物理内存探测

 

              在内核建立相应的内存管理区之前，先要进行物理内存的探测，获取相关的内存信息。对于X86架构，内核在void main()中调用detect_memory()来进行物理内存的探测。

void main(void)
{        
	...
	...
         /* Detect memory layout */
	detect_memory();
	...
	...
}

detect_memory()中分别通过调用0xE820H,0xE801H和0x88H从BIOS中获取内存布局和相关的信息。

int detect_memory(void)
{
	int err = -1;

	if (detect_memory_e820() > 0)
		err = 0;

	if (!detect_memory_e801())
		err = 0;

	if (!detect_memory_88())
		err = 0;

	return err;
}

这三个函数都通过int 0x15触发BIOS中断来获取相关信息

 

下面我们着重分析detect_memory_e820().在此之前先了解一个关键的数据结构--struct e820entry.该结构用来保存一个物理内存段的地址信息以及类型。

struct e820entry {
	__u64 addr;	/* start of memory segment */
	__u64 size;	/* size of memory segment */
	__u32 type;	/* type of memory segment */
} __attribute__((packed));

addr:该内存段的起始地址

size:该内存段的大小

type:该内存段的类型，可分为Usable (normal) RAM，Reserved - unusable，ACPI reclaimable memory，ACPI NVS memory，Area containing bad memory，要获取所有的内存段的信息，detect_memory_e820()通过一个do_while循环来不断触发int 0x15中断来获取每个内存段的信息，并且将这些信息保存在一个struct e820entry类型的数组中，即boot_params.e820_map，下面是相关代码

static int detect_memory_e820(void)
{
	int count = 0;
	struct biosregs ireg, oreg;
	struct e820entry *desc = boot_params.e820_map;
	static struct e820entry buf; /* static so it is zeroed */

	initregs(&ireg);
	ireg.ax  = 0xe820;
	ireg.cx  = sizeof buf;
	ireg.edx = SMAP;
	ireg.di  = (size_t)&buf;

	/*
	 * Note: at least one BIOS is known which assumes that the
	 * buffer pointed to by one e820 call is the same one as
	 * the previous call, and only changes modified fields.  Therefore,
	 * we use a temporary buffer and copy the results entry by entry.
	 *
	 * This routine deliberately does not try to account for
	 * ACPI 3+ extended attributes.  This is because there are
	 * BIOSes in the field which report zero for the valid bit for
	 * all ranges, and we don't currently make any use of the
	 * other attribute bits.  Revisit this if we see the extended
	 * attribute bits deployed in a meaningful way in the future.
	 */

	do {
		intcall(0x15, &ireg, &oreg); /*触发0x15中断*/
		ireg.ebx = oreg.ebx; /* for next iteration... */

		/* BIOSes which terminate the chain with CF = 1 as opposed
		   to %ebx = 0 don't always report the SMAP signature on
		   the final, failing, probe. */
		if (oreg.eflags & X86_EFLAGS_CF)
			break;

		/* Some BIOSes stop returning SMAP in the middle of
		   the search loop.  We don't know exactly how the BIOS
		   screwed up the map at that point, we might have a
		   partial map, the full map, or complete garbage, so
		   just return failure. */
		if (oreg.eax != SMAP) {
			count = 0;
			break;
		}

		*desc++ = buf;/*保存获取的内存段信息*/
		count++;      /*获取的内存段数目加1*/
	} while (ireg.ebx && count < ARRAY_SIZE(boot_params.e820_map));

	return boot_params.e820_entries = count;
}

其他两个函数还没弄太明白，只知道是用来获取扩展内存的大小的~其中0x88H获取的内存上限为64M(以1K为单位)，而0xe801可以获取到64M以上的内存(以64K为单位)，它们也将获取的信息保存在boot_params中以供后用。

       在start_kernel()-->setup_arch()中，我们可以看到很多与架构相关的初始化工作，接下来我们选择几个与内存管理相关的关键函数进行分析。

     

void __init setup_arch(char **cmdline_p)
{
	...
	...
	setup_memory_map();
	...
	...	 
	max_pfn = e820_end_of_ram_pfn(); /*找到最大的页框编号*/
	...
	/* max_low_pfn get updated here */
	find_low_pfn_range();/*设定高、低内存的分界线*/
	...
	...	
}

首先来看setup_memory_map().

