aboutsummaryrefslogtreecommitdiffstats
path: root/fs/binfmt_misc.c
blob: c4e83537ead77501f03d7fcb3a748727f2624d5e (plain) (blame)
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
47
48
49
50
51
52
53
54
55
56
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
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
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
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
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
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
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
292
293
294
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
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
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
418
419
420
421
422
423
424
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
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
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
695
696
697
698
699
700
701
702
703
704
705
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
741
/*
 *  binfmt_misc.c
 *
 *  Copyright (C) 1997 Richard Günther
 *
 *  binfmt_misc detects binaries via a magic or filename extension and invokes
 *  a specified wrapper. This should obsolete binfmt_java, binfmt_em86 and
 *  binfmt_mz.
 *
 *  1997-04-25 first version
 *  [...]
 *  1997-05-19 cleanup
 *  1997-06-26 hpa: pass the real filename rather than argv[0]
 *  1997-06-30 minor cleanup
 *  1997-08-09 removed extension stripping, locking cleanup
 *  2001-02-28 AV: rewritten into something that resembles C. Original didn't.
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/binfmts.h>
#include <linux/slab.h>
#include <linux/ctype.h>
#include <linux/file.h>
#include <linux/pagemap.h>
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/syscalls.h>
#include <linux/fs.h>

#include <asm/uaccess.h>

enum {
	VERBOSE_STATUS = 1 /* make it zero to save 400 bytes kernel memory */
};

static LIST_HEAD(entries);
static int enabled = 1;

enum {Enabled, Magic};
#define MISC_FMT_PRESERVE_ARGV0 (1<<31)
#define MISC_FMT_OPEN_BINARY (1<<30)
#define MISC_FMT_CREDENTIALS (1<<29)

typedef struct {
	struct list_head list;
	unsigned long flags;		/* type, status, etc. */
	int offset;			/* offset of magic */
	int size;			/* size of magic/mask */
	char *magic;			/* magic or filename extension */
	char *mask;			/* mask, NULL for exact match */
	char *interpreter;		/* filename of interpreter */
	char *name;
	struct dentry *dentry;
} Node;

static DEFINE_RWLOCK(entries_lock);
static struct file_system_type bm_fs_type;
static struct vfsmount *bm_mnt;
static int entry_count;

/* 
 * Check if we support the binfmt
 * if we do, return the node, else NULL
 * locking is done in load_misc_binary
 */
static Node *check_file(struct linux_binprm *bprm)
{
	char *p = strrchr(bprm->interp, '.');
	struct list_head *l;

	list_for_each(l, &entries) {
		Node *e = list_entry(l, Node, list);
		char *s;
		int j;

		if (!test_bit(Enabled, &e->flags))
			continue;

		if (!test_bit(Magic, &e->flags)) {
			if (p && !strcmp(e->magic, p + 1))
				return e;
			continue;
		}

		s = bprm->buf + e->offset;
		if (e->mask) {
			for (j = 0; j < e->size; j++)
				if ((*s++ ^ e->magic[j]) & e->mask[j])
					break;
		} else {
			for (j = 0; j < e->size; j++)
				if ((*s++ ^ e->magic[j]))
					break;
		}
		if (j == e->size)
			return e;
	}
	return NULL;
}

/*
 * the loader itself
 */
static int load_misc_binary(struct linux_binprm *bprm, struct pt_regs *regs)
{
	Node *fmt;
	struct file * interp_file = NULL;
	char iname[BINPRM_BUF_SIZE];
	char *iname_addr = iname;
	int retval;
	int fd_binary = -1;

	retval = -ENOEXEC;
	if (!enabled)
		goto _ret;

	retval = -ENOEXEC;
	if (bprm->recursion_depth > BINPRM_MAX_RECURSION)
		goto _ret;

	/* to keep locking time low, we copy the interpreter string */
	read_lock(&entries_lock);
	fmt = check_file(bprm);
	if (fmt)
		strlcpy(iname, fmt->interpreter, BINPRM_BUF_SIZE);
	read_unlock(&entries_lock);
	if (!fmt)
		goto _ret;

	if (!(fmt->flags & MISC_FMT_PRESERVE_ARGV0)) {
		retval = remove_arg_zero(bprm);
		if (retval)
			goto _ret;
	}

	if (fmt->flags & MISC_FMT_OPEN_BINARY) {

		/* if the binary should be opened on behalf of the
		 * interpreter than keep it open and assign descriptor
		 * to it */
 		fd_binary = get_unused_fd();
 		if (fd_binary < 0) {
 			retval = fd_binary;
 			goto _ret;
 		}
 		fd_install(fd_binary, bprm->file);

		/* if the binary is not readable than enforce mm->dumpable=0
		   regardless of the interpreter's permissions */
		if (file_permission(bprm->file, MAY_READ))
			bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP;

		allow_write_access(bprm->file);
		bprm->file = NULL;

		/* mark the bprm that fd should be passed to interp */
		bprm->interp_flags |= BINPRM_FLAGS_EXECFD;
		bprm->interp_data = fd_binary;

 	} else {
 		allow_write_access(bprm->file);
 		fput(bprm->file);
 		bprm->file = NULL;
 	}
	/* make argv[1] be the path to the binary */
	retval = copy_strings_kernel (1, &bprm->interp, bprm);
	if (retval < 0)
		goto _error;
	bprm->argc++;

	/* add the interp as argv[0] */
	retval = copy_strings_kernel (1, &iname_addr, bprm);
	if (retval < 0)
		goto _error;
	bprm->argc ++;

	bprm->interp = iname;	/* for binfmt_script */

	interp_file = open_exec (iname);
	retval = PTR_ERR (interp_file);
	if (IS_ERR (interp_file))
		goto _error;

	bprm->file = interp_file;
	if (fmt->flags & MISC_FMT_CREDENTIALS) {
		/*
		 * No need to call prepare_binprm(), it's already been
		 * done.  bprm->buf is stale, update from interp_file.
		 */
		memset(bprm->buf, 0, BINPRM_BUF_SIZE);
		retval = kernel_read(bprm->file, 0, bprm->buf, BINPRM_BUF_SIZE);
	} else
		retval = prepare_binprm (bprm);

	if (retval < 0)
		goto _error;

	bprm->recursion_depth++;

	retval = search_binary_handler (bprm, regs);
	if (retval < 0)
		goto _error;

_ret:
	return retval;
_error:
	if (fd_binary > 0)
		sys_close(fd_binary);
	bprm->interp_flags = 0;
	bprm->interp_data = 0;
	goto _ret;
}

/* Command parsers */

/*
 * parses and copies one argument enclosed in del from *sp to *dp,
 * recognising the \x special.
 * returns pointer to the copied argument or NULL in case of an
 * error (and sets err) or null argument length.
 */
static char *scanarg(char *s, char del)
{
	char c;

	while ((c = *s++) != del) {
		if (c == '\\' && *s == 'x') {
			s++;
			if (!isxdigit(*s++))
				return NULL;
			if (!isxdigit(*s++))
				return NULL;
		}
	}
	return s;
}

static int unquote(char *from)
{
	char c = 0, *s = from, *p = from;

	while ((c = *s++) != '\0') {
		if (c == '\\' && *s == 'x') {
			s++;
			c = toupper(*s++);
			*p = (c - (isdigit(c) ? '0' : 'A' - 10)) << 4;
			c = toupper(*s++);
			*p++ |= c - (isdigit(c) ? '0' : 'A' - 10);
			continue;
		}
		*p++ = c;
	}
	return p - from;
}

static char * check_special_flags (char * sfs, Node * e)
{
	char * p = sfs;
	int cont = 1;

	/* special flags */
	while (cont) {
		switch (*p) {
			case 'P':
				p++;
				e->flags |= MISC_FMT_PRESERVE_ARGV0;
				break;
			case 'O':
				p++;
				e->flags |= MISC_FMT_OPEN_BINARY;
				break;
			case 'C':
				p++;
				/* this flags also implies the
				   open-binary flag */
				e->flags |= (MISC_FMT_CREDENTIALS |
						MISC_FMT_OPEN_BINARY);
				break;
			default:
				cont = 0;
		}
	}

	return p;
}
/*
 * This registers a new binary format, it recognises the syntax
 * ':name:type:offset:magic:mask:interpreter:flags'
 * where the ':' is the IFS, that can be chosen with the first char
 */
static Node *create_entry(const char __user *buffer, size_t count)
{
	Node *e;
	int memsize, err;
	char *buf, *p;
	char del;

