cpuset.c 59.9 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
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
/*
 *  kernel/cpuset.c
 *
 *  Processor and Memory placement constraints for sets of tasks.
 *
 *  Copyright (C) 2003 BULL SA.
 *  Copyright (C) 2004 Silicon Graphics, Inc.
 *
 *  Portions derived from Patrick Mochel's sysfs code.
 *  sysfs is Copyright (c) 2001-3 Patrick Mochel
 *  Portions Copyright (c) 2004 Silicon Graphics, Inc.
 *
 *  2003-10-10 Written by Simon Derr <simon.derr@bull.net>
 *  2003-10-22 Updates by Stephen Hemminger.
 *  2004 May-July Rework by Paul Jackson <pj@sgi.com>
 *
 *  This file is subject to the terms and conditions of the GNU General Public
 *  License.  See the file COPYING in the main directory of the Linux
 *  distribution for more details.
 */

#include <linux/config.h>
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/cpuset.h>
#include <linux/err.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
#include <linux/kmod.h>
#include <linux/list.h>
35
#include <linux/mempolicy.h>
Linus Torvalds's avatar
Linus Torvalds committed
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/pagemap.h>
#include <linux/proc_fs.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/smp_lock.h>
#include <linux/spinlock.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/time.h>
#include <linux/backing-dev.h>
#include <linux/sort.h>

#include <asm/uaccess.h>
#include <asm/atomic.h>
#include <asm/semaphore.h>

57
#define CPUSET_SUPER_MAGIC		0x27e0eb
Linus Torvalds's avatar
Linus Torvalds committed
58

59
60
61
62
63
64
65
66
67
/* See "Frequency meter" comments, below. */

struct fmeter {
	int cnt;		/* unprocessed events count */
	int val;		/* most recent output value */
	time_t time;		/* clock (secs) when val computed */
	spinlock_t lock;	/* guards read or write of above */
};

Linus Torvalds's avatar
Linus Torvalds committed
68
69
70
71
72
struct cpuset {
	unsigned long flags;		/* "unsigned long" so bitops work */
	cpumask_t cpus_allowed;		/* CPUs allowed to tasks in cpuset */
	nodemask_t mems_allowed;	/* Memory Nodes allowed to tasks */

73
74
75
	/*
	 * Count is atomic so can incr (fork) or decr (exit) without a lock.
	 */
Linus Torvalds's avatar
Linus Torvalds committed
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
	atomic_t count;			/* count tasks using this cpuset */

	/*
	 * We link our 'sibling' struct into our parents 'children'.
	 * Our children link their 'sibling' into our 'children'.
	 */
	struct list_head sibling;	/* my parents children */
	struct list_head children;	/* my children */

	struct cpuset *parent;		/* my parent */
	struct dentry *dentry;		/* cpuset fs entry */

	/*
	 * Copy of global cpuset_mems_generation as of the most
	 * recent time this cpuset changed its mems_allowed.
	 */
92
93
94
	int mems_generation;

	struct fmeter fmeter;		/* memory_pressure filter */
Linus Torvalds's avatar
Linus Torvalds committed
95
96
97
98
99
100
};

/* bits in struct cpuset flags field */
typedef enum {
	CS_CPU_EXCLUSIVE,
	CS_MEM_EXCLUSIVE,
101
	CS_MEMORY_MIGRATE,
Linus Torvalds's avatar
Linus Torvalds committed
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
	CS_REMOVED,
	CS_NOTIFY_ON_RELEASE
} cpuset_flagbits_t;

/* convenient tests for these bits */
static inline int is_cpu_exclusive(const struct cpuset *cs)
{
	return !!test_bit(CS_CPU_EXCLUSIVE, &cs->flags);
}

static inline int is_mem_exclusive(const struct cpuset *cs)
{
	return !!test_bit(CS_MEM_EXCLUSIVE, &cs->flags);
}

static inline int is_removed(const struct cpuset *cs)
{
	return !!test_bit(CS_REMOVED, &cs->flags);
}

static inline int notify_on_release(const struct cpuset *cs)
{
	return !!test_bit(CS_NOTIFY_ON_RELEASE, &cs->flags);
}

127
128
129
130
131
static inline int is_memory_migrate(const struct cpuset *cs)
{
	return !!test_bit(CS_MEMORY_MIGRATE, &cs->flags);
}

Linus Torvalds's avatar
Linus Torvalds committed
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
/*
 * Increment this atomic integer everytime any cpuset changes its
 * mems_allowed value.  Users of cpusets can track this generation
 * number, and avoid having to lock and reload mems_allowed unless
 * the cpuset they're using changes generation.
 *
 * A single, global generation is needed because attach_task() could
 * reattach a task to a different cpuset, which must not have its
 * generation numbers aliased with those of that tasks previous cpuset.
 *
 * Generations are needed for mems_allowed because one task cannot
 * modify anothers memory placement.  So we must enable every task,
 * on every visit to __alloc_pages(), to efficiently check whether
 * its current->cpuset->mems_allowed has changed, requiring an update
 * of its current->mems_allowed.
 */
static atomic_t cpuset_mems_generation = ATOMIC_INIT(1);

static struct cpuset top_cpuset = {
	.flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)),
	.cpus_allowed = CPU_MASK_ALL,
	.mems_allowed = NODE_MASK_ALL,
	.count = ATOMIC_INIT(0),
	.sibling = LIST_HEAD_INIT(top_cpuset.sibling),
	.children = LIST_HEAD_INIT(top_cpuset.children),
};

static struct vfsmount *cpuset_mount;
160
static struct super_block *cpuset_sb;
Linus Torvalds's avatar
Linus Torvalds committed
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
 * We have two global cpuset semaphores below.  They can nest.
 * It is ok to first take manage_sem, then nest callback_sem.  We also
 * require taking task_lock() when dereferencing a tasks cpuset pointer.
 * See "The task_lock() exception", at the end of this comment.
 *
 * A task must hold both semaphores to modify cpusets.  If a task
 * holds manage_sem, then it blocks others wanting that semaphore,
 * ensuring that it is the only task able to also acquire callback_sem
 * and be able to modify cpusets.  It can perform various checks on
 * the cpuset structure first, knowing nothing will change.  It can
 * also allocate memory while just holding manage_sem.  While it is
 * performing these checks, various callback routines can briefly
 * acquire callback_sem to query cpusets.  Once it is ready to make
 * the changes, it takes callback_sem, blocking everyone else.
 *
 * Calls to the kernel memory allocator can not be made while holding
 * callback_sem, as that would risk double tripping on callback_sem
 * from one of the callbacks into the cpuset code from within
 * __alloc_pages().
 *
 * If a task is only holding callback_sem, then it has read-only
 * access to cpusets.
 *
 * The task_struct fields mems_allowed and mems_generation may only
 * be accessed in the context of that task, so require no locks.
 *
 * Any task can increment and decrement the count field without lock.
 * So in general, code holding manage_sem or callback_sem can't rely
 * on the count field not changing.  However, if the count goes to
 * zero, then only attach_task(), which holds both semaphores, can
 * increment it again.  Because a count of zero means that no tasks
 * are currently attached, therefore there is no way a task attached
 * to that cpuset can fork (the other way to increment the count).
 * So code holding manage_sem or callback_sem can safely assume that
 * if the count is zero, it will stay zero.  Similarly, if a task
 * holds manage_sem or callback_sem on a cpuset with zero count, it
 * knows that the cpuset won't be removed, as cpuset_rmdir() needs
 * both of those semaphores.
 *
 * A possible optimization to improve parallelism would be to make
 * callback_sem a R/W semaphore (rwsem), allowing the callback routines
 * to proceed in parallel, with read access, until the holder of
 * manage_sem needed to take this rwsem for exclusive write access
 * and modify some cpusets.
 *
 * The cpuset_common_file_write handler for operations that modify
 * the cpuset hierarchy holds manage_sem across the entire operation,
 * single threading all such cpuset modifications across the system.
 *
 * The cpuset_common_file_read() handlers only hold callback_sem across
 * small pieces of code, such as when reading out possibly multi-word
 * cpumasks and nodemasks.
 *
 * The fork and exit callbacks cpuset_fork() and cpuset_exit(), don't
 * (usually) take either semaphore.  These are the two most performance
 * critical pieces of code here.  The exception occurs on cpuset_exit(),
 * when a task in a notify_on_release cpuset exits.  Then manage_sem
220
 * is taken, and if the cpuset count is zero, a usermode call made
Linus Torvalds's avatar
Linus Torvalds committed
221
222
223
 * to /sbin/cpuset_release_agent with the name of the cpuset (path
 * relative to the root of cpuset file system) as the argument.
 *
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
 * A cpuset can only be deleted if both its 'count' of using tasks
 * is zero, and its list of 'children' cpusets is empty.  Since all
 * tasks in the system use _some_ cpuset, and since there is always at
 * least one task in the system (init, pid == 1), therefore, top_cpuset
 * always has either children cpusets and/or using tasks.  So we don't
 * need a special hack to ensure that top_cpuset cannot be deleted.
 *
 * The above "Tale of Two Semaphores" would be complete, but for:
 *
 *	The task_lock() exception
 *
 * The need for this exception arises from the action of attach_task(),
 * which overwrites one tasks cpuset pointer with another.  It does
 * so using both semaphores, however there are several performance
 * critical places that need to reference task->cpuset without the
 * expense of grabbing a system global semaphore.  Therefore except as
 * noted below, when dereferencing or, as in attach_task(), modifying
 * a tasks cpuset pointer we use task_lock(), which acts on a spinlock
 * (task->alloc_lock) already in the task_struct routinely used for
 * such matters.
Linus Torvalds's avatar
Linus Torvalds committed
244
245
 */

