accel/ivpu: Add Intel VPU MMU support

VPU Memory Management Unit is based on ARM MMU-600.
It allows the creation of multiple virtual address spaces for
the device and map noncontinuous host memory (there is no dedicated
memory on the VPU).

Address space is implemented as a struct ivpu_mmu_context, it has an ID,
drm_mm allocator for VPU addresses and struct ivpu_mmu_pgtable that
holds actual 3-level, 4KB page table.
Context with ID 0 (global context) is created upon driver initialization
and it's mainly used for mapping memory required to execute
the firmware.
Contexts with non-zero IDs are user contexts allocated each time
the devices is open()-ed and they map command buffers and other
workload-related memory.
Workloads executing in a given contexts have access only
to the memory mapped in this context.

This patch is has two main files:
  - ivpu_mmu_context.c handles MMU page tables and memory mapping
  - ivpu_mmu.c implements a driver that programs the MMU device

Co-developed-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Signed-off-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Co-developed-by: Krystian Pradzynski <krystian.pradzynski@linux.intel.com>
Signed-off-by: Krystian Pradzynski <krystian.pradzynski@linux.intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20230117092723.60441-3-jacek.lawrynowicz@linux.intel.com

9 files changed, 1479 insertions, 3 deletions

diff --git a/drivers/accel/ivpu/Makefile b/drivers/accel/ivpu/Makefile
index 2cc8394101cd..59cd7843b218 100644
--- a/drivers/accel/ivpu/Makefile
+++ b/drivers/accel/ivpu/Makefile
@@ -3,6 +3,8 @@
 
 intel_vpu-y := \
 	ivpu_drv.o \
-	ivpu_hw_mtl.o
+	ivpu_hw_mtl.o \
+	ivpu_mmu.o \
+	ivpu_mmu_context.o
 
 obj-$(CONFIG_DRM_ACCEL_IVPU) += intel_vpu.o
\ No newline at end of file
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 1134fb0028ad..69ca7dae8b57 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -15,6 +15,8 @@
 
 #include "ivpu_drv.h"
 #include "ivpu_hw.h"
+#include "ivpu_mmu.h"
+#include "ivpu_mmu_context.h"
 
 #ifndef DRIVER_VERSION_STR
 #define DRIVER_VERSION_STR __stringify(DRM_IVPU_DRIVER_MAJOR) "." \
@@ -37,23 +39,38 @@ MODULE_PARM_DESC(pll_max_ratio, "Maximum PLL ratio used to set VPU frequency");
 
 struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv)
 {
+	struct ivpu_device *vdev = file_priv->vdev;
+
 	kref_get(&file_priv->ref);
+
+	ivpu_dbg(vdev, KREF, "file_priv get: ctx %u refcount %u\n",
+		 file_priv->ctx.id, kref_read(&file_priv->ref));
+
 	return file_priv;
 }
 
 static void file_priv_release(struct kref *ref)
 {
 	struct ivpu_file_priv *file_priv = container_of(ref, struct ivpu_file_priv, ref);
+	struct ivpu_device *vdev = file_priv->vdev;
 
+	ivpu_dbg(vdev, FILE, "file_priv release: ctx %u\n", file_priv->ctx.id);
+
+	ivpu_mmu_user_context_fini(vdev, &file_priv->ctx);
+	WARN_ON(xa_erase_irq(&vdev->context_xa, file_priv->ctx.id) != file_priv);
 	kfree(file_priv);
 }
 
 void ivpu_file_priv_put(struct ivpu_file_priv **link)
 {
 	struct ivpu_file_priv *file_priv = *link;
+	struct ivpu_device *vdev = file_priv->vdev;
 
 	WARN_ON(!file_priv);
 
+	ivpu_dbg(vdev, KREF, "file_priv put: ctx %u refcount %u\n",
+		 file_priv->ctx.id, kref_read(&file_priv->ref));
+
 	*link = NULL;
 	kref_put(&file_priv->ref, file_priv_release);
 }
@@ -88,6 +105,9 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f
 	case DRM_IVPU_PARAM_CONTEXT_PRIORITY:
 		args->value = file_priv->priority;
 		break;
+	case DRM_IVPU_PARAM_CONTEXT_ID:
+		args->value = file_priv->ctx.id;
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -120,22 +140,59 @@ static int ivpu_open(struct drm_device *dev, struct drm_file *file)
 {
 	struct ivpu_device *vdev = to_ivpu_device(dev);
 	struct ivpu_file_priv *file_priv;
+	u32 ctx_id;
+	void *old;
+	int ret;
+
+	ret = xa_alloc_irq(&vdev->context_xa, &ctx_id, NULL, vdev->context_xa_limit, GFP_KERNEL);
+	if (ret) {
+		ivpu_err(vdev, "Failed to allocate context id: %d\n", ret);
+		return ret;
+	}
 
 	file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL);
-	if (!file_priv)
-		return -ENOMEM;
+	if (!file_priv) {
+		ret = -ENOMEM;
+		goto err_xa_erase;
+	}
 
 	file_priv->vdev = vdev;
 	file_priv->priority = DRM_IVPU_CONTEXT_PRIORITY_NORMAL;
 	kref_init(&file_priv->ref);
 
+	ret = ivpu_mmu_user_context_init(vdev, &file_priv->ctx, ctx_id);
+	if (ret)
+		goto err_free_file_priv;
+
+	old = xa_store_irq(&vdev->context_xa, ctx_id, file_priv, GFP_KERNEL);
+	if (xa_is_err(old)) {
+		ret = xa_err(old);
+		ivpu_err(vdev, "Failed to store context %u: %d\n", ctx_id, ret);
+		goto err_ctx_fini;
+	}
+
+	ivpu_dbg(vdev, FILE, "file_priv create: ctx %u process %s pid %d\n",
+		 ctx_id, current->comm, task_pid_nr(current));
+
 	file->driver_priv = file_priv;
 	return 0;
+
+err_ctx_fini:
+	ivpu_mmu_user_context_fini(vdev, &file_priv->ctx);
+err_free_file_priv:
+	kfree(file_priv);
+err_xa_erase:
+	xa_erase_irq(&vdev->context_xa, ctx_id);
+	return ret;
 }
 
 static void ivpu_postclose(struct drm_device *dev, struct drm_file *file)
 {
 	struct ivpu_file_priv *file_priv = file->driver_priv;
+	struct ivpu_device *vdev = to_ivpu_device(dev);
+
+	ivpu_dbg(vdev, FILE, "file_priv close: ctx %u process %s pid %d\n",
+		 file_priv->ctx.id, current->comm, task_pid_nr(current));
 
 	ivpu_file_priv_put(&file_priv);
 }
@@ -150,6 +207,7 @@ int ivpu_shutdown(struct ivpu_device *vdev)
 	int ret;
 
 	ivpu_hw_irq_disable(vdev);
+	ivpu_mmu_disable(vdev);
 
 	ret = ivpu_hw_power_down(vdev);
 	if (ret)
@@ -251,6 +309,10 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 	if (!vdev->hw)
 		return -ENOMEM;
 
