目录
linux内存管理
2019-05-05 by jinliang
物理内存
内存结构:
物理内存描述
内存模型:
- UMA 一致性内存访问
- NUMA 非一致性内存访问
查看手机发现CONFIG_NUMA未定义,所以当前手机为UMA模型
节点 pg_data_t
pg_data_t用于表示节点的基本元素,定义如下:
./include/linux/mmzone.h
typedef struct pglist_data {
//包含了节点中各个内存域的数据结构,最大3个,不足的话,其余数组用0填充.
struct zone node_zones[MAX_NR_ZONES];
//制定了备用节点机器内存域的列表,以便在当前节点没有可用空间时,在备用节点分配内存.
struct zonelist node_zonelists[MAX_ZONELISTS];
//节点中不同内存域的数目保存在nr_zones中.
int nr_zones;
#ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */
struct page *node_mem_map;
#ifdef CONFIG_PAGE_EXTENSION
struct page_ext *node_page_ext;
#endif
#endif
#ifndef CONFIG_NO_BOOTMEM
struct bootmem_data *bdata;
#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.
*
* pgdat_resize_lock() and pgdat_resize_unlock() are provided to
* manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG.
*
* Nests above zone->lock and zone->span_seqlock
*/
spinlock_t node_size_lock;
#endif
// 该节点第一个页帧的逻辑编号.系统所有节点的页帧是依次编号的,每个页帧的号码是全局唯一的.
unsigned long node_start_pfn;
// 制定了结点中页帧的数目,而node_spanned_pages则给出了该节点以页帧为单位计算的长度.二者
// 二者值可能不同,因为节点中可能有一些空洞,并不对应真正的页帧.
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;
wait_queue_head_t pfmemalloc_wait;
struct task_struct *kswapd; /* Protected by
mem_hotplug_begin/end() */
int kswapd_order;
enum zone_type kswapd_classzone_idx;
int kswapd_failures; /* Number of 'reclaimed == 0' runs */
/*
* This is a per-node reserve of pages that are not available
* to userspace allocations.
*/
unsigned long totalreserve_pages;
/* Write-intensive fields used by page reclaim */
ZONE_PADDING(_pad1_)
/* 用于对zone中LRU链表并行访问时进行保护的自旋锁*/
spinlock_t lru_lock;
/* Fields commonly accessed by the page reclaim scanner */
struct lruvec lruvec;
/*
* The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
* this node's LRU. Maintained by the pageout code.
*/
unsigned int inactive_ratio;
unsigned long flags;
ZONE_PADDING(_pad2_)
/* Per-node vmstats */
struct per_cpu_nodestat __percpu *per_cpu_nodestats;
atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS];
} pg_data_t;
管理区zone
一个管理区域通过struct zone_struct描述, 其被定义为zone_t, 用以表示内存的某个范围
./include/linux/mmzone.h
struct zone {
/* Read-mostly fields */
/* zone watermarks, access with *_wmark_pages(zone) macros */
/* 每個zone在系統啓動的時候会计算出3个水位值,分別是WMARK_MIN/WMARK_LOW WMARK_HIGH水位,
* 在這個頁面分配器和kswapd頁面回收中会用到*/
unsigned long watermark[NR_WMARK];
unsigned long nr_reserved_highatomic;
/*
* 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 being tons of freeable ram on the higher zones). This array is
* recalculated at runtime if the sysctl_lowmem_reserve_ratio sysctl
* changes.
*/
long lowmem_reserve[MAX_NR_ZONES];
#ifdef CONFIG_NUMA
int node;
#endif
/* 指向内存节点*/
struct pglist_data *zone_pgdat;
/*用于维护per-cpu上的一系列页面,以减少自旋锁的争用*/
struct per_cpu_pageset __percpu *pageset;
#ifndef CONFIG_SPARSEMEM
/*
* Flags for a pageblock_nr_pages block. See pageblock-flags.h.
