Release 4.15 kernel/cgroup/cpuset.c

/*
 *  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/memory.h>
#include <linux/export.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/sched/mm.h>
#include <linux/sched/task.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/time64.h>
#include <linux/backing-dev.h>
#include <linux/sort.h>
#include <linux/oom.h>
#include <linux/sched/isolation.h>
#include <linux/uaccess.h>
#include <linux/atomic.h>
#include <linux/mutex.h>
#include <linux/cgroup.h>
#include <linux/wait.h>


DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key);

DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key);

/* See "Frequency meter" comments, below. */


struct fmeter {
	
int cnt;		/* unprocessed events count */
	
int val;		/* most recent output value */
	
time64_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 */

	/*
         * On default hierarchy:
         *
         * The user-configured masks can only be changed by writing to
         * cpuset.cpus and cpuset.mems, and won't be limited by the
         * parent masks.
         *
         * The effective masks is the real masks that apply to the tasks
         * in the cpuset. They may be changed if the configured masks are
         * changed or hotplug happens.
         *
         * effective_mask == configured_mask & parent's effective_mask,
         * and if it ends up empty, it will inherit the parent's mask.
         *
         *
         * On legacy hierachy:
         *
         * The user-configured masks are always the same with effective masks.
         */

	/* user-configured CPUs and Memory Nodes allow to tasks */
	
cpumask_var_t cpus_allowed;
	
nodemask_t mems_allowed;

	/* effective CPUs and Memory Nodes allow to tasks */
	
cpumask_var_t effective_cpus;
	
nodemask_t effective_mems;

	/*
         * This is old Memory Nodes tasks took on.
         *
         * - top_cpuset.old_mems_allowed is initialized to mems_allowed.
         * - A new cpuset's old_mems_allowed is initialized when some
         *   task is moved into it.
         * - old_mems_allowed is used in cpuset_migrate_mm() when we change
         *   cpuset.mems_allowed and have tasks' nodemask updated, and
         *   then old_mems_allowed is updated to mems_allowed.
         */
	
nodemask_t old_mems_allowed;

	
struct fmeter fmeter;		/* memory_pressure filter */

	/*
         * Tasks are being attached to this cpuset.  Used to prevent
         * zeroing cpus/mems_allowed between ->can_attach() and ->attach().
         */
	
int attach_in_progress;

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

	/* for custom sched domain */
	
int relax_domain_level;
};



static inline struct cpuset *css_cs(struct cgroup_subsys_state *css)
{
	return css ? container_of(css, struct cpuset, css) : NULL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Menage
21
72.41%
1
50.00%
Tejun Heo
8
27.59%
1
50.00%
Total
29
100.00%
2
100.00%

/* Retrieve the cpuset for a task */


static inline struct cpuset *task_cs(struct task_struct *task)
{
	return css_cs(task_css(task, cpuset_cgrp_id));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Menage
22
88.00%
1
25.00%
Tejun Heo
3
12.00%
3
75.00%
Total
25
100.00%
4
100.00%



static inline struct cpuset *parent_cs(struct cpuset *cs)
{
	return css_cs(cs->css.parent);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Tejun Heo
24
100.00%
3
100.00%
Total
24
100.00%
3
100.00%

#ifdef CONFIG_NUMA


static inline bool task_has_mempolicy(struct task_struct *task)
{
	return task->mempolicy;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
David Rientjes
17
100.00%
1
100.00%
Total
17
100.00%
1
100.00%

#else


static inline bool task_has_mempolicy(struct task_struct *task)
{
	return false;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
David Rientjes
15
100.00%
1
100.00%
Total
15
100.00%
1
100.00%

#endif


/* bits in struct cpuset flags field */
typedef enum {
	
CS_ONLINE,
	
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 bool is_cpuset_online(struct cpuset *cs)
{
	return test_bit(CS_ONLINE, &cs->flags) && !css_is_dying(&cs->css);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Tejun Heo
31
96.88%
2
66.67%
Srivatsa S. Bhat
1
3.12%
1
33.33%
Total
32
100.00%
3
100.00%



