Merge tag 'drm-next-2023-08-30' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "The drm core grew a new generic gpu virtual address manager, and new
  execution locking helpers. These are used by nouveau now to provide
  uAPI support for the userspace Vulkan driver. AMD had a bunch of new
  IP core support, loads of refactoring around fbdev, but mostly just
  the usual amount of stuff across the board.

  core:
   - fix gfp flags in drmm_kmalloc

  gpuva:
   - add new generic GPU VA manager (for nouveau initially)

  syncobj:
   - add new DRM_IOCTL_SYNCOBJ_EVENTFD ioctl

  dma-buf:
   - acquire resv lock for mmap() in exporters
   - support dma-buf self import automatically
   - docs fixes

  backlight:
   - fix fbdev interactions

  atomic:
   - improve logging

  prime:
   - remove struct gem_prim_mmap plus driver updates

  gem:
   - drm_exec: add locking over multiple GEM objects
   - fix lockdep checking

  fbdev:
   - make fbdev userspace interfaces optional
   - use linux device instead of fbdev device
   - use deferred i/o helper macros in various drivers
   - Make FB core selectable without drivers
   - Remove obsolete flags FBINFO_DEFAULT and FBINFO_FLAG_DEFAULT
   - Add helper macros and Kconfig tokens for DMA-allocated framebuffer

  ttm:
   - support init_on_free
   - swapout fixes

  panel:
   - panel-edp: Support AUO B116XAB01.4
   - Support Visionox R66451 plus DT bindings
   - ld9040:
      - Backlight support
      - magic improved
      - Kconfig fix
   - Convert to of_device_get_match_data()
   - Fix Kconfig dependencies
   - simple:
      - Set bpc value to fix warning
      - Set connector type for AUO T215HVN01
      - Support Innolux G156HCE-L01 plus DT bindings
   - ili9881: Support TDO TL050HDV35 LCD panel plus DT bindings
   - startek: Support KD070FHFID015 MIPI-DSI panel plus DT bindings
   - sitronix-st7789v:
      - Support Inanbo T28CP45TN89 plus DT bindings
      - Support EDT ET028013DMA plus DT bindings
      - Various cleanups
   - edp: Add timings for N140HCA-EAC
   - Allow panels and touchscreens to power sequence together
   - Fix Innolux G156HCE-L01 LVDS clock

  bridge:
   - debugfs for chains support
   - dw-hdmi:
      - Improve support for YUV420 bus format
      - CEC suspend/resume
      - update EDID on HDMI detect
   - dw-mipi-dsi: Fix enable/disable of DSI controller
   - lt9611uxc: Use MODULE_FIRMWARE()
   - ps8640: Remove broken EDID code
   - samsung-dsim: Fix command transfer
   - tc358764:
      - Handle HS/VS polarity
      - Use BIT() macro
      - Various cleanups
   - adv7511: Fix low refresh rate
   - anx7625:
      - Switch to macros instead of hardcoded values
      - locking fixes
   - tc358767: fix hardware delays
   - sitronix-st7789v:
      - Support panel orientation
      - Support rotation property
      - Add support for Jasonic JT240MHQS-HWT-EK-E3 plus DT bindings

  amdgpu:
   - SDMA 6.1.0 support
   - HDP 6.1 support
   - SMUIO 14.0 support
   - PSP 14.0 support
   - IH 6.1 support
   - Lots of checkpatch cleanups
   - GFX 9.4.3 updates
   - Add USB PD and IFWI flashing documentation
   - GPUVM updates
   - RAS fixes
   - DRR fixes
   - FAMS fixes
   - Virtual display fixes
   - Soft IH fixes
   - SMU13 fixes
   - Rework PSP firmware loading for other IPs
   - Kernel doc fixes
   - DCN 3.0.1 fixes
   - LTTPR fixes
   - DP MST fixes
   - DCN 3.1.6 fixes
   - SMU 13.x fixes
   - PSP 13.x fixes
   - SubVP fixes
   - GC 9.4.3 fixes
   - Display bandwidth calculation fixes
   - VCN4 secure submission fixes
   - Allow building DC on RISC-V
   - Add visible FB info to bo_print_info
   - HBR3 fixes
   - GFX9 MCBP fix
   - GMC10 vmhub index fix
   - GMC11 vmhub index fix
   - Create a new doorbell manager
   - SR-IOV fixes
   - initial freesync panel replay support
   - revert zpos properly until igt regression is fixeed
   - use TTM to manage doorbell BAR
   - Expose both current and average power via hwmon if supported

