一个测试程序的运行轨迹:
*****************************************************
virt:0xaa398000
virtaddr = 0xaa398000
page_size = 1000
virt_pfn = aa398
offset = 551cc0
//用户态 申请4k内存 并写入值
[ 47.195130] in pagemap_read
[ 47.206743] buf = beda8a48
[ 47.209892] count = 8
[ 47.212545] ppos = dc1d7f70
[ 47.215695] *ppos = 551cc0
[ 47.218731] task->comm = mytest
[ 47.222388]
[ 47.222388]
[ 47.222388] pagemap_pmd_range start...
[ 47.229901] addr = aa398000
[ 47.233027] end = aa400000
[ 47.236061] pte = ffefe660
[ 47.239089] *pte = 9ed9375f
[ 47.242215] addr = aa398000
[ 47.245341] page = eb34e8ac
//根据虚拟地址获取到物理 地址
[ 47.248467]
[ 47.248467]
[ 47.248467] map_new_virtual:
[ 47.255264] page = eb34e8ac
[ 47.258375] vaddr = bfed6000
[ 47.261621] kaddr = 0xbfed6000
//kmap的日志 关键点 page
//#define __pfn_to_page(pfn) (mem_map + ((pfn) - ARCH_PFN_OFFSET))
//#define __page_to_pfn(page) ((unsigned long)((page) - mem_map) + ARCH_PFN_OFFSET)
//互为逆运算
//分配内存与映射内存 互为逆运算
[ 47.265053] walk.data: bfed6000: aa bb cc dd 55 55 55 55 55 55 55 55 55 55 55 55 ....UUUUUUUUUUUU
[ 47.275062] walk.data: bfed6010: 55 55 55 55 55 55 55 55 55 55 55 55 55 55 55 55 UUUUUUUUUUUUUUUU
[ 47.285074] walk.data: bfed6020: 55 55 55 55 55 55 55 55 55 55 55 55 55 55 55 55 UUUUUUUUUUUUUUUU
[ 47.295085] walk.data: bfed6030: 55 55 55 55 55 55 55 55 55 55 55 55 55 55 55 55 UUUUUUUUUUUUUUUU
[ 47.305097] pagemap_pmd_range end!!! err = 0
[ 47.305097]
//回到用户态 输出虚拟地址对应的物理内存地址
page = 810000000009ed93
virt:0xaa398000 phys:9ed93000
cnt = 1, pad = 55.
用户态程序:
#define phys_addr_t uint64_t
#define PFN_MASK_SIZE 8
phys_addr_t rte_mem_virt2phy( const void *virtaddr )
{
int fd, retval;
uint64_t page, physaddr;
unsigned long virt_pfn;
int page_size;
off_t offset;
/* standard page size */
page_size = getpagesize();
fd = open("/proc/self/pagemap", O_RDONLY);
if( fd < 0 ){
;;;;
}
virt_pfn = (unsigned long)virtaddr / page_size;
printf( "virtaddr = %p\n", virtaddr );
printf( "page_size = %x\n", page_size );
printf( "virt_pfn = %lx\n", virt_pfn );
offset = sizeof(uint64_t) * virt_pfn;
printf( "offset = %lx\n", offset );
if (lseek(fd, offset, SEEK_SET) == (off_t) -1) {
return -1;
}
retval = read(fd, &page, PFN_MASK_SIZE);
close(fd);
//the pfn (page frame number) are bits 0-54 (see
//pagemap.txt in linux Documentation)
if ((page & 0x7fffffffffffffULL) == 0){
return -1;
}
printf( "page = %llx\n", page );
physaddr = ((page & 0x7fffffffffffffULL) * page_size) + ((unsigned long)virtaddr % page_size);
//————————————————
//版权声明：本文为CSDN博主「宋宝华」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
//原文链接：https://blog.csdn.net/21cnbao/article/details/108989210
return physaddr;
}
int main( int argc __unused, char **argv __unused )
{
printf( "hello mytest, pid = %d.\n", getpid() );
uint8_t *p;
int cnt;
cnt = 0x00;
uint8_t pad= 0x55;
while(1){
cnt++;
p = malloc(3 * 1024);
printf("virt:%p \n", p);
if( p==NULL ){
sleep(5);
continue;
}
memset(p, pad, 3 * 1024);
p[0] = 0xaa;
p[1] = 0xbb;
p[2] = 0xcc;
p[3] = 0xdd;
printf("virt:%p phys:%llx\n", p, rte_mem_virt2phy(p));
printf("cnt = %d, pad = %x.\n", cnt, pad);
pad = pad + 0x11;
free(p);
//sleep(1);
break;
//*(p + 2 * 4096) = 10;
//printf("virt:%p phys:%llx\n", p + 2 * 4096, rte_mem_virt2phy(p + 2 * 4096));
}
return 0;
}
内核态程序:
/*
* High memory handling common code and variables.
*
* (C) 1999 Andrea Arcangeli, SuSE GmbH, andrea@suse.de
* Gerhard Wichert, Siemens AG, Gerhard.Wichert@pdb.siemens.de
*
*
* Redesigned the x86 32-bit VM architecture to deal with
* 64-bit physical space. With current x86 CPUs this
* means up to 64 Gigabytes physical RAM.
*
* Rewrote high memory support to move the page cache into
* high memory. Implemented permanent (schedulable) kmaps
* based on Linus' idea.
*
* Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
*/
#include <linux/mm.h>
#include <linux/export.h>
#include <linux/swap.h>
#include <linux/bio.h>
#include <linux/pagemap.h>
#include <linux/mempool.h>
#include <linux/blkdev.h>
#include <linux/init.h>
#include <linux/hash.h>
#include <linux/highmem.h>
#include <linux/kgdb.h>
#include <asm/tlbflush.h>
#if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32)
DEFINE_PER_CPU(int, __kmap_atomic_idx);
#endif
/*
* Virtual_count is not a pure "count".
* 0 means that it is not mapped, and has not been mapped
* since a TLB flush - it is usable.
* 1 means that there are no users, but it has been mapped
* since the last TLB flush - so we can't use it.
* n means that there are (n-1) current users of it.
*/
#ifdef CONFIG_HIGHMEM
/*
* Architecture with aliasing data cache may define the following family of
* helper functions in its asm/highmem.h to control cache color of virtual
* addresses where physical memory pages are mapped by kmap.
*/
#ifndef get_pkmap_color
/*
* Determine color of virtual address where the page should be mapped.
*/
static inline unsigned int get_pkmap_color(struct page *page)
{
return 0;
}
#define get_pkmap_color get_pkmap_color
/*
* Get next index for mapping inside PKMAP region for page with given color.
*/
static inline unsigned int get_next_pkmap_nr(unsigned int color)
{
static unsigned int last_pkmap_nr;
last_pkmap_nr = (last_pkmap_nr + 1) & LAST_PKMAP_MASK;
return last_pkmap_nr;
}
/*
* Determine if page index inside PKMAP region (pkmap_nr) of given color
* has wrapped around PKMAP region end. When this happens an attempt to
* flush all unused PKMAP slots is made.
*/
static inline int no_more_pkmaps(unsigned int pkmap_nr, unsigned int color)
{
return pkmap_nr == 0;
}
/*
* Get the number of PKMAP entries of the given color. If no free slot is
* found after checking that many entries, kmap will sleep waiting for
* someone to call kunmap and free PKMAP slot.
*/
static inline int get_pkmap_entries_count(unsigned int color)
{
return LAST_PKMAP;
}
/*
* Get head of a wait queue for PKMAP entries of the given color.
* Wait queues for different mapping colors should be independent to avoid
* unnecessary wakeups caused by freeing of slots of other colors.
*/
static inline wait_queue_head_t *get_pkmap_wait_queue_head(unsigned int color)
{
static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait);
return &pkmap_map_wait;
}
#endif
unsigned long totalhigh_pages __read_mostly;
EXPORT_SYMBOL(totalhigh_pages);
EXPORT_PER_CPU_SYMBOL(__kmap_atomic_idx);
unsigned int nr_free_highpages (void)
{
struct zone *zone;
unsigned int pages = 0;
for_each_populated_zone(zone) {
if (is_highmem(zone))
pages += zone_page_state(zone, NR_FREE_PAGES);
}
return pages;
}
static int pkmap_count[LAST_PKMAP];
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(kmap_lock);
pte_t * pkmap_page_table;
/*
* Most architectures have no use for kmap_high_get(), so let's abstract
* the disabling of IRQ out of the locking in that case to save on a
* potential useless overhead.
*/
#ifdef ARCH_NEEDS_KMAP_HIGH_GET
#define lock_kmap() spin_lock_irq(&kmap_lock)
#define unlock_kmap() spin_unlock_irq(&kmap_lock)
#define lock_kmap_any(flags) spin_lock_irqsave(&kmap_lock, flags)
#define unlock_kmap_any(flags) spin_unlock_irqrestore(&kmap_lock, flags)
#else
#define lock_kmap() spin_lock(&kmap_lock)
#define unlock_kmap() spin_unlock(&kmap_lock)
#define lock_kmap_any(flags) \
do { spin_lock(&kmap_lock); (void)(flags); } while (0)
#define unlock_kmap_any(flags) \
do { spin_unlock(&kmap_lock); (void)(flags); } while (0)
#endif
struct page *kmap_to_page(void *vaddr)
{
unsigned long addr = (unsigned long)vaddr;
if (addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP)) {
int i = PKMAP_NR(addr);
return pte_page(pkmap_page_table[i]);
}
return virt_to_page(addr);
}
EXPORT_SYMBOL(kmap_to_page);
static void flush_all_zero_pkmaps(void)
{
int i;
int need_flush = 0;
flush_cache_kmaps();
for (i = 0; i < LAST_PKMAP; i++) {
struct page *page;
/*
* zero means we don't have anything to do,
* >1 means that it is still in use. Only
* a count of 1 means that it is free but
* needs to be unmapped
*/
if (pkmap_count[i] != 1)
continue;
pkmap_count[i] = 0;
/* sanity check */
BUG_ON(pte_none(pkmap_page_table[i]));
/*
* Don't need an atomic fetch-and-clear op here;
* no-one has the page mapped, and cannot get at
* its virtual address (and hence PTE) without first
* getting the kmap_lock (which is held here).
* So no dangers, even with speculative execution.
