Merge tag 'drm-next-2022-05-25' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Intel have enabled DG2 on certain SKUs for laptops, AMD has started
  some new GPU support, msm has user allocated VA controls

  dma-buf:
   - add dma_resv_replace_fences
   - add dma_resv_get_singleton
   - make dma_excl_fence private

  core:
   - EDID parser refactorings
   - switch drivers to drm_mode_copy/duplicate
   - DRM managed mutex initialization

  display-helper:
   - put HDMI, SCDC, HDCP, DSC and DP into new module

  gem:
   - rework fence handling

  ttm:
   - rework bulk move handling
   - add common debugfs for resource managers
   - convert to kvcalloc

  format helpers:
   - support monochrome formats
   - RGB888, RGB565 to XRGB8888 conversions

  fbdev:
   - cfb/sys_imageblit fixes
   - pagelist corruption fix
   - create offb platform device
   - deferred io improvements

  sysfb:
   - Kconfig rework
   - support for VESA mode selection

  bridge:
   - conversions to devm_drm_of_get_bridge
   - conversions to panel_bridge
   - analogix_dp - autosuspend support
   - it66121 - audio support
   - tc358767 - DSI to DPI support
   - icn6211 - PLL/I2C fixes, DT property
   - adv7611 - enable DRM_BRIDGE_OP_HPD
   - anx7625 - fill ELD if no monitor
   - dw_hdmi - add audio support
   - lontium LT9211 support, i.MXMP LDB
   - it6505: Kconfig fix, DPCD set power fix
   - adv7511 - CEC support for ADV7535

  panel:
   - ltk035c5444t, B133UAN01, NV3052C panel support
   - DataImage FG040346DSSWBG04 support
   - st7735r - DT bindings fix
   - ssd130x - fixes

  i915:
   - DG2 laptop PCI-IDs ("motherboard down")
   - Initial RPL-P PCI IDs
   - compute engine ABI
   - DG2 Tile4 support
   - DG2 CCS clear color compression support
   - DG2 render/media compression formats support
   - ATS-M platform info
   - RPL-S PCI IDs added
   - Bump ADL-P DMC version to v2.16
   - Support static DRRS
   - Support multiple eDP/LVDS native mode refresh rates
   - DP HDR support for HSW+
   - Lots of display refactoring + fixes
   - GuC hwconfig support and query
   - sysfs support for multi-tile
   - fdinfo per-client gpu utilisation
   - add geometry subslices query
   - fix prime mmap with LMEM
   - fix vm open count and remove vma refcounts
   - contiguous allocation fixes
   - steered register write support
   - small PCI BAR enablement
   - GuC error capture support
   - sunset igpu legacy mmap support for newer devices
   - GuC version 70.1.1 support

  amdgpu:
   - Initial SoC21 support
   - SMU 13.x enablement
   - SMU 13.0.4 support
   - ttm_eu cleanups
   - USB-C, GPUVM updates
   - TMZ fixes for RV
   - RAS support for VCN
   - PM sysfs code cleanup
   - DC FP rework
   - extend CG/PG flags to 64-bit
   - SI dpm lockdep fix
   - runtime PM fixes

  amdkfd:
   - RAS/SVM fixes
   - TLB flush fixes
   - CRIU GWS support
   - ignore bogus MEC signals more efficiently

  msm:
   - Fourcc modifier for tiled but not compressed layouts
   - Support for userspace allocated IOVA (GPU virtual address)
   - DPU: DSC (Display Stream Compression) support
   - DP: eDP support
   - DP: conversion to use drm_bridge and drm_bridge_connector
   - Merge DPU1 and MDP5 MDSS driver
   - DPU: writeback support

  nouveau:
   - make some structures static
   - make some variables static
   - switch to drm_gem_plane_helper_prepare_fb

  radeon:
   - misc fixes/cleanups

  mxsfb:
   - rework crtc mode setting
   - LCDIF CRC support

  etnaviv:
   - fencing improvements
   - fix address space collisions
   - cleanup MMU reference handling

  gma500:
   - GEM/GTT improvements
   - connector handling fixes

  komeda:
   - switch to plane reset helper

  mediatek:
   - MIPI DSI improvements

  omapdrm:
   - GEM improvements

  qxl:
   - aarch64 support

  vc4:
   - add a CL submission tracepoint
   - HDMI YUV support
   - HDMI/clock improvements
   - drop is_hdmi caching

  virtio:
   - remove restriction of non-zero blob types

  vmwgfx:
   - support for cursormob and cursorbypass 4
   - fence improvements

  tidss:
   - reset DISPC on startup

  solomon:
   - SPI support
   - DT improvements

  sun4i:
   - allwinner D1 support
   - drop is_hdmi caching

  imx:
   - use swap() instead of open-coding
   - use devm_platform_ioremap_resource
   - remove redunant initializations

  ast:
   - Displayport support

  rockchip:
   - Refactor IOMMU initialisation
   - make some structures static
   - replace drm_detect_hdmi_monitor with drm_display_info.is_hdmi
   - support swapped YUV formats,
   - clock improvements
   - rk3568 support
   - VOP2 support

  mediatek:
   - MT8186 support

  tegra:
   - debugabillity improvements"

