Merge tag 'drm-fixes-2022-07-15' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "This is the regular fixes pull for this week. This has a bunch of
  amdgpu fixes, major one reverts the buddy allocator until it can be
  tested more, otherwise just small ones, then i915 has a bunch of
  fixes.

  The outstanding firmware regressions reported by phoronix will
  hopefully be dealt with ASAP.

  amdgpu:
   - revert buddy allocator support for now
   - DP MST blank screen fix for specific platforms
   - MEC firmware check fix for GC 10.3.7
   - Deep color fix for DCE
   - Fix possible divide by 0
   - Coverage blend mode fix
   - Fix cursor only commit timestamps

  i915:
   - Selftest fix
   - TTM fix sg_table construction
   - Error return fixes
   - Fix a performance regression related to waitboost
   - Fix GT resets"

* tag 'drm-fixes-2022-07-15' of git://anongit.freedesktop.org/drm/drm:
  drm/amd/display: Ensure valid event timestamp for cursor-only commits
  drm/amd/display: correct check of coverage blend mode
  drm/amd/pm: Prevent divide by zero
  drm/amd/display: Only use depth 36 bpp linebuffers on DCN display engines.
  drm/amdkfd: correct the MEC atomic support firmware checking for GC 10.3.7
  drm/amd/display: Ignore First MST Sideband Message Return Error
  drm/i915/selftests: fix subtraction overflow bug
  drm/i915/gem: Look for waitboosting across the whole object prior to individual waits
  drm/i915/gt: Serialize TLB invalidates with GT resets
  drm/i915/gt: Serialize GRDOM access between multiple engine resets
  drm/i915/ttm: fix sg_table construction
  drm/i915/selftests: fix a couple IS_ERR() vs NULL tests
  drm/i915: Fix vm use-after-free in vma destruction
  drm/i915/guc: ADL-N should use the same GuC FW as ADL-S
  drm/i915: fix a possible refcount leak in intel_dp_add_mst_connector()
  drm/i915/gvt: IS_ERR() vs NULL bug in intel_gvt_update_reg_whitelist()
  Revert "drm/amdgpu: add drm buddy support to amdgpu"

24 files changed, 433 insertions, 422 deletions

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index e88c497fa010..f65656df3619 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -256,7 +256,6 @@ config DRM_AMDGPU
 	select HWMON
 	select BACKLIGHT_CLASS_DEVICE
 	select INTERVAL_TREE
-	select DRM_BUDDY
 	help
 	  Choose this option if you have a recent AMD Radeon graphics card.
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
index 6546552e596c..acfa207cf970 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
@@ -30,15 +30,12 @@
 #include <drm/ttm/ttm_resource.h>
 #include <drm/ttm/ttm_range_manager.h>
 
-#include "amdgpu_vram_mgr.h"
-
 /* state back for walking over vram_mgr and gtt_mgr allocations */
 struct amdgpu_res_cursor {
 	uint64_t		start;
 	uint64_t		size;
 	uint64_t		remaining;
-	void			*node;
-	uint32_t		mem_type;
+	struct drm_mm_node	*node;
 };
 
 /**
@@ -55,63 +52,27 @@ static inline void amdgpu_res_first(struct ttm_resource *res,
 				    uint64_t start, uint64_t size,
 				    struct amdgpu_res_cursor *cur)
 {
-	struct drm_buddy_block *block;
-	struct list_head *head, *next;
 	struct drm_mm_node *node;
 
-	if (!res)
-		goto fallback;
-
-	BUG_ON(start + size > res->num_pages << PAGE_SHIFT);
-
-	cur->mem_type = res->mem_type;
-
-	switch (cur->mem_type) {
-	case TTM_PL_VRAM:
-		head = &to_amdgpu_vram_mgr_resource(res)->blocks;
-
-		block = list_first_entry_or_null(head,
-						 struct drm_buddy_block,
-						 link);
-		if (!block)
-			goto fallback;
-
-		while (start >= amdgpu_vram_mgr_block_size(block)) {
-			start -= amdgpu_vram_mgr_block_size(block);
-
-			next = block->link.next;
-			if (next != head)
-				block = list_entry(next, struct drm_buddy_block, link);
-		}
-
-		cur->start = amdgpu_vram_mgr_block_start(block) + start;
-		cur->size = min(amdgpu_vram_mgr_block_size(block) - start, size);
-		cur->remaining = size;
-		cur->node = block;
-		break;
-	case TTM_PL_TT:
-		node = to_ttm_range_mgr_node(res)->mm_nodes;
-		while (start >= node->size << PAGE_SHIFT)
-			start -= node++->size << PAGE_SHIFT;
-
-		cur->start = (node->start << PAGE_SHIFT) + start;
-		cur->size = min((node->size << PAGE_SHIFT) - start, size);
+	if (!res || res->mem_type == TTM_PL_SYSTEM) {
+		cur->start = start;
+		cur->size = size;
 		cur->remaining = size;
-		cur->node = node;
-		break;
-	default:
-		goto fallback;
+		cur->node = NULL;
+		WARN_ON(res && start + size > res->num_pages << PAGE_SHIFT);
+		return;
 	}
 
-	return;
+	BUG_ON(start + size > res->num_pages << PAGE_SHIFT);
 
-fallback:
-	cur->start = start;
-	cur->size = size;
+	node = to_ttm_range_mgr_node(res)->mm_nodes;
+	while (start >= node->size << PAGE_SHIFT)
+		start -= node++->size << PAGE_SHIFT;
+
+	cur->start = (node->start << PAGE_SHIFT) + start;
+	cur->size = min((node->size << PAGE_SHIFT) - start, size);
 	cur->remaining = size;
-	cur->node = NULL;
-	WARN_ON(res && start + size > res->num_pages << PAGE_SHIFT);
-	return;
+	cur->node = node;
 }
 
 /**
@@ -124,9 +85,7 @@ fallback:
  */
 static inline void amdgpu_res_next(struct amdgpu_res_cursor *cur, uint64_t size)
 {
-	struct drm_buddy_block *block;
-	struct drm_mm_node *node;
-	struct list_head *next;
+	struct drm_mm_node *node = cur->node;
 
 	BUG_ON(size > cur->remaining);
 
@@ -140,27 +99,9 @@ static inline void amdgpu_res_next(struct amdgpu_res_cursor *cur, uint64_t size)
 		return;
 	}
 
-	switch (cur->mem_type) {
-	case TTM_PL_VRAM:
-		block = cur->node;
-
-		next = block->link.next;
-		block = list_entry(next, struct drm_buddy_block, link);
-
-		cur->node = block;
-		cur->start = amdgpu_vram_mgr_block_start(block);
-		cur->size = min(amdgpu_vram_mgr_block_size(block), cur->remaining);
-		break;
-	case TTM_PL_TT:
-		node = cur->node;
-
-		cur->node = ++node;
-		cur->start = node->start << PAGE_SHIFT;
-		cur->size = min(node->size << PAGE_SHIFT, cur->remaining);
-		break;
-	default:
-		return;
-	}
+	cur->node = ++node;
+	cur->start = node->start << PAGE_SHIFT;
+	cur->size = min(node->size << PAGE_SHIFT, cur->remaining);
 }
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index 6a70818039dd..9120ae80ef52 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -26,7 +26,6 @@
 
 #include <linux/dma-direction.h>
 #include <drm/gpu_scheduler.h>
-#include "amdgpu_vram_mgr.h"
 #include "amdgpu.h"
 
