blob: e276db72284511f64ceb39917806f0cb7056e7f0 [file] [log] [blame]
/*
* 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/kthread.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/fs_context.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/deadline.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);
/*
* There could be abnormal cpuset configurations for cpu or memory
* node binding, add this key to provide a quick low-cost judgment
* of the situation.
*/
DEFINE_STATIC_KEY_FALSE(cpusets_insane_config_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 */
};
/*
* Invalid partition error code
*/
enum prs_errcode {
PERR_NONE = 0,
PERR_INVCPUS,
PERR_INVPARENT,
PERR_NOTPART,
PERR_NOTEXCL,
PERR_NOCPUS,
PERR_HOTPLUG,
PERR_CPUSEMPTY,
};
static const char * const perr_strings[] = {
[PERR_INVCPUS] = "Invalid cpu list in cpuset.cpus",
[PERR_INVPARENT] = "Parent is an invalid partition root",
[PERR_NOTPART] = "Parent is not a partition root",
[PERR_NOTEXCL] = "Cpu list in cpuset.cpus not exclusive",
[PERR_NOCPUS] = "Parent unable to distribute cpu downstream",
[PERR_HOTPLUG] = "No cpu available due to hotplug",
[PERR_CPUSEMPTY] = "cpuset.cpus is empty",
};
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 hierarchy:
*
* 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;
/*
* CPUs allocated to child sub-partitions (default hierarchy only)
* - CPUs granted by the parent = effective_cpus U subparts_cpus
* - effective_cpus and subparts_cpus are mutually exclusive.
*
* effective_cpus contains only onlined CPUs, but subparts_cpus
* may have offlined ones.
*/
cpumask_var_t subparts_cpus;
/*
* 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;
/* number of CPUs in subparts_cpus */
int nr_subparts_cpus;
/* partition root state */
int partition_root_state;
/*
* Default hierarchy only:
* use_parent_ecpus - set if using parent's effective_cpus
* child_ecpus_count - # of children with use_parent_ecpus set
*/
int use_parent_ecpus;
int child_ecpus_count;
/* Invalid partition error code, not lock protected */
enum prs_errcode prs_err;
/* Handle for cpuset.cpus.partition */
struct cgroup_file partition_file;
};
/*
* Partition root states:
*
* 0 - member (not a partition root)
* 1 - partition root
* 2 - partition root without load balancing (isolated)
* -1 - invalid partition root
* -2 - invalid isolated partition root
*/
#define PRS_MEMBER 0
#define PRS_ROOT 1
#define PRS_ISOLATED 2
#define PRS_INVALID_ROOT -1
#define PRS_INVALID_ISOLATED -2
static inline bool is_prs_invalid(int prs_state)
{
return prs_state < 0;
}
/*
* Temporary cpumasks for working with partitions that are passed among
* functions to avoid memory allocation in inner functions.
*/
struct tmpmasks {
cpumask_var_t addmask, delmask; /* For partition root */
cpumask_var_t new_cpus; /* For update_cpumasks_hier() */
};
static inline struct cpuset *css_cs(struct cgroup_subsys_state *css)
{
return css ? container_of(css, struct cpuset, css) : NULL;
}
/* 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));
}
static inline struct cpuset *parent_cs(struct cpuset *cs)
{
return css_cs(cs->css.parent);
}
/* 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);
}
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);
}
static inline int is_partition_valid(const struct cpuset *cs)
{
return cs->partition_root_state > 0;
}
static inline int is_partition_invalid(const struct cpuset *cs)
{
return cs->partition_root_state < 0;
}
/*
* Callers should hold callback_lock to modify partition_root_state.
*/
static inline void make_partition_invalid(struct cpuset *cs)
{
if (is_partition_valid(cs))
cs->partition_root_state = -cs->partition_root_state;
}
/*
* Send notification event of whenever partition_root_state changes.
*/
static inline void notify_partition_change(struct cpuset *cs, int old_prs)
{
if (old_prs == cs->partition_root_state)
return;
cgroup_file_notify(&cs->partition_file);
/* Reset prs_err if not invalid */
if (is_partition_valid(cs))
WRITE_ONCE(cs->prs_err, PERR_NONE);
}
static struct cpuset top_cpuset = {
.flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) |
(1 << CS_MEM_EXCLUSIVE)),
.partition_root_state = PRS_ROOT,
};
/**
* 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_rwsem 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. The cpuset code uses only cpuset_rwsem write lock. Other
* kernel subsystems can use cpuset_read_lock()/cpuset_read_unlock() to
* prevent change to cpuset structures.
*
* A task must hold both locks to modify cpusets. If a task holds
* cpuset_rwsem, it blocks others wanting that rwsem, 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_rwsem. 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
*/
DEFINE_STATIC_PERCPU_RWSEM(cpuset_rwsem);
void cpuset_read_lock(void)
{
percpu_down_read(&cpuset_rwsem);
}
void cpuset_read_unlock(void)
{
percpu_up_read(&cpuset_rwsem);
}
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);
static inline void check_insane_mems_config(nodemask_t *nodes)
{
if (!cpusets_insane_config() &&
movable_only_nodes(nodes)) {
static_branch_enable(&cpusets_insane_config_key);
pr_info("Unsupported (movable nodes only) cpuset configuration detected (nmask=%*pbl)!\n"
"Cpuset allocations might fail even with a lot of memory available.\n",
nodemask_pr_args(nodes));
}
}
/*
* Cgroup v2 behavior is used on the "cpus" and "mems" control files when
* on default hierarchy or when the cpuset_v2_mode flag is set by mounting
* the v1 cpuset cgroup filesystem with the "cpuset_v2_mode" mount option.
* With v2 behavior, "cpus" and "mems" are always what the users have
* requested and won't be changed by hotplug events. Only the effective
* cpus or mems will be affected.
*/
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);
}
/**
* partition_is_populated - check if partition has tasks
* @cs: partition root to be checked
* @excluded_child: a child cpuset to be excluded in task checking
* Return: true if there are tasks, false otherwise
*
* It is assumed that @cs is a valid partition root. @excluded_child should
* be non-NULL when this cpuset is going to become a partition itself.
*/
static inline bool partition_is_populated(struct cpuset *cs,
struct cpuset *excluded_child)
{
struct cgroup_subsys_state *css;
struct cpuset *child;
if (cs->css.cgroup->nr_populated_csets)
return true;
if (!excluded_child && !cs->nr_subparts_cpus)
return cgroup_is_populated(cs->css.cgroup);
rcu_read_lock();
cpuset_for_each_child(child, css, cs) {
if (child == excluded_child)
continue;
if (is_partition_valid(child))
continue;
if (cgroup_is_populated(child->css.cgroup)) {
rcu_read_unlock();
return true;
}
}
rcu_read_unlock();
return false;
}
/*
* Return in pmask the portion of a task's cpusets's cpus_allowed that
* are online and are capable of running the task. If none are found,
* walk up the cpuset hierarchy until we find one that does have some
* appropriate cpus.
*
* One way or another, we guarantee to return some non-empty subset
* of cpu_online_mask.
*
* Call with callback_lock or cpuset_rwsem held.
*/
static void guarantee_online_cpus(struct task_struct *tsk,
struct cpumask *pmask)
{
const struct cpumask *possible_mask = task_cpu_possible_mask(tsk);
struct cpuset *cs;
if (WARN_ON(!cpumask_and(pmask, possible_mask, cpu_online_mask)))
cpumask_copy(pmask, cpu_online_mask);
rcu_read_lock();
cs = task_cs(tsk);
while (!cpumask_intersects(cs->effective_cpus, pmask)) {
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 be
* identical to cpu_online_mask.
*/
goto out_unlock;
}
}
cpumask_and(pmask, pmask, cs->effective_cpus);
out_unlock:
rcu_read_unlock();
}
/*
* 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_rwsem 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]);
}
/*
* update task's spread flag if cpuset's page/slab spread flag is set
*
* Call with callback_lock or cpuset_rwsem held. The check can be skipped
* if on default hierarchy.
*/
static void cpuset_update_task_spread_flags(struct cpuset *cs,
struct task_struct *tsk)
{
if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys))
return;
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);
}
/*
* 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_rwsem.
*/
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);
}
/**
* alloc_cpumasks - allocate three cpumasks for cpuset
* @cs: the cpuset that have cpumasks to be allocated.
* @tmp: the tmpmasks structure pointer
* Return: 0 if successful, -ENOMEM otherwise.
*
* Only one of the two input arguments should be non-NULL.
*/
static inline int alloc_cpumasks(struct cpuset *cs, struct tmpmasks *tmp)
{
cpumask_var_t *pmask1, *pmask2, *pmask3;
if (cs) {
pmask1 = &cs->cpus_allowed;
pmask2 = &cs->effective_cpus;
pmask3 = &cs->subparts_cpus;
} else {
pmask1 = &tmp->new_cpus;
pmask2 = &tmp->addmask;
pmask3 = &tmp->delmask;
}
if (!zalloc_cpumask_var(pmask1, GFP_KERNEL))
return -ENOMEM;
if (!zalloc_cpumask_var(pmask2, GFP_KERNEL))
goto free_one;
if (!zalloc_cpumask_var(pmask3, GFP_KERNEL))
goto free_two;
return 0;
free_two:
free_cpumask_var(*pmask2);
free_one:
free_cpumask_var(*pmask1);
return -ENOMEM;
}
/**
* free_cpumasks - free cpumasks in a tmpmasks structure
* @cs: the cpuset that have cpumasks to be free.