* tag 'drm-next-2022-05-25' of git://anongit.freedesktop.org/drm/drm: (1740 commits)
  drm/i915/dsi: fix VBT send packet port selection for ICL+
  drm/i915/uc: Fix undefined behavior due to shift overflowing the constant
  drm/i915/reg: fix undefined behavior due to shift overflowing the constant
  drm/i915/gt: Fix use of static in macro mismatch
  drm/i915/audio: fix audio code enable/disable pipe logging
  drm/i915: Fix CFI violation with show_dynamic_id()
  drm/i915: Fix 'mixing different enum types' warnings in intel_display_power.c
  drm/i915/gt: Fix build error without CONFIG_PM
  drm/msm/dpu: handle pm_runtime_get_sync() errors in bind path
  drm/msm/dpu: add DRM_MODE_ROTATE_180 back to supported rotations
  drm/msm: don't free the IRQ if it was not requested
  drm/msm/dpu: limit writeback modes according to max_linewidth
  drm/amd: Don't reset dGPUs if the system is going to s2idle
  drm/amdgpu: Unmap legacy queue when MES is enabled
  drm: msm: fix possible memory leak in mdp5_crtc_cursor_set()
  drm/msm: Fix fb plane offset calculation
  drm/msm/a6xx: Fix refcount leak in a6xx_gpu_init
  drm/msm/dsi: don't powerup at modeset time for parade-ps8640
  drm/rockchip: Change register space names in vop2
  dt-bindings: display: rockchip: make reg-names mandatory for VOP2
  ...

1 files changed, 133 insertions, 1076 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index fc4563cf2828..2ceeaa4c793a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -89,6 +89,21 @@ struct amdgpu_prt_cb {
 };
 
 /**
+ * struct amdgpu_vm_tlb_seq_cb - Helper to increment the TLB flush sequence
+ */
+struct amdgpu_vm_tlb_seq_cb {
+	/**
+	 * @vm: pointer to the amdgpu_vm structure to set the fence sequence on
+	 */
+	struct amdgpu_vm *vm;
+
+	/**
+	 * @cb: callback
+	 */
+	struct dma_fence_cb cb;
+};
+
+/**
  * amdgpu_vm_set_pasid - manage pasid and vm ptr mapping
  *
  * @adev: amdgpu_device pointer
@@ -155,108 +170,6 @@ static inline void amdgpu_vm_eviction_unlock(struct amdgpu_vm *vm)
 }
 
 /**
- * amdgpu_vm_level_shift - return the addr shift for each level
- *
- * @adev: amdgpu_device pointer
- * @level: VMPT level
- *
- * Returns:
- * The number of bits the pfn needs to be right shifted for a level.
- */
-static unsigned amdgpu_vm_level_shift(struct amdgpu_device *adev,
-				      unsigned level)
-{
-	switch (level) {
-	case AMDGPU_VM_PDB2:
-	case AMDGPU_VM_PDB1:
-	case AMDGPU_VM_PDB0:
-		return 9 * (AMDGPU_VM_PDB0 - level) +
-			adev->vm_manager.block_size;
-	case AMDGPU_VM_PTB:
-		return 0;
-	default:
-		return ~0;
-	}
-}
-
-/**
- * amdgpu_vm_num_entries - return the number of entries in a PD/PT
- *
- * @adev: amdgpu_device pointer
- * @level: VMPT level
- *
- * Returns:
- * The number of entries in a page directory or page table.
- */
-static unsigned amdgpu_vm_num_entries(struct amdgpu_device *adev,
-				      unsigned level)
-{
-	unsigned shift = amdgpu_vm_level_shift(adev,
-					       adev->vm_manager.root_level);
-
-	if (level == adev->vm_manager.root_level)
-		/* For the root directory */
-		return round_up(adev->vm_manager.max_pfn, 1ULL << shift)
-			>> shift;
-	else if (level != AMDGPU_VM_PTB)
-		/* Everything in between */
-		return 512;
-	else
-		/* For the page tables on the leaves */
-		return AMDGPU_VM_PTE_COUNT(adev);
-}
-
-/**
- * amdgpu_vm_num_ats_entries - return the number of ATS entries in the root PD
- *
- * @adev: amdgpu_device pointer
- *
- * Returns:
- * The number of entries in the root page directory which needs the ATS setting.
- */
-static unsigned amdgpu_vm_num_ats_entries(struct amdgpu_device *adev)
-{
-	unsigned shift;
-
-	shift = amdgpu_vm_level_shift(adev, adev->vm_manager.root_level);
-	return AMDGPU_GMC_HOLE_START >> (shift + AMDGPU_GPU_PAGE_SHIFT);
-}
-
-/**
- * amdgpu_vm_entries_mask - the mask to get the entry number of a PD/PT
- *
- * @adev: amdgpu_device pointer
- * @level: VMPT level
- *
- * Returns:
- * The mask to extract the entry number of a PD/PT from an address.
- */
-static uint32_t amdgpu_vm_entries_mask(struct amdgpu_device *adev,
-				       unsigned int level)
-{
-	if (level <= adev->vm_manager.root_level)
-		return 0xffffffff;
-	else if (level != AMDGPU_VM_PTB)
-		return 0x1ff;
-	else
-		return AMDGPU_VM_PTE_COUNT(adev) - 1;
-}
-
-/**
- * amdgpu_vm_bo_size - returns the size of the BOs in bytes
- *
- * @adev: amdgpu_device pointer
- * @level: VMPT level
- *
- * Returns:
- * The size of the BO for a page directory or page table in bytes.
- */
-static unsigned amdgpu_vm_bo_size(struct amdgpu_device *adev, unsigned level)
-{
-	return AMDGPU_GPU_PAGE_ALIGN(amdgpu_vm_num_entries(adev, level) * 8);
-}
-
-/**
  * amdgpu_vm_bo_evicted - vm_bo is evicted
  *
  * @vm_bo: vm_bo which is evicted
@@ -358,9 +271,8 @@ static void amdgpu_vm_bo_done(struct amdgpu_vm_bo_base *vm_bo)
  * Initialize a bo_va_base structure and add it to the appropriate lists
  *
  */
-static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base,
-				   struct amdgpu_vm *vm,
-				   struct amdgpu_bo *bo)
+void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base,
+			    struct amdgpu_vm *vm, struct amdgpu_bo *bo)
 {
 	base->vm = vm;
 	base->bo = bo;
@@ -377,7 +289,7 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base,
 
