habanalabs: separate common code to dedicated folders

We separate some of the common code source files to different
folders for a better maintainability and testability.

Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>

3 files changed, 1528 insertions, 0 deletions

diff --git a/drivers/misc/habanalabs/common/mmu/Makefile b/drivers/misc/habanalabs/common/mmu/Makefile
new file mode 100644
index 000000000000..d852c3874658
--- /dev/null
+++ b/drivers/misc/habanalabs/common/mmu/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+HL_COMMON_MMU_FILES := common/mmu/mmu.o common/mmu/mmu_v1.o
diff --git a/drivers/misc/habanalabs/common/mmu/mmu.c b/drivers/misc/habanalabs/common/mmu/mmu.c
new file mode 100644
index 000000000000..97c51686fcfe
--- /dev/null
+++ b/drivers/misc/habanalabs/common/mmu/mmu.c
@@ -0,0 +1,560 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2016-2020 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include <linux/slab.h>
+
+#include "../habanalabs.h"
+
+bool hl_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);
+}
+
+/**
+ * hl_mmu_init() - initialize the MMU module.
+ * @hdev: habanalabs device structure.
+ *
+ * Return: 0 for success, non-zero for failure.
+ */
+int hl_mmu_init(struct hl_device *hdev)
+{
+	int rc = -EOPNOTSUPP;
+
+	if (!hdev->mmu_enable)
+		return 0;
+
+	if (hdev->mmu_func[MMU_DR_PGT].init != NULL) {
+		rc = hdev->mmu_func[MMU_DR_PGT].init(hdev);
+		if (rc)
+			return rc;
+	}
+
+	if (hdev->mmu_func[MMU_HR_PGT].init != NULL)
+		rc = hdev->mmu_func[MMU_HR_PGT].init(hdev);
+
+	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;
+
+	if (hdev->mmu_func[MMU_DR_PGT].fini != NULL)
+		hdev->mmu_func[MMU_DR_PGT].fini(hdev);
+
+	if (hdev->mmu_func[MMU_HR_PGT].fini != NULL)
+		hdev->mmu_func[MMU_HR_PGT].fini(hdev);
+}
+
+/**
+ * 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;
+	int rc = -EOPNOTSUPP;
+
+	if (!hdev->mmu_enable)
+		return 0;
+
+	mutex_init(&ctx->mmu_lock);
+
+	if (hdev->mmu_func[MMU_DR_PGT].ctx_init != NULL) {
+		rc = hdev->mmu_func[MMU_DR_PGT].ctx_init(ctx);
+		if (rc)
+			return rc;
+	}
+
+	if (hdev->mmu_func[MMU_HR_PGT].ctx_init != NULL)
+		rc = hdev->mmu_func[MMU_HR_PGT].ctx_init(ctx);
+
+	return rc;
+}
+
+/*
+ * 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;
+
+	if (!hdev->mmu_enable)
+		return;
+
+	if (hdev->mmu_func[MMU_DR_PGT].ctx_fini != NULL)
+		hdev->mmu_func[MMU_DR_PGT].ctx_fini(ctx);
+
+	if (hdev->mmu_func[MMU_HR_PGT].ctx_fini != NULL)
+		hdev->mmu_func[MMU_HR_PGT].ctx_fini(ctx);
+
+	mutex_destroy(&ctx->mmu_lock);
+}
+
+/*
+ * hl_mmu_unmap_page - 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_page(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, pgt_residency;
+	bool is_dram_addr;
+
+	if (!hdev->mmu_enable)
+		return 0;
+
+	is_dram_addr = hl_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;
+
+	pgt_residency = mmu_prop->host_resident ? MMU_HR_PGT : MMU_DR_PGT;
+	/*
+	 * 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 {
+		/*
+		 * MMU page size may differ from DRAM page size.
+		 * In such case work with the DRAM page size and let the MMU
+		 * scrambling routine to handle this mismatch when
+		 * calculating the address to remove from the MMU page table
+		 */
+		if (is_dram_addr && ((page_size % prop->dram_page_size) == 0)) {
+			real_page_size = prop->dram_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 = hdev->mmu_func[pgt_residency].unmap(ctx,
+						real_virt_addr, is_dram_addr);
+		if (rc)
+			break;
+
+		real_virt_addr += real_page_size;
+	}
+
+	if (flush_pte)
+		hdev->mmu_func[pgt_residency].flush(ctx);
+
+	return rc;
+}
+
+/*
+ * hl_mmu_map_page - 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_page(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, pgt_residency, mapped_cnt = 0;
+	bool is_dram_addr;
+
+
+	if (!hdev->mmu_enable)
+		return 0;
+
+	is_dram_addr = hl_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;
+
+	pgt_residency = mmu_prop->host_resident ? MMU_HR_PGT : MMU_DR_PGT;
+
+	/*
+	 * 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 if (is_dram_addr && ((page_size % prop->dram_page_size) == 0) &&
+			(prop->dram_page_size < mmu_prop->page_size)) {
+		/*
+		 * MMU page size may differ from DRAM page size.
