一些重要struct

//+++++++++++struct列表+++++++++++++++++++++++++++++++++++++++++++

struct mm_struct ;struct vm_area_struct

 /*这个参考《深入理解LINUX内存管理》学习笔记 */

typedef struct pglist_data;

struct zone;

struct page;

//++++++++++++以下是个struct的详细解析++++++++++++++++++++++++++++++++++

//struct mm_struct 可以由

current->mm

或者

task = get_proc_task(file->f_path.dentry->d_inode); //get_pid_task(proc_pid(inode), PIDTYPE_PID);

mm = get_task_mm(task);

得到。

struct mm_struct{struct vm_area_struct * mmap;/* 这个链表链接了属于这个内存描述符的所有 vm_area_struct 结构体。*/struct rb_root mm_rb;                      /* 由于属于一个内存描述符的内存区域可能非常多,为了加快内存区域的查找以及添加删除等操作的速度,内核用 mm_rb 表示一棵链接了所有内存区域的红黑树。*/       /*mmap 和 mm_rb 是用两种不同的数据结构表示同一批数据。*/ struct vm_area_struct * mmap_cache;;/* 指向最后一个引用的线性区对象*/#ifdef CONFIG_MMU  /* 在进程地址空间中搜索有效线性地址区间的方法   */unsigned long (*get_unmapped_area) (struct file *filp,unsigned long addr, unsigned long len,unsigned long pgoff, unsigned long flags);#endifunsigned long mmap_base;/* base of mmap area */unsigned long mmap_legacy_base;         /* base of mmap area in bottom-up allocations */unsigned long task_size;/* size of task vm space */unsigned long highest_vm_end;/* highest vma end address */pgd_t * pgd;  /*    指向页全局目录   */        atomic_t mm_users;        atomic_t mm_count;/*每一个进程如果拥有一个内存描述符,则会增加 mm_users 的计数,所有 mm_users 的计数只相当于 mm_count 的一个计数。比如n 个 Linux 线程共享同一个内存描述符,那么对应的内存描述符的 mm_users 计数则为n,而 mm_count 则可能只是 1。如果有内核执行序列想要访问一个内存描述符,则该执行序列先增加 mm_count 的计数,使用结束后减少 mm_count 的计数。一但mm_count 减为 0,表示该内存描述符没有任何引用,则它会被内核销毁。*/ int map_count;/* number of VMAs */    /*  线性区的个数   */spinlock_t page_table_lock;/* Protects page tables and some counters */        struct rw_semaphore mmap_sem;/*mmap_sem 是一个读写锁,凡是需要操作内存描述符中的内存区域时,则需要先得到相应的读锁或者写锁,使用结束后释放该锁*/struct list_head mmlist;/* List of maybe swapped mm's.These are globally strung * together off init_mm.mmlist, and are protected * by mmlist_lock *//*mm_list 字段是一个循环双链表。它链接了系统中所有的内存描述符。*/unsigned long hiwater_rss;/* High-watermark of RSS usage */   /*  进程所拥有的最大页框数   */unsigned long hiwater_vm; /*   进程线性区中的最大页数    */unsigned long total_vm;/* Total pages mapped */unsigned long locked_vm;/* Pages that have PG_mlocked set */  /*"锁住"而不能换出的页的个数*/unsigned long pinned_vm;/* Refcount permanently increased */unsigned long shared_vm;/* Shared pages (files) */  /*共享文件内存映射中的页数*/unsigned long exec_vm;/* VM_EXEC & ~VM_WRITE */ /*可执行内存映射中的页数*/unsigned long stack_vm;/* VM_GROWSUP/DOWN */  /*用户态堆栈中的页数*/unsigned long def_flags;unsigned long nr_ptes;/* Page table pages */unsigned long start_code, end_code, start_data, end_data; /*代码段的起始地址，代码段的最后地址，数据段的起始地址和数据段的最后的地址*/unsigned long start_brk, brk, start_stack;/*堆的起始地址，堆的当前最后地址，用户态堆栈的起始地址*/ unsigned long arg_start, arg_end, env_start, env_end;/*命令行参数的起始地址，命令行参数的最后地址，环境变量的起始地址，环境变量的最后地址*/unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */     /*    开始执行ELF程序时会使用到saved_auxv参数   *//* * Special counters, in some configurations protected by the * page_table_lock, in other configurations by being atomic. */struct mm_rss_stat rss_stat;struct linux_binfmt *binfmt;cpumask_var_t cpu_vm_mask_var;/* Architecture-specific MM context */mm_context_t context;unsigned long flags; /* Must use atomic bitops to access the bits */struct core_state *core_state; /* coredumping support */#ifdef CONFIG_AIOspinlock_tioctx_lock;struct hlist_headioctx_list;#endif#ifdef CONFIG_MM_OWNER/* * "owner" points to a task that is regarded as the canonical * user/owner of this mm. All of the following must be true in * order for it to be changed: * * current == mm->owner * current->mm != mm * new_owner->mm == mm * new_owner->alloc_lock is held */struct task_struct __rcu *owner;#endif/* store ref to file /proc/<pid>/exe symlink points to */struct file *exe_file;#ifdef CONFIG_MMU_NOTIFIERstruct mmu_notifier_mm *mmu_notifier_mm;#endif#ifdef CONFIG_TRANSPARENT_HUGEPAGEpgtable_t pmd_huge_pte; /* protected by page_table_lock */#endif#ifdef CONFIG_CPUMASK_OFFSTACKstruct cpumask cpumask_allocation;#endif#ifdef CONFIG_NUMA_BALANCING/* * numa_next_scan is the next time that the PTEs will be marked * pte_numa. NUMA hinting faults will gather statistics and migrate * pages to new nodes if necessary. */unsigned long numa_next_scan;/* numa_next_reset is when the PTE scanner period will be reset */unsigned long numa_next_reset;/* Restart point for scanning and setting pte_numa */unsigned long numa_scan_offset;/* numa_scan_seq prevents two threads setting pte_numa */int numa_scan_seq;/* * The first node a task was scheduled on. If a task runs on * a different node than Make PTE Scan Go Now. */int first_nid;#endif#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)/* * An operation with batched TLB flushing is going on. Anything that * can move process memory needs to flush the TLB when moving a * PROT_NONE or PROT_NUMA mapped page. */bool tlb_flush_pending;#endifstruct uprobes_state uprobes_state;};