*/
page = pte_page(pkmap_page_table[i]);
pte_clear(&init_mm, PKMAP_ADDR(i), &pkmap_page_table[i]);
set_page_address(page, NULL);
need_flush = 1;
}
if (need_flush)
flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP));
}
/**
* kmap_flush_unused - flush all unused kmap mappings in order to remove stray mappings
*/
void kmap_flush_unused(void)
{
lock_kmap();
flush_all_zero_pkmaps();
unlock_kmap();
}
//进一步查看map_new_virtual函数，我们知道pkmap是在虚拟地址空间已经预留出来的一部分地址，
//我们现在需要申请一个地址用于对特定page的映射。
//这个函数的目的就是找到未用的空闲pkmap地址，然后创建对应物理page和该虚拟地址之间的pte页表项
int debug_en_highmem = 0x00;
//https://cloud.tencent.com/developer/article/1381079
//https://blog.csdn.net/rikeyone/article/details/85223458
static inline unsigned long map_new_virtual(struct page *page)
{
unsigned long vaddr;
int count;
unsigned int last_pkmap_nr;
unsigned int color = get_pkmap_color(page);
struct task_struct *task;
task = current;
if( !strcmp(task->comm, "mytest") ){
debug_en_highmem = 0x01;
}else{
debug_en_highmem = 0x00;
}
start:
count = get_pkmap_entries_count(color);
/* Find an empty entry */
for (;;) {
last_pkmap_nr = get_next_pkmap_nr(color);
if (no_more_pkmaps(last_pkmap_nr, color)) {
flush_all_zero_pkmaps();
count = get_pkmap_entries_count(color);
}
if (!pkmap_count[last_pkmap_nr])
break; /* Found a usable entry */
if (--count)
continue;
/*
* Sleep for somebody else to unmap their entries
*/
{
DECLARE_WAITQUEUE(wait, current);
wait_queue_head_t *pkmap_map_wait =
get_pkmap_wait_queue_head(color);
__set_current_state(TASK_UNINTERRUPTIBLE);
add_wait_queue(pkmap_map_wait, &wait);
unlock_kmap();
schedule();
remove_wait_queue(pkmap_map_wait, &wait);
lock_kmap();
/* Somebody else might have mapped it while we slept */
if (page_address(page))
return (unsigned long)page_address(page);
/* Re-start */
goto start;
}
}
vaddr = PKMAP_ADDR(last_pkmap_nr);
//printk("task.name = %s\n", task->comm);
if( debug_en_highmem ){
printk("\n\n map_new_virtual: \n");
printk("page = %lx\n", page);
printk("vaddr = %lx\n", vaddr);
//printk("last_pkmap_nr = %lx\n", last_pkmap_nr);
//printk("&(pkmap_page_table[last_pkmap_nr]) = %lx\n", &(pkmap_page_table[last_pkmap_nr]) );
//printk("mk_pte(page, kmap_prot) = %lx\n", mk_pte(page, kmap_prot));
//dump_stack();
}else{
//printk("\n\n map_new_virtualxxxxx: \n");
//printk("pagex = %lx\n", page);
//printk("vaddrxcv = %lx\n", vaddr);
}
set_pte_at(&init_mm, vaddr, &(pkmap_page_table[last_pkmap_nr]), mk_pte(page, kmap_prot));
//#define __pfn_to_page(pfn) (mem_map + ((pfn) - ARCH_PFN_OFFSET))
//#define __page_to_pfn(page) ((unsigned long)((page) - mem_map) + ARCH_PFN_OFFSET)
//互为逆运算
pkmap_count[last_pkmap_nr] = 1;
set_page_address(page, (void *)vaddr);
return vaddr;
}
//循环查找pkmap区域,判断是否有空闲未用的虚拟地址页,
//如果找到未用的虚拟地址页，那么就中断循环，进行PTE页表的创建
//如果未找到空闲虚拟地址页，说明所有的pkmap区域都已经被内核其他路径申请完了，则要进行释放zero空的pkmap映射。
//释放后依然未找到空闲映射区，则申请映射的进程需要进行等待。
//等待一段时候，系统被唤醒后，重新执行这一系列申请动作。
//找到空闲映射区后，进行最后的PTE页表创建。
//set_page_address设置对应page的描述符，把申请的映射虚拟地址设置进去。
/**
* kmap_high - map a highmem page into memory
* @page: &struct page to map
*
* Returns the page's virtual memory address.
*
* We cannot call this from interrupts, as it may block.
*/
void *kmap_high(struct page *page)
{
unsigned long vaddr;
/*
* For highmem pages, we can't trust "virtual" until
* after we have the lock.
*/
lock_kmap();
vaddr = (unsigned long)page_address(page);
if (!vaddr)
vaddr = map_new_virtual(page);
pkmap_count[PKMAP_NR(vaddr)]++;
BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 2);
unlock_kmap();
return (void*) vaddr;
}
EXPORT_SYMBOL(kmap_high);
#ifdef ARCH_NEEDS_KMAP_HIGH_GET
/**
* kmap_high_get - pin a highmem page into memory
* @page: &struct page to pin
*
* Returns the page's current virtual memory address, or NULL if no mapping
* exists. If and only if a non null address is returned then a
* matching call to kunmap_high() is necessary.
*
* This can be called from any context.
*/
void *kmap_high_get(struct page *page)
{
unsigned long vaddr, flags;
lock_kmap_any(flags);
vaddr = (unsigned long)page_address(page);
if (vaddr) {
BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 1);
pkmap_count[PKMAP_NR(vaddr)]++;
}
unlock_kmap_any(flags);
return (void*) vaddr;
}
#endif
/**
* kunmap_high - unmap a highmem page into memory
* @page: &struct page to unmap
*
* If ARCH_NEEDS_KMAP_HIGH_GET is not defined then this may be called
* only from user context.
*/
void kunmap_high(struct page *page)
{
unsigned long vaddr;
unsigned long nr;
unsigned long flags;
int need_wakeup;
unsigned int color = get_pkmap_color(page);
wait_queue_head_t *pkmap_map_wait;
lock_kmap_any(flags);
vaddr = (unsigned long)page_address(page);
BUG_ON(!vaddr);
nr = PKMAP_NR(vaddr);
/*
* A count must never go down to zero
* without a TLB flush!
*/
need_wakeup = 0;
switch (--pkmap_count[nr]) {
case 0:
BUG();
case 1:
/*
* Avoid an unnecessary wake_up() function call.
* The common case is pkmap_count[] == 1, but
* no waiters.
* The tasks queued in the wait-queue are guarded
* by both the lock in the wait-queue-head and by
* the kmap_lock. As the kmap_lock is held here,
* no need for the wait-queue-head's lock. Simply
* test if the queue is empty.
*/
pkmap_map_wait = get_pkmap_wait_queue_head(color);
need_wakeup = waitqueue_active(pkmap_map_wait);
}
unlock_kmap_any(flags);
/* do wake-up, if needed, race-free outside of the spin lock */
if (need_wakeup)
wake_up(pkmap_map_wait);
}
EXPORT_SYMBOL(kunmap_high);
#endif
#if defined(HASHED_PAGE_VIRTUAL)
#define PA_HASH_ORDER 7
/*
* Describes one page->virtual association
*/
struct page_address_map {
struct page *page;
void *virtual;
struct list_head list;
};
static struct page_address_map page_address_maps[LAST_PKMAP];
/*
* Hash table bucket
*/
static struct page_address_slot {
struct list_head lh; /* List of page_address_maps */
spinlock_t lock; /* Protect this bucket's list */
} ____cacheline_aligned_in_smp page_address_htable[1<<PA_HASH_ORDER];
static struct page_address_slot *page_slot(const struct page *page)
{
return &page_address_htable[hash_ptr(page, PA_HASH_ORDER)];
}
//我们知道,在小于896M(低端内存)的物理地址空间和3G--3G+896M的线性地址空间是一一对应映射的
//所以我们只要知道page所对应的物理地址,就可以知道这个page对应的线性地址空间(pa+PAGE_OFFSET)
//那如何找一个page对应的物理地址呢?我们知道物理内存按照大小为(1<<PAGE_SHIFT)分为很多个页
//每个这样的页就对应一个struct page *page结构,这些页描述结构存放在一个称之为mem_map的数组里面
//而且是严格按照物理内存的顺序来存放的,也就是物理上的第一个页描述结构,作为mem_map数组的第一个元素,依次类推
//所以,每个页描述结构(page)在数组mem_map里的位置在乘以页的大小,就可以得到该页的物理地址了
//上面的代码就是依照这个原理来的:
//page_to_pfn(page)函数就是得到每个page在mem_map里的位置,
//左移PAGE_SHIFT就是乘以页的大小,这就得到了该页的物理地址
//这个物理地址加上个PAGE_OFFSET(3G)就得到了该page的线性地址了
//在低端内存中(小于896M),通过页(struct page *page)取得虚拟地址就是这样转换的
/**
* page_address - get the mapped virtual address of a page
* @page: &struct page to get the virtual address of
*
* Returns the page's virtual address.
