-
 static void gaudi_disable_clock_gating(struct hl_device *hdev)
 {
-	struct gaudi_device *gaudi = hdev->asic_specific;
 	u32 qman_offset;
 	int i;
 
@@ -3832,8 +3767,6 @@ static void gaudi_disable_clock_gating(struct hl_device *hdev)
 
 		qman_offset += (mmTPC1_QM_CGM_CFG - mmTPC0_QM_CGM_CFG);
 	}
-
-	gaudi->hw_cap_initialized &= ~(HW_CAP_CLK_GATE);
 }
 
 static void gaudi_enable_timestamp(struct hl_device *hdev)
@@ -3876,8 +3809,6 @@ static void gaudi_halt_engines(struct hl_device *hdev, bool hard_reset, bool fw_
 	gaudi_stop_hbm_dma_qmans(hdev);
 	gaudi_stop_pci_dma_qmans(hdev);
 
-	hdev->asic_funcs->disable_clock_gating(hdev);
-
 	msleep(wait_timeout_ms);
 
 	gaudi_pci_dma_stall(hdev);
@@ -3931,7 +3862,7 @@ static int gaudi_mmu_init(struct hl_device *hdev)
 	/* mem cache invalidation */
 	WREG32(mmSTLB_MEM_CACHE_INVALIDATION, 1);
 
-	hdev->asic_funcs->mmu_invalidate_cache(hdev, true, 0);
+	hl_mmu_invalidate_cache(hdev, true, 0);
 
 	WREG32(mmMMU_UP_MMU_ENABLE, 1);
 	WREG32(mmMMU_UP_SPI_MASK, 0xF);
@@ -4203,10 +4134,8 @@ static int gaudi_hw_init(struct hl_device *hdev)
 
 	/* In case the clock gating was enabled in preboot we need to disable
 	 * it here before touching the MME/TPC registers.
-	 * There is no need to take clk gating mutex because when this function
-	 * runs, no other relevant code can run
 	 */
-	hdev->asic_funcs->disable_clock_gating(hdev);
+	gaudi_disable_clock_gating(hdev);
 
 	/* SRAM scrambler must be initialized after CPU is running from HBM */
 	gaudi_init_scrambler_sram(hdev);
@@ -4232,8 +4161,6 @@ static int gaudi_hw_init(struct hl_device *hdev)
 
 	gaudi_init_nic_qmans(hdev);
 
-	hdev->asic_funcs->set_clock_gating(hdev);
-
 	gaudi_enable_timestamp(hdev);
 
 	/* MSI must be enabled before CPU queues and NIC are initialized */
@@ -4400,14 +4327,11 @@ skip_reset:
 			status);
 
 	if (gaudi) {
-		gaudi->hw_cap_initialized &= ~(HW_CAP_CPU | HW_CAP_CPU_Q |
-				HW_CAP_HBM | HW_CAP_PCI_DMA |
-				HW_CAP_MME | HW_CAP_TPC_MASK |
-				HW_CAP_HBM_DMA | HW_CAP_PLL |
-				HW_CAP_NIC_MASK | HW_CAP_MMU |
-				HW_CAP_SRAM_SCRAMBLER |
-				HW_CAP_HBM_SCRAMBLER |
-				HW_CAP_CLK_GATE);
+		gaudi->hw_cap_initialized &= ~(HW_CAP_CPU | HW_CAP_CPU_Q | HW_CAP_HBM |
+						HW_CAP_PCI_DMA | HW_CAP_MME | HW_CAP_TPC_MASK |
+						HW_CAP_HBM_DMA | HW_CAP_PLL | HW_CAP_NIC_MASK |
+						HW_CAP_MMU | HW_CAP_SRAM_SCRAMBLER |
+						HW_CAP_HBM_SCRAMBLER);
 
 		memset(gaudi->events_stat, 0, sizeof(gaudi->events_stat));
 
@@ -4884,7 +4808,6 @@ static int gaudi_hbm_scrubbing(struct hl_device *hdev)
 static int gaudi_scrub_device_mem(struct hl_device *hdev, u64 addr, u64 size)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
-	struct gaudi_device *gaudi = hdev->asic_specific;
 	int rc = 0;
 	u64 val = 0;
 
@@ -4919,17 +4842,11 @@ static int gaudi_scrub_device_mem(struct hl_device *hdev, u64 addr, u64 size)
 			return rc;
 		}
 
-		mutex_lock(&gaudi->clk_gate_mutex);
-		hdev->asic_funcs->disable_clock_gating(hdev);
-
 		/* Scrub HBM using all DMA channels in parallel */
 		rc = gaudi_hbm_scrubbing(hdev);
 		if (rc)
 			dev_err(hdev->dev,
 				"Failed to clear HBM in mem scrub all\n");
-
-		hdev->asic_funcs->set_clock_gating(hdev);
-		mutex_unlock(&gaudi->clk_gate_mutex);
 	}
 
 	return rc;
@@ -6188,7 +6105,6 @@ static int gaudi_debugfs_read32(struct hl_device *hdev, u64 addr,
 			bool user_address, u32 *val)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
-	struct gaudi_device *gaudi = hdev->asic_specific;
 	u64 hbm_bar_addr, host_phys_end;
 	int rc = 0;
 
@@ -6196,38 +6112,31 @@ static int gaudi_debugfs_read32(struct hl_device *hdev, u64 addr,
 
 	if ((addr >= CFG_BASE) && (addr < CFG_BASE + CFG_SIZE)) {
 
-		if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) &&
-				(hdev->clock_gating_mask &
-						GAUDI_CLK_GATE_DEBUGFS_MASK)) {
+		*val = RREG32(addr - CFG_BASE);
 
-			dev_err_ratelimited(hdev->dev,
-				"Can't read register - clock gating is enabled!\n");
-			rc = -EFAULT;
-		} else {
-			*val = RREG32(addr - CFG_BASE);
-		}
+	} else if ((addr >= SRAM_BASE_ADDR) && (addr < SRAM_BASE_ADDR + SRAM_BAR_SIZE)) {
+
+		*val = readl(hdev->pcie_bar[SRAM_BAR_ID] + (addr - SRAM_BASE_ADDR));
 
-	} else if ((addr >= SRAM_BASE_ADDR) &&
-			(addr < SRAM_BASE_ADDR + SRAM_BAR_SIZE)) {
-		*val = readl(hdev->pcie_bar[SRAM_BAR_ID] +
-				(addr - SRAM_BASE_ADDR));
 	} else if (addr < DRAM_PHYS_BASE + hdev->asic_prop.dram_size) {
-		u64 bar_base_addr = DRAM_PHYS_BASE +
-				(addr & ~(prop->dram_pci_bar_size - 0x1ull));
+
+		u64 bar_base_addr = DRAM_PHYS_BASE + (addr & ~(prop->dram_pci_bar_size - 0x1ull));
 
 		hbm_bar_addr = gaudi_set_hbm_bar_base(hdev, bar_base_addr);
-		if (hbm_bar_addr != U64_MAX) {
-			*val = readl(hdev->pcie_bar[HBM_BAR_ID] +
-						(addr - bar_base_addr));
 
-			hbm_bar_addr = gaudi_set_hbm_bar_base(hdev,
-						hbm_bar_addr);
+		if (hbm_bar_addr != U64_MAX) {
+			*val = readl(hdev->pcie_bar[HBM_BAR_ID] + (addr - bar_base_addr));
+			hbm_bar_addr = gaudi_set_hbm_bar_base(hdev, hbm_bar_addr);
 		}
+
 		if (hbm_bar_addr == U64_MAX)
 			rc = -EIO;
+
 	} else if (addr >= HOST_PHYS_BASE && addr < host_phys_end &&
 			user_address && !iommu_present(&pci_bus_type)) {
+
 		*val = *(u32 *) phys_to_virt(addr - HOST_PHYS_BASE);
+
 	} else {
 		rc = -EFAULT;
 	}
@@ -6239,7 +6148,6 @@ static int gaudi_debugfs_write32(struct hl_device *hdev, u64 addr,
 			bool user_address, u32 val)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
-	struct gaudi_device *gaudi = hdev->asic_specific;
 	u64 hbm_bar_addr, host_phys_end;
 	int rc = 0;
 
