e820获取物理内存分布

什么是 e820？

e820 是 BIOS 用来报告物理内存分布的一个基础设施。因此，e820 是一个很重要的东西，它报告了那些物理内存范围是可用的，那些范围是预留的。

e820 流程分析

linux 获取内存分布从 machine_specific_memory_setup 函数开始，这个函数在多个文件里都有定义，此处我们只看 include/asm-i386/mach-default/setup_arch_post.h 文件中的定义，函数的定义如下：

static char * __init machine_specific_memory_setup(void)
{
	char *who;
 
 
	who = "BIOS-e820";
 
	/*
	 * Try to copy the BIOS-supplied E820-map.
	 *
	 * Otherwise fake a memory map; one section from 0k->640k,
	 * the next section from 1mb->appropriate_mem_k
	 */
	sanitize_e820_map(E820_MAP, &E820_MAP_NR);
	if (copy_e820_map(E820_MAP, E820_MAP_NR) < 0) {
		unsigned long mem_size;
 
		/* compare results from other methods and take the greater */
		if (ALT_MEM_K < EXT_MEM_K) {
			mem_size = EXT_MEM_K;
			who = "BIOS-88";
		} else {
			mem_size = ALT_MEM_K;
			who = "BIOS-e801";
		}
 
		e820.nr_map = 0;
		add_memory_region(0, LOWMEMSIZE(), E820_RAM);
		add_memory_region(HIGH_MEMORY, mem_size << 10, E820_RAM);
  	}
	return who;
}

函数内部调用了 sanitize_e820_map 这个函数，这个函数很重要，它对 BIOS 报告的内存分布进行了一定的处理。调用函数时传递了 E820_MAP 和 E820_MAP_NR 这两个参数，这两个参数定义在 include/asm-i386/setup.h，定义如下：

#define E820_MAP_NR (*(char*) (PARAM+E820NR))
#define E820_MAP    ((struct e820entry *) (PARAM+E820MAP))

其中 PARAM 的定义如下：

extern unsigned char boot_params[PARAM_SIZE];
 
#define PARAM	(boot_params)

可以看到，其实 PARAM 就是一个字节数组，这个数组的大小为 PARAM_SIZE ，它的值为4096。
但是 boot_params 本身也是一个声明，它的定义在哪里呢？它定义在 asm/i386/kernel/setup.c 中，定义如下：

unsigned char __initdata boot_params[PARAM_SIZE];

其实，这里已经很明显了，E820NR 和 E820MAP 就是对应参数的偏移量，一个是 e820 映射的数量在这个数组中的偏移量，另一个就是 e820entry 开始的偏移量，他们的定义如下：

#define E820MAP	0x2d0		/* our map */
#define E820MAX	128		/* number of entries in E820MAP */
#define E820NR	0x1e8		/* # entries in E820MAP */

这样，传递给 sanitize_e820_map 函数的两个实参分别是 e820entry 数组的其实地址和存有这个数组的元素数量的内存地址。

另外，boot_params 这个数组的填充在 arch/i386/kernel/head.S 中，初始化代码如下：

/*
 * Copy bootup parameters out of the way.
 * Note: %esi still has the pointer to the real-mode data.
 */
movl $boot_params,%edi
movl $(PARAM_SIZE/4),%ecx
cld
rep
movsl
movl boot_params+NEW_CL_POINTER,%esi

处理 BIOS 报告的内存区域可能存在重叠的问题

sanitize_e820_map 函数定义在 arch/i386/kernel/setup.c 中，定义如下：

 
/*
 * Sanitize the BIOS e820 map.
 *
 * Some e820 responses include overlapping entries.  The following 
 * replaces the original e820 map with a new one, removing overlaps.
 *
 */
struct change_member {
	struct e820entry *pbios; /* pointer to original bios entry */
	unsigned long long addr; /* address for this change point */
};
static struct change_member change_point_list[2*E820MAX] __initdata;
static struct change_member *change_point[2*E820MAX] __initdata;
static struct e820entry *overlap_list[E820MAX] __initdata;
static struct e820entry new_bios[E820MAX] __initdata;
 
static int __init sanitize_e820_map(struct e820entry * biosmap, char * pnr_map)
{
	struct change_member *change_tmp;
	unsigned long current_type, last_type;
	unsigned long long last_addr;
	int chgidx, still_changing;
	int overlap_entries;
	int new_bios_entry;
	int old_nr, new_nr, chg_nr;
	int i;
 
	/*
		Visually we're performing the following (1,2,3,4 = memory types)...
 