  amdkfd:
   - Cleanup CRIU dma-buf handling
   - Use KIQ to unmap HIQ
   - GFX 9.4.3 debugger updates
   - GFX 9.4.2 debugger fixes
   - Enable cooperative groups fof gfx11
   - SVM fixes
   - Convert older APUs to use dGPU path like newer APUs
   - Drop IOMMUv2 path as it is no longer used
   - TBA fix for aldebaran

  i915:
   - ICL+ DSI modeset sequence
   - HDCP improvements
   - MTL display fixes and cleanups
   - HSW/BDW PSR1 restored
   - Init DDI ports in VBT order
   - General display refactors
   - Start using plane scale factor for relative data rate
   - Use shmem for dpt objects
   - Expose RPS thresholds in sysfs
   - Apply GuC SLPC min frequency softlimit correctly
   - Extend Wa_14015795083 to TGL, RKL, DG1 and ADL
   - Fix a VMA UAF for multi-gt platform
   - Do not use stolen on MTL due to HW bug
   - Check HuC and GuC version compatibility on MTL
   - avoid infinite GPU waits due to premature release of request memory
   - Fixes and updates for GSC memory allocation
   - Display SDVO fixes
   - Take stolen handling out of FBC code
   - Make i915_coherent_map_type GT-centric
   - Simplify shmem_create_from_object map_type

  msm:
   - SM6125 MDSS support
   - DPU: SM6125 DPU support
   - DSI: runtime PM support, burst mode support
   - DSI PHY: SM6125 support in 14nm DSI PHY driver
   - GPU: prepare for a7xx
   - fix a690 firmware
   - disable relocs on a6xx and newer

  radeon:
   - Lots of checkpatch cleanups

  ast:
   - improve device-model detection
   - Represent BMV as virtual connector
   - Report DP connection status

  nouveau:
   - add new exec/bind interface to support Vulkan
   - document some getparam ioctls
   - improve VRAM detection
   - various fixes/cleanups
   - workraound DPCD issues

  ivpu:
   - MMU updates
   - debugfs support
   - Support vpu4

  virtio:
   - add sync object support

  atmel-hlcdc:
   - Support inverted pixclock polarity

  etnaviv:
   - runtime PM cleanups
   - hang handling fixes

  exynos:
   - use fbdev DMA helpers
   - fix possible NULL ptr dereference

  komeda:
   - always attach encoder

  omapdrm:
   - use fbdev DMA helpers
ingenic:
   - kconfig regmap fixes

  loongson:
   - support display controller

  mediatek:
   - Small mtk-dpi cleanups
   - DisplayPort: support eDP and aux-bus
   - Fix coverity issues
   - Fix potential memory leak if vmap() fail

  mgag200:
   - minor fixes

  mxsfb:
   - support disabling overlay planes

  panfrost:
   - fix sync in IRQ handling

  ssd130x:
   - Support per-controller default resolution plus DT bindings
   - Reduce memory-allocation overhead
   - Improve intermediate buffer size computation
   - Fix allocation of temporary buffers
   - Fix pitch computation
   - Fix shadow plane allocation

  tegra:
   - use fbdev DMA helpers
   - Convert to devm_platform_ioremap_resource()
   - support bridge/connector
   - enable PM

  tidss:
   - Support TI AM625 plus DT bindings
   - Implement new connector model plus driver updates

  vkms:
   - improve write back support
   - docs fixes
   - support gamma LUT

  zynqmp-dpsub:
   - misc fixes"

* tag 'drm-next-2023-08-30' of git://anongit.freedesktop.org/drm/drm: (1327 commits)
  drm/gpuva_mgr: remove unused prev pointer in __drm_gpuva_sm_map()
  drm/tests/drm_kunit_helpers: Place correct function name in the comment header
  drm/nouveau: uapi: don't pass NO_PREFETCH flag implicitly
  drm/nouveau: uvmm: fix unset region pointer on remap
  drm/nouveau: sched: avoid job races between entities
  drm/i915: Fix HPD polling, reenabling the output poll work as needed
  drm: Add an HPD poll helper to reschedule the poll work
  drm/i915: Fix TLB-Invalidation seqno store
  drm/ttm/tests: Fix type conversion in ttm_pool_test
  drm/msm/a6xx: Bail out early if setting GPU OOB fails
  drm/msm/a6xx: Move LLC accessors to the common header
  drm/msm/a6xx: Introduce a6xx_llc_read
  drm/ttm/tests: Require MMU when testing
  drm/panel: simple: Fix Innolux G156HCE-L01 LVDS clock
  Revert "Revert "drm/amdgpu/display: change pipe policy for DCN 2.0""
  drm/amdgpu: Add memory vendor information
  drm/amd: flush any delayed gfxoff on suspend entry
  drm/amdgpu: skip fence GFX interrupts disable/enable for S0ix
  drm/amdgpu: Remove gfxoff check in GFX v9.4.3
  drm/amd/pm: Update pci link speed for smu v13.0.6
  ...

