discontig.c 20.7 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46
/*
 * Copyright (c) 2000, 2003 Silicon Graphics, Inc.  All rights reserved.
 * Copyright (c) 2001 Intel Corp.
 * Copyright (c) 2001 Tony Luck <tony.luck@intel.com>
 * Copyright (c) 2002 NEC Corp.
 * Copyright (c) 2002 Kimio Suganuma <k-suganuma@da.jp.nec.com>
 * Copyright (c) 2004 Silicon Graphics, Inc
 *	Russ Anderson <rja@sgi.com>
 *	Jesse Barnes <jbarnes@sgi.com>
 *	Jack Steiner <steiner@sgi.com>
 */

/*
 * Platform initialization for Discontig Memory
 */

#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/bootmem.h>
#include <linux/acpi.h>
#include <linux/efi.h>
#include <linux/nodemask.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/meminit.h>
#include <asm/numa.h>
#include <asm/sections.h>

/*
 * Track per-node information needed to setup the boot memory allocator, the
 * per-node areas, and the real VM.
 */
struct early_node_data {
	struct ia64_node_data *node_data;
	pg_data_t *pgdat;
	unsigned long pernode_addr;
	unsigned long pernode_size;
	struct bootmem_data bootmem_data;
	unsigned long num_physpages;
	unsigned long num_dma_physpages;
	unsigned long min_pfn;
	unsigned long max_pfn;
};

static struct early_node_data mem_data[MAX_NUMNODES] __initdata;
B
bob.picco 已提交
47
static nodemask_t memory_less_mask __initdata;
L
Linus Torvalds 已提交
48 49 50 51 52

/*
 * To prevent cache aliasing effects, align per-node structures so that they
 * start at addresses that are strided by node number.
 */
53
#define MAX_NODE_ALIGN_OFFSET	(32 * 1024 * 1024)
L
Linus Torvalds 已提交
54
#define NODEDATA_ALIGN(addr, node)						\
55 56
	((((addr) + 1024*1024-1) & ~(1024*1024-1)) + 				\
	     (((node)*PERCPU_PAGE_SIZE) & (MAX_NODE_ALIGN_OFFSET - 1)))
L
Linus Torvalds 已提交
57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94

/**
 * build_node_maps - callback to setup bootmem structs for each node
 * @start: physical start of range
 * @len: length of range
 * @node: node where this range resides
 *
 * We allocate a struct bootmem_data for each piece of memory that we wish to
 * treat as a virtually contiguous block (i.e. each node). Each such block
 * must start on an %IA64_GRANULE_SIZE boundary, so we round the address down
 * if necessary.  Any non-existent pages will simply be part of the virtual
 * memmap.  We also update min_low_pfn and max_low_pfn here as we receive
 * memory ranges from the caller.
 */
static int __init build_node_maps(unsigned long start, unsigned long len,
				  int node)
{
	unsigned long cstart, epfn, end = start + len;
	struct bootmem_data *bdp = &mem_data[node].bootmem_data;

	epfn = GRANULEROUNDUP(end) >> PAGE_SHIFT;
	cstart = GRANULEROUNDDOWN(start);

	if (!bdp->node_low_pfn) {
		bdp->node_boot_start = cstart;
		bdp->node_low_pfn = epfn;
	} else {
		bdp->node_boot_start = min(cstart, bdp->node_boot_start);
		bdp->node_low_pfn = max(epfn, bdp->node_low_pfn);
	}

	min_low_pfn = min(min_low_pfn, bdp->node_boot_start>>PAGE_SHIFT);
	max_low_pfn = max(max_low_pfn, bdp->node_low_pfn);

	return 0;
}

/**
B
bob.picco 已提交
95
 * early_nr_cpus_node - return number of cpus on a given node
L
Linus Torvalds 已提交
96 97
 * @node: node to check
 *
B
bob.picco 已提交
98
 * Count the number of cpus on @node.  We can't use nr_cpus_node() yet because
L
Linus Torvalds 已提交
99
 * acpi_boot_init() (which builds the node_to_cpu_mask array) hasn't been
B
bob.picco 已提交
100
 * called yet.  Note that node 0 will also count all non-existent cpus.
L
Linus Torvalds 已提交
101
 */
B
bob.picco 已提交
102
static int __init early_nr_cpus_node(int node)
L
Linus Torvalds 已提交
103 104 105 106 107
{
	int cpu, n = 0;

