numa_64.c

linux 内核源代码

	      FAKE_NODE_MIN_SIZE;

	/* Round down to nearest FAKE_NODE_MIN_SIZE. */
	size &= FAKE_NODE_MIN_HASH_MASK;
	if (!size) {
		printk(KERN_ERR "Not enough memory for each node.  "
		       "NUMA emulation disabled.\n");
		return -1;
	}

	for (i = node_start; i < num_nodes + node_start; i++) {
		u64 end = *addr + size;
		if (i < big)
			end += FAKE_NODE_MIN_SIZE;
		/*
		 * The final node can have the remaining system RAM.  Other
		 * nodes receive roughly the same amount of available pages.
		 */
		if (i == num_nodes + node_start - 1)
			end = max_addr;
		else
			while (end - *addr - e820_hole_size(*addr, end) <
			       size) {
				end += FAKE_NODE_MIN_SIZE;
				if (end > max_addr) {
					end = max_addr;
					break;
				}
			}
		if (setup_node_range(i, nodes, addr, end - *addr, max_addr) < 0)
			break;
	}
	return i - node_start + 1;
}

/*
 * Splits the remaining system RAM into chunks of size.  The remaining memory is
 * always assigned to a final node and can be asymmetric.  Returns the number of
 * nodes split.
 */
static int __init split_nodes_by_size(struct bootnode *nodes, u64 *addr,
				      u64 max_addr, int node_start, u64 size)
{
	int i = node_start;
	size = (size << 20) & FAKE_NODE_MIN_HASH_MASK;
	while (!setup_node_range(i++, nodes, addr, size, max_addr))
		;
	return i - node_start;
}

/*
 * Sets up the system RAM area from start_pfn to end_pfn according to the
 * numa=fake command-line option.
 */
static int __init numa_emulation(unsigned long start_pfn, unsigned long end_pfn)
{
	struct bootnode nodes[MAX_NUMNODES];
	u64 addr = start_pfn << PAGE_SHIFT;
	u64 max_addr = end_pfn << PAGE_SHIFT;
	int num_nodes = 0;
	int coeff_flag;
	int coeff = -1;
	int num = 0;
	u64 size;
	int i;

	memset(&nodes, 0, sizeof(nodes));
	/*
	 * If the numa=fake command-line is just a single number N, split the
	 * system RAM into N fake nodes.
	 */
	if (!strchr(cmdline, '*') && !strchr(cmdline, ',')) {
		num_nodes = split_nodes_equally(nodes, &addr, max_addr, 0,
						simple_strtol(cmdline, NULL, 0));
		if (num_nodes < 0)
			return num_nodes;
		goto out;
	}

	/* Parse the command line. */
	for (coeff_flag = 0; ; cmdline++) {
		if (*cmdline && isdigit(*cmdline)) {
			num = num * 10 + *cmdline - '0';
			continue;
		}
		if (*cmdline == '*') {
			if (num > 0)
				coeff = num;
			coeff_flag = 1;
		}
		if (!*cmdline || *cmdline == ',') {
			if (!coeff_flag)
				coeff = 1;
			/*
			 * Round down to the nearest FAKE_NODE_MIN_SIZE.
			 * Command-line coefficients are in megabytes.
			 */
			size = ((u64)num << 20) & FAKE_NODE_MIN_HASH_MASK;
			if (size)
				for (i = 0; i < coeff; i++, num_nodes++)
					if (setup_node_range(num_nodes, nodes,
						&addr, size, max_addr) < 0)
						goto done;
			if (!*cmdline)
				break;
			coeff_flag = 0;
			coeff = -1;
		}
		num = 0;
	}
done:
	if (!num_nodes)
		return -1;
	/* Fill remainder of system RAM, if appropriate. */
	if (addr < max_addr) {
		if (coeff_flag && coeff < 0) {
			/* Split remaining nodes into num-sized chunks */
			num_nodes += split_nodes_by_size(nodes, &addr, max_addr,
							 num_nodes, num);
			goto out;
		}
		switch (*(cmdline - 1)) {
		case '*':
			/* Split remaining nodes into coeff chunks */
			if (coeff <= 0)
				break;
			num_nodes += split_nodes_equally(nodes, &addr, max_addr,
							 num_nodes, coeff);
			break;
		case ',':
			/* Do not allocate remaining system RAM */
			break;
		default:
			/* Give one final node */
			setup_node_range(num_nodes, nodes, &addr,
					 max_addr - addr, max_addr);
			num_nodes++;
		}
	}
out:
	memnode_shift = compute_hash_shift(nodes, num_nodes);
	if (memnode_shift < 0) {
		memnode_shift = 0;
		printk(KERN_ERR "No NUMA hash function found.  NUMA emulation "
		       "disabled.\n");
		return -1;
	}

	/*
	 * We need to vacate all active ranges that may have been registered by
	 * SRAT and set acpi_numa to -1 so that srat_disabled() always returns
	 * true.  NUMA emulation has succeeded so we will not scan ACPI nodes.
	 */
	remove_all_active_ranges();
#ifdef CONFIG_ACPI_NUMA
	acpi_numa = -1;
#endif
	for_each_node_mask(i, node_possible_map) {
		e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
						nodes[i].end >> PAGE_SHIFT);
 		setup_node_bootmem(i, nodes[i].start, nodes[i].end);
	}
	acpi_fake_nodes(nodes, num_nodes);
 	numa_init_array();
 	return 0;
}
#endif /* CONFIG_NUMA_EMU */

void __init numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn)
{ 
	int i;

	nodes_clear(node_possible_map);