+		 * In such case work with the DRAM page size and let the MMU
+		 * scrambling routine handle this mismatch when calculating
+		 * the address to place in the MMU page table. (in that case
+		 * also make sure that the dram_page_size smaller than the
+		 * mmu page size)
+		 */
+		real_page_size = prop->dram_page_size;
+	} else {
+		dev_err(hdev->dev,
+			"page size of %u is not %uKB aligned, can't map\n",
+			page_size, mmu_prop->page_size >> 10);
+
+		return -EFAULT;
+	}
+
+	/*
+	 * Verify that the phys and virt addresses are aligned with the
+	 * MMU page size (in dram this means checking the address and MMU
+	 * after scrambling)
+	 */
+	if ((is_dram_addr &&
+			((hdev->asic_funcs->scramble_vaddr(hdev, phys_addr) &
+				(mmu_prop->page_size - 1)) ||
+			(hdev->asic_funcs->scramble_vaddr(hdev, virt_addr) &
+				(mmu_prop->page_size - 1)))) ||
+		(!is_dram_addr && ((phys_addr & (real_page_size - 1)) ||
+				(virt_addr & (real_page_size - 1)))))
+		dev_crit(hdev->dev,
+			"Mapping address 0x%llx with virtual address 0x%llx and page size of 0x%x is erroneous! Addresses must be divisible by page size",
+			phys_addr, virt_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 = hdev->mmu_func[pgt_residency].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)
+		hdev->mmu_func[pgt_residency].flush(ctx);
+
+	return 0;
+
+err:
+	real_virt_addr = virt_addr;
+	for (i = 0 ; i < mapped_cnt ; i++) {
+		if (hdev->mmu_func[pgt_residency].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;
+	}
+
+	hdev->mmu_func[pgt_residency].flush(ctx);
+
+	return rc;
+}
+
+/*
+ * hl_mmu_map_contiguous - implements a wrapper for hl_mmu_map_page
+ *                         for mapping contiguous physical memory
+ *
+ * @ctx: pointer to the context structure
+ * @virt_addr: virt addr to map from
+ * @phys_addr: phys addr to map to
+ * @size: size to map
+ *
+ */
+int hl_mmu_map_contiguous(struct hl_ctx *ctx, u64 virt_addr,
+					u64 phys_addr, u32 size)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	u64 curr_va, curr_pa;
+	u32 page_size;
+	bool flush_pte;
+	int rc = 0, off;
+
+	if (hl_mem_area_inside_range(virt_addr, size,
+			prop->dmmu.start_addr, prop->dmmu.end_addr))
+		page_size = prop->dmmu.page_size;
+	else if (hl_mem_area_inside_range(virt_addr, size,
+			prop->pmmu.start_addr, prop->pmmu.end_addr))
+		page_size = prop->pmmu.page_size;
+	else if (hl_mem_area_inside_range(virt_addr, size,
+			prop->pmmu_huge.start_addr, prop->pmmu_huge.end_addr))
+		page_size = prop->pmmu_huge.page_size;
+	else
+		return -EINVAL;
+
+	for (off = 0 ; off < size ; off += page_size) {
+		curr_va = virt_addr + off;
+		curr_pa = phys_addr + off;
+		flush_pte = (off + page_size) >= size;
+		rc = hl_mmu_map_page(ctx, curr_va, curr_pa, page_size,
+								flush_pte);
+		if (rc) {
+			dev_err(hdev->dev,
+				"Map failed for va 0x%llx to pa 0x%llx\n",
+				curr_va, curr_pa);
+			goto unmap;
+		}
+	}
+
+	return rc;
+
+unmap:
+	for (; off >= 0 ; off -= page_size) {
+		curr_va = virt_addr + off;
+		flush_pte = (off - (s32) page_size) < 0;
+		if (hl_mmu_unmap_page(ctx, curr_va, page_size, flush_pte))
+			dev_warn_ratelimited(hdev->dev,
+				"failed to unmap va 0x%llx\n", curr_va);
+	}
+
+	return rc;
+}
+
+/*
+ * hl_mmu_unmap_contiguous - implements a wrapper for hl_mmu_unmap_page
+ *                           for unmapping contiguous physical memory
+ *
+ * @ctx: pointer to the context structure