		Sample memory map (w/overlaps):
		   ____22__________________
		   ______________________4_
		   ____1111________________
		   _44_____________________
		   11111111________________
		   ____________________33__
		   ___________44___________
		   __________33333_________
		   ______________22________
		   ___________________2222_
		   _________111111111______
		   _____________________11_
		   _________________4______
 
		Sanitized equivalent (no overlap):
		   1_______________________
		   _44_____________________
		   ___1____________________
		   ____22__________________
		   ______11________________
		   _________1______________
		   __________3_____________
		   ___________44___________
		   _____________33_________
		   _______________2________
		   ________________1_______
		   _________________4______
		   ___________________2____
		   ____________________33__
		   ______________________4_
	*/
 
	/* if there's only one memory region, don't bother */
	if (*pnr_map < 2)
		return -1;
 
	old_nr = *pnr_map;
 
	/* bail out if we find any unreasonable addresses in bios map */
	for (i=0; i<old_nr; i++)
		if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr)
			return -1;
 
	/* create pointers for initial change-point information (for sorting) */
	for (i=0; i < 2*old_nr; i++)
		change_point[i] = &change_point_list[i];
 
	/* record all known change-points (starting and ending addresses),
	   omitting those that are for empty memory regions */
	chgidx = 0;
	for (i=0; i < old_nr; i++)	{
		if (biosmap[i].size != 0) {
			change_point[chgidx]->addr = biosmap[i].addr;
			change_point[chgidx++]->pbios = &biosmap[i];
			change_point[chgidx]->addr = biosmap[i].addr + biosmap[i].size;
			change_point[chgidx++]->pbios = &biosmap[i];
		}
	}
	chg_nr = chgidx;    	/* true number of change-points */
 
	/* sort change-point list by memory addresses (low -> high) */
	still_changing = 1;
	while (still_changing)	{
		still_changing = 0;
		for (i=1; i < chg_nr; i++)  {
			/* if <current_addr> > <last_addr>, swap */
			/* or, if current=<start_addr> & last=<end_addr>, swap */
			if ((change_point[i]->addr < change_point[i-1]->addr) ||
				((change_point[i]->addr == change_point[i-1]->addr) &&
				 (change_point[i]->addr == change_point[i]->pbios->addr) &&
				 (change_point[i-1]->addr != change_point[i-1]->pbios->addr))
			   )
			{
				change_tmp = change_point[i];
				change_point[i] = change_point[i-1];
				change_point[i-1] = change_tmp;
				still_changing=1;
			}
		}
	}
 
	/* create a new bios memory map, removing overlaps */
	overlap_entries=0;	 /* number of entries in the overlap table */
	new_bios_entry=0;	 /* index for creating new bios map entries */
	last_type = 0;		 /* start with undefined memory type */
	last_addr = 0;		 /* start with 0 as last starting address */
	/* loop through change-points, determining affect on the new bios map */
	for (chgidx=0; chgidx < chg_nr; chgidx++)
	{
		/* keep track of all overlapping bios entries */
		if (change_point[chgidx]->addr == change_point[chgidx]->pbios->addr)
		{
			/* add map entry to overlap list (> 1 entry implies an overlap) */
			overlap_list[overlap_entries++]=change_point[chgidx]->pbios;
		}
		else
		{
			/* remove entry from list (order independent, so swap with last) */
			for (i=0; i<overlap_entries; i++)
			{
				if (overlap_list[i] == change_point[chgidx]->pbios)
					overlap_list[i] = overlap_list[overlap_entries-1];
			}
			overlap_entries--;
		}
		/* if there are overlapping entries, decide which "type" to use */
		/* (larger value takes precedence -- 1=usable, 2,3,4,4+=unusable) */
		current_type = 0;
		for (i=0; i<overlap_entries; i++)
			if (overlap_list[i]->type > current_type)
				current_type = overlap_list[i]->type;
		/* continue building up new bios map based on this information */
		if (current_type != last_type)	{
			if (last_type != 0)	 {
				new_bios[new_bios_entry].size =
					change_point[chgidx]->addr - last_addr;
				/* move forward only if the new size was non-zero */
				if (new_bios[new_bios_entry].size != 0)
					if (++new_bios_entry >= E820MAX)
						break; 	/* no more space left for new bios entries */
			}
			if (current_type != 0)	{
				new_bios[new_bios_entry].addr = change_point[chgidx]->addr;
				new_bios[new_bios_entry].type = current_type;
				last_addr=change_point[chgidx]->addr;
			}
			last_type = current_type;
		}
	}
	new_nr = new_bios_entry;   /* retain count for new bios entries */
 
