1 files changed, 100 insertions, 92 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index ff5e52025266..2a241a5b12c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -24,11 +24,12 @@
 
 #include <linux/dma-mapping.h>
 #include <drm/ttm/ttm_range_manager.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_buddy.h>
 
 #include "amdgpu.h"
 #include "amdgpu_vm.h"
 #include "amdgpu_res_cursor.h"
-#include "amdgpu_atomfirmware.h"
 #include "atom.h"
 
 #define AMDGPU_MAX_SG_SEGMENT_SIZE	(2UL << 30)
@@ -52,15 +53,15 @@ to_amdgpu_device(struct amdgpu_vram_mgr *mgr)
 	return container_of(mgr, struct amdgpu_device, mman.vram_mgr);
 }
 
-static inline struct drm_buddy_block *
+static inline struct gpu_buddy_block *
 amdgpu_vram_mgr_first_block(struct list_head *list)
 {
-	return list_first_entry_or_null(list, struct drm_buddy_block, link);
+	return list_first_entry_or_null(list, struct gpu_buddy_block, link);
 }
 
 static inline bool amdgpu_is_vram_mgr_blocks_contiguous(struct list_head *head)
 {
-	struct drm_buddy_block *block;
+	struct gpu_buddy_block *block;
 	u64 start, size;
 
 	block = amdgpu_vram_mgr_first_block(head);
@@ -71,7 +72,7 @@ static inline bool amdgpu_is_vram_mgr_blocks_contiguous(struct list_head *head)
 		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);
+		block = list_entry(block->link.next, struct gpu_buddy_block, link);
 		if (start + size != amdgpu_vram_mgr_block_start(block))
 			return false;
 	}
@@ -81,7 +82,7 @@ static inline bool amdgpu_is_vram_mgr_blocks_contiguous(struct list_head *head)
 
 static inline u64 amdgpu_vram_mgr_blocks_size(struct list_head *head)
 {
-	struct drm_buddy_block *block;
+	struct gpu_buddy_block *block;
 	u64 size = 0;
 
 	list_for_each_entry(block, head, link)
@@ -234,6 +235,9 @@ static umode_t amdgpu_vram_attrs_is_visible(struct kobject *kobj,
 	    !adev->gmc.vram_vendor)
 		return 0;
 
+	if (!ttm_resource_manager_used(&adev->mman.vram_mgr.manager))
+		return 0;
+
 	return attr->mode;
 }
 
@@ -251,7 +255,7 @@ const struct attribute_group amdgpu_vram_mgr_attr_group = {
  * Calculate how many bytes of the DRM BUDDY block are inside visible VRAM
  */
 static u64 amdgpu_vram_mgr_vis_size(struct amdgpu_device *adev,
-				    struct drm_buddy_block *block)
+				    struct gpu_buddy_block *block)
 {
 	u64 start = amdgpu_vram_mgr_block_start(block);
 	u64 end = start + amdgpu_vram_mgr_block_size(block);
@@ -276,7 +280,7 @@ 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;
+	struct gpu_buddy_block *block;
 	u64 usage = 0;
 
 	if (amdgpu_gmc_vram_full_visible(&adev->gmc))
@@ -296,15 +300,15 @@ 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 gpu_buddy *mm = &mgr->mm;
 	struct amdgpu_vram_reservation *rsv, *temp;
-	struct drm_buddy_block *block;
+	struct gpu_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,
+		if (gpu_buddy_alloc_blocks(mm, rsv->start, rsv->start + rsv->size,
 					   rsv->size, mm->chunk_size, &rsv->allocated,
-					   DRM_BUDDY_RANGE_ALLOCATION))
+					   GPU_BUDDY_RANGE_ALLOCATION))
 			continue;
 
 		block = amdgpu_vram_mgr_first_block(&rsv->allocated);
@@ -337,7 +341,7 @@ int amdgpu_vram_mgr_reserve_range(struct amdgpu_vram_mgr *mgr,
 {
 	struct amdgpu_vram_reservation *rsv;
 
-	rsv = kzalloc(sizeof(*rsv), GFP_KERNEL);
+	rsv = kzalloc_obj(*rsv);
 	if (!rsv)
 		return -ENOMEM;
 
