cpuset.c 66.7 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34
/*
 *  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>
L
Linus Torvalds 已提交
36 37 38 39 40 41
#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>
42
#include <linux/rcupdate.h>
L
Linus Torvalds 已提交
43 44 45 46 47 48 49 50 51 52 53 54 55
#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>
56
#include <linux/mutex.h>
L
Linus Torvalds 已提交
57

58
#define CPUSET_SUPER_MAGIC		0x27e0eb
L
Linus Torvalds 已提交
59

60 61 62 63 64
/*
 * Tracks how many cpusets are currently defined in system.
 * When there is only one cpuset (the root cpuset) we can
 * short circuit some hooks.
 */
65
int number_of_cpusets __read_mostly;
66

67 68 69 70 71 72 73 74 75
/* 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 */
};

L
Linus Torvalds 已提交
76 77 78 79 80
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 */

81 82 83
	/*
	 * Count is atomic so can incr (fork) or decr (exit) without a lock.
	 */
L
Linus Torvalds 已提交
84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99
	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.
	 */
100 101 102
	int mems_generation;

	struct fmeter fmeter;		/* memory_pressure filter */
L
Linus Torvalds 已提交
103 104 105 106 107 108
};

/* bits in struct cpuset flags field */
typedef enum {
	CS_CPU_EXCLUSIVE,
	CS_MEM_EXCLUSIVE,
109
	CS_MEMORY_MIGRATE,
L
Linus Torvalds 已提交
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
	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);
}

135 136 137 138 139
static inline int is_memory_migrate(const struct cpuset *cs)
{
	return !!test_bit(CS_MEMORY_MIGRATE, &cs->flags);
}

L
Linus Torvalds 已提交
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
/*
 * 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;
168
static struct super_block *cpuset_sb;
L
Linus Torvalds 已提交
169 170

/*
171 172
 * We have two global cpuset mutexes below.  They can nest.
 * It is ok to first take manage_mutex, then nest callback_mutex.  We also
173 174 175
 * require taking task_lock() when dereferencing a tasks cpuset pointer.
 * See "The task_lock() exception", at the end of this comment.
 *
176 177 178
 * A task must hold both mutexes to modify cpusets.  If a task
 * holds manage_mutex, then it blocks others wanting that mutex,
 * ensuring that it is the only task able to also acquire callback_mutex
179 180
 * and be able to modify cpusets.  It can perform various checks on
 * the cpuset structure first, knowing nothing will change.  It can
181
 * also allocate memory while just holding manage_mutex.  While it is
182
 * performing these checks, various callback routines can briefly
183 184
 * acquire callback_mutex to query cpusets.  Once it is ready to make
 * the changes, it takes callback_mutex, blocking everyone else.
185 186
 *
 * Calls to the kernel memory allocator can not be made while holding
187
 * callback_mutex, as that would risk double tripping on callback_mutex
188 189 190
 * from one of the callbacks into the cpuset code from within
 * __alloc_pages().
 *
191
 * If a task is only holding callback_mutex, then it has read-only
192 193 194 195 196 197
 * 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.
198
 * So in general, code holding manage_mutex or callback_mutex can't rely
199
 * on the count field not changing.  However, if the count goes to
200
 * zero, then only attach_task(), which holds both mutexes, can
201 202 203
 * 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).
204
 * So code holding manage_mutex or callback_mutex can safely assume that
205
 * if the count is zero, it will stay zero.  Similarly, if a task
206
 * holds manage_mutex or callback_mutex on a cpuset with zero count, it
207
 * knows that the cpuset won't be removed, as cpuset_rmdir() needs
208
 * both of those mutexes.
209 210
 *
 * The cpuset_common_file_write handler for operations that modify
211
 * the cpuset hierarchy holds manage_mutex across the entire operation,
212 213
 * single threading all such cpuset modifications across the system.
 *
214
 * The cpuset_common_file_read() handlers only hold callback_mutex across
215 216 217 218
 * 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
219
 * (usually) take either mutex.  These are the two most performance
220
 * critical pieces of code here.  The exception occurs on cpuset_exit(),
221
 * when a task in a notify_on_release cpuset exits.  Then manage_mutex
222
 * is taken, and if the cpuset count is zero, a usermode call made
L
Linus Torvalds 已提交
223 224 225
 * to /sbin/cpuset_release_agent with the name of the cpuset (path
 * relative to the root of cpuset file system) as the argument.
 *
226 227 228 229 230 231 232 233 234 235 236 237 238
 * 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
239
 * so using both mutexes, however there are several performance
240
 * critical places that need to reference task->cpuset without the
241
 * expense of grabbing a system global mutex.  Therefore except as
242 243 244 245
 * 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.
246 247 248 249 250
 *
 * P.S.  One more locking exception.  RCU is used to guard the
 * update of a tasks cpuset pointer by attach_task() and the
 * access of task->cpuset->mems_generation via that pointer in
 * the routine cpuset_update_task_memory_state().
L
Linus Torvalds 已提交
251 252
 */

253 254
static DEFINE_MUTEX(manage_mutex);
static DEFINE_MUTEX(callback_mutex);
255

L
Linus Torvalds 已提交
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
/*
 * 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)
{
303
	struct dentry *d = lookup_one_len(name, parent, strlen(name));
L
Linus Torvalds 已提交
304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327
	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) {
E
Eric Dumazet 已提交
328
		struct dentry *d = list_entry(node, struct dentry, d_u.d_child);
L
Linus Torvalds 已提交
329 330 331 332 333 334 335 336 337 338 339
		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;
	}
E
Eric Dumazet 已提交
340
	list_del_init(&dentry->d_u.d_child);
L
Linus Torvalds 已提交
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
	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;
}