1 files changed, 209 insertions, 93 deletions

diff --git a/drivers/accel/ivpu/ivpu_mmu_context.c b/drivers/accel/ivpu/ivpu_mmu_context.c
index 8ce9b12ac356..1d2e554e2c4a 100644
--- a/drivers/accel/ivpu/ivpu_mmu_context.c
+++ b/drivers/accel/ivpu/ivpu_mmu_context.c
@@ -11,10 +11,12 @@
 #include "ivpu_mmu.h"
 #include "ivpu_mmu_context.h"
 
-#define IVPU_MMU_PGD_INDEX_MASK          GENMASK(38, 30)
+#define IVPU_MMU_PGD_INDEX_MASK          GENMASK(47, 39)
+#define IVPU_MMU_PUD_INDEX_MASK          GENMASK(38, 30)
 #define IVPU_MMU_PMD_INDEX_MASK          GENMASK(29, 21)
 #define IVPU_MMU_PTE_INDEX_MASK          GENMASK(20, 12)
-#define IVPU_MMU_ENTRY_FLAGS_MASK        GENMASK(11, 0)
+#define IVPU_MMU_ENTRY_FLAGS_MASK        (BIT(52) | GENMASK(11, 0))
+#define IVPU_MMU_ENTRY_FLAG_CONT         BIT(52)
 #define IVPU_MMU_ENTRY_FLAG_NG           BIT(11)
 #define IVPU_MMU_ENTRY_FLAG_AF           BIT(10)
 #define IVPU_MMU_ENTRY_FLAG_USER         BIT(6)
@@ -22,10 +24,13 @@
 #define IVPU_MMU_ENTRY_FLAG_TYPE_PAGE    BIT(1)
 #define IVPU_MMU_ENTRY_FLAG_VALID        BIT(0)
 
-#define IVPU_MMU_PAGE_SIZE    SZ_4K
-#define IVPU_MMU_PTE_MAP_SIZE (IVPU_MMU_PGTABLE_ENTRIES * IVPU_MMU_PAGE_SIZE)
-#define IVPU_MMU_PMD_MAP_SIZE (IVPU_MMU_PGTABLE_ENTRIES * IVPU_MMU_PTE_MAP_SIZE)
-#define IVPU_MMU_PGTABLE_SIZE (IVPU_MMU_PGTABLE_ENTRIES * sizeof(u64))
+#define IVPU_MMU_PAGE_SIZE       SZ_4K
+#define IVPU_MMU_CONT_PAGES_SIZE (IVPU_MMU_PAGE_SIZE * 16)
+#define IVPU_MMU_PTE_MAP_SIZE    (IVPU_MMU_PGTABLE_ENTRIES * IVPU_MMU_PAGE_SIZE)
+#define IVPU_MMU_PMD_MAP_SIZE    (IVPU_MMU_PGTABLE_ENTRIES * IVPU_MMU_PTE_MAP_SIZE)
+#define IVPU_MMU_PUD_MAP_SIZE    (IVPU_MMU_PGTABLE_ENTRIES * IVPU_MMU_PMD_MAP_SIZE)
+#define IVPU_MMU_PGD_MAP_SIZE    (IVPU_MMU_PGTABLE_ENTRIES * IVPU_MMU_PUD_MAP_SIZE)
+#define IVPU_MMU_PGTABLE_SIZE    (IVPU_MMU_PGTABLE_ENTRIES * sizeof(u64))
 
 #define IVPU_MMU_DUMMY_ADDRESS 0xdeadb000
 #define IVPU_MMU_ENTRY_VALID   (IVPU_MMU_ENTRY_FLAG_TYPE_PAGE | IVPU_MMU_ENTRY_FLAG_VALID)
@@ -36,167 +41,268 @@
 static int ivpu_mmu_pgtable_init(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable)
 {
 	dma_addr_t pgd_dma;
-	u64 *pgd;
 
