habanalabs: create common folder

For internal needs of our CI we need to move all the common code into a
common folder instead of putting them in the root folder of the driver.

Same applies to the common header files under include/

Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Reviewed-by: Omer Shpigelman <oshpigelman@habana.ai>

18 files changed, 14066 insertions, 0 deletions

diff --git a/drivers/misc/habanalabs/common/Makefile b/drivers/misc/habanalabs/common/Makefile
new file mode 100644
index 000000000000..97d03b5c8683
--- /dev/null
+++ b/drivers/misc/habanalabs/common/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0-only
+subdir-ccflags-y += -I$(src)/common
+
+HL_COMMON_FILES := common/habanalabs_drv.o common/device.o common/context.o \
+		common/asid.o common/habanalabs_ioctl.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/mmu.o common/firmware_if.o \
+		common/pci.o
diff --git a/drivers/misc/habanalabs/common/asid.c b/drivers/misc/habanalabs/common/asid.c
new file mode 100644
index 000000000000..a2fdf31cf27c
--- /dev/null
+++ b/drivers/misc/habanalabs/common/asid.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2019 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include "habanalabs.h"
+
+#include <linux/slab.h>
+
+int hl_asid_init(struct hl_device *hdev)
+{
+	hdev->asid_bitmap = kcalloc(BITS_TO_LONGS(hdev->asic_prop.max_asid),
+					sizeof(*hdev->asid_bitmap), GFP_KERNEL);
+	if (!hdev->asid_bitmap)
+		return -ENOMEM;
+
+	mutex_init(&hdev->asid_mutex);
+
+	/* ASID 0 is reserved for the kernel driver and device CPU */
+	set_bit(0, hdev->asid_bitmap);
+
+	return 0;
+}
+
+void hl_asid_fini(struct hl_device *hdev)
+{
+	mutex_destroy(&hdev->asid_mutex);
+	kfree(hdev->asid_bitmap);
+}
+
+unsigned long hl_asid_alloc(struct hl_device *hdev)
+{
+	unsigned long found;
+
+	mutex_lock(&hdev->asid_mutex);
+
+	found = find_first_zero_bit(hdev->asid_bitmap,
+					hdev->asic_prop.max_asid);
+	if (found == hdev->asic_prop.max_asid)
+		found = 0;
+	else
+		set_bit(found, hdev->asid_bitmap);
+
+	mutex_unlock(&hdev->asid_mutex);
+
+	return found;
+}
+
+void hl_asid_free(struct hl_device *hdev, unsigned long asid)
+{
+	if (WARN((asid == 0 || asid >= hdev->asic_prop.max_asid),
+						"Invalid ASID %lu", asid))
+		return;
+	clear_bit(asid, hdev->asid_bitmap);
+}
diff --git a/drivers/misc/habanalabs/common/command_buffer.c b/drivers/misc/habanalabs/common/command_buffer.c
new file mode 100644
index 000000000000..02d13f71b1df
--- /dev/null
+++ b/drivers/misc/habanalabs/common/command_buffer.c
@@ -0,0 +1,463 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2019 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include <uapi/misc/habanalabs.h>
+#include "habanalabs.h"
+
+#include <linux/mm.h>
+#include <linux/slab.h>
+
+static void cb_fini(struct hl_device *hdev, struct hl_cb *cb)
+{
+	hdev->asic_funcs->asic_dma_free_coherent(hdev, cb->size,
+			(void *) (uintptr_t) cb->kernel_address,
+			cb->bus_address);
+	kfree(cb);
+}
+
+static void cb_do_release(struct hl_device *hdev, struct hl_cb *cb)
+{
+	if (cb->is_pool) {
+		spin_lock(&hdev->cb_pool_lock);
+		list_add(&cb->pool_list, &hdev->cb_pool);
+		spin_unlock(&hdev->cb_pool_lock);
+	} else {
+		cb_fini(hdev, cb);
+	}
+}
+
+static void cb_release(struct kref *ref)
+{
+	struct hl_device *hdev;
+	struct hl_cb *cb;
+
+	cb = container_of(ref, struct hl_cb, refcount);
+	hdev = cb->hdev;
+
+	hl_debugfs_remove_cb(cb);
+
+	cb_do_release(hdev, cb);
+}
+
+static struct hl_cb *hl_cb_alloc(struct hl_device *hdev, u32 cb_size,
+					int ctx_id)
+{
+	struct hl_cb *cb;
+	void *p;
+
+	/*
+	 * We use of GFP_ATOMIC here because this function can be called from
+	 * the latency-sensitive code path for command submission. Due to H/W
+	 * limitations in some of the ASICs, the kernel must copy the user CB
+	 * that is designated for an external queue and actually enqueue
+	 * the kernel's copy. Hence, we must never sleep in this code section
+	 * and must use GFP_ATOMIC for all memory allocations.
+	 */
+	if (ctx_id == HL_KERNEL_ASID_ID)
+		cb = kzalloc(sizeof(*cb), GFP_ATOMIC);
+	else
+		cb = kzalloc(sizeof(*cb), GFP_KERNEL);
+
+	if (!cb)
+		return NULL;
+
+	if (ctx_id == HL_KERNEL_ASID_ID)
+		p = hdev->asic_funcs->asic_dma_alloc_coherent(hdev, cb_size,
+						&cb->bus_address, GFP_ATOMIC);
+	else
+		p = hdev->asic_funcs->asic_dma_alloc_coherent(hdev, cb_size,
+						&cb->bus_address,
+						GFP_USER | __GFP_ZERO);
+	if (!p) {
+		dev_err(hdev->dev,
+			"failed to allocate %d of dma memory for CB\n",
+			cb_size);
+		kfree(cb);
+		return NULL;
+	}
+
+	cb->kernel_address = (u64) (uintptr_t) p;
+	cb->size = cb_size;
+
+	return cb;
+}
+
+int hl_cb_create(struct hl_device *hdev, struct hl_cb_mgr *mgr,
+			u32 cb_size, u64 *handle, int ctx_id)
+{
+	struct hl_cb *cb;
+	bool alloc_new_cb = true;
+	int rc;
+
+	/*
+	 * Can't use generic function to check this because of special case
+	 * where we create a CB as part of the reset process
+	 */
+	if ((hdev->disabled) || ((atomic_read(&hdev->in_reset)) &&
+					(ctx_id != HL_KERNEL_ASID_ID))) {
+		dev_warn_ratelimited(hdev->dev,
+			"Device is disabled or in reset. Can't create new CBs\n");
+		rc = -EBUSY;
+		goto out_err;
+	}
+
+	if (cb_size > SZ_2M) {
+		dev_err(hdev->dev, "CB size %d must be less than %d\n",
+			cb_size, SZ_2M);
+		rc = -EINVAL;
+		goto out_err;
+	}
+
+	/* Minimum allocation must be PAGE SIZE */
+	if (cb_size < PAGE_SIZE)
+		cb_size = PAGE_SIZE;
+
+	if (ctx_id == HL_KERNEL_ASID_ID &&
+			cb_size <= hdev->asic_prop.cb_pool_cb_size) {
+
+		spin_lock(&hdev->cb_pool_lock);
+		if (!list_empty(&hdev->cb_pool)) {
+			cb = list_first_entry(&hdev->cb_pool, typeof(*cb),
+					pool_list);
+			list_del(&cb->pool_list);
+			spin_unlock(&hdev->cb_pool_lock);
+			alloc_new_cb = false;
+		} else {
+			spin_unlock(&hdev->cb_pool_lock);
+			dev_dbg(hdev->dev, "CB pool is empty\n");
+		}
+	}
+
+	if (alloc_new_cb) {
+		cb = hl_cb_alloc(hdev, cb_size, ctx_id);
+		if (!cb) {
+			rc = -ENOMEM;
+			goto out_err;
+		}
+	}
+
+	cb->hdev = hdev;
+	cb->ctx_id = ctx_id;
+
+	spin_lock(&mgr->cb_lock);
+	rc = idr_alloc(&mgr->cb_handles, cb, 1, 0, GFP_ATOMIC);
+	spin_unlock(&mgr->cb_lock);
+
+	if (rc < 0) {
+		dev_err(hdev->dev, "Failed to allocate IDR for a new CB\n");
+		goto release_cb;
+	}
+
+	cb->id = rc;
+
+	kref_init(&cb->refcount);
+	spin_lock_init(&cb->lock);
+
+	/*
+	 * idr is 32-bit so we can safely OR it with a mask that is above
+	 * 32 bit
+	 */
+	*handle = cb->id | HL_MMAP_CB_MASK;
+	*handle <<= PAGE_SHIFT;
+
+	hl_debugfs_add_cb(cb);
+
+	return 0;
+
+release_cb:
+	cb_do_release(hdev, cb);
+out_err:
+	*handle = 0;
+
+	return rc;
+}
+
+int hl_cb_destroy(struct hl_device *hdev, struct hl_cb_mgr *mgr, u64 cb_handle)
+{
+	struct hl_cb *cb;
+	u32 handle;
+	int rc = 0;
+
+	/*
+	 * handle was given to user to do mmap, I need to shift it back to
+	 * how the idr module gave it to me
+	 */
+	cb_handle >>= PAGE_SHIFT;
+	handle = (u32) cb_handle;
+
+	spin_lock(&mgr->cb_lock);
+
+	cb = idr_find(&mgr->cb_handles, handle);
+	if (cb) {
+		idr_remove(&mgr->cb_handles, handle);
+		spin_unlock(&mgr->cb_lock);
+		kref_put(&cb->refcount, cb_release);
+	} else {
+		spin_unlock(&mgr->cb_lock);
+		dev_err(hdev->dev,
+			"CB destroy failed, no match to handle 0x%x\n", handle);
+		rc = -EINVAL;
+	}
+
+	return rc;
+}
+
+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;
+	int rc;
+
+	if (hl_device_disabled_or_in_reset(hdev)) {
+		dev_warn_ratelimited(hdev->dev,
+			"Device is %s. Can't execute CB IOCTL\n",
+			atomic_read(&hdev->in_reset) ? "in_reset" : "disabled");
+		return -EBUSY;
+	}
+
+	switch (args->in.op) {
+	case HL_CB_OP_CREATE:
+		if (args->in.cb_size > HL_MAX_CB_SIZE) {
+			dev_err(hdev->dev,
+				"User requested CB size %d must be less than %d\n",
+				args->in.cb_size, HL_MAX_CB_SIZE);
+			rc = -EINVAL;
+		} else {
+			rc = hl_cb_create(hdev, &hpriv->cb_mgr,
+						args->in.cb_size, &handle,
+						hpriv->ctx->asid);
+		}
+
+		memset(args, 0, sizeof(*args));
+		args->out.cb_handle = handle;
+		break;
+
+	case HL_CB_OP_DESTROY:
+		rc = hl_cb_destroy(hdev, &hpriv->cb_mgr,
+					args->in.cb_handle);
+		break;
+
+	default:
+		rc = -ENOTTY;
+		break;
+	}
+
+	return rc;
+}
+
+static void cb_vm_close(struct vm_area_struct *vma)
+{
+	struct hl_cb *cb = (struct hl_cb *) vma->vm_private_data;
+	long new_mmap_size;
+
+	new_mmap_size = cb->mmap_size - (vma->vm_end - vma->vm_start);
+
+	if (new_mmap_size > 0) {
+		cb->mmap_size = new_mmap_size;
+		return;
+	}
+
+	spin_lock(&cb->lock);
+	cb->mmap = false;
+	spin_unlock(&cb->lock);
+
+	hl_cb_put(cb);
+	vma->vm_private_data = NULL;
+}
+
+static const struct vm_operations_struct cb_vm_ops = {
+	.close = cb_vm_close
+};
+
+int hl_cb_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma)
+{
+	struct hl_device *hdev = hpriv->hdev;
+	struct hl_cb *cb;
+	phys_addr_t address;
+	u32 handle;
+	int rc;
+
+	handle = vma->vm_pgoff;
+
+	/* reference was taken here */
+	cb = hl_cb_get(hdev, &hpriv->cb_mgr, handle);
+	if (!cb) {
+		dev_err(hdev->dev,
+			"CB mmap failed, no match to handle 0x%x\n", handle);
+		return -EINVAL;
+	}
+
+	/* Validation check */
+	if ((vma->vm_end - vma->vm_start) != ALIGN(cb->size, PAGE_SIZE)) {
+		dev_err(hdev->dev,
+			"CB mmap failed, mmap size 0x%lx != 0x%x cb size\n",
+			vma->vm_end - vma->vm_start, cb->size);
+		rc = -EINVAL;
+		goto put_cb;
+	}
+
+	spin_lock(&cb->lock);
+
+	if (cb->mmap) {
+		dev_err(hdev->dev,
+			"CB mmap failed, CB already mmaped to user\n");
+		rc = -EINVAL;
+		goto release_lock;
+	}
+
+	cb->mmap = true;
+
+	spin_unlock(&cb->lock);
+
+	vma->vm_ops = &cb_vm_ops;
+
+	/*
+	 * Note: We're transferring the cb reference to
+	 * vma->vm_private_data here.
+	 */
+
+	vma->vm_private_data = cb;
+
+	/* Calculate address for CB */
+	address = virt_to_phys((void *) (uintptr_t) cb->kernel_address);
+
+	rc = hdev->asic_funcs->cb_mmap(hdev, vma, cb->kernel_address,
+					address, cb->size);
+
+	if (rc) {
+		spin_lock(&cb->lock);
+		cb->mmap = false;
+		goto release_lock;
+	}
+
+	cb->mmap_size = cb->size;
+
+	return 0;
+
+release_lock:
+	spin_unlock(&cb->lock);
+put_cb:
+	hl_cb_put(cb);
+	return rc;
+}
+
+struct hl_cb *hl_cb_get(struct hl_device *hdev, struct hl_cb_mgr *mgr,
+			u32 handle)
+{
+	struct hl_cb *cb;
+
+	spin_lock(&mgr->cb_lock);
+	cb = idr_find(&mgr->cb_handles, handle);
+
+	if (!cb) {
+		spin_unlock(&mgr->cb_lock);
+		dev_warn(hdev->dev,
+			"CB get failed, no match to handle 0x%x\n", handle);
+		return NULL;
+	}
+
+	kref_get(&cb->refcount);
+
+	spin_unlock(&mgr->cb_lock);
+
+	return cb;
+
+}
+
+void hl_cb_put(struct hl_cb *cb)
+{
+	kref_put(&cb->refcount, cb_release);
+}
+
+void hl_cb_mgr_init(struct hl_cb_mgr *mgr)
+{
+	spin_lock_init(&mgr->cb_lock);
+	idr_init(&mgr->cb_handles);
+}
+
+void hl_cb_mgr_fini(struct hl_device *hdev, struct hl_cb_mgr *mgr)
+{
+	struct hl_cb *cb;
+	struct idr *idp;
+	u32 id;
+
+	idp = &mgr->cb_handles;
+
+	idr_for_each_entry(idp, cb, id) {
+		if (kref_put(&cb->refcount, cb_release) != 1)
+			dev_err(hdev->dev,
+				"CB %d for CTX ID %d is still alive\n",
+				id, cb->ctx_id);
+	}
+
+	idr_destroy(&mgr->cb_handles);
+}
+
+struct hl_cb *hl_cb_kernel_create(struct hl_device *hdev, u32 cb_size)
+{
+	u64 cb_handle;
+	struct hl_cb *cb;
+	int rc;
+
+	rc = hl_cb_create(hdev, &hdev->kernel_cb_mgr, cb_size, &cb_handle,
+			HL_KERNEL_ASID_ID);
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to allocate CB for the kernel driver %d\n", rc);
+		return NULL;
+	}
+
+	cb_handle >>= PAGE_SHIFT;
+	cb = hl_cb_get(hdev, &hdev->kernel_cb_mgr, (u32) cb_handle);
+	/* hl_cb_get should never fail here so use kernel WARN */
+	WARN(!cb, "Kernel CB handle invalid 0x%x\n", (u32) cb_handle);
+	if (!cb)
+		goto destroy_cb;
+
+	return cb;
+
+destroy_cb:
+	hl_cb_destroy(hdev, &hdev->kernel_cb_mgr, cb_handle << PAGE_SHIFT);
+
+	return NULL;
+}
+
+int hl_cb_pool_init(struct hl_device *hdev)
+{
+	struct hl_cb *cb;
+	int i;
+
+	INIT_LIST_HEAD(&hdev->cb_pool);
+	spin_lock_init(&hdev->cb_pool_lock);
+
+	for (i = 0 ; i < hdev->asic_prop.cb_pool_cb_cnt ; i++) {
+		cb = hl_cb_alloc(hdev, hdev->asic_prop.cb_pool_cb_size,
+				HL_KERNEL_ASID_ID);
+		if (cb) {
+			cb->is_pool = true;
+			list_add(&cb->pool_list, &hdev->cb_pool);
+		} else {
+			hl_cb_pool_fini(hdev);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+int hl_cb_pool_fini(struct hl_device *hdev)
+{
+	struct hl_cb *cb, *tmp;
+
+	list_for_each_entry_safe(cb, tmp, &hdev->cb_pool, pool_list) {
+		list_del(&cb->pool_list);
+		cb_fini(hdev, cb);
+	}
+
+	return 0;
+}
diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c
new file mode 100644
index 000000000000..c605be89f764
--- /dev/null
+++ b/drivers/misc/habanalabs/common/command_submission.c
@@ -0,0 +1,1232 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2019 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include <uapi/misc/habanalabs.h>
+#include "habanalabs.h"
+
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+
+#define HL_CS_FLAGS_SIG_WAIT	(HL_CS_FLAGS_SIGNAL | HL_CS_FLAGS_WAIT)
+
+static void job_wq_completion(struct work_struct *work);
+static long _hl_cs_wait_ioctl(struct hl_device *hdev,
+		struct hl_ctx *ctx, u64 timeout_us, u64 seq);
+static void cs_do_release(struct kref *ref);
+
+static void hl_sob_reset(struct kref *ref)
+{
+	struct hl_hw_sob *hw_sob = container_of(ref, struct hl_hw_sob,
+							kref);
+	struct hl_device *hdev = hw_sob->hdev;
+
+	hdev->asic_funcs->reset_sob(hdev, hw_sob);
+}
+
+void hl_sob_reset_error(struct kref *ref)
+{
+	struct hl_hw_sob *hw_sob = container_of(ref, struct hl_hw_sob,
+							kref);
+	struct hl_device *hdev = hw_sob->hdev;
+
+	dev_crit(hdev->dev,
+			"SOB release shouldn't be called here, q_idx: %d, sob_id: %d\n",
+			hw_sob->q_idx, hw_sob->sob_id);
+}
+
+static const char *hl_fence_get_driver_name(struct dma_fence *fence)
+{
+	return "HabanaLabs";
+}
+
+static const char *hl_fence_get_timeline_name(struct dma_fence *fence)
+{
+	struct hl_cs_compl *hl_cs_compl =
+		container_of(fence, struct hl_cs_compl, base_fence);
+
+	return dev_name(hl_cs_compl->hdev->dev);
+}
+
+static bool hl_fence_enable_signaling(struct dma_fence *fence)
+{
+	return true;
+}
+
+static void hl_fence_release(struct dma_fence *fence)
+{
+	struct hl_cs_compl *hl_cs_cmpl =
+		container_of(fence, struct hl_cs_compl, base_fence);
+	struct hl_device *hdev = hl_cs_cmpl->hdev;
+
+	/* EBUSY means the CS was never submitted and hence we don't have
+	 * an attached hw_sob object that we should handle here
+	 */
+	if (fence->error == -EBUSY)
+		goto free;
+
+	if ((hl_cs_cmpl->type == CS_TYPE_SIGNAL) ||
+			(hl_cs_cmpl->type == CS_TYPE_WAIT)) {
+
+		dev_dbg(hdev->dev,
+			"CS 0x%llx type %d finished, sob_id: %d, sob_val: 0x%x\n",
+			hl_cs_cmpl->cs_seq,
+			hl_cs_cmpl->type,
+			hl_cs_cmpl->hw_sob->sob_id,
+			hl_cs_cmpl->sob_val);
+
+		/*
+		 * A signal CS can get completion while the corresponding wait
+		 * for signal CS is on its way to the PQ. The wait for signal CS
+		 * will get stuck if the signal CS incremented the SOB to its
+		 * max value and there are no pending (submitted) waits on this
+		 * SOB.
+		 * We do the following to void this situation:
+		 * 1. The wait for signal CS must get a ref for the signal CS as
+		 *    soon as possible in cs_ioctl_signal_wait() and put it
+		 *    before being submitted to the PQ but after it incremented
+		 *    the SOB refcnt in init_signal_wait_cs().
+		 * 2. Signal/Wait for signal CS will decrement the SOB refcnt
+		 *    here.
+		 * These two measures guarantee that the wait for signal CS will
+		 * reset the SOB upon completion rather than the signal CS and
+		 * hence the above scenario is avoided.
+		 */
+		kref_put(&hl_cs_cmpl->hw_sob->kref, hl_sob_reset);
+	}
+
+free:
+	kfree_rcu(hl_cs_cmpl, base_fence.rcu);
+}
+
+static const struct dma_fence_ops hl_fence_ops = {
+	.get_driver_name = hl_fence_get_driver_name,
+	.get_timeline_name = hl_fence_get_timeline_name,
+	.enable_signaling = hl_fence_enable_signaling,
+	.release = hl_fence_release
+};
+
+static void cs_get(struct hl_cs *cs)
+{
+	kref_get(&cs->refcount);
+}
+
+static int cs_get_unless_zero(struct hl_cs *cs)
+{
+	return kref_get_unless_zero(&cs->refcount);
+}
+
+static void cs_put(struct hl_cs *cs)
+{
+	kref_put(&cs->refcount, cs_do_release);
+}
+
+static bool is_cb_patched(struct hl_device *hdev, struct hl_cs_job *job)
+{
+	/*
+	 * Patched CB is created for external queues jobs, and for H/W queues
+	 * jobs if the user CB was allocated by driver and MMU is disabled.
+	 */
+	return (job->queue_type == QUEUE_TYPE_EXT ||
+			(job->queue_type == QUEUE_TYPE_HW &&
+					job->is_kernel_allocated_cb &&
+					!hdev->mmu_enable));
+}
+
+/*
+ * cs_parser - parse the user command submission
+ *
+ * @hpriv	: pointer to the private data of the fd
+ * @job        : pointer to the job that holds the command submission info
+ *
+ * The function parses the command submission of the user. It calls the
+ * ASIC specific parser, which returns a list of memory blocks to send
+ * to the device as different command buffers
+ *
+ */
+static int cs_parser(struct hl_fpriv *hpriv, struct hl_cs_job *job)
+{
+	struct hl_device *hdev = hpriv->hdev;
+	struct hl_cs_parser parser;
+	int rc;
+
+	parser.ctx_id = job->cs->ctx->asid;
+	parser.cs_sequence = job->cs->sequence;
+	parser.job_id = job->id;
+
+	parser.hw_queue_id = job->hw_queue_id;
+	parser.job_userptr_list = &job->userptr_list;
+	parser.patched_cb = NULL;
+	parser.user_cb = job->user_cb;
+	parser.user_cb_size = job->user_cb_size;
+	parser.queue_type = job->queue_type;
+	parser.is_kernel_allocated_cb = job->is_kernel_allocated_cb;
+	job->patched_cb = NULL;
+
+	rc = hdev->asic_funcs->cs_parser(hdev, &parser);
+
+	if (is_cb_patched(hdev, job)) {
+		if (!rc) {
+			job->patched_cb = parser.patched_cb;
+			job->job_cb_size = parser.patched_cb_size;
+			job->contains_dma_pkt = parser.contains_dma_pkt;
+
+			spin_lock(&job->patched_cb->lock);
+			job->patched_cb->cs_cnt++;
+			spin_unlock(&job->patched_cb->lock);
+		}
+
+		/*
+		 * Whether the parsing worked or not, we don't need the
+		 * original CB anymore because it was already parsed and
+		 * won't be accessed again for this CS
+		 */
+		spin_lock(&job->user_cb->lock);
+		job->user_cb->cs_cnt--;
+		spin_unlock(&job->user_cb->lock);
+		hl_cb_put(job->user_cb);
+		job->user_cb = NULL;
+	} else if (!rc) {
+		job->job_cb_size = job->user_cb_size;
+	}
+
+	return rc;
+}
+
+static void free_job(struct hl_device *hdev, struct hl_cs_job *job)
+{
+	struct hl_cs *cs = job->cs;
+
+	if (is_cb_patched(hdev, job)) {
+		hl_userptr_delete_list(hdev, &job->userptr_list);
+
+		/*
+		 * We might arrive here from rollback and patched CB wasn't
+		 * created, so we need to check it's not NULL
+		 */
+		if (job->patched_cb) {
+			spin_lock(&job->patched_cb->lock);
+			job->patched_cb->cs_cnt--;
+			spin_unlock(&job->patched_cb->lock);
+
+			hl_cb_put(job->patched_cb);
+		}
+	}
+
+	/* For H/W queue jobs, if a user CB was allocated by driver and MMU is
+	 * enabled, the user CB isn't released in cs_parser() and thus should be
+	 * released here.
+	 */
+	if (job->queue_type == QUEUE_TYPE_HW &&
+			job->is_kernel_allocated_cb && hdev->mmu_enable) {
+		spin_lock(&job->user_cb->lock);
+		job->user_cb->cs_cnt--;
+		spin_unlock(&job->user_cb->lock);
+
+		hl_cb_put(job->user_cb);
+	}
+
+	/*
+	 * This is the only place where there can be multiple threads
+	 * modifying the list at the same time
+	 */
+	spin_lock(&cs->job_lock);
+	list_del(&job->cs_node);
+	spin_unlock(&cs->job_lock);
+
+	hl_debugfs_remove_job(hdev, job);
+
+	if (job->queue_type == QUEUE_TYPE_EXT ||
+			job->queue_type == QUEUE_TYPE_HW)
+		cs_put(cs);
+
+	kfree(job);
+}
+
+static void cs_counters_aggregate(struct hl_device *hdev, struct hl_ctx *ctx)
+{
+	hdev->aggregated_cs_counters.device_in_reset_drop_cnt +=
+			ctx->cs_counters.device_in_reset_drop_cnt;
+	hdev->aggregated_cs_counters.out_of_mem_drop_cnt +=
+			ctx->cs_counters.out_of_mem_drop_cnt;
+	hdev->aggregated_cs_counters.parsing_drop_cnt +=
+			ctx->cs_counters.parsing_drop_cnt;
+	hdev->aggregated_cs_counters.queue_full_drop_cnt +=
+			ctx->cs_counters.queue_full_drop_cnt;
+}
+
+static void cs_do_release(struct kref *ref)
+{
+	struct hl_cs *cs = container_of(ref, struct hl_cs,
+						refcount);
+	struct hl_device *hdev = cs->ctx->hdev;
+	struct hl_cs_job *job, *tmp;
+
+	cs->completed = true;
+
+	/*
+	 * Although if we reached here it means that all external jobs have
+	 * finished, because each one of them took refcnt to CS, we still
+	 * need to go over the internal jobs and free them. Otherwise, we
+	 * will have leaked memory and what's worse, the CS object (and
+	 * potentially the CTX object) could be released, while the JOB
+	 * still holds a pointer to them (but no reference).
+	 */
+	list_for_each_entry_safe(job, tmp, &cs->job_list, cs_node)
+		free_job(hdev, job);
+
+	/* We also need to update CI for internal queues */
+	if (cs->submitted) {
+		hdev->asic_funcs->hw_queues_lock(hdev);
+
+		hdev->cs_active_cnt--;
+		if (!hdev->cs_active_cnt) {
+			struct hl_device_idle_busy_ts *ts;
+
+			ts = &hdev->idle_busy_ts_arr[hdev->idle_busy_ts_idx++];
+			ts->busy_to_idle_ts = ktime_get();
+
+			if (hdev->idle_busy_ts_idx == HL_IDLE_BUSY_TS_ARR_SIZE)
+				hdev->idle_busy_ts_idx = 0;
+		} else if (hdev->cs_active_cnt < 0) {
+			dev_crit(hdev->dev, "CS active cnt %d is negative\n",
+				hdev->cs_active_cnt);
+		}
+
+		hdev->asic_funcs->hw_queues_unlock(hdev);
+
+		hl_int_hw_queue_update_ci(cs);
+
+		spin_lock(&hdev->hw_queues_mirror_lock);
+		/* remove CS from hw_queues mirror list */
+		list_del_init(&cs->mirror_node);
+		spin_unlock(&hdev->hw_queues_mirror_lock);
+
+		/*
+		 * Don't cancel TDR in case this CS was timedout because we
+		 * might be running from the TDR context
+		 */
+		if ((!cs->timedout) &&
+			(hdev->timeout_jiffies != MAX_SCHEDULE_TIMEOUT)) {
+			struct hl_cs *next;
+
+			if (cs->tdr_active)
+				cancel_delayed_work_sync(&cs->work_tdr);
+
+			spin_lock(&hdev->hw_queues_mirror_lock);
+
+			/* queue TDR for next CS */
+			next = list_first_entry_or_null(
+					&hdev->hw_queues_mirror_list,
+					struct hl_cs, mirror_node);
+
+			if ((next) && (!next->tdr_active)) {
+				next->tdr_active = true;
+				schedule_delayed_work(&next->work_tdr,
+							hdev->timeout_jiffies);
+			}
+
+			spin_unlock(&hdev->hw_queues_mirror_lock);
+		}
+	} else if (cs->type == CS_TYPE_WAIT) {
+		/*
+		 * In case the wait for signal CS was submitted, the put occurs
+		 * in init_signal_wait_cs() right before hanging on the PQ.
+		 */
+		dma_fence_put(cs->signal_fence);
+	}
+
+	/*
+	 * Must be called before hl_ctx_put because inside we use ctx to get
+	 * the device
+	 */
+	hl_debugfs_remove_cs(cs);
+
+	hl_ctx_put(cs->ctx);
+
+	/* We need to mark an error for not submitted because in that case
+	 * the dma fence release flow is different. Mainly, we don't need
+	 * to handle hw_sob for signal/wait
+	 */
+	if (cs->timedout)
+		dma_fence_set_error(cs->fence, -ETIMEDOUT);
+	else if (cs->aborted)
+		dma_fence_set_error(cs->fence, -EIO);
+	else if (!cs->submitted)
+		dma_fence_set_error(cs->fence, -EBUSY);
+
+	dma_fence_signal(cs->fence);
+	dma_fence_put(cs->fence);
+
+	cs_counters_aggregate(hdev, cs->ctx);
+
+	kfree(cs->jobs_in_queue_cnt);
+	kfree(cs);
+}
+
+static void cs_timedout(struct work_struct *work)
+{
+	struct hl_device *hdev;
+	int ctx_asid, rc;
+	struct hl_cs *cs = container_of(work, struct hl_cs,
+						 work_tdr.work);
+	rc = cs_get_unless_zero(cs);
+	if (!rc)
+		return;
+
+	if ((!cs->submitted) || (cs->completed)) {
+		cs_put(cs);
+		return;
+	}
+
+	/* Mark the CS is timed out so we won't try to cancel its TDR */
+	cs->timedout = true;
+
+	hdev = cs->ctx->hdev;
+	ctx_asid = cs->ctx->asid;
+
+	dev_err(hdev->dev,
+		"Command submission %llu has not finished in time!\n",
+		cs->sequence);
+
+	cs_put(cs);
+
+	if (hdev->reset_on_lockup)
+		hl_device_reset(hdev, false, false);
+}
+
+static int allocate_cs(struct hl_device *hdev, struct hl_ctx *ctx,
+			enum hl_cs_type cs_type, struct hl_cs **cs_new)
+{
+	struct hl_cs_compl *cs_cmpl;
+	struct dma_fence *other = NULL;
+	struct hl_cs *cs;
+	int rc;
+
+	cs = kzalloc(sizeof(*cs), GFP_ATOMIC);
+	if (!cs)
+		return -ENOMEM;
+
+	cs->ctx = ctx;
+	cs->submitted = false;
+	cs->completed = false;
+	cs->type = cs_type;
+	INIT_LIST_HEAD(&cs->job_list);
+	INIT_DELAYED_WORK(&cs->work_tdr, cs_timedout);
+	kref_init(&cs->refcount);
+	spin_lock_init(&cs->job_lock);
+
+	cs_cmpl = kmalloc(sizeof(*cs_cmpl), GFP_ATOMIC);
+	if (!cs_cmpl) {
+		rc = -ENOMEM;
+		goto free_cs;
+	}
+
+	cs_cmpl->hdev = hdev;
+	cs_cmpl->type = cs->type;
+	spin_lock_init(&cs_cmpl->lock);
+	cs->fence = &cs_cmpl->base_fence;
+
+	spin_lock(&ctx->cs_lock);
+
+	cs_cmpl->cs_seq = ctx->cs_sequence;
+	other = ctx->cs_pending[cs_cmpl->cs_seq &
+				(hdev->asic_prop.max_pending_cs - 1)];
+	if ((other) && (!dma_fence_is_signaled(other))) {
+		dev_dbg(hdev->dev,
+			"Rejecting CS because of too many in-flights CS\n");
+		rc = -EAGAIN;
+		goto free_fence;
+	}
+
+	cs->jobs_in_queue_cnt = kcalloc(hdev->asic_prop.max_queues,
+			sizeof(*cs->jobs_in_queue_cnt), GFP_ATOMIC);
+	if (!cs->jobs_in_queue_cnt) {
+		rc = -ENOMEM;
+		goto free_fence;
+	}
+
+	dma_fence_init(&cs_cmpl->base_fence, &hl_fence_ops, &cs_cmpl->lock,
+			ctx->asid, ctx->cs_sequence);
+
+	cs->sequence = cs_cmpl->cs_seq;
+
+	ctx->cs_pending[cs_cmpl->cs_seq &
+			(hdev->asic_prop.max_pending_cs - 1)] =
+							&cs_cmpl->base_fence;
+	ctx->cs_sequence++;
+
+	dma_fence_get(&cs_cmpl->base_fence);
+
+	dma_fence_put(other);
+
+	spin_unlock(&ctx->cs_lock);
+
+	*cs_new = cs;
+
+	return 0;
+
+free_fence:
+	spin_unlock(&ctx->cs_lock);
+	kfree(cs_cmpl);
+free_cs:
+	kfree(cs);
+	return rc;
+}
+
+static void cs_rollback(struct hl_device *hdev, struct hl_cs *cs)
+{
+	struct hl_cs_job *job, *tmp;
+
+	list_for_each_entry_safe(job, tmp, &cs->job_list, cs_node)
+		free_job(hdev, job);
+}
+
+void hl_cs_rollback_all(struct hl_device *hdev)
+{
+	int i;
+	struct hl_cs *cs, *tmp;
+
+	/* flush all completions */
+	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 H/W queues mirror list */
+	list_for_each_entry_safe(cs, tmp, &hdev->hw_queues_mirror_list,
+				mirror_node) {
+		cs_get(cs);
+		cs->aborted = true;
+		dev_warn_ratelimited(hdev->dev, "Killing CS %d.%llu\n",
+					cs->ctx->asid, cs->sequence);
+		cs_rollback(hdev, cs);
+		cs_put(cs);
+	}
+}
+
+static void job_wq_completion(struct work_struct *work)
+{
+	struct hl_cs_job *job = container_of(work, struct hl_cs_job,
+						finish_work);
+	struct hl_cs *cs = job->cs;
+	struct hl_device *hdev = cs->ctx->hdev;
+
+	/* job is no longer needed */
+	free_job(hdev, job);
+}
+
+static int validate_queue_index(struct hl_device *hdev,
+				struct hl_cs_chunk *chunk,
+				enum hl_queue_type *queue_type,
+				bool *is_kernel_allocated_cb)
+{
+	struct asic_fixed_properties *asic = &hdev->asic_prop;
+	struct hw_queue_properties *hw_queue_prop;
+
+	/* This must be checked here to prevent out-of-bounds access to
+	 * hw_queues_props array
+	 */
+	if (chunk->queue_index >= asic->max_queues) {
+		dev_err(hdev->dev, "Queue index %d is invalid\n",
+			chunk->queue_index);
+		return -EINVAL;
+	}
+
+	hw_queue_prop = &asic->hw_queues_props[chunk->queue_index];
+
+	if (hw_queue_prop->type == QUEUE_TYPE_NA) {
+		dev_err(hdev->dev, "Queue index %d is invalid\n",
+			chunk->queue_index);
+		return -EINVAL;
+	}
+
+	if (hw_queue_prop->driver_only) {
+		dev_err(hdev->dev,
+			"Queue index %d is restricted for the kernel driver\n",
+			chunk->queue_index);
+		return -EINVAL;
+	}
+
+	*queue_type = hw_queue_prop->type;
+	*is_kernel_allocated_cb = !!hw_queue_prop->requires_kernel_cb;
+
+	return 0;
+}
+
+static struct hl_cb *get_cb_from_cs_chunk(struct hl_device *hdev,
+					struct hl_cb_mgr *cb_mgr,
+					struct hl_cs_chunk *chunk)
+{
+	struct hl_cb *cb;
+	u32 cb_handle;
+
+	cb_handle = (u32) (chunk->cb_handle >> PAGE_SHIFT);
+
+	cb = hl_cb_get(hdev, cb_mgr, cb_handle);
+	if (!cb) {
+		dev_err(hdev->dev, "CB handle 0x%x invalid\n", cb_handle);
+		return NULL;
+	}
+
+	if ((chunk->cb_size < 8) || (chunk->cb_size > cb->size)) {
+		dev_err(hdev->dev, "CB size %u invalid\n", chunk->cb_size);
+		goto release_cb;
+	}
+
+	spin_lock(&cb->lock);
+	cb->cs_cnt++;
+	spin_unlock(&cb->lock);
+
+	return cb;
+
+release_cb:
+	hl_cb_put(cb);
+	return NULL;
+}
+
+struct hl_cs_job *hl_cs_allocate_job(struct hl_device *hdev,
+		enum hl_queue_type queue_type, bool is_kernel_allocated_cb)
+{
+	struct hl_cs_job *job;
+
+	job = kzalloc(sizeof(*job), GFP_ATOMIC);
+	if (!job)
+		return NULL;
+
+	job->queue_type = queue_type;
+	job->is_kernel_allocated_cb = is_kernel_allocated_cb;
+
+	if (is_cb_patched(hdev, job))
+		INIT_LIST_HEAD(&job->userptr_list);
+
+	if (job->queue_type == QUEUE_TYPE_EXT)
+		INIT_WORK(&job->finish_work, job_wq_completion);
+
+	return job;
+}
+
+static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks,
+				u32 num_chunks, u64 *cs_seq)
+{
+	struct hl_device *hdev = hpriv->hdev;
+	struct hl_cs_chunk *cs_chunk_array;
+	struct hl_cs_job *job;
+	struct hl_cs *cs;
+	struct hl_cb *cb;
+	bool int_queues_only = true;
+	u32 size_to_copy;
+	int rc, i;
+
+	*cs_seq = ULLONG_MAX;
+
+	if (num_chunks > HL_MAX_JOBS_PER_CS) {
+		dev_err(hdev->dev,
+			"Number of chunks can NOT be larger than %d\n",
+			HL_MAX_JOBS_PER_CS);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	cs_chunk_array = kmalloc_array(num_chunks, sizeof(*cs_chunk_array),
+					GFP_ATOMIC);
+	if (!cs_chunk_array) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	size_to_copy = num_chunks * sizeof(struct hl_cs_chunk);
+	if (copy_from_user(cs_chunk_array, chunks, size_to_copy)) {
+		dev_err(hdev->dev, "Failed to copy cs chunk array from user\n");
+		rc = -EFAULT;
+		goto free_cs_chunk_array;
+	}
+
+	/* increment refcnt for context */
+	hl_ctx_get(hdev, hpriv->ctx);
+
+	rc = allocate_cs(hdev, hpriv->ctx, CS_TYPE_DEFAULT, &cs);
+	if (rc) {
+		hl_ctx_put(hpriv->ctx);
+		goto free_cs_chunk_array;
+	}
+
+	*cs_seq = cs->sequence;
+
+	hl_debugfs_add_cs(cs);
+
+	/* Validate ALL the CS chunks before submitting the CS */
+	for (i = 0 ; i < num_chunks ; i++) {
+		struct hl_cs_chunk *chunk = &cs_chunk_array[i];
+		enum hl_queue_type queue_type;
+		bool is_kernel_allocated_cb;
+
+		rc = validate_queue_index(hdev, chunk, &queue_type,
+						&is_kernel_allocated_cb);
+		if (rc) {
+			hpriv->ctx->cs_counters.parsing_drop_cnt++;
+			goto free_cs_object;
+		}
+
+		if (is_kernel_allocated_cb) {
+			cb = get_cb_from_cs_chunk(hdev, &hpriv->cb_mgr, chunk);
+			if (!cb) {
+				hpriv->ctx->cs_counters.parsing_drop_cnt++;
+				rc = -EINVAL;
+				goto free_cs_object;
+			}
+		} else {
+			cb = (struct hl_cb *) (uintptr_t) chunk->cb_handle;
+		}
+
+		if (queue_type == QUEUE_TYPE_EXT || queue_type == QUEUE_TYPE_HW)
+			int_queues_only = false;
+
+		job = hl_cs_allocate_job(hdev, queue_type,
+						is_kernel_allocated_cb);
+		if (!job) {
+			hpriv->ctx->cs_counters.out_of_mem_drop_cnt++;
+			dev_err(hdev->dev, "Failed to allocate a new job\n");
+			rc = -ENOMEM;
+			if (is_kernel_allocated_cb)
+				goto release_cb;
+			else
+				goto free_cs_object;
+		}
+
+		job->id = i + 1;
+		job->cs = cs;
+		job->user_cb = cb;
+		job->user_cb_size = chunk->cb_size;
+		job->hw_queue_id = chunk->queue_index;
+
+		cs->jobs_in_queue_cnt[job->hw_queue_id]++;
+
+		list_add_tail(&job->cs_node, &cs->job_list);
+
+		/*
+		 * Increment CS reference. When CS reference is 0, CS is
+		 * done and can be signaled to user and free all its resources
+		 * Only increment for JOB on external or H/W queues, because
+		 * only for those JOBs we get completion
+		 */
+		if (job->queue_type == QUEUE_TYPE_EXT ||
+				job->queue_type == QUEUE_TYPE_HW)
+			cs_get(cs);
+
+		hl_debugfs_add_job(hdev, job);
+
+		rc = cs_parser(hpriv, job);
+		if (rc) {
+			hpriv->ctx->cs_counters.parsing_drop_cnt++;
+			dev_err(hdev->dev,
+				"Failed to parse JOB %d.%llu.%d, err %d, rejecting the CS\n",
+				cs->ctx->asid, cs->sequence, job->id, rc);
+			goto free_cs_object;
+		}
+	}
+
+	if (int_queues_only) {
+		hpriv->ctx->cs_counters.parsing_drop_cnt++;
+		dev_err(hdev->dev,
+			"Reject CS %d.%llu because only internal queues jobs are present\n",
+			cs->ctx->asid, cs->sequence);
+		rc = -EINVAL;
+		goto free_cs_object;
+	}
+
+	rc = hl_hw_queue_schedule_cs(cs);
+	if (rc) {
+		if (rc != -EAGAIN)
+			dev_err(hdev->dev,
+				"Failed to submit CS %d.%llu to H/W queues, error %d\n",
+				cs->ctx->asid, cs->sequence, rc);
+		goto free_cs_object;
+	}
+
+	rc = HL_CS_STATUS_SUCCESS;
+	goto put_cs;
+
+release_cb:
+	spin_lock(&cb->lock);
+	cb->cs_cnt--;
+	spin_unlock(&cb->lock);
+	hl_cb_put(cb);
+free_cs_object:
+	cs_rollback(hdev, cs);
+	*cs_seq = ULLONG_MAX;
+	/* The path below is both for good and erroneous exits */
+put_cs:
+	/* We finished with the CS in this function, so put the ref */
+	cs_put(cs);
+free_cs_chunk_array:
+	kfree(cs_chunk_array);
+out:
+	return rc;
+}
+
+static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type,
+				void __user *chunks, u32 num_chunks,
+				u64 *cs_seq)
+{
+	struct hl_device *hdev = hpriv->hdev;
+	struct hl_ctx *ctx = hpriv->ctx;
+	struct hl_cs_chunk *cs_chunk_array, *chunk;
+	struct hw_queue_properties *hw_queue_prop;
+	struct dma_fence *sig_fence = NULL;
+	struct hl_cs_job *job;
+	struct hl_cs *cs;
+	struct hl_cb *cb;
+	enum hl_queue_type q_type;
+	u64 *signal_seq_arr = NULL, signal_seq;
+	u32 size_to_copy, q_idx, signal_seq_arr_len, cb_size;
+	int rc;
+
+	*cs_seq = ULLONG_MAX;
+
+	if (num_chunks > HL_MAX_JOBS_PER_CS) {
+		dev_err(hdev->dev,
+			"Number of chunks can NOT be larger than %d\n",
+			HL_MAX_JOBS_PER_CS);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	cs_chunk_array = kmalloc_array(num_chunks, sizeof(*cs_chunk_array),
+					GFP_ATOMIC);
+	if (!cs_chunk_array) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	size_to_copy = num_chunks * sizeof(struct hl_cs_chunk);
+	if (copy_from_user(cs_chunk_array, chunks, size_to_copy)) {
+		dev_err(hdev->dev, "Failed to copy cs chunk array from user\n");
+		rc = -EFAULT;
+		goto free_cs_chunk_array;
+	}
+
+	/* currently it is guaranteed to have only one chunk */
+	chunk = &cs_chunk_array[0];
+	q_idx = chunk->queue_index;
+	hw_queue_prop = &hdev->asic_prop.hw_queues_props[q_idx];
+	q_type = hw_queue_prop->type;
+
+	if ((q_idx >= hdev->asic_prop.max_queues) ||
+			(!hw_queue_prop->supports_sync_stream)) {
+		dev_err(hdev->dev, "Queue index %d is invalid\n", q_idx);
+		rc = -EINVAL;
+		goto free_cs_chunk_array;
+	}
+
+	if (cs_type == CS_TYPE_WAIT) {
+		struct hl_cs_compl *sig_waitcs_cmpl;
+
+		signal_seq_arr_len = chunk->num_signal_seq_arr;
+
+		/* currently only one signal seq is supported */
+		if (signal_seq_arr_len != 1) {
+			dev_err(hdev->dev,
+				"Wait for signal CS supports only one signal CS seq\n");
+			rc = -EINVAL;
+			goto free_cs_chunk_array;
+		}
+
+		signal_seq_arr = kmalloc_array(signal_seq_arr_len,
+						sizeof(*signal_seq_arr),
+						GFP_ATOMIC);
+		if (!signal_seq_arr) {
+			rc = -ENOMEM;
+			goto free_cs_chunk_array;
+		}
+
+		size_to_copy = chunk->num_signal_seq_arr *
+				sizeof(*signal_seq_arr);
+		if (copy_from_user(signal_seq_arr,
+					u64_to_user_ptr(chunk->signal_seq_arr),
+					size_to_copy)) {
+			dev_err(hdev->dev,
+				"Failed to copy signal seq array from user\n");
+			rc = -EFAULT;
+			goto free_signal_seq_array;
+		}
+
+		/* currently it is guaranteed to have only one signal seq */
+		signal_seq = signal_seq_arr[0];
+		sig_fence = hl_ctx_get_fence(ctx, signal_seq);
+		if (IS_ERR(sig_fence)) {
+			dev_err(hdev->dev,
+				"Failed to get signal CS with seq 0x%llx\n",
+				signal_seq);
+			rc = PTR_ERR(sig_fence);
+			goto free_signal_seq_array;
+		}
+
+		if (!sig_fence) {
+			/* signal CS already finished */
+			rc = 0;
+			goto free_signal_seq_array;
+		}
+
+		sig_waitcs_cmpl =
+			container_of(sig_fence, struct hl_cs_compl, base_fence);
+
+		if (sig_waitcs_cmpl->type != CS_TYPE_SIGNAL) {
+			dev_err(hdev->dev,
+				"CS seq 0x%llx is not of a signal CS\n",
+				signal_seq);
+			dma_fence_put(sig_fence);
+			rc = -EINVAL;
+			goto free_signal_seq_array;
+		}
+
+		if (dma_fence_is_signaled(sig_fence)) {
+			/* signal CS already finished */
+			dma_fence_put(sig_fence);
+			rc = 0;
+			goto free_signal_seq_array;
+		}
+	}
+
+	/* increment refcnt for context */
+	hl_ctx_get(hdev, ctx);
+
+	rc = allocate_cs(hdev, ctx, cs_type, &cs);
+	if (rc) {
+		if (cs_type == CS_TYPE_WAIT)
+			dma_fence_put(sig_fence);
+		hl_ctx_put(ctx);
+		goto free_signal_seq_array;
+	}
+
+	/*
+	 * Save the signal CS fence for later initialization right before
+	 * hanging the wait CS on the queue.
+	 */
+	if (cs->type == CS_TYPE_WAIT)
+		cs->signal_fence = sig_fence;
+
+	hl_debugfs_add_cs(cs);
+
+	*cs_seq = cs->sequence;
+
+	job = hl_cs_allocate_job(hdev, q_type, true);
+	if (!job) {
+		ctx->cs_counters.out_of_mem_drop_cnt++;
+		dev_err(hdev->dev, "Failed to allocate a new job\n");
+		rc = -ENOMEM;
+		goto put_cs;
+	}
+
+	cb = hl_cb_kernel_create(hdev, PAGE_SIZE);
+	if (!cb) {
+		ctx->cs_counters.out_of_mem_drop_cnt++;
+		kfree(job);
+		rc = -EFAULT;
+		goto put_cs;
+	}
+
+	if (cs->type == CS_TYPE_WAIT)
+		cb_size = hdev->asic_funcs->get_wait_cb_size(hdev);
+	else
+		cb_size = hdev->asic_funcs->get_signal_cb_size(hdev);
+
+	job->id = 0;
+	job->cs = cs;
+	job->user_cb = cb;
+	job->user_cb->cs_cnt++;
+	job->user_cb_size = cb_size;
+	job->hw_queue_id = q_idx;
+
+	/*
+	 * No need in parsing, user CB is the patched CB.
+	 * We call hl_cb_destroy() out of two reasons - we don't need the CB in
+	 * the CB idr anymore and to decrement its refcount as it was
+	 * incremented inside hl_cb_kernel_create().
+	 */
+	job->patched_cb = job->user_cb;
+	job->job_cb_size = job->user_cb_size;
+	hl_cb_destroy(hdev, &hdev->kernel_cb_mgr, cb->id << PAGE_SHIFT);
+
+	cs->jobs_in_queue_cnt[job->hw_queue_id]++;
+
+	list_add_tail(&job->cs_node, &cs->job_list);
+
+	/* increment refcount as for external queues we get completion */
+	cs_get(cs);
+
+	hl_debugfs_add_job(hdev, job);
+
+	rc = hl_hw_queue_schedule_cs(cs);
+	if (rc) {
+		if (rc != -EAGAIN)
+			dev_err(hdev->dev,
+				"Failed to submit CS %d.%llu to H/W queues, error %d\n",
+				ctx->asid, cs->sequence, rc);
+		goto free_cs_object;
+	}
+
+	rc = HL_CS_STATUS_SUCCESS;
+	goto put_cs;
+
+free_cs_object:
+	cs_rollback(hdev, cs);
+	*cs_seq = ULLONG_MAX;
+	/* The path below is both for good and erroneous exits */
+put_cs:
+	/* We finished with the CS in this function, so put the ref */
+	cs_put(cs);
+free_signal_seq_array:
+	if (cs_type == CS_TYPE_WAIT)
+		kfree(signal_seq_arr);
+free_cs_chunk_array:
+	kfree(cs_chunk_array);
+out:
+	return rc;
+}
+
+int hl_cs_ioctl(struct hl_fpriv *hpriv, void *data)
+{
+	struct hl_device *hdev = hpriv->hdev;
+	union hl_cs_args *args = data;
+	struct hl_ctx *ctx = hpriv->ctx;
+	void __user *chunks_execute, *chunks_restore;
+	enum hl_cs_type cs_type;
+	u32 num_chunks_execute, num_chunks_restore, sig_wait_flags;
+	u64 cs_seq = ULONG_MAX;
+	int rc, do_ctx_switch;
+	bool need_soft_reset = false;
+
+	if (hl_device_disabled_or_in_reset(hdev)) {
+		dev_warn_ratelimited(hdev->dev,
+			"Device is %s. Can't submit new CS\n",
+			atomic_read(&hdev->in_reset) ? "in_reset" : "disabled");
+		rc = -EBUSY;
+		goto out;
+	}
+
+	sig_wait_flags = args->in.cs_flags & HL_CS_FLAGS_SIG_WAIT;
+
+	if (unlikely(sig_wait_flags == HL_CS_FLAGS_SIG_WAIT)) {
+		dev_err(hdev->dev,
+			"Signal and wait CS flags are mutually exclusive, context %d\n",
+		ctx->asid);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	if (unlikely((sig_wait_flags & HL_CS_FLAGS_SIG_WAIT) &&
+			(!hdev->supports_sync_stream))) {
+		dev_err(hdev->dev, "Sync stream CS is not supported\n");
+		rc = -EINVAL;
+		goto out;
+	}
+
+	if (args->in.cs_flags & HL_CS_FLAGS_SIGNAL)
+		cs_type = CS_TYPE_SIGNAL;
+	else if (args->in.cs_flags & HL_CS_FLAGS_WAIT)
+		cs_type = CS_TYPE_WAIT;
+	else
+		cs_type = CS_TYPE_DEFAULT;
+
+	chunks_execute = (void __user *) (uintptr_t) args->in.chunks_execute;
+	num_chunks_execute = args->in.num_chunks_execute;
+
+	if (cs_type == CS_TYPE_DEFAULT) {
+		if (!num_chunks_execute) {
+			dev_err(hdev->dev,
+				"Got execute CS with 0 chunks, context %d\n",
+				ctx->asid);
+			rc = -EINVAL;
+			goto out;
+		}
+	} else if (num_chunks_execute != 1) {
+		dev_err(hdev->dev,
+			"Sync stream CS mandates one chunk only, context %d\n",
+			ctx->asid);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	do_ctx_switch = atomic_cmpxchg(&ctx->thread_ctx_switch_token, 1, 0);
+
+	if (do_ctx_switch || (args->in.cs_flags & HL_CS_FLAGS_FORCE_RESTORE)) {
+		long ret;
+
+		chunks_restore =
+			(void __user *) (uintptr_t) args->in.chunks_restore;
+		num_chunks_restore = args->in.num_chunks_restore;
+
+		mutex_lock(&hpriv->restore_phase_mutex);
+
+		if (do_ctx_switch) {
+			rc = hdev->asic_funcs->context_switch(hdev, ctx->asid);
+			if (rc) {
+				dev_err_ratelimited(hdev->dev,
+					"Failed to switch to context %d, rejecting CS! %d\n",
+					ctx->asid, rc);
+				/*
+				 * If we timedout, or if the device is not IDLE
+				 * while we want to do context-switch (-EBUSY),
+				 * we need to soft-reset because QMAN is
+				 * probably stuck. However, we can't call to
+				 * reset here directly because of deadlock, so
+				 * need to do it at the very end of this
+				 * function
+				 */
+				if ((rc == -ETIMEDOUT) || (rc == -EBUSY))
+					need_soft_reset = true;
+				mutex_unlock(&hpriv->restore_phase_mutex);
+				goto out;
+			}
+		}
+
+		hdev->asic_funcs->restore_phase_topology(hdev);
+
+		if (!num_chunks_restore) {
+			dev_dbg(hdev->dev,
+			"Need to run restore phase but restore CS is empty\n");
+			rc = 0;
+		} else {
+			rc = cs_ioctl_default(hpriv, chunks_restore,
+						num_chunks_restore, &cs_seq);
+		}
+
+		mutex_unlock(&hpriv->restore_phase_mutex);
+
+		if (rc) {
+			dev_err(hdev->dev,
+				"Failed to submit restore CS for context %d (%d)\n",
+				ctx->asid, rc);
+			goto out;
+		}
+
+		/* Need to wait for restore completion before execution phase */
+		if (num_chunks_restore) {
+			ret = _hl_cs_wait_ioctl(hdev, ctx,
+					jiffies_to_usecs(hdev->timeout_jiffies),
+					cs_seq);
+			if (ret <= 0) {
+				dev_err(hdev->dev,
+					"Restore CS for context %d failed to complete %ld\n",
+					ctx->asid, ret);
+				rc = -ENOEXEC;
+				goto out;
+			}
+		}
+
+		ctx->thread_ctx_switch_wait_token = 1;
+	} else if (!ctx->thread_ctx_switch_wait_token) {
+		u32 tmp;
+
+		rc = hl_poll_timeout_memory(hdev,
+			&ctx->thread_ctx_switch_wait_token, tmp, (tmp == 1),
+			100, jiffies_to_usecs(hdev->timeout_jiffies), false);
+
+		if (rc == -ETIMEDOUT) {
+			dev_err(hdev->dev,
+				"context switch phase timeout (%d)\n", tmp);
+			goto out;
+		}
+	}
+
+	if (cs_type == CS_TYPE_DEFAULT)
+		rc = cs_ioctl_default(hpriv, chunks_execute, num_chunks_execute,
+					&cs_seq);
+	else
+		rc = cs_ioctl_signal_wait(hpriv, cs_type, chunks_execute,
+						num_chunks_execute, &cs_seq);
+
+out:
+	if (rc != -EAGAIN) {
+		memset(args, 0, sizeof(*args));
+		args->out.status = rc;
+		args->out.seq = cs_seq;
+	}
+
+	if (((rc == -ETIMEDOUT) || (rc == -EBUSY)) && (need_soft_reset))
+		hl_device_reset(hdev, false, false);
+
+	return rc;
+}
+
+static long _hl_cs_wait_ioctl(struct hl_device *hdev,
+		struct hl_ctx *ctx, u64 timeout_us, u64 seq)
+{
+	struct dma_fence *fence;
+	unsigned long timeout;
+	long rc;
+
+	if (timeout_us == MAX_SCHEDULE_TIMEOUT)
+		timeout = timeout_us;
+	else
+		timeout = usecs_to_jiffies(timeout_us);
+
+	hl_ctx_get(hdev, ctx);
+
+	fence = hl_ctx_get_fence(ctx, seq);
+	if (IS_ERR(fence)) {
+		rc = PTR_ERR(fence);
+		if (rc == -EINVAL)
+			dev_notice_ratelimited(hdev->dev,
+				"Can't wait on CS %llu because current CS is at seq %llu\n",
+				seq, ctx->cs_sequence);
+	} else if (fence) {
+		rc = dma_fence_wait_timeout(fence, true, timeout);
+		if (fence->error == -ETIMEDOUT)
+			rc = -ETIMEDOUT;
+		else if (fence->error == -EIO)
+			rc = -EIO;
+		dma_fence_put(fence);
+	} else {
+		dev_dbg(hdev->dev,
+			"Can't wait on seq %llu because current CS is at seq %llu (Fence is gone)\n",
+			seq, ctx->cs_sequence);
+		rc = 1;
+	}
+
+	hl_ctx_put(ctx);
+
+	return rc;
+}
+
+int hl_cs_wait_ioctl(struct hl_fpriv *hpriv, void *data)
+{
+	struct hl_device *hdev = hpriv->hdev;
+	union hl_wait_cs_args *args = data;
+	u64 seq = args->in.seq;
+	long rc;
+
+	rc = _hl_cs_wait_ioctl(hdev, hpriv->ctx, args->in.timeout_us, seq);
+
+	memset(args, 0, sizeof(*args));
+
+	if (rc < 0) {
+		if (rc == -ERESTARTSYS) {
+			dev_err_ratelimited(hdev->dev,
+				"user process got signal while waiting for CS handle %llu\n",
+				seq);
+			args->out.status = HL_WAIT_CS_STATUS_INTERRUPTED;
+			rc = -EINTR;
+		} else if (rc == -ETIMEDOUT) {
+			dev_err_ratelimited(hdev->dev,
+				"CS %llu has timed-out while user process is waiting for it\n",
+				seq);
+			args->out.status = HL_WAIT_CS_STATUS_TIMEDOUT;
+		} else if (rc == -EIO) {
+			dev_err_ratelimited(hdev->dev,
+				"CS %llu has been aborted while user process is waiting for it\n",
+				seq);
+			args->out.status = HL_WAIT_CS_STATUS_ABORTED;
+		}
+		return rc;
+	}
+
+	if (rc == 0)
+		args->out.status = HL_WAIT_CS_STATUS_BUSY;
+	else
+		args->out.status = HL_WAIT_CS_STATUS_COMPLETED;
+
+	return 0;
+}
diff --git a/drivers/misc/habanalabs/common/context.c b/drivers/misc/habanalabs/common/context.c
new file mode 100644
index 000000000000..1e3e5b19ecd9
--- /dev/null
+++ b/drivers/misc/habanalabs/common/context.c
@@ -0,0 +1,237 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2019 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include "habanalabs.h"
+
+#include <linux/slab.h>
+
+static void hl_ctx_fini(struct hl_ctx *ctx)
+{
+	struct hl_device *hdev = ctx->hdev;
+	int i;
+
+	/*
+	 * If we arrived here, there are no jobs waiting for this context
+	 * on its queues so we can safely remove it.
