linux 内存管理基于分段、分页把逻辑地址转换为物理地址,同时有些RAM永久的分配给了内核使用用来存放内核代码以及静态数据。其余的RAM为动态内存。linux中采用了很多有效的管理方法,包括页表管理、高端内存(临时映射区、固定映射区、永久映射区、非连续内存区)管理、为减小外部碎片的伙伴系统、为减小内部碎片的slab机制、伙伴系统未建立之前的页面分配制度以及紧急内存管理等等。。
此图copyfrom http://bbs.chinaunix.net/thread-2018659-2-1.html
页描述符:
页描述符记录页框的当前状态,类型为一个struct page的页描述符;所有的页描述符放在mem_map中,每个描述符场为32bytes,
/*
* 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.
*
* The objects in struct page are organized in double word blocks in
* order to allows us to use atomic double word operations on portions
* of struct page. That is currently only used by slub but the arrangement
* allows the use of atomic double word operations on the flags/mapping
* and lru list pointers also.
*/
struct page {
/* First double word block */描述了页框的状态
unsigned long flags; /* Atomic flags, some possibly
* updated asynchronously */
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.
*/
/* Second double word */
struct {
union {
pgoff_t index; /* Our offset within mapping. */
void *freelist; /* slub/slob first free object */
bool pfmemalloc; /* If set by the page allocator,
* ALLOC_NO_WATERMARKS was set
* and the low watermark was not
* met implying that the system
* is under some pressure. The
* caller should try ensure
* this page is only used to
* free other pages.
*/
};
union {
#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
/* Used for cmpxchg_double in slub */
unsigned long counters;
#else
/*
* Keep _count separate from slub cmpxchg_double data.
* As the rest of the double word is protected by
* slab_lock but _count is not.
*/
unsigned counters;
#endif
struct {
union {
/*
* Count of ptes mapped in
* mms, to show when page is
* mapped & limit reverse map
* searches.
*
* Used also for tail pages
* refcounting instead of
* _count. Tail pages cannot
* be mapped and keeping the
* tail page _count zero at
* all times guarantees
* get_page_unless_zero() will
* never succeed on tail
* pages.
*/
atomic_t _mapcount;
struct { /* SLUB */
unsigned inuse:16;
unsigned objects:15;
unsigned frozen:1;
};
int units; /* SLOB */
};
atomic_t _count; /* Usage count, see below. */
};
};
};
/* Third double word block */
union {
struct list_head lru; /* Pageout list, eg. active_list
* protected by zone->lru_lock !
*/
struct { /* slub per cpu partial pages */
struct page *next; /* Next partial slab */
#ifdef CONFIG_64BIT
int pages; /* Nr of partial slabs left */
int pobjects; /* Approximate # of objects */
#else
short int pages;
short int pobjects;
#endif
};
struct list_head list; /* slobs list of pages */
struct { /* slab fields */
struct kmem_cache *slab_cache;
struct slab *slab_page;
};
};
/* Remainder is not double word aligned */
union {
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.
*/
#if USE_SPLIT_PTLOCKS
spinlock_t ptl;
#endif
struct kmem_cache *slab; /* SLUB: Pointer to slab */
struct page *first_page; /* Compound tail pages */
};
/*
* 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
}
然而系统将物理内存划分为几个节点node,
内存的每个节点都由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。每个节点的物理内存又分为几个管理区zone,
typedef struct pglist_data {
struct zone <span style="white-space:pre"> </span>node_zones[MAX_NR_ZONES]; 节点管理区描述数组
struct zonelist node_zonelists[MAX_ZONELISTS];
//页分配器使用的zonelist数据结构;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
int nr_zones; 节点中管理区的个数
#ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */
struct page *node_mem_map<span style="white-space:pre"> </span>节点中页描述符数组
#ifdef CONFIG_MEMCG
struct page_cgroup *node_page_cgroup;
#endif
#endif
#ifndef CONFIG_NO_BOOTMEM
struct bootmem_data *bdata;<span style="white-space:pre"> </span>用在内核初始化阶段
#endif
#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.
