init.c

linux 内核源代码

#ifdef CONFIG_VIRTUAL_MEM_MAP
int vmemmap_find_next_valid_pfn(int node, int i)
{
	unsigned long end_address, hole_next_pfn;
	unsigned long stop_address;
	pg_data_t *pgdat = NODE_DATA(node);

	end_address = (unsigned long) &vmem_map[pgdat->node_start_pfn + i];
	end_address = PAGE_ALIGN(end_address);

	stop_address = (unsigned long) &vmem_map[
		pgdat->node_start_pfn + pgdat->node_spanned_pages];

	do {
		pgd_t *pgd;
		pud_t *pud;
		pmd_t *pmd;
		pte_t *pte;

		pgd = pgd_offset_k(end_address);
		if (pgd_none(*pgd)) {
			end_address += PGDIR_SIZE;
			continue;
		}

		pud = pud_offset(pgd, end_address);
		if (pud_none(*pud)) {
			end_address += PUD_SIZE;
			continue;
		}

		pmd = pmd_offset(pud, end_address);
		if (pmd_none(*pmd)) {
			end_address += PMD_SIZE;
			continue;
		}

		pte = pte_offset_kernel(pmd, end_address);
retry_pte:
		if (pte_none(*pte)) {
			end_address += PAGE_SIZE;
			pte++;
			if ((end_address < stop_address) &&
			    (end_address != ALIGN(end_address, 1UL << PMD_SHIFT)))
				goto retry_pte;
			continue;
		}
		/* Found next valid vmem_map page */
		break;
	} while (end_address < stop_address);

	end_address = min(end_address, stop_address);
	end_address = end_address - (unsigned long) vmem_map + sizeof(struct page) - 1;
	hole_next_pfn = end_address / sizeof(struct page);
	return hole_next_pfn - pgdat->node_start_pfn;
}

int __init
create_mem_map_page_table (u64 start, u64 end, void *arg)
{
	unsigned long address, start_page, end_page;
	struct page *map_start, *map_end;
	int node;
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	map_start = vmem_map + (__pa(start) >> PAGE_SHIFT);
	map_end   = vmem_map + (__pa(end) >> PAGE_SHIFT);

	start_page = (unsigned long) map_start & PAGE_MASK;
	end_page = PAGE_ALIGN((unsigned long) map_end);
	node = paddr_to_nid(__pa(start));

	for (address = start_page; address < end_page; address += PAGE_SIZE) {
		pgd = pgd_offset_k(address);
		if (pgd_none(*pgd))
			pgd_populate(&init_mm, pgd, alloc_bootmem_pages_node(NODE_DATA(node), PAGE_SIZE));
		pud = pud_offset(pgd, address);

		if (pud_none(*pud))
			pud_populate(&init_mm, pud, alloc_bootmem_pages_node(NODE_DATA(node), PAGE_SIZE));
		pmd = pmd_offset(pud, address);

		if (pmd_none(*pmd))
			pmd_populate_kernel(&init_mm, pmd, alloc_bootmem_pages_node(NODE_DATA(node), PAGE_SIZE));
		pte = pte_offset_kernel(pmd, address);

		if (pte_none(*pte))
			set_pte(pte, pfn_pte(__pa(alloc_bootmem_pages_node(NODE_DATA(node), PAGE_SIZE)) >> PAGE_SHIFT,
					     PAGE_KERNEL));
	}
	return 0;
}

struct memmap_init_callback_data {
	struct page *start;
	struct page *end;
	int nid;
	unsigned long zone;
};

static int __meminit
virtual_memmap_init (u64 start, u64 end, void *arg)
{
	struct memmap_init_callback_data *args;
	struct page *map_start, *map_end;

	args = (struct memmap_init_callback_data *) arg;
	map_start = vmem_map + (__pa(start) >> PAGE_SHIFT);
	map_end   = vmem_map + (__pa(end) >> PAGE_SHIFT);

	if (map_start < args->start)
		map_start = args->start;
	if (map_end > args->end)
		map_end = args->end;