	/* copy new bios mapping into original location */
	memcpy(biosmap, new_bios, new_nr*sizeof(struct e820entry));
	*pnr_map = new_nr;
 
	return 0;
}

sanitize_e820_map 函数的作用就是解决 BIOS 报告的内存区域存在重叠的问题，得到一个新的内存区域分布，然后分别更新分布和数量。

拷贝内存区域分布

处理完分布之后，就开始调用 copy_e820_map 函数，从这个函数的名称就可以看出来，这个函数的作用是拷贝内存区域分布，这个函数的定义如下：

/*
 * Copy the BIOS e820 map into a safe place.
 *
 * Sanity-check it while we're at it..
 *
 * If we're lucky and live on a modern system, the setup code
 * will have given us a memory map that we can use to properly
 * set up memory.  If we aren't, we'll fake a memory map.
 *
 * We check to see that the memory map contains at least 2 elements
 * before we'll use it, because the detection code in setup.S may
 * not be perfect and most every PC known to man has two memory
 * regions: one from 0 to 640k, and one from 1mb up.  (The IBM
 * thinkpad 560x, for example, does not cooperate with the memory
 * detection code.)
 */
static int __init copy_e820_map(struct e820entry * biosmap, int nr_map)
{
	/* Only one memory region (or negative)? Ignore it */
	if (nr_map < 2)
		return -1;
 
	do {
		unsigned long long start = biosmap->addr;
		unsigned long long size = biosmap->size;
		unsigned long long end = start + size;
		unsigned long type = biosmap->type;
 
		/* Overflow in 64 bits? Ignore the memory map. */
		if (start > end)
			return -1;
 
		/*
		 * Some BIOSes claim RAM in the 640k - 1M region.
		 * Not right. Fix it up.
		 */
		if (type == E820_RAM) {
			if (start < 0x100000ULL && end > 0xA0000ULL) {
				if (start < 0xA0000ULL)
					add_memory_region(start, 0xA0000ULL-start, type);
				if (end <= 0x100000ULL)
					continue;
				start = 0x100000ULL;
				size = end - start;
			}
		}
		add_memory_region(start, size, type);
	} while (biosmap++,--nr_map);
	return 0;
}

这个函数的在拷贝之前会对区域类型为 E820_RAM 的分布做一个特殊的处理，如果起始地址小于 0x10000 且结束地址大于 0xA0000，换句话说，如果内存区域和 640k - 1M 这部分区域存在重叠，那么必须得做一些特殊的处理。如果起始地址小于0xA0000，那么只添加 start-0xA0000 这段区域。如果结束地址小于等于0x100000，那么直接跳过此次循环，因为不需要在添加区域了，如果没有跳过此次循环，则说明 end 大于0x10000，那么就添加 0x100000-end 这段内存区域。

添加内存区域

函数内部调用了 add_memory_region 函数，这个函数也定义在 arch/i386/kernel/setup.c 中，它的定义如下：

static void __init add_memory_region(unsigned long long start,
                                  unsigned long long size, int type)
{
	int x;
 
	if (!efi_enabled) {
       		x = e820.nr_map;
 
		if (x == E820MAX) {
		    printk(KERN_ERR "Ooops! Too many entries in the memory map!\n");
		    return;
		}
 
		e820.map[x].addr = start;
		e820.map[x].size = size;
		e820.map[x].type = type;
		e820.nr_map++;
	}
} /* add_memory_region */

这个函数很简单，只是简单的将数据填充到 e820 的 map 数组中。

结尾

至此，e820 的整体流程已经全部分析完了，但是里面还存在一些细节，没有详细展开说明。不过本文的重点是讲解 e820 的整个流程，所以就不再详细说明了。