mmap_munmap_clone/memory2.c

/*
 *  linux/mm/memory.c
 *
 *  (C) 1991  Linus Torvalds
 */

/*
 * demand-loading started 01.12.91 - seems it is high on the list of
 * things wanted, and it should be easy to implement. - Linus
 */

/*
 * Ok, demand-loading was easy, shared pages a little bit tricker. Shared
 * pages started 02.12.91, seems to work. - Linus.
 *
 * Tested sharing by executing about 30 /bin/sh: under the old kernel it
 * would have taken more than the 6M I have free, but it worked well as
 * far as I could see.
 *
 * Also corrected some "invalidate()"s - I wasn't doing enough of them.
 */

#include <signal.h>
#include <asm/segment.h>
#include <asm/system.h>
#include <linux/sched.h>
#include <linux/head.h>
#include <linux/kernel.h>
#include <sys/stat.h>
#include <errno.h>
#include <sys/types.h>
volatile void do_exit(long code);

static inline volatile void oom(void)
{
	printk("out of memory\n\r");
	do_exit(SIGSEGV);
}

#define invalidate() \
__asm__("movl %%eax,%%cr3"::"a" (0))

/* these are not to be changed without changing head.s etc */
#define LOW_MEM 0x100000
#define PAGING_MEMORY (15*1024*1024)
#define PAGING_PAGES (PAGING_MEMORY>>12)
#define MAP_NR(addr) (((addr)-LOW_MEM)>>12)
#define USED 100

#define CODE_SPACE(addr) ((((addr)+4095)&~4095) < \
current->start_code + current->end_code)

static long HIGH_MEMORY = 0;

#define copy_page(from,to) \
__asm__("cld ; rep ; movsl"::"S" (from),"D" (to),"c" (1024))

static unsigned char mem_map [ PAGING_PAGES ] = {0,};

/*
 * Get physical address of first (actually last :-) free page, and mark it
 * used. If no free pages left, return 0.
 */
unsigned long get_free_page(void)
{
register unsigned long __res asm("ax");

__asm__("std ; repne ; scasb\n\t"
	"jne 1f\n\t"
	"movb $1,1(%%edi)\n\t"
	"sall $12,%%ecx\n\t"
	"addl %2,%%ecx\n\t"
	"movl %%ecx,%%edx\n\t"
	"movl $1024,%%ecx\n\t"
	"leal 4092(%%edx),%%edi\n\t"
	"rep ; stosl\n\t"
	"movl %%edx,%%eax\n\t"
	"1:"
	"cld\n\t"       /* by wyj */
	:"=a" (__res)
	:"0" (0),"i" (LOW_MEM),"c" (PAGING_PAGES),
	"D" (mem_map+PAGING_PAGES-1)
	);
return __res;
}

/*
 * Free a page of memory at physical address 'addr'. Used by
 * 'free_page_tables()'
 */
void free_page(unsigned long addr)
{
	if (addr < LOW_MEM) return;
	if (addr >= HIGH_MEMORY)
		panic("trying to free nonexistent page");
	addr -= LOW_MEM;
	addr >>= 12;
	if (mem_map[addr]--) return;
	mem_map[addr]=0;
	panic("trying to free free page");
}

/*
 * This function frees a continuos block of page tables, as needed
 * by 'exit()'. As does copy_page_tables(), this handles only 4Mb blocks.
 */
int free_page_tables(unsigned long from,unsigned long size)
{
	unsigned long *pg_table;
	unsigned long * dir, nr;

	if (from & 0x3fffff)
		panic("free_page_tables called with wrong alignment");
	if (!from)
		panic("Trying to free up swapper memory space");
	size = (size + 0x3fffff) >> 22;
	dir = (unsigned long *) ((from>>20) & 0xffc); /* _pg_dir = 0 */
	for ( ; size-->0 ; dir++) {
		if (!(1 & *dir))
			continue;
		pg_table = (unsigned long *) (0xfffff000 & *dir);
		for (nr=0 ; nr<1024 ; nr++) {
			if (1 & *pg_table)
				free_page(0xfffff000 & *pg_table);
			*pg_table = 0;
			pg_table++;
		}
		free_page(0xfffff000 & *dir);
		*dir = 0;
	}
	invalidate();
	return 0;
}