+	 * This is because for each CS, we increment the ref count and for
+	 * every CS that was finished we decrement it and we won't arrive
+	 * to this function unless the ref count is 0
+	 */
+
+	for (i = 0 ; i < hdev->asic_prop.max_pending_cs ; i++)
+		dma_fence_put(ctx->cs_pending[i]);
+
+	kfree(ctx->cs_pending);
+
+	if (ctx->asid != HL_KERNEL_ASID_ID) {
+		/* The engines are stopped as there is no executing CS, but the
+		 * Coresight might be still working by accessing addresses
+		 * related to the stopped engines. Hence stop it explicitly.
+		 * Stop only if this is the compute context, as there can be
+		 * only one compute context
+		 */
+		if ((hdev->in_debug) && (hdev->compute_ctx == ctx))
+			hl_device_set_debug_mode(hdev, false);
+
+		hl_vm_ctx_fini(ctx);
+		hl_asid_free(hdev, ctx->asid);
+	} else {
+		hl_mmu_ctx_fini(ctx);
+	}
+}
+
+void hl_ctx_do_release(struct kref *ref)
+{
+	struct hl_ctx *ctx;
+
+	ctx = container_of(ref, struct hl_ctx, refcount);
+
+	hl_ctx_fini(ctx);
+
+	if (ctx->hpriv)
+		hl_hpriv_put(ctx->hpriv);
+
+	kfree(ctx);
+}
+
+int hl_ctx_create(struct hl_device *hdev, struct hl_fpriv *hpriv)
+{
+	struct hl_ctx_mgr *mgr = &hpriv->ctx_mgr;
+	struct hl_ctx *ctx;
+	int rc;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx) {
+		rc = -ENOMEM;
+		goto out_err;
+	}
+
+	mutex_lock(&mgr->ctx_lock);
+	rc = idr_alloc(&mgr->ctx_handles, ctx, 1, 0, GFP_KERNEL);
+	mutex_unlock(&mgr->ctx_lock);
+
+	if (rc < 0) {
+		dev_err(hdev->dev, "Failed to allocate IDR for a new CTX\n");
+		goto free_ctx;
+	}
+
+	ctx->handle = rc;
+
+	rc = hl_ctx_init(hdev, ctx, false);
+	if (rc)
+		goto remove_from_idr;
+
+	hl_hpriv_get(hpriv);
+	ctx->hpriv = hpriv;
+
+	/* TODO: remove for multiple contexts per process */
+	hpriv->ctx = ctx;
+
+	/* TODO: remove the following line for multiple process support */
+	hdev->compute_ctx = ctx;
+
+	return 0;
+
+remove_from_idr:
+	mutex_lock(&mgr->ctx_lock);
+	idr_remove(&mgr->ctx_handles, ctx->handle);
+	mutex_unlock(&mgr->ctx_lock);
+free_ctx:
+	kfree(ctx);
+out_err:
+	return rc;
+}
+
+void hl_ctx_free(struct hl_device *hdev, struct hl_ctx *ctx)
+{
+	if (kref_put(&ctx->refcount, hl_ctx_do_release) == 1)
+		return;
+
+	dev_warn(hdev->dev,
+		"user process released device but its command submissions are still executing\n");
+}
+
+int hl_ctx_init(struct hl_device *hdev, struct hl_ctx *ctx, bool is_kernel_ctx)
+{
+	int rc = 0;
+
+	ctx->hdev = hdev;
+
+	kref_init(&ctx->refcount);
+
+	ctx->cs_sequence = 1;
+	spin_lock_init(&ctx->cs_lock);
+	atomic_set(&ctx->thread_ctx_switch_token, 1);
+	ctx->thread_ctx_switch_wait_token = 0;
+	ctx->cs_pending = kcalloc(hdev->asic_prop.max_pending_cs,
+				sizeof(struct dma_fence *),
+				GFP_KERNEL);
+	if (!ctx->cs_pending)
+		return -ENOMEM;
+
+	if (is_kernel_ctx) {
+		ctx->asid = HL_KERNEL_ASID_ID; /* Kernel driver gets ASID 0 */
+		rc = hl_mmu_ctx_init(ctx);
+		if (rc) {
+			dev_err(hdev->dev, "Failed to init mmu ctx module\n");
+			goto mem_ctx_err;
+		}
+	} else {
+		ctx->asid = hl_asid_alloc(hdev);
+		if (!ctx->asid) {
+			dev_err(hdev->dev, "No free ASID, failed to create context\n");
+			return -ENOMEM;
+		}
+
+		rc = hl_vm_ctx_init(ctx);
+		if (rc) {
+			dev_err(hdev->dev, "Failed to init mem ctx module\n");
+			rc = -ENOMEM;
+			goto mem_ctx_err;
+		}
+	}
+
+	return 0;
+
+mem_ctx_err:
+	if (ctx->asid != HL_KERNEL_ASID_ID)
+		hl_asid_free(hdev, ctx->asid);
+
+	return rc;
+}
+
+void hl_ctx_get(struct hl_device *hdev, struct hl_ctx *ctx)
+{
+	kref_get(&ctx->refcount);
+}
+
+int hl_ctx_put(struct hl_ctx *ctx)
+{
+	return kref_put(&ctx->refcount, hl_ctx_do_release);
+}
+
+struct dma_fence *hl_ctx_get_fence(struct hl_ctx *ctx, u64 seq)
+{
+	struct asic_fixed_properties *asic_prop = &ctx->hdev->asic_prop;
+	struct dma_fence *fence;
+
+	spin_lock(&ctx->cs_lock);
+
+	if (seq >= ctx->cs_sequence) {
+		spin_unlock(&ctx->cs_lock);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (seq + asic_prop->max_pending_cs < ctx->cs_sequence) {
+		spin_unlock(&ctx->cs_lock);
+		return NULL;
+	}
+
+	fence = dma_fence_get(
+			ctx->cs_pending[seq & (asic_prop->max_pending_cs - 1)]);
+	spin_unlock(&ctx->cs_lock);
+
+	return fence;
+}
+
+/*
+ * hl_ctx_mgr_init - initialize the context manager
+ *
+ * @mgr: pointer to context manager structure
+ *
+ * This manager is an object inside the hpriv object of the user process.
+ * The function is called when a user process opens the FD.
+ */
+void hl_ctx_mgr_init(struct hl_ctx_mgr *mgr)
+{
+	mutex_init(&mgr->ctx_lock);
+	idr_init(&mgr->ctx_handles);
+}
+
+/*
+ * hl_ctx_mgr_fini - finalize the context manager
+ *
+ * @hdev: pointer to device structure
+ * @mgr: pointer to context manager structure
+ *
+ * This function goes over all the contexts in the manager and frees them.
+ * It is called when a process closes the FD.
+ */
+void hl_ctx_mgr_fini(struct hl_device *hdev, struct hl_ctx_mgr *mgr)
+{
+	struct hl_ctx *ctx;
+	struct idr *idp;
+	u32 id;
+
+	idp = &mgr->ctx_handles;
+
+	idr_for_each_entry(idp, ctx, id)
+		hl_ctx_free(hdev, ctx);
+
+	idr_destroy(&mgr->ctx_handles);
+	mutex_destroy(&mgr->ctx_lock);
+}
diff --git a/drivers/misc/habanalabs/common/debugfs.c b/drivers/misc/habanalabs/common/debugfs.c
new file mode 100644
index 000000000000..fc4372c18ce2
--- /dev/null
+++ b/drivers/misc/habanalabs/common/debugfs.c
@@ -0,0 +1,1411 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2019 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include "habanalabs.h"
+#include "include/hw_ip/mmu/mmu_general.h"
+
+#include <linux/pci.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+
+#define MMU_ADDR_BUF_SIZE	40
+#define MMU_ASID_BUF_SIZE	10
+#define MMU_KBUF_SIZE		(MMU_ADDR_BUF_SIZE + MMU_ASID_BUF_SIZE)
+
+static struct dentry *hl_debug_root;
+
+static int hl_debugfs_i2c_read(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr,
+				u8 i2c_reg, u32 *val)
+{
+	struct armcp_packet pkt;
+	int rc;
+
+	if (hl_device_disabled_or_in_reset(hdev))
+		return -EBUSY;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_I2C_RD <<
+				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.i2c_bus = i2c_bus;
+	pkt.i2c_addr = i2c_addr;
+	pkt.i2c_reg = i2c_reg;
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+					HL_DEVICE_TIMEOUT_USEC, (long *) val);
+
+	if (rc)
+		dev_err(hdev->dev, "Failed to read from I2C, error %d\n", rc);
+
+	return rc;
+}
+
+static int hl_debugfs_i2c_write(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr,
+				u8 i2c_reg, u32 val)
+{
+	struct armcp_packet pkt;
+	int rc;
+
+	if (hl_device_disabled_or_in_reset(hdev))
+		return -EBUSY;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_I2C_WR <<
+				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.i2c_bus = i2c_bus;
+	pkt.i2c_addr = i2c_addr;
+	pkt.i2c_reg = i2c_reg;
+	pkt.value = cpu_to_le64(val);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+					HL_DEVICE_TIMEOUT_USEC, NULL);
+
+	if (rc)
+		dev_err(hdev->dev, "Failed to write to I2C, error %d\n", rc);
+
+	return rc;
+}
+
+static void hl_debugfs_led_set(struct hl_device *hdev, u8 led, u8 state)
+{
+	struct armcp_packet pkt;
+	int rc;
+
+	if (hl_device_disabled_or_in_reset(hdev))
+		return;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_LED_SET <<
+				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.led_index = cpu_to_le32(led);
+	pkt.value = cpu_to_le64(state);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+						HL_DEVICE_TIMEOUT_USEC, NULL);
+
+	if (rc)
+		dev_err(hdev->dev, "Failed to set LED %d, error %d\n", led, rc);
+}
+
+static int command_buffers_show(struct seq_file *s, void *data)
+{
+	struct hl_debugfs_entry *entry = s->private;
+	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
+	struct hl_cb *cb;
+	bool first = true;
+
+	spin_lock(&dev_entry->cb_spinlock);
+
+	list_for_each_entry(cb, &dev_entry->cb_list, debugfs_list) {
+		if (first) {
+			first = false;
+			seq_puts(s, "\n");
+			seq_puts(s, " CB ID   CTX ID   CB size    CB RefCnt    mmap?   CS counter\n");
+			seq_puts(s, "---------------------------------------------------------------\n");
+		}
+		seq_printf(s,
+			"   %03d        %d    0x%08x      %d          %d          %d\n",
+			cb->id, cb->ctx_id, cb->size,
+			kref_read(&cb->refcount),
+			cb->mmap, cb->cs_cnt);
+	}
+
+	spin_unlock(&dev_entry->cb_spinlock);
+
+	if (!first)
+		seq_puts(s, "\n");
+
+	return 0;
+}
+
+static int command_submission_show(struct seq_file *s, void *data)
+{
+	struct hl_debugfs_entry *entry = s->private;
+	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
+	struct hl_cs *cs;
+	bool first = true;
+
+	spin_lock(&dev_entry->cs_spinlock);
+
+	list_for_each_entry(cs, &dev_entry->cs_list, debugfs_list) {
+		if (first) {
+			first = false;
+			seq_puts(s, "\n");
+			seq_puts(s, " CS ID   CTX ASID   CS RefCnt   Submitted    Completed\n");
+			seq_puts(s, "------------------------------------------------------\n");
+		}
+		seq_printf(s,
+			"   %llu       %d          %d           %d            %d\n",
+			cs->sequence, cs->ctx->asid,
+			kref_read(&cs->refcount),
+			cs->submitted, cs->completed);
+	}
+
+	spin_unlock(&dev_entry->cs_spinlock);
+
+	if (!first)
+		seq_puts(s, "\n");
+
+	return 0;
+}
+
+static int command_submission_jobs_show(struct seq_file *s, void *data)
+{
+	struct hl_debugfs_entry *entry = s->private;
+	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
+	struct hl_cs_job *job;
+	bool first = true;
+
+	spin_lock(&dev_entry->cs_job_spinlock);
+
+	list_for_each_entry(job, &dev_entry->cs_job_list, debugfs_list) {
+		if (first) {
+			first = false;
+			seq_puts(s, "\n");
+			seq_puts(s, " JOB ID   CS ID    CTX ASID   H/W Queue\n");
+			seq_puts(s, "---------------------------------------\n");
+		}
+		if (job->cs)
+			seq_printf(s,
+				"    %02d       %llu         %d         %d\n",
+				job->id, job->cs->sequence, job->cs->ctx->asid,
+				job->hw_queue_id);
+		else
+			seq_printf(s,
+				"    %02d       0         %d         %d\n",
+				job->id, HL_KERNEL_ASID_ID, job->hw_queue_id);
+	}
+
+	spin_unlock(&dev_entry->cs_job_spinlock);
+
+	if (!first)
+		seq_puts(s, "\n");
+
+	return 0;
+}
+
+static int userptr_show(struct seq_file *s, void *data)
+{
+	struct hl_debugfs_entry *entry = s->private;
+	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
+	struct hl_userptr *userptr;
+	char dma_dir[4][30] = {"DMA_BIDIRECTIONAL", "DMA_TO_DEVICE",
+				"DMA_FROM_DEVICE", "DMA_NONE"};
+	bool first = true;
+
+	spin_lock(&dev_entry->userptr_spinlock);
+
+	list_for_each_entry(userptr, &dev_entry->userptr_list, debugfs_list) {
+		if (first) {
+			first = false;
+			seq_puts(s, "\n");
+			seq_puts(s, " user virtual address     size             dma dir\n");
+			seq_puts(s, "----------------------------------------------------------\n");
+		}
+		seq_printf(s,
+			"    0x%-14llx      %-10u    %-30s\n",
+			userptr->addr, userptr->size, dma_dir[userptr->dir]);
+	}
+
+	spin_unlock(&dev_entry->userptr_spinlock);
+
+	if (!first)
+		seq_puts(s, "\n");
+
+	return 0;
+}
+
+static int vm_show(struct seq_file *s, void *data)
+{
+	struct hl_debugfs_entry *entry = s->private;
+	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
+	struct hl_ctx *ctx;
+	struct hl_vm *vm;
+	struct hl_vm_hash_node *hnode;
+	struct hl_userptr *userptr;
+	struct hl_vm_phys_pg_pack *phys_pg_pack = NULL;
+	enum vm_type_t *vm_type;
+	bool once = true;
+	u64 j;
+	int i;
+
+	if (!dev_entry->hdev->mmu_enable)
+		return 0;
+
+	spin_lock(&dev_entry->ctx_mem_hash_spinlock);
+
+	list_for_each_entry(ctx, &dev_entry->ctx_mem_hash_list, debugfs_list) {
+		once = false;
+		seq_puts(s, "\n\n----------------------------------------------------");
+		seq_puts(s, "\n----------------------------------------------------\n\n");
+		seq_printf(s, "ctx asid: %u\n", ctx->asid);
+
+		seq_puts(s, "\nmappings:\n\n");
+		seq_puts(s, "    virtual address        size          handle\n");
+		seq_puts(s, "----------------------------------------------------\n");
+		mutex_lock(&ctx->mem_hash_lock);
+		hash_for_each(ctx->mem_hash, i, hnode, node) {
+			vm_type = hnode->ptr;
+
+			if (*vm_type == VM_TYPE_USERPTR) {
+				userptr = hnode->ptr;
+				seq_printf(s,
+					"    0x%-14llx      %-10u\n",
+					hnode->vaddr, userptr->size);
+			} else {
+				phys_pg_pack = hnode->ptr;
+				seq_printf(s,
+					"    0x%-14llx      %-10llu       %-4u\n",
+					hnode->vaddr, phys_pg_pack->total_size,
+					phys_pg_pack->handle);
+			}
+		}
+		mutex_unlock(&ctx->mem_hash_lock);
+
+		vm = &ctx->hdev->vm;
+		spin_lock(&vm->idr_lock);
+
+		if (!idr_is_empty(&vm->phys_pg_pack_handles))
+			seq_puts(s, "\n\nallocations:\n");
+
+		idr_for_each_entry(&vm->phys_pg_pack_handles, phys_pg_pack, i) {
+			if (phys_pg_pack->asid != ctx->asid)
+				continue;
+
+			seq_printf(s, "\nhandle: %u\n", phys_pg_pack->handle);
+			seq_printf(s, "page size: %u\n\n",
+						phys_pg_pack->page_size);
+			seq_puts(s, "   physical address\n");
+			seq_puts(s, "---------------------\n");
+			for (j = 0 ; j < phys_pg_pack->npages ; j++) {
+				seq_printf(s, "    0x%-14llx\n",
+						phys_pg_pack->pages[j]);
+			}
+		}
+		spin_unlock(&vm->idr_lock);
+
+	}
+
+	spin_unlock(&dev_entry->ctx_mem_hash_spinlock);
+
+	if (!once)
+		seq_puts(s, "\n");
+
+	return 0;
+}
+
+/* these inline functions are copied from mmu.c */
+static inline u64 get_hop0_addr(struct hl_ctx *ctx)
+{
+	return ctx->hdev->asic_prop.mmu_pgt_addr +
+			(ctx->asid * ctx->hdev->asic_prop.mmu_hop_table_size);
+}
+
+static inline u64 get_hopN_pte_addr(struct hl_ctx *ctx, u64 hop_addr,
+					u64 virt_addr, u64 mask, u64 shift)
+{
+	return hop_addr + ctx->hdev->asic_prop.mmu_pte_size *
+			((virt_addr & mask) >> shift);
+}
+
+static inline u64 get_hop0_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_specs,
+					u64 hop_addr, u64 vaddr)
+{
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_specs->hop0_mask,
+					mmu_specs->hop0_shift);
+}
+
+static inline u64 get_hop1_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_specs,
+					u64 hop_addr, u64 vaddr)
+{
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_specs->hop1_mask,
+					mmu_specs->hop1_shift);
+}
+
+static inline u64 get_hop2_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_specs,
+					u64 hop_addr, u64 vaddr)
+{
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_specs->hop2_mask,
+					mmu_specs->hop2_shift);
+}
+
+static inline u64 get_hop3_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_specs,
+					u64 hop_addr, u64 vaddr)
+{
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_specs->hop3_mask,
+					mmu_specs->hop3_shift);
+}
+
+static inline u64 get_hop4_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_specs,
+					u64 hop_addr, u64 vaddr)
+{
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_specs->hop4_mask,
+					mmu_specs->hop4_shift);
+}
+
+static inline u64 get_next_hop_addr(u64 curr_pte)
+{
+	if (curr_pte & PAGE_PRESENT_MASK)
+		return curr_pte & HOP_PHYS_ADDR_MASK;
+	else
+		return ULLONG_MAX;
+}
+
+static int mmu_show(struct seq_file *s, void *data)
+{
+	struct hl_debugfs_entry *entry = s->private;
+	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
+	struct hl_device *hdev = dev_entry->hdev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct hl_mmu_properties *mmu_prop;
+	struct hl_ctx *ctx;
+	bool is_dram_addr;
+
+	u64 hop0_addr = 0, hop0_pte_addr = 0, hop0_pte = 0,
+		hop1_addr = 0, hop1_pte_addr = 0, hop1_pte = 0,
+		hop2_addr = 0, hop2_pte_addr = 0, hop2_pte = 0,
+		hop3_addr = 0, hop3_pte_addr = 0, hop3_pte = 0,
+		hop4_addr = 0, hop4_pte_addr = 0, hop4_pte = 0,
+		virt_addr = dev_entry->mmu_addr;
+
+	if (!hdev->mmu_enable)
+		return 0;
+
+	if (dev_entry->mmu_asid == HL_KERNEL_ASID_ID)
+		ctx = hdev->kernel_ctx;
+	else
+		ctx = hdev->compute_ctx;
+
+	if (!ctx) {
+		dev_err(hdev->dev, "no ctx available\n");
+		return 0;
+	}
+
+	is_dram_addr = hl_mem_area_inside_range(virt_addr, prop->dmmu.page_size,
+						prop->dmmu.start_addr,
+						prop->dmmu.end_addr);
+
+	/* shifts and masks are the same in PMMU and HPMMU, use one of them */
+	mmu_prop = is_dram_addr ? &prop->dmmu : &prop->pmmu;
+
+	mutex_lock(&ctx->mmu_lock);
+
+	/* the following lookup is copied from unmap() in mmu.c */
+
+	hop0_addr = get_hop0_addr(ctx);
+	hop0_pte_addr = get_hop0_pte_addr(ctx, mmu_prop, hop0_addr, virt_addr);
+	hop0_pte = hdev->asic_funcs->read_pte(hdev, hop0_pte_addr);
+	hop1_addr = get_next_hop_addr(hop0_pte);
+
+	if (hop1_addr == ULLONG_MAX)
+		goto not_mapped;
+
+	hop1_pte_addr = get_hop1_pte_addr(ctx, mmu_prop, hop1_addr, virt_addr);
+	hop1_pte = hdev->asic_funcs->read_pte(hdev, hop1_pte_addr);
+	hop2_addr = get_next_hop_addr(hop1_pte);
+
+	if (hop2_addr == ULLONG_MAX)
+		goto not_mapped;
+
+	hop2_pte_addr = get_hop2_pte_addr(ctx, mmu_prop, hop2_addr, virt_addr);
+	hop2_pte = hdev->asic_funcs->read_pte(hdev, hop2_pte_addr);
+	hop3_addr = get_next_hop_addr(hop2_pte);
+
+	if (hop3_addr == ULLONG_MAX)
+		goto not_mapped;
+
+	hop3_pte_addr = get_hop3_pte_addr(ctx, mmu_prop, hop3_addr, virt_addr);
+	hop3_pte = hdev->asic_funcs->read_pte(hdev, hop3_pte_addr);
+
+	if (!(hop3_pte & LAST_MASK)) {
+		hop4_addr = get_next_hop_addr(hop3_pte);
+
+		if (hop4_addr == ULLONG_MAX)
+			goto not_mapped;
+
+		hop4_pte_addr = get_hop4_pte_addr(ctx, mmu_prop, hop4_addr,
+							virt_addr);
+		hop4_pte = hdev->asic_funcs->read_pte(hdev, hop4_pte_addr);
+		if (!(hop4_pte & PAGE_PRESENT_MASK))
+			goto not_mapped;
+	} else {
+		if (!(hop3_pte & PAGE_PRESENT_MASK))
+			goto not_mapped;
+	}
+
+	seq_printf(s, "asid: %u, virt_addr: 0x%llx\n",
+			dev_entry->mmu_asid, dev_entry->mmu_addr);
+
+	seq_printf(s, "hop0_addr: 0x%llx\n", hop0_addr);
+	seq_printf(s, "hop0_pte_addr: 0x%llx\n", hop0_pte_addr);
+	seq_printf(s, "hop0_pte: 0x%llx\n", hop0_pte);
+
+	seq_printf(s, "hop1_addr: 0x%llx\n", hop1_addr);
+	seq_printf(s, "hop1_pte_addr: 0x%llx\n", hop1_pte_addr);
+	seq_printf(s, "hop1_pte: 0x%llx\n", hop1_pte);
+
+	seq_printf(s, "hop2_addr: 0x%llx\n", hop2_addr);
+	seq_printf(s, "hop2_pte_addr: 0x%llx\n", hop2_pte_addr);
+	seq_printf(s, "hop2_pte: 0x%llx\n", hop2_pte);
+
+	seq_printf(s, "hop3_addr: 0x%llx\n", hop3_addr);
+	seq_printf(s, "hop3_pte_addr: 0x%llx\n", hop3_pte_addr);
+	seq_printf(s, "hop3_pte: 0x%llx\n", hop3_pte);
+
+	if (!(hop3_pte & LAST_MASK)) {
+		seq_printf(s, "hop4_addr: 0x%llx\n", hop4_addr);
+		seq_printf(s, "hop4_pte_addr: 0x%llx\n", hop4_pte_addr);
+		seq_printf(s, "hop4_pte: 0x%llx\n", hop4_pte);
+	}
+
+	goto out;
+
+not_mapped:
+	dev_err(hdev->dev, "virt addr 0x%llx is not mapped to phys addr\n",
+			virt_addr);
+out:
+	mutex_unlock(&ctx->mmu_lock);
+
+	return 0;
+}
+
+static ssize_t mmu_asid_va_write(struct file *file, const char __user *buf,
+		size_t count, loff_t *f_pos)
+{
+	struct seq_file *s = file->private_data;
+	struct hl_debugfs_entry *entry = s->private;
+	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
+	struct hl_device *hdev = dev_entry->hdev;
+	char kbuf[MMU_KBUF_SIZE];
+	char *c;
+	ssize_t rc;
+
+	if (!hdev->mmu_enable)
+		return count;
+
+	if (count > sizeof(kbuf) - 1)
+		goto err;
+	if (copy_from_user(kbuf, buf, count))
+		goto err;
+	kbuf[count] = 0;
+
+	c = strchr(kbuf, ' ');
+	if (!c)
+		goto err;
+	*c = '\0';
+
+	rc = kstrtouint(kbuf, 10, &dev_entry->mmu_asid);
+	if (rc)
+		goto err;
+
+	if (strncmp(c+1, "0x", 2))
+		goto err;
+	rc = kstrtoull(c+3, 16, &dev_entry->mmu_addr);
+	if (rc)
+		goto err;
+
+	return count;
+
+err:
+	dev_err(hdev->dev, "usage: echo <asid> <0xaddr> > mmu\n");
+
+	return -EINVAL;
+}
+
+static int engines_show(struct seq_file *s, void *data)
+{
+	struct hl_debugfs_entry *entry = s->private;
+	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
+	struct hl_device *hdev = dev_entry->hdev;
+
+	if (atomic_read(&hdev->in_reset)) {
+		dev_warn_ratelimited(hdev->dev,
+				"Can't check device idle during reset\n");
+		return 0;
+	}
+
+	hdev->asic_funcs->is_device_idle(hdev, NULL, s);
+
+	return 0;
+}
+
+static bool hl_is_device_va(struct hl_device *hdev, u64 addr)
+{
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+
+	if (!hdev->mmu_enable)
+		goto out;
+
+	if (hdev->dram_supports_virtual_memory &&
+		(addr >= prop->dmmu.start_addr && addr < prop->dmmu.end_addr))
+		return true;
+
+	if (addr >= prop->pmmu.start_addr &&
+		addr < prop->pmmu.end_addr)
+		return true;
+
+	if (addr >= prop->pmmu_huge.start_addr &&
+		addr < prop->pmmu_huge.end_addr)
+		return true;
+out:
+	return false;
+}
+
+static int device_va_to_pa(struct hl_device *hdev, u64 virt_addr,
+				u64 *phys_addr)
+{
+	struct hl_ctx *ctx = hdev->compute_ctx;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct hl_mmu_properties *mmu_prop;
+	u64 hop_addr, hop_pte_addr, hop_pte;
+	u64 offset_mask = HOP4_MASK | FLAGS_MASK;
+	int rc = 0;
+	bool is_dram_addr;
+
+	if (!ctx) {
+		dev_err(hdev->dev, "no ctx available\n");
+		return -EINVAL;
+	}
+
+	is_dram_addr = hl_mem_area_inside_range(virt_addr, prop->dmmu.page_size,
+						prop->dmmu.start_addr,
+						prop->dmmu.end_addr);
+
+	/* shifts and masks are the same in PMMU and HPMMU, use one of them */
+	mmu_prop = is_dram_addr ? &prop->dmmu : &prop->pmmu;
+
+	mutex_lock(&ctx->mmu_lock);
+
+	/* hop 0 */
+	hop_addr = get_hop0_addr(ctx);
+	hop_pte_addr = get_hop0_pte_addr(ctx, mmu_prop, hop_addr, virt_addr);
+	hop_pte = hdev->asic_funcs->read_pte(hdev, hop_pte_addr);
+
+	/* hop 1 */
+	hop_addr = get_next_hop_addr(hop_pte);
+	if (hop_addr == ULLONG_MAX)
+		goto not_mapped;
+	hop_pte_addr = get_hop1_pte_addr(ctx, mmu_prop, hop_addr, virt_addr);
+	hop_pte = hdev->asic_funcs->read_pte(hdev, hop_pte_addr);
+
+	/* hop 2 */
+	hop_addr = get_next_hop_addr(hop_pte);
+	if (hop_addr == ULLONG_MAX)
+		goto not_mapped;
+	hop_pte_addr = get_hop2_pte_addr(ctx, mmu_prop, hop_addr, virt_addr);
+	hop_pte = hdev->asic_funcs->read_pte(hdev, hop_pte_addr);
+
+	/* hop 3 */
+	hop_addr = get_next_hop_addr(hop_pte);
+	if (hop_addr == ULLONG_MAX)
+		goto not_mapped;
+	hop_pte_addr = get_hop3_pte_addr(ctx, mmu_prop, hop_addr, virt_addr);
+	hop_pte = hdev->asic_funcs->read_pte(hdev, hop_pte_addr);
+
+	if (!(hop_pte & LAST_MASK)) {
+		/* hop 4 */
+		hop_addr = get_next_hop_addr(hop_pte);
+		if (hop_addr == ULLONG_MAX)
+			goto not_mapped;
+		hop_pte_addr = get_hop4_pte_addr(ctx, mmu_prop, hop_addr,
+							virt_addr);
+		hop_pte = hdev->asic_funcs->read_pte(hdev, hop_pte_addr);
+
+		offset_mask = FLAGS_MASK;
+	}
+
+	if (!(hop_pte & PAGE_PRESENT_MASK))
+		goto not_mapped;
+
+	*phys_addr = (hop_pte & ~offset_mask) | (virt_addr & offset_mask);
+
+	goto out;
+
+not_mapped:
+	dev_err(hdev->dev, "virt addr 0x%llx is not mapped to phys addr\n",
+			virt_addr);
+	rc = -EINVAL;
+out:
+	mutex_unlock(&ctx->mmu_lock);
+	return rc;
+}
+
+static ssize_t hl_data_read32(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[32];
+	u64 addr = entry->addr;
+	u32 val;
+	ssize_t rc;
+
+	if (atomic_read(&hdev->in_reset)) {
+		dev_warn_ratelimited(hdev->dev, "Can't read during reset\n");
+		return 0;
+	}
+
+	if (*ppos)
+		return 0;
+
+	if (hl_is_device_va(hdev, addr)) {
+		rc = device_va_to_pa(hdev, addr, &addr);
+		if (rc)
+			return rc;
+	}
+
+	rc = hdev->asic_funcs->debugfs_read32(hdev, addr, &val);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to read from 0x%010llx\n", addr);
+		return rc;
+	}
+
+	sprintf(tmp_buf, "0x%08x\n", val);
+	return simple_read_from_buffer(buf, count, ppos, tmp_buf,
+			strlen(tmp_buf));
+}
+
+static ssize_t hl_data_write32(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 addr = entry->addr;
+	u32 value;
+	ssize_t rc;
+
+	if (atomic_read(&hdev->in_reset)) {
+		dev_warn_ratelimited(hdev->dev, "Can't write during reset\n");
+		return 0;
+	}
+
+	rc = kstrtouint_from_user(buf, count, 16, &value);
+	if (rc)
+		return rc;
+
+	if (hl_is_device_va(hdev, addr)) {
+		rc = device_va_to_pa(hdev, addr, &addr);
+		if (rc)
+			return rc;
+	}
+
+	rc = hdev->asic_funcs->debugfs_write32(hdev, addr, value);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to write 0x%08x to 0x%010llx\n",
+			value, addr);
+		return rc;
+	}
+
+	return count;
+}
+
+static ssize_t hl_data_read64(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[32];
+	u64 addr = entry->addr;
+	u64 val;
+	ssize_t rc;
+
+	if (*ppos)
+		return 0;
+
+	if (hl_is_device_va(hdev, addr)) {
+		rc = device_va_to_pa(hdev, addr, &addr);
+		if (rc)
+			return rc;
+	}
+
+	rc = hdev->asic_funcs->debugfs_read64(hdev, addr, &val);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to read from 0x%010llx\n", addr);
+		return rc;
+	}
+
+	sprintf(tmp_buf, "0x%016llx\n", val);
+	return simple_read_from_buffer(buf, count, ppos, tmp_buf,
+			strlen(tmp_buf));
+}
+
+static ssize_t hl_data_write64(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 addr = entry->addr;
+	u64 value;
+	ssize_t rc;
+
+	rc = kstrtoull_from_user(buf, count, 16, &value);
+	if (rc)
+		return rc;
+
+	if (hl_is_device_va(hdev, addr)) {
+		rc = device_va_to_pa(hdev, addr, &addr);
+		if (rc)
+			return rc;
+	}
+
+	rc = hdev->asic_funcs->debugfs_write64(hdev, addr, value);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to write 0x%016llx to 0x%010llx\n",
+			value, addr);
+		return rc;
+	}
+
+	return count;
+}
+
+static ssize_t hl_get_power_state(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];
+	int i;
+
+	if (*ppos)
+		return 0;
+
+	if (hdev->pdev->current_state == PCI_D0)
+		i = 1;
+	else if (hdev->pdev->current_state == PCI_D3hot)
+		i = 2;
+	else
+		i = 3;
+
+	sprintf(tmp_buf,
+		"current power state: %d\n1 - D0\n2 - D3hot\n3 - Unknown\n", i);
+	return simple_read_from_buffer(buf, count, ppos, tmp_buf,
+			strlen(tmp_buf));
+}
+
+static ssize_t hl_set_power_state(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;
+	u32 value;
+	ssize_t rc;
+
+	rc = kstrtouint_from_user(buf, count, 10, &value);
+	if (rc)
+		return rc;
+
+	if (value == 1) {
+		pci_set_power_state(hdev->pdev, PCI_D0);
+		pci_restore_state(hdev->pdev);
+		rc = pci_enable_device(hdev->pdev);
+	} else if (value == 2) {
+		pci_save_state(hdev->pdev);
+		pci_disable_device(hdev->pdev);
+		pci_set_power_state(hdev->pdev, PCI_D3hot);
+	} else {
+		dev_dbg(hdev->dev, "invalid power state value %u\n", value);
+		return -EINVAL;
+	}
+
+	return count;
+}
+
+static ssize_t hl_i2c_data_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[32];
+	u32 val;
+	ssize_t rc;
+
+	if (*ppos)
+		return 0;
+
+	rc = hl_debugfs_i2c_read(hdev, entry->i2c_bus, entry->i2c_addr,
+			entry->i2c_reg, &val);
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to read from I2C bus %d, addr %d, reg %d\n",
+			entry->i2c_bus, entry->i2c_addr, entry->i2c_reg);
+		return rc;
+	}
+
+	sprintf(tmp_buf, "0x%02x\n", val);
+	rc = simple_read_from_buffer(buf, count, ppos, tmp_buf,
+			strlen(tmp_buf));
+
+	return rc;
+}
+
+static ssize_t hl_i2c_data_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;
+	u32 value;
+	ssize_t rc;
+
+	rc = kstrtouint_from_user(buf, count, 16, &value);
+	if (rc)
+		return rc;
+
+	rc = hl_debugfs_i2c_write(hdev, entry->i2c_bus, entry->i2c_addr,
+			entry->i2c_reg, value);
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to write 0x%02x to I2C bus %d, addr %d, reg %d\n",
+			value, entry->i2c_bus, entry->i2c_addr, entry->i2c_reg);
+		return rc;
+	}
+
+	return count;
+}
+
+static ssize_t hl_led0_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;
+	u32 value;
+	ssize_t rc;
+
+	rc = kstrtouint_from_user(buf, count, 10, &value);
+	if (rc)
+		return rc;
+
+	value = value ? 1 : 0;
+
+	hl_debugfs_led_set(hdev, 0, value);
+
+	return count;
+}
+
+static ssize_t hl_led1_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;
+	u32 value;
+	ssize_t rc;
+
+	rc = kstrtouint_from_user(buf, count, 10, &value);
+	if (rc)
+		return rc;
+
+	value = value ? 1 : 0;
+
+	hl_debugfs_led_set(hdev, 1, value);
+
+	return count;
+}
+
+static ssize_t hl_led2_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;
+	u32 value;
+	ssize_t rc;
+
+	rc = kstrtouint_from_user(buf, count, 10, &value);
+	if (rc)
+		return rc;
+
+	value = value ? 1 : 0;
+
+	hl_debugfs_led_set(hdev, 2, value);
+
+	return count;
+}
+
+static ssize_t hl_device_read(struct file *f, char __user *buf,
+					size_t count, loff_t *ppos)
+{
+	static const char *help =
+		"Valid values: disable, enable, suspend, resume, cpu_timeout\n";
+	return simple_read_from_buffer(buf, count, ppos, help, strlen(help));
+}
+
+static ssize_t hl_device_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;
+	char data[30] = {0};
+
+	/* don't allow partial writes */
+	if (*ppos != 0)
+		return 0;
+
+	simple_write_to_buffer(data, 29, ppos, buf, count);
+
+	if (strncmp("disable", data, strlen("disable")) == 0) {
+		hdev->disabled = true;
+	} else if (strncmp("enable", data, strlen("enable")) == 0) {
+		hdev->disabled = false;
+	} else if (strncmp("suspend", data, strlen("suspend")) == 0) {
+		hdev->asic_funcs->suspend(hdev);
+	} else if (strncmp("resume", data, strlen("resume")) == 0) {
+		hdev->asic_funcs->resume(hdev);
+	} else if (strncmp("cpu_timeout", data, strlen("cpu_timeout")) == 0) {
+		hdev->device_cpu_disabled = true;
+	} else {
+		dev_err(hdev->dev,
+			"Valid values: disable, enable, suspend, resume, cpu_timeout\n");
+		count = -EINVAL;
+	}
+
+	return count;
+}
+
+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, "%d\n", hdev->clock_gating);
+	rc = simple_read_from_buffer(buf, strlen(tmp_buf) + 1, ppos, tmp_buf,
+			strlen(tmp_buf) + 1);
+
+	return rc;
+}
+
+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;
+	u32 value;
+	ssize_t rc;
+
+	if (atomic_read(&hdev->in_reset)) {
+		dev_warn_ratelimited(hdev->dev,
+				"Can't change clock gating during reset\n");
+		return 0;
+	}
+
+	rc = kstrtouint_from_user(buf, count, 10, &value);
+	if (rc)
+		return rc;
+
+	if (value) {
+		hdev->clock_gating = 1;
+		if (hdev->asic_funcs->enable_clock_gating)
+			hdev->asic_funcs->enable_clock_gating(hdev);
+	} else {
+		if (hdev->asic_funcs->disable_clock_gating)
+			hdev->asic_funcs->disable_clock_gating(hdev);
+		hdev->clock_gating = 0;
+	}
+
+	return count;
+}
+
+static ssize_t hl_stop_on_err_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, "%d\n", hdev->stop_on_err);
+	rc = simple_read_from_buffer(buf, strlen(tmp_buf) + 1, ppos, tmp_buf,
+			strlen(tmp_buf) + 1);
+
+	return rc;
+}
+
+static ssize_t hl_stop_on_err_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;
+	u32 value;
+	ssize_t rc;
+
+	if (atomic_read(&hdev->in_reset)) {
+		dev_warn_ratelimited(hdev->dev,
+				"Can't change stop on error during reset\n");
+		return 0;
+	}
+
+	rc = kstrtouint_from_user(buf, count, 10, &value);
+	if (rc)
+		return rc;
+
+	hdev->stop_on_err = value ? 1 : 0;
+
+	hl_device_reset(hdev, false, false);
+
+	return count;
+}
+
+static const struct file_operations hl_data32b_fops = {
+	.owner = THIS_MODULE,
+	.read = hl_data_read32,
+	.write = hl_data_write32
+};
+
+static const struct file_operations hl_data64b_fops = {
+	.owner = THIS_MODULE,
+	.read = hl_data_read64,
+	.write = hl_data_write64
+};
+
+static const struct file_operations hl_i2c_data_fops = {
+	.owner = THIS_MODULE,
+	.read = hl_i2c_data_read,
+	.write = hl_i2c_data_write
+};
+
+static const struct file_operations hl_power_fops = {
+	.owner = THIS_MODULE,
+	.read = hl_get_power_state,
+	.write = hl_set_power_state
+};
+
+static const struct file_operations hl_led0_fops = {
+	.owner = THIS_MODULE,
+	.write = hl_led0_write
+};
+
+static const struct file_operations hl_led1_fops = {
+	.owner = THIS_MODULE,
+	.write = hl_led1_write
+};
+
+static const struct file_operations hl_led2_fops = {
+	.owner = THIS_MODULE,
+	.write = hl_led2_write
+};
+
+static const struct file_operations hl_device_fops = {
+	.owner = THIS_MODULE,
+	.read = hl_device_read,
+	.write = hl_device_write
+};
+
+static const struct file_operations hl_clk_gate_fops = {
+	.owner = THIS_MODULE,
+	.read = hl_clk_gate_read,
+	.write = hl_clk_gate_write
+};
+
+static const struct file_operations hl_stop_on_err_fops = {
+	.owner = THIS_MODULE,
+	.read = hl_stop_on_err_read,
+	.write = hl_stop_on_err_write
+};
+
+static const struct hl_info_list hl_debugfs_list[] = {
+	{"command_buffers", command_buffers_show, NULL},
+	{"command_submission", command_submission_show, NULL},
+	{"command_submission_jobs", command_submission_jobs_show, NULL},
+	{"userptr", userptr_show, NULL},
+	{"vm", vm_show, NULL},
+	{"mmu", mmu_show, mmu_asid_va_write},
+	{"engines", engines_show, NULL}
+};
+
+static int hl_debugfs_open(struct inode *inode, struct file *file)
+{
+	struct hl_debugfs_entry *node = inode->i_private;
+
+	return single_open(file, node->info_ent->show, node);
+}
+
+static ssize_t hl_debugfs_write(struct file *file, const char __user *buf,
+		size_t count, loff_t *f_pos)
+{
+	struct hl_debugfs_entry *node = file->f_inode->i_private;
+
+	if (node->info_ent->write)
+		return node->info_ent->write(file, buf, count, f_pos);
+	else
+		return -EINVAL;
+
+}
+
+static const struct file_operations hl_debugfs_fops = {
+	.owner = THIS_MODULE,
+	.open = hl_debugfs_open,
+	.read = seq_read,
+	.write = hl_debugfs_write,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+void hl_debugfs_add_device(struct hl_device *hdev)
+{
+	struct hl_dbg_device_entry *dev_entry = &hdev->hl_debugfs;
+	int count = ARRAY_SIZE(hl_debugfs_list);
+	struct hl_debugfs_entry *entry;
+	struct dentry *ent;
+	int i;
+
+	dev_entry->hdev = hdev;
+	dev_entry->entry_arr = kmalloc_array(count,
+					sizeof(struct hl_debugfs_entry),
+					GFP_KERNEL);
+	if (!dev_entry->entry_arr)
+		return;
+
+	INIT_LIST_HEAD(&dev_entry->file_list);
+	INIT_LIST_HEAD(&dev_entry->cb_list);
+	INIT_LIST_HEAD(&dev_entry->cs_list);
+	INIT_LIST_HEAD(&dev_entry->cs_job_list);
+	INIT_LIST_HEAD(&dev_entry->userptr_list);
+	INIT_LIST_HEAD(&dev_entry->ctx_mem_hash_list);
+	mutex_init(&dev_entry->file_mutex);
+	spin_lock_init(&dev_entry->cb_spinlock);
+	spin_lock_init(&dev_entry->cs_spinlock);
+	spin_lock_init(&dev_entry->cs_job_spinlock);
+	spin_lock_init(&dev_entry->userptr_spinlock);
+	spin_lock_init(&dev_entry->ctx_mem_hash_spinlock);
+
+	dev_entry->root = debugfs_create_dir(dev_name(hdev->dev),
+						hl_debug_root);
+
+	debugfs_create_x64("addr",
+				0644,
+				dev_entry->root,
+				&dev_entry->addr);
+
+	debugfs_create_file("data32",
+				0644,
+				dev_entry->root,
+				dev_entry,
+				&hl_data32b_fops);
+
+	debugfs_create_file("data64",
+				0644,
+				dev_entry->root,
+				dev_entry,
+				&hl_data64b_fops);
+
+	debugfs_create_file("set_power_state",
+				0200,
+				dev_entry->root,
+				dev_entry,
+				&hl_power_fops);
+
+	debugfs_create_u8("i2c_bus",
+				0644,
+				dev_entry->root,
+				&dev_entry->i2c_bus);
+
+	debugfs_create_u8("i2c_addr",
+				0644,
+				dev_entry->root,
+				&dev_entry->i2c_addr);
+
+	debugfs_create_u8("i2c_reg",
+				0644,
+				dev_entry->root,
+				&dev_entry->i2c_reg);
+
+	debugfs_create_file("i2c_data",
+				0644,
+				dev_entry->root,
+				dev_entry,
+				&hl_i2c_data_fops);
+
+	debugfs_create_file("led0",
+				0200,
+				dev_entry->root,
+				dev_entry,
+				&hl_led0_fops);
+
+	debugfs_create_file("led1",
+				0200,
+				dev_entry->root,
+				dev_entry,
+				&hl_led1_fops);
+
+	debugfs_create_file("led2",
+				0200,
+				dev_entry->root,
+				dev_entry,
+				&hl_led2_fops);
+
+	debugfs_create_file("device",
+				0200,
+				dev_entry->root,
+				dev_entry,
+				&hl_device_fops);
+
+	debugfs_create_file("clk_gate",
+				0200,
+				dev_entry->root,
+				dev_entry,
+				&hl_clk_gate_fops);
+
+	debugfs_create_file("stop_on_err",
+				0644,
+				dev_entry->root,
+				dev_entry,
+				&hl_stop_on_err_fops);
+
+	for (i = 0, entry = dev_entry->entry_arr ; i < count ; i++, entry++) {
+
+		ent = debugfs_create_file(hl_debugfs_list[i].name,
+					0444,
+					dev_entry->root,
+					entry,
+					&hl_debugfs_fops);
+		entry->dent = ent;
+		entry->info_ent = &hl_debugfs_list[i];
+		entry->dev_entry = dev_entry;
+	}
+}
+
+void hl_debugfs_remove_device(struct hl_device *hdev)
+{
+	struct hl_dbg_device_entry *entry = &hdev->hl_debugfs;
+
+	debugfs_remove_recursive(entry->root);
+
+	mutex_destroy(&entry->file_mutex);
+	kfree(entry->entry_arr);
+}
+
+void hl_debugfs_add_file(struct hl_fpriv *hpriv)
+{
+	struct hl_dbg_device_entry *dev_entry = &hpriv->hdev->hl_debugfs;
+
+	mutex_lock(&dev_entry->file_mutex);
+	list_add(&hpriv->debugfs_list, &dev_entry->file_list);
+	mutex_unlock(&dev_entry->file_mutex);
+}
+
+void hl_debugfs_remove_file(struct hl_fpriv *hpriv)
+{
+	struct hl_dbg_device_entry *dev_entry = &hpriv->hdev->hl_debugfs;
+
+	mutex_lock(&dev_entry->file_mutex);
+	list_del(&hpriv->debugfs_list);
+	mutex_unlock(&dev_entry->file_mutex);
+}
+
+void hl_debugfs_add_cb(struct hl_cb *cb)
+{
+	struct hl_dbg_device_entry *dev_entry = &cb->hdev->hl_debugfs;
+
+	spin_lock(&dev_entry->cb_spinlock);
+	list_add(&cb->debugfs_list, &dev_entry->cb_list);
+	spin_unlock(&dev_entry->cb_spinlock);
+}
+
+void hl_debugfs_remove_cb(struct hl_cb *cb)
+{
+	struct hl_dbg_device_entry *dev_entry = &cb->hdev->hl_debugfs;
+
+	spin_lock(&dev_entry->cb_spinlock);
+	list_del(&cb->debugfs_list);
+	spin_unlock(&dev_entry->cb_spinlock);
+}
+
+void hl_debugfs_add_cs(struct hl_cs *cs)
+{
+	struct hl_dbg_device_entry *dev_entry = &cs->ctx->hdev->hl_debugfs;
+
+	spin_lock(&dev_entry->cs_spinlock);
+	list_add(&cs->debugfs_list, &dev_entry->cs_list);
+	spin_unlock(&dev_entry->cs_spinlock);
+}
+
+void hl_debugfs_remove_cs(struct hl_cs *cs)
+{
+	struct hl_dbg_device_entry *dev_entry = &cs->ctx->hdev->hl_debugfs;
+
+	spin_lock(&dev_entry->cs_spinlock);
+	list_del(&cs->debugfs_list);
+	spin_unlock(&dev_entry->cs_spinlock);
+}
+
+void hl_debugfs_add_job(struct hl_device *hdev, struct hl_cs_job *job)
+{
+	struct hl_dbg_device_entry *dev_entry = &hdev->hl_debugfs;
+
+	spin_lock(&dev_entry->cs_job_spinlock);
+	list_add(&job->debugfs_list, &dev_entry->cs_job_list);
+	spin_unlock(&dev_entry->cs_job_spinlock);
+}
+
+void hl_debugfs_remove_job(struct hl_device *hdev, struct hl_cs_job *job)
+{
+	struct hl_dbg_device_entry *dev_entry = &hdev->hl_debugfs;
+
+	spin_lock(&dev_entry->cs_job_spinlock);
+	list_del(&job->debugfs_list);
+	spin_unlock(&dev_entry->cs_job_spinlock);
+}
+
+void hl_debugfs_add_userptr(struct hl_device *hdev, struct hl_userptr *userptr)
+{
+	struct hl_dbg_device_entry *dev_entry = &hdev->hl_debugfs;
+
+	spin_lock(&dev_entry->userptr_spinlock);
+	list_add(&userptr->debugfs_list, &dev_entry->userptr_list);
+	spin_unlock(&dev_entry->userptr_spinlock);
+}
+
+void hl_debugfs_remove_userptr(struct hl_device *hdev,
+				struct hl_userptr *userptr)
+{
+	struct hl_dbg_device_entry *dev_entry = &hdev->hl_debugfs;
+
+	spin_lock(&dev_entry->userptr_spinlock);
+	list_del(&userptr->debugfs_list);
+	spin_unlock(&dev_entry->userptr_spinlock);
+}
+
+void hl_debugfs_add_ctx_mem_hash(struct hl_device *hdev, struct hl_ctx *ctx)
+{
+	struct hl_dbg_device_entry *dev_entry = &hdev->hl_debugfs;
+
+	spin_lock(&dev_entry->ctx_mem_hash_spinlock);
+	list_add(&ctx->debugfs_list, &dev_entry->ctx_mem_hash_list);
+	spin_unlock(&dev_entry->ctx_mem_hash_spinlock);
+}
+
+void hl_debugfs_remove_ctx_mem_hash(struct hl_device *hdev, struct hl_ctx *ctx)
+{
+	struct hl_dbg_device_entry *dev_entry = &hdev->hl_debugfs;
+
+	spin_lock(&dev_entry->ctx_mem_hash_spinlock);
+	list_del(&ctx->debugfs_list);
+	spin_unlock(&dev_entry->ctx_mem_hash_spinlock);
+}
+
+void __init hl_debugfs_init(void)
+{
+	hl_debug_root = debugfs_create_dir("habanalabs", NULL);
+}
+
+void hl_debugfs_fini(void)
+{
+	debugfs_remove_recursive(hl_debug_root);
+}
diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c
new file mode 100644
index 000000000000..84800efec10d
--- /dev/null
+++ b/drivers/misc/habanalabs/common/device.c
@@ -0,0 +1,1506 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2019 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#define pr_fmt(fmt)			"habanalabs: " fmt
+
+#include "habanalabs.h"
+
+#include <linux/pci.h>
+#include <linux/sched/signal.h>
+#include <linux/hwmon.h>
+#include <uapi/misc/habanalabs.h>
+
+#define HL_PLDM_PENDING_RESET_PER_SEC	(HL_PENDING_RESET_PER_SEC * 10)
+
+bool hl_device_disabled_or_in_reset(struct hl_device *hdev)
+{
+	if ((hdev->disabled) || (atomic_read(&hdev->in_reset)))
+		return true;
+	else
+		return false;
+}
+
+enum hl_device_status hl_device_status(struct hl_device *hdev)
+{
+	enum hl_device_status status;
+
+	if (hdev->disabled)
+		status = HL_DEVICE_STATUS_MALFUNCTION;
+	else if (atomic_read(&hdev->in_reset))
+		status = HL_DEVICE_STATUS_IN_RESET;
+	else
+		status = HL_DEVICE_STATUS_OPERATIONAL;
+
+	return status;
+}
+
+static void hpriv_release(struct kref *ref)
+{
+	struct hl_fpriv *hpriv;
+	struct hl_device *hdev;
+
+	hpriv = container_of(ref, struct hl_fpriv, refcount);
+
+	hdev = hpriv->hdev;
+
+	put_pid(hpriv->taskpid);
+
+	hl_debugfs_remove_file(hpriv);
+
+	mutex_destroy(&hpriv->restore_phase_mutex);
+
+	mutex_lock(&hdev->fpriv_list_lock);
+	list_del(&hpriv->dev_node);
+	hdev->compute_ctx = NULL;
+	mutex_unlock(&hdev->fpriv_list_lock);
+
+	kfree(hpriv);
+}
+
+void hl_hpriv_get(struct hl_fpriv *hpriv)
+{
+	kref_get(&hpriv->refcount);
+}
+
+void hl_hpriv_put(struct hl_fpriv *hpriv)
+{
+	kref_put(&hpriv->refcount, hpriv_release);
+}
+
+/*
+ * hl_device_release - release function for habanalabs device
+ *
+ * @inode: pointer to inode structure
+ * @filp: pointer to file structure
+ *
+ * Called when process closes an habanalabs device
+ */
+static int hl_device_release(struct inode *inode, struct file *filp)
+{
+	struct hl_fpriv *hpriv = filp->private_data;
+
+	hl_cb_mgr_fini(hpriv->hdev, &hpriv->cb_mgr);
+	hl_ctx_mgr_fini(hpriv->hdev, &hpriv->ctx_mgr);
+
+	filp->private_data = NULL;
+
+	hl_hpriv_put(hpriv);
+
+	return 0;
+}
+
+static int hl_device_release_ctrl(struct inode *inode, struct file *filp)
+{
+	struct hl_fpriv *hpriv = filp->private_data;
+	struct hl_device *hdev;
+
+	filp->private_data = NULL;
+
+	hdev = hpriv->hdev;
+
+	mutex_lock(&hdev->fpriv_list_lock);
+	list_del(&hpriv->dev_node);
+	mutex_unlock(&hdev->fpriv_list_lock);
+
+	kfree(hpriv);
+
+	return 0;
+}
+
+/*
+ * hl_mmap - mmap function for habanalabs device
+ *
+ * @*filp: pointer to file structure
+ * @*vma: pointer to vm_area_struct of the process
+ *
+ * Called when process does an mmap on habanalabs device. Call the device's mmap
+ * function at the end of the common code.
+ */
+static int hl_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct hl_fpriv *hpriv = filp->private_data;
+
+	if ((vma->vm_pgoff & HL_MMAP_CB_MASK) == HL_MMAP_CB_MASK) {
+		vma->vm_pgoff ^= HL_MMAP_CB_MASK;
+		return hl_cb_mmap(hpriv, vma);
+	}
+
+	return -EINVAL;
+}
+
+static const struct file_operations hl_ops = {
+	.owner = THIS_MODULE,
+	.open = hl_device_open,
+	.release = hl_device_release,
+	.mmap = hl_mmap,
+	.unlocked_ioctl = hl_ioctl,
+	.compat_ioctl = hl_ioctl
+};
+
+static const struct file_operations hl_ctrl_ops = {
+	.owner = THIS_MODULE,
+	.open = hl_device_open_ctrl,
+	.release = hl_device_release_ctrl,
+	.unlocked_ioctl = hl_ioctl_control,
+	.compat_ioctl = hl_ioctl_control
+};
+
+static void device_release_func(struct device *dev)
+{
+	kfree(dev);
+}
+
+/*
+ * device_init_cdev - Initialize cdev and device for habanalabs device
+ *
+ * @hdev: pointer to habanalabs device structure
+ * @hclass: pointer to the class object of the device
+ * @minor: minor number of the specific device
+ * @fpos: file operations to install for this device
+ * @name: name of the device as it will appear in the filesystem
+ * @cdev: pointer to the char device object that will be initialized
+ * @dev: pointer to the device object that will be initialized
+ *
+ * Initialize a cdev and a Linux device for habanalabs's device.