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

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Jackson
24
100.00%
1
100.00%
Total
24
100.00%
1
100.00%



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

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Jackson
24
100.00%
1
100.00%
Total
24
100.00%
1
100.00%



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

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Menage
24
100.00%
1
100.00%
Total
24
100.00%
1
100.00%



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

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Jackson
24
100.00%
1
100.00%
Total
24
100.00%
1
100.00%



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

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Jackson
24
100.00%
1
100.00%
Total
24
100.00%
1
100.00%



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

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Jackson
24
100.00%
1
100.00%
Total
24
100.00%
1
100.00%



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

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Jackson
24
100.00%
1
100.00%
Total
24
100.00%
1
100.00%


static struct cpuset top_cpuset = {
	.flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) |
		  (1 << CS_MEM_EXCLUSIVE)),
};

/**
 * cpuset_for_each_child - traverse online children of a cpuset
 * @child_cs: loop cursor pointing to the current child
 * @pos_css: used for iteration
 * @parent_cs: target cpuset to walk children of
 *
 * Walk @child_cs through the online children of @parent_cs.  Must be used
 * with RCU read locked.
 */

#define cpuset_for_each_child(child_cs, pos_css, parent_cs)		\
	css_for_each_child((pos_css), &(parent_cs)->css)                \
                if (is_cpuset_online(((child_cs) = css_cs((pos_css)))))

/**
 * cpuset_for_each_descendant_pre - pre-order walk of a cpuset's descendants
 * @des_cs: loop cursor pointing to the current descendant
 * @pos_css: used for iteration
 * @root_cs: target cpuset to walk ancestor of
 *
 * Walk @des_cs through the online descendants of @root_cs.  Must be used
 * with RCU read locked.  The caller may modify @pos_css by calling
 * css_rightmost_descendant() to skip subtree.  @root_cs is included in the
 * iteration and the first node to be visited.
 */

#define cpuset_for_each_descendant_pre(des_cs, pos_css, root_cs)	\
	css_for_each_descendant_pre((pos_css), &(root_cs)->css)         \
                if (is_cpuset_online(((des_cs) = css_cs((pos_css)))))

/*
 * There are two global locks guarding cpuset structures - cpuset_mutex and
 * callback_lock. 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 locks to modify cpusets.  If a task holds
 * cpuset_mutex, then it blocks others wanting that mutex, ensuring that it
 * is the only task able to also acquire callback_lock 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 cpuset_mutex.  While it is performing these checks, various
 * callback routines can briefly acquire callback_lock to query cpusets.
 * Once it is ready to make the changes, it takes callback_lock, blocking
 * everyone else.
 *
 * Calls to the kernel memory allocator can not be made while holding
 * callback_lock, as that would risk double tripping on callback_lock
 * from one of the callbacks into the cpuset code from within
 * __alloc_pages().
 *
 * If a task is only holding callback_lock, then it has read-only
 * access to cpusets.
 *
 * Now, the task_struct fields mems_allowed and mempolicy may be changed
 * by other task, we use alloc_lock in the task_struct fields to protect
 * them.
 *
 * The cpuset_common_file_read() handlers only hold callback_lock 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(cpuset_mutex);
static DEFINE_SPINLOCK(callback_lock);


static struct workqueue_struct *cpuset_migrate_mm_wq;

/*
 * CPU / memory hotplug is handled asynchronously.
 */
static void cpuset_hotplug_workfn(struct work_struct *work);
static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn);

static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq);

/*
 * Cgroup v2 behavior is used when on default hierarchy or the
 * cgroup_v2_mode flag is set.
 */


static inline bool is_in_v2_mode(void)
{
	return cgroup_subsys_on_dfl(cpuset_cgrp_subsys) ||
	      (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Waiman Long
25
100.00%
1
100.00%
Total
25
100.00%
1
100.00%