/*
 *  Well, here is one of the most complicated functions in mm. It
 * copies a range of linerar addresses by copying only the pages.
 * Let's hope this is bug-free, 'cause this one I don't want to debug :-)
 *
 * Note! We don't copy just any chunks of memory - addresses have to
 * be divisible by 4Mb (one page-directory entry), as this makes the
 * function easier. It's used only by fork anyway.
 *
 * NOTE 2!! When from==0 we are copying kernel space for the first
 * fork(). Then we DONT want to copy a full page-directory entry, as
 * that would lead to some serious memory waste - we just copy the
 * first 160 pages - 640kB. Even that is more than we need, but it
 * doesn't take any more memory - we don't copy-on-write in the low
 * 1 Mb-range, so the pages can be shared with the kernel. Thus the
 * special case for nr=xxxx.
 */
int copy_page_tables(unsigned long from,unsigned long to,long size)
{
	unsigned long * from_page_table;
	unsigned long * to_page_table;
	unsigned long this_page;
	unsigned long * from_dir, * to_dir;
	unsigned long nr;

	if ((from&0x3fffff) || (to&0x3fffff))
		panic("copy_page_tables called with wrong alignment");
	from_dir = (unsigned long *) ((from>>20) & 0xffc); /* _pg_dir = 0 */
	to_dir = (unsigned long *) ((to>>20) & 0xffc);
	size = ((unsigned) (size+0x3fffff)) >> 22;
	for( ; size-->0 ; from_dir++,to_dir++) {
		if (1 & *to_dir)
			panic("copy_page_tables: already exist");
		if (!(1 & *from_dir))
			continue;
		from_page_table = (unsigned long *) (0xfffff000 & *from_dir);
		if (!(to_page_table = (unsigned long *) get_free_page()))
			return -1;	/* Out of memory, see freeing */
		*to_dir = ((unsigned long) to_page_table) | 7;
		nr = (from==0)?0xA0:1024;
		for ( ; nr-- > 0 ; from_page_table++,to_page_table++) {
			this_page = *from_page_table;
			if (!(1 & this_page))
				continue;
			this_page &= ~2;
			*to_page_table = this_page;
			if (this_page > LOW_MEM) {
				*from_page_table = this_page;
				this_page -= LOW_MEM;
				this_page >>= 12;
				mem_map[this_page]++;
			}
		}
	}
	invalidate();
	return 0;
}

/*
 * This function puts a page in memory at the wanted address.
 * It returns the physical address of the page gotten, 0 if
 * out of memory (either when trying to access page-table or
 * page.)
 */
unsigned long put_page(unsigned long page,unsigned long address)
{
	unsigned long tmp, *page_table;

/* NOTE !!! This uses the fact that _pg_dir=0 */

	if (page < LOW_MEM || page >= HIGH_MEMORY)
		printk("Trying to put page %p at %p\n",page,address);
	if (mem_map[(page-LOW_MEM)>>12] != 1)
		printk("mem_map disagrees with %p at %p\n",page,address);
	page_table = (unsigned long *) ((address>>20) & 0xffc);
	if ((*page_table)&1)
		page_table = (unsigned long *) (0xfffff000 & *page_table);
	else {
		if (!(tmp=get_free_page()))
			return 0;
		*page_table = tmp|7;
		page_table = (unsigned long *) tmp;
	}
	page_table[(address>>12) & 0x3ff] = page | 7;
/* no need for invalidate */
	return page;
}

void un_wp_page(unsigned long * table_entry)
{
	unsigned long old_page,new_page;

	old_page = 0xfffff000 & *table_entry;
	if (old_page >= LOW_MEM && mem_map[MAP_NR(old_page)]==1) {
		*table_entry |= 2;
		invalidate();
		return;
	}
	if (!(new_page=get_free_page()))
		oom();
	if (old_page >= LOW_MEM)
		mem_map[MAP_NR(old_page)]--;
	*table_entry = new_page | 7;
	invalidate();
	copy_page(old_page,new_page);
}	