+ */
+static int device_init_cdev(struct hl_device *hdev, struct class *hclass,
+				int minor, const struct file_operations *fops,
+				char *name, struct cdev *cdev,
+				struct device **dev)
+{
+	cdev_init(cdev, fops);
+	cdev->owner = THIS_MODULE;
+
+	*dev = kzalloc(sizeof(**dev), GFP_KERNEL);
+	if (!*dev)
+		return -ENOMEM;
+
+	device_initialize(*dev);
+	(*dev)->devt = MKDEV(hdev->major, minor);
+	(*dev)->class = hclass;
+	(*dev)->release = device_release_func;
+	dev_set_drvdata(*dev, hdev);
+	dev_set_name(*dev, "%s", name);
+
+	return 0;
+}
+
+static int device_cdev_sysfs_add(struct hl_device *hdev)
+{
+	int rc;
+
+	rc = cdev_device_add(&hdev->cdev, hdev->dev);
+	if (rc) {
+		dev_err(hdev->dev,
+			"failed to add a char device to the system\n");
+		return rc;
+	}
+
+	rc = cdev_device_add(&hdev->cdev_ctrl, hdev->dev_ctrl);
+	if (rc) {
+		dev_err(hdev->dev,
+			"failed to add a control char device to the system\n");
+		goto delete_cdev_device;
+	}
+
+	/* hl_sysfs_init() must be done after adding the device to the system */
+	rc = hl_sysfs_init(hdev);
+	if (rc) {
+		dev_err(hdev->dev, "failed to initialize sysfs\n");
+		goto delete_ctrl_cdev_device;
+	}
+
+	hdev->cdev_sysfs_created = true;
+
+	return 0;
+
+delete_ctrl_cdev_device:
+	cdev_device_del(&hdev->cdev_ctrl, hdev->dev_ctrl);
+delete_cdev_device:
+	cdev_device_del(&hdev->cdev, hdev->dev);
+	return rc;
+}
+
+static void device_cdev_sysfs_del(struct hl_device *hdev)
+{
+	/* device_release() won't be called so must free devices explicitly */
+	if (!hdev->cdev_sysfs_created) {
+		kfree(hdev->dev_ctrl);
+		kfree(hdev->dev);
+		return;
+	}
+
+	hl_sysfs_fini(hdev);
+	cdev_device_del(&hdev->cdev_ctrl, hdev->dev_ctrl);
+	cdev_device_del(&hdev->cdev, hdev->dev);
+}
+
+/*
+ * device_early_init - do some early initialization for the habanalabs device
+ *
+ * @hdev: pointer to habanalabs device structure
+ *
+ * Install the relevant function pointers and call the early_init function,
+ * if such a function exists
+ */
+static int device_early_init(struct hl_device *hdev)
+{
+	int i, rc;
+	char workq_name[32];
+
+	switch (hdev->asic_type) {
+	case ASIC_GOYA:
+		goya_set_asic_funcs(hdev);
+		strlcpy(hdev->asic_name, "GOYA", sizeof(hdev->asic_name));
+		break;
+	case ASIC_GAUDI:
+		gaudi_set_asic_funcs(hdev);
+		sprintf(hdev->asic_name, "GAUDI");
+		break;
+	default:
+		dev_err(hdev->dev, "Unrecognized ASIC type %d\n",
+			hdev->asic_type);
+		return -EINVAL;
+	}
+
+	rc = hdev->asic_funcs->early_init(hdev);
+	if (rc)
+		return rc;
+
+	rc = hl_asid_init(hdev);
+	if (rc)
+		goto early_fini;
+
+	if (hdev->asic_prop.completion_queues_count) {
+		hdev->cq_wq = kcalloc(hdev->asic_prop.completion_queues_count,
+				sizeof(*hdev->cq_wq),
+				GFP_ATOMIC);
+		if (!hdev->cq_wq) {
+			rc = -ENOMEM;
+			goto asid_fini;
+		}
+	}
+
+	for (i = 0 ; i < hdev->asic_prop.completion_queues_count ; i++) {
+		snprintf(workq_name, 32, "hl-free-jobs-%u", i);
+		hdev->cq_wq[i] = create_singlethread_workqueue(workq_name);
+		if (hdev->cq_wq == NULL) {
+			dev_err(hdev->dev, "Failed to allocate CQ workqueue\n");
+			rc = -ENOMEM;
+			goto free_cq_wq;
+		}
+	}
+
+	hdev->eq_wq = alloc_workqueue("hl-events", WQ_UNBOUND, 0);
+	if (hdev->eq_wq == NULL) {
+		dev_err(hdev->dev, "Failed to allocate EQ workqueue\n");
+		rc = -ENOMEM;
+		goto free_cq_wq;
+	}
+
+	hdev->hl_chip_info = kzalloc(sizeof(struct hwmon_chip_info),
+					GFP_KERNEL);
+	if (!hdev->hl_chip_info) {
+		rc = -ENOMEM;
+		goto free_eq_wq;
+	}
+
+	hdev->idle_busy_ts_arr = kmalloc_array(HL_IDLE_BUSY_TS_ARR_SIZE,
+					sizeof(struct hl_device_idle_busy_ts),
+					(GFP_KERNEL | __GFP_ZERO));
+	if (!hdev->idle_busy_ts_arr) {
+		rc = -ENOMEM;
+		goto free_chip_info;
+	}
+
+	hl_cb_mgr_init(&hdev->kernel_cb_mgr);
+
+	mutex_init(&hdev->send_cpu_message_lock);
+	mutex_init(&hdev->debug_lock);
+	mutex_init(&hdev->mmu_cache_lock);
+	INIT_LIST_HEAD(&hdev->hw_queues_mirror_list);
+	spin_lock_init(&hdev->hw_queues_mirror_lock);
+	INIT_LIST_HEAD(&hdev->fpriv_list);
+	mutex_init(&hdev->fpriv_list_lock);
+	atomic_set(&hdev->in_reset, 0);
+
+	return 0;
+
+free_chip_info:
+	kfree(hdev->hl_chip_info);
+free_eq_wq:
+	destroy_workqueue(hdev->eq_wq);
+free_cq_wq:
+	for (i = 0 ; i < hdev->asic_prop.completion_queues_count ; i++)
+		if (hdev->cq_wq[i])
+			destroy_workqueue(hdev->cq_wq[i]);
+	kfree(hdev->cq_wq);
+asid_fini:
+	hl_asid_fini(hdev);
+early_fini:
+	if (hdev->asic_funcs->early_fini)
+		hdev->asic_funcs->early_fini(hdev);
+
+	return rc;
+}
+
+/*
+ * device_early_fini - finalize all that was done in device_early_init
+ *
+ * @hdev: pointer to habanalabs device structure
+ *
+ */
+static void device_early_fini(struct hl_device *hdev)
+{
+	int i;
+
+	mutex_destroy(&hdev->mmu_cache_lock);
+	mutex_destroy(&hdev->debug_lock);
+	mutex_destroy(&hdev->send_cpu_message_lock);
+
+	mutex_destroy(&hdev->fpriv_list_lock);
+
+	hl_cb_mgr_fini(hdev, &hdev->kernel_cb_mgr);
+
+	kfree(hdev->idle_busy_ts_arr);
+	kfree(hdev->hl_chip_info);
+
+	destroy_workqueue(hdev->eq_wq);
+
+	for (i = 0 ; i < hdev->asic_prop.completion_queues_count ; i++)
+		destroy_workqueue(hdev->cq_wq[i]);
+	kfree(hdev->cq_wq);
+
+	hl_asid_fini(hdev);
+
+	if (hdev->asic_funcs->early_fini)
+		hdev->asic_funcs->early_fini(hdev);
+}
+
+static void set_freq_to_low_job(struct work_struct *work)
+{
+	struct hl_device *hdev = container_of(work, struct hl_device,
+						work_freq.work);
+
+	mutex_lock(&hdev->fpriv_list_lock);
+
+	if (!hdev->compute_ctx)
+		hl_device_set_frequency(hdev, PLL_LOW);
+
+	mutex_unlock(&hdev->fpriv_list_lock);
+
+	schedule_delayed_work(&hdev->work_freq,
+			usecs_to_jiffies(HL_PLL_LOW_JOB_FREQ_USEC));
+}
+
+static void hl_device_heartbeat(struct work_struct *work)
+{
+	struct hl_device *hdev = container_of(work, struct hl_device,
+						work_heartbeat.work);
+
+	if (hl_device_disabled_or_in_reset(hdev))
+		goto reschedule;
+
+	if (!hdev->asic_funcs->send_heartbeat(hdev))
+		goto reschedule;
+
+	dev_err(hdev->dev, "Device heartbeat failed!\n");
+	hl_device_reset(hdev, true, false);
+
+	return;
+
+reschedule:
+	schedule_delayed_work(&hdev->work_heartbeat,
+			usecs_to_jiffies(HL_HEARTBEAT_PER_USEC));
+}
+
+/*
+ * device_late_init - do late stuff initialization for the habanalabs device
+ *
+ * @hdev: pointer to habanalabs device structure
+ *
+ * Do stuff that either needs the device H/W queues to be active or needs
+ * to happen after all the rest of the initialization is finished
+ */
+static int device_late_init(struct hl_device *hdev)
+{
+	int rc;
+
+	if (hdev->asic_funcs->late_init) {
+		rc = hdev->asic_funcs->late_init(hdev);
+		if (rc) {
+			dev_err(hdev->dev,
+				"failed late initialization for the H/W\n");
+			return rc;
+		}
+	}
+
+	hdev->high_pll = hdev->asic_prop.high_pll;
+
+	/* force setting to low frequency */
+	hdev->curr_pll_profile = PLL_LOW;
+
+	if (hdev->pm_mng_profile == PM_AUTO)
+		hdev->asic_funcs->set_pll_profile(hdev, PLL_LOW);
+	else
+		hdev->asic_funcs->set_pll_profile(hdev, PLL_LAST);
+
+	INIT_DELAYED_WORK(&hdev->work_freq, set_freq_to_low_job);
+	schedule_delayed_work(&hdev->work_freq,
+	usecs_to_jiffies(HL_PLL_LOW_JOB_FREQ_USEC));
+
+	if (hdev->heartbeat) {
+		INIT_DELAYED_WORK(&hdev->work_heartbeat, hl_device_heartbeat);
+		schedule_delayed_work(&hdev->work_heartbeat,
+				usecs_to_jiffies(HL_HEARTBEAT_PER_USEC));
+	}
+
+	hdev->late_init_done = true;
+
+	return 0;
+}
+
+/*
+ * device_late_fini - finalize all that was done in device_late_init
+ *
+ * @hdev: pointer to habanalabs device structure
+ *
+ */
+static void device_late_fini(struct hl_device *hdev)
+{
+	if (!hdev->late_init_done)
+		return;
+
+	cancel_delayed_work_sync(&hdev->work_freq);
+	if (hdev->heartbeat)
+		cancel_delayed_work_sync(&hdev->work_heartbeat);
+
+	if (hdev->asic_funcs->late_fini)
+		hdev->asic_funcs->late_fini(hdev);
+
+	hdev->late_init_done = false;
+}
+
+uint32_t hl_device_utilization(struct hl_device *hdev, uint32_t period_ms)
+{
+	struct hl_device_idle_busy_ts *ts;
+	ktime_t zero_ktime, curr = ktime_get();
+	u32 overlap_cnt = 0, last_index = hdev->idle_busy_ts_idx;
+	s64 period_us, last_start_us, last_end_us, last_busy_time_us,
+		total_busy_time_us = 0, total_busy_time_ms;
+
+	zero_ktime = ktime_set(0, 0);
+	period_us = period_ms * USEC_PER_MSEC;
+	ts = &hdev->idle_busy_ts_arr[last_index];
+
+	/* check case that device is currently in idle */
+	if (!ktime_compare(ts->busy_to_idle_ts, zero_ktime) &&
+			!ktime_compare(ts->idle_to_busy_ts, zero_ktime)) {
+
+		last_index--;
+		/* Handle case idle_busy_ts_idx was 0 */
+		if (last_index > HL_IDLE_BUSY_TS_ARR_SIZE)
+			last_index = HL_IDLE_BUSY_TS_ARR_SIZE - 1;
+
+		ts = &hdev->idle_busy_ts_arr[last_index];
+	}
+
+	while (overlap_cnt < HL_IDLE_BUSY_TS_ARR_SIZE) {
+		/* Check if we are in last sample case. i.e. if the sample
+		 * begun before the sampling period. This could be a real
+		 * sample or 0 so need to handle both cases
+		 */
+		last_start_us = ktime_to_us(
+				ktime_sub(curr, ts->idle_to_busy_ts));
+
+		if (last_start_us > period_us) {
+
+			/* First check two cases:
+			 * 1. If the device is currently busy
+			 * 2. If the device was idle during the whole sampling
+			 *    period
+			 */
+
+			if (!ktime_compare(ts->busy_to_idle_ts, zero_ktime)) {
+				/* Check if the device is currently busy */
+				if (ktime_compare(ts->idle_to_busy_ts,
+						zero_ktime))
+					return 100;
+
+				/* We either didn't have any activity or we
+				 * reached an entry which is 0. Either way,
+				 * exit and return what was accumulated so far
+				 */
+				break;
+			}
+
+			/* If sample has finished, check it is relevant */
+			last_end_us = ktime_to_us(
+					ktime_sub(curr, ts->busy_to_idle_ts));
+
+			if (last_end_us > period_us)
+				break;
+
+			/* It is relevant so add it but with adjustment */
+			last_busy_time_us = ktime_to_us(
+						ktime_sub(ts->busy_to_idle_ts,
+						ts->idle_to_busy_ts));
+			total_busy_time_us += last_busy_time_us -
+					(last_start_us - period_us);
+			break;
+		}
+
+		/* Check if the sample is finished or still open */
+		if (ktime_compare(ts->busy_to_idle_ts, zero_ktime))
+			last_busy_time_us = ktime_to_us(
+						ktime_sub(ts->busy_to_idle_ts,
+						ts->idle_to_busy_ts));
+		else
+			last_busy_time_us = ktime_to_us(
+					ktime_sub(curr, ts->idle_to_busy_ts));
+
+		total_busy_time_us += last_busy_time_us;
+
+		last_index--;
+		/* Handle case idle_busy_ts_idx was 0 */
+		if (last_index > HL_IDLE_BUSY_TS_ARR_SIZE)
+			last_index = HL_IDLE_BUSY_TS_ARR_SIZE - 1;
+
+		ts = &hdev->idle_busy_ts_arr[last_index];
+
+		overlap_cnt++;
+	}
+
+	total_busy_time_ms = DIV_ROUND_UP_ULL(total_busy_time_us,
+						USEC_PER_MSEC);
+
+	return DIV_ROUND_UP_ULL(total_busy_time_ms * 100, period_ms);
+}
+
+/*
+ * hl_device_set_frequency - set the frequency of the device
+ *
+ * @hdev: pointer to habanalabs device structure
+ * @freq: the new frequency value
+ *
+ * Change the frequency if needed. This function has no protection against
+ * concurrency, therefore it is assumed that the calling function has protected
+ * itself against the case of calling this function from multiple threads with
+ * different values
+ *
+ * Returns 0 if no change was done, otherwise returns 1
+ */
+int hl_device_set_frequency(struct hl_device *hdev, enum hl_pll_frequency freq)
+{
+	if ((hdev->pm_mng_profile == PM_MANUAL) ||
+			(hdev->curr_pll_profile == freq))
+		return 0;
+
+	dev_dbg(hdev->dev, "Changing device frequency to %s\n",
+		freq == PLL_HIGH ? "high" : "low");
+
+	hdev->asic_funcs->set_pll_profile(hdev, freq);
+
+	hdev->curr_pll_profile = freq;
+
+	return 1;
+}
+
+int hl_device_set_debug_mode(struct hl_device *hdev, bool enable)
+{
+	int rc = 0;
+
+	mutex_lock(&hdev->debug_lock);
+
+	if (!enable) {
+		if (!hdev->in_debug) {
+			dev_err(hdev->dev,
+				"Failed to disable debug mode because device was not in debug mode\n");
+			rc = -EFAULT;
+			goto out;
+		}
+
+		if (!hdev->hard_reset_pending)
+			hdev->asic_funcs->halt_coresight(hdev);
+
+		hdev->in_debug = 0;
+
+		if (!hdev->hard_reset_pending)
+			hdev->asic_funcs->enable_clock_gating(hdev);
+
+		goto out;
+	}
+
+	if (hdev->in_debug) {
+		dev_err(hdev->dev,
+			"Failed to enable debug mode because device is already in debug mode\n");
+		rc = -EFAULT;
+		goto out;
+	}
+
+	hdev->asic_funcs->disable_clock_gating(hdev);
+	hdev->in_debug = 1;
+
+out:
+	mutex_unlock(&hdev->debug_lock);
+
+	return rc;
+}
+
+/*
+ * hl_device_suspend - initiate device suspend
+ *
+ * @hdev: pointer to habanalabs device structure
+ *
+ * Puts the hw in the suspend state (all asics).
+ * Returns 0 for success or an error on failure.
+ * Called at driver suspend.
+ */
+int hl_device_suspend(struct hl_device *hdev)
+{
+	int rc;
+
+	pci_save_state(hdev->pdev);
+
+	/* Block future CS/VM/JOB completion operations */
+	rc = atomic_cmpxchg(&hdev->in_reset, 0, 1);
+	if (rc) {
+		dev_err(hdev->dev, "Can't suspend while in reset\n");
+		return -EIO;
+	}
+
+	/* This blocks all other stuff that is not blocked by in_reset */
+	hdev->disabled = true;
+
+	/*
+	 * Flush anyone that is inside the critical section of enqueue
+	 * jobs to the H/W
+	 */
+	hdev->asic_funcs->hw_queues_lock(hdev);
+	hdev->asic_funcs->hw_queues_unlock(hdev);
+
+	/* Flush processes that are sending message to CPU */
+	mutex_lock(&hdev->send_cpu_message_lock);
+	mutex_unlock(&hdev->send_cpu_message_lock);
+
+	rc = hdev->asic_funcs->suspend(hdev);
+	if (rc)
+		dev_err(hdev->dev,
+			"Failed to disable PCI access of device CPU\n");
+
+	/* Shut down the device */
+	pci_disable_device(hdev->pdev);
+	pci_set_power_state(hdev->pdev, PCI_D3hot);
+
+	return 0;
+}
+
+/*
+ * hl_device_resume - initiate device resume
+ *
+ * @hdev: pointer to habanalabs device structure
+ *
+ * Bring the hw back to operating state (all asics).
+ * Returns 0 for success or an error on failure.
+ * Called at driver resume.
+ */
+int hl_device_resume(struct hl_device *hdev)
+{
+	int rc;
+
+	pci_set_power_state(hdev->pdev, PCI_D0);
+	pci_restore_state(hdev->pdev);
+	rc = pci_enable_device_mem(hdev->pdev);
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to enable PCI device in resume\n");
+		return rc;
+	}
+
+	pci_set_master(hdev->pdev);
+
+	rc = hdev->asic_funcs->resume(hdev);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to resume device after suspend\n");
+		goto disable_device;
+	}
+
+
+	hdev->disabled = false;
+	atomic_set(&hdev->in_reset, 0);
+
+	rc = hl_device_reset(hdev, true, false);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to reset device during resume\n");
+		goto disable_device;
+	}
+
+	return 0;
+
+disable_device:
+	pci_clear_master(hdev->pdev);
+	pci_disable_device(hdev->pdev);
+
+	return rc;
+}
+
+static int device_kill_open_processes(struct hl_device *hdev)
+{
+	u16 pending_total, pending_cnt;
+	struct hl_fpriv	*hpriv;
+	struct task_struct *task = NULL;
+
+	if (hdev->pldm)
+		pending_total = HL_PLDM_PENDING_RESET_PER_SEC;
+	else
+		pending_total = HL_PENDING_RESET_PER_SEC;
+
+	/* Giving time for user to close FD, and for processes that are inside
+	 * hl_device_open to finish
+	 */
+	if (!list_empty(&hdev->fpriv_list))
+		ssleep(1);
+
+	mutex_lock(&hdev->fpriv_list_lock);
+
+	/* This section must be protected because we are dereferencing
+	 * pointers that are freed if the process exits
+	 */
+	list_for_each_entry(hpriv, &hdev->fpriv_list, dev_node) {
+		task = get_pid_task(hpriv->taskpid, PIDTYPE_PID);
+		if (task) {
+			dev_info(hdev->dev, "Killing user process pid=%d\n",
+				task_pid_nr(task));
+			send_sig(SIGKILL, task, 1);
+			usleep_range(1000, 10000);
+
+			put_task_struct(task);
+		}
+	}
+
+	mutex_unlock(&hdev->fpriv_list_lock);
+
+	/* We killed the open users, but because the driver cleans up after the
+	 * user contexts are closed (e.g. mmu mappings), we need to wait again
+	 * to make sure the cleaning phase is finished before continuing with
+	 * the reset
+	 */
+
+	pending_cnt = pending_total;
+
+	while ((!list_empty(&hdev->fpriv_list)) && (pending_cnt)) {
+		dev_info(hdev->dev,
+			"Waiting for all unmap operations to finish before hard reset\n");
+
+		pending_cnt--;
+
+		ssleep(1);
+	}
+
+	return list_empty(&hdev->fpriv_list) ? 0 : -EBUSY;
+}
+
+static void device_hard_reset_pending(struct work_struct *work)
+{
+	struct hl_device_reset_work *device_reset_work =
+		container_of(work, struct hl_device_reset_work, reset_work);
+	struct hl_device *hdev = device_reset_work->hdev;
+
+	hl_device_reset(hdev, true, true);
+
+	kfree(device_reset_work);
+}
+
+/*
+ * hl_device_reset - reset the device
+ *
+ * @hdev: pointer to habanalabs device structure
+ * @hard_reset: should we do hard reset to all engines or just reset the
+ *              compute/dma engines
+ * @from_hard_reset_thread: is the caller the hard-reset thread
+ *
+ * Block future CS and wait for pending CS to be enqueued
+ * Call ASIC H/W fini
+ * Flush all completions
+ * Re-initialize all internal data structures
+ * Call ASIC H/W init, late_init
+ * Test queues
+ * Enable device
+ *
+ * Returns 0 for success or an error on failure.
+ */
+int hl_device_reset(struct hl_device *hdev, bool hard_reset,
+			bool from_hard_reset_thread)
+{
+	int i, rc;
+
+	if (!hdev->init_done) {
+		dev_err(hdev->dev,
+			"Can't reset before initialization is done\n");
+		return 0;
+	}
+
+	if ((!hard_reset) && (!hdev->supports_soft_reset)) {
+		dev_dbg(hdev->dev, "Doing hard-reset instead of soft-reset\n");
+		hard_reset = true;
+	}
+
+	/*
+	 * Prevent concurrency in this function - only one reset should be
+	 * done at any given time. Only need to perform this if we didn't
+	 * get from the dedicated hard reset thread
+	 */
+	if (!from_hard_reset_thread) {
+		/* Block future CS/VM/JOB completion operations */
+		rc = atomic_cmpxchg(&hdev->in_reset, 0, 1);
+		if (rc)
+			return 0;
+
+		if (hard_reset) {
+			/* Disable PCI access from device F/W so he won't send
+			 * us additional interrupts. We disable MSI/MSI-X at
+			 * the halt_engines function and we can't have the F/W
+			 * sending us interrupts after that. We need to disable
+			 * the access here because if the device is marked
+			 * disable, the message won't be send. Also, in case
+			 * of heartbeat, the device CPU is marked as disable
+			 * so this message won't be sent
+			 */
+			if (hl_fw_send_pci_access_msg(hdev,
+					ARMCP_PACKET_DISABLE_PCI_ACCESS))
+				dev_warn(hdev->dev,
+					"Failed to disable PCI access by F/W\n");
+		}
+
+		/* This also blocks future CS/VM/JOB completion operations */
+		hdev->disabled = true;
+
+		/* Flush anyone that is inside the critical section of enqueue
+		 * jobs to the H/W
+		 */
+		hdev->asic_funcs->hw_queues_lock(hdev);
+		hdev->asic_funcs->hw_queues_unlock(hdev);
+
+		/* Flush anyone that is inside device open */
+		mutex_lock(&hdev->fpriv_list_lock);
+		mutex_unlock(&hdev->fpriv_list_lock);
+
+		dev_err(hdev->dev, "Going to RESET device!\n");
+	}
+
+again:
+	if ((hard_reset) && (!from_hard_reset_thread)) {
+		struct hl_device_reset_work *device_reset_work;
+
+		hdev->hard_reset_pending = true;
+
+		device_reset_work = kzalloc(sizeof(*device_reset_work),
+						GFP_ATOMIC);
+		if (!device_reset_work) {
+			rc = -ENOMEM;
+			goto out_err;
+		}
+
+		/*
+		 * Because the reset function can't run from interrupt or
+		 * from heartbeat work, we need to call the reset function
+		 * from a dedicated work
+		 */
+		INIT_WORK(&device_reset_work->reset_work,
+				device_hard_reset_pending);
+		device_reset_work->hdev = hdev;
+		schedule_work(&device_reset_work->reset_work);
+
+		return 0;
+	}
+
+	if (hard_reset) {
+		device_late_fini(hdev);
+
+		/*
+		 * Now that the heartbeat thread is closed, flush processes
+		 * which are sending messages to CPU
+		 */
+		mutex_lock(&hdev->send_cpu_message_lock);
+		mutex_unlock(&hdev->send_cpu_message_lock);
+	}
+
+	/*
+	 * Halt the engines and disable interrupts so we won't get any more
+	 * completions from H/W and we won't have any accesses from the
+	 * H/W to the host machine
+	 */
+	hdev->asic_funcs->halt_engines(hdev, hard_reset);
+
+	/* Go over all the queues, release all CS and their jobs */
+	hl_cs_rollback_all(hdev);
+
+	if (hard_reset) {
+		/* Kill processes here after CS rollback. This is because the
+		 * process can't really exit until all its CSs are done, which
+		 * is what we do in cs rollback
+		 */
+		rc = device_kill_open_processes(hdev);
+		if (rc) {
+			dev_crit(hdev->dev,
+				"Failed to kill all open processes, stopping hard reset\n");
+			goto out_err;
+		}
+
+		/* Flush the Event queue workers to make sure no other thread is
+		 * reading or writing to registers during the reset
+		 */
+		flush_workqueue(hdev->eq_wq);
+	}
+
+	/* Release kernel context */
+	if ((hard_reset) && (hl_ctx_put(hdev->kernel_ctx) == 1))
+		hdev->kernel_ctx = NULL;
+
+	/* Reset the H/W. It will be in idle state after this returns */
+	hdev->asic_funcs->hw_fini(hdev, hard_reset);
+
+	if (hard_reset) {
+		hl_vm_fini(hdev);
+		hl_mmu_fini(hdev);
+		hl_eq_reset(hdev, &hdev->event_queue);
+	}
+
+	/* Re-initialize PI,CI to 0 in all queues (hw queue, cq) */
+	hl_hw_queue_reset(hdev, hard_reset);
+	for (i = 0 ; i < hdev->asic_prop.completion_queues_count ; i++)
+		hl_cq_reset(hdev, &hdev->completion_queue[i]);
+
+	hdev->idle_busy_ts_idx = 0;
+	hdev->idle_busy_ts_arr[0].busy_to_idle_ts = ktime_set(0, 0);
+	hdev->idle_busy_ts_arr[0].idle_to_busy_ts = ktime_set(0, 0);
+
+	if (hdev->cs_active_cnt)
+		dev_crit(hdev->dev, "CS active cnt %d is not 0 during reset\n",
+			hdev->cs_active_cnt);
+
+	mutex_lock(&hdev->fpriv_list_lock);
+
+	/* Make sure the context switch phase will run again */
+	if (hdev->compute_ctx) {
+		atomic_set(&hdev->compute_ctx->thread_ctx_switch_token, 1);
+		hdev->compute_ctx->thread_ctx_switch_wait_token = 0;
+	}
+
+	mutex_unlock(&hdev->fpriv_list_lock);
+
+	/* Finished tear-down, starting to re-initialize */
+
+	if (hard_reset) {
+		hdev->device_cpu_disabled = false;
+		hdev->hard_reset_pending = false;
+
+		if (hdev->kernel_ctx) {
+			dev_crit(hdev->dev,
+				"kernel ctx was alive during hard reset, something is terribly wrong\n");
+			rc = -EBUSY;
+			goto out_err;
+		}
+
+		rc = hl_mmu_init(hdev);
+		if (rc) {
+			dev_err(hdev->dev,
+				"Failed to initialize MMU S/W after hard reset\n");
+			goto out_err;
+		}
+
+		/* Allocate the kernel context */
+		hdev->kernel_ctx = kzalloc(sizeof(*hdev->kernel_ctx),
+						GFP_KERNEL);
+		if (!hdev->kernel_ctx) {
+			rc = -ENOMEM;
+			goto out_err;
+		}
+
+		hdev->compute_ctx = NULL;
+
+		rc = hl_ctx_init(hdev, hdev->kernel_ctx, true);
+		if (rc) {
+			dev_err(hdev->dev,
+				"failed to init kernel ctx in hard reset\n");
+			kfree(hdev->kernel_ctx);
+			hdev->kernel_ctx = NULL;
+			goto out_err;
+		}
+	}
+
+	rc = hdev->asic_funcs->hw_init(hdev);
+	if (rc) {
+		dev_err(hdev->dev,
+			"failed to initialize the H/W after reset\n");
+		goto out_err;
+	}
+
+	hdev->disabled = false;
+
+	/* Check that the communication with the device is working */
+	rc = hdev->asic_funcs->test_queues(hdev);
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to detect if device is alive after reset\n");
+		goto out_err;
+	}
+
+	if (hard_reset) {
+		rc = device_late_init(hdev);
+		if (rc) {
+			dev_err(hdev->dev,
+				"Failed late init after hard reset\n");
+			goto out_err;
+		}
+
+		rc = hl_vm_init(hdev);
+		if (rc) {
+			dev_err(hdev->dev,
+				"Failed to init memory module after hard reset\n");
+			goto out_err;
+		}
+
+		hl_set_max_power(hdev, hdev->max_power);
+	} else {
+		rc = hdev->asic_funcs->soft_reset_late_init(hdev);
+		if (rc) {
+			dev_err(hdev->dev,
+				"Failed late init after soft reset\n");
+			goto out_err;
+		}
+	}
+
+	atomic_set(&hdev->in_reset, 0);
+
+	if (hard_reset)
+		hdev->hard_reset_cnt++;
+	else
+		hdev->soft_reset_cnt++;
+
+	dev_warn(hdev->dev, "Successfully finished resetting the device\n");
+
+	return 0;
+
+out_err:
+	hdev->disabled = true;
+
+	if (hard_reset) {
+		dev_err(hdev->dev,
+			"Failed to reset! Device is NOT usable\n");
+		hdev->hard_reset_cnt++;
+	} else {
+		dev_err(hdev->dev,
+			"Failed to do soft-reset, trying hard reset\n");
+		hdev->soft_reset_cnt++;
+		hard_reset = true;
+		goto again;
+	}
+
+	atomic_set(&hdev->in_reset, 0);
+
+	return rc;
+}
+
+/*
+ * hl_device_init - main initialization function for habanalabs device
+ *
+ * @hdev: pointer to habanalabs device structure
+ *
+ * Allocate an id for the device, do early initialization and then call the
+ * ASIC specific initialization functions. Finally, create the cdev and the
+ * Linux device to expose it to the user
+ */
+int hl_device_init(struct hl_device *hdev, struct class *hclass)
+{
+	int i, rc, cq_cnt, cq_ready_cnt;
+	char *name;
+	bool add_cdev_sysfs_on_err = false;
+
+	name = kasprintf(GFP_KERNEL, "hl%d", hdev->id / 2);
+	if (!name) {
+		rc = -ENOMEM;
+		goto out_disabled;
+	}
+
+	/* Initialize cdev and device structures */
+	rc = device_init_cdev(hdev, hclass, hdev->id, &hl_ops, name,
+				&hdev->cdev, &hdev->dev);
+
+	kfree(name);
+
+	if (rc)
+		goto out_disabled;
+
+	name = kasprintf(GFP_KERNEL, "hl_controlD%d", hdev->id / 2);
+	if (!name) {
+		rc = -ENOMEM;
+		goto free_dev;
+	}
+
+	/* Initialize cdev and device structures for control device */
+	rc = device_init_cdev(hdev, hclass, hdev->id_control, &hl_ctrl_ops,
+				name, &hdev->cdev_ctrl, &hdev->dev_ctrl);
+
+	kfree(name);
+
+	if (rc)
+		goto free_dev;
+
+	/* Initialize ASIC function pointers and perform early init */
+	rc = device_early_init(hdev);
+	if (rc)
+		goto free_dev_ctrl;
+
+	/*
+	 * Start calling ASIC initialization. First S/W then H/W and finally
+	 * late init
+	 */
+	rc = hdev->asic_funcs->sw_init(hdev);
+	if (rc)
+		goto early_fini;
+
+	/*
+	 * Initialize the H/W queues. Must be done before hw_init, because
+	 * there the addresses of the kernel queue are being written to the
+	 * registers of the device
+	 */
+	rc = hl_hw_queues_create(hdev);
+	if (rc) {
+		dev_err(hdev->dev, "failed to initialize kernel queues\n");
+		goto sw_fini;
+	}
+
+	cq_cnt = hdev->asic_prop.completion_queues_count;
+
+	/*
+	 * Initialize the completion queues. Must be done before hw_init,
+	 * because there the addresses of the completion queues are being
+	 * passed as arguments to request_irq
+	 */
+	if (cq_cnt) {
+		hdev->completion_queue = kcalloc(cq_cnt,
+				sizeof(*hdev->completion_queue),
+				GFP_KERNEL);
+
+		if (!hdev->completion_queue) {
+			dev_err(hdev->dev,
+				"failed to allocate completion queues\n");
+			rc = -ENOMEM;
+			goto hw_queues_destroy;
+		}
+	}
+
+	for (i = 0, cq_ready_cnt = 0 ; i < cq_cnt ; i++, cq_ready_cnt++) {
+		rc = hl_cq_init(hdev, &hdev->completion_queue[i],
+				hdev->asic_funcs->get_queue_id_for_cq(hdev, i));
+		if (rc) {
+			dev_err(hdev->dev,
+				"failed to initialize completion queue\n");
+			goto cq_fini;
+		}
+		hdev->completion_queue[i].cq_idx = i;
+	}
+
+	/*
+	 * Initialize the event queue. Must be done before hw_init,
+	 * because there the address of the event queue is being
+	 * passed as argument to request_irq
+	 */
+	rc = hl_eq_init(hdev, &hdev->event_queue);
+	if (rc) {
+		dev_err(hdev->dev, "failed to initialize event queue\n");
+		goto cq_fini;
+	}
+
+	/* MMU S/W must be initialized before kernel context is created */
+	rc = hl_mmu_init(hdev);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to initialize MMU S/W structures\n");
+		goto eq_fini;
+	}
+
+	/* Allocate the kernel context */
+	hdev->kernel_ctx = kzalloc(sizeof(*hdev->kernel_ctx), GFP_KERNEL);
+	if (!hdev->kernel_ctx) {
+		rc = -ENOMEM;
+		goto mmu_fini;
+	}
+
+	hdev->compute_ctx = NULL;
+
+	rc = hl_ctx_init(hdev, hdev->kernel_ctx, true);
+	if (rc) {
+		dev_err(hdev->dev, "failed to initialize kernel context\n");
+		kfree(hdev->kernel_ctx);
+		goto mmu_fini;
+	}
+
+	rc = hl_cb_pool_init(hdev);
+	if (rc) {
+		dev_err(hdev->dev, "failed to initialize CB pool\n");
+		goto release_ctx;
+	}
+
+	hl_debugfs_add_device(hdev);
+
+	if (hdev->asic_funcs->get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) {
+		dev_info(hdev->dev,
+			"H/W state is dirty, must reset before initializing\n");
+		hdev->asic_funcs->halt_engines(hdev, true);
+		hdev->asic_funcs->hw_fini(hdev, true);
+	}
+
+	/*
+	 * From this point, in case of an error, add char devices and create
+	 * sysfs nodes as part of the error flow, to allow debugging.
+	 */
+	add_cdev_sysfs_on_err = true;
+
+	rc = hdev->asic_funcs->hw_init(hdev);
+	if (rc) {
+		dev_err(hdev->dev, "failed to initialize the H/W\n");
+		rc = 0;
+		goto out_disabled;
+	}
+
+	hdev->disabled = false;
+
+	/* Check that the communication with the device is working */
+	rc = hdev->asic_funcs->test_queues(hdev);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to detect if device is alive\n");
+		rc = 0;
+		goto out_disabled;
+	}
+
+	rc = device_late_init(hdev);
+	if (rc) {
+		dev_err(hdev->dev, "Failed late initialization\n");
+		rc = 0;
+		goto out_disabled;
+	}
+
+	dev_info(hdev->dev, "Found %s device with %lluGB DRAM\n",
+		hdev->asic_name,
+		hdev->asic_prop.dram_size / 1024 / 1024 / 1024);
+
+	rc = hl_vm_init(hdev);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to initialize memory module\n");
+		rc = 0;
+		goto out_disabled;
+	}
+
+	/*
+	 * Expose devices and sysfs nodes to user.
+	 * From here there is no need to add char devices and create sysfs nodes
+	 * in case of an error.
+	 */
+	add_cdev_sysfs_on_err = false;
+	rc = device_cdev_sysfs_add(hdev);
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to add char devices and sysfs nodes\n");
+		rc = 0;
+		goto out_disabled;
+	}
+
+	/*
+	 * hl_hwmon_init() must be called after device_late_init(), because only
+	 * there we get the information from the device about which
+	 * hwmon-related sensors the device supports.
+	 * Furthermore, it must be done after adding the device to the system.
+	 */
+	rc = hl_hwmon_init(hdev);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to initialize hwmon\n");
+		rc = 0;
+		goto out_disabled;
+	}
+
+	dev_notice(hdev->dev,
+		"Successfully added device to habanalabs driver\n");
+
+	hdev->init_done = true;
+
+	return 0;
+
+release_ctx:
+	if (hl_ctx_put(hdev->kernel_ctx) != 1)
+		dev_err(hdev->dev,
+			"kernel ctx is still alive on initialization failure\n");
+mmu_fini:
+	hl_mmu_fini(hdev);
+eq_fini:
+	hl_eq_fini(hdev, &hdev->event_queue);
+cq_fini:
+	for (i = 0 ; i < cq_ready_cnt ; i++)
+		hl_cq_fini(hdev, &hdev->completion_queue[i]);
+	kfree(hdev->completion_queue);
+hw_queues_destroy:
+	hl_hw_queues_destroy(hdev);
+sw_fini:
+	hdev->asic_funcs->sw_fini(hdev);
+early_fini:
+	device_early_fini(hdev);
+free_dev_ctrl:
+	kfree(hdev->dev_ctrl);
+free_dev:
+	kfree(hdev->dev);
+out_disabled:
+	hdev->disabled = true;
+	if (add_cdev_sysfs_on_err)
+		device_cdev_sysfs_add(hdev);
+	if (hdev->pdev)
+		dev_err(&hdev->pdev->dev,
+			"Failed to initialize hl%d. Device is NOT usable !\n",
+			hdev->id / 2);
+	else
+		pr_err("Failed to initialize hl%d. Device is NOT usable !\n",
+			hdev->id / 2);
+
+	return rc;
+}
+
+/*
+ * hl_device_fini - main tear-down function for habanalabs device
+ *
+ * @hdev: pointer to habanalabs device structure
+ *
+ * Destroy the device, call ASIC fini functions and release the id
+ */
+void hl_device_fini(struct hl_device *hdev)
+{
+	int i, rc;
+	ktime_t timeout;
+
+	dev_info(hdev->dev, "Removing device\n");
+
+	/*
+	 * This function is competing with the reset function, so try to
+	 * take the reset atomic and if we are already in middle of reset,
+	 * wait until reset function is finished. Reset function is designed
+	 * to always finish. However, in Gaudi, because of all the network
+	 * ports, the hard reset could take between 10-30 seconds
+	 */
+
+	timeout = ktime_add_us(ktime_get(),
+				HL_HARD_RESET_MAX_TIMEOUT * 1000 * 1000);
+	rc = atomic_cmpxchg(&hdev->in_reset, 0, 1);
+	while (rc) {
+		usleep_range(50, 200);
+		rc = atomic_cmpxchg(&hdev->in_reset, 0, 1);
+		if (ktime_compare(ktime_get(), timeout) > 0) {
+			WARN(1, "Failed to remove device because reset function did not finish\n");
+			return;
+		}
+	}
+
+	/* Mark device as disabled */
+	hdev->disabled = true;
+
+	/* Flush anyone that is inside the critical section of enqueue
+	 * jobs to the H/W
+	 */
+	hdev->asic_funcs->hw_queues_lock(hdev);
+	hdev->asic_funcs->hw_queues_unlock(hdev);
+
+	/* Flush anyone that is inside device open */
+	mutex_lock(&hdev->fpriv_list_lock);
+	mutex_unlock(&hdev->fpriv_list_lock);
+
+	hdev->hard_reset_pending = true;
+
+	hl_hwmon_fini(hdev);
+
+	device_late_fini(hdev);
+
+	hl_debugfs_remove_device(hdev);
+
+	/*
+	 * Halt the engines and disable interrupts so we won't get any more
+	 * completions from H/W and we won't have any accesses from the
+	 * H/W to the host machine
+	 */
+	hdev->asic_funcs->halt_engines(hdev, true);
+
+	/* Go over all the queues, release all CS and their jobs */
+	hl_cs_rollback_all(hdev);
+
+	/* Kill processes here after CS rollback. This is because the process
+	 * can't really exit until all its CSs are done, which is what we
+	 * do in cs rollback
+	 */
+	rc = device_kill_open_processes(hdev);
+	if (rc)
+		dev_crit(hdev->dev, "Failed to kill all open processes\n");
+
+	hl_cb_pool_fini(hdev);
+
+	/* Release kernel context */
+	if ((hdev->kernel_ctx) && (hl_ctx_put(hdev->kernel_ctx) != 1))
+		dev_err(hdev->dev, "kernel ctx is still alive\n");
+
+	/* Reset the H/W. It will be in idle state after this returns */
+	hdev->asic_funcs->hw_fini(hdev, true);
+
+	hl_vm_fini(hdev);
+
+	hl_mmu_fini(hdev);
+
+	hl_eq_fini(hdev, &hdev->event_queue);
+
+	for (i = 0 ; i < hdev->asic_prop.completion_queues_count ; i++)
+		hl_cq_fini(hdev, &hdev->completion_queue[i]);
+	kfree(hdev->completion_queue);
+
+	hl_hw_queues_destroy(hdev);
+
+	/* Call ASIC S/W finalize function */
+	hdev->asic_funcs->sw_fini(hdev);
+
+	device_early_fini(hdev);
+
+	/* Hide devices and sysfs nodes from user */
+	device_cdev_sysfs_del(hdev);
+
+	pr_info("removed device successfully\n");
+}
+
+/*
+ * MMIO register access helper functions.
+ */
+
+/*
+ * hl_rreg - Read an MMIO register
+ *
+ * @hdev: pointer to habanalabs device structure
+ * @reg: MMIO register offset (in bytes)
+ *
+ * Returns the value of the MMIO register we are asked to read
+ *
+ */
+inline u32 hl_rreg(struct hl_device *hdev, u32 reg)
+{
+	return readl(hdev->rmmio + reg);
+}
+
+/*
+ * hl_wreg - Write to an MMIO register
+ *
+ * @hdev: pointer to habanalabs device structure
+ * @reg: MMIO register offset (in bytes)
+ * @val: 32-bit value
+ *
+ * Writes the 32-bit value into the MMIO register
+ *
+ */
+inline void hl_wreg(struct hl_device *hdev, u32 reg, u32 val)
+{
+	writel(val, hdev->rmmio + reg);
+}
diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
new file mode 100644
index 000000000000..b2b84510b932
--- /dev/null
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -0,0 +1,589 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2019 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include "habanalabs.h"
+#include "include/common/hl_boot_if.h"
+
+#include <linux/firmware.h>
+#include <linux/genalloc.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/slab.h>
+
+/**
+ * hl_fw_load_fw_to_device() - Load F/W code to device's memory.
+ *
+ * @hdev: pointer to hl_device structure.
+ * @fw_name: the firmware image name
+ * @dst: IO memory mapped address space to copy firmware to
+ *
+ * Copy fw code from firmware file to device memory.
+ *
+ * Return: 0 on success, non-zero for failure.
+ */
+int hl_fw_load_fw_to_device(struct hl_device *hdev, const char *fw_name,
+				void __iomem *dst)
+{
+	const struct firmware *fw;
+	const u64 *fw_data;
+	size_t fw_size;
+	int rc;
+
+	rc = request_firmware(&fw, fw_name, hdev->dev);
+	if (rc) {
+		dev_err(hdev->dev, "Firmware file %s is not found!\n", fw_name);
+		goto out;
+	}
+
+	fw_size = fw->size;
+	if ((fw_size % 4) != 0) {
+		dev_err(hdev->dev, "Illegal %s firmware size %zu\n",
+			fw_name, fw_size);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	dev_dbg(hdev->dev, "%s firmware size == %zu\n", fw_name, fw_size);
+
+	fw_data = (const u64 *) fw->data;
+
+	memcpy_toio(dst, fw_data, fw_size);
+
+out:
+	release_firmware(fw);
+	return rc;
+}
+
+int hl_fw_send_pci_access_msg(struct hl_device *hdev, u32 opcode)
+{
+	struct armcp_packet pkt = {};
+
+	pkt.ctl = cpu_to_le32(opcode << ARMCP_PKT_CTL_OPCODE_SHIFT);
+
+	return hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt,
+				sizeof(pkt), HL_DEVICE_TIMEOUT_USEC, NULL);
+}
+
+int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
+				u16 len, u32 timeout, long *result)
+{
+	struct armcp_packet *pkt;
+	dma_addr_t pkt_dma_addr;
+	u32 tmp;
+	int rc = 0;
+
+	pkt = hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev, len,
+								&pkt_dma_addr);
+	if (!pkt) {
+		dev_err(hdev->dev,
+			"Failed to allocate DMA memory for packet to CPU\n");
+		return -ENOMEM;
+	}
+
+	memcpy(pkt, msg, len);
+
+	mutex_lock(&hdev->send_cpu_message_lock);
+
+	if (hdev->disabled)
+		goto out;
+
+	if (hdev->device_cpu_disabled) {
+		rc = -EIO;
+		goto out;
+	}
+
+	rc = hl_hw_queue_send_cb_no_cmpl(hdev, hw_queue_id, len, pkt_dma_addr);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to send CB on CPU PQ (%d)\n", rc);
+		goto out;
+	}
+
+	rc = hl_poll_timeout_memory(hdev, &pkt->fence, tmp,
+				(tmp == ARMCP_PACKET_FENCE_VAL), 1000,
+				timeout, true);
+
+	hl_hw_queue_inc_ci_kernel(hdev, hw_queue_id);
+
+	if (rc == -ETIMEDOUT) {
+		dev_err(hdev->dev, "Device CPU packet timeout (0x%x)\n", tmp);
+		hdev->device_cpu_disabled = true;
+		goto out;
+	}
+
+	tmp = le32_to_cpu(pkt->ctl);
+
+	rc = (tmp & ARMCP_PKT_CTL_RC_MASK) >> ARMCP_PKT_CTL_RC_SHIFT;
+	if (rc) {
+		dev_err(hdev->dev, "F/W ERROR %d for CPU packet %d\n",
+			rc,
+			(tmp & ARMCP_PKT_CTL_OPCODE_MASK)
+						>> ARMCP_PKT_CTL_OPCODE_SHIFT);
+		rc = -EIO;
+	} else if (result) {
+		*result = (long) le64_to_cpu(pkt->result);
+	}
+
+out:
+	mutex_unlock(&hdev->send_cpu_message_lock);
+
+	hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, len, pkt);
+
+	return rc;
+}
+
+int hl_fw_unmask_irq(struct hl_device *hdev, u16 event_type)
+{
+	struct armcp_packet pkt;
+	long result;
+	int rc;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_UNMASK_RAZWI_IRQ <<
+				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.value = cpu_to_le64(event_type);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+			HL_DEVICE_TIMEOUT_USEC, &result);
+
+	if (rc)
+		dev_err(hdev->dev, "failed to unmask RAZWI IRQ %d", event_type);
+
+	return rc;
+}
+
+int hl_fw_unmask_irq_arr(struct hl_device *hdev, const u32 *irq_arr,
+		size_t irq_arr_size)
+{
+	struct armcp_unmask_irq_arr_packet *pkt;
+	size_t total_pkt_size;
+	long result;
+	int rc;
+
+	total_pkt_size = sizeof(struct armcp_unmask_irq_arr_packet) +
+			irq_arr_size;
+
+	/* data should be aligned to 8 bytes in order to ArmCP to copy it */
+	total_pkt_size = (total_pkt_size + 0x7) & ~0x7;
+
+	/* total_pkt_size is casted to u16 later on */
+	if (total_pkt_size > USHRT_MAX) {
+		dev_err(hdev->dev, "too many elements in IRQ array\n");
+		return -EINVAL;
+	}
+
+	pkt = kzalloc(total_pkt_size, GFP_KERNEL);
+	if (!pkt)
+		return -ENOMEM;
+
+	pkt->length = cpu_to_le32(irq_arr_size / sizeof(irq_arr[0]));
+	memcpy(&pkt->irqs, irq_arr, irq_arr_size);
+
+	pkt->armcp_pkt.ctl = cpu_to_le32(ARMCP_PACKET_UNMASK_RAZWI_IRQ_ARRAY <<
+						ARMCP_PKT_CTL_OPCODE_SHIFT);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) pkt,
+			total_pkt_size, HL_DEVICE_TIMEOUT_USEC, &result);
+
+	if (rc)
+		dev_err(hdev->dev, "failed to unmask IRQ array\n");
+
+	kfree(pkt);
+
+	return rc;
+}
+
+int hl_fw_test_cpu_queue(struct hl_device *hdev)
+{
+	struct armcp_packet test_pkt = {};
+	long result;
+	int rc;
+
+	test_pkt.ctl = cpu_to_le32(ARMCP_PACKET_TEST <<
+					ARMCP_PKT_CTL_OPCODE_SHIFT);
+	test_pkt.value = cpu_to_le64(ARMCP_PACKET_FENCE_VAL);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &test_pkt,
+			sizeof(test_pkt), HL_DEVICE_TIMEOUT_USEC, &result);
+
+	if (!rc) {
+		if (result != ARMCP_PACKET_FENCE_VAL)
+			dev_err(hdev->dev,
+				"CPU queue test failed (0x%08lX)\n", result);
+	} else {
+		dev_err(hdev->dev, "CPU queue test failed, error %d\n", rc);
+	}
+
+	return rc;
+}
+
+void *hl_fw_cpu_accessible_dma_pool_alloc(struct hl_device *hdev, size_t size,
+						dma_addr_t *dma_handle)
+{
+	u64 kernel_addr;
+
+	kernel_addr = gen_pool_alloc(hdev->cpu_accessible_dma_pool, size);
+
+	*dma_handle = hdev->cpu_accessible_dma_address +
+		(kernel_addr - (u64) (uintptr_t) hdev->cpu_accessible_dma_mem);
+
+	return (void *) (uintptr_t) kernel_addr;
+}
+
+void hl_fw_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size,
+					void *vaddr)
+{
+	gen_pool_free(hdev->cpu_accessible_dma_pool, (u64) (uintptr_t) vaddr,
+			size);
+}
+
+int hl_fw_send_heartbeat(struct hl_device *hdev)
+{
+	struct armcp_packet hb_pkt = {};
+	long result;
+	int rc;
+
+	hb_pkt.ctl = cpu_to_le32(ARMCP_PACKET_TEST <<
+					ARMCP_PKT_CTL_OPCODE_SHIFT);
+	hb_pkt.value = cpu_to_le64(ARMCP_PACKET_FENCE_VAL);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &hb_pkt,
+			sizeof(hb_pkt), HL_DEVICE_TIMEOUT_USEC, &result);
+
+	if ((rc) || (result != ARMCP_PACKET_FENCE_VAL))
+		rc = -EIO;
+
+	return rc;
+}
+
+int hl_fw_armcp_info_get(struct hl_device *hdev)
+{
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct armcp_packet pkt = {};
+	void *armcp_info_cpu_addr;
+	dma_addr_t armcp_info_dma_addr;
+	long result;
+	int rc;
+
+	armcp_info_cpu_addr =
+			hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev,
+					sizeof(struct armcp_info),
+					&armcp_info_dma_addr);
+	if (!armcp_info_cpu_addr) {
+		dev_err(hdev->dev,
+			"Failed to allocate DMA memory for ArmCP info packet\n");
+		return -ENOMEM;
+	}
+
+	memset(armcp_info_cpu_addr, 0, sizeof(struct armcp_info));
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_INFO_GET <<
+				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.addr = cpu_to_le64(armcp_info_dma_addr);
+	pkt.data_max_size = cpu_to_le32(sizeof(struct armcp_info));
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+					HL_ARMCP_INFO_TIMEOUT_USEC, &result);
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to handle ArmCP info pkt, error %d\n", rc);
+		goto out;
+	}
+
+	memcpy(&prop->armcp_info, armcp_info_cpu_addr,
+			sizeof(prop->armcp_info));
+
+	rc = hl_build_hwmon_channel_info(hdev, prop->armcp_info.sensors);
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to build hwmon channel info, error %d\n", rc);
+		rc = -EFAULT;
+		goto out;
+	}
+
+out:
+	hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev,
+			sizeof(struct armcp_info), armcp_info_cpu_addr);
+
+	return rc;
+}
+
+int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size)
+{
+	struct armcp_packet pkt = {};
+	void *eeprom_info_cpu_addr;
+	dma_addr_t eeprom_info_dma_addr;
+	long result;
+	int rc;
+
+	eeprom_info_cpu_addr =
+			hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev,
+					max_size, &eeprom_info_dma_addr);
+	if (!eeprom_info_cpu_addr) {
+		dev_err(hdev->dev,
+			"Failed to allocate DMA memory for ArmCP EEPROM packet\n");
+		return -ENOMEM;
+	}
+
+	memset(eeprom_info_cpu_addr, 0, max_size);
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_EEPROM_DATA_GET <<
+				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.addr = cpu_to_le64(eeprom_info_dma_addr);
+	pkt.data_max_size = cpu_to_le32(max_size);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+			HL_ARMCP_EEPROM_TIMEOUT_USEC, &result);
+
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to handle ArmCP EEPROM packet, error %d\n", rc);
+		goto out;
+	}
+
+	/* result contains the actual size */
+	memcpy(data, eeprom_info_cpu_addr, min((size_t)result, max_size));
+
+out:
+	hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, max_size,
+			eeprom_info_cpu_addr);
+
+	return rc;
+}
+
+static void fw_read_errors(struct hl_device *hdev, u32 boot_err0_reg)
+{
+	u32 err_val;
+
+	/* Some of the firmware status codes are deprecated in newer f/w
+	 * versions. In those versions, the errors are reported
+	 * in different registers. Therefore, we need to check those
+	 * registers and print the exact errors. Moreover, there
+	 * may be multiple errors, so we need to report on each error
+	 * separately. Some of the error codes might indicate a state
+	 * that is not an error per-se, but it is an error in production
+	 * environment
+	 */
+	err_val = RREG32(boot_err0_reg);
+	if (!(err_val & CPU_BOOT_ERR0_ENABLED))
+		return;
+
+	if (err_val & CPU_BOOT_ERR0_DRAM_INIT_FAIL)
+		dev_err(hdev->dev,
+			"Device boot error - DRAM initialization failed\n");
+	if (err_val & CPU_BOOT_ERR0_FIT_CORRUPTED)
+		dev_err(hdev->dev, "Device boot error - FIT image corrupted\n");
+	if (err_val & CPU_BOOT_ERR0_TS_INIT_FAIL)
+		dev_err(hdev->dev,
+			"Device boot error - Thermal Sensor initialization failed\n");
+	if (err_val & CPU_BOOT_ERR0_DRAM_SKIPPED)
+		dev_warn(hdev->dev,
+			"Device boot warning - Skipped DRAM initialization\n");
+	if (err_val & CPU_BOOT_ERR0_BMC_WAIT_SKIPPED)
+		dev_warn(hdev->dev,
+			"Device boot error - Skipped waiting for BMC\n");
+	if (err_val & CPU_BOOT_ERR0_NIC_DATA_NOT_RDY)
+		dev_err(hdev->dev,
+			"Device boot error - Serdes data from BMC not available\n");
+	if (err_val & CPU_BOOT_ERR0_NIC_FW_FAIL)
+		dev_err(hdev->dev,
+			"Device boot error - NIC F/W initialization failed\n");
+}
+
+static void hl_detect_cpu_boot_status(struct hl_device *hdev, u32 status)
+{
+	switch (status) {
+	case CPU_BOOT_STATUS_NA:
+		dev_err(hdev->dev,
+			"Device boot error - BTL did NOT run\n");
+		break;
+	case CPU_BOOT_STATUS_IN_WFE:
+		dev_err(hdev->dev,
+			"Device boot error - Stuck inside WFE loop\n");
+		break;
+	case CPU_BOOT_STATUS_IN_BTL:
+		dev_err(hdev->dev,
+			"Device boot error - Stuck in BTL\n");
+		break;
+	case CPU_BOOT_STATUS_IN_PREBOOT:
+		dev_err(hdev->dev,
+			"Device boot error - Stuck in Preboot\n");
+		break;
+	case CPU_BOOT_STATUS_IN_SPL:
+		dev_err(hdev->dev,
+			"Device boot error - Stuck in SPL\n");
+		break;
+	case CPU_BOOT_STATUS_IN_UBOOT:
+		dev_err(hdev->dev,
+			"Device boot error - Stuck in u-boot\n");
+		break;
+	case CPU_BOOT_STATUS_DRAM_INIT_FAIL:
+		dev_err(hdev->dev,
+			"Device boot error - DRAM initialization failed\n");
+		break;
+	case CPU_BOOT_STATUS_UBOOT_NOT_READY:
+		dev_err(hdev->dev,
+			"Device boot error - u-boot stopped by user\n");
+		break;
+	case CPU_BOOT_STATUS_TS_INIT_FAIL:
+		dev_err(hdev->dev,
+			"Device boot error - Thermal Sensor initialization failed\n");
+		break;
+	default:
+		dev_err(hdev->dev,
+			"Device boot error - Invalid status code %d\n",
+			status);
+		break;
+	}
+}
+
+int hl_fw_init_cpu(struct hl_device *hdev, u32 cpu_boot_status_reg,
+			u32 msg_to_cpu_reg, u32 cpu_msg_status_reg,
+			u32 boot_err0_reg, bool skip_bmc,
+			u32 cpu_timeout, u32 boot_fit_timeout)
+{
+	u32 status;
+	int rc;
+
+	dev_info(hdev->dev, "Going to wait for device boot (up to %lds)\n",
+		cpu_timeout / USEC_PER_SEC);
+
+	/* Wait for boot FIT request */
+	rc = hl_poll_timeout(
+		hdev,
+		cpu_boot_status_reg,
+		status,
+		status == CPU_BOOT_STATUS_WAITING_FOR_BOOT_FIT,
+		10000,
+		boot_fit_timeout);
+
+	if (rc) {
+		dev_dbg(hdev->dev,
+			"No boot fit request received, resuming boot\n");
+	} else {
+		rc = hdev->asic_funcs->load_boot_fit_to_device(hdev);
+		if (rc)
+			goto out;
+
+		/* Clear device CPU message status */
+		WREG32(cpu_msg_status_reg, CPU_MSG_CLR);
+
+		/* Signal device CPU that boot loader is ready */
+		WREG32(msg_to_cpu_reg, KMD_MSG_FIT_RDY);
+
+		/* Poll for CPU device ack */
+		rc = hl_poll_timeout(
+			hdev,
+			cpu_msg_status_reg,
+			status,
+			status == CPU_MSG_OK,
+			10000,
+			boot_fit_timeout);
+
+		if (rc) {
+			dev_err(hdev->dev,
+				"Timeout waiting for boot fit load ack\n");
+			goto out;
+		}
+
+		/* Clear message */
+		WREG32(msg_to_cpu_reg, KMD_MSG_NA);
+	}
+
+	/* Make sure CPU boot-loader is running */
+	rc = hl_poll_timeout(
+		hdev,
+		cpu_boot_status_reg,
+		status,
+		(status == CPU_BOOT_STATUS_DRAM_RDY) ||
+		(status == CPU_BOOT_STATUS_NIC_FW_RDY) ||
+		(status == CPU_BOOT_STATUS_READY_TO_BOOT) ||
+		(status == CPU_BOOT_STATUS_SRAM_AVAIL),
+		10000,
+		cpu_timeout);
+
+	/* Read U-Boot, preboot versions now in case we will later fail */
+	hdev->asic_funcs->read_device_fw_version(hdev, FW_COMP_UBOOT);
+	hdev->asic_funcs->read_device_fw_version(hdev, FW_COMP_PREBOOT);
+
+	/* Some of the status codes below are deprecated in newer f/w
+	 * versions but we keep them here for backward compatibility
+	 */
+	if (rc) {
+		hl_detect_cpu_boot_status(hdev, status);
+		rc = -EIO;
+		goto out;
+	}
+
+	if (!hdev->fw_loading) {
+		dev_info(hdev->dev, "Skip loading FW\n");
+		goto out;
+	}
+
+	if (status == CPU_BOOT_STATUS_SRAM_AVAIL)
+		goto out;
+
+	dev_info(hdev->dev,
+		"Loading firmware to device, may take some time...\n");
+
+	rc = hdev->asic_funcs->load_firmware_to_device(hdev);
+	if (rc)
+		goto out;
+
+	if (skip_bmc) {
+		WREG32(msg_to_cpu_reg, KMD_MSG_SKIP_BMC);
+
+		rc = hl_poll_timeout(
+			hdev,
+			cpu_boot_status_reg,
+			status,
+			(status == CPU_BOOT_STATUS_BMC_WAITING_SKIPPED),
+			10000,
+			cpu_timeout);
+
+		if (rc) {
+			dev_err(hdev->dev,
+				"Failed to get ACK on skipping BMC, %d\n",
+				status);
+			WREG32(msg_to_cpu_reg, KMD_MSG_NA);
+			rc = -EIO;
+			goto out;
+		}
+	}
+
+	WREG32(msg_to_cpu_reg, KMD_MSG_FIT_RDY);
+
+	rc = hl_poll_timeout(
+		hdev,
+		cpu_boot_status_reg,
+		status,
+		(status == CPU_BOOT_STATUS_SRAM_AVAIL),
+		10000,
+		cpu_timeout);
+
+	/* Clear message */
+	WREG32(msg_to_cpu_reg, KMD_MSG_NA);
+
+	if (rc) {
+		if (status == CPU_BOOT_STATUS_FIT_CORRUPTED)
+			dev_err(hdev->dev,
+				"Device reports FIT image is corrupted\n");
+		else
+			dev_err(hdev->dev,
+				"Failed to load firmware to device, %d\n",
+				status);
+
+		rc = -EIO;
+		goto out;
+	}
+
+	dev_info(hdev->dev, "Successfully loaded firmware to device\n");
+
+out:
+	fw_read_errors(hdev, boot_err0_reg);
+
+	return rc;
+}
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
new file mode 100644
index 000000000000..82532f1f94cb
--- /dev/null
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -0,0 +1,1948 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright 2016-2019 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ *
+ */
+
+#ifndef HABANALABSP_H_
+#define HABANALABSP_H_
+
+#include "include/common/armcp_if.h"
+#include "include/common/qman_if.h"
+#include <uapi/misc/habanalabs.h>
+
+#include <linux/cdev.h>
+#include <linux/iopoll.h>
+#include <linux/irqreturn.h>
+#include <linux/dma-fence.h>
+#include <linux/dma-direction.h>
+#include <linux/scatterlist.h>
+#include <linux/hashtable.h>
+
+#define HL_NAME				"habanalabs"
+
+#define HL_MMAP_CB_MASK			(0x8000000000000000ull >> PAGE_SHIFT)
+
+#define HL_PENDING_RESET_PER_SEC	30
+
+#define HL_HARD_RESET_MAX_TIMEOUT	120
+
+#define HL_DEVICE_TIMEOUT_USEC		1000000 /* 1 s */
+
+#define HL_HEARTBEAT_PER_USEC		5000000 /* 5 s */
+
+#define HL_PLL_LOW_JOB_FREQ_USEC	5000000 /* 5 s */
+
+#define HL_ARMCP_INFO_TIMEOUT_USEC	10000000 /* 10s */
+#define HL_ARMCP_EEPROM_TIMEOUT_USEC	10000000 /* 10s */
+
+#define HL_PCI_ELBI_TIMEOUT_MSEC	10 /* 10ms */
+
+#define HL_SIM_MAX_TIMEOUT_US		10000000 /* 10s */
+
+#define HL_IDLE_BUSY_TS_ARR_SIZE	4096
+
+/* Memory */
+#define MEM_HASH_TABLE_BITS		7 /* 1 << 7 buckets */
+
+/* MMU */
+#define MMU_HASH_TABLE_BITS		7 /* 1 << 7 buckets */
+
+/*
+ * HL_RSVD_SOBS 'sync stream' reserved sync objects per QMAN stream
+ * HL_RSVD_MONS 'sync stream' reserved monitors per QMAN stream
+ */
+#define HL_RSVD_SOBS			4
+#define HL_RSVD_MONS			2
+
+#define HL_RSVD_SOBS_IN_USE		2
+#define HL_RSVD_MONS_IN_USE		1
+
+#define HL_MAX_SOB_VAL			(1 << 15)
+
+#define IS_POWER_OF_2(n)		(n != 0 && ((n & (n - 1)) == 0))
+#define IS_MAX_PENDING_CS_VALID(n)	(IS_POWER_OF_2(n) && (n > 1))
+
+#define HL_PCI_NUM_BARS			6
+
+/**
+ * struct pgt_info - MMU hop page info.