	/* some sanity checks */
	err = -EINVAL;
	if ((count < 11) || (count > 256))
		goto out;

	err = -ENOMEM;
	memsize = sizeof(Node) + count + 8;
	e = kmalloc(memsize, GFP_USER);
	if (!e)
		goto out;

	p = buf = (char *)e + sizeof(Node);

	memset(e, 0, sizeof(Node));
	if (copy_from_user(buf, buffer, count))
		goto Efault;

	del = *p++;	/* delimeter */

	memset(buf+count, del, 8);

	e->name = p;
	p = strchr(p, del);
	if (!p)
		goto Einval;
	*p++ = '\0';
	if (!e->name[0] ||
	    !strcmp(e->name, ".") ||
	    !strcmp(e->name, "..") ||
	    strchr(e->name, '/'))
		goto Einval;
	switch (*p++) {
		case 'E': e->flags = 1<<Enabled; break;
		case 'M': e->flags = (1<<Enabled) | (1<<Magic); break;
		default: goto Einval;
	}
	if (*p++ != del)
		goto Einval;
	if (test_bit(Magic, &e->flags)) {
		char *s = strchr(p, del);
		if (!s)
			goto Einval;
		*s++ = '\0';
		e->offset = simple_strtoul(p, &p, 10);
		if (*p++)
			goto Einval;
		e->magic = p;
		p = scanarg(p, del);
		if (!p)
			goto Einval;
		p[-1] = '\0';
		if (!e->magic[0])
			goto Einval;
		e->mask = p;
		p = scanarg(p, del);
		if (!p)
			goto Einval;
		p[-1] = '\0';
		if (!e->mask[0])
			e->mask = NULL;
		e->size = unquote(e->magic);
		if (e->mask && unquote(e->mask) != e->size)
			goto Einval;
		if (e->size + e->offset > BINPRM_BUF_SIZE)
			goto Einval;
	} else {
		p = strchr(p, del);
		if (!p)
			goto Einval;
		*p++ = '\0';
		e->magic = p;
		p = strchr(p, del);
		if (!p)
			goto Einval;
		*p++ = '\0';
		if (!e->magic[0] || strchr(e->magic, '/'))
			goto Einval;
		p = strchr(p, del);
		if (!p)
			goto Einval;
		*p++ = '\0';
	}
	e->interpreter = p;
	p = strchr(p, del);
	if (!p)
		goto Einval;
	*p++ = '\0';
	if (!e->interpreter[0])
		goto Einval;


	p = check_special_flags (p, e);

	if (*p == '\n')
		p++;
	if (p != buf + count)
		goto Einval;
	return e;

out:
	return ERR_PTR(err);

Efault:
	kfree(e);
	return ERR_PTR(-EFAULT);
Einval:
	kfree(e);
	return ERR_PTR(-EINVAL);
}

/*
 * Set status of entry/binfmt_misc:
 * '1' enables, '0' disables and '-1' clears entry/binfmt_misc
 */
static int parse_command(const char __user *buffer, size_t count)
{
	char s[4];

	if (!count)
		return 0;
	if (count > 3)
		return -EINVAL;
	if (copy_from_user(s, buffer, count))
		return -EFAULT;
	if (s[count-1] == '\n')
		count--;
	if (count == 1 && s[0] == '0')
		return 1;
	if (count == 1 && s[0] == '1')
		return 2;
	if (count == 2 && s[0] == '-' && s[1] == '1')
		return 3;
	return -EINVAL;
}

/* generic stuff */

static void entry_status(Node *e, char *page)
{
	char *dp;
	char *status = "disabled";
	const char * flags = "flags: ";

	if (test_bit(Enabled, &e->flags))
		status = "enabled";

	if (!VERBOSE_STATUS) {
		sprintf(page, "%s\n", status);
		return;
	}

	sprintf(page, "%s\ninterpreter %s\n", status, e->interpreter);
	dp = page + strlen(page);

	/* print the special flags */
	sprintf (dp, "%s", flags);
	dp += strlen (flags);
	if (e->flags & MISC_FMT_PRESERVE_ARGV0) {
		*dp ++ = 'P';
	}
	if (e->flags & MISC_FMT_OPEN_BINARY) {
		*dp ++ = 'O';
	}
	if (e->flags & MISC_FMT_CREDENTIALS) {
		*dp ++ = 'C';
	}
	*dp ++ = '\n';


	if (!test_bit(Magic, &e->flags)) {
		sprintf(dp, "extension .%s\n", e->magic);
	} else {
		int i;

		sprintf(dp, "offset %i\nmagic ", e->offset);
		dp = page + strlen(page);
		for (i = 0; i < e->size; i++) {
			sprintf(dp, "%02x", 0xff & (int) (e->magic[i]));
			dp += 2;
		}
		if (e->mask) {
			sprintf(dp, "\nmask ");
			dp += 6;
			for (i = 0; i < e->size; i++) {
				sprintf(dp, "%02x", 0xff & (int) (e->mask[i]));
				dp += 2;
			}
		}
		*dp++ = '\n';
		*dp = '\0';
	}
}

static struct inode *bm_get_inode(struct super_block *sb, int mode)
{
	struct inode * inode = new_inode(sb);

	if (inode) {
		inode->i_mode = mode;
		inode->i_atime = inode->i_mtime = inode->i_ctime =
			current_fs_time(inode->i_sb);
	}
	return inode;
}

static void bm_clear_inode(struct inode *inode)
{
	kfree(inode->i_private);
}

static void kill_node(Node *e)
{
	struct dentry *dentry;

	write_lock(&entries_lock);
	dentry = e->dentry;
	if (dentry) {
		list_del_init(&e->list);
		e->dentry = NULL;
	}
	write_unlock(&entries_lock);

	if (dentry) {
		dentry->d_inode->i_nlink--;
		d_drop(dentry);
		dput(dentry);
		simple_release_fs(&bm_mnt, &entry_count);
	}
}

/* /<entry> */

static ssize_t
bm_entry_read(struct file * file, char __user * buf, size_t nbytes, loff_t *ppos)
{
	Node *e = file->f_path.dentry->d_inode->i_private;
	ssize_t res;
	char *page;

	if (!(page = (char*) __get_free_page(GFP_KERNEL)))
		return -ENOMEM;

	entry_status(e, page);

	res = simple_read_from_buffer(buf, nbytes, ppos, page, strlen(page));

	free_page((unsigned long) page);
	return res;
}

static ssize_t bm_entry_write(struct file *file, const char __user *buffer,
				size_t count, loff_t *ppos)
{
	struct dentry *root;
	Node *e = file->f_path.dentry->d_inode->i_private;
	int res = parse_command(buffer, count);

	switch (res) {
		case 1: clear_bit(Enabled, &e->flags);
			break;
		case 2: set_bit(Enabled, &e->flags);
			break;
		case 3: root = dget(file->f_path.mnt->mnt_sb->s_root);
			mutex_lock(&root->d_inode->i_mutex);

			kill_node(e);

			mutex_unlock(&root->d_inode->i_mutex);
			dput(root);
			break;
		default: return res;
	}
	return count;
}

static const struct file_operations bm_entry_operations = {
	.read		= bm_entry_read,
	.write		= bm_entry_write,
};

/* /register */

static ssize_t bm_register_write(struct file *file, const char __user *buffer,
			       size_t count, loff_t *ppos)
{
	Node *e;
	struct inode *inode;
	struct dentry *root, *dentry;
	struct super_block *sb = file->f_path.mnt->mnt_sb;
	int err = 0;

	e = create_entry(buffer, count);

	if (IS_ERR(e))
		return PTR_ERR(e);

	root = dget(sb->s_root);
	mutex_lock(&root->d_inode->i_mutex);
	dentry = lookup_one_len(e->name, root, strlen(e->name));
	err = PTR_ERR(dentry);
	if (IS_ERR(dentry))
		goto out;

	err = -EEXIST;
	if (dentry->d_inode)
		goto out2;

	inode = bm_get_inode(sb, S_IFREG | 0644);

	err = -ENOMEM;
	if (!inode)
		goto out2;

	err = simple_pin_fs(&bm_fs_type, &bm_mnt, &entry_count);
	if (err) {
		iput(inode);
		inode = NULL;
		goto out2;
	}

	e->dentry = dget(dentry);
	inode->i_private = e;
	inode->i_fop = &bm_entry_operations;

	d_instantiate(dentry, inode);
	write_lock(&entries_lock);
	list_add(&e->list, &entries);
	write_unlock(&entries_lock);

	err = 0;
out2:
	dput(dentry);
out:
	mutex_unlock(&root->d_inode->i_mutex);
	dput(root);

	if (err) {
		kfree(e);
		return -EINVAL;
	}
	return count;
}

static const struct file_operations bm_register_operations = {
	.write		= bm_register_write,
};