+	vdev->mmu = drmm_kzalloc(&vdev->drm, sizeof(*vdev->mmu), GFP_KERNEL);
+	if (!vdev->mmu)
+		return -ENOMEM;
+
 	vdev->hw->ops = &ivpu_hw_mtl_ops;
 	vdev->platform = IVPU_PLATFORM_INVALID;
 	vdev->context_xa_limit.min = IVPU_GLOBAL_CONTEXT_MMU_SSID + 1;
@@ -283,8 +345,24 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 		goto err_xa_destroy;
 	}
 
+	ret = ivpu_mmu_global_context_init(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to initialize global MMU context: %d\n", ret);
+		goto err_power_down;
+	}
+
+	ret = ivpu_mmu_init(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to initialize MMU device: %d\n", ret);
+		goto err_mmu_gctx_fini;
+	}
+
 	return 0;
 
+err_mmu_gctx_fini:
+	ivpu_mmu_global_context_fini(vdev);
+err_power_down:
+	ivpu_hw_power_down(vdev);
 err_xa_destroy:
 	xa_destroy(&vdev->context_xa);
 	return ret;
@@ -293,6 +371,7 @@ err_xa_destroy:
 static void ivpu_dev_fini(struct ivpu_device *vdev)
 {
 	ivpu_shutdown(vdev);
+	ivpu_mmu_global_context_fini(vdev);
 
 	drm_WARN_ON(&vdev->drm, !xa_empty(&vdev->context_xa));
 	xa_destroy(&vdev->context_xa);
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index d0b006893b1c..b9ce66f40696 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -15,6 +15,8 @@
 #include <linux/xarray.h>
 #include <uapi/drm/ivpu_accel.h>
 
+#include "ivpu_mmu_context.h"
+
 #define DRIVER_NAME "intel_vpu"
 #define DRIVER_DESC "Driver for Intel Versatile Processing Unit (VPU)"
 #define DRIVER_DATE "20230117"
@@ -71,6 +73,7 @@ struct ivpu_wa_table {
 };
 
 struct ivpu_hw_info;
+struct ivpu_mmu_info;
 
 struct ivpu_device {
 	struct drm_device drm;
@@ -81,7 +84,9 @@ struct ivpu_device {
 
 	struct ivpu_wa_table wa;
 	struct ivpu_hw_info *hw;
+	struct ivpu_mmu_info *mmu;
 
+	struct ivpu_mmu_context gctx;
 	struct xarray context_xa;
 	struct xa_limit context_xa_limit;
 
@@ -100,7 +105,9 @@ struct ivpu_device {
 struct ivpu_file_priv {
 	struct kref ref;
 	struct ivpu_device *vdev;
+	struct ivpu_mmu_context ctx;
 	u32 priority;
+	bool has_mmu_faults;
 };
 
 extern int ivpu_dbg_mask;
diff --git a/drivers/accel/ivpu/ivpu_hw_mtl.c b/drivers/accel/ivpu/ivpu_hw_mtl.c
index 8a1b1c03f77b..eaba2b8248b8 100644
--- a/drivers/accel/ivpu/ivpu_hw_mtl.c
+++ b/drivers/accel/ivpu/ivpu_hw_mtl.c
@@ -7,6 +7,7 @@
 #include "ivpu_hw_mtl_reg.h"
 #include "ivpu_hw_reg_io.h"
 #include "ivpu_hw.h"
+#include "ivpu_mmu.h"
 
 #define TILE_FUSE_ENABLE_BOTH	     0x0
 #define TILE_FUSE_ENABLE_UPPER	     0x1
@@ -930,6 +931,15 @@ static u32 ivpu_hw_mtl_irqv_handler(struct ivpu_device *vdev, int irq)
 
 	REGV_WR32(MTL_VPU_HOST_SS_ICB_CLEAR_0, status);
 
+	if (REG_TEST_FLD(MTL_VPU_HOST_SS_ICB_STATUS_0, MMU_IRQ_0_INT, status))
+		ivpu_mmu_irq_evtq_handler(vdev);
+
+	if (REG_TEST_FLD(MTL_VPU_HOST_SS_ICB_STATUS_0, MMU_IRQ_1_INT, status))
+		ivpu_dbg(vdev, IRQ, "MMU sync complete\n");
+
+	if (REG_TEST_FLD(MTL_VPU_HOST_SS_ICB_STATUS_0, MMU_IRQ_2_INT, status))
+		ivpu_mmu_irq_gerr_handler(vdev);
+
 	if (REG_TEST_FLD(MTL_VPU_HOST_SS_ICB_STATUS_0, CPU_INT_REDIRECT_0_INT, status))
 		ivpu_hw_mtl_irq_wdt_mss_handler(vdev);
 
diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
new file mode 100644
index 000000000000..ff5ef6da1fd3
--- /dev/null
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -0,0 +1,876 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-2023 Intel Corporation
+ */
+
+#include <linux/circ_buf.h>
+#include <linux/highmem.h>
+
+#include "ivpu_drv.h"
+#include "ivpu_hw_mtl_reg.h"
+#include "ivpu_hw_reg_io.h"
+#include "ivpu_mmu.h"
+#include "ivpu_mmu_context.h"
+
+#define IVPU_MMU_IDR0_REF		0x080f3e0f
+#define IVPU_MMU_IDR0_REF_SIMICS	0x080f3e1f
+#define IVPU_MMU_IDR1_REF		0x0e739d18
+#define IVPU_MMU_IDR3_REF		0x0000003c
+#define IVPU_MMU_IDR5_REF		0x00040070
+#define IVPU_MMU_IDR5_REF_SIMICS	0x00000075
+#define IVPU_MMU_IDR5_REF_FPGA		0x00800075
+
+#define IVPU_MMU_CDTAB_ENT_SIZE		64
+#define IVPU_MMU_CDTAB_ENT_COUNT_LOG2	8 /* 256 entries */
+#define IVPU_MMU_CDTAB_ENT_COUNT	((u32)1 << IVPU_MMU_CDTAB_ENT_COUNT_LOG2)
+
+#define IVPU_MMU_STREAM_ID0		0
+#define IVPU_MMU_STREAM_ID3		3
+
+#define IVPU_MMU_STRTAB_ENT_SIZE	64
+#define IVPU_MMU_STRTAB_ENT_COUNT	4
+#define IVPU_MMU_STRTAB_CFG_LOG2SIZE	2
+#define IVPU_MMU_STRTAB_CFG		IVPU_MMU_STRTAB_CFG_LOG2SIZE
+
+#define IVPU_MMU_Q_COUNT_LOG2		4 /* 16 entries */
+#define IVPU_MMU_Q_COUNT		((u32)1 << IVPU_MMU_Q_COUNT_LOG2)
+#define IVPU_MMU_Q_WRAP_BIT		(IVPU_MMU_Q_COUNT << 1)
+#define IVPU_MMU_Q_WRAP_MASK		(IVPU_MMU_Q_WRAP_BIT - 1)
+#define IVPU_MMU_Q_IDX_MASK		(IVPU_MMU_Q_COUNT - 1)
+#define IVPU_MMU_Q_IDX(val)		((val) & IVPU_MMU_Q_IDX_MASK)
+
+#define IVPU_MMU_CMDQ_CMD_SIZE		16
+#define IVPU_MMU_CMDQ_SIZE		(IVPU_MMU_Q_COUNT * IVPU_MMU_CMDQ_CMD_SIZE)
+
+#define IVPU_MMU_EVTQ_CMD_SIZE		32
+#define IVPU_MMU_EVTQ_SIZE		(IVPU_MMU_Q_COUNT * IVPU_MMU_EVTQ_CMD_SIZE)
+
+#define IVPU_MMU_CMD_OPCODE		GENMASK(7, 0)
+
+#define IVPU_MMU_CMD_SYNC_0_CS		GENMASK(13, 12)
+#define IVPU_MMU_CMD_SYNC_0_MSH		GENMASK(23, 22)
+#define IVPU_MMU_CMD_SYNC_0_MSI_ATTR	GENMASK(27, 24)
+#define IVPU_MMU_CMD_SYNC_0_MSI_ATTR	GENMASK(27, 24)
+#define IVPU_MMU_CMD_SYNC_0_MSI_DATA	GENMASK(63, 32)
+
+#define IVPU_MMU_CMD_CFGI_0_SSEC	BIT(10)
+#define IVPU_MMU_CMD_CFGI_0_SSV		BIT(11)
+#define IVPU_MMU_CMD_CFGI_0_SSID	GENMASK(31, 12)
+#define IVPU_MMU_CMD_CFGI_0_SID		GENMASK(63, 32)
+#define IVPU_MMU_CMD_CFGI_1_RANGE	GENMASK(4, 0)
+
+#define IVPU_MMU_CMD_TLBI_0_ASID	GENMASK(63, 48)
+#define IVPU_MMU_CMD_TLBI_0_VMID	GENMASK(47, 32)
+
+#define CMD_PREFETCH_CFG		0x1
+#define CMD_CFGI_STE			0x3
+#define CMD_CFGI_ALL			0x4
+#define CMD_CFGI_CD			0x5
+#define CMD_CFGI_CD_ALL			0x6
+#define CMD_TLBI_NH_ASID		0x11
+#define CMD_TLBI_EL2_ALL		0x20
+#define CMD_TLBI_NSNH_ALL		0x30
+#define CMD_SYNC			0x46
+
+#define IVPU_MMU_EVT_F_UUT		0x01
+#define IVPU_MMU_EVT_C_BAD_STREAMID	0x02
+#define IVPU_MMU_EVT_F_STE_FETCH	0x03
+#define IVPU_MMU_EVT_C_BAD_STE		0x04
+#define IVPU_MMU_EVT_F_BAD_ATS_TREQ	0x05
+#define IVPU_MMU_EVT_F_STREAM_DISABLED	0x06
+#define IVPU_MMU_EVT_F_TRANSL_FORBIDDEN	0x07
+#define IVPU_MMU_EVT_C_BAD_SUBSTREAMID	0x08
+#define IVPU_MMU_EVT_F_CD_FETCH		0x09
+#define IVPU_MMU_EVT_C_BAD_CD		0x0a
+#define IVPU_MMU_EVT_F_WALK_EABT	0x0b
+#define IVPU_MMU_EVT_F_TRANSLATION	0x10
+#define IVPU_MMU_EVT_F_ADDR_SIZE	0x11
+#define IVPU_MMU_EVT_F_ACCESS		0x12
+#define IVPU_MMU_EVT_F_PERMISSION	0x13
+#define IVPU_MMU_EVT_F_TLB_CONFLICT	0x20
+#define IVPU_MMU_EVT_F_CFG_CONFLICT	0x21
+#define IVPU_MMU_EVT_E_PAGE_REQUEST	0x24
+#define IVPU_MMU_EVT_F_VMS_FETCH	0x25
+
+#define IVPU_MMU_EVT_OP_MASK		GENMASK_ULL(7, 0)
+#define IVPU_MMU_EVT_SSID_MASK		GENMASK_ULL(31, 12)
+
+#define IVPU_MMU_Q_BASE_RWA		BIT(62)
+#define IVPU_MMU_Q_BASE_ADDR_MASK	GENMASK_ULL(51, 5)
+#define IVPU_MMU_STRTAB_BASE_RA		BIT(62)
+#define IVPU_MMU_STRTAB_BASE_ADDR_MASK	GENMASK_ULL(51, 6)
+
+#define IVPU_MMU_IRQ_EVTQ_EN		BIT(2)