* @tmp: the tmpmasks structure pointer
*/
static inline void free_cpumasks(struct cpuset *cs, struct tmpmasks *tmp)
{
if (cs) {
free_cpumask_var(cs->cpus_allowed);
free_cpumask_var(cs->effective_cpus);
free_cpumask_var(cs->subparts_cpus);
}
if (tmp) {
free_cpumask_var(tmp->new_cpus);
free_cpumask_var(tmp->addmask);
free_cpumask_var(tmp->delmask);
}
}
/**
* 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_cpumasks(trial, NULL)) {
kfree(trial);
return NULL;
}
cpumask_copy(trial->cpus_allowed, cs->cpus_allowed);
cpumask_copy(trial->effective_cpus, cs->effective_cpus);
return trial;
}
/**
* free_cpuset - free the cpuset
* @cs: the cpuset to be freed
*/
static inline void free_cpuset(struct cpuset *cs)
{
free_cpumasks(cs, NULL);
kfree(cs);
}
/*
* validate_change_legacy() - Validate conditions specific to legacy (v1)
* behavior.
*/
static int validate_change_legacy(struct cpuset *cur, struct cpuset *trial)
{
struct cgroup_subsys_state *css;
struct cpuset *c, *par;
int ret;
WARN_ON_ONCE(!rcu_read_lock_held());
/* 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;
/* On legacy hierarchy, we must be a subset of our parent cpuset. */
ret = -EACCES;
par = parent_cs(cur);
if (par && !is_cpuset_subset(trial, par))
goto out;
ret = 0;
out:
return ret;
}
/*
* 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_rwsem 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 = 0;
rcu_read_lock();
if (!is_in_v2_mode())
ret = validate_change_legacy(cur, trial);
if (ret)
goto out;
/* Remaining checks don't apply to root cpuset */
if (cur == &top_cpuset)
goto out;
par = parent_cs(cur);
/*
* 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;
/*
* 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;
}
ret = 0;
out:
rcu_read_unlock();
return ret;
}
#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);
}
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;
}
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();
}
/* Must be called with cpuset_rwsem held. */
static inline int nr_cpusets(void)
{
/* jump label reference count + the top-level cpuset */
return static_key_count(&cpusets_enabled_key.key) + 1;
}
/*
* 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/admin-guide/cgroup-v1/cpusets.rst
* 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_rwsem held.
*
* The three key local variables below are:
* cp - cpuset pointer, used (together with pos_css) to perform a
* top-down scan of all cpusets. 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; /* top-down scan of cpusets */
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;
bool root_load_balance = is_sched_load_balance(&top_cpuset);
doms = NULL;
dattr = NULL;
csa = NULL;
/* Special case for the 99% of systems with one, full, sched domain */
if (root_load_balance && !top_cpuset.nr_subparts_cpus) {
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_TYPE_DOMAIN));
goto done;
}
csa = kmalloc_array(nr_cpusets(), sizeof(cp), GFP_KERNEL);
if (!csa)
goto done;
csn = 0;
rcu_read_lock();
if (root_load_balance)
csa[csn++] = &top_cpuset;
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 root is load-balancing, we can skip @cp if it
* is a subset of the root's effective_cpus.
*/
if (!cpumask_empty(cp->cpus_allowed) &&
!(is_sched_load_balance(cp) &&
cpumask_intersects(cp->cpus_allowed,
housekeeping_cpumask(HK_TYPE_DOMAIN))))
continue;
if (root_load_balance &&
cpumask_subset(cp->cpus_allowed, top_cpuset.effective_cpus))
continue;
if (is_sched_load_balance(cp) &&
!cpumask_empty(cp->effective_cpus))
csa[csn++] = cp;
/* skip @cp's subtree if not a partition root */
if (!is_partition_valid(cp))
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_array(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_TYPE_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;
}
static void update_tasks_root_domain(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)))
dl_add_task_root_domain(task);
css_task_iter_end(&it);
}
static void rebuild_root_domains(void)
{
struct cpuset *cs = NULL;
struct cgroup_subsys_state *pos_css;
percpu_rwsem_assert_held(&cpuset_rwsem);
lockdep_assert_cpus_held();
lockdep_assert_held(&sched_domains_mutex);
rcu_read_lock();
/*
* Clear default root domain DL accounting, it will be computed again
* if a task belongs to it.
*/
dl_clear_root_domain(&def_root_domain);
cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
if (cpumask_empty(cs->effective_cpus)) {
pos_css = css_rightmost_descendant(pos_css);
continue;
}
css_get(&cs->css);
rcu_read_unlock();
update_tasks_root_domain(cs);
rcu_read_lock();
css_put(&cs->css);
}
rcu_read_unlock();
}
static void
partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
struct sched_domain_attr *dattr_new)
{
mutex_lock(&sched_domains_mutex);
partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
rebuild_root_domains();
mutex_unlock(&sched_domains_mutex);
}
/*
* 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_rwsem held. Takes cpus_read_lock().
*/
static void rebuild_sched_domains_locked(void)
{
struct cgroup_subsys_state *pos_css;
struct sched_domain_attr *attr;
cpumask_var_t *doms;
struct cpuset *cs;
int ndoms;
lockdep_assert_cpus_held();
percpu_rwsem_assert_held(&cpuset_rwsem);
/*
* If we have raced with CPU hotplug, return early to avoid
* passing doms with offlined cpu to partition_sched_domains().
* Anyways, cpuset_hotplug_workfn() will rebuild sched domains.
*
* With no CPUs in any subpartitions, top_cpuset's effective CPUs
* should be the same as the active CPUs, so checking only top_cpuset
* is enough to detect racing CPU offlines.
*/
if (!top_cpuset.nr_subparts_cpus &&
!cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask))
return;
/*
* With subpartition CPUs, however, the effective CPUs of a partition
* root should be only a subset of the active CPUs. Since a CPU in any
* partition root could be offlined, all must be checked.
*/
if (top_cpuset.nr_subparts_cpus) {
rcu_read_lock();
cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
if (!is_partition_valid(cs)) {
pos_css = css_rightmost_descendant(pos_css);
continue;
}
if (!cpumask_subset(cs->effective_cpus,
cpu_active_mask)) {
rcu_read_unlock();
return;
}
}
rcu_read_unlock();
}
/* Generate domain masks and attrs */
ndoms = generate_sched_domains(&doms, &attr);
/* Have scheduler rebuild the domains */
partition_and_rebuild_sched_domains(ndoms, doms, attr);
}
#else /* !CONFIG_SMP */
static void rebuild_sched_domains_locked(void)
{
}
#endif /* CONFIG_SMP */
void rebuild_sched_domains(void)
{
cpus_read_lock();
percpu_down_write(&cpuset_rwsem);
rebuild_sched_domains_locked();
percpu_up_write(&cpuset_rwsem);
cpus_read_unlock();
}
/**
* 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
* @new_cpus: the temp variable for the new effective_cpus mask
*
* Iterate through each task of @cs updating its cpus_allowed to the
* effective cpuset's. As this function is called with cpuset_rwsem held,
* cpuset membership stays stable.
*/
static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
{
struct css_task_iter it;
struct task_struct *task;
bool top_cs = cs == &top_cpuset;
css_task_iter_start(&cs->css, 0, &it);
while ((task = css_task_iter_next(&it))) {
/*
* Percpu kthreads in top_cpuset are ignored
*/
if (top_cs && (task->flags & PF_KTHREAD) &&
kthread_is_per_cpu(task))
continue;
cpumask_and(new_cpus, cs->effective_cpus,
task_cpu_possible_mask(task));
set_cpus_allowed_ptr(task, new_cpus);
}
css_task_iter_end(&it);
}
/**
* compute_effective_cpumask - Compute the effective cpumask of the cpuset
* @new_cpus: the temp variable for the new effective_cpus mask
* @cs: the cpuset the need to recompute the new effective_cpus mask
* @parent: the parent cpuset
*
* If the parent has subpartition CPUs, include them in the list of
* allowable CPUs in computing the new effective_cpus mask. Since offlined
* CPUs are not removed from subparts_cpus, we have to use cpu_active_mask
* to mask those out.
*/
static void compute_effective_cpumask(struct cpumask *new_cpus,
struct cpuset *cs, struct cpuset *parent)
{
if (parent->nr_subparts_cpus) {
cpumask_or(new_cpus, parent->effective_cpus,
parent->subparts_cpus);
cpumask_and(new_cpus, new_cpus, cs->cpus_allowed);
cpumask_and(new_cpus, new_cpus, cpu_active_mask);
} else {
cpumask_and(new_cpus, cs->cpus_allowed, parent->effective_cpus);
}
}
/*
* Commands for update_parent_subparts_cpumask
*/
enum subparts_cmd {
partcmd_enable, /* Enable partition root */
partcmd_disable, /* Disable partition root */
partcmd_update, /* Update parent's subparts_cpus */
partcmd_invalidate, /* Make partition invalid */
};
static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
int turning_on);
/**
* update_parent_subparts_cpumask - update subparts_cpus mask of parent cpuset
* @cpuset: The cpuset that requests change in partition root state
* @cmd: Partition root state change command
* @newmask: Optional new cpumask for partcmd_update
* @tmp: Temporary addmask and delmask
* Return: 0 or a partition root state error code
*
* For partcmd_enable, the cpuset is being transformed from a non-partition
* root to a partition root. The cpus_allowed mask of the given cpuset will
* be put into parent's subparts_cpus and taken away from parent's
* effective_cpus. The function will return 0 if all the CPUs listed in
* cpus_allowed can be granted or an error code will be returned.