@@ -6247,38 +6155,31 @@ static int gaudi_debugfs_write32(struct hl_device *hdev, u64 addr,
 
 	if ((addr >= CFG_BASE) && (addr < CFG_BASE + CFG_SIZE)) {
 
-		if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) &&
-				(hdev->clock_gating_mask &
-						GAUDI_CLK_GATE_DEBUGFS_MASK)) {
+		WREG32(addr - CFG_BASE, val);
 
-			dev_err_ratelimited(hdev->dev,
-				"Can't write register - clock gating is enabled!\n");
-			rc = -EFAULT;
-		} else {
-			WREG32(addr - CFG_BASE, val);
-		}
+	} else if ((addr >= SRAM_BASE_ADDR) && (addr < SRAM_BASE_ADDR + SRAM_BAR_SIZE)) {
+
+		writel(val, hdev->pcie_bar[SRAM_BAR_ID] + (addr - SRAM_BASE_ADDR));
 
-	} else if ((addr >= SRAM_BASE_ADDR) &&
-			(addr < SRAM_BASE_ADDR + SRAM_BAR_SIZE)) {
-		writel(val, hdev->pcie_bar[SRAM_BAR_ID] +
-					(addr - SRAM_BASE_ADDR));
 	} else if (addr < DRAM_PHYS_BASE + hdev->asic_prop.dram_size) {
-		u64 bar_base_addr = DRAM_PHYS_BASE +
-				(addr & ~(prop->dram_pci_bar_size - 0x1ull));
+
+		u64 bar_base_addr = DRAM_PHYS_BASE + (addr & ~(prop->dram_pci_bar_size - 0x1ull));
 
 		hbm_bar_addr = gaudi_set_hbm_bar_base(hdev, bar_base_addr);
-		if (hbm_bar_addr != U64_MAX) {
-			writel(val, hdev->pcie_bar[HBM_BAR_ID] +
-						(addr - bar_base_addr));
 
-			hbm_bar_addr = gaudi_set_hbm_bar_base(hdev,
-						hbm_bar_addr);
+		if (hbm_bar_addr != U64_MAX) {
+			writel(val, hdev->pcie_bar[HBM_BAR_ID] + (addr - bar_base_addr));
+			hbm_bar_addr = gaudi_set_hbm_bar_base(hdev, hbm_bar_addr);
 		}
+
 		if (hbm_bar_addr == U64_MAX)
 			rc = -EIO;
+
 	} else if (addr >= HOST_PHYS_BASE && addr < host_phys_end &&
 			user_address && !iommu_present(&pci_bus_type)) {
+
 		*(u32 *) phys_to_virt(addr - HOST_PHYS_BASE) = val;
+
 	} else {
 		rc = -EFAULT;
 	}
@@ -6290,7 +6191,6 @@ static int gaudi_debugfs_read64(struct hl_device *hdev, u64 addr,
 				bool user_address, u64 *val)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
-	struct gaudi_device *gaudi = hdev->asic_specific;
 	u64 hbm_bar_addr, host_phys_end;
 	int rc = 0;
 
@@ -6298,42 +6198,35 @@ static int gaudi_debugfs_read64(struct hl_device *hdev, u64 addr,
 
 	if ((addr >= CFG_BASE) && (addr <= CFG_BASE + CFG_SIZE - sizeof(u64))) {
 
-		if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) &&
-				(hdev->clock_gating_mask &
-						GAUDI_CLK_GATE_DEBUGFS_MASK)) {
-
-			dev_err_ratelimited(hdev->dev,
-				"Can't read register - clock gating is enabled!\n");
-			rc = -EFAULT;
-		} else {
-			u32 val_l = RREG32(addr - CFG_BASE);
-			u32 val_h = RREG32(addr + sizeof(u32) - CFG_BASE);
+		u32 val_l = RREG32(addr - CFG_BASE);
+		u32 val_h = RREG32(addr + sizeof(u32) - CFG_BASE);
 
-			*val = (((u64) val_h) << 32) | val_l;
-		}
+		*val = (((u64) val_h) << 32) | val_l;
 
 	} else if ((addr >= SRAM_BASE_ADDR) &&
-		   (addr <= SRAM_BASE_ADDR + SRAM_BAR_SIZE - sizeof(u64))) {
-		*val = readq(hdev->pcie_bar[SRAM_BAR_ID] +
-				(addr - SRAM_BASE_ADDR));
-	} else if (addr <=
-		    DRAM_PHYS_BASE + hdev->asic_prop.dram_size - sizeof(u64)) {
-		u64 bar_base_addr = DRAM_PHYS_BASE +
-				(addr & ~(prop->dram_pci_bar_size - 0x1ull));
+			(addr <= SRAM_BASE_ADDR + SRAM_BAR_SIZE - sizeof(u64))) {
+
+		*val = readq(hdev->pcie_bar[SRAM_BAR_ID] + (addr - SRAM_BASE_ADDR));
+
+	} else if (addr <= DRAM_PHYS_BASE + hdev->asic_prop.dram_size - sizeof(u64)) {
+
+		u64 bar_base_addr = DRAM_PHYS_BASE + (addr & ~(prop->dram_pci_bar_size - 0x1ull));
 
 		hbm_bar_addr = gaudi_set_hbm_bar_base(hdev, bar_base_addr);
-		if (hbm_bar_addr != U64_MAX) {
-			*val = readq(hdev->pcie_bar[HBM_BAR_ID] +
-						(addr - bar_base_addr));
 
-			hbm_bar_addr = gaudi_set_hbm_bar_base(hdev,
-						hbm_bar_addr);
+		if (hbm_bar_addr != U64_MAX) {
+			*val = readq(hdev->pcie_bar[HBM_BAR_ID] + (addr - bar_base_addr));
+			hbm_bar_addr = gaudi_set_hbm_bar_base(hdev, hbm_bar_addr);
 		}
+
 		if (hbm_bar_addr == U64_MAX)
 			rc = -EIO;
+
 	} else if (addr >= HOST_PHYS_BASE && addr < host_phys_end &&
 			user_address && !iommu_present(&pci_bus_type)) {
+
 		*val = *(u64 *) phys_to_virt(addr - HOST_PHYS_BASE);
+
 	} else {
 		rc = -EFAULT;
 	}
@@ -6345,7 +6238,6 @@ static int gaudi_debugfs_write64(struct hl_device *hdev, u64 addr,
 				bool user_address, u64 val)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
-	struct gaudi_device *gaudi = hdev->asic_specific;
 	u64 hbm_bar_addr, host_phys_end;
 	int rc = 0;
 
@@ -6353,41 +6245,33 @@ static int gaudi_debugfs_write64(struct hl_device *hdev, u64 addr,
 
 	if ((addr >= CFG_BASE) && (addr <= CFG_BASE + CFG_SIZE - sizeof(u64))) {
 
-		if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) &&
-				(hdev->clock_gating_mask &
-						GAUDI_CLK_GATE_DEBUGFS_MASK)) {
-
-			dev_err_ratelimited(hdev->dev,
-				"Can't write register - clock gating is enabled!\n");
-			rc = -EFAULT;
-		} else {
-			WREG32(addr - CFG_BASE, lower_32_bits(val));
-			WREG32(addr + sizeof(u32) - CFG_BASE,
-				upper_32_bits(val));
-		}
+		WREG32(addr - CFG_BASE, lower_32_bits(val));
+		WREG32(addr + sizeof(u32) - CFG_BASE, upper_32_bits(val));
 
 	} else if ((addr >= SRAM_BASE_ADDR) &&
-		   (addr <= SRAM_BASE_ADDR + SRAM_BAR_SIZE - sizeof(u64))) {
-		writeq(val, hdev->pcie_bar[SRAM_BAR_ID] +
-					(addr - SRAM_BASE_ADDR));
-	} else if (addr <=
-		    DRAM_PHYS_BASE + hdev->asic_prop.dram_size - sizeof(u64)) {
-		u64 bar_base_addr = DRAM_PHYS_BASE +
-				(addr & ~(prop->dram_pci_bar_size - 0x1ull));
+			(addr <= SRAM_BASE_ADDR + SRAM_BAR_SIZE - sizeof(u64))) {
+
+		writeq(val, hdev->pcie_bar[SRAM_BAR_ID] + (addr - SRAM_BASE_ADDR));
+
+	} else if (addr <= DRAM_PHYS_BASE + hdev->asic_prop.dram_size - sizeof(u64)) {
+
+		u64 bar_base_addr = DRAM_PHYS_BASE + (addr & ~(prop->dram_pci_bar_size - 0x1ull));
 
 		hbm_bar_addr = gaudi_set_hbm_bar_base(hdev, bar_base_addr);
-		if (hbm_bar_addr != U64_MAX) {
-			writeq(val, hdev->pcie_bar[HBM_BAR_ID] +
-						(addr - bar_base_addr));
 