/*
 * This routine handles present pages, when users try to write
 * to a shared page. It is done by copying the page to a new address
 * and decrementing the shared-page counter for the old page.
 *
 * If it's in code space we exit with a segment error.
 */
void do_wp_page(unsigned long error_code,unsigned long address)
{
#if 0
/* we cannot do this yet: the estdio library writes to code space */
/* stupid, stupid. I really want the libc.a from GNU */
	if (CODE_SPACE(address))
		do_exit(SIGSEGV);
#endif
	un_wp_page((unsigned long *)
		(((address>>10) & 0xffc) + (0xfffff000 &
		*((unsigned long *) ((address>>20) &0xffc)))));

}

void write_verify(unsigned long address)
{
	unsigned long page;

	if (!( (page = *((unsigned long *) ((address>>20) & 0xffc)) )&1))
		return;
	page &= 0xfffff000;
	page += ((address>>10) & 0xffc);
	if ((3 & *(unsigned long *) page) == 1)  /* non-writeable, present */
		un_wp_page((unsigned long *) page);
	return;
}

void get_empty_page(unsigned long address)
{
	unsigned long tmp;

	if (!(tmp=get_free_page()) || !put_page(tmp,address)) {
		free_page(tmp);		/* 0 is ok - ignored */
		oom();
	}
}

/*
 * try_to_share() checks the page at address "address" in the task "p",
 * to see if it exists, and if it is clean. If so, share it with the current
 * task.
 *
 * NOTE! This assumes we have checked that p != current, and that they
 * share the same executable.
 */
static int try_to_share(unsigned long address, struct task_struct * p)
{
	unsigned long from;
	unsigned long to;
	unsigned long from_page;
	unsigned long to_page;
	unsigned long phys_addr;

	from_page = to_page = ((address>>20) & 0xffc);
	from_page += ((p->start_code>>20) & 0xffc);
	to_page += ((current->start_code>>20) & 0xffc);
/* is there a page-directory at from? */
	from = *(unsigned long *) from_page;
	if (!(from & 1))
		return 0;
	from &= 0xfffff000;
	from_page = from + ((address>>10) & 0xffc);
	phys_addr = *(unsigned long *) from_page;
/* is the page clean and present? */
	if ((phys_addr & 0x41) != 0x01)
		return 0;
	phys_addr &= 0xfffff000;
	if (phys_addr >= HIGH_MEMORY || phys_addr < LOW_MEM)
		return 0;
	to = *(unsigned long *) to_page;
	if (!(to & 1))
		if (to = get_free_page())
			*(unsigned long *) to_page = to | 7;
		else
			oom();
	to &= 0xfffff000;
	to_page = to + ((address>>10) & 0xffc);
	if (1 & *(unsigned long *) to_page)
		panic("try_to_share: to_page already exists");
/* share them: write-protect */
	*(unsigned long *) from_page &= ~2;
	*(unsigned long *) to_page = *(unsigned long *) from_page;
	invalidate();
	phys_addr -= LOW_MEM;
	phys_addr >>= 12;
	mem_map[phys_addr]++;
	return 1;
}

/*
 * share_page() tries to find a process that could share a page with
 * the current one. Address is the address of the wanted page relative
 * to the current data space.
 *
 * We first check if it is at all feasible by checking executable->i_count.
 * It should be >1 if there are other tasks sharing this inode.
 */
static int share_page(unsigned long address)
{
	struct task_struct ** p;

	if (!current->executable)
		return 0;
	if (current->executable->i_count < 2)
		return 0;
	for (p = &LAST_TASK ; p > &FIRST_TASK ; --p) {
		if (!*p)
			continue;
		if (current == *p)
			continue;
		if ((*p)->executable != current->executable)
			continue;
		if (try_to_share(address,*p))
			return 1;
	}
	return 0;
}

void do_no_page(unsigned long error_code,unsigned long address)
{
	int nr[4];
	unsigned long tmp;
	unsigned long page;
	int block,i;