246
247
static DECLARE_MUTEX(manage_sem);
static DECLARE_MUTEX(callback_sem);
248

Linus Torvalds's avatar
Linus Torvalds committed
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
/*
 * A couple of forward declarations required, due to cyclic reference loop:
 *  cpuset_mkdir -> cpuset_create -> cpuset_populate_dir -> cpuset_add_file
 *  -> cpuset_create_file -> cpuset_dir_inode_operations -> cpuset_mkdir.
 */

static int cpuset_mkdir(struct inode *dir, struct dentry *dentry, int mode);
static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry);

static struct backing_dev_info cpuset_backing_dev_info = {
	.ra_pages = 0,		/* No readahead */
	.capabilities	= BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
};

static struct inode *cpuset_new_inode(mode_t mode)
{
	struct inode *inode = new_inode(cpuset_sb);

	if (inode) {
		inode->i_mode = mode;
		inode->i_uid = current->fsuid;
		inode->i_gid = current->fsgid;
		inode->i_blksize = PAGE_CACHE_SIZE;
		inode->i_blocks = 0;
		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
		inode->i_mapping->backing_dev_info = &cpuset_backing_dev_info;
	}
	return inode;
}

static void cpuset_diput(struct dentry *dentry, struct inode *inode)
{
	/* is dentry a directory ? if so, kfree() associated cpuset */
	if (S_ISDIR(inode->i_mode)) {
		struct cpuset *cs = dentry->d_fsdata;
		BUG_ON(!(is_removed(cs)));
		kfree(cs);
	}
	iput(inode);
}

static struct dentry_operations cpuset_dops = {
	.d_iput = cpuset_diput,
};

static struct dentry *cpuset_get_dentry(struct dentry *parent, const char *name)
{
296
	struct dentry *d = lookup_one_len(name, parent, strlen(name));
Linus Torvalds's avatar
Linus Torvalds committed
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
	if (!IS_ERR(d))
		d->d_op = &cpuset_dops;
	return d;
}

static void remove_dir(struct dentry *d)
{
	struct dentry *parent = dget(d->d_parent);

	d_delete(d);
	simple_rmdir(parent->d_inode, d);
	dput(parent);
}

/*
 * NOTE : the dentry must have been dget()'ed
 */
static void cpuset_d_remove_dir(struct dentry *dentry)
{
	struct list_head *node;

	spin_lock(&dcache_lock);
	node = dentry->d_subdirs.next;
	while (node != &dentry->d_subdirs) {
		struct dentry *d = list_entry(node, struct dentry, d_child);
		list_del_init(node);
		if (d->d_inode) {
			d = dget_locked(d);
			spin_unlock(&dcache_lock);
			d_delete(d);
			simple_unlink(dentry->d_inode, d);
			dput(d);
			spin_lock(&dcache_lock);
		}
		node = dentry->d_subdirs.next;
	}
	list_del_init(&dentry->d_child);
	spin_unlock(&dcache_lock);
	remove_dir(dentry);
}

static struct super_operations cpuset_ops = {
	.statfs = simple_statfs,
	.drop_inode = generic_delete_inode,
};

static int cpuset_fill_super(struct super_block *sb, void *unused_data,
							int unused_silent)
{
	struct inode *inode;
	struct dentry *root;

	sb->s_blocksize = PAGE_CACHE_SIZE;
	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
	sb->s_magic = CPUSET_SUPER_MAGIC;
	sb->s_op = &cpuset_ops;
	cpuset_sb = sb;

	inode = cpuset_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR);
	if (inode) {
		inode->i_op = &simple_dir_inode_operations;
		inode->i_fop = &simple_dir_operations;
		/* directories start off with i_nlink == 2 (for "." entry) */
		inode->i_nlink++;
	} else {
		return -ENOMEM;
	}

	root = d_alloc_root(inode);
	if (!root) {
		iput(inode);
		return -ENOMEM;
	}
	sb->s_root = root;
	return 0;
}

static struct super_block *cpuset_get_sb(struct file_system_type *fs_type,
					int flags, const char *unused_dev_name,
					void *data)
{
	return get_sb_single(fs_type, flags, data, cpuset_fill_super);
}

static struct file_system_type cpuset_fs_type = {
	.name = "cpuset",
	.get_sb = cpuset_get_sb,
	.kill_sb = kill_litter_super,
};

/* struct cftype:
 *
 * The files in the cpuset filesystem mostly have a very simple read/write
 * handling, some common function will take care of it. Nevertheless some cases
 * (read tasks) are special and therefore I define this structure for every
 * kind of file.
 *
 *
 * When reading/writing to a file:
 *	- the cpuset to use in file->f_dentry->d_parent->d_fsdata
 *	- the 'cftype' of the file is file->f_dentry->d_fsdata
 */

struct cftype {
	char *name;
	int private;
	int (*open) (struct inode *inode, struct file *file);
	ssize_t (*read) (struct file *file, char __user *buf, size_t nbytes,
							loff_t *ppos);
	int (*write) (struct file *file, const char __user *buf, size_t nbytes,
							loff_t *ppos);
	int (*release) (struct inode *inode, struct file *file);
};

static inline struct cpuset *__d_cs(struct dentry *dentry)
{
	return dentry->d_fsdata;
}

static inline struct cftype *__d_cft(struct dentry *dentry)
{
	return dentry->d_fsdata;
}

/*
422
 * Call with manage_sem held.  Writes path of cpuset into buf.
Linus Torvalds's avatar
Linus Torvalds committed
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
 * Returns 0 on success, -errno on error.
 */

static int cpuset_path(const struct cpuset *cs, char *buf, int buflen)
{
	char *start;

	start = buf + buflen;

	*--start = '\0';
	for (;;) {
		int len = cs->dentry->d_name.len;
		if ((start -= len) < buf)
			return -ENAMETOOLONG;
		memcpy(start, cs->dentry->d_name.name, len);
		cs = cs->parent;
		if (!cs)
			break;
		if (!cs->parent)
			continue;
		if (--start < buf)
			return -ENAMETOOLONG;
		*start = '/';
	}
	memmove(buf, start, buf + buflen - start);
	return 0;
}

/*
 * Notify userspace when a cpuset is released, by running
 * /sbin/cpuset_release_agent with the name of the cpuset (path
 * relative to the root of cpuset file system) as the argument.
 *
 * Most likely, this user command will try to rmdir this cpuset.
 *
 * This races with the possibility that some other task will be
 * attached to this cpuset before it is removed, or that some other
 * user task will 'mkdir' a child cpuset of this cpuset.  That's ok.
 * The presumed 'rmdir' will fail quietly if this cpuset is no longer
 * unused, and this cpuset will be reprieved from its death sentence,
 * to continue to serve a useful existence.  Next time it's released,
 * we will get notified again, if it still has 'notify_on_release' set.
 *
466
467
468
469
470
471
472
473
 * The final arg to call_usermodehelper() is 0, which means don't
 * wait.  The separate /sbin/cpuset_release_agent task is forked by
 * call_usermodehelper(), then control in this thread returns here,
 * without waiting for the release agent task.  We don't bother to
 * wait because the caller of this routine has no use for the exit
 * status of the /sbin/cpuset_release_agent task, so no sense holding
 * our caller up for that.
 *
474
475
476
477
478
 * When we had only one cpuset semaphore, we had to call this
 * without holding it, to avoid deadlock when call_usermodehelper()
 * allocated memory.  With two locks, we could now call this while
 * holding manage_sem, but we still don't, so as to minimize
 * the time manage_sem is held.
Linus Torvalds's avatar
Linus Torvalds committed
479
480
 */

481
static void cpuset_release_agent(const char *pathbuf)
Linus Torvalds's avatar
Linus Torvalds committed
482
483
484
485
{
	char *argv[3], *envp[3];
	int i;

486
487
488
	if (!pathbuf)
		return;

Linus Torvalds's avatar
Linus Torvalds committed
489
490
	i = 0;
	argv[i++] = "/sbin/cpuset_release_agent";
491
	argv[i++] = (char *)pathbuf;
Linus Torvalds's avatar
Linus Torvalds committed
492
493
494
495
496
497
498
499
	argv[i] = NULL;

	i = 0;
	/* minimal command environment */
	envp[i++] = "HOME=/";
	envp[i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
	envp[i] = NULL;

500
501
	call_usermodehelper(argv[0], argv, envp, 0);
	kfree(pathbuf);
Linus Torvalds's avatar
Linus Torvalds committed
502
503
504
505
506
507
}

/*
 * Either cs->count of using tasks transitioned to zero, or the
 * cs->children list of child cpusets just became empty.  If this
 * cs is notify_on_release() and now both the user count is zero and
508
509
 * the list of children is empty, prepare cpuset path in a kmalloc'd
 * buffer, to be returned via ppathbuf, so that the caller can invoke
510
511
 * cpuset_release_agent() with it later on, once manage_sem is dropped.
 * Call here with manage_sem held.
512
513
514
515
516
 *
 * This check_for_release() routine is responsible for kmalloc'ing
 * pathbuf.  The above cpuset_release_agent() is responsible for
 * kfree'ing pathbuf.  The caller of these routines is responsible
 * for providing a pathbuf pointer, initialized to NULL, then
517
518
 * calling check_for_release() with manage_sem held and the address
 * of the pathbuf pointer, then dropping manage_sem, then calling
519
 * cpuset_release_agent() with pathbuf, as set by check_for_release().
Linus Torvalds's avatar
Linus Torvalds committed
520
521
 */

