linux内核源码分析之内存
Posted 为了维护世界和平_
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了linux内核源码分析之内存相关的知识，希望对你有一定的参考价值。
目录
一、内存管理子系统
可以分为：用户空间、内核空间以及硬件
1，用户空间：
使用malloc()申请，free()释放。malloc()/free()是glibc库的内存分配器ptmalloc提供的接口，ptmalloc使用系统调用brk或mmap向内核以页为单位申请内存，然后进行分成小内存块分配给应用程序。
2，内核空间：
虚拟内存管理负责从进程的虚拟地址空间分配虚拟页，sys_brk来扩大或收缩堆，sys_mmap用来在内存映射区域分配虚拟页，sys_munmap用来释放虚拟页。页分配器负责分配物理页，使用分配器是伙伴分配器。
内核空间扩展功能，从不连续页分配器提供分配内存的接口vmalloc和释放内存接口vfree。在内存碎片化的时候，申请连续物理页的成功率比较低，可以申请不连续的物理页，映射到连续的虚拟页，即虚拟地址连续而物理地址不连续。
内存控制组用来控制进程的内存资源。当内存碎片化的时候，找不到连续的物理页，内存碎片整理通过迁移方式得到连续的物理页。在内存不足的时候，页回收负责回收物理页。
3，硬件：
MMU包括一个页表缓存，保存最近使用过得页表映射，避免每次把虚拟地址转化为物理地址都需要查询内存中的页表。解决处理器执行速度和内存速度不匹配问题，中间加一个缓存。一级缓存分为数据缓存和指令缓存。二级缓存用于协调一级缓存和内存之间的工作效率。
二、用户虚拟地址空间划分
进程的用户虚拟地址空间起始地址是0，长度是TASK_SIZE,由每种处理器架构自己定义。
ARM64架构定义的宏TASK_SIZE
32位用户空间程序：TASK_SIZE的值是TASK_SIZE_32 ,即0x100000000, 4GB
32位用户空间程序：TASK_SIZE的值是TASK_SIZE_64
程序源码定义如下：
arch/arm64/include/asm/processor.h
#define TASK_SIZE_64 (UL(1) << vabits_actual)
#define TASK_SIZE_32 UL(0x100000000) 一个进程的虚拟地址空间主要由两个数据结构描述。一个是最高层的mm_struct，另一个是vm_area_struct。每个进程只有一个mm_struct结构
mm_struct结构描述一个进程整个虚拟地址空间
vm_area_struct描述虚拟地址空间的一个区间（成为虚拟区）。
三、mm_struct结构
struct mm_struct
struct
struct vm_area_struct *mmap; /* list of VMAs 虚拟内存区域链表 */
struct rb_root mm_rb;//虚拟内存区域红黑树
u64 vmacache_seqnum; /* per-thread vmacache */
#ifdef CONFIG_MMU//在内存映射区域找到一个没有映射的区域
unsigned long (*get_unmapped_area) (struct file *filp,
unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags);
#endif
unsigned long mmap_base; /* base of mmap area 内存映射区域的起始地址*/
unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */
#ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
/* Base adresses for compatible mmap() */
unsigned long mmap_compat_base;
unsigned long mmap_compat_legacy_base;
#endif
unsigned long task_size; /* size of task vm space 用户虚拟地址空间长度*/
unsigned long highest_vm_end; /* highest vma end address */
pgd_t * pgd;//指向全局目录，即第一级页表
#ifdef CONFIG_MEMBARRIER
/**
* @membarrier_state: Flags controlling membarrier behavior.
*
* This field is close to @pgd to hopefully fit in the same
* cache-line, which needs to be touched by switch_mm().
*/
atomic_t membarrier_state;
#endif
/**
* @mm_users: The number of users including userspace.
*
* Use mmget()/mmget_not_zero()/mmput() to modify. When this
* drops to 0 (i.e. when the task exits and there are no other
* temporary reference holders), we also release a reference on
* @mm_count (which may then free the &struct mm_struct if
* @mm_count also drops to 0).
*/
atomic_t mm_users;//共享一个用户虚拟地址空间的进程的数量，也就是线程组包含的进程的数据
/**
* @mm_count: The number of references to &struct mm_struct
* (@mm_users count as 1).
*
* Use mmgrab()/mmdrop() to modify. When this drops to 0, the
* &struct mm_struct is freed.
*/
atomic_t mm_count;//内存描述符的引用计数
#ifdef CONFIG_MMU
atomic_long_t pgtables_bytes; /* PTE page table pages */
#endif
int map_count; /* number of VMAs */
spinlock_t page_table_lock; /* Protects page tables and some
* counters
*/
struct rw_semaphore mmap_sem;
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
*/
unsigned long hiwater_rss; /* 进程所拥有的最大页框数High-watermark of RSS usage */
unsigned long hiwater_vm; /* 进程线性区中最大页数High-water virtual memory usage */
unsigned long total_vm; /* 进程地址空间的大小Total pages mapped */
unsigned long locked_vm; /* 锁住而不能换成的页的个数Pages that have PG_mlocked set */
atomic64_t pinned_vm; /* Refcount permanently increased */
unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */
unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */
unsigned long stack_vm; /* VM_STACK */
unsigned long def_flags;
spinlock_t arg_lock; /* protect the below fields */
//代码段的起始地址和结束地址，数据段的起始地址和结束地址
unsigned long start_code, end_code, start_data, end_data;
//堆的起始地址和结束地址，栈的起始地址
unsigned long start_brk, brk, start_stack;
//参数字符串起始地址和结束地址，环境变量的起始地址和结束地址
unsigned long arg_start, arg_end, env_start, env_end;
unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
/*
* 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;
/* Architecture-specific MM context */
//处理器架构特定的内存管理上下文
mm_context_t context;
unsigned long flags; /* Must use atomic bitops to access */
struct core_state *core_state; /* coredumping support */
#ifdef CONFIG_AIO
spinlock_t ioctx_lock;
struct kioctx_table __rcu *ioctx_table;
#endif
/* store ref to file /proc/<pid>/exe symlink points to */
struct file __rcu *exe_file;
...