/* /status */

static ssize_t
bm_status_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
{
	char *s = enabled ? "enabled\n" : "disabled\n";

	return simple_read_from_buffer(buf, nbytes, ppos, s, strlen(s));
}

static ssize_t bm_status_write(struct file * file, const char __user * buffer,
		size_t count, loff_t *ppos)
{
	int res = parse_command(buffer, count);
	struct dentry *root;

	switch (res) {
		case 1: enabled = 0; break;
		case 2: enabled = 1; break;
		case 3: root = dget(file->f_path.mnt->mnt_sb->s_root);
			mutex_lock(&root->d_inode->i_mutex);

			while (!list_empty(&entries))
				kill_node(list_entry(entries.next, Node, list));

			mutex_unlock(&root->d_inode->i_mutex);
			dput(root);
		default: return res;
	}
	return count;
}

static const struct file_operations bm_status_operations = {
	.read		= bm_status_read,
	.write		= bm_status_write,
};

/* Superblock handling */

static const struct super_operations s_ops = {
	.statfs		= simple_statfs,
	.clear_inode	= bm_clear_inode,
};

static int bm_fill_super(struct super_block * sb, void * data, int silent)
{
	static struct tree_descr bm_files[] = {
		[2] = {"status", &bm_status_operations, S_IWUSR|S_IRUGO},
		[3] = {"register", &bm_register_operations, S_IWUSR},
		/* last one */ {""}
	};
	int err = simple_fill_super(sb, 0x42494e4d, bm_files);
	if (!err)
		sb->s_op = &s_ops;
	return err;
}

static int bm_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
{
	return get_sb_single(fs_type, flags, data, bm_fill_super, mnt);
}

static struct linux_binfmt misc_format = {
	.module = THIS_MODULE,
	.load_binary = load_misc_binary,
};

static struct file_system_type bm_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "binfmt_misc",
	.get_sb		= bm_get_sb,
	.kill_sb	= kill_litter_super,
};

static int __init init_misc_binfmt(void)
{
	int err = register_filesystem(&bm_fs_type);
	if (!err) {
		err = register_binfmt(&misc_format);
		if (err)
			unregister_filesystem(&bm_fs_type);
	}
	return err;
}

static void __exit exit_misc_binfmt(void)
{
	unregister_binfmt(&misc_format);
	unregister_filesystem(&bm_fs_type);
}

core_initcall(init_misc_binfmt);
module_exit(exit_misc_binfmt);
MODULE_LICENSE("GPL");
3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294
/*
 *  linux/mm/page_alloc.c
 *
 *  Manages the free list, the system allocates free pages here.
 *  Note that kmalloc() lives in slab.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *  Swap reorganised 29.12.95, Stephen Tweedie
 *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
 *  Reshaped it to be a zoned allocator, Ingo Molnar, Red Hat, 1999
 *  Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999
 *  Zone balancing, Kanoj Sarcar, SGI, Jan 2000
 *  Per cpu hot/cold page lists, bulk allocation, Martin J. Bligh, Sept 2002
 *          (lots of bits borrowed from Ingo Molnar & Andrew Morton)
 */

#include <linux/stddef.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
#include <linux/bootmem.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/suspend.h>
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
#include <linux/notifier.h>
#include <linux/topology.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/memory_hotplug.h>
#include <linux/nodemask.h>
#include <linux/vmalloc.h>
#include <linux/mempolicy.h>
#include <linux/stop_machine.h>
#include <linux/sort.h>
#include <linux/pfn.h>
#include <linux/backing-dev.h>

#include <asm/tlbflush.h>
#include <asm/div64.h>
#include "internal.h"

/*
 * MCD - HACK: Find somewhere to initialize this EARLY, or make this
 * initializer cleaner
 */
nodemask_t node_online_map __read_mostly = { { [0] = 1UL } };
EXPORT_SYMBOL(node_online_map);
nodemask_t node_possible_map __read_mostly = NODE_MASK_ALL;
EXPORT_SYMBOL(node_possible_map);
unsigned long totalram_pages __read_mostly;
unsigned long totalreserve_pages __read_mostly;
long nr_swap_pages;
int percpu_pagelist_fraction;

static void __free_pages_ok(struct page *page, unsigned int order);

/*
 * results with 256, 32 in the lowmem_reserve sysctl:
 *	1G machine -> (16M dma, 800M-16M normal, 1G-800M high)
 *	1G machine -> (16M dma, 784M normal, 224M high)
 *	NORMAL allocation will leave 784M/256 of ram reserved in the ZONE_DMA
 *	HIGHMEM allocation will leave 224M/32 of ram reserved in ZONE_NORMAL
 *	HIGHMEM allocation will (224M+784M)/256 of ram reserved in ZONE_DMA
 *
 * TBD: should special case ZONE_DMA32 machines here - in those we normally
 * don't need any ZONE_NORMAL reservation
 */
int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = {
	 256,
#ifdef CONFIG_ZONE_DMA32
	 256,
#endif
#ifdef CONFIG_HIGHMEM
	 32
#endif
};

EXPORT_SYMBOL(totalram_pages);

static char *zone_names[MAX_NR_ZONES] = {
	 "DMA",
#ifdef CONFIG_ZONE_DMA32
	 "DMA32",
#endif
	 "Normal",
#ifdef CONFIG_HIGHMEM
	 "HighMem"
#endif
};

int min_free_kbytes = 1024;

unsigned long __meminitdata nr_kernel_pages;
unsigned long __meminitdata nr_all_pages;
static unsigned long __initdata dma_reserve;

#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
  /*
   * MAX_ACTIVE_REGIONS determines the maxmimum number of distinct
   * ranges of memory (RAM) that may be registered with add_active_range().
   * Ranges passed to add_active_range() will be merged if possible
   * so the number of times add_active_range() can be called is
   * related to the number of nodes and the number of holes
   */
  #ifdef CONFIG_MAX_ACTIVE_REGIONS
    /* Allow an architecture to set MAX_ACTIVE_REGIONS to save memory */
    #define MAX_ACTIVE_REGIONS CONFIG_MAX_ACTIVE_REGIONS
  #else
    #if MAX_NUMNODES >= 32
      /* If there can be many nodes, allow up to 50 holes per node */
      #define MAX_ACTIVE_REGIONS (MAX_NUMNODES*50)
    #else
      /* By default, allow up to 256 distinct regions */
      #define MAX_ACTIVE_REGIONS 256
    #endif
  #endif

  struct node_active_region __initdata early_node_map[MAX_ACTIVE_REGIONS];
  int __initdata nr_nodemap_entries;
  unsigned long __initdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
  unsigned long __initdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
  unsigned long __initdata node_boundary_start_pfn[MAX_NUMNODES];
  unsigned long __initdata node_boundary_end_pfn[MAX_NUMNODES];
#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */

#ifdef CONFIG_DEBUG_VM
static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
{
	int ret = 0;
	unsigned seq;
	unsigned long pfn = page_to_pfn(page);

	do {
		seq = zone_span_seqbegin(zone);
		if (pfn >= zone->zone_start_pfn + zone->spanned_pages)
			ret = 1;
		else if (pfn < zone->zone_start_pfn)
			ret = 1;
	} while (zone_span_seqretry(zone, seq));

	return ret;
}

static int page_is_consistent(struct zone *zone, struct page *page)
{
#ifdef CONFIG_HOLES_IN_ZONE
	if (!pfn_valid(page_to_pfn(page)))
		return 0;
#endif
	if (zone != page_zone(page))
		return 0;

	return 1;
}
/*
 * Temporary debugging check for pages not lying within a given zone.
 */
static int bad_range(struct zone *zone, struct page *page)
{
	if (page_outside_zone_boundaries(zone, page))
		return 1;
	if (!page_is_consistent(zone, page))
		return 1;

	return 0;
}
#else
static inline int bad_range(struct zone *zone, struct page *page)
{
	return 0;
}
#endif

static void bad_page(struct page *page)
{
	printk(KERN_EMERG "Bad page state in process '%s'\n"
		KERN_EMERG "page:%p flags:0x%0*lx mapping:%p mapcount:%d count:%d\n"
		KERN_EMERG "Trying to fix it up, but a reboot is needed\n"
		KERN_EMERG "Backtrace:\n",
		current->comm, page, (int)(2*sizeof(unsigned long)),
		(unsigned long)page->flags, page->mapping,
		page_mapcount(page), page_count(page));
	dump_stack();
	page->flags &= ~(1 << PG_lru	|
			1 << PG_private |
			1 << PG_locked	|
			1 << PG_active	|
			1 << PG_dirty	|
			1 << PG_reclaim |
			1 << PG_slab    |
			1 << PG_swapcache |
			1 << PG_writeback |
			1 << PG_buddy );
	set_page_count(page, 0);
	reset_page_mapcount(page);
	page->mapping = NULL;
	add_taint(TAINT_BAD_PAGE);
}