/*
429
 * Call with manage_mutex held.  Writes path of cpuset into buf.
L
Linus Torvalds 已提交
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
 * 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.
 *
473 474 475 476 477 478 479 480
 * 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.
 *
481
 * When we had only one cpuset mutex, we had to call this
482 483
 * without holding it, to avoid deadlock when call_usermodehelper()
 * allocated memory.  With two locks, we could now call this while
484 485
 * holding manage_mutex, but we still don't, so as to minimize
 * the time manage_mutex is held.
L
Linus Torvalds 已提交
486 487
 */

488
static void cpuset_release_agent(const char *pathbuf)
L
Linus Torvalds 已提交
489 490 491 492
{
	char *argv[3], *envp[3];
	int i;

493 494 495
	if (!pathbuf)
		return;

L
Linus Torvalds 已提交
496 497
	i = 0;
	argv[i++] = "/sbin/cpuset_release_agent";
498
	argv[i++] = (char *)pathbuf;
L
Linus Torvalds 已提交
499 500 501 502 503 504 505 506
	argv[i] = NULL;

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

507 508
	call_usermodehelper(argv[0], argv, envp, 0);
	kfree(pathbuf);
L
Linus Torvalds 已提交
509 510 511 512 513 514
}

/*
 * 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
515 516
 * 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
517 518
 * cpuset_release_agent() with it later on, once manage_mutex is dropped.
 * Call here with manage_mutex held.
519 520 521 522 523
 *
 * 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
524 525
 * calling check_for_release() with manage_mutex held and the address
 * of the pathbuf pointer, then dropping manage_mutex, then calling
526
 * cpuset_release_agent() with pathbuf, as set by check_for_release().
L
Linus Torvalds 已提交
527 528
 */

529
static void check_for_release(struct cpuset *cs, char **ppathbuf)
L
Linus Torvalds 已提交
530 531 532 533 534 535 536 537 538
{
	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)
539 540 541
			kfree(buf);
		else
			*ppathbuf = buf;
L
Linus Torvalds 已提交
542 543 544 545 546 547 548 549 550 551 552 553 554 555
	}
}

/*
 * 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.
 *
556
 * Call with callback_mutex held.
L
Linus Torvalds 已提交
557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579
 */

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.
 *
580
 * Call with callback_mutex held.
L
Linus Torvalds 已提交
581 582 583 584 585 586 587 588 589 590 591 592 593
 */

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));
}

594 595 596 597 598 599
/**
 * 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.
600
 *
601 602 603 604
 * 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().
 *
605 606
 * Call without callback_mutex or task_lock() held.  May be called
 * with or without manage_mutex held.  Doesn't need task_lock to guard
607 608 609
 * 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
610
 * cpuset pointer.  This routine also might acquire callback_mutex and
611
 * current->mm->mmap_sem during call.
612
 *
613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630
 * Reading current->cpuset->mems_generation doesn't need task_lock
 * to guard the current->cpuset derefence, because it is guarded
 * from concurrent freeing of current->cpuset by attach_task(),
 * using RCU.
 *
 * The rcu_dereference() is technically probably not needed,
 * as I don't actually mind if I see a new cpuset pointer but
 * an old value of mems_generation.  However this really only
 * matters on alpha systems using cpusets heavily.  If I dropped
 * that rcu_dereference(), it would save them a memory barrier.
 * For all other arch's, rcu_dereference is a no-op anyway, and for
 * alpha systems not using cpusets, another planned optimization,
 * avoiding the rcu critical section for tasks in the root cpuset
 * which is statically allocated, so can't vanish, will make this
 * irrelevant.  Better to use RCU as intended, than to engage in
 * some cute trick to save a memory barrier that is impossible to
 * test, for alpha systems using cpusets heavily, which might not
 * even exist.
631 632 633 634 635
 *
 * 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.
L
Linus Torvalds 已提交
636 637
 */

638
void cpuset_update_task_memory_state(void)
L
Linus Torvalds 已提交
639
{
640
	int my_cpusets_mem_gen;
641
	struct task_struct *tsk = current;
642
	struct cpuset *cs;
643

644 645 646 647 648 649 650 651 652
	if (tsk->cpuset == &top_cpuset) {
		/* Don't need rcu for top_cpuset.  It's never freed. */
		my_cpusets_mem_gen = top_cpuset.mems_generation;
	} else {
		rcu_read_lock();
		cs = rcu_dereference(tsk->cpuset);
		my_cpusets_mem_gen = cs->mems_generation;
		rcu_read_unlock();
	}
L
Linus Torvalds 已提交
653

654
	if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) {
655
		mutex_lock(&callback_mutex);
656 657 658 659 660
		task_lock(tsk);
		cs = tsk->cpuset;	/* Maybe changed when task not locked */
		guarantee_online_mems(cs, &tsk->mems_allowed);
		tsk->cpuset_mems_generation = cs->mems_generation;
		task_unlock(tsk);
661
		mutex_unlock(&callback_mutex);
662
		mpol_rebind_task(tsk, &tsk->mems_allowed);
L
Linus Torvalds 已提交
663 664 665 666 667 668 669 670
	}
}

