drm/amdgpu: add drm buddy support to amdgpu

- Switch to drm buddy allocator
- Add resource cursor support for drm buddy

v2(Matthew Auld):
  - replace spinlock with mutex as we call kmem_cache_zalloc
    (..., GFP_KERNEL) in drm_buddy_alloc() function

  - lock drm_buddy_block_trim() function as it calls
    mark_free/mark_split are all globally visible

v3(Matthew Auld):
  - remove trim method error handling as we address the failure case
    at drm_buddy_block_trim() function

v4:
  - fix warnings reported by kernel test robot <lkp@intel.com>

v5:
  - fix merge conflict issue

v6:
  - fix warnings reported by kernel test robot <lkp@intel.com>

v7:
  - remove DRM_BUDDY_RANGE_ALLOCATION flag usage

v8:
  - keep DRM_BUDDY_RANGE_ALLOCATION flag usage
  - resolve conflicts created by drm/amdgpu: remove VRAM accounting v2

v9(Christian):
  - merged the below patch
     - drm/amdgpu: move vram inline functions into a header
  - rename label name as fallback
  - move struct amdgpu_vram_mgr to amdgpu_vram_mgr.h
  - remove unnecessary flags from struct amdgpu_vram_reservation
  - rewrite block NULL check condition
  - change else style as per coding standard
  - rewrite the node max size
  - add a helper function to fetch the first entry from the list

v10(Christian):
   - rename amdgpu_get_node() function name as amdgpu_vram_mgr_first_block

v11:
   - if size is not aligned with min_page_size, enable is_contiguous flag,
     therefore, the size round up to the power of two and trimmed to the
     original size.
v12:
   - rename the function names having prefix as amdgpu_vram_mgr_*()
   - modify the round_up() logic conforming to contiguous flag enablement
     or if size is not aligned to min_block_size
   - modify the trim logic
   - rename node as block wherever applicable

Signed-off-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220407224843.2416-1-Arunpravin.PaneerSelvam@amd.com
Signed-off-by: Christian König <christian.koenig@amd.com>

1 files changed, 78 insertions, 19 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
index acfa207cf970..6546552e596c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
@@ -30,12 +30,15 @@
 #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;
-	struct drm_mm_node	*node;
+	void			*node;
+	uint32_t		mem_type;
 };
 
 /**
@@ -52,27 +55,63 @@ 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 || res->mem_type == TTM_PL_SYSTEM) {
-		cur->start = start;
-		cur->size = size;
-		cur->remaining = size;
-		cur->node = NULL;
-		WARN_ON(res && start + size > res->num_pages << PAGE_SHIFT);
-		return;
-	}
+	if (!res)
+		goto fallback;
 
 	BUG_ON(start + size > res->num_pages << PAGE_SHIFT);
 
-	node = to_ttm_range_mgr_node(res)->mm_nodes;
-	while (start >= node->size << PAGE_SHIFT)
-		start -= node++->size << 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);
+		cur->remaining = size;
+		cur->node = node;
+		break;
+	default:
+		goto fallback;
+	}
 
-	cur->start = (node->start << PAGE_SHIFT) + start;
-	cur->size = min((node->size << PAGE_SHIFT) - start, size);
+	return;
+
+fallback:
+	cur->start = start;
+	cur->size = size;
 	cur->remaining = size;
-	cur->node = node;
+	cur->node = NULL;
+	WARN_ON(res && start + size > res->num_pages << PAGE_SHIFT);
+	return;
 }
 
 /**
@@ -85,7 +124,9 @@ static inline void amdgpu_res_first(struct ttm_resource *res,
  */
 static inline void amdgpu_res_next(struct amdgpu_res_cursor *cur, uint64_t size)
 {
-	struct drm_mm_node *node = cur->node;
+	struct drm_buddy_block *block;
+	struct drm_mm_node *node;
+	struct list_head *next;
 
 	BUG_ON(size > cur->remaining);
 
@@ -99,9 +140,27 @@ static inline void amdgpu_res_next(struct amdgpu_res_cursor *cur, uint64_t size)
 		return;
 	}
 
-	cur->node = ++node;
-	cur->start = node->start << PAGE_SHIFT;
-	cur->size = min(node->size << PAGE_SHIFT, cur->remaining);
+	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;
+	}
 }
 
 #endif