/*
* The mm_cpumask needs to be at the end of mm_struct, because it
* is dynamically sized based on nr_cpu_ids.
*/
unsigned long cpu_bitmap[];
;四、vm_area_struct结构
此结构定义内存VMM内存区域。每个VM区域/任务都有一个。VM区域是进程虚拟内存空间的任何部分，它对页面错误处理程序（即共享库、可执行区域等）具有特殊规则
struct vm_area_struct
/* The first cache line has the info for VMA tree walking. */
//虚拟内存地址空间的首地址和末尾地址
unsigned long vm_start; /* Our start address within vm_mm. */
unsigned long vm_end; /* The first byte after our end address
within vm_mm. */
/* linked list of VM areas per task, sorted by address */
struct vm_area_struct *vm_next, *vm_prev;//链表操作
//如果采用链表组织化，会影响到它搜索速度问题，解决此问题采用红黑树，每个进程结构体mm_struct中都
//创建一个红黑树，将VMA作为一个节点加入到红黑树中，提高速度
struct rb_node vm_rb;
/*
* Largest free memory gap in bytes to the left of this VMA.
* Either between this VMA and vma->vm_prev, or between one of the
* VMAs below us in the VMA rbtree and its ->vm_prev. This helps
* get_unmapped_area find a free area of the right size.
*/
unsigned long rb_subtree_gap;
/* Second cache line starts here. */
struct mm_struct *vm_mm; /* The address space we belong to. */
//支持查询一个文件区间被映射到哪些虚拟内存区域，把一个文件映射到所有内存区域加入该文件地址空间结构
struct
struct rb_node rb;
unsigned long rb_subtree_last;
shared;
/*
* A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
* list, after a COW of one of the file pages. A MAP_SHARED vma
* can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack
* or brk vma (with NULL file) can only be in an anon_vma list.
*/
struct list_head anon_vma_chain; /* Serialized by mmap_sem &
* page_table_lock */
struct anon_vma *anon_vma; /* Serialized by page_table_lock */
/* Function pointers to deal with this struct. 成员如下*/
//void (*open)(struct vm_area_struct * area);
//void (*close)(struct vm_area_struct * area);
//int (*split)(struct vm_area_struct * area, unsigned long addr);
//int (*mremap)(struct vm_area_struct * area);
//vm_fault_t (*fault)(struct vm_fault *vmf);
//vm_fault_t (*huge_fault)(struct vm_fault *vmf,
// enum page_entry_size pe_size);
//内存操作
const struct vm_operations_struct *vm_ops;
/* Information about our backing store: */
unsigned long vm_pgoff; /* 文件偏移 Offset (within vm_file) in PAGE_SIZE
units */
struct file * vm_file; /* 文件，如果是私有的匿名映射，该成员是空指针File we map to (can be NULL). */
void * vm_private_data; /* 指向内存区的私有数据 was vm_pte (shared mem) */
/*
* Access permissions of this VMA.
* See vmf_insert_mixed_prot() for discussion.
*/
pgprot_t vm_page_prot;
unsigned long vm_flags; /* Flags, see mm.h. */
...
__randomize_layout;五、结构体之间的关系
六、文件映射
const struct vm_operations_struct *vm_ops;
/* Function pointers to deal with this struct. 成员如下*/
void (*open)(struct vm_area_struct * area);//创建虚拟内存区域时调用open
void (*close)(struct vm_area_struct * area);
int (*split)(struct vm_area_struct * area, unsigned long addr);
int (*mremap)(struct vm_area_struct * area);//移动内存区域
vm_fault_t (*fault)(struct vm_fault *vmf);//访问文件映射的虚拟页，如果没有映射到物理页，产生缺页异常，异常处理程序调用falut把文件的数据读到文件页缓存当中
//与fault类似，区别是huge_fault方法针对透明巨型页的文件映射
vm_fault_t (*huge_fault)(struct vm_fault *vmf, enum page_entry_size pe_size);
//读文件映射的虚拟页时，如果没有映射到物理页，生成缺页异常，异常处理程序除了读入正在访问的文件页，还会预读后续页，调用map_pages方法在文件的页缓存中分配物理页
void (*map_pages)(struct vm_fault *vmf,
pgoff_t start_pgoff, pgoff_t end_pgoff);
unsigned long (*pagesize)(struct vm_area_struct * area);
/* notification that a previously read-only page is about to become
* writable, if an error is returned it will cause a SIGBUS */
vm_fault_t (*page_mkwrite)(struct vm_fault *vmf);
//第一次写私有的文件映射时，生成页错误异常，异常处理程序执行写时复制，
//调用page_mkwrite方法以通知文件系统页即将变成可写，以便文件系统检查是否允许写，或者等待页进入合适的状态
/* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */
vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf);
/* called by access_process_vm when get_user_pages() fails, typically
* for use by special VMAs that can switch between memory and hardware
*/
int (*access)(struct vm_area_struct *vma, unsigned long addr,
void *buf, int len, int write);
参考链接
https://ke.qq.com/course/4032547/12394914843035683?flowToken=1042700
以上是关于linux内核源码分析之内存的主要内容，如果未能解决你的问题，请参考以下文章