*/
void *page_address(const struct page *page)
{
unsigned long flags;
void *ret;
struct page_address_slot *pas;
if (!PageHighMem(page))
return lowmem_page_address(page);
//判断是否属于高端内存,如果不是,那么就是属于低
//端内存的,通过上面的方法可以直接找到
pas = page_slot(page);
//见下分析，pas指向page对应的page_address_map结构所在的链表表头
ret = NULL;
spin_lock_irqsave(&pas->lock, flags);
if (!list_empty(&pas->lh)) {
struct page_address_map *pam;
list_for_each_entry(pam, &pas->lh, list) {
if (pam->page == page) {
//遍历hash链表 找到page匹配项 返回其虚地址(线性地址)
ret = pam->virtual;
goto done;
}
}
}
done:
spin_unlock_irqrestore(&pas->lock, flags);
return ret;
}
EXPORT_SYMBOL(page_address);
//在高端内存中,由于不能通过像在低端内存中一样，直接通过物理地址加PAGE_OFFSET得到线性地址，
//所以引入了一个结构叫做 page_address_map结构，该结构保存有每个page（仅高端内存中的）和对应的虚拟地址，
//所有的高端内存中的这种映射都通过链表链接起来，这个结构是在高端内存映射的时候建立，并加入到链表中的。
//又因为如果内存远远大于896M，那么高端内存中的page就比较多(（内存-896M）/4K个页，假设页大小为4K），
//如果只用一个链表来表示，那么查找起来就比较耗时了，所以这里引入了HASH算法，
//采用多个链表，每个page通过一定的hash算法，对应到一个链表上，总够有128个链表：
//PA_HASH_ORDER=7, 所以一共有1<<7（128）个链表，每一个page通过HASH算法后对应一个 page_address_htable链表,
//然后再遍历这个链表来找到对应的PAGE和虚拟地址。
//page通过HASH算法后对应一个 page_address_htable链表的代码如下：
//https://www.cnblogs.com/alantu2018/default.html?page=21
//https://www.cnblogs.com/alantu2018/category/1163287.html?page=1
/**
* set_page_address - set a page's virtual address
* @page: &struct page to set
* @virtual: virtual address to use
*/
//将一页加入hash链表
void set_page_address(struct page *page, void *virtual)
{
unsigned long flags;
struct page_address_slot *pas;
struct page_address_map *pam;
BUG_ON(!PageHighMem(page));
pas = page_slot(page);
if (virtual) { /* Add */
pam = &page_address_maps[PKMAP_NR((unsigned long)virtual)];
pam->page = page;
pam->virtual = virtual;
spin_lock_irqsave(&pas->lock, flags);
list_add_tail(&pam->list, &pas->lh);
spin_unlock_irqrestore(&pas->lock, flags);
} else { /* Remove */
spin_lock_irqsave(&pas->lock, flags);
list_for_each_entry(pam, &pas->lh, list) {
if (pam->page == page) {
list_del(&pam->list);
spin_unlock_irqrestore(&pas->lock, flags);
goto done;
}
}
spin_unlock_irqrestore(&pas->lock, flags);
}
done:
return;
}
void __init page_address_init(void)
{
int i;
for (i = 0; i < ARRAY_SIZE(page_address_htable); i++) {
INIT_LIST_HEAD(&page_address_htable[i].lh);
spin_lock_init(&page_address_htable[i].lock);
}
}
#endif /* defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) */
mm/pagewalk.c
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/sched.h>
#include <linux/hugetlb.h>
int debug_en_pagewalk = 0x00;
static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
pte_t *pte;
int err = 0;
pte = pte_offset_map(pmd, addr);
for (;;) {
err = walk->pte_entry(pte, addr, addr + PAGE_SIZE, walk);
if (err)
break;
addr += PAGE_SIZE;
if (addr == end)
break;
pte++;
}
pte_unmap(pte);
return err;
}
static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
pmd_t *pmd;
unsigned long next;
int err = 0;
pmd = pmd_offset(pud, addr);
if( debug_en_pagewalk ){
//printk("pmd = %p\n", pmd);
}
do {
again:
next = pmd_addr_end(addr, end);
if( debug_en_pagewalk ){
//printk("next = %lx\n", next);
//printk("end = %lx\n", end);
}
if (pmd_none(*pmd) || !walk->vma) {
if (walk->pte_hole){
err = walk->pte_hole(addr, next, walk);
//pagemap_pte_hole
}
if (err)
break;
continue;
}
/*
* This implies that each ->pmd_entry() handler
* needs to know about pmd_trans_huge() pmds
*/
if (walk->pmd_entry){
err = walk->pmd_entry(pmd, addr, next, walk);
//pagemap_pmd_range
}
if( debug_en_pagewalk ){
//printk("err = %lx\n", err);
}
if (err)
break;
/*
* Check this here so we only break down trans_huge
* pages when we _need_ to
*/
if( debug_en_pagewalk ){
//printk("walk->pte_entry = %pF\n", walk->pte_entry);
}
if (!walk->pte_entry)
continue;
split_huge_pmd(walk->vma, pmd, addr);
if (pmd_trans_unstable(pmd))
goto again;
err = walk_pte_range(pmd, addr, next, walk);
if (err)
break;
} while (pmd++, addr = next, addr != end);
return err;
}
static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
pud_t *pud;
unsigned long next;
int err = 0;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud)) {
if (walk->pte_hole)
err = walk->pte_hole(addr, next, walk);
if (err)
break;
continue;
}
if (walk->pmd_entry || walk->pte_entry)
err = walk_pmd_range(pud, addr, next, walk);
if (err)
break;
} while (pud++, addr = next, addr != end);
return err;
}
static int walk_pgd_range(unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
pgd_t *pgd;
unsigned long next;
int err = 0;
pgd = pgd_offset(walk->mm, addr);
if( debug_en_pagewalk ){
//printk("1walk->mm = %p\n", walk->mm);
//printk("addr = %lx\n", addr);
//printk("end = %lx\n", end);
//printk("pgd = %p\n", pgd);
}
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd)) {
if (walk->pte_hole)
err = walk->pte_hole(addr, next, walk);
if (err)
break;
continue;
}
if (walk->pmd_entry || walk->pte_entry)
err = walk_pud_range(pgd, addr, next, walk);
if (err)
break;
} while (pgd++, addr = next, addr != end);
return err;
}
#ifdef CONFIG_HUGETLB_PAGE
static unsigned long hugetlb_entry_end(struct hstate *h, unsigned long addr,
unsigned long end)
{
unsigned long boundary = (addr & huge_page_mask(h)) + huge_page_size(h);
return boundary < end ? boundary : end;
}
static int walk_hugetlb_range(unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
struct vm_area_struct *vma = walk->vma;
struct hstate *h = hstate_vma(vma);
unsigned long next;
unsigned long hmask = huge_page_mask(h);
pte_t *pte;
int err = 0;
do {
next = hugetlb_entry_end(h, addr, end);
pte = huge_pte_offset(walk->mm, addr & hmask);
if (pte)
err = walk->hugetlb_entry(pte, hmask, addr, next, walk);
else if (walk->pte_hole)
err = walk->pte_hole(addr, next, walk);
if (err)
break;
} while (addr = next, addr != end);
return err;
}
#else /* CONFIG_HUGETLB_PAGE */
static int walk_hugetlb_range(unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
return 0;
}
#endif /* CONFIG_HUGETLB_PAGE */
/*
* Decide whether we really walk over the current vma on [@start, @end)
* or skip it via the returned value. Return 0 if we do walk over the
* current vma, and return 1 if we skip the vma. Negative values means
* error, where we abort the current walk.
*/
static int walk_page_test(unsigned long start, unsigned long end,
struct mm_walk *walk)
{
struct vm_area_struct *vma = walk->vma;
if (walk->test_walk)
return walk->test_walk(start, end, walk);
/*
* vma(VM_PFNMAP) doesn't have any valid struct pages behind VM_PFNMAP
* range, so we don't walk over it as we do for normal vmas. However,
* Some callers are interested in handling hole range and they don't
* want to just ignore any single address range. Such users certainly
* define their ->pte_hole() callbacks, so let's delegate them to handle
* vma(VM_PFNMAP).
*/
if (vma->vm_flags & VM_PFNMAP) {
int err = 1;
if (walk->pte_hole)
err = walk->pte_hole(start, end, walk);
return err ? err : 1;
}
return 0;
}
static int __walk_page_range(unsigned long start, unsigned long end,
struct mm_walk *walk)
{
int err = 0;
struct vm_area_struct *vma = walk->vma;
if (vma && is_vm_hugetlb_page(vma)) {
if (walk->hugetlb_entry)
err = walk_hugetlb_range(start, end, walk);
} else
err = walk_pgd_range(start, end, walk);
return err;
}
/**
* walk_page_range - walk page table with caller specific callbacks
*
* Recursively walk the page table tree of the process represented by @walk->mm
* within the virtual address range [@start, @end). During walking, we can do
* some caller-specific works for each entry, by setting up pmd_entry(),
* pte_entry(), and/or hugetlb_entry(). If you don't set up for some of these
* callbacks, the associated entries/pages are just ignored.
* The return values of these callbacks are commonly defined like below:
* - 0 : succeeded to handle the current entry, and if you don't reach the
* end address yet, continue to walk.
* - >0 : succeeded to handle the current entry, and return to the caller
* with caller specific value.
* - <0 : failed to handle the current entry, and return to the caller
* with error code.
*
* Before starting to walk page table, some callers want to check whether
* they really want to walk over the current vma, typically by checking
* its vm_flags. walk_page_test() and @walk->test_walk() are used for this
* purpose.
*
* struct mm_walk keeps current values of some common data like vma and pmd,
* which are useful for the access from callbacks. If you want to pass some
* caller-specific data to callbacks, @walk->private should be helpful.
*
* Locking:
* Callers of walk_page_range() and walk_page_vma() should hold
* @walk->mm->mmap_sem, because these function traverse vma list and/or
* access to vma's data.
*/
int walk_page_range(unsigned long start, unsigned long end,
struct mm_walk *walk)
{
int err = 0;
unsigned long next;
struct vm_area_struct *vma;
struct task_struct *task;
int debug_en;
rcu_read_lock();
task = rcu_dereference(walk->mm->owner);
rcu_read_unlock();
//printk("task->comm = %s\n", task->comm);
if( !strcmp(task->comm, "mytest") ){
debug_en_pagewalk = 0x01;
}else{
debug_en_pagewalk = 0x00;
}
if (start >= end)
return -EINVAL;
if (!walk->mm)
return -EINVAL;
VM_BUG_ON_MM(!rwsem_is_locked(&walk->mm->mmap_sem), walk->mm);
vma = find_vma(walk->mm, start);
if( debug_en_pagewalk ){
//printk("vma = %p\n", vma);
//printk("start = %lx\n", start);
//printk("vma->vm_start = %lx\n", vma->vm_start);
//printk("vma->vm_end = %lx\n", vma->vm_end);
//printk("end = %lx\n", end);
}
do {
if (!vma) { /* after the last vma */
walk->vma = NULL;
next = end;
} else if (start < vma->vm_start) { /* outside vma */
walk->vma = NULL;
next = min(end, vma->vm_start);
} else { /* inside vma */
walk->vma = vma;
next = min(end, vma->vm_end);
vma = vma->vm_next;
err = walk_page_test(start, next, walk);
if (err > 0) {
/*
* positive return values are purely for
* controlling the pagewalk, so should never
* be passed to the callers.
*/
err = 0;
continue;
}
if (err < 0)
break;
}
if (walk->vma || walk->pte_hole){
if( debug_en_pagewalk ){
//printk("startx = %lx\n", start);
//printk("nextc = %lx\n", next);
}
err = __walk_page_range(start, next, walk);
if( debug_en_pagewalk ){
break;
}
}
if (err)
break;
} while (start = next, start < end);
return err;
}
int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk)
{
int err;
if (!walk->mm)
return -EINVAL;
VM_BUG_ON(!rwsem_is_locked(&walk->mm->mmap_sem));
VM_BUG_ON(!vma);
walk->vma = vma;
err = walk_page_test(vma->vm_start, vma->vm_end, walk);
if (err > 0)
return 0;
if (err < 0)
return err;
return __walk_page_range(vma->vm_start, vma->vm_end, walk);
}
fs/proc/task_mmu.c
#include <linux/mm.h>
#include <linux/vmacache.h>
#include <linux/hugetlb.h>
#include <linux/huge_mm.h>
#include <linux/mount.h>
#include <linux/seq_file.h>
#include <linux/highmem.h>
#include <linux/ptrace.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/mempolicy.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/mmu_notifier.h>
#include <linux/page_idle.h>
#include <linux/shmem_fs.h>
#include <asm/elf.h>
#include <asm/uaccess.h>
#include <asm/tlbflush.h>
#include "internal.h"
void task_mem(struct seq_file *m, struct mm_struct *mm)
{
unsigned long text, lib, swap, ptes, pmds, anon, file, shmem;
unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
anon = get_mm_counter(mm, MM_ANONPAGES);
file = get_mm_counter(mm, MM_FILEPAGES);
shmem = get_mm_counter(mm, MM_SHMEMPAGES);
/*
* Note: to minimize their overhead, mm maintains hiwater_vm and
* hiwater_rss only when about to *lower* total_vm or rss. Any
* collector of these hiwater stats must therefore get total_vm
* and rss too, which will usually be the higher. Barriers? not
* worth the effort, such snapshots can always be inconsistent.
