linux使用于广泛的体系结构,因此需要用一种与体系结构无关的方式来描述内存。linux用VM描述和管理内存。在VM中兽药的普遍概念就是非一致内存访问。对于大型机器而言,内存会分成许多簇,依据簇与处理器“距离”的不同,访问不同的簇会有不同的代价。
每个簇都被认为是一个节点(pg_data_t),每个节点被分成很多的成为管理区(zone)的块,用于表示内存中的某个范围。除了ZONE_DMA,ZONE_NORMAL,ZONE_HIGHMEM以外,linux2.6.32中引入了ZONE_MOVABLE,用于适应大块连续内存的分配。
每个物理页面由一个page结构体描述,所有的结构都存储在一个全局的mem_map数组中(非平板模式),该数组通常存放在ZONE_NORMAL的首部,或者就在校内存系统中为装入内核映像而预留的区域之后。
节点
内存的每个节点都有pg_data_t描述,在分配一个页面时,linux采用节点局部分配的策略,从最靠近运行中的CPU的节点分配内存。由于进程往往是在同一个CPU上运行,因此从当前节点得到的内存很可能被用到。
- /*
- * The pg_data_t structure is used in machines with CONFIG_DISCONTIGMEM
- * (mostly NUMA machines?) to denote a higher-level memory zone than the
- * zone denotes.
- *
- * On NUMA machines, each NUMA node would have a pg_data_t to describe
- * it’s memory layout.
- *
- * Memory statistics and page replacement data structures are maintained on a
- * per-zone basis.
- */
- struct bootmem_data;
- typedef struct pglist_data {
- /*该节点内的内存区。可能的区域类型用zone_type表示。 */
- struct zone node_zones[MAX_NR_ZONES];
- /* 该节点的备用内存区。当节点没有可用内存时,就从备用区中分配内存。*/
- struct zonelist node_zonelists[MAX_ZONELISTS];
- /*可用内存区数目,即node_zones数据中保存的最后一个有效区域的索引*/
- int nr_zones;
- #ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */
- /* 在平坦型的内存模型中,它指向本节点第一个页面的描述符。 */
- struct page *node_mem_map;
- #ifdef CONFIG_CGROUP_MEM_RES_CTLR
- /*cgroup相关*/
- struct page_cgroup *node_page_cgroup;
- #endif
- #endif
- /**
- * 在内存子系统初始化以前,即boot阶段也需要进行内存管理。
- * 此结构用于这个阶段的内存管理。
- */
- struct bootmem_data *bdata;
- #ifdef CONFIG_MEMORY_HOTPLUG
- /*
- * Must be held any time you expect node_start_pfn, node_present_pages
- * or node_spanned_pages stay constant. Holding this will also
- * guarantee that any pfn_valid() stays that way.
- *
- * Nests above zone->lock and zone->size_seqlock.
- */
- /*当系统支持内存热插拨时,用于保护本结构中的与节点大小相关的字段。
- 哪调用node_start_pfn,node_present_pages,node_spanned_pages相关的代码时,需要使用该锁。
- */
- spinlock_t node_size_lock;
- #endif
- /*起始页面帧号,指出该节点在全局mem_map中
- 的偏移*/
- unsigned long node_start_pfn;
- unsigned long node_present_pages; /* total number of physical pages */
- unsigned long node_spanned_pages; /* total size of physical page range, including holes */
- /*节点编号*/
- int node_id;
- /*等待该节点内的交换守护进程的等待队列。将节点中的页帧换出时会用到。*/
- wait_queue_head_t kswapd_wait;
- /*负责该节点的交换守��进程。*/
- struct task_struct *kswapd;
- /*由页交换子系统使用,定义要释放的区域大小。*/
- int kswapd_max_order;
- } pg_data_t;
每个管理区由一个zone结构体描述,对于管理区的类型描述如下
- enum zone_type {
- #ifdef CONFIG_ZONE_DMA
- /*
- * ZONE_DMA is used when there are devices that are not able
- * to do DMA to all of addressable memory (ZONE_NORMAL). Then we
- * carve out the portion of memory that is needed for these devices.
- * The range is arch specific.
- *
- * Some examples
- *
- * Architecture Limit
- * —————————
- * parisc, ia64, sparc <4G
- * s390 <2G
- * arm Various
- * alpha Unlimited or 0-16MB.
- *
- * i386, x86_64 and multiple other arches
- * <16M.
- */
- ZONE_DMA,
- #endif
- #ifdef CONFIG_ZONE_DMA32
- /*
- * x86_64 needs two ZONE_DMAs because it supports devices that are
- * only able to do DMA to the lower 16M but also 32 bit devices that
- * can only do DMA areas below 4G.
- */
- ZONE_DMA32,
- #endif
- /*
- * Normal addressable memory is in ZONE_NORMAL. DMA operations can be
- * performed on pages in ZONE_NORMAL if the DMA devices support
- * transfers to all addressable memory.