#ifdef CONFIG_NUMA_EMU
	if (cmdline && !numa_emulation(start_pfn, end_pfn))
 		return;
	nodes_clear(node_possible_map);
#endif

#ifdef CONFIG_ACPI_NUMA
	if (!numa_off && !acpi_scan_nodes(start_pfn << PAGE_SHIFT,
					  end_pfn << PAGE_SHIFT))
 		return;
	nodes_clear(node_possible_map);
#endif

#ifdef CONFIG_K8_NUMA
	if (!numa_off && !k8_scan_nodes(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT))
		return;
	nodes_clear(node_possible_map);
#endif
	printk(KERN_INFO "%s\n",
	       numa_off ? "NUMA turned off" : "No NUMA configuration found");

	printk(KERN_INFO "Faking a node at %016lx-%016lx\n", 
	       start_pfn << PAGE_SHIFT,
	       end_pfn << PAGE_SHIFT); 
		/* setup dummy node covering all memory */ 
	memnode_shift = 63; 
	memnodemap = memnode.embedded_map;
	memnodemap[0] = 0;
	nodes_clear(node_online_map);
	node_set_online(0);
	node_set(0, node_possible_map);
	for (i = 0; i < NR_CPUS; i++)
		numa_set_node(i, 0);
	node_to_cpumask[0] = cpumask_of_cpu(0);
	e820_register_active_regions(0, start_pfn, end_pfn);
	setup_node_bootmem(0, start_pfn << PAGE_SHIFT, end_pfn << PAGE_SHIFT);
}

__cpuinit void numa_add_cpu(int cpu)
{
	set_bit(cpu, &node_to_cpumask[cpu_to_node(cpu)]);
} 

void __cpuinit numa_set_node(int cpu, int node)
{
	cpu_pda(cpu)->nodenumber = node;
	cpu_to_node(cpu) = node;
}

unsigned long __init numa_free_all_bootmem(void) 
{ 
	int i;
	unsigned long pages = 0;
	for_each_online_node(i) {
		pages += free_all_bootmem_node(NODE_DATA(i));
	}
	return pages;
} 

void __init paging_init(void)
{ 
	int i;
	unsigned long max_zone_pfns[MAX_NR_ZONES];
	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
	max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
	max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
	max_zone_pfns[ZONE_NORMAL] = end_pfn;

	sparse_memory_present_with_active_regions(MAX_NUMNODES);
	sparse_init();

	for_each_online_node(i) {
		setup_node_zones(i); 
	}

	free_area_init_nodes(max_zone_pfns);
} 

static __init int numa_setup(char *opt)
{ 
	if (!opt)
		return -EINVAL;
	if (!strncmp(opt,"off",3))
		numa_off = 1;
#ifdef CONFIG_NUMA_EMU
	if (!strncmp(opt, "fake=", 5))
		cmdline = opt + 5;
#endif
#ifdef CONFIG_ACPI_NUMA
 	if (!strncmp(opt,"noacpi",6))
 		acpi_numa = -1;
	if (!strncmp(opt,"hotadd=", 7))
		hotadd_percent = simple_strtoul(opt+7, NULL, 10);
#endif
	return 0;
} 

early_param("numa", numa_setup);

/*
 * Setup early cpu_to_node.
 *
 * Populate cpu_to_node[] only if x86_cpu_to_apicid[],
 * and apicid_to_node[] tables have valid entries for a CPU.
 * This means we skip cpu_to_node[] initialisation for NUMA
 * emulation and faking node case (when running a kernel compiled
 * for NUMA on a non NUMA box), which is OK as cpu_to_node[]
 * is already initialized in a round robin manner at numa_init_array,
 * prior to this call, and this initialization is good enough
 * for the fake NUMA cases.
 */
void __init init_cpu_to_node(void)
{
	int i;
 	for (i = 0; i < NR_CPUS; i++) {
		u8 apicid = x86_cpu_to_apicid_init[i];
		if (apicid == BAD_APICID)
			continue;
		if (apicid_to_node[apicid] == NUMA_NO_NODE)
			continue;
		numa_set_node(i,apicid_to_node[apicid]);
	}
}

EXPORT_SYMBOL(cpu_to_node);
EXPORT_SYMBOL(node_to_cpumask);
EXPORT_SYMBOL(memnode);
EXPORT_SYMBOL(node_data);

#ifdef CONFIG_DISCONTIGMEM
/*
 * Functions to convert PFNs from/to per node page addresses.
 * These are out of line because they are quite big.
 * They could be all tuned by pre caching more state.
 * Should do that.
 */

int pfn_valid(unsigned long pfn)
{
	unsigned nid;
	if (pfn >= num_physpages)
		return 0;
	nid = pfn_to_nid(pfn);
	if (nid == 0xff)
		return 0;
	return pfn >= node_start_pfn(nid) && (pfn) < node_end_pfn(nid);
}
EXPORT_SYMBOL(pfn_valid);
#endif