/************************************************************************** * * Copyright 2006 Tungsten Graphics, Inc., Bismarck, ND., USA. * Copyright 2016 Intel Corporation * All Rights Reserved. * * 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, sub license, 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 (including the * next paragraph) 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 NON-INFRINGEMENT. IN NO EVENT SHALL * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS 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. * * **************************************************************************/ /* * Generic simple memory manager implementation. Intended to be used as a base * class implementation for more advanced memory managers. * * Note that the algorithm used is quite simple and there might be substantial * performance gains if a smarter free list is implemented. Currently it is * just an unordered stack of free regions. This could easily be improved if * an RB-tree is used instead. At least if we expect heavy fragmentation. * * Aligned allocations can also see improvement. * * Authors: * Thomas Hellström <thomas-at-tungstengraphics-dot-com> */ #include <linux/export.h>#include <linux/interval_tree_generic.h>#include <linux/seq_file.h>#include <linux/slab.h>#include <linux/stacktrace.h> #include <drm/drm_mm.h>#include <drm/drm_print.h> /** * DOC: Overview * * drm_mm provides a simple range allocator. The drivers are free to use the * resource allocator from the linux core if it suits them, the upside of drm_mm * is that it's in the DRM core. Which means that it's easier to extend for * some of the crazier special purpose needs of gpus. * * The main data struct is &drm_mm, allocations are tracked in &drm_mm_node. * Drivers are free to embed either of them into their own suitable * datastructures. drm_mm itself will not do any memory allocations of its own, * so if drivers choose not to embed nodes they need to still allocate them * themselves. * * The range allocator also supports reservation of preallocated blocks. This is * useful for taking over initial mode setting configurations from the firmware, * where an object needs to be created which exactly matches the firmware's * scanout target. As long as the range is still free it can be inserted anytime * after the allocator is initialized, which helps with avoiding looped * dependencies in the driver load sequence. * * drm_mm maintains a stack of most recently freed holes, which of all * simplistic datastructures seems to be a fairly decent approach to clustering * allocations and avoiding too much fragmentation. This means free space * searches are O(num_holes). Given that all the fancy features drm_mm supports * something better would be fairly complex and since gfx thrashing is a fairly * steep cliff not a real concern. Removing a node again is O(1). * * drm_mm supports a few features: Alignment and range restrictions can be * supplied. Furthermore every &drm_mm_node has a color value (which is just an * opaque unsigned long) which in conjunction with a driver callback can be used * to implement sophisticated placement restrictions. The i915 DRM driver uses * this to implement guard pages between incompatible caching domains in the * graphics TT. * * Two behaviors are supported for searching and allocating: bottom-up and * top-down. The default is bottom-up. Top-down allocation can be used if the * memory area has different restrictions, or just to reduce fragmentation. * * Finally iteration helpers to walk all nodes and all holes are provided as are * some basic allocator dumpers for debugging. * * Note that this range allocator is not thread-safe, drivers need to protect * modifications with their own locking. The idea behind this is that for a full * memory manager additional data needs to be protected anyway, hence internal * locking would be fully redundant. */ #ifdef CONFIG_DRM_DEBUG_MM#include <linux/stackdepot.h> #define STACKDEPTH 32#define BUFSZ 4096 static noinline void save_stack(struct drm_mm_node *node){	unsigned long entries[STACKDEPTH];	unsigned int n; 	n = stack_trace_save(entries, ARRAY_SIZE(entries), 1); 	/* May be called under spinlock, so avoid sleeping */	node->stack = stack_depot_save(entries, n, GFP_NOWAIT);} static void show_leaks(struct drm_mm *mm){	struct drm_mm_node *node;	char *buf; 	buf = kmalloc(BUFSZ, GFP_KERNEL);	if (!buf)		return; 	list_for_each_entry(node, drm_mm_nodes(mm), node_list) {		if (!node->stack) {			DRM_ERROR("node [%08llx + %08llx]: unknown owner\n",				  node->start, node->size);			continue;		} 		