/*
 * 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
671
 * are only set if the other's are set.  Call holding manage_mutex.
L
Linus Torvalds 已提交
672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688
 */

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
689
 * manage_mutex held.
L
Linus Torvalds 已提交
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
 *
 * '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;
}

735 736 737 738 739 740 741 742
/*
 * 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
 *
743
 * Call with manage_mutex held.  May nest a call to the
744 745
 * lock_cpu_hotplug()/unlock_cpu_hotplug() pair.
 */
746

747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787
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();
}

788
/*
789
 * Call with manage_mutex held.  May take callback_mutex during call.
790 791
 */

L
Linus Torvalds 已提交
792 793 794
static int update_cpumask(struct cpuset *cs, char *buf)
{
	struct cpuset trialcs;
795
	int retval, cpus_unchanged;
L
Linus Torvalds 已提交
796 797 798 799 800 801 802 803 804

	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);
805 806 807
	if (retval < 0)
		return retval;
	cpus_unchanged = cpus_equal(cs->cpus_allowed, trialcs.cpus_allowed);
808
	mutex_lock(&callback_mutex);
809
	cs->cpus_allowed = trialcs.cpus_allowed;
810
	mutex_unlock(&callback_mutex);
811 812 813
	if (is_cpu_exclusive(cs) && !cpus_unchanged)
		update_cpu_domains(cs);
	return 0;
L
Linus Torvalds 已提交
814 815
}

816
/*
817 818 819
 * Handle user request to change the 'mems' memory placement
 * of a cpuset.  Needs to validate the request, update the
 * cpusets mems_allowed and mems_generation, and for each
820 821 822
 * task in the cpuset, rebind any vma mempolicies and if
 * the cpuset is marked 'memory_migrate', migrate the tasks
 * pages to the new memory.
823
 *
824
 * Call with manage_mutex held.  May take callback_mutex during call.
825 826 827
 * Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
 * lock each such tasks mm->mmap_sem, scan its vma's and rebind
 * their mempolicies to the cpusets new mems_allowed.
828 829
 */

L
Linus Torvalds 已提交
830 831 832
static int update_nodemask(struct cpuset *cs, char *buf)
{
	struct cpuset trialcs;
833
	nodemask_t oldmem;
834 835 836
	struct task_struct *g, *p;
	struct mm_struct **mmarray;
	int i, n, ntasks;
837
	int migrate;
838
	int fudge;
L
Linus Torvalds 已提交
839 840 841 842 843
	int retval;

	trialcs = *cs;
	retval = nodelist_parse(buf, trialcs.mems_allowed);
	if (retval < 0)
844
		goto done;
L
Linus Torvalds 已提交
845
	nodes_and(trialcs.mems_allowed, trialcs.mems_allowed, node_online_map);
846 847 848 849 850
	oldmem = cs->mems_allowed;
	if (nodes_equal(oldmem, trialcs.mems_allowed)) {
		retval = 0;		/* Too easy - nothing to do */
		goto done;
	}
851 852 853
	if (nodes_empty(trialcs.mems_allowed)) {
		retval = -ENOSPC;
		goto done;
L
Linus Torvalds 已提交
854
	}
855 856 857 858
	retval = validate_change(cs, &trialcs);
	if (retval < 0)
		goto done;

859
	mutex_lock(&callback_mutex);
860 861 862
	cs->mems_allowed = trialcs.mems_allowed;
	atomic_inc(&cpuset_mems_generation);
	cs->mems_generation = atomic_read(&cpuset_mems_generation);
863
	mutex_unlock(&callback_mutex);
864

865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918
	set_cpuset_being_rebound(cs);		/* causes mpol_copy() rebind */

	fudge = 10;				/* spare mmarray[] slots */
	fudge += cpus_weight(cs->cpus_allowed);	/* imagine one fork-bomb/cpu */
	retval = -ENOMEM;

	/*
	 * Allocate mmarray[] to hold mm reference for each task
	 * in cpuset cs.  Can't kmalloc GFP_KERNEL while holding
	 * tasklist_lock.  We could use GFP_ATOMIC, but with a
	 * few more lines of code, we can retry until we get a big
	 * enough mmarray[] w/o using GFP_ATOMIC.
	 */
	while (1) {
		ntasks = atomic_read(&cs->count);	/* guess */
		ntasks += fudge;
		mmarray = kmalloc(ntasks * sizeof(*mmarray), GFP_KERNEL);
		if (!mmarray)
			goto done;
		write_lock_irq(&tasklist_lock);		/* block fork */
		if (atomic_read(&cs->count) <= ntasks)
			break;				/* got enough */
		write_unlock_irq(&tasklist_lock);	/* try again */
		kfree(mmarray);
	}

	n = 0;

	/* Load up mmarray[] with mm reference for each task in cpuset. */
	do_each_thread(g, p) {
		struct mm_struct *mm;

		if (n >= ntasks) {
			printk(KERN_WARNING
				"Cpuset mempolicy rebind incomplete.\n");
			continue;
		}
		if (p->cpuset != cs)
			continue;
		mm = get_task_mm(p);
		if (!mm)
			continue;
		mmarray[n++] = mm;
	} while_each_thread(g, p);
	write_unlock_irq(&tasklist_lock);