/*
 * Higher-order pages are called "compound pages".  They are structured thusly:
 *
 * The first PAGE_SIZE page is called the "head page".
 *
 * The remaining PAGE_SIZE pages are called "tail pages".
 *
 * All pages have PG_compound set.  All pages have their ->private pointing at
 * the head page (even the head page has this).
 *
 * The first tail page's ->lru.next holds the address of the compound page's
 * put_page() function.  Its ->lru.prev holds the order of allocation.
 * This usage means that zero-order pages may not be compound.
 */

static void free_compound_page(struct page *page)
{
	__free_pages_ok(page, (unsigned long)page[1].lru.prev);
}

static void prep_compound_page(struct page *page, unsigned long order)
{
	int i;
	int nr_pages = 1 << order;

	page[1].lru.next = (void *)free_compound_page;	/* set dtor */
	page[1].lru.prev = (void *)order;
	for (i = 0; i < nr_pages; i++) {
		struct page *p = page + i;

		__SetPageCompound(p);
		set_page_private(p, (unsigned long)page);
	}
}

static void destroy_compound_page(struct page *page, unsigned long order)
{
	int i;
	int nr_pages = 1 << order;

	if (unlikely((unsigned long)page[1].lru.prev != order))
		bad_page(page);

	for (i = 0; i < nr_pages; i++) {
		struct page *p = page + i;

		if (unlikely(!PageCompound(p) |
				(page_private(p) != (unsigned long)page)))
			bad_page(page);
		__ClearPageCompound(p);
	}
}

static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags)
{
	int i;

	VM_BUG_ON((gfp_flags & (__GFP_WAIT | __GFP_HIGHMEM)) == __GFP_HIGHMEM);
	/*
	 * clear_highpage() will use KM_USER0, so it's a bug to use __GFP_ZERO
	 * and __GFP_HIGHMEM from hard or soft interrupt context.
	 */
	VM_BUG_ON((gfp_flags & __GFP_HIGHMEM) && in_interrupt());
	for (i = 0; i < (1 << order); i++)
		clear_highpage(page + i);
}

/*
 * function for dealing with page's order in buddy system.
 * zone->lock is already acquired when we use these.
 * So, we don't need atomic page->flags operations here.
 */
static inline unsigned long page_order(struct page *page)
{
	return page_private(page);
}

static inline void set_page_order(struct page *page, int order)
{
	set_page_private(page, order);
	__SetPageBuddy(page);
}

static inline void rmv_page_order(struct page *page)
{
	__ClearPageBuddy(page);
	set_page_private(page, 0);
}

/*
 * Locate the struct page for both the matching buddy in our
 * pair (buddy1) and the combined O(n+1) page they form (page).
 *
 * 1) Any buddy B1 will have an order O twin B2 which satisfies
 * the following equation:
 *     B2 = B1 ^ (1 << O)
 * For example, if the starting buddy (buddy2) is #8 its order
 * 1 buddy is #10:
 *     B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10
 *
 * 2) Any buddy B will have an order O+1 parent P which
 * satisfies the following equation:
 *     P = B & ~(1 << O)
 *
 * Assumption: *_mem_map is contiguous at least up to MAX_ORDER
 */
static inline struct page *
__page_find_buddy(struct page *page, unsigned long page_idx, unsigned int order)
{
	unsigned long buddy_idx = page_idx ^ (1 << order);

	return page + (buddy_idx - page_idx);
}

static inline unsigned long
__find_combined_index(unsigned long page_idx, unsigned int order)
{
	return (page_idx & ~(1 << order));
}

/*
 * This function checks whether a page is free && is the buddy
 * we can do coalesce a page and its buddy if
 * (a) the buddy is not in a hole &&
 * (b) the buddy is in the buddy system &&
 * (c) a page and its buddy have the same order &&
 * (d) a page and its buddy are in the same zone.
 *
 * For recording whether a page is in the buddy system, we use PG_buddy.
 * Setting, clearing, and testing PG_buddy is serialized by zone->lock.
 *
 * For recording page's order, we use page_private(page).
 */
static inline int page_is_buddy(struct page *page, struct page *buddy,
								int order)
{
#ifdef CONFIG_HOLES_IN_ZONE
	if (!pfn_valid(page_to_pfn(buddy)))
		return 0;
#endif

	if (page_zone_id(page) != page_zone_id(buddy))
		return 0;

	if (PageBuddy(buddy) && page_order(buddy) == order) {
		BUG_ON(page_count(buddy) != 0);
		return 1;
	}
	return 0;
}

/*
 * Freeing function for a buddy system allocator.
 *
 * The concept of a buddy system is to maintain direct-mapped table
 * (containing bit values) for memory blocks of various "orders".
 * The bottom level table contains the map for the smallest allocatable
 * units of memory (here, pages), and each level above it describes
 * pairs of units from the levels below, hence, "buddies".
 * At a high level, all that happens here is marking the table entry
 * at the bottom level available, and propagating the changes upward
 * as necessary, plus some accounting needed to play nicely with other
 * parts of the VM system.
 * At each level, we keep a list of pages, which are heads of continuous
 * free pages of length of (1 << order) and marked with PG_buddy. Page's
 * order is recorded in page_private(page) field.
 * So when we are allocating or freeing one, we can derive the state of the
 * other.  That is, if we allocate a small block, and both were   
 * free, the remainder of the region must be split into blocks.   
 * If a block is freed, and its buddy is also free, then this
 * triggers coalescing into a block of larger size.            
 *
 * -- wli
 */

static inline void __free_one_page(struct page *page,
		struct zone *zone, unsigned int order)
{
	unsigned long page_idx;
	int order_size = 1 << order;

	if (unlikely(PageCompound(page)))
		destroy_compound_page(page, order);

	page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1);

	VM_BUG_ON(page_idx & (order_size - 1));
	VM_BUG_ON(bad_range(zone, page));

	zone->free_pages += order_size;
	while (order < MAX_ORDER-1) {
		unsigned long combined_idx;
		struct free_area *area;
		struct page *buddy;

		buddy = __page_find_buddy(page, page_idx, order);
		if (!page_is_buddy(page, buddy, order))
			break;		/* Move the buddy up one level. */

		list_del(&buddy->lru);
		area = zone->free_area + order;
		area->nr_free--;
		rmv_page_order(buddy);
		combined_idx = __find_combined_index(page_idx, order);
		page = page + (combined_idx - page_idx);
		page_idx = combined_idx;
		order++;
	}
	set_page_order(page, order);
	list_add(&page->lru, &zone->free_area[order].free_list);
	zone->free_area[order].nr_free++;
}

static inline int free_pages_check(struct page *page)
{
	if (unlikely(page_mapcount(page) |
		(page->mapping != NULL)  |
		(page_count(page) != 0)  |
		(page->flags & (
			1 << PG_lru	|
			1 << PG_private |
			1 << PG_locked	|
			1 << PG_active	|
			1 << PG_reclaim	|
			1 << PG_slab	|
			1 << PG_swapcache |
			1 << PG_writeback |
			1 << PG_reserved |
			1 << PG_buddy ))))
		bad_page(page);
	if (PageDirty(page))
		__ClearPageDirty(page);
	/*
	 * For now, we report if PG_reserved was found set, but do not
	 * clear it, and do not free the page.  But we shall soon need
	 * to do more, for when the ZERO_PAGE count wraps negative.
	 */
	return PageReserved(page);
}