@@ -396,43 +400,33 @@ out:
 	return ret;
 }
 
-static void amdgpu_dummy_vram_mgr_debug(struct ttm_resource_manager *man,
-				  struct drm_printer *printer)
-{
-	DRM_DEBUG_DRIVER("Dummy vram mgr debug\n");
-}
-
-static bool amdgpu_dummy_vram_mgr_compatible(struct ttm_resource_manager *man,
-				       struct ttm_resource *res,
-				       const struct ttm_place *place,
-				       size_t size)
+int amdgpu_vram_mgr_query_address_block_info(struct amdgpu_vram_mgr *mgr,
+			uint64_t address, struct amdgpu_vram_block_info *info)
 {
-	DRM_DEBUG_DRIVER("Dummy vram mgr compatible\n");
-	return false;
-}
+	struct amdgpu_vram_mgr_resource *vres;
+	struct gpu_buddy_block *block;
+	u64 start, size;
+	int ret = -ENOENT;
 
-static bool amdgpu_dummy_vram_mgr_intersects(struct ttm_resource_manager *man,
-				       struct ttm_resource *res,
-				       const struct ttm_place *place,
-				       size_t size)
-{
-	DRM_DEBUG_DRIVER("Dummy vram mgr intersects\n");
-	return true;
-}
+	mutex_lock(&mgr->lock);
+	list_for_each_entry(vres, &mgr->allocated_vres_list, vres_node) {
+		list_for_each_entry(block, &vres->blocks, link) {
+			start = amdgpu_vram_mgr_block_start(block);
+			size = amdgpu_vram_mgr_block_size(block);
+			if ((start <= address) && (address < (start + size))) {
+				info->start = start;
+				info->size = size;
+				memcpy(&info->task, &vres->task, sizeof(vres->task));
+				ret = 0;
+				goto out;
+			}
+		}
+	}
 
-static void amdgpu_dummy_vram_mgr_del(struct ttm_resource_manager *man,
-				struct ttm_resource *res)
-{
-	DRM_DEBUG_DRIVER("Dummy vram mgr deleted\n");
-}
+out:
+	mutex_unlock(&mgr->lock);
 
-static int amdgpu_dummy_vram_mgr_new(struct ttm_resource_manager *man,
-			       struct ttm_buffer_object *tbo,
-			       const struct ttm_place *place,
-			       struct ttm_resource **res)
-{
-	DRM_DEBUG_DRIVER("Dummy vram mgr new\n");
-	return -ENOSPC;
+	return ret;
 }
 
 /**
@@ -457,13 +451,13 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 	struct amdgpu_vram_mgr_resource *vres;
 	u64 size, remaining_size, lpfn, fpfn;
 	unsigned int adjust_dcc_size = 0;
-	struct drm_buddy *mm = &mgr->mm;
-	struct drm_buddy_block *block;
+	struct gpu_buddy *mm = &mgr->mm;
+	struct gpu_buddy_block *block;
 	unsigned long pages_per_block;
 	int r;
 
 	lpfn = (u64)place->lpfn << PAGE_SHIFT;
-	if (!lpfn)
+	if (!lpfn || lpfn > man->size)
 		lpfn = man->size;
 
 	fpfn = (u64)place->fpfn << PAGE_SHIFT;
@@ -485,7 +479,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 					tbo->page_alignment);
 	}
 
-	vres = kzalloc(sizeof(*vres), GFP_KERNEL);
+	vres = kzalloc_obj(*vres);
 	if (!vres)
 		return -ENOMEM;
 
@@ -500,17 +494,17 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 	INIT_LIST_HEAD(&vres->blocks);
 
 	if (place->flags & TTM_PL_FLAG_TOPDOWN)
-		vres->flags |= DRM_BUDDY_TOPDOWN_ALLOCATION;
+		vres->flags |= GPU_BUDDY_TOPDOWN_ALLOCATION;
 
 	if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)
-		vres->flags |= DRM_BUDDY_CONTIGUOUS_ALLOCATION;
+		vres->flags |= GPU_BUDDY_CONTIGUOUS_ALLOCATION;
 
 	if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CLEARED)
-		vres->flags |= DRM_BUDDY_CLEAR_ALLOCATION;
+		vres->flags |= GPU_BUDDY_CLEAR_ALLOCATION;
 
 	if (fpfn || lpfn != mgr->mm.size)
 		/* Allocate blocks in desired range */
-		vres->flags |= DRM_BUDDY_RANGE_ALLOCATION;
+		vres->flags |= GPU_BUDDY_RANGE_ALLOCATION;
 
 	if (bo->flags & AMDGPU_GEM_CREATE_GFX12_DCC &&
 	    adev->gmc.gmc_funcs->get_dcc_alignment)
@@ -523,7 +517,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 		dcc_size = roundup_pow_of_two(vres->base.size + adjust_dcc_size);
 		remaining_size = (u64)dcc_size;
 
-		vres->flags |= DRM_BUDDY_TRIM_DISABLE;
+		vres->flags |= GPU_BUDDY_TRIM_DISABLE;
 	}
 
 	mutex_lock(&mgr->lock);
@@ -543,7 +537,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 
 		BUG_ON(min_block_size < mm->chunk_size);
 