	/*
	 * Now that we've dropped the tasklist spinlock, we can
	 * rebind the vma mempolicies of each mm in mmarray[] to their
	 * new cpuset, and release that mm.  The mpol_rebind_mm()
	 * call takes mmap_sem, which we couldn't take while holding
	 * tasklist_lock.  Forks can happen again now - the mpol_copy()
	 * cpuset_being_rebound check will catch such forks, and rebind
	 * their vma mempolicies too.  Because we still hold the global
919
	 * cpuset manage_mutex, we know that no other rebind effort will
920 921
	 * be contending for the global variable cpuset_being_rebound.
	 * It's ok if we rebind the same mm twice; mpol_rebind_mm()
922
	 * is idempotent.  Also migrate pages in each mm to new nodes.
923
	 */
924
	migrate = is_memory_migrate(cs);
925 926 927 928
	for (i = 0; i < n; i++) {
		struct mm_struct *mm = mmarray[i];

		mpol_rebind_mm(mm, &cs->mems_allowed);
929 930 931 932
		if (migrate) {
			do_migrate_pages(mm, &oldmem, &cs->mems_allowed,
							MPOL_MF_MOVE_ALL);
		}
933 934 935 936 937 938 939
		mmput(mm);
	}

	/* We're done rebinding vma's to this cpusets new mems_allowed. */
	kfree(mmarray);
	set_cpuset_being_rebound(NULL);
	retval = 0;
940
done:
L
Linus Torvalds 已提交
941 942 943
	return retval;
}

944
/*
945
 * Call with manage_mutex held.
946 947 948 949 950 951 952 953 954 955 956
 */

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;
}

L
Linus Torvalds 已提交
957 958 959
/*
 * 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,
960
 *				CS_NOTIFY_ON_RELEASE, CS_MEMORY_MIGRATE)
L
Linus Torvalds 已提交
961 962
 * cs:	the cpuset to update
 * buf:	the buffer where we read the 0 or 1
963
 *
964
 * Call with manage_mutex held.
L
Linus Torvalds 已提交
965 966 967 968 969 970
 */

static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf)
{
	int turning_on;
	struct cpuset trialcs;
971
	int err, cpu_exclusive_changed;
L
Linus Torvalds 已提交
972 973 974 975 976 977 978 979 980 981

	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);
982 983 984 985
	if (err < 0)
		return err;
	cpu_exclusive_changed =
		(is_cpu_exclusive(cs) != is_cpu_exclusive(&trialcs));
986
	mutex_lock(&callback_mutex);
987 988 989 990
	if (turning_on)
		set_bit(bit, &cs->flags);
	else
		clear_bit(bit, &cs->flags);
991
	mutex_unlock(&callback_mutex);
992 993 994 995

	if (cpu_exclusive_changed)
                update_cpu_domains(cs);
	return 0;
L
Linus Torvalds 已提交
996 997
}

998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095
/*
 * 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;
}

1096 1097 1098 1099 1100
/*
 * 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.
 *
1101
 * Call holding manage_mutex.  May take callback_mutex and task_lock of
1102 1103 1104
 * the task 'pid' during call.
 */

1105
static int attach_task(struct cpuset *cs, char *pidbuf, char **ppathbuf)
L
Linus Torvalds 已提交
1106 1107 1108 1109 1110
{
	pid_t pid;
	struct task_struct *tsk;
	struct cpuset *oldcs;
	cpumask_t cpus;
1111
	nodemask_t from, to;
1112
	struct mm_struct *mm;
L
Linus Torvalds 已提交
1113

1114
	if (sscanf(pidbuf, "%d", &pid) != 1)
L
Linus Torvalds 已提交
1115 1116 1117 1118 1119 1120 1121 1122
		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);
1123
		if (!tsk || tsk->flags & PF_EXITING) {
L
Linus Torvalds 已提交
1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140
			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);
	}

1141
	mutex_lock(&callback_mutex);
1142

L
Linus Torvalds 已提交
1143 1144 1145 1146
	task_lock(tsk);
	oldcs = tsk->cpuset;
	if (!oldcs) {
		task_unlock(tsk);
1147
		mutex_unlock(&callback_mutex);
L
Linus Torvalds 已提交
1148 1149 1150 1151
		put_task_struct(tsk);
		return -ESRCH;
	}
	atomic_inc(&cs->count);
1152
	rcu_assign_pointer(tsk->cpuset, cs);
L
Linus Torvalds 已提交
1153 1154 1155 1156 1157
	task_unlock(tsk);

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

1158 1159 1160
	from = oldcs->mems_allowed;
	to = cs->mems_allowed;

1161
	mutex_unlock(&callback_mutex);
1162 1163 1164 1165 1166 1167 1168

	mm = get_task_mm(tsk);
	if (mm) {
		mpol_rebind_mm(mm, &to);
		mmput(mm);
	}

1169 1170
	if (is_memory_migrate(cs))
		do_migrate_pages(tsk->mm, &from, &to, MPOL_MF_MOVE_ALL);
L
Linus Torvalds 已提交
1171
	put_task_struct(tsk);
1172
	synchronize_rcu();
L
Linus Torvalds 已提交
1173
	if (atomic_dec_and_test(&oldcs->count))
1174
		check_for_release(oldcs, ppathbuf);
L
Linus Torvalds 已提交
1175 1176 1177 1178 1179 1180 1181 1182
	return 0;
}