+ * @node: hash linked-list node for the pgts shadow hash of pgts.
+ * @phys_addr: physical address of the pgt.
+ * @shadow_addr: shadow hop in the host.
+ * @ctx: pointer to the owner ctx.
+ * @num_of_ptes: indicates how many ptes are used in the pgt.
+ *
+ * The MMU page tables hierarchy is placed on the DRAM. When a new level (hop)
+ * is needed during mapping, a new page is allocated and this structure holds
+ * its essential information. During unmapping, if no valid PTEs remained in the
+ * page, it is freed with its pgt_info structure.
+ */
+struct pgt_info {
+	struct hlist_node	node;
+	u64			phys_addr;
+	u64			shadow_addr;
+	struct hl_ctx		*ctx;
+	int			num_of_ptes;
+};
+
+struct hl_device;
+struct hl_fpriv;
+
+/**
+ * enum hl_pci_match_mode - pci match mode per region
+ * @PCI_ADDRESS_MATCH_MODE: address match mode
+ * @PCI_BAR_MATCH_MODE: bar match mode
+ */
+enum hl_pci_match_mode {
+	PCI_ADDRESS_MATCH_MODE,
+	PCI_BAR_MATCH_MODE
+};
+
+/**
+ * enum hl_fw_component - F/W components to read version through registers.
+ * @FW_COMP_UBOOT: u-boot.
+ * @FW_COMP_PREBOOT: preboot.
+ */
+enum hl_fw_component {
+	FW_COMP_UBOOT,
+	FW_COMP_PREBOOT
+};
+
+/**
+ * enum hl_queue_type - Supported QUEUE types.
+ * @QUEUE_TYPE_NA: queue is not available.
+ * @QUEUE_TYPE_EXT: external queue which is a DMA channel that may access the
+ *                  host.
+ * @QUEUE_TYPE_INT: internal queue that performs DMA inside the device's
+ *			memories and/or operates the compute engines.
+ * @QUEUE_TYPE_CPU: S/W queue for communication with the device's CPU.
+ * @QUEUE_TYPE_HW: queue of DMA and compute engines jobs, for which completion
+ *                 notifications are sent by H/W.
+ */
+enum hl_queue_type {
+	QUEUE_TYPE_NA,
+	QUEUE_TYPE_EXT,
+	QUEUE_TYPE_INT,
+	QUEUE_TYPE_CPU,
+	QUEUE_TYPE_HW
+};
+
+enum hl_cs_type {
+	CS_TYPE_DEFAULT,
+	CS_TYPE_SIGNAL,
+	CS_TYPE_WAIT
+};
+
+/*
+ * struct hl_inbound_pci_region - inbound region descriptor
+ * @mode: pci match mode for this region
+ * @addr: region target address
+ * @size: region size in bytes
+ * @offset_in_bar: offset within bar (address match mode)
+ * @bar: bar id
+ */
+struct hl_inbound_pci_region {
+	enum hl_pci_match_mode	mode;
+	u64			addr;
+	u64			size;
+	u64			offset_in_bar;
+	u8			bar;
+};
+
+/*
+ * struct hl_outbound_pci_region - outbound region descriptor
+ * @addr: region target address
+ * @size: region size in bytes
+ */
+struct hl_outbound_pci_region {
+	u64	addr;
+	u64	size;
+};
+
+/*
+ * struct hl_hw_sob - H/W SOB info.
+ * @hdev: habanalabs device structure.
+ * @kref: refcount of this SOB. The SOB will reset once the refcount is zero.
+ * @sob_id: id of this SOB.
+ * @q_idx: the H/W queue that uses this SOB.
+ */
+struct hl_hw_sob {
+	struct hl_device	*hdev;
+	struct kref		kref;
+	u32			sob_id;
+	u32			q_idx;
+};
+
+/**
+ * struct hw_queue_properties - queue information.
+ * @type: queue type.
+ * @driver_only: true if only the driver is allowed to send a job to this queue,
+ *               false otherwise.
+ * @requires_kernel_cb: true if a CB handle must be provided for jobs on this
+ *                      queue, false otherwise (a CB address must be provided).
+ * @supports_sync_stream: True if queue supports sync stream
+ */
+struct hw_queue_properties {
+	enum hl_queue_type	type;
+	u8			driver_only;
+	u8			requires_kernel_cb;
+	u8			supports_sync_stream;
+};
+
+/**
+ * enum vm_type_t - virtual memory mapping request information.
+ * @VM_TYPE_USERPTR: mapping of user memory to device virtual address.
+ * @VM_TYPE_PHYS_PACK: mapping of DRAM memory to device virtual address.
+ */
+enum vm_type_t {
+	VM_TYPE_USERPTR = 0x1,
+	VM_TYPE_PHYS_PACK = 0x2
+};
+
+/**
+ * enum hl_device_hw_state - H/W device state. use this to understand whether
+ *                           to do reset before hw_init or not
+ * @HL_DEVICE_HW_STATE_CLEAN: H/W state is clean. i.e. after hard reset
+ * @HL_DEVICE_HW_STATE_DIRTY: H/W state is dirty. i.e. we started to execute
+ *                            hw_init
+ */
+enum hl_device_hw_state {
+	HL_DEVICE_HW_STATE_CLEAN = 0,
+	HL_DEVICE_HW_STATE_DIRTY
+};
+
+/**
+ * struct hl_mmu_properties - ASIC specific MMU address translation properties.
+ * @start_addr: virtual start address of the memory region.
+ * @end_addr: virtual end address of the memory region.
+ * @hop0_shift: shift of hop 0 mask.
+ * @hop1_shift: shift of hop 1 mask.
+ * @hop2_shift: shift of hop 2 mask.
+ * @hop3_shift: shift of hop 3 mask.
+ * @hop4_shift: shift of hop 4 mask.
+ * @hop0_mask: mask to get the PTE address in hop 0.
+ * @hop1_mask: mask to get the PTE address in hop 1.
+ * @hop2_mask: mask to get the PTE address in hop 2.
+ * @hop3_mask: mask to get the PTE address in hop 3.
+ * @hop4_mask: mask to get the PTE address in hop 4.
+ * @page_size: default page size used to allocate memory.
+ */
+struct hl_mmu_properties {
+	u64	start_addr;
+	u64	end_addr;
+	u64	hop0_shift;
+	u64	hop1_shift;
+	u64	hop2_shift;
+	u64	hop3_shift;
+	u64	hop4_shift;
+	u64	hop0_mask;
+	u64	hop1_mask;
+	u64	hop2_mask;
+	u64	hop3_mask;
+	u64	hop4_mask;
+	u32	page_size;
+};
+
+/**
+ * struct asic_fixed_properties - ASIC specific immutable properties.
+ * @hw_queues_props: H/W queues properties.
+ * @armcp_info: received various information from ArmCP regarding the H/W, e.g.
+ *		available sensors.
+ * @uboot_ver: F/W U-boot version.
+ * @preboot_ver: F/W Preboot version.
+ * @dmmu: DRAM MMU address translation properties.
+ * @pmmu: PCI (host) MMU address translation properties.
+ * @pmmu_huge: PCI (host) MMU address translation properties for memory
+ *              allocated with huge pages.
+ * @sram_base_address: SRAM physical start address.
+ * @sram_end_address: SRAM physical end address.
+ * @sram_user_base_address - SRAM physical start address for user access.
+ * @dram_base_address: DRAM physical start address.
+ * @dram_end_address: DRAM physical end address.
+ * @dram_user_base_address: DRAM physical start address for user access.
+ * @dram_size: DRAM total size.
+ * @dram_pci_bar_size: size of PCI bar towards DRAM.
+ * @max_power_default: max power of the device after reset
+ * @dram_size_for_default_page_mapping: DRAM size needed to map to avoid page
+ *                                      fault.
+ * @pcie_dbi_base_address: Base address of the PCIE_DBI block.
+ * @pcie_aux_dbi_reg_addr: Address of the PCIE_AUX DBI register.
+ * @mmu_pgt_addr: base physical address in DRAM of MMU page tables.
+ * @mmu_dram_default_page_addr: DRAM default page physical address.
+ * @mmu_pgt_size: MMU page tables total size.
+ * @mmu_pte_size: PTE size in MMU page tables.
+ * @mmu_hop_table_size: MMU hop table size.
+ * @mmu_hop0_tables_total_size: total size of MMU hop0 tables.
+ * @dram_page_size: page size for MMU DRAM allocation.
+ * @cfg_size: configuration space size on SRAM.
+ * @sram_size: total size of SRAM.
+ * @max_asid: maximum number of open contexts (ASIDs).
+ * @num_of_events: number of possible internal H/W IRQs.
+ * @psoc_pci_pll_nr: PCI PLL NR value.
+ * @psoc_pci_pll_nf: PCI PLL NF value.
+ * @psoc_pci_pll_od: PCI PLL OD value.
+ * @psoc_pci_pll_div_factor: PCI PLL DIV FACTOR 1 value.
+ * @psoc_timestamp_frequency: frequency of the psoc timestamp clock.
+ * @high_pll: high PLL frequency used by the device.
+ * @cb_pool_cb_cnt: number of CBs in the CB pool.
+ * @cb_pool_cb_size: size of each CB in the CB pool.
+ * @max_pending_cs: maximum of concurrent pending command submissions
+ * @max_queues: maximum amount of queues in the system
+ * @sync_stream_first_sob: first sync object available for sync stream use
+ * @sync_stream_first_mon: first monitor available for sync stream use
+ * @tpc_enabled_mask: which TPCs are enabled.
+ * @completion_queues_count: number of completion queues.
+ */
+struct asic_fixed_properties {
+	struct hw_queue_properties	*hw_queues_props;
+	struct armcp_info		armcp_info;
+	char				uboot_ver[VERSION_MAX_LEN];
+	char				preboot_ver[VERSION_MAX_LEN];
+	struct hl_mmu_properties	dmmu;
+	struct hl_mmu_properties	pmmu;
+	struct hl_mmu_properties	pmmu_huge;
+	u64				sram_base_address;
+	u64				sram_end_address;
+	u64				sram_user_base_address;
+	u64				dram_base_address;
+	u64				dram_end_address;
+	u64				dram_user_base_address;
+	u64				dram_size;
+	u64				dram_pci_bar_size;
+	u64				max_power_default;
+	u64				dram_size_for_default_page_mapping;
+	u64				pcie_dbi_base_address;
+	u64				pcie_aux_dbi_reg_addr;
+	u64				mmu_pgt_addr;
+	u64				mmu_dram_default_page_addr;
+	u32				mmu_pgt_size;
+	u32				mmu_pte_size;
+	u32				mmu_hop_table_size;
+	u32				mmu_hop0_tables_total_size;
+	u32				dram_page_size;
+	u32				cfg_size;
+	u32				sram_size;
+	u32				max_asid;
+	u32				num_of_events;
+	u32				psoc_pci_pll_nr;
+	u32				psoc_pci_pll_nf;
+	u32				psoc_pci_pll_od;
+	u32				psoc_pci_pll_div_factor;
+	u32				psoc_timestamp_frequency;
+	u32				high_pll;
+	u32				cb_pool_cb_cnt;
+	u32				cb_pool_cb_size;
+	u32				max_pending_cs;
+	u32				max_queues;
+	u16				sync_stream_first_sob;
+	u16				sync_stream_first_mon;
+	u8				tpc_enabled_mask;
+	u8				completion_queues_count;
+};
+
+/**
+ * struct hl_cs_compl - command submission completion object.
+ * @base_fence: kernel fence object.
+ * @lock: spinlock to protect fence.
+ * @hdev: habanalabs device structure.
+ * @hw_sob: the H/W SOB used in this signal/wait CS.
+ * @cs_seq: command submission sequence number.
+ * @type: type of the CS - signal/wait.
+ * @sob_val: the SOB value that is used in this signal/wait CS.
+ */
+struct hl_cs_compl {
+	struct dma_fence	base_fence;
+	spinlock_t		lock;
+	struct hl_device	*hdev;
+	struct hl_hw_sob	*hw_sob;
+	u64			cs_seq;
+	enum hl_cs_type		type;
+	u16			sob_val;
+};
+
+/*
+ * Command Buffers
+ */
+
+/**
+ * struct hl_cb_mgr - describes a Command Buffer Manager.
+ * @cb_lock: protects cb_handles.
+ * @cb_handles: an idr to hold all command buffer handles.
+ */
+struct hl_cb_mgr {
+	spinlock_t		cb_lock;
+	struct idr		cb_handles; /* protected by cb_lock */
+};
+
+/**
+ * struct hl_cb - describes a Command Buffer.
+ * @refcount: reference counter for usage of the CB.
+ * @hdev: pointer to device this CB belongs to.
+ * @lock: spinlock to protect mmap/cs flows.
+ * @debugfs_list: node in debugfs list of command buffers.
+ * @pool_list: node in pool list of command buffers.
+ * @kernel_address: Holds the CB's kernel virtual address.
+ * @bus_address: Holds the CB's DMA address.
+ * @mmap_size: Holds the CB's size that was mmaped.
+ * @size: holds the CB's size.
+ * @id: the CB's ID.
+ * @cs_cnt: holds number of CS that this CB participates in.
+ * @ctx_id: holds the ID of the owner's context.
+ * @mmap: true if the CB is currently mmaped to user.
+ * @is_pool: true if CB was acquired from the pool, false otherwise.
+ */
+struct hl_cb {
+	struct kref		refcount;
+	struct hl_device	*hdev;
+	spinlock_t		lock;
+	struct list_head	debugfs_list;
+	struct list_head	pool_list;
+	u64			kernel_address;
+	dma_addr_t		bus_address;
+	u32			mmap_size;
+	u32			size;
+	u32			id;
+	u32			cs_cnt;
+	u32			ctx_id;
+	u8			mmap;
+	u8			is_pool;
+};
+
+
+/*
+ * QUEUES
+ */
+
+struct hl_cs_job;
+
+/* Queue length of external and HW queues */
+#define HL_QUEUE_LENGTH			4096
+#define HL_QUEUE_SIZE_IN_BYTES		(HL_QUEUE_LENGTH * HL_BD_SIZE)
+
+#if (HL_MAX_JOBS_PER_CS > HL_QUEUE_LENGTH)
+#error "HL_QUEUE_LENGTH must be greater than HL_MAX_JOBS_PER_CS"
+#endif
+
+/* HL_CQ_LENGTH is in units of struct hl_cq_entry */
+#define HL_CQ_LENGTH			HL_QUEUE_LENGTH
+#define HL_CQ_SIZE_IN_BYTES		(HL_CQ_LENGTH * HL_CQ_ENTRY_SIZE)
+
+/* Must be power of 2 */
+#define HL_EQ_LENGTH			64
+#define HL_EQ_SIZE_IN_BYTES		(HL_EQ_LENGTH * HL_EQ_ENTRY_SIZE)
+
+/* Host <-> ArmCP shared memory size */
+#define HL_CPU_ACCESSIBLE_MEM_SIZE	SZ_2M
+
+/**
+ * struct hl_hw_queue - describes a H/W transport queue.
+ * @hw_sob: array of the used H/W SOBs by this H/W queue.
+ * @shadow_queue: pointer to a shadow queue that holds pointers to jobs.
+ * @queue_type: type of queue.
+ * @kernel_address: holds the queue's kernel virtual address.
+ * @bus_address: holds the queue's DMA address.
+ * @pi: holds the queue's pi value.
+ * @ci: holds the queue's ci value, AS CALCULATED BY THE DRIVER (not real ci).
+ * @hw_queue_id: the id of the H/W queue.
+ * @cq_id: the id for the corresponding CQ for this H/W queue.
+ * @msi_vec: the IRQ number of the H/W queue.
+ * @int_queue_len: length of internal queue (number of entries).
+ * @next_sob_val: the next value to use for the currently used SOB.
+ * @base_sob_id: the base SOB id of the SOBs used by this queue.
+ * @base_mon_id: the base MON id of the MONs used by this queue.
+ * @valid: is the queue valid (we have array of 32 queues, not all of them
+ *         exist).
+ * @curr_sob_offset: the id offset to the currently used SOB from the
+ *                   HL_RSVD_SOBS that are being used by this queue.
+ * @supports_sync_stream: True if queue supports sync stream
+ */
+struct hl_hw_queue {
+	struct hl_hw_sob	hw_sob[HL_RSVD_SOBS];
+	struct hl_cs_job	**shadow_queue;
+	enum hl_queue_type	queue_type;
+	u64			kernel_address;
+	dma_addr_t		bus_address;
+	u32			pi;
+	atomic_t		ci;
+	u32			hw_queue_id;
+	u32			cq_id;
+	u32			msi_vec;
+	u16			int_queue_len;
+	u16			next_sob_val;
+	u16			base_sob_id;
+	u16			base_mon_id;
+	u8			valid;
+	u8			curr_sob_offset;
+	u8			supports_sync_stream;
+};
+
+/**
+ * struct hl_cq - describes a completion queue
+ * @hdev: pointer to the device structure
+ * @kernel_address: holds the queue's kernel virtual address
+ * @bus_address: holds the queue's DMA address
+ * @cq_idx: completion queue index in array
+ * @hw_queue_id: the id of the matching H/W queue
+ * @ci: ci inside the queue
+ * @pi: pi inside the queue
+ * @free_slots_cnt: counter of free slots in queue
+ */
+struct hl_cq {
+	struct hl_device	*hdev;
+	u64			kernel_address;
+	dma_addr_t		bus_address;
+	u32			cq_idx;
+	u32			hw_queue_id;
+	u32			ci;
+	u32			pi;
+	atomic_t		free_slots_cnt;
+};
+
+/**
+ * struct hl_eq - describes the event queue (single one per device)
+ * @hdev: pointer to the device structure
+ * @kernel_address: holds the queue's kernel virtual address
+ * @bus_address: holds the queue's DMA address
+ * @ci: ci inside the queue
+ */
+struct hl_eq {
+	struct hl_device	*hdev;
+	u64			kernel_address;
+	dma_addr_t		bus_address;
+	u32			ci;
+};
+
+
+/*
+ * ASICs
+ */
+
+/**
+ * enum hl_asic_type - supported ASIC types.
+ * @ASIC_INVALID: Invalid ASIC type.
+ * @ASIC_GOYA: Goya device.
+ * @ASIC_GAUDI: Gaudi device.
+ */
+enum hl_asic_type {
+	ASIC_INVALID,
+	ASIC_GOYA,
+	ASIC_GAUDI
+};
+
+struct hl_cs_parser;
+
+/**
+ * enum hl_pm_mng_profile - power management profile.
+ * @PM_AUTO: internal clock is set by the Linux driver.
+ * @PM_MANUAL: internal clock is set by the user.
+ * @PM_LAST: last power management type.
+ */
+enum hl_pm_mng_profile {
+	PM_AUTO = 1,
+	PM_MANUAL,
+	PM_LAST
+};
+
+/**
+ * enum hl_pll_frequency - PLL frequency.
+ * @PLL_HIGH: high frequency.
+ * @PLL_LOW: low frequency.
+ * @PLL_LAST: last frequency values that were configured by the user.
+ */
+enum hl_pll_frequency {
+	PLL_HIGH = 1,
+	PLL_LOW,
+	PLL_LAST
+};
+
+#define PLL_REF_CLK 50
+
+enum div_select_defs {
+	DIV_SEL_REF_CLK = 0,
+	DIV_SEL_PLL_CLK = 1,
+	DIV_SEL_DIVIDED_REF = 2,
+	DIV_SEL_DIVIDED_PLL = 3,
+};
+
+/**
+ * struct hl_asic_funcs - ASIC specific functions that are can be called from
+ *                        common code.
+ * @early_init: sets up early driver state (pre sw_init), doesn't configure H/W.
+ * @early_fini: tears down what was done in early_init.
+ * @late_init: sets up late driver/hw state (post hw_init) - Optional.
+ * @late_fini: tears down what was done in late_init (pre hw_fini) - Optional.
+ * @sw_init: sets up driver state, does not configure H/W.
+ * @sw_fini: tears down driver state, does not configure H/W.
+ * @hw_init: sets up the H/W state.
+ * @hw_fini: tears down the H/W state.
+ * @halt_engines: halt engines, needed for reset sequence. This also disables
+ *                interrupts from the device. Should be called before
+ *                hw_fini and before CS rollback.
+ * @suspend: handles IP specific H/W or SW changes for suspend.
+ * @resume: handles IP specific H/W or SW changes for resume.
+ * @cb_mmap: maps a CB.
+ * @ring_doorbell: increment PI on a given QMAN.
+ * @pqe_write: Write the PQ entry to the PQ. This is ASIC-specific
+ *             function because the PQs are located in different memory areas
+ *             per ASIC (SRAM, DRAM, Host memory) and therefore, the method of
+ *             writing the PQE must match the destination memory area
+ *             properties.
+ * @asic_dma_alloc_coherent: Allocate coherent DMA memory by calling
+ *                           dma_alloc_coherent(). This is ASIC function because
+ *                           its implementation is not trivial when the driver
+ *                           is loaded in simulation mode (not upstreamed).
+ * @asic_dma_free_coherent:  Free coherent DMA memory by calling
+ *                           dma_free_coherent(). This is ASIC function because
+ *                           its implementation is not trivial when the driver
+ *                           is loaded in simulation mode (not upstreamed).
+ * @get_int_queue_base: get the internal queue base address.
+ * @test_queues: run simple test on all queues for sanity check.
+ * @asic_dma_pool_zalloc: small DMA allocation of coherent memory from DMA pool.
+ *                        size of allocation is HL_DMA_POOL_BLK_SIZE.
+ * @asic_dma_pool_free: free small DMA allocation from pool.
+ * @cpu_accessible_dma_pool_alloc: allocate CPU PQ packet from DMA pool.
+ * @cpu_accessible_dma_pool_free: free CPU PQ packet from DMA pool.
+ * @hl_dma_unmap_sg: DMA unmap scatter-gather list.
+ * @cs_parser: parse Command Submission.
+ * @asic_dma_map_sg: DMA map scatter-gather list.
+ * @get_dma_desc_list_size: get number of LIN_DMA packets required for CB.
+ * @add_end_of_cb_packets: Add packets to the end of CB, if device requires it.
+ * @update_eq_ci: update event queue CI.
+ * @context_switch: called upon ASID context switch.
+ * @restore_phase_topology: clear all SOBs amd MONs.
+ * @debugfs_read32: debug interface for reading u32 from DRAM/SRAM.
+ * @debugfs_write32: debug interface for writing u32 to DRAM/SRAM.
+ * @add_device_attr: add ASIC specific device attributes.
+ * @handle_eqe: handle event queue entry (IRQ) from ArmCP.
+ * @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.
+ * @mmu_invalidate_cache: flush MMU STLB host/DRAM cache, either with soft
+ *                        (L1 only) or hard (L0 & L1) flush.
+ * @mmu_invalidate_cache_range: flush specific MMU STLB cache lines with
+ *                              ASID-VA-size mask.
+ * @send_heartbeat: send is-alive packet to ArmCP and verify response.
+ * @enable_clock_gating: enable clock gating for reducing power consumption.
+ * @disable_clock_gating: disable clock for accessing registers on HBW.
+ * @debug_coresight: perform certain actions on Coresight for debugging.
+ * @is_device_idle: return true if device is idle, false otherwise.
+ * @soft_reset_late_init: perform certain actions needed after soft reset.
+ * @hw_queues_lock: acquire H/W queues lock.
+ * @hw_queues_unlock: release H/W queues lock.
+ * @get_pci_id: retrieve PCI ID.
+ * @get_eeprom_data: retrieve EEPROM data from F/W.
+ * @send_cpu_message: send buffer to ArmCP.
+ * @get_hw_state: retrieve the H/W state
+ * @pci_bars_map: Map PCI BARs.
+ * @set_dram_bar_base: Set DRAM BAR to map specific device address. Returns
+ *                     old address the bar pointed to or U64_MAX for failure
+ * @init_iatu: Initialize the iATU unit inside the PCI controller.
+ * @rreg: Read a register. Needed for simulator support.
+ * @wreg: Write a register. Needed for simulator support.
+ * @halt_coresight: stop the ETF and ETR traces.
+ * @get_clk_rate: Retrieve the ASIC current and maximum clock rate in MHz
+ * @get_queue_id_for_cq: Get the H/W queue id related to the given CQ index.
+ * @read_device_fw_version: read the device's firmware versions that are
+ *                          contained in registers
+ * @load_firmware_to_device: load the firmware to the device's memory
+ * @load_boot_fit_to_device: load boot fit to device's memory
+ * @get_signal_cb_size: Get signal CB size.
+ * @get_wait_cb_size: Get wait CB size.
+ * @gen_signal_cb: Generate a signal CB.
+ * @gen_wait_cb: Generate a wait CB.
+ * @reset_sob: Reset a SOB.
+ * @set_dma_mask_from_fw: set the DMA mask in the driver according to the
+ *                        firmware configuration
+ * @get_device_time: Get the device time.
+ */
+struct hl_asic_funcs {
+	int (*early_init)(struct hl_device *hdev);
+	int (*early_fini)(struct hl_device *hdev);
+	int (*late_init)(struct hl_device *hdev);
+	void (*late_fini)(struct hl_device *hdev);
+	int (*sw_init)(struct hl_device *hdev);
+	int (*sw_fini)(struct hl_device *hdev);
+	int (*hw_init)(struct hl_device *hdev);
+	void (*hw_fini)(struct hl_device *hdev, bool hard_reset);
+	void (*halt_engines)(struct hl_device *hdev, bool hard_reset);
+	int (*suspend)(struct hl_device *hdev);
+	int (*resume)(struct hl_device *hdev);
+	int (*cb_mmap)(struct hl_device *hdev, struct vm_area_struct *vma,
+			u64 kaddress, phys_addr_t paddress, u32 size);
+	void (*ring_doorbell)(struct hl_device *hdev, u32 hw_queue_id, u32 pi);
+	void (*pqe_write)(struct hl_device *hdev, __le64 *pqe,
+			struct hl_bd *bd);
+	void* (*asic_dma_alloc_coherent)(struct hl_device *hdev, size_t size,
+					dma_addr_t *dma_handle, gfp_t flag);
+	void (*asic_dma_free_coherent)(struct hl_device *hdev, size_t size,
+					void *cpu_addr, dma_addr_t dma_handle);
+	void* (*get_int_queue_base)(struct hl_device *hdev, u32 queue_id,
+				dma_addr_t *dma_handle, u16 *queue_len);
+	int (*test_queues)(struct hl_device *hdev);
+	void* (*asic_dma_pool_zalloc)(struct hl_device *hdev, size_t size,
+				gfp_t mem_flags, dma_addr_t *dma_handle);
+	void (*asic_dma_pool_free)(struct hl_device *hdev, void *vaddr,
+				dma_addr_t dma_addr);
+	void* (*cpu_accessible_dma_pool_alloc)(struct hl_device *hdev,
+				size_t size, dma_addr_t *dma_handle);
+	void (*cpu_accessible_dma_pool_free)(struct hl_device *hdev,
+				size_t size, void *vaddr);
+	void (*hl_dma_unmap_sg)(struct hl_device *hdev,
+				struct scatterlist *sgl, int nents,
+				enum dma_data_direction dir);
+	int (*cs_parser)(struct hl_device *hdev, struct hl_cs_parser *parser);
+	int (*asic_dma_map_sg)(struct hl_device *hdev,
+				struct scatterlist *sgl, int nents,
+				enum dma_data_direction dir);
+	u32 (*get_dma_desc_list_size)(struct hl_device *hdev,
+					struct sg_table *sgt);
+	void (*add_end_of_cb_packets)(struct hl_device *hdev,
+					u64 kernel_address, u32 len,
+					u64 cq_addr, u32 cq_val, u32 msix_num,
+					bool eb);
+	void (*update_eq_ci)(struct hl_device *hdev, u32 val);
+	int (*context_switch)(struct hl_device *hdev, u32 asid);
+	void (*restore_phase_topology)(struct hl_device *hdev);
+	int (*debugfs_read32)(struct hl_device *hdev, u64 addr, u32 *val);
+	int (*debugfs_write32)(struct hl_device *hdev, u64 addr, u32 val);
+	int (*debugfs_read64)(struct hl_device *hdev, u64 addr, u64 *val);
+	int (*debugfs_write64)(struct hl_device *hdev, u64 addr, u64 val);
+	void (*add_device_attr)(struct hl_device *hdev,
+				struct attribute_group *dev_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);
+	void (*write_pte)(struct hl_device *hdev, u64 addr, u64 val);
+	int (*mmu_invalidate_cache)(struct hl_device *hdev, bool is_hard,
+					u32 flags);
+	int (*mmu_invalidate_cache_range)(struct hl_device *hdev, bool is_hard,
+			u32 asid, u64 va, u64 size);
+	int (*send_heartbeat)(struct hl_device *hdev);
+	void (*enable_clock_gating)(struct hl_device *hdev);
+	void (*disable_clock_gating)(struct hl_device *hdev);
+	int (*debug_coresight)(struct hl_device *hdev, void *data);
+	bool (*is_device_idle)(struct hl_device *hdev, u32 *mask,
+				struct seq_file *s);
+	int (*soft_reset_late_init)(struct hl_device *hdev);
+	void (*hw_queues_lock)(struct hl_device *hdev);
+	void (*hw_queues_unlock)(struct hl_device *hdev);
+	u32 (*get_pci_id)(struct hl_device *hdev);
+	int (*get_eeprom_data)(struct hl_device *hdev, void *data,
+				size_t max_size);
+	int (*send_cpu_message)(struct hl_device *hdev, u32 *msg,
+				u16 len, u32 timeout, long *result);
+	enum hl_device_hw_state (*get_hw_state)(struct hl_device *hdev);
+	int (*pci_bars_map)(struct hl_device *hdev);
+	u64 (*set_dram_bar_base)(struct hl_device *hdev, u64 addr);
+	int (*init_iatu)(struct hl_device *hdev);
+	u32 (*rreg)(struct hl_device *hdev, u32 reg);
+	void (*wreg)(struct hl_device *hdev, u32 reg, u32 val);
+	void (*halt_coresight)(struct hl_device *hdev);
+	int (*get_clk_rate)(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk);
+	u32 (*get_queue_id_for_cq)(struct hl_device *hdev, u32 cq_idx);
+	void (*read_device_fw_version)(struct hl_device *hdev,
+					enum hl_fw_component fwc);
+	int (*load_firmware_to_device)(struct hl_device *hdev);
+	int (*load_boot_fit_to_device)(struct hl_device *hdev);
+	u32 (*get_signal_cb_size)(struct hl_device *hdev);
+	u32 (*get_wait_cb_size)(struct hl_device *hdev);
+	void (*gen_signal_cb)(struct hl_device *hdev, void *data, u16 sob_id);
+	void (*gen_wait_cb)(struct hl_device *hdev, void *data, u16 sob_id,
+				u16 sob_val, u16 mon_id, u32 q_idx);
+	void (*reset_sob)(struct hl_device *hdev, void *data);
+	void (*set_dma_mask_from_fw)(struct hl_device *hdev);
+	u64 (*get_device_time)(struct hl_device *hdev);
+};
+
+
+/*
+ * CONTEXTS
+ */
+
+#define HL_KERNEL_ASID_ID	0
+
+/**
+ * struct hl_va_range - virtual addresses range.
+ * @lock: protects the virtual addresses list.
+ * @list: list of virtual addresses blocks available for mappings.
+ * @start_addr: range start address.
+ * @end_addr: range end address.
+ */
+struct hl_va_range {
+	struct mutex		lock;
+	struct list_head	list;
+	u64			start_addr;
+	u64			end_addr;
+};
+
+/**
+ * struct hl_ctx - user/kernel context.
+ * @mem_hash: holds mapping from virtual address to virtual memory area
+ *		descriptor (hl_vm_phys_pg_list or hl_userptr).
+ * @mmu_shadow_hash: holds a mapping from shadow address to pgt_info structure.
+ * @hpriv: pointer to the private (Kernel Driver) data of the process (fd).
+ * @hdev: pointer to the device structure.
+ * @refcount: reference counter for the context. Context is released only when
+ *		this hits 0l. It is incremented on CS and CS_WAIT.
+ * @cs_pending: array of DMA fence objects representing pending CS.
+ * @host_va_range: holds available virtual addresses for host mappings.
+ * @host_huge_va_range: holds available virtual addresses for host mappings
+ *                      with huge pages.
+ * @dram_va_range: holds available virtual addresses for DRAM mappings.
+ * @mem_hash_lock: protects the mem_hash.
+ * @mmu_lock: protects the MMU page tables. Any change to the PGT, modifying the
+ *            MMU hash or walking the PGT requires talking this lock.
+ * @debugfs_list: node in debugfs list of contexts.
+ * @cs_sequence: sequence number for CS. Value is assigned to a CS and passed
+ *			to user so user could inquire about CS. It is used as
+ *			index to cs_pending array.
+ * @dram_default_hops: array that holds all hops addresses needed for default
+ *                     DRAM mapping.
+ * @cs_lock: spinlock to protect cs_sequence.
+ * @dram_phys_mem: amount of used physical DRAM memory by this context.
+ * @thread_ctx_switch_token: token to prevent multiple threads of the same
+ *				context	from running the context switch phase.
+ *				Only a single thread should run it.
+ * @thread_ctx_switch_wait_token: token to prevent the threads that didn't run
+ *				the context switch phase from moving to their
+ *				execution phase before the context switch phase
+ *				has finished.
+ * @asid: context's unique address space ID in the device's MMU.
+ * @handle: context's opaque handle for user
+ */
+struct hl_ctx {
+	DECLARE_HASHTABLE(mem_hash, MEM_HASH_TABLE_BITS);
+	DECLARE_HASHTABLE(mmu_shadow_hash, MMU_HASH_TABLE_BITS);
+	struct hl_fpriv		*hpriv;
+	struct hl_device	*hdev;
+	struct kref		refcount;
+	struct dma_fence	**cs_pending;
+	struct hl_va_range	*host_va_range;
+	struct hl_va_range	*host_huge_va_range;
+	struct hl_va_range	*dram_va_range;
+	struct mutex		mem_hash_lock;
+	struct mutex		mmu_lock;
+	struct list_head	debugfs_list;
+	struct hl_cs_counters	cs_counters;
+	u64			cs_sequence;
+	u64			*dram_default_hops;
+	spinlock_t		cs_lock;
+	atomic64_t		dram_phys_mem;
+	atomic_t		thread_ctx_switch_token;
+	u32			thread_ctx_switch_wait_token;
+	u32			asid;
+	u32			handle;
+};
+
+/**
+ * struct hl_ctx_mgr - for handling multiple contexts.
+ * @ctx_lock: protects ctx_handles.
+ * @ctx_handles: idr to hold all ctx handles.
+ */
+struct hl_ctx_mgr {
+	struct mutex		ctx_lock;
+	struct idr		ctx_handles;
+};
+
+
+
+/*
+ * COMMAND SUBMISSIONS
+ */
+
+/**
+ * struct hl_userptr - memory mapping chunk information
+ * @vm_type: type of the VM.
+ * @job_node: linked-list node for hanging the object on the Job's list.
+ * @vec: pointer to the frame vector.
+ * @sgt: pointer to the scatter-gather table that holds the pages.
+ * @dir: for DMA unmapping, the direction must be supplied, so save it.
+ * @debugfs_list: node in debugfs list of command submissions.
+ * @addr: user-space virtual address of the start of the memory area.
+ * @size: size of the memory area to pin & map.
+ * @dma_mapped: true if the SG was mapped to DMA addresses, false otherwise.
+ */
+struct hl_userptr {
+	enum vm_type_t		vm_type; /* must be first */
+	struct list_head	job_node;
+	struct frame_vector	*vec;
+	struct sg_table		*sgt;
+	enum dma_data_direction dir;
+	struct list_head	debugfs_list;
+	u64			addr;
+	u32			size;
+	u8			dma_mapped;
+};
+
+/**
+ * struct hl_cs - command submission.
+ * @jobs_in_queue_cnt: per each queue, maintain counter of submitted jobs.
+ * @ctx: the context this CS belongs to.
+ * @job_list: list of the CS's jobs in the various queues.
+ * @job_lock: spinlock for the CS's jobs list. Needed for free_job.
+ * @refcount: reference counter for usage of the CS.
+ * @fence: pointer to the fence object of this CS.
+ * @signal_fence: pointer to the fence object of the signal CS (used by wait
+ *                CS only).
+ * @finish_work: workqueue object to run when CS is completed by H/W.
+ * @work_tdr: delayed work node for TDR.
+ * @mirror_node : node in device mirror list of command submissions.
+ * @debugfs_list: node in debugfs list of command submissions.
+ * @sequence: the sequence number of this CS.
+ * @type: CS_TYPE_*.
+ * @submitted: true if CS was submitted to H/W.
+ * @completed: true if CS was completed by device.
+ * @timedout : true if CS was timedout.
+ * @tdr_active: true if TDR was activated for this CS (to prevent
+ *		double TDR activation).
+ * @aborted: true if CS was aborted due to some device error.
+ */
+struct hl_cs {
+	u16			*jobs_in_queue_cnt;
+	struct hl_ctx		*ctx;
+	struct list_head	job_list;
+	spinlock_t		job_lock;
+	struct kref		refcount;
+	struct dma_fence	*fence;
+	struct dma_fence	*signal_fence;
+	struct work_struct	finish_work;
+	struct delayed_work	work_tdr;
+	struct list_head	mirror_node;
+	struct list_head	debugfs_list;
+	u64			sequence;
+	enum hl_cs_type		type;
+	u8			submitted;
+	u8			completed;
+	u8			timedout;
+	u8			tdr_active;
+	u8			aborted;
+};
+
+/**
+ * struct hl_cs_job - command submission job.
+ * @cs_node: the node to hang on the CS jobs list.
+ * @cs: the CS this job belongs to.
+ * @user_cb: the CB we got from the user.
+ * @patched_cb: in case of patching, this is internal CB which is submitted on
+ *		the queue instead of the CB we got from the IOCTL.
+ * @finish_work: workqueue object to run when job is completed.
+ * @userptr_list: linked-list of userptr mappings that belong to this job and
+ *			wait for completion.
+ * @debugfs_list: node in debugfs list of command submission jobs.
+ * @queue_type: the type of the H/W queue this job is submitted to.
+ * @id: the id of this job inside a CS.
+ * @hw_queue_id: the id of the H/W queue this job is submitted to.
+ * @user_cb_size: the actual size of the CB we got from the user.
+ * @job_cb_size: the actual size of the CB that we put on the queue.
+ * @is_kernel_allocated_cb: true if the CB handle we got from the user holds a
+ *                          handle to a kernel-allocated CB object, false
+ *                          otherwise (SRAM/DRAM/host address).
+ * @contains_dma_pkt: whether the JOB contains at least one DMA packet. This
+ *                    info is needed later, when adding the 2xMSG_PROT at the
+ *                    end of the JOB, to know which barriers to put in the
+ *                    MSG_PROT packets. Relevant only for GAUDI as GOYA doesn't
+ *                    have streams so the engine can't be busy by another
+ *                    stream.
+ */
+struct hl_cs_job {
+	struct list_head	cs_node;
+	struct hl_cs		*cs;
+	struct hl_cb		*user_cb;
+	struct hl_cb		*patched_cb;
+	struct work_struct	finish_work;
+	struct list_head	userptr_list;
+	struct list_head	debugfs_list;
+	enum hl_queue_type	queue_type;
+	u32			id;
+	u32			hw_queue_id;
+	u32			user_cb_size;
+	u32			job_cb_size;
+	u8			is_kernel_allocated_cb;
+	u8			contains_dma_pkt;
+};
+
+/**
+ * struct hl_cs_parser - command submission parser properties.
+ * @user_cb: the CB we got from the user.
+ * @patched_cb: in case of patching, this is internal CB which is submitted on
+ *		the queue instead of the CB we got from the IOCTL.
+ * @job_userptr_list: linked-list of userptr mappings that belong to the related
+ *			job and wait for completion.
+ * @cs_sequence: the sequence number of the related CS.
+ * @queue_type: the type of the H/W queue this job is submitted to.
+ * @ctx_id: the ID of the context the related CS belongs to.
+ * @hw_queue_id: the id of the H/W queue this job is submitted to.
+ * @user_cb_size: the actual size of the CB we got from the user.
+ * @patched_cb_size: the size of the CB after parsing.
+ * @job_id: the id of the related job inside the related CS.
+ * @is_kernel_allocated_cb: true if the CB handle we got from the user holds a
+ *                          handle to a kernel-allocated CB object, false
+ *                          otherwise (SRAM/DRAM/host address).
+ * @contains_dma_pkt: whether the JOB contains at least one DMA packet. This
+ *                    info is needed later, when adding the 2xMSG_PROT at the
+ *                    end of the JOB, to know which barriers to put in the
+ *                    MSG_PROT packets. Relevant only for GAUDI as GOYA doesn't
+ *                    have streams so the engine can't be busy by another
+ *                    stream.
+ */
+struct hl_cs_parser {
+	struct hl_cb		*user_cb;
+	struct hl_cb		*patched_cb;
+	struct list_head	*job_userptr_list;
+	u64			cs_sequence;
+	enum hl_queue_type	queue_type;
+	u32			ctx_id;
+	u32			hw_queue_id;
+	u32			user_cb_size;
+	u32			patched_cb_size;
+	u8			job_id;
+	u8			is_kernel_allocated_cb;
+	u8			contains_dma_pkt;
+};
+
+
+/*
+ * MEMORY STRUCTURE
+ */
+
+/**
+ * struct hl_vm_hash_node - hash element from virtual address to virtual
+ *				memory area descriptor (hl_vm_phys_pg_list or
+ *				hl_userptr).
+ * @node: node to hang on the hash table in context object.
+ * @vaddr: key virtual address.
+ * @ptr: value pointer (hl_vm_phys_pg_list or hl_userptr).
+ */
+struct hl_vm_hash_node {
+	struct hlist_node	node;
+	u64			vaddr;
+	void			*ptr;
+};
+
+/**
+ * struct hl_vm_phys_pg_pack - physical page pack.
+ * @vm_type: describes the type of the virtual area descriptor.
+ * @pages: the physical page array.
+ * @npages: num physical pages in the pack.
+ * @total_size: total size of all the pages in this list.
+ * @mapping_cnt: number of shared mappings.
+ * @asid: the context related to this list.
+ * @page_size: size of each page in the pack.
+ * @flags: HL_MEM_* flags related to this list.
+ * @handle: the provided handle related to this list.
+ * @offset: offset from the first page.
+ * @contiguous: is contiguous physical memory.
+ * @created_from_userptr: is product of host virtual address.
+ */
+struct hl_vm_phys_pg_pack {
+	enum vm_type_t		vm_type; /* must be first */
+	u64			*pages;
+	u64			npages;
+	u64			total_size;
+	atomic_t		mapping_cnt;
+	u32			asid;
+	u32			page_size;
+	u32			flags;
+	u32			handle;
+	u32			offset;
+	u8			contiguous;
+	u8			created_from_userptr;
+};
+
+/**
+ * struct hl_vm_va_block - virtual range block information.
+ * @node: node to hang on the virtual range list in context object.
+ * @start: virtual range start address.
+ * @end: virtual range end address.
+ * @size: virtual range size.
+ */
+struct hl_vm_va_block {
+	struct list_head	node;
+	u64			start;
+	u64			end;
+	u64			size;
+};
+
+/**
+ * struct hl_vm - virtual memory manager for MMU.
+ * @dram_pg_pool: pool for DRAM physical pages of 2MB.
+ * @dram_pg_pool_refcount: reference counter for the pool usage.
+ * @idr_lock: protects the phys_pg_list_handles.
+ * @phys_pg_pack_handles: idr to hold all device allocations handles.
+ * @init_done: whether initialization was done. We need this because VM
+ *		initialization might be skipped during device initialization.
+ */
+struct hl_vm {
+	struct gen_pool		*dram_pg_pool;
+	struct kref		dram_pg_pool_refcount;
+	spinlock_t		idr_lock;
+	struct idr		phys_pg_pack_handles;
+	u8			init_done;
+};
+
+
+/*
+ * DEBUG, PROFILING STRUCTURE
+ */
+
+/**
+ * struct hl_debug_params - Coresight debug parameters.
+ * @input: pointer to component specific input parameters.
+ * @output: pointer to component specific output parameters.
+ * @output_size: size of output buffer.
+ * @reg_idx: relevant register ID.
+ * @op: component operation to execute.
+ * @enable: true if to enable component debugging, false otherwise.
+ */
+struct hl_debug_params {
+	void *input;
+	void *output;
+	u32 output_size;
+	u32 reg_idx;
+	u32 op;
+	bool enable;
+};
+
+/*
+ * FILE PRIVATE STRUCTURE
+ */
+
+/**
+ * struct hl_fpriv - process information stored in FD private data.
+ * @hdev: habanalabs device structure.
+ * @filp: pointer to the given file structure.
+ * @taskpid: current process ID.
+ * @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.
+ * @debugfs_list: list of relevant ASIC debugfs.
+ * @dev_node: node in the device list of file private data
+ * @refcount: number of related contexts.
+ * @restore_phase_mutex: lock for context switch and restore phase.
+ * @is_control: true for control device, false otherwise
+ */
+struct hl_fpriv {
+	struct hl_device	*hdev;
+	struct file		*filp;
+	struct pid		*taskpid;
+	struct hl_ctx		*ctx;
+	struct hl_ctx_mgr	ctx_mgr;
+	struct hl_cb_mgr	cb_mgr;
+	struct list_head	debugfs_list;
+	struct list_head	dev_node;
+	struct kref		refcount;
+	struct mutex		restore_phase_mutex;
+	u8			is_control;
+};
+
+
+/*
+ * DebugFS
+ */
+
+/**
+ * struct hl_info_list - debugfs file ops.
+ * @name: file name.
+ * @show: function to output information.
+ * @write: function to write to the file.
+ */
+struct hl_info_list {
+	const char	*name;
+	int		(*show)(struct seq_file *s, void *data);
+	ssize_t		(*write)(struct file *file, const char __user *buf,
+				size_t count, loff_t *f_pos);
+};
+
+/**
+ * struct hl_debugfs_entry - debugfs dentry wrapper.
+ * @dent: base debugfs entry structure.
+ * @info_ent: dentry realted ops.
+ * @dev_entry: ASIC specific debugfs manager.
+ */
+struct hl_debugfs_entry {
+	struct dentry			*dent;
+	const struct hl_info_list	*info_ent;
+	struct hl_dbg_device_entry	*dev_entry;
+};
+
+/**
+ * struct hl_dbg_device_entry - ASIC specific debugfs manager.
+ * @root: root dentry.
+ * @hdev: habanalabs device structure.
+ * @entry_arr: array of available hl_debugfs_entry.
+ * @file_list: list of available debugfs files.
+ * @file_mutex: protects file_list.
+ * @cb_list: list of available CBs.
+ * @cb_spinlock: protects cb_list.
+ * @cs_list: list of available CSs.
+ * @cs_spinlock: protects cs_list.
+ * @cs_job_list: list of available CB jobs.
+ * @cs_job_spinlock: protects cs_job_list.
+ * @userptr_list: list of available userptrs (virtual memory chunk descriptor).
+ * @userptr_spinlock: protects userptr_list.
+ * @ctx_mem_hash_list: list of available contexts with MMU mappings.
+ * @ctx_mem_hash_spinlock: protects cb_list.
+ * @addr: next address to read/write from/to in read/write32.
+ * @mmu_addr: next virtual address to translate to physical address in mmu_show.
+ * @mmu_asid: ASID to use while translating in mmu_show.
+ * @i2c_bus: generic u8 debugfs file for bus value to use in i2c_data_read.
+ * @i2c_bus: generic u8 debugfs file for address value to use in i2c_data_read.
+ * @i2c_bus: generic u8 debugfs file for register value to use in i2c_data_read.
+ */
+struct hl_dbg_device_entry {
+	struct dentry			*root;
+	struct hl_device		*hdev;
+	struct hl_debugfs_entry		*entry_arr;
+	struct list_head		file_list;
+	struct mutex			file_mutex;
+	struct list_head		cb_list;
+	spinlock_t			cb_spinlock;
+	struct list_head		cs_list;
+	spinlock_t			cs_spinlock;
+	struct list_head		cs_job_list;
+	spinlock_t			cs_job_spinlock;
+	struct list_head		userptr_list;
+	spinlock_t			userptr_spinlock;
+	struct list_head		ctx_mem_hash_list;
+	spinlock_t			ctx_mem_hash_spinlock;
+	u64				addr;
+	u64				mmu_addr;
+	u32				mmu_asid;
+	u8				i2c_bus;
+	u8				i2c_addr;
+	u8				i2c_reg;
+};
+
+
+/*
+ * DEVICES
+ */
+
+/* Theoretical limit only. A single host can only contain up to 4 or 8 PCIe
+ * x16 cards. In extreme cases, there are hosts that can accommodate 16 cards.
+ */
+#define HL_MAX_MINORS	256
+
+/*
+ * Registers read & write functions.
+ */
+
+u32 hl_rreg(struct hl_device *hdev, u32 reg);
+void hl_wreg(struct hl_device *hdev, u32 reg, u32 val);
+
+#define RREG32(reg) hdev->asic_funcs->rreg(hdev, (reg))
+#define WREG32(reg, v) hdev->asic_funcs->wreg(hdev, (reg), (v))
+#define DREG32(reg) pr_info("REGISTER: " #reg " : 0x%08X\n",	\
+			hdev->asic_funcs->rreg(hdev, (reg)))
+
+#define WREG32_P(reg, val, mask)				\
+	do {							\
+		u32 tmp_ = RREG32(reg);				\
+		tmp_ &= (mask);					\
+		tmp_ |= ((val) & ~(mask));			\
+		WREG32(reg, tmp_);				\
+	} while (0)
+#define WREG32_AND(reg, and) WREG32_P(reg, 0, and)
+#define WREG32_OR(reg, or) WREG32_P(reg, or, ~(or))
+
+#define RMWREG32(reg, val, mask)				\
+	do {							\
+		u32 tmp_ = RREG32(reg);				\
+		tmp_ &= ~(mask);				\
+		tmp_ |= ((val) << __ffs(mask));			\
+		WREG32(reg, tmp_);				\
+	} while (0)
+
+#define RREG32_MASK(reg, mask) ((RREG32(reg) & mask) >> __ffs(mask))
+
+#define REG_FIELD_SHIFT(reg, field) reg##_##field##_SHIFT
+#define REG_FIELD_MASK(reg, field) reg##_##field##_MASK
+#define WREG32_FIELD(reg, offset, field, val)	\
+	WREG32(mm##reg + offset, (RREG32(mm##reg + offset) & \
+				~REG_FIELD_MASK(reg, field)) | \
+				(val) << REG_FIELD_SHIFT(reg, field))
+
+/* Timeout should be longer when working with simulator but cap the
+ * increased timeout to some maximum
+ */
+#define hl_poll_timeout(hdev, addr, val, cond, sleep_us, timeout_us) \
+({ \
+	ktime_t __timeout; \
+	if (hdev->pdev) \
+		__timeout = ktime_add_us(ktime_get(), timeout_us); \
+	else \
+		__timeout = ktime_add_us(ktime_get(),\
+				min((u64)(timeout_us * 10), \
+					(u64) HL_SIM_MAX_TIMEOUT_US)); \
+	might_sleep_if(sleep_us); \
+	for (;;) { \
+		(val) = RREG32(addr); \
+		if (cond) \
+			break; \
+		if (timeout_us && ktime_compare(ktime_get(), __timeout) > 0) { \
+			(val) = RREG32(addr); \
+			break; \
+		} \
+		if (sleep_us) \
+			usleep_range((sleep_us >> 2) + 1, sleep_us); \
+	} \
+	(cond) ? 0 : -ETIMEDOUT; \
+})
+
+/*
+ * address in this macro points always to a memory location in the
+ * host's (server's) memory. That location is updated asynchronously
+ * either by the direct access of the device or by another core.
+ *
+ * To work both in LE and BE architectures, we need to distinguish between the
+ * two states (device or another core updates the memory location). Therefore,
+ * if mem_written_by_device is true, the host memory being polled will be
+ * updated directly by the device. If false, the host memory being polled will
+ * be updated by host CPU. Required so host knows whether or not the memory
+ * might need to be byte-swapped before returning value to caller.
+ */
+#define hl_poll_timeout_memory(hdev, addr, val, cond, sleep_us, timeout_us, \
+				mem_written_by_device) \
+({ \
+	ktime_t __timeout; \
+	if (hdev->pdev) \
+		__timeout = ktime_add_us(ktime_get(), timeout_us); \
+	else \
+		__timeout = ktime_add_us(ktime_get(),\
+				min((u64)(timeout_us * 10), \
+					(u64) HL_SIM_MAX_TIMEOUT_US)); \
+	might_sleep_if(sleep_us); \
+	for (;;) { \
+		/* Verify we read updates done by other cores or by device */ \
+		mb(); \
+		(val) = *((u32 *) (uintptr_t) (addr)); \
+		if (mem_written_by_device) \
+			(val) = le32_to_cpu(*(__le32 *) &(val)); \
+		if (cond) \
+			break; \
+		if (timeout_us && ktime_compare(ktime_get(), __timeout) > 0) { \
+			(val) = *((u32 *) (uintptr_t) (addr)); \
+			if (mem_written_by_device) \
+				(val) = le32_to_cpu(*(__le32 *) &(val)); \
+			break; \
+		} \
+		if (sleep_us) \
+			usleep_range((sleep_us >> 2) + 1, sleep_us); \
+	} \
+	(cond) ? 0 : -ETIMEDOUT; \
+})
+
+#define hl_poll_timeout_device_memory(hdev, addr, val, cond, sleep_us, \
+					timeout_us) \
+({ \
+	ktime_t __timeout; \
+	if (hdev->pdev) \
+		__timeout = ktime_add_us(ktime_get(), timeout_us); \
+	else \
+		__timeout = ktime_add_us(ktime_get(),\
+				min((u64)(timeout_us * 10), \
+					(u64) HL_SIM_MAX_TIMEOUT_US)); \
+	might_sleep_if(sleep_us); \
+	for (;;) { \
+		(val) = readl(addr); \
+		if (cond) \
+			break; \
+		if (timeout_us && ktime_compare(ktime_get(), __timeout) > 0) { \
+			(val) = readl(addr); \
+			break; \
+		} \
+		if (sleep_us) \
+			usleep_range((sleep_us >> 2) + 1, sleep_us); \
+	} \
+	(cond) ? 0 : -ETIMEDOUT; \
+})
+
+struct hwmon_chip_info;
+
+/**
+ * struct hl_device_reset_work - reset workqueue task wrapper.
+ * @reset_work: reset work to be done.
+ * @hdev: habanalabs device structure.
+ */
+struct hl_device_reset_work {
+	struct work_struct		reset_work;
+	struct hl_device		*hdev;
+};
+
+/**
+ * struct hl_device_idle_busy_ts - used for calculating device utilization rate.