-			hbm_bar_addr = gaudi_set_hbm_bar_base(hdev,
-						hbm_bar_addr);
+		if (hbm_bar_addr != U64_MAX) {
+			writeq(val, hdev->pcie_bar[HBM_BAR_ID] + (addr - bar_base_addr));
+			hbm_bar_addr = gaudi_set_hbm_bar_base(hdev, hbm_bar_addr);
 		}
+
 		if (hbm_bar_addr == U64_MAX)
 			rc = -EIO;
+
 	} else if (addr >= HOST_PHYS_BASE && addr < host_phys_end &&
 			user_address && !iommu_present(&pci_bus_type)) {
+
 		*(u64 *) phys_to_virt(addr - HOST_PHYS_BASE) = val;
+
 	} else {
 		rc = -EFAULT;
 	}
@@ -6446,7 +6330,6 @@ static int gaudi_debugfs_read_dma(struct hl_device *hdev, u64 addr, u32 size,
 				void *blob_addr)
 {
 	u32 dma_core_sts0, err_cause, cfg1, size_left, pos, size_to_dma;
-	struct gaudi_device *gaudi = hdev->asic_specific;
 	u32 qm_glbl_sts0, qm_cgm_sts;
 	u64 dma_offset, qm_offset;
 	dma_addr_t dma_addr;
@@ -6462,10 +6345,6 @@ static int gaudi_debugfs_read_dma(struct hl_device *hdev, u64 addr, u32 size,
 	if (!kernel_addr)
 		return -ENOMEM;
 
-	mutex_lock(&gaudi->clk_gate_mutex);
-
-	hdev->asic_funcs->disable_clock_gating(hdev);
-
 	hdev->asic_funcs->hw_queues_lock(hdev);
 
 	dma_id = gaudi_dma_assignment[GAUDI_PCI_DMA_1];
@@ -6550,10 +6429,6 @@ static int gaudi_debugfs_read_dma(struct hl_device *hdev, u64 addr, u32 size,
 out:
 	hdev->asic_funcs->hw_queues_unlock(hdev);
 
-	hdev->asic_funcs->set_clock_gating(hdev);
-
-	mutex_unlock(&gaudi->clk_gate_mutex);
-
 	hdev->asic_funcs->asic_dma_free_coherent(hdev, SZ_2M, kernel_addr,
 						dma_addr);
 
@@ -6601,10 +6476,6 @@ static void gaudi_mmu_prepare(struct hl_device *hdev, u32 asid)
 		return;
 	}
 
-	mutex_lock(&gaudi->clk_gate_mutex);
-
-	hdev->asic_funcs->disable_clock_gating(hdev);
-
 	gaudi_mmu_prepare_reg(hdev, mmDMA0_QM_GLBL_NON_SECURE_PROPS_0, asid);
 	gaudi_mmu_prepare_reg(hdev, mmDMA0_QM_GLBL_NON_SECURE_PROPS_1, asid);
 	gaudi_mmu_prepare_reg(hdev, mmDMA0_QM_GLBL_NON_SECURE_PROPS_2, asid);
@@ -6882,10 +6753,6 @@ static void gaudi_mmu_prepare(struct hl_device *hdev, u32 asid)
 
 	gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER, asid);
 	gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER, asid);
-
-	hdev->asic_funcs->set_clock_gating(hdev);
-
-	mutex_unlock(&gaudi->clk_gate_mutex);
 }
 
 static int gaudi_send_job_on_qman0(struct hl_device *hdev,
@@ -7266,10 +7133,8 @@ static int gaudi_extract_ecc_info(struct hl_device *hdev,
 		struct ecc_info_extract_params *params, u64 *ecc_address,
 		u64 *ecc_syndrom, u8 *memory_wrapper_idx)
 {
-	struct gaudi_device *gaudi = hdev->asic_specific;
 	u32 i, num_mem_regs, reg, err_bit;
 	u64 err_addr, err_word = 0;
-	int rc = 0;
 
 	num_mem_regs = params->num_memories / 32 +
 			((params->num_memories % 32) ? 1 : 0);
@@ -7282,11 +7147,6 @@ static int gaudi_extract_ecc_info(struct hl_device *hdev,
 	else
 		err_addr = params->block_address + GAUDI_ECC_SERR0_OFFSET;
 
-	if (params->disable_clock_gating) {
-		mutex_lock(&gaudi->clk_gate_mutex);
-		hdev->asic_funcs->disable_clock_gating(hdev);
-	}
-
 	/* Set invalid wrapper index */
 	*memory_wrapper_idx = 0xFF;
 
@@ -7303,8 +7163,7 @@ static int gaudi_extract_ecc_info(struct hl_device *hdev,
 
 	if (*memory_wrapper_idx == 0xFF) {
 		dev_err(hdev->dev, "ECC error information cannot be found\n");
-		rc = -EINVAL;
-		goto enable_clk_gate;
+		return -EINVAL;
 	}
 
 	WREG32(params->block_address + GAUDI_ECC_MEM_SEL_OFFSET,
@@ -7324,14 +7183,7 @@ static int gaudi_extract_ecc_info(struct hl_device *hdev,
 
 	WREG32(params->block_address + GAUDI_ECC_MEM_INFO_CLR_OFFSET, reg);
 
-enable_clk_gate:
-	if (params->disable_clock_gating) {
-		hdev->asic_funcs->set_clock_gating(hdev);
-
-		mutex_unlock(&gaudi->clk_gate_mutex);
-	}
-
-	return rc;
+	return 0;
 }
 
 /*
@@ -7589,7 +7441,6 @@ static void gaudi_handle_ecc_event(struct hl_device *hdev, u16 event_type,
 		params.block_address = mmTPC0_CFG_BASE + index * TPC_CFG_OFFSET;
 		params.num_memories = 90;
 		params.derr = false;
-		params.disable_clock_gating = true;
 		extract_info_from_fw = false;
 		break;
 	case GAUDI_EVENT_TPC0_DERR ... GAUDI_EVENT_TPC7_DERR:
@@ -7598,7 +7449,6 @@ static void gaudi_handle_ecc_event(struct hl_device *hdev, u16 event_type,
 			mmTPC0_CFG_BASE + index * TPC_CFG_OFFSET;
 		params.num_memories = 90;
 		params.derr = true;
-		params.disable_clock_gating = true;
 		extract_info_from_fw = false;
 		break;
 	case GAUDI_EVENT_MME0_ACC_SERR:
@@ -7609,7 +7459,6 @@ static void gaudi_handle_ecc_event(struct hl_device *hdev, u16 event_type,
 		params.block_address = mmMME0_ACC_BASE + index * MME_ACC_OFFSET;
 		params.num_memories = 128;
 		params.derr = false;
-		params.disable_clock_gating = true;
 		extract_info_from_fw = false;
 		break;
 	case GAUDI_EVENT_MME0_ACC_DERR:
@@ -7620,7 +7469,6 @@ static void gaudi_handle_ecc_event(struct hl_device *hdev, u16 event_type,
 		params.block_address = mmMME0_ACC_BASE + index * MME_ACC_OFFSET;
 		params.num_memories = 128;
 		params.derr = true;
-		params.disable_clock_gating = true;
 		extract_info_from_fw = false;
 		break;
 	case GAUDI_EVENT_MME0_SBAB_SERR:
@@ -7632,7 +7480,6 @@ static void gaudi_handle_ecc_event(struct hl_device *hdev, u16 event_type,
 			mmMME0_SBAB_BASE + index * MME_ACC_OFFSET;
 		params.num_memories = 33;
 		params.derr = false;
-		params.disable_clock_gating = true;
 		extract_info_from_fw = false;
 		break;
 	case GAUDI_EVENT_MME0_SBAB_DERR:
@@ -7644,7 +7491,6 @@ static void gaudi_handle_ecc_event(struct hl_device *hdev, u16 event_type,
 			mmMME0_SBAB_BASE + index * MME_ACC_OFFSET;
 		params.num_memories = 33;
 		params.derr = true;
-		params.disable_clock_gating = true;
 		extract_info_from_fw = false;
 		break;
 	default:
@@ -7819,6 +7665,48 @@ static void gaudi_print_fw_alive_info(struct hl_device *hdev,
 		fw_alive->thread_id, fw_alive->uptime_seconds);
 }
 
