diff options
Diffstat (limited to 'drivers/gpu/drm/drm_mm.c')
| -rw-r--r-- | drivers/gpu/drm/drm_mm.c | 1023 |
1 files changed, 466 insertions, 557 deletions
diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c index ca1e344f318d..8bfb0b327267 100644 --- a/drivers/gpu/drm/drm_mm.c +++ b/drivers/gpu/drm/drm_mm.c @@ -1,6 +1,7 @@ /************************************************************************** * * 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 @@ -31,9 +32,9 @@ * 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. + * 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. * @@ -58,8 +59,8 @@ * * 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 allocations of its own, so if - * drivers choose not to embed nodes they need to still allocate them + * 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 @@ -67,7 +68,7 @@ * 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 - * depencies in the driver load sequence. + * 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 @@ -77,33 +78,25 @@ * 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. Further more every &drm_mm_node has a color value (which is just an - * opaqua unsigned long) which in conjunction with a driver callback can be used + * 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. + * 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 on 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. */ -static struct drm_mm_node *drm_mm_search_free_generic(const struct drm_mm *mm, - u64 size, - unsigned alignment, - unsigned long color, - enum drm_mm_search_flags flags); -static struct drm_mm_node *drm_mm_search_free_in_range_generic(const struct drm_mm *mm, - u64 size, - unsigned alignment, - unsigned long color, - u64 start, - u64 end, - enum drm_mm_search_flags flags); - #ifdef CONFIG_DRM_DEBUG_MM #include <linux/stackdepot.h> @@ -138,7 +131,7 @@ static void show_leaks(struct drm_mm *mm) if (!buf) return; - list_for_each_entry(node, &mm->head_node.node_list, node_list) { + list_for_each_entry(node, drm_mm_nodes(mm), node_list) { struct stack_trace trace = { .entries = entries, .max_entries = STACKDEPTH @@ -174,9 +167,9 @@ INTERVAL_TREE_DEFINE(struct drm_mm_node, rb, START, LAST, static inline, drm_mm_interval_tree) struct drm_mm_node * -__drm_mm_interval_first(struct drm_mm *mm, u64 start, u64 last) +__drm_mm_interval_first(const struct drm_mm *mm, u64 start, u64 last) { - return drm_mm_interval_tree_iter_first(&mm->interval_tree, + return drm_mm_interval_tree_iter_first((struct rb_root *)&mm->interval_tree, start, last); } EXPORT_SYMBOL(__drm_mm_interval_first); @@ -225,66 +218,151 @@ static void drm_mm_interval_tree_add_node(struct drm_mm_node *hole_node, &drm_mm_interval_tree_augment); } -static void drm_mm_insert_helper(struct drm_mm_node *hole_node, - struct drm_mm_node *node, - u64 size, unsigned alignment, - unsigned long color, - enum drm_mm_allocator_flags flags) +#define RB_INSERT(root, member, expr) do { \ + struct rb_node **link = &root.rb_node, *rb = NULL; \ + u64 x = expr(node); \ + while (*link) { \ + rb = *link; \ + if (x < expr(rb_entry(rb, struct drm_mm_node, member))) \ + link = &rb->rb_left; \ + else \ + link = &rb->rb_right; \ + } \ + rb_link_node(&node->member, rb, link); \ + rb_insert_color(&node->member, &root); \ +} while (0) + +#define HOLE_SIZE(NODE) ((NODE)->hole_size) +#define HOLE_ADDR(NODE) (__drm_mm_hole_node_start(NODE)) + +static void add_hole(struct drm_mm_node *node) { - struct drm_mm *mm = hole_node->mm; - u64 hole_start = drm_mm_hole_node_start(hole_node); - u64 hole_end = drm_mm_hole_node_end(hole_node); - u64 adj_start = hole_start; - u64 adj_end = hole_end; + struct drm_mm *mm = node->mm; - BUG_ON(node->allocated); + node->hole_size = + __drm_mm_hole_node_end(node) - __drm_mm_hole_node_start(node); + DRM_MM_BUG_ON(!drm_mm_hole_follows(node)); - if (mm->color_adjust) - mm->color_adjust(hole_node, color, &adj_start, &adj_end); + RB_INSERT(mm->holes_size, rb_hole_size, HOLE_SIZE); + RB_INSERT(mm->holes_addr, rb_hole_addr, HOLE_ADDR); + + list_add(&node->hole_stack, &mm->hole_stack); +} - if (flags & DRM_MM_CREATE_TOP) - adj_start = adj_end - size; +static void rm_hole(struct drm_mm_node *node) +{ + DRM_MM_BUG_ON(!drm_mm_hole_follows(node)); - if (alignment) { - u64 tmp = adj_start; - unsigned rem; + list_del(&node->hole_stack); + rb_erase(&node->rb_hole_size, &node->mm->holes_size); + rb_erase(&node->rb_hole_addr, &node->mm->holes_addr); + node->hole_size = 0; - rem = do_div(tmp, alignment); - if (rem) { - if (flags & DRM_MM_CREATE_TOP) - adj_start -= rem; - else - adj_start += alignment - rem; + 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 inline