522
static void check_for_release(struct cpuset *cs, char **ppathbuf)
Linus Torvalds's avatar
Linus Torvalds committed
523
524
525
526
527
528
529
530
531
{
	if (notify_on_release(cs) && atomic_read(&cs->count) == 0 &&
	    list_empty(&cs->children)) {
		char *buf;

		buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
		if (!buf)
			return;
		if (cpuset_path(cs, buf, PAGE_SIZE) < 0)
532
533
534
			kfree(buf);
		else
			*ppathbuf = buf;
Linus Torvalds's avatar
Linus Torvalds committed
535
536
537
538
539
540
541
542
543
544
545
546
547
548
	}
}

/*
 * Return in *pmask the portion of a cpusets's cpus_allowed that
 * are online.  If none are online, walk up the cpuset hierarchy
 * until we find one that does have some online cpus.  If we get
 * all the way to the top and still haven't found any online cpus,
 * return cpu_online_map.  Or if passed a NULL cs from an exit'ing
 * task, return cpu_online_map.
 *
 * One way or another, we guarantee to return some non-empty subset
 * of cpu_online_map.
 *
549
 * Call with callback_sem held.
Linus Torvalds's avatar
Linus Torvalds committed
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
 */

static void guarantee_online_cpus(const struct cpuset *cs, cpumask_t *pmask)
{
	while (cs && !cpus_intersects(cs->cpus_allowed, cpu_online_map))
		cs = cs->parent;
	if (cs)
		cpus_and(*pmask, cs->cpus_allowed, cpu_online_map);
	else
		*pmask = cpu_online_map;
	BUG_ON(!cpus_intersects(*pmask, cpu_online_map));
}

/*
 * Return in *pmask the portion of a cpusets's mems_allowed that
 * are online.  If none are online, walk up the cpuset hierarchy
 * until we find one that does have some online mems.  If we get
 * all the way to the top and still haven't found any online mems,
 * return node_online_map.
 *
 * One way or another, we guarantee to return some non-empty subset
 * of node_online_map.
 *
573
 * Call with callback_sem held.
Linus Torvalds's avatar
Linus Torvalds committed
574
575
576
577
578
579
580
581
582
583
584
585
586
 */

static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask)
{
	while (cs && !nodes_intersects(cs->mems_allowed, node_online_map))
		cs = cs->parent;
	if (cs)
		nodes_and(*pmask, cs->mems_allowed, node_online_map);
	else
		*pmask = node_online_map;
	BUG_ON(!nodes_intersects(*pmask, node_online_map));
}

587
588
589
590
591
592
/**
 * cpuset_update_task_memory_state - update task memory placement
 *
 * If the current tasks cpusets mems_allowed changed behind our
 * backs, update current->mems_allowed, mems_generation and task NUMA
 * mempolicy to the new value.
593
 *
594
595
596
597
598
599
600
601
602
603
604
605
606
 * Task mempolicy is updated by rebinding it relative to the
 * current->cpuset if a task has its memory placement changed.
 * Do not call this routine if in_interrupt().
 *
 * Call without callback_sem or task_lock() held.  May be called
 * with or without manage_sem held.  Except in early boot or
 * an exiting task, when tsk->cpuset is NULL, this routine will
 * acquire task_lock().  We don't need to use task_lock to guard
 * against another task changing a non-NULL cpuset pointer to NULL,
 * as that is only done by a task on itself, and if the current task
 * is here, it is not simultaneously in the exit code NULL'ing its
 * cpuset pointer.  This routine also might acquire callback_sem and
 * current->mm->mmap_sem during call.
607
608
609
610
611
612
613
614
615
616
617
618
 *
 * The task_lock() is required to dereference current->cpuset safely.
 * Without it, we could pick up the pointer value of current->cpuset
 * in one instruction, and then attach_task could give us a different
 * cpuset, and then the cpuset we had could be removed and freed,
 * and then on our next instruction, we could dereference a no longer
 * valid cpuset pointer to get its mems_generation field.
 *
 * This routine is needed to update the per-task mems_allowed data,
 * within the tasks context, when it is trying to allocate memory
 * (in various mm/mempolicy.c routines) and notices that some other
 * task has been modifying its cpuset.
Linus Torvalds's avatar
Linus Torvalds committed
619
620
 */

621
void cpuset_update_task_memory_state()
Linus Torvalds's avatar
Linus Torvalds committed
622
{
623
	int my_cpusets_mem_gen;
624
625
	struct task_struct *tsk = current;
	struct cpuset *cs = tsk->cpuset;
626

627
628
629
630
631
632
	if (unlikely(!cs))
		return;

	task_lock(tsk);
	my_cpusets_mem_gen = cs->mems_generation;
	task_unlock(tsk);
Linus Torvalds's avatar
Linus Torvalds committed
633

634
635
	if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) {
		nodemask_t oldmem = tsk->mems_allowed;
636
		int migrate;
637
638

		down(&callback_sem);
639
640
		task_lock(tsk);
		cs = tsk->cpuset;	/* Maybe changed when task not locked */
641
		migrate = is_memory_migrate(cs);
642
643
644
		guarantee_online_mems(cs, &tsk->mems_allowed);
		tsk->cpuset_mems_generation = cs->mems_generation;
		task_unlock(tsk);
645
		up(&callback_sem);
646
647
		numa_policy_rebind(&oldmem, &tsk->mems_allowed);
		if (!nodes_equal(oldmem, tsk->mems_allowed)) {
648
			if (migrate) {
649
650
				do_migrate_pages(tsk->mm, &oldmem,
					&tsk->mems_allowed,
651
652
653
					MPOL_MF_MOVE_ALL);
			}
		}
Linus Torvalds's avatar
Linus Torvalds committed
654
655
656
657
658
659
660
661
	}
}

/*
 * is_cpuset_subset(p, q) - Is cpuset p a subset of cpuset q?
 *
 * One cpuset is a subset of another if all its allowed CPUs and
 * Memory Nodes are a subset of the other, and its exclusive flags
662
 * are only set if the other's are set.  Call holding manage_sem.
Linus Torvalds's avatar
Linus Torvalds committed
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
 */

static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q)
{
	return	cpus_subset(p->cpus_allowed, q->cpus_allowed) &&
		nodes_subset(p->mems_allowed, q->mems_allowed) &&
		is_cpu_exclusive(p) <= is_cpu_exclusive(q) &&
		is_mem_exclusive(p) <= is_mem_exclusive(q);
}

/*
 * validate_change() - Used to validate that any proposed cpuset change
 *		       follows the structural rules for cpusets.
 *
 * If we replaced the flag and mask values of the current cpuset
 * (cur) with those values in the trial cpuset (trial), would
 * our various subset and exclusive rules still be valid?  Presumes
680
 * manage_sem held.
Linus Torvalds's avatar
Linus Torvalds committed
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
 *
 * 'cur' is the address of an actual, in-use cpuset.  Operations
 * such as list traversal that depend on the actual address of the
 * cpuset in the list must use cur below, not trial.
 *
 * 'trial' is the address of bulk structure copy of cur, with
 * perhaps one or more of the fields cpus_allowed, mems_allowed,
 * or flags changed to new, trial values.
 *
 * Return 0 if valid, -errno if not.
 */

static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
{
	struct cpuset *c, *par;

	/* Each of our child cpusets must be a subset of us */
	list_for_each_entry(c, &cur->children, sibling) {
		if (!is_cpuset_subset(c, trial))
			return -EBUSY;
	}

	/* Remaining checks don't apply to root cpuset */
	if ((par = cur->parent) == NULL)
		return 0;

	/* We must be a subset of our parent cpuset */
	if (!is_cpuset_subset(trial, par))
		return -EACCES;

	/* If either I or some sibling (!= me) is exclusive, we can't overlap */
	list_for_each_entry(c, &par->children, sibling) {
		if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
		    c != cur &&
		    cpus_intersects(trial->cpus_allowed, c->cpus_allowed))
			return -EINVAL;
		if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) &&
		    c != cur &&
		    nodes_intersects(trial->mems_allowed, c->mems_allowed))
			return -EINVAL;
	}

	return 0;
}

726
727
728
729
730
731
732
733
/*
 * For a given cpuset cur, partition the system as follows
 * a. All cpus in the parent cpuset's cpus_allowed that are not part of any
 *    exclusive child cpusets
 * b. All cpus in the current cpuset's cpus_allowed that are not part of any
 *    exclusive child cpusets
 * Build these two partitions by calling partition_sched_domains
 *
734
 * Call with manage_sem held.  May nest a call to the
735
736
 * lock_cpu_hotplug()/unlock_cpu_hotplug() pair.
 */
737

738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
static void update_cpu_domains(struct cpuset *cur)
{
	struct cpuset *c, *par = cur->parent;
	cpumask_t pspan, cspan;

	if (par == NULL || cpus_empty(cur->cpus_allowed))
		return;