/*
 * 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 struct dentry *cpuset_mount(struct file_system_type *fs_type,
			 int flags, const char *unused_dev_name, void *data)
{
	struct file_system_type *cgroup_fs = get_fs_type("cgroup");
	struct dentry *ret = ERR_PTR(-ENODEV);
	if (cgroup_fs) {
		char mountopts[] =
			"cpuset,noprefix,"
			"release_agent=/sbin/cpuset_release_agent";
		ret = cgroup_fs->mount(cgroup_fs, flags,
					   unused_dev_name, mountopts);
		put_filesystem(cgroup_fs);
	}
	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Menage
62
75.61%
1
33.33%
Al Viro
11
13.41%
1
33.33%
Paul Jackson
9
10.98%
1
33.33%
Total
82
100.00%
3
100.00%


static struct file_system_type cpuset_fs_type = {
	.name = "cpuset",
	.mount = cpuset_mount,
};

/*
 * 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.
 *
 * One way or another, we guarantee to return some non-empty subset
 * of cpu_online_mask.
 *
 * Call with callback_lock or cpuset_mutex held.
 */


static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
{
	while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) {
		cs = parent_cs(cs);
		if (unlikely(!cs)) {
			/*
                         * The top cpuset doesn't have any online cpu as a
                         * consequence of a race between cpuset_hotplug_work
                         * and cpu hotplug notifier.  But we know the top
                         * cpuset's effective_cpus is on its way to to be
                         * identical to cpu_online_mask.
                         */
			cpumask_copy(pmask, cpu_online_mask);
			return;
		}
	}
	cpumask_and(pmask, cs->effective_cpus, cpu_online_mask);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Jackson
22
32.84%
1
14.29%
Joonwoo Park
21
31.34%
1
14.29%
Paul Menage
13
19.40%
1
14.29%
Li Zefan
8
11.94%
3
42.86%
Tejun Heo
3
4.48%
1
14.29%
Total
67
100.00%
7
100.00%

/*
 * 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.  The top cpuset always has some mems online.
 *
 * One way or another, we guarantee to return some non-empty subset
 * of node_states[N_MEMORY].
 *
 * Call with callback_lock or cpuset_mutex held.
 */


static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask)
{
	while (!nodes_intersects(cs->effective_mems, node_states[N_MEMORY]))
		cs = parent_cs(cs);
	nodes_and(*pmask, cs->effective_mems, node_states[N_MEMORY]);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Menage
24
46.15%
1
20.00%
Paul Jackson
21
40.38%
1
20.00%
Tejun Heo
3
5.77%
1
20.00%
Li Zefan
2
3.85%
1
20.00%
Lai Jiangshan
2
3.85%
1
20.00%
Total
52
100.00%
5
100.00%

/*
 * update task's spread flag if cpuset's page/slab spread flag is set
 *
 * Call with callback_lock or cpuset_mutex held.
 */


static void cpuset_update_task_spread_flag(struct cpuset *cs,
					struct task_struct *tsk)
{
	if (is_spread_page(cs))
		task_set_spread_page(tsk);
	else
		task_clear_spread_page(tsk);

	if (is_spread_slab(cs))
		task_set_spread_slab(tsk);
	else
		task_clear_spread_slab(tsk);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Miao Xie
40
76.92%
1
50.00%
Li Zefan
12
23.08%
1
50.00%
Total
52
100.00%
2
100.00%

/*
 * 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 cpuset_mutex.
 */



static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q)
{
	return	cpumask_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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Menage
57
93.44%
1
33.33%
Paul Jackson
3
4.92%
1
33.33%
Li Zefan
1
1.64%
1
33.33%
Total
61
100.00%
3
100.00%