-	pgd = dma_alloc_wc(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, &pgd_dma, GFP_KERNEL);
-	if (!pgd)
+	pgtable->pgd_dma_ptr = dma_alloc_coherent(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, &pgd_dma,
+						  GFP_KERNEL);
+	if (!pgtable->pgd_dma_ptr)
 		return -ENOMEM;
 
-	pgtable->pgd = pgd;
 	pgtable->pgd_dma = pgd_dma;
 
 	return 0;
 }
 
-static void ivpu_mmu_pgtable_free(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable)
+static void ivpu_mmu_pgtable_free(struct ivpu_device *vdev, u64 *cpu_addr, dma_addr_t dma_addr)
 {
-	int pgd_index, pmd_index;
+	if (cpu_addr)
+		dma_free_coherent(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, cpu_addr,
+				  dma_addr & ~IVPU_MMU_ENTRY_FLAGS_MASK);
+}
+
+static void ivpu_mmu_pgtables_free(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable)
+{
+	int pgd_idx, pud_idx, pmd_idx;
+	dma_addr_t pud_dma, pmd_dma, pte_dma;
+	u64 *pud_dma_ptr, *pmd_dma_ptr, *pte_dma_ptr;
 
-	for (pgd_index = 0; pgd_index < IVPU_MMU_PGTABLE_ENTRIES; ++pgd_index) {
-		u64 **pmd_entries = pgtable->pgd_cpu_entries[pgd_index];
-		u64 *pmd = pgtable->pgd_entries[pgd_index];
+	for (pgd_idx = 0; pgd_idx < IVPU_MMU_PGTABLE_ENTRIES; ++pgd_idx) {
+		pud_dma_ptr = pgtable->pud_ptrs[pgd_idx];
+		pud_dma = pgtable->pgd_dma_ptr[pgd_idx];
 
-		if (!pmd_entries)
+		if (!pud_dma_ptr)
 			continue;
 
-		for (pmd_index = 0; pmd_index < IVPU_MMU_PGTABLE_ENTRIES; ++pmd_index) {
-			if (pmd_entries[pmd_index])
-				dma_free_wc(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE,
-					    pmd_entries[pmd_index],
-					    pmd[pmd_index] & ~IVPU_MMU_ENTRY_FLAGS_MASK);
+		for (pud_idx = 0; pud_idx < IVPU_MMU_PGTABLE_ENTRIES; ++pud_idx) {
+			pmd_dma_ptr = pgtable->pmd_ptrs[pgd_idx][pud_idx];
+			pmd_dma = pgtable->pud_ptrs[pgd_idx][pud_idx];
+
+			if (!pmd_dma_ptr)
+				continue;
+
+			for (pmd_idx = 0; pmd_idx < IVPU_MMU_PGTABLE_ENTRIES; ++pmd_idx) {
+				pte_dma_ptr = pgtable->pte_ptrs[pgd_idx][pud_idx][pmd_idx];
+				pte_dma = pgtable->pmd_ptrs[pgd_idx][pud_idx][pmd_idx];
+
+				ivpu_mmu_pgtable_free(vdev, pte_dma_ptr, pte_dma);
+			}
+
+			kfree(pgtable->pte_ptrs[pgd_idx][pud_idx]);
+			ivpu_mmu_pgtable_free(vdev, pmd_dma_ptr, pmd_dma);
 		}
 
-		kfree(pmd_entries);
-		dma_free_wc(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, pgtable->pgd_entries[pgd_index],
-			    pgtable->pgd[pgd_index] & ~IVPU_MMU_ENTRY_FLAGS_MASK);
+		kfree(pgtable->pmd_ptrs[pgd_idx]);
+		kfree(pgtable->pte_ptrs[pgd_idx]);
+		ivpu_mmu_pgtable_free(vdev, pud_dma_ptr, pud_dma);
 	}
 