/*
 * Frees a list of pages. 
 * Assumes all pages on list are in same zone, and of same order.
 * count is the number of pages to free.
 *
 * If the zone was previously in an "all pages pinned" state then look to
 * see if this freeing clears that state.
 *
 * And clear the zone's pages_scanned counter, to hold off the "all pages are
 * pinned" detection logic.
 */
static void free_pages_bulk(struct zone *zone, int count,
					struct list_head *list, int order)
{
	spin_lock(&zone->lock);
	zone->all_unreclaimable = 0;
	zone->pages_scanned = 0;
	while (count--) {
		struct page *page;

		VM_BUG_ON(list_empty(list));
		page = list_entry(list->prev, struct page, lru);
		/* have to delete it as __free_one_page list manipulates */
		list_del(&page->lru);
		__free_one_page(page, zone, order);
	}
	spin_unlock(&zone->lock);
}

static void free_one_page(struct zone *zone, struct page *page, int order)
{
	spin_lock(&zone->lock);
	zone->all_unreclaimable = 0;
	zone->pages_scanned = 0;
	__free_one_page(page, zone, order);
	spin_unlock(&zone->lock);
}

static void __free_pages_ok(struct page *page, unsigned int order)
{
	unsigned long flags;
	int i;
	int reserved = 0;

	for (i = 0 ; i < (1 << order) ; ++i)
		reserved += free_pages_check(page + i);
	if (reserved)
		return;

	if (!PageHighMem(page))
		debug_check_no_locks_freed(page_address(page),PAGE_SIZE<<order);
	arch_free_page(page, order);
	kernel_map_pages(page, 1 << order, 0);

	local_irq_save(flags);
	__count_vm_events(PGFREE, 1 << order);
	free_one_page(page_zone(page), page, order);
	local_irq_restore(flags);
}

/*
 * permit the bootmem allocator to evade page validation on high-order frees
 */
void fastcall __init __free_pages_bootmem(struct page *page, unsigned int order)
{
	if (order == 0) {
		__ClearPageReserved(page);
		set_page_count(page, 0);
		set_page_refcounted(page);
		__free_page(page);
	} else {
		int loop;

		prefetchw(page);
		for (loop = 0; loop < BITS_PER_LONG; loop++) {
			struct page *p = &page[loop];

			if (loop + 1 < BITS_PER_LONG)
				prefetchw(p + 1);
			__ClearPageReserved(p);
			set_page_count(p, 0);
		}

		set_page_refcounted(page);
		__free_pages(page, order);
	}
}


/*
 * The order of subdivision here is critical for the IO subsystem.
 * Please do not alter this order without good reasons and regression
 * testing. Specifically, as large blocks of memory are subdivided,
 * the order in which smaller blocks are delivered depends on the order
 * they're subdivided in this function. This is the primary factor
 * influencing the order in which pages are delivered to the IO
 * subsystem according to empirical testing, and this is also justified
 * by considering the behavior of a buddy system containing a single
 * large block of memory acted on by a series of small allocations.
 * This behavior is a critical factor in sglist merging's success.
 *
 * -- wli
 */
static inline void expand(struct zone *zone, struct page *page,
 	int low, int high, struct free_area *area)
{
	unsigned long size = 1 << high;

	while (high > low) {
		area--;
		high--;
		size >>= 1;
		VM_BUG_ON(bad_range(zone, &page[size]));
		list_add(&page[size].lru, &area->free_list);
		area->nr_free++;
		set_page_order(&page[size], high);
	}
}

/*
 * This page is about to be returned from the page allocator
 */
static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
{
	if (unlikely(page_mapcount(page) |
		(page->mapping != NULL)  |
		(page_count(page) != 0)  |
		(page->flags & (
			1 << PG_lru	|
			1 << PG_private	|
			1 << PG_locked	|
			1 << PG_active	|
			1 << PG_dirty	|
			1 << PG_reclaim	|
			1 << PG_slab    |
			1 << PG_swapcache |
			1 << PG_writeback |
			1 << PG_reserved |
			1 << PG_buddy ))))
		bad_page(page);

	/*
	 * For now, we report if PG_reserved was found set, but do not
	 * clear it, and do not allocate the page: as a safety net.
	 */
	if (PageReserved(page))
		return 1;

	page->flags &= ~(1 << PG_uptodate | 1 << PG_error |
			1 << PG_referenced | 1 << PG_arch_1 |
			1 << PG_checked | 1 << PG_mappedtodisk);
	set_page_private(page, 0);
	set_page_refcounted(page);

	arch_alloc_page(page, order);
	kernel_map_pages(page, 1 << order, 1);

	if (gfp_flags & __GFP_ZERO)
		prep_zero_page(page, order, gfp_flags);

	if (order && (gfp_flags & __GFP_COMP))
		prep_compound_page(page, order);

	return 0;
}

/* 
 * Do the hard work of removing an element from the buddy allocator.
 * Call me with the zone->lock already held.
 */
static struct page *__rmqueue(struct zone *zone, unsigned int order)
{
	struct free_area * area;
	unsigned int current_order;
	struct page *page;

	for (current_order = order; current_order < MAX_ORDER; ++current_order) {
		area = zone->free_area + current_order;
		if (list_empty(&area->free_list))
			continue;

		page = list_entry(area->free_list.next, struct page, lru);
		list_del(&page->lru);
		rmv_page_order(page);
		area->nr_free--;
		zone->free_pages -= 1UL << order;
		expand(zone, page, order, current_order, area);
		return page;
	}

	return NULL;
}

/* 
 * Obtain a specified number of elements from the buddy allocator, all under
 * a single hold of the lock, for efficiency.  Add them to the supplied list.
 * Returns the number of new pages which were placed at *list.
 */
static int rmqueue_bulk(struct zone *zone, unsigned int order, 
			unsigned long count, struct list_head *list)
{
	int i;
	
	spin_lock(&zone->lock);
	for (i = 0; i < count; ++i) {
		struct page *page = __rmqueue(zone, order);
		if (unlikely(page == NULL))
			break;
		list_add_tail(&page->lru, list);
	}
	spin_unlock(&zone->lock);
	return i;
}

#ifdef CONFIG_NUMA
/*
 * Called from the slab reaper to drain pagesets on a particular node that
 * belongs to the currently executing processor.
 * Note that this function must be called with the thread pinned to
 * a single processor.
 */
void drain_node_pages(int nodeid)
{
	int i;
	enum zone_type z;
	unsigned long flags;

	for (z = 0; z < MAX_NR_ZONES; z++) {
		struct zone *zone = NODE_DATA(nodeid)->node_zones + z;
		struct per_cpu_pageset *pset;

		if (!populated_zone(zone))
			continue;

		pset = zone_pcp(zone, smp_processor_id());
		for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
			struct per_cpu_pages *pcp;

			pcp = &pset->pcp[i];
			if (pcp->count) {
				local_irq_save(flags);
				free_pages_bulk(zone, pcp->count, &pcp->list, 0);
				pcp->count = 0;
				local_irq_restore(flags);
			}
		}
	}
}
#endif

#if defined(CONFIG_PM) || defined(CONFIG_HOTPLUG_CPU)
static void __drain_pages(unsigned int cpu)
{
	unsigned long flags;
	struct zone *zone;
	int i;

	for_each_zone(zone) {
		struct per_cpu_pageset *pset;

		pset = zone_pcp(zone, cpu);
		for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
			struct per_cpu_pages *pcp;

			pcp = &pset->pcp[i];
			local_irq_save(flags);
			free_pages_bulk(zone, pcp->count, &pcp->list, 0);
			pcp->count = 0;
			local_irq_restore(flags);
		}
	}
}
#endif /* CONFIG_PM || CONFIG_HOTPLUG_CPU */

#ifdef CONFIG_PM

void mark_free_pages(struct zone *zone)
{
	unsigned long pfn, max_zone_pfn;
	unsigned long flags;
	int order;
	struct list_head *curr;

	if (!zone->spanned_pages)
		return;

	spin_lock_irqsave(&zone->lock, flags);

	max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
	for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
		if (pfn_valid(pfn)) {
			struct page *page = pfn_to_page(pfn);

			if (!PageNosave(page))
				ClearPageNosaveFree(page);
		}

	for (order = MAX_ORDER - 1; order >= 0; --order)
		list_for_each(curr, &zone->free_area[order].free_list) {
			unsigned long i;

			pfn = page_to_pfn(list_entry(curr, struct page, lru));
			for (i = 0; i < (1UL << order); i++)
				SetPageNosaveFree(pfn_to_page(pfn + i));
		}

	spin_unlock_irqrestore(&zone->lock, flags);
}

/*
 * Spill all of this CPU's per-cpu pages back into the buddy allocator.
 */
void drain_local_pages(void)
{
	unsigned long flags;

	local_irq_save(flags);	
	__drain_pages(smp_processor_id());
	local_irq_restore(flags);	
}
#endif /* CONFIG_PM */