+ * @virt_addr: virt addr to unmap
+ * @size: size to unmap
+ *
+ */
+int hl_mmu_unmap_contiguous(struct hl_ctx *ctx, u64 virt_addr, u32 size)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	u64 curr_va;
+	u32 page_size;
+	bool flush_pte;
+	int rc = 0, off;
+
+	if (hl_mem_area_inside_range(virt_addr, size,
+			prop->dmmu.start_addr, prop->dmmu.end_addr))
+		page_size = prop->dmmu.page_size;
+	else if (hl_mem_area_inside_range(virt_addr, size,
+			prop->pmmu.start_addr, prop->pmmu.end_addr))
+		page_size = prop->pmmu.page_size;
+	else if (hl_mem_area_inside_range(virt_addr, size,
+			prop->pmmu_huge.start_addr, prop->pmmu_huge.end_addr))
+		page_size = prop->pmmu_huge.page_size;
+	else
+		return -EINVAL;
+
+	for (off = 0 ; off < size ; off += page_size) {
+		curr_va = virt_addr + off;
+		flush_pte = (off + page_size) >= size;
+		rc = hl_mmu_unmap_page(ctx, curr_va, page_size, flush_pte);
+		if (rc)
+			dev_warn_ratelimited(hdev->dev,
+				"Unmap failed for va 0x%llx\n", curr_va);
+	}
+
+	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)
+{
+	struct hl_device *hdev = ctx->hdev;
+
+	if (!hdev->mmu_enable)
+		return;
+
+	if (hdev->mmu_func[MMU_DR_PGT].swap_out != NULL)
+		hdev->mmu_func[MMU_DR_PGT].swap_out(ctx);
+
+	if (hdev->mmu_func[MMU_HR_PGT].swap_out != NULL)
+		hdev->mmu_func[MMU_HR_PGT].swap_out(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)
+{
+	struct hl_device *hdev = ctx->hdev;
+
+	if (!hdev->mmu_enable)
+		return;
+
+	if (hdev->mmu_func[MMU_DR_PGT].swap_in != NULL)
+		hdev->mmu_func[MMU_DR_PGT].swap_in(ctx);
+
+	if (hdev->mmu_func[MMU_HR_PGT].swap_in != NULL)
+		hdev->mmu_func[MMU_HR_PGT].swap_in(ctx);
+}
+
+int hl_mmu_va_to_pa(struct hl_ctx *ctx, u64 virt_addr, u64 *phys_addr)
+{
+	struct hl_mmu_hop_info hops;
+	u64 tmp_addr;
+	int rc;
+
+	rc = hl_mmu_get_tlb_info(ctx, virt_addr, &hops);
+	if (rc)
+		return rc;
+
+	/* last hop holds the phys address and flags */
+	tmp_addr = hops.hop_info[hops.used_hops - 1].hop_pte_val;
+	*phys_addr = (tmp_addr & HOP_PHYS_ADDR_MASK) | (virt_addr & FLAGS_MASK);
+
+	return 0;
+}
+
+int hl_mmu_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr,
+			struct hl_mmu_hop_info *hops)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct hl_mmu_properties *mmu_prop;
+	int rc;
+	bool is_dram_addr;
+
+	if (!hdev->mmu_enable)
+		return -EOPNOTSUPP;
+
+	hops->scrambled_vaddr = virt_addr;      /* assume no scrambling */
+
+	is_dram_addr = hl_mem_area_inside_range(virt_addr, prop->dmmu.page_size,
+						prop->dmmu.start_addr,
+						prop->dmmu.end_addr);
+
+	/* host-residency is the same in PMMU and HPMMU, use one of them */
+	mmu_prop = is_dram_addr ? &prop->dmmu : &prop->pmmu;
+
+	mutex_lock(&ctx->mmu_lock);
+
+	if (mmu_prop->host_resident)
+		rc = hdev->mmu_func[MMU_HR_PGT].get_tlb_info(ctx,
+							virt_addr, hops);
+	else
+		rc = hdev->mmu_func[MMU_DR_PGT].get_tlb_info(ctx,
+							virt_addr, hops);
+
+	mutex_unlock(&ctx->mmu_lock);
+
+	return rc;
+}
+
+int hl_mmu_if_set_funcs(struct hl_device *hdev)
+{
+	if (!hdev->mmu_enable)
+		return 0;
+
+	switch (hdev->asic_type) {
+	case ASIC_GOYA:
+	case ASIC_GAUDI:
+		hl_mmu_v1_set_funcs(hdev, &hdev->mmu_func[MMU_DR_PGT]);
+		break;
+	default:
+		dev_err(hdev->dev, "Unrecognized ASIC type %d\n",
+			hdev->asic_type);
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+/**
+ * hl_mmu_scramble_vaddr() - The generic mmu virtual address scrambling routine.