 	dma_resv_assert_held(vm->root.bo->tbo.base.resv);
 
-	vm->bulk_moveable = false;
+	ttm_bo_set_bulk_move(&bo->tbo, &vm->lru_bulk_move);
 	if (bo->tbo.type == ttm_bo_type_kernel && bo->parent)
 		amdgpu_vm_bo_relocated(base);
 	else
@@ -396,228 +308,6 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base,
 }
 
 /**
- * amdgpu_vm_pt_parent - get the parent page directory
- *
- * @pt: child page table
- *
- * Helper to get the parent entry for the child page table. NULL if we are at
- * the root page directory.
- */
-static struct amdgpu_vm_bo_base *amdgpu_vm_pt_parent(struct amdgpu_vm_bo_base *pt)
-{
-	struct amdgpu_bo *parent = pt->bo->parent;
-
-	if (!parent)
-		return NULL;
-
-	return parent->vm_bo;
-}
-
-/*
- * amdgpu_vm_pt_cursor - state for for_each_amdgpu_vm_pt
- */
-struct amdgpu_vm_pt_cursor {
-	uint64_t pfn;
-	struct amdgpu_vm_bo_base *parent;
-	struct amdgpu_vm_bo_base *entry;
-	unsigned level;
-};
-
-/**
- * amdgpu_vm_pt_start - start PD/PT walk
- *
- * @adev: amdgpu_device pointer
- * @vm: amdgpu_vm structure
- * @start: start address of the walk
- * @cursor: state to initialize
- *
- * Initialize a amdgpu_vm_pt_cursor to start a walk.
- */
-static void amdgpu_vm_pt_start(struct amdgpu_device *adev,
-			       struct amdgpu_vm *vm, uint64_t start,
-			       struct amdgpu_vm_pt_cursor *cursor)
-{
-	cursor->pfn = start;
-	cursor->parent = NULL;
-	cursor->entry = &vm->root;
-	cursor->level = adev->vm_manager.root_level;
-}
-
-/**
- * amdgpu_vm_pt_descendant - go to child node
- *
- * @adev: amdgpu_device pointer
- * @cursor: current state
- *
- * Walk to the child node of the current node.
- * Returns:
- * True if the walk was possible, false otherwise.
- */
-static bool amdgpu_vm_pt_descendant(struct amdgpu_device *adev,
-				    struct amdgpu_vm_pt_cursor *cursor)
-{
-	unsigned mask, shift, idx;
-
-	if ((cursor->level == AMDGPU_VM_PTB) || !cursor->entry ||
-	    !cursor->entry->bo)
-		return false;
-
-	mask = amdgpu_vm_entries_mask(adev, cursor->level);
-	shift = amdgpu_vm_level_shift(adev, cursor->level);
-
-	++cursor->level;
-	idx = (cursor->pfn >> shift) & mask;
-	cursor->parent = cursor->entry;
-	cursor->entry = &to_amdgpu_bo_vm(cursor->entry->bo)->entries[idx];
-	return true;
-}
-
-/**
- * amdgpu_vm_pt_sibling - go to sibling node
- *
- * @adev: amdgpu_device pointer
- * @cursor: current state
- *
- * Walk to the sibling node of the current node.
- * Returns:
- * True if the walk was possible, false otherwise.
- */
-static bool amdgpu_vm_pt_sibling(struct amdgpu_device *adev,
-				 struct amdgpu_vm_pt_cursor *cursor)
-{
-	unsigned shift, num_entries;
-
-	/* Root doesn't have a sibling */
-	if (!cursor->parent)
-		return false;
-
-	/* Go to our parents and see if we got a sibling */
-	shift = amdgpu_vm_level_shift(adev, cursor->level - 1);
-	num_entries = amdgpu_vm_num_entries(adev, cursor->level - 1);
-
-	if (cursor->entry == &to_amdgpu_bo_vm(cursor->parent->bo)->entries[num_entries - 1])
-		return false;
-
-	cursor->pfn += 1ULL << shift;
-	cursor->pfn &= ~((1ULL << shift) - 1);
-	++cursor->entry;
-	return true;
-}
-
-/**
- * amdgpu_vm_pt_ancestor - go to parent node
- *
- * @cursor: current state
- *
- * Walk to the parent node of the current node.
- * Returns:
- * True if the walk was possible, false otherwise.
- */
-static bool amdgpu_vm_pt_ancestor(struct amdgpu_vm_pt_cursor *cursor)
-{
-	if (!cursor->parent)
-		return false;
-
-	--cursor->level;
-	cursor->entry = cursor->parent;
-	cursor->parent = amdgpu_vm_pt_parent(cursor->parent);
-	return true;
-}
-
-/**
- * amdgpu_vm_pt_next - get next PD/PT in hieratchy
- *
- * @adev: amdgpu_device pointer
- * @cursor: current state
- *
- * Walk the PD/PT tree to the next node.
- */
-static void amdgpu_vm_pt_next(struct amdgpu_device *adev,
-			      struct amdgpu_vm_pt_cursor *cursor)
-{
-	/* First try a newborn child */
-	if (amdgpu_vm_pt_descendant(adev, cursor))
-		return;
-
-	/* If that didn't worked try to find a sibling */
-	while (!amdgpu_vm_pt_sibling(adev, cursor)) {
-		/* No sibling, go to our parents and grandparents */
-		if (!amdgpu_vm_pt_ancestor(cursor)) {
-			cursor->pfn = ~0ll;
-			return;
-		}
-	}
-}
-
-/**
- * amdgpu_vm_pt_first_dfs - start a deep first search
- *
- * @adev: amdgpu_device structure
- * @vm: amdgpu_vm structure
- * @start: optional cursor to start with
- * @cursor: state to initialize
- *
- * Starts a deep first traversal of the PD/PT tree.
- */
-static void amdgpu_vm_pt_first_dfs(struct amdgpu_device *adev,
-				   struct amdgpu_vm *vm,
-				   struct amdgpu_vm_pt_cursor *start,
-				   struct amdgpu_vm_pt_cursor *cursor)
-{
-	if (start)
-		*cursor = *start;
-	else
-		amdgpu_vm_pt_start(adev, vm, 0, cursor);
-	while (amdgpu_vm_pt_descendant(adev, cursor));
-}
-
-/**
- * amdgpu_vm_pt_continue_dfs - check if the deep first search should continue
- *
- * @start: starting point for the search
- * @entry: current entry
- *
- * Returns:
- * True when the search should continue, false otherwise.
- */
-static bool amdgpu_vm_pt_continue_dfs(struct amdgpu_vm_pt_cursor *start,
-				      struct amdgpu_vm_bo_base *entry)
-{
-	return entry && (!start || entry != start->entry);
-}
-
-/**
- * amdgpu_vm_pt_next_dfs - get the next node for a deep first search
- *
- * @adev: amdgpu_device structure
- * @cursor: current state
- *
- * Move the cursor to the next node in a deep first search.
- */
-static void amdgpu_vm_pt_next_dfs(struct amdgpu_device *adev,
-				  struct amdgpu_vm_pt_cursor *cursor)
-{
-	if (!cursor->entry)
-		return;
-
-	if (!cursor->parent)
-		cursor->entry = NULL;
-	else if (amdgpu_vm_pt_sibling(adev, cursor))
-		while (amdgpu_vm_pt_descendant(adev, cursor));
-	else
-		amdgpu_vm_pt_ancestor(cursor);
-}
-
-/*
- * for_each_amdgpu_vm_pt_dfs_safe - safe deep first search of all PDs/PTs
- */
-#define for_each_amdgpu_vm_pt_dfs_safe(adev, vm, start, cursor, entry)		\
-	for (amdgpu_vm_pt_first_dfs((adev), (vm), (start), &(cursor)),		\
-	     (entry) = (cursor).entry, amdgpu_vm_pt_next_dfs((adev), &(cursor));\
-	     amdgpu_vm_pt_continue_dfs((start), (entry));			\
-	     (entry) = (cursor).entry, amdgpu_vm_pt_next_dfs((adev), &(cursor)))
-
-/**
  * amdgpu_vm_get_pd_bo - add the VM PD to a validation list
  *
  * @vm: vm providing the BOs
@@ -640,36 +330,6 @@ void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
 }
 