+ * @idle_to_busy_ts: timestamp where device changed from idle to busy.
+ * @busy_to_idle_ts: timestamp where device changed from busy to idle.
+ */
+struct hl_device_idle_busy_ts {
+	ktime_t				idle_to_busy_ts;
+	ktime_t				busy_to_idle_ts;
+};
+
+/**
+ * struct hl_device - habanalabs device structure.
+ * @pdev: pointer to PCI device, can be NULL in case of simulator device.
+ * @pcie_bar_phys: array of available PCIe bars physical addresses.
+ *		   (required only for PCI address match mode)
+ * @pcie_bar: array of available PCIe bars virtual addresses.
+ * @rmmio: configuration area address on SRAM.
+ * @cdev: related char device.
+ * @cdev_ctrl: char device for control operations only (INFO IOCTL)
+ * @dev: related kernel basic device structure.
+ * @dev_ctrl: related kernel device structure for the control device
+ * @work_freq: delayed work to lower device frequency if possible.
+ * @work_heartbeat: delayed work for ArmCP is-alive check.
+ * @asic_name: ASIC specific nmae.
+ * @asic_type: ASIC specific type.
+ * @completion_queue: array of hl_cq.
+ * @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.
+ * @kernel_ctx: Kernel driver context structure.
+ * @kernel_queues: array of hl_hw_queue.
+ * @hw_queues_mirror_list: CS mirror list for TDR.
+ * @hw_queues_mirror_lock: protects hw_queues_mirror_list.
+ * @kernel_cb_mgr: command buffer manager for creating/destroying/handling CGs.
+ * @event_queue: event queue for IRQ from ArmCP.
+ * @dma_pool: DMA pool for small allocations.
+ * @cpu_accessible_dma_mem: Host <-> ArmCP shared memory CPU address.
+ * @cpu_accessible_dma_address: Host <-> ArmCP shared memory DMA address.
+ * @cpu_accessible_dma_pool: Host <-> ArmCP shared memory pool.
+ * @asid_bitmap: holds used/available ASIDs.
+ * @asid_mutex: protects asid_bitmap.
+ * @send_cpu_message_lock: enforces only one message in Host <-> ArmCP queue.
+ * @debug_lock: protects critical section of setting debug mode for device
+ * @asic_prop: ASIC specific immutable properties.
+ * @asic_funcs: ASIC specific functions.
+ * @asic_specific: ASIC specific information to use only from ASIC files.
+ * @mmu_pgt_pool: pool of available MMU hops.
+ * @vm: virtual memory manager for MMU.
+ * @mmu_cache_lock: protects MMU cache invalidation as it can serve one context.
+ * @mmu_shadow_hop0: shadow mapping of the MMU hop 0 zone.
+ * @hwmon_dev: H/W monitor device.
+ * @pm_mng_profile: current power management profile.
+ * @hl_chip_info: ASIC's sensors information.
+ * @hl_debugfs: device's debugfs manager.
+ * @cb_pool: list of preallocated CBs.
+ * @cb_pool_lock: protects the CB pool.
+ * @fpriv_list: list of file private data structures. Each structure is created
+ *              when a user opens the device
+ * @fpriv_list_lock: protects the fpriv_list
+ * @compute_ctx: current compute context executing.
+ * @idle_busy_ts_arr: array to hold time stamps of transitions from idle to busy
+ *                    and vice-versa
+ * @aggregated_cs_counters: aggregated cs counters among all contexts
+ * @dram_used_mem: current DRAM memory consumption.
+ * @timeout_jiffies: device CS timeout value.
+ * @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
+ * @in_reset: is device in reset flow.
+ * @curr_pll_profile: current PLL profile.
+ * @cs_active_cnt: number of active command submissions on this device (active
+ *                 means already in H/W queues)
+ * @major: habanalabs kernel driver major.
+ * @high_pll: high PLL profile frequency.
+ * @soft_reset_cnt: number of soft reset since the driver was loaded.
+ * @hard_reset_cnt: number of hard reset since the driver was loaded.
+ * @idle_busy_ts_idx: index of current entry in idle_busy_ts_arr
+ * @id: device minor.
+ * @id_control: minor of the control device
+ * @cpu_pci_msb_addr: 50-bit extension bits for the device CPU's 40-bit
+ *                    addresses.
+ * @disabled: is device disabled.
+ * @late_init_done: is late init stage was done during initialization.
+ * @hwmon_initialized: is H/W monitor sensors was initialized.
+ * @hard_reset_pending: is there a hard reset work pending.
+ * @heartbeat: is heartbeat sanity check towards ArmCP enabled.
+ * @reset_on_lockup: true if a reset should be done in case of stuck CS, false
+ *                   otherwise.
+ * @dram_supports_virtual_memory: is MMU enabled towards DRAM.
+ * @dram_default_page_mapping: is DRAM default page mapping enabled.
+ * @pmmu_huge_range: is a different virtual addresses range used for PMMU with
+ *                   huge pages.
+ * @init_done: is the initialization of the device done.
+ * @mmu_enable: is MMU enabled.
+ * @mmu_huge_page_opt: is MMU huge pages optimization enabled.
+ * @clock_gating: is clock gating enabled.
+ * @device_cpu_disabled: is the device CPU disabled (due to timeouts)
+ * @dma_mask: the dma mask that was set for this device
+ * @in_debug: is device under debug. This, together with fpriv_list, enforces
+ *            that only a single user is configuring the debug 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.
+ * @sync_stream_queue_idx: helper index for sync stream queues initialization.
+ * @supports_coresight: is CoreSight supported.
+ * @supports_soft_reset: is soft reset supported.
+ */
+struct hl_device {
+	struct pci_dev			*pdev;
+	u64				pcie_bar_phys[HL_PCI_NUM_BARS];
+	void __iomem			*pcie_bar[HL_PCI_NUM_BARS];
+	void __iomem			*rmmio;
+	struct cdev			cdev;
+	struct cdev			cdev_ctrl;
+	struct device			*dev;
+	struct device			*dev_ctrl;
+	struct delayed_work		work_freq;
+	struct delayed_work		work_heartbeat;
+	char				asic_name[16];
+	enum hl_asic_type		asic_type;
+	struct hl_cq			*completion_queue;
+	struct workqueue_struct		**cq_wq;
+	struct workqueue_struct		*eq_wq;
+	struct hl_ctx			*kernel_ctx;
+	struct hl_hw_queue		*kernel_queues;
+	struct list_head		hw_queues_mirror_list;
+	spinlock_t			hw_queues_mirror_lock;
+	struct hl_cb_mgr		kernel_cb_mgr;
+	struct hl_eq			event_queue;
+	struct dma_pool			*dma_pool;
+	void				*cpu_accessible_dma_mem;
+	dma_addr_t			cpu_accessible_dma_address;
+	struct gen_pool			*cpu_accessible_dma_pool;
+	unsigned long			*asid_bitmap;
+	struct mutex			asid_mutex;
+	struct mutex			send_cpu_message_lock;
+	struct mutex			debug_lock;
+	struct asic_fixed_properties	asic_prop;
+	const struct hl_asic_funcs	*asic_funcs;
+	void				*asic_specific;
+	struct gen_pool			*mmu_pgt_pool;
+	struct hl_vm			vm;
+	struct mutex			mmu_cache_lock;
+	void				*mmu_shadow_hop0;
+	struct device			*hwmon_dev;
+	enum hl_pm_mng_profile		pm_mng_profile;
+	struct hwmon_chip_info		*hl_chip_info;
+
+	struct hl_dbg_device_entry	hl_debugfs;
+
+	struct list_head		cb_pool;
+	spinlock_t			cb_pool_lock;
+
+	struct list_head		fpriv_list;
+	struct mutex			fpriv_list_lock;
+
+	struct hl_ctx			*compute_ctx;
+
+	struct hl_device_idle_busy_ts	*idle_busy_ts_arr;
+
+	struct hl_cs_counters		aggregated_cs_counters;
+
+	atomic64_t			dram_used_mem;
+	u64				timeout_jiffies;
+	u64				max_power;
+	atomic_t			in_reset;
+	enum hl_pll_frequency		curr_pll_profile;
+	int				cs_active_cnt;
+	u32				major;
+	u32				high_pll;
+	u32				soft_reset_cnt;
+	u32				hard_reset_cnt;
+	u32				idle_busy_ts_idx;
+	u16				id;
+	u16				id_control;
+	u16				cpu_pci_msb_addr;
+	u8				disabled;
+	u8				late_init_done;
+	u8				hwmon_initialized;
+	u8				hard_reset_pending;
+	u8				heartbeat;
+	u8				reset_on_lockup;
+	u8				dram_supports_virtual_memory;
+	u8				dram_default_page_mapping;
+	u8				pmmu_huge_range;
+	u8				init_done;
+	u8				clock_gating;
+	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;
+	u8				sync_stream_queue_idx;
+	u8				supports_coresight;
+	u8				supports_soft_reset;
+
+	/* Parameters for bring-up */
+	u8				mmu_enable;
+	u8				mmu_huge_page_opt;
+	u8				cpu_enable;
+	u8				reset_pcilink;
+	u8				cpu_queues_enable;
+	u8				fw_loading;
+	u8				pldm;
+	u8				axi_drain;
+	u8				sram_scrambler_enable;
+	u8				dram_scrambler_enable;
+	u8				hard_reset_on_fw_events;
+	u8				bmc_enable;
+	u8				rl_enable;
+};
+
+
+/*
+ * IOCTLs
+ */
+
+/**
+ * typedef hl_ioctl_t - typedef for ioctl function in the driver
+ * @hpriv: pointer to the FD's private data, which contains state of
+ *		user process
+ * @data: pointer to the input/output arguments structure of the IOCTL
+ *
+ * Return: 0 for success, negative value for error
+ */
+typedef int hl_ioctl_t(struct hl_fpriv *hpriv, void *data);
+
+/**
+ * struct hl_ioctl_desc - describes an IOCTL entry of the driver.
+ * @cmd: the IOCTL code as created by the kernel macros.
+ * @func: pointer to the driver's function that should be called for this IOCTL.
+ */
+struct hl_ioctl_desc {
+	unsigned int cmd;
+	hl_ioctl_t *func;
+};
+
+
+/*
+ * Kernel module functions that can be accessed by entire module
+ */
+
+/**
+ * hl_mem_area_inside_range() - Checks whether address+size are inside a range.
+ * @address: The start address of the area we want to validate.
+ * @size: The size in bytes of the area we want to validate.
+ * @range_start_address: The start address of the valid range.
+ * @range_end_address: The end address of the valid range.
+ *
+ * Return: true if the area is inside the valid range, false otherwise.
+ */
+static inline bool hl_mem_area_inside_range(u64 address, u32 size,
+				u64 range_start_address, u64 range_end_address)
+{
+	u64 end_address = address + size;
+
+	if ((address >= range_start_address) &&
+			(end_address <= range_end_address) &&
+			(end_address > address))
+		return true;
+
+	return false;
+}
+
+/**
+ * hl_mem_area_crosses_range() - Checks whether address+size crossing a range.
+ * @address: The start address of the area we want to validate.
+ * @size: The size in bytes of the area we want to validate.
+ * @range_start_address: The start address of the valid range.
+ * @range_end_address: The end address of the valid range.
+ *
+ * Return: true if the area overlaps part or all of the valid range,
+ *		false otherwise.
+ */
+static inline bool hl_mem_area_crosses_range(u64 address, u32 size,
+				u64 range_start_address, u64 range_end_address)
+{
+	u64 end_address = address + size;
+
+	if ((address >= range_start_address) &&
+			(address < range_end_address))
+		return true;
+
+	if ((end_address >= range_start_address) &&
+			(end_address < range_end_address))
+		return true;
+
+	if ((address < range_start_address) &&
+			(end_address >= range_end_address))
+		return true;
+
+	return false;
+}
+
+int hl_device_open(struct inode *inode, struct file *filp);
+int hl_device_open_ctrl(struct inode *inode, struct file *filp);
+bool hl_device_disabled_or_in_reset(struct hl_device *hdev);
+enum hl_device_status hl_device_status(struct hl_device *hdev);
+int hl_device_set_debug_mode(struct hl_device *hdev, bool enable);
+int create_hdev(struct hl_device **dev, struct pci_dev *pdev,
+		enum hl_asic_type asic_type, int minor);
+void destroy_hdev(struct hl_device *hdev);
+int hl_hw_queues_create(struct hl_device *hdev);
+void hl_hw_queues_destroy(struct hl_device *hdev);
+int hl_hw_queue_send_cb_no_cmpl(struct hl_device *hdev, u32 hw_queue_id,
+				u32 cb_size, u64 cb_ptr);
+int hl_hw_queue_schedule_cs(struct hl_cs *cs);
+u32 hl_hw_queue_add_ptr(u32 ptr, u16 val);
+void hl_hw_queue_inc_ci_kernel(struct hl_device *hdev, u32 hw_queue_id);
+void hl_int_hw_queue_update_ci(struct hl_cs *cs);
+void hl_hw_queue_reset(struct hl_device *hdev, bool hard_reset);
+
+#define hl_queue_inc_ptr(p)		hl_hw_queue_add_ptr(p, 1)
+#define hl_pi_2_offset(pi)		((pi) & (HL_QUEUE_LENGTH - 1))
+
+int hl_cq_init(struct hl_device *hdev, struct hl_cq *q, u32 hw_queue_id);
+void hl_cq_fini(struct hl_device *hdev, struct hl_cq *q);
+int hl_eq_init(struct hl_device *hdev, struct hl_eq *q);
+void hl_eq_fini(struct hl_device *hdev, struct hl_eq *q);
+void hl_cq_reset(struct hl_device *hdev, struct hl_cq *q);
+void hl_eq_reset(struct hl_device *hdev, struct hl_eq *q);
+irqreturn_t hl_irq_handler_cq(int irq, void *arg);
+irqreturn_t hl_irq_handler_eq(int irq, void *arg);
+u32 hl_cq_inc_ptr(u32 ptr);
+
+int hl_asid_init(struct hl_device *hdev);
+void hl_asid_fini(struct hl_device *hdev);
+unsigned long hl_asid_alloc(struct hl_device *hdev);
+void hl_asid_free(struct hl_device *hdev, unsigned long asid);
+
+int hl_ctx_create(struct hl_device *hdev, struct hl_fpriv *hpriv);
+void hl_ctx_free(struct hl_device *hdev, struct hl_ctx *ctx);
+int hl_ctx_init(struct hl_device *hdev, struct hl_ctx *ctx, bool is_kernel_ctx);
+void hl_ctx_do_release(struct kref *ref);
+void hl_ctx_get(struct hl_device *hdev,	struct hl_ctx *ctx);
+int hl_ctx_put(struct hl_ctx *ctx);
+struct dma_fence *hl_ctx_get_fence(struct hl_ctx *ctx, u64 seq);
+void hl_ctx_mgr_init(struct hl_ctx_mgr *mgr);
+void hl_ctx_mgr_fini(struct hl_device *hdev, struct hl_ctx_mgr *mgr);
+
+int hl_device_init(struct hl_device *hdev, struct class *hclass);
+void hl_device_fini(struct hl_device *hdev);
+int hl_device_suspend(struct hl_device *hdev);
+int hl_device_resume(struct hl_device *hdev);
+int hl_device_reset(struct hl_device *hdev, bool hard_reset,
+			bool from_hard_reset_thread);
+void hl_hpriv_get(struct hl_fpriv *hpriv);
+void hl_hpriv_put(struct hl_fpriv *hpriv);
+int hl_device_set_frequency(struct hl_device *hdev, enum hl_pll_frequency freq);
+uint32_t hl_device_utilization(struct hl_device *hdev, uint32_t period_ms);
+
+int hl_build_hwmon_channel_info(struct hl_device *hdev,
+		struct armcp_sensor *sensors_arr);
+
+int hl_sysfs_init(struct hl_device *hdev);
+void hl_sysfs_fini(struct hl_device *hdev);
+
+int hl_hwmon_init(struct hl_device *hdev);
+void hl_hwmon_fini(struct hl_device *hdev);
+
+int hl_cb_create(struct hl_device *hdev, struct hl_cb_mgr *mgr, u32 cb_size,
+		u64 *handle, int ctx_id);
+int hl_cb_destroy(struct hl_device *hdev, struct hl_cb_mgr *mgr, u64 cb_handle);
+int hl_cb_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma);
+struct hl_cb *hl_cb_get(struct hl_device *hdev,	struct hl_cb_mgr *mgr,
+			u32 handle);
+void hl_cb_put(struct hl_cb *cb);
+void hl_cb_mgr_init(struct hl_cb_mgr *mgr);
+void hl_cb_mgr_fini(struct hl_device *hdev, struct hl_cb_mgr *mgr);
+struct hl_cb *hl_cb_kernel_create(struct hl_device *hdev, u32 cb_size);
+int hl_cb_pool_init(struct hl_device *hdev);
+int hl_cb_pool_fini(struct hl_device *hdev);
+
+void hl_cs_rollback_all(struct hl_device *hdev);
+struct hl_cs_job *hl_cs_allocate_job(struct hl_device *hdev,
+		enum hl_queue_type queue_type, bool is_kernel_allocated_cb);
+void hl_sob_reset_error(struct kref *ref);
+
+void goya_set_asic_funcs(struct hl_device *hdev);
+void gaudi_set_asic_funcs(struct hl_device *hdev);
+
+int hl_vm_ctx_init(struct hl_ctx *ctx);
+void hl_vm_ctx_fini(struct hl_ctx *ctx);
+
+int hl_vm_init(struct hl_device *hdev);
+void hl_vm_fini(struct hl_device *hdev);
+
+int hl_pin_host_memory(struct hl_device *hdev, u64 addr, u64 size,
+			struct hl_userptr *userptr);
+void hl_unpin_host_memory(struct hl_device *hdev, struct hl_userptr *userptr);
+void hl_userptr_delete_list(struct hl_device *hdev,
+				struct list_head *userptr_list);
+bool hl_userptr_is_pinned(struct hl_device *hdev, u64 addr, u32 size,
+				struct list_head *userptr_list,
+				struct hl_userptr **userptr);
+
+int hl_mmu_init(struct hl_device *hdev);
+void hl_mmu_fini(struct hl_device *hdev);
+int hl_mmu_ctx_init(struct hl_ctx *ctx);
+void hl_mmu_ctx_fini(struct hl_ctx *ctx);
+int hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr,
+		u32 page_size, bool flush_pte);
+int hl_mmu_unmap(struct hl_ctx *ctx, u64 virt_addr, u32 page_size,
+		bool flush_pte);
+void hl_mmu_swap_out(struct hl_ctx *ctx);
+void hl_mmu_swap_in(struct hl_ctx *ctx);
+
+int hl_fw_load_fw_to_device(struct hl_device *hdev, const char *fw_name,
+				void __iomem *dst);
+int hl_fw_send_pci_access_msg(struct hl_device *hdev, u32 opcode);
+int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
+				u16 len, u32 timeout, long *result);
+int hl_fw_unmask_irq(struct hl_device *hdev, u16 event_type);
+int hl_fw_unmask_irq_arr(struct hl_device *hdev, const u32 *irq_arr,
+		size_t irq_arr_size);
+int hl_fw_test_cpu_queue(struct hl_device *hdev);
+void *hl_fw_cpu_accessible_dma_pool_alloc(struct hl_device *hdev, size_t size,
+						dma_addr_t *dma_handle);
+void hl_fw_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size,
+					void *vaddr);
+int hl_fw_send_heartbeat(struct hl_device *hdev);
+int hl_fw_armcp_info_get(struct hl_device *hdev);
+int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size);
+int hl_fw_init_cpu(struct hl_device *hdev, u32 cpu_boot_status_reg,
+			u32 msg_to_cpu_reg, u32 cpu_msg_status_reg,
+			u32 boot_err0_reg, bool skip_bmc,
+			u32 cpu_timeout, u32 boot_fit_timeout);
+
+int hl_pci_bars_map(struct hl_device *hdev, const char * const name[3],
+			bool is_wc[3]);
+int hl_pci_iatu_write(struct hl_device *hdev, u32 addr, u32 data);
+int hl_pci_set_dram_bar_base(struct hl_device *hdev, u8 inbound_region, u8 bar,
+				u64 addr);
+int hl_pci_set_inbound_region(struct hl_device *hdev, u8 region,
+		struct hl_inbound_pci_region *pci_region);
+int hl_pci_set_outbound_region(struct hl_device *hdev,
+		struct hl_outbound_pci_region *pci_region);
+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, u64 value);
+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);
+
+#ifdef CONFIG_DEBUG_FS
+
+void hl_debugfs_init(void);
+void hl_debugfs_fini(void);
+void hl_debugfs_add_device(struct hl_device *hdev);
+void hl_debugfs_remove_device(struct hl_device *hdev);
+void hl_debugfs_add_file(struct hl_fpriv *hpriv);
+void hl_debugfs_remove_file(struct hl_fpriv *hpriv);
+void hl_debugfs_add_cb(struct hl_cb *cb);
+void hl_debugfs_remove_cb(struct hl_cb *cb);
+void hl_debugfs_add_cs(struct hl_cs *cs);
+void hl_debugfs_remove_cs(struct hl_cs *cs);
+void hl_debugfs_add_job(struct hl_device *hdev, struct hl_cs_job *job);
+void hl_debugfs_remove_job(struct hl_device *hdev, struct hl_cs_job *job);
+void hl_debugfs_add_userptr(struct hl_device *hdev, struct hl_userptr *userptr);
+void hl_debugfs_remove_userptr(struct hl_device *hdev,
+				struct hl_userptr *userptr);
+void hl_debugfs_add_ctx_mem_hash(struct hl_device *hdev, struct hl_ctx *ctx);
+void hl_debugfs_remove_ctx_mem_hash(struct hl_device *hdev, struct hl_ctx *ctx);
+
+#else
+
+static inline void __init hl_debugfs_init(void)
+{
+}
+
+static inline void hl_debugfs_fini(void)
+{
+}
+
+static inline void hl_debugfs_add_device(struct hl_device *hdev)
+{
+}
+
+static inline void hl_debugfs_remove_device(struct hl_device *hdev)
+{
+}
+
+static inline void hl_debugfs_add_file(struct hl_fpriv *hpriv)
+{
+}
+
+static inline void hl_debugfs_remove_file(struct hl_fpriv *hpriv)
+{
+}
+
+static inline void hl_debugfs_add_cb(struct hl_cb *cb)
+{
+}
+
+static inline void hl_debugfs_remove_cb(struct hl_cb *cb)
+{
+}
+
+static inline void hl_debugfs_add_cs(struct hl_cs *cs)
+{
+}
+
+static inline void hl_debugfs_remove_cs(struct hl_cs *cs)
+{
+}
+
+static inline void hl_debugfs_add_job(struct hl_device *hdev,
+					struct hl_cs_job *job)
+{
+}
+
+static inline void hl_debugfs_remove_job(struct hl_device *hdev,
+					struct hl_cs_job *job)
+{
+}
+
+static inline void hl_debugfs_add_userptr(struct hl_device *hdev,
+					struct hl_userptr *userptr)
+{
+}
+
+static inline void hl_debugfs_remove_userptr(struct hl_device *hdev,
+					struct hl_userptr *userptr)
+{
+}
+
+static inline void hl_debugfs_add_ctx_mem_hash(struct hl_device *hdev,
+					struct hl_ctx *ctx)
+{
+}
+
+static inline void hl_debugfs_remove_ctx_mem_hash(struct hl_device *hdev,
+					struct hl_ctx *ctx)
+{
+}
+
+#endif
+
+/* IOCTLs */
+long hl_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
+long hl_ioctl_control(struct file *filep, unsigned int cmd, unsigned long arg);
+int hl_cb_ioctl(struct hl_fpriv *hpriv, void *data);
+int hl_cs_ioctl(struct hl_fpriv *hpriv, void *data);
+int hl_cs_wait_ioctl(struct hl_fpriv *hpriv, void *data);
+int hl_mem_ioctl(struct hl_fpriv *hpriv, void *data);
+
+#endif /* HABANALABSP_H_ */
diff --git a/drivers/misc/habanalabs/common/habanalabs_drv.c b/drivers/misc/habanalabs/common/habanalabs_drv.c
new file mode 100644
index 000000000000..f38664b03865
--- /dev/null
+++ b/drivers/misc/habanalabs/common/habanalabs_drv.c
@@ -0,0 +1,529 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2019 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ *
+ */
+
+#define pr_fmt(fmt)		"habanalabs: " fmt
+
+#include "habanalabs.h"
+
+#include <linux/pci.h>
+#include <linux/module.h>
+
+#define HL_DRIVER_AUTHOR	"HabanaLabs Kernel Driver Team"
+
+#define HL_DRIVER_DESC		"Driver for HabanaLabs's AI Accelerators"
+
+MODULE_AUTHOR(HL_DRIVER_AUTHOR);
+MODULE_DESCRIPTION(HL_DRIVER_DESC);
+MODULE_LICENSE("GPL v2");
+
+static int hl_major;
+static struct class *hl_class;
+static DEFINE_IDR(hl_devs_idr);
+static DEFINE_MUTEX(hl_devs_idr_lock);
+
+static int timeout_locked = 5;
+static int reset_on_lockup = 1;
+
+module_param(timeout_locked, int, 0444);
+MODULE_PARM_DESC(timeout_locked,
+	"Device lockup timeout in seconds (0 = disabled, default 5s)");
+
+module_param(reset_on_lockup, int, 0444);
+MODULE_PARM_DESC(reset_on_lockup,
+	"Do device reset on lockup (0 = no, 1 = yes, default yes)");
+
+#define PCI_VENDOR_ID_HABANALABS	0x1da3
+
+#define PCI_IDS_GOYA			0x0001
+#define PCI_IDS_GAUDI			0x1000
+
+static const struct pci_device_id ids[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_HABANALABS, PCI_IDS_GOYA), },
+	{ PCI_DEVICE(PCI_VENDOR_ID_HABANALABS, PCI_IDS_GAUDI), },
+	{ 0, }
+};
+MODULE_DEVICE_TABLE(pci, ids);
+
+/*
+ * get_asic_type - translate device id to asic type
+ *
+ * @device: id of the PCI device
+ *
+ * Translate device id to asic type.
+ * In case of unidentified device, return -1
+ */
+static enum hl_asic_type get_asic_type(u16 device)
+{
+	enum hl_asic_type asic_type;
+
+	switch (device) {
+	case PCI_IDS_GOYA:
+		asic_type = ASIC_GOYA;
+		break;
+	case PCI_IDS_GAUDI:
+		asic_type = ASIC_GAUDI;
+		break;
+	default:
+		asic_type = ASIC_INVALID;
+		break;
+	}
+
+	return asic_type;
+}
+
+/*
+ * hl_device_open - open function for habanalabs device
+ *
+ * @inode: pointer to inode structure
+ * @filp: pointer to file structure
+ *
+ * Called when process opens an habanalabs device.
+ */
+int hl_device_open(struct inode *inode, struct file *filp)
+{
+	struct hl_device *hdev;
+	struct hl_fpriv *hpriv;
+	int rc;
+
+	mutex_lock(&hl_devs_idr_lock);
+	hdev = idr_find(&hl_devs_idr, iminor(inode));
+	mutex_unlock(&hl_devs_idr_lock);
+
+	if (!hdev) {
+		pr_err("Couldn't find device %d:%d\n",
+			imajor(inode), iminor(inode));
+		return -ENXIO;
+	}
+
+	hpriv = kzalloc(sizeof(*hpriv), GFP_KERNEL);
+	if (!hpriv)
+		return -ENOMEM;
+
+	hpriv->hdev = hdev;
+	filp->private_data = hpriv;
+	hpriv->filp = filp;
+	mutex_init(&hpriv->restore_phase_mutex);
+	kref_init(&hpriv->refcount);
+	nonseekable_open(inode, filp);
+
+	hl_cb_mgr_init(&hpriv->cb_mgr);
+	hl_ctx_mgr_init(&hpriv->ctx_mgr);
+
+	hpriv->taskpid = find_get_pid(current->pid);
+
+	mutex_lock(&hdev->fpriv_list_lock);
+
+	if (hl_device_disabled_or_in_reset(hdev)) {
+		dev_err_ratelimited(hdev->dev,
+			"Can't open %s because it is disabled or in reset\n",
+			dev_name(hdev->dev));
+		rc = -EPERM;
+		goto out_err;
+	}
+
+	if (hdev->in_debug) {
+		dev_err_ratelimited(hdev->dev,
+			"Can't open %s because it is being debugged by another user\n",
+			dev_name(hdev->dev));
+		rc = -EPERM;
+		goto out_err;
+	}
+
+	if (hdev->compute_ctx) {
+		dev_dbg_ratelimited(hdev->dev,
+			"Can't open %s because another user is working on it\n",
+			dev_name(hdev->dev));
+		rc = -EBUSY;
+		goto out_err;
+	}
+
+	rc = hl_ctx_create(hdev, hpriv);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to create context %d\n", rc);
+		goto out_err;
+	}
+
+	/* Device is IDLE at this point so it is legal to change PLLs.
+	 * There is no need to check anything because if the PLL is
+	 * already HIGH, the set function will return without doing
+	 * anything
+	 */
+	hl_device_set_frequency(hdev, PLL_HIGH);
+
+	list_add(&hpriv->dev_node, &hdev->fpriv_list);
+	mutex_unlock(&hdev->fpriv_list_lock);
+
+	hl_debugfs_add_file(hpriv);
+
+	return 0;
+
+out_err:
+	mutex_unlock(&hdev->fpriv_list_lock);
+
+	hl_cb_mgr_fini(hpriv->hdev, &hpriv->cb_mgr);
+	hl_ctx_mgr_fini(hpriv->hdev, &hpriv->ctx_mgr);
+	filp->private_data = NULL;
+	mutex_destroy(&hpriv->restore_phase_mutex);
+	put_pid(hpriv->taskpid);
+
+	kfree(hpriv);
+
+	return rc;
+}
+
+int hl_device_open_ctrl(struct inode *inode, struct file *filp)
+{
+	struct hl_device *hdev;
+	struct hl_fpriv *hpriv;
+	int rc;
+
+	mutex_lock(&hl_devs_idr_lock);
+	hdev = idr_find(&hl_devs_idr, iminor(inode));
+	mutex_unlock(&hl_devs_idr_lock);
+
+	if (!hdev) {
+		pr_err("Couldn't find device %d:%d\n",
+			imajor(inode), iminor(inode));
+		return -ENXIO;
+	}
+
+	hpriv = kzalloc(sizeof(*hpriv), GFP_KERNEL);
+	if (!hpriv)
+		return -ENOMEM;
+
+	mutex_lock(&hdev->fpriv_list_lock);
+
+	if (hl_device_disabled_or_in_reset(hdev)) {
+		dev_err_ratelimited(hdev->dev_ctrl,
+			"Can't open %s because it is disabled or in reset\n",
+			dev_name(hdev->dev_ctrl));
+		rc = -EPERM;
+		goto out_err;
+	}
+
+	list_add(&hpriv->dev_node, &hdev->fpriv_list);
+	mutex_unlock(&hdev->fpriv_list_lock);
+
+	hpriv->hdev = hdev;
+	filp->private_data = hpriv;
+	hpriv->filp = filp;
+	hpriv->is_control = true;
+	nonseekable_open(inode, filp);
+
+	hpriv->taskpid = find_get_pid(current->pid);
+
+	return 0;
+
+out_err:
+	mutex_unlock(&hdev->fpriv_list_lock);
+	kfree(hpriv);
+	return rc;
+}
+
+static void set_driver_behavior_per_device(struct hl_device *hdev)
+{
+	hdev->mmu_enable = 1;
+	hdev->cpu_enable = 1;
+	hdev->fw_loading = 1;
+	hdev->cpu_queues_enable = 1;
+	hdev->heartbeat = 1;
+	hdev->clock_gating = 1;
+
+	hdev->reset_pcilink = 0;
+	hdev->axi_drain = 0;
+	hdev->sram_scrambler_enable = 1;
+	hdev->dram_scrambler_enable = 1;
+	hdev->bmc_enable = 1;
+	hdev->hard_reset_on_fw_events = 1;
+}
+
+/*
+ * create_hdev - create habanalabs device instance
+ *
+ * @dev: will hold the pointer to the new habanalabs device structure
+ * @pdev: pointer to the pci device
+ * @asic_type: in case of simulator device, which device is it
+ * @minor: in case of simulator device, the minor of the device
+ *
+ * Allocate memory for habanalabs device and initialize basic fields
+ * Identify the ASIC type
+ * Allocate ID (minor) for the device (only for real devices)
+ */
+int create_hdev(struct hl_device **dev, struct pci_dev *pdev,
+		enum hl_asic_type asic_type, int minor)
+{
+	struct hl_device *hdev;
+	int rc, main_id, ctrl_id = 0;
+
+	*dev = NULL;
+
+	hdev = kzalloc(sizeof(*hdev), GFP_KERNEL);
+	if (!hdev)
+		return -ENOMEM;
+
+	/* First, we must find out which ASIC are we handling. This is needed
+	 * to configure the behavior of the driver (kernel parameters)
+	 */
+	if (pdev) {
+		hdev->asic_type = get_asic_type(pdev->device);
+		if (hdev->asic_type == ASIC_INVALID) {
+			dev_err(&pdev->dev, "Unsupported ASIC\n");
+			rc = -ENODEV;
+			goto free_hdev;
+		}
+	} else {
+		hdev->asic_type = asic_type;
+	}
+
+	hdev->major = hl_major;
+	hdev->reset_on_lockup = reset_on_lockup;
+	hdev->pldm = 0;
+
+	set_driver_behavior_per_device(hdev);
+
+	if (timeout_locked)
+		hdev->timeout_jiffies = msecs_to_jiffies(timeout_locked * 1000);
+	else
+		hdev->timeout_jiffies = MAX_SCHEDULE_TIMEOUT;
+
+	hdev->disabled = true;
+	hdev->pdev = pdev; /* can be NULL in case of simulator device */
+
+	/* Set default DMA mask to 32 bits */
+	hdev->dma_mask = 32;
+
+	mutex_lock(&hl_devs_idr_lock);
+
+	/* Always save 2 numbers, 1 for main device and 1 for control.
+	 * They must be consecutive
+	 */
+	main_id = idr_alloc(&hl_devs_idr, hdev, 0, HL_MAX_MINORS,
+				GFP_KERNEL);
+
+	if (main_id >= 0)
+		ctrl_id = idr_alloc(&hl_devs_idr, hdev, main_id + 1,
+					main_id + 2, GFP_KERNEL);
+
+	mutex_unlock(&hl_devs_idr_lock);
+
+	if ((main_id < 0) || (ctrl_id < 0)) {
+		if ((main_id == -ENOSPC) || (ctrl_id == -ENOSPC))
+			pr_err("too many devices in the system\n");
+
+		if (main_id >= 0) {
+			mutex_lock(&hl_devs_idr_lock);
+			idr_remove(&hl_devs_idr, main_id);
+			mutex_unlock(&hl_devs_idr_lock);
+		}
+
+		rc = -EBUSY;
+		goto free_hdev;
+	}
+
+	hdev->id = main_id;
+	hdev->id_control = ctrl_id;
+
+	*dev = hdev;
+
+	return 0;
+
+free_hdev:
+	kfree(hdev);
+	return rc;
+}
+
+/*
+ * destroy_hdev - destroy habanalabs device instance
+ *
+ * @dev: pointer to the habanalabs device structure
+ *
+ */
+void destroy_hdev(struct hl_device *hdev)
+{
+	/* Remove device from the device list */
+	mutex_lock(&hl_devs_idr_lock);
+	idr_remove(&hl_devs_idr, hdev->id);
+	idr_remove(&hl_devs_idr, hdev->id_control);
+	mutex_unlock(&hl_devs_idr_lock);
+
+	kfree(hdev);
+}
+
+static int hl_pmops_suspend(struct device *dev)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+
+	pr_debug("Going to suspend PCI device\n");
+
+	if (!hdev) {
+		pr_err("device pointer is NULL in suspend\n");
+		return 0;
+	}
+
+	return hl_device_suspend(hdev);
+}
+
+static int hl_pmops_resume(struct device *dev)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+
+	pr_debug("Going to resume PCI device\n");
+
+	if (!hdev) {
+		pr_err("device pointer is NULL in resume\n");
+		return 0;
+	}
+
+	return hl_device_resume(hdev);
+}
+
+/*
+ * hl_pci_probe - probe PCI habanalabs devices
+ *
+ * @pdev: pointer to pci device
+ * @id: pointer to pci device id structure
+ *
+ * Standard PCI probe function for habanalabs device.
+ * Create a new habanalabs device and initialize it according to the
+ * device's type
+ */
+static int hl_pci_probe(struct pci_dev *pdev,
+				const struct pci_device_id *id)
+{
+	struct hl_device *hdev;
+	int rc;
+
+	dev_info(&pdev->dev, HL_NAME
+		 " device found [%04x:%04x] (rev %x)\n",
+		 (int)pdev->vendor, (int)pdev->device, (int)pdev->revision);
+
+	rc = create_hdev(&hdev, pdev, ASIC_INVALID, -1);
+	if (rc)
+		return rc;
+
+	pci_set_drvdata(pdev, hdev);
+
+	rc = hl_device_init(hdev, hl_class);
+	if (rc) {
+		dev_err(&pdev->dev, "Fatal error during habanalabs device init\n");
+		rc = -ENODEV;
+		goto disable_device;
+	}
+
+	return 0;
+
+disable_device:
+	pci_set_drvdata(pdev, NULL);
+	destroy_hdev(hdev);
+
+	return rc;
+}
+
+/*
+ * hl_pci_remove - remove PCI habanalabs devices
+ *
+ * @pdev: pointer to pci device
+ *
+ * Standard PCI remove function for habanalabs device
+ */
+static void hl_pci_remove(struct pci_dev *pdev)
+{
+	struct hl_device *hdev;
+
+	hdev = pci_get_drvdata(pdev);
+	if (!hdev)
+		return;
+
+	hl_device_fini(hdev);
+	pci_set_drvdata(pdev, NULL);
+
+	destroy_hdev(hdev);
+}
+
+static const struct dev_pm_ops hl_pm_ops = {
+	.suspend = hl_pmops_suspend,
+	.resume = hl_pmops_resume,
+};
+
+static struct pci_driver hl_pci_driver = {
+	.name = HL_NAME,
+	.id_table = ids,
+	.probe = hl_pci_probe,
+	.remove = hl_pci_remove,
+	.driver.pm = &hl_pm_ops,
+};
+
+/*
+ * hl_init - Initialize the habanalabs kernel driver
+ */
+static int __init hl_init(void)
+{
+	int rc;
+	dev_t dev;
+
+	pr_info("loading driver\n");
+
+	rc = alloc_chrdev_region(&dev, 0, HL_MAX_MINORS, HL_NAME);
+	if (rc < 0) {
+		pr_err("unable to get major\n");
+		return rc;
+	}
+
+	hl_major = MAJOR(dev);
+
+	hl_class = class_create(THIS_MODULE, HL_NAME);
+	if (IS_ERR(hl_class)) {
+		pr_err("failed to allocate class\n");
+		rc = PTR_ERR(hl_class);
+		goto remove_major;
+	}
+
+	hl_debugfs_init();
+
+	rc = pci_register_driver(&hl_pci_driver);
+	if (rc) {
+		pr_err("failed to register pci device\n");
+		goto remove_debugfs;
+	}
+
+	pr_debug("driver loaded\n");
+
+	return 0;
+
+remove_debugfs:
+	hl_debugfs_fini();
+	class_destroy(hl_class);
+remove_major:
+	unregister_chrdev_region(MKDEV(hl_major, 0), HL_MAX_MINORS);
+	return rc;
+}
+
+/*
+ * hl_exit - Release all resources of the habanalabs kernel driver
+ */
+static void __exit hl_exit(void)
+{
+	pci_unregister_driver(&hl_pci_driver);
+
+	/*
+	 * Removing debugfs must be after all devices or simulator devices
+	 * have been removed because otherwise we get a bug in the
+	 * debugfs module for referencing NULL objects
+	 */
+	hl_debugfs_fini();
+
+	class_destroy(hl_class);
+	unregister_chrdev_region(MKDEV(hl_major, 0), HL_MAX_MINORS);
+
+	idr_destroy(&hl_devs_idr);
+
+	pr_debug("driver removed\n");
+}
+
+module_init(hl_init);
+module_exit(hl_exit);
diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
new file mode 100644
index 000000000000..5af1c03da473
--- /dev/null
+++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
@@ -0,0 +1,546 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2019 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include <uapi/misc/habanalabs.h>
+#include "habanalabs.h"
+
+#include <linux/fs.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+
+static u32 hl_debug_struct_size[HL_DEBUG_OP_TIMESTAMP + 1] = {
+	[HL_DEBUG_OP_ETR] = sizeof(struct hl_debug_params_etr),
+	[HL_DEBUG_OP_ETF] = sizeof(struct hl_debug_params_etf),
+	[HL_DEBUG_OP_STM] = sizeof(struct hl_debug_params_stm),
+	[HL_DEBUG_OP_FUNNEL] = 0,
+	[HL_DEBUG_OP_BMON] = sizeof(struct hl_debug_params_bmon),
+	[HL_DEBUG_OP_SPMU] = sizeof(struct hl_debug_params_spmu),
+	[HL_DEBUG_OP_TIMESTAMP] = 0
+
+};
+
+static int device_status_info(struct hl_device *hdev, struct hl_info_args *args)
+{
+	struct hl_info_device_status dev_stat = {0};
+	u32 size = args->return_size;
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+
+	if ((!size) || (!out))
+		return -EINVAL;
+
+	dev_stat.status = hl_device_status(hdev);
+
+	return copy_to_user(out, &dev_stat,
+			min((size_t)size, sizeof(dev_stat))) ? -EFAULT : 0;
+}
+
+static int hw_ip_info(struct hl_device *hdev, struct hl_info_args *args)
+{
+	struct hl_info_hw_ip_info hw_ip = {0};
+	u32 size = args->return_size;
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	u64 sram_kmd_size, dram_kmd_size;
+
+	if ((!size) || (!out))
+		return -EINVAL;
+
+	sram_kmd_size = (prop->sram_user_base_address -
+				prop->sram_base_address);
+	dram_kmd_size = (prop->dram_user_base_address -
+				prop->dram_base_address);
+
+	hw_ip.device_id = hdev->asic_funcs->get_pci_id(hdev);
+	hw_ip.sram_base_address = prop->sram_user_base_address;
+	hw_ip.dram_base_address = prop->dram_user_base_address;
+	hw_ip.tpc_enabled_mask = prop->tpc_enabled_mask;
+	hw_ip.sram_size = prop->sram_size - sram_kmd_size;
+	hw_ip.dram_size = prop->dram_size - dram_kmd_size;
+	if (hw_ip.dram_size > PAGE_SIZE)
+		hw_ip.dram_enabled = 1;
+	hw_ip.num_of_events = prop->num_of_events;
+
+	memcpy(hw_ip.armcp_version, prop->armcp_info.armcp_version,
+		min(VERSION_MAX_LEN, HL_INFO_VERSION_MAX_LEN));
+
+	memcpy(hw_ip.card_name, prop->armcp_info.card_name,
+		min(CARD_NAME_MAX_LEN, HL_INFO_CARD_NAME_MAX_LEN));
+
+	hw_ip.armcp_cpld_version = le32_to_cpu(prop->armcp_info.cpld_version);
+	hw_ip.module_id = le32_to_cpu(prop->armcp_info.card_location);
+
+	hw_ip.psoc_pci_pll_nr = prop->psoc_pci_pll_nr;
+	hw_ip.psoc_pci_pll_nf = prop->psoc_pci_pll_nf;
+	hw_ip.psoc_pci_pll_od = prop->psoc_pci_pll_od;
+	hw_ip.psoc_pci_pll_div_factor = prop->psoc_pci_pll_div_factor;
+
+	return copy_to_user(out, &hw_ip,
+		min((size_t)size, sizeof(hw_ip))) ? -EFAULT : 0;
+}
+
+static int hw_events_info(struct hl_device *hdev, bool aggregate,
+			struct hl_info_args *args)
+{
+	u32 size, max_size = args->return_size;
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+	void *arr;
+
+	if ((!max_size) || (!out))
+		return -EINVAL;
+
+	arr = hdev->asic_funcs->get_events_stat(hdev, aggregate, &size);
+
+	return copy_to_user(out, arr, min(max_size, size)) ? -EFAULT : 0;
+}
+
+static int dram_usage_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
+{
+	struct hl_device *hdev = hpriv->hdev;
+	struct hl_info_dram_usage dram_usage = {0};
+	u32 max_size = args->return_size;
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	u64 dram_kmd_size;
+
+	if ((!max_size) || (!out))
+		return -EINVAL;
+
+	dram_kmd_size = (prop->dram_user_base_address -
+				prop->dram_base_address);
+	dram_usage.dram_free_mem = (prop->dram_size - dram_kmd_size) -
+					atomic64_read(&hdev->dram_used_mem);
+	if (hpriv->ctx)
+		dram_usage.ctx_dram_mem =
+			atomic64_read(&hpriv->ctx->dram_phys_mem);
+
+	return copy_to_user(out, &dram_usage,
+		min((size_t) max_size, sizeof(dram_usage))) ? -EFAULT : 0;
+}
+
+static int hw_idle(struct hl_device *hdev, struct hl_info_args *args)
+{
+	struct hl_info_hw_idle hw_idle = {0};
+	u32 max_size = args->return_size;
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+
+	if ((!max_size) || (!out))
+		return -EINVAL;
+
+	hw_idle.is_idle = hdev->asic_funcs->is_device_idle(hdev,
+					&hw_idle.busy_engines_mask, NULL);
+
+	return copy_to_user(out, &hw_idle,
+		min((size_t) max_size, sizeof(hw_idle))) ? -EFAULT : 0;
+}
+
+static int debug_coresight(struct hl_device *hdev, struct hl_debug_args *args)
+{
+	struct hl_debug_params *params;
+	void *input = NULL, *output = NULL;
+	int rc;
+
+	params = kzalloc(sizeof(*params), GFP_KERNEL);
+	if (!params)
+		return -ENOMEM;
+
+	params->reg_idx = args->reg_idx;
+	params->enable = args->enable;
+	params->op = args->op;
+
+	if (args->input_ptr && args->input_size) {
+		input = kzalloc(hl_debug_struct_size[args->op], GFP_KERNEL);
+		if (!input) {
+			rc = -ENOMEM;
+			goto out;
+		}
+
+		if (copy_from_user(input, u64_to_user_ptr(args->input_ptr),
+					args->input_size)) {
+			rc = -EFAULT;
+			dev_err(hdev->dev, "failed to copy input debug data\n");
+			goto out;
+		}
+
+		params->input = input;
+	}
+
+	if (args->output_ptr && args->output_size) {
+		output = kzalloc(args->output_size, GFP_KERNEL);
+		if (!output) {
+			rc = -ENOMEM;
+			goto out;
+		}
+
+		params->output = output;
+		params->output_size = args->output_size;
+	}
+
+	rc = hdev->asic_funcs->debug_coresight(hdev, params);
+	if (rc) {
+		dev_err(hdev->dev,
+			"debug coresight operation failed %d\n", rc);
+		goto out;
+	}
+
+	if (output && copy_to_user((void __user *) (uintptr_t) args->output_ptr,
+					output, args->output_size)) {
+		dev_err(hdev->dev, "copy to user failed in debug ioctl\n");
+		rc = -EFAULT;
+		goto out;
+	}
+
+
+out:
+	kfree(params);
+	kfree(output);
+	kfree(input);
+
+	return rc;
+}
+
+static int device_utilization(struct hl_device *hdev, struct hl_info_args *args)
+{
+	struct hl_info_device_utilization device_util = {0};
+	u32 max_size = args->return_size;
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+
+	if ((!max_size) || (!out))
+		return -EINVAL;
+
+	if ((args->period_ms < 100) || (args->period_ms > 1000) ||
+		(args->period_ms % 100)) {
+		dev_err(hdev->dev,
+			"period %u must be between 100 - 1000 and must be divisible by 100\n",
+			args->period_ms);
+		return -EINVAL;
+	}
+
+	device_util.utilization = hl_device_utilization(hdev, args->period_ms);
+
+	return copy_to_user(out, &device_util,
+		min((size_t) max_size, sizeof(device_util))) ? -EFAULT : 0;
+}
+
+static int get_clk_rate(struct hl_device *hdev, struct hl_info_args *args)
+{
+	struct hl_info_clk_rate clk_rate = {0};
+	u32 max_size = args->return_size;
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+	int rc;
+
+	if ((!max_size) || (!out))
+		return -EINVAL;
+
+	rc = hdev->asic_funcs->get_clk_rate(hdev, &clk_rate.cur_clk_rate_mhz,
+						&clk_rate.max_clk_rate_mhz);
+	if (rc)
+		return rc;
+
+	return copy_to_user(out, &clk_rate,
+		min((size_t) max_size, sizeof(clk_rate))) ? -EFAULT : 0;
+}
+
+static int get_reset_count(struct hl_device *hdev, struct hl_info_args *args)
+{
+	struct hl_info_reset_count reset_count = {0};
+	u32 max_size = args->return_size;
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+
+	if ((!max_size) || (!out))
+		return -EINVAL;
+
+	reset_count.hard_reset_cnt = hdev->hard_reset_cnt;
+	reset_count.soft_reset_cnt = hdev->soft_reset_cnt;
+
+	return copy_to_user(out, &reset_count,
+		min((size_t) max_size, sizeof(reset_count))) ? -EFAULT : 0;
+}
+
+static int time_sync_info(struct hl_device *hdev, struct hl_info_args *args)
+{
+	struct hl_info_time_sync time_sync = {0};
+	u32 max_size = args->return_size;
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+
+	if ((!max_size) || (!out))
+		return -EINVAL;
+
+	time_sync.device_time = hdev->asic_funcs->get_device_time(hdev);
+	time_sync.host_time = ktime_get_raw_ns();
+
+	return copy_to_user(out, &time_sync,
+		min((size_t) max_size, sizeof(time_sync))) ? -EFAULT : 0;
+}
+
+static int cs_counters_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
+{
+	struct hl_device *hdev = hpriv->hdev;
+	struct hl_info_cs_counters cs_counters = {0};
+	u32 max_size = args->return_size;
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+
+	if ((!max_size) || (!out))
+		return -EINVAL;
+
+	memcpy(&cs_counters.cs_counters, &hdev->aggregated_cs_counters,
+			sizeof(struct hl_cs_counters));
+
+	if (hpriv->ctx)
+		memcpy(&cs_counters.ctx_cs_counters, &hpriv->ctx->cs_counters,
+				sizeof(struct hl_cs_counters));
+
+	return copy_to_user(out, &cs_counters,
+		min((size_t) max_size, sizeof(cs_counters))) ? -EFAULT : 0;
+}
+
+static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
+				struct device *dev)
+{
+	struct hl_info_args *args = data;
+	struct hl_device *hdev = hpriv->hdev;
+	int rc;
+
+	/*
+	 * Information is returned for the following opcodes even if the device
+	 * is disabled or in reset.
+	 */
+	switch (args->op) {
+	case HL_INFO_HW_IP_INFO:
+		return hw_ip_info(hdev, args);
+
+	case HL_INFO_DEVICE_STATUS:
+		return device_status_info(hdev, args);
+
+	case HL_INFO_RESET_COUNT:
+		return get_reset_count(hdev, args);
+
+	default:
+		break;
+	}
+
+	if (hl_device_disabled_or_in_reset(hdev)) {
+		dev_warn_ratelimited(dev,
+			"Device is %s. Can't execute INFO IOCTL\n",
+			atomic_read(&hdev->in_reset) ? "in_reset" : "disabled");
+		return -EBUSY;
+	}
+
+	switch (args->op) {
+	case HL_INFO_HW_EVENTS:
+		rc = hw_events_info(hdev, false, args);
+		break;
+
+	case HL_INFO_DRAM_USAGE:
+		rc = dram_usage_info(hpriv, args);
+		break;
+
+	case HL_INFO_HW_IDLE:
+		rc = hw_idle(hdev, args);
+		break;
+
+	case HL_INFO_DEVICE_UTILIZATION:
+		rc = device_utilization(hdev, args);
+		break;
+
+	case HL_INFO_HW_EVENTS_AGGREGATE:
+		rc = hw_events_info(hdev, true, args);
+		break;
+
+	case HL_INFO_CLK_RATE:
+		rc = get_clk_rate(hdev, args);
+		break;
+
+	case HL_INFO_TIME_SYNC:
+		return time_sync_info(hdev, args);
+
+	case HL_INFO_CS_COUNTERS:
+		return cs_counters_info(hpriv, args);
+
+	default:
+		dev_err(dev, "Invalid request %d\n", args->op);
+		rc = -ENOTTY;
+		break;
+	}
+
+	return rc;
+}
+
+static int hl_info_ioctl(struct hl_fpriv *hpriv, void *data)
+{
+	return _hl_info_ioctl(hpriv, data, hpriv->hdev->dev);
+}
+
+static int hl_info_ioctl_control(struct hl_fpriv *hpriv, void *data)
+{
+	return _hl_info_ioctl(hpriv, data, hpriv->hdev->dev_ctrl);
+}
+
+static int hl_debug_ioctl(struct hl_fpriv *hpriv, void *data)
+{
+	struct hl_debug_args *args = data;
+	struct hl_device *hdev = hpriv->hdev;
+	int rc = 0;
+
+	if (hl_device_disabled_or_in_reset(hdev)) {
+		dev_warn_ratelimited(hdev->dev,
+			"Device is %s. Can't execute DEBUG IOCTL\n",
+			atomic_read(&hdev->in_reset) ? "in_reset" : "disabled");
+		return -EBUSY;
+	}
+
+	switch (args->op) {
+	case HL_DEBUG_OP_ETR:
+	case HL_DEBUG_OP_ETF:
+	case HL_DEBUG_OP_STM:
+	case HL_DEBUG_OP_FUNNEL:
+	case HL_DEBUG_OP_BMON:
+	case HL_DEBUG_OP_SPMU:
+	case HL_DEBUG_OP_TIMESTAMP:
+		if (!hdev->in_debug) {
+			dev_err_ratelimited(hdev->dev,
+				"Rejecting debug configuration request because device not in debug mode\n");
+			return -EFAULT;
+		}
+		args->input_size =
+			min(args->input_size, hl_debug_struct_size[args->op]);
+		rc = debug_coresight(hdev, args);
+		break;
+	case HL_DEBUG_OP_SET_MODE:
+		rc = hl_device_set_debug_mode(hdev, (bool) args->enable);
+		break;
+	default:
+		dev_err(hdev->dev, "Invalid request %d\n", args->op);
+		rc = -ENOTTY;
+		break;
+	}
+
+	return rc;
+}
+
+#define HL_IOCTL_DEF(ioctl, _func) \
+	[_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func}
+
+static const struct hl_ioctl_desc hl_ioctls[] = {
+	HL_IOCTL_DEF(HL_IOCTL_INFO, hl_info_ioctl),
+	HL_IOCTL_DEF(HL_IOCTL_CB, hl_cb_ioctl),
+	HL_IOCTL_DEF(HL_IOCTL_CS, hl_cs_ioctl),
+	HL_IOCTL_DEF(HL_IOCTL_WAIT_CS, hl_cs_wait_ioctl),
+	HL_IOCTL_DEF(HL_IOCTL_MEMORY, hl_mem_ioctl),
+	HL_IOCTL_DEF(HL_IOCTL_DEBUG, hl_debug_ioctl)
+};
+
+static const struct hl_ioctl_desc hl_ioctls_control[] = {
+	HL_IOCTL_DEF(HL_IOCTL_INFO, hl_info_ioctl_control)
+};
+
+static long _hl_ioctl(struct file *filep, unsigned int cmd, unsigned long arg,
+		const struct hl_ioctl_desc *ioctl, struct device *dev)
+{
+	struct hl_fpriv *hpriv = filep->private_data;
+	struct hl_device *hdev = hpriv->hdev;
+	unsigned int nr = _IOC_NR(cmd);
+	char stack_kdata[128] = {0};
+	char *kdata = NULL;
+	unsigned int usize, asize;
+	hl_ioctl_t *func;
+	u32 hl_size;
+	int retcode;
+
+	if (hdev->hard_reset_pending) {
+		dev_crit_ratelimited(hdev->dev_ctrl,
+			"Device HARD reset pending! Please close FD\n");
+		return -ENODEV;
+	}
+
+	/* Do not trust userspace, use our own definition */
+	func = ioctl->func;
+
+	if (unlikely(!func)) {
+		dev_dbg(dev, "no function\n");
+		retcode = -ENOTTY;
+		goto out_err;
+	}
+
+	hl_size = _IOC_SIZE(ioctl->cmd);
+	usize = asize = _IOC_SIZE(cmd);
+	if (hl_size > asize)
+		asize = hl_size;
+
+	cmd = ioctl->cmd;
+
+	if (cmd & (IOC_IN | IOC_OUT)) {
+		if (asize <= sizeof(stack_kdata)) {
+			kdata = stack_kdata;
+		} else {
+			kdata = kzalloc(asize, GFP_KERNEL);
+			if (!kdata) {
+				retcode = -ENOMEM;
+				goto out_err;
+			}
+		}
+	}
+
+	if (cmd & IOC_IN) {
+		if (copy_from_user(kdata, (void __user *)arg, usize)) {
+			retcode = -EFAULT;
+			goto out_err;
+		}
+	} else if (cmd & IOC_OUT) {
+		memset(kdata, 0, usize);
+	}
+
+	retcode = func(hpriv, kdata);
+
+	if ((cmd & IOC_OUT) && copy_to_user((void __user *)arg, kdata, usize))
+		retcode = -EFAULT;
+
+out_err:
+	if (retcode)
+		dev_dbg(dev, "error in ioctl: pid=%d, cmd=0x%02x, nr=0x%02x\n",
+			  task_pid_nr(current), cmd, nr);
+
+	if (kdata != stack_kdata)
+		kfree(kdata);
+
+	return retcode;
+}
+
+long hl_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
+{
+	struct hl_fpriv *hpriv = filep->private_data;
+	struct hl_device *hdev = hpriv->hdev;
+	const struct hl_ioctl_desc *ioctl = NULL;
+	unsigned int nr = _IOC_NR(cmd);
+
+	if ((nr >= HL_COMMAND_START) && (nr < HL_COMMAND_END)) {
+		ioctl = &hl_ioctls[nr];
+	} else {
+		dev_err(hdev->dev, "invalid ioctl: pid=%d, nr=0x%02x\n",
+			task_pid_nr(current), nr);
+		return -ENOTTY;
+	}
+
+	return _hl_ioctl(filep, cmd, arg, ioctl, hdev->dev);
+}
+
+long hl_ioctl_control(struct file *filep, unsigned int cmd, unsigned long arg)
+{
+	struct hl_fpriv *hpriv = filep->private_data;
+	struct hl_device *hdev = hpriv->hdev;
+	const struct hl_ioctl_desc *ioctl = NULL;
+	unsigned int nr = _IOC_NR(cmd);
+
+	if (nr == _IOC_NR(HL_IOCTL_INFO)) {
+		ioctl = &hl_ioctls_control[nr];
+	} else {
+		dev_err(hdev->dev_ctrl, "invalid ioctl: pid=%d, nr=0x%02x\n",
+			task_pid_nr(current), nr);
+		return -ENOTTY;
+	}
+
+	return _hl_ioctl(filep, cmd, arg, ioctl, hdev->dev_ctrl);
+}
diff --git a/drivers/misc/habanalabs/common/hw_queue.c b/drivers/misc/habanalabs/common/hw_queue.c
new file mode 100644
index 000000000000..287681646071
--- /dev/null
+++ b/drivers/misc/habanalabs/common/hw_queue.c
@@ -0,0 +1,918 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2019 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include "habanalabs.h"
+
+#include <linux/slab.h>
+
+/*
+ * hl_queue_add_ptr - add to pi or ci and checks if it wraps around
+ *
+ * @ptr: the current pi/ci value
+ * @val: the amount to add
+ *
+ * Add val to ptr. It can go until twice the queue length.