	/*
	 * Get all cpus from parent's cpus_allowed not part of exclusive
	 * children
	 */
	pspan = par->cpus_allowed;
	list_for_each_entry(c, &par->children, sibling) {
		if (is_cpu_exclusive(c))
			cpus_andnot(pspan, pspan, c->cpus_allowed);
	}
	if (is_removed(cur) || !is_cpu_exclusive(cur)) {
		cpus_or(pspan, pspan, cur->cpus_allowed);
		if (cpus_equal(pspan, cur->cpus_allowed))
			return;
		cspan = CPU_MASK_NONE;
	} else {
		if (cpus_empty(pspan))
			return;
		cspan = cur->cpus_allowed;
		/*
		 * Get all cpus from current cpuset's cpus_allowed not part
		 * of exclusive children
		 */
		list_for_each_entry(c, &cur->children, sibling) {
			if (is_cpu_exclusive(c))
				cpus_andnot(cspan, cspan, c->cpus_allowed);
		}
	}

	lock_cpu_hotplug();
	partition_sched_domains(&pspan, &cspan);
	unlock_cpu_hotplug();
}

779
780
781
782
/*
 * Call with manage_sem held.  May take callback_sem during call.
 */

Linus Torvalds's avatar
Linus Torvalds committed
783
784
785
static int update_cpumask(struct cpuset *cs, char *buf)
{
	struct cpuset trialcs;
786
	int retval, cpus_unchanged;
Linus Torvalds's avatar
Linus Torvalds committed
787
788
789
790
791
792
793
794
795

	trialcs = *cs;
	retval = cpulist_parse(buf, trialcs.cpus_allowed);
	if (retval < 0)
		return retval;
	cpus_and(trialcs.cpus_allowed, trialcs.cpus_allowed, cpu_online_map);
	if (cpus_empty(trialcs.cpus_allowed))
		return -ENOSPC;
	retval = validate_change(cs, &trialcs);
796
797
798
	if (retval < 0)
		return retval;
	cpus_unchanged = cpus_equal(cs->cpus_allowed, trialcs.cpus_allowed);
799
	down(&callback_sem);
800
	cs->cpus_allowed = trialcs.cpus_allowed;
801
	up(&callback_sem);
802
803
804
	if (is_cpu_exclusive(cs) && !cpus_unchanged)
		update_cpu_domains(cs);
	return 0;
Linus Torvalds's avatar
Linus Torvalds committed
805
806
}

807
808
809
810
/*
 * Call with manage_sem held.  May take callback_sem during call.
 */

Linus Torvalds's avatar
Linus Torvalds committed
811
812
813
814
815
816
817
818
static int update_nodemask(struct cpuset *cs, char *buf)
{
	struct cpuset trialcs;
	int retval;

	trialcs = *cs;
	retval = nodelist_parse(buf, trialcs.mems_allowed);
	if (retval < 0)
819
		goto done;
Linus Torvalds's avatar
Linus Torvalds committed
820
	nodes_and(trialcs.mems_allowed, trialcs.mems_allowed, node_online_map);
821
822
823
	if (nodes_empty(trialcs.mems_allowed)) {
		retval = -ENOSPC;
		goto done;
Linus Torvalds's avatar
Linus Torvalds committed
824
	}
825
826
827
828
829
830
831
832
833
834
835
	retval = validate_change(cs, &trialcs);
	if (retval < 0)
		goto done;

	down(&callback_sem);
	cs->mems_allowed = trialcs.mems_allowed;
	atomic_inc(&cpuset_mems_generation);
	cs->mems_generation = atomic_read(&cpuset_mems_generation);
	up(&callback_sem);

done:
Linus Torvalds's avatar
Linus Torvalds committed
836
837
838
	return retval;
}

839
840
841
842
843
844
845
846
847
848
849
850
851
/*
 * Call with manage_sem held.
 */

static int update_memory_pressure_enabled(struct cpuset *cs, char *buf)
{
	if (simple_strtoul(buf, NULL, 10) != 0)
		cpuset_memory_pressure_enabled = 1;
	else
		cpuset_memory_pressure_enabled = 0;
	return 0;
}

Linus Torvalds's avatar
Linus Torvalds committed
852
853
854
/*
 * update_flag - read a 0 or a 1 in a file and update associated flag
 * bit:	the bit to update (CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE,
855
 *				CS_NOTIFY_ON_RELEASE, CS_MEMORY_MIGRATE)
Linus Torvalds's avatar
Linus Torvalds committed
856
857
 * cs:	the cpuset to update
 * buf:	the buffer where we read the 0 or 1
858
859
 *
 * Call with manage_sem held.
Linus Torvalds's avatar
Linus Torvalds committed
860
861
862
863
864
865
 */

static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf)
{
	int turning_on;
	struct cpuset trialcs;
866
	int err, cpu_exclusive_changed;
Linus Torvalds's avatar
Linus Torvalds committed
867
868
869
870
871
872
873
874
875
876

	turning_on = (simple_strtoul(buf, NULL, 10) != 0);

	trialcs = *cs;
	if (turning_on)
		set_bit(bit, &trialcs.flags);
	else
		clear_bit(bit, &trialcs.flags);

	err = validate_change(cs, &trialcs);
877
878
879
880
	if (err < 0)
		return err;
	cpu_exclusive_changed =
		(is_cpu_exclusive(cs) != is_cpu_exclusive(&trialcs));
881
	down(&callback_sem);
882
883
884
885
	if (turning_on)
		set_bit(bit, &cs->flags);
	else
		clear_bit(bit, &cs->flags);
886
	up(&callback_sem);
887
888
889
890

	if (cpu_exclusive_changed)
                update_cpu_domains(cs);
	return 0;
Linus Torvalds's avatar
Linus Torvalds committed
891
892
}

893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
/*
 * Frequency meter - How fast is some event occuring?
 *
 * These routines manage a digitally filtered, constant time based,
 * event frequency meter.  There are four routines:
 *   fmeter_init() - initialize a frequency meter.
 *   fmeter_markevent() - called each time the event happens.
 *   fmeter_getrate() - returns the recent rate of such events.
 *   fmeter_update() - internal routine used to update fmeter.
 *
 * A common data structure is passed to each of these routines,
 * which is used to keep track of the state required to manage the
 * frequency meter and its digital filter.
 *
 * The filter works on the number of events marked per unit time.
 * The filter is single-pole low-pass recursive (IIR).  The time unit
 * is 1 second.  Arithmetic is done using 32-bit integers scaled to
 * simulate 3 decimal digits of precision (multiplied by 1000).
 *
 * With an FM_COEF of 933, and a time base of 1 second, the filter
 * has a half-life of 10 seconds, meaning that if the events quit
 * happening, then the rate returned from the fmeter_getrate()
 * will be cut in half each 10 seconds, until it converges to zero.
 *
 * It is not worth doing a real infinitely recursive filter.  If more
 * than FM_MAXTICKS ticks have elapsed since the last filter event,
 * just compute FM_MAXTICKS ticks worth, by which point the level
 * will be stable.
 *
 * Limit the count of unprocessed events to FM_MAXCNT, so as to avoid
 * arithmetic overflow in the fmeter_update() routine.
 *
 * Given the simple 32 bit integer arithmetic used, this meter works
 * best for reporting rates between one per millisecond (msec) and
 * one per 32 (approx) seconds.  At constant rates faster than one
 * per msec it maxes out at values just under 1,000,000.  At constant
 * rates between one per msec, and one per second it will stabilize
 * to a value N*1000, where N is the rate of events per second.
 * At constant rates between one per second and one per 32 seconds,
 * it will be choppy, moving up on the seconds that have an event,
 * and then decaying until the next event.  At rates slower than
 * about one in 32 seconds, it decays all the way back to zero between
 * each event.
 */

#define FM_COEF 933		/* coefficient for half-life of 10 secs */
#define FM_MAXTICKS ((time_t)99) /* useless computing more ticks than this */
#define FM_MAXCNT 1000000	/* limit cnt to avoid overflow */
#define FM_SCALE 1000		/* faux fixed point scale */

/* Initialize a frequency meter */
static void fmeter_init(struct fmeter *fmp)
{
	fmp->cnt = 0;
	fmp->val = 0;
	fmp->time = 0;
	spin_lock_init(&fmp->lock);
}

/* Internal meter update - process cnt events and update value */
static void fmeter_update(struct fmeter *fmp)
{
	time_t now = get_seconds();
	time_t ticks = now - fmp->time;

	if (ticks == 0)
		return;

	ticks = min(FM_MAXTICKS, ticks);
	while (ticks-- > 0)
		fmp->val = (FM_COEF * fmp->val) / FM_SCALE;
	fmp->time = now;

	fmp->val += ((FM_SCALE - FM_COEF) * fmp->cnt) / FM_SCALE;
	fmp->cnt = 0;
}

/* Process any previous ticks, then bump cnt by one (times scale). */
static void fmeter_markevent(struct fmeter *fmp)
{
	spin_lock(&fmp->lock);
	fmeter_update(fmp);
	fmp->cnt = min(FM_MAXCNT, fmp->cnt + FM_SCALE);
	spin_unlock(&fmp->lock);
}

/* Process any previous ticks, then return current value. */
static int fmeter_getrate(struct fmeter *fmp)
{
	int val;

	spin_lock(&fmp->lock);
	fmeter_update(fmp);
	val = fmp->val;
	spin_unlock(&fmp->lock);
	return val;
}