 /**
- * amdgpu_vm_del_from_lru_notify - update bulk_moveable flag
- *
- * @bo: BO which was removed from the LRU
- *
- * Make sure the bulk_moveable flag is updated when a BO is removed from the
- * LRU.
- */
-void amdgpu_vm_del_from_lru_notify(struct ttm_buffer_object *bo)
-{
-	struct amdgpu_bo *abo;
-	struct amdgpu_vm_bo_base *bo_base;
-
-	if (!amdgpu_bo_is_amdgpu_bo(bo))
-		return;
-
-	if (bo->pin_count)
-		return;
-
-	abo = ttm_to_amdgpu_bo(bo);
-	if (!abo->parent)
-		return;
-	for (bo_base = abo->vm_bo; bo_base; bo_base = bo_base->next) {
-		struct amdgpu_vm *vm = bo_base->vm;
-
-		if (abo->tbo.base.resv == vm->root.bo->tbo.base.resv)
-			vm->bulk_moveable = false;
-	}
-
-}
-/**
  * amdgpu_vm_move_to_lru_tail - move all BOs to the end of LRU
  *
  * @adev: amdgpu device pointer
@@ -681,35 +341,9 @@ void amdgpu_vm_del_from_lru_notify(struct ttm_buffer_object *bo)
 void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev,
 				struct amdgpu_vm *vm)
 {
-	struct amdgpu_vm_bo_base *bo_base;
-
-	if (vm->bulk_moveable) {
-		spin_lock(&adev->mman.bdev.lru_lock);
-		ttm_bo_bulk_move_lru_tail(&vm->lru_bulk_move);
-		spin_unlock(&adev->mman.bdev.lru_lock);
-		return;
-	}
-
-	memset(&vm->lru_bulk_move, 0, sizeof(vm->lru_bulk_move));
-
 	spin_lock(&adev->mman.bdev.lru_lock);
-	list_for_each_entry(bo_base, &vm->idle, vm_status) {
-		struct amdgpu_bo *bo = bo_base->bo;
-		struct amdgpu_bo *shadow = amdgpu_bo_shadowed(bo);
-
-		if (!bo->parent)
-			continue;
-
-		ttm_bo_move_to_lru_tail(&bo->tbo, bo->tbo.resource,
-					&vm->lru_bulk_move);
-		if (shadow)
-			ttm_bo_move_to_lru_tail(&shadow->tbo,
-						shadow->tbo.resource,
-						&vm->lru_bulk_move);
-	}
+	ttm_lru_bulk_move_tail(&vm->lru_bulk_move);
 	spin_unlock(&adev->mman.bdev.lru_lock);
-
-	vm->bulk_moveable = true;
 }
 
 /**
@@ -732,8 +366,6 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	struct amdgpu_vm_bo_base *bo_base, *tmp;
 	int r;
 
-	vm->bulk_moveable &= list_empty(&vm->evicted);
-
 	list_for_each_entry_safe(bo_base, tmp, &vm->evicted, vm_status) {
 		struct amdgpu_bo *bo = bo_base->bo;
 		struct amdgpu_bo *shadow = amdgpu_bo_shadowed(bo);
@@ -784,312 +416,6 @@ bool amdgpu_vm_ready(struct amdgpu_vm *vm)
 }
 
