Linux物理內存描述三個層級的struct:
pglist_data//描述內存節點
zone//描述節點內的分區,有normal、DMA、highmem
page//描述一頁,通常爲4K大小
各結構體成員的具體含義,詳見下面代碼中的註釋,英文註釋清晰處請直接參考
/*
* 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 {
struct zone node_zones[MAX_NR_ZONES];//該節點內的內存區
struct zonelist node_zonelists[MAX_ZONELISTS];//節點的備用內存區,也就是所有節點的內存區鏈表,當該節點沒有可用的內存時,就從備用內存區分配;事實上,除非分配內存時指定了GFP_THISNODE標誌,否則均從備用內存區內存區分配,選擇的優先順序是Highmem>Normal>DMA
/*可用內存區數目*/
int nr_zones;
#ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */
struct page *node_mem_map;//本節點第一個頁面的描述符指針
#endif
#ifndef CONFIG_NO_BOOTMEM
struct bootmem_data *bdata;//內核啓動階段Bootmem分配器用來管理內存的struct,其成員node_bootmem_map是bit map指針,每一個bit描述一個頁是否已經被使用
#endif
unsigned long node_start_pfn;//該節點內起始頁面的幀號,即該節點在全局mem_map中的index
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;
wait_queue_head_t kswapd_wait;//該節點的頁交換守護進程的等待隊列,在節點中的頁需要換出時使用
struct task_struct *kswapd;//負該節點的頁交換的守護進程
int kswapd_max_order;//最大可交換的頁數
} pg_data_t;
struct zone {
/* Fields commonly accessed by the page allocator */
/* zone watermarks, access with *_wmark_pages(zone) macros */
unsigned long watermark[NR_WMARK];//管理區的三個水線值:高水線、低水線、MIN水線
#ifdef CONFIG_NUMA
int node;//該內存區所屬的節點
/*
* zone reclaim becomes active if more unmapped pages exist.
*/
unsigned long min_unmapped_pages;//可回收頁面數超過此值啓動回收
unsigned long min_slab_pages;//本管理區中,用於slab的可回收頁面數大於此值時,將回收slab中的緩存頁
#endif
struct per_cpu_pageset __percpu *pageset;//每個cpu頁面緩存,由單個頁組成的頁鏈表,用於在申請單個頁面時使用,
//由於是每個cpu有自己的pageset,這樣可以避免使用鎖,避免該頁被其他cpu使用造成緩存失效,避免內存區被分解爲很多小塊,
//另外per_cpu_pages中有三個成員count,high,batch,分別表示該緩存中的頁數、頁數上限,如果頁數超過了上限,就釋放batch個
//頁回夥伴系統,如果沒有緩存頁可用分配就從buddy中釋放batch個頁到緩存,關於high、batch兩個值的計算分別由函數zone_batchsize,
//setup_pageset完成,結論是:當本zone大約512M時,batch=32,high=6*32=192,當本zone小約512M時,batch=present_pages/1024/4,
//也就是high~=0.15%的本區總內存
/*
* free areas of different sizes
*/
spinlock_t lock;//保護free_area的自旋鎖
#ifdef CONFIG_MEMORY_HOTPLUG
/* see spanned/present_pages for more description */
seqlock_t span_seqlock;//保護spanned/present_pages,不發生熱插拔,這兩個值不會改變,故使用順序所seqlock,兩個變量含義下面介紹
#endif
struct free_area free_area[MAX_ORDER];//Buddy管理的11個隊列,每個隊列的節點管理的內存大小爲2^n個頁面,11個隊列,n從1~11
ZONE_PADDING(_pad1_)//填充字段,確保後面成員緩存行對齊
/* Fields commonly accessed by the page reclaim scanner */
//Linux 中的頁面回收是基於 LRU(least recently used,即最近最少使用 ) 算法的。LRU 算法基於這樣一個事實,
//過去一段時間內頻繁使用的頁面,在不久的將來很可能會被再次訪問到。反過來說,已經很久沒有訪問過的頁面在未來較短的時間內
//也不會被頻繁訪問到。因此,在物理內存不夠用的情況下,這樣的頁面成爲被換出的最佳候選者。LRU 算法的基本原理很簡單,
//爲每個物理頁面綁定一個計數器,用以標識該頁面的訪問頻度。
spinlock_t lru_lock;
struct zone_lru {
struct list_head list;
} lru[NR_LRU_LISTS];
struct zone_reclaim_stat reclaim_stat;
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()
* invocation.
*
* 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;
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.
*/
struct pglist_data *zone_pgdat;//該區所在的節點
/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
unsigned long zone_start_pfn;//管理區的第一個頁面在全局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;
} ____cacheline_internodealigned_in_smp;
/*
* 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 */
struct page *first_page; /* Compound tail pages */如果該頁在buddy中,並且不是buddy中的第一個頁,那麼該指針指向第一個頁
};
union {
pgoff_t index; /* Our offset within mapping. */如果該頁是文件映射,那麼表示本頁面在文件中的偏移
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
};