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

typedef enum {
	FILE_ROOT,
	FILE_DIR,
1183
	FILE_MEMORY_MIGRATE,
L
Linus Torvalds 已提交
1184 1185 1186 1187 1188
	FILE_CPULIST,
	FILE_MEMLIST,
	FILE_CPU_EXCLUSIVE,
	FILE_MEM_EXCLUSIVE,
	FILE_NOTIFY_ON_RELEASE,
1189 1190
	FILE_MEMORY_PRESSURE_ENABLED,
	FILE_MEMORY_PRESSURE,
L
Linus Torvalds 已提交
1191 1192 1193 1194 1195 1196 1197 1198 1199 1200
	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;
1201
	char *pathbuf = NULL;
L
Linus Torvalds 已提交
1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217
	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 */

1218
	mutex_lock(&manage_mutex);
L
Linus Torvalds 已提交
1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240

	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;
1241 1242 1243
	case FILE_MEMORY_MIGRATE:
		retval = update_flag(CS_MEMORY_MIGRATE, cs, buffer);
		break;
1244 1245 1246 1247 1248 1249
	case FILE_MEMORY_PRESSURE_ENABLED:
		retval = update_memory_pressure_enabled(cs, buffer);
		break;
	case FILE_MEMORY_PRESSURE:
		retval = -EACCES;
		break;
L
Linus Torvalds 已提交
1250
	case FILE_TASKLIST:
1251
		retval = attach_task(cs, buffer, &pathbuf);
L
Linus Torvalds 已提交
1252 1253 1254 1255 1256 1257 1258 1259 1260
		break;
	default:
		retval = -EINVAL;
		goto out2;
	}

	if (retval == 0)
		retval = nbytes;
out2:
1261
	mutex_unlock(&manage_mutex);
1262
	cpuset_release_agent(pathbuf);
L
Linus Torvalds 已提交
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
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;

1301
	mutex_lock(&callback_mutex);
L
Linus Torvalds 已提交
1302
	mask = cs->cpus_allowed;
1303
	mutex_unlock(&callback_mutex);
L
Linus Torvalds 已提交
1304 1305 1306 1307 1308 1309 1310 1311

	return cpulist_scnprintf(page, PAGE_SIZE, mask);
}

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

1312
	mutex_lock(&callback_mutex);
L
Linus Torvalds 已提交
1313
	mask = cs->mems_allowed;
1314
	mutex_unlock(&callback_mutex);
L
Linus Torvalds 已提交
1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349

	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;
1350 1351 1352
	case FILE_MEMORY_MIGRATE:
		*s++ = is_memory_migrate(cs) ? '1' : '0';
		break;
1353 1354 1355 1356 1357 1358
	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;
L
Linus Torvalds 已提交
1359 1360 1361 1362 1363 1364
	default:
		retval = -EINVAL;
		goto out;
	}
	*s++ = '\n';

A
Al Viro 已提交
1365
	retval = simple_read_from_buffer(buf, nbytes, ppos, page, s - page);
L
Linus Torvalds 已提交
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
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;
}

P
Paul Jackson 已提交
1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430
/*
 * 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);
}

L
Linus Torvalds 已提交
1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442
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,
P
Paul Jackson 已提交
1443
	.rename = cpuset_rename,
L
Linus Torvalds 已提交
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 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.
1477
 *	cs:	the cpuset we create the directory for.
L
Linus Torvalds 已提交
1478 1479 1480 1481 1482 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
 *		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;

1510
	mutex_lock(&dir->d_inode->i_mutex);
L
Linus Torvalds 已提交
1511 1512 1513 1514 1515 1516 1517 1518
	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);
1519
	mutex_unlock(&dir->d_inode->i_mutex);
L
Linus Torvalds 已提交
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
	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'.
1547 1548 1549
 * 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.
L
Linus Torvalds 已提交
1550
 */
1551
static int pid_array_load(pid_t *pidarray, int npids, struct cpuset *cs)
L
Linus Torvalds 已提交
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
{
	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;
}

1591 1592 1593 1594
/*
 * Handle an open on 'tasks' file.  Prepare a buffer listing the
 * process id's of tasks currently attached to the cpuset being opened.
 *
1595
 * Does not require any specific cpuset mutexes, and does not take any.
1596
 */
L
Linus Torvalds 已提交
1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706
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,
};

1707 1708 1709 1710 1711
static struct cftype cft_memory_migrate = {
	.name = "memory_migrate",
	.private = FILE_MEMORY_MIGRATE,
};

1712 1713 1714 1715 1716 1717 1718 1719 1720 1721
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,
};

L
Linus Torvalds 已提交
1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735
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;
1736 1737
	if ((err = cpuset_add_file(cs_dentry, &cft_memory_migrate)) < 0)
		return err;
1738 1739
	if ((err = cpuset_add_file(cs_dentry, &cft_memory_pressure)) < 0)
		return err;
L
Linus Torvalds 已提交
1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750
	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
 *
1751
 *	Must be called with the mutex on the parent inode held
L
Linus Torvalds 已提交
1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762
 */

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;

1763
	mutex_lock(&manage_mutex);
1764
	cpuset_update_task_memory_state();
L
Linus Torvalds 已提交
1765 1766 1767 1768 1769 1770 1771 1772 1773 1774
	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);
1775
	fmeter_init(&cs->fmeter);
L
Linus Torvalds 已提交
1776 1777 1778

	cs->parent = parent;

1779
	mutex_lock(&callback_mutex);
L
Linus Torvalds 已提交
1780
	list_add(&cs->sibling, &cs->parent->children);
1781
	number_of_cpusets++;
1782
	mutex_unlock(&callback_mutex);
L
Linus Torvalds 已提交
1783 1784 1785 1786 1787 1788