+#define IVPU_MMU_IRQ_GERROR_EN		BIT(0)
+
+#define IVPU_MMU_CR0_ATSCHK		BIT(4)
+#define IVPU_MMU_CR0_CMDQEN		BIT(3)
+#define IVPU_MMU_CR0_EVTQEN		BIT(2)
+#define IVPU_MMU_CR0_PRIQEN		BIT(1)
+#define IVPU_MMU_CR0_SMMUEN		BIT(0)
+
+#define IVPU_MMU_CR1_TABLE_SH		GENMASK(11, 10)
+#define IVPU_MMU_CR1_TABLE_OC		GENMASK(9, 8)
+#define IVPU_MMU_CR1_TABLE_IC		GENMASK(7, 6)
+#define IVPU_MMU_CR1_QUEUE_SH		GENMASK(5, 4)
+#define IVPU_MMU_CR1_QUEUE_OC		GENMASK(3, 2)
+#define IVPU_MMU_CR1_QUEUE_IC		GENMASK(1, 0)
+#define IVPU_MMU_CACHE_NC		0
+#define IVPU_MMU_CACHE_WB		1
+#define IVPU_MMU_CACHE_WT		2
+#define IVPU_MMU_SH_NSH			0
+#define IVPU_MMU_SH_OSH			2
+#define IVPU_MMU_SH_ISH			3
+
+#define IVPU_MMU_CMDQ_OP		GENMASK_ULL(7, 0)
+
+#define IVPU_MMU_CD_0_TCR_T0SZ		GENMASK_ULL(5, 0)
+#define IVPU_MMU_CD_0_TCR_TG0		GENMASK_ULL(7, 6)
+#define IVPU_MMU_CD_0_TCR_IRGN0		GENMASK_ULL(9, 8)
+#define IVPU_MMU_CD_0_TCR_ORGN0		GENMASK_ULL(11, 10)
+#define IVPU_MMU_CD_0_TCR_SH0		GENMASK_ULL(13, 12)
+#define IVPU_MMU_CD_0_TCR_EPD0		BIT_ULL(14)
+#define IVPU_MMU_CD_0_TCR_EPD1		BIT_ULL(30)
+#define IVPU_MMU_CD_0_ENDI		BIT(15)
+#define IVPU_MMU_CD_0_V			BIT(31)
+#define IVPU_MMU_CD_0_TCR_IPS		GENMASK_ULL(34, 32)
+#define IVPU_MMU_CD_0_TCR_TBI0		BIT_ULL(38)
+#define IVPU_MMU_CD_0_AA64		BIT(41)
+#define IVPU_MMU_CD_0_S			BIT(44)
+#define IVPU_MMU_CD_0_R			BIT(45)
+#define IVPU_MMU_CD_0_A			BIT(46)
+#define IVPU_MMU_CD_0_ASET		BIT(47)
+#define IVPU_MMU_CD_0_ASID		GENMASK_ULL(63, 48)
+
+#define IVPU_MMU_CD_1_TTB0_MASK		GENMASK_ULL(51, 4)
+
+#define IVPU_MMU_STE_0_S1CDMAX		GENMASK_ULL(63, 59)
+#define IVPU_MMU_STE_0_S1FMT		GENMASK_ULL(5, 4)
+#define IVPU_MMU_STE_0_S1FMT_LINEAR	0
+#define IVPU_MMU_STE_DWORDS		8
+#define IVPU_MMU_STE_0_CFG_S1_TRANS	5
+#define IVPU_MMU_STE_0_CFG		GENMASK_ULL(3, 1)
+#define IVPU_MMU_STE_0_S1CTXPTR_MASK	GENMASK_ULL(51, 6)
+#define IVPU_MMU_STE_0_V			BIT(0)
+
+#define IVPU_MMU_STE_1_STRW_NSEL1	0ul
+#define IVPU_MMU_STE_1_CONT		GENMASK_ULL(16, 13)
+#define IVPU_MMU_STE_1_STRW		GENMASK_ULL(31, 30)
+#define IVPU_MMU_STE_1_PRIVCFG		GENMASK_ULL(49, 48)
+#define IVPU_MMU_STE_1_PRIVCFG_UNPRIV	2ul
+#define IVPU_MMU_STE_1_INSTCFG		GENMASK_ULL(51, 50)
+#define IVPU_MMU_STE_1_INSTCFG_DATA	2ul
+#define IVPU_MMU_STE_1_MEV		BIT(19)
+#define IVPU_MMU_STE_1_S1STALLD		BIT(27)
+#define IVPU_MMU_STE_1_S1C_CACHE_NC	0ul
+#define IVPU_MMU_STE_1_S1C_CACHE_WBRA	1ul
+#define IVPU_MMU_STE_1_S1C_CACHE_WT	2ul
+#define IVPU_MMU_STE_1_S1C_CACHE_WB	3ul
+#define IVPU_MMU_STE_1_S1CIR		GENMASK_ULL(3, 2)
+#define IVPU_MMU_STE_1_S1COR		GENMASK_ULL(5, 4)
+#define IVPU_MMU_STE_1_S1CSH		GENMASK_ULL(7, 6)
+#define IVPU_MMU_STE_1_S1DSS		GENMASK_ULL(1, 0)
+#define IVPU_MMU_STE_1_S1DSS_TERMINATE	0x0
+
+#define IVPU_MMU_REG_TIMEOUT_US		(10 * USEC_PER_MSEC)
+#define IVPU_MMU_QUEUE_TIMEOUT_US	(100 * USEC_PER_MSEC)
+
+#define IVPU_MMU_GERROR_ERR_MASK ((REG_FLD(MTL_VPU_HOST_MMU_GERROR, CMDQ)) | \
+				  (REG_FLD(MTL_VPU_HOST_MMU_GERROR, EVTQ_ABT)) | \
+				  (REG_FLD(MTL_VPU_HOST_MMU_GERROR, PRIQ_ABT)) | \
+				  (REG_FLD(MTL_VPU_HOST_MMU_GERROR, MSI_CMDQ_ABT)) | \
+				  (REG_FLD(MTL_VPU_HOST_MMU_GERROR, MSI_EVTQ_ABT)) | \
+				  (REG_FLD(MTL_VPU_HOST_MMU_GERROR, MSI_PRIQ_ABT)) | \
+				  (REG_FLD(MTL_VPU_HOST_MMU_GERROR, MSI_ABT)))
+
+static char *ivpu_mmu_event_to_str(u32 cmd)
+{
+	switch (cmd) {
+	case IVPU_MMU_EVT_F_UUT:
+		return "Unsupported Upstream Transaction";
+	case IVPU_MMU_EVT_C_BAD_STREAMID:
+		return "Transaction StreamID out of range";
+	case IVPU_MMU_EVT_F_STE_FETCH:
+		return "Fetch of STE caused external abort";
+	case IVPU_MMU_EVT_C_BAD_STE:
+		return "Used STE invalid";
+	case IVPU_MMU_EVT_F_BAD_ATS_TREQ:
+		return "Address Request disallowed for a StreamID";
+	case IVPU_MMU_EVT_F_STREAM_DISABLED:
+		return "Transaction marks non-substream disabled";
+	case IVPU_MMU_EVT_F_TRANSL_FORBIDDEN:
+		return "MMU bypass is disallowed for this StreamID";
+	case IVPU_MMU_EVT_C_BAD_SUBSTREAMID:
+		return "Invalid StreamID";
+	case IVPU_MMU_EVT_F_CD_FETCH:
+		return "Fetch of CD caused external abort";
+	case IVPU_MMU_EVT_C_BAD_CD:
+		return "Fetched CD invalid";
+	case IVPU_MMU_EVT_F_WALK_EABT:
+		return " An external abort occurred fetching a TLB";
+	case IVPU_MMU_EVT_F_TRANSLATION:
+		return "Translation fault";
+	case IVPU_MMU_EVT_F_ADDR_SIZE:
+		return " Output address caused address size fault";
+	case IVPU_MMU_EVT_F_ACCESS:
+		return "Access flag fault";
+	case IVPU_MMU_EVT_F_PERMISSION:
+		return "Permission fault occurred on page access";
+	case IVPU_MMU_EVT_F_TLB_CONFLICT:
+		return "A TLB conflict";
+	case IVPU_MMU_EVT_F_CFG_CONFLICT:
+		return "A configuration cache conflict";
+	case IVPU_MMU_EVT_E_PAGE_REQUEST:
+		return "Page request hint from a client device";
+	case IVPU_MMU_EVT_F_VMS_FETCH:
+		return "Fetch of VMS caused external abort";
+	default:
+		return "Unknown CMDQ command";
+	}
+}
+
+static void ivpu_mmu_config_check(struct ivpu_device *vdev)
+{
+	u32 val_ref;
+	u32 val;
+
+	if (ivpu_is_simics(vdev))
+		val_ref = IVPU_MMU_IDR0_REF_SIMICS;
+	else
+		val_ref = IVPU_MMU_IDR0_REF;
+
+	val = REGV_RD32(MTL_VPU_HOST_MMU_IDR0);
+	if (val != val_ref)
+		ivpu_dbg(vdev, MMU, "IDR0 0x%x != IDR0_REF 0x%x\n", val, val_ref);
+
+	val = REGV_RD32(MTL_VPU_HOST_MMU_IDR1);
+	if (val != IVPU_MMU_IDR1_REF)
+		ivpu_dbg(vdev, MMU, "IDR1 0x%x != IDR1_REF 0x%x\n", val, IVPU_MMU_IDR1_REF);
+
+	val = REGV_RD32(MTL_VPU_HOST_MMU_IDR3);
+	if (val != IVPU_MMU_IDR3_REF)
+		ivpu_dbg(vdev, MMU, "IDR3 0x%x != IDR3_REF 0x%x\n", val, IVPU_MMU_IDR3_REF);
+
+	if (ivpu_is_simics(vdev))
+		val_ref = IVPU_MMU_IDR5_REF_SIMICS;
+	else if (ivpu_is_fpga(vdev))
+		val_ref = IVPU_MMU_IDR5_REF_FPGA;
+	else
+		val_ref = IVPU_MMU_IDR5_REF;
+
+	val = REGV_RD32(MTL_VPU_HOST_MMU_IDR5);
+	if (val != val_ref)
+		ivpu_dbg(vdev, MMU, "IDR5 0x%x != IDR5_REF 0x%x\n", val, val_ref);
+}
+
+static int ivpu_mmu_cdtab_alloc(struct ivpu_device *vdev)
+{
+	struct ivpu_mmu_info *mmu = vdev->mmu;
+	struct ivpu_mmu_cdtab *cdtab = &mmu->cdtab;
+	size_t size = IVPU_MMU_CDTAB_ENT_COUNT * IVPU_MMU_CDTAB_ENT_SIZE;
+
+	cdtab->base = dmam_alloc_coherent(vdev->drm.dev, size, &cdtab->dma, GFP_KERNEL);
+	if (!cdtab->base)
+		return -ENOMEM;
+
+	ivpu_dbg(vdev, MMU, "CDTAB alloc: dma=%pad size=%zu\n", &cdtab->dma, size);
+
+	return 0;
+}
+
+static int ivpu_mmu_strtab_alloc(struct ivpu_device *vdev)
+{
+	struct ivpu_mmu_info *mmu = vdev->mmu;
+	struct ivpu_mmu_strtab *strtab = &mmu->strtab;
+	size_t size = IVPU_MMU_STRTAB_ENT_COUNT * IVPU_MMU_STRTAB_ENT_SIZE;
+
+	strtab->base = dmam_alloc_coherent(vdev->drm.dev, size, &strtab->dma, GFP_KERNEL);
+	if (!strtab->base)
+		return -ENOMEM;
+
+	strtab->base_cfg = IVPU_MMU_STRTAB_CFG;
+	strtab->dma_q = IVPU_MMU_STRTAB_BASE_RA;
+	strtab->dma_q |= strtab->dma & IVPU_MMU_STRTAB_BASE_ADDR_MASK;
+
+	ivpu_dbg(vdev, MMU, "STRTAB alloc: dma=%pad dma_q=%pad size=%zu\n",
+		 &strtab->dma, &strtab->dma_q, size);
+
+	return 0;
+}
+
+static int ivpu_mmu_cmdq_alloc(struct ivpu_device *vdev)
+{
+	struct ivpu_mmu_info *mmu = vdev->mmu;
+	struct ivpu_mmu_queue *q = &mmu->cmdq;
+
+	q->base = dmam_alloc_coherent(vdev->drm.dev, IVPU_MMU_CMDQ_SIZE, &q->dma, GFP_KERNEL);
+	if (!q->base)
+		return -ENOMEM;
+
+	q->dma_q = IVPU_MMU_Q_BASE_RWA;
+	q->dma_q |= q->dma & IVPU_MMU_Q_BASE_ADDR_MASK;
+	q->dma_q |= IVPU_MMU_Q_COUNT_LOG2;
+
+	ivpu_dbg(vdev, MMU, "CMDQ alloc: dma=%pad dma_q=%pad size=%u\n",
+		 &q->dma, &q->dma_q, IVPU_MMU_CMDQ_SIZE);
+
+	return 0;
+}
+
+static int ivpu_mmu_evtq_alloc(struct ivpu_device *vdev)
+{
+	struct ivpu_mmu_info *mmu = vdev->mmu;