/**
 * alloc_trial_cpuset - allocate a trial cpuset
 * @cs: the cpuset that the trial cpuset duplicates
 */


static struct cpuset *alloc_trial_cpuset(struct cpuset *cs)
{
	struct cpuset *trial;

	trial = kmemdup(cs, sizeof(*cs), GFP_KERNEL);
	if (!trial)
		return NULL;

	if (!alloc_cpumask_var(&trial->cpus_allowed, GFP_KERNEL))
		goto free_cs;
	if (!alloc_cpumask_var(&trial->effective_cpus, GFP_KERNEL))
		goto free_cpus;

	cpumask_copy(trial->cpus_allowed, cs->cpus_allowed);
	cpumask_copy(trial->effective_cpus, cs->effective_cpus);
	return trial;

free_cpus:
	free_cpumask_var(trial->cpus_allowed);
free_cs:
	kfree(trial);
	return NULL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Li Zefan
117
100.00%
3
100.00%
Total
117
100.00%
3
100.00%

/**
 * free_trial_cpuset - free the trial cpuset
 * @trial: the trial cpuset to be freed
 */


static void free_trial_cpuset(struct cpuset *trial)
{
	free_cpumask_var(trial->effective_cpus);
	free_cpumask_var(trial->cpus_allowed);
	kfree(trial);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Li Zefan
30
100.00%
3
100.00%
Total
30
100.00%
3
100.00%

/*
 * 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
 * cpuset_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(struct cpuset *cur, struct cpuset *trial)
{
	struct cgroup_subsys_state *css;
	struct cpuset *c, *par;
	int ret;

	rcu_read_lock();

	/* Each of our child cpusets must be a subset of us */
	ret = -EBUSY;
	cpuset_for_each_child(c, css, cur)
		if (!is_cpuset_subset(c, trial))
			goto out;

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

	par = parent_cs(cur);

	/* On legacy hiearchy, we must be a subset of our parent cpuset. */
	ret = -EACCES;
	if (!is_in_v2_mode() && !is_cpuset_subset(trial, par))
		goto out;

	/*
         * If either I or some sibling (!= me) is exclusive, we can't
         * overlap
         */
	ret = -EINVAL;
	cpuset_for_each_child(c, css, par) {
		if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
		    c != cur &&
		    cpumask_intersects(trial->cpus_allowed, c->cpus_allowed))
			goto out;
		if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) &&
		    c != cur &&
		    nodes_intersects(trial->mems_allowed, c->mems_allowed))
			goto out;
	}

	/*
         * Cpusets with tasks - existing or newly being attached - can't
         * be changed to have empty cpus_allowed or mems_allowed.
         */
	ret = -ENOSPC;
	if ((cgroup_is_populated(cur->css.cgroup) || cur->attach_in_progress)) {
		if (!cpumask_empty(cur->cpus_allowed) &&
		    cpumask_empty(trial->cpus_allowed))
			goto out;
		if (!nodes_empty(cur->mems_allowed) &&
		    nodes_empty(trial->mems_allowed))
			goto out;
	}

	/*
         * We can't shrink if we won't have enough room for SCHED_DEADLINE
         * tasks.
         */
	ret = -EBUSY;
	if (is_cpu_exclusive(cur) &&
	    !cpuset_cpumask_can_shrink(cur->cpus_allowed,
				       trial->cpus_allowed))
		goto out;

	ret = 0;
out:
	rcu_read_unlock();
	return ret;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Jackson
102
34.93%
3
17.65%
Tejun Heo
80
27.40%
5
29.41%
Paul Menage
46
15.75%
2
11.76%
Li Zefan
32
10.96%
4
23.53%
Juri Lelli
28
9.59%
1
5.88%
Dave Hansen
2
0.68%
1
5.88%
Waiman Long
2
0.68%
1
5.88%
Total
292
100.00%
17
100.00%