*
* For partcmd_disable, the cpuset is being transformed from a partition
* root back to a non-partition root. Any CPUs in cpus_allowed that are in
* parent's subparts_cpus will be taken away from that cpumask and put back
* into parent's effective_cpus. 0 will always be returned.
*
* For partcmd_update, if the optional newmask is specified, the cpu list is
* to be changed from cpus_allowed to newmask. Otherwise, cpus_allowed is
* assumed to remain the same. The cpuset should either be a valid or invalid
* partition root. The partition root state may change from valid to invalid
* or vice versa. An error code will only be returned if transitioning from
* invalid to valid violates the exclusivity rule.
*
* For partcmd_invalidate, the current partition will be made invalid.
*
* The partcmd_enable and partcmd_disable commands are used by
* update_prstate(). An error code may be returned and the caller will check
* for error.
*
* The partcmd_update command is used by update_cpumasks_hier() with newmask
* NULL and update_cpumask() with newmask set. The partcmd_invalidate is used
* by update_cpumask() with NULL newmask. In both cases, the callers won't
* check for error and so partition_root_state and prs_error will be updated
* directly.
*/
static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
struct cpumask *newmask,
struct tmpmasks *tmp)
{
struct cpuset *parent = parent_cs(cs);
int adding; /* Moving cpus from effective_cpus to subparts_cpus */
int deleting; /* Moving cpus from subparts_cpus to effective_cpus */
int old_prs, new_prs;
int part_error = PERR_NONE; /* Partition error? */
percpu_rwsem_assert_held(&cpuset_rwsem);
/*
* The parent must be a partition root.
* The new cpumask, if present, or the current cpus_allowed must
* not be empty.
*/
if (!is_partition_valid(parent)) {
return is_partition_invalid(parent)
? PERR_INVPARENT : PERR_NOTPART;
}
if ((newmask && cpumask_empty(newmask)) ||
(!newmask && cpumask_empty(cs->cpus_allowed)))
return PERR_CPUSEMPTY;
/*
* new_prs will only be changed for the partcmd_update and
* partcmd_invalidate commands.
*/
adding = deleting = false;
old_prs = new_prs = cs->partition_root_state;
if (cmd == partcmd_enable) {
/*
* Enabling partition root is not allowed if cpus_allowed
* doesn't overlap parent's cpus_allowed.
*/
if (!cpumask_intersects(cs->cpus_allowed, parent->cpus_allowed))
return PERR_INVCPUS;
/*
* A parent can be left with no CPU as long as there is no
* task directly associated with the parent partition.
*/
if (cpumask_subset(parent->effective_cpus, cs->cpus_allowed) &&
partition_is_populated(parent, cs))
return PERR_NOCPUS;
cpumask_copy(tmp->addmask, cs->cpus_allowed);
adding = true;
} else if (cmd == partcmd_disable) {
/*
* Need to remove cpus from parent's subparts_cpus for valid
* partition root.
*/
deleting = !is_prs_invalid(old_prs) &&
cpumask_and(tmp->delmask, cs->cpus_allowed,
parent->subparts_cpus);
} else if (cmd == partcmd_invalidate) {
if (is_prs_invalid(old_prs))
return 0;
/*
* Make the current partition invalid. It is assumed that
* invalidation is caused by violating cpu exclusivity rule.
*/
deleting = cpumask_and(tmp->delmask, cs->cpus_allowed,
parent->subparts_cpus);
if (old_prs > 0) {
new_prs = -old_prs;
part_error = PERR_NOTEXCL;
}
} else if (newmask) {
/*
* partcmd_update with newmask:
*
* Compute add/delete mask to/from subparts_cpus
*
* delmask = cpus_allowed & ~newmask & parent->subparts_cpus
* addmask = newmask & parent->cpus_allowed
* & ~parent->subparts_cpus
*/
cpumask_andnot(tmp->delmask, cs->cpus_allowed, newmask);
deleting = cpumask_and(tmp->delmask, tmp->delmask,
parent->subparts_cpus);
cpumask_and(tmp->addmask, newmask, parent->cpus_allowed);
adding = cpumask_andnot(tmp->addmask, tmp->addmask,
parent->subparts_cpus);
/*
* Make partition invalid if parent's effective_cpus could
* become empty and there are tasks in the parent.
*/
if (adding &&
cpumask_subset(parent->effective_cpus, tmp->addmask) &&
!cpumask_intersects(tmp->delmask, cpu_active_mask) &&
partition_is_populated(parent, cs)) {
part_error = PERR_NOCPUS;
adding = false;
deleting = cpumask_and(tmp->delmask, cs->cpus_allowed,
parent->subparts_cpus);
}
} else {
/*
* partcmd_update w/o newmask:
*
* delmask = cpus_allowed & parent->subparts_cpus
* addmask = cpus_allowed & parent->cpus_allowed
* & ~parent->subparts_cpus
*
* This gets invoked either due to a hotplug event or from
* update_cpumasks_hier(). This can cause the state of a
* partition root to transition from valid to invalid or vice
* versa. So we still need to compute the addmask and delmask.
* A partition error happens when:
* 1) Cpuset is valid partition, but parent does not distribute
* out any CPUs.
* 2) Parent has tasks and all its effective CPUs will have
* to be distributed out.
*/
cpumask_and(tmp->addmask, cs->cpus_allowed,
parent->cpus_allowed);
adding = cpumask_andnot(tmp->addmask, tmp->addmask,
parent->subparts_cpus);
if ((is_partition_valid(cs) && !parent->nr_subparts_cpus) ||
(adding &&
cpumask_subset(parent->effective_cpus, tmp->addmask) &&
partition_is_populated(parent, cs))) {
part_error = PERR_NOCPUS;
adding = false;
}
if (part_error && is_partition_valid(cs) &&
parent->nr_subparts_cpus)
deleting = cpumask_and(tmp->delmask, cs->cpus_allowed,
parent->subparts_cpus);
}
if (part_error)
WRITE_ONCE(cs->prs_err, part_error);
if (cmd == partcmd_update) {
/*
* Check for possible transition between valid and invalid
* partition root.
*/
switch (cs->partition_root_state) {
case PRS_ROOT:
case PRS_ISOLATED:
if (part_error)
new_prs = -old_prs;
break;
case PRS_INVALID_ROOT:
case PRS_INVALID_ISOLATED:
if (!part_error)
new_prs = -old_prs;
break;
}
}
if (!adding && !deleting && (new_prs == old_prs))
return 0;
/*
* Transitioning between invalid to valid or vice versa may require
* changing CS_CPU_EXCLUSIVE and CS_SCHED_LOAD_BALANCE.
*/
if (old_prs != new_prs) {
if (is_prs_invalid(old_prs) && !is_cpu_exclusive(cs) &&
(update_flag(CS_CPU_EXCLUSIVE, cs, 1) < 0))
return PERR_NOTEXCL;
if (is_prs_invalid(new_prs) && is_cpu_exclusive(cs))
update_flag(CS_CPU_EXCLUSIVE, cs, 0);
}
/*
* Change the parent's subparts_cpus.
* Newly added CPUs will be removed from effective_cpus and
* newly deleted ones will be added back to effective_cpus.
*/
spin_lock_irq(&callback_lock);
if (adding) {
cpumask_or(parent->subparts_cpus,
parent->subparts_cpus, tmp->addmask);
cpumask_andnot(parent->effective_cpus,
parent->effective_cpus, tmp->addmask);
}
if (deleting) {
cpumask_andnot(parent->subparts_cpus,
parent->subparts_cpus, tmp->delmask);
/*
* Some of the CPUs in subparts_cpus might have been offlined.
*/
cpumask_and(tmp->delmask, tmp->delmask, cpu_active_mask);
cpumask_or(parent->effective_cpus,
parent->effective_cpus, tmp->delmask);
}
parent->nr_subparts_cpus = cpumask_weight(parent->subparts_cpus);
if (old_prs != new_prs)
cs->partition_root_state = new_prs;
spin_unlock_irq(&callback_lock);
if (adding || deleting)
update_tasks_cpumask(parent, tmp->addmask);
/*
* Set or clear CS_SCHED_LOAD_BALANCE when partcmd_update, if necessary.
* rebuild_sched_domains_locked() may be called.
*/
if (old_prs != new_prs) {
if (old_prs == PRS_ISOLATED)
update_flag(CS_SCHED_LOAD_BALANCE, cs, 1);
else if (new_prs == PRS_ISOLATED)
update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);
}
notify_partition_change(cs, old_prs);
return 0;
}
/*
* update_cpumasks_hier - Update effective cpumasks and tasks in the subtree
* @cs: the cpuset to consider
* @tmp: temp variables for calculating effective_cpus & partition setup
* @force: don't skip any descendant cpusets if set
*
* When configured cpumask is changed, the effective cpumasks of this cpuset
* and all its descendants need to be updated.
*
* On legacy hierarchy, effective_cpus will be the same with cpu_allowed.
*
* Called with cpuset_rwsem held
*/
static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
bool force)
{
struct cpuset *cp;
struct cgroup_subsys_state *pos_css;
bool need_rebuild_sched_domains = false;
int old_prs, new_prs;
rcu_read_lock();
cpuset_for_each_descendant_pre(cp, pos_css, cs) {
struct cpuset *parent = parent_cs(cp);
bool update_parent = false;
compute_effective_cpumask(tmp->new_cpus, cp, parent);
/*
* If it becomes empty, inherit the effective mask of the
* parent, which is guaranteed to have some CPUs unless
* it is a partition root that has explicitly distributed
* out all its CPUs.
