伙伴系统内存块拆分和合并
看一个辅助函数，用于伙伴系统中内存块的拆分、合并
/* * The order of subdivision here is critical for the IO subsystem. * Please do not alter this order without good reasons and regression * testing. Specifically, as large blocks of memory are subdivided, * the order in which smaller blocks are delivered depends on the order * they're subdivided in this function. This is the primary factor * influencing the order in which pages are delivered to the IO * subsystem according to empirical testing, and this is also justified * by considering the behavior of a buddy system containing a single * large block of memory acted on by a series of small allocations. * This behavior is a critical factor in sglist merging's success. * * -- wli */ /*此函数主要用于下面这种情况: 分配函数从high中分割出去了low大小的内存； 然后要将high留下的内存块合并放到伙伴系统中；*/ static inline void expand(struct zone *zone, struct page *page, int low, int high, struct free_area *area, int migratetype) { unsigned long size = 1 << high; while (high > low) {/*因为去掉了low的大小，所以最后肯定剩下的 是low的大小(2的指数运算)*/ area--;/*减一到order减一的area*/ high--;/*order减一*/ size >>= 1;/*大小除以2*/ VM_BUG_ON(bad_range(zone, &page[size])); /*加到指定的伙伴系统中*/ list_add(&page[size].lru, &area->free_list[migratetype]); area->nr_free++;/*空闲块加一*/ set_page_order(&page[size], high);/*设置相关order*/ } }
3.2.2 从备用链表中分配页面
/* Remove an element from the buddy allocator from the fallback list */ static inline struct page * __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) { struct free_area * area; int current_order; struct page *page; int migratetype, i; /* Find the largest possible block of pages in the other list */ /* 从最高阶搜索,这样可以尽量的将其他迁移列表中的大块分割,避免形成过多的碎片 */ for (current_order = MAX_ORDER-1; current_order >= order; --current_order) { for (i = 0; i < MIGRATE_TYPES - 1; i++) { /*回调到下一个migratetype*/ migratetype = fallbacks[start_migratetype][i]; /* MIGRATE_RESERVE handled later if necessary */ /* 本函数不处理MIGRATE_RESERVE类型的迁移链表,如果本函数返回NULL, 则上层函数直接从MIGRATE_RESERVE中分配 */ if (migratetype == MIGRATE_RESERVE) continue;/*访问下一个类型*/ area = &(zone->free_area[current_order]); /*如果指定order和类型的链表为空*/ if (list_empty(&area->free_list[migratetype])) continue;/*访问下一个类型*/ /*得到指定类型和order的页面基址*/ page = list_entry(area->free_list[migratetype].next, struct page, lru); area->nr_free--;/*空闲块数减一*/ /* * If breaking a large block of pages, move all free * pages to the preferred allocation list. If falling * back for a reclaimable kernel allocation, be more * agressive about taking ownership of free pages */ if (unlikely(current_order >= (pageblock_order >> 1)) ||/* 要分割的页面是一个大页面,则将整个页面全部迁移到当前迁移类型的链表中, 这样可以避免过多的碎片 */ start_migratetype == MIGRATE_RECLAIMABLE ||/* 目前分配的是可回收页面,这类页面有突发的特点,将页面全部迁移到可回收链表中, 可以避免将其他迁移链表分割成太多的碎片 */ page_group_by_mobility_disabled) {/* 指定了迁移策略,总是将被分割的页面迁移 */ unsigned long pages; /*移动到先前类型的伙伴系统中*/ pages = move_freepages_block(zone, page, start_migratetype); /* Claim the whole block if over half of it is free */ /* pages是移动的页面数,如果可移动的页面数量较多, 则将整个大内存块的迁移类型修改 */ if (pages >= (1 << (pageblock_order-1)) || page_group_by_mobility_disabled) /*设置页面标示*/ set_pageblock_migratetype(page, start_migratetype); migratetype = start_migratetype; } /* Remove the page from the freelists */ list_del(&page->lru); rmv_page_order(page); /* Take ownership for orders >= pageblock_order */ if (current_order >= pageblock_order)//大于pageblock_order的部分设置相应标示 /*这个不太可能，因为pageblock_order为10*/ change_pageblock_range(page, current_order, start_migratetype); /*拆分和合并*/ expand(zone, page, order, current_order, area, migratetype); trace_mm_page_alloc_extfrag(page, order, current_order, start_migratetype, migratetype); return page; } } return NULL; }
备用链表
/* * This array describes the order lists are fallen back to when * the free lists for the desirable migrate type are depleted */ /*指定类型的链表为空时，这个数组规定 回调的到那个类型的链表*/ static int fallbacks[MIGRATE_TYPES][MIGRATE_TYPES-1] = { [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, [MIGRATE_RESERVE] = { MIGRATE_RESERVE, MIGRATE_RESERVE, MIGRATE_RESERVE }, /* Never used */ };
移动到指定类型的伙伴系统中
/*将指定区域段的页面移动到指定类型的 伙伴系统中，其实就是将页面的类型做了 更改，但是是采用移动的方式 功能和上面函数类似，但是要求以 页面块方式对其*/ static int move_freepages_block(struct zone *zone, struct page *page, int migratetype) { unsigned long start_pfn, end_pfn; struct page *start_page, *end_page; /*如下是对齐操作，其中变量pageblock_nr_pages为MAX_ORDER-1*/ start_pfn = page_to_pfn(page); start_pfn = start_pfn & ~(pageblock_nr_pages-1); start_page = pfn_to_page(start_pfn); end_page = start_page + pageblock_nr_pages - 1; end_pfn = start_pfn + pageblock_nr_pages - 1; /* Do not cross zone boundaries */ if (start_pfn < zone->zone_start_pfn) start_page = page; /*结束边界检查*/ if (end_pfn >= zone->zone_start_pfn + zone->spanned_pages) return 0; /*调用上面函数*/ return move_freepages(zone, start_page, end_page, migratetype); }
/* * Move the free pages in a range to the free lists of the requested type. * Note that start_page and end_pages are not aligned on a pageblock * boundary. If alignment is required, use move_freepages_block() */ /*将指定区域段的页面移动到指定类型的 伙伴系统中，其实就是将页面的类型做了 更改，但是是采用移动的方式*/ static int move_freepages(struct zone *zone, struct page *start_page, struct page *end_page, int migratetype) { struct page *page; unsigned long order; int pages_moved = 0; #ifndef CONFIG_HOLES_IN_ZONE /* * page_zone is not safe to call in this context when * CONFIG_HOLES_IN_ZONE is set. This bug check is probably redundant * anyway as we check zone boundaries in move_freepages_block(). * Remove at a later date when no bug reports exist related to * grouping pages by mobility */ BUG_ON(page_zone(start_page) != page_zone(end_page)); #endif for (page = start_page; page <= end_page;) { /* Make sure we are not inadvertently changing nodes */ VM_BUG_ON(page_to_nid(page) != zone_to_nid(zone)); if (!pfn_valid_within(page_to_pfn(page))) { page++; continue; } if (!PageBuddy(page)) { page++; continue; } order = page_order(page); list_del(&page->lru);/*将页面块从原来的伙伴系统链表*/ /*中删除，注意，这里不是一个页面 *而是以该页面的伙伴块*/ list_add(&page->lru,/*添加到指定order和类型下的伙伴系统链表*/ &zone->free_area[order].free_list[migratetype]); page += 1 << order;/*移动页面数往上定位*/ pages_moved += 1 << order;/*移动的页面数*/ } return pages_moved; }