cpuset.c

Kernel code of linux kernel

/*
 *  kernel/cpuset.c
 *
 *  Processor and Memory placement constraints for sets of tasks.
 *
 *  Copyright (C) 2003 BULL SA.
 *  Copyright (C) 2004-2007 Silicon Graphics, Inc.
 *  Copyright (C) 2006 Google, Inc
 *
 *  Portions derived from Patrick Mochel's sysfs code.
 *  sysfs is Copyright (c) 2001-3 Patrick Mochel
 *
 *  2003-10-10 Written by Simon Derr.
 *  2003-10-22 Updates by Stephen Hemminger.
 *  2004 May-July Rework by Paul Jackson.
 *  2006 Rework by Paul Menage to use generic cgroups
 *  2008 Rework of the scheduler domains and CPU hotplug handling
 *       by Max Krasnyansky
 *
 *  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/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>
#include <linux/mempolicy.h>
#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/rcupdate.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/security.h>
#include <linux/slab.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 <linux/mutex.h>
#include <linux/workqueue.h>
#include <linux/cgroup.h>

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

/* Forward declare cgroup structures */
struct cgroup_subsys cpuset_subsys;
struct cpuset;

/* 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 */
};

struct cpuset {
	struct cgroup_subsys_state css;

	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 */

	struct cpuset *parent;		/* my parent */

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

	struct fmeter fmeter;		/* memory_pressure filter */

	/* partition number for rebuild_sched_domains() */
	int pn;

	/* for custom sched domain */
	int relax_domain_level;

	/* used for walking a cpuset heirarchy */
	struct list_head stack_list;
};

/* Retrieve the cpuset for a cgroup */
static inline struct cpuset *cgroup_cs(struct cgroup *cont)
{
	return container_of(cgroup_subsys_state(cont, cpuset_subsys_id),
			    struct cpuset, css);
}

/* Retrieve the cpuset for a task */
static inline struct cpuset *task_cs(struct task_struct *task)
{
	return container_of(task_subsys_state(task, cpuset_subsys_id),
			    struct cpuset, css);
}
struct cpuset_hotplug_scanner {
	struct cgroup_scanner scan;
	struct cgroup *to;
};

/* bits in struct cpuset flags field */
typedef enum {
	CS_CPU_EXCLUSIVE,
	CS_MEM_EXCLUSIVE,
	CS_MEM_HARDWALL,
	CS_MEMORY_MIGRATE,
	CS_SCHED_LOAD_BALANCE,
	CS_SPREAD_PAGE,
	CS_SPREAD_SLAB,
} 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_mem_hardwall(const struct cpuset *cs)
{
	return test_bit(CS_MEM_HARDWALL, &cs->flags);
}

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

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

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

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

/*
 * Increment this 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 cpuset_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 another's 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.
 *
 * Since writes to cpuset_mems_generation are guarded by the cgroup lock
 * there is no need to mark it atomic.
 */
static int cpuset_mems_generation;

static struct cpuset top_cpuset = {
	.flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)),
	.cpus_allowed = CPU_MASK_ALL,
	.mems_allowed = NODE_MASK_ALL,
};

/*
 * There are two global mutexes guarding cpuset structures.  The first
 * is the main control groups cgroup_mutex, accessed via
 * cgroup_lock()/cgroup_unlock().  The second is the cpuset-specific
 * callback_mutex, below. They can nest.  It is ok to first take
 * cgroup_mutex, then nest callback_mutex.  We also require taking
 * task_lock() when dereferencing a task's cpuset pointer.  See "The
 * task_lock() exception", at the end of this comment.
 *
 * A task must hold both mutexes to modify cpusets.  If a task
 * holds cgroup_mutex, then it blocks others wanting that mutex,
 * ensuring that it is the only task able to also acquire callback_mutex
 * 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 cgroup_mutex.  While it is
 * performing these checks, various callback routines can briefly
 * acquire callback_mutex to query cpusets.  Once it is ready to make
 * the changes, it takes callback_mutex, blocking everyone else.
 *
 * Calls to the kernel memory allocator can not be made while holding
 * callback_mutex, as that would risk double tripping on callback_mutex
 * from one of the callbacks into the cpuset code from within
 * __alloc_pages().
 *
 * If a task is only holding callback_mutex, 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.
 *
 * The cpuset_common_file_read() handlers only hold callback_mutex across
 * small pieces of code, such as when reading out possibly multi-word
 * cpumasks and nodemasks.
 *
 * Accessing a task's cpuset should be done in accordance with the
 * guidelines for accessing subsystem state in kernel/cgroup.c
 */

static DEFINE_MUTEX(callback_mutex);

/*
 * This is ugly, but preserves the userspace API for existing cpuset
 * users. If someone tries to mount the "cpuset" filesystem, we
 * silently switch it to mount "cgroup" instead
 */
static int cpuset_get_sb(struct file_system_type *fs_type,
			 int flags, const char *unused_dev_name,
			 void *data, struct vfsmount *mnt)
{
	struct file_system_type *cgroup_fs = get_fs_type("cgroup");
	int ret = -ENODEV;
	if (cgroup_fs) {
		char mountopts[] =
			"cpuset,noprefix,"
			"release_agent=/sbin/cpuset_release_agent";
		ret = cgroup_fs->get_sb(cgroup_fs, flags,
					   unused_dev_name, mountopts, mnt);
		put_filesystem(cgroup_fs);
	}
	return ret;
}

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

/*
 * 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.
 *
 * Call with callback_mutex held.
 */

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, with memory.  If none are online with memory, 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_states[N_HIGH_MEMORY].
 *
 * One way or another, we guarantee to return some non-empty subset
 * of node_states[N_HIGH_MEMORY].
 *
 * Call with callback_mutex held.
 */

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

/**
 * 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.
 *
 * 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_mutex or task_lock() held.  May be
 * called with or without cgroup_mutex held.  Thanks in part to
 * 'the_top_cpuset_hack', the task's cpuset pointer will never
 * be NULL.  This routine also might acquire callback_mutex during
 * call.
 *
 * 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 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.
 *
 * 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.
 */

void cpuset_update_task_memory_state(void)
{
	int my_cpusets_mem_gen;
	struct task_struct *tsk = current;
	struct cpuset *cs;

	if (task_cs(tsk) == &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();
		my_cpusets_mem_gen = task_cs(tsk)->mems_generation;
		rcu_read_unlock();
	}

	if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) {
		mutex_lock(&callback_mutex);
		task_lock(tsk);
		cs = task_cs(tsk); /* Maybe changed when task not locked */
		guarantee_online_mems(cs, &tsk->mems_allowed);
		tsk->cpuset_mems_generation = cs->mems_generation;
		if (is_spread_page(cs))
			tsk->flags |= PF_SPREAD_PAGE;
		else
			tsk->flags &= ~PF_SPREAD_PAGE;
		if (is_spread_slab(cs))
			tsk->flags |= PF_SPREAD_SLAB;
		else
			tsk->flags &= ~PF_SPREAD_SLAB;
		task_unlock(tsk);
		mutex_unlock(&callback_mutex);
		mpol_rebind_task(tsk, &tsk->mems_allowed);
	}
}

/*
 * 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
 * are only set if the other's are set.  Call holding cgroup_mutex.
 */

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
 * cgroup_mutex held.
 *
 * '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 cgroup *cont;
	struct cpuset *c, *par;

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

	/* Remaining checks don't apply to root cpuset */
	if (cur == &top_cpuset)
		return 0;

	par = cur->parent;

	/* We must be a subset of our parent cpuset */