* In SPARSEMEM, this map is stored in struct mem_section
*/
unsigned long *pageblock_flags;
#endif /* CONFIG_SPARSEMEM */
/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
/* zone中开始页面的页帧号*/
unsigned long zone_start_pfn;
/*
* spanned_pages is the total pages spanned by the zone, including
* holes, which is calculated as:
* spanned_pages = zone_end_pfn - zone_start_pfn;
*
* present_pages is physical pages existing within the zone, which
* is calculated as:
* present_pages = spanned_pages - absent_pages(pages in holes);
*
* managed_pages is present pages managed by the buddy system, which
* is calculated as (reserved_pages includes pages allocated by the
* bootmem allocator):
* managed_pages = present_pages - reserved_pages;
*
* So present_pages may be used by memory hotplug or memory power
* management logic to figure out unmanaged pages by checking
* (present_pages - managed_pages). And managed_pages should be used
* by page allocator and vm scanner to calculate all kinds of watermarks
* and thresholds.
*
* Locking rules:
*
* zone_start_pfn and spanned_pages are 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 span_seq 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.
*
* Write access to present_pages at runtime should be protected by
* mem_hotplug_begin/end(). Any reader who can't tolerant drift of
* present_pages should get_online_mems() to get a stable value.
*
* Read access to managed_pages should be safe because it's unsigned
* long. Write access to zone->managed_pages and totalram_pages are
* protected by managed_page_count_lock at runtime. Idealy only
* adjust_managed_page_count() should be used instead of directly
* touching zone->managed_pages and totalram_pages.
*/
/* zone中被伙伴系统管理的页面数量*/
unsigned long managed_pages;
/*zone中包含的页面数量*/
unsigned long spanned_pages;
// zone中实际管理的页面数量,对一些体系结构来说,其值和spanned_pages相等
unsigned long present_pages;
const char *name;
#ifdef CONFIG_MEMORY_ISOLATION
/*
* Number of isolated pageblock. It is used to solve incorrect
* freepage counting problem due to racy retrieving migratetype
* of pageblock. Protected by zone->lock.
*/
unsigned long nr_isolate_pageblock;
#endif
#ifdef CONFIG_MEMORY_HOTPLUG
/* see spanned/present_pages for more description */
seqlock_t span_seqlock;
#endif
int initialized;
/* Write-intensive fields used from the page allocator */
ZONE_PADDING(_pad1_)
/* free areas of different sizes */
// 管理空闲区域的数组,包含管理链表等
struct free_area free_area[MAX_ORDER];
/* zone flags, see below */
unsigned long flags;
/* Primarily protects free_area */
// 并行访问时用于对zone保护的自旋锁.
spinlock_t lock;
/* Write-intensive fields used by compaction and vmstats. */
ZONE_PADDING(_pad2_)
/*
* 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;
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/* pfn where compaction free scanner should start */
unsigned long compact_cached_free_pfn;
/* pfn where async and sync compaction migration scanner should start */
unsigned long compact_cached_migrate_pfn[2];
#endif
#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
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/* Set to true when the PG_migrate_skip bits should be cleared */
bool compact_blockskip_flush;
#endif
bool contiguous;
ZONE_PADDING(_pad3_)
/* Zone statistics */
atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS];
} ____cacheline_internodealigned_in_smp;
page
页帧(page frame)代表了系统内存的最小单位, 堆内存中的每个页都会创建一个struct page的一个实例.
mm_types.h
/*
* 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.
*/
/*
* flags存储了体系结构无关的标志,用于描述页的属性.
* _count是一个使用的计数,表示内核中引用该页的次数,在其值达到0时,内核就知道page实例当前不适用,
* 因此可以删除.如果其值大于0,该实例决不会从内存中删除
* _mapcount表示在也表中有多少项指向该页
* lru是一个表头,用于在各种链表上维护该页,以便将页按不同类别分组,最重要的类别是活动和不活动页
* 内核可以将多个毗连的页合并为一个较大的复合页.*/
struct page {
/* First double word block */
/* 原子标志,有些情况下会异步更新*/
unsigned long flags; /* Atomic flags, some possibly
* updated asynchronously */
union {
/* 如果最低位为0,则指向inode address_space或为null,
* 如果页映射为匿名内存,最低位置位1,而且该指针指向anon_vam对象*/
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.