-	dma_free_wc(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, pgtable->pgd,
-		    pgtable->pgd_dma & ~IVPU_MMU_ENTRY_FLAGS_MASK);
+	ivpu_mmu_pgtable_free(vdev, pgtable->pgd_dma_ptr, pgtable->pgd_dma);
+}
+
+static u64*
+ivpu_mmu_ensure_pud(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable, int pgd_idx)
+{
+	u64 *pud_dma_ptr = pgtable->pud_ptrs[pgd_idx];
+	dma_addr_t pud_dma;
+
+	if (pud_dma_ptr)
+		return pud_dma_ptr;
+
+	pud_dma_ptr = dma_alloc_wc(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, &pud_dma, GFP_KERNEL);
+	if (!pud_dma_ptr)
+		return NULL;
+
+	drm_WARN_ON(&vdev->drm, pgtable->pmd_ptrs[pgd_idx]);
+	pgtable->pmd_ptrs[pgd_idx] = kzalloc(IVPU_MMU_PGTABLE_SIZE, GFP_KERNEL);
+	if (!pgtable->pmd_ptrs[pgd_idx])
+		goto err_free_pud_dma_ptr;
+
+	drm_WARN_ON(&vdev->drm, pgtable->pte_ptrs[pgd_idx]);
+	pgtable->pte_ptrs[pgd_idx] = kzalloc(IVPU_MMU_PGTABLE_SIZE, GFP_KERNEL);
+	if (!pgtable->pte_ptrs[pgd_idx])
+		goto err_free_pmd_ptrs;
+
+	pgtable->pud_ptrs[pgd_idx] = pud_dma_ptr;
+	pgtable->pgd_dma_ptr[pgd_idx] = pud_dma | IVPU_MMU_ENTRY_VALID;
+
+	return pud_dma_ptr;
+
+err_free_pmd_ptrs:
+	kfree(pgtable->pmd_ptrs[pgd_idx]);
+
+err_free_pud_dma_ptr:
+	ivpu_mmu_pgtable_free(vdev, pud_dma_ptr, pud_dma);
+	return NULL;
 }
 
 static u64*
-ivpu_mmu_ensure_pmd(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable, u64 pgd_index)
+ivpu_mmu_ensure_pmd(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable, int pgd_idx,
+		    int pud_idx)
 {
-	u64 **pmd_entries;
+	u64 *pmd_dma_ptr = pgtable->pmd_ptrs[pgd_idx][pud_idx];
 	dma_addr_t pmd_dma;
-	u64 *pmd;
 
-	if (pgtable->pgd_entries[pgd_index])
-		return pgtable->pgd_entries[pgd_index];
+	if (pmd_dma_ptr)
+		return pmd_dma_ptr;
 
-	pmd = dma_alloc_wc(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, &pmd_dma, GFP_KERNEL);
-	if (!pmd)
+	pmd_dma_ptr = dma_alloc_wc(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, &pmd_dma, GFP_KERNEL);
+	if (!pmd_dma_ptr)
 		return NULL;
 
-	pmd_entries = kzalloc(IVPU_MMU_PGTABLE_SIZE, GFP_KERNEL);
-	if (!pmd_entries)
-		goto err_free_pgd;
+	drm_WARN_ON(&vdev->drm, pgtable->pte_ptrs[pgd_idx][pud_idx]);
+	pgtable->pte_ptrs[pgd_idx][pud_idx] = kzalloc(IVPU_MMU_PGTABLE_SIZE, GFP_KERNEL);
+	if (!pgtable->pte_ptrs[pgd_idx][pud_idx])
+		goto err_free_pmd_dma_ptr;
 
-	pgtable->pgd_entries[pgd_index] = pmd;
-	pgtable->pgd_cpu_entries[pgd_index] = pmd_entries;
-	pgtable->pgd[pgd_index] = pmd_dma | IVPU_MMU_ENTRY_VALID;
+	pgtable->pmd_ptrs[pgd_idx][pud_idx] = pmd_dma_ptr;
+	pgtable->pud_ptrs[pgd_idx][pud_idx] = pmd_dma | IVPU_MMU_ENTRY_VALID;
 
-	return pmd;
+	return pmd_dma_ptr;
 
-err_free_pgd:
-	dma_free_wc(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, pmd, pmd_dma);
+err_free_pmd_dma_ptr:
+	ivpu_mmu_pgtable_free(vdev, pmd_dma_ptr, pmd_dma);
 	return NULL;
 }
 
 static u64*
 ivpu_mmu_ensure_pte(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable,
-		    int pgd_index, int pmd_index)
+		    int pgd_idx, int pud_idx, int pmd_idx)
 {
+	u64 *pte_dma_ptr = pgtable->pte_ptrs[pgd_idx][pud_idx][pmd_idx];
 	dma_addr_t pte_dma;
-	u64 *pte;
 
-	if (pgtable->pgd_cpu_entries[pgd_index][pmd_index])
-		return pgtable->pgd_cpu_entries[pgd_index][pmd_index];
+	if (pte_dma_ptr)
+		return pte_dma_ptr;
 