	for (cpu = 0; cpu < NR_CPUS; cpu++)
		if (node == node_cpuid[cpu].nid)
B
bob.picco 已提交
108
			n++;
L
Linus Torvalds 已提交
109 110 111 112

	return n;
}

B
bob.picco 已提交
113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128
/**
 * compute_pernodesize - compute size of pernode data
 * @node: the node id.
 */
static unsigned long __init compute_pernodesize(int node)
{
	unsigned long pernodesize = 0, cpus;

	cpus = early_nr_cpus_node(node);
	pernodesize += PERCPU_PAGE_SIZE * cpus;
	pernodesize += node * L1_CACHE_BYTES;
	pernodesize += L1_CACHE_ALIGN(sizeof(pg_data_t));
	pernodesize += L1_CACHE_ALIGN(sizeof(struct ia64_node_data));
	pernodesize = PAGE_ALIGN(pernodesize);
	return pernodesize;
}
L
Linus Torvalds 已提交
129

T
Tony Luck 已提交
130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156
/**
 * per_cpu_node_setup - setup per-cpu areas on each node
 * @cpu_data: per-cpu area on this node
 * @node: node to setup
 *
 * Copy the static per-cpu data into the region we just set aside and then
 * setup __per_cpu_offset for each CPU on this node.  Return a pointer to
 * the end of the area.
 */
static void *per_cpu_node_setup(void *cpu_data, int node)
{
#ifdef CONFIG_SMP
	int cpu;

	for (cpu = 0; cpu < NR_CPUS; cpu++) {
		if (node == node_cpuid[cpu].nid) {
			memcpy(__va(cpu_data), __phys_per_cpu_start,
			       __per_cpu_end - __per_cpu_start);
			__per_cpu_offset[cpu] = (char*)__va(cpu_data) -
				__per_cpu_start;
			cpu_data += PERCPU_PAGE_SIZE;
		}
	}
#endif
	return cpu_data;
}

L
Linus Torvalds 已提交
157
/**
B
bob.picco 已提交
158 159 160 161
 * fill_pernode - initialize pernode data.
 * @node: the node id.
 * @pernode: physical address of pernode data
 * @pernodesize: size of the pernode data
L
Linus Torvalds 已提交
162
 */
B
bob.picco 已提交
163 164
static void __init fill_pernode(int node, unsigned long pernode,
	unsigned long pernodesize)
L
Linus Torvalds 已提交
165
{
B
bob.picco 已提交
166
	void *cpu_data;
T
Tony Luck 已提交
167
	int cpus = early_nr_cpus_node(node);
B
bob.picco 已提交
168
	struct bootmem_data *bdp = &mem_data[node].bootmem_data;
L
Linus Torvalds 已提交
169

B
bob.picco 已提交
170 171 172
	mem_data[node].pernode_addr = pernode;
	mem_data[node].pernode_size = pernodesize;
	memset(__va(pernode), 0, pernodesize);
L
Linus Torvalds 已提交
173

B
bob.picco 已提交
174 175 176 177 178 179 180 181 182 183 184 185 186
	cpu_data = (void *)pernode;
	pernode += PERCPU_PAGE_SIZE * cpus;
	pernode += node * L1_CACHE_BYTES;

	mem_data[node].pgdat = __va(pernode);
	pernode += L1_CACHE_ALIGN(sizeof(pg_data_t));

	mem_data[node].node_data = __va(pernode);
	pernode += L1_CACHE_ALIGN(sizeof(struct ia64_node_data));

	mem_data[node].pgdat->bdata = bdp;
	pernode += L1_CACHE_ALIGN(sizeof(pg_data_t));

T
Tony Luck 已提交
187
	cpu_data = per_cpu_node_setup(cpu_data, node);
L
Linus Torvalds 已提交
188