u64 rb_hole_size(struct rb_node *rb) +{ + return rb_entry(rb, struct drm_mm_node, rb_hole_size)->hole_size; +} + +static struct drm_mm_node *best_hole(struct drm_mm *mm, u64 size) +{ + struct rb_node *best = NULL; + struct rb_node **link = &mm->holes_size.rb_node; + + while (*link) { + struct rb_node *rb = *link; + + if (size <= rb_hole_size(rb)) { + link = &rb->rb_left; + best = rb; + } else { + link = &rb->rb_right; } } - BUG_ON(adj_start < hole_start); - BUG_ON(adj_end > hole_end); + return rb_hole_size_to_node(best); +} + +static struct drm_mm_node *find_hole(struct drm_mm *mm, u64 addr) +{ + struct drm_mm_node *node = NULL; + struct rb_node **link = &mm->holes_addr.rb_node; - if (adj_start == hole_start) { - hole_node->hole_follows = 0; - list_del(&hole_node->hole_stack); + while (*link) { + u64 hole_start; + + node = rb_hole_addr_to_node(*link); + hole_start = __drm_mm_hole_node_start(node); + + if (addr < hole_start) + link = &node->rb_hole_addr.rb_left; + else if (addr > hole_start + node->hole_size) + link = &node->rb_hole_addr.rb_right; + else + break; } - node->start = adj_start; - node->size = size; - node->mm = mm; - node->color = color; - node->allocated = 1; + 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) +{ + if (RB_EMPTY_ROOT(&mm->holes_size)) + return NULL; - list_add(&node->node_list, &hole_node->node_list); + switch (mode) { + default: + case DRM_MM_INSERT_BEST: + return best_hole(mm, size); - drm_mm_interval_tree_add_node(hole_node, node); + case DRM_MM_INSERT_LOW: + return find_hole(mm, start); - BUG_ON(node->start + node->size > adj_end); + case DRM_MM_INSERT_HIGH: + return find_hole(mm, end); - node->hole_follows = 0; - if (__drm_mm_hole_node_start(node) < hole_end) { - list_add(&node->hole_stack, &mm->hole_stack); - node->hole_follows = 1; + case DRM_MM_INSERT_EVICT: + return list_first_entry_or_null(&mm->hole_stack, + struct drm_mm_node, + hole_stack); } +} - save_stack(node); +static struct drm_mm_node * +next_hole(struct drm_mm *mm, + struct drm_mm_node *node, + enum drm_mm_insert_mode mode) +{ + switch (mode) { + default: + case DRM_MM_INSERT_BEST: + return rb_hole_size_to_node(rb_next(&node->rb_hole_size)); + + case DRM_MM_INSERT_LOW: + return rb_hole_addr_to_node(rb_next(&node->rb_hole_addr)); + + case DRM_MM_INSERT_HIGH: + return rb_hole_addr_to_node(rb_prev(&node->rb_hole_addr)); + + case DRM_MM_INSERT_EVICT: + node = list_next_entry(node, hole_stack); + return &node->hole_stack == &mm->hole_stack ? NULL : node; + } } /** @@ -292,11 +370,11 @@ static void drm_mm_insert_helper(struct drm_mm_node *hole_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. 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. + * 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. @@ -308,28 +386,17 @@ int drm_mm_reserve_node(struct drm_mm *mm, struct drm_mm_node *node) u64 hole_start, hole_end; u64 adj_start, adj_end; - if (WARN_ON(node->size == 0)) - return -EINVAL; - end = node->start + node->size; + if (unlikely(end <= node->start)) + return -ENOSPC; /* Find the relevant hole to add our node to */ - hole = drm_mm_interval_tree_iter_first(&mm->interval_tree, - node->start, ~(u64)0); - if (hole) { - if (hole->start < end) - return -ENOSPC; - } else { - hole = list_entry(&mm->head_node.node_list, - typeof(*hole), node_list); - } - - hole = list_last_entry(&hole->node_list, typeof(*hole), node_list); - if (!hole->hole_follows) + hole = find_hole(mm, node->start); + if (!hole) return -ENOSPC; adj_start = hole_start = __drm_mm_hole_node_start(hole); - adj_end = hole_end = __drm_mm_hole_node_end(hole); + adj_end = hole_end = hole_start + hole->hole_size; if (mm->color_adjust) mm->color_adjust(hole, node->color, &adj_start, &adj_end); @@ -338,174 +405,130 @@ int drm_mm_reserve_node(struct drm_mm *mm, struct drm_mm_node *node) return -ENOSPC; node->mm = mm; - node->allocated = 1; list_add(&node->node_list, &hole->node_list); - drm_mm_interval_tree_add_node(hole, node); + node->allocated = true; + node->hole_size = 0; - if (node->start == hole_start) { - hole->hole_follows = 0; - list_del(&hole->hole_stack); - } - - node->hole_follows = 0; - if (end != hole_end) { - list_add(&node->hole_stack, &mm->hole_stack); - node->hole_follows = 1; - } + 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); /** - * drm_mm_insert_node_generic - search for space and insert @node + * drm_mm_insert_node_in_range - ranged search for space and insert @node * @mm: drm_mm to allocate from * @node: preallocate node to insert * @size: size of the allocation * @alignment: alignment of the allocation * @color: opaque tag value to use for this node - * @sflags: flags to fine-tune the allocation