*/
hiwater_vm = total_vm = mm->total_vm;
if (hiwater_vm < mm->hiwater_vm)
hiwater_vm = mm->hiwater_vm;
hiwater_rss = total_rss = anon + file + shmem;
if (hiwater_rss < mm->hiwater_rss)
hiwater_rss = mm->hiwater_rss;
text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
swap = get_mm_counter(mm, MM_SWAPENTS);
ptes = PTRS_PER_PTE * sizeof(pte_t) * atomic_long_read(&mm->nr_ptes);
pmds = PTRS_PER_PMD * sizeof(pmd_t) * mm_nr_pmds(mm);
seq_printf(m,
"VmPeak:\t%8lu kB\n"
"VmSize:\t%8lu kB\n"
"VmLck:\t%8lu kB\n"
"VmPin:\t%8lu kB\n"
"VmHWM:\t%8lu kB\n"
"VmRSS:\t%8lu kB\n"
"RssAnon:\t%8lu kB\n"
"RssFile:\t%8lu kB\n"
"RssShmem:\t%8lu kB\n"
"VmData:\t%8lu kB\n"
"VmStk:\t%8lu kB\n"
"VmExe:\t%8lu kB\n"
"VmLib:\t%8lu kB\n"
"VmPTE:\t%8lu kB\n"
"VmPMD:\t%8lu kB\n"
"VmSwap:\t%8lu kB\n",
hiwater_vm << (PAGE_SHIFT-10),
total_vm << (PAGE_SHIFT-10),
mm->locked_vm << (PAGE_SHIFT-10),
mm->pinned_vm << (PAGE_SHIFT-10),
hiwater_rss << (PAGE_SHIFT-10),
total_rss << (PAGE_SHIFT-10),
anon << (PAGE_SHIFT-10),
file << (PAGE_SHIFT-10),
shmem << (PAGE_SHIFT-10),
mm->data_vm << (PAGE_SHIFT-10),
mm->stack_vm << (PAGE_SHIFT-10), text, lib,
ptes >> 10,
pmds >> 10,
swap << (PAGE_SHIFT-10));
hugetlb_report_usage(m, mm);
}
unsigned long task_vsize(struct mm_struct *mm)
{
return PAGE_SIZE * mm->total_vm;
}
unsigned long task_statm(struct mm_struct *mm,
unsigned long *shared, unsigned long *text,
unsigned long *data, unsigned long *resident)
{
*shared = get_mm_counter(mm, MM_FILEPAGES) +
get_mm_counter(mm, MM_SHMEMPAGES);
*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
>> PAGE_SHIFT;
*data = mm->data_vm + mm->stack_vm;
*resident = *shared + get_mm_counter(mm, MM_ANONPAGES);
return mm->total_vm;
}
#ifdef CONFIG_NUMA
/*
* Save get_task_policy() for show_numa_map().
*/
static void hold_task_mempolicy(struct proc_maps_private *priv)
{
struct task_struct *task = priv->task;
task_lock(task);
priv->task_mempolicy = get_task_policy(task);
mpol_get(priv->task_mempolicy);
task_unlock(task);
}
static void release_task_mempolicy(struct proc_maps_private *priv)
{
mpol_put(priv->task_mempolicy);
}
#else
static void hold_task_mempolicy(struct proc_maps_private *priv)
{
}
static void release_task_mempolicy(struct proc_maps_private *priv)
{
}
#endif
static void seq_print_vma_name(struct seq_file *m, struct vm_area_struct *vma)
{
const char __user *name = vma_get_anon_name(vma);
struct mm_struct *mm = vma->vm_mm;
unsigned long page_start_vaddr;
unsigned long page_offset;
unsigned long num_pages;
unsigned long max_len = NAME_MAX;
int i;
page_start_vaddr = (unsigned long)name & PAGE_MASK;
page_offset = (unsigned long)name - page_start_vaddr;
num_pages = DIV_ROUND_UP(page_offset + max_len, PAGE_SIZE);
seq_puts(m, "[anon:");
for (i = 0; i < num_pages; i++) {
int len;
int write_len;
const char *kaddr;
long pages_pinned;
struct page *page;
pages_pinned = get_user_pages_remote(current, mm,
page_start_vaddr, 1, 0, &page, NULL);
if (pages_pinned < 1) {
seq_puts(m, "<fault>]");
return;
}
kaddr = (const char *)kmap(page);
len = min(max_len, PAGE_SIZE - page_offset);
write_len = strnlen(kaddr + page_offset, len);
seq_write(m, kaddr + page_offset, write_len);
kunmap(page);
put_page(page);
/* if strnlen hit a null terminator then we're done */
if (write_len != len)
break;
max_len -= len;
page_offset = 0;
page_start_vaddr += PAGE_SIZE;
}
seq_putc(m, ']');
}
static void vma_stop(struct proc_maps_private *priv)
{
struct mm_struct *mm = priv->mm;
release_task_mempolicy(priv);
up_read(&mm->mmap_sem);
mmput(mm);
}
static struct vm_area_struct *
m_next_vma(struct proc_maps_private *priv, struct vm_area_struct *vma)
{
if (vma == priv->tail_vma)
return NULL;
return vma->vm_next ?: priv->tail_vma;
}
static void m_cache_vma(struct seq_file *m, struct vm_area_struct *vma)
{
if (m->count < m->size) /* vma is copied successfully */
m->version = m_next_vma(m->private, vma) ? vma->vm_end : -1UL;
}
static void *m_start(struct seq_file *m, loff_t *ppos)
{
struct proc_maps_private *priv = m->private;
unsigned long last_addr = m->version;
struct mm_struct *mm;
struct vm_area_struct *vma;
unsigned int pos = *ppos;
/* See m_cache_vma(). Zero at the start or after lseek. */
if (last_addr == -1UL)
return NULL;
priv->task = get_proc_task(priv->inode);
if (!priv->task)
return ERR_PTR(-ESRCH);
mm = priv->mm;
if (!mm || !atomic_inc_not_zero(&mm->mm_users))
return NULL;
down_read(&mm->mmap_sem);
hold_task_mempolicy(priv);
priv->tail_vma = get_gate_vma(mm);
if (last_addr) {
vma = find_vma(mm, last_addr - 1);
if (vma && vma->vm_start <= last_addr)
vma = m_next_vma(priv, vma);
if (vma)
return vma;
}
m->version = 0;
if (pos < mm->map_count) {
for (vma = mm->mmap; pos; pos--) {
m->version = vma->vm_start;
vma = vma->vm_next;
}
return vma;
}
/* we do not bother to update m->version in this case */
if (pos == mm->map_count && priv->tail_vma)
return priv->tail_vma;
vma_stop(priv);
return NULL;
}
static void *m_next(struct seq_file *m, void *v, loff_t *pos)
{
struct proc_maps_private *priv = m->private;
struct vm_area_struct *next;
(*pos)++;
next = m_next_vma(priv, v);
if (!next)
vma_stop(priv);
return next;
}
static void m_stop(struct seq_file *m, void *v)
{
struct proc_maps_private *priv = m->private;
if (!IS_ERR_OR_NULL(v))
vma_stop(priv);
if (priv->task) {
put_task_struct(priv->task);
priv->task = NULL;
}
}
static int proc_maps_open(struct inode *inode, struct file *file,
const struct seq_operations *ops, int psize)
{
struct proc_maps_private *priv = __seq_open_private(file, ops, psize);
if (!priv)
return -ENOMEM;
priv->inode = inode;
priv->mm = proc_mem_open(inode, PTRACE_MODE_READ);
if (IS_ERR(priv->mm)) {
int err = PTR_ERR(priv->mm);
seq_release_private(inode, file);
return err;
}
return 0;
}
static int proc_map_release(struct inode *inode, struct file *file)
{
struct seq_file *seq = file->private_data;
struct proc_maps_private *priv = seq->private;
if (priv->mm)
mmdrop(priv->mm);
return seq_release_private(inode, file);
}
static int do_maps_open(struct inode *inode, struct file *file,
const struct seq_operations *ops)
{
return proc_maps_open(inode, file, ops,
sizeof(struct proc_maps_private));
}
/*
* Indicate if the VMA is a stack for the given task; for
* /proc/PID/maps that is the stack of the main task.
*/
static int is_stack(struct proc_maps_private *priv,
struct vm_area_struct *vma)
{
/*
* We make no effort to guess what a given thread considers to be
* its "stack". It's not even well-defined for programs written
* languages like Go.
*/
return vma->vm_start <= vma->vm_mm->start_stack &&
vma->vm_end >= vma->vm_mm->start_stack;
}
static void
show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
{
struct mm_struct *mm = vma->vm_mm;
struct file *file = vma->vm_file;
struct proc_maps_private *priv = m->private;
vm_flags_t flags = vma->vm_flags;
unsigned long ino = 0;
unsigned long long pgoff = 0;
unsigned long start, end;
dev_t dev = 0;
const char *name = NULL;
if (file) {
struct inode *inode = file_inode(vma->vm_file);
dev = inode->i_sb->s_dev;
ino = inode->i_ino;
pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
}
/* We don't show the stack guard page in /proc/maps */
start = vma->vm_start;
end = vma->vm_end;
seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
start,
end,
flags & VM_READ ? 'r' : '-',
flags & VM_WRITE ? 'w' : '-',
flags & VM_EXEC ? 'x' : '-',
flags & VM_MAYSHARE ? 's' : 'p',
pgoff,
MAJOR(dev), MINOR(dev), ino);
/*
* Print the dentry name for named mappings, and a
* special [heap] marker for the heap:
*/
if (file) {
seq_pad(m, ' ');
seq_file_path(m, file, "\n");
goto done;
}
if (vma->vm_ops && vma->vm_ops->name) {
name = vma->vm_ops->name(vma);
if (name)
goto done;
}
name = arch_vma_name(vma);
if (!name) {
if (!mm) {
name = "[vdso]";
goto done;
}
if (vma->vm_start <= mm->brk &&
vma->vm_end >= mm->start_brk) {
name = "[heap]";
goto done;
}
if (is_stack(priv, vma)) {
name = "[stack]";
goto done;
}
if (vma_get_anon_name(vma)) {
seq_pad(m, ' ');
seq_print_vma_name(m, vma);
}
}
done:
if (name) {
seq_pad(m, ' ');
seq_puts(m, name);
}
seq_putc(m, '\n');
}
static int show_map(struct seq_file *m, void *v, int is_pid)
{
show_map_vma(m, v, is_pid);
m_cache_vma(m, v);
return 0;
}
static int show_pid_map(struct seq_file *m, void *v)
{
return show_map(m, v, 1);
}
static int show_tid_map(struct seq_file *m, void *v)
{
return show_map(m, v, 0);
}
static const struct seq_operations proc_pid_maps_op = {
.start = m_start,
.next = m_next,
.stop = m_stop,
.show = show_pid_map
};
static const struct seq_operations proc_tid_maps_op = {
.start = m_start,
.next = m_next,
.stop = m_stop,
.show = show_tid_map
};
static int pid_maps_open(struct inode *inode, struct file *file)
{
return do_maps_open(inode, file, &proc_pid_maps_op);
}
static int tid_maps_open(struct inode *inode, struct file *file)
{
return do_maps_open(inode, file, &proc_tid_maps_op);
}
const struct file_operations proc_pid_maps_operations = {
.open = pid_maps_open,
.read = seq_read,
.llseek = seq_lseek,
.release = proc_map_release,
};
const struct file_operations proc_tid_maps_operations = {
.open = tid_maps_open,
.read = seq_read,
.llseek = seq_lseek,
.release = proc_map_release,
};
/*
* Proportional Set Size(PSS): my share of RSS.