+ * @hdev: pointer to device data.
+ * @virt_addr: The virtual address to scramble.
+ *
+ * Return: The scrambled virtual address.
+ */
+u64 hl_mmu_scramble_vaddr(struct hl_device *hdev, u64 virt_addr)
+{
+	return virt_addr;
+}
diff --git a/drivers/misc/habanalabs/common/mmu/mmu_v1.c b/drivers/misc/habanalabs/common/mmu/mmu_v1.c
new file mode 100644
index 000000000000..c5e93ff32586
--- /dev/null
+++ b/drivers/misc/habanalabs/common/mmu/mmu_v1.c
@@ -0,0 +1,966 @@
+// 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/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_priv.dr.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_priv.dr.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_priv.dr.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_priv.dr.mmu_shadow_hop0 +
+			(ctx->asid * ctx->hdev->asic_prop.mmu_hop_table_size);
+}
+
+static 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 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 ((!prop->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 ((!prop->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_v1_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.
+ */
+static int hl_mmu_v1_init(struct hl_device *hdev)
+{
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	int rc;
+
+	hdev->mmu_priv.dr.mmu_pgt_pool =
+			gen_pool_create(__ffs(prop->mmu_hop_table_size), -1);
+
+	if (!hdev->mmu_priv.dr.mmu_pgt_pool) {
+		dev_err(hdev->dev, "Failed to create page gen pool\n");
+		return -ENOMEM;
+	}
+
+	rc = gen_pool_add(hdev->mmu_priv.dr.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_priv.dr.mmu_shadow_hop0 = kvmalloc_array(prop->max_asid,
+						prop->mmu_hop_table_size,
+						GFP_KERNEL | __GFP_ZERO);
+	if (ZERO_OR_NULL_PTR(hdev->mmu_priv.dr.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_priv.dr.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.
+ */
+static void hl_mmu_v1_fini(struct hl_device *hdev)
+{
+	/* MMU H/W fini was already done in device hw_fini() */
+
+	if (!ZERO_OR_NULL_PTR(hdev->mmu_priv.hr.mmu_shadow_hop0)) {
+		kvfree(hdev->mmu_priv.dr.mmu_shadow_hop0);
+		gen_pool_destroy(hdev->mmu_priv.dr.mmu_pgt_pool);
+	}
+
+	/* Make sure that if we arrive here again without init was called we
+	 * won't cause kernel panic. This can happen for example if we fail
+	 * during hard reset code at certain points
+	 */
+	hdev->mmu_priv.dr.mmu_shadow_hop0 = NULL;
+}
+
+/**
+ * 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.
+ */
+static int hl_mmu_v1_ctx_init(struct hl_ctx *ctx)
+{
+	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
+ */
+static void hl_mmu_v1_ctx_fini(struct hl_ctx *ctx)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct pgt_info *pgt_info;
+	struct hlist_node *tmp;
+	int i;
+
+	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);
+	}
+}
+
+static int _hl_mmu_v1_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;
+}
+
+static int _hl_mmu_v1_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_v1_swap_out - marks all mapping of the given ctx as swapped out
+ *
+ * @ctx: pointer to the context structure
+ *
+ */
+static void hl_mmu_v1_swap_out(struct hl_ctx *ctx)
+{
+
+}
+
+/*
+ * hl_mmu_v1_swap_in - marks all mapping of the given ctx as swapped in
+ *
+ * @ctx: pointer to the context structure
+ *
+ */
+static void hl_mmu_v1_swap_in(struct hl_ctx *ctx)