	address &= 0xfffff000;
	tmp = address - current->start_code;
	if (!current->executable || tmp >= current->end_data) {
		get_empty_page(address);
		return;
	}
	if (share_page(tmp))
		return;
	if (!(page = get_free_page()))
		oom();
/* remember that 1 block is used for header */
	block = 1 + tmp/BLOCK_SIZE;
	for (i=0 ; i<4 ; block++,i++)
		nr[i] = bmap(current->executable,block);
	bread_page(page,current->executable->i_dev,nr);
	i = tmp + 4096 - current->end_data;
	tmp = page + 4096;
	while (i-- > 0) {
		tmp--;
		*(char *)tmp = 0;
	}
	if (put_page(page,address))
		return;
	free_page(page);
	oom();
}
void do_no_page1(unsigned long address)
{
	int nr[4];
	unsigned long tmp;
	unsigned long page;
	int block,i;
	address &= 0xfffff000;
	tmp = address - current->start_code;
	if (!current->executable || tmp >= current->end_data) {
		get_empty_page(address);
		return;
	}
	if (share_page(tmp))
		return;
	if (!(page = get_free_page()))
		oom();
	block = 1 + tmp/BLOCK_SIZE;
	for (i=0 ; i<4 ; block++,i++)
		nr[i] = bmap(current->executable,block);
	bread_page(page,current->executable->i_dev,nr);
	i = tmp + 4096 - current->end_data;
	tmp = page + 4096;
	while (i-- > 0) {
		tmp--;
		*(char *)tmp = 0;
	}
	if (put_page(page,address))
		return;
	free_page(page);
	oom();
}
void mem_init(long start_mem, long end_mem)
{
	int i;

	HIGH_MEMORY = end_mem;
	for (i=0 ; i<PAGING_PAGES ; i++)
		mem_map[i] = USED;
	i = MAP_NR(start_mem);
	end_mem -= start_mem;
	end_mem >>= 12;
	while (end_mem-->0)
		mem_map[i++]=0;
}

void calc_mem(void)
{
	int i,j,k,free=0;
	long * pg_tbl;

	for(i=0 ; i<PAGING_PAGES ; i++)
		if (!mem_map[i]) free++;
	printk("%d pages free (of %d)\n\r",free,PAGING_PAGES);
	for(i=2 ; i<1024 ; i++) {
		if (1&pg_dir[i]) {
			pg_tbl=(long *) (0xfffff000 & pg_dir[i]);
			for(j=k=0 ; j<1024 ; j++)
				if (pg_tbl[j]&1)
					k++;
			printk("Pg-dir[%d] uses %d pages\n",i,k);
		}
	}
}
int mem_read(unsigned int fd,off_t off,char * buf,int count)
{
	struct file * file;
	struct m_inode * inode;

	if (fd>=NR_OPEN || count<0 || !(file=current->filp[fd]))
		return -EINVAL;
	if (!count)
		return 0;
	verify_area(buf,count);
	inode = file->f_inode;
	file->f_pos = off;
	if (inode->i_pipe)
		return (file->f_mode&1)?read_pipe(inode,buf,count):-EIO;
	if (S_ISCHR(inode->i_mode))
		return rw_char(READ,inode->i_zone[0],buf,count,&file->f_pos);
	if (S_ISBLK(inode->i_mode))
		return block_read(inode->i_zone[0],&file->f_pos,buf,count);
	if (S_ISDIR(inode->i_mode) || S_ISREG(inode->i_mode)) {
		if (count+file->f_pos > inode->i_size)
			count = inode->i_size - file->f_pos;
		if (count<=0)
			return 0;
		return file_read(inode,file,buf,count);
	}
	printk("(Read)inode->i_mode=%06o\n\r",inode->i_mode);
	return -EINVAL;
}

//long sys_mmap(void *start,size_t len,int prot,int flags,int fd,off_t off){
//有时需要建立共享内存 所以需要将其他进程的地址空间也映射到该文件
long sys_mmap(void *start,size_t len,...){
	int prot = 3,flags=1,fd=3,off = 0;
	int block;
	size_t l=len;
	struct buffer_head * bh;
	void * buf=start;
	int tempprot=0;
	struct m_inode *dir = current->filp[fd]->f_inode;
	size_t size=len;
	if (size%PAGE_SIZE)	size = size/4096*4096+4096;
	printk("Size is %ld \n",size);
	//必须要有读权限 如果没有 直接返回-1
	if(!(prot&PROT_READ)){
		printk(" Permission denied \n");
		return -1;
	}
	//如果是空的 由其自己分配内存
	if(start==NULL){
		//需要由程序分配合适的地址空间
		//由于是借助链表实现 所以需要搜索来找到合适的地址进行使用
		if(current->mmap==NULL)	buf = 0x2000000;//直接从中间
		else if(current->mmap->next==NULL)	buf = current->mmap->vm_end;
		