search - * @aflags: flags to fine-tune the allocation behavior + * @range_start: start of the allowed range for this node + * @range_end: end of the allowed range for this node + * @mode: fine-tune the allocation search and placement * - * The preallocated node must be cleared to 0. + * The preallocated @node must be cleared to 0. * * Returns: * 0 on success, -ENOSPC if there's no suitable hole. */ -int drm_mm_insert_node_generic(struct drm_mm *mm, struct drm_mm_node *node, - u64 size, unsigned alignment, - unsigned long color, - enum drm_mm_search_flags sflags, - enum drm_mm_allocator_flags aflags) +int drm_mm_insert_node_in_range(struct drm_mm * const mm, + struct drm_mm_node * const node, + u64 size, u64 alignment, + unsigned long color, + u64 range_start, u64 range_end, + enum drm_mm_insert_mode mode) { - struct drm_mm_node *hole_node; + struct drm_mm_node *hole; + u64 remainder_mask; - if (WARN_ON(size == 0)) - return -EINVAL; + DRM_MM_BUG_ON(range_start >= range_end); - hole_node = drm_mm_search_free_generic(mm, size, alignment, - color, sflags); - if (!hole_node) + if (unlikely(size == 0 || range_end - range_start < size)) return -ENOSPC; - drm_mm_insert_helper(hole_node, node, size, alignment, color, aflags); - return 0; -} -EXPORT_SYMBOL(drm_mm_insert_node_generic); - -static void drm_mm_insert_helper_range(struct drm_mm_node *hole_node, - struct drm_mm_node *node, - u64 size, unsigned alignment, - unsigned long color, - u64 start, u64 end, - enum drm_mm_allocator_flags flags) -{ - struct drm_mm *mm = hole_node->mm; - u64 hole_start = drm_mm_hole_node_start(hole_node); - u64 hole_end = drm_mm_hole_node_end(hole_node); - u64 adj_start = hole_start; - u64 adj_end = hole_end; + if (alignment <= 1) + alignment = 0; - BUG_ON(!hole_node->hole_follows || node->allocated); + remainder_mask = is_power_of_2(alignment) ? alignment - 1 : 0; + for (hole = first_hole(mm, range_start, range_end, size, mode); hole; + hole = next_hole(mm, hole, mode)) { + u64 hole_start = __drm_mm_hole_node_start(hole); + u64 hole_end = hole_start + hole->hole_size; + u64 adj_start, adj_end; + u64 col_start, col_end; - if (adj_start < start) - adj_start = start; - if (adj_end > end) - adj_end = end; + if (mode == DRM_MM_INSERT_LOW && hole_start >= range_end) + break; - if (mm->color_adjust) - mm->color_adjust(hole_node, color, &adj_start, &adj_end); + if (mode == DRM_MM_INSERT_HIGH && hole_end <= range_start) + break; - if (flags & DRM_MM_CREATE_TOP) - adj_start = adj_end - size; + col_start = hole_start; + col_end = hole_end; + if (mm->color_adjust) + mm->color_adjust(hole, color, &col_start, &col_end); - if (alignment) { - u64 tmp = adj_start; - unsigned rem; + adj_start = max(col_start, range_start); + adj_end = min(col_end, range_end); - rem = do_div(tmp, alignment); - if (rem) { - if (flags & DRM_MM_CREATE_TOP) - adj_start -= rem; - else - adj_start += alignment - rem; - } - } + if (adj_end <= adj_start || adj_end - adj_start < size) + continue; - if (adj_start == hole_start) { - hole_node->hole_follows = 0; - list_del(&hole_node->hole_stack); - } + if (mode == DRM_MM_INSERT_HIGH) + adj_start = adj_end - size; - node->start = adj_start; - node->size = size; - node->mm = mm; - node->color = color; - node->allocated = 1; + if (alignment) { + u64 rem; - list_add(&node->node_list, &hole_node->node_list); + if (likely(remainder_mask)) + rem = adj_start & remainder_mask; + else + div64_u64_rem(adj_start, alignment, &rem); + if (rem) { + adj_start -= rem; + if (mode != DRM_MM_INSERT_HIGH) + adj_start += alignment; - drm_mm_interval_tree_add_node(hole_node, node); + if (adj_start < max(col_start, range_start) || + min(col_end, range_end) - adj_start < size) + continue; - BUG_ON(node->start < start); - BUG_ON(node->start < adj_start); - BUG_ON(node->start + node->size > adj_end); - BUG_ON(node->start + node->size > end); + if (adj_end <= adj_start || + adj_end - adj_start < size) + continue; + } + } - node->hole_follows = 0; - if (__drm_mm_hole_node_start(node) < hole_end) { - list_add(&node->hole_stack, &mm->hole_stack); - node->hole_follows = 1; - } + node->mm = mm; + node->size = size; + node->start = adj_start; + node->color = color; + node->hole_size = 0; - save_stack(node); -} + list_add(&node->node_list, &hole->node_list); + drm_mm_interval_tree_add_node(hole, node); + node->allocated = true; -/** - * drm_mm_insert_node_in_range_generic - ranged search for space and insert @node - * @mm: drm_mm to allocate from - * @node: preallocate node to insert - * @size: size of the allocation - * @alignment: alignment of the allocation - * @color: opaque tag value to use for this node - * @start: start of the allowed