*/
if (is_in_v2_mode() && cpumask_empty(tmp->new_cpus)) {
if (is_partition_valid(cp) &&
cpumask_equal(cp->cpus_allowed, cp->subparts_cpus))
goto update_parent_subparts;
cpumask_copy(tmp->new_cpus, parent->effective_cpus);
if (!cp->use_parent_ecpus) {
cp->use_parent_ecpus = true;
parent->child_ecpus_count++;
}
} else if (cp->use_parent_ecpus) {
cp->use_parent_ecpus = false;
WARN_ON_ONCE(!parent->child_ecpus_count);
parent->child_ecpus_count--;
}
/*
* Skip the whole subtree if the cpumask remains the same
* and has no partition root state and force flag not set.
*/
if (!cp->partition_root_state && !force &&
cpumask_equal(tmp->new_cpus, cp->effective_cpus)) {
pos_css = css_rightmost_descendant(pos_css);
continue;
}
update_parent_subparts:
/*
* update_parent_subparts_cpumask() should have been called
* for cs already in update_cpumask(). We should also call
* update_tasks_cpumask() again for tasks in the parent
* cpuset if the parent's subparts_cpus changes.
*/
old_prs = new_prs = cp->partition_root_state;
if ((cp != cs) && old_prs) {
switch (parent->partition_root_state) {
case PRS_ROOT:
case PRS_ISOLATED:
update_parent = true;
break;
default:
/*
* When parent is not a partition root or is
* invalid, child partition roots become
* invalid too.
*/
if (is_partition_valid(cp))
new_prs = -cp->partition_root_state;
WRITE_ONCE(cp->prs_err,
is_partition_invalid(parent)
? PERR_INVPARENT : PERR_NOTPART);
break;
}
}
if (!css_tryget_online(&cp->css))
continue;
rcu_read_unlock();
if (update_parent) {
update_parent_subparts_cpumask(cp, partcmd_update, NULL,
tmp);
/*
* The cpuset partition_root_state may become
* invalid. Capture it.
*/
new_prs = cp->partition_root_state;
}
spin_lock_irq(&callback_lock);
if (cp->nr_subparts_cpus && !is_partition_valid(cp)) {
/*
* Put all active subparts_cpus back to effective_cpus.
*/
cpumask_or(tmp->new_cpus, tmp->new_cpus,
cp->subparts_cpus);
cpumask_and(tmp->new_cpus, tmp->new_cpus,
cpu_active_mask);
cp->nr_subparts_cpus = 0;
cpumask_clear(cp->subparts_cpus);
}
cpumask_copy(cp->effective_cpus, tmp->new_cpus);
if (cp->nr_subparts_cpus) {
/*
* Make sure that effective_cpus & subparts_cpus
* are mutually exclusive.
*/
cpumask_andnot(cp->effective_cpus, cp->effective_cpus,
cp->subparts_cpus);
}
cp->partition_root_state = new_prs;
spin_unlock_irq(&callback_lock);
notify_partition_change(cp, old_prs);
WARN_ON(!is_in_v2_mode() &&
!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
update_tasks_cpumask(cp, tmp->new_cpus);
/*
* On legacy hierarchy, if the effective cpumask of any non-
* empty cpuset is changed, we need to rebuild sched domains.
* On default hierarchy, the cpuset needs to be a partition
* root as well.
*/
if (!cpumask_empty(cp->cpus_allowed) &&
is_sched_load_balance(cp) &&
(!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) ||
is_partition_valid(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();
}
/**
* update_sibling_cpumasks - Update siblings cpumasks
* @parent: Parent cpuset
* @cs: Current cpuset
* @tmp: Temp variables
*/
static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs,
struct tmpmasks *tmp)
{
struct cpuset *sibling;
struct cgroup_subsys_state *pos_css;
percpu_rwsem_assert_held(&cpuset_rwsem);
/*
* Check all its siblings and call update_cpumasks_hier()
* if their use_parent_ecpus flag is set in order for them
* to use the right effective_cpus value.
*
* The update_cpumasks_hier() function may sleep. So we have to
* release the RCU read lock before calling it.
*/
rcu_read_lock();
cpuset_for_each_child(sibling, pos_css, parent) {
if (sibling == cs)
continue;
if (!sibling->use_parent_ecpus)
continue;
if (!css_tryget_online(&sibling->css))
continue;
rcu_read_unlock();
update_cpumasks_hier(sibling, tmp, false);
rcu_read_lock();
css_put(&sibling->css);
}
rcu_read_unlock();
}
/**
* 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, struct cpuset *trialcs,
const char *buf)
{
int retval;
struct tmpmasks tmp;
bool invalidate = false;
/* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */
if (cs == &top_cpuset)
return -EACCES;
/*
* An empty cpus_allowed is ok only if the cpuset has no tasks.
* Since cpulist_parse() fails on an empty mask, we special case
* that parsing. The validate_change() call ensures that cpusets
* with tasks have cpus.
*/
if (!*buf) {
cpumask_clear(trialcs->cpus_allowed);
} else {
retval = cpulist_parse(buf, trialcs->cpus_allowed);
if (retval < 0)
return retval;
if (!cpumask_subset(trialcs->cpus_allowed,
top_cpuset.cpus_allowed))
return -EINVAL;
}
/* Nothing to do if the cpus didn't change */
if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed))
return 0;
#ifdef CONFIG_CPUMASK_OFFSTACK
/*
* Use the cpumasks in trialcs for tmpmasks when they are pointers
* to allocated cpumasks.
*
* Note that update_parent_subparts_cpumask() uses only addmask &
* delmask, but not new_cpus.
*/
tmp.addmask = trialcs->subparts_cpus;
tmp.delmask = trialcs->effective_cpus;
tmp.new_cpus = NULL;
#endif
retval = validate_change(cs, trialcs);
if ((retval == -EINVAL) && cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) {
struct cpuset *cp, *parent;
struct cgroup_subsys_state *css;
/*
* The -EINVAL error code indicates that partition sibling
* CPU exclusivity rule has been violated. We still allow
* the cpumask change to proceed while invalidating the
* partition. However, any conflicting sibling partitions
* have to be marked as invalid too.
*/
invalidate = true;
rcu_read_lock();
parent = parent_cs(cs);
cpuset_for_each_child(cp, css, parent)
if (is_partition_valid(cp) &&
cpumask_intersects(trialcs->cpus_allowed, cp->cpus_allowed)) {
rcu_read_unlock();
update_parent_subparts_cpumask(cp, partcmd_invalidate, NULL, &tmp);
rcu_read_lock();
}
rcu_read_unlock();
retval = 0;
}
if (retval < 0)
return retval;
if (cs->partition_root_state) {
if (invalidate)
update_parent_subparts_cpumask(cs, partcmd_invalidate,
NULL, &tmp);
else
update_parent_subparts_cpumask(cs, partcmd_update,
trialcs->cpus_allowed, &tmp);
}
compute_effective_cpumask(trialcs->effective_cpus, trialcs,
parent_cs(cs));
spin_lock_irq(&callback_lock);
cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
/*
* Make sure that subparts_cpus, if not empty, is a subset of
* cpus_allowed. Clear subparts_cpus if partition not valid or
* empty effective cpus with tasks.
*/
if (cs->nr_subparts_cpus) {
if (!is_partition_valid(cs) ||
(cpumask_subset(trialcs->effective_cpus, cs->subparts_cpus) &&
partition_is_populated(cs, NULL))) {
cs->nr_subparts_cpus = 0;
cpumask_clear(cs->subparts_cpus);
} else {
cpumask_and(cs->subparts_cpus, cs->subparts_cpus,
cs->cpus_allowed);
cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus);
}
}
spin_unlock_irq(&callback_lock);
#ifdef CONFIG_CPUMASK_OFFSTACK
/* Now trialcs->cpus_allowed is available */
tmp.new_cpus = trialcs->cpus_allowed;
#endif
/* effective_cpus will be updated here */
update_cpumasks_hier(cs, &tmp, false);
if (cs->partition_root_state) {
struct cpuset *parent = parent_cs(cs);
/*
* For partition root, update the cpumasks of sibling
* cpusets if they use parent's effective_cpus.
*/
if (parent->child_ecpus_count)
update_sibling_cpumasks(parent, cs, &tmp);
}
return 0;
}
/*
* Migrate memory region from one set of nodes to another. This is
* performed asynchronously as it can be called from process migration path
* holding locks involved in process management. All mm migrations are
* performed in the queued order and can be waited for by flushing
* cpuset_migrate_mm_wq.
*/
struct cpuset_migrate_mm_work {
struct work_struct work;
struct mm_struct *mm;
nodemask_t from;
nodemask_t to;
};
static void cpuset_migrate_mm_workfn(struct work_struct *work)
{
struct cpuset_migrate_mm_work *mwork =
container_of(work, struct cpuset_migrate_mm_work, work);
/* on a wq worker, no need to worry about %current's mems_allowed */
do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL);
mmput(mwork->mm);
kfree(mwork);
}
static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
const nodemask_t *to)
{
struct cpuset_migrate_mm_work *mwork;
if (nodes_equal(*from, *to)) {
mmput(mm);
return;
}
mwork = kzalloc(sizeof(*mwork), GFP_KERNEL);
if (mwork) {
mwork->mm = mm;
mwork->from = *from;
mwork->to = *to;
INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn);
queue_work(cpuset_migrate_mm_wq, &mwork->work);
} else {
mmput(mm);
}
}
static void cpuset_post_attach(void)
{
flush_workqueue(cpuset_migrate_mm_wq);
}
/*
* cpuset_change_task_nodemask - change task's mems_allowed and mempolicy
* @tsk: the task to change
* @newmems: new nodes that the task will be set
*
* We use the mems_allowed_seq seqlock to safely update both tsk->mems_allowed
* and rebind an eventual tasks' mempolicy. If the task is allocating in
* parallel, it might temporarily see an empty intersection, which results in
* a seqlock check and retry before OOM or allocation failure.