	}
	//初始化
	struct vmarea_struct *m1 = (struct vmarea_struct *)malloc(sizeof(struct vmarea_struct));
	m1->mode = prot;
	m1->flag = flags;
	m1->next = NULL;
	m1->size = size;
	m1->vm_start = buf;
	m1->vm_end  = (unsigned long)buf+size;
	m1->fd = fd;
	
	m1->off = off;
	if(current->mmap==NULL)	current->mmap = m1;
	else{//插到最后一个位置
		struct vmarea_struct *m2=current->mmap;
		for(m2;m2->next;m2=m2->next)
			;
		m2->next = m1;
	}
	printk("buf is %ld  \n",buf);
	//接下来进行映射等操作
	//参考了try_to_share的实现
	unsigned long from;
	unsigned long to;
	unsigned long from_page;
	unsigned long to_page;
	unsigned long phys_addr;
	unsigned long page;
	unsigned long tmp;
	unsigned long vm_address=m1->vm_start;
	while(vm_address<m1->vm_end){
		from_page = to_page = ((vm_address>>20)&0xffc);//逻辑的页目录项偏移
		from_page +=((current->start_code>>20)&0xffc);//该进程目录项地址 
		//from处是否存在页目录项 否则进行申请
		from = *(unsigned long *) from_page;
		from &=0xfffff000;
		from_page = from +((vm_address>>10)&0xffc);//页表项指针
		phys_addr = *(unsigned long *) from_page;//页表项内容
		if(!(page = get_free_page())){
			printk("no free page\n");
			return -1;
		}
	/*	phys_addr = page |0x7;
		mem_map[(page-LOW_MEM)>>12]++;*/
		/*if(!(*(unsigned long *) from_page & 0x1)){
			if(page = get_free_page())
				phys_addr = page |0x7,mem_map[(page-LOW_MEM)>>12]++;
			else
				oom();
		}*/
		put_page(page,vm_address);
		//对页面分配权限
		*(unsigned long *)from_page &= (prot&PROT_WRITE)?0xffffffff:0xfffffffd;
		//对flags进行处理,重点处理的是MAP_SHARE,私有的话不需要进行多余的处理
		//需要将所有进程共享同一页面
		if(flags&MAP_SHARED){
			struct task_struct ** task;
			for (task = &LAST_TASK ; task>&FIRST_TASK;--task){
				if (!*task)
					continue;
				else if (current == *task)
					continue;
				else if(!try_to_share(vm_address,*task))
					printk("current pid %d cann't share memory\n",(*task)->pid);
			}
			
