discontig.c

h内核

					__per_cpu_start;
				cpu_data += PERCPU_PAGE_SIZE;
			}
		}
	}

	return 0;
}

/**
 * free_node_bootmem - free bootmem allocator memory for use
 * @start: physical start of range
 * @len: length of range
 * @node: node where this range resides
 *
 * Simply calls the bootmem allocator to free the specified ranged from
 * the given pg_data_t's bdata struct.  After this function has been called
 * for all the entries in the EFI memory map, the bootmem allocator will
 * be ready to service allocation requests.
 */
static int __init free_node_bootmem(unsigned long start, unsigned long len,
				    int node)
{
	free_bootmem_node(mem_data[node].pgdat, start, len);

	return 0;
}

/**
 * reserve_pernode_space - reserve memory for per-node space
 *
 * Reserve the space used by the bootmem maps & per-node space in the boot
 * allocator so that when we actually create the real mem maps we don't
 * use their memory.
 */
static void __init reserve_pernode_space(void)
{
	unsigned long base, size, pages;
	struct bootmem_data *bdp;
	int node;

	for_each_online_node(node) {
		pg_data_t *pdp = mem_data[node].pgdat;

		bdp = pdp->bdata;

		/* First the bootmem_map itself */
		pages = bdp->node_low_pfn - (bdp->node_boot_start>>PAGE_SHIFT);
		size = bootmem_bootmap_pages(pages) << PAGE_SHIFT;
		base = __pa(bdp->node_bootmem_map);
		reserve_bootmem_node(pdp, base, size);

		/* Now the per-node space */
		size = mem_data[node].pernode_size;
		base = __pa(mem_data[node].pernode_addr);
		reserve_bootmem_node(pdp, base, size);
	}
}

/**
 * initialize_pernode_data - fixup per-cpu & per-node pointers
 *
 * Each node's per-node area has a copy of the global pg_data_t list, so
 * we copy that to each node here, as well as setting the per-cpu pointer
 * to the local node data structure.  The active_cpus field of the per-node
 * structure gets setup by the platform_cpu_init() function later.
 */
static void __init initialize_pernode_data(void)
{
	int cpu, node;
	pg_data_t *pgdat_list[MAX_NUMNODES];

	for_each_online_node(node)
		pgdat_list[node] = mem_data[node].pgdat;

	/* Copy the pg_data_t list to each node and init the node field */
	for_each_online_node(node) {
		memcpy(mem_data[node].node_data->pg_data_ptrs, pgdat_list,
		       sizeof(pgdat_list));
	}

	/* Set the node_data pointer for each per-cpu struct */
	for (cpu = 0; cpu < NR_CPUS; cpu++) {
		node = node_cpuid[cpu].nid;
		per_cpu(cpu_info, cpu).node_data = mem_data[node].node_data;
	}
}

/**
 * find_memory - walk the EFI memory map and setup the bootmem allocator
 *
 * Called early in boot to setup the bootmem allocator, and to
 * allocate the per-cpu and per-node structures.
 */
void __init find_memory(void)
{
	int node;

	reserve_memory();

	if (num_online_nodes() == 0) {
		printk(KERN_ERR "node info missing!\n");
		node_set_online(0);
	}

	min_low_pfn = -1;
	max_low_pfn = 0;

	if (num_online_nodes() > 1)
		reassign_cpu_only_nodes();

	/* These actually end up getting called by call_pernode_memory() */
	efi_memmap_walk(filter_rsvd_memory, build_node_maps);
	efi_memmap_walk(filter_rsvd_memory, find_pernode_space);

	/*
	 * Initialize the boot memory maps in reverse order since that's
	 * what the bootmem allocator expects
	 */
	for (node = MAX_NUMNODES - 1; node >= 0; node--) {
		unsigned long pernode, pernodesize, map;
		struct bootmem_data *bdp;

		if (!node_online(node))
			continue;

		bdp = &mem_data[node].bootmem_data;
		pernode = mem_data[node].pernode_addr;
		pernodesize = mem_data[node].pernode_size;
		map = pernode + pernodesize;