stack_depot_snprint(node->stack, buf, BUFSZ, 0);		DRM_ERROR("node [%08llx + %08llx]: inserted at\n%s",			  node->start, node->size, buf);	} 	kfree(buf);} #undef STACKDEPTH#undef BUFSZ#elsestatic void save_stack(struct drm_mm_node *node) { }static void show_leaks(struct drm_mm *mm) { }#endif #define START(node) ((node)->start)#define LAST(node)  ((node)->start + (node)->size - 1) INTERVAL_TREE_DEFINE(struct drm_mm_node, rb,		     u64, __subtree_last,		     START, LAST, static inline __maybe_unused, drm_mm_interval_tree) struct drm_mm_node *__drm_mm_interval_first(const struct drm_mm *mm, u64 start, u64 last){	return drm_mm_interval_tree_iter_first((struct rb_root_cached *)&mm->interval_tree,					       start, last) ?: (struct drm_mm_node *)&mm->head_node;}EXPORT_SYMBOL(__drm_mm_interval_first); static void drm_mm_interval_tree_add_node(struct drm_mm_node *hole_node,					  struct drm_mm_node *node){	struct drm_mm *mm = hole_node->mm;	struct rb_node **link, *rb;	struct drm_mm_node *parent;	bool leftmost; 	node->__subtree_last = LAST(node); 	if (drm_mm_node_allocated(hole_node)) {		rb = &hole_node->rb;		while (rb) {			parent = rb_entry(rb, struct drm_mm_node, rb);			if (parent->__subtree_last >= node->__subtree_last)				break; 			parent->__subtree_last = node->__subtree_last;			rb = rb_parent(rb);		} 		rb = &hole_node->rb;		link = &hole_node->rb.rb_right;		leftmost = false;	} else {		rb = NULL;		link = &mm->interval_tree.rb_root.rb_node;		leftmost = true;	} 	while (*link) {		rb = *link;		parent = rb_entry(rb, struct drm_mm_node, rb);		if (parent->__subtree_last < node->__subtree_last)			parent->__subtree_last = node->__subtree_last;		if (node->start < parent->start) {			link = &parent->rb.rb_left;		} else {			link = &parent->rb.rb_right;			leftmost = false;		}	} 	rb_link_node(&node->rb, rb, link);	rb_insert_augmented_cached(&node->rb, &mm->interval_tree, leftmost,				   &drm_mm_interval_tree_augment);} #define HOLE_SIZE(NODE) ((NODE)->hole_size)#define HOLE_ADDR(NODE) (__drm_mm_hole_node_start(NODE)) static u64 rb_to_hole_size(struct rb_node *rb){	return rb_entry(rb, struct drm_mm_node, rb_hole_size)->hole_size;} static void insert_hole_size(struct rb_root_cached *root,			     struct drm_mm_node *node){	struct rb_node **link = &root->rb_root.rb_node, *rb = NULL;	u64 x = node->hole_size;	bool first = true; 	while (*link) {		rb = *link;		if (x > rb_to_hole_size(rb)) {			link = &rb->rb_left;		} else {			link = &rb->rb_right;			first = false;		}	} 	rb_link_node(&node->rb_hole_size, rb, link);	rb_insert_color_cached(&node->rb_hole_size, root, first);} RB_DECLARE_CALLBACKS_MAX(static, augment_callbacks,			 struct drm_mm_node, rb_hole_addr,			 u64, subtree_max_hole, HOLE_SIZE) static void insert_hole_addr(struct rb_root *root, struct drm_mm_node *node){	struct rb_node **link = &root->rb_node, *rb_parent = NULL;	u64 start = HOLE_ADDR(node), subtree_max_hole = node->subtree_max_hole;	struct drm_mm_node *parent; 	while (*link) {		rb_parent = *link;		parent = rb_entry(rb_parent, struct drm_mm_node, rb_hole_addr);		if (parent->subtree_max_hole < subtree_max_hole)			parent->subtree_max_hole = subtree_max_hole;		if (start < HOLE_ADDR(parent))			link = &parent->rb_hole_addr.rb_left;		else			link = &parent->rb_hole_addr.rb_right;	} 	rb_link_node(&node->rb_hole_addr, rb_parent, link);	rb_insert_augmented(&node->rb_hole_addr, root, &augment_callbacks);} static void add_hole(struct drm_mm_node *node){	struct drm_mm *mm = node->mm; 	node->hole_size =		__drm_mm_hole_node_end(node) - __drm_mm_hole_node_start(node);	node->subtree_max_hole = node->hole_size;	DRM_MM_BUG_ON(!drm_mm_hole_follows(node)); 	insert_hole_size(&mm->holes_size, node);	insert_hole_addr(&mm->holes_addr, node); 	list_add(&node->hole_stack, &mm->hole_stack);} static void rm_hole(struct drm_mm_node *node){	DRM_MM_BUG_ON(!drm_mm_hole_follows(node)); 	list_del(&node->hole_stack);	rb_erase_cached(&node->rb_hole_size, &node->mm->holes_size);	rb_erase_augmented(&node->rb_hole_addr, &node->mm->holes_addr,			   &augment_callbacks);	node->hole_size = 0;	node->subtree_max_hole = 0; 	DRM_MM_BUG_ON(drm_mm_hole_follows(node));} static inline struct drm_mm_node *rb_hole_size_to_node(struct rb_node *rb){	return rb_entry_safe(rb, struct drm_mm_node, rb_hole_size);} static inline struct drm_mm_node *rb_hole_addr_to_node(struct rb_node *rb){	return rb_entry_safe(rb, struct drm_mm_node, rb_hole_addr);} static struct drm_mm_node *best_hole(struct drm_mm *mm, u64 size){	struct rb_node *rb = mm->holes_size.rb_root.rb_node;	struct drm_mm_node *best = NULL; 	do {		struct drm_mm_node *node =			rb_entry(rb, struct drm_mm_node, rb_hole_size); 		