B
bob.picco 已提交
189 190
	return;
}
T
Tony Luck 已提交
191

L
Linus Torvalds 已提交
192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222
/**
 * find_pernode_space - allocate memory for memory map and per-node structures
 * @start: physical start of range
 * @len: length of range
 * @node: node where this range resides
 *
 * This routine reserves space for the per-cpu data struct, the list of
 * pg_data_ts and the per-node data struct.  Each node will have something like
 * the following in the first chunk of addr. space large enough to hold it.
 *
 *    ________________________
 *   |                        |
 *   |~~~~~~~~~~~~~~~~~~~~~~~~| <-- NODEDATA_ALIGN(start, node) for the first
 *   |    PERCPU_PAGE_SIZE *  |     start and length big enough
 *   |    cpus_on_this_node   | Node 0 will also have entries for all non-existent cpus.
 *   |------------------------|
 *   |   local pg_data_t *    |
 *   |------------------------|
 *   |  local ia64_node_data  |
 *   |------------------------|
 *   |          ???           |
 *   |________________________|
 *
 * Once this space has been set aside, the bootmem maps are initialized.  We
 * could probably move the allocation of the per-cpu and ia64_node_data space
 * outside of this function and use alloc_bootmem_node(), but doing it here
 * is straightforward and we get the alignments we want so...
 */
static int __init find_pernode_space(unsigned long start, unsigned long len,
				     int node)
{
B
bob.picco 已提交
223
	unsigned long epfn;
L
Linus Torvalds 已提交
224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246
	unsigned long pernodesize = 0, pernode, pages, mapsize;
	struct bootmem_data *bdp = &mem_data[node].bootmem_data;

	epfn = (start + len) >> PAGE_SHIFT;

	pages = bdp->node_low_pfn - (bdp->node_boot_start >> PAGE_SHIFT);
	mapsize = bootmem_bootmap_pages(pages) << PAGE_SHIFT;

	/*
	 * Make sure this memory falls within this node's usable memory
	 * since we may have thrown some away in build_maps().
	 */
	if (start < bdp->node_boot_start || epfn > bdp->node_low_pfn)
		return 0;

	/* Don't setup this node's local space twice... */
	if (mem_data[node].pernode_addr)
		return 0;

	/*
	 * Calculate total size needed, incl. what's necessary
	 * for good alignment and alias prevention.
	 */
B
bob.picco 已提交
247
	pernodesize = compute_pernodesize(node);
L
Linus Torvalds 已提交
248 249 250
	pernode = NODEDATA_ALIGN(start, node);

	/* Is this range big enough for what we want to store here? */
B
bob.picco 已提交
251 252
	if (start + len > (pernode + pernodesize + mapsize))
		fill_pernode(node, pernode, pernodesize);
L
Linus Torvalds 已提交
253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291

	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;

B
bob.picco 已提交
292 293 294
		if (node_isset(node, memory_less_mask))
			continue;

L
Linus Torvalds 已提交
295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320
		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)
{
	pg_data_t *pgdat_list[MAX_NUMNODES];
T
Tony Luck 已提交
321
	int cpu, node;
L
Linus Torvalds 已提交
322 323 324 325 326 327 328 329 330

	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));
	}
T
Tony Luck 已提交
331
#ifdef CONFIG_SMP
L
Linus Torvalds 已提交
332 333 334 335 336
	/* 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;
	}
T
Tony Luck 已提交
337 338 339 340 341 342 343 344 345 346
#else
	{
		struct cpuinfo_ia64 *cpu0_cpu_info;
		cpu = 0;
		node = node_cpuid[cpu].nid;
		cpu0_cpu_info = (struct cpuinfo_ia64 *)(__phys_per_cpu_start +
			((char *)&per_cpu__cpu_info - __per_cpu_start));
		cpu0_cpu_info->node_data = mem_data[node].node_data;
	}
#endif /* CONFIG_SMP */
L
Linus Torvalds 已提交
347 348
}