-	pte = dma_alloc_wc(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, &pte_dma, GFP_KERNEL);
-	if (!pte)
+	pte_dma_ptr = dma_alloc_wc(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, &pte_dma, GFP_KERNEL);
+	if (!pte_dma_ptr)
 		return NULL;
 
-	pgtable->pgd_cpu_entries[pgd_index][pmd_index] = pte;
-	pgtable->pgd_entries[pgd_index][pmd_index] = pte_dma | IVPU_MMU_ENTRY_VALID;
+	pgtable->pte_ptrs[pgd_idx][pud_idx][pmd_idx] = pte_dma_ptr;
+	pgtable->pmd_ptrs[pgd_idx][pud_idx][pmd_idx] = pte_dma | IVPU_MMU_ENTRY_VALID;
 
-	return pte;
+	return pte_dma_ptr;
 }
 
 static int
 ivpu_mmu_context_map_page(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
-			  u64 vpu_addr, dma_addr_t dma_addr, int prot)
+			  u64 vpu_addr, dma_addr_t dma_addr, u64 prot)
 {
 	u64 *pte;
-	int pgd_index = FIELD_GET(IVPU_MMU_PGD_INDEX_MASK, vpu_addr);
-	int pmd_index = FIELD_GET(IVPU_MMU_PMD_INDEX_MASK, vpu_addr);
-	int pte_index = FIELD_GET(IVPU_MMU_PTE_INDEX_MASK, vpu_addr);
+	int pgd_idx = FIELD_GET(IVPU_MMU_PGD_INDEX_MASK, vpu_addr);
+	int pud_idx = FIELD_GET(IVPU_MMU_PUD_INDEX_MASK, vpu_addr);
+	int pmd_idx = FIELD_GET(IVPU_MMU_PMD_INDEX_MASK, vpu_addr);
+	int pte_idx = FIELD_GET(IVPU_MMU_PTE_INDEX_MASK, vpu_addr);
+
+	/* Allocate PUD - second level page table if needed */
+	if (!ivpu_mmu_ensure_pud(vdev, &ctx->pgtable, pgd_idx))
+		return -ENOMEM;
 
-	/* Allocate PMD - second level page table if needed */
-	if (!ivpu_mmu_ensure_pmd(vdev, &ctx->pgtable, pgd_index))
+	/* Allocate PMD - third level page table if needed */
+	if (!ivpu_mmu_ensure_pmd(vdev, &ctx->pgtable, pgd_idx, pud_idx))
 		return -ENOMEM;
 
-	/* Allocate PTE - third level page table if needed */
-	pte = ivpu_mmu_ensure_pte(vdev, &ctx->pgtable, pgd_index, pmd_index);
+	/* Allocate PTE - fourth level page table if needed */
+	pte = ivpu_mmu_ensure_pte(vdev, &ctx->pgtable, pgd_idx, pud_idx, pmd_idx);
 	if (!pte)
 		return -ENOMEM;
 
-	/* Update PTE - third level page table with DMA address */
-	pte[pte_index] = dma_addr | prot;
+	/* Update PTE */
+	pte[pte_idx] = dma_addr | prot;
+
+	return 0;
+}
+
+static int
+ivpu_mmu_context_map_cont_64k(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, u64 vpu_addr,
+			      dma_addr_t dma_addr, u64 prot)
+{
+	size_t size = IVPU_MMU_CONT_PAGES_SIZE;
+
+	drm_WARN_ON(&vdev->drm, !IS_ALIGNED(vpu_addr, size));
+	drm_WARN_ON(&vdev->drm, !IS_ALIGNED(dma_addr, size));
+
+	prot |= IVPU_MMU_ENTRY_FLAG_CONT;
+
+	while (size) {
+		int ret = ivpu_mmu_context_map_page(vdev, ctx, vpu_addr, dma_addr, prot);
+
+		if (ret)
+			return ret;
+
+		size -= IVPU_MMU_PAGE_SIZE;
+		vpu_addr += IVPU_MMU_PAGE_SIZE;
+		dma_addr += IVPU_MMU_PAGE_SIZE;
+	}
 
 	return 0;
 }
 
 static void ivpu_mmu_context_unmap_page(struct ivpu_mmu_context *ctx, u64 vpu_addr)
 {
-	int pgd_index = FIELD_GET(IVPU_MMU_PGD_INDEX_MASK, vpu_addr);
-	int pmd_index = FIELD_GET(IVPU_MMU_PMD_INDEX_MASK, vpu_addr);
-	int pte_index = FIELD_GET(IVPU_MMU_PTE_INDEX_MASK, vpu_addr);
+	int pgd_idx = FIELD_GET(IVPU_MMU_PGD_INDEX_MASK, vpu_addr);
+	int pud_idx = FIELD_GET(IVPU_MMU_PUD_INDEX_MASK, vpu_addr);
+	int pmd_idx = FIELD_GET(IVPU_MMU_PMD_INDEX_MASK, vpu_addr);
+	int pte_idx = FIELD_GET(IVPU_MMU_PTE_INDEX_MASK, vpu_addr);
 