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

	/*
1789
	 * Release manage_mutex before cpuset_populate_dir() because it
1790
	 * will down() this new directory's i_mutex and if we race with
L
Linus Torvalds 已提交
1791 1792
	 * another mkdir, we might deadlock.
	 */
1793
	mutex_unlock(&manage_mutex);
L
Linus Torvalds 已提交
1794 1795 1796 1797 1798 1799

	err = cpuset_populate_dir(cs->dentry);
	/* If err < 0, we have a half-filled directory - oh well ;) */
	return 0;
err:
	list_del(&cs->sibling);
1800
	mutex_unlock(&manage_mutex);
L
Linus Torvalds 已提交
1801 1802 1803 1804 1805 1806 1807 1808
	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;

1809
	/* the vfs holds inode->i_mutex already */
L
Linus Torvalds 已提交
1810 1811 1812 1813 1814 1815 1816 1817
	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;
1818
	char *pathbuf = NULL;
L
Linus Torvalds 已提交
1819

1820
	/* the vfs holds both inode->i_mutex already */
L
Linus Torvalds 已提交
1821

1822
	mutex_lock(&manage_mutex);
1823
	cpuset_update_task_memory_state();
L
Linus Torvalds 已提交
1824
	if (atomic_read(&cs->count) > 0) {
1825
		mutex_unlock(&manage_mutex);
L
Linus Torvalds 已提交
1826 1827 1828
		return -EBUSY;
	}
	if (!list_empty(&cs->children)) {
1829
		mutex_unlock(&manage_mutex);
L
Linus Torvalds 已提交
1830 1831 1832
		return -EBUSY;
	}
	parent = cs->parent;
1833
	mutex_lock(&callback_mutex);
L
Linus Torvalds 已提交
1834
	set_bit(CS_REMOVED, &cs->flags);
1835 1836
	if (is_cpu_exclusive(cs))
		update_cpu_domains(cs);
L
Linus Torvalds 已提交
1837
	list_del(&cs->sibling);	/* delete my sibling from parent->children */
1838
	spin_lock(&cs->dentry->d_lock);
L
Linus Torvalds 已提交
1839 1840 1841 1842 1843
	d = dget(cs->dentry);
	cs->dentry = NULL;
	spin_unlock(&d->d_lock);
	cpuset_d_remove_dir(d);
	dput(d);
1844
	number_of_cpusets--;
1845
	mutex_unlock(&callback_mutex);
1846 1847
	if (list_empty(&parent->children))
		check_for_release(parent, &pathbuf);
1848
	mutex_unlock(&manage_mutex);
1849
	cpuset_release_agent(pathbuf);
L
Linus Torvalds 已提交
1850 1851 1852
	return 0;
}

1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867
/*
 * cpuset_init_early - just enough so that the calls to
 * cpuset_update_task_memory_state() in early init code
 * are harmless.
 */

int __init cpuset_init_early(void)
{
	struct task_struct *tsk = current;

	tsk->cpuset = &top_cpuset;
	tsk->cpuset->mems_generation = atomic_read(&cpuset_mems_generation);
	return 0;
}

L
Linus Torvalds 已提交
1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881
/**
 * 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;

1882
	fmeter_init(&top_cpuset.fmeter);
L
Linus Torvalds 已提交
1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902
	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;
1903
	number_of_cpusets = 1;
L
Linus Torvalds 已提交
1904
	err = cpuset_populate_dir(root);
1905 1906 1907
	/* memory_pressure_enabled is in root cpuset only */
	if (err == 0)
		err = cpuset_add_file(root, &cft_memory_pressure_enabled);
L
Linus Torvalds 已提交
1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925
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.
1926
 * @tsk: pointer to task_struct of forking parent process.
L
Linus Torvalds 已提交
1927
 *
1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939
 * 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.
L
Linus Torvalds 已提交
1940 1941
 **/

1942
void cpuset_fork(struct task_struct *child)
L
Linus Torvalds 已提交
1943
{
1944 1945 1946 1947
	task_lock(current);
	child->cpuset = current->cpuset;
	atomic_inc(&child->cpuset->count);
	task_unlock(current);
L
Linus Torvalds 已提交
1948 1949 1950 1951 1952 1953 1954 1955
}