991
992
993
994
995
996
997
998
999
/*
 * Attack task specified by pid in 'pidbuf' to cpuset 'cs', possibly
 * writing the path of the old cpuset in 'ppathbuf' if it needs to be
 * notified on release.
 *
 * Call holding manage_sem.  May take callback_sem and task_lock of
 * the task 'pid' during call.
 */

1000
static int attach_task(struct cpuset *cs, char *pidbuf, char **ppathbuf)
Linus Torvalds's avatar
Linus Torvalds committed
1001
1002
1003
1004
1005
{
	pid_t pid;
	struct task_struct *tsk;
	struct cpuset *oldcs;
	cpumask_t cpus;
1006
	nodemask_t from, to;
Linus Torvalds's avatar
Linus Torvalds committed
1007

1008
	if (sscanf(pidbuf, "%d", &pid) != 1)
Linus Torvalds's avatar
Linus Torvalds committed
1009
1010
1011
1012
1013
1014
1015
1016
		return -EIO;
	if (cpus_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
		return -ENOSPC;

	if (pid) {
		read_lock(&tasklist_lock);

		tsk = find_task_by_pid(pid);
1017
		if (!tsk || tsk->flags & PF_EXITING) {
Linus Torvalds's avatar
Linus Torvalds committed
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
			read_unlock(&tasklist_lock);
			return -ESRCH;
		}

		get_task_struct(tsk);
		read_unlock(&tasklist_lock);

		if ((current->euid) && (current->euid != tsk->uid)
		    && (current->euid != tsk->suid)) {
			put_task_struct(tsk);
			return -EACCES;
		}
	} else {
		tsk = current;
		get_task_struct(tsk);
	}

1035
1036
	down(&callback_sem);

Linus Torvalds's avatar
Linus Torvalds committed
1037
1038
1039
1040
	task_lock(tsk);
	oldcs = tsk->cpuset;
	if (!oldcs) {
		task_unlock(tsk);
1041
		up(&callback_sem);
Linus Torvalds's avatar
Linus Torvalds committed
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
		put_task_struct(tsk);
		return -ESRCH;
	}
	atomic_inc(&cs->count);
	tsk->cpuset = cs;
	task_unlock(tsk);

	guarantee_online_cpus(cs, &cpus);
	set_cpus_allowed(tsk, cpus);

1052
1053
1054
	from = oldcs->mems_allowed;
	to = cs->mems_allowed;

1055
	up(&callback_sem);
1056
1057
	if (is_memory_migrate(cs))
		do_migrate_pages(tsk->mm, &from, &to, MPOL_MF_MOVE_ALL);
Linus Torvalds's avatar
Linus Torvalds committed
1058
1059
	put_task_struct(tsk);
	if (atomic_dec_and_test(&oldcs->count))
1060
		check_for_release(oldcs, ppathbuf);
Linus Torvalds's avatar
Linus Torvalds committed
1061
1062
1063
1064
1065
1066
1067
1068
	return 0;
}

/* The various types of files and directories in a cpuset file system */

typedef enum {
	FILE_ROOT,
	FILE_DIR,
1069
	FILE_MEMORY_MIGRATE,
Linus Torvalds's avatar
Linus Torvalds committed
1070
1071
1072
1073
1074
	FILE_CPULIST,
	FILE_MEMLIST,
	FILE_CPU_EXCLUSIVE,
	FILE_MEM_EXCLUSIVE,
	FILE_NOTIFY_ON_RELEASE,
1075
1076
	FILE_MEMORY_PRESSURE_ENABLED,
	FILE_MEMORY_PRESSURE,
Linus Torvalds's avatar
Linus Torvalds committed
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
	FILE_TASKLIST,
} cpuset_filetype_t;

static ssize_t cpuset_common_file_write(struct file *file, const char __user *userbuf,
					size_t nbytes, loff_t *unused_ppos)
{
	struct cpuset *cs = __d_cs(file->f_dentry->d_parent);
	struct cftype *cft = __d_cft(file->f_dentry);
	cpuset_filetype_t type = cft->private;
	char *buffer;
1087
	char *pathbuf = NULL;
Linus Torvalds's avatar
Linus Torvalds committed
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
	int retval = 0;

	/* Crude upper limit on largest legitimate cpulist user might write. */
	if (nbytes > 100 + 6 * NR_CPUS)
		return -E2BIG;

	/* +1 for nul-terminator */
	if ((buffer = kmalloc(nbytes + 1, GFP_KERNEL)) == 0)
		return -ENOMEM;

	if (copy_from_user(buffer, userbuf, nbytes)) {
		retval = -EFAULT;
		goto out1;
	}
	buffer[nbytes] = 0;	/* nul-terminate */

1104
	down(&manage_sem);
Linus Torvalds's avatar
Linus Torvalds committed
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126

	if (is_removed(cs)) {
		retval = -ENODEV;
		goto out2;
	}

	switch (type) {
	case FILE_CPULIST:
		retval = update_cpumask(cs, buffer);
		break;
	case FILE_MEMLIST:
		retval = update_nodemask(cs, buffer);
		break;
	case FILE_CPU_EXCLUSIVE:
		retval = update_flag(CS_CPU_EXCLUSIVE, cs, buffer);
		break;
	case FILE_MEM_EXCLUSIVE:
		retval = update_flag(CS_MEM_EXCLUSIVE, cs, buffer);
		break;
	case FILE_NOTIFY_ON_RELEASE:
		retval = update_flag(CS_NOTIFY_ON_RELEASE, cs, buffer);
		break;
1127
1128
1129
	case FILE_MEMORY_MIGRATE:
		retval = update_flag(CS_MEMORY_MIGRATE, cs, buffer);
		break;
1130
1131
1132
1133
1134
1135
	case FILE_MEMORY_PRESSURE_ENABLED:
		retval = update_memory_pressure_enabled(cs, buffer);
		break;
	case FILE_MEMORY_PRESSURE:
		retval = -EACCES;
		break;
Linus Torvalds's avatar
Linus Torvalds committed
1136
	case FILE_TASKLIST:
1137
		retval = attach_task(cs, buffer, &pathbuf);
Linus Torvalds's avatar
Linus Torvalds committed
1138
1139
1140
1141
1142
1143
1144
1145
1146
		break;
	default:
		retval = -EINVAL;
		goto out2;
	}

	if (retval == 0)
		retval = nbytes;
out2:
1147
	up(&manage_sem);
1148
	cpuset_release_agent(pathbuf);
Linus Torvalds's avatar
Linus Torvalds committed
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
out1:
	kfree(buffer);
	return retval;
}

static ssize_t cpuset_file_write(struct file *file, const char __user *buf,
						size_t nbytes, loff_t *ppos)
{
	ssize_t retval = 0;
	struct cftype *cft = __d_cft(file->f_dentry);
	if (!cft)
		return -ENODEV;

	/* special function ? */
	if (cft->write)
		retval = cft->write(file, buf, nbytes, ppos);
	else
		retval = cpuset_common_file_write(file, buf, nbytes, ppos);

	return retval;
}

/*
 * These ascii lists should be read in a single call, by using a user
 * buffer large enough to hold the entire map.  If read in smaller
 * chunks, there is no guarantee of atomicity.  Since the display format
 * used, list of ranges of sequential numbers, is variable length,
 * and since these maps can change value dynamically, one could read
 * gibberish by doing partial reads while a list was changing.
 * A single large read to a buffer that crosses a page boundary is
 * ok, because the result being copied to user land is not recomputed
 * across a page fault.
 */

static int cpuset_sprintf_cpulist(char *page, struct cpuset *cs)
{
	cpumask_t mask;

1187
	down(&callback_sem);
Linus Torvalds's avatar
Linus Torvalds committed
1188
	mask = cs->cpus_allowed;
1189
	up(&callback_sem);
Linus Torvalds's avatar
Linus Torvalds committed
1190
1191
1192
1193
1194
1195
1196
1197

	return cpulist_scnprintf(page, PAGE_SIZE, mask);
}

static int cpuset_sprintf_memlist(char *page, struct cpuset *cs)
{
	nodemask_t mask;

1198
	down(&callback_sem);
Linus Torvalds's avatar
Linus Torvalds committed
1199
	mask = cs->mems_allowed;
1200
	up(&callback_sem);
Linus Torvalds's avatar
Linus Torvalds committed
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235

	return nodelist_scnprintf(page, PAGE_SIZE, mask);
}

static ssize_t cpuset_common_file_read(struct file *file, char __user *buf,
				size_t nbytes, loff_t *ppos)
{
	struct cftype *cft = __d_cft(file->f_dentry);
	struct cpuset *cs = __d_cs(file->f_dentry->d_parent);
	cpuset_filetype_t type = cft->private;
	char *page;
	ssize_t retval = 0;
	char *s;