 #define AMDGPU_PL_GDS		(TTM_PL_PRIV + 0)
@@ -39,6 +38,15 @@
 
 #define AMDGPU_POISON	0xd0bed0be
 
+struct amdgpu_vram_mgr {
+	struct ttm_resource_manager manager;
+	struct drm_mm mm;
+	spinlock_t lock;
+	struct list_head reservations_pending;
+	struct list_head reserved_pages;
+	atomic64_t vis_usage;
+};
+
 struct amdgpu_gtt_mgr {
 	struct ttm_resource_manager manager;
 	struct drm_mm mm;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 49e4092f447f..0a7611648573 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -32,10 +32,8 @@
 #include "atom.h"
 
 struct amdgpu_vram_reservation {
-	u64 start;
-	u64 size;
-	struct list_head allocated;
-	struct list_head blocks;
+	struct list_head node;
+	struct drm_mm_node mm_node;
 };
 
 static inline struct amdgpu_vram_mgr *
@@ -188,18 +186,18 @@ const struct attribute_group amdgpu_vram_mgr_attr_group = {
 };
 
 /**
- * amdgpu_vram_mgr_vis_size - Calculate visible block size
+ * amdgpu_vram_mgr_vis_size - Calculate visible node size
  *
  * @adev: amdgpu_device pointer
- * @block: DRM BUDDY block structure
+ * @node: MM node structure
  *
- * Calculate how many bytes of the DRM BUDDY block are inside visible VRAM
+ * Calculate how many bytes of the MM node are inside visible VRAM
  */
 static u64 amdgpu_vram_mgr_vis_size(struct amdgpu_device *adev,
-				    struct drm_buddy_block *block)
+				    struct drm_mm_node *node)
 {
-	u64 start = amdgpu_vram_mgr_block_start(block);
-	u64 end = start + amdgpu_vram_mgr_block_size(block);
+	uint64_t start = node->start << PAGE_SHIFT;
+	uint64_t end = (node->size + node->start) << PAGE_SHIFT;
 
 	if (start >= adev->gmc.visible_vram_size)
 		return 0;
@@ -220,9 +218,9 @@ u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	struct ttm_resource *res = bo->tbo.resource;
-	struct amdgpu_vram_mgr_resource *vres = to_amdgpu_vram_mgr_resource(res);
-	struct drm_buddy_block *block;
-	u64 usage = 0;
+	unsigned pages = res->num_pages;
+	struct drm_mm_node *mm;
+	u64 usage;
 
 	if (amdgpu_gmc_vram_full_visible(&adev->gmc))
 		return amdgpu_bo_size(bo);
@@ -230,8 +228,9 @@ u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo)
 	if (res->start >= adev->gmc.visible_vram_size >> PAGE_SHIFT)
 		return 0;
 
-	list_for_each_entry(block, &vres->blocks, link)
-		usage += amdgpu_vram_mgr_vis_size(adev, block);
+	mm = &container_of(res, struct ttm_range_mgr_node, base)->mm_nodes[0];
+	for (usage = 0; pages; pages -= mm->size, mm++)
+		usage += amdgpu_vram_mgr_vis_size(adev, mm);
 
 	return usage;
 }
@@ -241,30 +240,23 @@ static void amdgpu_vram_mgr_do_reserve(struct ttm_resource_manager *man)
 {
 	struct amdgpu_vram_mgr *mgr = to_vram_mgr(man);
 	struct amdgpu_device *adev = to_amdgpu_device(mgr);
-	struct drm_buddy *mm = &mgr->mm;
+	struct drm_mm *mm = &mgr->mm;
 	struct amdgpu_vram_reservation *rsv, *temp;
-	struct drm_buddy_block *block;
 	uint64_t vis_usage;
 
-	list_for_each_entry_safe(rsv, temp, &mgr->reservations_pending, blocks) {
-		if (drm_buddy_alloc_blocks(mm, rsv->start, rsv->start + rsv->size,
-					   rsv->size, mm->chunk_size, &rsv->allocated,
-					   DRM_BUDDY_RANGE_ALLOCATION))
-			continue;
-
-		block = amdgpu_vram_mgr_first_block(&rsv->allocated);
-		if (!block)
+	list_for_each_entry_safe(rsv, temp, &mgr->reservations_pending, node) {
+		if (drm_mm_reserve_node(mm, &rsv->mm_node))
 			continue;
 
 		dev_dbg(adev->dev, "Reservation 0x%llx - %lld, Succeeded\n",
-			rsv->start, rsv->size);
+			rsv->mm_node.start, rsv->mm_node.size);
 
-		vis_usage = amdgpu_vram_mgr_vis_size(adev, block);
+		vis_usage = amdgpu_vram_mgr_vis_size(adev, &rsv->mm_node);
 		atomic64_add(vis_usage, &mgr->vis_usage);
 		spin_lock(&man->bdev->lru_lock);
-		man->usage += rsv->size;
+		man->usage += rsv->mm_node.size << PAGE_SHIFT;
 		spin_unlock(&man->bdev->lru_lock);
-		list_move(&rsv->blocks, &mgr->reserved_pages);
+		list_move(&rsv->node, &mgr->reserved_pages);
 	}
 }
 
@@ -286,16 +278,14 @@ int amdgpu_vram_mgr_reserve_range(struct amdgpu_vram_mgr *mgr,
 	if (!rsv)
 		return -ENOMEM;
 
-	INIT_LIST_HEAD(&rsv->allocated);
-	INIT_LIST_HEAD(&rsv->blocks);
+	INIT_LIST_HEAD(&rsv->node);
+	rsv->mm_node.start = start >> PAGE_SHIFT;
+	rsv->mm_node.size = size >> PAGE_SHIFT;
 
-	rsv->start = start;
-	rsv->size = size;
-
-	mutex_lock(&mgr->lock);
-	list_add_tail(&rsv->blocks, &mgr->reservations_pending);
+	spin_lock(&mgr->lock);
+	list_add_tail(&rsv->node, &mgr->reservations_pending);
 	amdgpu_vram_mgr_do_reserve(&mgr->manager);
-	mutex_unlock(&mgr->lock);
+	spin_unlock(&mgr->lock);
 
 	return 0;
 }
@@ -317,19 +307,19 @@ int amdgpu_vram_mgr_query_page_status(struct amdgpu_vram_mgr *mgr,
 	struct amdgpu_vram_reservation *rsv;
 	int ret;
 
-	mutex_lock(&mgr->lock);
+	spin_lock(&mgr->lock);
 
-	list_for_each_entry(rsv, &mgr->reservations_pending, blocks) {
-		if (rsv->start <= start &&
-		    (start < (rsv->start + rsv->size))) {
+	list_for_each_entry(rsv, &mgr->reservations_pending, node) {
+		if ((rsv->mm_node.start <= start) &&
+		    (start < (rsv->mm_node.start + rsv->mm_node.size))) {
 			ret = -EBUSY;
 			goto out;
 		}
 	}
 
-	list_for_each_entry(rsv, &mgr->reserved_pages, blocks) {
-		if (rsv->start <= start &&
-		    (start < (rsv->start + rsv->size))) {
+	list_for_each_entry(rsv, &mgr->reserved_pages, node) {
+		if ((rsv->mm_node.start <= start) &&
+		    (start < (rsv->mm_node.start + rsv->mm_node.size))) {
 			ret = 0;
 			goto out;
 		}
@@ -337,11 +327,33 @@ int amdgpu_vram_mgr_query_page_status(struct amdgpu_vram_mgr *mgr,
 
 	ret = -ENOENT;
 out:
-	mutex_unlock(&mgr->lock);
+	spin_unlock(&mgr->lock);
 	return ret;
 }
 