*/
static void cpuset_change_task_nodemask(struct task_struct *tsk,
nodemask_t *newmems)
{
task_lock(tsk);
local_irq_disable();
write_seqcount_begin(&tsk->mems_allowed_seq);
nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
mpol_rebind_task(tsk, newmems);
tsk->mems_allowed = *newmems;
write_seqcount_end(&tsk->mems_allowed_seq);
local_irq_enable();
task_unlock(tsk);
}
static void *cpuset_being_rebound;
/**
* update_tasks_nodemask - Update the nodemasks of tasks in the cpuset.
* @cs: the cpuset in which each task's mems_allowed mask needs to be changed
*
* Iterate through each task of @cs updating its mems_allowed to the
* effective cpuset's. As this function is called with cpuset_rwsem held,
* cpuset membership stays stable.
*/
static void update_tasks_nodemask(struct cpuset *cs)
{
static nodemask_t newmems; /* protected by cpuset_rwsem */
struct css_task_iter it;
struct task_struct *task;
cpuset_being_rebound = cs; /* causes mpol_dup() rebind */
guarantee_online_mems(cs, &newmems);
/*
* The mpol_rebind_mm() call takes mmap_lock, which we couldn't
* take while holding tasklist_lock. Forks can happen - the
* mpol_dup() cpuset_being_rebound check will catch such forks,
* and rebind their vma mempolicies too. Because we still hold
* the global cpuset_rwsem, we know that no other rebind effort
* will be contending for the global variable cpuset_being_rebound.
* It's ok if we rebind the same mm twice; mpol_rebind_mm()
* is idempotent. Also migrate pages in each mm to new nodes.
*/
css_task_iter_start(&cs->css, 0, &it);
while ((task = css_task_iter_next(&it))) {
struct mm_struct *mm;
bool migrate;
cpuset_change_task_nodemask(task, &newmems);
mm = get_task_mm(task);
if (!mm)
continue;
migrate = is_memory_migrate(cs);
mpol_rebind_mm(mm, &cs->mems_allowed);
if (migrate)
cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems);
else
mmput(mm);
}
css_task_iter_end(&it);
/*
* All the tasks' nodemasks have been updated, update
* cs->old_mems_allowed.
*/
cs->old_mems_allowed = newmems;
/* We're done rebinding vmas to this cpuset's new mems_allowed. */
cpuset_being_rebound = NULL;
}
/*
* update_nodemasks_hier - Update effective nodemasks and tasks in the subtree
* @cs: the cpuset to consider
* @new_mems: a temp variable for calculating new effective_mems
*
* When configured nodemask is changed, the effective nodemasks of this cpuset
* and all its descendants need to be updated.
*
* On legacy hierarchy, effective_mems will be the same with mems_allowed.
*
* Called with cpuset_rwsem held
*/
static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
{
struct cpuset *cp;
struct cgroup_subsys_state *pos_css;
rcu_read_lock();
cpuset_for_each_descendant_pre(cp, pos_css, cs) {
struct cpuset *parent = parent_cs(cp);
nodes_and(*new_mems, cp->mems_allowed, parent->effective_mems);
/*
* If it becomes empty, inherit the effective mask of the
* parent, which is guaranteed to have some MEMs.
*/
if (is_in_v2_mode() && nodes_empty(*new_mems))
*new_mems = parent->effective_mems;
/* Skip the whole subtree if the nodemask remains the same. */
if (nodes_equal(*new_mems, cp->effective_mems)) {
pos_css = css_rightmost_descendant(pos_css);
continue;
}
if (!css_tryget_online(&cp->css))
continue;
rcu_read_unlock();
spin_lock_irq(&callback_lock);
cp->effective_mems = *new_mems;
spin_unlock_irq(&callback_lock);
WARN_ON(!is_in_v2_mode() &&
!nodes_equal(cp->mems_allowed, cp->effective_mems));
update_tasks_nodemask(cp);
rcu_read_lock();
css_put(&cp->css);
}
rcu_read_unlock();
}
/*
* Handle user request to change the 'mems' memory placement
* of a cpuset. Needs to validate the request, update the
* cpusets mems_allowed, and for each task in the cpuset,
* update mems_allowed and rebind task's mempolicy and any vma
* mempolicies and if the cpuset is marked 'memory_migrate',
* migrate the tasks pages to the new memory.
*
* Call with cpuset_rwsem held. May take callback_lock during call.
* Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
* lock each such tasks mm->mmap_lock, scan its vma's and rebind
* their mempolicies to the cpusets new mems_allowed.
*/
static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
const char *buf)
{
int retval;
/*
* top_cpuset.mems_allowed tracks node_stats[N_MEMORY];
* it's read-only
*/
if (cs == &top_cpuset) {
retval = -EACCES;
goto done;
}
/*
* An empty mems_allowed is ok iff there are no tasks in the cpuset.
* Since nodelist_parse() fails on an empty mask, we special case
* that parsing. The validate_change() call ensures that cpusets
* with tasks have memory.
*/
if (!*buf) {
nodes_clear(trialcs->mems_allowed);
} else {
retval = nodelist_parse(buf, trialcs->mems_allowed);
if (retval < 0)
goto done;
if (!nodes_subset(trialcs->mems_allowed,
top_cpuset.mems_allowed)) {
retval = -EINVAL;
goto done;
}
}
if (nodes_equal(cs->mems_allowed, trialcs->mems_allowed)) {
retval = 0; /* Too easy - nothing to do */
goto done;
}
retval = validate_change(cs, trialcs);
if (retval < 0)
goto done;
check_insane_mems_config(&trialcs->mems_allowed);
spin_lock_irq(&callback_lock);
cs->mems_allowed = trialcs->mems_allowed;
spin_unlock_irq(&callback_lock);
/* use trialcs->mems_allowed as a temp variable */
update_nodemasks_hier(cs, &trialcs->mems_allowed);
done:
return retval;
}
bool current_cpuset_is_being_rebound(void)
{
bool ret;
rcu_read_lock();
ret = task_cs(current) == cpuset_being_rebound;
rcu_read_unlock();
return ret;
}
static int update_relax_domain_level(struct cpuset *cs, s64 val)
{
#ifdef CONFIG_SMP
if (val < -1 || val >= sched_domain_level_max)
return -EINVAL;
#endif
if (val != cs->relax_domain_level) {
cs->relax_domain_level = val;
if (!cpumask_empty(cs->cpus_allowed) &&
is_sched_load_balance(cs))
rebuild_sched_domains_locked();
}
return 0;
}
/**
* update_tasks_flags - update the spread flags of tasks in the cpuset.
* @cs: the cpuset in which each task's spread flags needs to be changed
*
* Iterate through each task of @cs updating its spread flags. As this
* function is called with cpuset_rwsem held, cpuset membership stays
* stable.
*/
static void update_tasks_flags(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)))
cpuset_update_task_spread_flags(cs, task);
css_task_iter_end(&it);
}
/*
* update_flag - read a 0 or a 1 in a file and update associated flag
* bit: the bit to update (see cpuset_flagbits_t)
* cs: the cpuset to update
* turning_on: whether the flag is being set or cleared
*
* Call with cpuset_rwsem held.
*/
static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
int turning_on)
{
struct cpuset *trialcs;
int balance_flag_changed;
int spread_flag_changed;
int err;
trialcs = alloc_trial_cpuset(cs);
if (!trialcs)
return -ENOMEM;
if (turning_on)
set_bit(bit, &trialcs->flags);
else
clear_bit(bit, &trialcs->flags);
err = validate_change(cs, trialcs);
if (err < 0)
goto out;
balance_flag_changed = (is_sched_load_balance(cs) !=
is_sched_load_balance(trialcs));
spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs))
|| (is_spread_page(cs) != is_spread_page(trialcs)));
spin_lock_irq(&callback_lock);
cs->flags = trialcs->flags;
spin_unlock_irq(&callback_lock);
if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed)
rebuild_sched_domains_locked();
if (spread_flag_changed)
update_tasks_flags(cs);
out:
free_cpuset(trialcs);
return err;
}
/**
* update_prstate - update partition_root_state
* @cs: the cpuset to update
* @new_prs: new partition root state
* Return: 0 if successful, != 0 if error
*
* Call with cpuset_rwsem held.
*/
static int update_prstate(struct cpuset *cs, int new_prs)
{
int err = PERR_NONE, old_prs = cs->partition_root_state;
bool sched_domain_rebuilt = false;
struct cpuset *parent = parent_cs(cs);
struct tmpmasks tmpmask;
if (old_prs == new_prs)
return 0;
/*
* For a previously invalid partition root, leave it at being
* invalid if new_prs is not "member".
*/
if (new_prs && is_prs_invalid(old_prs)) {
cs->partition_root_state = -new_prs;
return 0;
}
if (alloc_cpumasks(NULL, &tmpmask))
return -ENOMEM;
if (!old_prs) {
/*
* Turning on partition root requires setting the
* CS_CPU_EXCLUSIVE bit implicitly as well and cpus_allowed
* cannot be empty.