//++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

struct vm_area_struct  {  struct mm_struct * vm_mm; /*指向该 VMA 属于的内存描述符。*/  unsigned long vm_start; /*虚拟区开始的地址*/  unsigned long vm_end; /*虚拟区结束的地址,但不包括 vm_end 指向的地址,即vm_end 是虚拟内存区域的最后一个有效字节的后一个字节。*/  struct vm_area_struct *vm_next;/*链接虚存区*/  pgprot_t vm_page_prot; /*虚存区的保护权限*/  unsigned long vm_flags; /*虚存区的标志*/  short vm_avl_height;/*AVL的高度*/  struct vm_area_struct * vm_avl_left; /*左虚存区节点*/  struct vm_area_struct * vm_avl_right;/*右虚存区节点*/  struct vm_area_struct *vm_next_share;  struct vm_area_struct **vm_pprev_share;  struct vm_operations_struct * vm_ops;/*对虚存区操作的函数*/  unsigned long vm_pgoff; /* 映射文件中的偏移量*/  struct file * vm_file;/*vm_file 是该内存区域对应的文件,如果内存区域是匿名的,则该字段被置为 NULL。*/  unsigned long vm_raend;/  voidvoid * vm_private_data; /*指向内存区的私有数据*/  }; 

//++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

//++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

//++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

typedef struct pglist_data {struct zone node_zones[MAX_NR_ZONES];          /*节点中的管理区 分别为ZONE_DMA,ZONE_NORMAL,ZONE_HIGHMEM*//*list中zone的顺序代表了分配内存的顺序，前者分配内存失败将会到后者的区域中分配内存;当调用free_area_init_core()时，由mm/page_alloc.c文件中的build_zonelists()函数设置*/struct zonelist node_zonelists[MAX_ZONELISTS]; int nr_zones;     /*节点中管理区的数目，不一定为3个，有的节点中可能不存在ZONE_DMA*/#ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */struct page *node_mem_map;  /*node中的第一个page，它可以指向mem_map中的任何一个page*/#ifdef CONFIG_CGROUP_MEM_RES_CTLRstruct page_cgroup *node_page_cgroup;#endif#endifstruct bootmem_data *bdata;/*这个仅用于boot 的内存分配*/#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;#endifunsigned long node_start_pfn;     /*pfn是page frame number的缩写。这个成员是用于表示node中的开始那个page在物理内存中的位置的;  该节点的起始页框编号*/unsigned long node_present_pages; /* total number of physical pages ;node中的真正可以使用的page数量*/unsigned long node_spanned_pages; /* total size of physical page  range, including holes ;   */int node_id;                      /*节点标识符，代表当前节点是系统中的第几个节点*/wait_queue_head_t kswapd_wait;    /*页换出进程使用的等待队列*/struct task_struct *kswapd;       /*指向页换出进程的进程描述符*/int kswapd_max_order;             /*kswapd将要创建的空闲块的大小取对数的值*/}