 /**
+ * amdgpu_vram_mgr_virt_start - update virtual start address
+ *
+ * @mem: ttm_resource to update
+ * @node: just allocated node
+ *
+ * Calculate a virtual BO start address to easily check if everything is CPU
+ * accessible.
+ */
+static void amdgpu_vram_mgr_virt_start(struct ttm_resource *mem,
+				       struct drm_mm_node *node)
+{
+	unsigned long start;
+
+	start = node->start + node->size;
+	if (start > mem->num_pages)
+		start -= mem->num_pages;
+	else
+		start = 0;
+	mem->start = max(mem->start, start);
+}
+
+/**
  * amdgpu_vram_mgr_new - allocate new ranges
  *
  * @man: TTM memory type manager
@@ -356,44 +368,46 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 			       const struct ttm_place *place,
 			       struct ttm_resource **res)
 {
-	u64 vis_usage = 0, max_bytes, cur_size, min_block_size;
+	unsigned long lpfn, num_nodes, pages_per_node, pages_left, pages;
 	struct amdgpu_vram_mgr *mgr = to_vram_mgr(man);
 	struct amdgpu_device *adev = to_amdgpu_device(mgr);
-	struct amdgpu_vram_mgr_resource *vres;
-	u64 size, remaining_size, lpfn, fpfn;
-	struct drm_buddy *mm = &mgr->mm;
-	struct drm_buddy_block *block;
-	unsigned long pages_per_block;
+	uint64_t vis_usage = 0, mem_bytes, max_bytes;
+	struct ttm_range_mgr_node *node;
+	struct drm_mm *mm = &mgr->mm;
+	enum drm_mm_insert_mode mode;
+	unsigned i;
 	int r;
 
-	lpfn = place->lpfn << PAGE_SHIFT;
+	lpfn = place->lpfn;
 	if (!lpfn)
-		lpfn = man->size;
-
-	fpfn = place->fpfn << PAGE_SHIFT;
+		lpfn = man->size >> PAGE_SHIFT;
 
 	max_bytes = adev->gmc.mc_vram_size;
 	if (tbo->type != ttm_bo_type_kernel)
 		max_bytes -= AMDGPU_VM_RESERVED_VRAM;
 
+	mem_bytes = tbo->base.size;
 	if (place->flags & TTM_PL_FLAG_CONTIGUOUS) {
-		pages_per_block = ~0ul;
+		pages_per_node = ~0ul;
+		num_nodes = 1;
 	} else {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		pages_per_block = HPAGE_PMD_NR;
+		pages_per_node = HPAGE_PMD_NR;
 #else
 		/* default to 2MB */
-		pages_per_block = 2UL << (20UL - PAGE_SHIFT);
+		pages_per_node = 2UL << (20UL - PAGE_SHIFT);
 #endif
-		pages_per_block = max_t(uint32_t, pages_per_block,
-					tbo->page_alignment);
+		pages_per_node = max_t(uint32_t, pages_per_node,
+				       tbo->page_alignment);
+		num_nodes = DIV_ROUND_UP_ULL(PFN_UP(mem_bytes), pages_per_node);
 	}
 
-	vres = kzalloc(sizeof(*vres), GFP_KERNEL);
-	if (!vres)
+	node = kvmalloc(struct_size(node, mm_nodes, num_nodes),
+			GFP_KERNEL | __GFP_ZERO);
+	if (!node)
 		return -ENOMEM;
 
-	ttm_resource_init(tbo, place, &vres->base);
+	ttm_resource_init(tbo, place, &node->base);
 
 	/* bail out quickly if there's likely not enough VRAM for this BO */
 	if (ttm_resource_manager_usage(man) > max_bytes) {
@@ -401,130 +415,66 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 		goto error_fini;
 	}
 
-	INIT_LIST_HEAD(&vres->blocks);
-
+	mode = DRM_MM_INSERT_BEST;
 	if (place->flags & TTM_PL_FLAG_TOPDOWN)
-		vres->flags |= DRM_BUDDY_TOPDOWN_ALLOCATION;
-
-	if (fpfn || lpfn != man->size)
-		/* Allocate blocks in desired range */
-		vres->flags |= DRM_BUDDY_RANGE_ALLOCATION;
-
-	remaining_size = vres->base.num_pages << PAGE_SHIFT;
-
-	mutex_lock(&mgr->lock);
-	while (remaining_size) {
-		if (tbo->page_alignment)
-			min_block_size = tbo->page_alignment << PAGE_SHIFT;
-		else
-			min_block_size = mgr->default_page_size;
-
-		BUG_ON(min_block_size < mm->chunk_size);
-
-		/* Limit maximum size to 2GiB due to SG table limitations */
-		size = min(remaining_size, 2ULL << 30);
-
-		if (size >= pages_per_block << PAGE_SHIFT)
-			min_block_size = pages_per_block << PAGE_SHIFT;
-
-		cur_size = size;
-
-		if (fpfn + size != place->lpfn << PAGE_SHIFT) {
-			/*
-			 * Except for actual range allocation, modify the size and
-			 * min_block_size conforming to continuous flag enablement
-			 */
-			if (place->flags & TTM_PL_FLAG_CONTIGUOUS) {
-				size = roundup_pow_of_two(size);
-				min_block_size = size;
-			/*
-			 * Modify the size value if size is not
-			 * aligned with min_block_size
-			 */
-			} else if (!IS_ALIGNED(size, min_block_size)) {
-				size = round_up(size, min_block_size);
+		mode = DRM_MM_INSERT_HIGH;
+
+	pages_left = node->base.num_pages;
+
+	/* Limit maximum size to 2GB due to SG table limitations */
+	pages = min(pages_left, 2UL << (30 - PAGE_SHIFT));
+
+	i = 0;
+	spin_lock(&mgr->lock);
+	while (pages_left) {
+		uint32_t alignment = tbo->page_alignment;
+
+		if (pages >= pages_per_node)
+			alignment = pages_per_node;
+
+		r = drm_mm_insert_node_in_range(mm, &node->mm_nodes[i], pages,
+						alignment, 0, place->fpfn,
+						lpfn, mode);
+		if (unlikely(r)) {
+			if (pages > pages_per_node) {
+				if (is_power_of_2(pages))
+					pages = pages / 2;
+				else
+					pages = rounddown_pow_of_two(pages);
+				continue;
 			}
+			goto error_free;
 		}
 
-		r = drm_buddy_alloc_blocks(mm, fpfn,
-					   lpfn,
-					   size,
-					   min_block_size,
-					   &vres->blocks,
-					   vres->flags);
-		if (unlikely(r))
-			goto error_free_blocks;
-
-		if (size > remaining_size)
-			remaining_size = 0;
-		else
-			remaining_size -= size;
-	}
-	mutex_unlock(&mgr->lock);
-
-	if (cur_size != size) {
-		struct drm_buddy_block *block;
-		struct list_head *trim_list;
-		u64 original_size;
-		LIST_HEAD(temp);
-
-		trim_list = &vres->blocks;
-		original_size = vres->base.num_pages << PAGE_SHIFT;
-
-		/*
-		 * If size value is rounded up to min_block_size, trim the last
-		 * block to the required size
-		 */
-		if (!list_is_singular(&vres->blocks)) {
-			block = list_last_entry(&vres->blocks, typeof(*block), link);
-			list_move_tail(&block->link, &temp);
-			trim_list = &temp;
-			/*
-			 * Compute the original_size value by subtracting the
-			 * last block size with (aligned size - original size)
-			 */
-			original_size = amdgpu_vram_mgr_block_size(block) - (size - cur_size);
-		}
+		vis_usage += amdgpu_vram_mgr_vis_size(adev, &node->mm_nodes[i]);
+		amdgpu_vram_mgr_virt_start(&node->base, &node->mm_nodes[i]);
+		pages_left -= pages;
+		++i;
 
-		mutex_lock(&mgr->lock);
-		drm_buddy_block_trim(mm,
-				     original_size,
-				     trim_list);
-		mutex_unlock(&mgr->lock);
-
-		if (!list_empty(&temp))
-			list_splice_tail(trim_list, &vres->blocks);
-	}
-
-	list_for_each_entry(block, &vres->blocks, link)
-		vis_usage += amdgpu_vram_mgr_vis_size(adev, block);
-
-	block = amdgpu_vram_mgr_first_block(&vres->blocks);
-	if (!block) {
-		r = -EINVAL;
-		goto error_fini;
+		if (pages > pages_left)
+			pages = pages_left;
 	}
+	spin_unlock(&mgr->lock);
 