+	struct ivpu_mmu_queue *q = &mmu->evtq;
+
+	q->base = dmam_alloc_coherent(vdev->drm.dev, IVPU_MMU_EVTQ_SIZE, &q->dma, GFP_KERNEL);
+	if (!q->base)
+		return -ENOMEM;
+
+	q->dma_q = IVPU_MMU_Q_BASE_RWA;
+	q->dma_q |= q->dma & IVPU_MMU_Q_BASE_ADDR_MASK;
+	q->dma_q |= IVPU_MMU_Q_COUNT_LOG2;
+
+	ivpu_dbg(vdev, MMU, "EVTQ alloc: dma=%pad dma_q=%pad size=%u\n",
+		 &q->dma, &q->dma_q, IVPU_MMU_EVTQ_SIZE);
+
+	return 0;
+}
+
+static int ivpu_mmu_structs_alloc(struct ivpu_device *vdev)
+{
+	int ret;
+
+	ret = ivpu_mmu_cdtab_alloc(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to allocate cdtab: %d\n", ret);
+		return ret;
+	}
+
+	ret = ivpu_mmu_strtab_alloc(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to allocate strtab: %d\n", ret);
+		return ret;
+	}
+
+	ret = ivpu_mmu_cmdq_alloc(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to allocate cmdq: %d\n", ret);
+		return ret;
+	}
+
+	ret = ivpu_mmu_evtq_alloc(vdev);
+	if (ret)
+		ivpu_err(vdev, "Failed to allocate evtq: %d\n", ret);
+
+	return ret;
+}
+
+static int ivpu_mmu_reg_write(struct ivpu_device *vdev, u32 reg, u32 val)
+{
+	u32 reg_ack = reg + 4; /* ACK register is 4B after base register */
+	u32 val_ack;
+	int ret;
+
+	REGV_WR32(reg, val);
+
+	ret = REGV_POLL(reg_ack, val_ack, (val == val_ack), IVPU_MMU_REG_TIMEOUT_US);
+	if (ret)
+		ivpu_err(vdev, "Failed to write register 0x%x\n", reg);
+
+	return ret;
+}
+
+static int ivpu_mmu_irqs_setup(struct ivpu_device *vdev)
+{
+	u32 irq_ctrl = IVPU_MMU_IRQ_EVTQ_EN | IVPU_MMU_IRQ_GERROR_EN;
+	int ret;
+
+	ret = ivpu_mmu_reg_write(vdev, MTL_VPU_HOST_MMU_IRQ_CTRL, 0);
+	if (ret)
+		return ret;
+
+	return ivpu_mmu_reg_write(vdev, MTL_VPU_HOST_MMU_IRQ_CTRL, irq_ctrl);
+}
+
+static int ivpu_mmu_cmdq_wait_for_cons(struct ivpu_device *vdev)
+{
+	struct ivpu_mmu_queue *cmdq = &vdev->mmu->cmdq;
+
+	return REGV_POLL(MTL_VPU_HOST_MMU_CMDQ_CONS, cmdq->cons, (cmdq->prod == cmdq->cons),
+			 IVPU_MMU_QUEUE_TIMEOUT_US);
+}
+
+static int ivpu_mmu_cmdq_cmd_write(struct ivpu_device *vdev, const char *name, u64 data0, u64 data1)
+{
+	struct ivpu_mmu_queue *q = &vdev->mmu->cmdq;
+	u64 *queue_buffer = q->base;
+	int idx = IVPU_MMU_Q_IDX(q->prod) * (IVPU_MMU_CMDQ_CMD_SIZE / sizeof(*queue_buffer));
+
+	if (!CIRC_SPACE(IVPU_MMU_Q_IDX(q->prod), IVPU_MMU_Q_IDX(q->cons), IVPU_MMU_Q_COUNT)) {
+		ivpu_err(vdev, "Failed to write MMU CMD %s\n", name);
+		return -EBUSY;
+	}
+
+	queue_buffer[idx] = data0;
+	queue_buffer[idx + 1] = data1;
+	q->prod = (q->prod + 1) & IVPU_MMU_Q_WRAP_MASK;
+
+	ivpu_dbg(vdev, MMU, "CMD write: %s data: 0x%llx 0x%llx\n", name, data0, data1);
+
+	return 0;
+}
+
+static int ivpu_mmu_cmdq_sync(struct ivpu_device *vdev)
+{
+	struct ivpu_mmu_queue *q = &vdev->mmu->cmdq;
+	u64 val;
+	int ret;
+
+	val = FIELD_PREP(IVPU_MMU_CMD_OPCODE, CMD_SYNC) |
+	      FIELD_PREP(IVPU_MMU_CMD_SYNC_0_CS, 0x2) |
+	      FIELD_PREP(IVPU_MMU_CMD_SYNC_0_MSH, 0x3) |
+	      FIELD_PREP(IVPU_MMU_CMD_SYNC_0_MSI_ATTR, 0xf);
+
+	ret = ivpu_mmu_cmdq_cmd_write(vdev, "SYNC", val, 0);
+	if (ret)
+		return ret;
+
+	clflush_cache_range(q->base, IVPU_MMU_CMDQ_SIZE);
+	REGV_WR32(MTL_VPU_HOST_MMU_CMDQ_PROD, q->prod);
+
+	ret = ivpu_mmu_cmdq_wait_for_cons(vdev);
+	if (ret)
+		ivpu_err(vdev, "Timed out waiting for consumer: %d\n", ret);
+
+	return ret;
+}
+
+static int ivpu_mmu_cmdq_write_cfgi_all(struct ivpu_device *vdev)
+{
+	u64 data0 = FIELD_PREP(IVPU_MMU_CMD_OPCODE, CMD_CFGI_ALL);
+	u64 data1 = FIELD_PREP(IVPU_MMU_CMD_CFGI_1_RANGE, 0x1f);
+
+	return ivpu_mmu_cmdq_cmd_write(vdev, "CFGI_ALL", data0, data1);
+}
+
+static int ivpu_mmu_cmdq_write_tlbi_nh_asid(struct ivpu_device *vdev, u16 ssid)
+{
+	u64 val = FIELD_PREP(IVPU_MMU_CMD_OPCODE, CMD_TLBI_NH_ASID) |
+		  FIELD_PREP(IVPU_MMU_CMD_TLBI_0_ASID, ssid);
+