B
bob.picco 已提交
349 350 351 352 353 354 355
/**
 * memory_less_node_alloc - * attempt to allocate memory on the best NUMA slit
 * 	node but fall back to any other node when __alloc_bootmem_node fails
 *	for best.
 * @nid: node id
 * @pernodesize: size of this node's pernode data
 */
B
Bob Picco 已提交
356
static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize)
B
bob.picco 已提交
357 358 359
{
	void *ptr = NULL;
	u8 best = 0xff;
B
Bob Picco 已提交
360
	int bestnode = -1, node, anynode = 0;
B
bob.picco 已提交
361 362 363 364 365 366 367 368

	for_each_online_node(node) {
		if (node_isset(node, memory_less_mask))
			continue;
		else if (node_distance(nid, node) < best) {
			best = node_distance(nid, node);
			bestnode = node;
		}
B
Bob Picco 已提交
369
		anynode = node;
B
bob.picco 已提交
370 371
	}

B
Bob Picco 已提交
372 373 374 375 376
	if (bestnode == -1)
		bestnode = anynode;

	ptr = __alloc_bootmem_node(mem_data[bestnode].pgdat, pernodesize,
		PERCPU_PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
B
bob.picco 已提交
377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417

	return ptr;
}

/**
 * pgdat_insert - insert the pgdat into global pgdat_list
 * @pgdat: the pgdat for a node.
 */
static void __init pgdat_insert(pg_data_t *pgdat)
{
	pg_data_t *prev = NULL, *next;

	for_each_pgdat(next)
		if (pgdat->node_id < next->node_id)
			break;
		else
			prev = next;

	if (prev) {
		prev->pgdat_next = pgdat;
		pgdat->pgdat_next = next;
	} else {
		pgdat->pgdat_next = pgdat_list;
		pgdat_list = pgdat;
	}

	return;
}

/**
 * memory_less_nodes - allocate and initialize CPU only nodes pernode
 *	information.
 */
static void __init memory_less_nodes(void)
{
	unsigned long pernodesize;
	void *pernode;
	int node;

	for_each_node_mask(node, memory_less_mask) {
		pernodesize = compute_pernodesize(node);
B
Bob Picco 已提交
418
		pernode = memory_less_node_alloc(node, pernodesize);
B
bob.picco 已提交
419 420 421 422 423 424
		fill_pernode(node, __pa(pernode), pernodesize);
	}

	return;
}

425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455
#ifdef CONFIG_SPARSEMEM
/**
 * register_sparse_mem - notify SPARSEMEM that this memory range exists.
 * @start: physical start of range
 * @end: physical end of range
 * @arg: unused
 *
 * Simply calls SPARSEMEM to register memory section(s).
 */
static int __init register_sparse_mem(unsigned long start, unsigned long end,
	void *arg)
{
	int nid;

	start = __pa(start) >> PAGE_SHIFT;
	end = __pa(end) >> PAGE_SHIFT;
	nid = early_pfn_to_nid(start);
	memory_present(nid, start, end);

	return 0;
}

static void __init arch_sparse_init(void)
{
	efi_memmap_walk(register_sparse_mem, NULL);
	sparse_init();
}
#else
#define arch_sparse_init() do {} while (0)
#endif

L
Linus Torvalds 已提交
456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472
/**
 * 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);
	}

B
bob.picco 已提交
473
	nodes_or(memory_less_mask, memory_less_mask, node_online_map);
L
Linus Torvalds 已提交
474 475 476 477 478 479 480
	min_low_pfn = -1;
	max_low_pfn = 0;

	/* 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);

B
bob.picco 已提交
481 482 483 484 485
	for_each_online_node(node)
		if (mem_data[node].bootmem_data.node_low_pfn) {
			node_clear(node, memory_less_mask);
			mem_data[node].min_pfn = ~0UL;
		}
L
Linus Torvalds 已提交
486 487 488 489 490 491 492 493 494 495
	/*
	 * 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;
B
bob.picco 已提交
496 497
		else if (node_isset(node, memory_less_mask))
			continue;
L
Linus Torvalds 已提交
498 499 500 501 502 503 504 505 506 507 508 509 510 511 512

