分析
<h2>概述</h2>
<p>1、malloc 的区域，可以被合并到某个区域内。也就是说：并不是每个 malloc 就会创建一个新的 vm_area</p>
<h2>进程虚拟内存</h2>
<p>每个进程都有 mm 结构，定义如下：</p>
<pre><code class="language-c">// file: include/linux/mm_types.h
struct mm_struct {
struct {
struct vm_area_struct *mmap; /* list of VMAs */ // 描述各个虚拟内存区域，按照从低到高的地址进行排序。双向不循环链表的方式方便遍历
struct rb_root mm_rb; // 同上，红黑树的方式方便查找虚拟地址属于哪个区域。这是根节点
u64 vmacache_seqnum; /* per-thread vmacache */
#ifdef CONFIG_MMU
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 */ // 映射区起始地址
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 */ // 用户空间界限 0x0000 7fff ffff 0000
unsigned long highest_vm_end; /* highest vma end address */
pgd_t * pgd;
/**
* @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 &amp;struct mm_struct if
* @mm_count also drops to 0).
*/
atomic_t mm_users;
/**
* @mm_count: The number of references to &amp;struct mm_struct
* (@mm_users count as 1).
*
* Use mmgrab()/mmdrop() to modify. When this drops to 0, the
* &amp;struct mm_struct is freed.
*/
atomic_t mm_count;
#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; /* High-watermark of RSS usage */
unsigned long hiwater_vm; /* High-water virtual memory usage */
unsigned long total_vm; /* Total pages mapped */
unsigned long locked_vm; /* Pages that have PG_mlocked set */
unsigned long pinned_vm; /* Refcount permanently increased */
unsigned long data_vm; /* VM_WRITE &amp; ~VM_SHARED &amp; ~VM_STACK */
unsigned long exec_vm; /* VM_EXEC &amp; ~VM_WRITE &amp; ~VM_STACK */
unsigned long stack_vm; /* VM_STACK */
unsigned long def_flags;
spinlock_t arg_lock; /* protect the below fields */
unsigned long start_code, end_code, start_data, end_data; // 各个段
unsigned long start_brk, brk, start_stack;
unsigned long arg_start, arg_end, env_start, env_end; // 据说是在栈的最高地址
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 */
mm_context_t context;
unsigned long flags; /* Must use atomic bitops to access */
struct core_state *core_state; /* coredumping support */
#ifdef CONFIG_MEMBARRIER
atomic_t membarrier_state;
#endif
#ifdef CONFIG_AIO
spinlock_t ioctx_lock;
struct kioctx_table __rcu *ioctx_table;
#endif
#ifdef CONFIG_MEMCG
/*
* &quot;owner&quot; 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-&gt;owner
* current-&gt;mm != mm
* new_owner-&gt;mm == mm
* new_owner-&gt;alloc_lock is held
*/
struct task_struct __rcu *owner;
#endif
struct user_namespace *user_ns;
/* store ref to file /proc/&lt;pid&gt;/exe symlink points to */
struct file __rcu *exe_file;
#ifdef CONFIG_MMU_NOTIFIER
struct mmu_notifier_mm *mmu_notifier_mm;
#endif
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) &amp;&amp; !USE_SPLIT_PMD_PTLOCKS
pgtable_t pmd_huge_pte; /* protected by page_table_lock */
#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;
/* 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;
#endif
/*
* 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.
*/
atomic_t tlb_flush_pending;
#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
/* See flush_tlb_batched_pending() */
bool tlb_flush_batched;
#endif
struct uprobes_state uprobes_state;
#ifdef CONFIG_HUGETLB_PAGE
atomic_long_t hugetlb_usage;
#endif
struct work_struct async_put_work;
#if IS_ENABLED(CONFIG_HMM)
/* HMM needs to track a few things per mm */
struct hmm *hmm;
#endif
} __randomize_layout;
/*
* 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[];
};
</code></pre>
<p>其中 <code>struct vm_area_struct *mmap</code> 描述的是各个虚拟内存区域的信息，可以通过 <code>pmap pid</code> 查看，就是遍历的这个链表。</p>
<pre><code class="language-c">// file: include/linux/mm_types.h
/*
* This struct defines a memory VMM memory area. There is one of these
* per VM-area/task. A VM area is any part of the process virtual memory
* space that has a special rule for the page-fault handlers (ie a shared
* library, the executable area etc).
*/
struct vm_area_struct {
/* The first cache line has the info for VMA tree walking. */
unsigned long vm_start; /* Our start address within vm_mm. */ // 最低地址
unsigned long vm_end; /* The first byte after our end address // 最高地址（不含）
within vm_mm. */
/* linked list of VM areas per task, sorted by address */
struct vm_area_struct *vm_next, *vm_prev; // 双向链表方式
struct rb_node vm_rb; // 红黑树方式
/*
* Largest free memory gap in bytes to the left of this VMA.
* Either between this VMA and vma-&gt;vm_prev, or between one of the
* VMAs below us in the VMA rbtree and its -&gt;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. */ // 回链。每个虚拟地址区域都有回链
pgprot_t vm_page_prot; /* Access permissions of this VMA. */ // 偏向于页这一级别的权限
unsigned long vm_flags; /* Flags, see mm.h. */ // 偏向于整个虚拟内存区域的权限
/*
* For areas with an address space and backing store,
* linkage into the address_space-&gt;i_mmap interval tree.
*/
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 &amp;
* page_table_lock */
struct anon_vma *anon_vma; /* Serialized by page_table_lock */ // 匿名映射，例如 malloc 较大内存时
/* Function pointers to deal with this struct. */
const struct vm_operations_struct *vm_ops; // ops
/* Information about our backing store: */
unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE
units */
struct file * vm_file; /* File we map to (can be NULL). */ // 文件映射
void * vm_private_data; /* was vm_pte (shared mem) */
atomic_long_t swap_readahead_info;
#ifndef CONFIG_MMU
struct vm_region *vm_region; /* NOMMU mapping region */
#endif
#ifdef CONFIG_NUMA
struct mempolicy *vm_policy; /* NUMA policy for the VMA */
#endif
struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
} __randomize_layout;</code></pre>
<h2>内核虚拟地址</h2>
<p>可通过 <code>cat /proc/iomem</code> 查看物理内存布局。</p>