*
* PSS of a process is the count of pages it has in memory, where each
* page is divided by the number of processes sharing it. So if a
* process has 1000 pages all to itself, and 1000 shared with one other
* process, its PSS will be 1500.
*
* To keep (accumulated) division errors low, we adopt a 64bit
* fixed-point pss counter to minimize division errors. So (pss >>
* PSS_SHIFT) would be the real byte count.
*
* A shift of 12 before division means (assuming 4K page size):
* - 1M 3-user-pages add up to 8KB errors;
* - supports mapcount up to 2^24, or 16M;
* - supports PSS up to 2^52 bytes, or 4PB.
*/
#define PSS_SHIFT 12
#ifdef CONFIG_PROC_PAGE_MONITOR
struct mem_size_stats {
unsigned long resident;
unsigned long shared_clean;
unsigned long shared_dirty;
unsigned long private_clean;
unsigned long private_dirty;
unsigned long referenced;
unsigned long anonymous;
unsigned long anonymous_thp;
unsigned long shmem_thp;
unsigned long swap;
unsigned long shared_hugetlb;
unsigned long private_hugetlb;
u64 pss;
u64 swap_pss;
bool check_shmem_swap;
};
static void smaps_account(struct mem_size_stats *mss, struct page *page,
bool compound, bool young, bool dirty)
{
int i, nr = compound ? 1 << compound_order(page) : 1;
unsigned long size = nr * PAGE_SIZE;
if (PageAnon(page))
mss->anonymous += size;
mss->resident += size;
/* Accumulate the size in pages that have been accessed. */
if (young || page_is_young(page) || PageReferenced(page))
mss->referenced += size;
/*
* page_count(page) == 1 guarantees the page is mapped exactly once.
* If any subpage of the compound page mapped with PTE it would elevate
* page_count().
*/
if (page_count(page) == 1) {
if (dirty || PageDirty(page))
mss->private_dirty += size;
else
mss->private_clean += size;
mss->pss += (u64)size << PSS_SHIFT;
return;
}
for (i = 0; i < nr; i++, page++) {
int mapcount = page_mapcount(page);
if (mapcount >= 2) {
if (dirty || PageDirty(page))
mss->shared_dirty += PAGE_SIZE;
else
mss->shared_clean += PAGE_SIZE;
mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount;
} else {
if (dirty || PageDirty(page))
mss->private_dirty += PAGE_SIZE;
else
mss->private_clean += PAGE_SIZE;
mss->pss += PAGE_SIZE << PSS_SHIFT;
}
}
}
#ifdef CONFIG_SHMEM
static int smaps_pte_hole(unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
struct mem_size_stats *mss = walk->private;
mss->swap += shmem_partial_swap_usage(
walk->vma->vm_file->f_mapping, addr, end);
return 0;
}
#endif
static void smaps_pte_entry(pte_t *pte, unsigned long addr,
struct mm_walk *walk)
{
struct mem_size_stats *mss = walk->private;
struct vm_area_struct *vma = walk->vma;
struct page *page = NULL;
if (pte_present(*pte)) {
page = vm_normal_page(vma, addr, *pte);
} else if (is_swap_pte(*pte)) {
swp_entry_t swpent = pte_to_swp_entry(*pte);
if (!non_swap_entry(swpent)) {
int mapcount;
mss->swap += PAGE_SIZE;
mapcount = swp_swapcount(swpent);
if (mapcount >= 2) {
u64 pss_delta = (u64)PAGE_SIZE << PSS_SHIFT;
do_div(pss_delta, mapcount);
mss->swap_pss += pss_delta;
} else {
mss->swap_pss += (u64)PAGE_SIZE << PSS_SHIFT;
}
} else if (is_migration_entry(swpent))
page = migration_entry_to_page(swpent);
} else if (unlikely(IS_ENABLED(CONFIG_SHMEM) && mss->check_shmem_swap
&& pte_none(*pte))) {
page = find_get_entry(vma->vm_file->f_mapping,
linear_page_index(vma, addr));
if (!page)
return;
if (radix_tree_exceptional_entry(page))
mss->swap += PAGE_SIZE;
else
put_page(page);
return;
}
if (!page)
return;
smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte));
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
struct mm_walk *walk)
{
struct mem_size_stats *mss = walk->private;
struct vm_area_struct *vma = walk->vma;
struct page *page;
/* FOLL_DUMP will return -EFAULT on huge zero page */
page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP);
if (IS_ERR_OR_NULL(page))
return;
if (PageAnon(page))
mss->anonymous_thp += HPAGE_PMD_SIZE;
else if (PageSwapBacked(page))
mss->shmem_thp += HPAGE_PMD_SIZE;
else if (is_zone_device_page(page))
/* pass */;
else
VM_BUG_ON_PAGE(1, page);
smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd));
}
#else
static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
struct mm_walk *walk)
{
}
#endif
static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
struct vm_area_struct *vma = walk->vma;
pte_t *pte;
spinlock_t *ptl;
ptl = pmd_trans_huge_lock(pmd, vma);
if (ptl) {
smaps_pmd_entry(pmd, addr, walk);
spin_unlock(ptl);
return 0;
}
if (pmd_trans_unstable(pmd))
return 0;
/*
* The mmap_sem held all the way back in m_start() is what
* keeps khugepaged out of here and from collapsing things
* in here.
*/
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
for (; addr != end; pte++, addr += PAGE_SIZE)
smaps_pte_entry(pte, addr, walk);
pte_unmap_unlock(pte - 1, ptl);
cond_resched();
return 0;
}
static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
{
/*
* Don't forget to update Documentation/ on changes.
*/
static const char mnemonics[BITS_PER_LONG][2] = {
/*
* In case if we meet a flag we don't know about.
*/
[0 ... (BITS_PER_LONG-1)] = "??",
[ilog2(VM_READ)] = "rd",
[ilog2(VM_WRITE)] = "wr",
[ilog2(VM_EXEC)] = "ex",
[ilog2(VM_SHARED)] = "sh",
[ilog2(VM_MAYREAD)] = "mr",
[ilog2(VM_MAYWRITE)] = "mw",
[ilog2(VM_MAYEXEC)] = "me",
[ilog2(VM_MAYSHARE)] = "ms",
[ilog2(VM_GROWSDOWN)] = "gd",
[ilog2(VM_PFNMAP)] = "pf",
[ilog2(VM_DENYWRITE)] = "dw",
#ifdef CONFIG_X86_INTEL_MPX
[ilog2(VM_MPX)] = "mp",
#endif
[ilog2(VM_LOCKED)] = "lo",
[ilog2(VM_IO)] = "io",
[ilog2(VM_SEQ_READ)] = "sr",
[ilog2(VM_RAND_READ)] = "rr",
[ilog2(VM_DONTCOPY)] = "dc",
[ilog2(VM_DONTEXPAND)] = "de",
[ilog2(VM_ACCOUNT)] = "ac",
[ilog2(VM_NORESERVE)] = "nr",
[ilog2(VM_HUGETLB)] = "ht",
[ilog2(VM_ARCH_1)] = "ar",
[ilog2(VM_DONTDUMP)] = "dd",
#ifdef CONFIG_MEM_SOFT_DIRTY
[ilog2(VM_SOFTDIRTY)] = "sd",
#endif
[ilog2(VM_MIXEDMAP)] = "mm",
[ilog2(VM_HUGEPAGE)] = "hg",
[ilog2(VM_NOHUGEPAGE)] = "nh",
[ilog2(VM_MERGEABLE)] = "mg",
[ilog2(VM_UFFD_MISSING)]= "um",
[ilog2(VM_UFFD_WP)] = "uw",
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
/* These come out via ProtectionKey: */
[ilog2(VM_PKEY_BIT0)] = "",
[ilog2(VM_PKEY_BIT1)] = "",
[ilog2(VM_PKEY_BIT2)] = "",
[ilog2(VM_PKEY_BIT3)] = "",
#endif
};
size_t i;
seq_puts(m, "VmFlags: ");
for (i = 0; i < BITS_PER_LONG; i++) {
if (!mnemonics[i][0])
continue;
if (vma->vm_flags & (1UL << i)) {
seq_printf(m, "%c%c ",
mnemonics[i][0], mnemonics[i][1]);
}
}
seq_putc(m, '\n');
}
#ifdef CONFIG_HUGETLB_PAGE
static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
struct mem_size_stats *mss = walk->private;
struct vm_area_struct *vma = walk->vma;
struct page *page = NULL;
if (pte_present(*pte)) {
page = vm_normal_page(vma, addr, *pte);
} else if (is_swap_pte(*pte)) {
swp_entry_t swpent = pte_to_swp_entry(*pte);
if (is_migration_entry(swpent))
page = migration_entry_to_page(swpent);
}
if (page) {
int mapcount = page_mapcount(page);
if (mapcount >= 2)
mss->shared_hugetlb += huge_page_size(hstate_vma(vma));
else
mss->private_hugetlb += huge_page_size(hstate_vma(vma));
}
return 0;
}
#endif /* HUGETLB_PAGE */
void __weak arch_show_smap(struct seq_file *m, struct vm_area_struct *vma)
{
}
static int show_smap(struct seq_file *m, void *v, int is_pid)
{
struct vm_area_struct *vma = v;
struct mem_size_stats mss;
struct mm_walk smaps_walk = {
.pmd_entry = smaps_pte_range,
#ifdef CONFIG_HUGETLB_PAGE
.hugetlb_entry = smaps_hugetlb_range,
#endif
.mm = vma->vm_mm,
.private = &mss,
};
memset(&mss, 0, sizeof mss);
#ifdef CONFIG_SHMEM
if (vma->vm_file && shmem_mapping(vma->vm_file->f_mapping)) {
/*
* For shared or readonly shmem mappings we know that all
* swapped out pages belong to the shmem object, and we can
* obtain the swap value much more efficiently. For private
* writable mappings, we might have COW pages that are
* not affected by the parent swapped out pages of the shmem
* object, so we have to distinguish them during the page walk.