range for this node - * @end: end of the allowed range for this node - * @sflags: flags to fine-tune the allocation search - * @aflags: flags to fine-tune the allocation behavior - * - * The preallocated node must be cleared to 0. - * - * Returns: - * 0 on success, -ENOSPC if there's no suitable hole. - */ -int drm_mm_insert_node_in_range_generic(struct drm_mm *mm, struct drm_mm_node *node, - u64 size, unsigned alignment, - unsigned long color, - u64 start, u64 end, - enum drm_mm_search_flags sflags, - enum drm_mm_allocator_flags aflags) -{ - struct drm_mm_node *hole_node; + rm_hole(hole); + if (adj_start > hole_start) + add_hole(hole); + if (adj_start + size < hole_end) + add_hole(node); - if (WARN_ON(size == 0)) - return -EINVAL; - - hole_node = drm_mm_search_free_in_range_generic(mm, - size, alignment, color, - start, end, sflags); - if (!hole_node) - return -ENOSPC; + save_stack(node); + return 0; + } - drm_mm_insert_helper_range(hole_node, node, - size, alignment, color, - start, end, aflags); - return 0; + return -ENOSPC; } -EXPORT_SYMBOL(drm_mm_insert_node_in_range_generic); +EXPORT_SYMBOL(drm_mm_insert_node_in_range); /** * drm_mm_remove_node - Remove a memory node from the allocator. @@ -513,150 +536,30 @@ EXPORT_SYMBOL(drm_mm_insert_node_in_range_generic); * * This just removes a node from its drm_mm allocator. The node does not need to * be cleared again before it can be re-inserted into this or any other drm_mm - * allocator. It is a bug to call this function on a un-allocated node. + * allocator. It is a bug to call this function on a unallocated node. */ void drm_mm_remove_node(struct drm_mm_node *node) { struct drm_mm *mm = node->mm; struct drm_mm_node *prev_node; - if (WARN_ON(!node->allocated)) - return; - - BUG_ON(node->scanned_block || node->scanned_prev_free - || node->scanned_next_free); - - prev_node = - list_entry(node->node_list.prev, struct drm_mm_node, node_list); + DRM_MM_BUG_ON(!node->allocated); + DRM_MM_BUG_ON(node->scanned_block); - if (node->hole_follows) { - BUG_ON(__drm_mm_hole_node_start(node) == - __drm_mm_hole_node_end(node)); - list_del(&node->hole_stack); - } else - BUG_ON(__drm_mm_hole_node_start(node) != - __drm_mm_hole_node_end(node)); + prev_node = list_prev_entry(node, node_list); - - if (!prev_node->hole_follows) { - prev_node->hole_follows = 1; - list_add(&prev_node->hole_stack, &mm->hole_stack); - } else - list_move(&prev_node->hole_stack, &mm->hole_stack); + if (drm_mm_hole_follows(node)) + rm_hole(node); drm_mm_interval_tree_remove(node, &mm->interval_tree); list_del(&node->node_list); - node->allocated = 0; -} -EXPORT_SYMBOL(drm_mm_remove_node); - -static int check_free_hole(u64 start, u64 end, u64 size, unsigned alignment) -{ - if (end - start < size) - return 0; - - if (alignment) { - u64 tmp = start; - unsigned rem; - - rem = do_div(tmp, alignment); - if (rem) - start += alignment - rem; - } - - return end >= start + size; -} + node->allocated = false; -static struct drm_mm_node *drm_mm_search_free_generic(const struct drm_mm *mm, - u64 size, - unsigned alignment, - unsigned long color, - enum drm_mm_search_flags flags) -{ - struct drm_mm_node *entry; - struct drm_mm_node *best; - u64 adj_start; - u64 adj_end; - u64 best_size; - - BUG_ON(mm->scanned_blocks); - - best = NULL; - best_size = ~0UL; - - __drm_mm_for_each_hole(entry, mm, adj_start, adj_end, - flags & DRM_MM_SEARCH_BELOW) { - u64 hole_size = adj_end - adj_start; - - if (mm->color_adjust) { - mm->color_adjust(entry, color, &adj_start, &adj_end); - if (adj_end <= adj_start) - continue; - } - - if (!check_free_hole(adj_start, adj_end, size, alignment)) - continue; - - if (!(flags & DRM_MM_SEARCH_BEST)) - return entry; - - if (hole_size < best_size) { - best = entry; - best_size = hole_size; - } - } - - return best; -} - -static struct drm_mm_node *drm_mm_search_free_in_range_generic(const struct drm_mm *mm, - u64 size, - unsigned alignment, - unsigned long color, - u64 start, - u64 end, - enum drm_mm_search_flags flags) -{ - struct drm_mm_node *entry; - struct drm_mm_node *best; - u64 adj_start; - u64 adj_end; - u64 best_size; - - BUG_ON(mm->scanned_blocks); - - best = NULL; - best_size = ~0UL; - - __drm_mm_for_each_hole(entry, mm, adj_start, adj_end, - flags & DRM_MM_SEARCH_BELOW) { - u64 hole_size = adj_end - adj_start; - - if (adj_start < start) - adj_start = start; - if (adj_end > end) - adj_end = end; - - if (mm->color_adjust) { - mm->color_adjust(entry, color, &adj_start, &adj_end); - if (adj_end <= adj_start) - continue; - } - - if (!check_free_hole(adj_start, adj_end, size, alignment)) - continue; - - if (!