*/
spinlock_t node_size_lock;
#endif
unsigned long node_start_pfn;<span style="white-space:pre"> </span>节点中第一个页框的下标
unsigned long node_present_pages; /* total number of physical pages */
unsigned long node_spanned_pages; /* total size of physical page
range, including holes */
int node_id;<span style="white-space:pre"> </span>节点标识符
wait_queue_head_t kswapd_wait;<span style="white-space:pre"> </span>kswapd页换出守护进程使用的等待队列
wait_queue_head_t pfmemalloc_wait;
struct task_struct *kswapd; 指向kswapd的内核线程/* Protected by lock_memory_hotplug() */
int kswapd_max_order; <span style="white-space:pre"> </span>kswapd线程要创建空闲块取对数的值
enum zone_type classzone_idx;
} pg_data_t;
所有的节点描述符存放在一个单向链表中,他的第一个元素由pgdat_list变量所指向
每个内存节点的物理内存划分3个管理区 zone_DMA /zone_normal /zone_highmem
管理区描述符字段
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];
/*
* When free pages are below this point, additional steps are taken
* when reading the number of free pages to avoid per-cpu counter
* drift allowing watermarks to be breached
*/
unsigned long percpu_drift_mark;
/*
* 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.
*/
<span style="white-space:pre"> </span>/ * 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];
/*
* This is a per-zone reserve of pages that should not be
* considered dirtyable memory.
*/
unsigned long dirty_balance_reserve;
#ifdef CONFIG_NUMA
int node; /*所属的NUMA节点。*/
/*
* 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;
#endif
<span style="white-space:pre"> </span>/*每cpu高速缓存所用到,
<span style="white-space:pre"> </span> <span style="white-space:pre"> </span> <span style="white-space:pre">* 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。
*/ </span>
struct per_cpu_pageset __percpu *pageset;
/*
* free areas of different sizes
*/
spinlock_t lock;
int all_unreclaimable; /* All pages pinned */
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/* pfn where the last incremental compaction isolated free pages */
unsigned long compact_cached_free_pfn;
#endif
#ifdef CONFIG_MEMORY_HOTPLUG
/* see spanned/present_pages for more description */
<span style="white-space:pre"> /*该锁用于保护伙伴系统数据结构。即保护free_area相关数据。*</span>/
seqlock_t span_seqlock;
#endif
#ifdef CONFIG_CMA
/*
* CMA needs to increase watermark levels during the allocation
* process to make sure that the system is not starved.
*/
unsigned long min_cma_pages;
#endif
<span style="white-space:pre"> /*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*/ </span>
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 */
#ifdef CONFIG_COMPACTION
/*
* On compaction failure, 1<<compact_defer_shift compactions
* are skipped before trying again. The number attempted since
* last failure is tracked with compact_considered.
*/
unsigned int compact_considered;
unsigned int compact_defer_shift;
int compact_order_failed;
#endif
<span style="white-space:pre"> /*填充的未用字段,确保后面的字段是缓存行对齐的*/ </span>
ZONE_PADDING(_pad1_)
<span style="white-space:pre"> </span>/*
<span style="white-space:pre"> </span> * lru用于确定哪些字段是活跃的,哪些不是活跃的,
<span style="white-space:pre"> </span> *并据此确定应当被写回到磁盘以释放内存。
<span style="white-space:pre"> </span>*/
/* Fields commonly accessed by the page reclaim scanner */
spinlock_t lru_lock;
struct lruvec lruvec;
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];
/*
* The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
* this zone's LRU. Maintained by the pageout code.
*/
unsigned int inactive_ratio;
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 */
unsigned long zone_start_pfn; /*管理区的页面在mem_map中的偏移*/
/*
* 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;
#ifdef CONFIG_MEMORY_ISOLATION
/*
* the number of MIGRATE_ISOLATE *pageblock*.
* We need this for free page counting. Look at zone_watermark_ok_safe.
* It's protected by zone->lock
*/
int nr_pageblock_isolate;
#endif
}