+static void gaudi_print_nic_axi_irq_info(struct hl_device *hdev, u16 event_type,
+						void *data)
+{
+	char desc[64] = "", *type;
+	struct eq_nic_sei_event *eq_nic_sei = data;
+	u16 nic_id = event_type - GAUDI_EVENT_NIC_SEI_0;
+
+	switch (eq_nic_sei->axi_error_cause) {
+	case RXB:
+		type = "RXB";
+		break;
+	case RXE:
+		type = "RXE";
+		break;
+	case TXS:
+		type = "TXS";
+		break;
+	case TXE:
+		type = "TXE";
+		break;
+	case QPC_RESP:
+		type = "QPC_RESP";
+		break;
+	case NON_AXI_ERR:
+		type = "NON_AXI_ERR";
+		break;
+	case TMR:
+		type = "TMR";
+		break;
+	default:
+		dev_err(hdev->dev, "unknown NIC AXI cause %d\n",
+			eq_nic_sei->axi_error_cause);
+		type = "N/A";
+		break;
+	}
+
+	snprintf(desc, sizeof(desc), "NIC%d_%s%d", nic_id, type,
+			eq_nic_sei->id);
+	dev_err_ratelimited(hdev->dev, "Received H/W interrupt %d [\"%s\"]\n",
+		event_type, desc);
+}
+
 static int gaudi_non_hard_reset_late_init(struct hl_device *hdev)
 {
 	/* GAUDI doesn't support any reset except hard-reset */
@@ -7966,19 +7854,9 @@ static int gaudi_hbm_event_to_dev(u16 hbm_event_type)
 static bool gaudi_tpc_read_interrupts(struct hl_device *hdev, u8 tpc_id,
 					char *interrupt_name)
 {
-	struct gaudi_device *gaudi = hdev->asic_specific;
 	u32 tpc_offset = tpc_id * TPC_CFG_OFFSET, tpc_interrupts_cause, i;
 	bool soft_reset_required = false;
 
-	/* Accessing the TPC_INTR_CAUSE registers requires disabling the clock
-	 * gating, and thus cannot be done in CPU-CP and should be done instead
-	 * by the driver.
-	 */
-
-	mutex_lock(&gaudi->clk_gate_mutex);
-
-	hdev->asic_funcs->disable_clock_gating(hdev);
-
 	tpc_interrupts_cause = RREG32(mmTPC0_CFG_TPC_INTR_CAUSE + tpc_offset) &
 				TPC0_CFG_TPC_INTR_CAUSE_CAUSE_MASK;
 
@@ -7996,10 +7874,6 @@ static bool gaudi_tpc_read_interrupts(struct hl_device *hdev, u8 tpc_id,
 	/* Clear interrupts */
 	WREG32(mmTPC0_CFG_TPC_INTR_CAUSE + tpc_offset, 0);
 
-	hdev->asic_funcs->set_clock_gating(hdev);
-
-	mutex_unlock(&gaudi->clk_gate_mutex);
-
 	return soft_reset_required;
 }
 
@@ -8066,6 +7940,7 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
 				struct hl_eq_entry *eq_entry)
 {
 	struct gaudi_device *gaudi = hdev->asic_specific;
+	u64 data = le64_to_cpu(eq_entry->data[0]);
 	u32 ctl = le32_to_cpu(eq_entry->hdr.ctl);
 	u32 fw_fatal_err_flag = 0;
 	u16 event_type = ((ctl & EQ_CTL_EVENT_TYPE_MASK)
@@ -8102,6 +7977,7 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
 	case GAUDI_EVENT_PSOC_MEM_DERR:
 	case GAUDI_EVENT_PSOC_CORESIGHT_DERR:
 	case GAUDI_EVENT_SRAM0_DERR ... GAUDI_EVENT_SRAM28_DERR:
+	case GAUDI_EVENT_NIC0_DERR ... GAUDI_EVENT_NIC4_DERR:
 	case GAUDI_EVENT_DMA_IF0_DERR ... GAUDI_EVENT_DMA_IF3_DERR:
 	case GAUDI_EVENT_HBM_0_DERR ... GAUDI_EVENT_HBM_3_DERR:
 	case GAUDI_EVENT_MMU_DERR:
@@ -8202,6 +8078,7 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
 	case GAUDI_EVENT_PSOC_MEM_SERR:
 	case GAUDI_EVENT_PSOC_CORESIGHT_SERR:
 	case GAUDI_EVENT_SRAM0_SERR ... GAUDI_EVENT_SRAM28_SERR:
+	case GAUDI_EVENT_NIC0_SERR ... GAUDI_EVENT_NIC4_SERR:
 	case GAUDI_EVENT_DMA_IF0_SERR ... GAUDI_EVENT_DMA_IF3_SERR:
 	case GAUDI_EVENT_HBM_0_SERR ... GAUDI_EVENT_HBM_3_SERR:
 		fallthrough;
@@ -8263,6 +8140,11 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
 		hl_fw_unmask_irq(hdev, event_type);
 		break;
 
+	case GAUDI_EVENT_NIC_SEI_0 ... GAUDI_EVENT_NIC_SEI_4:
+		gaudi_print_nic_axi_irq_info(hdev, event_type, &data);
+		hl_fw_unmask_irq(hdev, event_type);
+		break;
+
 	case GAUDI_EVENT_DMA_IF_SEI_0 ... GAUDI_EVENT_DMA_IF_SEI_3:
 		gaudi_print_irq_info(hdev, event_type, false);
 		gaudi_print_sm_sei_info(hdev, event_type,
@@ -8274,6 +8156,9 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
 		hl_fw_unmask_irq(hdev, event_type);
 		break;
 
+	case GAUDI_EVENT_STATUS_NIC0_ENG0 ... GAUDI_EVENT_STATUS_NIC4_ENG1:
+		break;
+
 	case GAUDI_EVENT_FIX_POWER_ENV_S ... GAUDI_EVENT_FIX_THERMAL_ENV_E:
 		gaudi_print_clk_change_info(hdev, event_type);
 		hl_fw_unmask_irq(hdev, event_type);
@@ -8314,7 +8199,7 @@ reset_device:
 					| HL_DRV_RESET_BYPASS_REQ_TO_FW
 					| fw_fatal_err_flag);
 	else if (hdev->hard_reset_on_fw_events)
-		hl_device_reset(hdev, HL_DRV_RESET_HARD | fw_fatal_err_flag);
+		hl_device_reset(hdev, HL_DRV_RESET_HARD | HL_DRV_RESET_DELAY | fw_fatal_err_flag);
 	else
 		hl_fw_unmask_irq(hdev, event_type);
 }
@@ -8461,10 +8346,6 @@ static bool gaudi_is_device_idle(struct hl_device *hdev, u64 *mask_arr,
 	u64 offset;
 	int i, dma_id, port;
 
-	mutex_lock(&gaudi->clk_gate_mutex);
-
-	hdev->asic_funcs->disable_clock_gating(hdev);
-
 	if (s)
 		seq_puts(s,
 			"\nDMA  is_idle  QM_GLBL_STS0  QM_CGM_STS  DMA_CORE_STS0\n"
@@ -8585,10 +8466,6 @@ static bool gaudi_is_device_idle(struct hl_device *hdev, u64 *mask_arr,
 	if (s)
 		seq_puts(s, "\n");
 
-	hdev->asic_funcs->set_clock_gating(hdev);
-
-	mutex_unlock(&gaudi->clk_gate_mutex);
-
 	return is_idle;
 }
 
@@ -8628,10 +8505,8 @@ static int gaudi_get_eeprom_data(struct hl_device *hdev, void *data,
  * this function should be used only during initialization and/or after reset,
  * when there are no active users.
  */
-static int gaudi_run_tpc_kernel(struct hl_device *hdev, u64 tpc_kernel,
-				u32 tpc_id)
+static int gaudi_run_tpc_kernel(struct hl_device *hdev, u64 tpc_kernel,	u32 tpc_id)
 {
-	struct gaudi_device *gaudi = hdev->asic_specific;
 	u64 kernel_timeout;
 	u32 status, offset;
 	int rc;
@@ -8643,10 +8518,6 @@ static int gaudi_run_tpc_kernel(struct hl_device *hdev, u64 tpc_kernel,
 	else
 		kernel_timeout = HL_DEVICE_TIMEOUT_USEC;
 