 /**
- * amdgpu_vm_clear_bo - initially clear the PDs/PTs
- *
- * @adev: amdgpu_device pointer
- * @vm: VM to clear BO from
- * @vmbo: BO to clear
- * @immediate: use an immediate update
- *
- * Root PD needs to be reserved when calling this.
- *
- * Returns:
- * 0 on success, errno otherwise.
- */
-static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
-			      struct amdgpu_vm *vm,
-			      struct amdgpu_bo_vm *vmbo,
-			      bool immediate)
-{
-	struct ttm_operation_ctx ctx = { true, false };
-	unsigned level = adev->vm_manager.root_level;
-	struct amdgpu_vm_update_params params;
-	struct amdgpu_bo *ancestor = &vmbo->bo;
-	struct amdgpu_bo *bo = &vmbo->bo;
-	unsigned entries, ats_entries;
-	uint64_t addr;
-	int r, idx;
-
-	/* Figure out our place in the hierarchy */
-	if (ancestor->parent) {
-		++level;
-		while (ancestor->parent->parent) {
-			++level;
-			ancestor = ancestor->parent;
-		}
-	}
-
-	entries = amdgpu_bo_size(bo) / 8;
-	if (!vm->pte_support_ats) {
-		ats_entries = 0;
-
-	} else if (!bo->parent) {
-		ats_entries = amdgpu_vm_num_ats_entries(adev);
-		ats_entries = min(ats_entries, entries);
-		entries -= ats_entries;
-
-	} else {
-		struct amdgpu_vm_bo_base *pt;
-
-		pt = ancestor->vm_bo;
-		ats_entries = amdgpu_vm_num_ats_entries(adev);
-		if ((pt - to_amdgpu_bo_vm(vm->root.bo)->entries) >= ats_entries) {
-			ats_entries = 0;
-		} else {
-			ats_entries = entries;
-			entries = 0;
-		}
-	}
-
-	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
-	if (r)
-		return r;
-
-	if (vmbo->shadow) {
-		struct amdgpu_bo *shadow = vmbo->shadow;
-
-		r = ttm_bo_validate(&shadow->tbo, &shadow->placement, &ctx);
-		if (r)
-			return r;
-	}
-
-	if (!drm_dev_enter(adev_to_drm(adev), &idx))
-		return -ENODEV;
-
-	r = vm->update_funcs->map_table(vmbo);
-	if (r)
-		goto exit;
-
-	memset(&params, 0, sizeof(params));
-	params.adev = adev;
-	params.vm = vm;
-	params.immediate = immediate;
-
-	r = vm->update_funcs->prepare(&params, NULL, AMDGPU_SYNC_EXPLICIT);
-	if (r)
-		goto exit;
-
-	addr = 0;
-	if (ats_entries) {
-		uint64_t value = 0, flags;
-
-		flags = AMDGPU_PTE_DEFAULT_ATC;
-		if (level != AMDGPU_VM_PTB) {
-			/* Handle leaf PDEs as PTEs */
-			flags |= AMDGPU_PDE_PTE;
-			amdgpu_gmc_get_vm_pde(adev, level, &value, &flags);
-		}
-
-		r = vm->update_funcs->update(&params, vmbo, addr, 0, ats_entries,
-					     value, flags);
-		if (r)
-			goto exit;
-
-		addr += ats_entries * 8;
-	}
-
-	if (entries) {
-		uint64_t value = 0, flags = 0;
-
-		if (adev->asic_type >= CHIP_VEGA10) {
-			if (level != AMDGPU_VM_PTB) {
-				/* Handle leaf PDEs as PTEs */
-				flags |= AMDGPU_PDE_PTE;
-				amdgpu_gmc_get_vm_pde(adev, level,
-						      &value, &flags);
-			} else {
-				/* Workaround for fault priority problem on GMC9 */
-				flags = AMDGPU_PTE_EXECUTABLE;
-			}
-		}
-
-		r = vm->update_funcs->update(&params, vmbo, addr, 0, entries,
-					     value, flags);
-		if (r)
-			goto exit;
-	}
-
-	r = vm->update_funcs->commit(&params, NULL);
-exit:
-	drm_dev_exit(idx);
-	return r;
-}
-
-/**
- * amdgpu_vm_pt_create - create bo for PD/PT
- *
- * @adev: amdgpu_device pointer
- * @vm: requesting vm
- * @level: the page table level
- * @immediate: use a immediate update
- * @vmbo: pointer to the buffer object pointer
- */
-static int amdgpu_vm_pt_create(struct amdgpu_device *adev,
-			       struct amdgpu_vm *vm,
-			       int level, bool immediate,
-			       struct amdgpu_bo_vm **vmbo)
-{
-	struct amdgpu_bo_param bp;
-	struct amdgpu_bo *bo;
-	struct dma_resv *resv;
-	unsigned int num_entries;
-	int r;
-
-	memset(&bp, 0, sizeof(bp));
-
-	bp.size = amdgpu_vm_bo_size(adev, level);
-	bp.byte_align = AMDGPU_GPU_PAGE_SIZE;
-	bp.domain = AMDGPU_GEM_DOMAIN_VRAM;
-	bp.domain = amdgpu_bo_get_preferred_domain(adev, bp.domain);