#ifdef CONFIG_SMP
/*
 * Helper routine for generate_sched_domains().
 * Do cpusets a, b have overlapping effective cpus_allowed masks?
 */


static int cpusets_overlap(struct cpuset *a, struct cpuset *b)
{
	return cpumask_intersects(a->effective_cpus, b->effective_cpus);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Jackson
25
89.29%
1
33.33%
Li Zefan
3
10.71%
2
66.67%
Total
28
100.00%
3
100.00%


static void

update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c)
{
	if (dattr->relax_domain_level < c->relax_domain_level)
		dattr->relax_domain_level = c->relax_domain_level;
	return;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Hidetoshi Seto
35
100.00%
1
100.00%
Total
35
100.00%
1
100.00%



static void update_domain_attr_tree(struct sched_domain_attr *dattr,
				    struct cpuset *root_cs)
{
	struct cpuset *cp;
	struct cgroup_subsys_state *pos_css;

	rcu_read_lock();
	cpuset_for_each_descendant_pre(cp, pos_css, root_cs) {
		/* skip the whole subtree if @cp doesn't have any CPU */
		if (cpumask_empty(cp->cpus_allowed)) {
			pos_css = css_rightmost_descendant(pos_css);
			continue;
		}

		if (is_sched_load_balance(cp))
			update_domain_attr(dattr, cp);
	}
	rcu_read_unlock();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Lai Jiangshan
51
67.11%
1
20.00%
Tejun Heo
24
31.58%
3
60.00%
Li Zefan
1
1.32%
1
20.00%
Total
76
100.00%
5
100.00%

/* Must be called with cpuset_mutex held.  */


static inline int nr_cpusets(void)
{
	/* jump label reference count + the top-level cpuset */
	return static_key_count(&cpusets_enabled_key.key) + 1;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paolo Bonzini
21
100.00%
1
100.00%
Total
21
100.00%
1
100.00%

/*
 * generate_sched_domains()
 *
 * This function builds a partial partition of the systems CPUs
 * A 'partial partition' is a set of non-overlapping subsets whose
 * union is a subset of that set.
 * The output of this function needs to be passed to kernel/sched/core.c
 * partition_sched_domains() routine, which will rebuild the scheduler's
 * load balancing domains (sched domains) as specified by that partial
 * partition.
 *
 * See "What is sched_load_balance" in Documentation/cgroups/cpusets.txt
 * for a background explanation of this.
 *
 * Does not return errors, on the theory that the callers of this
 * routine would rather not worry about failures to rebuild sched
 * domains when operating in the severe memory shortage situations
 * that could cause allocation failures below.
 *
 * Must be called with cpuset_mutex held.
 *
 * The three key local variables below are:
 *    q  - a linked-list queue of cpuset pointers, used to implement a
 *         top-down scan of all cpusets.  This scan loads a pointer
 *         to each cpuset marked is_sched_load_balance into the
 *         array 'csa'.  For our purposes, rebuilding the schedulers
 *         sched domains, we can ignore !is_sched_load_balance cpusets.
 *  csa  - (for CpuSet Array) Array of pointers to all the cpusets
 *         that need to be load balanced, for convenient iterative
 *         access by the subsequent code that finds the best partition,
 *         i.e the set of domains (subsets) of CPUs such that the
 *         cpus_allowed of every cpuset marked is_sched_load_balance
 *         is a subset of one of these domains, while there are as
 *         many such domains as possible, each as small as possible.
 * doms  - Conversion of 'csa' to an array of cpumasks, for passing to
 *         the kernel/sched/core.c routine partition_sched_domains() in a
 *         convenient format, that can be easily compared to the prior
 *         value to determine what partition elements (sched domains)
 *         were changed (added or removed.)
 *
 * Finding the best partition (set of domains):
 *      The triple nested loops below over i, j, k scan over the
 *      load balanced cpusets (using the array of cpuset pointers in
 *      csa[]) looking for pairs of cpusets that have overlapping
 *      cpus_allowed, but which don't have the same 'pn' partition
 *      number and gives them in the same partition number.  It keeps
 *      looping on the 'restart' label until it can no longer find
 *      any such pairs.
 *
 *      The union of the cpus_allowed masks from the set of
 *      all cpusets having the same 'pn' value then form the one
 *      element of the partition (one sched domain) to be passed to
 *      partition_sched_domains().
 */