+	return ivpu_mmu_cmdq_cmd_write(vdev, "TLBI_NH_ASID", val, 0);
+}
+
+static int ivpu_mmu_cmdq_write_tlbi_nsnh_all(struct ivpu_device *vdev)
+{
+	u64 val = FIELD_PREP(IVPU_MMU_CMD_OPCODE, CMD_TLBI_NSNH_ALL);
+
+	return ivpu_mmu_cmdq_cmd_write(vdev, "TLBI_NSNH_ALL", val, 0);
+}
+
+static int ivpu_mmu_reset(struct ivpu_device *vdev)
+{
+	struct ivpu_mmu_info *mmu = vdev->mmu;
+	u32 val;
+	int ret;
+
+	memset(mmu->cmdq.base, 0, IVPU_MMU_CMDQ_SIZE);
+	clflush_cache_range(mmu->cmdq.base, IVPU_MMU_CMDQ_SIZE);
+	mmu->cmdq.prod = 0;
+	mmu->cmdq.cons = 0;
+
+	memset(mmu->evtq.base, 0, IVPU_MMU_EVTQ_SIZE);
+	clflush_cache_range(mmu->evtq.base, IVPU_MMU_EVTQ_SIZE);
+	mmu->evtq.prod = 0;
+	mmu->evtq.cons = 0;
+
+	ret = ivpu_mmu_reg_write(vdev, MTL_VPU_HOST_MMU_CR0, 0);
+	if (ret)
+		return ret;
+
+	val = FIELD_PREP(IVPU_MMU_CR1_TABLE_SH, IVPU_MMU_SH_ISH) |
+	      FIELD_PREP(IVPU_MMU_CR1_TABLE_OC, IVPU_MMU_CACHE_WB) |
+	      FIELD_PREP(IVPU_MMU_CR1_TABLE_IC, IVPU_MMU_CACHE_WB) |
+	      FIELD_PREP(IVPU_MMU_CR1_QUEUE_SH, IVPU_MMU_SH_ISH) |
+	      FIELD_PREP(IVPU_MMU_CR1_QUEUE_OC, IVPU_MMU_CACHE_WB) |
+	      FIELD_PREP(IVPU_MMU_CR1_QUEUE_IC, IVPU_MMU_CACHE_WB);
+	REGV_WR32(MTL_VPU_HOST_MMU_CR1, val);
+
+	REGV_WR64(MTL_VPU_HOST_MMU_STRTAB_BASE, mmu->strtab.dma_q);
+	REGV_WR32(MTL_VPU_HOST_MMU_STRTAB_BASE_CFG, mmu->strtab.base_cfg);
+
+	REGV_WR64(MTL_VPU_HOST_MMU_CMDQ_BASE, mmu->cmdq.dma_q);
+	REGV_WR32(MTL_VPU_HOST_MMU_CMDQ_PROD, 0);
+	REGV_WR32(MTL_VPU_HOST_MMU_CMDQ_CONS, 0);
+
+	val = IVPU_MMU_CR0_CMDQEN;
+	ret = ivpu_mmu_reg_write(vdev, MTL_VPU_HOST_MMU_CR0, val);
+	if (ret)
+		return ret;
+
+	ret = ivpu_mmu_cmdq_write_cfgi_all(vdev);
+	if (ret)
+		return ret;
+
+	ret = ivpu_mmu_cmdq_write_tlbi_nsnh_all(vdev);
+	if (ret)
+		return ret;
+
+	ret = ivpu_mmu_cmdq_sync(vdev);
+	if (ret)
+		return ret;
+
+	REGV_WR64(MTL_VPU_HOST_MMU_EVTQ_BASE, mmu->evtq.dma_q);
+	REGV_WR32(MTL_VPU_HOST_MMU_EVTQ_PROD_SEC, 0);
+	REGV_WR32(MTL_VPU_HOST_MMU_EVTQ_CONS_SEC, 0);
+
+	val |= IVPU_MMU_CR0_EVTQEN;
+	ret = ivpu_mmu_reg_write(vdev, MTL_VPU_HOST_MMU_CR0, val);
+	if (ret)
+		return ret;
+
+	val |= IVPU_MMU_CR0_ATSCHK;
+	ret = ivpu_mmu_reg_write(vdev, MTL_VPU_HOST_MMU_CR0, val);
+	if (ret)
+		return ret;
+
+	ret = ivpu_mmu_irqs_setup(vdev);
+	if (ret)
+		return ret;
+
+	val |= IVPU_MMU_CR0_SMMUEN;
+	return ivpu_mmu_reg_write(vdev, MTL_VPU_HOST_MMU_CR0, val);
+}
+
+static void ivpu_mmu_strtab_link_cd(struct ivpu_device *vdev, u32 sid)
+{
+	struct ivpu_mmu_info *mmu = vdev->mmu;
+	struct ivpu_mmu_strtab *strtab = &mmu->strtab;
+	struct ivpu_mmu_cdtab *cdtab = &mmu->cdtab;
+	u64 *entry = strtab->base + (sid * IVPU_MMU_STRTAB_ENT_SIZE);
+	u64 str[2];
+
+	str[0] = FIELD_PREP(IVPU_MMU_STE_0_CFG, IVPU_MMU_STE_0_CFG_S1_TRANS) |
+		 FIELD_PREP(IVPU_MMU_STE_0_S1CDMAX, IVPU_MMU_CDTAB_ENT_COUNT_LOG2) |
+		 FIELD_PREP(IVPU_MMU_STE_0_S1FMT, IVPU_MMU_STE_0_S1FMT_LINEAR) |
+		 IVPU_MMU_STE_0_V |
+		 (cdtab->dma & IVPU_MMU_STE_0_S1CTXPTR_MASK);
+
+	str[1] = FIELD_PREP(IVPU_MMU_STE_1_S1DSS, IVPU_MMU_STE_1_S1DSS_TERMINATE) |
+		 FIELD_PREP(IVPU_MMU_STE_1_S1CIR, IVPU_MMU_STE_1_S1C_CACHE_NC) |
+		 FIELD_PREP(IVPU_MMU_STE_1_S1COR, IVPU_MMU_STE_1_S1C_CACHE_NC) |
+		 FIELD_PREP(IVPU_MMU_STE_1_S1CSH, IVPU_MMU_SH_NSH) |
+		 FIELD_PREP(IVPU_MMU_STE_1_PRIVCFG, IVPU_MMU_STE_1_PRIVCFG_UNPRIV) |
+		 FIELD_PREP(IVPU_MMU_STE_1_INSTCFG, IVPU_MMU_STE_1_INSTCFG_DATA) |
+		 FIELD_PREP(IVPU_MMU_STE_1_STRW, IVPU_MMU_STE_1_STRW_NSEL1) |
+		 FIELD_PREP(IVPU_MMU_STE_1_CONT, IVPU_MMU_STRTAB_CFG_LOG2SIZE) |
+		 IVPU_MMU_STE_1_MEV |
+		 IVPU_MMU_STE_1_S1STALLD;
+
+	WRITE_ONCE(entry[1], str[1]);
+	WRITE_ONCE(entry[0], str[0]);
+
+	clflush_cache_range(entry, IVPU_MMU_STRTAB_ENT_SIZE);
+
+	ivpu_dbg(vdev, MMU, "STRTAB write entry (SSID=%u): 0x%llx, 0x%llx\n", sid, str[0], str[1]);