-	bp.flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS |
-		AMDGPU_GEM_CREATE_CPU_GTT_USWC;
-
-	if (level < AMDGPU_VM_PTB)
-		num_entries = amdgpu_vm_num_entries(adev, level);
-	else
-		num_entries = 0;
-
-	bp.bo_ptr_size = struct_size((*vmbo), entries, num_entries);
-
-	if (vm->use_cpu_for_update)
-		bp.flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
-
-	bp.type = ttm_bo_type_kernel;
-	bp.no_wait_gpu = immediate;
-	if (vm->root.bo)
-		bp.resv = vm->root.bo->tbo.base.resv;
-
-	r = amdgpu_bo_create_vm(adev, &bp, vmbo);
-	if (r)
-		return r;
-
-	bo = &(*vmbo)->bo;
-	if (vm->is_compute_context || (adev->flags & AMD_IS_APU)) {
-		(*vmbo)->shadow = NULL;
-		return 0;
-	}
-
-	if (!bp.resv)
-		WARN_ON(dma_resv_lock(bo->tbo.base.resv,
-				      NULL));
-	resv = bp.resv;
-	memset(&bp, 0, sizeof(bp));
-	bp.size = amdgpu_vm_bo_size(adev, level);
-	bp.domain = AMDGPU_GEM_DOMAIN_GTT;
-	bp.flags = AMDGPU_GEM_CREATE_CPU_GTT_USWC;
-	bp.type = ttm_bo_type_kernel;
-	bp.resv = bo->tbo.base.resv;
-	bp.bo_ptr_size = sizeof(struct amdgpu_bo);
-
-	r = amdgpu_bo_create(adev, &bp, &(*vmbo)->shadow);
-
-	if (!resv)
-		dma_resv_unlock(bo->tbo.base.resv);
-
-	if (r) {
-		amdgpu_bo_unref(&bo);
-		return r;
-	}
-
-	(*vmbo)->shadow->parent = amdgpu_bo_ref(bo);
-	amdgpu_bo_add_to_shadow_list(*vmbo);
-
-	return 0;
-}
-
-/**
- * amdgpu_vm_alloc_pts - Allocate a specific page table
- *
- * @adev: amdgpu_device pointer
- * @vm: VM to allocate page tables for
- * @cursor: Which page table to allocate
- * @immediate: use an immediate update
- *
- * Make sure a specific page table or directory is allocated.
- *
- * Returns:
- * 1 if page table needed to be allocated, 0 if page table was already
- * allocated, negative errno if an error occurred.
- */
-static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,
-			       struct amdgpu_vm *vm,
-			       struct amdgpu_vm_pt_cursor *cursor,
-			       bool immediate)
-{
-	struct amdgpu_vm_bo_base *entry = cursor->entry;
-	struct amdgpu_bo *pt_bo;
-	struct amdgpu_bo_vm *pt;
-	int r;
-
-	if (entry->bo)
-		return 0;
-
-	r = amdgpu_vm_pt_create(adev, vm, cursor->level, immediate, &pt);
-	if (r)
-		return r;
-
-	/* Keep a reference to the root directory to avoid
-	 * freeing them up in the wrong order.
-	 */
-	pt_bo = &pt->bo;
-	pt_bo->parent = amdgpu_bo_ref(cursor->parent->bo);
-	amdgpu_vm_bo_base_init(entry, vm, pt_bo);
-	r = amdgpu_vm_clear_bo(adev, vm, pt, immediate);
-	if (r)
-		goto error_free_pt;
-
-	return 0;
-
-error_free_pt:
-	amdgpu_bo_unref(&pt->shadow);
-	amdgpu_bo_unref(&pt_bo);
-	return r;
-}
-
-/**
- * amdgpu_vm_free_table - fre one PD/PT
- *
- * @entry: PDE to free
- */
-static void amdgpu_vm_free_table(struct amdgpu_vm_bo_base *entry)
-{
-	struct amdgpu_bo *shadow;
-
-	if (!entry->bo)
-		return;
-	shadow = amdgpu_bo_shadowed(entry->bo);
-	entry->bo->vm_bo = NULL;
-	list_del(&entry->vm_status);
-	amdgpu_bo_unref(&shadow);
-	amdgpu_bo_unref(&entry->bo);
-}
-
-/**
- * amdgpu_vm_free_pts - free PD/PT levels
- *
- * @adev: amdgpu device structure
- * @vm: amdgpu vm structure
- * @start: optional cursor where to start freeing PDs/PTs
- *
- * Free the page directory or page table level and all sub levels.
- */
-static void amdgpu_vm_free_pts(struct amdgpu_device *adev,
-			       struct amdgpu_vm *vm,
-			       struct amdgpu_vm_pt_cursor *start)
-{
-	struct amdgpu_vm_pt_cursor cursor;
-	struct amdgpu_vm_bo_base *entry;
-
-	vm->bulk_moveable = false;
-
-	for_each_amdgpu_vm_pt_dfs_safe(adev, vm, start, cursor, entry)
-		amdgpu_vm_free_table(entry);
-
-	if (start)
-		amdgpu_vm_free_table(start->entry);
-}
-
-/**
  * amdgpu_vm_check_compute_bug - check whether asic has compute vm bug
  *
  * @adev: amdgpu_device pointer
@@ -1255,7 +581,8 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
 	}
 	dma_fence_put(fence);
 