-	vres->base.start = amdgpu_vram_mgr_block_start(block) >> PAGE_SHIFT;
-
-	if (amdgpu_is_vram_mgr_blocks_contiguous(&vres->blocks))
-		vres->base.placement |= TTM_PL_FLAG_CONTIGUOUS;
+	if (i == 1)
+		node->base.placement |= TTM_PL_FLAG_CONTIGUOUS;
 
 	if (adev->gmc.xgmi.connected_to_cpu)
-		vres->base.bus.caching = ttm_cached;
+		node->base.bus.caching = ttm_cached;
 	else
-		vres->base.bus.caching = ttm_write_combined;
+		node->base.bus.caching = ttm_write_combined;
 
 	atomic64_add(vis_usage, &mgr->vis_usage);
-	*res = &vres->base;
+	*res = &node->base;
 	return 0;
 
-error_free_blocks:
-	drm_buddy_free_list(mm, &vres->blocks);
-	mutex_unlock(&mgr->lock);
+error_free:
+	while (i--)
+		drm_mm_remove_node(&node->mm_nodes[i]);
+	spin_unlock(&mgr->lock);
 error_fini:
-	ttm_resource_fini(man, &vres->base);
-	kfree(vres);
+	ttm_resource_fini(man, &node->base);
+	kvfree(node);
 
 	return r;
 }
@@ -540,26 +490,27 @@ error_fini:
 static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man,
 				struct ttm_resource *res)
 {
-	struct amdgpu_vram_mgr_resource *vres = to_amdgpu_vram_mgr_resource(res);
+	struct ttm_range_mgr_node *node = to_ttm_range_mgr_node(res);
 	struct amdgpu_vram_mgr *mgr = to_vram_mgr(man);
 	struct amdgpu_device *adev = to_amdgpu_device(mgr);
-	struct drm_buddy *mm = &mgr->mm;
-	struct drm_buddy_block *block;
 	uint64_t vis_usage = 0;
+	unsigned i, pages;
 
-	mutex_lock(&mgr->lock);
-	list_for_each_entry(block, &vres->blocks, link)
-		vis_usage += amdgpu_vram_mgr_vis_size(adev, block);
+	spin_lock(&mgr->lock);
+	for (i = 0, pages = res->num_pages; pages;
+	     pages -= node->mm_nodes[i].size, ++i) {
+		struct drm_mm_node *mm = &node->mm_nodes[i];
 
+		drm_mm_remove_node(mm);
+		vis_usage += amdgpu_vram_mgr_vis_size(adev, mm);
+	}
 	amdgpu_vram_mgr_do_reserve(man);
-
-	drm_buddy_free_list(mm, &vres->blocks);
-	mutex_unlock(&mgr->lock);
+	spin_unlock(&mgr->lock);
 
 	atomic64_sub(vis_usage, &mgr->vis_usage);
 
 	ttm_resource_fini(man, res);
-	kfree(vres);
+	kvfree(node);
 }
 
 /**
@@ -591,7 +542,7 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
 	if (!*sgt)
 		return -ENOMEM;
 
-	/* Determine the number of DRM_BUDDY blocks to export */
+	/* Determine the number of DRM_MM nodes to export */
 	amdgpu_res_first(res, offset, length, &cursor);
 	while (cursor.remaining) {
 		num_entries++;
@@ -607,10 +558,10 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
 		sg->length = 0;
 
 	/*
-	 * Walk down DRM_BUDDY blocks to populate scatterlist nodes
-	 * @note: Use iterator api to get first the DRM_BUDDY block
+	 * Walk down DRM_MM nodes to populate scatterlist nodes
+	 * @note: Use iterator api to get first the DRM_MM node
 	 * and the number of bytes from it. Access the following
-	 * DRM_BUDDY block(s) if more buffer needs to exported
+	 * DRM_MM node(s) if more buffer needs to exported
 	 */
 	amdgpu_res_first(res, offset, length, &cursor);
 	for_each_sgtable_sg((*sgt), sg, i) {
@@ -697,22 +648,13 @@ static void amdgpu_vram_mgr_debug(struct ttm_resource_manager *man,
 				  struct drm_printer *printer)
 {
 	struct amdgpu_vram_mgr *mgr = to_vram_mgr(man);
-	struct drm_buddy *mm = &mgr->mm;
-	struct drm_buddy_block *block;
 
 	drm_printf(printer, "  vis usage:%llu\n",
 		   amdgpu_vram_mgr_vis_usage(mgr));
 
-	mutex_lock(&mgr->lock);
-	drm_printf(printer, "default_page_size: %lluKiB\n",
-		   mgr->default_page_size >> 10);
-
-	drm_buddy_print(mm, printer);
-
-	drm_printf(printer, "reserved:\n");
-	list_for_each_entry(block, &mgr->reserved_pages, link)
-		drm_buddy_block_print(mm, block, printer);
-	mutex_unlock(&mgr->lock);
+	spin_lock(&mgr->lock);
+	drm_mm_print(&mgr->mm, printer);
+	spin_unlock(&mgr->lock);
 }
 
 static const struct ttm_resource_manager_func amdgpu_vram_mgr_func = {
@@ -732,21 +674,16 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_vram_mgr *mgr = &adev->mman.vram_mgr;
 	struct ttm_resource_manager *man = &mgr->manager;
-	int err;
 
 	ttm_resource_manager_init(man, &adev->mman.bdev,
 				  adev->gmc.real_vram_size);
 
 	man->func = &amdgpu_vram_mgr_func;
 
-	err = drm_buddy_init(&mgr->mm, man->size, PAGE_SIZE);
-	if (err)
-		return err;
-
-	mutex_init(&mgr->lock);
+	drm_mm_init(&mgr->mm, 0, man->size >> PAGE_SHIFT);
+	spin_lock_init(&mgr->lock);
 	INIT_LIST_HEAD(&mgr->reservations_pending);
 	INIT_LIST_HEAD(&mgr->reserved_pages);
-	mgr->default_page_size = PAGE_SIZE;
 
 	ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_VRAM, &mgr->manager);
 	ttm_resource_manager_set_used(man, true);
@@ -774,16 +711,16 @@ void amdgpu_vram_mgr_fini(struct amdgpu_device *adev)
 	if (ret)
 		return;
 
-	mutex_lock(&mgr->lock);
-	list_for_each_entry_safe(rsv, temp, &mgr->reservations_pending, blocks)
+	spin_lock(&mgr->lock);
+	list_for_each_entry_safe(rsv, temp, &mgr->reservations_pending, node)
 		kfree(rsv);
 
-	list_for_each_entry_safe(rsv, temp, &mgr->reserved_pages, blocks) {
-		drm_buddy_free_list(&mgr->mm, &rsv->blocks);
+	list_for_each_entry_safe(rsv, temp, &mgr->reserved_pages, node) {
+		drm_mm_remove_node(&rsv->mm_node);
 		kfree(rsv);
 	}
-	drm_buddy_fini(&mgr->mm);
-	mutex_unlock(&mgr->lock);
+	drm_mm_takedown(&mgr->mm);
+	spin_unlock(&mgr->lock);
 