- */
- ZONE_NORMAL,
- #ifdef CONFIG_HIGHMEM
- /*
- * A memory area that is only addressable by the kernel through
- * mapping portions into its own address space. This is for example
- * used by i386 to allow the kernel to address the memory beyond
- * 900MB. The kernel will set up special mappings (page
- * table entries on i386) for each page that the kernel needs to
- * access.
- */
- ZONE_HIGHMEM,
- #endif
- /*
- 这是一个伪内存段。为了防止形成物理内存碎片,
- 可以将虚拟地址对应的物理地址进行迁移。
- */
- ZONE_MOVABLE,
- __MAX_NR_ZONES
- };
管理区用于跟踪诸如页面使用情况统计数,空闲区域信息和锁信息等。
- struct zone {
- /* Fields commonly accessed by the page allocator */
- /* zone watermarks, access with *_wmark_pages(zone) macros */
- /*本管理区的三个水线值:高水线(比较充足)、低水线、MIN水线。*/
- unsigned long watermark[NR_WMARK];
- /*
- * We don’t know if the memory that we’re going to allocate will be freeable
- * or/and it will be released eventually, so to avoid totally wasting several
- * GB of ram we must reserve some of the lower zone memory (otherwise we risk
- * to run OOM on the lower zones despite there’s tons of freeable ram
- * on the higher zones). This array is recalculated at runtime if the
- * sysctl_lowmem_reserve_ratio sysctl changes.
- */
- /**
- * 当高端内存、normal内存区域中无法分配到内存时,需要从normal、DMA区域中分配内存。
- * 为了避免DMA区域被消耗光,需要额外保留一些内存供驱动使用。
- * 该字段就是指从上级内存区退到回内存区时,需要额外保留的内存数量。
- */
- unsigned long lowmem_reserve[MAX_NR_ZONES];
- #ifdef CONFIG_NUMA
- /*所属的NUMA节点。*/
- int node;
- /*
- * zone reclaim becomes active if more unmapped pages exist.
- */
- /*当可回收的页超过此值时,将进行页面回收。*/
- unsigned long min_unmapped_pages;
- /*当管理区中,用于slab的可回收页大于此值时,将回收slab中的缓存页。*/
- unsigned long min_slab_pages;
- /*
- * 每CPU的页面缓存。
- * 当分配单个页面时,首先从该缓存中分配页面。这样可以:
- *避免使用全局的锁
- * 避免同一个页面反复被不同的CPU分配,引起缓存行的失效。
- * 避免将管理区中的大块分割成碎片。
- */
- struct per_cpu_pageset *pageset[NR_CPUS];
- #else
- struct per_cpu_pageset pageset[NR_CPUS];
- #endif
- /*
- * free areas of different sizes
- */
- /*该锁用于保护伙伴系统数据结构。即保护free_area相关数据。*/
- spinlock_t lock;
- #ifdef CONFIG_MEMORY_HOTPLUG
- /* see spanned/present_pages for more description */
- /*用于保护spanned/present_pages等变量。这些变量几乎不会发生变化,除非发生了内存热插拨操作。
- 这几个变量并不被lock字段保护。并且主要用于读,因此使用读写锁。*/
- seqlock_t span_seqlock;
- #endif
- /*伙伴系统的主要变量。这个数组定义了11个队列,每个队列中的元素都是大小为2^n的页面*/
- struct free_area free_area[MAX_ORDER];
- #ifndef CONFIG_SPARSEMEM
- /*
- * Flags for a pageblock_nr_pages block. See pageblock-flags.h.
- * In SPARSEMEM, this map is stored in struct mem_section
- */
- /*本管理区里的页面标志数组*/
- unsigned long *pageblock_flags;
- #endif /* CONFIG_SPARSEMEM */
- /*填充的未用字段,确保后面的字段是缓存行对齐的*/
- ZONE_PADDING(_pad1_)
- /* Fields commonly accessed by the page reclaim scanner */
- /*
- * lru相关的字段用于内存回收。这个字段用于保护这几个回收相关的字段。
- * lru用于确定哪些字段是活跃的,哪些不是活跃的,并据此确定应当被写回到磁盘以释放内存。
- */
- spinlock_t lru_lock;
- /* 匿名活动页、匿名不活动页、文件活动页、文件不活动页链表头*/
- struct zone_lru {
- struct list_head list;
- } lru[NR_LRU_LISTS];
- /*页面回收状态*/
- struct zone_reclaim_stat reclaim_stat;
- /*自从最后一次回收页面以来,扫过的页面数*/
- unsigned long pages_scanned; /* since last reclaim */
- unsigned long flags; /* zone flags, see below */
- /* Zone statistics */
- atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
- /*
- * prev_priority holds the scanning priority for this zone. It is
- * defined as the scanning priority at which we achieved our reclaim
- * target at the previous try_to_free_pages() or balance_pgdat()
- * invokation.
- *
- * We use prev_priority as a measure of how much stress page reclaim is
- * under – it drives the swappiness decision: whether to unmap mapped
- * pages.
- *
- * Access to both this field is quite racy even on uniprocessor. But
- * it is expected to average out OK.
- */
- int prev_priority;
- /*
- * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
- * this zone’s LRU. Maintained by the pageout code.