*/
if (cpumask_empty(cs->cpus_allowed)) {
err = PERR_CPUSEMPTY;
goto out;
}
err = update_flag(CS_CPU_EXCLUSIVE, cs, 1);
if (err) {
err = PERR_NOTEXCL;
goto out;
}
err = update_parent_subparts_cpumask(cs, partcmd_enable,
NULL, &tmpmask);
if (err) {
update_flag(CS_CPU_EXCLUSIVE, cs, 0);
goto out;
}
if (new_prs == PRS_ISOLATED) {
/*
* Disable the load balance flag should not return an
* error unless the system is running out of memory.
*/
update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);
sched_domain_rebuilt = true;
}
} else if (old_prs && new_prs) {
/*
* A change in load balance state only, no change in cpumasks.
*/
update_flag(CS_SCHED_LOAD_BALANCE, cs, (new_prs != PRS_ISOLATED));
sched_domain_rebuilt = true;
goto out; /* Sched domain is rebuilt in update_flag() */
} else {
/*
* Switching back to member is always allowed even if it
* disables child partitions.
*/
update_parent_subparts_cpumask(cs, partcmd_disable, NULL,
&tmpmask);
/*
* If there are child partitions, they will all become invalid.
*/
if (unlikely(cs->nr_subparts_cpus)) {
spin_lock_irq(&callback_lock);
cs->nr_subparts_cpus = 0;
cpumask_clear(cs->subparts_cpus);
compute_effective_cpumask(cs->effective_cpus, cs, parent);
spin_unlock_irq(&callback_lock);
}
/* Turning off CS_CPU_EXCLUSIVE will not return error */
update_flag(CS_CPU_EXCLUSIVE, cs, 0);
if (!is_sched_load_balance(cs)) {
/* Make sure load balance is on */
update_flag(CS_SCHED_LOAD_BALANCE, cs, 1);
sched_domain_rebuilt = true;
}
}
update_tasks_cpumask(parent, tmpmask.new_cpus);
if (parent->child_ecpus_count)
update_sibling_cpumasks(parent, cs, &tmpmask);
if (!sched_domain_rebuilt)
rebuild_sched_domains_locked();
out:
/*
* Make partition invalid if an error happen
*/
if (err)
new_prs = -new_prs;
spin_lock_irq(&callback_lock);
cs->partition_root_state = new_prs;
WRITE_ONCE(cs->prs_err, err);
spin_unlock_irq(&callback_lock);
/*
* Update child cpusets, if present.
* Force update if switching back to member.
*/
if (!list_empty(&cs->css.children))
update_cpumasks_hier(cs, &tmpmask, !new_prs);
notify_partition_change(cs, old_prs);
free_cpumasks(NULL, &tmpmask);
return 0;
}
/*
* Frequency meter - How fast is some event occurring?
*
* 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 ((u32)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)
{
time64_t now;
u32 ticks;
now = ktime_get_seconds();
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;
}
static struct cpuset *cpuset_attach_old_cs;
/*
* Check to see if a cpuset can accept a new task
* For v1, cpus_allowed and mems_allowed can't be empty.
* For v2, effective_cpus can't be empty.
* Note that in v1, effective_cpus = cpus_allowed.
*/
static int cpuset_can_attach_check(struct cpuset *cs)
{
if (cpumask_empty(cs->effective_cpus) ||
(!is_in_v2_mode() && nodes_empty(cs->mems_allowed)))
return -ENOSPC;
return 0;
}
/* Called by cgroups to determine if a cpuset is usable; cpuset_rwsem held */
static int cpuset_can_attach(struct cgroup_taskset *tset)
{
struct cgroup_subsys_state *css;
struct cpuset *cs;
struct task_struct *task;
int ret;
/* used later by cpuset_attach() */
cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css));
cs = css_cs(css);
percpu_down_write(&cpuset_rwsem);
/* Check to see if task is allowed in the cpuset */
ret = cpuset_can_attach_check(cs);
if (ret)
goto out_unlock;
cgroup_taskset_for_each(task, css, tset) {
ret = task_can_attach(task, cs->effective_cpus);
if (ret)
goto out_unlock;
ret = security_task_setscheduler(task);
if (ret)
goto out_unlock;
}
/*
* Mark attach is in progress. This makes validate_change() fail
* changes which zero cpus/mems_allowed.
*/
cs->attach_in_progress++;
out_unlock:
percpu_up_write(&cpuset_rwsem);
return ret;
}
static void cpuset_cancel_attach(struct cgroup_taskset *tset)
{
struct cgroup_subsys_state *css;
struct cpuset *cs;
cgroup_taskset_first(tset, &css);
cs = css_cs(css);
percpu_down_write(&cpuset_rwsem);
cs->attach_in_progress--;
if (!cs->attach_in_progress)
wake_up(&cpuset_attach_wq);
percpu_up_write(&cpuset_rwsem);
}
/*
* Protected by cpuset_rwsem. cpus_attach is used only by cpuset_attach_task()
* but we can't allocate it dynamically there. Define it global and
* allocate from cpuset_init().
*/
static cpumask_var_t cpus_attach;
static nodemask_t cpuset_attach_nodemask_to;
static void cpuset_attach_task(struct cpuset *cs, struct task_struct *task)
{
percpu_rwsem_assert_held(&cpuset_rwsem);
if (cs != &top_cpuset)
guarantee_online_cpus(task, cpus_attach);
else
cpumask_copy(cpus_attach, task_cpu_possible_mask(task));
/*
* can_attach beforehand should guarantee that this doesn't
* fail. TODO: have a better way to handle failure here
*/
WARN_ON_ONCE(set_cpus_allowed_ptr(task, cpus_attach));
cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to);
cpuset_update_task_spread_flags(cs, task);
}
static void cpuset_attach(struct cgroup_taskset *tset)
{
struct task_struct *task;
struct task_struct *leader;
struct cgroup_subsys_state *css;
struct cpuset *cs;
struct cpuset *oldcs = cpuset_attach_old_cs;
cgroup_taskset_first(tset, &css);
cs = css_cs(css);
lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */
percpu_down_write(&cpuset_rwsem);
guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
cgroup_taskset_for_each(task, css, tset)
cpuset_attach_task(cs, task);
/*
* Change mm for all threadgroup leaders. This is expensive and may
* sleep and should be moved outside migration path proper.
*/
cpuset_attach_nodemask_to = cs->effective_mems;
cgroup_taskset_for_each_leader(leader, css, tset) {
struct mm_struct *mm = get_task_mm(leader);
if (mm) {
mpol_rebind_mm(mm, &cpuset_attach_nodemask_to);
/*
* old_mems_allowed is the same with mems_allowed
* here, except if this task is being moved
* automatically due to hotplug. In that case
* @mems_allowed has been updated and is empty, so
* @old_mems_allowed is the right nodesets that we
* migrate mm from.
*/
if (is_memory_migrate(cs))
cpuset_migrate_mm(mm, &oldcs->old_mems_allowed,
&cpuset_attach_nodemask_to);
else
mmput(mm);
}
}
cs->old_mems_allowed = cpuset_attach_nodemask_to;
cs->attach_in_progress--;
if (!cs->attach_in_progress)
wake_up(&cpuset_attach_wq);
percpu_up_write(&cpuset_rwsem);
}
/* The various types of files and directories in a cpuset file system */
typedef enum {
FILE_MEMORY_MIGRATE,
FILE_CPULIST,
FILE_MEMLIST,
FILE_EFFECTIVE_CPULIST,
FILE_EFFECTIVE_MEMLIST,
FILE_SUBPARTS_CPULIST,
FILE_CPU_EXCLUSIVE,
FILE_MEM_EXCLUSIVE,
FILE_MEM_HARDWALL,
FILE_SCHED_LOAD_BALANCE,
FILE_PARTITION_ROOT,
FILE_SCHED_RELAX_DOMAIN_LEVEL,
FILE_MEMORY_PRESSURE_ENABLED,
FILE_MEMORY_PRESSURE,
FILE_SPREAD_PAGE,
FILE_SPREAD_SLAB,
} cpuset_filetype_t;
static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
u64 val)
{
struct cpuset *cs = css_cs(css);
cpuset_filetype_t type = cft->private;
int retval = 0;
cpus_read_lock();
percpu_down_write(&cpuset_rwsem);
if (!is_cpuset_online(cs)) {
retval = -ENODEV;
goto out_unlock;
}
switch (type) {
case FILE_CPU_EXCLUSIVE:
retval = update_flag(CS_CPU_EXCLUSIVE, cs, val);
break;
case FILE_MEM_EXCLUSIVE:
retval = update_flag(CS_MEM_EXCLUSIVE, cs, val);
break;
case FILE_MEM_HARDWALL:
retval = update_flag(CS_MEM_HARDWALL, cs, val);
break;
case FILE_SCHED_LOAD_BALANCE:
retval = update_flag(CS_SCHED_LOAD_BALANCE, cs, val);
break;
case FILE_MEMORY_MIGRATE:
retval = update_flag(CS_MEMORY_MIGRATE, cs, val);
break;
case FILE_MEMORY_PRESSURE_ENABLED:
cpuset_memory_pressure_enabled = !!val;
break;
case FILE_SPREAD_PAGE:
retval = update_flag(CS_SPREAD_PAGE, cs, val);
break;
case FILE_SPREAD_SLAB:
retval = update_flag(CS_SPREAD_SLAB, cs, val);
break;
default:
retval = -EINVAL;
break;
}
out_unlock:
percpu_up_write(&cpuset_rwsem);
cpus_read_unlock();
return retval;
}
static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft,
s64 val)
{
struct cpuset *cs = css_cs(css);
cpuset_filetype_t type = cft->private;
int retval = -ENODEV;
cpus_read_lock();
percpu_down_write(&cpuset_rwsem);
if (!is_cpuset_online(cs))
goto out_unlock;
switch (type) {
case FILE_SCHED_RELAX_DOMAIN_LEVEL:
retval = update_relax_domain_level(cs, val);
break;
default:
retval = -EINVAL;
break;
}
out_unlock:
percpu_up_write(&cpuset_rwsem);
cpus_read_unlock();
return retval;
}
/*
* Common handling for a write to a "cpus" or "mems" file.