/*
 * Free a 0-order page
 */
static void fastcall free_hot_cold_page(struct page *page, int cold)
{
	struct zone *zone = page_zone(page);
	struct per_cpu_pages *pcp;
	unsigned long flags;

	if (PageAnon(page))
		page->mapping = NULL;
	if (free_pages_check(page))
		return;

	if (!PageHighMem(page))
		debug_check_no_locks_freed(page_address(page), PAGE_SIZE);
	arch_free_page(page, 0);
	kernel_map_pages(page, 1, 0);

	pcp = &zone_pcp(zone, get_cpu())->pcp[cold];
	local_irq_save(flags);
	__count_vm_event(PGFREE);
	list_add(&page->lru, &pcp->list);
	pcp->count++;
	if (pcp->count >= pcp->high) {
		free_pages_bulk(zone, pcp->batch, &pcp->list, 0);
		pcp->count -= pcp->batch;
	}
	local_irq_restore(flags);
	put_cpu();
}

void fastcall free_hot_page(struct page *page)
{
	free_hot_cold_page(page, 0);
}
	
void fastcall free_cold_page(struct page *page)
{
	free_hot_cold_page(page, 1);
}

/*
 * split_page takes a non-compound higher-order page, and splits it into
 * n (1<<order) sub-pages: page[0..n]
 * Each sub-page must be freed individually.
 *
 * Note: this is probably too low level an operation for use in drivers.
 * Please consult with lkml before using this in your driver.
 */
void split_page(struct page *page, unsigned int order)
{
	int i;

	VM_BUG_ON(PageCompound(page));
	VM_BUG_ON(!page_count(page));
	for (i = 1; i < (1 << order); i++)
		set_page_refcounted(page + i);
}

/*
 * Really, prep_compound_page() should be called from __rmqueue_bulk().  But
 * we cheat by calling it from here, in the order > 0 path.  Saves a branch
 * or two.
 */
static struct page *buffered_rmqueue(struct zonelist *zonelist,
			struct zone *zone, int order, gfp_t gfp_flags)
{
	unsigned long flags;
	struct page *page;
	int cold = !!(gfp_flags & __GFP_COLD);
	int cpu;

again:
	cpu  = get_cpu();
	if (likely(order == 0)) {
		struct per_cpu_pages *pcp;

		pcp = &zone_pcp(zone, cpu)->pcp[cold];
		local_irq_save(flags);
		if (!pcp->count) {
			pcp->count = rmqueue_bulk(zone, 0,
						pcp->batch, &pcp->list);
			if (unlikely(!pcp->count))
				goto failed;
		}
		page = list_entry(pcp->list.next, struct page, lru);
		list_del(&page->lru);
		pcp->count--;
	} else {
		spin_lock_irqsave(&zone->lock, flags);
		page = __rmqueue(zone, order);
		spin_unlock(&zone->lock);
		if (!page)
			goto failed;
	}

	__count_zone_vm_events(PGALLOC, zone, 1 << order);
	zone_statistics(zonelist, zone);
	local_irq_restore(flags);
	put_cpu();

	VM_BUG_ON(bad_range(zone, page));
	if (prep_new_page(page, order, gfp_flags))
		goto again;
	return page;

failed:
	local_irq_restore(flags);
	put_cpu();
	return NULL;
}

#define ALLOC_NO_WATERMARKS	0x01 /* don't check watermarks at all */
#define ALLOC_WMARK_MIN		0x02 /* use pages_min watermark */
#define ALLOC_WMARK_LOW		0x04 /* use pages_low watermark */
#define ALLOC_WMARK_HIGH	0x08 /* use pages_high watermark */
#define ALLOC_HARDER		0x10 /* try to alloc harder */
#define ALLOC_HIGH		0x20 /* __GFP_HIGH set */
#define ALLOC_CPUSET		0x40 /* check for correct cpuset */

/*
 * Return 1 if free pages are above 'mark'. This takes into account the order
 * of the allocation.
 */
int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
		      int classzone_idx, int alloc_flags)
{
	/* free_pages my go negative - that's OK */
	unsigned long min = mark;
	long free_pages = z->free_pages - (1 << order) + 1;
	int o;

	if (alloc_flags & ALLOC_HIGH)
		min -= min / 2;
	if (alloc_flags & ALLOC_HARDER)
		min -= min / 4;

	if (free_pages <= min + z->lowmem_reserve[classzone_idx])
		return 0;
	for (o = 0; o < order; o++) {
		/* At the next order, this order's pages become unavailable */
		free_pages -= z->free_area[o].nr_free << o;

		/* Require fewer higher order pages to be free */
		min >>= 1;

		if (free_pages <= min)
			return 0;
	}
	return 1;
}

#ifdef CONFIG_NUMA
/*
 * zlc_setup - Setup for "zonelist cache".  Uses cached zone data to
 * skip over zones that are not allowed by the cpuset, or that have
 * been recently (in last second) found to be nearly full.  See further
 * comments in mmzone.h.  Reduces cache footprint of zonelist scans
 * that have to skip over alot of full or unallowed zones.
 *
 * If the zonelist cache is present in the passed in zonelist, then
 * returns a pointer to the allowed node mask (either the current
 * tasks mems_allowed, or node_online_map.)
 *
 * If the zonelist cache is not available for this zonelist, does
 * nothing and returns NULL.
 *
 * If the fullzones BITMAP in the zonelist cache is stale (more than
 * a second since last zap'd) then we zap it out (clear its bits.)
 *
 * We hold off even calling zlc_setup, until after we've checked the
 * first zone in the zonelist, on the theory that most allocations will
 * be satisfied from that first zone, so best to examine that zone as
 * quickly as we can.
 */
static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
{
	struct zonelist_cache *zlc;	/* cached zonelist speedup info */
	nodemask_t *allowednodes;	/* zonelist_cache approximation */

	zlc = zonelist->zlcache_ptr;
	if (!zlc)
		return NULL;

	if (jiffies - zlc->last_full_zap > 1 * HZ) {
		bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
		zlc->last_full_zap = jiffies;
	}

	allowednodes = !in_interrupt() && (alloc_flags & ALLOC_CPUSET) ?
					&cpuset_current_mems_allowed :
					&node_online_map;
	return allowednodes;
}

/*
 * Given 'z' scanning a zonelist, run a couple of quick checks to see
 * if it is worth looking at further for free memory:
 *  1) Check that the zone isn't thought to be full (doesn't have its
 *     bit set in the zonelist_cache fullzones BITMAP).
 *  2) Check that the zones node (obtained from the zonelist_cache
 *     z_to_n[] mapping) is allowed in the passed in allowednodes mask.
 * Return true (non-zero) if zone is worth looking at further, or
 * else return false (zero) if it is not.
 *
 * This check -ignores- the distinction between various watermarks,
 * such as GFP_HIGH, GFP_ATOMIC, PF_MEMALLOC, ...  If a zone is
 * found to be full for any variation of these watermarks, it will
 * be considered full for up to one second by all requests, unless
 * we are so low on memory on all allowed nodes that we are forced
 * into the second scan of the zonelist.
 *
 * In the second scan we ignore this zonelist cache and exactly
 * apply the watermarks to all zones, even it is slower to do so.
 * We are low on memory in the second scan, and should leave no stone
 * unturned looking for a free page.
 */
static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zone **z,
						nodemask_t *allowednodes)
{
	struct zonelist_cache *zlc;	/* cached zonelist speedup info */
	int i;				/* index of *z in zonelist zones */
	int n;				/* node that zone *z is on */

	zlc = zonelist->zlcache_ptr;
	if (!zlc)
		return 1;

	i = z - zonelist->zones;
	n = zlc->z_to_n[i];

	/* This zone is worth trying if it is allowed but not full */
	return node_isset(n, *allowednodes) && !test_bit(i, zlc->fullzones);
}