-	mutex_lock(&gaudi->clk_gate_mutex);
-
-	hdev->asic_funcs->disable_clock_gating(hdev);
-
 	WREG32(mmTPC0_CFG_QM_KERNEL_BASE_ADDRESS_LOW + offset,
 			lower_32_bits(tpc_kernel));
 	WREG32(mmTPC0_CFG_QM_KERNEL_BASE_ADDRESS_HIGH + offset,
@@ -8686,8 +8557,6 @@ static int gaudi_run_tpc_kernel(struct hl_device *hdev, u64 tpc_kernel,
 		dev_err(hdev->dev,
 			"Timeout while waiting for TPC%d icache prefetch\n",
 			tpc_id);
-		hdev->asic_funcs->set_clock_gating(hdev);
-		mutex_unlock(&gaudi->clk_gate_mutex);
 		return -EIO;
 	}
 
@@ -8711,8 +8580,6 @@ static int gaudi_run_tpc_kernel(struct hl_device *hdev, u64 tpc_kernel,
 		dev_err(hdev->dev,
 			"Timeout while waiting for TPC%d vector pipe\n",
 			tpc_id);
-		hdev->asic_funcs->set_clock_gating(hdev);
-		mutex_unlock(&gaudi->clk_gate_mutex);
 		return -EIO;
 	}
 
@@ -8724,9 +8591,6 @@ static int gaudi_run_tpc_kernel(struct hl_device *hdev, u64 tpc_kernel,
 		1000,
 		kernel_timeout);
 
-	hdev->asic_funcs->set_clock_gating(hdev);
-	mutex_unlock(&gaudi->clk_gate_mutex);
-
 	if (rc) {
 		dev_err(hdev->dev,
 			"Timeout while waiting for TPC%d kernel to execute\n",
@@ -8791,7 +8655,7 @@ static int gaudi_internal_cb_pool_init(struct hl_device *hdev,
 			hdev->internal_cb_pool_dma_addr,
 			HOST_SPACE_INTERNAL_CB_SZ);
 
-	hdev->asic_funcs->mmu_invalidate_cache(hdev, false, MMU_OP_USERPTR);
+	hl_mmu_invalidate_cache(hdev, false, MMU_OP_USERPTR);
 	mutex_unlock(&ctx->mmu_lock);
 
 	if (rc)
@@ -8826,7 +8690,7 @@ static void gaudi_internal_cb_pool_fini(struct hl_device *hdev,
 			HOST_SPACE_INTERNAL_CB_SZ);
 	hl_unreserve_va_block(hdev, ctx, hdev->internal_cb_va_base,
 			HOST_SPACE_INTERNAL_CB_SZ);
-	hdev->asic_funcs->mmu_invalidate_cache(hdev, true, MMU_OP_USERPTR);
+	hl_mmu_invalidate_cache(hdev, true, MMU_OP_USERPTR);
 	mutex_unlock(&ctx->mmu_lock);
 
 	gen_pool_destroy(hdev->internal_cb_pool);
@@ -9204,14 +9068,7 @@ static void gaudi_reset_sob(struct hl_device *hdev, void *data)
 
 static void gaudi_set_dma_mask_from_fw(struct hl_device *hdev)
 {
-	if (RREG32(mmPSOC_GLOBAL_CONF_NON_RST_FLOPS_0) ==
-							HL_POWER9_HOST_MAGIC) {
-		hdev->power9_64bit_dma_enable = 1;
-		hdev->dma_mask = 64;
-	} else {
-		hdev->power9_64bit_dma_enable = 0;
-		hdev->dma_mask = 48;
-	}
+	hdev->dma_mask = 48;
 }
 
 static u64 gaudi_get_device_time(struct hl_device *hdev)
@@ -9293,23 +9150,15 @@ static int gaudi_gen_sync_to_engine_map(struct hl_device *hdev,
 				struct hl_sync_to_engine_map *map)
 {
 	struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
-	struct gaudi_device *gaudi = hdev->asic_specific;
 	int i, j, rc;
 	u32 reg_value;
 
 	/* Iterate over TPC engines */
 	for (i = 0; i < sds->props[SP_NUM_OF_TPC_ENGINES]; ++i) {
-		/* TPC registered must be accessed with clock gating disabled */
-		mutex_lock(&gaudi->clk_gate_mutex);
-		hdev->asic_funcs->disable_clock_gating(hdev);
 
 		reg_value = RREG32(sds->props[SP_TPC0_CFG_SO] +
 					sds->props[SP_NEXT_TPC] * i);
 
-		/* We can reenable clock_gating */
-		hdev->asic_funcs->set_clock_gating(hdev);
-		mutex_unlock(&gaudi->clk_gate_mutex);
-
 		rc = gaudi_add_sync_to_engine_map_entry(map, reg_value,
 							ENGINE_TPC, i);
 		if (rc)
@@ -9319,20 +9168,11 @@ static int gaudi_gen_sync_to_engine_map(struct hl_device *hdev,
 	/* Iterate over MME engines */
 	for (i = 0; i < sds->props[SP_NUM_OF_MME_ENGINES]; ++i) {
 		for (j = 0; j < sds->props[SP_SUB_MME_ENG_NUM]; ++j) {
-			/* MME registered must be accessed with clock gating
-			 * disabled
-			 */
-			mutex_lock(&gaudi->clk_gate_mutex);
-			hdev->asic_funcs->disable_clock_gating(hdev);
 
 			reg_value = RREG32(sds->props[SP_MME_CFG_SO] +
 						sds->props[SP_NEXT_MME] * i +
 						j * sizeof(u32));
 
-			/* We can reenable clock_gating */
-			hdev->asic_funcs->set_clock_gating(hdev);
-			mutex_unlock(&gaudi->clk_gate_mutex);
-
 			rc = gaudi_add_sync_to_engine_map_entry(
 				map, reg_value, ENGINE_MME,
 				i * sds->props[SP_SUB_MME_ENG_NUM] + j);
@@ -9537,6 +9377,29 @@ static u32 *gaudi_get_stream_master_qid_arr(void)
 	return gaudi_stream_master;
 }
 
+static ssize_t infineon_ver_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+	struct cpucp_info *cpucp_info;
+
+	cpucp_info = &hdev->asic_prop.cpucp_info;
+
+	return sprintf(buf, "%#04x\n", le32_to_cpu(cpucp_info->infineon_version));
+}
+
+static DEVICE_ATTR_RO(infineon_ver);
+
+static struct attribute *gaudi_vrm_dev_attrs[] = {
+	&dev_attr_infineon_ver.attr,
+};
+
+static void gaudi_add_device_attr(struct hl_device *hdev, struct attribute_group *dev_clk_attr_grp,
+					struct attribute_group *dev_vrm_attr_grp)
+{
+	hl_sysfs_add_dev_clk_attr(hdev, dev_clk_attr_grp);
+	dev_vrm_attr_grp->attrs = gaudi_vrm_dev_attrs;
+}
+
 static const struct hl_asic_funcs gaudi_funcs = {
 	.early_init = gaudi_early_init,
 	.early_fini = gaudi_early_fini,
@@ -9574,17 +9437,14 @@ static const struct hl_asic_funcs gaudi_funcs = {
 	.debugfs_read64 = gaudi_debugfs_read64,
 	.debugfs_write64 = gaudi_debugfs_write64,
 	.debugfs_read_dma = gaudi_debugfs_read_dma,
-	.add_device_attr = hl_add_device_attr,
+	.add_device_attr = gaudi_add_device_attr,
 	.handle_eqe = gaudi_handle_eqe,
-	.set_pll_profile = hl_set_pll_profile,
 	.get_events_stat = gaudi_get_events_stat,
 	.read_pte = gaudi_read_pte,
 	.write_pte = gaudi_write_pte,
 	.mmu_invalidate_cache = gaudi_mmu_invalidate_cache,
 	.mmu_invalidate_cache_range = gaudi_mmu_invalidate_cache_range,
 	.send_heartbeat = gaudi_send_heartbeat,
-	.set_clock_gating = gaudi_set_clock_gating,
-	.disable_clock_gating = gaudi_disable_clock_gating,
 	.debug_coresight = gaudi_debug_coresight,
 	.is_device_idle = gaudi_is_device_idle,
 	.non_hard_reset_late_init = gaudi_non_hard_reset_late_init,
@@ -9600,7 +9460,6 @@ static const struct hl_asic_funcs gaudi_funcs = {
 	.halt_coresight = gaudi_halt_coresight,
 	.ctx_init = gaudi_ctx_init,
 	.ctx_fini = gaudi_ctx_fini,
-	.get_clk_rate = hl_get_clk_rate,
 	.get_queue_id_for_cq = gaudi_get_queue_id_for_cq,
 	.load_firmware_to_device = gaudi_load_firmware_to_device,
 	.load_boot_fit_to_device = gaudi_load_boot_fit_to_device,
@@ -9626,7 +9485,8 @@ static const struct hl_asic_funcs gaudi_funcs = {
 	.state_dump_init = gaudi_state_dump_init,
 	.get_sob_addr = gaudi_get_sob_addr,
 	.set_pci_memory_regions = gaudi_set_pci_memory_regions,
-	.get_stream_master_qid_arr = gaudi_get_stream_master_qid_arr
+	.get_stream_master_qid_arr = gaudi_get_stream_master_qid_arr,
+	.is_valid_dram_page_size = NULL
 };
 