 	ttm_resource_manager_cleanup(man);
 	ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_VRAM, NULL);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h
deleted file mode 100644
index 9a2db87186c7..000000000000
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h
+++ /dev/null
@@ -1,89 +0,0 @@
-/* SPDX-License-Identifier: MIT
- * Copyright 2021 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- */
-
-#ifndef __AMDGPU_VRAM_MGR_H__
-#define __AMDGPU_VRAM_MGR_H__
-
-#include <drm/drm_buddy.h>
-
-struct amdgpu_vram_mgr {
-	struct ttm_resource_manager manager;
-	struct drm_buddy mm;
-	/* protects access to buffer objects */
-	struct mutex lock;
-	struct list_head reservations_pending;
-	struct list_head reserved_pages;
-	atomic64_t vis_usage;
-	u64 default_page_size;
-};
-
-struct amdgpu_vram_mgr_resource {
-	struct ttm_resource base;
-	struct list_head blocks;
-	unsigned long flags;
-};
-
-static inline u64 amdgpu_vram_mgr_block_start(struct drm_buddy_block *block)
-{
-	return drm_buddy_block_offset(block);
-}
-
-static inline u64 amdgpu_vram_mgr_block_size(struct drm_buddy_block *block)
-{
-	return PAGE_SIZE << drm_buddy_block_order(block);
-}
-
-static inline struct drm_buddy_block *
-amdgpu_vram_mgr_first_block(struct list_head *list)
-{
-	return list_first_entry_or_null(list, struct drm_buddy_block, link);
-}
-
-static inline bool amdgpu_is_vram_mgr_blocks_contiguous(struct list_head *head)
-{
-	struct drm_buddy_block *block;
-	u64 start, size;
-
-	block = amdgpu_vram_mgr_first_block(head);
-	if (!block)
-		return false;
-
-	while (head != block->link.next) {
-		start = amdgpu_vram_mgr_block_start(block);
-		size = amdgpu_vram_mgr_block_size(block);
-
-		block = list_entry(block->link.next, struct drm_buddy_block, link);
-		if (start + size != amdgpu_vram_mgr_block_start(block))
-			return false;
-	}
-
-	return true;
-}
-
-static inline struct amdgpu_vram_mgr_resource *
-to_amdgpu_vram_mgr_resource(struct ttm_resource *res)
-{
-	return container_of(res, struct amdgpu_vram_mgr_resource, base);
-}
-
-#endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index bf4200457772..a08769c5e94b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -184,6 +184,8 @@ static void kfd_device_info_init(struct kfd_dev *kfd,
 			/* Navi2x+, Navi1x+ */
 			if (gc_version == IP_VERSION(10, 3, 6))
 				kfd->device_info.no_atomic_fw_version = 14;
+			else if (gc_version == IP_VERSION(10, 3, 7))
+				kfd->device_info.no_atomic_fw_version = 3;
 			else if (gc_version >= IP_VERSION(10, 3, 0))
 				kfd->device_info.no_atomic_fw_version = 92;
 			else if (gc_version >= IP_VERSION(10, 1, 1))
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 1c2984bbda51..93ac33a8de9a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -72,6 +72,7 @@
 #include <linux/pci.h>
 #include <linux/firmware.h>
 #include <linux/component.h>
+#include <linux/dmi.h>
 
 #include <drm/display/drm_dp_mst_helper.h>
 #include <drm/display/drm_hdmi_helper.h>
@@ -462,6 +463,26 @@ static void dm_pflip_high_irq(void *interrupt_params)
 		     vrr_active, (int) !e);
 }
 
+static void dm_crtc_handle_vblank(struct amdgpu_crtc *acrtc)
+{
+	struct drm_crtc *crtc = &acrtc->base;
+	struct drm_device *dev = crtc->dev;
+	unsigned long flags;
+
+	drm_crtc_handle_vblank(crtc);
+
+	spin_lock_irqsave(&dev->event_lock, flags);
+
+	/* Send completion event for cursor-only commits */
+	if (acrtc->event && acrtc->pflip_status != AMDGPU_FLIP_SUBMITTED) {
+		drm_crtc_send_vblank_event(crtc, acrtc->event);
+		drm_crtc_vblank_put(crtc);
+		acrtc->event = NULL;
+	}
+
+	spin_unlock_irqrestore(&dev->event_lock, flags);
+}
+
 static void dm_vupdate_high_irq(void *interrupt_params)
 {
 	struct common_irq_params *irq_params = interrupt_params;
@@ -500,7 +521,7 @@ static void dm_vupdate_high_irq(void *interrupt_params)
 		 * if a pageflip happened inside front-porch.
 		 */
 		if (vrr_active) {
-			drm_crtc_handle_vblank(&acrtc->base);
+			dm_crtc_handle_vblank(acrtc);
 
 			/* BTR processing for pre-DCE12 ASICs */
 			if (acrtc->dm_irq_params.stream &&
@@ -552,7 +573,7 @@ static void dm_crtc_high_irq(void *interrupt_params)
 	 * to dm_vupdate_high_irq after end of front-porch.
 	 */
 	if (!vrr_active)
-		drm_crtc_handle_vblank(&acrtc->base);
+		dm_crtc_handle_vblank(acrtc);
 
 	/**
 	 * Following stuff must happen at start of vblank, for crc
@@ -1382,6 +1403,41 @@ static bool dm_should_disable_stutter(struct pci_dev *pdev)
 	return false;
 }
 
+static const struct dmi_system_id hpd_disconnect_quirk_table[] = {
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3660"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3260"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3460"),
+		},
+	},
+	{}
+};
+
+static void retrieve_dmi_info(struct amdgpu_display_manager *dm)
+{
+	const struct dmi_system_id *dmi_id;
+
+	dm->aux_hpd_discon_quirk = false;
+
+	dmi_id = dmi_first_match(hpd_disconnect_quirk_table);
+	if (dmi_id) {
+		dm->aux_hpd_discon_quirk = true;
+		DRM_INFO("aux_hpd_discon_quirk attached\n");
+	}
+}
+
 static int amdgpu_dm_init(struct amdgpu_device *adev)
 {
 	struct dc_init_data init_data;
@@ -1508,6 +1564,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	}
 
 	INIT_LIST_HEAD(&adev->dm.da_list);
+
+	retrieve_dmi_info(&adev->dm);
+
 	/* Display Core create. */
 	adev->dm.dc = dc_create(&init_data);
 
@@ -5407,7 +5466,7 @@ fill_blending_from_plane_state(const struct drm_plane_state *plane_state,
 			}
 		}
 
-		if (per_pixel_alpha && plane_state->pixel_blend_mode == DRM_MODE_BLEND_COVERAGE)
+		if (*per_pixel_alpha && plane_state->pixel_blend_mode == DRM_MODE_BLEND_COVERAGE)
 			*pre_multiplied_alpha = false;
 	}
 
@@ -9135,6 +9194,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 	struct amdgpu_bo *abo;
 	uint32_t target_vblank, last_flip_vblank;
 	bool vrr_active = amdgpu_dm_vrr_active(acrtc_state);
+	bool cursor_update = false;
 	bool pflip_present = false;
 	struct {
 		struct dc_surface_update surface_updates[MAX_SURFACES];
@@ -9170,8 +9230,13 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 		struct dm_plane_state *dm_new_plane_state = to_dm_plane_state(new_plane_state);
 
 		/* Cursor plane is handled after stream updates */
-		if (plane->type == DRM_PLANE_TYPE_CURSOR)
+		if (plane->type == DRM_PLANE_TYPE_CURSOR) {
+			if ((fb && crtc == pcrtc) ||
+			    (old_plane_state->fb && old_plane_state->crtc == pcrtc))
+				cursor_update = true;
+
 			continue;
+		}
 
 		if (!fb || !crtc || pcrtc != crtc)
 			continue;
@@ -9334,6 +9399,17 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 				bundle->stream_update.vrr_infopacket =
 					&acrtc_state->stream->vrr_infopacket;
 		}
+	} else if (cursor_update && acrtc_state->active_planes > 0 &&
+		   !acrtc_state->force_dpms_off &&
+		   acrtc_attach->base.state->event) {
+		drm_crtc_vblank_get(pcrtc);
+
+		spin_lock_irqsave(&pcrtc->dev->event_lock, flags);
+
+		acrtc_attach->event = acrtc_attach->base.state->event;
+		acrtc_attach->base.state->event = NULL;
+
+		spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags);
 	}
 