		}
		vm_address += PAGE_SIZE; 
	}
	char *p1=(char *)buf;
	mem_read(fd,off,p1,size);
	/*if (!(block = dir->i_zone[0]))
		return NULL;
	if (!(bh = bread(dir->i_dev,block)))
		return NULL;
	char *s = (char *) bh->b_data;
	char *p1=(char *)s;
	char *p2=(char *)buf;
	while(len--)
		put_fs_byte(*(p1++),p2++);*/
	return buf;
}
/*取消映射
取消映射分为以下几步：
	1.从当前进程的虚拟地址结构出发，找到要取消映射的虚拟地址
	2.判断权限 若是具有可写权限 需要将内容写入到对应的文件之中 可参考sys_wirte的实现
	3.判断该虚拟地址是否是所有共享
	4.清空该页面的内容
	5.取消该进程/所有进程的读写权限
要注意的是：
	该结构是一个单向链表 所以链表删除的时候需要谨慎一些
*/
//取消进程p的共享 与try_share很类似 只是少了几步
static int cancle_share(unsigned long address, struct task_struct * p)
{
	unsigned long from;
	unsigned long from_page;	
	unsigned long phys_addr;
	from_page = ((address>>20) & 0xffc);
	from_page += ((p->start_code>>20) & 0xffc);
/* is there a page-directory at from? */
	from = *(unsigned long *) from_page;
	from &= 0xfffff000;
	from_page = from + ((address>>10) & 0xffc);
	phys_addr = *(unsigned long *) from_page;
/* is the page clean and present? */
	phys_addr &= 0xfffff000;
	if (phys_addr >= HIGH_MEMORY || phys_addr < LOW_MEM)
		return 0;
/* share them: write-protect */
	*(unsigned long *) from_page &= ~1;
	phys_addr -= LOW_MEM;
	phys_addr >>= 12;
	mem_map[phys_addr]--;
	return 1;
}
//如果页面具有写权限，很可能被修改过，所以需要将映射页面内容写入文件
//dir是映射文件i节点,off是从文件那个地方开始写,buf是要写到文件的内容,size是写多少字节
int mmap_wirte(int fd,off_t pos,char *buf,int count){
	struct file * file;
	struct m_inode * inode;
	if (fd>=NR_OPEN || count <0 || !(file=current->filp[fd]))
		return -EINVAL;
	if (!count)
		return 0;
	inode=file->f_inode;
	file->f_pos = pos;
	if (inode->i_pipe)
		return (file->f_mode&2)?write_pipe(inode,buf,count):-EIO;
	if (S_ISCHR(inode->i_mode))
		return rw_char(WRITE,inode->i_zone[0],buf,count,&file->f_pos);
	if (S_ISBLK(inode->i_mode))
		return block_write(inode->i_zone[0],&file->f_pos,buf,count);
	if (S_ISREG(inode->i_mode))
		return file_write(inode,file,buf,count);
	printk("(Write)inode->i_mode=%06o\n\r",inode->i_mode);
	return -EINVAL;
}
//将page页面的内容保存到对应的文件
int sys_munmap(void *address1,size_t len){
	struct vmarea_struct *m1 = current->mmap;
	struct vmarea_struct *pre = NULL;
	//寻找对应的虚拟地址结构
	if(!m1){
		printk("No vm_aread struct address is NULL \n");
		return 0;
	}
	//b遍历所有的结构来进行U型你找
	for(m1;m1;m1=m1->next)
		if(m1->vm_start==address1){
			pre = m1;
			break;
		}
	//需要判断一下是否是真的找到了
	if(m1->vm_start!=address1){
		printk("address is wrong \n");
		return 0;
	}
	//判断权限
	int j = 0;
	char *buf = (char *)address1;
	char *s1 = (char *)address1;
	if(m1->mode&PROT_WRITE){
		if(!(mmap_wirte(m1->fd,m1->off,buf,m1->size))){
			printk("wirte is wrong \n");
			return -1;
		}
	}
	//进行页面的删除 其实很简单 只需要pre只能m1->next即可
	pre->next = m1->next;
	//首先释放掉当前页面
	unsigned long from;
	unsigned long to;
	unsigned long from_page;
	unsigned long to_page;
	unsigned long phys_addr;
	unsigned long tpage;
	unsigned long address=m1->vm_start;
	if(len%PAGE_SIZE)	len = len/4096*4096+PAGE_SIZE;
	while(address<len+m1->vm_start&&address<m1->vm_end){
		from_page = to_page = ((address>>20)&0xffc);//逻辑的页目录项偏移
		from_page +=((current->start_code>>20)&0xffc);//该进程目录项地址
		from = *(unsigned long *) from_page;
		from &=0xfffff000;
		from_page = from +((address>>10)&0xffc);//页表项指针
		phys_addr = *(unsigned long *) from_page;//页表项内容 
		//主要是针对页表项进行修改
		*(unsigned long *)from_page &= ~1;
		address += PAGE_SIZE;
	}
	//接下来对共享进行处理
	//如果是共享的话
	//当前进程已经处理过了 着重处理的是对应页面的进程
	address = m1->vm_start;
	if(m1->flag&MAP_SHARED){
		//其实与mmap设置共享内存类似,如何设置出来的就如何取消掉
		//仍旧是参照try_to_share的实现
		struct task_struct **p;
		for (p = &LAST_TASK ; p > &FIRST_TASK ; --p)
		{
			//当前进程已经处理过了 就没必要再处理了
			if(current == *p)
				continue;
			cancle_share(address,*p);
		}
	}
	//free(m1);//释放掉结构体占用的内存
	return 0;
}