		/* Sanity check... */
		if (!pernode)
			panic("pernode space for node %d "
			      "could not be allocated!", node);

		init_bootmem_node(mem_data[node].pgdat,
				  map>>PAGE_SHIFT,
				  bdp->node_boot_start>>PAGE_SHIFT,
				  bdp->node_low_pfn);
	}

	efi_memmap_walk(filter_rsvd_memory, free_node_bootmem);

	reserve_pernode_space();
	initialize_pernode_data();

	max_pfn = max_low_pfn;

	find_initrd();
}

/**
 * per_cpu_init - setup per-cpu variables
 *
 * find_pernode_space() does most of this already, we just need to set
 * local_per_cpu_offset
 */
void *per_cpu_init(void)
{
	int cpu;

	if (smp_processor_id() == 0) {
		for (cpu = 0; cpu < NR_CPUS; cpu++) {
			per_cpu(local_per_cpu_offset, cpu) =
				__per_cpu_offset[cpu];
		}
	}

	return __per_cpu_start + __per_cpu_offset[smp_processor_id()];
}

/**
 * show_mem - give short summary of memory stats
 *
 * Shows a simple page count of reserved and used pages in the system.
 * For discontig machines, it does this on a per-pgdat basis.
 */
void show_mem(void)
{
	int i, total_reserved = 0;
	int total_shared = 0, total_cached = 0;
	unsigned long total_present = 0;
	pg_data_t *pgdat;

	printk("Mem-info:\n");
	show_free_areas();
	printk("Free swap:       %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
	for_each_pgdat(pgdat) {
		unsigned long present = pgdat->node_present_pages;
		int shared = 0, cached = 0, reserved = 0;
		printk("Node ID: %d\n", pgdat->node_id);
		for(i = 0; i < pgdat->node_spanned_pages; i++) {
			if (!ia64_pfn_valid(pgdat->node_start_pfn+i))
				continue;
			if (PageReserved(pgdat->node_mem_map+i))
				reserved++;
			else if (PageSwapCache(pgdat->node_mem_map+i))
				cached++;
			else if (page_count(pgdat->node_mem_map+i))
				shared += page_count(pgdat->node_mem_map+i)-1;
		}
		total_present += present;
		total_reserved += reserved;
		total_cached += cached;
		total_shared += shared;
		printk("\t%ld pages of RAM\n", present);
		printk("\t%d reserved pages\n", reserved);
		printk("\t%d pages shared\n", shared);
		printk("\t%d pages swap cached\n", cached);
	}
	printk("%ld pages of RAM\n", total_present);
	printk("%d reserved pages\n", total_reserved);
	printk("%d pages shared\n", total_shared);
	printk("%d pages swap cached\n", total_cached);
	printk("Total of %ld pages in page table cache\n", pgtable_cache_size);
	printk("%d free buffer pages\n", nr_free_buffer_pages());
}

/**
 * call_pernode_memory - use SRAT to call callback functions with node info
 * @start: physical start of range
 * @len: length of range
 * @arg: function to call for each range
 *
 * efi_memmap_walk() knows nothing about layout of memory across nodes. Find
 * out to which node a block of memory belongs.  Ignore memory that we cannot
 * identify, and split blocks that run across multiple nodes.
 *
 * Take this opportunity to round the start address up and the end address
 * down to page boundaries.
 */
void call_pernode_memory(unsigned long start, unsigned long len, void *arg)
{
	unsigned long rs, re, end = start + len;
	void (*func)(unsigned long, unsigned long, int);
	int i;

	start = PAGE_ALIGN(start);
	end &= PAGE_MASK;
	if (start >= end)
		return;

	func = arg;

	if (!num_node_memblks) {
		/* No SRAT table, so assume one node (node 0) */
		if (start < end)
			(*func)(start, end - start, 0);
		return;
	}

	for (i = 0; i < num_node_memblks; i++) {
		rs = max(start, node_memblk[i].start_paddr);
		re = min(end, node_memblk[i].start_paddr +
			 node_memblk[i].size);