+{
+
+}
+
+static inline u64 get_hop_pte_addr(struct hl_ctx *ctx,
+				struct hl_mmu_properties *mmu_prop,
+				int hop_num, u64 hop_addr, u64 virt_addr)
+{
+	switch (hop_num) {
+	case 0:
+		return get_hop0_pte_addr(ctx, mmu_prop, hop_addr, virt_addr);
+	case 1:
+		return get_hop1_pte_addr(ctx, mmu_prop, hop_addr, virt_addr);
+	case 2:
+		return get_hop2_pte_addr(ctx, mmu_prop, hop_addr, virt_addr);
+	case 3:
+		return get_hop3_pte_addr(ctx, mmu_prop, hop_addr, virt_addr);
+	case 4:
+		return get_hop4_pte_addr(ctx, mmu_prop, hop_addr, virt_addr);
+	default:
+		break;
+	}
+	return U64_MAX;
+}
+
+static int hl_mmu_v1_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr,
+				struct hl_mmu_hop_info *hops)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct hl_mmu_properties *mmu_prop;
+	bool is_dram_addr, is_pmmu_addr, is_pmmu_h_addr, is_huge;
+	int i, used_hops;
+
+	is_dram_addr = hl_mem_area_inside_range(virt_addr, prop->dmmu.page_size,
+						prop->dmmu.start_addr,
+						prop->dmmu.end_addr);
+	is_pmmu_addr = hl_mem_area_inside_range(virt_addr, prop->pmmu.page_size,
+						prop->pmmu.start_addr,
+						prop->pmmu.end_addr);
+	is_pmmu_h_addr = hl_mem_area_inside_range(virt_addr,
+						prop->pmmu_huge.page_size,
+						prop->pmmu_huge.start_addr,
+						prop->pmmu_huge.end_addr);
+	if (is_dram_addr) {
+		mmu_prop = &prop->dmmu;
+		is_huge = true;
+	} else if (is_pmmu_addr) {
+		mmu_prop = &prop->pmmu;
+		is_huge = false;
+	} else if (is_pmmu_h_addr) {
+		mmu_prop = &prop->pmmu_huge;
+		is_huge = true;
+	} else {
+		return -EINVAL;
+	}
+
+	used_hops = mmu_prop->num_hops;
+
+	/* huge pages use lesser hops */
+	if (is_huge)
+		used_hops--;
+
+	hops->hop_info[0].hop_addr = get_phys_hop0_addr(ctx);
+	hops->hop_info[0].hop_pte_addr =
+			get_hop_pte_addr(ctx, mmu_prop, 0,
+					hops->hop_info[0].hop_addr, virt_addr);
+	hops->hop_info[0].hop_pte_val =
+			hdev->asic_funcs->read_pte(hdev,
+						hops->hop_info[0].hop_pte_addr);
+
+	for (i = 1 ; i < used_hops ; i++) {
+		hops->hop_info[i].hop_addr =
+			get_next_hop_addr(ctx,
+					hops->hop_info[i - 1].hop_pte_val);
+		if (hops->hop_info[i].hop_addr == ULLONG_MAX)
+			return -EFAULT;
+
+		hops->hop_info[i].hop_pte_addr =
+				get_hop_pte_addr(ctx, mmu_prop, i,
+						hops->hop_info[i].hop_addr,
+						virt_addr);
+		hops->hop_info[i].hop_pte_val =
+				hdev->asic_funcs->read_pte(hdev,
+						hops->hop_info[i].hop_pte_addr);
+
+		if (!(hops->hop_info[i].hop_pte_val & PAGE_PRESENT_MASK))
+			return -EFAULT;
+
+		if (hops->hop_info[i].hop_pte_val & LAST_MASK)
+			break;
+	}
+
+	/* if passed over all hops then no last hop was found */
+	if (i == mmu_prop->num_hops)
+		return -EFAULT;
+
+	if (!(hops->hop_info[i].hop_pte_val & PAGE_PRESENT_MASK))
+		return -EFAULT;
+
+	hops->used_hops = i + 1;
+
+	return 0;
+}
+
+/*
+ * hl_mmu_v1_prepare - prepare mmu  for working with mmu v1
+ *
+ * @hdev: pointer to the device structure
+ */
+void hl_mmu_v1_set_funcs(struct hl_device *hdev, struct hl_mmu_funcs *mmu)
+{
+	mmu->init = hl_mmu_v1_init;
+	mmu->fini = hl_mmu_v1_fini;
+	mmu->ctx_init = hl_mmu_v1_ctx_init;
+	mmu->ctx_fini = hl_mmu_v1_ctx_fini;
+	mmu->map = _hl_mmu_v1_map;
+	mmu->unmap = _hl_mmu_v1_unmap;
+	mmu->flush = flush;
+	mmu->swap_out = hl_mmu_v1_swap_out;
+	mmu->swap_in = hl_mmu_v1_swap_in;
+	mmu->get_tlb_info = hl_mmu_v1_get_tlb_info;
+}