*/
void *s_mem; /* slab first object */
atomic_t compound_mapcount; /* first tail page */
/* page_deferred_list().next -- second tail page */
};
/* Second double word */
union {
/* 在映射内偏移量*/
pgoff_t index; /* Our offset within mapping. */
/* */
void *freelist; /* sl[aou]b first free object */
/* page_deferred_list().prev -- second tail page */
};
union {
#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
/* Used for cmpxchg_double in slub */
unsigned long counters;
#else
/*
* Keep _refcount separate from slub cmpxchg_double data.
* As the rest of the double word is protected by slab_lock
* but _refcount is not.
*/
unsigned counters;
#endif
struct {
union {
/*
* Count of ptes mapped in mms, to show when
* page is mapped & limit reverse map searches.
*
* Extra information about page type may be
* stored here for pages that are never mapped,
* in which case the value MUST BE <= -2.
* See page-flags.h for more details.
*/
/* 内存管理子系统中映射页表项计数*/
atomic_t _mapcount;
unsigned int active; /* SLAB */
struct { /* SLUB */
/* 用于slub分配其:对象数目*/
unsigned inuse:16;
unsigned objects:15;
unsigned frozen:1;
};
int units; /* SLOB */
};
/*
* Usage count, *USE WRAPPER FUNCTION* when manual
* accounting. See page_ref.h
*/
atomic_t _refcount;
};
};
/*
* Third double word block
*
* WARNING: bit 0 of the first word encode PageTail(). That means
* the rest users of the storage space MUST NOT use the bit to
* avoid collision and false-positive PageTail().
*/
union {
struct list_head lru; /* Pageout list, eg. active_list
* protected by zone_lru_lock !
* Can be used as a generic list
* by the page owner.
*/
struct dev_pagemap *pgmap; /* ZONE_DEVICE pages are never on an
* lru or handled by a slab
* allocator, this points to the
* hosting device page map.
*/
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 rcu_head rcu_head; /* Used by SLAB
* when destroying via RCU
*/
/* Tail pages of compound page */
struct {
unsigned long compound_head; /* If bit zero is set */
/* First tail page only */
#ifdef CONFIG_64BIT
/*
* On 64 bit system we have enough space in struct page
* to encode compound_dtor and compound_order with
* unsigned int. It can help compiler generate better or
* smaller code on some archtectures.
*/
unsigned int compound_dtor;
unsigned int compound_order;
#else
unsigned short int compound_dtor;
unsigned short int compound_order;
#endif
};
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
struct {
unsigned long __pad; /* do not overlay pmd_huge_pte
* with compound_head to avoid
* possible bit 0 collision.
*/
pgtable_t pmd_huge_pte; /* protected by page->ptl */
};
#endif
};
/* Remainder is not double word aligned */
union {
/* 由映射私有,不透明数据:
* 如果设置了pageprivate,通常用于buffer_heads
* 如果设置了pageswapcache,则用于视频_entry_t
* 如果设置了PG_buddy,则用于表示伙伴系统中的阶*/
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_PTE_PTLOCKS
#if ALLOC_SPLIT_PTLOCKS
spinlock_t *ptl;
#else
spinlock_t ptl;
#endif
#endif
struct kmem_cache *slab_cache; /* SL[AU]B: Pointer to slab */
};
#ifdef CONFIG_MEMCG
struct mem_cgroup *mem_cgroup;
#endif
/*
* 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 LAST_CPUPID_NOT_IN_PAGE_FLAGS
int _last_cpupid;
#endif
}
页表
物理内存初始化
memblock
memblock用于开机阶段的内存管理.