 /**
diff --git a/drivers/misc/habanalabs/gaudi/gaudiP.h b/drivers/misc/habanalabs/gaudi/gaudiP.h
index 8ac16a9b7d15..54de7c599072 100644
--- a/drivers/misc/habanalabs/gaudi/gaudiP.h
+++ b/drivers/misc/habanalabs/gaudi/gaudiP.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0
  *
- * Copyright 2019-2020 HabanaLabs, Ltd.
+ * Copyright 2019-2022 HabanaLabs, Ltd.
  * All Rights Reserved.
  *
  */
@@ -177,7 +177,6 @@
 #define HW_CAP_MSI		BIT(6)
 #define HW_CAP_CPU_Q		BIT(7)
 #define HW_CAP_HBM_DMA		BIT(8)
-#define HW_CAP_CLK_GATE		BIT(9)
 #define HW_CAP_SRAM_SCRAMBLER	BIT(10)
 #define HW_CAP_HBM_SCRAMBLER	BIT(11)
 
@@ -313,8 +312,6 @@ struct gaudi_internal_qman_info {
  * struct gaudi_device - ASIC specific manage structure.
  * @cpucp_info_get: get information on device from CPU-CP
  * @hw_queues_lock: protects the H/W queues from concurrent access.
- * @clk_gate_mutex: protects code areas that require clock gating to be disabled
- *                  temporarily
  * @internal_qmans: Internal QMANs information. The array size is larger than
  *                  the actual number of internal queues because they are not in
  *                  consecutive order.
@@ -337,7 +334,6 @@ struct gaudi_device {
 
 	/* TODO: remove hw_queues_lock after moving to scheduler code */
 	spinlock_t			hw_queues_lock;
-	struct mutex			clk_gate_mutex;
 
 	struct gaudi_internal_qman_info	internal_qmans[GAUDI_QUEUE_ID_SIZE];
 
@@ -355,8 +351,6 @@ struct gaudi_device {
 
 void gaudi_init_security(struct hl_device *hdev);
 void gaudi_ack_protection_bits_errors(struct hl_device *hdev);
-void gaudi_add_device_attr(struct hl_device *hdev,
-			struct attribute_group *dev_attr_grp);
 int gaudi_debug_coresight(struct hl_device *hdev, struct hl_ctx *ctx, void *data);
 void gaudi_halt_coresight(struct hl_device *hdev, struct hl_ctx *ctx);
 void gaudi_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid);
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index fbcc7bbf44b3..ec9358bcbf0b 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 /*
- * Copyright 2016-2021 HabanaLabs, Ltd.
+ * Copyright 2016-2022 HabanaLabs, Ltd.
  * All Rights Reserved.
  */
 
@@ -430,6 +430,9 @@ int goya_set_fixed_properties(struct hl_device *hdev)
 	prop->dmmu.page_size = PAGE_SIZE_2MB;
 	prop->dmmu.num_hops = MMU_ARCH_5_HOPS;
 	prop->dmmu.last_mask = LAST_MASK;
+	/* TODO: will be duplicated until implementing per-MMU props */
+	prop->dmmu.hop_table_size = prop->mmu_hop_table_size;
+	prop->dmmu.hop0_tables_total_size = prop->mmu_hop0_tables_total_size;
 
 	/* shifts and masks are the same in PMMU and DMMU */
 	memcpy(&prop->pmmu, &prop->dmmu, sizeof(prop->dmmu));
@@ -438,6 +441,9 @@ int goya_set_fixed_properties(struct hl_device *hdev)
 	prop->pmmu.page_size = PAGE_SIZE_4KB;
 	prop->pmmu.num_hops = MMU_ARCH_5_HOPS;
 	prop->pmmu.last_mask = LAST_MASK;
+	/* TODO: will be duplicated until implementing per-MMU props */
+	prop->pmmu.hop_table_size = prop->mmu_hop_table_size;
+	prop->pmmu.hop0_tables_total_size = prop->mmu_hop0_tables_total_size;
 
 	/* PMMU and HPMMU are the same except of page size */
 	memcpy(&prop->pmmu_huge, &prop->pmmu, sizeof(prop->pmmu));
@@ -477,6 +483,10 @@ int goya_set_fixed_properties(struct hl_device *hdev)
 
 	prop->use_get_power_for_reset_history = true;
 
+	prop->configurable_stop_on_err = true;
+
+	prop->set_max_power_on_device_init = true;
+
 	return 0;
 }
 
@@ -893,7 +903,7 @@ int goya_late_init(struct hl_device *hdev)
 
 	goya->pm_mng_profile = PM_AUTO;
 
-	hdev->asic_funcs->set_pll_profile(hdev, PLL_LOW);
+	goya_set_pll_profile(hdev, PLL_LOW);
 
 	schedule_delayed_work(&goya->goya_work->work_freq,
 		usecs_to_jiffies(HL_PLL_LOW_JOB_FREQ_USEC));
@@ -2700,8 +2710,7 @@ int goya_mmu_init(struct hl_device *hdev)
 	WREG32_AND(mmSTLB_STLB_FEATURE_EN,
 			(~STLB_STLB_FEATURE_EN_FOLLOWER_EN_MASK));
 
-	hdev->asic_funcs->mmu_invalidate_cache(hdev, true,
-					MMU_OP_USERPTR | MMU_OP_PHYS_PACK);
+	hl_mmu_invalidate_cache(hdev, true, MMU_OP_USERPTR | MMU_OP_PHYS_PACK);
 
 	WREG32(mmMMU_MMU_ENABLE, 1);
 	WREG32(mmMMU_SPI_MASK, 0xF);
@@ -5341,7 +5350,7 @@ static int goya_mmu_invalidate_cache_range(struct hl_device *hdev,
 	/* Treat as invalidate all because there is no range invalidation
 	 * in Goya
 	 */
-	return hdev->asic_funcs->mmu_invalidate_cache(hdev, is_hard, flags);
+	return hl_mmu_invalidate_cache(hdev, is_hard, flags);
 }
 
 int goya_send_heartbeat(struct hl_device *hdev)
@@ -5391,16 +5400,6 @@ int goya_cpucp_info_get(struct hl_device *hdev)
 	return 0;
 }
 