+ */
+inline u32 hl_hw_queue_add_ptr(u32 ptr, u16 val)
+{
+	ptr += val;
+	ptr &= ((HL_QUEUE_LENGTH << 1) - 1);
+	return ptr;
+}
+static inline int queue_ci_get(atomic_t *ci, u32 queue_len)
+{
+	return atomic_read(ci) & ((queue_len << 1) - 1);
+}
+
+static inline int queue_free_slots(struct hl_hw_queue *q, u32 queue_len)
+{
+	int delta = (q->pi - queue_ci_get(&q->ci, queue_len));
+
+	if (delta >= 0)
+		return (queue_len - delta);
+	else
+		return (abs(delta) - queue_len);
+}
+
+void hl_int_hw_queue_update_ci(struct hl_cs *cs)
+{
+	struct hl_device *hdev = cs->ctx->hdev;
+	struct hl_hw_queue *q;
+	int i;
+
+	if (hdev->disabled)
+		return;
+
+	q = &hdev->kernel_queues[0];
+	for (i = 0 ; i < hdev->asic_prop.max_queues ; i++, q++) {
+		if (q->queue_type == QUEUE_TYPE_INT)
+			atomic_add(cs->jobs_in_queue_cnt[i], &q->ci);
+	}
+}
+
+/*
+ * ext_and_hw_queue_submit_bd() - Submit a buffer descriptor to an external or a
+ *                                H/W queue.
+ * @hdev: pointer to habanalabs device structure
+ * @q: pointer to habanalabs queue structure
+ * @ctl: BD's control word
+ * @len: BD's length
+ * @ptr: BD's pointer
+ *
+ * This function assumes there is enough space on the queue to submit a new
+ * BD to it. It initializes the next BD and calls the device specific
+ * function to set the pi (and doorbell)
+ *
+ * This function must be called when the scheduler mutex is taken
+ *
+ */
+static void ext_and_hw_queue_submit_bd(struct hl_device *hdev,
+			struct hl_hw_queue *q, u32 ctl, u32 len, u64 ptr)
+{
+	struct hl_bd *bd;
+
+	bd = (struct hl_bd *) (uintptr_t) q->kernel_address;
+	bd += hl_pi_2_offset(q->pi);
+	bd->ctl = cpu_to_le32(ctl);
+	bd->len = cpu_to_le32(len);
+	bd->ptr = cpu_to_le64(ptr);
+
+	q->pi = hl_queue_inc_ptr(q->pi);
+	hdev->asic_funcs->ring_doorbell(hdev, q->hw_queue_id, q->pi);
+}
+
+/*
+ * ext_queue_sanity_checks - perform some sanity checks on external queue
+ *
+ * @hdev              : pointer to hl_device structure
+ * @q                 :	pointer to hl_hw_queue structure
+ * @num_of_entries    : how many entries to check for space
+ * @reserve_cq_entry  :	whether to reserve an entry in the cq
+ *
+ * H/W queues spinlock should be taken before calling this function
+ *
+ * Perform the following:
+ * - Make sure we have enough space in the h/w queue
+ * - Make sure we have enough space in the completion queue
+ * - Reserve space in the completion queue (needs to be reversed if there
+ *   is a failure down the road before the actual submission of work). Only
+ *   do this action if reserve_cq_entry is true
+ *
+ */
+static int ext_queue_sanity_checks(struct hl_device *hdev,
+				struct hl_hw_queue *q, int num_of_entries,
+				bool reserve_cq_entry)
+{
+	atomic_t *free_slots =
+			&hdev->completion_queue[q->cq_id].free_slots_cnt;
+	int free_slots_cnt;
+
+	/* Check we have enough space in the queue */
+	free_slots_cnt = queue_free_slots(q, HL_QUEUE_LENGTH);
+
+	if (free_slots_cnt < num_of_entries) {
+		dev_dbg(hdev->dev, "Queue %d doesn't have room for %d CBs\n",
+			q->hw_queue_id, num_of_entries);
+		return -EAGAIN;
+	}
+
+	if (reserve_cq_entry) {
+		/*
+		 * Check we have enough space in the completion queue
+		 * Add -1 to counter (decrement) unless counter was already 0
+		 * In that case, CQ is full so we can't submit a new CB because
+		 * we won't get ack on its completion
+		 * atomic_add_unless will return 0 if counter was already 0
+		 */
+		if (atomic_add_negative(num_of_entries * -1, free_slots)) {
+			dev_dbg(hdev->dev, "No space for %d on CQ %d\n",
+				num_of_entries, q->hw_queue_id);
+			atomic_add(num_of_entries, free_slots);
+			return -EAGAIN;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * int_queue_sanity_checks - perform some sanity checks on internal queue
+ *
+ * @hdev              : pointer to hl_device structure
+ * @q                 :	pointer to hl_hw_queue structure
+ * @num_of_entries    : how many entries to check for space
+ *
+ * H/W queues spinlock should be taken before calling this function
+ *
+ * Perform the following:
+ * - Make sure we have enough space in the h/w queue
+ *
+ */
+static int int_queue_sanity_checks(struct hl_device *hdev,
+					struct hl_hw_queue *q,
+					int num_of_entries)
+{
+	int free_slots_cnt;
+
+	if (num_of_entries > q->int_queue_len) {
+		dev_err(hdev->dev,
+			"Cannot populate queue %u with %u jobs\n",
+			q->hw_queue_id, num_of_entries);
+		return -ENOMEM;
+	}
+
+	/* Check we have enough space in the queue */
+	free_slots_cnt = queue_free_slots(q, q->int_queue_len);
+
+	if (free_slots_cnt < num_of_entries) {
+		dev_dbg(hdev->dev, "Queue %d doesn't have room for %d CBs\n",
+			q->hw_queue_id, num_of_entries);
+		return -EAGAIN;
+	}
+
+	return 0;
+}
+
+/*
+ * hw_queue_sanity_checks() - Make sure we have enough space in the h/w queue
+ * @hdev: Pointer to hl_device structure.
+ * @q: Pointer to hl_hw_queue structure.
+ * @num_of_entries: How many entries to check for space.
+ *
+ * Notice: We do not reserve queue entries so this function mustn't be called
+ *         more than once per CS for the same queue
+ *
+ */
+static int hw_queue_sanity_checks(struct hl_device *hdev, struct hl_hw_queue *q,
+					int num_of_entries)
+{
+	int free_slots_cnt;
+
+	/* Check we have enough space in the queue */
+	free_slots_cnt = queue_free_slots(q, HL_QUEUE_LENGTH);
+
+	if (free_slots_cnt < num_of_entries) {
+		dev_dbg(hdev->dev, "Queue %d doesn't have room for %d CBs\n",
+			q->hw_queue_id, num_of_entries);
+		return -EAGAIN;
+	}
+
+	return 0;
+}
+
+/*
+ * hl_hw_queue_send_cb_no_cmpl - send a single CB (not a JOB) without completion
+ *
+ * @hdev: pointer to hl_device structure
+ * @hw_queue_id: Queue's type
+ * @cb_size: size of CB
+ * @cb_ptr: pointer to CB location
+ *
+ * This function sends a single CB, that must NOT generate a completion entry
+ *
+ */
+int hl_hw_queue_send_cb_no_cmpl(struct hl_device *hdev, u32 hw_queue_id,
+				u32 cb_size, u64 cb_ptr)
+{
+	struct hl_hw_queue *q = &hdev->kernel_queues[hw_queue_id];
+	int rc = 0;
+
+	/*
+	 * The CPU queue is a synchronous queue with an effective depth of
+	 * a single entry (although it is allocated with room for multiple
+	 * entries). Therefore, there is a different lock, called
+	 * send_cpu_message_lock, that serializes accesses to the CPU queue.
+	 * As a result, we don't need to lock the access to the entire H/W
+	 * queues module when submitting a JOB to the CPU queue
+	 */
+	if (q->queue_type != QUEUE_TYPE_CPU)
+		hdev->asic_funcs->hw_queues_lock(hdev);
+
+	if (hdev->disabled) {
+		rc = -EPERM;
+		goto out;
+	}
+
+	/*
+	 * hl_hw_queue_send_cb_no_cmpl() is called for queues of a H/W queue
+	 * type only on init phase, when the queues are empty and being tested,
+	 * so there is no need for sanity checks.
+	 */
+	if (q->queue_type != QUEUE_TYPE_HW) {
+		rc = ext_queue_sanity_checks(hdev, q, 1, false);
+		if (rc)
+			goto out;
+	}
+
+	ext_and_hw_queue_submit_bd(hdev, q, 0, cb_size, cb_ptr);
+
+out:
+	if (q->queue_type != QUEUE_TYPE_CPU)
+		hdev->asic_funcs->hw_queues_unlock(hdev);
+
+	return rc;
+}
+
+/*
+ * ext_queue_schedule_job - submit a JOB to an external queue
+ *
+ * @job: pointer to the job that needs to be submitted to the queue
+ *
+ * This function must be called when the scheduler mutex is taken
+ *
+ */
+static void ext_queue_schedule_job(struct hl_cs_job *job)
+{
+	struct hl_device *hdev = job->cs->ctx->hdev;
+	struct hl_hw_queue *q = &hdev->kernel_queues[job->hw_queue_id];
+	struct hl_cq_entry cq_pkt;
+	struct hl_cq *cq;
+	u64 cq_addr;
+	struct hl_cb *cb;
+	u32 ctl;
+	u32 len;
+	u64 ptr;
+
+	/*
+	 * Update the JOB ID inside the BD CTL so the device would know what
+	 * to write in the completion queue
+	 */
+	ctl = ((q->pi << BD_CTL_SHADOW_INDEX_SHIFT) & BD_CTL_SHADOW_INDEX_MASK);
+
+	cb = job->patched_cb;
+	len = job->job_cb_size;
+	ptr = cb->bus_address;
+
+	cq_pkt.data = cpu_to_le32(
+				((q->pi << CQ_ENTRY_SHADOW_INDEX_SHIFT)
+					& CQ_ENTRY_SHADOW_INDEX_MASK) |
+				(1 << CQ_ENTRY_SHADOW_INDEX_VALID_SHIFT) |
+				(1 << CQ_ENTRY_READY_SHIFT));
+
+	/*
+	 * No need to protect pi_offset because scheduling to the
+	 * H/W queues is done under the scheduler mutex
+	 *
+	 * No need to check if CQ is full because it was already
+	 * checked in ext_queue_sanity_checks
+	 */
+	cq = &hdev->completion_queue[q->cq_id];
+	cq_addr = cq->bus_address + cq->pi * sizeof(struct hl_cq_entry);
+
+	hdev->asic_funcs->add_end_of_cb_packets(hdev, cb->kernel_address, len,
+						cq_addr,
+						le32_to_cpu(cq_pkt.data),
+						q->msi_vec,
+						job->contains_dma_pkt);
+
+	q->shadow_queue[hl_pi_2_offset(q->pi)] = job;
+
+	cq->pi = hl_cq_inc_ptr(cq->pi);
+
+	ext_and_hw_queue_submit_bd(hdev, q, ctl, len, ptr);
+}
+
+/*
+ * int_queue_schedule_job - submit a JOB to an internal queue
+ *
+ * @job: pointer to the job that needs to be submitted to the queue
+ *
+ * This function must be called when the scheduler mutex is taken
+ *
+ */
+static void int_queue_schedule_job(struct hl_cs_job *job)
+{
+	struct hl_device *hdev = job->cs->ctx->hdev;
+	struct hl_hw_queue *q = &hdev->kernel_queues[job->hw_queue_id];
+	struct hl_bd bd;
+	__le64 *pi;
+
+	bd.ctl = 0;
+	bd.len = cpu_to_le32(job->job_cb_size);
+	bd.ptr = cpu_to_le64((u64) (uintptr_t) job->user_cb);
+
+	pi = (__le64 *) (uintptr_t) (q->kernel_address +
+		((q->pi & (q->int_queue_len - 1)) * sizeof(bd)));
+
+	q->pi++;
+	q->pi &= ((q->int_queue_len << 1) - 1);
+
+	hdev->asic_funcs->pqe_write(hdev, pi, &bd);
+
+	hdev->asic_funcs->ring_doorbell(hdev, q->hw_queue_id, q->pi);
+}
+
+/*
+ * hw_queue_schedule_job - submit a JOB to a H/W queue
+ *
+ * @job: pointer to the job that needs to be submitted to the queue
+ *
+ * This function must be called when the scheduler mutex is taken
+ *
+ */
+static void hw_queue_schedule_job(struct hl_cs_job *job)
+{
+	struct hl_device *hdev = job->cs->ctx->hdev;
+	struct hl_hw_queue *q = &hdev->kernel_queues[job->hw_queue_id];
+	u64 ptr;
+	u32 offset, ctl, len;
+
+	/*
+	 * Upon PQE completion, COMP_DATA is used as the write data to the
+	 * completion queue (QMAN HBW message), and COMP_OFFSET is used as the
+	 * write address offset in the SM block (QMAN LBW message).
+	 * The write address offset is calculated as "COMP_OFFSET << 2".
+	 */
+	offset = job->cs->sequence & (hdev->asic_prop.max_pending_cs - 1);
+	ctl = ((offset << BD_CTL_COMP_OFFSET_SHIFT) & BD_CTL_COMP_OFFSET_MASK) |
+		((q->pi << BD_CTL_COMP_DATA_SHIFT) & BD_CTL_COMP_DATA_MASK);
+
+	len = job->job_cb_size;
+
+	/*
+	 * A patched CB is created only if a user CB was allocated by driver and
+	 * MMU is disabled. If MMU is enabled, the user CB should be used
+	 * instead. If the user CB wasn't allocated by driver, assume that it
+	 * holds an address.
+	 */
+	if (job->patched_cb)
+		ptr = job->patched_cb->bus_address;
+	else if (job->is_kernel_allocated_cb)
+		ptr = job->user_cb->bus_address;
+	else
+		ptr = (u64) (uintptr_t) job->user_cb;
+
+	ext_and_hw_queue_submit_bd(hdev, q, ctl, len, ptr);
+}
+
+/*
+ * init_signal_wait_cs - initialize a signal/wait CS
+ * @cs: pointer to the signal/wait CS
+ *
+ * H/W queues spinlock should be taken before calling this function
+ */
+static void init_signal_wait_cs(struct hl_cs *cs)
+{
+	struct hl_ctx *ctx = cs->ctx;
+	struct hl_device *hdev = ctx->hdev;
+	struct hl_hw_queue *hw_queue;
+	struct hl_cs_compl *cs_cmpl =
+			container_of(cs->fence, struct hl_cs_compl, base_fence);
+
+	struct hl_hw_sob *hw_sob;
+	struct hl_cs_job *job;
+	u32 q_idx;
+
+	/* There is only one job in a signal/wait CS */
+	job = list_first_entry(&cs->job_list, struct hl_cs_job,
+				cs_node);
+	q_idx = job->hw_queue_id;
+	hw_queue = &hdev->kernel_queues[q_idx];
+
+	if (cs->type & CS_TYPE_SIGNAL) {
+		hw_sob = &hw_queue->hw_sob[hw_queue->curr_sob_offset];
+
+		cs_cmpl->hw_sob = hw_sob;
+		cs_cmpl->sob_val = hw_queue->next_sob_val++;
+
+		dev_dbg(hdev->dev,
+			"generate signal CB, sob_id: %d, sob val: 0x%x, q_idx: %d\n",
+			cs_cmpl->hw_sob->sob_id, cs_cmpl->sob_val, q_idx);
+
+		hdev->asic_funcs->gen_signal_cb(hdev, job->patched_cb,
+					cs_cmpl->hw_sob->sob_id);
+
+		kref_get(&hw_sob->kref);
+
+		/* check for wraparound */
+		if (hw_queue->next_sob_val == HL_MAX_SOB_VAL) {
+			/*
+			 * Decrement as we reached the max value.
+			 * The release function won't be called here as we've
+			 * just incremented the refcount.
+			 */
+			kref_put(&hw_sob->kref, hl_sob_reset_error);
+			hw_queue->next_sob_val = 1;
+			/* only two SOBs are currently in use */
+			hw_queue->curr_sob_offset =
+					(hw_queue->curr_sob_offset + 1) %
+						HL_RSVD_SOBS_IN_USE;
+
+			dev_dbg(hdev->dev, "switched to SOB %d, q_idx: %d\n",
+					hw_queue->curr_sob_offset, q_idx);
+		}
+	} else if (cs->type & CS_TYPE_WAIT) {
+		struct hl_cs_compl *signal_cs_cmpl;
+
+		signal_cs_cmpl = container_of(cs->signal_fence,
+						struct hl_cs_compl,
+						base_fence);
+
+		/* copy the the SOB id and value of the signal CS */
+		cs_cmpl->hw_sob = signal_cs_cmpl->hw_sob;
+		cs_cmpl->sob_val = signal_cs_cmpl->sob_val;
+
+		dev_dbg(hdev->dev,
+			"generate wait CB, sob_id: %d, sob_val: 0x%x, mon_id: %d, q_idx: %d\n",
+			cs_cmpl->hw_sob->sob_id, cs_cmpl->sob_val,
+			hw_queue->base_mon_id, q_idx);
+
+		hdev->asic_funcs->gen_wait_cb(hdev, job->patched_cb,
+						cs_cmpl->hw_sob->sob_id,
+						cs_cmpl->sob_val,
+						hw_queue->base_mon_id,
+						q_idx);
+
+		kref_get(&cs_cmpl->hw_sob->kref);
+		/*
+		 * Must put the signal fence after the SOB refcnt increment so
+		 * the SOB refcnt won't turn 0 and reset the SOB before the
+		 * wait CS was submitted.
+		 */
+		mb();
+		dma_fence_put(cs->signal_fence);
+		cs->signal_fence = NULL;
+	}
+}
+
+/*
+ * hl_hw_queue_schedule_cs - schedule a command submission
+ * @cs: pointer to the CS
+ */
+int hl_hw_queue_schedule_cs(struct hl_cs *cs)
+{
+	struct hl_ctx *ctx = cs->ctx;
+	struct hl_device *hdev = ctx->hdev;
+	struct hl_cs_job *job, *tmp;
+	struct hl_hw_queue *q;
+	u32 max_queues;
+	int rc = 0, i, cq_cnt;
+
+	hdev->asic_funcs->hw_queues_lock(hdev);
+
+	if (hl_device_disabled_or_in_reset(hdev)) {
+		ctx->cs_counters.device_in_reset_drop_cnt++;
+		dev_err(hdev->dev,
+			"device is disabled or in reset, CS rejected!\n");
+		rc = -EPERM;
+		goto out;
+	}
+
+	max_queues = hdev->asic_prop.max_queues;
+
+	q = &hdev->kernel_queues[0];
+	for (i = 0, cq_cnt = 0 ; i < max_queues ; i++, q++) {
+		if (cs->jobs_in_queue_cnt[i]) {
+			switch (q->queue_type) {
+			case QUEUE_TYPE_EXT:
+				rc = ext_queue_sanity_checks(hdev, q,
+						cs->jobs_in_queue_cnt[i], true);
+				break;
+			case QUEUE_TYPE_INT:
+				rc = int_queue_sanity_checks(hdev, q,
+						cs->jobs_in_queue_cnt[i]);
+				break;
+			case QUEUE_TYPE_HW:
+				rc = hw_queue_sanity_checks(hdev, q,
+						cs->jobs_in_queue_cnt[i]);
+				break;
+			default:
+				dev_err(hdev->dev, "Queue type %d is invalid\n",
+					q->queue_type);
+				rc = -EINVAL;
+				break;
+			}
+
+			if (rc) {
+				ctx->cs_counters.queue_full_drop_cnt++;
+				goto unroll_cq_resv;
+			}
+
+			if (q->queue_type == QUEUE_TYPE_EXT)
+				cq_cnt++;
+		}
+	}
+
+	if ((cs->type == CS_TYPE_SIGNAL) || (cs->type == CS_TYPE_WAIT))
+		init_signal_wait_cs(cs);
+
+	spin_lock(&hdev->hw_queues_mirror_lock);
+	list_add_tail(&cs->mirror_node, &hdev->hw_queues_mirror_list);
+
+	/* Queue TDR if the CS is the first entry and if timeout is wanted */
+	if ((hdev->timeout_jiffies != MAX_SCHEDULE_TIMEOUT) &&
+			(list_first_entry(&hdev->hw_queues_mirror_list,
+					struct hl_cs, mirror_node) == cs)) {
+		cs->tdr_active = true;
+		schedule_delayed_work(&cs->work_tdr, hdev->timeout_jiffies);
+		spin_unlock(&hdev->hw_queues_mirror_lock);
+	} else {
+		spin_unlock(&hdev->hw_queues_mirror_lock);
+	}
+
+	if (!hdev->cs_active_cnt++) {
+		struct hl_device_idle_busy_ts *ts;
+
+		ts = &hdev->idle_busy_ts_arr[hdev->idle_busy_ts_idx];
+		ts->busy_to_idle_ts = ktime_set(0, 0);
+		ts->idle_to_busy_ts = ktime_get();
+	}
+
+	list_for_each_entry_safe(job, tmp, &cs->job_list, cs_node)
+		switch (job->queue_type) {
+		case QUEUE_TYPE_EXT:
+			ext_queue_schedule_job(job);
+			break;
+		case QUEUE_TYPE_INT:
+			int_queue_schedule_job(job);
+			break;
+		case QUEUE_TYPE_HW:
+			hw_queue_schedule_job(job);
+			break;
+		default:
+			break;
+		}
+
+	cs->submitted = true;
+
+	goto out;
+
+unroll_cq_resv:
+	q = &hdev->kernel_queues[0];
+	for (i = 0 ; (i < max_queues) && (cq_cnt > 0) ; i++, q++) {
+		if ((q->queue_type == QUEUE_TYPE_EXT) &&
+						(cs->jobs_in_queue_cnt[i])) {
+			atomic_t *free_slots =
+				&hdev->completion_queue[i].free_slots_cnt;
+			atomic_add(cs->jobs_in_queue_cnt[i], free_slots);
+			cq_cnt--;
+		}
+	}
+
+out:
+	hdev->asic_funcs->hw_queues_unlock(hdev);
+
+	return rc;
+}
+
+/*
+ * hl_hw_queue_inc_ci_kernel - increment ci for kernel's queue
+ *
+ * @hdev: pointer to hl_device structure
+ * @hw_queue_id: which queue to increment its ci
+ */
+void hl_hw_queue_inc_ci_kernel(struct hl_device *hdev, u32 hw_queue_id)
+{
+	struct hl_hw_queue *q = &hdev->kernel_queues[hw_queue_id];
+
+	atomic_inc(&q->ci);
+}
+
+static int ext_and_cpu_queue_init(struct hl_device *hdev, struct hl_hw_queue *q,
+					bool is_cpu_queue)
+{
+	void *p;
+	int rc;
+
+	if (is_cpu_queue)
+		p = hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev,
+							HL_QUEUE_SIZE_IN_BYTES,
+							&q->bus_address);
+	else
+		p = hdev->asic_funcs->asic_dma_alloc_coherent(hdev,
+						HL_QUEUE_SIZE_IN_BYTES,
+						&q->bus_address,
+						GFP_KERNEL | __GFP_ZERO);
+	if (!p)
+		return -ENOMEM;
+
+	q->kernel_address = (u64) (uintptr_t) p;
+
+	q->shadow_queue = kmalloc_array(HL_QUEUE_LENGTH,
+					sizeof(*q->shadow_queue),
+					GFP_KERNEL);
+	if (!q->shadow_queue) {
+		dev_err(hdev->dev,
+			"Failed to allocate shadow queue for H/W queue %d\n",
+			q->hw_queue_id);
+		rc = -ENOMEM;
+		goto free_queue;
+	}
+
+	/* Make sure read/write pointers are initialized to start of queue */
+	atomic_set(&q->ci, 0);
+	q->pi = 0;
+
+	return 0;
+
+free_queue:
+	if (is_cpu_queue)
+		hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev,
+					HL_QUEUE_SIZE_IN_BYTES,
+					(void *) (uintptr_t) q->kernel_address);
+	else
+		hdev->asic_funcs->asic_dma_free_coherent(hdev,
+					HL_QUEUE_SIZE_IN_BYTES,
+					(void *) (uintptr_t) q->kernel_address,
+					q->bus_address);
+
+	return rc;
+}
+
+static int int_queue_init(struct hl_device *hdev, struct hl_hw_queue *q)
+{
+	void *p;
+
+	p = hdev->asic_funcs->get_int_queue_base(hdev, q->hw_queue_id,
+					&q->bus_address, &q->int_queue_len);
+	if (!p) {
+		dev_err(hdev->dev,
+			"Failed to get base address for internal queue %d\n",
+			q->hw_queue_id);
+		return -EFAULT;
+	}
+
+	q->kernel_address = (u64) (uintptr_t) p;
+	q->pi = 0;
+	atomic_set(&q->ci, 0);
+
+	return 0;
+}
+
+static int cpu_queue_init(struct hl_device *hdev, struct hl_hw_queue *q)
+{
+	return ext_and_cpu_queue_init(hdev, q, true);
+}
+
+static int ext_queue_init(struct hl_device *hdev, struct hl_hw_queue *q)
+{
+	return ext_and_cpu_queue_init(hdev, q, false);
+}
+
+static int hw_queue_init(struct hl_device *hdev, struct hl_hw_queue *q)
+{
+	void *p;
+
+	p = hdev->asic_funcs->asic_dma_alloc_coherent(hdev,
+						HL_QUEUE_SIZE_IN_BYTES,
+						&q->bus_address,
+						GFP_KERNEL | __GFP_ZERO);
+	if (!p)
+		return -ENOMEM;
+
+	q->kernel_address = (u64) (uintptr_t) p;
+
+	/* Make sure read/write pointers are initialized to start of queue */
+	atomic_set(&q->ci, 0);
+	q->pi = 0;
+
+	return 0;
+}
+
+static void sync_stream_queue_init(struct hl_device *hdev, u32 q_idx)
+{
+	struct hl_hw_queue *hw_queue = &hdev->kernel_queues[q_idx];
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct hl_hw_sob *hw_sob;
+	int sob, queue_idx = hdev->sync_stream_queue_idx++;
+
+	hw_queue->base_sob_id =
+		prop->sync_stream_first_sob + queue_idx * HL_RSVD_SOBS;
+	hw_queue->base_mon_id =
+		prop->sync_stream_first_mon + queue_idx * HL_RSVD_MONS;
+	hw_queue->next_sob_val = 1;
+	hw_queue->curr_sob_offset = 0;
+
+	for (sob = 0 ; sob < HL_RSVD_SOBS ; sob++) {
+		hw_sob = &hw_queue->hw_sob[sob];
+		hw_sob->hdev = hdev;
+		hw_sob->sob_id = hw_queue->base_sob_id + sob;
+		hw_sob->q_idx = q_idx;
+		kref_init(&hw_sob->kref);
+	}
+}
+
+static void sync_stream_queue_reset(struct hl_device *hdev, u32 q_idx)
+{
+	struct hl_hw_queue *hw_queue = &hdev->kernel_queues[q_idx];
+
+	/*
+	 * In case we got here due to a stuck CS, the refcnt might be bigger
+	 * than 1 and therefore we reset it.
+	 */
+	kref_init(&hw_queue->hw_sob[hw_queue->curr_sob_offset].kref);
+	hw_queue->curr_sob_offset = 0;
+	hw_queue->next_sob_val = 1;
+}
+
+/*
+ * queue_init - main initialization function for H/W queue object
+ *
+ * @hdev: pointer to hl_device device structure
+ * @q: pointer to hl_hw_queue queue structure
+ * @hw_queue_id: The id of the H/W queue
+ *
+ * Allocate dma-able memory for the queue and initialize fields
+ * Returns 0 on success
+ */
+static int queue_init(struct hl_device *hdev, struct hl_hw_queue *q,
+			u32 hw_queue_id)
+{
+	int rc;
+
+	q->hw_queue_id = hw_queue_id;
+
+	switch (q->queue_type) {
+	case QUEUE_TYPE_EXT:
+		rc = ext_queue_init(hdev, q);
+		break;
+	case QUEUE_TYPE_INT:
+		rc = int_queue_init(hdev, q);
+		break;
+	case QUEUE_TYPE_CPU:
+		rc = cpu_queue_init(hdev, q);
+		break;
+	case QUEUE_TYPE_HW:
+		rc = hw_queue_init(hdev, q);
+		break;
+	case QUEUE_TYPE_NA:
+		q->valid = 0;
+		return 0;
+	default:
+		dev_crit(hdev->dev, "wrong queue type %d during init\n",
+			q->queue_type);
+		rc = -EINVAL;
+		break;
+	}
+
+	if (q->supports_sync_stream)
+		sync_stream_queue_init(hdev, q->hw_queue_id);
+
+	if (rc)
+		return rc;
+
+	q->valid = 1;
+
+	return 0;
+}
+
+/*
+ * hw_queue_fini - destroy queue
+ *
+ * @hdev: pointer to hl_device device structure
+ * @q: pointer to hl_hw_queue queue structure
+ *
+ * Free the queue memory
+ */
+static void queue_fini(struct hl_device *hdev, struct hl_hw_queue *q)
+{
+	if (!q->valid)
+		return;
+
+	/*
+	 * If we arrived here, there are no jobs waiting on this queue
+	 * so we can safely remove it.
+	 * This is because this function can only called when:
+	 * 1. Either a context is deleted, which only can occur if all its
+	 *    jobs were finished
+	 * 2. A context wasn't able to be created due to failure or timeout,
+	 *    which means there are no jobs on the queue yet
+	 *
+	 * The only exception are the queues of the kernel context, but
+	 * if they are being destroyed, it means that the entire module is
+	 * being removed. If the module is removed, it means there is no open
+	 * user context. It also means that if a job was submitted by
+	 * the kernel driver (e.g. context creation), the job itself was
+	 * released by the kernel driver when a timeout occurred on its
+	 * Completion. Thus, we don't need to release it again.
+	 */
+
+	if (q->queue_type == QUEUE_TYPE_INT)
+		return;
+
+	kfree(q->shadow_queue);
+
+	if (q->queue_type == QUEUE_TYPE_CPU)
+		hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev,
+					HL_QUEUE_SIZE_IN_BYTES,
+					(void *) (uintptr_t) q->kernel_address);
+	else
+		hdev->asic_funcs->asic_dma_free_coherent(hdev,
+					HL_QUEUE_SIZE_IN_BYTES,
+					(void *) (uintptr_t) q->kernel_address,
+					q->bus_address);
+}
+
+int hl_hw_queues_create(struct hl_device *hdev)
+{
+	struct asic_fixed_properties *asic = &hdev->asic_prop;
+	struct hl_hw_queue *q;
+	int i, rc, q_ready_cnt;
+
+	hdev->kernel_queues = kcalloc(asic->max_queues,
+				sizeof(*hdev->kernel_queues), GFP_KERNEL);
+
+	if (!hdev->kernel_queues) {
+		dev_err(hdev->dev, "Not enough memory for H/W queues\n");
+		return -ENOMEM;
+	}
+
+	/* Initialize the H/W queues */
+	for (i = 0, q_ready_cnt = 0, q = hdev->kernel_queues;
+			i < asic->max_queues ; i++, q_ready_cnt++, q++) {
+
+		q->queue_type = asic->hw_queues_props[i].type;
+		q->supports_sync_stream =
+				asic->hw_queues_props[i].supports_sync_stream;
+		rc = queue_init(hdev, q, i);
+		if (rc) {
+			dev_err(hdev->dev,
+				"failed to initialize queue %d\n", i);
+			goto release_queues;
+		}
+	}
+
+	return 0;
+
+release_queues:
+	for (i = 0, q = hdev->kernel_queues ; i < q_ready_cnt ; i++, q++)
+		queue_fini(hdev, q);
+
+	kfree(hdev->kernel_queues);
+
+	return rc;
+}
+
+void hl_hw_queues_destroy(struct hl_device *hdev)
+{
+	struct hl_hw_queue *q;
+	u32 max_queues = hdev->asic_prop.max_queues;
+	int i;
+
+	for (i = 0, q = hdev->kernel_queues ; i < max_queues ; i++, q++)
+		queue_fini(hdev, q);
+
+	kfree(hdev->kernel_queues);
+}
+
+void hl_hw_queue_reset(struct hl_device *hdev, bool hard_reset)
+{
+	struct hl_hw_queue *q;
+	u32 max_queues = hdev->asic_prop.max_queues;
+	int i;
+
+	for (i = 0, q = hdev->kernel_queues ; i < max_queues ; i++, q++) {
+		if ((!q->valid) ||
+			((!hard_reset) && (q->queue_type == QUEUE_TYPE_CPU)))
+			continue;
+		q->pi = 0;
+		atomic_set(&q->ci, 0);
+
+		if (q->supports_sync_stream)
+			sync_stream_queue_reset(hdev, q->hw_queue_id);
+	}
+}
diff --git a/drivers/misc/habanalabs/common/hwmon.c b/drivers/misc/habanalabs/common/hwmon.c
new file mode 100644
index 000000000000..8c6cd77e6af6
--- /dev/null
+++ b/drivers/misc/habanalabs/common/hwmon.c
@@ -0,0 +1,579 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2019 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include "habanalabs.h"
+
+#include <linux/pci.h>
+#include <linux/hwmon.h>
+
+#define SENSORS_PKT_TIMEOUT		1000000	/* 1s */
+#define HWMON_NR_SENSOR_TYPES		(hwmon_pwm + 1)
+
+int hl_build_hwmon_channel_info(struct hl_device *hdev,
+				struct armcp_sensor *sensors_arr)
+{
+	u32 counts[HWMON_NR_SENSOR_TYPES] = {0};
+	u32 *sensors_by_type[HWMON_NR_SENSOR_TYPES] = {NULL};
+	u32 sensors_by_type_next_index[HWMON_NR_SENSOR_TYPES] = {0};
+	struct hwmon_channel_info **channels_info;
+	u32 num_sensors_for_type, num_active_sensor_types = 0,
+			arr_size = 0, *curr_arr;
+	enum hwmon_sensor_types type;
+	int rc, i, j;
+
+	for (i = 0 ; i < ARMCP_MAX_SENSORS ; i++) {
+		type = le32_to_cpu(sensors_arr[i].type);
+
+		if ((type == 0) && (sensors_arr[i].flags == 0))
+			break;
+
+		if (type >= HWMON_NR_SENSOR_TYPES) {
+			dev_err(hdev->dev,
+				"Got wrong sensor type %d from device\n", type);
+			return -EINVAL;
+		}
+
+		counts[type]++;
+		arr_size++;
+	}
+
+	for (i = 0 ; i < HWMON_NR_SENSOR_TYPES ; i++) {
+		if (counts[i] == 0)
+			continue;
+
+		num_sensors_for_type = counts[i] + 1;
+		curr_arr = kcalloc(num_sensors_for_type, sizeof(*curr_arr),
+				GFP_KERNEL);
+		if (!curr_arr) {
+			rc = -ENOMEM;
+			goto sensors_type_err;
+		}
+
+		num_active_sensor_types++;
+		sensors_by_type[i] = curr_arr;
+	}
+
+	for (i = 0 ; i < arr_size ; i++) {
+		type = le32_to_cpu(sensors_arr[i].type);
+		curr_arr = sensors_by_type[type];
+		curr_arr[sensors_by_type_next_index[type]++] =
+				le32_to_cpu(sensors_arr[i].flags);
+	}
+
+	channels_info = kcalloc(num_active_sensor_types + 1,
+			sizeof(*channels_info), GFP_KERNEL);
+	if (!channels_info) {
+		rc = -ENOMEM;
+		goto channels_info_array_err;
+	}
+
+	for (i = 0 ; i < num_active_sensor_types ; i++) {
+		channels_info[i] = kzalloc(sizeof(*channels_info[i]),
+				GFP_KERNEL);
+		if (!channels_info[i]) {
+			rc = -ENOMEM;
+			goto channel_info_err;
+		}
+	}
+
+	for (i = 0, j = 0 ; i < HWMON_NR_SENSOR_TYPES ; i++) {
+		if (!sensors_by_type[i])
+			continue;
+
+		channels_info[j]->type = i;
+		channels_info[j]->config = sensors_by_type[i];
+		j++;
+	}
+
+	hdev->hl_chip_info->info =
+			(const struct hwmon_channel_info **)channels_info;
+
+	return 0;
+
+channel_info_err:
+	for (i = 0 ; i < num_active_sensor_types ; i++)
+		if (channels_info[i]) {
+			kfree(channels_info[i]->config);
+			kfree(channels_info[i]);
+		}
+	kfree(channels_info);
+channels_info_array_err:
+sensors_type_err:
+	for (i = 0 ; i < HWMON_NR_SENSOR_TYPES ; i++)
+		kfree(sensors_by_type[i]);
+
+	return rc;
+}
+
+static int hl_read(struct device *dev, enum hwmon_sensor_types type,
+			u32 attr, int channel, long *val)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+	int rc;
+
+	if (hl_device_disabled_or_in_reset(hdev))
+		return -ENODEV;
+
+	switch (type) {
+	case hwmon_temp:
+		switch (attr) {
+		case hwmon_temp_input:
+		case hwmon_temp_max:
+		case hwmon_temp_crit:
+		case hwmon_temp_max_hyst:
+		case hwmon_temp_crit_hyst:
+		case hwmon_temp_offset:
+		case hwmon_temp_highest:
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		rc = hl_get_temperature(hdev, channel, attr, val);
+		break;
+	case hwmon_in:
+		switch (attr) {
+		case hwmon_in_input:
+		case hwmon_in_min:
+		case hwmon_in_max:
+		case hwmon_in_highest:
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		rc = hl_get_voltage(hdev, channel, attr, val);
+		break;
+	case hwmon_curr:
+		switch (attr) {
+		case hwmon_curr_input:
+		case hwmon_curr_min:
+		case hwmon_curr_max:
+		case hwmon_curr_highest:
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		rc = hl_get_current(hdev, channel, attr, val);
+		break;
+	case hwmon_fan:
+		switch (attr) {
+		case hwmon_fan_input:
+		case hwmon_fan_min:
+		case hwmon_fan_max:
+			break;
+		default:
+			return -EINVAL;
+		}
+		rc = hl_get_fan_speed(hdev, channel, attr, val);
+		break;
+	case hwmon_pwm:
+		switch (attr) {
+		case hwmon_pwm_input:
+		case hwmon_pwm_enable:
+			break;
+		default:
+			return -EINVAL;
+		}
+		rc = hl_get_pwm_info(hdev, channel, attr, val);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return rc;
+}
+
+static int hl_write(struct device *dev, enum hwmon_sensor_types type,
+			u32 attr, int channel, long val)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+
+	if (hl_device_disabled_or_in_reset(hdev))
+		return -ENODEV;
+
+	switch (type) {
+	case hwmon_temp:
+		switch (attr) {
+		case hwmon_temp_offset:
+		case hwmon_temp_reset_history:
+			break;
+		default:
+			return -EINVAL;
+		}
+		hl_set_temperature(hdev, channel, attr, val);
+		break;
+	case hwmon_pwm:
+		switch (attr) {
+		case hwmon_pwm_input:
+		case hwmon_pwm_enable:
+			break;
+		default:
+			return -EINVAL;
+		}
+		hl_set_pwm_info(hdev, channel, attr, val);
+		break;
+	case hwmon_in:
+		switch (attr) {
+		case hwmon_in_reset_history:
+			break;
+		default:
+			return -EINVAL;
+		}
+		hl_set_voltage(hdev, channel, attr, val);
+		break;
+	case hwmon_curr:
+		switch (attr) {
+		case hwmon_curr_reset_history:
+			break;
+		default:
+			return -EINVAL;
+		}
+		hl_set_current(hdev, channel, attr, val);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static umode_t hl_is_visible(const void *data, enum hwmon_sensor_types type,
+				u32 attr, int channel)
+{
+	switch (type) {
+	case hwmon_temp:
+		switch (attr) {
+		case hwmon_temp_input:
+		case hwmon_temp_max:
+		case hwmon_temp_max_hyst:
+		case hwmon_temp_crit:
+		case hwmon_temp_crit_hyst:
+		case hwmon_temp_highest:
+			return 0444;
+		case hwmon_temp_offset:
+			return 0644;
+		case hwmon_temp_reset_history:
+			return 0200;
+		}
+		break;
+	case hwmon_in:
+		switch (attr) {
+		case hwmon_in_input:
+		case hwmon_in_min:
+		case hwmon_in_max:
+		case hwmon_in_highest:
+			return 0444;
+		case hwmon_in_reset_history:
+			return 0200;
+		}
+		break;
+	case hwmon_curr:
+		switch (attr) {
+		case hwmon_curr_input:
+		case hwmon_curr_min:
+		case hwmon_curr_max:
+		case hwmon_curr_highest:
+			return 0444;
+		case hwmon_curr_reset_history:
+			return 0200;
+		}
+		break;
+	case hwmon_fan:
+		switch (attr) {
+		case hwmon_fan_input:
+		case hwmon_fan_min:
+		case hwmon_fan_max:
+			return 0444;
+		}
+		break;
+	case hwmon_pwm:
+		switch (attr) {
+		case hwmon_pwm_input:
+		case hwmon_pwm_enable:
+			return 0644;
+		}
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static const struct hwmon_ops hl_hwmon_ops = {
+	.is_visible = hl_is_visible,
+	.read = hl_read,
+	.write = hl_write
+};
+
+int hl_get_temperature(struct hl_device *hdev,
+			int sensor_index, u32 attr, long *value)
+{
+	struct armcp_packet pkt;
+	int rc;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_TEMPERATURE_GET <<
+				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.sensor_index = __cpu_to_le16(sensor_index);
+	pkt.type = __cpu_to_le16(attr);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+			SENSORS_PKT_TIMEOUT, value);
+
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to get temperature from sensor %d, error %d\n",
+			sensor_index, rc);
+		*value = 0;
+	}
+
+	return rc;
+}
+
+int hl_set_temperature(struct hl_device *hdev,
+			int sensor_index, u32 attr, long value)
+{
+	struct armcp_packet pkt;
+	int rc;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_TEMPERATURE_SET <<
+				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.sensor_index = __cpu_to_le16(sensor_index);
+	pkt.type = __cpu_to_le16(attr);
+	pkt.value = __cpu_to_le64(value);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+						SENSORS_PKT_TIMEOUT, NULL);
+
+	if (rc)
+		dev_err(hdev->dev,
+			"Failed to set temperature of sensor %d, error %d\n",
+			sensor_index, rc);
+
+	return rc;
+}
+
+int hl_get_voltage(struct hl_device *hdev,
+			int sensor_index, u32 attr, long *value)
+{
+	struct armcp_packet pkt;
+	int rc;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_VOLTAGE_GET <<
+				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.sensor_index = __cpu_to_le16(sensor_index);
+	pkt.type = __cpu_to_le16(attr);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+					SENSORS_PKT_TIMEOUT, value);
+
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to get voltage from sensor %d, error %d\n",
+			sensor_index, rc);
+		*value = 0;
+	}
+
+	return rc;
+}
+
+int hl_get_current(struct hl_device *hdev,
+			int sensor_index, u32 attr, long *value)
+{
+	struct armcp_packet pkt;
+	int rc;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_CURRENT_GET <<
+				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.sensor_index = __cpu_to_le16(sensor_index);
+	pkt.type = __cpu_to_le16(attr);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+					SENSORS_PKT_TIMEOUT, value);
+
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to get current from sensor %d, error %d\n",
+			sensor_index, rc);
+		*value = 0;
+	}
+
+	return rc;
+}
+
+int hl_get_fan_speed(struct hl_device *hdev,
+			int sensor_index, u32 attr, long *value)
+{
+	struct armcp_packet pkt;
+	int rc;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_FAN_SPEED_GET <<
+				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.sensor_index = __cpu_to_le16(sensor_index);
+	pkt.type = __cpu_to_le16(attr);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+					SENSORS_PKT_TIMEOUT, value);
+
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to get fan speed from sensor %d, error %d\n",
+			sensor_index, rc);
+		*value = 0;
+	}
+
+	return rc;
+}
+
+int hl_get_pwm_info(struct hl_device *hdev,
+			int sensor_index, u32 attr, long *value)
+{
+	struct armcp_packet pkt;
+	int rc;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_PWM_GET <<
+				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.sensor_index = __cpu_to_le16(sensor_index);
+	pkt.type = __cpu_to_le16(attr);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+					SENSORS_PKT_TIMEOUT, value);
+
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to get pwm info from sensor %d, error %d\n",
+			sensor_index, rc);
+		*value = 0;
+	}
+
+	return rc;
+}
+
+void hl_set_pwm_info(struct hl_device *hdev, int sensor_index, u32 attr,
+			long value)
+{
+	struct armcp_packet pkt;
+	int rc;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_PWM_SET <<
+				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.sensor_index = __cpu_to_le16(sensor_index);
+	pkt.type = __cpu_to_le16(attr);
+	pkt.value = cpu_to_le64(value);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+					SENSORS_PKT_TIMEOUT, NULL);
+
+	if (rc)
+		dev_err(hdev->dev,
+			"Failed to set pwm info to sensor %d, error %d\n",
+			sensor_index, rc);
+}
+
+int hl_set_voltage(struct hl_device *hdev,
+			int sensor_index, u32 attr, long value)
+{
+	struct armcp_packet pkt;
+	int rc;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_VOLTAGE_SET <<
+				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.sensor_index = __cpu_to_le16(sensor_index);
+	pkt.type = __cpu_to_le16(attr);
+	pkt.value = __cpu_to_le64(value);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+						SENSORS_PKT_TIMEOUT, NULL);
+
+	if (rc)
+		dev_err(hdev->dev,
+			"Failed to set voltage of sensor %d, error %d\n",
+			sensor_index, rc);
+
+	return rc;
+}
+
+int hl_set_current(struct hl_device *hdev,
+			int sensor_index, u32 attr, long value)
+{
+	struct armcp_packet pkt;
+	int rc;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_CURRENT_SET <<
+				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.sensor_index = __cpu_to_le16(sensor_index);
+	pkt.type = __cpu_to_le16(attr);
+	pkt.value = __cpu_to_le64(value);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+						SENSORS_PKT_TIMEOUT, NULL);
+
+	if (rc)
+		dev_err(hdev->dev,
+			"Failed to set current of sensor %d, error %d\n",
+			sensor_index, rc);
+
+	return rc;
+}
+
+int hl_hwmon_init(struct hl_device *hdev)
+{
+	struct device *dev = hdev->pdev ? &hdev->pdev->dev : hdev->dev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	int rc;
+
+	if ((hdev->hwmon_initialized) || !(hdev->fw_loading))
+		return 0;
+
+	if (hdev->hl_chip_info->info) {
+		hdev->hl_chip_info->ops = &hl_hwmon_ops;
+
+		hdev->hwmon_dev = hwmon_device_register_with_info(dev,
+					prop->armcp_info.card_name, hdev,
+					hdev->hl_chip_info, NULL);
+		if (IS_ERR(hdev->hwmon_dev)) {
+			rc = PTR_ERR(hdev->hwmon_dev);
+			dev_err(hdev->dev,
+				"Unable to register hwmon device: %d\n", rc);
+			return rc;
+		}
+
+		dev_info(hdev->dev, "%s: add sensors information\n",
+			dev_name(hdev->hwmon_dev));
+
+		hdev->hwmon_initialized = true;
+	} else {
+		dev_info(hdev->dev, "no available sensors\n");
+	}
+
+	return 0;
+}
+
+void hl_hwmon_fini(struct hl_device *hdev)
+{
+	if (!hdev->hwmon_initialized)
+		return;
+
+	hwmon_device_unregister(hdev->hwmon_dev);
+}
diff --git a/drivers/misc/habanalabs/common/irq.c b/drivers/misc/habanalabs/common/irq.c
new file mode 100644
index 000000000000..c8db717023f5
--- /dev/null
+++ b/drivers/misc/habanalabs/common/irq.c
@@ -0,0 +1,320 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2019 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include "habanalabs.h"
+
+#include <linux/slab.h>
+
+/**
+ * struct hl_eqe_work - This structure is used to schedule work of EQ
+ *                      entry and armcp_reset event
+ *
+ * @eq_work:          workqueue object to run when EQ entry is received
+ * @hdev:             pointer to device structure
+ * @eq_entry:         copy of the EQ entry
+ */
+struct hl_eqe_work {
+	struct work_struct	eq_work;
+	struct hl_device	*hdev;
+	struct hl_eq_entry	eq_entry;
+};
+
+/**
+ * hl_cq_inc_ptr - increment ci or pi of cq
+ *
+ * @ptr: the current ci or pi value of the completion queue
+ *
+ * Increment ptr by 1. If it reaches the number of completion queue
+ * entries, set it to 0
+ */
+inline u32 hl_cq_inc_ptr(u32 ptr)
+{
+	ptr++;
+	if (unlikely(ptr == HL_CQ_LENGTH))
+		ptr = 0;
+	return ptr;
+}
+
+/**
+ * hl_eq_inc_ptr - increment ci of eq
+ *
+ * @ptr: the current ci value of the event queue
+ *
+ * Increment ptr by 1. If it reaches the number of event queue
+ * entries, set it to 0
+ */
+inline u32 hl_eq_inc_ptr(u32 ptr)
+{
+	ptr++;
+	if (unlikely(ptr == HL_EQ_LENGTH))
+		ptr = 0;
+	return ptr;
+}
+
+static void irq_handle_eqe(struct work_struct *work)
+{
+	struct hl_eqe_work *eqe_work = container_of(work, struct hl_eqe_work,
+							eq_work);
+	struct hl_device *hdev = eqe_work->hdev;
+
+	hdev->asic_funcs->handle_eqe(hdev, &eqe_work->eq_entry);
+
+	kfree(eqe_work);
+}
+
+/**
+ * hl_irq_handler_cq - irq handler for completion queue
+ *
+ * @irq: irq number
+ * @arg: pointer to completion queue structure
+ *
+ */
+irqreturn_t hl_irq_handler_cq(int irq, void *arg)
+{
+	struct hl_cq *cq = arg;
+	struct hl_device *hdev = cq->hdev;
+	struct hl_hw_queue *queue;
+	struct hl_cs_job *job;
+	bool shadow_index_valid;
+	u16 shadow_index;
+	struct hl_cq_entry *cq_entry, *cq_base;
+
+	if (hdev->disabled) {
+		dev_dbg(hdev->dev,
+			"Device disabled but received IRQ %d for CQ %d\n",
+			irq, cq->hw_queue_id);
+		return IRQ_HANDLED;
+	}
+
+	cq_base = (struct hl_cq_entry *) (uintptr_t) cq->kernel_address;
+
+	while (1) {
+		bool entry_ready = ((le32_to_cpu(cq_base[cq->ci].data) &
+					CQ_ENTRY_READY_MASK)
+						>> CQ_ENTRY_READY_SHIFT);
+
+		if (!entry_ready)
+			break;
+
+		cq_entry = (struct hl_cq_entry *) &cq_base[cq->ci];
+
+		/* Make sure we read CQ entry contents after we've
+		 * checked the ownership bit.
+		 */
+		dma_rmb();
+
+		shadow_index_valid = ((le32_to_cpu(cq_entry->data) &
+					CQ_ENTRY_SHADOW_INDEX_VALID_MASK)
+					>> CQ_ENTRY_SHADOW_INDEX_VALID_SHIFT);
+
+		shadow_index = (u16) ((le32_to_cpu(cq_entry->data) &
+					CQ_ENTRY_SHADOW_INDEX_MASK)
+					>> CQ_ENTRY_SHADOW_INDEX_SHIFT);
+
+		queue = &hdev->kernel_queues[cq->hw_queue_id];
+
+		if ((shadow_index_valid) && (!hdev->disabled)) {
+			job = queue->shadow_queue[hl_pi_2_offset(shadow_index)];
+			queue_work(hdev->cq_wq[cq->cq_idx], &job->finish_work);
+		}
+
+		atomic_inc(&queue->ci);
+
+		/* Clear CQ entry ready bit */
+		cq_entry->data = cpu_to_le32(le32_to_cpu(cq_entry->data) &
+						~CQ_ENTRY_READY_MASK);
+
+		cq->ci = hl_cq_inc_ptr(cq->ci);
+
+		/* Increment free slots */
+		atomic_inc(&cq->free_slots_cnt);
+	}
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * hl_irq_handler_eq - irq handler for event queue
+ *
+ * @irq: irq number
+ * @arg: pointer to event queue structure
+ *
+ */
+irqreturn_t hl_irq_handler_eq(int irq, void *arg)
+{
+	struct hl_eq *eq = arg;
+	struct hl_device *hdev = eq->hdev;
+	struct hl_eq_entry *eq_entry;
+	struct hl_eq_entry *eq_base;
+	struct hl_eqe_work *handle_eqe_work;
+
+	eq_base = (struct hl_eq_entry *) (uintptr_t) eq->kernel_address;
+
+	while (1) {
+		bool entry_ready =
+			((le32_to_cpu(eq_base[eq->ci].hdr.ctl) &
+				EQ_CTL_READY_MASK) >> EQ_CTL_READY_SHIFT);
+
+		if (!entry_ready)
+			break;
+
+		eq_entry = &eq_base[eq->ci];
+
+		/*
+		 * Make sure we read EQ entry contents after we've
+		 * checked the ownership bit.
+		 */
+		dma_rmb();
+
+		if (hdev->disabled) {
+			dev_warn(hdev->dev,
+				"Device disabled but received IRQ %d for EQ\n",
+					irq);
+			goto skip_irq;
+		}
+
+		handle_eqe_work = kmalloc(sizeof(*handle_eqe_work), GFP_ATOMIC);
+		if (handle_eqe_work) {
+			INIT_WORK(&handle_eqe_work->eq_work, irq_handle_eqe);
+			handle_eqe_work->hdev = hdev;
+
+			memcpy(&handle_eqe_work->eq_entry, eq_entry,
+					sizeof(*eq_entry));
+
+			queue_work(hdev->eq_wq, &handle_eqe_work->eq_work);
+		}
+skip_irq:
+		/* Clear EQ entry ready bit */
+		eq_entry->hdr.ctl =
+			cpu_to_le32(le32_to_cpu(eq_entry->hdr.ctl) &
+							~EQ_CTL_READY_MASK);
+
+		eq->ci = hl_eq_inc_ptr(eq->ci);
+
+		hdev->asic_funcs->update_eq_ci(hdev, eq->ci);
+	}
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * hl_cq_init - main initialization function for an cq object
+ *
+ * @hdev: pointer to device structure
+ * @q: pointer to cq structure
+ * @hw_queue_id: The H/W queue ID this completion queue belongs to
+ *
+ * Allocate dma-able memory for the completion queue and initialize fields
+ * Returns 0 on success
+ */
+int hl_cq_init(struct hl_device *hdev, struct hl_cq *q, u32 hw_queue_id)
+{
+	void *p;
+
+	p = hdev->asic_funcs->asic_dma_alloc_coherent(hdev, HL_CQ_SIZE_IN_BYTES,
+				&q->bus_address, GFP_KERNEL | __GFP_ZERO);
+	if (!p)
+		return -ENOMEM;
+
+	q->hdev = hdev;
+	q->kernel_address = (u64) (uintptr_t) p;
+	q->hw_queue_id = hw_queue_id;
+	q->ci = 0;
+	q->pi = 0;
+
+	atomic_set(&q->free_slots_cnt, HL_CQ_LENGTH);
+
+	return 0;
+}
+
+/**
+ * hl_cq_fini - destroy completion queue
+ *
+ * @hdev: pointer to device structure
+ * @q: pointer to cq structure
+ *
+ * Free the completion queue memory
+ */
+void hl_cq_fini(struct hl_device *hdev, struct hl_cq *q)
+{
+	hdev->asic_funcs->asic_dma_free_coherent(hdev, HL_CQ_SIZE_IN_BYTES,
+			(void *) (uintptr_t) q->kernel_address, q->bus_address);
+}
+
+void hl_cq_reset(struct hl_device *hdev, struct hl_cq *q)
+{
+	q->ci = 0;
+	q->pi = 0;
+
+	atomic_set(&q->free_slots_cnt, HL_CQ_LENGTH);
+
+	/*
+	 * It's not enough to just reset the PI/CI because the H/W may have
+	 * written valid completion entries before it was halted and therefore
+	 * we need to clean the actual queues so we won't process old entries
+	 * when the device is operational again
+	 */
+
+	memset((void *) (uintptr_t) q->kernel_address, 0, HL_CQ_SIZE_IN_BYTES);
+}
+
+/**
+ * hl_eq_init - main initialization function for an event queue object
+ *
+ * @hdev: pointer to device structure
+ * @q: pointer to eq structure
+ *
+ * Allocate dma-able memory for the event queue and initialize fields
+ * Returns 0 on success
+ */
+int hl_eq_init(struct hl_device *hdev, struct hl_eq *q)
+{
+	void *p;
+
+	p = hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev,
+							HL_EQ_SIZE_IN_BYTES,
+							&q->bus_address);
+	if (!p)
+		return -ENOMEM;
+
+	q->hdev = hdev;
+	q->kernel_address = (u64) (uintptr_t) p;
+	q->ci = 0;
+
+	return 0;
+}
+
+/**
+ * hl_eq_fini - destroy event queue
+ *
+ * @hdev: pointer to device structure
+ * @q: pointer to eq structure
+ *
+ * Free the event queue memory
+ */
+void hl_eq_fini(struct hl_device *hdev, struct hl_eq *q)
+{
+	flush_workqueue(hdev->eq_wq);
+
+	hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev,
+					HL_EQ_SIZE_IN_BYTES,
+					(void *) (uintptr_t) q->kernel_address);
+}
+
+void hl_eq_reset(struct hl_device *hdev, struct hl_eq *q)
+{
+	q->ci = 0;
+
+	/*
+	 * It's not enough to just reset the PI/CI because the H/W may have
+	 * written valid completion entries before it was halted and therefore
+	 * we need to clean the actual queues so we won't process old entries
+	 * when the device is operational again
+	 */
+
+	memset((void *) (uintptr_t) q->kernel_address, 0, HL_EQ_SIZE_IN_BYTES);
+}
diff --git a/drivers/misc/habanalabs/common/memory.c b/drivers/misc/habanalabs/common/memory.c
new file mode 100644
index 000000000000..e4e1693e5c6c
--- /dev/null
+++ b/drivers/misc/habanalabs/common/memory.c
@@ -0,0 +1,1843 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2019 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include <uapi/misc/habanalabs.h>
+#include "habanalabs.h"
+#include "include/hw_ip/mmu/mmu_general.h"
+
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/genalloc.h>
+
+#define HL_MMU_DEBUG	0
+
+/*
+ * The va ranges in context object contain a list with the available chunks of
+ * device virtual memory.
+ * There is one range for host allocations and one for DRAM allocations.
+ *
+ * On initialization each range contains one chunk of all of its available
+ * virtual range which is a half of the total device virtual range.
+ *
+ * On each mapping of physical pages, a suitable virtual range chunk (with a
+ * minimum size) is selected from the list. If the chunk size equals the
+ * requested size, the chunk is returned. Otherwise, the chunk is split into
+ * two chunks - one to return as result and a remainder to stay in the list.
+ *
+ * On each Unmapping of a virtual address, the relevant virtual chunk is
+ * returned to the list. The chunk is added to the list and if its edges match
+ * the edges of the adjacent chunks (means a contiguous chunk can be created),
+ * the chunks are merged.