+}
+
+static int ivpu_mmu_strtab_init(struct ivpu_device *vdev)
+{
+	ivpu_mmu_strtab_link_cd(vdev, IVPU_MMU_STREAM_ID0);
+	ivpu_mmu_strtab_link_cd(vdev, IVPU_MMU_STREAM_ID3);
+
+	return 0;
+}
+
+int ivpu_mmu_invalidate_tlb(struct ivpu_device *vdev, u16 ssid)
+{
+	struct ivpu_mmu_info *mmu = vdev->mmu;
+	int ret;
+
+	ret = mutex_lock_interruptible(&mmu->lock);
+	if (ret)
+		return ret;
+
+	if (!mmu->on) {
+		ret = 0;
+		goto unlock;
+	}
+
+	ret = ivpu_mmu_cmdq_write_tlbi_nh_asid(vdev, ssid);
+	if (ret)
+		goto unlock;
+
+	ret = ivpu_mmu_cmdq_sync(vdev);
+unlock:
+	mutex_unlock(&mmu->lock);
+	return ret;
+}
+
+static int ivpu_mmu_cd_add(struct ivpu_device *vdev, u32 ssid, u64 cd_dma)
+{
+	struct ivpu_mmu_info *mmu = vdev->mmu;
+	struct ivpu_mmu_cdtab *cdtab = &mmu->cdtab;
+	u64 *entry;
+	u64 cd[4];
+	int ret;
+
+	if (ssid > IVPU_MMU_CDTAB_ENT_COUNT)
+		return -EINVAL;
+
+	entry = cdtab->base + (ssid * IVPU_MMU_CDTAB_ENT_SIZE);
+
+	if (cd_dma != 0) {
+		cd[0] = FIELD_PREP(IVPU_MMU_CD_0_TCR_T0SZ, 26) |
+			FIELD_PREP(IVPU_MMU_CD_0_TCR_TG0, 0) |
+			FIELD_PREP(IVPU_MMU_CD_0_TCR_IRGN0, 0) |
+			FIELD_PREP(IVPU_MMU_CD_0_TCR_ORGN0, 0) |
+			FIELD_PREP(IVPU_MMU_CD_0_TCR_SH0, 0) |
+			FIELD_PREP(IVPU_MMU_CD_0_TCR_IPS, 3) |
+			FIELD_PREP(IVPU_MMU_CD_0_ASID, ssid) |
+			IVPU_MMU_CD_0_TCR_EPD1 |
+			IVPU_MMU_CD_0_AA64 |
+			IVPU_MMU_CD_0_R |
+			IVPU_MMU_CD_0_ASET |
+			IVPU_MMU_CD_0_V;
+		cd[1] = cd_dma & IVPU_MMU_CD_1_TTB0_MASK;
+		cd[2] = 0;
+		cd[3] = 0x0000000000007444;
+
+		/* For global context generate memory fault on VPU */
+		if (ssid == IVPU_GLOBAL_CONTEXT_MMU_SSID)
+			cd[0] |= IVPU_MMU_CD_0_A;
+	} else {
+		memset(cd, 0, sizeof(cd));
+	}
+
+	WRITE_ONCE(entry[1], cd[1]);
+	WRITE_ONCE(entry[2], cd[2]);
+	WRITE_ONCE(entry[3], cd[3]);
+	WRITE_ONCE(entry[0], cd[0]);
+
+	clflush_cache_range(entry, IVPU_MMU_CDTAB_ENT_SIZE);
+
+	ivpu_dbg(vdev, MMU, "CDTAB %s entry (SSID=%u, dma=%pad): 0x%llx, 0x%llx, 0x%llx, 0x%llx\n",
+		 cd_dma ? "write" : "clear", ssid, &cd_dma, cd[0], cd[1], cd[2], cd[3]);
+
+	ret = mutex_lock_interruptible(&mmu->lock);
+	if (ret)
+		return ret;
+
+	if (!mmu->on) {
+		ret = 0;
+		goto unlock;
+	}
+
+	ret = ivpu_mmu_cmdq_write_cfgi_all(vdev);
+	if (ret)
+		goto unlock;
+
+	ret = ivpu_mmu_cmdq_sync(vdev);
+unlock:
+	mutex_unlock(&mmu->lock);
+	return ret;
+}
+
+static int ivpu_mmu_cd_add_gbl(struct ivpu_device *vdev)
+{
+	int ret;
+
+	ret = ivpu_mmu_cd_add(vdev, 0, vdev->gctx.pgtable.pgd_dma);
+	if (ret)
+		ivpu_err(vdev, "Failed to add global CD entry: %d\n", ret);
+
+	return ret;
+}
+
+static int ivpu_mmu_cd_add_user(struct ivpu_device *vdev, u32 ssid, dma_addr_t cd_dma)
+{
+	int ret;
+
+	if (ssid == 0) {
+		ivpu_err(vdev, "Invalid SSID: %u\n", ssid);
+		return -EINVAL;
+	}
+
+	ret = ivpu_mmu_cd_add(vdev, ssid, cd_dma);
+	if (ret)
+		ivpu_err(vdev, "Failed to add CD entry SSID=%u: %d\n", ssid, ret);
+
+	return ret;
+}
+
+int ivpu_mmu_init(struct ivpu_device *vdev)
+{
+	struct ivpu_mmu_info *mmu = vdev->mmu;
+	int ret;
+
+	ivpu_dbg(vdev, MMU, "Init..\n");
+
+	drmm_mutex_init(&vdev->drm, &mmu->lock);
+	ivpu_mmu_config_check(vdev);
+
+	ret = ivpu_mmu_structs_alloc(vdev);
+	if (ret)
+		return ret;
+
+	ret = ivpu_mmu_strtab_init(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to initialize strtab: %d\n", ret);
+		return ret;
+	}
+
+	ret = ivpu_mmu_cd_add_gbl(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to initialize strtab: %d\n", ret);
+		return ret;
+	}
+
+	ret = ivpu_mmu_enable(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to resume MMU: %d\n", ret);
+		return ret;
+	}
+
+	ivpu_dbg(vdev, MMU, "Init done\n");
+
+	return 0;
+}
+
+int ivpu_mmu_enable(struct ivpu_device *vdev)
+{
+	struct ivpu_mmu_info *mmu = vdev->mmu;
+	int ret;
+
+	mutex_lock(