if (size <= node->hole_size) {			best = node;			rb = rb->rb_right;		} else {			rb = rb->rb_left;		}	} while (rb); 	return best;} static bool usable_hole_addr(struct rb_node *rb, u64 size){	return rb && rb_hole_addr_to_node(rb)->subtree_max_hole >= size;} static struct drm_mm_node *find_hole_addr(struct drm_mm *mm, u64 addr, u64 size){	struct rb_node *rb = mm->holes_addr.rb_node;	struct drm_mm_node *node = NULL; 	while (rb) {		u64 hole_start; 		if (!usable_hole_addr(rb, size))			break; 		node = rb_hole_addr_to_node(rb);		hole_start = __drm_mm_hole_node_start(node); 		if (addr < hole_start)			rb = node->rb_hole_addr.rb_left;		else if (addr > hole_start + node->hole_size)			rb = node->rb_hole_addr.rb_right;		else			break;	} 	return node;} static struct drm_mm_node *first_hole(struct drm_mm *mm,	   u64 start, u64 end, u64 size,	   enum drm_mm_insert_mode mode){	switch (mode) {	default:	case DRM_MM_INSERT_BEST:		return best_hole(mm, size); 	case DRM_MM_INSERT_LOW:		return find_hole_addr(mm, start, size); 	case DRM_MM_INSERT_HIGH:		return find_hole_addr(mm, end, size); 	case DRM_MM_INSERT_EVICT:		return list_first_entry_or_null(&mm->hole_stack,						struct drm_mm_node,						hole_stack);	}} /** * DECLARE_NEXT_HOLE_ADDR - macro to declare next hole functions * @name: name of function to declare * @first: first rb member to traverse (either rb_left or rb_right). * @last: last rb member to traverse (either rb_right or rb_left). * * This macro declares a function to return the next hole of the addr rb tree. * While traversing the tree we take the searched size into account and only * visit branches with potential big enough holes. */ #define DECLARE_NEXT_HOLE_ADDR(name, first, last)			\static struct drm_mm_node *name(struct drm_mm_node *entry, u64 size)	\{									\	struct rb_node *parent, *node = &entry->rb_hole_addr;		\									\	if (!entry || RB_EMPTY_NODE(node))				\		return NULL;						\									\	if (usable_hole_addr(node->first, size)) {			\		node = node->first;					\		while (usable_hole_addr(node->last, size))		\			node = node->last;				\		return rb_hole_addr_to_node(node);			\	}								\									\	while ((parent = rb_parent(node)) && node == parent->first)	\		node = parent;						\									\	return rb_hole_addr_to_node(parent);				\} DECLARE_NEXT_HOLE_ADDR(next_hole_high_addr, rb_left, rb_right)DECLARE_NEXT_HOLE_ADDR(next_hole_low_addr, rb_right, rb_left) static struct drm_mm_node *next_hole(struct drm_mm *mm,	  struct drm_mm_node *node,	  u64 size,	  enum drm_mm_insert_mode mode){	switch (mode) {	default:	case DRM_MM_INSERT_BEST:		return rb_hole_size_to_node(rb_prev(&node->rb_hole_size)); 	case DRM_MM_INSERT_LOW:		return next_hole_low_addr(node, size); 	case DRM_MM_INSERT_HIGH:		return next_hole_high_addr(node, size); 	case DRM_MM_INSERT_EVICT:		node = list_next_entry(node, hole_stack);		return &node->hole_stack == &mm->hole_stack ? NULL : node;	}} /** * drm_mm_reserve_node - insert an pre-initialized node * @mm: drm_mm allocator to insert @node into * @node: drm_mm_node to insert * * This functions inserts an already set-up &drm_mm_node into the allocator, * meaning that start, size and color must be set by the caller. All other * fields must be cleared to 0. This is useful to initialize the allocator with * preallocated objects which must be set-up before the range allocator can be * set-up, e.g. when taking over a firmware framebuffer. * * Returns: * 0 on success, -ENOSPC if there's no hole where @node is. */int drm_mm_reserve_node(struct drm_mm *mm, struct drm_mm_node *node){	struct drm_mm_node *hole;	u64 hole_start, hole_end;	u64 adj_start, adj_end;	u64 end; 	end = node->start + node->size;	if (unlikely(end <= node->start))		return -ENOSPC; 	/* Find the relevant hole to add our node to */	hole = find_hole_addr(mm, node->start, 0);	if (!hole)		return -ENOSPC; 	adj_start = hole_start = __drm_mm_hole_node_start(hole);	adj_end = hole_end = hole_start + hole->hole_size; 	if (mm->color_adjust)		mm->color_adjust(hole, node->color, &adj_start, &adj_end); 	if (adj_start > node->start || adj_end < end)		return -ENOSPC; 	node->mm = mm; 	__set_bit(DRM_MM_NODE_ALLOCATED_BIT, &node->flags);	list_add(&node->node_list, &hole->node_list);	drm_mm_interval_tree_add_node(hole, node);	node->hole_size = 0; 	rm_hole(hole);	if (node->start > hole_start)		add_hole(hole);	if (end < hole_end)		add_hole(node); 	save_stack(node);	return 0;}EXPORT_SYMBOL(drm_mm_reserve_node); static u64 rb_to_hole_size_or_zero(struct rb_node *rb){	return rb ? rb_to_hole_size(rb) : 0;} /** * drm_mm_insert_node_in_range - ranged search for space and insert @node

Lines 1–500 of 1007. Load more