-	if (ring->funcs->emit_gds_switch && gds_switch_needed) {
+	if (!ring->is_mes_queue && ring->funcs->emit_gds_switch &&
+	    gds_switch_needed) {
 		id->gds_base = job->gds_base;
 		id->gds_size = job->gds_size;
 		id->gws_base = job->gws_base;
@@ -1336,53 +663,6 @@ uint64_t amdgpu_vm_map_gart(const dma_addr_t *pages_addr, uint64_t addr)
 }
 
 /**
- * amdgpu_vm_update_pde - update a single level in the hierarchy
- *
- * @params: parameters for the update
- * @vm: requested vm
- * @entry: entry to update
- *
- * Makes sure the requested entry in parent is up to date.
- */
-static int amdgpu_vm_update_pde(struct amdgpu_vm_update_params *params,
-				struct amdgpu_vm *vm,
-				struct amdgpu_vm_bo_base *entry)
-{
-	struct amdgpu_vm_bo_base *parent = amdgpu_vm_pt_parent(entry);
-	struct amdgpu_bo *bo = parent->bo, *pbo;
-	uint64_t pde, pt, flags;
-	unsigned level;
-
-	for (level = 0, pbo = bo->parent; pbo; ++level)
-		pbo = pbo->parent;
-
-	level += params->adev->vm_manager.root_level;
-	amdgpu_gmc_get_pde_for_bo(entry->bo, level, &pt, &flags);
-	pde = (entry - to_amdgpu_bo_vm(parent->bo)->entries) * 8;
-	return vm->update_funcs->update(params, to_amdgpu_bo_vm(bo), pde, pt,
-					1, 0, flags);
-}
-
-/**
- * amdgpu_vm_invalidate_pds - mark all PDs as invalid
- *
- * @adev: amdgpu_device pointer
- * @vm: related vm
- *
- * Mark all PD level as invalid after an error.
- */
-static void amdgpu_vm_invalidate_pds(struct amdgpu_device *adev,
-				     struct amdgpu_vm *vm)
-{
-	struct amdgpu_vm_pt_cursor cursor;
-	struct amdgpu_vm_bo_base *entry;
-
-	for_each_amdgpu_vm_pt_dfs_safe(adev, vm, NULL, cursor, entry)
-		if (entry->bo && !entry->moved)
-			amdgpu_vm_bo_relocated(entry);
-}
-
-/**
  * amdgpu_vm_update_pdes - make sure that all directories are valid
  *
  * @adev: amdgpu_device pointer
@@ -1398,6 +678,7 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
 			  struct amdgpu_vm *vm, bool immediate)
 {
 	struct amdgpu_vm_update_params params;
+	struct amdgpu_vm_bo_base *entry;
 	int r, idx;
 
 	if (list_empty(&vm->relocated))
@@ -1413,17 +694,10 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
 
 	r = vm->update_funcs->prepare(&params, NULL, AMDGPU_SYNC_EXPLICIT);
 	if (r)
-		goto exit;
-
-	while (!list_empty(&vm->relocated)) {
-		struct amdgpu_vm_bo_base *entry;
-
-		entry = list_first_entry(&vm->relocated,
-					 struct amdgpu_vm_bo_base,
-					 vm_status);
-		amdgpu_vm_bo_idle(entry);
+		goto error;
 