-		r = drm_buddy_alloc_blocks(mm, fpfn,
+		r = gpu_buddy_alloc_blocks(mm, fpfn,
 					   lpfn,
 					   size,
 					   min_block_size,
@@ -552,7 +546,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 
 		if (unlikely(r == -ENOSPC) && pages_per_block == ~0ul &&
 		    !(place->flags & TTM_PL_FLAG_CONTIGUOUS)) {
-			vres->flags &= ~DRM_BUDDY_CONTIGUOUS_ALLOCATION;
+			vres->flags &= ~GPU_BUDDY_CONTIGUOUS_ALLOCATION;
 			pages_per_block = max_t(u32, 2UL << (20UL - PAGE_SHIFT),
 						tbo->page_alignment);
 
@@ -568,8 +562,12 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 			remaining_size -= size;
 	}
 
+	vres->task.pid = task_pid_nr(current);
+	get_task_comm(vres->task.comm, current);
+	list_add_tail(&vres->vres_node, &mgr->allocated_vres_list);
+
 	if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS && adjust_dcc_size) {
-		struct drm_buddy_block *dcc_block;
+		struct gpu_buddy_block *dcc_block;
 		unsigned long dcc_start;
 		u64 trim_start;
 
@@ -579,7 +577,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 			roundup((unsigned long)amdgpu_vram_mgr_block_start(dcc_block),
 				adjust_dcc_size);
 		trim_start = (u64)dcc_start;
-		drm_buddy_block_trim(mm, &trim_start,
+		gpu_buddy_block_trim(mm, &trim_start,
 				     (u64)vres->base.size,
 				     &vres->blocks);
 	}
@@ -617,7 +615,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 	return 0;
 
 error_free_blocks:
-	drm_buddy_free_list(mm, &vres->blocks, 0);
+	gpu_buddy_free_list(mm, &vres->blocks, 0);
 	mutex_unlock(&mgr->lock);
 error_fini:
 	ttm_resource_fini(man, &vres->base);
@@ -640,17 +638,20 @@ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man,
 	struct amdgpu_vram_mgr_resource *vres = to_amdgpu_vram_mgr_resource(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;
+	struct gpu_buddy *mm = &mgr->mm;
+	struct gpu_buddy_block *block;
 	uint64_t vis_usage = 0;
 
 	mutex_lock(&mgr->lock);
+
+	list_del(&vres->vres_node);
+	memset(&vres->task, 0, sizeof(vres->task));
+
 	list_for_each_entry(block, &vres->blocks, link)
 		vis_usage += amdgpu_vram_mgr_vis_size(adev, block);
 
+	gpu_buddy_free_list(mm, &vres->blocks, vres->flags);
 	amdgpu_vram_mgr_do_reserve(man);
-
-	drm_buddy_free_list(mm, &vres->blocks, vres->flags);
 	mutex_unlock(&mgr->lock);
 
 	atomic64_sub(vis_usage, &mgr->vis_usage);
@@ -684,11 +685,11 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
 	int num_entries = 0;
 	int i, r;
 
-	*sgt = kmalloc(sizeof(**sgt), GFP_KERNEL);
+	*sgt = kmalloc_obj(**sgt);
 	if (!*sgt)
 		return -ENOMEM;
 
-	/* Determine the number of DRM_BUDDY blocks to export */
+	/* Determine the number of GPU_BUDDY blocks to export */
 	amdgpu_res_first(res, offset, length, &cursor);
 	while (cursor.remaining) {
 		num_entries++;
@@ -704,10 +705,10 @@ 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 GPU_BUDDY blocks to populate scatterlist nodes
+	 * @note: Use iterator api to get first the GPU_BUDDY block
 	 * and the number of bytes from it. Access the following
-	 * DRM_BUDDY block(s) if more buffer needs to exported
+	 * GPU_BUDDY block(s) if more buffer needs to exported
 	 */
 	amdgpu_res_first(res, offset, length, &cursor);
 	for_each_sgtable_sg((*sgt), sg, i) {
@@ -783,6 +784,23 @@ uint64_t amdgpu_vram_mgr_vis_usage(struct amdgpu_vram_mgr *mgr)
 }
 