* Unless we know that the shmem object (or the part mapped by
* our VMA) has no swapped out pages at all.
*/
unsigned long shmem_swapped = shmem_swap_usage(vma);
if (!shmem_swapped || (vma->vm_flags & VM_SHARED) ||
!(vma->vm_flags & VM_WRITE)) {
mss.swap = shmem_swapped;
} else {
mss.check_shmem_swap = true;
smaps_walk.pte_hole = smaps_pte_hole;
}
}
#endif
/* mmap_sem is held in m_start */
walk_page_vma(vma, &smaps_walk);
show_map_vma(m, vma, is_pid);
if (vma_get_anon_name(vma)) {
seq_puts(m, "Name: ");
seq_print_vma_name(m, vma);
seq_putc(m, '\n');
}
seq_printf(m,
"Size: %8lu kB\n"
"Rss: %8lu kB\n"
"Pss: %8lu kB\n"
"Shared_Clean: %8lu kB\n"
"Shared_Dirty: %8lu kB\n"
"Private_Clean: %8lu kB\n"
"Private_Dirty: %8lu kB\n"
"Referenced: %8lu kB\n"
"Anonymous: %8lu kB\n"
"AnonHugePages: %8lu kB\n"
"ShmemPmdMapped: %8lu kB\n"
"Shared_Hugetlb: %8lu kB\n"
"Private_Hugetlb: %7lu kB\n"
"Swap: %8lu kB\n"
"SwapPss: %8lu kB\n"
"KernelPageSize: %8lu kB\n"
"MMUPageSize: %8lu kB\n"
"Locked: %8lu kB\n",
(vma->vm_end - vma->vm_start) >> 10,
mss.resident >> 10,
(unsigned long)(mss.pss >> (10 + PSS_SHIFT)),
mss.shared_clean >> 10,
mss.shared_dirty >> 10,
mss.private_clean >> 10,
mss.private_dirty >> 10,
mss.referenced >> 10,
mss.anonymous >> 10,
mss.anonymous_thp >> 10,
mss.shmem_thp >> 10,
mss.shared_hugetlb >> 10,
mss.private_hugetlb >> 10,
mss.swap >> 10,
(unsigned long)(mss.swap_pss >> (10 + PSS_SHIFT)),
vma_kernel_pagesize(vma) >> 10,
vma_mmu_pagesize(vma) >> 10,
(vma->vm_flags & VM_LOCKED) ?
(unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0);
arch_show_smap(m, vma);
show_smap_vma_flags(m, vma);
m_cache_vma(m, vma);
return 0;
}
static int show_pid_smap(struct seq_file *m, void *v)
{
return show_smap(m, v, 1);
}
static int show_tid_smap(struct seq_file *m, void *v)
{
return show_smap(m, v, 0);
}
static const struct seq_operations proc_pid_smaps_op = {
.start = m_start,
.next = m_next,
.stop = m_stop,
.show = show_pid_smap
};
static const struct seq_operations proc_tid_smaps_op = {
.start = m_start,
.next = m_next,
.stop = m_stop,
.show = show_tid_smap
};
static int pid_smaps_open(struct inode *inode, struct file *file)
{
return do_maps_open(inode, file, &proc_pid_smaps_op);
}
static int tid_smaps_open(struct inode *inode, struct file *file)
{
return do_maps_open(inode, file, &proc_tid_smaps_op);
}
const struct file_operations proc_pid_smaps_operations = {
.open = pid_smaps_open,
.read = seq_read,
.llseek = seq_lseek,
.release = proc_map_release,
};
const struct file_operations proc_tid_smaps_operations = {
.open = tid_smaps_open,
.read = seq_read,
.llseek = seq_lseek,
.release = proc_map_release,
};
enum clear_refs_types {
CLEAR_REFS_ALL = 1,
CLEAR_REFS_ANON,
CLEAR_REFS_MAPPED,
CLEAR_REFS_SOFT_DIRTY,
CLEAR_REFS_MM_HIWATER_RSS,
CLEAR_REFS_LAST,
};
struct clear_refs_private {
enum clear_refs_types type;
};
#ifdef CONFIG_MEM_SOFT_DIRTY
static inline void clear_soft_dirty(struct vm_area_struct *vma,
unsigned long addr, pte_t *pte)
{
/*
* The soft-dirty tracker uses #PF-s to catch writes
* to pages, so write-protect the pte as well. See the
* Documentation/vm/soft-dirty.txt for full description
* of how soft-dirty works.
*/
pte_t ptent = *pte;
if (pte_present(ptent)) {
ptent = ptep_modify_prot_start(vma->vm_mm, addr, pte);
ptent = pte_wrprotect(ptent);
ptent = pte_clear_soft_dirty(ptent);
ptep_modify_prot_commit(vma->vm_mm, addr, pte, ptent);
} else if (is_swap_pte(ptent)) {
ptent = pte_swp_clear_soft_dirty(ptent);
set_pte_at(vma->vm_mm, addr, pte, ptent);
}
}
#else
static inline void clear_soft_dirty(struct vm_area_struct *vma,
unsigned long addr, pte_t *pte)
{
}
#endif
#if defined(CONFIG_MEM_SOFT_DIRTY) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmdp)
{
pmd_t pmd = *pmdp;
/* See comment in change_huge_pmd() */
pmdp_invalidate(vma, addr, pmdp);
if (pmd_dirty(*pmdp))
pmd = pmd_mkdirty(pmd);
if (pmd_young(*pmdp))
pmd = pmd_mkyoung(pmd);
pmd = pmd_wrprotect(pmd);
pmd = pmd_clear_soft_dirty(pmd);
set_pmd_at(vma->vm_mm, addr, pmdp, pmd);
}
#else
static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmdp)
{
}
#endif
static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
struct clear_refs_private *cp = walk->private;
struct vm_area_struct *vma = walk->vma;
pte_t *pte, ptent;
spinlock_t *ptl;
struct page *page;
ptl = pmd_trans_huge_lock(pmd, vma);
if (ptl) {
if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
clear_soft_dirty_pmd(vma, addr, pmd);
goto out;
}
page = pmd_page(*pmd);
/* Clear accessed and referenced bits. */
pmdp_test_and_clear_young(vma, addr, pmd);
test_and_clear_page_young(page);
ClearPageReferenced(page);
out:
spin_unlock(ptl);
return 0;
}
if (pmd_trans_unstable(pmd))
return 0;
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
for (; addr != end; pte++, addr += PAGE_SIZE) {
ptent = *pte;
if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
clear_soft_dirty(vma, addr, pte);
continue;
}
if (!pte_present(ptent))
continue;
page = vm_normal_page(vma, addr, ptent);
if (!page)
continue;
/* Clear accessed and referenced bits. */
ptep_test_and_clear_young(vma, addr, pte);
test_and_clear_page_young(page);
ClearPageReferenced(page);
}
pte_unmap_unlock(pte - 1, ptl);
cond_resched();
return 0;
}
static int clear_refs_test_walk(unsigned long start, unsigned long end,
struct mm_walk *walk)
{
struct clear_refs_private *cp = walk->private;
struct vm_area_struct *vma = walk->vma;
if (vma->vm_flags & VM_PFNMAP)
return 1;
/*
* Writing 1 to /proc/pid/clear_refs affects all pages.
* Writing 2 to /proc/pid/clear_refs only affects anonymous pages.
* Writing 3 to /proc/pid/clear_refs only affects file mapped pages.
* Writing 4 to /proc/pid/clear_refs affects all pages.
*/
if (cp->type == CLEAR_REFS_ANON && vma->vm_file)
return 1;
if (cp->type == CLEAR_REFS_MAPPED && !vma->vm_file)
return 1;
return 0;
}
static ssize_t clear_refs_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
struct task_struct *task;
char buffer[PROC_NUMBUF];
struct mm_struct *mm;
struct vm_area_struct *vma;
enum clear_refs_types type;
int itype;
int rv;
memset(buffer, 0, sizeof(buffer));
if (count > sizeof(buffer) - 1)
count = sizeof(buffer) - 1;
if (copy_from_user(buffer, buf, count))
return -EFAULT;
rv = kstrtoint(strstrip(buffer), 10, &itype);
if (rv < 0)
return rv;
type = (enum clear_refs_types)itype;
if (type < CLEAR_REFS_ALL || type >= CLEAR_REFS_LAST)
return -EINVAL;
task = get_proc_task(file_inode(file));
if (!task)
return -ESRCH;
mm = get_task_mm(task);
if (mm) {
struct clear_refs_private cp = {
.type = type,
};
struct mm_walk clear_refs_walk = {
.pmd_entry = clear_refs_pte_range,
.test_walk = clear_refs_test_walk,
.mm = mm,
.private = &cp,
};
if (type == CLEAR_REFS_MM_HIWATER_RSS) {
if (down_write_killable(&mm->mmap_sem)) {
count = -EINTR;
goto out_mm;
}
/*
* Writing 5 to /proc/pid/clear_refs resets the peak
* resident set size to this mm's current rss value.