 	/* Update the planes if changed or disable if we don't have any. */
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index aa34c0068f41..e80ef93f6550 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -540,6 +540,14 @@ struct amdgpu_display_manager {
 	 * last successfully applied backlight values.
 	 */
 	u32 actual_brightness[AMDGPU_DM_MAX_NUM_EDP];
+
+	/**
+	 * @aux_hpd_discon_quirk:
+	 *
+	 * quirk for hpd discon while aux is on-going.
+	 * occurred on certain intel platform
+	 */
+	bool aux_hpd_discon_quirk;
 };
 
 enum dsc_clock_force_state {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 9221b6690a4a..2b9b095e5f03 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -56,6 +56,8 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 	ssize_t result = 0;
 	struct aux_payload payload;
 	enum aux_return_code_type operation_result;
+	struct amdgpu_device *adev;
+	struct ddc_service *ddc;
 
 	if (WARN_ON(msg->size > 16))
 		return -E2BIG;
@@ -74,6 +76,21 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 	result = dc_link_aux_transfer_raw(TO_DM_AUX(aux)->ddc_service, &payload,
 				      &operation_result);
 
+	/*
+	 * w/a on certain intel platform where hpd is unexpected to pull low during
+	 * 1st sideband message transaction by return AUX_RET_ERROR_HPD_DISCON
+	 * aux transaction is succuess in such case, therefore bypass the error
+	 */
+	ddc = TO_DM_AUX(aux)->ddc_service;
+	adev = ddc->ctx->driver_context;
+	if (adev->dm.aux_hpd_discon_quirk) {
+		if (msg->address == DP_SIDEBAND_MSG_DOWN_REQ_BASE &&
+			operation_result == AUX_RET_ERROR_HPD_DISCON) {
+			result = 0;
+			operation_result = AUX_RET_SUCCESS;
+		}
+	}
+
 	if (payload.write && result >= 0)
 		result = msg->size;
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 6774dd8bb53e..3fe3fbac1e63 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1117,12 +1117,13 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	 * on certain displays, such as the Sharp 4k. 36bpp is needed
 	 * to support SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616 and
 	 * SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616 with actual > 10 bpc
-	 * precision on at least DCN display engines. However, at least
-	 * Carrizo with DCE_VERSION_11_0 does not like 36 bpp lb depth,
-	 * so use only 30 bpp on DCE_VERSION_11_0. Testing with DCE 11.2 and 8.3
-	 * did not show such problems, so this seems to be the exception.
+	 * precision on DCN display engines, but apparently not for DCE, as
+	 * far as testing on DCE-11.2 and DCE-8 showed. Various DCE parts have
+	 * problems: Carrizo with DCE_VERSION_11_0 does not like 36 bpp lb depth,
+	 * neither do DCE-8 at 4k resolution, or DCE-11.2 (broken identify pixel
+	 * passthrough). Therefore only use 36 bpp on DCN where it is actually needed.
 	 */
-	if (plane_state->ctx->dce_version > DCE_VERSION_11_0)
+	if (plane_state->ctx->dce_version > DCE_VERSION_MAX)
 		pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_36BPP;
 	else
 		pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_30BPP;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index 5f8809f6990d..2fbd2926a531 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -1228,6 +1228,8 @@ int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu,
 	uint32_t crystal_clock_freq = 2500;
 	uint32_t tach_period;
 
+	if (speed == 0)
+		return -EINVAL;
 	/*
 	 * To prevent from possible overheat, some ASICs may have requirement
 	 * for minimum fan speed:
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index 4c25d9b2f138..d30ebcaec8b9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -620,10 +620,15 @@ i915_ttm_resource_get_st(struct drm_i915_gem_object *obj,
 			 struct ttm_resource *res)
 {
 	struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
+	u64 page_alignment;
 
 	if (!i915_ttm_gtt_binds_lmem(res))
 		return i915_ttm_tt_get_st(bo->ttm);
 
+	page_alignment = bo->page_alignment << PAGE_SHIFT;
+	if (!page_alignment)
+		page_alignment = obj->mm.region->min_page_size;
+
 	/*
 	 * If CPU mapping differs, we need to add the ttm_tt pages to
 	 * the resulting st. Might make sense for GGTT.
@@ -634,7 +639,8 @@ i915_ttm_resource_get_st(struct drm_i915_gem_object *obj,
 			struct i915_refct_sgt *rsgt;
 
 			rsgt = intel_region_ttm_resource_to_rsgt(obj->mm.region,
-								 res);
+								 res,
+								 page_alignment);
 			if (IS_ERR(rsgt))
 				return rsgt;
 
@@ -643,7 +649,8 @@ i915_ttm_resource_get_st(struct drm_i915_gem_object *obj,
 		return i915_refct_sgt_get(obj->ttm.cached_io_rsgt);
 	}
 
-	return intel_region_ttm_resource_to_rsgt(obj->mm.region, res);
+	return intel_region_ttm_resource_to_rsgt(obj->mm.region, res,
+						 page_alignment);
 }
 
 static int i915_ttm_truncate(struct drm_i915_gem_object *obj)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c
index 319936f91ac5..e6e01c2a74a6 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c
@@ -9,6 +9,7 @@
 #include <linux/jiffies.h>
 
 #include "gt/intel_engine.h"
+#include "gt/intel_rps.h"
 
 #include "i915_gem_ioctls.h"
 #include "i915_gem_object.h"
@@ -31,6 +32,37 @@ i915_gem_object_wait_fence(struct dma_fence *fence,
 				      timeout);
 }
 
+static void
+i915_gem_object_boost(struct dma_resv *resv, unsigned int flags)
+{
+	struct dma_resv_iter cursor;
+	struct dma_fence *fence;
+
+	/*
+	 * Prescan all fences for potential boosting before we begin waiting.
+	 *
+	 * When we wait, we wait on outstanding fences serially. If the
+	 * dma-resv contains a sequence such as 1:1, 1:2 instead of a reduced
+	 * form 1:2, then as we look at each wait in turn we see that each
+	 * request is currently executing and not worthy of boosting. But if
+	 * we only happen to look at the final fence in the sequence (because
+	 * of request coalescing or splitting between read/write arrays by
+	 * the iterator), then we would boost. As such our decision to boost
+	 * or not is delicately balanced on the order we wait on fences.
+	 *
+	 * So instead of looking for boosts sequentially, look for all boosts
+	 * upfront and then wait on the outstanding fences.
+	 */
+
+	dma_resv_iter_begin(&cursor, resv,
+			    dma_resv_usage_rw(flags & I915_WAIT_ALL));
+	dma_resv_for_each_fence_unlocked(&cursor, fence)
+		if (dma_fence_is_i915(fence) &&
+		    !i915_request_started(to_request(fence)))
+			intel_rps_boost(to_request(fence));
+	dma_resv_iter_end(&cursor);
+}
+
 static long
 i915_gem_object_wait_reservation(struct dma_resv *resv,
 				 unsigned int flags,
@@ -40,6 +72,8 @@ i915_gem_object_wait_reservation(struct dma_resv *resv,
 	struct dma_fence *fence;
 	long ret = timeout ?: 1;
 
+	i915_gem_object_boost(resv, flags);
+
 	dma_resv_iter_begin(&cursor, resv,
 			    dma_resv_usage_rw(flags & I915_WAIT_ALL));
 	dma_resv_for_each_fence_unlocked(&cursor, fence) {
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 51a0fe60c050..531af6ad7007 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -1209,6 +1209,20 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 	mutex_lock(&gt->tlb_invalidate_lock);
 	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
 
+	spin_lock_irq(&uncore->lock); /* serialise invalidate with GT reset */
+
+	for_each_engine(engine, gt, id) {
+		struct reg_and_bit rb;
+
+		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
+		if (!i915_mmio_reg_offset(rb.reg))
+			continue;
+
+		intel_uncore_write_fw(uncore, rb.reg, rb.bit);
+	}
+
+	spin_unlock_irq(&uncore->lock);
+
 	for_each_engine(engine, gt, id) {
 		/*
 		 * HW architecture suggest typical invalidation time at 40us,
@@ -1223,7 +1237,6 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 		if (!i915_mmio_reg_offset(rb.reg))
 			continue;
 