*/
static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
struct cpuset *cs = css_cs(of_css(of));
struct cpuset *trialcs;
int retval = -ENODEV;
buf = strstrip(buf);
/*
* CPU or memory hotunplug may leave @cs w/o any execution
* resources, in which case the hotplug code asynchronously updates
* configuration and transfers all tasks to the nearest ancestor
* which can execute.
*
* As writes to "cpus" or "mems" may restore @cs's execution
* resources, wait for the previously scheduled operations before
* proceeding, so that we don't end up keep removing tasks added
* after execution capability is restored.
*
* cpuset_hotplug_work calls back into cgroup core via
* cgroup_transfer_tasks() and waiting for it from a cgroupfs
* operation like this one can lead to a deadlock through kernfs
* active_ref protection. Let's break the protection. Losing the
* protection is okay as we check whether @cs is online after
* grabbing cpuset_rwsem anyway. This only happens on the legacy
* hierarchies.
*/
css_get(&cs->css);
kernfs_break_active_protection(of->kn);
flush_work(&cpuset_hotplug_work);
cpus_read_lock();
percpu_down_write(&cpuset_rwsem);
if (!is_cpuset_online(cs))
goto out_unlock;
trialcs = alloc_trial_cpuset(cs);
if (!trialcs) {
retval = -ENOMEM;
goto out_unlock;
}
switch (of_cft(of)->private) {
case FILE_CPULIST:
retval = update_cpumask(cs, trialcs, buf);
break;
case FILE_MEMLIST:
retval = update_nodemask(cs, trialcs, buf);
break;
default:
retval = -EINVAL;
break;
}
free_cpuset(trialcs);
out_unlock:
percpu_up_write(&cpuset_rwsem);
cpus_read_unlock();
kernfs_unbreak_active_protection(of->kn);
css_put(&cs->css);
flush_workqueue(cpuset_migrate_mm_wq);
return retval ?: nbytes;
}
/*
* 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.
*/
static int cpuset_common_seq_show(struct seq_file *sf, void *v)
{
struct cpuset *cs = css_cs(seq_css(sf));
cpuset_filetype_t type = seq_cft(sf)->private;
int ret = 0;
spin_lock_irq(&callback_lock);
switch (type) {
case FILE_CPULIST:
seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_allowed));
break;
case FILE_MEMLIST:
seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->mems_allowed));
break;
case FILE_EFFECTIVE_CPULIST:
seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->effective_cpus));
break;
case FILE_EFFECTIVE_MEMLIST:
seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems));
break;
case FILE_SUBPARTS_CPULIST:
seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->subparts_cpus));
break;
default:
ret = -EINVAL;
}
spin_unlock_irq(&callback_lock);
return ret;
}
static u64 cpuset_read_u64(struct cgroup_subsys_state *css, struct cftype *cft)
{
struct cpuset *cs = css_cs(css);
cpuset_filetype_t type = cft->private;
switch (type) {
case FILE_CPU_EXCLUSIVE:
return is_cpu_exclusive(cs);
case FILE_MEM_EXCLUSIVE:
return is_mem_exclusive(cs);
case FILE_MEM_HARDWALL:
return is_mem_hardwall(cs);
case FILE_SCHED_LOAD_BALANCE:
return is_sched_load_balance(cs);
case FILE_MEMORY_MIGRATE:
return is_memory_migrate(cs);
case FILE_MEMORY_PRESSURE_ENABLED:
return cpuset_memory_pressure_enabled;
case FILE_MEMORY_PRESSURE:
return fmeter_getrate(&cs->fmeter);
case FILE_SPREAD_PAGE:
return is_spread_page(cs);
case FILE_SPREAD_SLAB:
return is_spread_slab(cs);
default:
BUG();
}
/* Unreachable but makes gcc happy */
return 0;
}
static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft)
{
struct cpuset *cs = css_cs(css);
cpuset_filetype_t type = cft->private;
switch (type) {
case FILE_SCHED_RELAX_DOMAIN_LEVEL:
return cs->relax_domain_level;
default:
BUG();
}
/* Unreachable but makes gcc happy */
return 0;
}
static int sched_partition_show(struct seq_file *seq, void *v)
{
struct cpuset *cs = css_cs(seq_css(seq));
const char *err, *type = NULL;
switch (cs->partition_root_state) {
case PRS_ROOT:
seq_puts(seq, "root\n");
break;
case PRS_ISOLATED:
seq_puts(seq, "isolated\n");
break;
case PRS_MEMBER:
seq_puts(seq, "member\n");
break;
case PRS_INVALID_ROOT:
type = "root";
fallthrough;
case PRS_INVALID_ISOLATED:
if (!type)
type = "isolated";
err = perr_strings[READ_ONCE(cs->prs_err)];
if (err)
seq_printf(seq, "%s invalid (%s)\n", type, err);
else
seq_printf(seq, "%s invalid\n", type);
break;
}
return 0;
}
static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off)
{
struct cpuset *cs = css_cs(of_css(of));
int val;
int retval = -ENODEV;
buf = strstrip(buf);
/*
* Convert "root" to ENABLED, and convert "member" to DISABLED.
*/
if (!strcmp(buf, "root"))
val = PRS_ROOT;
else if (!strcmp(buf, "member"))
val = PRS_MEMBER;
else if (!strcmp(buf, "isolated"))
val = PRS_ISOLATED;
else
return -EINVAL;
css_get(&cs->css);
cpus_read_lock();
percpu_down_write(&cpuset_rwsem);
if (!is_cpuset_online(cs))
goto out_unlock;
retval = update_prstate(cs, val);
out_unlock:
percpu_up_write(&cpuset_rwsem);
cpus_read_unlock();
css_put(&cs->css);
return retval ?: nbytes;
}
/*
* for the common functions, 'private' gives the type of file
*/
static struct cftype legacy_files[] = {
{
.name = "cpus",
.seq_show = cpuset_common_seq_show,
.write = cpuset_write_resmask,
.max_write_len = (100U + 6 * NR_CPUS),
.private = FILE_CPULIST,
},
{
.name = "mems",
.seq_show = cpuset_common_seq_show,
.write = cpuset_write_resmask,
.max_write_len = (100U + 6 * MAX_NUMNODES),
.private = FILE_MEMLIST,
},
{
.name = "effective_cpus",
.seq_show = cpuset_common_seq_show,
.private = FILE_EFFECTIVE_CPULIST,
},
{
.name = "effective_mems",
.seq_show = cpuset_common_seq_show,
.private = FILE_EFFECTIVE_MEMLIST,
},
{
.name = "cpu_exclusive",
.read_u64 = cpuset_read_u64,
.write_u64 = cpuset_write_u64,
.private = FILE_CPU_EXCLUSIVE,
},
{
.name = "mem_exclusive",
.read_u64 = cpuset_read_u64,
.write_u64 = cpuset_write_u64,
.private = FILE_MEM_EXCLUSIVE,
},
{
.name = "mem_hardwall",
.read_u64 = cpuset_read_u64,
.write_u64 = cpuset_write_u64,
.private = FILE_MEM_HARDWALL,
},
{
.name = "sched_load_balance",
.read_u64 = cpuset_read_u64,
.write_u64 = cpuset_write_u64,
.private = FILE_SCHED_LOAD_BALANCE,
},
{
.name = "sched_relax_domain_level",
.read_s64 = cpuset_read_s64,
.write_s64 = cpuset_write_s64,
.private = FILE_SCHED_RELAX_DOMAIN_LEVEL,
},
{
.name = "memory_migrate",
.read_u64 = cpuset_read_u64,
.write_u64 = cpuset_write_u64,
.private = FILE_MEMORY_MIGRATE,
},
{
.name = "memory_pressure",
.read_u64 = cpuset_read_u64,
.private = FILE_MEMORY_PRESSURE,
},
{
.name = "memory_spread_page",
.read_u64 = cpuset_read_u64,
.write_u64 = cpuset_write_u64,
.private = FILE_SPREAD_PAGE,
},
{
.name = "memory_spread_slab",
.read_u64 = cpuset_read_u64,
.write_u64 = cpuset_write_u64,
.private = FILE_SPREAD_SLAB,
},
{
.name = "memory_pressure_enabled",
.flags = CFTYPE_ONLY_ON_ROOT,
.read_u64 = cpuset_read_u64,
.write_u64 = cpuset_write_u64,
.private = FILE_MEMORY_PRESSURE_ENABLED,
},
{ } /* terminate */
};
/*
* This is currently a minimal set for the default hierarchy. It can be
* expanded later on by migrating more features and control files from v1.