-static void goya_set_clock_gating(struct hl_device *hdev)
-{
-	/* clock gating not supported in Goya */
-}
-
-static void goya_disable_clock_gating(struct hl_device *hdev)
-{
-	/* clock gating not supported in Goya */
-}
-
 static bool goya_is_device_idle(struct hl_device *hdev, u64 *mask_arr,
 					u8 mask_len, struct seq_file *s)
 {
@@ -5564,16 +5563,7 @@ static void goya_reset_sob_group(struct hl_device *hdev, u16 sob_group)
 
 static void goya_set_dma_mask_from_fw(struct hl_device *hdev)
 {
-	if (RREG32(mmPSOC_GLOBAL_CONF_NON_RST_FLOPS_0) ==
-							HL_POWER9_HOST_MAGIC) {
-		dev_dbg(hdev->dev, "Working in 64-bit DMA mode\n");
-		hdev->power9_64bit_dma_enable = 1;
-		hdev->dma_mask = 64;
-	} else {
-		dev_dbg(hdev->dev, "Working in 48-bit DMA mode\n");
-		hdev->power9_64bit_dma_enable = 0;
-		hdev->dma_mask = 48;
-	}
+	hdev->dma_mask = 48;
 }
 
 u64 goya_get_device_time(struct hl_device *hdev)
@@ -5727,15 +5717,12 @@ static const struct hl_asic_funcs goya_funcs = {
 	.debugfs_read_dma = goya_debugfs_read_dma,
 	.add_device_attr = goya_add_device_attr,
 	.handle_eqe = goya_handle_eqe,
-	.set_pll_profile = goya_set_pll_profile,
 	.get_events_stat = goya_get_events_stat,
 	.read_pte = goya_read_pte,
 	.write_pte = goya_write_pte,
 	.mmu_invalidate_cache = goya_mmu_invalidate_cache,
 	.mmu_invalidate_cache_range = goya_mmu_invalidate_cache_range,
 	.send_heartbeat = goya_send_heartbeat,
-	.set_clock_gating = goya_set_clock_gating,
-	.disable_clock_gating = goya_disable_clock_gating,
 	.debug_coresight = goya_debug_coresight,
 	.is_device_idle = goya_is_device_idle,
 	.non_hard_reset_late_init = goya_non_hard_reset_late_init,
@@ -5751,7 +5738,6 @@ static const struct hl_asic_funcs goya_funcs = {
 	.halt_coresight = goya_halt_coresight,
 	.ctx_init = goya_ctx_init,
 	.ctx_fini = goya_ctx_fini,
-	.get_clk_rate = hl_get_clk_rate,
 	.get_queue_id_for_cq = goya_get_queue_id_for_cq,
 	.load_firmware_to_device = goya_load_firmware_to_device,
 	.load_boot_fit_to_device = goya_load_boot_fit_to_device,
@@ -5778,6 +5764,7 @@ static const struct hl_asic_funcs goya_funcs = {
 	.get_sob_addr = &goya_get_sob_addr,
 	.set_pci_memory_regions = goya_set_pci_memory_regions,
 	.get_stream_master_qid_arr = goya_get_stream_master_qid_arr,
+	.is_valid_dram_page_size = NULL
 };
 
 /*
diff --git a/drivers/misc/habanalabs/goya/goyaP.h b/drivers/misc/habanalabs/goya/goyaP.h
index 3740fd25bf84..647f57402616 100644
--- a/drivers/misc/habanalabs/goya/goyaP.h
+++ b/drivers/misc/habanalabs/goya/goyaP.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0
  *
- * Copyright 2016-2019 HabanaLabs, Ltd.
+ * Copyright 2016-2022 HabanaLabs, Ltd.
  * All Rights Reserved.
  *
  */
@@ -217,8 +217,8 @@ u64 goya_get_max_power(struct hl_device *hdev);
 void goya_set_max_power(struct hl_device *hdev, u64 value);
 
 void goya_set_pll_profile(struct hl_device *hdev, enum hl_pll_frequency freq);
-void goya_add_device_attr(struct hl_device *hdev,
-			struct attribute_group *dev_attr_grp);
+void goya_add_device_attr(struct hl_device *hdev, struct attribute_group *dev_clk_attr_grp,
+				struct attribute_group *dev_vrm_attr_grp);
 int goya_cpucp_info_get(struct hl_device *hdev);
 int goya_debug_coresight(struct hl_device *hdev, struct hl_ctx *ctx, void *data);
 void goya_halt_coresight(struct hl_device *hdev, struct hl_ctx *ctx);
diff --git a/drivers/misc/habanalabs/goya/goya_hwmgr.c b/drivers/misc/habanalabs/goya/goya_hwmgr.c
index 76b47749affe..6580fc6a486a 100644
--- a/drivers/misc/habanalabs/goya/goya_hwmgr.c
+++ b/drivers/misc/habanalabs/goya/goya_hwmgr.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 /*
- * Copyright 2016-2021 HabanaLabs, Ltd.
+ * Copyright 2016-2022 HabanaLabs, Ltd.
  * All Rights Reserved.
  */
 
@@ -11,21 +11,24 @@ void goya_set_pll_profile(struct hl_device *hdev, enum hl_pll_frequency freq)
 {
 	struct goya_device *goya = hdev->asic_specific;
 
+	if (!hdev->pdev)
+		return;
+
 	switch (freq) {
 	case PLL_HIGH:
-		hl_set_frequency(hdev, HL_GOYA_MME_PLL, hdev->high_pll);
-		hl_set_frequency(hdev, HL_GOYA_TPC_PLL, hdev->high_pll);
-		hl_set_frequency(hdev, HL_GOYA_IC_PLL, hdev->high_pll);
+		hl_fw_set_frequency(hdev, HL_GOYA_MME_PLL, hdev->high_pll);
+		hl_fw_set_frequency(hdev, HL_GOYA_TPC_PLL, hdev->high_pll);
+		hl_fw_set_frequency(hdev, HL_GOYA_IC_PLL, hdev->high_pll);
 		break;
 	case PLL_LOW:
-		hl_set_frequency(hdev, HL_GOYA_MME_PLL, GOYA_PLL_FREQ_LOW);
-		hl_set_frequency(hdev, HL_GOYA_TPC_PLL, GOYA_PLL_FREQ_LOW);
-		hl_set_frequency(hdev, HL_GOYA_IC_PLL, GOYA_PLL_FREQ_LOW);
+		hl_fw_set_frequency(hdev, HL_GOYA_MME_PLL, GOYA_PLL_FREQ_LOW);
+		hl_fw_set_frequency(hdev, HL_GOYA_TPC_PLL, GOYA_PLL_FREQ_LOW);
+		hl_fw_set_frequency(hdev, HL_GOYA_IC_PLL, GOYA_PLL_FREQ_LOW);
 		break;
 	case PLL_LAST:
-		hl_set_frequency(hdev, HL_GOYA_MME_PLL, goya->mme_clk);
-		hl_set_frequency(hdev, HL_GOYA_TPC_PLL, goya->tpc_clk);
-		hl_set_frequency(hdev, HL_GOYA_IC_PLL, goya->ic_clk);
+		hl_fw_set_frequency(hdev, HL_GOYA_MME_PLL, goya->mme_clk);
+		hl_fw_set_frequency(hdev, HL_GOYA_TPC_PLL, goya->tpc_clk);
+		hl_fw_set_frequency(hdev, HL_GOYA_IC_PLL, goya->ic_clk);
 		break;
 	default:
 		dev_err(hdev->dev, "unknown frequency setting\n");
@@ -41,7 +44,7 @@ static ssize_t mme_clk_show(struct device *dev, struct device_attribute *attr,
 	if (!hl_device_operational(hdev, NULL))
 		return -ENODEV;
 
-	value = hl_get_frequency(hdev, HL_GOYA_MME_PLL, false);
+	value = hl_fw_get_frequency(hdev, HL_GOYA_MME_PLL, false);
 
 	if (value < 0)
 		return value;
@@ -74,7 +77,7 @@ static ssize_t mme_clk_store(struct device *dev, struct device_attribute *attr,
 		goto fail;
 	}
 
-	hl_set_frequency(hdev, HL_GOYA_MME_PLL, value);
+	hl_fw_set_frequency(hdev, HL_GOYA_MME_PLL, value);
 	goya->mme_clk = value;
 
 fail:
@@ -90,7 +93,7 @@ static ssize_t tpc_clk_show(struct device *dev, struct device_attribute *attr,
 	if (!hl_device_operational(hdev, NULL))
 		return -ENODEV;
 
-	value = hl_get_frequency(hdev, HL_GOYA_TPC_PLL, false);
+	value = hl_fw_get_frequency(hdev, HL_GOYA_TPC_PLL, false);
 
 	if (value < 0)
 		return value;
@@ -123,7 +126,7 @@ static ssize_t tpc_clk_store(struct device *dev, struct device_attribute *attr,
 		goto fail;
 	}
 
-	hl_set_frequency(hdev, HL_GOYA_TPC_PLL, value);
+	hl_fw_set_frequency(hdev, HL_GOYA_TPC_PLL, value);
 	goya->tpc_clk = value;
 
 fail:
@@ -139,7 +142,7 @@ static ssize_t ic_clk_show(struct device *dev, struct device_attribute *attr,
 	if (!hl_device_operational(hdev, NULL))
 		return -ENODEV;
 