/*
 * Given 'z' scanning a zonelist, set the corresponding bit in
 * zlc->fullzones, so that subsequent attempts to allocate a page
 * from that zone don't waste time re-examining it.
 */
static void zlc_mark_zone_full(struct zonelist *zonelist, struct zone **z)
{
	struct zonelist_cache *zlc;	/* cached zonelist speedup info */
	int i;				/* index of *z in zonelist zones */

	zlc = zonelist->zlcache_ptr;
	if (!zlc)
		return;

	i = z - zonelist->zones;

	set_bit(i, zlc->fullzones);
}

#else	/* CONFIG_NUMA */

static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
{
	return NULL;
}

static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zone **z,
				nodemask_t *allowednodes)
{
	return 1;
}

static void zlc_mark_zone_full(struct zonelist *zonelist, struct zone **z)
{
}
#endif	/* CONFIG_NUMA */

/*
 * get_page_from_freelist goes through the zonelist trying to allocate
 * a page.
 */
static struct page *
get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
		struct zonelist *zonelist, int alloc_flags)
{
	struct zone **z;
	struct page *page = NULL;
	int classzone_idx = zone_idx(zonelist->zones[0]);
	struct zone *zone;
	nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */
	int zlc_active = 0;		/* set if using zonelist_cache */
	int did_zlc_setup = 0;		/* just call zlc_setup() one time */

zonelist_scan:
	/*
	 * Scan zonelist, looking for a zone with enough free.
	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
	 */
	z = zonelist->zones;

	do {
		if (NUMA_BUILD && zlc_active &&
			!zlc_zone_worth_trying(zonelist, z, allowednodes))
				continue;
		zone = *z;
		if (unlikely(NUMA_BUILD && (gfp_mask & __GFP_THISNODE) &&
			zone->zone_pgdat != zonelist->zones[0]->zone_pgdat))
				break;
		if ((alloc_flags & ALLOC_CPUSET) &&
			!cpuset_zone_allowed(zone, gfp_mask))
				goto try_next_zone;

		if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
			unsigned long mark;
			if (alloc_flags & ALLOC_WMARK_MIN)
				mark = zone->pages_min;
			else if (alloc_flags & ALLOC_WMARK_LOW)
				mark = zone->pages_low;
			else
				mark = zone->pages_high;
			if (!zone_watermark_ok(zone, order, mark,
				    classzone_idx, alloc_flags)) {
				if (!zone_reclaim_mode ||
				    !zone_reclaim(zone, gfp_mask, order))
					goto this_zone_full;
			}
		}

		page = buffered_rmqueue(zonelist, zone, order, gfp_mask);
		if (page)
			break;
this_zone_full:
		if (NUMA_BUILD)
			zlc_mark_zone_full(zonelist, z);
try_next_zone:
		if (NUMA_BUILD && !did_zlc_setup) {
			/* we do zlc_setup after the first zone is tried */
			allowednodes = zlc_setup(zonelist, alloc_flags);
			zlc_active = 1;
			did_zlc_setup = 1;
		}
	} while (*(++z) != NULL);

	if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) {
		/* Disable zlc cache for second zonelist scan */
		zlc_active = 0;
		goto zonelist_scan;
	}
	return page;
}

/*
 * This is the 'heart' of the zoned buddy allocator.
 */
struct page * fastcall
__alloc_pages(gfp_t gfp_mask, unsigned int order,
		struct zonelist *zonelist)
{
	const gfp_t wait = gfp_mask & __GFP_WAIT;
	struct zone **z;
	struct page *page;
	struct reclaim_state reclaim_state;
	struct task_struct *p = current;
	int do_retry;
	int alloc_flags;
	int did_some_progress;

	might_sleep_if(wait);

restart:
	z = zonelist->zones;  /* the list of zones suitable for gfp_mask */

	if (unlikely(*z == NULL)) {
		/* Should this ever happen?? */
		return NULL;
	}

	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
				zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET);
	if (page)
		goto got_pg;

	for (z = zonelist->zones; *z; z++)
		wakeup_kswapd(*z, order);

	/*
	 * OK, we're below the kswapd watermark and have kicked background
	 * reclaim. Now things get more complex, so set up alloc_flags according
	 * to how we want to proceed.
	 *
	 * The caller may dip into page reserves a bit more if the caller
	 * cannot run direct reclaim, or if the caller has realtime scheduling
	 * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
	 * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
	 */
	alloc_flags = ALLOC_WMARK_MIN;
	if ((unlikely(rt_task(p)) && !in_interrupt()) || !wait)
		alloc_flags |= ALLOC_HARDER;
	if (gfp_mask & __GFP_HIGH)
		alloc_flags |= ALLOC_HIGH;
	if (wait)
		alloc_flags |= ALLOC_CPUSET;

	/*
	 * Go through the zonelist again. Let __GFP_HIGH and allocations
	 * coming from realtime tasks go deeper into reserves.
	 *
	 * This is the last chance, in general, before the goto nopage.
	 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
	 */
	page = get_page_from_freelist(gfp_mask, order, zonelist, alloc_flags);
	if (page)
		goto got_pg;

	/* This allocation should allow future memory freeing. */

rebalance:
	if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
			&& !in_interrupt()) {
		if (!(gfp_mask & __GFP_NOMEMALLOC)) {
nofail_alloc:
			/* go through the zonelist yet again, ignoring mins */
			page = get_page_from_freelist(gfp_mask, order,
				zonelist, ALLOC_NO_WATERMARKS);
			if (page)
				goto got_pg;
			if (gfp_mask & __GFP_NOFAIL) {
				congestion_wait(WRITE, HZ/50);
				goto nofail_alloc;
			}
		}
		goto nopage;
	}

	/* Atomic allocations - we can't balance anything */
	if (!wait)
		goto nopage;

	cond_resched();

	/* We now go into synchronous reclaim */
	cpuset_memory_pressure_bump();
	p->flags |= PF_MEMALLOC;
	reclaim_state.reclaimed_slab = 0;
	p->reclaim_state = &reclaim_state;

	did_some_progress = try_to_free_pages(zonelist->zones, gfp_mask);

	p->reclaim_state = NULL;
	p->flags &= ~PF_MEMALLOC;

	cond_resched();

	if (likely(did_some_progress)) {
		page = get_page_from_freelist(gfp_mask, order,
						zonelist, alloc_flags);
		if (page)
			goto got_pg;
	} else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
		/*
		 * Go through the zonelist yet one more time, keep
		 * very high watermark here, this is only to catch
		 * a parallel oom killing, we must fail if we're still
		 * under heavy pressure.
		 */
		page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
				zonelist, ALLOC_WMARK_HIGH|ALLOC_CPUSET);
		if (page)
			goto got_pg;

		out_of_memory(zonelist, gfp_mask, order);
		goto restart;
	}

	/*
	 * Don't let big-order allocations loop unless the caller explicitly
	 * requests that.  Wait for some write requests to complete then retry.
	 *
	 * In this implementation, __GFP_REPEAT means __GFP_NOFAIL for order
	 * <= 3, but that may not be true in other implementations.
	 */
	do_retry = 0;
	if (!(gfp_mask & __GFP_NORETRY)) {
		if ((order <= 3) || (gfp_mask & __GFP_REPEAT))
			do_retry = 1;
		if (gfp_mask & __GFP_NOFAIL)
			do_retry = 1;
	}
	if (do_retry) {
		congestion_wait(WRITE, HZ/50);
		goto rebalance;
	}

nopage:
	if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) {
		printk(KERN_WARNING "%s: page allocation failure."
			" order:%d, mode:0x%x\n",
			p->comm, order, gfp_mask);
		dump_stack();
		show_mem();
	}
got_pg:
	return page;
}

EXPORT_SYMBOL(__alloc_pages);

/*
 * Common helper functions.
 */
fastcall unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
{
	struct page * page;
	page = alloc_pages(gfp_mask, order);
	if (!page)
		return 0;
	return (unsigned long) page_address(page);
}

EXPORT_SYMBOL(__get_free_pages);

fastcall unsigned long get_zeroed_page(gfp_t gfp_mask)
{
	struct page * page;

	/*
	 * get_zeroed_page() returns a 32-bit address, which cannot represent
	 * a highmem page
	 */
	VM_BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0);

	page = alloc_pages(gfp_mask | __GFP_ZERO, 0);
	if (page)
		return (unsigned long) page_address(page);
	return 0;
}