//++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

struct zone {/* Fields commonly accessed by the page allocator *//* zone watermarks, access with *_wmark_pages(zone) macros */unsigned long watermark[NR_WMARK];/*该管理区的三个水平线值，min,low,high*//* * 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. */ /*每个管理区必须保留的页框数*/ /*为了防止一些代码必须运行在低地址区域，所以事先保留一些低地址区域的内存*/unsigned longlowmem_reserve[MAX_NR_ZONES]; #ifdef CONFIG_NUMA           /*如果定义了NUMA*/int node;           /*该管理区所属节点的节点号*//* * zone reclaim becomes active if more unmapped pages exist. */unsigned longmin_unmapped_pages;  /*当可回收的页面数大于该变量时，管理区将回收页面*/unsigned longmin_slab_pages;      /*同上，只不过该标准用于slab回收页面中*/struct per_cpu_pageset*pageset[NR_CPUS];   /*每个CPU使用的页面缓存*/#elsestruct per_cpu_pagesetpageset[NR_CPUS];#endif/* * free areas of different sizes */spinlock_tlock;       /*保护该管理区的自旋锁*/#ifdef CONFIG_MEMORY_HOTPLUG/* see spanned/present_pages for more description */seqlock_tspan_seqlock;#endifstruct free_areafree_area[MAX_ORDER];/*标识出管理区中的空闲页框块;    页面使用状态的信息，以每个bit标识对应的page是否可以分配*/#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_PADDING(_pad1_)/* Fields commonly accessed by the page reclaim scanner */spinlock_tlru_lock;/*（最近最少使用算法)的自旋锁*/struct zone_lru {struct list_head list;} lru[NR_LRU_LISTS];    struct zone_reclaim_stat reclaim_stat; /*页面回收的状态*//*管理区回收页框时使用的计数器，记录到上一次回收，一共扫过的页框数*/unsigned longpages_scanned;   /* since last reclaim */unsigned longflags;   /* zone flags, see below *//* Zone statistics */atomic_long_tvm_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;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;   /*等待一个page释放的等待队列哈希表。它会被wait_on_page(),unlock_page()函数使用. 用哈希表，而不用一个等待队列的原因，防止进程长期等待资源。*/unsigned longwait_table_hash_nr_entries;   /*散列表数组的大小*/unsigned longwait_table_bits;              /*散列表数组的大小对2取log的结果*//* * Discontig memory support fields. */struct pglist_data*zone_pgdat;              /*管理区所属节点 ;指向这个zone所在的pglist_data对象*/unsigned longzone_start_pfn; /*管理区的起始页框号  zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */    /*     * 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     * lock_memory_hotplug()/unlock_memory_hotplug().  Any reader who can't     * tolerant drift of present_pages should hold memory hotplug lock 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.     *//*这个地方参考free_area_init_core()*/unsigned longspanned_pages;/*管理区的大小,包括洞*/unsigned longpresent_pages;/*管理区的大小，不包括洞,  可能包含dma_reserve，以及mem_map结构提所占用的;*/unsigned long              managed_pages;   /* * rarely used fields: */const char*name; /*指向管理区的名称，为"DMA","NORMAL"或"HighMem"*/}

//++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

struct page {    /* First double word block */    unsigned long flags;        /*flags 字段存储了页面的状态信息,例如:表示页面刚被写了数据的脏位;该页面是否被锁定在内存中不充许置换到交换分区的标志。*//*为空表示该页属于交换高速缓存；mapping字段非空，且最低位是1，mapping字段中存放的是指向anon_vma描述符的指针,表示该页为匿名页；mapping字段非空，且最低位是0，mapping字段指向对应文件的address_space对象,表示该页为映射页；*/    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 {/*这个成员根据page的使用的目的有2种可能的含义。第一种情况：如果page是file mapping的一部分，它指明在文件中的偏移。如果page是交换缓存，则它指明在address_space所声明的对象:swapper_space（交换地址空间）中的偏移。第二种情况：如果这个page是一个特殊的进程将要释放的一个page块，则这是一个将要释放的page块的序列值，这个值在__free_page_ok()函数中设置。*/            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;   //_mapcount字段存放引用页框的页表项数目，确定其是否共享；                    struct { /* SLUB */                        unsigned inuse:16;                        unsigned objects:15;                        unsigned frozen:1;                    };                    int units;  /* SLOB */                };                atomic_t _count;        /* page的访问计数，当为0是，说明page是空闲的，当大于0的时候，说明page被一个或多个进程真正使用或者kernel用于在等待I/O*//*_count 字段和_mapcount字段都是引用计数,它们用来共同维护 page 页面的生命期。_mapcount 表示一个页面拥有多少页表项指向它,_count 被称为 page 的使用计数,所有的_mapcount 计数只相当于_count 计数中的一次计数。如果内核代码中某执行序列在访问某个页面时需要确保该页面存在,则在访问前给_count 计数加一,访问结束后_count 计数减一。当_count 计数减到负数时表示没有任何内核需要使用该页面,则表示该页面没被使用。内核代码不应该直接访问_count 计数,而应该使用 page_count 函数。该函数用一个struct page 的指针做为参数,当该页空闲时函数返回 0,否则返回一个正数表示参数指向的页面正被使用。*/         };        };    };    /* 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 *slab_page; /* slab fields */    };    /* 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_cache;  /* SL[AU]B: 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    struct task_struct *tsk_dirty;  /* task that sets this page dirty */#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#ifdef LAST_NID_NOT_IN_PAGE_FLAGS    int _last_nid;#endif#ifdef CONFIG_PAGE_OWNER    int order;    gfp_t gfp_mask;    struct stack_trace trace;    unsigned long trace_entries[8];#endif}

//++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

<span style="font-size:18px;"><span style="font-size:12px;"></span></span><pre name="code" class="objc">mapping字段