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

	s = page;

	switch (type) {
	case FILE_CPULIST:
		s += cpuset_sprintf_cpulist(s, cs);
		break;
	case FILE_MEMLIST:
		s += cpuset_sprintf_memlist(s, cs);
		break;
	case FILE_CPU_EXCLUSIVE:
		*s++ = is_cpu_exclusive(cs) ? '1' : '0';
		break;
	case FILE_MEM_EXCLUSIVE:
		*s++ = is_mem_exclusive(cs) ? '1' : '0';
		break;
	case FILE_NOTIFY_ON_RELEASE:
		*s++ = notify_on_release(cs) ? '1' : '0';
		break;
1236
1237
1238
	case FILE_MEMORY_MIGRATE:
		*s++ = is_memory_migrate(cs) ? '1' : '0';
		break;
1239
1240
1241
1242
1243
1244
	case FILE_MEMORY_PRESSURE_ENABLED:
		*s++ = cpuset_memory_pressure_enabled ? '1' : '0';
		break;
	case FILE_MEMORY_PRESSURE:
		s += sprintf(s, "%d", fmeter_getrate(&cs->fmeter));
		break;
Linus Torvalds's avatar
Linus Torvalds committed
1245
1246
1247
1248
1249
1250
	default:
		retval = -EINVAL;
		goto out;
	}
	*s++ = '\n';

Al Viro's avatar
Al Viro committed
1251
	retval = simple_read_from_buffer(buf, nbytes, ppos, page, s - page);
Linus Torvalds's avatar
Linus Torvalds committed
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
out:
	free_page((unsigned long)page);
	return retval;
}

static ssize_t cpuset_file_read(struct file *file, char __user *buf, size_t nbytes,
								loff_t *ppos)
{
	ssize_t retval = 0;
	struct cftype *cft = __d_cft(file->f_dentry);
	if (!cft)
		return -ENODEV;

	/* special function ? */
	if (cft->read)
		retval = cft->read(file, buf, nbytes, ppos);
	else
		retval = cpuset_common_file_read(file, buf, nbytes, ppos);

	return retval;
}

static int cpuset_file_open(struct inode *inode, struct file *file)
{
	int err;
	struct cftype *cft;

	err = generic_file_open(inode, file);
	if (err)
		return err;

	cft = __d_cft(file->f_dentry);
	if (!cft)
		return -ENODEV;
	if (cft->open)
		err = cft->open(inode, file);
	else
		err = 0;

	return err;
}

static int cpuset_file_release(struct inode *inode, struct file *file)
{
	struct cftype *cft = __d_cft(file->f_dentry);
	if (cft->release)
		return cft->release(inode, file);
	return 0;
}

Paul Jackson's avatar
Paul Jackson committed
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
/*
 * cpuset_rename - Only allow simple rename of directories in place.
 */
static int cpuset_rename(struct inode *old_dir, struct dentry *old_dentry,
                  struct inode *new_dir, struct dentry *new_dentry)
{
	if (!S_ISDIR(old_dentry->d_inode->i_mode))
		return -ENOTDIR;
	if (new_dentry->d_inode)
		return -EEXIST;
	if (old_dir != new_dir)
		return -EIO;
	return simple_rename(old_dir, old_dentry, new_dir, new_dentry);
}

Linus Torvalds's avatar
Linus Torvalds committed
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
static struct file_operations cpuset_file_operations = {
	.read = cpuset_file_read,
	.write = cpuset_file_write,
	.llseek = generic_file_llseek,
	.open = cpuset_file_open,
	.release = cpuset_file_release,
};

static struct inode_operations cpuset_dir_inode_operations = {
	.lookup = simple_lookup,
	.mkdir = cpuset_mkdir,
	.rmdir = cpuset_rmdir,
Paul Jackson's avatar
Paul Jackson committed
1329
	.rename = cpuset_rename,
Linus Torvalds's avatar
Linus Torvalds committed
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
};

static int cpuset_create_file(struct dentry *dentry, int mode)
{
	struct inode *inode;

	if (!dentry)
		return -ENOENT;
	if (dentry->d_inode)
		return -EEXIST;

	inode = cpuset_new_inode(mode);
	if (!inode)
		return -ENOMEM;

	if (S_ISDIR(mode)) {
		inode->i_op = &cpuset_dir_inode_operations;
		inode->i_fop = &simple_dir_operations;

		/* start off with i_nlink == 2 (for "." entry) */
		inode->i_nlink++;
	} else if (S_ISREG(mode)) {
		inode->i_size = 0;
		inode->i_fop = &cpuset_file_operations;
	}

	d_instantiate(dentry, inode);
	dget(dentry);	/* Extra count - pin the dentry in core */
	return 0;
}

/*
 *	cpuset_create_dir - create a directory for an object.
1363
 *	cs:	the cpuset we create the directory for.
Linus Torvalds's avatar
Linus Torvalds committed
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
 *		It must have a valid ->parent field
 *		And we are going to fill its ->dentry field.
 *	name:	The name to give to the cpuset directory. Will be copied.
 *	mode:	mode to set on new directory.
 */

static int cpuset_create_dir(struct cpuset *cs, const char *name, int mode)
{
	struct dentry *dentry = NULL;
	struct dentry *parent;
	int error = 0;

	parent = cs->parent->dentry;
	dentry = cpuset_get_dentry(parent, name);
	if (IS_ERR(dentry))
		return PTR_ERR(dentry);
	error = cpuset_create_file(dentry, S_IFDIR | mode);
	if (!error) {
		dentry->d_fsdata = cs;
		parent->d_inode->i_nlink++;
		cs->dentry = dentry;
	}
	dput(dentry);

	return error;
}

static int cpuset_add_file(struct dentry *dir, const struct cftype *cft)
{
	struct dentry *dentry;
	int error;

	down(&dir->d_inode->i_sem);
	dentry = cpuset_get_dentry(dir, cft->name);
	if (!IS_ERR(dentry)) {
		error = cpuset_create_file(dentry, 0644 | S_IFREG);
		if (!error)
			dentry->d_fsdata = (void *)cft;
		dput(dentry);
	} else
		error = PTR_ERR(dentry);
	up(&dir->d_inode->i_sem);
	return error;
}

/*
 * Stuff for reading the 'tasks' file.
 *
 * Reading this file can return large amounts of data if a cpuset has
 * *lots* of attached tasks. So it may need several calls to read(),
 * but we cannot guarantee that the information we produce is correct
 * unless we produce it entirely atomically.
 *
 * Upon tasks file open(), a struct ctr_struct is allocated, that
 * will have a pointer to an array (also allocated here).  The struct
 * ctr_struct * is stored in file->private_data.  Its resources will
 * be freed by release() when the file is closed.  The array is used
 * to sprintf the PIDs and then used by read().
 */

/* cpusets_tasks_read array */

struct ctr_struct {
	char *buf;
	int bufsz;
};

/*
 * Load into 'pidarray' up to 'npids' of the tasks using cpuset 'cs'.
1433
1434
1435
 * Return actual number of pids loaded.  No need to task_lock(p)
 * when reading out p->cpuset, as we don't really care if it changes
 * on the next cycle, and we are not going to try to dereference it.
Linus Torvalds's avatar
Linus Torvalds committed
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
 */
static inline int pid_array_load(pid_t *pidarray, int npids, struct cpuset *cs)
{
	int n = 0;
	struct task_struct *g, *p;

	read_lock(&tasklist_lock);

	do_each_thread(g, p) {
		if (p->cpuset == cs) {
			pidarray[n++] = p->pid;
			if (unlikely(n == npids))
				goto array_full;
		}
	} while_each_thread(g, p);

array_full:
	read_unlock(&tasklist_lock);
	return n;
}

static int cmppid(const void *a, const void *b)
{
	return *(pid_t *)a - *(pid_t *)b;
}

/*
 * Convert array 'a' of 'npids' pid_t's to a string of newline separated
 * decimal pids in 'buf'.  Don't write more than 'sz' chars, but return
 * count 'cnt' of how many chars would be written if buf were large enough.
 */
static int pid_array_to_buf(char *buf, int sz, pid_t *a, int npids)
{
	int cnt = 0;
	int i;

	for (i = 0; i < npids; i++)
		cnt += snprintf(buf + cnt, max(sz - cnt, 0), "%d\n", a[i]);
	return cnt;
}

1477
1478
1479
1480
1481
1482
/*
 * Handle an open on 'tasks' file.  Prepare a buffer listing the
 * process id's of tasks currently attached to the cpuset being opened.
 *
 * Does not require any specific cpuset semaphores, and does not take any.
 */
Linus Torvalds's avatar
Linus Torvalds committed
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
static int cpuset_tasks_open(struct inode *unused, struct file *file)
{
	struct cpuset *cs = __d_cs(file->f_dentry->d_parent);
	struct ctr_struct *ctr;
	pid_t *pidarray;
	int npids;
	char c;

	if (!(file->f_mode & FMODE_READ))
		return 0;

	ctr = kmalloc(sizeof(*ctr), GFP_KERNEL);
	if (!ctr)
		goto err0;

	/*
	 * If cpuset gets more users after we read count, we won't have
	 * enough space - tough.  This race is indistinguishable to the
	 * caller from the case that the additional cpuset users didn't
	 * show up until sometime later on.
	 */
	npids = atomic_read(&cs->count);
	pidarray = kmalloc(npids * sizeof(pid_t), GFP_KERNEL);
	if (!pidarray)
		goto err1;

	npids = pid_array_load(pidarray, npids, cs);
	sort(pidarray, npids, sizeof(pid_t), cmppid, NULL);