static int generate_sched_domains(cpumask_var_t **domains,
			struct sched_domain_attr **attributes)
{
	struct cpuset *cp;	/* scans q */
	struct cpuset **csa;	/* array of all cpuset ptrs */
	int csn;		/* how many cpuset ptrs in csa so far */
	int i, j, k;		/* indices for partition finding loops */
	cpumask_var_t *doms;	/* resulting partition; i.e. sched domains */
	struct sched_domain_attr *dattr;  /* attributes for custom domains */
	int ndoms = 0;		/* number of sched domains in result */
	int nslot;		/* next empty doms[] struct cpumask slot */
	struct cgroup_subsys_state *pos_css;

	doms = NULL;
	dattr = NULL;
	csa = NULL;

	/* Special case for the 99% of systems with one, full, sched domain */
	if (is_sched_load_balance(&top_cpuset)) {
		ndoms = 1;
		doms = alloc_sched_domains(ndoms);
		if (!doms)
			goto done;

		dattr = kmalloc(sizeof(struct sched_domain_attr), GFP_KERNEL);
		if (dattr) {
			*dattr = SD_ATTR_INIT;
			update_domain_attr_tree(dattr, &top_cpuset);
		}
		cpumask_and(doms[0], top_cpuset.effective_cpus,
			    housekeeping_cpumask(HK_FLAG_DOMAIN));

		goto done;
	}

	csa = kmalloc(nr_cpusets() * sizeof(cp), GFP_KERNEL);
	if (!csa)
		goto done;
	csn = 0;

	rcu_read_lock();
	cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) {
		if (cp == &top_cpuset)
			continue;
		/*
                 * Continue traversing beyond @cp iff @cp has some CPUs and
                 * isn't load balancing.  The former is obvious.  The
                 * latter: All child cpusets contain a subset of the
                 * parent's cpus, so just skip them, and then we call
                 * update_domain_attr_tree() to calc relax_domain_level of
                 * the corresponding sched domain.
                 */
		if (!cpumask_empty(cp->cpus_allowed) &&
		    !(is_sched_load_balance(cp) &&
		      cpumask_intersects(cp->cpus_allowed,
					 housekeeping_cpumask(HK_FLAG_DOMAIN))))
			continue;

		if (is_sched_load_balance(cp))
			csa[csn++] = cp;

		/* skip @cp's subtree */
		pos_css = css_rightmost_descendant(pos_css);
	}
	rcu_read_unlock();

	for (i = 0; i < csn; i++)
		csa[i]->pn = i;
	ndoms = csn;

restart:
	/* Find the best partition (set of sched domains) */
	for (i = 0; i < csn; i++) {
		struct cpuset *a = csa[i];
		int apn = a->pn;

		for (j = 0; j < csn; j++) {
			struct cpuset *b = csa[j];
			int bpn = b->pn;

			if (apn != bpn && cpusets_overlap(a, b)) {
				for (k = 0; k < csn; k++) {
					struct cpuset *c = csa[k];

					if (c->pn == bpn)
						c->pn = apn;
				}
				ndoms--;	/* one less element */
				goto restart;
			}
		}
	}

	/*
         * Now we know how many domains to create.
         * Convert <csn, csa> to <ndoms, doms> and populate cpu masks.
         */
	doms = alloc_sched_domains(ndoms);
	if (!doms)
		goto done;

	/*
         * The rest of the code, including the scheduler, can deal with
         * dattr==NULL case. No need to abort if alloc fails.
         */
	dattr = kmalloc(ndoms * sizeof(struct sched_domain_attr), GFP_KERNEL);

	for (nslot = 0, i = 0; i < csn; i++) {
		struct cpuset *a = csa[i];
		struct cpumask *dp;
		int apn = a->pn;

		if (apn < 0) {
			/* Skip completed partitions */
			continue;
		}

		dp = doms[nslot];

		if (nslot == ndoms) {
			static int warnings = 10;
			if (warnings) {
				pr_warn("rebuild_sched_domains confused: nslot %d, ndoms %d, csn %d, i %d, apn %d\n",
					nslot, ndoms, csn, i, apn);
				warnings--;
			}
			continue;
		}

		cpumask_clear(dp);
		if (dattr)
			*(dattr + nslot) = SD_ATTR_INIT;
		for (j = i; j < csn; j++) {
			struct cpuset *b = csa[j];

			if (apn == b->pn) {
				cpumask_or(dp, dp, b->effective_cpus);
				cpumask_and(dp, dp, housekeeping_cpumask(HK_FLAG_DOMAIN));
				if (dattr)
					update_domain_attr_tree(dattr + nslot, b);