 	/* Update PTE with dummy physical address and clear flags */
-	ctx->pgtable.pgd_cpu_entries[pgd_index][pmd_index][pte_index] = IVPU_MMU_ENTRY_INVALID;
+	ctx->pgtable.pte_ptrs[pgd_idx][pud_idx][pmd_idx][pte_idx] = IVPU_MMU_ENTRY_INVALID;
 }
 
 static void
 ivpu_mmu_context_flush_page_tables(struct ivpu_mmu_context *ctx, u64 vpu_addr, size_t size)
 {
+	struct ivpu_mmu_pgtable *pgtable = &ctx->pgtable;
 	u64 end_addr = vpu_addr + size;
-	u64 *pgd = ctx->pgtable.pgd;
 
 	/* Align to PMD entry (2 MB) */
 	vpu_addr &= ~(IVPU_MMU_PTE_MAP_SIZE - 1);
 
 	while (vpu_addr < end_addr) {
-		int pgd_index = FIELD_GET(IVPU_MMU_PGD_INDEX_MASK, vpu_addr);
-		u64 pmd_end = (pgd_index + 1) * (u64)IVPU_MMU_PMD_MAP_SIZE;
-		u64 *pmd = ctx->pgtable.pgd_entries[pgd_index];
-
-		while (vpu_addr < end_addr && vpu_addr < pmd_end) {
-			int pmd_index = FIELD_GET(IVPU_MMU_PMD_INDEX_MASK, vpu_addr);
-			u64 *pte = ctx->pgtable.pgd_cpu_entries[pgd_index][pmd_index];
-
-			clflush_cache_range(pte, IVPU_MMU_PGTABLE_SIZE);
-			vpu_addr += IVPU_MMU_PTE_MAP_SIZE;
+		int pgd_idx = FIELD_GET(IVPU_MMU_PGD_INDEX_MASK, vpu_addr);
+		u64 pud_end = (pgd_idx + 1) * (u64)IVPU_MMU_PUD_MAP_SIZE;
+
+		while (vpu_addr < end_addr && vpu_addr < pud_end) {
+			int pud_idx = FIELD_GET(IVPU_MMU_PUD_INDEX_MASK, vpu_addr);
+			u64 pmd_end = (pud_idx + 1) * (u64)IVPU_MMU_PMD_MAP_SIZE;
+
+			while (vpu_addr < end_addr && vpu_addr < pmd_end) {
+				int pmd_idx = FIELD_GET(IVPU_MMU_PMD_INDEX_MASK, vpu_addr);
+
+				clflush_cache_range(pgtable->pte_ptrs[pgd_idx][pud_idx][pmd_idx],
+						    IVPU_MMU_PGTABLE_SIZE);
+				vpu_addr += IVPU_MMU_PTE_MAP_SIZE;
+			}
+			clflush_cache_range(pgtable->pmd_ptrs[pgd_idx][pud_idx],
+					    IVPU_MMU_PGTABLE_SIZE);
 		}
-		clflush_cache_range(pmd, IVPU_MMU_PGTABLE_SIZE);
+		clflush_cache_range(pgtable->pud_ptrs[pgd_idx], IVPU_MMU_PGTABLE_SIZE);
 	}
-	clflush_cache_range(pgd, IVPU_MMU_PGTABLE_SIZE);
+	clflush_cache_range(pgtable->pgd_dma_ptr, IVPU_MMU_PGTABLE_SIZE);
 }
 