		if (rs < re)
			(*func)(rs, re - rs, node_memblk[i].nid);

		if (re == end)
			break;
	}
}

/**
 * count_node_pages - callback to build per-node memory info structures
 * @start: physical start of range
 * @len: length of range
 * @node: node where this range resides
 *
 * Each node has it's own number of physical pages, DMAable pages, start, and
 * end page frame number.  This routine will be called by call_pernode_memory()
 * for each piece of usable memory and will setup these values for each node.
 * Very similar to build_maps().
 */
static __init int count_node_pages(unsigned long start, unsigned long len, int node)
{
	unsigned long end = start + len;

	mem_data[node].num_physpages += len >> PAGE_SHIFT;
	if (start <= __pa(MAX_DMA_ADDRESS))
		mem_data[node].num_dma_physpages +=
			(min(end, __pa(MAX_DMA_ADDRESS)) - start) >>PAGE_SHIFT;
	start = GRANULEROUNDDOWN(start);
	start = ORDERROUNDDOWN(start);
	end = GRANULEROUNDUP(end);
	mem_data[node].max_pfn = max(mem_data[node].max_pfn,
				     end >> PAGE_SHIFT);
	mem_data[node].min_pfn = min(mem_data[node].min_pfn,
				     start >> PAGE_SHIFT);

	return 0;
}

/**
 * paging_init - setup page tables
 *
 * paging_init() sets up the page tables for each node of the system and frees
 * the bootmem allocator memory for general use.
 */
void __init paging_init(void)
{
	unsigned long max_dma;
	unsigned long zones_size[MAX_NR_ZONES];
	unsigned long zholes_size[MAX_NR_ZONES];
	unsigned long pfn_offset = 0;
	int node;

	max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;

	/* so min() will work in count_node_pages */
	for_each_online_node(node)
		mem_data[node].min_pfn = ~0UL;

	efi_memmap_walk(filter_rsvd_memory, count_node_pages);

	for_each_online_node(node) {
		memset(zones_size, 0, sizeof(zones_size));
		memset(zholes_size, 0, sizeof(zholes_size));

		num_physpages += mem_data[node].num_physpages;

		if (mem_data[node].min_pfn >= max_dma) {
			/* All of this node's memory is above ZONE_DMA */
			zones_size[ZONE_NORMAL] = mem_data[node].max_pfn -
				mem_data[node].min_pfn;
			zholes_size[ZONE_NORMAL] = mem_data[node].max_pfn -
				mem_data[node].min_pfn -
				mem_data[node].num_physpages;
		} else if (mem_data[node].max_pfn < max_dma) {
			/* All of this node's memory is in ZONE_DMA */
			zones_size[ZONE_DMA] = mem_data[node].max_pfn -
				mem_data[node].min_pfn;
			zholes_size[ZONE_DMA] = mem_data[node].max_pfn -
				mem_data[node].min_pfn -
				mem_data[node].num_dma_physpages;
		} else {
			/* This node has memory in both zones */
			zones_size[ZONE_DMA] = max_dma -
				mem_data[node].min_pfn;
			zholes_size[ZONE_DMA] = zones_size[ZONE_DMA] -
				mem_data[node].num_dma_physpages;
			zones_size[ZONE_NORMAL] = mem_data[node].max_pfn -
				max_dma;
			zholes_size[ZONE_NORMAL] = zones_size[ZONE_NORMAL] -
				(mem_data[node].num_physpages -
				 mem_data[node].num_dma_physpages);
		}

		if (node == 0) {
			vmalloc_end -=
				PAGE_ALIGN(max_low_pfn * sizeof(struct page));
			vmem_map = (struct page *) vmalloc_end;

			efi_memmap_walk(create_mem_map_page_table, NULL);
			printk("Virtual mem_map starts at 0x%p\n", vmem_map);
		}

		pfn_offset = mem_data[node].min_pfn;

		NODE_DATA(node)->node_mem_map = vmem_map + pfn_offset;
		free_area_init_node(node, NODE_DATA(node), zones_size,
				    pfn_offset, zholes_size);
	}

	zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page));
}