*/
static struct cftype dfl_files[] = {
{
.name = "cpus",
.seq_show = cpuset_common_seq_show,
.write = cpuset_write_resmask,
.max_write_len = (100U + 6 * NR_CPUS),
.private = FILE_CPULIST,
.flags = CFTYPE_NOT_ON_ROOT,
},
{
.name = "mems",
.seq_show = cpuset_common_seq_show,
.write = cpuset_write_resmask,
.max_write_len = (100U + 6 * MAX_NUMNODES),
.private = FILE_MEMLIST,
.flags = CFTYPE_NOT_ON_ROOT,
},
{
.name = "cpus.effective",
.seq_show = cpuset_common_seq_show,
.private = FILE_EFFECTIVE_CPULIST,
},
{
.name = "mems.effective",
.seq_show = cpuset_common_seq_show,
.private = FILE_EFFECTIVE_MEMLIST,
},
{
.name = "cpus.partition",
.seq_show = sched_partition_show,
.write = sched_partition_write,
.private = FILE_PARTITION_ROOT,
.flags = CFTYPE_NOT_ON_ROOT,
.file_offset = offsetof(struct cpuset, partition_file),
},
{
.name = "cpus.subpartitions",
.seq_show = cpuset_common_seq_show,
.private = FILE_SUBPARTS_CPULIST,
.flags = CFTYPE_DEBUG,
},
{ } /* terminate */
};
/*
* cpuset_css_alloc - allocate a cpuset css
* cgrp: control group that the new cpuset will be part of
*/
static struct cgroup_subsys_state *
cpuset_css_alloc(struct cgroup_subsys_state *parent_css)
{
struct cpuset *cs;
if (!parent_css)
return &top_cpuset.css;
cs = kzalloc(sizeof(*cs), GFP_KERNEL);
if (!cs)
return ERR_PTR(-ENOMEM);
if (alloc_cpumasks(cs, NULL)) {
kfree(cs);
return ERR_PTR(-ENOMEM);
}
__set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
nodes_clear(cs->mems_allowed);
nodes_clear(cs->effective_mems);
fmeter_init(&cs->fmeter);
cs->relax_domain_level = -1;
/* Set CS_MEMORY_MIGRATE for default hierarchy */
if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys))
__set_bit(CS_MEMORY_MIGRATE, &cs->flags);
return &cs->css;
}
static int cpuset_css_online(struct cgroup_subsys_state *css)
{
struct cpuset *cs = css_cs(css);
struct cpuset *parent = parent_cs(cs);
struct cpuset *tmp_cs;
struct cgroup_subsys_state *pos_css;
if (!parent)
return 0;
cpus_read_lock();
percpu_down_write(&cpuset_rwsem);
set_bit(CS_ONLINE, &cs->flags);
if (is_spread_page(parent))
set_bit(CS_SPREAD_PAGE, &cs->flags);
if (is_spread_slab(parent))
set_bit(CS_SPREAD_SLAB, &cs->flags);
cpuset_inc();
spin_lock_irq(&callback_lock);
if (is_in_v2_mode()) {
cpumask_copy(cs->effective_cpus, parent->effective_cpus);
cs->effective_mems = parent->effective_mems;
cs->use_parent_ecpus = true;
parent->child_ecpus_count++;
}
spin_unlock_irq(&callback_lock);
if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags))
goto out_unlock;
/*
* Clone @parent's configuration if CGRP_CPUSET_CLONE_CHILDREN is
* set. This flag handling is implemented in cgroup core for
* historical reasons - the flag may be specified during mount.
*
* Currently, if any sibling cpusets have exclusive cpus or mem, we
* refuse to clone the configuration - thereby refusing the task to
* be entered, and as a result refusing the sys_unshare() or
* clone() which initiated it. If this becomes a problem for some
* users who wish to allow that scenario, then this could be
* changed to grant parent->cpus_allowed-sibling_cpus_exclusive
* (and likewise for mems) to the new cgroup.
*/
rcu_read_lock();
cpuset_for_each_child(tmp_cs, pos_css, parent) {
if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs)) {
rcu_read_unlock();
goto out_unlock;
}
}
rcu_read_unlock();
spin_lock_irq(&callback_lock);
cs->mems_allowed = parent->mems_allowed;
cs->effective_mems = parent->mems_allowed;
cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
spin_unlock_irq(&callback_lock);
out_unlock:
percpu_up_write(&cpuset_rwsem);
cpus_read_unlock();
return 0;
}
/*
* If the cpuset being removed has its flag 'sched_load_balance'
* enabled, then simulate turning sched_load_balance off, which
* will call rebuild_sched_domains_locked(). That is not needed
* in the default hierarchy where only changes in partition
* will cause repartitioning.
*
* If the cpuset has the 'sched.partition' flag enabled, simulate
* turning 'sched.partition" off.
*/
static void cpuset_css_offline(struct cgroup_subsys_state *css)
{
struct cpuset *cs = css_cs(css);
cpus_read_lock();
percpu_down_write(&cpuset_rwsem);
if (is_partition_valid(cs))
update_prstate(cs, 0);
if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
is_sched_load_balance(cs))
update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);
if (cs->use_parent_ecpus) {
struct cpuset *parent = parent_cs(cs);
cs->use_parent_ecpus = false;
parent->child_ecpus_count--;
}
cpuset_dec();
clear_bit(CS_ONLINE, &cs->flags);
percpu_up_write(&cpuset_rwsem);
cpus_read_unlock();
}
static void cpuset_css_free(struct cgroup_subsys_state *css)
{
struct cpuset *cs = css_cs(css);
free_cpuset(cs);
}
static void cpuset_bind(struct cgroup_subsys_state *root_css)
{
percpu_down_write(&cpuset_rwsem);
spin_lock_irq(&callback_lock);
if (is_in_v2_mode()) {
cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask);
top_cpuset.mems_allowed = node_possible_map;
} else {
cpumask_copy(top_cpuset.cpus_allowed,
top_cpuset.effective_cpus);
top_cpuset.mems_allowed = top_cpuset.effective_mems;
}
spin_unlock_irq(&callback_lock);
percpu_up_write(&cpuset_rwsem);
}
/*
* In case the child is cloned into a cpuset different from its parent,
* additional checks are done to see if the move is allowed.
*/
static int cpuset_can_fork(struct task_struct *task, struct css_set *cset)
{
struct cpuset *cs = css_cs(cset->subsys[cpuset_cgrp_id]);
bool same_cs;
int ret;
rcu_read_lock();
same_cs = (cs == task_cs(current));
rcu_read_unlock();
if (same_cs)
return 0;
lockdep_assert_held(&cgroup_mutex);
percpu_down_write(&cpuset_rwsem);
/* Check to see if task is allowed in the cpuset */
ret = cpuset_can_attach_check(cs);
if (ret)
goto out_unlock;
ret = task_can_attach(task, cs->effective_cpus);
if (ret)
goto out_unlock;
ret = security_task_setscheduler(task);
if (ret)
goto out_unlock;
/*
* Mark attach is in progress. This makes validate_change() fail
* changes which zero cpus/mems_allowed.
*/
cs->attach_in_progress++;
out_unlock:
percpu_up_write(&cpuset_rwsem);
return ret;
}
static void cpuset_cancel_fork(struct task_struct *task, struct css_set *cset)
{
struct cpuset *cs = css_cs(cset->subsys[cpuset_cgrp_id]);
bool same_cs;
rcu_read_lock();
same_cs = (cs == task_cs(current));
rcu_read_unlock();
if (same_cs)
return;
percpu_down_write(&cpuset_rwsem);
cs->attach_in_progress--;
if (!cs->attach_in_progress)
wake_up(&cpuset_attach_wq);
percpu_up_write(&cpuset_rwsem);
}
/*
* Make sure the new task conform to the current state of its parent,
* which could have been changed by cpuset just after it inherits the
* state from the parent and before it sits on the cgroup's task list.
*/
static void cpuset_fork(struct task_struct *task)
{
struct cpuset *cs;
bool same_cs;
rcu_read_lock();
cs = task_cs(task);
same_cs = (cs == task_cs(current));
rcu_read_unlock();
if (same_cs) {
if (cs == &top_cpuset)
return;
set_cpus_allowed_ptr(task, current->cpus_ptr);
task->mems_allowed = current->mems_allowed;
return;
}
/* CLONE_INTO_CGROUP */
percpu_down_write(&cpuset_rwsem);
guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
cpuset_attach_task(cs, task);
cs->attach_in_progress--;
if (!cs->attach_in_progress)
wake_up(&cpuset_attach_wq);
percpu_up_write(&cpuset_rwsem);
}
struct cgroup_subsys cpuset_cgrp_subsys = {
.css_alloc = cpuset_css_alloc,
.css_online = cpuset_css_online,
.css_offline = cpuset_css_offline,
.css_free = cpuset_css_free,
.can_attach = cpuset_can_attach,
.cancel_attach = cpuset_cancel_attach,
.attach = cpuset_attach,
.post_attach = cpuset_post_attach,
.bind = cpuset_bind,
.can_fork = cpuset_can_fork,
.cancel_fork = cpuset_cancel_fork,
.fork = cpuset_fork,
.legacy_cftypes = legacy_files,
.dfl_cftypes = dfl_files,
.early_init = true,
.threaded = true,
};
/**
* cpuset_init - initialize cpusets at system boot
*
* Description: Initialize top_cpuset
**/
int __init cpuset_init(void)
{
BUG_ON(percpu_init_rwsem(&cpuset_rwsem));