+ *
+ * On finish, the list is checked to have only one chunk of all the relevant
+ * virtual range (which is a half of the device total virtual range).
+ * If not (means not all mappings were unmapped), a warning is printed.
+ */
+
+/*
+ * alloc_device_memory - allocate device memory
+ *
+ * @ctx                 : current context
+ * @args                : host parameters containing the requested size
+ * @ret_handle          : result handle
+ *
+ * This function does the following:
+ * - Allocate the requested size rounded up to 2MB pages
+ * - Return unique handle
+ */
+static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args,
+				u32 *ret_handle)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct hl_vm *vm = &hdev->vm;
+	struct hl_vm_phys_pg_pack *phys_pg_pack;
+	u64 paddr = 0, total_size, num_pgs, i;
+	u32 num_curr_pgs, page_size, page_shift;
+	int handle, rc;
+	bool contiguous;
+
+	num_curr_pgs = 0;
+	page_size = hdev->asic_prop.dram_page_size;
+	page_shift = __ffs(page_size);
+	num_pgs = (args->alloc.mem_size + (page_size - 1)) >> page_shift;
+	total_size = num_pgs << page_shift;
+
+	contiguous = args->flags & HL_MEM_CONTIGUOUS;
+
+	if (contiguous) {
+		paddr = (u64) gen_pool_alloc(vm->dram_pg_pool, total_size);
+		if (!paddr) {
+			dev_err(hdev->dev,
+				"failed to allocate %llu huge contiguous pages\n",
+				num_pgs);
+			return -ENOMEM;
+		}
+	}
+
+	phys_pg_pack = kzalloc(sizeof(*phys_pg_pack), GFP_KERNEL);
+	if (!phys_pg_pack) {
+		rc = -ENOMEM;
+		goto pages_pack_err;
+	}
+
+	phys_pg_pack->vm_type = VM_TYPE_PHYS_PACK;
+	phys_pg_pack->asid = ctx->asid;
+	phys_pg_pack->npages = num_pgs;
+	phys_pg_pack->page_size = page_size;
+	phys_pg_pack->total_size = total_size;
+	phys_pg_pack->flags = args->flags;
+	phys_pg_pack->contiguous = contiguous;
+
+	phys_pg_pack->pages = kvmalloc_array(num_pgs, sizeof(u64), GFP_KERNEL);
+	if (!phys_pg_pack->pages) {
+		rc = -ENOMEM;
+		goto pages_arr_err;
+	}
+
+	if (phys_pg_pack->contiguous) {
+		for (i = 0 ; i < num_pgs ; i++)
+			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 (!phys_pg_pack->pages[i]) {
+				dev_err(hdev->dev,
+					"Failed to allocate device memory (out of memory)\n");
+				rc = -ENOMEM;
+				goto page_err;
+			}
+
+			num_curr_pgs++;
+		}
+	}
+
+	spin_lock(&vm->idr_lock);
+	handle = idr_alloc(&vm->phys_pg_pack_handles, phys_pg_pack, 1, 0,
+				GFP_ATOMIC);
+	spin_unlock(&vm->idr_lock);
+
+	if (handle < 0) {
+		dev_err(hdev->dev, "Failed to get handle for page\n");
+		rc = -EFAULT;
+		goto idr_err;
+	}
+
+	for (i = 0 ; i < num_pgs ; i++)
+		kref_get(&vm->dram_pg_pool_refcount);
+
+	phys_pg_pack->handle = handle;
+
+	atomic64_add(phys_pg_pack->total_size, &ctx->dram_phys_mem);
+	atomic64_add(phys_pg_pack->total_size, &hdev->dram_used_mem);
+
+	*ret_handle = handle;
+
+	return 0;
+
+idr_err:
+page_err:
+	if (!phys_pg_pack->contiguous)
+		for (i = 0 ; i < num_curr_pgs ; i++)
+			gen_pool_free(vm->dram_pg_pool, phys_pg_pack->pages[i],
+					page_size);
+
+	kvfree(phys_pg_pack->pages);
+pages_arr_err:
+	kfree(phys_pg_pack);
+pages_pack_err:
+	if (contiguous)
+		gen_pool_free(vm->dram_pg_pool, paddr, total_size);
+
+	return rc;
+}
+
+/*
+ * dma_map_host_va - DMA mapping of the given host virtual address.
+ * @hdev: habanalabs device structure
+ * @addr: the host virtual address of the memory area
+ * @size: the size of the memory area
+ * @p_userptr: pointer to result userptr structure
+ *
+ * This function does the following:
+ * - Allocate userptr structure
+ * - Pin the given host memory using the userptr structure
+ * - Perform DMA mapping to have the DMA addresses of the pages
+ */
+static int dma_map_host_va(struct hl_device *hdev, u64 addr, u64 size,
+				struct hl_userptr **p_userptr)
+{
+	struct hl_userptr *userptr;
+	int rc;
+
+	userptr = kzalloc(sizeof(*userptr), GFP_KERNEL);
+	if (!userptr) {
+		rc = -ENOMEM;
+		goto userptr_err;
+	}
+
+	rc = hl_pin_host_memory(hdev, addr, size, userptr);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to pin host memory\n");
+		goto pin_err;
+	}
+
+	rc = hdev->asic_funcs->asic_dma_map_sg(hdev, userptr->sgt->sgl,
+					userptr->sgt->nents, DMA_BIDIRECTIONAL);
+	if (rc) {
+		dev_err(hdev->dev, "failed to map sgt with DMA region\n");
+		goto dma_map_err;
+	}
+
+	userptr->dma_mapped = true;
+	userptr->dir = DMA_BIDIRECTIONAL;
+	userptr->vm_type = VM_TYPE_USERPTR;
+
+	*p_userptr = userptr;
+
+	return 0;
+
+dma_map_err:
+	hl_unpin_host_memory(hdev, userptr);
+pin_err:
+	kfree(userptr);
+userptr_err:
+
+	return rc;
+}
+
+/*
+ * dma_unmap_host_va - DMA unmapping of the given host virtual address.
+ * @hdev: habanalabs device structure
+ * @userptr: userptr to free
+ *
+ * This function does the following:
+ * - Unpins the physical pages
+ * - Frees the userptr structure
+ */
+static void dma_unmap_host_va(struct hl_device *hdev,
+				struct hl_userptr *userptr)
+{
+	hl_unpin_host_memory(hdev, userptr);
+	kfree(userptr);
+}
+
+/*
+ * dram_pg_pool_do_release - free DRAM pages pool
+ *
+ * @ref                 : pointer to reference object
+ *
+ * This function does the following:
+ * - Frees the idr structure of physical pages handles
+ * - Frees the generic pool of DRAM physical pages
+ */
+static void dram_pg_pool_do_release(struct kref *ref)
+{
+	struct hl_vm *vm = container_of(ref, struct hl_vm,
+			dram_pg_pool_refcount);
+
+	/*
+	 * free the idr here as only here we know for sure that there are no
+	 * allocated physical pages and hence there are no handles in use
+	 */
+	idr_destroy(&vm->phys_pg_pack_handles);
+	gen_pool_destroy(vm->dram_pg_pool);
+}
+
+/*
+ * free_phys_pg_pack - free physical page pack
+ * @hdev: habanalabs device structure
+ * @phys_pg_pack: physical page pack to free
+ *
+ * This function does the following:
+ * - For DRAM memory only, iterate over the pack and free each physical block
+ *   structure by returning it to the general pool
+ * - Free the hl_vm_phys_pg_pack structure
+ */
+static void free_phys_pg_pack(struct hl_device *hdev,
+				struct hl_vm_phys_pg_pack *phys_pg_pack)
+{
+	struct hl_vm *vm = &hdev->vm;
+	u64 i;
+
+	if (!phys_pg_pack->created_from_userptr) {
+		if (phys_pg_pack->contiguous) {
+			gen_pool_free(vm->dram_pg_pool, phys_pg_pack->pages[0],
+					phys_pg_pack->total_size);
+
+			for (i = 0; i < phys_pg_pack->npages ; i++)
+				kref_put(&vm->dram_pg_pool_refcount,
+					dram_pg_pool_do_release);
+		} else {
+			for (i = 0 ; i < phys_pg_pack->npages ; i++) {
+				gen_pool_free(vm->dram_pg_pool,
+						phys_pg_pack->pages[i],
+						phys_pg_pack->page_size);
+				kref_put(&vm->dram_pg_pool_refcount,
+					dram_pg_pool_do_release);
+			}
+		}
+	}
+
+	kvfree(phys_pg_pack->pages);
+	kfree(phys_pg_pack);
+}
+
+/*
+ * free_device_memory - free device memory
+ *
+ * @ctx                  : current context
+ * @handle              : handle of the memory chunk to free
+ *
+ * This function does the following:
+ * - Free the device memory related to the given handle
+ */
+static int free_device_memory(struct hl_ctx *ctx, u32 handle)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct hl_vm *vm = &hdev->vm;
+	struct hl_vm_phys_pg_pack *phys_pg_pack;
+
+	spin_lock(&vm->idr_lock);
+	phys_pg_pack = idr_find(&vm->phys_pg_pack_handles, handle);
+	if (phys_pg_pack) {
+		if (atomic_read(&phys_pg_pack->mapping_cnt) > 0) {
+			dev_err(hdev->dev, "handle %u is mapped, cannot free\n",
+				handle);
+			spin_unlock(&vm->idr_lock);
+			return -EINVAL;
+		}
+
+		/*
+		 * must remove from idr before the freeing of the physical
+		 * pages as the refcount of the pool is also the trigger of the
+		 * idr destroy
+		 */
+		idr_remove(&vm->phys_pg_pack_handles, handle);
+		spin_unlock(&vm->idr_lock);
+
+		atomic64_sub(phys_pg_pack->total_size, &ctx->dram_phys_mem);
+		atomic64_sub(phys_pg_pack->total_size, &hdev->dram_used_mem);
+
+		free_phys_pg_pack(hdev, phys_pg_pack);
+	} else {
+		spin_unlock(&vm->idr_lock);
+		dev_err(hdev->dev,
+			"free device memory failed, no match for handle %u\n",
+			handle);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * clear_va_list_locked - free virtual addresses list
+ *
+ * @hdev                : habanalabs device structure
+ * @va_list             : list of virtual addresses to free
+ *
+ * This function does the following:
+ * - Iterate over the list and free each virtual addresses block
+ *
+ * This function should be called only when va_list lock is taken
+ */
+static void clear_va_list_locked(struct hl_device *hdev,
+		struct list_head *va_list)
+{
+	struct hl_vm_va_block *va_block, *tmp;
+
+	list_for_each_entry_safe(va_block, tmp, va_list, node) {
+		list_del(&va_block->node);
+		kfree(va_block);
+	}
+}
+
+/*
+ * print_va_list_locked    - print virtual addresses list
+ *
+ * @hdev                : habanalabs device structure
+ * @va_list             : list of virtual addresses to print
+ *
+ * This function does the following:
+ * - Iterate over the list and print each virtual addresses block
+ *
+ * This function should be called only when va_list lock is taken
+ */
+static void print_va_list_locked(struct hl_device *hdev,
+		struct list_head *va_list)
+{
+#if HL_MMU_DEBUG
+	struct hl_vm_va_block *va_block;
+
+	dev_dbg(hdev->dev, "print va list:\n");
+
+	list_for_each_entry(va_block, va_list, node)
+		dev_dbg(hdev->dev,
+			"va block, start: 0x%llx, end: 0x%llx, size: %llu\n",
+			va_block->start, va_block->end, va_block->size);
+#endif
+}
+
+/*
+ * merge_va_blocks_locked - merge a virtual block if possible
+ *
+ * @hdev                : pointer to the habanalabs device structure
+ * @va_list             : pointer to the virtual addresses block list
+ * @va_block            : virtual block to merge with adjacent blocks
+ *
+ * This function does the following:
+ * - Merge the given blocks with the adjacent blocks if their virtual ranges
+ *   create a contiguous virtual range
+ *
+ * This Function should be called only when va_list lock is taken
+ */
+static void merge_va_blocks_locked(struct hl_device *hdev,
+		struct list_head *va_list, struct hl_vm_va_block *va_block)
+{
+	struct hl_vm_va_block *prev, *next;
+
+	prev = list_prev_entry(va_block, node);
+	if (&prev->node != va_list && prev->end + 1 == va_block->start) {
+		prev->end = va_block->end;
+		prev->size = prev->end - prev->start;
+		list_del(&va_block->node);
+		kfree(va_block);
+		va_block = prev;
+	}
+
+	next = list_next_entry(va_block, node);
+	if (&next->node != va_list && va_block->end + 1 == next->start) {
+		next->start = va_block->start;
+		next->size = next->end - next->start;
+		list_del(&va_block->node);
+		kfree(va_block);
+	}
+}
+
+/*
+ * add_va_block_locked - add a virtual block to the virtual addresses list
+ *
+ * @hdev                : pointer to the habanalabs device structure
+ * @va_list             : pointer to the virtual addresses block list
+ * @start               : start virtual address
+ * @end                 : end virtual address
+ *
+ * This function does the following:
+ * - Add the given block to the virtual blocks list and merge with other
+ * blocks if a contiguous virtual block can be created
+ *
+ * This Function should be called only when va_list lock is taken
+ */
+static int add_va_block_locked(struct hl_device *hdev,
+		struct list_head *va_list, u64 start, u64 end)
+{
+	struct hl_vm_va_block *va_block, *res = NULL;
+	u64 size = end - start;
+
+	print_va_list_locked(hdev, va_list);
+
+	list_for_each_entry(va_block, va_list, node) {
+		/* TODO: remove upon matureness */
+		if (hl_mem_area_crosses_range(start, size, va_block->start,
+				va_block->end)) {
+			dev_err(hdev->dev,
+				"block crossing ranges at start 0x%llx, end 0x%llx\n",
+				va_block->start, va_block->end);
+			return -EINVAL;
+		}
+
+		if (va_block->end < start)
+			res = va_block;
+	}
+
+	va_block = kmalloc(sizeof(*va_block), GFP_KERNEL);
+	if (!va_block)
+		return -ENOMEM;
+
+	va_block->start = start;
+	va_block->end = end;
+	va_block->size = size;
+
+	if (!res)
+		list_add(&va_block->node, va_list);
+	else
+		list_add(&va_block->node, &res->node);
+
+	merge_va_blocks_locked(hdev, va_list, va_block);
+
+	print_va_list_locked(hdev, va_list);
+
+	return 0;
+}
+
+/*
+ * add_va_block - wrapper for add_va_block_locked
+ *
+ * @hdev                : pointer to the habanalabs device structure
+ * @va_list             : pointer to the virtual addresses block list
+ * @start               : start virtual address
+ * @end                 : end virtual address
+ *
+ * This function does the following:
+ * - Takes the list lock and calls add_va_block_locked
+ */
+static inline int add_va_block(struct hl_device *hdev,
+		struct hl_va_range *va_range, u64 start, u64 end)
+{
+	int rc;
+
+	mutex_lock(&va_range->lock);
+	rc = add_va_block_locked(hdev, &va_range->list, start, end);
+	mutex_unlock(&va_range->lock);
+
+	return rc;
+}
+
+/*
+ * get_va_block - get a virtual block with the requested size
+ *
+ * @hdev            : pointer to the habanalabs device structure
+ * @va_range        : pointer to the virtual addresses range
+ * @size            : requested block size
+ * @hint_addr       : hint for request address by the user
+ * @is_userptr      : is host or DRAM memory
+ *
+ * This function does the following:
+ * - Iterate on the virtual block list to find a suitable virtual block for the
+ *   requested size
+ * - Reserve the requested block and update the list
+ * - Return the start address of the virtual block
+ */
+static u64 get_va_block(struct hl_device *hdev,
+			struct hl_va_range *va_range, u64 size, u64 hint_addr,
+			bool is_userptr)
+{
+	struct hl_vm_va_block *va_block, *new_va_block = NULL;
+	u64 valid_start, valid_size, prev_start, prev_end, page_mask,
+		res_valid_start = 0, res_valid_size = 0;
+	u32 page_size;
+	bool add_prev = false;
+
+	if (is_userptr)
+		/*
+		 * We cannot know if the user allocated memory with huge pages
+		 * or not, hence we continue with the biggest possible
+		 * granularity.
+		 */
+		page_size = hdev->asic_prop.pmmu_huge.page_size;
+	else
+		page_size = hdev->asic_prop.dmmu.page_size;
+
+	page_mask = ~((u64)page_size - 1);
+
+	mutex_lock(&va_range->lock);
+
+	print_va_list_locked(hdev, &va_range->list);
+
+	list_for_each_entry(va_block, &va_range->list, node) {
+		/* calc the first possible aligned addr */
+		valid_start = va_block->start;
+
+		if (valid_start & (page_size - 1)) {
+			valid_start &= page_mask;
+			valid_start += page_size;
+			if (valid_start > va_block->end)
+				continue;
+		}
+
+		valid_size = va_block->end - valid_start;
+
+		if (valid_size >= size &&
+			(!new_va_block || valid_size < res_valid_size)) {
+			new_va_block = va_block;
+			res_valid_start = valid_start;
+			res_valid_size = valid_size;
+		}
+
+		if (hint_addr && hint_addr >= valid_start &&
+				((hint_addr + size) <= va_block->end)) {
+			new_va_block = va_block;
+			res_valid_start = hint_addr;
+			res_valid_size = valid_size;
+			break;
+		}
+	}
+
+	if (!new_va_block) {
+		dev_err(hdev->dev, "no available va block for size %llu\n",
+				size);
+		goto out;
+	}
+
+	if (res_valid_start > new_va_block->start) {
+		prev_start = new_va_block->start;
+		prev_end = res_valid_start - 1;
+
+		new_va_block->start = res_valid_start;
+		new_va_block->size = res_valid_size;
+
+		add_prev = true;
+	}
+
+	if (new_va_block->size > size) {
+		new_va_block->start += size;
+		new_va_block->size = new_va_block->end - new_va_block->start;
+	} else {
+		list_del(&new_va_block->node);
+		kfree(new_va_block);
+	}
+
+	if (add_prev)
+		add_va_block_locked(hdev, &va_range->list, prev_start,
+				prev_end);
+
+	print_va_list_locked(hdev, &va_range->list);
+out:
+	mutex_unlock(&va_range->lock);
+
+	return res_valid_start;
+}
+
+/*
+ * get_sg_info - get number of pages and the DMA address from SG list
+ *
+ * @sg                 : the SG list
+ * @dma_addr           : pointer to DMA address to return
+ *
+ * Calculate the number of consecutive pages described by the SG list. Take the
+ * offset of the address in the first page, add to it the length and round it up
+ * to the number of needed pages.
+ */
+static u32 get_sg_info(struct scatterlist *sg, dma_addr_t *dma_addr)
+{
+	*dma_addr = sg_dma_address(sg);
+
+	return ((((*dma_addr) & (PAGE_SIZE - 1)) + sg_dma_len(sg)) +
+			(PAGE_SIZE - 1)) >> PAGE_SHIFT;
+}
+
+/*
+ * init_phys_pg_pack_from_userptr - initialize physical page pack from host
+ *                                  memory
+ * @ctx: current context
+ * @userptr: userptr to initialize from
+ * @pphys_pg_pack: result pointer
+ *
+ * This function does the following:
+ * - Pin the physical pages related to the given virtual block
+ * - Create a physical page pack from the physical pages related to the given
+ *   virtual block
+ */
+static int init_phys_pg_pack_from_userptr(struct hl_ctx *ctx,
+				struct hl_userptr *userptr,
+				struct hl_vm_phys_pg_pack **pphys_pg_pack)
+{
+	struct hl_vm_phys_pg_pack *phys_pg_pack;
+	struct scatterlist *sg;
+	dma_addr_t dma_addr;
+	u64 page_mask, total_npages;
+	u32 npages, page_size = PAGE_SIZE,
+		huge_page_size = ctx->hdev->asic_prop.pmmu_huge.page_size;
+	bool first = true, is_huge_page_opt = true;
+	int rc, i, j;
+	u32 pgs_in_huge_page = huge_page_size >> __ffs(page_size);
+
+	phys_pg_pack = kzalloc(sizeof(*phys_pg_pack), GFP_KERNEL);
+	if (!phys_pg_pack)
+		return -ENOMEM;
+
+	phys_pg_pack->vm_type = userptr->vm_type;
+	phys_pg_pack->created_from_userptr = true;
+	phys_pg_pack->asid = ctx->asid;
+	atomic_set(&phys_pg_pack->mapping_cnt, 1);
+
+	/* Only if all dma_addrs are aligned to 2MB and their
+	 * sizes is at least 2MB, we can use huge page mapping.
+	 * We limit the 2MB optimization to this condition,
+	 * since later on we acquire the related VA range as one
+	 * consecutive block.
+	 */
+	total_npages = 0;
+	for_each_sg(userptr->sgt->sgl, sg, userptr->sgt->nents, i) {
+		npages = get_sg_info(sg, &dma_addr);
+
+		total_npages += npages;
+
+		if ((npages % pgs_in_huge_page) ||
+					(dma_addr & (huge_page_size - 1)))
+			is_huge_page_opt = false;
+	}
+
+	if (is_huge_page_opt) {
+		page_size = huge_page_size;
+		do_div(total_npages, pgs_in_huge_page);
+	}
+
+	page_mask = ~(((u64) page_size) - 1);
+
+	phys_pg_pack->pages = kvmalloc_array(total_npages, sizeof(u64),
+						GFP_KERNEL);
+	if (!phys_pg_pack->pages) {
+		rc = -ENOMEM;
+		goto page_pack_arr_mem_err;
+	}
+
+	phys_pg_pack->npages = total_npages;
+	phys_pg_pack->page_size = page_size;
+	phys_pg_pack->total_size = total_npages * page_size;
+
+	j = 0;
+	for_each_sg(userptr->sgt->sgl, sg, userptr->sgt->nents, i) {
+		npages = get_sg_info(sg, &dma_addr);
+
+		/* align down to physical page size and save the offset */
+		if (first) {
+			first = false;
+			phys_pg_pack->offset = dma_addr & (page_size - 1);
+			dma_addr &= page_mask;
+		}
+
+		while (npages) {
+			phys_pg_pack->pages[j++] = dma_addr;
+			dma_addr += page_size;
+
+			if (is_huge_page_opt)
+				npages -= pgs_in_huge_page;
+			else
+				npages--;
+		}
+	}
+
+	*pphys_pg_pack = phys_pg_pack;
+
+	return 0;
+
+page_pack_arr_mem_err:
+	kfree(phys_pg_pack);
+
+	return rc;
+}
+
+/*
+ * map_phys_pg_pack - maps the physical page pack.
+ * @ctx: current context
+ * @vaddr: start address of the virtual area to map from
+ * @phys_pg_pack: the pack of physical pages to map to
+ *
+ * This function does the following:
+ * - Maps each chunk of virtual memory to matching physical chunk
+ * - Stores number of successful mappings in the given argument
+ * - Returns 0 on success, error code otherwise
+ */
+static int map_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr,
+				struct hl_vm_phys_pg_pack *phys_pg_pack)
+{
+	struct hl_device *hdev = ctx->hdev;
+	u64 next_vaddr = vaddr, paddr, mapped_pg_cnt = 0, i;
+	u32 page_size = phys_pg_pack->page_size;
+	int rc = 0;
+
+	for (i = 0 ; i < phys_pg_pack->npages ; i++) {
+		paddr = phys_pg_pack->pages[i];
+
+		rc = hl_mmu_map(ctx, next_vaddr, paddr, page_size,
+				(i + 1) == phys_pg_pack->npages);
+		if (rc) {
+			dev_err(hdev->dev,
+				"map failed for handle %u, npages: %llu, mapped: %llu",
+				phys_pg_pack->handle, phys_pg_pack->npages,
+				mapped_pg_cnt);
+			goto err;
+		}
+
+		mapped_pg_cnt++;
+		next_vaddr += page_size;
+	}
+
+	return 0;
+
+err:
+	next_vaddr = vaddr;
+	for (i = 0 ; i < mapped_pg_cnt ; i++) {
+		if (hl_mmu_unmap(ctx, next_vaddr, page_size,
+					(i + 1) == mapped_pg_cnt))
+			dev_warn_ratelimited(hdev->dev,
+				"failed to unmap handle %u, va: 0x%llx, pa: 0x%llx, page size: %u\n",
+					phys_pg_pack->handle, next_vaddr,
+					phys_pg_pack->pages[i], page_size);
+
+		next_vaddr += page_size;
+	}
+
+	return rc;
+}
+
+/*
+ * unmap_phys_pg_pack - unmaps the physical page pack
+ * @ctx: current context
+ * @vaddr: start address of the virtual area to unmap
+ * @phys_pg_pack: the pack of physical pages to unmap
+ */
+static void unmap_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr,
+				struct hl_vm_phys_pg_pack *phys_pg_pack)
+{
+	struct hl_device *hdev = ctx->hdev;
+	u64 next_vaddr, i;
+	u32 page_size;
+
+	page_size = phys_pg_pack->page_size;
+	next_vaddr = vaddr;
+
+	for (i = 0 ; i < phys_pg_pack->npages ; i++, next_vaddr += page_size) {
+		if (hl_mmu_unmap(ctx, next_vaddr, page_size,
+				       (i + 1) == phys_pg_pack->npages))
+			dev_warn_ratelimited(hdev->dev,
+			"unmap failed for vaddr: 0x%llx\n", next_vaddr);
+
+		/*
+		 * unmapping on Palladium can be really long, so avoid a CPU
+		 * soft lockup bug by sleeping a little between unmapping pages
+		 */
+		if (hdev->pldm)
+			usleep_range(500, 1000);
+	}
+}
+
+static int get_paddr_from_handle(struct hl_ctx *ctx, struct hl_mem_in *args,
+				u64 *paddr)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct hl_vm *vm = &hdev->vm;
+	struct hl_vm_phys_pg_pack *phys_pg_pack;
+	u32 handle;
+
+	handle = lower_32_bits(args->map_device.handle);
+	spin_lock(&vm->idr_lock);
+	phys_pg_pack = idr_find(&vm->phys_pg_pack_handles, handle);
+	if (!phys_pg_pack) {
+		spin_unlock(&vm->idr_lock);
+		dev_err(hdev->dev, "no match for handle %u\n", handle);
+		return -EINVAL;
+	}
+
+	*paddr = phys_pg_pack->pages[0];
+
+	spin_unlock(&vm->idr_lock);
+
+	return 0;
+}
+
+/*
+ * map_device_va - map the given memory
+ *
+ * @ctx	         : current context
+ * @args         : host parameters with handle/host virtual address
+ * @device_addr	 : pointer to result device virtual address
+ *
+ * This function does the following:
+ * - If given a physical device memory handle, map to a device virtual block
+ *   and return the start address of this block
+ * - If given a host virtual address and size, find the related physical pages,
+ *   map a device virtual block to this pages and return the start address of
+ *   this block
+ */
+static int map_device_va(struct hl_ctx *ctx, struct hl_mem_in *args,
+		u64 *device_addr)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct hl_vm *vm = &hdev->vm;
+	struct hl_vm_phys_pg_pack *phys_pg_pack;
+	struct hl_userptr *userptr = NULL;
+	struct hl_vm_hash_node *hnode;
+	struct hl_va_range *va_range;
+	enum vm_type_t *vm_type;
+	u64 ret_vaddr, hint_addr;
+	u32 handle = 0;
+	int rc;
+	bool is_userptr = args->flags & HL_MEM_USERPTR;
+
+	/* Assume failure */
+	*device_addr = 0;
+
+	if (is_userptr) {
+		u64 addr = args->map_host.host_virt_addr,
+			size = args->map_host.mem_size;
+
+		rc = dma_map_host_va(hdev, addr, size, &userptr);
+		if (rc) {
+			dev_err(hdev->dev, "failed to get userptr from va\n");
+			return rc;
+		}
+
+		rc = init_phys_pg_pack_from_userptr(ctx, userptr,
+				&phys_pg_pack);
+		if (rc) {
+			dev_err(hdev->dev,
+				"unable to init page pack for vaddr 0x%llx\n",
+				addr);
+			goto init_page_pack_err;
+		}
+
+		vm_type = (enum vm_type_t *) userptr;
+		hint_addr = args->map_host.hint_addr;
+		handle = phys_pg_pack->handle;
+	} else {
+		handle = lower_32_bits(args->map_device.handle);
+
+		spin_lock(&vm->idr_lock);
+		phys_pg_pack = idr_find(&vm->phys_pg_pack_handles, handle);
+		if (!phys_pg_pack) {
+			spin_unlock(&vm->idr_lock);
+			dev_err(hdev->dev,
+				"no match for handle %u\n", handle);
+			return -EINVAL;
+		}
+
+		/* increment now to avoid freeing device memory while mapping */
+		atomic_inc(&phys_pg_pack->mapping_cnt);
+
+		spin_unlock(&vm->idr_lock);
+
+		vm_type = (enum vm_type_t *) phys_pg_pack;
+
+		hint_addr = args->map_device.hint_addr;
+	}
+
+	/*
+	 * relevant for mapping device physical memory only, as host memory is
+	 * implicitly shared
+	 */
+	if (!is_userptr && !(phys_pg_pack->flags & HL_MEM_SHARED) &&
+			phys_pg_pack->asid != ctx->asid) {
+		dev_err(hdev->dev,
+			"Failed to map memory, handle %u is not shared\n",
+			handle);
+		rc = -EPERM;
+		goto shared_err;
+	}
+
+	hnode = kzalloc(sizeof(*hnode), GFP_KERNEL);
+	if (!hnode) {
+		rc = -ENOMEM;
+		goto hnode_err;
+	}
+
+	if (is_userptr)
+		if (phys_pg_pack->page_size == hdev->asic_prop.pmmu.page_size)
+			va_range = ctx->host_va_range;
+		else
+			va_range = ctx->host_huge_va_range;
+	else
+		va_range = ctx->dram_va_range;
+
+	ret_vaddr = get_va_block(hdev, va_range, phys_pg_pack->total_size,
+					hint_addr, is_userptr);
+	if (!ret_vaddr) {
+		dev_err(hdev->dev, "no available va block for handle %u\n",
+				handle);
+		rc = -ENOMEM;
+		goto va_block_err;
+	}
+
+	mutex_lock(&ctx->mmu_lock);
+
+	rc = map_phys_pg_pack(ctx, ret_vaddr, phys_pg_pack);
+	if (rc) {
+		mutex_unlock(&ctx->mmu_lock);
+		dev_err(hdev->dev, "mapping page pack failed for handle %u\n",
+				handle);
+		goto map_err;
+	}
+
+	rc = hdev->asic_funcs->mmu_invalidate_cache(hdev, false, *vm_type);
+
+	mutex_unlock(&ctx->mmu_lock);
+
+	if (rc) {
+		dev_err(hdev->dev,
+			"mapping handle %u failed due to MMU cache invalidation\n",
+			handle);
+		goto map_err;
+	}
+
+	ret_vaddr += phys_pg_pack->offset;
+
+	hnode->ptr = vm_type;
+	hnode->vaddr = ret_vaddr;
+
+	mutex_lock(&ctx->mem_hash_lock);
+	hash_add(ctx->mem_hash, &hnode->node, ret_vaddr);
+	mutex_unlock(&ctx->mem_hash_lock);
+
+	*device_addr = ret_vaddr;
+
+	if (is_userptr)
+		free_phys_pg_pack(hdev, phys_pg_pack);
+
+	return 0;
+
+map_err:
+	if (add_va_block(hdev, va_range, ret_vaddr,
+				ret_vaddr + phys_pg_pack->total_size - 1))
+		dev_warn(hdev->dev,
+			"release va block failed for handle 0x%x, vaddr: 0x%llx\n",
+				handle, ret_vaddr);
+
+va_block_err:
+	kfree(hnode);
+hnode_err:
+shared_err:
+	atomic_dec(&phys_pg_pack->mapping_cnt);
+	if (is_userptr)
+		free_phys_pg_pack(hdev, phys_pg_pack);
+init_page_pack_err:
+	if (is_userptr)
+		dma_unmap_host_va(hdev, userptr);
+
+	return rc;
+}
+
+/*
+ * unmap_device_va      - unmap the given device virtual address
+ *
+ * @ctx                 : current context
+ * @vaddr               : device virtual address to unmap
+ * @ctx_free            : true if in context free flow, false otherwise.
+ *
+ * This function does the following:
+ * - Unmap the physical pages related to the given virtual address
+ * - return the device virtual block to the virtual block list
+ */
+static int unmap_device_va(struct hl_ctx *ctx, u64 vaddr, bool ctx_free)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct hl_vm_phys_pg_pack *phys_pg_pack = NULL;
+	struct hl_vm_hash_node *hnode = NULL;
+	struct hl_userptr *userptr = NULL;
+	struct hl_va_range *va_range;
+	enum vm_type_t *vm_type;
+	bool is_userptr;
+	int rc = 0;
+
+	/* protect from double entrance */
+	mutex_lock(&ctx->mem_hash_lock);
+	hash_for_each_possible(ctx->mem_hash, hnode, node, (unsigned long)vaddr)
+		if (vaddr == hnode->vaddr)
+			break;
+
+	if (!hnode) {
+		mutex_unlock(&ctx->mem_hash_lock);
+		dev_err(hdev->dev,
+			"unmap failed, no mem hnode for vaddr 0x%llx\n",
+			vaddr);
+		return -EINVAL;
+	}
+
+	hash_del(&hnode->node);
+	mutex_unlock(&ctx->mem_hash_lock);
+
+	vm_type = hnode->ptr;
+
+	if (*vm_type == VM_TYPE_USERPTR) {
+		is_userptr = true;
+		userptr = hnode->ptr;
+		rc = init_phys_pg_pack_from_userptr(ctx, userptr,
+							&phys_pg_pack);
+		if (rc) {
+			dev_err(hdev->dev,
+				"unable to init page pack for vaddr 0x%llx\n",
+				vaddr);
+			goto vm_type_err;
+		}
+
+		if (phys_pg_pack->page_size ==
+					hdev->asic_prop.pmmu.page_size)
+			va_range = ctx->host_va_range;
+		else
+			va_range = ctx->host_huge_va_range;
+	} else if (*vm_type == VM_TYPE_PHYS_PACK) {
+		is_userptr = false;
+		va_range = ctx->dram_va_range;
+		phys_pg_pack = hnode->ptr;
+	} else {
+		dev_warn(hdev->dev,
+			"unmap failed, unknown vm desc for vaddr 0x%llx\n",
+				vaddr);
+		rc = -EFAULT;
+		goto vm_type_err;
+	}
+
+	if (atomic_read(&phys_pg_pack->mapping_cnt) == 0) {
+		dev_err(hdev->dev, "vaddr 0x%llx is not mapped\n", vaddr);
+		rc = -EINVAL;
+		goto mapping_cnt_err;
+	}
+
+	vaddr &= ~(((u64) phys_pg_pack->page_size) - 1);
+
+	mutex_lock(&ctx->mmu_lock);
+
+	unmap_phys_pg_pack(ctx, vaddr, phys_pg_pack);
+
+	/*
+	 * During context free this function is called in a loop to clean all
+	 * the context mappings. Hence the cache invalidation can be called once
+	 * at the loop end rather than for each iteration
+	 */
+	if (!ctx_free)
+		rc = hdev->asic_funcs->mmu_invalidate_cache(hdev, true,
+								*vm_type);
+
+	mutex_unlock(&ctx->mmu_lock);
+
+	/*
+	 * If the context is closing we don't need to check for the MMU cache
+	 * invalidation return code and update the VA free list as in this flow
+	 * we invalidate the MMU cache outside of this unmap function and the VA
+	 * free list will be freed anyway.
+	 */
+	if (!ctx_free) {
+		int tmp_rc;
+
+		if (rc)
+			dev_err(hdev->dev,
+				"unmapping vaddr 0x%llx failed due to MMU cache invalidation\n",
+				vaddr);
+
+		tmp_rc = add_va_block(hdev, va_range, vaddr,
+					vaddr + phys_pg_pack->total_size - 1);
+		if (tmp_rc) {
+			dev_warn(hdev->dev,
+					"add va block failed for vaddr: 0x%llx\n",
+					vaddr);
+			if (!rc)
+				rc = tmp_rc;
+		}
+	}
+
+	atomic_dec(&phys_pg_pack->mapping_cnt);
+	kfree(hnode);
+
+	if (is_userptr) {
+		free_phys_pg_pack(hdev, phys_pg_pack);
+		dma_unmap_host_va(hdev, userptr);
+	}
+
+	return rc;
+
+mapping_cnt_err:
+	if (is_userptr)
+		free_phys_pg_pack(hdev, phys_pg_pack);
+vm_type_err:
+	mutex_lock(&ctx->mem_hash_lock);
+	hash_add(ctx->mem_hash, &hnode->node, vaddr);
+	mutex_unlock(&ctx->mem_hash_lock);
+
+	return rc;
+}
+
+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 device_addr = 0;
+	u32 handle = 0;
+	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");
+			rc = -EINVAL;
+			goto out;
+		}
+
+		/* Force contiguous as there are no real MMU
+		 * translations to overcome physical memory gaps
+		 */
+		args->in.flags |= HL_MEM_CONTIGUOUS;
+		rc = alloc_device_memory(ctx, &args->in, &handle);
+
+		memset(args, 0, sizeof(*args));
+		args->out.handle = (__u64) handle;
+		break;
+
+	case HL_MEM_OP_FREE:
+		rc = free_device_memory(ctx, args->in.free.handle);
+		break;
+
+	case HL_MEM_OP_MAP:
+		if (args->in.flags & HL_MEM_USERPTR) {
+			device_addr = args->in.map_host.host_virt_addr;
+			rc = 0;
+		} else {
+			rc = get_paddr_from_handle(ctx, &args->in,
+					&device_addr);
+		}
+
+		memset(args, 0, sizeof(*args));
+		args->out.device_virt_addr = device_addr;
+		break;
+
+	case HL_MEM_OP_UNMAP:
+		rc = 0;
+		break;
+
+	default:
+		dev_err(hdev->dev, "Unknown opcode for memory IOCTL\n");
+		rc = -ENOTTY;
+		break;
+	}
+
+out:
+	return rc;
+}
+
+int hl_mem_ioctl(struct hl_fpriv *hpriv, void *data)
+{
+	union hl_mem_args *args = data;
+	struct hl_device *hdev = hpriv->hdev;
+	struct hl_ctx *ctx = hpriv->ctx;
+	u64 device_addr = 0;
+	u32 handle = 0;
+	int rc;
+
+	if (hl_device_disabled_or_in_reset(hdev)) {
+		dev_warn_ratelimited(hdev->dev,
+			"Device is %s. Can't execute MEMORY IOCTL\n",
+			atomic_read(&hdev->in_reset) ? "in_reset" : "disabled");
+		return -EBUSY;
+	}
+
+	if (!hdev->mmu_enable)
+		return mem_ioctl_no_mmu(hpriv, args);
+
+	switch (args->in.op) {
+	case HL_MEM_OP_ALLOC:
+		if (!hdev->dram_supports_virtual_memory) {
+			dev_err(hdev->dev, "DRAM alloc is not supported\n");
+			rc = -EINVAL;
+			goto out;
+		}
+
+		if (args->in.alloc.mem_size == 0) {
+			dev_err(hdev->dev,
+				"alloc size must be larger than 0\n");
+			rc = -EINVAL;
+			goto out;
+		}
+		rc = alloc_device_memory(ctx, &args->in, &handle);
+
+		memset(args, 0, sizeof(*args));
+		args->out.handle = (__u64) handle;
+		break;
+
+	case HL_MEM_OP_FREE:
+		rc = free_device_memory(ctx, args->in.free.handle);
+		break;
+
+	case HL_MEM_OP_MAP:
+		rc = map_device_va(ctx, &args->in, &device_addr);
+
+		memset(args, 0, sizeof(*args));
+		args->out.device_virt_addr = device_addr;
+		break;
+
+	case HL_MEM_OP_UNMAP:
+		rc = unmap_device_va(ctx, args->in.unmap.device_virt_addr,
+					false);
+		break;
+
+	default:
+		dev_err(hdev->dev, "Unknown opcode for memory IOCTL\n");
+		rc = -ENOTTY;
+		break;
+	}
+
+out:
+	return rc;
+}
+
+static int get_user_memory(struct hl_device *hdev, u64 addr, u64 size,
+				u32 npages, u64 start, u32 offset,
+				struct hl_userptr *userptr)
+{
+	int rc;
+
+	if (!access_ok((void __user *) (uintptr_t) addr, size)) {
+		dev_err(hdev->dev, "user pointer is invalid - 0x%llx\n", addr);
+		return -EFAULT;
+	}
+
+	userptr->vec = frame_vector_create(npages);
+	if (!userptr->vec) {
+		dev_err(hdev->dev, "Failed to create frame vector\n");
+		return -ENOMEM;
+	}
+
+	rc = get_vaddr_frames(start, npages, FOLL_FORCE | FOLL_WRITE,
+				userptr->vec);
+
+	if (rc != npages) {
+		dev_err(hdev->dev,
+			"Failed to map host memory, user ptr probably wrong\n");
+		if (rc < 0)
+			goto destroy_framevec;
+		rc = -EFAULT;
+		goto put_framevec;
+	}
+
+	if (frame_vector_to_pages(userptr->vec) < 0) {
+		dev_err(hdev->dev,
+			"Failed to translate frame vector to pages\n");
+		rc = -EFAULT;
+		goto put_framevec;
+	}
+
+	rc = sg_alloc_table_from_pages(userptr->sgt,
+					frame_vector_pages(userptr->vec),
+					npages, offset, size, GFP_ATOMIC);
+	if (rc < 0) {
+		dev_err(hdev->dev, "failed to create SG table from pages\n");
+		goto put_framevec;
+	}
+
+	return 0;
+
+put_framevec:
+	put_vaddr_frames(userptr->vec);
+destroy_framevec:
+	frame_vector_destroy(userptr->vec);
+	return rc;
+}
+
+/*
+ * hl_pin_host_memory - pins a chunk of host memory.
+ * @hdev: pointer to the habanalabs device structure
+ * @addr: the host virtual address of the memory area
+ * @size: the size of the memory area
+ * @userptr: pointer to hl_userptr structure
+ *
+ * This function does the following:
+ * - Pins the physical pages
+ * - Create an SG list from those pages
+ */
+int hl_pin_host_memory(struct hl_device *hdev, u64 addr, u64 size,
+					struct hl_userptr *userptr)
+{
+	u64 start, end;
+	u32 npages, offset;
+	int rc;
+
+	if (!size) {
+		dev_err(hdev->dev, "size to pin is invalid - %llu\n", size);
+		return -EINVAL;
+	}
+
+	/*
+	 * If the combination of the address and size requested for this memory
+	 * region causes an integer overflow, return error.
+	 */
+	if (((addr + size) < addr) ||
+			PAGE_ALIGN(addr + size) < (addr + size)) {
+		dev_err(hdev->dev,
+			"user pointer 0x%llx + %llu causes integer overflow\n",
+			addr, size);
+		return -EINVAL;
+	}
+
+	/*
+	 * This function can be called also from data path, hence use atomic
+	 * always as it is not a big allocation.
+	 */
+	userptr->sgt = kzalloc(sizeof(*userptr->sgt), GFP_ATOMIC);
+	if (!userptr->sgt)
+		return -ENOMEM;
+
+	start = addr & PAGE_MASK;
+	offset = addr & ~PAGE_MASK;
+	end = PAGE_ALIGN(addr + size);
+	npages = (end - start) >> PAGE_SHIFT;
+
+	userptr->size = size;
+	userptr->addr = addr;
+	userptr->dma_mapped = false;
+	INIT_LIST_HEAD(&userptr->job_node);
+
+	rc = get_user_memory(hdev, addr, size, npages, start, offset,
+				userptr);
+	if (rc) {
+		dev_err(hdev->dev,
+			"failed to get user memory for address 0x%llx\n",
+			addr);
+		goto free_sgt;
+	}
+
+	hl_debugfs_add_userptr(hdev, userptr);
+
+	return 0;
+
+free_sgt:
+	kfree(userptr->sgt);
+	return rc;
+}
+
+/*
+ * hl_unpin_host_memory - unpins a chunk of host memory.
+ * @hdev: pointer to the habanalabs device structure
+ * @userptr: pointer to hl_userptr structure
+ *
+ * This function does the following:
+ * - Unpins the physical pages related to the host memory
+ * - Free the SG list
+ */
+void hl_unpin_host_memory(struct hl_device *hdev, struct hl_userptr *userptr)
+{
+	struct page **pages;
+
+	hl_debugfs_remove_userptr(hdev, userptr);
+
+	if (userptr->dma_mapped)
+		hdev->asic_funcs->hl_dma_unmap_sg(hdev, userptr->sgt->sgl,
+							userptr->sgt->nents,
+							userptr->dir);
+
+	pages = frame_vector_pages(userptr->vec);
+	if (!IS_ERR(pages)) {
+		int i;
+
+		for (i = 0; i < frame_vector_count(userptr->vec); i++)
+			set_page_dirty_lock(pages[i]);
+	}
+	put_vaddr_frames(userptr->vec);
+	frame_vector_destroy(userptr->vec);
+
+	list_del(&userptr->job_node);
+
+	sg_free_table(userptr->sgt);
+	kfree(userptr->sgt);
+}
+
+/*
+ * hl_userptr_delete_list - clear userptr list
+ *
+ * @hdev                : pointer to the habanalabs device structure
+ * @userptr_list        : pointer to the list to clear
+ *
+ * This function does the following:
+ * - Iterates over the list and unpins the host memory and frees the userptr
+ *   structure.
+ */
+void hl_userptr_delete_list(struct hl_device *hdev,
+				struct list_head *userptr_list)
+{
+	struct hl_userptr *userptr, *tmp;
+
+	list_for_each_entry_safe(userptr, tmp, userptr_list, job_node) {
+		hl_unpin_host_memory(hdev, userptr);
+		kfree(userptr);
+	}
+
+	INIT_LIST_HEAD(userptr_list);
+}
+
+/*
+ * hl_userptr_is_pinned - returns whether the given userptr is pinned
+ *
+ * @hdev                : pointer to the habanalabs device structure
+ * @userptr_list        : pointer to the list to clear
+ * @userptr             : pointer to userptr to check
+ *
+ * This function does the following:
+ * - Iterates over the list and checks if the given userptr is in it, means is
+ *   pinned. If so, returns true, otherwise returns false.
+ */
+bool hl_userptr_is_pinned(struct hl_device *hdev, u64 addr,
+				u32 size, struct list_head *userptr_list,
+				struct hl_userptr **userptr)
+{
+	list_for_each_entry((*userptr), userptr_list, job_node) {
+		if ((addr == (*userptr)->addr) && (size == (*userptr)->size))
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * va_range_init - initialize virtual addresses range
+ * @hdev: pointer to the habanalabs device structure
+ * @va_range: pointer to the range to initialize
+ * @start: range start address
+ * @end: range end address
+ *
+ * This function does the following:
+ * - Initializes the virtual addresses list of the given range with the given
+ *   addresses.
+ */
+static int va_range_init(struct hl_device *hdev, struct hl_va_range *va_range,
+				u64 start, u64 end)
+{
+	int rc;
+
+	INIT_LIST_HEAD(&va_range->list);
+
+	/* PAGE_SIZE alignment */
+
+	if (start & (PAGE_SIZE - 1)) {
+		start &= PAGE_MASK;
+		start += PAGE_SIZE;
+	}
+
+	if (end & (PAGE_SIZE - 1))
+		end &= PAGE_MASK;
+
+	if (start >= end) {
+		dev_err(hdev->dev, "too small vm range for va list\n");
+		return -EFAULT;
+	}
+
+	rc = add_va_block(hdev, va_range, start, end);
+
+	if (rc) {
+		dev_err(hdev->dev, "Failed to init host va list\n");
+		return rc;
+	}
+
+	va_range->start_addr = start;
+	va_range->end_addr = end;
+
+	return 0;
+}
+
+/*
+ * va_range_fini() - clear a virtual addresses range
+ * @hdev: pointer to the habanalabs structure
+ * va_range: pointer to virtual addresses range
+ *
+ * This function does the following:
+ * - Frees the virtual addresses block list and its lock
+ */
+static void va_range_fini(struct hl_device *hdev,
+		struct hl_va_range *va_range)
+{
+	mutex_lock(&va_range->lock);
+	clear_va_list_locked(hdev, &va_range->list);
+	mutex_unlock(&va_range->lock);
+
+	mutex_destroy(&va_range->lock);
+	kfree(va_range);
+}
+
+/*
+ * vm_ctx_init_with_ranges() - initialize virtual memory for context
+ * @ctx: pointer to the habanalabs context structure
+ * @host_range_start: host virtual addresses range start.
+ * @host_range_end: host virtual addresses range end.
+ * @host_huge_range_start: host virtual addresses range start for memory
+ *                          allocated with huge pages.
+ * @host_huge_range_end: host virtual addresses range end for memory allocated
+ *                        with huge pages.
+ * @dram_range_start: dram virtual addresses range start.
+ * @dram_range_end: dram virtual addresses range end.
+ *
+ * This function initializes the following:
+ * - MMU for context
+ * - Virtual address to area descriptor hashtable
+ * - Virtual block list of available virtual memory
+ */
+static int vm_ctx_init_with_ranges(struct hl_ctx *ctx,
+					u64 host_range_start,
+					u64 host_range_end,
+					u64 host_huge_range_start,
+					u64 host_huge_range_end,
+					u64 dram_range_start,
+					u64 dram_range_end)
+{
+	struct hl_device *hdev = ctx->hdev;
+	int rc;
+
+	ctx->host_va_range = kzalloc(sizeof(*ctx->host_va_range), GFP_KERNEL);
+	if (!ctx->host_va_range)
+		return -ENOMEM;
+
+	ctx->host_huge_va_range = kzalloc(sizeof(*ctx->host_huge_va_range),
+						GFP_KERNEL);
+	if (!ctx->host_huge_va_range) {
+		rc =  -ENOMEM;
+		goto host_huge_va_range_err;
+	}
+
+	ctx->dram_va_range = kzalloc(sizeof(*ctx->dram_va_range), GFP_KERNEL);
+	if (!ctx->dram_va_range) {
+		rc = -ENOMEM;
+		goto dram_va_range_err;
+	}
+
+	rc = hl_mmu_ctx_init(ctx);
+	if (rc) {
+		dev_err(hdev->dev, "failed to init context %d\n", ctx->asid);
+		goto mmu_ctx_err;
+	}
+
+	mutex_init(&ctx->mem_hash_lock);
+	hash_init(ctx->mem_hash);
+
+	mutex_init(&ctx->host_va_range->lock);
+
+	rc = va_range_init(hdev, ctx->host_va_range, host_range_start,
+				host_range_end);
+	if (rc) {
+		dev_err(hdev->dev, "failed to init host vm range\n");
+		goto host_page_range_err;
+	}
+
+	if (hdev->pmmu_huge_range) {
+		mutex_init(&ctx->host_huge_va_range->lock);
+
+		rc = va_range_init(hdev, ctx->host_huge_va_range,
+					host_huge_range_start,
+					host_huge_range_end);
+		if (rc) {
+			dev_err(hdev->dev,
+				"failed to init host huge vm range\n");
+			goto host_hpage_range_err;
+		}
+	} else {
+		ctx->host_huge_va_range = ctx->host_va_range;
+	}
+
+	mutex_init(&ctx->dram_va_range->lock);
+
+	rc = va_range_init(hdev, ctx->dram_va_range, dram_range_start,
+			dram_range_end);
+	if (rc) {
+		dev_err(hdev->dev, "failed to init dram vm range\n");
+		goto dram_vm_err;
+	}
+
+	hl_debugfs_add_ctx_mem_hash(hdev, ctx);
+
+	return 0;
+
+dram_vm_err:
+	mutex_destroy(&ctx->dram_va_range->lock);
+
+	if (hdev->pmmu_huge_range) {
+		mutex_lock(&ctx->host_huge_va_range->lock);
+		clear_va_list_locked(hdev, &ctx->host_huge_va_range->list);
+		mutex_unlock(&ctx->host_huge_va_range->lock);
+	}
+host_hpage_range_err:
+	if (hdev->pmmu_huge_range)
+		mutex_destroy(&ctx->host_huge_va_range->lock);
+	mutex_lock(&ctx->host_va_range->lock);
+	clear_va_list_locked(hdev, &ctx->host_va_range->list);
+	mutex_unlock(&ctx->host_va_range->lock);
+host_page_range_err:
+	mutex_destroy(&ctx->host_va_range->lock);
+	mutex_destroy(&ctx->mem_hash_lock);
+	hl_mmu_ctx_fini(ctx);
+mmu_ctx_err:
+	kfree(ctx->dram_va_range);
+dram_va_range_err:
+	kfree(ctx->host_huge_va_range);
+host_huge_va_range_err:
+	kfree(ctx->host_va_range);
+
+	return rc;
+}
+
+int hl_vm_ctx_init(struct hl_ctx *ctx)
+{
+	struct asic_fixed_properties *prop = &ctx->hdev->asic_prop;
+	u64 host_range_start, host_range_end, host_huge_range_start,
+		host_huge_range_end, dram_range_start, dram_range_end;
+
+	atomic64_set(&ctx->dram_phys_mem, 0);
+
+	/*
+	 * - If MMU is enabled, init the ranges as usual.
+	 * - If MMU is disabled, in case of host mapping, the returned address
+	 *   is the given one.
+	 *   In case of DRAM mapping, the returned address is the physical
+	 *   address of the memory related to the given handle.
+	 */
+	if (ctx->hdev->mmu_enable) {
+		dram_range_start = prop->dmmu.start_addr;
+		dram_range_end = prop->dmmu.end_addr;
+		host_range_start = prop->pmmu.start_addr;
+		host_range_end = prop->pmmu.end_addr;
+		host_huge_range_start = prop->pmmu_huge.start_addr;
+		host_huge_range_end = prop->pmmu_huge.end_addr;
+	} else {
+		dram_range_start = prop->dram_user_base_address;
+		dram_range_end = prop->dram_end_address;
+		host_range_start = prop->dram_user_base_address;
+		host_range_end = prop->dram_end_address;
+		host_huge_range_start = prop->dram_user_base_address;
+		host_huge_range_end = prop->dram_end_address;
+	}
+
+	return vm_ctx_init_with_ranges(ctx, host_range_start, host_range_end,
+					host_huge_range_start,
+					host_huge_range_end,
+					dram_range_start,
+					dram_range_end);
+}
+
+/*
+ * hl_vm_ctx_fini       - virtual memory teardown of context
+ *
+ * @ctx                 : pointer to the habanalabs context structure
+ *
+ * This function perform teardown the following:
+ * - Virtual block list of available virtual memory
+ * - Virtual address to area descriptor hashtable
+ * - MMU for context
+ *
+ * In addition this function does the following:
+ * - Unmaps the existing hashtable nodes if the hashtable is not empty. The
+ *   hashtable should be empty as no valid mappings should exist at this
+ *   point.
+ * - Frees any existing physical page list from the idr which relates to the
+ *   current context asid.
+ * - This function checks the virtual block list for correctness. At this point
+ *   the list should contain one element which describes the whole virtual
+ *   memory range of the context. Otherwise, a warning is printed.
+ */
+void hl_vm_ctx_fini(struct hl_ctx *ctx)
+{
+	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 hlist_node *tmp_node;
+	int i;
+
+	hl_debugfs_remove_ctx_mem_hash(hdev, ctx);
+
+	/*
+	 * Clearly something went wrong on hard reset so no point in printing
+	 * another side effect error
+	 */
+	if (!hdev->hard_reset_pending && !hash_empty(ctx->mem_hash))
+		dev_notice(hdev->dev,
+			"user released device without removing its memory mappings\n");
+
+	hash_for_each_safe(ctx->mem_hash, i, tmp_node, hnode, node) {
+		dev_dbg(hdev->dev,
+			"hl_mem_hash_node of vaddr 0x%llx of asid %d is still alive\n",
+			hnode->vaddr, ctx->asid);
+		unmap_device_va(ctx, hnode->vaddr, true);
+	}
+
+	/* invalidate the cache once after the unmapping loop */
+	hdev->asic_funcs->mmu_invalidate_cache(hdev, true, VM_TYPE_USERPTR);
+	hdev->asic_funcs->mmu_invalidate_cache(hdev, true, VM_TYPE_PHYS_PACK);
+
+	spin_lock(&vm->idr_lock);
+	idr_for_each_entry(&vm->phys_pg_pack_handles, phys_pg_list, i)
+		if (phys_pg_list->asid == ctx->asid) {
+			dev_dbg(hdev->dev,
+				"page list 0x%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);
+			idr_remove(&vm->phys_pg_pack_handles, i);
+		}
+	spin_unlock(&vm->idr_lock);
+
+	va_range_fini(hdev, ctx->dram_va_range);
+	if (hdev->pmmu_huge_range)
+		va_range_fini(hdev, ctx->host_huge_va_range);
+	va_range_fini(hdev, ctx->host_va_range);
+
+	mutex_destroy(&ctx->mem_hash_lock);
+	hl_mmu_ctx_fini(ctx);
+}
+
+/*
+ * hl_vm_init           - initialize virtual memory module
+ *
+ * @hdev                : pointer to the habanalabs device structure
+ *
+ * This function initializes the following:
+ * - MMU module
+ * - DRAM physical pages pool of 2MB
+ * - Idr for device memory allocation handles
+ */
+int hl_vm_init(struct hl_device *hdev)
+{
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct hl_vm *vm = &hdev->vm;
+	int rc;
+
+	vm->dram_pg_pool = gen_pool_create(__ffs(prop->dram_page_size), -1);
+	if (!vm->dram_pg_pool) {
+		dev_err(hdev->dev, "Failed to create dram page pool\n");
+		return -ENOMEM;
+	}
+
+	kref_init(&vm->dram_pg_pool_refcount);
+
+	rc = gen_pool_add(vm->dram_pg_pool, prop->dram_user_base_address,
+			prop->dram_end_address - prop->dram_user_base_address,
+			-1);
+
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to add memory to dram page pool %d\n", rc);
+		goto pool_add_err;
+	}
+
+	spin_lock_init(&vm->idr_lock);
+	idr_init(&vm->phys_pg_pack_handles);
+
+	atomic64_set(&hdev->dram_used_mem, 0);
+
+	vm->init_done = true;
+
+	return 0;
+
+pool_add_err:
+	gen_pool_destroy(vm->dram_pg_pool);
+
+	return rc;
+}
+
+/*
+ * hl_vm_fini           - virtual memory module teardown
+ *
+ * @hdev                : pointer to the habanalabs device structure
+ *
+ * This function perform teardown to the following:
+ * - Idr for device memory allocation handles
+ * - DRAM physical pages pool of 2MB
+ * - MMU module
+ */
+void hl_vm_fini(struct hl_device *hdev)
+{
+	struct hl_vm *vm = &hdev->vm;
+
+	if (!vm->init_done)
+		return;
+
+	/*
+	 * At this point all the contexts should be freed and hence no DRAM
+	 * memory should be in use. Hence the DRAM pool should be freed here.