	/* Call pid_array_to_buf() twice, first just to get bufsz */
	ctr->bufsz = pid_array_to_buf(&c, sizeof(c), pidarray, npids) + 1;
	ctr->buf = kmalloc(ctr->bufsz, GFP_KERNEL);
	if (!ctr->buf)
		goto err2;
	ctr->bufsz = pid_array_to_buf(ctr->buf, ctr->bufsz, pidarray, npids);

	kfree(pidarray);
	file->private_data = ctr;
	return 0;

err2:
	kfree(pidarray);
err1:
	kfree(ctr);
err0:
	return -ENOMEM;
}

static ssize_t cpuset_tasks_read(struct file *file, char __user *buf,
						size_t nbytes, loff_t *ppos)
{
	struct ctr_struct *ctr = file->private_data;

	if (*ppos + nbytes > ctr->bufsz)
		nbytes = ctr->bufsz - *ppos;
	if (copy_to_user(buf, ctr->buf + *ppos, nbytes))
		return -EFAULT;
	*ppos += nbytes;
	return nbytes;
}

static int cpuset_tasks_release(struct inode *unused_inode, struct file *file)
{
	struct ctr_struct *ctr;

	if (file->f_mode & FMODE_READ) {
		ctr = file->private_data;
		kfree(ctr->buf);
		kfree(ctr);
	}
	return 0;
}

/*
 * for the common functions, 'private' gives the type of file
 */

static struct cftype cft_tasks = {
	.name = "tasks",
	.open = cpuset_tasks_open,
	.read = cpuset_tasks_read,
	.release = cpuset_tasks_release,
	.private = FILE_TASKLIST,
};

static struct cftype cft_cpus = {
	.name = "cpus",
	.private = FILE_CPULIST,
};

static struct cftype cft_mems = {
	.name = "mems",
	.private = FILE_MEMLIST,
};

static struct cftype cft_cpu_exclusive = {
	.name = "cpu_exclusive",
	.private = FILE_CPU_EXCLUSIVE,
};

static struct cftype cft_mem_exclusive = {
	.name = "mem_exclusive",
	.private = FILE_MEM_EXCLUSIVE,
};

static struct cftype cft_notify_on_release = {
	.name = "notify_on_release",
	.private = FILE_NOTIFY_ON_RELEASE,
};

1593
1594
1595
1596
1597
static struct cftype cft_memory_migrate = {
	.name = "memory_migrate",
	.private = FILE_MEMORY_MIGRATE,
};

1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
static struct cftype cft_memory_pressure_enabled = {
	.name = "memory_pressure_enabled",
	.private = FILE_MEMORY_PRESSURE_ENABLED,
};

static struct cftype cft_memory_pressure = {
	.name = "memory_pressure",
	.private = FILE_MEMORY_PRESSURE,
};

Linus Torvalds's avatar
Linus Torvalds committed
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
static int cpuset_populate_dir(struct dentry *cs_dentry)
{
	int err;

	if ((err = cpuset_add_file(cs_dentry, &cft_cpus)) < 0)
		return err;
	if ((err = cpuset_add_file(cs_dentry, &cft_mems)) < 0)
		return err;
	if ((err = cpuset_add_file(cs_dentry, &cft_cpu_exclusive)) < 0)
		return err;
	if ((err = cpuset_add_file(cs_dentry, &cft_mem_exclusive)) < 0)
		return err;
	if ((err = cpuset_add_file(cs_dentry, &cft_notify_on_release)) < 0)
		return err;
1622
1623
	if ((err = cpuset_add_file(cs_dentry, &cft_memory_migrate)) < 0)
		return err;
1624
1625
	if ((err = cpuset_add_file(cs_dentry, &cft_memory_pressure)) < 0)
		return err;
Linus Torvalds's avatar
Linus Torvalds committed
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
	if ((err = cpuset_add_file(cs_dentry, &cft_tasks)) < 0)
		return err;
	return 0;
}

/*
 *	cpuset_create - create a cpuset
 *	parent:	cpuset that will be parent of the new cpuset.
 *	name:		name of the new cpuset. Will be strcpy'ed.
 *	mode:		mode to set on new inode
 *
 *	Must be called with the semaphore on the parent inode held
 */

static long cpuset_create(struct cpuset *parent, const char *name, int mode)
{
	struct cpuset *cs;
	int err;

	cs = kmalloc(sizeof(*cs), GFP_KERNEL);
	if (!cs)
		return -ENOMEM;

1649
	down(&manage_sem);
1650
	cpuset_update_task_memory_state();
Linus Torvalds's avatar
Linus Torvalds committed
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
	cs->flags = 0;
	if (notify_on_release(parent))
		set_bit(CS_NOTIFY_ON_RELEASE, &cs->flags);
	cs->cpus_allowed = CPU_MASK_NONE;
	cs->mems_allowed = NODE_MASK_NONE;
	atomic_set(&cs->count, 0);
	INIT_LIST_HEAD(&cs->sibling);
	INIT_LIST_HEAD(&cs->children);
	atomic_inc(&cpuset_mems_generation);
	cs->mems_generation = atomic_read(&cpuset_mems_generation);
1661
	fmeter_init(&cs->fmeter);
Linus Torvalds's avatar
Linus Torvalds committed
1662
1663
1664

	cs->parent = parent;

1665
	down(&callback_sem);
Linus Torvalds's avatar
Linus Torvalds committed
1666
	list_add(&cs->sibling, &cs->parent->children);
1667
	up(&callback_sem);
Linus Torvalds's avatar
Linus Torvalds committed
1668
1669
1670
1671
1672
1673

	err = cpuset_create_dir(cs, name, mode);
	if (err < 0)
		goto err;

	/*
1674
	 * Release manage_sem before cpuset_populate_dir() because it
Linus Torvalds's avatar
Linus Torvalds committed
1675
1676
1677
	 * will down() this new directory's i_sem and if we race with
	 * another mkdir, we might deadlock.
	 */
1678
	up(&manage_sem);
Linus Torvalds's avatar
Linus Torvalds committed
1679
1680
1681
1682
1683
1684

	err = cpuset_populate_dir(cs->dentry);
	/* If err < 0, we have a half-filled directory - oh well ;) */
	return 0;
err:
	list_del(&cs->sibling);
1685
	up(&manage_sem);
Linus Torvalds's avatar
Linus Torvalds committed
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
	kfree(cs);
	return err;
}

static int cpuset_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
	struct cpuset *c_parent = dentry->d_parent->d_fsdata;

	/* the vfs holds inode->i_sem already */
	return cpuset_create(c_parent, dentry->d_name.name, mode | S_IFDIR);
}

static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry)
{
	struct cpuset *cs = dentry->d_fsdata;
	struct dentry *d;
	struct cpuset *parent;
1703
	char *pathbuf = NULL;
Linus Torvalds's avatar
Linus Torvalds committed
1704
1705
1706

	/* the vfs holds both inode->i_sem already */

1707
	down(&manage_sem);
1708
	cpuset_update_task_memory_state();
Linus Torvalds's avatar
Linus Torvalds committed
1709
	if (atomic_read(&cs->count) > 0) {
1710
		up(&manage_sem);
Linus Torvalds's avatar
Linus Torvalds committed
1711
1712
1713
		return -EBUSY;
	}
	if (!list_empty(&cs->children)) {
1714
		up(&manage_sem);
Linus Torvalds's avatar
Linus Torvalds committed
1715
1716
1717
		return -EBUSY;
	}
	parent = cs->parent;
1718
	down(&callback_sem);
Linus Torvalds's avatar
Linus Torvalds committed
1719
	set_bit(CS_REMOVED, &cs->flags);
1720
1721
	if (is_cpu_exclusive(cs))
		update_cpu_domains(cs);
Linus Torvalds's avatar
Linus Torvalds committed
1722
	list_del(&cs->sibling);	/* delete my sibling from parent->children */
1723
	spin_lock(&cs->dentry->d_lock);
Linus Torvalds's avatar
Linus Torvalds committed
1724
1725
1726
1727
1728
	d = dget(cs->dentry);
	cs->dentry = NULL;
	spin_unlock(&d->d_lock);
	cpuset_d_remove_dir(d);
	dput(d);
1729
1730
1731
1732
	up(&callback_sem);
	if (list_empty(&parent->children))
		check_for_release(parent, &pathbuf);
	up(&manage_sem);
1733
	cpuset_release_agent(pathbuf);
Linus Torvalds's avatar
Linus Torvalds committed
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
	return 0;
}

/**
 * cpuset_init - initialize cpusets at system boot
 *
 * Description: Initialize top_cpuset and the cpuset internal file system,
 **/

int __init cpuset_init(void)
{
	struct dentry *root;
	int err;

	top_cpuset.cpus_allowed = CPU_MASK_ALL;
	top_cpuset.mems_allowed = NODE_MASK_ALL;

1751
	fmeter_init(&top_cpuset.fmeter);
Linus Torvalds's avatar
Linus Torvalds committed
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
	atomic_inc(&cpuset_mems_generation);
	top_cpuset.mems_generation = atomic_read(&cpuset_mems_generation);

	init_task.cpuset = &top_cpuset;

	err = register_filesystem(&cpuset_fs_type);
	if (err < 0)
		goto out;
	cpuset_mount = kern_mount(&cpuset_fs_type);
	if (IS_ERR(cpuset_mount)) {
		printk(KERN_ERR "cpuset: could not mount!\n");
		err = PTR_ERR(cpuset_mount);
		cpuset_mount = NULL;
		goto out;
	}
	root = cpuset_mount->mnt_sb->s_root;
	root->d_fsdata = &top_cpuset;
	root->d_inode->i_nlink++;
	top_cpuset.dentry = root;
	root->d_inode->i_op = &cpuset_dir_inode_operations;
	err = cpuset_populate_dir(root);
1773
1774
1775
	/* memory_pressure_enabled is in root cpuset only */
	if (err == 0)
		err = cpuset_add_file(root, &cft_memory_pressure_enabled);
Linus Torvalds's avatar
Linus Torvalds committed
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
out:
	return err;
}