	/*
	 * We have to initialize "out of bounds" struct page elements that fit completely
	 * on the same pages that were allocated for the "in bounds" elements because they
	 * may be referenced later (and found to be "reserved").
	 */
	map_start -= ((unsigned long) map_start & (PAGE_SIZE - 1)) / sizeof(struct page);
	map_end += ((PAGE_ALIGN((unsigned long) map_end) - (unsigned long) map_end)
		    / sizeof(struct page));

	if (map_start < map_end)
		memmap_init_zone((unsigned long)(map_end - map_start),
				 args->nid, args->zone, page_to_pfn(map_start),
				 MEMMAP_EARLY);
	return 0;
}

void __meminit
memmap_init (unsigned long size, int nid, unsigned long zone,
	     unsigned long start_pfn)
{
	if (!vmem_map)
		memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY);
	else {
		struct page *start;
		struct memmap_init_callback_data args;

		start = pfn_to_page(start_pfn);
		args.start = start;
		args.end = start + size;
		args.nid = nid;
		args.zone = zone;

		efi_memmap_walk(virtual_memmap_init, &args);
	}
}

int
ia64_pfn_valid (unsigned long pfn)
{
	char byte;
	struct page *pg = pfn_to_page(pfn);

	return     (__get_user(byte, (char __user *) pg) == 0)
		&& ((((u64)pg & PAGE_MASK) == (((u64)(pg + 1) - 1) & PAGE_MASK))
			|| (__get_user(byte, (char __user *) (pg + 1) - 1) == 0));
}
EXPORT_SYMBOL(ia64_pfn_valid);

int __init
find_largest_hole (u64 start, u64 end, void *arg)
{
	u64 *max_gap = arg;

	static u64 last_end = PAGE_OFFSET;

	/* NOTE: this algorithm assumes efi memmap table is ordered */

	if (*max_gap < (start - last_end))
		*max_gap = start - last_end;
	last_end = end;
	return 0;
}

#endif /* CONFIG_VIRTUAL_MEM_MAP */

int __init
register_active_ranges(u64 start, u64 end, void *arg)
{
	int nid = paddr_to_nid(__pa(start));

	if (nid < 0)
		nid = 0;
#ifdef CONFIG_KEXEC
	if (start > crashk_res.start && start < crashk_res.end)
		start = crashk_res.end;
	if (end > crashk_res.start && end < crashk_res.end)
		end = crashk_res.start;
#endif

	if (start < end)
		add_active_range(nid, __pa(start) >> PAGE_SHIFT,
			__pa(end) >> PAGE_SHIFT);
	return 0;
}

static int __init
count_reserved_pages (u64 start, u64 end, void *arg)
{
	unsigned long num_reserved = 0;
	unsigned long *count = arg;

	for (; start < end; start += PAGE_SIZE)
		if (PageReserved(virt_to_page(start)))
			++num_reserved;
	*count += num_reserved;
	return 0;
}

int
find_max_min_low_pfn (unsigned long start, unsigned long end, void *arg)
{
	unsigned long pfn_start, pfn_end;
#ifdef CONFIG_FLATMEM
	pfn_start = (PAGE_ALIGN(__pa(start))) >> PAGE_SHIFT;
	pfn_end = (PAGE_ALIGN(__pa(end - 1))) >> PAGE_SHIFT;
#else
	pfn_start = GRANULEROUNDDOWN(__pa(start)) >> PAGE_SHIFT;
	pfn_end = GRANULEROUNDUP(__pa(end - 1)) >> PAGE_SHIFT;
#endif
	min_low_pfn = min(min_low_pfn, pfn_start);
	max_low_pfn = max(max_low_pfn, pfn_end);
	return 0;
}

/*
 * Boot command-line option "nolwsys" can be used to disable the use of any light-weight
 * system call handler.  When this option is in effect, all fsyscalls will end up bubbling
 * down into the kernel and calling the normal (heavy-weight) syscall handler.  This is
 * useful for performance testing, but conceivably could also come in handy for debugging
 * purposes.
 */

static int nolwsys __initdata;

static int __init
nolwsys_setup (char *s)
{
	nolwsys = 1;
	return 1;
}

__setup("nolwsys", nolwsys_setup);

void __init
mem_init (void)
{
	long reserved_pages, codesize, datasize, initsize;
	pg_data_t *pgdat;
	int i;
	static struct kcore_list kcore_mem, kcore_vmem, kcore_kernel;