 

void __init setup_memory_map(void)
{
	char *who;

	who = x86_init.resources.memory_setup();
	memcpy(&e820_saved, &e820, sizeof(struct e820map));
	printk(KERN_INFO "BIOS-provided physical RAM map:\n");
	e820_print_map(who);
}

该函数中，通过结构体x86_init_resources调用memory_setup(),在x86_init.c中，我们可以看到该函数指针的初始化

struct x86_init_ops x86_init __initdata = {

	.resources = {
		.probe_roms		= x86_init_noop,
		.reserve_resources	= reserve_standard_io_resources,
		.memory_setup		= default_machine_specific_memory_setup,
	},

跟踪找到default_machine_specific_memory_setup(),

char *__init default_machine_specific_memory_setup(void)
{
	char *who = "BIOS-e820";
	u32 new_nr;
	/*
	 * 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
	 */
	new_nr = boot_params.e820_entries;
	sanitize_e820_map(boot_params.e820_map,  /*消除重叠的内存段*/
			ARRAY_SIZE(boot_params.e820_map),
			&new_nr);
	boot_params.e820_entries = new_nr;
	/*将内存布局的信息从boot_params.e820_map拷贝到struct e820map e820*/
	if (append_e820_map(boot_params.e820_map, boot_params.e820_entries)
	  < 0) {
		u64 mem_size;

		/* compare results from other methods and take the greater */
		if (boot_params.alt_mem_k
		    < boot_params.screen_info.ext_mem_k) {
			mem_size = boot_params.screen_info.ext_mem_k;
			who = "BIOS-88";
		} else {
			mem_size = boot_params.alt_mem_k;
			who = "BIOS-e801";
		}

		e820.nr_map = 0;
		e820_add_region(0, LOWMEMSIZE(), E820_RAM);
		e820_add_region(HIGH_MEMORY, mem_size << 10, E820_RAM);
	}

	/* In case someone cares... */
	return who;
}

可以看到该函数主要完成两个功能：

1.消除内存段的重叠部分

2.将内存布局信息从boot_params.e820_map拷贝到e820中

跟踪append_e820_map()-->__append_e820_map()

static int __init __append_e820_map(struct e820entry *biosmap, int nr_map)
{
	while (nr_map) {
		u64 start = biosmap->addr;
		u64 size = biosmap->size;
		u64 end = start + size;
		u32 type = biosmap->type;

		/* Overflow in 64 bits? Ignore the memory map. */
		if (start > end)
			return -1;

		e820_add_region(start, size, type);

		biosmap++;
		nr_map--;
	}
	return 0;
}

其中传给biosmap的参数为boot_params.e820_map,即内存布局的起始地址，传给nr_map的参数为boot_params.e820_entries，即获取的内存段的数目。在该函数中，对每个段调用e820_add_region,来看看这个函数

void __init e820_add_region(u64 start, u64 size, int type)
{
	__e820_add_region(&e820, start, size, type);
}

 

static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
					 int type)
{
	int x = e820x->nr_map;

	if (x >= ARRAY_SIZE(e820x->map)) {
		printk(KERN_ERR "Ooops! Too many entries in the memory map!\n");
		return;
	}

	e820x->map[x].addr = start;
	e820x->map[x].size = size;
	e820x->map[x].type = type;
	e820x->nr_map++;
}

最终由__e820_add_region()函数将内存段的信息保存到e820的map数组中。

下面再来看看e820_end_of_ram_pfn()，该函数用来遍历所有内存段的页框，找到低端内存的最大页框编号

unsigned long __init e820_end_of_ram_pfn(void)
{
	return e820_end_pfn(MAX_ARCH_PFN, E820_RAM);
}

E820_RAM代表可用内存

MAX_ARCH_PFN的定义如下

#ifdef CONFIG_X86_32
# ifdef CONFIG_X86_PAE
#  define MAX_ARCH_PFN		(1ULL<<(36-PAGE_SHIFT))
# else
#  define MAX_ARCH_PFN		(1ULL<<(32-PAGE_SHIFT))
# endif
#else /* CONFIG_X86_32 */
# define MAX_ARCH_PFN MAXMEM>>PAGE_SHIFT
#endif

 

这里可以看到如果定义了CONFIG_X86_32，那么在没使用PAE的情况下，MAX_ARCH_PFN的值就为4GB内存对应的页框号，而如果定义了则MAX_ARCH_PFN的值为MAXMEM对应的页框号，我们来看MAXMEM的定义：

#define MAXMEM	(VMALLOC_END - PAGE_OFFSET - __VMALLOC_RESERVE)

这里面的宏都和线性地址的最后1GB有关，其中__VANALLOC_RESERVE为128M，下图说明了第4GB的内存划分

结合这个图我们可以得出MAXMEM为一个略小于896M的值（896M-8K-4M-4M），即略小于低端内存的上限，高端内存的起始地址，这样是为了避免某些情况下产生的OOPS。

走得貌似有点远了，再回到e820_end_of_ram_pfn(),跟踪e820_end_pfn(MAX_ARCH_PFN, E820_RAM)：

static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
{
	int i;
	unsigned long last_pfn = 0;
	unsigned long max_arch_pfn = MAX_ARCH_PFN;

	for (i = 0; i < e820.nr_map; i++) {  /*循环遍历内存布局数组*/
		struct e820entry *ei = &e820.map[i];
		unsigned long start_pfn;
		unsigned long end_pfn;

		if (ei->type != type)
			continue;

		start_pfn = ei->addr >> PAGE_SHIFT;
		end_pfn = (ei->addr + ei->size) >> PAGE_SHIFT;

		if (start_pfn >= limit_pfn)/*起始地址大于MAX_ARCH_PFN，无视之*/
			continue;
		if (end_pfn > limit_pfn) { /*结束地址大于MAX_ARCH_PFN则直接最大页框编号设为MAX_ARCH_PFN*/
									
			last_pfn = limit_pfn;
			break;
		}
		if (end_pfn > last_pfn)    /*该内存段的末地址大于之前找到的最大页框编号，
								则重置最大页框编号*/
			last_pfn = end_pfn;
	}

	if (last_pfn > max_arch_pfn)
		last_pfn = max_arch_pfn;

	printk(KERN_INFO "last_pfn = %#lx max_arch_pfn = %#lx\n",
			 last_pfn, max_arch_pfn);
	return last_pfn;
}