(flags & DRM_MM_SEARCH_BEST)) - return entry; - - if (hole_size < best_size) { - best = entry; - best_size = hole_size; - } - } - - return best; + if (drm_mm_hole_follows(prev_node)) + rm_hole(prev_node); + add_hole(prev_node); } +EXPORT_SYMBOL(drm_mm_remove_node); /** * drm_mm_replace_node - move an allocation from @old to @new @@ -669,119 +572,114 @@ static struct drm_mm_node *drm_mm_search_free_in_range_generic(const struct drm_ */ void drm_mm_replace_node(struct drm_mm_node *old, struct drm_mm_node *new) { + DRM_MM_BUG_ON(!old->allocated); + + *new = *old; + list_replace(&old->node_list, &new->node_list); - list_replace(&old->hole_stack, &new->hole_stack); rb_replace_node(&old->rb, &new->rb, &old->mm->interval_tree); - new->hole_follows = old->hole_follows; - new->mm = old->mm; - new->start = old->start; - new->size = old->size; - new->color = old->color; - new->__subtree_last = old->__subtree_last; - - old->allocated = 0; - new->allocated = 1; + + if (drm_mm_hole_follows(old)) { + list_replace(&old->hole_stack, &new->hole_stack); + rb_replace_node(&old->rb_hole_size, + &new->rb_hole_size, + &old->mm->holes_size); + rb_replace_node(&old->rb_hole_addr, + &new->rb_hole_addr, + &old->mm->holes_addr); + } + + old->allocated = false; + new->allocated = true; } EXPORT_SYMBOL(drm_mm_replace_node); /** - * DOC: lru scan roaster + * DOC: lru scan roster * * Very often GPUs need to have continuous allocations for a given object. When * evicting objects to make space for a new one it is therefore not most * efficient when we simply start to select all objects from the tail of an LRU * until there's a suitable hole: Especially for big objects or nodes that * otherwise have special allocation constraints there's a good chance we evict - * lots of (smaller) objects unecessarily. + * lots of (smaller) objects unnecessarily. * * The DRM range allocator supports this use-case through the scanning * interfaces. First a scan operation needs to be initialized with - * drm_mm_init_scan() or drm_mm_init_scan_with_range(). The the driver adds - * objects to the roaster (probably by walking an LRU list, but this can be - * freely implemented) until a suitable hole is found or there's no further - * evitable object. - * - * The the driver must walk through all objects again in exactly the reverse + * drm_mm_scan_init() or drm_mm_scan_init_with_range(). The driver adds + * objects to the roster, probably by walking an LRU list, but this can be + * freely implemented. Eviction candiates are added using + * drm_mm_scan_add_block() until a suitable hole is found or there are no + * further evictable objects. Eviction roster metadata is tracked in &struct + * drm_mm_scan. + * + * The driver must walk through all objects again in exactly the reverse * order to restore the allocator state. Note that while the allocator is used * in the scan mode no other operation is allowed. * - * Finally the driver evicts all objects selected in the scan. Adding and - * removing an object is O(1), and since freeing a node is also O(1) the overall - * complexity is O(scanned_objects). So like the free stack which needs to be - * walked before a scan operation even begins this is linear in the number of - * objects. It doesn't seem to hurt badly. - */ - -/** - * drm_mm_init_scan - initialize lru scanning - * @mm: drm_mm to scan - * @size: size of the allocation - * @alignment: alignment of the allocation - * @color: opaque tag value to use for the allocation - * - * This simply sets up the scanning routines with the parameters for the desired - * hole. Note that there's no need to specify allocation flags, since they only - * change the place a node is allocated from within a suitable hole. - * - * Warning: - * As long as the scan list is non-empty, no other operations than - * adding/removing nodes to/from the scan list are allowed. + * Finally the driver evicts all objects selected (drm_mm_scan_remove_block() + * reported true) in the scan, and any overlapping nodes after color adjustment + * (drm_mm_scan_color_evict()). Adding and removing an object is O(1), and + * since freeing a node is also O(1) the overall complexity is + * O(scanned_objects). So like the free stack which needs to be walked before a + * scan operation even begins this is linear in the number of objects. It + * doesn't seem to hurt too badly. */ -void drm_mm_init_scan(struct drm_mm *mm, - u64 size, - unsigned alignment, - unsigned long color) -{ - mm->scan_color = color; - mm->scan_alignment = alignment; - mm->scan_size = size; - mm->scanned_blocks = 0; - mm->scan_hit_start = 0; - mm->scan_hit_end = 0; - mm->scan_check_range = 0; - mm->prev_scanned_node = NULL; -} -EXPORT_SYMBOL(drm_mm_init_scan); /** - * drm_mm_init_scan - initialize range-restricted lru scanning + * drm_mm_scan_init_with_range - initialize range-restricted lru scanning + * @scan: scan state * @mm: drm_mm to scan * @size: size of the allocation * @alignment: alignment of the allocation * @color: opaque tag value to use for the allocation * @start: start of the allowed range for the allocation * @end: end of the allowed range for the allocation + * @mode: fine-tune the allocation search and placement * * This simply sets up the scanning routines with the parameters for the desired - * hole. Note that there's no need to specify allocation flags, since they only - * change the place a node is allocated from within a suitable hole. + * hole. * * Warning: * As long as the scan list is non-empty, no other operations than * adding/removing nodes to/from the scan list are allowed. */ -void drm_mm_init_scan_with_range(struct drm_mm *mm, +void drm_mm_scan_init_with_range(struct drm_mm_scan *scan, + struct drm_mm *mm, u64 size, - unsigned alignment, + u64 alignment, unsigned long color, u64 start, - u64 end) + u64 end, + enum drm_mm_insert_mode mode) { - mm->scan_color = color; - mm->scan_alignment = alignment; - mm->scan_size = size; - mm->scanned_blocks = 0; - mm->scan_hit_start = 0; - mm->scan_hit_end = 0; - mm->scan_start = start; - mm->scan_end = end; - mm->scan_check_range = 1; - mm->prev_scanned_node = NULL; + DRM_MM_BUG_ON(start >= end); + DRM_MM_BUG_ON(!size || size > end - start); + DRM_MM_BUG_ON(mm->scan_active); + + scan->mm = mm; + + if (alignment <= 1) + alignment = 0; + + scan->color = color; + scan->alignment = alignment; + scan->remainder_mask = is_power_of_2(alignment) ? alignment - 1 : 0; + scan->size = size; + scan->mode = mode; + + DRM_MM_BUG_ON(end <= start); + scan->range_start = start; + scan->range_end = end; + + scan->hit_start = U64_MAX; + scan->hit_end = 0; } -EXPORT_SYMBOL(drm_mm_init_scan_with_range); +EXPORT_SYMBOL(drm_mm_scan_init_with_range); /** * drm_mm_scan_add_block - add a node to the scan list + * @scan: the active drm_mm scanner * @node: drm_mm_node to add * * Add a node to the scan list that might be freed to make space for the desired @@ -790,105 +688,165 @@ EXPORT_SYMBOL(drm_mm_init_scan_with_range); * Returns: * True if a hole has been found, false otherwise. */ -bool drm_mm_scan_add_block(struct drm_mm_node *node) +bool drm_mm_scan_add_block(struct drm_mm_scan *scan, + struct drm_mm_node *node) { - struct drm_mm *mm = node->mm; - struct drm_mm_node *prev_node; + struct drm_mm *mm = scan->mm; + struct drm_mm_node *hole; u64 hole_start, hole_end; + u64 col_start, col_end; u64 adj_start, adj_end; - mm->scanned_blocks++; + DRM_MM_BUG_ON(node->mm != mm); + DRM_MM_BUG_ON(!node->allocated); + DRM_MM_BUG_ON(node->scanned_block); + node->scanned_block = true; + mm->scan_active++; + + /* Remove this block from the node_list so that we enlarge the hole + * (distance between the end of our previous node and the start of + * or next), without poisoning the link so that we can restore it + * later in drm_mm_scan_remove_block(). + */ + hole = list_prev_entry(node, node_list); + DRM_MM_BUG_ON(list_next_entry(hole, node_list) != node); + __list_del_entry(&node->node_list); + + hole_start = __drm_mm_hole_node_start(hole); + hole_end = __drm_mm_hole_node_end(hole); + + col_start = hole_start; + col_end = hole_end; + if (mm->color_adjust) + mm->color_adjust(hole, scan->color, &col_start, &col_end); - BUG_ON(node->scanned_block); - node->scanned_block = 1; + adj_start = max(col_start, scan->range_start); + adj_end = min(col_end, scan->range_end); + if (adj_end <= adj_start || adj_end - adj_start < scan->size) + return false; - prev_node = list_entry(node->node_list.prev, struct drm_mm_node, - node_list); + if (scan->mode == DRM_MM_INSERT_HIGH) + adj_start = adj_end - scan->size; - node->scanned_preceeds_hole = prev_node->hole_follows; - prev_node->hole_follows = 1; - list_del(&node->node_list); - node->node_list.prev = &prev_node->node_list; - node->node_list.next = &mm->prev_scanned_node->node_list; - mm->prev_scanned_node = node; - - adj_start = hole_start = drm_mm_hole_node_start(prev_node); - adj_end = hole_end = drm_mm_hole_node_end(prev_node); - - if (mm->scan_check_range) { - if (adj_start < mm->scan_start) - adj_start = mm->scan_start; - if (adj_end > mm->scan_end) - adj_end = mm->scan_end; - } + if (scan->alignment) { + u64 rem; - if (mm->color_adjust) - mm->color_adjust(prev_node, mm->scan_color, - &adj_start, &adj_end); - - if (check_free_hole(adj_start, adj_end, - mm->scan_size, mm->scan_alignment)) { - mm->scan_hit_start = hole_start; - mm->scan_hit_end = hole_end; - return true; + if (likely(scan->remainder_mask)) + rem = adj_start & scan->remainder_mask; + else + div64_u64_rem(adj_start, scan->alignment, &rem); + if (rem) { + adj_start -= rem; + if (scan->mode != DRM_MM_INSERT_HIGH) + adj_start += scan->alignment; + if (adj_start < max(col_start, scan->range_start) || + min(col_end, scan->range_end) - adj_start < scan->size) + return false; + + if (adj_end <= adj_start || + adj_end - adj_start < scan->size) + return false; + } } - return false; + scan->hit_start = adj_start; + scan->hit_end = adj_start + scan->size; + + DRM_MM_BUG_ON(scan->hit_start >= scan->hit_end); + DRM_MM_BUG_ON(scan->hit_start < hole_start); + DRM_MM_BUG_ON(scan->hit_end > hole_end); + + return true; } EXPORT_SYMBOL(drm_mm_scan_add_block); /** * drm_mm_scan_remove_block - remove a node from the scan list + * @scan: the active drm_mm scanner * @node: drm_mm_node to remove * - * Nodes _must_ be removed in the exact same order from the scan list as they - * have been added, otherwise the internal state of the memory manager will be - * corrupted. + * Nodes **must** be removed in exactly the reverse order from the scan list as + * they have been added (e.g. using list_add() as they are added and then + * list_for_each() over that eviction list to remove), otherwise the internal + * state of the memory manager will be corrupted. * * When the scan list is empty, the selected memory nodes can be freed. An - * immediately following drm_mm_search_free with !DRM_MM_SEARCH_BEST will then - * return the just freed block (because its at the top of the free_stack list). + * immediately following drm_mm_insert_node_in_range_generic() or one of the + * simpler versions of that function with !DRM_MM_SEARCH_BEST will then return + * the just freed block (because its at the top of the free_stack list). * * Returns: * True if this block should be evicted, false otherwise. Will always * return false when no hole has been found. */ -bool drm_mm_scan_remove_block(struct drm_mm_node *node) +bool drm_mm_scan_remove_block(struct drm_mm_scan *scan, + struct drm_mm_node *node) { - struct drm_mm *mm = node->mm; struct drm_mm_node *prev_node; - mm->scanned_blocks--; - - BUG_ON(!node->scanned_block); - node->scanned_block = 0; - - prev_node = list_entry(node->node_list.prev, struct drm_mm_node, - node_list); - - prev_node->hole_follows = node->scanned_preceeds_hole; + DRM_MM_BUG_ON(node->mm != scan->mm); + DRM_MM_BUG_ON(!node->scanned_block); + node->scanned_block = false; + + DRM_MM_BUG_ON(!node->mm->scan_active); + node->mm->scan_active--; + + /* During drm_mm_scan_add_block() we decoupled this node leaving + * its pointers intact. Now that the caller is walking back along + * the eviction list we can restore this block into its rightful + * place on the full node_list. To confirm that the caller is walking + * backwards correctly we check that prev_node->next == node->next, + * i.e. both believe the same node should be on the other side of the + * hole. + */ + prev_node = list_prev_entry(node, node_list); + DRM_MM_BUG_ON(list_next_entry(prev_node, node_list) != + list_next_entry(node, node_list)); list_add(&node->node_list, &prev_node->node_list); - return (drm_mm_hole_node_end(node) > mm->scan_hit_start && - node->start < mm->scan_hit_end); + return (node->start + node->size > scan->hit_start && + node->start < scan->hit_end); } EXPORT_SYMBOL(drm_mm_scan_remove_block); /** - * drm_mm_clean - checks whether an allocator is clean - * @mm: drm_mm allocator to check + * drm_mm_scan_color_evict - evict overlapping nodes on either side of hole + * @scan: drm_mm scan with target hole + * + * After completing an eviction scan and removing the selected nodes, we may + * need to remove a few more nodes from either side of the target hole if + * mm.color_adjust is being used. * * Returns: - * True if the allocator is completely free, false if there's still a node - * allocated in it. + * A node to evict, or NULL if there are no overlapping nodes. */ -bool drm_mm_clean(struct drm_mm * mm) +struct drm_mm_node *drm_mm_scan_color_evict(struct drm_mm_scan *scan) { - struct list_head *head = &mm->head_node.node_list; + struct drm_mm *mm = scan->mm; + struct drm_mm_node *hole; + u64 hole_start, hole_end; + + DRM_MM_BUG_ON(list_empty(&mm->hole_stack)); + + if (!mm->color_adjust) + return NULL; + + hole = list_first_entry(&mm->hole_stack, typeof(*hole), hole_stack); + hole_start = __drm_mm_hole_node_start(hole); + hole_end = hole_start + hole->hole_size; - return (head->next->next == head); + DRM_MM_BUG_ON(hole_start > scan->hit_start); + DRM_MM_BUG_ON(hole_end < scan->hit_end); + + mm->color_adjust(hole, scan->color, &hole_start, &hole_end); + if (hole_start > scan->hit_start) + return