*/
reset_mm_hiwater_rss(mm);
up_write(&mm->mmap_sem);
goto out_mm;
}
down_read(&mm->mmap_sem);
if (type == CLEAR_REFS_SOFT_DIRTY) {
for (vma = mm->mmap; vma; vma = vma->vm_next) {
if (!(vma->vm_flags & VM_SOFTDIRTY))
continue;
up_read(&mm->mmap_sem);
if (down_write_killable(&mm->mmap_sem)) {
count = -EINTR;
goto out_mm;
}
for (vma = mm->mmap; vma; vma = vma->vm_next) {
vma->vm_flags &= ~VM_SOFTDIRTY;
vma_set_page_prot(vma);
}
downgrade_write(&mm->mmap_sem);
break;
}
mmu_notifier_invalidate_range_start(mm, 0, -1);
}
walk_page_range(0, mm->highest_vm_end, &clear_refs_walk);
if (type == CLEAR_REFS_SOFT_DIRTY)
mmu_notifier_invalidate_range_end(mm, 0, -1);
flush_tlb_mm(mm);
up_read(&mm->mmap_sem);
out_mm:
mmput(mm);
}
put_task_struct(task);
return count;
}
const struct file_operations proc_clear_refs_operations = {
.write = clear_refs_write,
.llseek = noop_llseek,
};
typedef struct {
u64 pme;
} pagemap_entry_t;
struct pagemapread {
int pos, len; /* units: PM_ENTRY_BYTES, not bytes */
pagemap_entry_t *buffer;
bool show_pfn;
};
#define PAGEMAP_WALK_SIZE (PMD_SIZE)
#define PAGEMAP_WALK_MASK (PMD_MASK)
#define PM_ENTRY_BYTES sizeof(pagemap_entry_t)
#define PM_PFRAME_BITS 55
#define PM_PFRAME_MASK GENMASK_ULL(PM_PFRAME_BITS - 1, 0)
#define PM_SOFT_DIRTY BIT_ULL(55)
#define PM_MMAP_EXCLUSIVE BIT_ULL(56)
#define PM_FILE BIT_ULL(61)
#define PM_SWAP BIT_ULL(62)
#define PM_PRESENT BIT_ULL(63)
#define PM_END_OF_BUFFER 1
static inline pagemap_entry_t make_pme(u64 frame, u64 flags)
{
return (pagemap_entry_t) { .pme = (frame & PM_PFRAME_MASK) | flags };
}
static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme,
struct pagemapread *pm)
{
pm->buffer[pm->pos++] = *pme;
if (pm->pos >= pm->len)
return PM_END_OF_BUFFER;
return 0;
}
static int pagemap_pte_hole(unsigned long start, unsigned long end,
struct mm_walk *walk)
{
struct pagemapread *pm = walk->private;
unsigned long addr = start;
int err = 0;
//dump_stack();
while (addr < end) {
struct vm_area_struct *vma = find_vma(walk->mm, addr);
pagemap_entry_t pme = make_pme(0, 0);
/* End of address space hole, which we mark as non-present. */
unsigned long hole_end;
if (vma)
hole_end = min(end, vma->vm_start);
else
hole_end = end;
for (; addr < hole_end; addr += PAGE_SIZE) {
err = add_to_pagemap(addr, &pme, pm);
if (err)
goto out;
}
if (!vma)
break;
/* Addresses in the VMA. */
if (vma->vm_flags & VM_SOFTDIRTY)
pme = make_pme(0, PM_SOFT_DIRTY);
for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) {
err = add_to_pagemap(addr, &pme, pm);
if (err)
goto out;
}
}
out:
return err;
}
#if 0
CPU: 0 PID: 3363 Comm: mytest Tainted: G O 4.9.118 #1465
[ 98.979100] Hardware name: sun8iw15
[ 98.982981] [<c01112c8>] (unwind_backtrace) from [<c010cd7c>] (show_stack+0x20/0x24)
[ 98.991604] [<c010cd7c>] (show_stack) from [<c0484e10>] (dump_stack+0x78/0x94)
[ 98.999652] [<c0484e10>] (dump_stack) from [<c02f782c>] (pagemap_pmd_range+0xb4/0x2a8)
[ 99.008467] [<c02f782c>] (pagemap_pmd_range) from [<c0270c7c>] (walk_pgd_range+0x108/0x184)
[ 99.017758] [<c0270c7c>] (walk_pgd_range) from [<c0270e38>] (walk_page_range+0xe0/0x104)
[ 99.026761] [<c0270e38>] (walk_page_range) from [<c02f7bc8>] (pagemap_read+0x1a8/0x2e0)
[ 99.035672] [<c02f7bc8>] (pagemap_read) from [<c02905b8>] (__vfs_read+0x48/0x13c)
[ 99.044003] [<c02905b8>] (__vfs_read) from [<c02913a0>] (vfs_read+0xa0/0x154)
[ 99.051938] [<c02913a0>] (vfs_read) from [<c0292470>] (SyS_read+0x60/0xb0)
[ 99.059596] [<c0292470>] (SyS_read) from [<c0107f40>] (ret_fast_syscall+0x0/0x48)
#endif
static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
struct vm_area_struct *vma, unsigned long addr, pte_t pte)
{
u64 frame = 0, flags = 0;
struct page *page = NULL;
//printk("addr = %lx\n", addr);
//printk("pte = %lx\n", pte);
//dump_stack();
if (pte_present(pte)) {
//printk("pte.0\n");
//printk("pm->show_pfn = %lx\n", pm->show_pfn);
if (pm->show_pfn)
frame = pte_pfn(pte);
flags |= PM_PRESENT;
page = vm_normal_page(vma, addr, pte);
printk("addr = %lx\n", addr);
printk("page = %lx\n", page);
void *kaddr = kmap(page);
kaddr = (unsigned int)kaddr | (addr & 0xfff);
printk("kaddr = 0x%lx\n", kaddr);
print_hex_dump_bytes("walk.data: ", DUMP_PREFIX_ADDRESS, (u8 *)(kaddr), 0x40 );
kunmap(page);
if (pte_soft_dirty(pte))
flags |= PM_SOFT_DIRTY;
} else if (is_swap_pte(pte)) {
printk("pte.1\n");
swp_entry_t entry;
if (pte_swp_soft_dirty(pte))
flags |= PM_SOFT_DIRTY;
entry = pte_to_swp_entry(pte);
frame = swp_type(entry) |
(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
flags |= PM_SWAP;
if (is_migration_entry(entry))
page = migration_entry_to_page(entry);
}
if (page && !PageAnon(page))
flags |= PM_FILE;
if (page && page_mapcount(page) == 1)
flags |= PM_MMAP_EXCLUSIVE;
if (vma->vm_flags & VM_SOFTDIRTY)
flags |= PM_SOFT_DIRTY;
return make_pme(frame, flags);
}
static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
struct vm_area_struct *vma = walk->vma;
struct pagemapread *pm = walk->private;
spinlock_t *ptl;
pte_t *pte, *orig_pte;
int err = 0;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
kkkk
ptl = pmd_trans_huge_lock(pmdp, vma);
if (ptl) {
u64 flags = 0, frame = 0;
pmd_t pmd = *pmdp;
if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(pmd))
flags |= PM_SOFT_DIRTY;
/*
* Currently pmd for thp is always present because thp
* can not be swapped-out, migrated, or HWPOISONed
* (split in such cases instead.)
* This if-check is just to prepare for future implementation.
*/
if (pmd_present(pmd)) {
struct page *page = pmd_page(pmd);
if (page_mapcount(page) == 1)
flags |= PM_MMAP_EXCLUSIVE;
flags |= PM_PRESENT;
if (pm->show_pfn)
frame = pmd_pfn(pmd) +
((addr & ~PMD_MASK) >> PAGE_SHIFT);
}
for (; addr != end; addr += PAGE_SIZE) {
pagemap_entry_t pme = make_pme(frame, flags);
err = add_to_pagemap(addr, &pme, pm);
if (err)
break;
if (pm->show_pfn && (flags & PM_PRESENT))
frame++;
}
spin_unlock(ptl);
return err;
}
if (pmd_trans_unstable(pmdp))
return 0;
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
/*
* We can assume that @vma always points to a valid one and @end never
* goes beyond vma->vm_end.
*/
orig_pte = pte = pte_offset_map_lock(walk->mm, pmdp, addr, &ptl);
printk("\n\npagemap_pmd_range start...\n");
for (; addr < end; pte++, addr += PAGE_SIZE) {
pagemap_entry_t pme;
printk("addr = %lx\n", addr);
printk("end = %lx\n", end);
printk("pte = %p\n", pte);
printk("*pte = %lx\n", *pte);
pme = pte_to_pagemap_entry(pm, vma, addr, *pte);
err = add_to_pagemap(addr, &pme, pm);
if (!err)
break;
}
printk("pagemap_pmd_range end!!! err = %d\n\n", err);
pte_unmap_unlock(orig_pte, ptl);
cond_resched();
return err;
}
#ifdef CONFIG_HUGETLB_PAGE
/* This function walks within one hugetlb entry in the single call */
static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask,
unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
struct pagemapread *pm = walk->private;
struct vm_area_struct *vma = walk->vma;
u64 flags = 0, frame = 0;
int err = 0;
pte_t pte;
if (vma->vm_flags & VM_SOFTDIRTY)
flags |= PM_SOFT_DIRTY;
pte = huge_ptep_get(ptep);
if (pte_present(pte)) {
struct page *page = pte_page(pte);
if (!PageAnon(page))
flags |= PM_FILE;
if (page_mapcount(page) == 1)
flags |= PM_MMAP_EXCLUSIVE;
flags |= PM_PRESENT;
if (pm->show_pfn)
frame = pte_pfn(pte) +
((addr & ~hmask) >> PAGE_SHIFT);
}
for (; addr != end; addr += PAGE_SIZE) {
pagemap_entry_t pme = make_pme(frame, flags);
err = add_to_pagemap(addr, &pme, pm);
if (err)
return err;
if (pm->show_pfn && (flags & PM_PRESENT))
frame++;
}
cond_resched();
return err;
}
#endif /* HUGETLB_PAGE */
extern int debug_en_pagewalk;
/*
* /proc/pid/pagemap - an array mapping virtual pages to pfns
*
* For each page in the address space, this file contains one 64-bit entry
* consisting of the following:
*
* Bits 0-54 page frame number (PFN) if present
* Bits 0-4 swap type if swapped
* Bits 5-54 swap offset if swapped
* Bit 55 pte is soft-dirty (see Documentation/vm/soft-dirty.txt)
* Bit 56 page exclusively mapped
* Bits 57-60 zero
* Bit 61 page is file-page or shared-anon
* Bit 62 page swapped
* Bit 63 page present
*
* If the page is not present but in swap, then the PFN contains an
* encoding of the swap file number and the page's offset into the
* swap. Unmapped pages return a null PFN. This allows determining
* precisely which pages are mapped (or in swap) and comparing mapped
* pages between processes.
*
* Efficient users of this interface will use /proc/pid/maps to
* determine which areas of memory are actually mapped and llseek to
* skip over unmapped regions.
*/
static ssize_t pagemap_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
struct mm_struct *mm = file->private_data;
struct pagemapread pm;
struct mm_walk pagemap_walk = {};
unsigned long src;
unsigned long svpfn;
unsigned long start_vaddr;
unsigned long end_vaddr;
int ret = 0, copied = 0;
struct task_struct *task;
printk("\n\n\n\n\n*****************************************************\n");
printk("in pagemap_read\n");
printk("buf = %p\n", buf);
printk("count = %x\n", count);
printk("ppos = %p\n", ppos);
printk("*ppos = %llx\n", *ppos);
task = mm->owner;
printk("task->comm = %s\n", task->comm);
//task = current;
//if( task->comm[0]=='c' && task->comm[1]=='a' && task->comm[2]=='t' ){
// debug_en = 0x01;
//printk("mm->mm_users = %lx\n", mm->mm_users);
//printk("mm = %p\n", mm);
if (!mm || !atomic_inc_not_zero(&mm->mm_users))
goto out;
//printk("mm->mm_users = %lx\n", mm->mm_users);
ret = -EINVAL;
/* file position must be aligned */
if ((*ppos % PM_ENTRY_BYTES) || (count % PM_ENTRY_BYTES))
goto out_mm;
ret = 0;
if (!count)
goto out_mm;
/* do not disclose physical addresses: attack vector */
pm.show_pfn = file_ns_capable(file, &init_user_ns, CAP_SYS_ADMIN);
pm.len = (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
pm.buffer = kmalloc(pm.len * PM_ENTRY_BYTES, GFP_TEMPORARY);
ret = -ENOMEM;
if (!pm.buffer)
goto out_mm;
pagemap_walk.pmd_entry = pagemap_pmd_range;
pagemap_walk.pte_hole = pagemap_pte_hole;
#ifdef CONFIG_HUGETLB_PAGE
pagemap_walk.hugetlb_entry = pagemap_hugetlb_range;
#endif
pagemap_walk.mm = mm;
pagemap_walk.private = ±
src = *ppos;
svpfn = src / PM_ENTRY_BYTES;
start_vaddr = svpfn << PAGE_SHIFT;
end_vaddr = mm->task_size;
/* watch out for wraparound */
if (svpfn > mm->task_size >> PAGE_SHIFT)
start_vaddr = end_vaddr;
/*
* The odds are that this will stop walking way
* before end_vaddr, because the length of the
* user buffer is tracked in "pm", and the walk
* will stop when we hit the end of the buffer.