				/* Done with this partition */
				b->pn = -1;
			}
		}
		nslot++;
	}
	BUG_ON(nslot != ndoms);

done:
	kfree(csa);

	/*
         * Fallback to the default domain if kmalloc() failed.
         * See comments in partition_sched_domains().
         */
	if (doms == NULL)
		ndoms = 1;

	*domains    = doms;
	*attributes = dattr;
	return ndoms;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Jackson
423
61.39%
1
4.35%
Hidetoshi Seto
75
10.89%
1
4.35%
Maksim Krasnyanskiy
58
8.42%
1
4.35%
Tejun Heo
35
5.08%
4
17.39%
Li Zefan
27
3.92%
6
26.09%
Rik Van Riel
20
2.90%
1
4.35%
Rusty Russell
14
2.03%
1
4.35%
Frédéric Weisbecker
12
1.74%
1
4.35%
Lai Jiangshan
10
1.45%
2
8.70%
Miao Xie
6
0.87%
1
4.35%
Paul Menage
3
0.44%
1
4.35%
Mel Gorman
2
0.29%
1
4.35%
Ingo Molnar
2
0.29%
1
4.35%
Fabian Frederick
2
0.29%
1
4.35%
Total
689
100.00%
23
100.00%

/*
 * Rebuild scheduler domains.
 *
 * If the flag 'sched_load_balance' of any cpuset with non-empty
 * 'cpus' changes, or if the 'cpus' allowed changes in any cpuset
 * which has that flag enabled, or if any cpuset with a non-empty
 * 'cpus' is removed, then call this routine to rebuild the
 * scheduler's dynamic sched domains.
 *
 * Call with cpuset_mutex held.  Takes get_online_cpus().
 */


static void rebuild_sched_domains_locked(void)
{
	struct sched_domain_attr *attr;
	cpumask_var_t *doms;
	int ndoms;

	lockdep_assert_held(&cpuset_mutex);
	get_online_cpus();

	/*
         * We have raced with CPU hotplug. Don't do anything to avoid
         * passing doms with offlined cpu to partition_sched_domains().
         * Anyways, hotplug work item will rebuild sched domains.
         */
	if (!cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask))
		goto out;

	/* Generate domain masks and attrs */
	ndoms = generate_sched_domains(&doms, &attr);

	/* Have scheduler rebuild the domains */
	partition_sched_domains(ndoms, doms, attr);
out:
	put_online_cpus();
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Maksim Krasnyanskiy
31
43.06%
1
10.00%
Li Zefan
18
25.00%
2
20.00%
Paul Jackson
9
12.50%
1
10.00%
Tejun Heo
7
9.72%
2
20.00%
Paul Menage
3
4.17%
1
10.00%
Gautham R. Shenoy
2
2.78%
1
10.00%
Hidetoshi Seto
1
1.39%
1
10.00%
Rusty Russell
1
1.39%
1
10.00%
Total
72
100.00%
10
100.00%

#else /* !CONFIG_SMP */


static void rebuild_sched_domains_locked(void)
{
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul Menage
5
71.43%
1
50.00%
Tejun Heo
2
28.57%
1
50.00%
Total
7
100.00%
2
100.00%