/**
 * cpuset_exit - detach cpuset from exiting task
 * @tsk: pointer to task_struct of exiting process
 *
 * Description: Detach cpuset from @tsk and release it.
 *
1956
 * Note that cpusets marked notify_on_release force every task in
1957
 * them to take the global manage_mutex mutex when exiting.
1958 1959 1960 1961 1962
 * 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
1963 1964
 * goes to zero, except inside a critical section guarded by manage_mutex
 * or callback_mutex.   Otherwise a zero cpuset use count is a license to
1965 1966
 * any other task to nuke the cpuset immediately, via cpuset_rmdir().
 *
1967 1968 1969
 * This routine has to take manage_mutex, not callback_mutex, because
 * it is holding that mutex while calling check_for_release(),
 * which calls kmalloc(), so can't be called holding callback_mutex().
1970 1971 1972
 *
 * We don't need to task_lock() this reference to tsk->cpuset,
 * because tsk is already marked PF_EXITING, so attach_task() won't
P
Paul Jackson 已提交
1973
 * mess with it, or task is a failed fork, never visible to attach_task.
1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006
 *
 * Hack:
 *
 *    Set the exiting tasks cpuset to the root cpuset (top_cpuset).
 *
 *    Don't leave a task unable to allocate memory, as that is an
 *    accident waiting to happen should someone add a callout in
 *    do_exit() after the cpuset_exit() call that might allocate.
 *    If a task tries to allocate memory with an invalid cpuset,
 *    it will oops in cpuset_update_task_memory_state().
 *
 *    We call cpuset_exit() while the task is still competent to
 *    handle notify_on_release(), then leave the task attached to
 *    the root cpuset (top_cpuset) for the remainder of its exit.
 *
 *    To do this properly, we would increment the reference count on
 *    top_cpuset, and near the very end of the kernel/exit.c do_exit()
 *    code we would add a second cpuset function call, to drop that
 *    reference.  This would just create an unnecessary hot spot on
 *    the top_cpuset reference count, to no avail.
 *
 *    Normally, holding a reference to a cpuset without bumping its
 *    count is unsafe.   The cpuset could go away, or someone could
 *    attach us to a different cpuset, decrementing the count on
 *    the first cpuset that we never incremented.  But in this case,
 *    top_cpuset isn't going away, and either task has PF_EXITING set,
 *    which wards off any attach_task() attempts, or task is a failed
 *    fork, never visible to attach_task.
 *
 *    Another way to do this would be to set the cpuset pointer
 *    to NULL here, and check in cpuset_update_task_memory_state()
 *    for a NULL pointer.  This hack avoids that NULL check, for no
 *    cost (other than this way too long comment ;).
L
Linus Torvalds 已提交
2007 2008 2009 2010 2011 2012 2013
 **/

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

	cs = tsk->cpuset;
2014
	tsk->cpuset = &top_cpuset;	/* Hack - see comment above */
L
Linus Torvalds 已提交
2015

2016
	if (notify_on_release(cs)) {
2017 2018
		char *pathbuf = NULL;

2019
		mutex_lock(&manage_mutex);
2020
		if (atomic_dec_and_test(&cs->count))
2021
			check_for_release(cs, &pathbuf);
2022
		mutex_unlock(&manage_mutex);
2023
		cpuset_release_agent(pathbuf);
2024 2025
	} else {
		atomic_dec(&cs->count);
L
Linus Torvalds 已提交
2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038
	}
}

/**
 * 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.
 **/

2039
cpumask_t cpuset_cpus_allowed(struct task_struct *tsk)
L
Linus Torvalds 已提交
2040 2041 2042
{
	cpumask_t mask;

2043
	mutex_lock(&callback_mutex);
2044
	task_lock(tsk);
L
Linus Torvalds 已提交
2045
	guarantee_online_cpus(tsk->cpuset, &mask);
2046
	task_unlock(tsk);
2047
	mutex_unlock(&callback_mutex);
L
Linus Torvalds 已提交
2048 2049 2050 2051 2052 2053 2054 2055 2056

	return mask;
}

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

2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070
/**
 * 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;

2071
	mutex_lock(&callback_mutex);
2072 2073 2074
	task_lock(tsk);
	guarantee_online_mems(tsk->cpuset, &mask);
	task_unlock(tsk);
2075
	mutex_unlock(&callback_mutex);
2076 2077 2078 2079

	return mask;
}

2080 2081 2082 2083
/**
 * cpuset_zonelist_valid_mems_allowed - check zonelist vs. curremt mems_allowed
 * @zl: the zonelist to be checked
 *
L
Linus Torvalds 已提交
2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098
 * 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;
}

2099 2100
/*
 * nearest_exclusive_ancestor() - Returns the nearest mem_exclusive
2101
 * ancestor to the specified cpuset.  Call holding callback_mutex.
2102 2103 2104 2105 2106 2107 2108 2109 2110 2111
 * 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;
}

2112
/**
2113 2114 2115
 * 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)
2116
 *
2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127
 * 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.
 *
2128
 * Scanning up parent cpusets requires callback_mutex.  The __alloc_pages()
2129 2130 2131 2132
 * 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
2133
 * short of memory, might require taking the callback_mutex mutex.
2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149
 *
 * 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.
 **/

2150
int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
L
Linus Torvalds 已提交
2151
{
2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163
	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;

2164 2165 2166
	if (current->flags & PF_EXITING) /* Let dying task have memory */
		return 1;

2167
	/* Not hardwall and node outside mems_allowed: scan up cpusets */
2168
	mutex_lock(&callback_mutex);
2169 2170 2171 2172 2173

	task_lock(current);
	cs = nearest_exclusive_ancestor(current->cpuset);
	task_unlock(current);

2174
	allowed = node_isset(node, cs->mems_allowed);
2175
	mutex_unlock(&callback_mutex);
2176
	return allowed;
L
Linus Torvalds 已提交
2177 2178
}

P
Paul Jackson 已提交
2179 2180 2181
/**
 * cpuset_lock - lock out any changes to cpuset structures
 *
2182
 * The out of memory (oom) code needs to mutex_lock cpusets
P
Paul Jackson 已提交
2183
 * from being changed while it scans the tasklist looking for a
2184
 * task in an overlapping cpuset.  Expose callback_mutex via this
P
Paul Jackson 已提交
2185 2186
 * cpuset_lock() routine, so the oom code can lock it, before
 * locking the task list.  The tasklist_lock is a spinlock, so
2187
 * must be taken inside callback_mutex.
P
Paul Jackson 已提交
2188 2189 2190 2191
 */

void cpuset_lock(void)
{
2192
	mutex_lock(&callback_mutex);
P
Paul Jackson 已提交
2193 2194 2195 2196 2197 2198 2199 2200 2201 2202
}