 static int
 ivpu_mmu_context_map_pages(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
-			   u64 vpu_addr, dma_addr_t dma_addr, size_t size, int prot)
+			   u64 vpu_addr, dma_addr_t dma_addr, size_t size, u64 prot)
 {
+	int map_size;
+	int ret;
+
 	while (size) {
-		int ret = ivpu_mmu_context_map_page(vdev, ctx, vpu_addr, dma_addr, prot);
+		if (!ivpu_disable_mmu_cont_pages && size >= IVPU_MMU_CONT_PAGES_SIZE &&
+		    IS_ALIGNED(vpu_addr | dma_addr, IVPU_MMU_CONT_PAGES_SIZE)) {
+			ret = ivpu_mmu_context_map_cont_64k(vdev, ctx, vpu_addr, dma_addr, prot);
+			map_size = IVPU_MMU_CONT_PAGES_SIZE;
+		} else {
+			ret = ivpu_mmu_context_map_page(vdev, ctx, vpu_addr, dma_addr, prot);
+			map_size = IVPU_MMU_PAGE_SIZE;
+		}
 
 		if (ret)
 			return ret;
 
-		vpu_addr += IVPU_MMU_PAGE_SIZE;
-		dma_addr += IVPU_MMU_PAGE_SIZE;
-		size -= IVPU_MMU_PAGE_SIZE;
+		vpu_addr += map_size;
+		dma_addr += map_size;
+		size -= map_size;
 	}
 
 	return 0;
@@ -216,8 +322,8 @@ ivpu_mmu_context_map_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 			 u64 vpu_addr, struct sg_table *sgt,  bool llc_coherent)
 {
 	struct scatterlist *sg;
-	int prot;
 	int ret;
+	u64 prot;
 	u64 i;
 
 	if (!IS_ALIGNED(vpu_addr, IVPU_MMU_PAGE_SIZE))
@@ -237,7 +343,7 @@ ivpu_mmu_context_map_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 	mutex_lock(&ctx->lock);
 
 	for_each_sgtable_dma_sg(sgt, sg, i) {
-		u64 dma_addr = sg_dma_address(sg) - sg->offset;
+		dma_addr_t dma_addr = sg_dma_address(sg) - sg->offset;
 		size_t size = sg_dma_len(sg) + sg->offset;
 
 		ret = ivpu_mmu_context_map_pages(vdev, ctx, vpu_addr, dma_addr, size, prot);
@@ -293,8 +399,14 @@ ivpu_mmu_context_insert_node_locked(struct ivpu_mmu_context *ctx,
 {
 	lockdep_assert_held(&ctx->lock);
 
-	return drm_mm_insert_node_in_range(&ctx->mm, node, size, IVPU_MMU_PAGE_SIZE,
-					  0, range->start, range->end, DRM_MM_INSERT_BEST);
+	if (!ivpu_disable_mmu_cont_pages && size >= IVPU_MMU_CONT_PAGES_SIZE) {
+		if (!drm_mm_insert_node_in_range(&ctx->mm, node, size, IVPU_MMU_CONT_PAGES_SIZE, 0,
+						 range->start, range->end, DRM_MM_INSERT_BEST))
+			return 0;
+	}
+
+	return drm_mm_insert_node_in_range(&ctx->mm, node, size, IVPU_MMU_PAGE_SIZE, 0,
+					   range->start, range->end, DRM_MM_INSERT_BEST);
 }
 
 void
@@ -319,11 +431,11 @@ ivpu_mmu_context_init(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, u3
 		return ret;
 
 	if (!context_id) {
-		start = vdev->hw->ranges.global_low.start;
-		end = vdev->hw->ranges.global_high.end;
+		start = vdev->hw->ranges.global.start;
+		end = vdev->hw->ranges.shave.end;
 	} else {
-		start = vdev->hw->ranges.user_low.start;
-		end = vdev->hw->ranges.user_high.end;
+		start = vdev->hw->ranges.user.start;
+		end = vdev->hw->ranges.dma.end;
 	}
 
 	drm_mm_init(&ctx->mm, start, end - start);
@@ -334,11 +446,15 @@ ivpu_mmu_context_init(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, u3
 
 static void ivpu_mmu_context_fini(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx)
 {
-	drm_WARN_ON(&vdev->drm, !ctx->pgtable.pgd);
+	if (drm_WARN_ON(&vdev->drm, !ctx->pgtable.pgd_dma_ptr))
+		return;
 
 	mutex_destroy(&ctx->lock);
-	ivpu_mmu_pgtable_free(vdev, &ctx->pgtable);
+	ivpu_mmu_pgtables_free(vdev, &ctx->pgtable);
 	drm_mm_takedown(&ctx->mm);
+
+	ctx->pgtable.pgd_dma_ptr = NULL;
+	ctx->pgtable.pgd_dma = 0;
 }
 
 int ivpu_mmu_global_context_init(struct ivpu_device *vdev)