*/
ret = 0;
//printk("pm.buffer = %p\n", pm.buffer);
//printk("start_vaddr = %lx\n", start_vaddr);
//printk("end_vaddr = %lx\n", end_vaddr);
while (count && (start_vaddr < end_vaddr)) {
int len;
unsigned long end;
pm.pos = 0;
end = (start_vaddr + PAGEMAP_WALK_SIZE) & PAGEMAP_WALK_MASK;
//PAGEMAP_WALK_SIZE = 200000
//PAGEMAP_WALK_MASK = ffe00000
//printk("PAGEMAP_WALK_SIZE = %lx\n", PAGEMAP_WALK_SIZE);
//printk("PAGEMAP_WALK_MASK = %lx\n", PAGEMAP_WALK_MASK);
/* overflow ? */
if (end < start_vaddr || end > end_vaddr)
end = end_vaddr;
down_read(&mm->mmap_sem);
//printk("task_mmu start_vaddr = %lx\n", start_vaddr);
//printk("task_mmu end = %lx\n", end);
ret = walk_page_range(start_vaddr, end, &pagemap_walk);
up_read(&mm->mmap_sem);
start_vaddr = end;
len = min(count, PM_ENTRY_BYTES * pm.pos);
//printk("PM_ENTRY_BYTES = %lx\n", PM_ENTRY_BYTES);
//PM_ENTRY_BYTES = 8
//printk("pm.pos = %lx\n", pm.pos);
//printk("count = %lx\n", count);
//printk("len = %lx\n", len);
if (copy_to_user(buf, pm.buffer, len)) {
ret = -EFAULT;
goto out_free;
}
copied += len;
buf += len;
count -= len;
}
*ppos += copied;
if (!ret || ret == PM_END_OF_BUFFER)
ret = copied;
out_free:
kfree(pm.buffer);
out_mm:
mmput(mm);
out:
debug_en_pagewalk = 0x00;
return ret;
}
static int pagemap_open(struct inode *inode, struct file *file)
{
struct mm_struct *mm;
mm = proc_mem_open(inode, PTRACE_MODE_READ);
if (IS_ERR(mm))
return PTR_ERR(mm);
file->private_data = mm;
return 0;
}
static int pagemap_release(struct inode *inode, struct file *file)
{
struct mm_struct *mm = file->private_data;
if (mm)
mmdrop(mm);
return 0;
}
const struct file_operations proc_pagemap_operations = {
.llseek = mem_lseek, /* borrow this */
.read = pagemap_read,
.open = pagemap_open,
.release = pagemap_release,
};
#endif /* CONFIG_PROC_PAGE_MONITOR */
#ifdef CONFIG_NUMA
struct numa_maps {
unsigned long pages;
unsigned long anon;
unsigned long active;
unsigned long writeback;
unsigned long mapcount_max;
unsigned long dirty;
unsigned long swapcache;
unsigned long node[MAX_NUMNODES];
};
struct numa_maps_private {
struct proc_maps_private proc_maps;
struct numa_maps md;
};
static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty,
unsigned long nr_pages)
{
int count = page_mapcount(page);
md->pages += nr_pages;
if (pte_dirty || PageDirty(page))
md->dirty += nr_pages;
if (PageSwapCache(page))
md->swapcache += nr_pages;
if (PageActive(page) || PageUnevictable(page))
md->active += nr_pages;
if (PageWriteback(page))
md->writeback += nr_pages;
if (PageAnon(page))
md->anon += nr_pages;
if (count > md->mapcount_max)
md->mapcount_max = count;
md->node[page_to_nid(page)] += nr_pages;
}
static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma,
unsigned long addr)
{
struct page *page;
int nid;
if (!pte_present(pte))
return NULL;
page = vm_normal_page(vma, addr, pte);
if (!page)
return NULL;
if (PageReserved(page))
return NULL;
nid = page_to_nid(page);
if (!node_isset(nid, node_states[N_MEMORY]))
return NULL;
return page;
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static struct page *can_gather_numa_stats_pmd(pmd_t pmd,
struct vm_area_struct *vma,
unsigned long addr)
{
struct page *page;
int nid;
if (!pmd_present(pmd))
return NULL;
page = vm_normal_page_pmd(vma, addr, pmd);
if (!page)
return NULL;
if (PageReserved(page))
return NULL;
nid = page_to_nid(page);
if (!node_isset(nid, node_states[N_MEMORY]))
return NULL;
return page;
}
#endif
static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
struct numa_maps *md = walk->private;
struct vm_area_struct *vma = walk->vma;
spinlock_t *ptl;
pte_t *orig_pte;
pte_t *pte;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
ptl = pmd_trans_huge_lock(pmd, vma);
if (ptl) {
struct page *page;
page = can_gather_numa_stats_pmd(*pmd, vma, addr);
if (page)
gather_stats(page, md, pmd_dirty(*pmd),
HPAGE_PMD_SIZE/PAGE_SIZE);
spin_unlock(ptl);
return 0;
}
if (pmd_trans_unstable(pmd))
return 0;
#endif
orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
do {
struct page *page = can_gather_numa_stats(*pte, vma, addr);
if (!page)
continue;
gather_stats(page, md, pte_dirty(*pte), 1);
} while (pte++, addr += PAGE_SIZE, addr != end);
pte_unmap_unlock(orig_pte, ptl);
return 0;
}
#ifdef CONFIG_HUGETLB_PAGE
static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask,
unsigned long addr, unsigned long end, struct mm_walk *walk)
{
pte_t huge_pte = huge_ptep_get(pte);
struct numa_maps *md;
struct page *page;
if (!pte_present(huge_pte))
return 0;
page = pte_page(huge_pte);
if (!page)
return 0;
md = walk->private;
gather_stats(page, md, pte_dirty(huge_pte), 1);
return 0;
}
#else
static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask,
unsigned long addr, unsigned long end, struct mm_walk *walk)
{
return 0;
}
#endif
/*
* Display pages allocated per node and memory policy via /proc.
*/
static int show_numa_map(struct seq_file *m, void *v, int is_pid)
{
struct numa_maps_private *numa_priv = m->private;
struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
struct vm_area_struct *vma = v;
struct numa_maps *md = &numa_priv->md;
struct file *file = vma->vm_file;
struct mm_struct *mm = vma->vm_mm;
struct mm_walk walk = {
.hugetlb_entry = gather_hugetlb_stats,
.pmd_entry = gather_pte_stats,
.private = md,
.mm = mm,
};
struct mempolicy *pol;
char buffer[64];
int nid;
if (!mm)
return 0;
/* Ensure we start with an empty set of numa_maps statistics. */
memset(md, 0, sizeof(*md));
pol = __get_vma_policy(vma, vma->vm_start);
if (pol) {
mpol_to_str(buffer, sizeof(buffer), pol);
mpol_cond_put(pol);
} else {
mpol_to_str(buffer, sizeof(buffer), proc_priv->task_mempolicy);
}
seq_printf(m, "%08lx %s", vma->vm_start, buffer);
if (file) {
seq_puts(m, " file=");
seq_file_path(m, file, "\n\t= ");
} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
seq_puts(m, " heap");
} else if (is_stack(proc_priv, vma)) {
seq_puts(m, " stack");
}
if (is_vm_hugetlb_page(vma))
seq_puts(m, " huge");
/* mmap_sem is held by m_start */
walk_page_vma(vma, &walk);
if (!md->pages)
goto out;
if (md->anon)
seq_printf(m, " anon=%lu", md->anon);
if (md->dirty)
seq_printf(m, " dirty=%lu", md->dirty);
if (md->pages != md->anon && md->pages != md->dirty)
seq_printf(m, " mapped=%lu", md->pages);
if (md->mapcount_max > 1)
seq_printf(m, " mapmax=%lu", md->mapcount_max);
if (md->swapcache)
seq_printf(m, " swapcache=%lu", md->swapcache);
if (md->active < md->pages && !is_vm_hugetlb_page(vma))
seq_printf(m, " active=%lu", md->active);
if (md->writeback)
seq_printf(m, " writeback=%lu", md->writeback);
for_each_node_state(nid, N_MEMORY)
if (md->node[nid])
seq_printf(m, " N%d=%lu", nid, md->node[nid]);
seq_printf(m, " kernelpagesize_kB=%lu", vma_kernel_pagesize(vma) >> 10);
out:
seq_putc(m, '\n');
m_cache_vma(m, vma);
return 0;
}
static int show_pid_numa_map(struct seq_file *m, void *v)
{
return show_numa_map(m, v, 1);
}
static int show_tid_numa_map(struct seq_file *m, void *v)
{
return show_numa_map(m, v, 0);
}
static const struct seq_operations proc_pid_numa_maps_op = {
.start = m_start,
.next = m_next,
.stop = m_stop,
.show = show_pid_numa_map,
};
static const struct seq_operations proc_tid_numa_maps_op = {
.start = m_start,
.next = m_next,
.stop = m_stop,
.show = show_tid_numa_map,
};
static int numa_maps_open(struct inode *inode, struct file *file,
const struct seq_operations *ops)
{
return proc_maps_open(inode, file, ops,
sizeof(struct numa_maps_private));
}
static int pid_numa_maps_open(struct inode *inode, struct file *file)
{
return numa_maps_open(inode, file, &proc_pid_numa_maps_op);
}
static int tid_numa_maps_open(struct inode *inode, struct file *file)
{
return numa_maps_open(inode, file, &proc_tid_numa_maps_op);
}
const struct file_operations proc_pid_numa_maps_operations = {
.open = pid_numa_maps_open,
.read = seq_read,
.llseek = seq_lseek,
.release = proc_map_release,
};
const struct file_operations proc_tid_numa_maps_operations = {
.open = tid_numa_maps_open,
.read = seq_read,
.llseek = seq_lseek,
.release = proc_map_release,
};
#endif /* CONFIG_NUMA */
扫一扫
1744
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