/**
 * cpuset_unlock - release lock on cpuset changes
 *
 * Undo the lock taken in a previous cpuset_lock() call.
 */

void cpuset_unlock(void)
{
2203
	mutex_unlock(&callback_mutex);
P
Paul Jackson 已提交
2204 2205
}

2206 2207 2208 2209 2210 2211 2212 2213 2214
/**
 * cpuset_excl_nodes_overlap - Do we overlap @p's mem_exclusive ancestors?
 * @p: pointer to task_struct of some other task.
 *
 * Description: Return true if the nearest mem_exclusive ancestor
 * cpusets of tasks @p and current overlap.  Used by oom killer to
 * determine if task @p's memory usage might impact the memory
 * available to the current task.
 *
2215
 * Call while holding callback_mutex.
2216 2217 2218 2219 2220 2221 2222
 **/

int cpuset_excl_nodes_overlap(const struct task_struct *p)
{
	const struct cpuset *cs1, *cs2;	/* my and p's cpuset ancestors */
	int overlap = 0;		/* do cpusets overlap? */

2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238
	task_lock(current);
	if (current->flags & PF_EXITING) {
		task_unlock(current);
		goto done;
	}
	cs1 = nearest_exclusive_ancestor(current->cpuset);
	task_unlock(current);

	task_lock((struct task_struct *)p);
	if (p->flags & PF_EXITING) {
		task_unlock((struct task_struct *)p);
		goto done;
	}
	cs2 = nearest_exclusive_ancestor(p->cpuset);
	task_unlock((struct task_struct *)p);

2239 2240 2241 2242 2243
	overlap = nodes_intersects(cs1->mems_allowed, cs2->mems_allowed);
done:
	return overlap;
}

2244 2245 2246 2247 2248 2249
/*
 * Collection of memory_pressure is suppressed unless
 * this flag is enabled by writing "1" to the special
 * cpuset file 'memory_pressure_enabled' in the root cpuset.
 */

2250
int cpuset_memory_pressure_enabled __read_mostly;
2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279

/**
 * cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims.
 *
 * Keep a running average of the rate of synchronous (direct)
 * page reclaim efforts initiated by tasks in each cpuset.
 *
 * This represents the rate at which some task in the cpuset
 * ran low on memory on all nodes it was allowed to use, and
 * had to enter the kernels page reclaim code in an effort to
 * create more free memory by tossing clean pages or swapping
 * or writing dirty pages.
 *
 * Display to user space in the per-cpuset read-only file
 * "memory_pressure".  Value displayed is an integer
 * representing the recent rate of entry into the synchronous
 * (direct) page reclaim by any task attached to the cpuset.
 **/

void __cpuset_memory_pressure_bump(void)
{
	struct cpuset *cs;

	task_lock(current);
	cs = current->cpuset;
	fmeter_markevent(&cs->fmeter);
	task_unlock(current);
}

L
Linus Torvalds 已提交
2280 2281 2282 2283
/*
 * proc_cpuset_show()
 *  - Print tasks cpuset path into seq_file.
 *  - Used for /proc/<pid>/cpuset.
2284 2285
 *  - No need to task_lock(tsk) on this tsk->cpuset reference, as it
 *    doesn't really matter if tsk->cpuset changes after we read it,
2286
 *    and we take manage_mutex, keeping attach_task() from changing it
2287
 *    anyway.
L
Linus Torvalds 已提交
2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301
 */

static int proc_cpuset_show(struct seq_file *m, void *v)
{
	struct cpuset *cs;
	struct task_struct *tsk;
	char *buf;
	int retval = 0;

	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
	if (!buf)
		return -ENOMEM;

	tsk = m->private;
2302
	mutex_lock(&manage_mutex);
L
Linus Torvalds 已提交
2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314
	cs = tsk->cpuset;
	if (!cs) {
		retval = -EINVAL;
		goto out;
	}

	retval = cpuset_path(cs, buf, PAGE_SIZE);
	if (retval < 0)
		goto out;
	seq_puts(m, buf);
	seq_putc(m, '\n');
out:
2315
	mutex_unlock(&manage_mutex);
L
Linus Torvalds 已提交
2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343
	kfree(buf);
	return retval;
}

static int cpuset_open(struct inode *inode, struct file *file)
{
	struct task_struct *tsk = PROC_I(inode)->task;
	return single_open(file, proc_cpuset_show, tsk);
}

struct file_operations proc_cpuset_operations = {
	.open		= cpuset_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= single_release,
};

/* Display task cpus_allowed, mems_allowed in /proc/<pid>/status file. */
char *cpuset_task_status_allowed(struct task_struct *task, char *buffer)
{
	buffer += sprintf(buffer, "Cpus_allowed:\t");
	buffer += cpumask_scnprintf(buffer, PAGE_SIZE, task->cpus_allowed);
	buffer += sprintf(buffer, "\n");
	buffer += sprintf(buffer, "Mems_allowed:\t");
	buffer += nodemask_scnprintf(buffer, PAGE_SIZE, task->mems_allowed);
	buffer += sprintf(buffer, "\n");
	return buffer;
}