-		intel_uncore_write_fw(uncore, rb.reg, rb.bit);
 		if (__intel_wait_for_register_fw(uncore,
 						 rb.reg, rb.bit, 0,
 						 timeout_us, timeout_ms,
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index a5338c3fde7a..c68d36fb5bbd 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -300,9 +300,9 @@ static int gen6_hw_domain_reset(struct intel_gt *gt, u32 hw_domain_mask)
 	return err;
 }
 
-static int gen6_reset_engines(struct intel_gt *gt,
-			      intel_engine_mask_t engine_mask,
-			      unsigned int retry)
+static int __gen6_reset_engines(struct intel_gt *gt,
+				intel_engine_mask_t engine_mask,
+				unsigned int retry)
 {
 	struct intel_engine_cs *engine;
 	u32 hw_mask;
@@ -321,6 +321,20 @@ static int gen6_reset_engines(struct intel_gt *gt,
 	return gen6_hw_domain_reset(gt, hw_mask);
 }
 
+static int gen6_reset_engines(struct intel_gt *gt,
+			      intel_engine_mask_t engine_mask,
+			      unsigned int retry)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&gt->uncore->lock, flags);
+	ret = __gen6_reset_engines(gt, engine_mask, retry);
+	spin_unlock_irqrestore(&gt->uncore->lock, flags);
+
+	return ret;
+}
+
 static struct intel_engine_cs *find_sfc_paired_vecs_engine(struct intel_engine_cs *engine)
 {
 	int vecs_id;
@@ -487,9 +501,9 @@ static void gen11_unlock_sfc(struct intel_engine_cs *engine)
 	rmw_clear_fw(uncore, sfc_lock.lock_reg, sfc_lock.lock_bit);
 }
 
-static int gen11_reset_engines(struct intel_gt *gt,
-			       intel_engine_mask_t engine_mask,
-			       unsigned int retry)
+static int __gen11_reset_engines(struct intel_gt *gt,
+				 intel_engine_mask_t engine_mask,
+				 unsigned int retry)
 {
 	struct intel_engine_cs *engine;
 	intel_engine_mask_t tmp;
@@ -583,8 +597,11 @@ static int gen8_reset_engines(struct intel_gt *gt,
 	struct intel_engine_cs *engine;
 	const bool reset_non_ready = retry >= 1;
 	intel_engine_mask_t tmp;
+	unsigned long flags;
 	int ret;
 
+	spin_lock_irqsave(&gt->uncore->lock, flags);
+
 	for_each_engine_masked(engine, gt, engine_mask, tmp) {
 		ret = gen8_engine_reset_prepare(engine);
 		if (ret && !reset_non_ready)
@@ -612,17 +629,19 @@ static int gen8_reset_engines(struct intel_gt *gt,
 	 * This is best effort, so ignore any error from the initial reset.
 	 */
 	if (IS_DG2(gt->i915) && engine_mask == ALL_ENGINES)
-		gen11_reset_engines(gt, gt->info.engine_mask, 0);
+		__gen11_reset_engines(gt, gt->info.engine_mask, 0);
 
 	if (GRAPHICS_VER(gt->i915) >= 11)
-		ret = gen11_reset_engines(gt, engine_mask, retry);
+		ret = __gen11_reset_engines(gt, engine_mask, retry);
 	else
-		ret = gen6_reset_engines(gt, engine_mask, retry);
+		ret = __gen6_reset_engines(gt, engine_mask, retry);
 
 skip_reset:
 	for_each_engine_masked(engine, gt, engine_mask, tmp)
 		gen8_engine_reset_cancel(engine);
 
+	spin_unlock_irqrestore(&gt->uncore->lock, flags);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 8b2c11dbe354..1109088fe8f6 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -176,8 +176,8 @@ static int live_lrc_layout(void *arg)
 			continue;
 
 		hw = shmem_pin_map(engine->default_state);
-		if (IS_ERR(hw)) {
-			err = PTR_ERR(hw);
+		if (!hw) {
+			err = -ENOMEM;
 			break;
 		}
 		hw += LRC_STATE_OFFSET / sizeof(*hw);
@@ -365,8 +365,8 @@ static int live_lrc_fixed(void *arg)
 			continue;
 
 		hw = shmem_pin_map(engine->default_state);
-		if (IS_ERR(hw)) {
-			err = PTR_ERR(hw);
+		if (!hw) {
+			err = -ENOMEM;
 			break;
 		}
 		hw += LRC_STATE_OFFSET / sizeof(*hw);
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index b9eb75a2b400..1c35a41620ae 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -3117,9 +3117,9 @@ void intel_gvt_update_reg_whitelist(struct intel_vgpu *vgpu)
 			continue;
 
 		vaddr = shmem_pin_map(engine->default_state);
-		if (IS_ERR(vaddr)) {
-			gvt_err("failed to map %s->default state, err:%zd\n",
-				engine->name, PTR_ERR(vaddr));
+		if (!vaddr) {
+			gvt_err("failed to map %s->default state\n",
+				engine->name);
 			return;
 		}
 
diff --git a/drivers/gpu/drm/i915/i915_scatterlist.c b/drivers/gpu/drm/i915/i915_scatterlist.c
index 159571b9bd24..f63b50b71e10 100644
--- a/drivers/gpu/drm/i915/i915_scatterlist.c
+++ b/drivers/gpu/drm/i915/i915_scatterlist.c
@@ -68,6 +68,7 @@ void i915_refct_sgt_init(struct i915_refct_sgt *rsgt, size_t size)
  * drm_mm_node
  * @node: The drm_mm_node.
  * @region_start: An offset to add to the dma addresses of the sg list.
+ * @page_alignment: Required page alignment for each sg entry. Power of two.
  *
  * Create a struct sg_table, initializing it from a struct drm_mm_node,
  * taking a maximum segment length into account, splitting into segments
@@ -77,15 +78,18 @@ void i915_refct_sgt_init(struct i915_refct_sgt *rsgt, size_t size)
  * error code cast to an error pointer on failure.
  */
 struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node,
-					      u64 region_start)
+					      u64 region_start,
+					      u64 page_alignment)
 {
-	const u64 max_segment = SZ_1G; /* Do we have a limit on this? */
+	const u64 max_segment = round_down(UINT_MAX, page_alignment);
 	u64 segment_pages = max_segment >> PAGE_SHIFT;
 	u64 block_size, offset, prev_end;
 	struct i915_refct_sgt *rsgt;
 	struct sg_table *st;
 	struct scatterlist *sg;
 
+	GEM_BUG_ON(!max_segment);
+
 	rsgt = kmalloc(sizeof(*rsgt), GFP_KERNEL);
 	if (!rsgt)
 		return ERR_PTR(-ENOMEM);
@@ -112,6 +116,8 @@ struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node,
 				sg = __sg_next(sg);
 
 			sg_dma_address(sg) = region_start + offset;
+			GEM_BUG_ON(!IS_ALIGNED(sg_dma_address(sg),
+					       page_alignment));
 			sg_dma_len(sg) = 0;
 			sg->length = 0;
 			st->nents++;
@@ -138,6 +144,7 @@ struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node,
  * i915_buddy_block list
  * @res: The struct i915_ttm_buddy_resource.
  * @region_start: An offset to add to the dma addresses of the sg list.
+ * @page_alignment: Required page alignment for each sg entry. Power of two.
  *
  * Create a struct sg_table, initializing it from struct i915_buddy_block list,
  * taking a maximum segment length into account, splitting into segments
@@ -147,11 +154,12 @@ struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node,
  * error code cast to an error pointer on failure.
  */
 struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res,
-						     u64 region_start)
+						     u64 region_start,
+						     u64 page_alignment)
 {
 	struct i915_ttm_buddy_resource *bman_res = to_ttm_buddy_resource(res);
 	const u64 size = res->num_pages << PAGE_SHIFT;
-	const u64 max_segment = rounddown(UINT_MAX, PAGE_SIZE);
+	const u64 max_segment = round_down(UINT_MAX, page_alignment);
 	struct drm_buddy *mm = bman_res->mm;
 	struct list_head *blocks = &bman_res->blocks;
 	struct drm_buddy_block *block;
@@ -161,6 +169,7 @@ struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res,
 	resource_size_t prev_end;
 