EXPORT_SYMBOL(get_zeroed_page);

void __pagevec_free(struct pagevec *pvec)
{
	int i = pagevec_count(pvec);

	while (--i >= 0)
		free_hot_cold_page(pvec->pages[i], pvec->cold);
}

fastcall void __free_pages(struct page *page, unsigned int order)
{
	if (put_page_testzero(page)) {
		if (order == 0)
			free_hot_page(page);
		else
			__free_pages_ok(page, order);
	}
}

EXPORT_SYMBOL(__free_pages);

fastcall void free_pages(unsigned long addr, unsigned int order)
{
	if (addr != 0) {
		VM_BUG_ON(!virt_addr_valid((void *)addr));
		__free_pages(virt_to_page((void *)addr), order);
	}
}

EXPORT_SYMBOL(free_pages);

/*
 * Total amount of free (allocatable) RAM:
 */
unsigned int nr_free_pages(void)
{
	unsigned int sum = 0;
	struct zone *zone;

	for_each_zone(zone)
		sum += zone->free_pages;

	return sum;
}

EXPORT_SYMBOL(nr_free_pages);

#ifdef CONFIG_NUMA
unsigned int nr_free_pages_pgdat(pg_data_t *pgdat)
{
	unsigned int sum = 0;
	enum zone_type i;

	for (i = 0; i < MAX_NR_ZONES; i++)
		sum += pgdat->node_zones[i].free_pages;

	return sum;
}
#endif

static unsigned int nr_free_zone_pages(int offset)
{
	/* Just pick one node, since fallback list is circular */
	pg_data_t *pgdat = NODE_DATA(numa_node_id());
	unsigned int sum = 0;

	struct zonelist *zonelist = pgdat->node_zonelists + offset;
	struct zone **zonep = zonelist->zones;
	struct zone *zone;

	for (zone = *zonep++; zone; zone = *zonep++) {
		unsigned long size = zone->present_pages;
		unsigned long high = zone->pages_high;
		if (size > high)
			sum += size - high;
	}

	return sum;
}

/*
 * Amount of free RAM allocatable within ZONE_DMA and ZONE_NORMAL
 */
unsigned int nr_free_buffer_pages(void)
{
	return nr_free_zone_pages(gfp_zone(GFP_USER));
}

/*
 * Amount of free RAM allocatable within all zones
 */
unsigned int nr_free_pagecache_pages(void)
{
	return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER));
}

static inline void show_node(struct zone *zone)
{
	if (NUMA_BUILD)
		printk("Node %ld ", zone_to_nid(zone));
}

void si_meminfo(struct sysinfo *val)
{
	val->totalram = totalram_pages;
	val->sharedram = 0;
	val->freeram = nr_free_pages();
	val->bufferram = nr_blockdev_pages();
	val->totalhigh = totalhigh_pages;
	val->freehigh = nr_free_highpages();
	val->mem_unit = PAGE_SIZE;
}

EXPORT_SYMBOL(si_meminfo);

#ifdef CONFIG_NUMA
void si_meminfo_node(struct sysinfo *val, int nid)
{
	pg_data_t *pgdat = NODE_DATA(nid);

	val->totalram = pgdat->node_present_pages;
	val->freeram = nr_free_pages_pgdat(pgdat);
#ifdef CONFIG_HIGHMEM
	val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].present_pages;
	val->freehigh = pgdat->node_zones[ZONE_HIGHMEM].free_pages;
#else
	val->totalhigh = 0;
	val->freehigh = 0;
#endif
	val->mem_unit = PAGE_SIZE;
}
#endif

#define K(x) ((x) << (PAGE_SHIFT-10))

/*
 * Show free area list (used inside shift_scroll-lock stuff)
 * We also calculate the percentage fragmentation. We do this by counting the
 * memory on each free list with the exception of the first item on the list.
 */
void show_free_areas(void)
{
	int cpu;
	unsigned long active;
	unsigned long inactive;
	unsigned long free;
	struct zone *zone;

	for_each_zone(zone) {
		if (!populated_zone(zone))
			continue;

		show_node(zone);
		printk("%s per-cpu:\n", zone->name);

		for_each_online_cpu(cpu) {
			struct per_cpu_pageset *pageset;

			pageset = zone_pcp(zone, cpu);

			printk("CPU %4d: Hot: hi:%5d, btch:%4d usd:%4d   "
			       "Cold: hi:%5d, btch:%4d usd:%4d\n",
			       cpu, pageset->pcp[0].high,
			       pageset->pcp[0].batch, pageset->pcp[0].count,
			       pageset->pcp[1].high, pageset->pcp[1].batch,
			       pageset->pcp[1].count);
		}
	}

	get_zone_counts(&active, &inactive, &free);

	printk("Active:%lu inactive:%lu dirty:%lu writeback:%lu "
		"unstable:%lu free:%u slab:%lu mapped:%lu pagetables:%lu\n",
		active,
		inactive,
		global_page_state(NR_FILE_DIRTY),
		global_page_state(NR_WRITEBACK),
		global_page_state(NR_UNSTABLE_NFS),
		nr_free_pages(),
		global_page_state(NR_SLAB_RECLAIMABLE) +
			global_page_state(NR_SLAB_UNRECLAIMABLE),
		global_page_state(NR_FILE_MAPPED),
		global_page_state(NR_PAGETABLE));

	for_each_zone(zone) {
		int i;

		if (!populated_zone(zone))
			continue;

		show_node(zone);
		printk("%s"
			" free:%lukB"
			" min:%lukB"
			" low:%lukB"
			" high:%lukB"
			" active:%lukB"
			" inactive:%lukB"
			" present:%lukB"
			" pages_scanned:%lu"
			" all_unreclaimable? %s"
			"\n",
			zone->name,
			K(zone->free_pages),
			K(zone->pages_min),
			K(zone->pages_low),
			K(zone->pages_high),
			K(zone->nr_active),
			K(zone->nr_inactive),
			K(zone->present_pages),
			zone->pages_scanned,
			(zone->all_unreclaimable ? "yes" : "no")
			);
		printk("lowmem_reserve[]:");
		for (i = 0; i < MAX_NR_ZONES; i++)
			printk(" %lu", zone->lowmem_reserve[i]);
		printk("\n");
	}

	for_each_zone(zone) {
 		unsigned long nr[MAX_ORDER], flags, order, total = 0;

		if (!populated_zone(zone))
			continue;

		show_node(zone);
		printk("%s: ", zone->name);

		spin_lock_irqsave(&zone->lock, flags);
		for (order = 0; order < MAX_ORDER; order++) {
			nr[order] = zone->free_area[order].nr_free;
			total += nr[order] << order;
		}
		spin_unlock_irqrestore(&zone->lock, flags);
		for (order = 0; order < MAX_ORDER; order++)
			printk("%lu*%lukB ", nr[order], K(1UL) << order);
		printk("= %lukB\n", K(total));
	}

	show_swap_cache_info();
}

/*
 * Builds allocation fallback zone lists.
 *
 * Add all populated zones of a node to the zonelist.
 */
static int __meminit build_zonelists_node(pg_data_t *pgdat,
			struct zonelist *zonelist, int nr_zones, enum zone_type zone_type)
{
	struct zone *zone;

	BUG_ON(zone_type >= MAX_NR_ZONES);
	zone_type++;

	do {
		zone_type--;
		zone = pgdat->node_zones + zone_type;
		if (populated_zone(zone)) {
			zonelist->zones[nr_zones++] = zone;
			check_highest_zone(zone_type);
		}

	} while (zone_type);
	return nr_zones;
}

#ifdef CONFIG_NUMA
#define MAX_NODE_LOAD (num_online_nodes())
static int __meminitdata node_load[MAX_NUMNODES];
/**
 * find_next_best_node - find the next node that should appear in a given node's fallback list
 * @node: node whose fallback list we're appending
 * @used_node_mask: nodemask_t of already used nodes
 *
 * We use a number of factors to determine which is the next node that should
 * appear on a given node's fallback list.  The node should not have appeared
 * already in @node's fallback list, and it should be the next closest node
 * according to the distance array (which contains arbitrary distance values
 * from each node to each node in the system), and should also prefer nodes
 * with no CPUs, since presumably they'll have very little allocation pressure
 * on them otherwise.
 * It returns -1 if no node is found.
 */
static int __meminit find_next_best_node(int node, nodemask_t *used_node_mask)
{
	int n, val;
	int min_val = INT_MAX;
	int best_node = -1;

	/* Use the local node if we haven't already */
	if (!node_isset(node, *used_node_mask)) {
		node_set(node, *used_node_mask);
		return node;
	}