-	value = hl_get_frequency(hdev, HL_GOYA_IC_PLL, false);
+	value = hl_fw_get_frequency(hdev, HL_GOYA_IC_PLL, false);
 
 	if (value < 0)
 		return value;
@@ -172,7 +175,7 @@ static ssize_t ic_clk_store(struct device *dev, struct device_attribute *attr,
 		goto fail;
 	}
 
-	hl_set_frequency(hdev, HL_GOYA_IC_PLL, value);
+	hl_fw_set_frequency(hdev, HL_GOYA_IC_PLL, value);
 	goya->ic_clk = value;
 
 fail:
@@ -188,7 +191,7 @@ static ssize_t mme_clk_curr_show(struct device *dev,
 	if (!hl_device_operational(hdev, NULL))
 		return -ENODEV;
 
-	value = hl_get_frequency(hdev, HL_GOYA_MME_PLL, true);
+	value = hl_fw_get_frequency(hdev, HL_GOYA_MME_PLL, true);
 
 	if (value < 0)
 		return value;
@@ -205,7 +208,7 @@ static ssize_t tpc_clk_curr_show(struct device *dev,
 	if (!hl_device_operational(hdev, NULL))
 		return -ENODEV;
 
-	value = hl_get_frequency(hdev, HL_GOYA_TPC_PLL, true);
+	value = hl_fw_get_frequency(hdev, HL_GOYA_TPC_PLL, true);
 
 	if (value < 0)
 		return value;
@@ -222,7 +225,7 @@ static ssize_t ic_clk_curr_show(struct device *dev,
 	if (!hl_device_operational(hdev, NULL))
 		return -ENODEV;
 
-	value = hl_get_frequency(hdev, HL_GOYA_IC_PLL, true);
+	value = hl_fw_get_frequency(hdev, HL_GOYA_IC_PLL, true);
 
 	if (value < 0)
 		return value;
@@ -347,7 +350,7 @@ static DEVICE_ATTR_RW(pm_mng_profile);
 static DEVICE_ATTR_RW(tpc_clk);
 static DEVICE_ATTR_RO(tpc_clk_curr);
 
-static struct attribute *goya_dev_attrs[] = {
+static struct attribute *goya_clk_dev_attrs[] = {
 	&dev_attr_high_pll.attr,
 	&dev_attr_ic_clk.attr,
 	&dev_attr_ic_clk_curr.attr,
@@ -356,11 +359,27 @@ static struct attribute *goya_dev_attrs[] = {
 	&dev_attr_pm_mng_profile.attr,
 	&dev_attr_tpc_clk.attr,
 	&dev_attr_tpc_clk_curr.attr,
-	NULL,
 };
 
-void goya_add_device_attr(struct hl_device *hdev,
-			struct attribute_group *dev_attr_grp)
+static ssize_t infineon_ver_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+	struct cpucp_info *cpucp_info;
+
+	cpucp_info = &hdev->asic_prop.cpucp_info;
+
+	return sprintf(buf, "%#04x\n", le32_to_cpu(cpucp_info->infineon_version));
+}
+
+static DEVICE_ATTR_RO(infineon_ver);
+
+static struct attribute *goya_vrm_dev_attrs[] = {
+	&dev_attr_infineon_ver.attr,
+};
+
+void goya_add_device_attr(struct hl_device *hdev, struct attribute_group *dev_clk_attr_grp,
+				struct attribute_group *dev_vrm_attr_grp)
 {
-	dev_attr_grp->attrs = goya_dev_attrs;
+	dev_clk_attr_grp->attrs = goya_clk_dev_attrs;
+	dev_vrm_attr_grp->attrs = goya_vrm_dev_attrs;
 }
diff --git a/drivers/misc/habanalabs/include/common/cpucp_if.h b/drivers/misc/habanalabs/include/common/cpucp_if.h
index 737c39f33f05..f00db22f98fb 100644
--- a/drivers/misc/habanalabs/include/common/cpucp_if.h
+++ b/drivers/misc/habanalabs/include/common/cpucp_if.h
@@ -780,6 +780,7 @@ struct cpucp_security_info {
  *                     (0 = functional 1 = binned)
  * @xbar_binning_mask: Xbar binning mask, 1 bit per Xbar instance
  *                     (0 = functional 1 = binned)
+ * @fw_os_version: Firmware OS Version
  */
 struct cpucp_info {
 	struct cpucp_sensor sensors[CPUCP_MAX_SENSORS];
@@ -807,6 +808,7 @@ struct cpucp_info {
 	__le32 reserved6;
 	__u8 pll_map[PLL_MAP_LEN];
 	__le64 mme_binning_mask;
+	__u8 fw_os_version[VERSION_MAX_LEN];
 };
 
 struct cpucp_mac_addr {
diff --git a/drivers/misc/habanalabs/include/common/hl_boot_if.h b/drivers/misc/habanalabs/include/common/hl_boot_if.h
index 135e21d6edc9..15f91ae9de6e 100644
--- a/drivers/misc/habanalabs/include/common/hl_boot_if.h
+++ b/drivers/misc/habanalabs/include/common/hl_boot_if.h
@@ -33,6 +33,7 @@ enum cpu_boot_err {
 	CPU_BOOT_ERR_BOOT_FW_CRIT_ERR = 18,
 	CPU_BOOT_ERR_BINNING_FAIL = 19,
 	CPU_BOOT_ERR_TPM_FAIL = 20,
+	CPU_BOOT_ERR_TMP_THRESH_INIT_FAIL = 21,
 	CPU_BOOT_ERR_ENABLED = 31,
 	CPU_BOOT_ERR_SCND_EN = 63,
 	CPU_BOOT_ERR_LAST = 64 /* we have 2 registers of 32 bits */
@@ -111,6 +112,9 @@ enum cpu_boot_err {
  *
  * CPU_BOOT_ERR0_TPM_FAIL		TPM verification flow failed.
  *
+ * CPU_BOOT_ERR0_TMP_THRESH_INIT_FAIL	Failed to set threshold for tmperature
+ *					sensor.
+ *
  * CPU_BOOT_ERR0_ENABLED		Error registers enabled.
  *					This is a main indication that the
  *					running FW populates the error
@@ -134,6 +138,7 @@ enum cpu_boot_err {
 #define CPU_BOOT_ERR0_BOOT_FW_CRIT_ERR		(1 << CPU_BOOT_ERR_BOOT_FW_CRIT_ERR)
 #define CPU_BOOT_ERR0_BINNING_FAIL		(1 << CPU_BOOT_ERR_BINNING_FAIL)
 #define CPU_BOOT_ERR0_TPM_FAIL			(1 << CPU_BOOT_ERR_TPM_FAIL)
+#define CPU_BOOT_ERR0_TMP_THRESH_INIT_FAIL	(1 << CPU_BOOT_ERR_TMP_THRESH_INIT_FAIL)
 #define CPU_BOOT_ERR0_ENABLED			(1 << CPU_BOOT_ERR_ENABLED)
 #define CPU_BOOT_ERR1_ENABLED			(1 << CPU_BOOT_ERR_ENABLED)
 
diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h b/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h
index d966bd4dfea6..c07ed4ed304c 100644
--- a/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h
+++ b/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h
@@ -311,6 +311,16 @@ enum gaudi_async_event_id {
 	GAUDI_EVENT_FW_ALIVE_S = 645,
 	GAUDI_EVENT_DEV_RESET_REQ = 646,
 	GAUDI_EVENT_PKT_QUEUE_OUT_SYNC = 647,
+	GAUDI_EVENT_STATUS_NIC0_ENG0 = 648,
+	GAUDI_EVENT_STATUS_NIC0_ENG1 = 649,
+	GAUDI_EVENT_STATUS_NIC1_ENG0 = 650,
+	GAUDI_EVENT_STATUS_NIC1_ENG1 = 651,
+	GAUDI_EVENT_STATUS_NIC2_ENG0 = 652,
+	GAUDI_EVENT_STATUS_NIC2_ENG1 = 653,
+	GAUDI_EVENT_STATUS_NIC3_ENG0 = 654,
+	GAUDI_EVENT_STATUS_NIC3_ENG1 = 655,
+	GAUDI_EVENT_STATUS_NIC4_ENG0 = 656,
+	GAUDI_EVENT_STATUS_NIC4_ENG1 = 657,
 	GAUDI_EVENT_FIX_POWER_ENV_S = 658,
 	GAUDI_EVENT_FIX_POWER_ENV_E = 659,
 	GAUDI_EVENT_FIX_THERMAL_ENV_S = 660,