-		r = amdgpu_vm_update_pde(&params, vm, entry);
+	list_for_each_entry(entry, &vm->relocated, vm_status) {
+		r = amdgpu_vm_pde_update(&params, entry);
 		if (r)
 			goto error;
 	}
@@ -1431,297 +705,71 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
 	r = vm->update_funcs->commit(&params, &vm->last_update);
 	if (r)
 		goto error;
-	drm_dev_exit(idx);
-	return 0;
-
-error:
-	amdgpu_vm_invalidate_pds(adev, vm);
-exit:
-	drm_dev_exit(idx);
-	return r;
-}
-
-/*
- * amdgpu_vm_update_flags - figure out flags for PTE updates
- *
- * Make sure to set the right flags for the PTEs at the desired level.
- */
-static void amdgpu_vm_update_flags(struct amdgpu_vm_update_params *params,
-				   struct amdgpu_bo_vm *pt, unsigned int level,
-				   uint64_t pe, uint64_t addr,
-				   unsigned int count, uint32_t incr,
-				   uint64_t flags)
-
-{
-	if (level != AMDGPU_VM_PTB) {
-		flags |= AMDGPU_PDE_PTE;
-		amdgpu_gmc_get_vm_pde(params->adev, level, &addr, &flags);
 
-	} else if (params->adev->asic_type >= CHIP_VEGA10 &&
-		   !(flags & AMDGPU_PTE_VALID) &&
-		   !(flags & AMDGPU_PTE_PRT)) {
+	/* vm_flush_needed after updating PDEs */
+	atomic64_inc(&vm->tlb_seq);
 
-		/* Workaround for fault priority problem on GMC9 */
-		flags |= AMDGPU_PTE_EXECUTABLE;
+	while (!list_empty(&vm->relocated)) {
+		entry = list_first_entry(&vm->relocated,
+					 struct amdgpu_vm_bo_base,
+					 vm_status);
+		amdgpu_vm_bo_idle(entry);
 	}
 
-	params->vm->update_funcs->update(params, pt, pe, addr, count, incr,
-					 flags);
+error:
+	drm_dev_exit(idx);
+	return r;
 }
 
 /**
- * amdgpu_vm_fragment - get fragment for PTEs
+ * amdgpu_vm_tlb_seq_cb - make sure to increment tlb sequence
+ * @fence: unused
+ * @cb: the callback structure
  *
- * @params: see amdgpu_vm_update_params definition
- * @start: first PTE to handle
- * @end: last PTE to handle
- * @flags: hw mapping flags
- * @frag: resulting fragment size
- * @frag_end: end of this fragment
- *
- * Returns the first possible fragment for the start and end address.
+ * Increments the tlb sequence to make sure that future CS execute a VM flush.
  */
-static void amdgpu_vm_fragment(struct amdgpu_vm_update_params *params,
-			       uint64_t start, uint64_t end, uint64_t flags,
-			       unsigned int *frag, uint64_t *frag_end)
+static void amdgpu_vm_tlb_seq_cb(struct dma_fence *fence,
+				 struct dma_fence_cb *cb)
 {
-	/**
-	 * The MC L1 TLB supports variable sized pages, based on a fragment
-	 * field in the PTE. When this field is set to a non-zero value, page
-	 * granularity is increased from 4KB to (1 << (12 + frag)). The PTE
-	 * flags are considered valid for all PTEs within the fragment range
-	 * and corresponding mappings are assumed to be physically contiguous.
-	 *
-	 * The L1 TLB can store a single PTE for the whole fragment,
-	 * significantly increasing the space available for translation
-	 * caching. This leads to large improvements in throughput when the
-	 * TLB is under pressure.
-	 *
-	 * The L2 TLB distributes small and large fragments into two
-	 * asymmetric partitions. The large fragment cache is significantly
-	 * larger. Thus, we try to use large fragments wherever possible.
-	 * Userspace can support this by aligning virtual base address and
-	 * allocation size to the fragment size.
-	 *
-	 * Starting with Vega10 the fragment size only controls the L1. The L2
-	 * is now directly feed with small/huge/giant pages from the walker.
-	 */
-	unsigned max_frag;
+	struct amdgpu_vm_tlb_seq_cb *tlb_cb;
 
-	if (params->adev->asic_type < CHIP_VEGA10)
-		max_frag = params->adev->vm_manager.fragment_size;
-	else
-		max_frag = 31;
-
-	/* system pages are non continuously */
-	if (params->pages_addr) {
-		*frag = 0;
-		*frag_end = end;
-		return;
-	}
-
-	/* This intentionally wraps around if no bit is set */
-	*frag = min((unsigned)ffs(start) - 1, (unsigned)fls64(end - start) - 1);
-	if (*frag >= max_frag) {
-		*frag = max_frag;
-		*frag_end = end & ~((1ULL << max_frag) - 1);
-	} else {
-		*frag_end = start + (1 << *frag);
-	}
+	tlb_cb = container_of(cb, typeof(*tlb_cb), cb);
+	atomic64_inc(&tlb_cb->vm->tlb_seq);
+	kfree(tlb_cb);
 }
 
 /**
- * amdgpu_vm_update_ptes - make sure that page tables are valid
+ * amdgpu_vm_update_range - update a range in the vm page table
  *
- * @params: see amdgpu_vm_update_params definition
- * @start: start of GPU address range
- * @end: end of GPU addr