- */
- unsigned int inactive_ratio;
- /*为cache对齐*/
- ZONE_PADDING(_pad2_)
- /* Rarely used or read-mostly fields */
- /*
- * wait_table — the array holding the hash table
- * wait_table_hash_nr_entries — the size of the hash table array
- * wait_table_bits — wait_table_size == (1 << wait_table_bits)
- *
- * The purpose of all these is to keep track of the people
- * waiting for a page to become available and make them
- * runnable again when possible. The trouble is that this
- * consumes a lot of space, especially when so few things
- * wait on pages at a given time. So instead of using
- * per-page waitqueues, we use a waitqueue hash table.
- *
- * The bucket discipline is to sleep on the same queue when
- * colliding and wake all in that wait queue when removing.
- * When something wakes, it must check to be sure its page is
- * truly available, a la thundering herd. The cost of a
- * collision is great, but given the expected load of the
- * table, they should be so rare as to be outweighed by the
- * benefits from the saved space.
- *
- * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the
- * primary users of these fields, and in mm/page_alloc.c
- * free_area_init_core() performs the initialization of them.
- */
- wait_queue_head_t * wait_table;
- unsigned long wait_table_hash_nr_entries;
- unsigned long wait_table_bits;
- /*
- * Discontig memory support fields.
- */
- /*管理区属于的节点*/
- struct pglist_data *zone_pgdat;
- /* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
- /*管理区的页面在mem_map中的偏移*/
- unsigned long zone_start_pfn;
- /*
- * zone_start_pfn, spanned_pages and present_pages are all
- * protected by span_seqlock. It is a seqlock because it has
- * to be read outside of zone->lock, and it is done in the main
- * allocator path. But, it is written quite infrequently.
- *
- * The lock is declared along with zone->lock because it is
- * frequently read in proximity to zone->lock. It’s good to
- * give them a chance of being in the same cacheline.
- */
- unsigned long spanned_pages; /* total size, including holes */
- unsigned long present_pages; /* amount of memory (excluding holes) */
- /*
- * rarely used fields:
- */
- const char *name;
- } ____cacheline_internodealigned_in_smp;
页面
系统中每个物理页面都有一个相关联的page用于记录该页面的状态。
- /*
- * Each physical page in the system has a struct page associated with
- * it to keep track of whatever it is we are using the page for at the
- * moment. Note that we have no way to track which tasks are using
- * a page, though if it is a pagecache page, rmap structures can tell us
- * who is mapping it.
- */
- struct page {
- unsigned long flags; /* Atomic flags, some possibly
- * updated asynchronously */
- atomic_t _count; /* Usage count, see below. */
- union {
- atomic_t _mapcount; /* Count of ptes mapped in mms,
- * to show when page is mapped
- * & limit reverse map searches.
- */
- struct { /* SLUB */
- u16 inuse;
- u16 objects;
- };
- };
- union {
- struct {
- unsigned long private; /* Mapping-private opaque data:
- * usually used for buffer_heads
- * if PagePrivate set; used for
- * swp_entry_t if PageSwapCache;
- * indicates order in the buddy
- * system if PG_buddy is set.
- */
- struct address_space *mapping; /* If low bit clear, points to
- * inode address_space, or NULL.
- * If page mapped as anonymous
- * memory, low bit is set, and
- * it points to anon_vma object:
- * see PAGE_MAPPING_ANON below.
- */
- };
- #if USE_SPLIT_PTLOCKS
- spinlock_t ptl;
- #endif
- struct kmem_cache *slab; /* SLUB: Pointer to slab */
- /* 如果属于伙伴系统,并且不是伙伴系统中的第一个页
- 则指向第一个页*/
- struct page *first_page; /* Compound tail pages */
- };
- union {/*如果是文件映射,那么表示本页面在文件中的位置(偏移)*/
- pgoff_t index; /* Our offset within mapping. */
- void *freelist; /* SLUB: freelist req. slab lock */
- };
- struct list_head lru; /* Pageout list, eg. active_list
- * protected by zone->lru_lock !
- */
- /*
- * On machines where all RAM is mapped into kernel address space,
- * we can simply calculate the virtual address. On machines with
- * highmem some memory is mapped into kernel virtual memory
- * dynamically, so we need a place to store that address.
- * Note that this field could be 16 bits on x86 … 😉
- *
- * Architectures with slow multiplication can define
- * WANT_PAGE_VIRTUAL in asm/page.h
- */
- #if defined(WANT_PAGE_VIRTUAL)
- void *virtual; /* Kernel virtual address (NULL if
- not kmapped, ie. highmem) */
- #endif /* WANT_PAGE_VIRTUAL */
- #ifdef CONFIG_WANT_PAGE_DEBUG_FLAGS
- unsigned long debug_flags; /* Use atomic bitops on this */
- #endif
- #ifdef CONFIG_KMEMCHECK
- /*
- * kmemcheck wants to track the status of each byte in a page; this
- * is a pointer to such a status block. NULL if not tracked.
- */
- void *shadow;
- #endif
- };