#endif /* CONFIG_SMP */



void rebuild_sched_domains(void)
{
	mutex_lock(&cpuset_mutex);
	rebuild_sched_domains_locked();
	mutex_unlock(&cpuset_mutex);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Maksim Krasnyanskiy
11
50.00%
1
16.67%
Tejun Heo
8
36.36%
2
33.33%
Paul Jackson
2
9.09%
2
33.33%
Paul Menage
1
4.55%
1
16.67%
Total
22
100.00%
6
100.00%

/**
 * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset.
 * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed
 *
 * Iterate through each task of @cs updating its cpus_allowed to the
 * effective cpuset's.  As this function is called with cpuset_mutex held,
 * cpuset membership stays stable.
 */


static void update_tasks_cpumask(struct cpuset *cs)
{
	struct css_task_iter it;
	struct task_struct *task;

	css_task_iter_start(&cs->css, 0, &it);
	while ((task = css_task_iter_next(&it)))
		set_cpus_allowed_ptr(task, cs->effective_cpus);
	css_task_iter_end(&it);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Tejun Heo
44
73.33%
4
40.00%
Li Zefan
6
10.00%
3
30.00%
Miao Xie
6
10.00%
1
10.00%
Cliff Wickman
3
5.00%
1
10.00%
Adrian Bunk
1
1.67%
1
10.00%
Total
60
100.00%
10
100.00%

/*
 * update_cpumasks_hier - Update effective cpumasks and tasks in the subtree
 * @cs: the cpuset to consider
 * @new_cpus: temp variable for calculating new effective_cpus
 *
 * When congifured cpumask is changed, the effective cpumasks of this cpuset
 * and all its descendants need to be updated.
 *
 * On legacy hierachy, effective_cpus will be the same with cpu_allowed.
 *
 * Called with cpuset_mutex held
 */


static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
{
	struct cpuset *cp;
	struct cgroup_subsys_state *pos_css;
	bool need_rebuild_sched_domains = false;

	rcu_read_lock();
	cpuset_for_each_descendant_pre(cp, pos_css, cs) {
		struct cpuset *parent = parent_cs(cp);

		cpumask_and(new_cpus, cp->cpus_allowed, parent->effective_cpus);

		/*
                 * If it becomes empty, inherit the effective mask of the
                 * parent, which is guaranteed to have some CPUs.
                 */
		if (is_in_v2_mode() && cpumask_empty(new_cpus))
			cpumask_copy(new_cpus, parent->effective_cpus);

		/* Skip the whole subtree if the cpumask remains the same. */
		if (cpumask_equal(new_cpus, cp->effective_cpus)) {
			pos_css = css_rightmost_descendant(pos_css);
			continue;
		}

		if (!css_tryget_online(&cp->css))
			continue;
		rcu_read_unlock();

		spin_lock_irq(&callback_lock);
		cpumask_copy(cp->effective_cpus, new_cpus);
		spin_unlock_irq(&callback_lock);

		WARN_ON(!is_in_v2_mode() &&
			!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));

		update_tasks_cpumask(cp);

		/*
                 * If the effective cpumask of any non-empty cpuset is changed,
                 * we need to rebuild sched domains.
                 */
		if (!cpumask_empty(cp->cpus_allowed) &&
		    is_sched_load_balance(cp))
			need_rebuild_sched_domains = true;

		rcu_read_lock();
		css_put(&cp->css);
	}
	rcu_read_unlock();

	if (need_rebuild_sched_domains)
		rebuild_sched_domains_locked();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Li Zefan
180
85.71%
5
35.71%
Tejun Heo
11
5.24%
3
21.43%
Paul Jackson
7
3.33%
1
7.14%
Vladimir Davydov
4
1.90%
1
7.14%
Waiman Long
4
1.90%
1
7.14%
Paul Menage
3
1.43%
2
14.29%
Cliff Wickman
1
0.48%
1
7.14%
Total
210
100.00%
14
100.00%

/**
 * update_cpumask - update the cpus_allowed mask of a cpuset and all tasks in it
 * @cs: the cpuset to consider
 * @trialcs: trial cpuset
 * @buf: buffer of cpu numbers written to this cpuset
 */


static int update_cpumask(struct cpuset *cs,