 

最后分析一个函数，setup_arch()-->find_low_pfn_range().该函数用来划分低端内存和高端内存的界限，也可以说是确定高端内存的起始地址。再看这个函数之前，还得先看几个宏定义

#define MAXMEM_PFN	PFN_DOWN(MAXMEM)
#define PFN_UP(x)	(((x) + PAGE_SIZE-1) >> PAGE_SHIFT)
#define PFN_DOWN(x)	((x) >> PAGE_SHIFT)

可以看出

PFN_DOWN(x)计算出地址值x对应的页框的编号

PFN_UP(x)计算出地址值对应的页框的下一个页框的编号

MAXMEM_PFN为MAXMEM对应的页框编号

再看具体的代码：

void __init find_low_pfn_range(void)
{
	/* it could update max_pfn */

	if (max_pfn <= MAXMEM_PFN)    /*实际物理内存小于等于低端内存896M*/
		lowmem_pfn_init();
	else			      /*实际的物理内存大于896M*/
		highmem_pfn_init();
}

当实际的物理内存小于等于低端内存时，由lowmem_pfn_init()进行分配

void __init lowmem_pfn_init(void)
{
	/* max_low_pfn is 0, we already have early_res support */
	/*将分界线初始化为实际物理内存的最大页框号，由于系统的内存小于896M，
	所以全部内存为低端内存，如需要高端内存，则从中分一部分出来进行分配*/
	max_low_pfn = max_pfn;

	if (highmem_pages == -1)
		highmem_pages = 0;
#ifdef CONFIG_HIGHMEM  /*如果用户定义了HIGHMEM，即需要分配高端内存*/
	if (highmem_pages >= max_pfn) {       /*如果高端内存的页起始地址>=最大页框号，则无法分配*/
		printk(KERN_ERR MSG_HIGHMEM_TOO_BIG,
			pages_to_mb(highmem_pages), pages_to_mb(max_pfn));
		highmem_pages = 0;
	}
	if (highmem_pages) {
		/*这个条件保证低端内存不能小于64M*/
		if (max_low_pfn - highmem_pages < 64*1024*1024/PAGE_SIZE) {
			printk(KERN_ERR MSG_LOWMEM_TOO_SMALL,
				pages_to_mb(highmem_pages));
			highmem_pages = 0;
		}
		max_low_pfn -= highmem_pages; /*设定好低、高端内存的分界线*/
	}
#else
	if (highmem_pages)
		printk(KERN_ERR "ignoring highmem size on non-highmem kernel!\n");
#endif
}



 
当实际的物理内存大于896M，由highmem_pfn_init()进行分配
void __init highmem_pfn_init(void)
{
	max_low_pfn = MAXMEM_PFN; /*设定高端内存和低端内存的分界线*/
	
								
	if (highmem_pages == -1)  /*未设定高端内存的页框数*/
		highmem_pages = max_pfn - MAXMEM_PFN;  /*默认为最大页框数减去MAXMEM_PFN*/

	if (highmem_pages + MAXMEM_PFN < max_pfn)      /*高端内存页框数加上MAXMEM_PFN小于最大页框数*/
		max_pfn = MAXMEM_PFN + highmem_pages;  /*将最大页框数下调到前两者的和*/

	if (highmem_pages + MAXMEM_PFN > max_pfn){     /*申请的高端内存超过范围则不分配*/
		printk(KERN_WARNING MSG_HIGHMEM_TOO_SMALL,
			pages_to_mb(max_pfn - MAXMEM_PFN),
			pages_to_mb(highmem_pages));
		highmem_pages = 0;
	}
#ifndef CONFIG_HIGHMEM
	/* Maximum memory usable is what is directly addressable */
	printk(KERN_WARNING "Warning only %ldMB will be used.\n", MAXMEM>>20);
	if (max_pfn > MAX_NONPAE_PFN)
		printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n");
	else
		printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
	max_pfn = MAXMEM_PFN;
#else /* !CONFIG_HIGHMEM */
#ifndef CONFIG_HIGHMEM64G
	if (max_pfn > MAX_NONPAE_PFN) {
		max_pfn = MAX_NONPAE_PFN;
		printk(KERN_WARNING MSG_HIGHMEM_TRIMMED);
	}
#endif /* !CONFIG_HIGHMEM64G */
#endif /* !CONFIG_HIGHMEM */
}







至此，已将内存探测和高低端内存的划分分析完了，接下来再分析管理区的初始化。