	BUG_ON(PTRS_PER_PGD * sizeof(pgd_t) != PAGE_SIZE);
	BUG_ON(PTRS_PER_PMD * sizeof(pmd_t) != PAGE_SIZE);
	BUG_ON(PTRS_PER_PTE * sizeof(pte_t) != PAGE_SIZE);

#ifdef CONFIG_PCI
	/*
	 * This needs to be called _after_ the command line has been parsed but _before_
	 * any drivers that may need the PCI DMA interface are initialized or bootmem has
	 * been freed.
	 */
	platform_dma_init();
#endif

#ifdef CONFIG_FLATMEM
	if (!mem_map)
		BUG();
	max_mapnr = max_low_pfn;
#endif

	high_memory = __va(max_low_pfn * PAGE_SIZE);

	kclist_add(&kcore_mem, __va(0), max_low_pfn * PAGE_SIZE);
	kclist_add(&kcore_vmem, (void *)VMALLOC_START, VMALLOC_END-VMALLOC_START);
	kclist_add(&kcore_kernel, _stext, _end - _stext);

	for_each_online_pgdat(pgdat)
		if (pgdat->bdata->node_bootmem_map)
			totalram_pages += free_all_bootmem_node(pgdat);

	reserved_pages = 0;
	efi_memmap_walk(count_reserved_pages, &reserved_pages);

	codesize =  (unsigned long) _etext - (unsigned long) _stext;
	datasize =  (unsigned long) _edata - (unsigned long) _etext;
	initsize =  (unsigned long) __init_end - (unsigned long) __init_begin;

	printk(KERN_INFO "Memory: %luk/%luk available (%luk code, %luk reserved, "
	       "%luk data, %luk init)\n", (unsigned long) nr_free_pages() << (PAGE_SHIFT - 10),
	       num_physpages << (PAGE_SHIFT - 10), codesize >> 10,
	       reserved_pages << (PAGE_SHIFT - 10), datasize >> 10, initsize >> 10);


	/*
	 * For fsyscall entrpoints with no light-weight handler, use the ordinary
	 * (heavy-weight) handler, but mark it by setting bit 0, so the fsyscall entry
	 * code can tell them apart.
	 */
	for (i = 0; i < NR_syscalls; ++i) {
		extern unsigned long fsyscall_table[NR_syscalls];
		extern unsigned long sys_call_table[NR_syscalls];

		if (!fsyscall_table[i] || nolwsys)
			fsyscall_table[i] = sys_call_table[i] | 1;
	}
	setup_gate();

#ifdef CONFIG_IA32_SUPPORT
	ia32_mem_init();
#endif
}

#ifdef CONFIG_MEMORY_HOTPLUG
void online_page(struct page *page)
{
	ClearPageReserved(page);
	init_page_count(page);
	__free_page(page);
	totalram_pages++;
	num_physpages++;
}

int arch_add_memory(int nid, u64 start, u64 size)
{
	pg_data_t *pgdat;
	struct zone *zone;
	unsigned long start_pfn = start >> PAGE_SHIFT;
	unsigned long nr_pages = size >> PAGE_SHIFT;
	int ret;

	pgdat = NODE_DATA(nid);

	zone = pgdat->node_zones + ZONE_NORMAL;
	ret = __add_pages(zone, start_pfn, nr_pages);

	if (ret)
		printk("%s: Problem encountered in __add_pages() as ret=%d\n",
		       __FUNCTION__,  ret);

	return ret;
}
#ifdef CONFIG_MEMORY_HOTREMOVE
int remove_memory(u64 start, u64 size)
{
	unsigned long start_pfn, end_pfn;
	unsigned long timeout = 120 * HZ;
	int ret;
	start_pfn = start >> PAGE_SHIFT;
	end_pfn = start_pfn + (size >> PAGE_SHIFT);
	ret = offline_pages(start_pfn, end_pfn, timeout);
	if (ret)
		goto out;
	/* we can free mem_map at this point */
out:
	return ret;
}
EXPORT_SYMBOL_GPL(remove_memory);
#endif /* CONFIG_MEMORY_HOTREMOVE */
#endif