+	 */
+	if (kref_put(&vm->dram_pg_pool_refcount, dram_pg_pool_do_release) != 1)
+		dev_warn(hdev->dev, "dram_pg_pool was not destroyed on %s\n",
+				__func__);
+
+	vm->init_done = false;
+}
diff --git a/drivers/misc/habanalabs/common/mmu.c b/drivers/misc/habanalabs/common/mmu.c
new file mode 100644
index 000000000000..04303950e630
--- /dev/null
+++ b/drivers/misc/habanalabs/common/mmu.c
@@ -0,0 +1,1037 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2019 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include "habanalabs.h"
+#include "include/hw_ip/mmu/mmu_general.h"
+
+#include <linux/genalloc.h>
+#include <linux/slab.h>
+
+static inline u64 get_phys_addr(struct hl_ctx *ctx, u64 shadow_addr);
+
+static struct pgt_info *get_pgt_info(struct hl_ctx *ctx, u64 hop_addr)
+{
+	struct pgt_info *pgt_info = NULL;
+
+	hash_for_each_possible(ctx->mmu_shadow_hash, pgt_info, node,
+				(unsigned long) hop_addr)
+		if (hop_addr == pgt_info->shadow_addr)
+			break;
+
+	return pgt_info;
+}
+
+static void _free_hop(struct hl_ctx *ctx, struct pgt_info *pgt_info)
+{
+	struct hl_device *hdev = ctx->hdev;
+
+	gen_pool_free(hdev->mmu_pgt_pool, pgt_info->phys_addr,
+			hdev->asic_prop.mmu_hop_table_size);
+	hash_del(&pgt_info->node);
+	kfree((u64 *) (uintptr_t) pgt_info->shadow_addr);
+	kfree(pgt_info);
+}
+
+static void free_hop(struct hl_ctx *ctx, u64 hop_addr)
+{
+	struct pgt_info *pgt_info = get_pgt_info(ctx, hop_addr);
+
+	_free_hop(ctx, pgt_info);
+}
+
+static u64 alloc_hop(struct hl_ctx *ctx)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct pgt_info *pgt_info;
+	u64 phys_addr, shadow_addr;
+
+	pgt_info = kmalloc(sizeof(*pgt_info), GFP_KERNEL);
+	if (!pgt_info)
+		return ULLONG_MAX;
+
+	phys_addr = (u64) gen_pool_alloc(hdev->mmu_pgt_pool,
+					prop->mmu_hop_table_size);
+	if (!phys_addr) {
+		dev_err(hdev->dev, "failed to allocate page\n");
+		goto pool_add_err;
+	}
+
+	shadow_addr = (u64) (uintptr_t) kzalloc(prop->mmu_hop_table_size,
+						GFP_KERNEL);
+	if (!shadow_addr)
+		goto shadow_err;
+
+	pgt_info->phys_addr = phys_addr;
+	pgt_info->shadow_addr = shadow_addr;
+	pgt_info->ctx = ctx;
+	pgt_info->num_of_ptes = 0;
+	hash_add(ctx->mmu_shadow_hash, &pgt_info->node, shadow_addr);
+
+	return shadow_addr;
+
+shadow_err:
+	gen_pool_free(hdev->mmu_pgt_pool, phys_addr, prop->mmu_hop_table_size);
+pool_add_err:
+	kfree(pgt_info);
+
+	return ULLONG_MAX;
+}
+
+static inline u64 get_phys_hop0_addr(struct hl_ctx *ctx)
+{
+	return ctx->hdev->asic_prop.mmu_pgt_addr +
+			(ctx->asid * ctx->hdev->asic_prop.mmu_hop_table_size);
+}
+
+static inline u64 get_hop0_addr(struct hl_ctx *ctx)
+{
+	return (u64) (uintptr_t) ctx->hdev->mmu_shadow_hop0 +
+			(ctx->asid * ctx->hdev->asic_prop.mmu_hop_table_size);
+}
+
+static inline void flush(struct hl_ctx *ctx)
+{
+	/* flush all writes from all cores to reach PCI */
+	mb();
+	ctx->hdev->asic_funcs->read_pte(ctx->hdev, get_phys_hop0_addr(ctx));
+}
+
+/* transform the value to physical address when writing to H/W */
+static inline void write_pte(struct hl_ctx *ctx, u64 shadow_pte_addr, u64 val)
+{
+	/*
+	 * The value to write is actually the address of the next shadow hop +
+	 * flags at the 12 LSBs.
+	 * Hence in order to get the value to write to the physical PTE, we
+	 * clear the 12 LSBs and translate the shadow hop to its associated
+	 * physical hop, and add back the original 12 LSBs.
+	 */
+	u64 phys_val = get_phys_addr(ctx, val & HOP_PHYS_ADDR_MASK) |
+				(val & FLAGS_MASK);
+
+	ctx->hdev->asic_funcs->write_pte(ctx->hdev,
+					get_phys_addr(ctx, shadow_pte_addr),
+					phys_val);
+
+	*(u64 *) (uintptr_t) shadow_pte_addr = val;
+}
+
+/* do not transform the value to physical address when writing to H/W */
+static inline void write_final_pte(struct hl_ctx *ctx, u64 shadow_pte_addr,
+					u64 val)
+{
+	ctx->hdev->asic_funcs->write_pte(ctx->hdev,
+					get_phys_addr(ctx, shadow_pte_addr),
+					val);
+	*(u64 *) (uintptr_t) shadow_pte_addr = val;
+}
+
+/* clear the last and present bits */
+static inline void clear_pte(struct hl_ctx *ctx, u64 pte_addr)
+{
+	/* no need to transform the value to physical address */
+	write_final_pte(ctx, pte_addr, 0);
+}
+
+static inline void get_pte(struct hl_ctx *ctx, u64 hop_addr)
+{
+	get_pgt_info(ctx, hop_addr)->num_of_ptes++;
+}
+
+/*
+ * put_pte - decrement the num of ptes and free the hop if possible
+ *
+ * @ctx: pointer to the context structure
+ * @hop_addr: addr of the hop
+ *
+ * This function returns the number of ptes left on this hop. If the number is
+ * 0, it means the pte was freed.
+ */
+static inline int put_pte(struct hl_ctx *ctx, u64 hop_addr)
+{
+	struct pgt_info *pgt_info = get_pgt_info(ctx, hop_addr);
+	int num_of_ptes_left;
+
+	pgt_info->num_of_ptes--;
+
+	/*
+	 * Need to save the number of ptes left because free_hop might free
+	 * the pgt_info
+	 */
+	num_of_ptes_left = pgt_info->num_of_ptes;
+	if (!num_of_ptes_left)
+		_free_hop(ctx, pgt_info);
+
+	return num_of_ptes_left;
+}
+
+static inline u64 get_hopN_pte_addr(struct hl_ctx *ctx, u64 hop_addr,
+					u64 virt_addr, u64 mask, u64 shift)
+{
+	return hop_addr + ctx->hdev->asic_prop.mmu_pte_size *
+			((virt_addr & mask) >> shift);
+}
+
+static inline u64 get_hop0_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_prop,
+					u64 hop_addr, u64 vaddr)
+{
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_prop->hop0_mask,
+					mmu_prop->hop0_shift);
+}
+
+static inline u64 get_hop1_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_prop,
+					u64 hop_addr, u64 vaddr)
+{
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_prop->hop1_mask,
+					mmu_prop->hop1_shift);
+}
+
+static inline u64 get_hop2_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_prop,
+					u64 hop_addr, u64 vaddr)
+{
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_prop->hop2_mask,
+					mmu_prop->hop2_shift);
+}
+
+static inline u64 get_hop3_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_prop,
+					u64 hop_addr, u64 vaddr)
+{
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_prop->hop3_mask,
+					mmu_prop->hop3_shift);
+}
+
+static inline u64 get_hop4_pte_addr(struct hl_ctx *ctx,
+					struct hl_mmu_properties *mmu_prop,
+					u64 hop_addr, u64 vaddr)
+{
+	return get_hopN_pte_addr(ctx, hop_addr, vaddr, mmu_prop->hop4_mask,
+					mmu_prop->hop4_shift);
+}
+
+static inline u64 get_next_hop_addr(struct hl_ctx *ctx, u64 curr_pte)
+{
+	if (curr_pte & PAGE_PRESENT_MASK)
+		return curr_pte & 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);
+
+	if (hop_addr == ULLONG_MAX) {
+		hop_addr = alloc_hop(ctx);
+		*is_new_hop = (hop_addr != ULLONG_MAX);
+	}
+
+	return hop_addr;
+}
+
+/* translates shadow address inside hop to a physical address */
+static inline u64 get_phys_addr(struct hl_ctx *ctx, u64 shadow_addr)
+{
+	u64 page_mask = (ctx->hdev->asic_prop.mmu_hop_table_size - 1);
+	u64 shadow_hop_addr = shadow_addr & ~page_mask;
+	u64 pte_offset = shadow_addr & page_mask;
+	u64 phys_hop_addr;
+
+	if (shadow_hop_addr != get_hop0_addr(ctx))
+		phys_hop_addr = get_pgt_info(ctx, shadow_hop_addr)->phys_addr;
+	else
+		phys_hop_addr = get_phys_hop0_addr(ctx);
+
+	return phys_hop_addr + pte_offset;
+}
+
+static bool is_dram_va(struct hl_device *hdev, u64 virt_addr)
+{
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+
+	return hl_mem_area_inside_range(virt_addr, prop->dmmu.page_size,
+					prop->dmmu.start_addr,
+					prop->dmmu.end_addr);
+}
+
+static int dram_default_mapping_init(struct hl_ctx *ctx)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	u64 num_of_hop3, total_hops, hop0_addr, hop1_addr, hop2_addr,
+		hop2_pte_addr, hop3_pte_addr, pte_val;
+	int rc, i, j, hop3_allocated = 0;
+
+	if ((!hdev->dram_supports_virtual_memory) ||
+			(!hdev->dram_default_page_mapping) ||
+			(ctx->asid == HL_KERNEL_ASID_ID))
+		return 0;
+
+	num_of_hop3 = prop->dram_size_for_default_page_mapping;
+	do_div(num_of_hop3, prop->dram_page_size);
+	do_div(num_of_hop3, PTE_ENTRIES_IN_HOP);
+
+	/* add hop1 and hop2 */
+	total_hops = num_of_hop3 + 2;
+
+	ctx->dram_default_hops = kzalloc(HL_PTE_SIZE * total_hops,  GFP_KERNEL);
+	if (!ctx->dram_default_hops)
+		return -ENOMEM;
+
+	hop0_addr = get_hop0_addr(ctx);
+
+	hop1_addr = alloc_hop(ctx);
+	if (hop1_addr == ULLONG_MAX) {
+		dev_err(hdev->dev, "failed to alloc hop 1\n");
+		rc = -ENOMEM;
+		goto hop1_err;
+	}
+
+	ctx->dram_default_hops[total_hops - 1] = hop1_addr;
+
+	hop2_addr = alloc_hop(ctx);
+	if (hop2_addr == ULLONG_MAX) {
+		dev_err(hdev->dev, "failed to alloc hop 2\n");
+		rc = -ENOMEM;
+		goto hop2_err;
+	}
+
+	ctx->dram_default_hops[total_hops - 2] = hop2_addr;
+
+	for (i = 0 ; i < num_of_hop3 ; i++) {
+		ctx->dram_default_hops[i] = alloc_hop(ctx);
+		if (ctx->dram_default_hops[i] == ULLONG_MAX) {
+			dev_err(hdev->dev, "failed to alloc hop 3, i: %d\n", i);
+			rc = -ENOMEM;
+			goto hop3_err;
+		}
+		hop3_allocated++;
+	}
+
+	/* need only pte 0 in hops 0 and 1 */
+	pte_val = (hop1_addr & HOP_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
+	write_pte(ctx, hop0_addr, pte_val);
+
+	pte_val = (hop2_addr & HOP_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
+	write_pte(ctx, hop1_addr, pte_val);
+	get_pte(ctx, hop1_addr);
+
+	hop2_pte_addr = hop2_addr;
+	for (i = 0 ; i < num_of_hop3 ; i++) {
+		pte_val = (ctx->dram_default_hops[i] & HOP_PHYS_ADDR_MASK) |
+				PAGE_PRESENT_MASK;
+		write_pte(ctx, hop2_pte_addr, pte_val);
+		get_pte(ctx, hop2_addr);
+		hop2_pte_addr += HL_PTE_SIZE;
+	}
+
+	pte_val = (prop->mmu_dram_default_page_addr & HOP_PHYS_ADDR_MASK) |
+			LAST_MASK | PAGE_PRESENT_MASK;
+
+	for (i = 0 ; i < num_of_hop3 ; i++) {
+		hop3_pte_addr = ctx->dram_default_hops[i];
+		for (j = 0 ; j < PTE_ENTRIES_IN_HOP ; j++) {
+			write_final_pte(ctx, hop3_pte_addr, pte_val);
+			get_pte(ctx, ctx->dram_default_hops[i]);
+			hop3_pte_addr += HL_PTE_SIZE;
+		}
+	}
+
+	flush(ctx);
+
+	return 0;
+
+hop3_err:
+	for (i = 0 ; i < hop3_allocated ; i++)
+		free_hop(ctx, ctx->dram_default_hops[i]);
+
+	free_hop(ctx, hop2_addr);
+hop2_err:
+	free_hop(ctx, hop1_addr);
+hop1_err:
+	kfree(ctx->dram_default_hops);
+
+	return rc;
+}
+
+static void dram_default_mapping_fini(struct hl_ctx *ctx)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	u64 num_of_hop3, total_hops, hop0_addr, hop1_addr, hop2_addr,
+		hop2_pte_addr, hop3_pte_addr;
+	int i, j;
+
+	if ((!hdev->dram_supports_virtual_memory) ||
+			(!hdev->dram_default_page_mapping) ||
+			(ctx->asid == HL_KERNEL_ASID_ID))
+		return;
+
+	num_of_hop3 = prop->dram_size_for_default_page_mapping;
+	do_div(num_of_hop3, prop->dram_page_size);
+	do_div(num_of_hop3, PTE_ENTRIES_IN_HOP);
+
+	hop0_addr = get_hop0_addr(ctx);
+	/* add hop1 and hop2 */
+	total_hops = num_of_hop3 + 2;
+	hop1_addr = ctx->dram_default_hops[total_hops - 1];
+	hop2_addr = ctx->dram_default_hops[total_hops - 2];
+
+	for (i = 0 ; i < num_of_hop3 ; i++) {
+		hop3_pte_addr = ctx->dram_default_hops[i];
+		for (j = 0 ; j < PTE_ENTRIES_IN_HOP ; j++) {
+			clear_pte(ctx, hop3_pte_addr);
+			put_pte(ctx, ctx->dram_default_hops[i]);
+			hop3_pte_addr += HL_PTE_SIZE;
+		}
+	}
+
+	hop2_pte_addr = hop2_addr;
+	hop2_pte_addr = hop2_addr;
+	for (i = 0 ; i < num_of_hop3 ; i++) {
+		clear_pte(ctx, hop2_pte_addr);
+		put_pte(ctx, hop2_addr);
+		hop2_pte_addr += HL_PTE_SIZE;
+	}
+
+	clear_pte(ctx, hop1_addr);
+	put_pte(ctx, hop1_addr);
+	clear_pte(ctx, hop0_addr);
+
+	kfree(ctx->dram_default_hops);
+
+	flush(ctx);
+}
+
+/**
+ * hl_mmu_init() - initialize the MMU module.
+ * @hdev: habanalabs device structure.
+ *
+ * This function does the following:
+ * - Create a pool of pages for pgt_infos.
+ * - Create a shadow table for pgt
+ *
+ * Return: 0 for success, non-zero for failure.
+ */
+int hl_mmu_init(struct hl_device *hdev)
+{
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	int rc;
+
+	if (!hdev->mmu_enable)
+		return 0;
+
+	hdev->mmu_pgt_pool =
+			gen_pool_create(__ffs(prop->mmu_hop_table_size), -1);
+
+	if (!hdev->mmu_pgt_pool) {
+		dev_err(hdev->dev, "Failed to create page gen pool\n");
+		return -ENOMEM;
+	}
+
+	rc = gen_pool_add(hdev->mmu_pgt_pool, prop->mmu_pgt_addr +
+			prop->mmu_hop0_tables_total_size,
+			prop->mmu_pgt_size - prop->mmu_hop0_tables_total_size,
+			-1);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to add memory to page gen pool\n");
+		goto err_pool_add;
+	}
+
+	hdev->mmu_shadow_hop0 = kvmalloc_array(prop->max_asid,
+					prop->mmu_hop_table_size,
+					GFP_KERNEL | __GFP_ZERO);
+	if (!hdev->mmu_shadow_hop0) {
+		rc = -ENOMEM;
+		goto err_pool_add;
+	}
+
+	/* MMU H/W init will be done in device hw_init() */
+
+	return 0;
+
+err_pool_add:
+	gen_pool_destroy(hdev->mmu_pgt_pool);
+
+	return rc;
+}
+
+/**
+ * hl_mmu_fini() - release the MMU module.
+ * @hdev: habanalabs device structure.
+ *
+ * This function does the following:
+ * - Disable MMU in H/W.
+ * - Free the pgt_infos pool.
+ *
+ * All contexts should be freed before calling this function.
+ */
+void hl_mmu_fini(struct hl_device *hdev)
+{
+	if (!hdev->mmu_enable)
+		return;
+
+	/* MMU H/W fini was already done in device hw_fini() */
+
+	kvfree(hdev->mmu_shadow_hop0);
+	gen_pool_destroy(hdev->mmu_pgt_pool);
+}
+
+/**
+ * hl_mmu_ctx_init() - initialize a context for using the MMU module.
+ * @ctx: pointer to the context structure to initialize.
+ *
+ * Initialize a mutex to protect the concurrent mapping flow, a hash to hold all
+ * page tables hops related to this context.
+ * Return: 0 on success, non-zero otherwise.
+ */
+int hl_mmu_ctx_init(struct hl_ctx *ctx)
+{
+	struct hl_device *hdev = ctx->hdev;
+
+	if (!hdev->mmu_enable)
+		return 0;
+
+	mutex_init(&ctx->mmu_lock);
+	hash_init(ctx->mmu_shadow_hash);
+
+	return dram_default_mapping_init(ctx);
+}
+
+/*
+ * hl_mmu_ctx_fini - disable a ctx from using the mmu module
+ *
+ * @ctx: pointer to the context structure
+ *
+ * This function does the following:
+ * - Free any pgts which were not freed yet
+ * - Free the mutex
+ * - Free DRAM default page mapping hops
+ */
+void hl_mmu_ctx_fini(struct hl_ctx *ctx)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct pgt_info *pgt_info;
+	struct hlist_node *tmp;
+	int i;
+
+	if (!hdev->mmu_enable)
+		return;
+
+	dram_default_mapping_fini(ctx);
+
+	if (!hash_empty(ctx->mmu_shadow_hash))
+		dev_err(hdev->dev, "ctx %d is freed while it has pgts in use\n",
+			ctx->asid);
+
+	hash_for_each_safe(ctx->mmu_shadow_hash, i, tmp, pgt_info, node) {
+		dev_err_ratelimited(hdev->dev,
+			"pgt_info of addr 0x%llx of asid %d was not destroyed, num_ptes: %d\n",
+			pgt_info->phys_addr, ctx->asid, pgt_info->num_of_ptes);
+		_free_hop(ctx, pgt_info);
+	}
+
+	mutex_destroy(&ctx->mmu_lock);
+}
+
+static int _hl_mmu_unmap(struct hl_ctx *ctx, u64 virt_addr, bool is_dram_addr)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct hl_mmu_properties *mmu_prop;
+	u64 hop0_addr = 0, hop0_pte_addr = 0,
+		hop1_addr = 0, hop1_pte_addr = 0,
+		hop2_addr = 0, hop2_pte_addr = 0,
+		hop3_addr = 0, hop3_pte_addr = 0,
+		hop4_addr = 0, hop4_pte_addr = 0,
+		curr_pte;
+	bool is_huge, clear_hop3 = true;
+
+	/* shifts and masks are the same in PMMU and HPMMU, use one of them */
+	mmu_prop = is_dram_addr ? &prop->dmmu : &prop->pmmu;
+
+	hop0_addr = get_hop0_addr(ctx);
+	hop0_pte_addr = get_hop0_pte_addr(ctx, mmu_prop, hop0_addr, virt_addr);
+
+	curr_pte = *(u64 *) (uintptr_t) hop0_pte_addr;
+
+	hop1_addr = get_next_hop_addr(ctx, curr_pte);
+
+	if (hop1_addr == ULLONG_MAX)
+		goto not_mapped;
+
+	hop1_pte_addr = get_hop1_pte_addr(ctx, mmu_prop, hop1_addr, virt_addr);
+
+	curr_pte = *(u64 *) (uintptr_t) hop1_pte_addr;
+
+	hop2_addr = get_next_hop_addr(ctx, curr_pte);
+
+	if (hop2_addr == ULLONG_MAX)
+		goto not_mapped;
+
+	hop2_pte_addr = get_hop2_pte_addr(ctx, mmu_prop, hop2_addr, virt_addr);
+
+	curr_pte = *(u64 *) (uintptr_t) hop2_pte_addr;
+
+	hop3_addr = get_next_hop_addr(ctx, curr_pte);
+
+	if (hop3_addr == ULLONG_MAX)
+		goto not_mapped;
+
+	hop3_pte_addr = get_hop3_pte_addr(ctx, mmu_prop, hop3_addr, virt_addr);
+
+	curr_pte = *(u64 *) (uintptr_t) hop3_pte_addr;
+
+	is_huge = curr_pte & LAST_MASK;
+
+	if (is_dram_addr && !is_huge) {
+		dev_err(hdev->dev,
+				"DRAM unmapping should use huge pages only\n");
+		return -EFAULT;
+	}
+
+	if (!is_huge) {
+		hop4_addr = get_next_hop_addr(ctx, curr_pte);
+
+		if (hop4_addr == ULLONG_MAX)
+			goto not_mapped;
+
+		hop4_pte_addr = get_hop4_pte_addr(ctx, mmu_prop, hop4_addr,
+							virt_addr);
+
+		curr_pte = *(u64 *) (uintptr_t) hop4_pte_addr;
+
+		clear_hop3 = false;
+	}
+
+	if (hdev->dram_default_page_mapping && is_dram_addr) {
+		u64 default_pte = (prop->mmu_dram_default_page_addr &
+				HOP_PHYS_ADDR_MASK) | LAST_MASK |
+					PAGE_PRESENT_MASK;
+		if (curr_pte == default_pte) {
+			dev_err(hdev->dev,
+				"DRAM: hop3 PTE points to zero page, can't unmap, va: 0x%llx\n",
+					virt_addr);
+			goto not_mapped;
+		}
+
+		if (!(curr_pte & PAGE_PRESENT_MASK)) {
+			dev_err(hdev->dev,
+				"DRAM: hop3 PTE is cleared! can't unmap, va: 0x%llx\n",
+					virt_addr);
+			goto not_mapped;
+		}
+
+		write_final_pte(ctx, hop3_pte_addr, default_pte);
+		put_pte(ctx, hop3_addr);
+	} else {
+		if (!(curr_pte & PAGE_PRESENT_MASK))
+			goto not_mapped;
+
+		if (hop4_addr)
+			clear_pte(ctx, hop4_pte_addr);
+		else
+			clear_pte(ctx, hop3_pte_addr);
+
+		if (hop4_addr && !put_pte(ctx, hop4_addr))
+			clear_hop3 = true;
+
+		if (!clear_hop3)
+			goto mapped;
+
+		clear_pte(ctx, hop3_pte_addr);
+
+		if (put_pte(ctx, hop3_addr))
+			goto mapped;
+
+		clear_pte(ctx, hop2_pte_addr);
+
+		if (put_pte(ctx, hop2_addr))
+			goto mapped;
+
+		clear_pte(ctx, hop1_pte_addr);
+
+		if (put_pte(ctx, hop1_addr))
+			goto mapped;
+
+		clear_pte(ctx, hop0_pte_addr);
+	}
+
+mapped:
+	return 0;
+
+not_mapped:
+	dev_err(hdev->dev, "virt addr 0x%llx is not mapped to phys addr\n",
+		virt_addr);
+
+	return -EINVAL;
+}
+
+/*
+ * hl_mmu_unmap - unmaps a virtual addr
+ *
+ * @ctx: pointer to the context structure
+ * @virt_addr: virt addr to map from
+ * @page_size: size of the page to unmap
+ * @flush_pte: whether to do a PCI flush
+ *
+ * This function does the following:
+ * - Check that the virt addr is mapped
+ * - Unmap the virt addr and frees pgts if possible
+ * - Returns 0 on success, -EINVAL if the given addr is not mapped
+ *
+ * Because this function changes the page tables in the device and because it
+ * changes the MMU hash, it must be protected by a lock.
+ * However, because it maps only a single page, the lock should be implemented
+ * in a higher level in order to protect the entire mapping of the memory area
+ *
+ * For optimization reasons PCI flush may be requested once after unmapping of
+ * large area.
+ */
+int hl_mmu_unmap(struct hl_ctx *ctx, u64 virt_addr, u32 page_size,
+		bool flush_pte)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct hl_mmu_properties *mmu_prop;
+	u64 real_virt_addr;
+	u32 real_page_size, npages;
+	int i, rc = 0;
+	bool is_dram_addr;
+
+	if (!hdev->mmu_enable)
+		return 0;
+
+	is_dram_addr = is_dram_va(hdev, virt_addr);
+
+	if (is_dram_addr)
+		mmu_prop = &prop->dmmu;
+	else if ((page_size % prop->pmmu_huge.page_size) == 0)
+		mmu_prop = &prop->pmmu_huge;
+	else
+		mmu_prop = &prop->pmmu;
+
+	/*
+	 * The H/W handles mapping of specific page sizes. Hence if the page
+	 * size is bigger, we break it to sub-pages and unmap them separately.
+	 */
+	if ((page_size % mmu_prop->page_size) == 0) {
+		real_page_size = mmu_prop->page_size;
+	} else {
+		dev_err(hdev->dev,
+			"page size of %u is not %uKB aligned, can't unmap\n",
+			page_size, mmu_prop->page_size >> 10);
+
+		return -EFAULT;
+	}
+
+	npages = page_size / real_page_size;
+	real_virt_addr = virt_addr;
+
+	for (i = 0 ; i < npages ; i++) {
+		rc = _hl_mmu_unmap(ctx, real_virt_addr, is_dram_addr);
+		if (rc)
+			break;
+
+		real_virt_addr += real_page_size;
+	}
+
+	if (flush_pte)
+		flush(ctx);
+
+	return rc;
+}
+
+static int _hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr,
+			u32 page_size, bool is_dram_addr)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct hl_mmu_properties *mmu_prop;
+	u64 hop0_addr = 0, hop0_pte_addr = 0,
+		hop1_addr = 0, hop1_pte_addr = 0,
+		hop2_addr = 0, hop2_pte_addr = 0,
+		hop3_addr = 0, hop3_pte_addr = 0,
+		hop4_addr = 0, hop4_pte_addr = 0,
+		curr_pte = 0;
+	bool hop1_new = false, hop2_new = false, hop3_new = false,
+		hop4_new = false, is_huge;
+	int rc = -ENOMEM;
+
+	/*
+	 * This mapping function can map a page or a huge page. For huge page
+	 * there are only 3 hops rather than 4. Currently the DRAM allocation
+	 * uses huge pages only but user memory could have been allocated with
+	 * one of the two page sizes. Since this is a common code for all the
+	 * three cases, we need this hugs page check.
+	 */
+	if (is_dram_addr) {
+		mmu_prop = &prop->dmmu;
+		is_huge = true;
+	} else if (page_size == prop->pmmu_huge.page_size) {
+		mmu_prop = &prop->pmmu_huge;
+		is_huge = true;
+	} else {
+		mmu_prop = &prop->pmmu;
+		is_huge = false;
+	}
+
+	hop0_addr = get_hop0_addr(ctx);
+	hop0_pte_addr = get_hop0_pte_addr(ctx, mmu_prop, hop0_addr, virt_addr);
+	curr_pte = *(u64 *) (uintptr_t) hop0_pte_addr;
+
+	hop1_addr = get_alloc_next_hop_addr(ctx, curr_pte, &hop1_new);
+	if (hop1_addr == ULLONG_MAX)
+		goto err;
+
+	hop1_pte_addr = get_hop1_pte_addr(ctx, mmu_prop, hop1_addr, virt_addr);
+	curr_pte = *(u64 *) (uintptr_t) hop1_pte_addr;
+
+	hop2_addr = get_alloc_next_hop_addr(ctx, curr_pte, &hop2_new);
+	if (hop2_addr == ULLONG_MAX)
+		goto err;
+
+	hop2_pte_addr = get_hop2_pte_addr(ctx, mmu_prop, hop2_addr, virt_addr);
+	curr_pte = *(u64 *) (uintptr_t) hop2_pte_addr;
+
+	hop3_addr = get_alloc_next_hop_addr(ctx, curr_pte, &hop3_new);
+	if (hop3_addr == ULLONG_MAX)
+		goto err;
+
+	hop3_pte_addr = get_hop3_pte_addr(ctx, mmu_prop, hop3_addr, virt_addr);
+	curr_pte = *(u64 *) (uintptr_t) hop3_pte_addr;
+
+	if (!is_huge) {
+		hop4_addr = get_alloc_next_hop_addr(ctx, curr_pte, &hop4_new);
+		if (hop4_addr == ULLONG_MAX)
+			goto err;
+
+		hop4_pte_addr = get_hop4_pte_addr(ctx, mmu_prop, hop4_addr,
+							virt_addr);
+		curr_pte = *(u64 *) (uintptr_t) hop4_pte_addr;
+	}
+
+	if (hdev->dram_default_page_mapping && is_dram_addr) {
+		u64 default_pte = (prop->mmu_dram_default_page_addr &
+					HOP_PHYS_ADDR_MASK) | LAST_MASK |
+						PAGE_PRESENT_MASK;
+
+		if (curr_pte != default_pte) {
+			dev_err(hdev->dev,
+				"DRAM: mapping already exists for virt_addr 0x%llx\n",
+					virt_addr);
+			rc = -EINVAL;
+			goto err;
+		}
+
+		if (hop1_new || hop2_new || hop3_new || hop4_new) {
+			dev_err(hdev->dev,
+				"DRAM mapping should not allocate more hops\n");
+			rc = -EFAULT;
+			goto err;
+		}
+	} else if (curr_pte & PAGE_PRESENT_MASK) {
+		dev_err(hdev->dev,
+			"mapping already exists for virt_addr 0x%llx\n",
+				virt_addr);
+
+		dev_dbg(hdev->dev, "hop0 pte: 0x%llx (0x%llx)\n",
+			*(u64 *) (uintptr_t) hop0_pte_addr, hop0_pte_addr);
+		dev_dbg(hdev->dev, "hop1 pte: 0x%llx (0x%llx)\n",
+			*(u64 *) (uintptr_t) hop1_pte_addr, hop1_pte_addr);
+		dev_dbg(hdev->dev, "hop2 pte: 0x%llx (0x%llx)\n",
+			*(u64 *) (uintptr_t) hop2_pte_addr, hop2_pte_addr);
+		dev_dbg(hdev->dev, "hop3 pte: 0x%llx (0x%llx)\n",
+			*(u64 *) (uintptr_t) hop3_pte_addr, hop3_pte_addr);
+
+		if (!is_huge)
+			dev_dbg(hdev->dev, "hop4 pte: 0x%llx (0x%llx)\n",
+				*(u64 *) (uintptr_t) hop4_pte_addr,
+				hop4_pte_addr);
+
+		rc = -EINVAL;
+		goto err;
+	}
+
+	curr_pte = (phys_addr & HOP_PHYS_ADDR_MASK) | LAST_MASK
+			| PAGE_PRESENT_MASK;
+
+	if (is_huge)
+		write_final_pte(ctx, hop3_pte_addr, curr_pte);
+	else
+		write_final_pte(ctx, hop4_pte_addr, curr_pte);
+
+	if (hop1_new) {
+		curr_pte =
+			(hop1_addr & HOP_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
+		write_pte(ctx, hop0_pte_addr, curr_pte);
+	}
+	if (hop2_new) {
+		curr_pte =
+			(hop2_addr & HOP_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
+		write_pte(ctx, hop1_pte_addr, curr_pte);
+		get_pte(ctx, hop1_addr);
+	}
+	if (hop3_new) {
+		curr_pte =
+			(hop3_addr & HOP_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK;
+		write_pte(ctx, hop2_pte_addr, curr_pte);
+		get_pte(ctx, hop2_addr);
+	}
+
+	if (!is_huge) {
+		if (hop4_new) {
+			curr_pte = (hop4_addr & HOP_PHYS_ADDR_MASK) |
+					PAGE_PRESENT_MASK;
+			write_pte(ctx, hop3_pte_addr, curr_pte);
+			get_pte(ctx, hop3_addr);
+		}
+
+		get_pte(ctx, hop4_addr);
+	} else {
+		get_pte(ctx, hop3_addr);
+	}
+
+	return 0;
+
+err:
+	if (hop4_new)
+		free_hop(ctx, hop4_addr);
+	if (hop3_new)
+		free_hop(ctx, hop3_addr);
+	if (hop2_new)
+		free_hop(ctx, hop2_addr);
+	if (hop1_new)
+		free_hop(ctx, hop1_addr);
+
+	return rc;
+}
+
+/*
+ * hl_mmu_map - maps a virtual addr to physical addr
+ *
+ * @ctx: pointer to the context structure
+ * @virt_addr: virt addr to map from
+ * @phys_addr: phys addr to map to
+ * @page_size: physical page size
+ * @flush_pte: whether to do a PCI flush
+ *
+ * This function does the following:
+ * - Check that the virt addr is not mapped
+ * - Allocate pgts as necessary in order to map the virt addr to the phys
+ * - Returns 0 on success, -EINVAL if addr is already mapped, or -ENOMEM.
+ *
+ * Because this function changes the page tables in the device and because it
+ * changes the MMU hash, it must be protected by a lock.
+ * However, because it maps only a single page, the lock should be implemented
+ * in a higher level in order to protect the entire mapping of the memory area
+ *
+ * For optimization reasons PCI flush may be requested once after mapping of
+ * large area.
+ */
+int hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, u32 page_size,
+		bool flush_pte)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct hl_mmu_properties *mmu_prop;
+	u64 real_virt_addr, real_phys_addr;
+	u32 real_page_size, npages;
+	int i, rc, mapped_cnt = 0;
+	bool is_dram_addr;
+
+	if (!hdev->mmu_enable)
+		return 0;
+
+	is_dram_addr = is_dram_va(hdev, virt_addr);
+
+	if (is_dram_addr)
+		mmu_prop = &prop->dmmu;
+	else if ((page_size % prop->pmmu_huge.page_size) == 0)
+		mmu_prop = &prop->pmmu_huge;
+	else
+		mmu_prop = &prop->pmmu;
+
+	/*
+	 * The H/W handles mapping of specific page sizes. Hence if the page
+	 * size is bigger, we break it to sub-pages and map them separately.
+	 */
+	if ((page_size % mmu_prop->page_size) == 0) {
+		real_page_size = mmu_prop->page_size;
+	} else {
+		dev_err(hdev->dev,
+			"page size of %u is not %uKB aligned, can't unmap\n",
+			page_size, mmu_prop->page_size >> 10);
+
+		return -EFAULT;
+	}
+
+	WARN_ONCE((phys_addr & (real_page_size - 1)),
+		"Mapping 0x%llx with page size of 0x%x is erroneous! Address must be divisible by page size",
+		phys_addr, real_page_size);
+
+	npages = page_size / real_page_size;
+	real_virt_addr = virt_addr;
+	real_phys_addr = phys_addr;
+
+	for (i = 0 ; i < npages ; i++) {
+		rc = _hl_mmu_map(ctx, real_virt_addr, real_phys_addr,
+				real_page_size, is_dram_addr);
+		if (rc)
+			goto err;
+
+		real_virt_addr += real_page_size;
+		real_phys_addr += real_page_size;
+		mapped_cnt++;
+	}
+
+	if (flush_pte)
+		flush(ctx);
+
+	return 0;
+
+err:
+	real_virt_addr = virt_addr;
+	for (i = 0 ; i < mapped_cnt ; i++) {
+		if (_hl_mmu_unmap(ctx, real_virt_addr, is_dram_addr))
+			dev_warn_ratelimited(hdev->dev,
+				"failed to unmap va: 0x%llx\n", real_virt_addr);
+
+		real_virt_addr += real_page_size;
+	}
+
+	flush(ctx);
+
+	return rc;
+}
+
+/*
+ * hl_mmu_swap_out - marks all mapping of the given ctx as swapped out
+ *
+ * @ctx: pointer to the context structure
+ *
+ */
+void hl_mmu_swap_out(struct hl_ctx *ctx)
+{
+
+}
+
+/*
+ * hl_mmu_swap_in - marks all mapping of the given ctx as swapped in
+ *
+ * @ctx: pointer to the context structure
+ *
+ */
+void hl_mmu_swap_in(struct hl_ctx *ctx)
+{
+
+}
diff --git a/drivers/misc/habanalabs/common/pci.c b/drivers/misc/habanalabs/common/pci.c
new file mode 100644
index 000000000000..1791f6623c69
--- /dev/null
+++ b/drivers/misc/habanalabs/common/pci.c
@@ -0,0 +1,400 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2019 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include "habanalabs.h"
+#include "include/hw_ip/pci/pci_general.h"
+
+#include <linux/pci.h>
+#include <linux/bitfield.h>
+
+#define HL_PLDM_PCI_ELBI_TIMEOUT_MSEC	(HL_PCI_ELBI_TIMEOUT_MSEC * 10)
+
+#define IATU_REGION_CTRL_REGION_EN_MASK		BIT(31)
+#define IATU_REGION_CTRL_MATCH_MODE_MASK	BIT(30)
+#define IATU_REGION_CTRL_NUM_MATCH_EN_MASK	BIT(19)
+#define IATU_REGION_CTRL_BAR_NUM_MASK		GENMASK(10, 8)
+
+/**
+ * hl_pci_bars_map() - Map PCI BARs.
+ * @hdev: Pointer to hl_device structure.
+ * @name: Array of BAR names.
+ * @is_wc: Array with flag per BAR whether a write-combined mapping is needed.
+ *
+ * Request PCI regions and map them to kernel virtual addresses.
+ *
+ * Return: 0 on success, non-zero for failure.
+ */
+int hl_pci_bars_map(struct hl_device *hdev, const char * const name[3],
+			bool is_wc[3])
+{
+	struct pci_dev *pdev = hdev->pdev;
+	int rc, i, bar;
+
+	rc = pci_request_regions(pdev, HL_NAME);
+	if (rc) {
+		dev_err(hdev->dev, "Cannot obtain PCI resources\n");
+		return rc;
+	}
+
+	for (i = 0 ; i < 3 ; i++) {
+		bar = i * 2; /* 64-bit BARs */
+		hdev->pcie_bar[bar] = is_wc[i] ?
+				pci_ioremap_wc_bar(pdev, bar) :
+				pci_ioremap_bar(pdev, bar);
+		if (!hdev->pcie_bar[bar]) {
+			dev_err(hdev->dev, "pci_ioremap%s_bar failed for %s\n",
+					is_wc[i] ? "_wc" : "", name[i]);
+			rc = -ENODEV;
+			goto err;
+		}
+	}
+
+	return 0;
+
+err:
+	for (i = 2 ; i >= 0 ; i--) {
+		bar = i * 2; /* 64-bit BARs */
+		if (hdev->pcie_bar[bar])
+			iounmap(hdev->pcie_bar[bar]);
+	}
+
+	pci_release_regions(pdev);
+
+	return rc;
+}
+
+/**
+ * hl_pci_bars_unmap() - Unmap PCI BARS.
+ * @hdev: Pointer to hl_device structure.
+ *
+ * Release all PCI BARs and unmap their virtual addresses.
+ */
+static void hl_pci_bars_unmap(struct hl_device *hdev)
+{
+	struct pci_dev *pdev = hdev->pdev;
+	int i, bar;
+
+	for (i = 2 ; i >= 0 ; i--) {
+		bar = i * 2; /* 64-bit BARs */
+		iounmap(hdev->pcie_bar[bar]);
+	}
+
+	pci_release_regions(pdev);
+}
+
+/**
+ * hl_pci_elbi_write() - Write through the ELBI interface.
+ * @hdev: Pointer to hl_device structure.
+ * @addr: Address to write to
+ * @data: Data to write
+ *
+ * Return: 0 on success, negative value for failure.
+ */
+static int hl_pci_elbi_write(struct hl_device *hdev, u64 addr, u32 data)
+{
+	struct pci_dev *pdev = hdev->pdev;
+	ktime_t timeout;
+	u64 msec;
+	u32 val;
+
+	if (hdev->pldm)
+		msec = HL_PLDM_PCI_ELBI_TIMEOUT_MSEC;
+	else
+		msec = HL_PCI_ELBI_TIMEOUT_MSEC;
+
+	/* Clear previous status */
+	pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_STS, 0);
+
+	pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_ADDR, (u32) addr);
+	pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_DATA, data);
+	pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_CTRL,
+				PCI_CONFIG_ELBI_CTRL_WRITE);
+
+	timeout = ktime_add_ms(ktime_get(), msec);
+	for (;;) {
+		pci_read_config_dword(pdev, mmPCI_CONFIG_ELBI_STS, &val);
+		if (val & PCI_CONFIG_ELBI_STS_MASK)
+			break;
+		if (ktime_compare(ktime_get(), timeout) > 0) {
+			pci_read_config_dword(pdev, mmPCI_CONFIG_ELBI_STS,
+						&val);
+			break;
+		}
+
+		usleep_range(300, 500);
+	}
+
+	if ((val & PCI_CONFIG_ELBI_STS_MASK) == PCI_CONFIG_ELBI_STS_DONE)
+		return 0;
+
+	if (val & PCI_CONFIG_ELBI_STS_ERR) {
+		dev_err(hdev->dev, "Error writing to ELBI\n");
+		return -EIO;
+	}
+
+	if (!(val & PCI_CONFIG_ELBI_STS_MASK)) {
+		dev_err(hdev->dev, "ELBI write didn't finish in time\n");
+		return -EIO;
+	}
+
+	dev_err(hdev->dev, "ELBI write has undefined bits in status\n");
+	return -EIO;
+}
+
+/**
+ * hl_pci_iatu_write() - iatu write routine.
+ * @hdev: Pointer to hl_device structure.
+ * @addr: Address to write to
+ * @data: Data to write
+ *
+ * Return: 0 on success, negative value for failure.
+ */
+int hl_pci_iatu_write(struct hl_device *hdev, u32 addr, u32 data)
+{
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	u32 dbi_offset;
+	int rc;
+
+	dbi_offset = addr & 0xFFF;
+
+	rc = hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0x00300000);
+	rc |= hl_pci_elbi_write(hdev, prop->pcie_dbi_base_address + dbi_offset,
+				data);
+
+	if (rc)
+		return -EIO;
+
+	return 0;
+}
+
+/**
+ * hl_pci_reset_link_through_bridge() - Reset PCI link.
+ * @hdev: Pointer to hl_device structure.
+ */
+static void hl_pci_reset_link_through_bridge(struct hl_device *hdev)
+{
+	struct pci_dev *pdev = hdev->pdev;
+	struct pci_dev *parent_port;
+	u16 val;
+
+	parent_port = pdev->bus->self;
+	pci_read_config_word(parent_port, PCI_BRIDGE_CONTROL, &val);
+	val |= PCI_BRIDGE_CTL_BUS_RESET;
+	pci_write_config_word(parent_port, PCI_BRIDGE_CONTROL, val);
+	ssleep(1);
+
+	val &= ~(PCI_BRIDGE_CTL_BUS_RESET);
+	pci_write_config_word(parent_port, PCI_BRIDGE_CONTROL, val);
+	ssleep(3);
+}
+
+/**
+ * hl_pci_set_inbound_region() - Configure inbound region
+ * @hdev: Pointer to hl_device structure.
+ * @region: Inbound region number.
+ * @pci_region: Inbound region parameters.
+ *
+ * Configure the iATU inbound region.
+ *
+ * Return: 0 on success, negative value for failure.
+ */
+int hl_pci_set_inbound_region(struct hl_device *hdev, u8 region,
+		struct hl_inbound_pci_region *pci_region)
+{
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	u64 bar_phys_base, region_base, region_end_address;
+	u32 offset, ctrl_reg_val;
+	int rc = 0;
+
+	/* region offset */
+	offset = (0x200 * region) + 0x100;
+
+	if (pci_region->mode == PCI_ADDRESS_MATCH_MODE) {
+		bar_phys_base = hdev->pcie_bar_phys[pci_region->bar];
+		region_base = bar_phys_base + pci_region->offset_in_bar;
+		region_end_address = region_base + pci_region->size - 1;
+
+		rc |= hl_pci_iatu_write(hdev, offset + 0x8,
+				lower_32_bits(region_base));
+		rc |= hl_pci_iatu_write(hdev, offset + 0xC,
+				upper_32_bits(region_base));
+		rc |= hl_pci_iatu_write(hdev, offset + 0x10,
+				lower_32_bits(region_end_address));
+	}
+
+	/* Point to the specified address */
+	rc = hl_pci_iatu_write(hdev, offset + 0x14,
+			lower_32_bits(pci_region->addr));
+	rc |= hl_pci_iatu_write(hdev, offset + 0x18,
+			upper_32_bits(pci_region->addr));
+	rc |= hl_pci_iatu_write(hdev, offset + 0x0, 0);
+
+	/* Enable + bar/address match + match enable + bar number */
+	ctrl_reg_val = FIELD_PREP(IATU_REGION_CTRL_REGION_EN_MASK, 1);
+	ctrl_reg_val |= FIELD_PREP(IATU_REGION_CTRL_MATCH_MODE_MASK,
+			pci_region->mode);
+	ctrl_reg_val |= FIELD_PREP(IATU_REGION_CTRL_NUM_MATCH_EN_MASK, 1);
+
+	if (pci_region->mode == PCI_BAR_MATCH_MODE)
+		ctrl_reg_val |= FIELD_PREP(IATU_REGION_CTRL_BAR_NUM_MASK,
+				pci_region->bar);
+
+	rc |= hl_pci_iatu_write(hdev, offset + 0x4, ctrl_reg_val);
+
+	/* Return the DBI window to the default location */
+	rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0);
+	rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr + 4, 0);
+
+	if (rc)
+		dev_err(hdev->dev, "failed to map bar %u to 0x%08llx\n",
+				pci_region->bar, pci_region->addr);
+
+	return rc;
+}
+
+/**
+ * hl_pci_set_outbound_region() - Configure outbound region 0
+ * @hdev: Pointer to hl_device structure.
+ * @pci_region: Outbound region parameters.
+ *
+ * Configure the iATU outbound region 0.
+ *
+ * Return: 0 on success, negative value for failure.
+ */
+int hl_pci_set_outbound_region(struct hl_device *hdev,
+		struct hl_outbound_pci_region *pci_region)
+{
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	u64 outbound_region_end_address;
+	int rc = 0;
+
+	/* Outbound Region 0 */
+	outbound_region_end_address =
+			pci_region->addr + pci_region->size - 1;
+	rc |= hl_pci_iatu_write(hdev, 0x008,
+				lower_32_bits(pci_region->addr));
+	rc |= hl_pci_iatu_write(hdev, 0x00C,
+				upper_32_bits(pci_region->addr));
+	rc |= hl_pci_iatu_write(hdev, 0x010,
+				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, 0x020,
+				upper_32_bits(outbound_region_end_address));
+	/* Increase region size */
+	rc |= hl_pci_iatu_write(hdev, 0x000, 0x00002000);
+	/* Enable */
+	rc |= hl_pci_iatu_write(hdev, 0x004, 0x80000000);
+
+	/* Return the DBI window to the default location */
+	rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0);
+	rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr + 4, 0);
+
+	return rc;
+}
+
+/**
+ * hl_pci_set_dma_mask() - Set DMA masks for the device.
+ * @hdev: Pointer to hl_device structure.
+ *
+ * This function sets the DMA masks (regular and consistent) for a specified
+ * value. If it doesn't succeed, it tries to set it to a fall-back value
+ *
+ * Return: 0 on success, non-zero for failure.
+ */
+static int hl_pci_set_dma_mask(struct hl_device *hdev)
+{
+	struct pci_dev *pdev = hdev->pdev;
+	int rc;
+
+	/* set DMA mask */
+	rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(hdev->dma_mask));
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to set pci dma mask to %d bits, error %d\n",
+			hdev->dma_mask, rc);
+		return rc;
+	}
+
+	rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(hdev->dma_mask));
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to set pci consistent dma mask to %d bits, error %d\n",
+			hdev->dma_mask, rc);
+		return rc;
+	}
+
+	return 0;
+}
+
+/**
+ * hl_pci_init() - PCI initialization code.
+ * @hdev: Pointer to hl_device structure.
+ *
+ * Set DMA masks, initialize the PCI controller and map the PCI BARs.
+ *
+ * Return: 0 on success, non-zero for failure.
+ */
+int hl_pci_init(struct hl_device *hdev)
+{
+	struct pci_dev *pdev = hdev->pdev;
+	int rc;
+
+	if (hdev->reset_pcilink)
+		hl_pci_reset_link_through_bridge(hdev);
+
+	rc = pci_enable_device_mem(pdev);
+	if (rc) {
+		dev_err(hdev->dev, "can't enable PCI device\n");
+		return rc;
+	}
+
+	pci_set_master(pdev);
+
+	rc = hdev->asic_funcs->pci_bars_map(hdev);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to initialize PCI BARs\n");
+		goto disable_device;
+	}
+
+	rc = hdev->asic_funcs->init_iatu(hdev);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to initialize iATU\n");
+		goto disable_device;
+	}
+
+	rc = hl_pci_set_dma_mask(hdev);
+	if (rc)
+		goto disable_device;
+
+	return 0;
+
+disable_device:
+	pci_clear_master(pdev);
+	pci_disable_device(pdev);
+
+	return rc;
+}
+
+/**
+ * hl_fw_fini() - PCI finalization code.
+ * @hdev: Pointer to hl_device structure
+ *
+ * Unmap PCI bars and disable PCI device.
+ */
+void hl_pci_fini(struct hl_device *hdev)
+{
+	hl_pci_bars_unmap(hdev);
+
+	pci_clear_master(hdev->pdev);
+	pci_disable_device(hdev->pdev);
+}
diff --git a/drivers/misc/habanalabs/common/sysfs.c b/drivers/misc/habanalabs/common/sysfs.c
new file mode 100644
index 000000000000..5d78d5e1c782
--- /dev/null
+++ b/drivers/misc/habanalabs/common/sysfs.c
@@ -0,0 +1,442 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2019 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include "habanalabs.h"
+
+#include <linux/pci.h>
+
+#define SET_CLK_PKT_TIMEOUT	1000000	/* 1s */
+#define SET_PWR_PKT_TIMEOUT	1000000	/* 1s */
+
+long hl_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr)
+{
+	struct armcp_packet pkt;
+	long result;
+	int rc;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	if (curr)
+		pkt.ctl = cpu_to_le32(ARMCP_PACKET_FREQUENCY_CURR_GET <<
+						ARMCP_PKT_CTL_OPCODE_SHIFT);
+	else
+		pkt.ctl = cpu_to_le32(ARMCP_PACKET_FREQUENCY_GET <<
+						ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.pll_index = cpu_to_le32(pll_index);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+						SET_CLK_PKT_TIMEOUT, &result);
+
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to get frequency of PLL %d, error %d\n",
+			pll_index, rc);
+		result = rc;
+	}
+
+	return result;
+}
+
+void hl_set_frequency(struct hl_device *hdev, u32 pll_index, u64 freq)
+{
+	struct armcp_packet pkt;
+	int rc;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_FREQUENCY_SET <<
+					ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.pll_index = cpu_to_le32(pll_index);
+	pkt.value = cpu_to_le64(freq);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+					SET_CLK_PKT_TIMEOUT, NULL);
+
+	if (rc)
+		dev_err(hdev->dev,
+			"Failed to set frequency to PLL %d, error %d\n",
+			pll_index, rc);
+}
+
+u64 hl_get_max_power(struct hl_device *hdev)
+{
+	struct armcp_packet pkt;
+	long result;
+	int rc;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_MAX_POWER_GET <<
+				ARMCP_PKT_CTL_OPCODE_SHIFT);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+						SET_PWR_PKT_TIMEOUT, &result);
+
+	if (rc) {
+		dev_err(hdev->dev, "Failed to get max power, error %d\n", rc);
+		result = rc;
+	}
+
+	return result;
+}
+
+void hl_set_max_power(struct hl_device *hdev, u64 value)
+{
+	struct armcp_packet pkt;
+	int rc;
+
+	memset(&pkt, 0, sizeof(pkt));
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_MAX_POWER_SET <<
+				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.value = cpu_to_le64(value);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+					SET_PWR_PKT_TIMEOUT, NULL);
+
+	if (rc)
+		dev_err(hdev->dev, "Failed to set max power, error %d\n", rc);
+}
+
+static ssize_t uboot_ver_show(struct device *dev, struct device_attribute *attr,
+				char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%s\n", hdev->asic_prop.uboot_ver);
+}
+
+static ssize_t armcp_kernel_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.armcp_info.kernel_version);
+}
+
+static ssize_t armcp_ver_show(struct device *dev, struct device_attribute *attr,
+				char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%s\n", hdev->asic_prop.armcp_info.armcp_version);
+}
+
+static ssize_t cpld_ver_show(struct device *dev, struct device_attribute *attr,
+				char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+
+	return sprintf(buf, "0x%08x\n",
+			hdev->asic_prop.armcp_info.cpld_version);
+}
+
+static ssize_t infineon_ver_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+
+	return sprintf(buf, "0x%04x\n",
+			hdev->asic_prop.armcp_info.infineon_version);
+}
+
+static ssize_t fuse_ver_show(struct device *dev, struct device_attribute *attr,
+				char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%s\n", hdev->asic_prop.armcp_info.fuse_version);
+}
+
+static ssize_t thermal_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.armcp_info.thermal_version);
+}
+
+static ssize_t preboot_btl_ver_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%s\n", hdev->asic_prop.preboot_ver);
+}
+
+static ssize_t soft_reset_store(struct device *dev,
+				struct device_attribute *attr, const char *buf,
+				size_t count)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+	long value;
+	int rc;
+
+	rc = kstrtoul(buf, 0, &value);
+
+	if (rc) {
+		count = -EINVAL;
+		goto out;
+	}
+
+	if (!hdev->supports_soft_reset) {
+		dev_err(hdev->dev, "Device does not support soft-reset\n");
+		goto out;
+	}
+
+	dev_warn(hdev->dev, "Soft-Reset requested through sysfs\n");
+
+	hl_device_reset(hdev, false, false);
+
+out:
+	return count;
+}
+
+static ssize_t hard_reset_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+	long value;
+	int rc;
+
+	rc = kstrtoul(buf, 0, &value);
+
+	if (rc) {
+		count = -EINVAL;
+		goto out;
+	}
+
+	dev_warn(hdev->dev, "Hard-Reset requested through sysfs\n");
+
+	hl_device_reset(hdev, true, false);
+
+out:
+	return count;
+}
+
+static ssize_t device_type_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+	char *str;
+
+	switch (hdev->asic_type) {
+	case ASIC_GOYA:
+		str = "GOYA";
+		break;
+	case ASIC_GAUDI:
+		str = "GAUDI";
+		break;
+	default:
+		dev_err(hdev->dev, "Unrecognized ASIC type %d\n",
+				hdev->asic_type);
+		return -EINVAL;
+	}
+
+	return sprintf(buf, "%s\n", str);
+}
+
+static ssize_t pci_addr_show(struct device *dev, struct device_attribute *attr,
+				char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%04x:%02x:%02x.%x\n",
+			pci_domain_nr(hdev->pdev->bus),
+			hdev->pdev->bus->number,
+			PCI_SLOT(hdev->pdev->devfn),
+			PCI_FUNC(hdev->pdev->devfn));
+}
+
+static ssize_t status_show(struct device *dev, struct device_attribute *attr,
+				char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+	char *str;
+
+	if (atomic_read(&hdev->in_reset))
+		str = "In reset";
+	else if (hdev->disabled)
+		str = "Malfunction";
+	else
+		str = "Operational";
+
+	return sprintf(buf, "%s\n", str);
+}
+
+static ssize_t soft_reset_cnt_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d\n", hdev->soft_reset_cnt);
+}
+
+static ssize_t hard_reset_cnt_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d\n", hdev->hard_reset_cnt);
+}
+
+static ssize_t max_power_show(struct device *dev, struct device_attribute *attr,
+				char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+	long val;
+
+	if (hl_device_disabled_or_in_reset(hdev))
+		return -ENODEV;
+
+	val = hl_get_max_power(hdev);
+
+	return sprintf(buf, "%lu\n", val);
+}
+
+static ssize_t max_power_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+	unsigned long value;
+	int rc;
+
+	if (hl_device_disabled_or_in_reset(hdev)) {
+		count = -ENODEV;
+		goto out;
+	}
+
+	rc = kstrtoul(buf, 0, &value);
+
+	if (rc) {
+		count = -EINVAL;
+		goto out;
+	}
+
+	hdev->max_power = value;
+	hl_set_max_power(hdev, value);
+
+out:
+	return count;
+}
+
+static ssize_t eeprom_read_handler(struct file *filp, struct kobject *kobj,
+			struct bin_attribute *attr, char *buf, loff_t offset,
+			size_t max_size)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct hl_device *hdev = dev_get_drvdata(dev);
+	char *data;
+	int rc;
+
+	if (!max_size)
+		return -EINVAL;
+
+	data = kzalloc(max_size, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	rc = hdev->asic_funcs->get_eeprom_data(hdev, data, max_size);
+	if (rc)
+		goto out;
+
+	memcpy(buf, data, max_size);
+
+out:
+	kfree(data);
+
+	return max_size;
+}
+
+static DEVICE_ATTR_RO(armcp_kernel_ver);
+static DEVICE_ATTR_RO(armcp_ver);
+static DEVICE_ATTR_RO(cpld_ver);
+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);
+static DEVICE_ATTR_WO(soft_reset);
+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 struct bin_attribute bin_attr_eeprom = {
+	.attr = {.name = "eeprom", .mode = (0444)},
+	.size = PAGE_SIZE,
+	.read = eeprom_read_handler
+};
+
+static struct attribute *hl_dev_attrs[] = {
+	&dev_attr_armcp_kernel_ver.attr,
+	&dev_attr_armcp_ver.attr,
+	&dev_attr_cpld_ver.attr,
+	&dev_attr_device_type.attr,
+	&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_soft_reset.attr,
+	&dev_attr_soft_reset_cnt.attr,
+	&dev_attr_status.attr,
+	&dev_attr_thermal_ver.attr,
+	&dev_attr_uboot_ver.attr,
+	NULL,
+};
+
+static struct bin_attribute *hl_dev_bin_attrs[] = {
+	&bin_attr_eeprom,
+	NULL
+};
+
+static struct attribute_group hl_dev_attr_group = {
+	.attrs = hl_dev_attrs,
+	.bin_attrs = hl_dev_bin_attrs,
+};
+
+static struct attribute_group hl_dev_clks_attr_group;
+
+static const struct attribute_group *hl_dev_attr_groups[] = {
+	&hl_dev_attr_group,
+	&hl_dev_clks_attr_group,
+	NULL,
+};
+
+int hl_sysfs_init(struct hl_device *hdev)
+{
+	int rc;
+
+	if (hdev->asic_type == ASIC_GOYA)
+		hdev->pm_mng_profile = PM_AUTO;
+	else
+		hdev->pm_mng_profile = PM_MANUAL;
+	hdev->max_power = hdev->asic_prop.max_power_default;
+
+	hdev->asic_funcs->add_device_attr(hdev, &hl_dev_clks_attr_group);
+
+	rc = device_add_groups(hdev->dev, hl_dev_attr_groups);
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to add groups to device, error %d\n", rc);
+		return rc;
+	}
+
+	return 0;
+}
+
+void hl_sysfs_fini(struct hl_device *hdev)
+{
+	device_remove_groups(hdev->dev, hl_dev_attr_groups);
+}