 	GEM_BUG_ON(list_empty(blocks));
+	GEM_BUG_ON(!max_segment);
 
 	rsgt = kmalloc(sizeof(*rsgt), GFP_KERNEL);
 	if (!rsgt)
@@ -191,6 +200,8 @@ struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res,
 					sg = __sg_next(sg);
 
 				sg_dma_address(sg) = region_start + offset;
+				GEM_BUG_ON(!IS_ALIGNED(sg_dma_address(sg),
+						       page_alignment));
 				sg_dma_len(sg) = 0;
 				sg->length = 0;
 				st->nents++;
diff --git a/drivers/gpu/drm/i915/i915_scatterlist.h b/drivers/gpu/drm/i915/i915_scatterlist.h
index 12c6a1684081..b13e4cdea923 100644
--- a/drivers/gpu/drm/i915/i915_scatterlist.h
+++ b/drivers/gpu/drm/i915/i915_scatterlist.h
@@ -213,9 +213,11 @@ static inline void __i915_refct_sgt_init(struct i915_refct_sgt *rsgt,
 void i915_refct_sgt_init(struct i915_refct_sgt *rsgt, size_t size);
 
 struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node,
-					      u64 region_start);
+					      u64 region_start,
+					      u64 page_alignment);
 
 struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res,
-						     u64 region_start);
+						     u64 region_start,
+						     u64 page_alignment);
 
 #endif
diff --git a/drivers/gpu/drm/i915/intel_region_ttm.c b/drivers/gpu/drm/i915/intel_region_ttm.c
index 62ff77445b01..6873808a7015 100644
--- a/drivers/gpu/drm/i915/intel_region_ttm.c
+++ b/drivers/gpu/drm/i915/intel_region_ttm.c
@@ -152,6 +152,7 @@ int intel_region_ttm_fini(struct intel_memory_region *mem)
  * Convert an opaque TTM resource manager resource to a refcounted sg_table.
  * @mem: The memory region.
  * @res: The resource manager resource obtained from the TTM resource manager.
+ * @page_alignment: Required page alignment for each sg entry. Power of two.
  *
  * The gem backends typically use sg-tables for operations on the underlying
  * io_memory. So provide a way for the backends to translate the
@@ -161,16 +162,19 @@ int intel_region_ttm_fini(struct intel_memory_region *mem)
  */
 struct i915_refct_sgt *
 intel_region_ttm_resource_to_rsgt(struct intel_memory_region *mem,
-				  struct ttm_resource *res)
+				  struct ttm_resource *res,
+				  u64 page_alignment)
 {
 	if (mem->is_range_manager) {
 		struct ttm_range_mgr_node *range_node =
 			to_ttm_range_mgr_node(res);
 
 		return i915_rsgt_from_mm_node(&range_node->mm_nodes[0],
-					      mem->region.start);
+					      mem->region.start,
+					      page_alignment);
 	} else {
-		return i915_rsgt_from_buddy_resource(res, mem->region.start);
+		return i915_rsgt_from_buddy_resource(res, mem->region.start,
+						     page_alignment);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/intel_region_ttm.h b/drivers/gpu/drm/i915/intel_region_ttm.h
index cf9d86dcf409..98fba5155619 100644
--- a/drivers/gpu/drm/i915/intel_region_ttm.h
+++ b/drivers/gpu/drm/i915/intel_region_ttm.h
@@ -24,7 +24,8 @@ int intel_region_ttm_fini(struct intel_memory_region *mem);
 
 struct i915_refct_sgt *
 intel_region_ttm_resource_to_rsgt(struct intel_memory_region *mem,
-				  struct ttm_resource *res);
+				  struct ttm_resource *res,
+				  u64 page_alignment);
 
 void intel_region_ttm_resource_free(struct intel_memory_region *mem,
 				    struct ttm_resource *res);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 8633bec18fa7..ab9f17fc85bc 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -742,7 +742,7 @@ static int pot_hole(struct i915_address_space *vm,
 		u64 addr;
 
 		for (addr = round_up(hole_start + min_alignment, step) - min_alignment;
-		     addr <= round_down(hole_end - (2 * min_alignment), step) - min_alignment;
+		     hole_end > addr && hole_end - addr >= 2 * min_alignment;
 		     addr += step) {
 			err = i915_vma_pin(vma, 0, 0, addr | flags);
 			if (err) {
diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
index 73eb53edb8de..3b18e5905c86 100644
--- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
@@ -451,7 +451,6 @@ out_put:
 
 static int igt_mock_max_segment(void *arg)
 {
-	const unsigned int max_segment = rounddown(UINT_MAX, PAGE_SIZE);
 	struct intel_memory_region *mem = arg;
 	struct drm_i915_private *i915 = mem->i915;
 	struct i915_ttm_buddy_resource *res;
@@ -460,7 +459,10 @@ static int igt_mock_max_segment(void *arg)
 	struct drm_buddy *mm;
 	struct list_head *blocks;
 	struct scatterlist *sg;
+	I915_RND_STATE(prng);
 	LIST_HEAD(objects);
+	unsigned int max_segment;
+	unsigned int ps;
 	u64 size;
 	int err = 0;
 
@@ -472,7 +474,13 @@ static int igt_mock_max_segment(void *arg)
 	 */
 
 	size = SZ_8G;
-	mem = mock_region_create(i915, 0, size, PAGE_SIZE, 0, 0);
+	ps = PAGE_SIZE;
+	if (i915_prandom_u64_state(&prng) & 1)
+		ps = SZ_64K; /* For something like DG2 */
+
+	max_segment = round_down(UINT_MAX, ps);
+
+	mem = mock_region_create(i915, 0, size, ps, 0, 0);
 	if (IS_ERR(mem))
 		return PTR_ERR(mem);
 
@@ -498,12 +506,21 @@ static int igt_mock_max_segment(void *arg)
 	}
 
 	for (sg = obj->mm.pages->sgl; sg; sg = sg_next(sg)) {
+		dma_addr_t daddr = sg_dma_address(sg);
+
 		if (sg->length > max_segment) {
 			pr_err("%s: Created an oversized scatterlist entry, %u > %u\n",
 			       __func__, sg->length, max_segment);
 			err = -EINVAL;
 			goto out_close;
 		}
+
+		if (!IS_ALIGNED(daddr, ps)) {
+			pr_err("%s: Created an unaligned scatterlist entry, addr=%pa, ps=%u\n",
+			       __func__,  &daddr, ps);
+			err = -EINVAL;
+			goto out_close;
+		}
 	}
 
 out_close:
diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c
index 670557ce1024..bac21fe84ca5 100644
--- a/drivers/gpu/drm/i915/selftests/mock_region.c
+++ b/drivers/gpu/drm/i915/selftests/mock_region.c
@@ -33,7 +33,8 @@ static int mock_region_get_pages(struct drm_i915_gem_object *obj)
 		return PTR_ERR(obj->mm.res);
 
 	obj->mm.rsgt = intel_region_ttm_resource_to_rsgt(obj->mm.region,
-							 obj->mm.res);
+							 obj->mm.res,
+							 obj->mm.region->min_page_size);
 	if (IS_ERR(obj->mm.rsgt)) {
 		err = PTR_ERR(obj->mm.rsgt);
 		goto err_free_resource;