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

		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();
B
bob.picco 已提交
513
	memory_less_nodes();
L
Linus Torvalds 已提交
514 515 516 517 518 519 520
	initialize_pernode_data();

	max_pfn = max_low_pfn;

	find_initrd();
}

T
Tony Luck 已提交
521
#ifdef CONFIG_SMP
L
Linus Torvalds 已提交
522 523 524 525 526 527
/**
 * per_cpu_init - setup per-cpu variables
 *
 * find_pernode_space() does most of this already, we just need to set
 * local_per_cpu_offset
 */
528
void __cpuinit *per_cpu_init(void)
L
Linus Torvalds 已提交
529 530
{
	int cpu;
A
Ashok Raj 已提交
531 532
	static int first_time = 1;

L
Linus Torvalds 已提交
533

T
Tony Luck 已提交
534 535 536
	if (smp_processor_id() != 0)
		return __per_cpu_start + __per_cpu_offset[smp_processor_id()];

A
Ashok Raj 已提交
537 538 539 540 541
	if (first_time) {
		first_time = 0;
		for (cpu = 0; cpu < NR_CPUS; cpu++)
			per_cpu(local_per_cpu_offset, cpu) = __per_cpu_offset[cpu];
	}
L
Linus Torvalds 已提交
542 543 544

	return __per_cpu_start + __per_cpu_offset[smp_processor_id()];
}
T
Tony Luck 已提交
545
#endif /* CONFIG_SMP */
L
Linus Torvalds 已提交
546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563

/**
 * 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) {
564 565
		unsigned long present;
		unsigned long flags;
L
Linus Torvalds 已提交
566
		int shared = 0, cached = 0, reserved = 0;
567

L
Linus Torvalds 已提交
568
		printk("Node ID: %d\n", pgdat->node_id);
569 570
		pgdat_resize_lock(pgdat, &flags);
		present = pgdat->node_present_pages;
L
Linus Torvalds 已提交
571
		for(i = 0; i < pgdat->node_spanned_pages; i++) {
572 573 574 575
			struct page *page;
			if (pfn_valid(pgdat->node_start_pfn + i))
				page = pfn_to_page(pgdat->node_start_pfn + i);
			else
L
Linus Torvalds 已提交
576
				continue;
577
			if (PageReserved(page))
L
Linus Torvalds 已提交
578
				reserved++;
579
			else if (PageSwapCache(page))
L
Linus Torvalds 已提交
580
				cached++;
581 582
			else if (page_count(page))
				shared += page_count(page)-1;
L
Linus Torvalds 已提交
583
		}
584
		pgdat_resize_unlock(pgdat, &flags);
L
Linus Torvalds 已提交
585 586 587 588 589 590 591 592 593 594 595 596 597
		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);
598 599
	printk("Total of %ld pages in page table cache\n",
		pgtable_quicklist_total_size());
L
Linus Torvalds 已提交
600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694
	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;

695 696
	arch_sparse_init();

L
Linus Torvalds 已提交
697 698
	efi_memmap_walk(filter_rsvd_memory, count_node_pages);

699
#ifdef CONFIG_VIRTUAL_MEM_MAP
B
bob.picco 已提交
700 701 702 703
	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);
704
#endif
B
bob.picco 已提交
705

L
Linus Torvalds 已提交
706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740
	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);
		}

		pfn_offset = mem_data[node].min_pfn;

741
#ifdef CONFIG_VIRTUAL_MEM_MAP
L
Linus Torvalds 已提交
742
		NODE_DATA(node)->node_mem_map = vmem_map + pfn_offset;
743
#endif
L
Linus Torvalds 已提交
744 745 746 747
		free_area_init_node(node, NODE_DATA(node), zones_size,
				    pfn_offset, zholes_size);
	}

B
bob.picco 已提交
748 749 750 751 752 753
	/*
	 * Make memory less nodes become a member of the known nodes.
	 */
	for_each_node_mask(node, memory_less_mask)
		pgdat_insert(mem_data[node].pgdat);

L
Linus Torvalds 已提交
754 755
	zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page));
}