hole; + if (hole_end < scan->hit_end) + return list_next_entry(hole, node_list); + + return NULL; } -EXPORT_SYMBOL(drm_mm_clean); +EXPORT_SYMBOL(drm_mm_scan_color_evict); /** * drm_mm_init - initialize a drm-mm allocator @@ -898,26 +856,26 @@ EXPORT_SYMBOL(drm_mm_clean); * * Note that @mm must be cleared to 0 before calling this function. */ -void drm_mm_init(struct drm_mm * mm, u64 start, u64 size) +void drm_mm_init(struct drm_mm *mm, u64 start, u64 size) { + DRM_MM_BUG_ON(start + size <= start); + + mm->color_adjust = NULL; + INIT_LIST_HEAD(&mm->hole_stack); - mm->scanned_blocks = 0; + mm->interval_tree = RB_ROOT; + mm->holes_size = RB_ROOT; + mm->holes_addr = RB_ROOT; /* Clever trick to avoid a special case in the free hole tracking. */ INIT_LIST_HEAD(&mm->head_node.node_list); - mm->head_node.allocated = 0; - mm->head_node.hole_follows = 1; - mm->head_node.scanned_block = 0; - mm->head_node.scanned_prev_free = 0; - mm->head_node.scanned_next_free = 0; + mm->head_node.allocated = false; mm->head_node.mm = mm; mm->head_node.start = start + size; - mm->head_node.size = start - mm->head_node.start; - list_add_tail(&mm->head_node.hole_stack, &mm->hole_stack); + mm->head_node.size = -size; + add_hole(&mm->head_node); - mm->interval_tree = RB_ROOT; - - mm->color_adjust = NULL; + mm->scan_active = 0; } EXPORT_SYMBOL(drm_mm_init); @@ -930,95 +888,46 @@ EXPORT_SYMBOL(drm_mm_init); */ void drm_mm_takedown(struct drm_mm *mm) { - if (WARN(!list_empty(&mm->head_node.node_list), + if (WARN(!drm_mm_clean(mm), "Memory manager not clean during takedown.\n")) show_leaks(mm); - } EXPORT_SYMBOL(drm_mm_takedown); -static u64 drm_mm_debug_hole(struct drm_mm_node *entry, - const char *prefix) +static u64 drm_mm_dump_hole(struct drm_printer *p, const struct drm_mm_node *entry) { - u64 hole_start, hole_end, hole_size; - - if (entry->hole_follows) { - hole_start = drm_mm_hole_node_start(entry); - hole_end = drm_mm_hole_node_end(entry); - hole_size = hole_end - hole_start; - pr_debug("%s %#llx-%#llx: %llu: free\n", prefix, hole_start, - hole_end, hole_size); - return hole_size; - } - - return 0; -} - -/** - * drm_mm_debug_table - dump allocator state to dmesg - * @mm: drm_mm allocator to dump - * @prefix: prefix to use for dumping to dmesg - */ -void drm_mm_debug_table(struct drm_mm *mm, const char *prefix) -{ - struct drm_mm_node *entry; - u64 total_used = 0, total_free = 0, total = 0; + u64 start, size; - total_free += drm_mm_debug_hole(&mm->head_node, prefix); - - drm_mm_for_each_node(entry, mm) { - pr_debug("%s %#llx-%#llx: %llu: used\n", prefix, entry->start, - entry->start + entry->size, entry->size); - total_used += entry->size; - total_free += drm_mm_debug_hole(entry, prefix); + size = entry->hole_size; + if (size) { + start = drm_mm_hole_node_start(entry); + drm_printf(p, "%#018llx-%#018llx: %llu: free\n", + start, start + size, size); } - total = total_free + total_used; - pr_debug("%s total: %llu, used %llu free %llu\n", prefix, total, - total_used, total_free); + return size; } -EXPORT_SYMBOL(drm_mm_debug_table); - -#if defined(CONFIG_DEBUG_FS) -static u64 drm_mm_dump_hole(struct seq_file *m, struct drm_mm_node *entry) -{ - u64 hole_start, hole_end, hole_size; - - if (entry->hole_follows) { - hole_start = drm_mm_hole_node_start(entry); - hole_end = drm_mm_hole_node_end(entry); - hole_size = hole_end - hole_start; - seq_printf(m, "%#018llx-%#018llx: %llu: free\n", hole_start, - hole_end, hole_size); - return hole_size; - } - - return 0; -} - /** - * drm_mm_dump_table - dump allocator state to a seq_file - * @m: seq_file to dump to - * @mm: drm_mm allocator to dump + * drm_mm_print - print allocator state + * @mm: drm_mm allocator to print + * @p: DRM printer to use */ -int drm_mm_dump_table(struct seq_file *m, struct drm_mm *mm) +void drm_mm_print(const struct drm_mm *mm, struct drm_printer *p) { - struct drm_mm_node *entry; + const struct drm_mm_node *entry; u64 total_used = 0, total_free = 0, total = 0; - total_free += drm_mm_dump_hole(m, &mm->head_node); + total_free += drm_mm_dump_hole(p, &mm->head_node); drm_mm_for_each_node(entry, mm) { - seq_printf(m, "%#018llx-%#018llx: %llu: used\n", entry->start, + drm_printf(p, "%#018llx-%#018llx: %llu: used\n", entry->start, entry->start + entry->size, entry->size); total_used += entry->size; - total_free += drm_mm_dump_hole(m, entry); + total_free += drm_mm_dump_hole(p, entry); } total = total_free + total_used; - seq_printf(m, "total: %llu, used %llu free %llu\n", total, + drm_printf(p, "total: %llu, used %llu free %llu\n", total, total_used, total_free); - return 0; } -EXPORT_SYMBOL(drm_mm_dump_table); -#endif +EXPORT_SYMBOL(drm_mm_print); |