/**
 * cpuset_init_smp - initialize cpus_allowed
 *
 * Description: Finish top cpuset after cpu, node maps are initialized
 **/

void __init cpuset_init_smp(void)
{
	top_cpuset.cpus_allowed = cpu_online_map;
	top_cpuset.mems_allowed = node_online_map;
}

/**
 * cpuset_fork - attach newly forked task to its parents cpuset.
1794
 * @tsk: pointer to task_struct of forking parent process.
Linus Torvalds's avatar
Linus Torvalds committed
1795
 *
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
 * Description: A task inherits its parent's cpuset at fork().
 *
 * A pointer to the shared cpuset was automatically copied in fork.c
 * by dup_task_struct().  However, we ignore that copy, since it was
 * not made under the protection of task_lock(), so might no longer be
 * a valid cpuset pointer.  attach_task() might have already changed
 * current->cpuset, allowing the previously referenced cpuset to
 * be removed and freed.  Instead, we task_lock(current) and copy
 * its present value of current->cpuset for our freshly forked child.
 *
 * At the point that cpuset_fork() is called, 'current' is the parent
 * task, and the passed argument 'child' points to the child task.
Linus Torvalds's avatar
Linus Torvalds committed
1808
1809
 **/

1810
void cpuset_fork(struct task_struct *child)
Linus Torvalds's avatar
Linus Torvalds committed
1811
{
1812
1813
1814
1815
	task_lock(current);
	child->cpuset = current->cpuset;
	atomic_inc(&child->cpuset->count);
	task_unlock(current);
Linus Torvalds's avatar
Linus Torvalds committed
1816
1817
1818
1819
1820
1821
1822
1823
}

/**
 * cpuset_exit - detach cpuset from exiting task
 * @tsk: pointer to task_struct of exiting process
 *
 * Description: Detach cpuset from @tsk and release it.
 *
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
 * Note that cpusets marked notify_on_release force every task in
 * them to take the global manage_sem semaphore when exiting.
 * This could impact scaling on very large systems.  Be reluctant to
 * use notify_on_release cpusets where very high task exit scaling
 * is required on large systems.
 *
 * Don't even think about derefencing 'cs' after the cpuset use count
 * goes to zero, except inside a critical section guarded by manage_sem
 * or callback_sem.   Otherwise a zero cpuset use count is a license to
 * any other task to nuke the cpuset immediately, via cpuset_rmdir().
 *
 * This routine has to take manage_sem, not callback_sem, because
 * it is holding that semaphore while calling check_for_release(),
 * which calls kmalloc(), so can't be called holding callback__sem().
 *
 * We don't need to task_lock() this reference to tsk->cpuset,
 * because tsk is already marked PF_EXITING, so attach_task() won't
Paul Jackson's avatar
Paul Jackson committed
1841
 * mess with it, or task is a failed fork, never visible to attach_task.
Linus Torvalds's avatar
Linus Torvalds committed
1842
1843
1844
1845
1846
1847
1848
1849
1850
 **/

void cpuset_exit(struct task_struct *tsk)
{
	struct cpuset *cs;

	cs = tsk->cpuset;
	tsk->cpuset = NULL;

1851
	if (notify_on_release(cs)) {
1852
1853
		char *pathbuf = NULL;

1854
		down(&manage_sem);
1855
		if (atomic_dec_and_test(&cs->count))
1856
			check_for_release(cs, &pathbuf);
1857
		up(&manage_sem);
1858
		cpuset_release_agent(pathbuf);
1859
1860
	} else {
		atomic_dec(&cs->count);
Linus Torvalds's avatar
Linus Torvalds committed
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
	}
}

/**
 * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset.
 * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed.
 *
 * Description: Returns the cpumask_t cpus_allowed of the cpuset
 * attached to the specified @tsk.  Guaranteed to return some non-empty
 * subset of cpu_online_map, even if this means going outside the
 * tasks cpuset.
 **/

1874
cpumask_t cpuset_cpus_allowed(struct task_struct *tsk)
Linus Torvalds's avatar
Linus Torvalds committed
1875
1876
1877
{
	cpumask_t mask;

1878
	down(&callback_sem);
1879
	task_lock(tsk);
Linus Torvalds's avatar
Linus Torvalds committed
1880
	guarantee_online_cpus(tsk->cpuset, &mask);
1881
	task_unlock(tsk);
1882
	up(&callback_sem);
Linus Torvalds's avatar
Linus Torvalds committed
1883
1884
1885
1886
1887
1888
1889
1890
1891

	return mask;
}

void cpuset_init_current_mems_allowed(void)
{
	current->mems_allowed = NODE_MASK_ALL;
}

1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
/**
 * cpuset_mems_allowed - return mems_allowed mask from a tasks cpuset.
 * @tsk: pointer to task_struct from which to obtain cpuset->mems_allowed.
 *
 * Description: Returns the nodemask_t mems_allowed of the cpuset
 * attached to the specified @tsk.  Guaranteed to return some non-empty
 * subset of node_online_map, even if this means going outside the
 * tasks cpuset.
 **/

nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
{
	nodemask_t mask;

	down(&callback_sem);
	task_lock(tsk);
	guarantee_online_mems(tsk->cpuset, &mask);
	task_unlock(tsk);
	up(&callback_sem);

	return mask;
}

1915
1916
1917
1918
/**
 * cpuset_zonelist_valid_mems_allowed - check zonelist vs. curremt mems_allowed
 * @zl: the zonelist to be checked
 *
Linus Torvalds's avatar
Linus Torvalds committed
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
 * Are any of the nodes on zonelist zl allowed in current->mems_allowed?
 */
int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl)
{
	int i;

	for (i = 0; zl->zones[i]; i++) {
		int nid = zl->zones[i]->zone_pgdat->node_id;

		if (node_isset(nid, current->mems_allowed))
			return 1;
	}
	return 0;
}

1934
1935
/*
 * nearest_exclusive_ancestor() - Returns the nearest mem_exclusive
1936
 * ancestor to the specified cpuset.  Call holding callback_sem.
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
 * If no ancestor is mem_exclusive (an unusual configuration), then
 * returns the root cpuset.
 */
static const struct cpuset *nearest_exclusive_ancestor(const struct cpuset *cs)
{
	while (!is_mem_exclusive(cs) && cs->parent)
		cs = cs->parent;
	return cs;
}

1947
/**
1948
1949
1950
 * cpuset_zone_allowed - Can we allocate memory on zone z's memory node?
 * @z: is this zone on an allowed node?
 * @gfp_mask: memory allocation flags (we use __GFP_HARDWALL)
1951
 *
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
 * If we're in interrupt, yes, we can always allocate.  If zone
 * z's node is in our tasks mems_allowed, yes.  If it's not a
 * __GFP_HARDWALL request and this zone's nodes is in the nearest
 * mem_exclusive cpuset ancestor to this tasks cpuset, yes.
 * Otherwise, no.
 *
 * GFP_USER allocations are marked with the __GFP_HARDWALL bit,
 * and do not allow allocations outside the current tasks cpuset.
 * GFP_KERNEL allocations are not so marked, so can escape to the
 * nearest mem_exclusive ancestor cpuset.
 *
1963
 * Scanning up parent cpusets requires callback_sem.  The __alloc_pages()
1964
1965
1966
1967
 * routine only calls here with __GFP_HARDWALL bit _not_ set if
 * it's a GFP_KERNEL allocation, and all nodes in the current tasks
 * mems_allowed came up empty on the first pass over the zonelist.
 * So only GFP_KERNEL allocations, if all nodes in the cpuset are
1968
 * short of memory, might require taking the callback_sem semaphore.
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
 *
 * The first loop over the zonelist in mm/page_alloc.c:__alloc_pages()
 * calls here with __GFP_HARDWALL always set in gfp_mask, enforcing
 * hardwall cpusets - no allocation on a node outside the cpuset is
 * allowed (unless in interrupt, of course).
 *
 * The second loop doesn't even call here for GFP_ATOMIC requests
 * (if the __alloc_pages() local variable 'wait' is set).  That check
 * and the checks below have the combined affect in the second loop of
 * the __alloc_pages() routine that:
 *	in_interrupt - any node ok (current task context irrelevant)
 *	GFP_ATOMIC   - any node ok
 *	GFP_KERNEL   - any node in enclosing mem_exclusive cpuset ok
 *	GFP_USER     - only nodes in current tasks mems allowed ok.
 **/

1985
int cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
Linus Torvalds's avatar
Linus Torvalds committed
1986
{
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
	int node;			/* node that zone z is on */
	const struct cpuset *cs;	/* current cpuset ancestors */
	int allowed = 1;		/* is allocation in zone z allowed? */

	if (in_interrupt())
		return 1;
	node = z->zone_pgdat->node_id;
	if (node_isset(node, current->mems_allowed))
		return 1;
	if (gfp_mask & __GFP_HARDWALL)	/* If hardwall request, stop here */
		return 0;

1999
2000
2001
	if (current->flags & PF_EXITING) /* Let dying task have memory */
		return 1;

2002
	/* Not hardwall and node outside mems_allowed: scan up cpusets */