 /**
+ * amdgpu_vram_mgr_clear_reset_blocks - reset clear blocks
+ *
+ * @adev: amdgpu device pointer
+ *
+ * Reset the cleared drm buddy blocks.
+ */
+void amdgpu_vram_mgr_clear_reset_blocks(struct amdgpu_device *adev)
+{
+	struct amdgpu_vram_mgr *mgr = &adev->mman.vram_mgr;
+	struct gpu_buddy *mm = &mgr->mm;
+
+	mutex_lock(&mgr->lock);
+	gpu_buddy_reset_clear(mm, false);
+	mutex_unlock(&mgr->lock);
+}
+
+/**
  * amdgpu_vram_mgr_intersects - test each drm buddy block for intersection
  *
  * @man: TTM memory type manager
@@ -798,7 +816,7 @@ static bool amdgpu_vram_mgr_intersects(struct ttm_resource_manager *man,
 				       size_t size)
 {
 	struct amdgpu_vram_mgr_resource *mgr = to_amdgpu_vram_mgr_resource(res);
-	struct drm_buddy_block *block;
+	struct gpu_buddy_block *block;
 
 	/* Check each drm buddy block individually */
 	list_for_each_entry(block, &mgr->blocks, link) {
@@ -831,7 +849,7 @@ static bool amdgpu_vram_mgr_compatible(struct ttm_resource_manager *man,
 				       size_t size)
 {
 	struct amdgpu_vram_mgr_resource *mgr = to_amdgpu_vram_mgr_resource(res);
-	struct drm_buddy_block *block;
+	struct gpu_buddy_block *block;
 
 	/* Check each drm buddy block individually */
 	list_for_each_entry(block, &mgr->blocks, link) {
@@ -860,7 +878,7 @@ 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 gpu_buddy *mm = &mgr->mm;
 	struct amdgpu_vram_reservation *rsv;
 
 	drm_printf(printer, "  vis usage:%llu\n",
@@ -879,14 +897,6 @@ static void amdgpu_vram_mgr_debug(struct ttm_resource_manager *man,
 	mutex_unlock(&mgr->lock);
 }
 
-static const struct ttm_resource_manager_func amdgpu_dummy_vram_mgr_func = {
-	.alloc	= amdgpu_dummy_vram_mgr_new,
-	.free	= amdgpu_dummy_vram_mgr_del,
-	.intersects = amdgpu_dummy_vram_mgr_intersects,
-	.compatible = amdgpu_dummy_vram_mgr_compatible,
-	.debug	= amdgpu_dummy_vram_mgr_debug
-};
-
 static const struct ttm_resource_manager_func amdgpu_vram_mgr_func = {
 	.alloc	= amdgpu_vram_mgr_new,
 	.free	= amdgpu_vram_mgr_del,
@@ -908,24 +918,22 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev)
 	struct ttm_resource_manager *man = &mgr->manager;
 	int err;
 
+	man->cg = drmm_cgroup_register_region(adev_to_drm(adev), "vram", adev->gmc.real_vram_size);
+	if (IS_ERR(man->cg))
+		return PTR_ERR(man->cg);
 	ttm_resource_manager_init(man, &adev->mman.bdev,
 				  adev->gmc.real_vram_size);
 
 	mutex_init(&mgr->lock);
 	INIT_LIST_HEAD(&mgr->reservations_pending);
 	INIT_LIST_HEAD(&mgr->reserved_pages);
+	INIT_LIST_HEAD(&mgr->allocated_vres_list);
 	mgr->default_page_size = PAGE_SIZE;
 
-	if (!adev->gmc.is_app_apu) {
-		man->func = &amdgpu_vram_mgr_func;
-
-		err = drm_buddy_init(&mgr->mm, man->size, PAGE_SIZE);
-		if (err)
-			return err;
-	} else {
-		man->func = &amdgpu_dummy_vram_mgr_func;
-		DRM_INFO("Setup dummy vram mgr\n");
-	}
+	man->func = &amdgpu_vram_mgr_func;
+	err = gpu_buddy_init(&mgr->mm, man->size, PAGE_SIZE);
+	if (err)
+		return err;
 
 	ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_VRAM, &mgr->manager);
 	ttm_resource_manager_set_used(man, true);
@@ -958,11 +966,11 @@ void amdgpu_vram_mgr_fini(struct amdgpu_device *adev)
 		kfree(rsv);
 
 	list_for_each_entry_safe(rsv, temp, &mgr->reserved_pages, blocks) {
-		drm_buddy_free_list(&mgr->mm, &rsv->allocated, 0);
+		gpu_buddy_free_list(&mgr->mm, &rsv->allocated, 0);
 		kfree(rsv);
 	}
 	if (!adev->gmc.is_app_apu)
-		drm_buddy_fini(&mgr->mm);
+		gpu_buddy_fini(&mgr->mm);
 	mutex_unlock(&mgr->lock);
 
 	ttm_resource_manager_cleanup(man);