diff options
Diffstat (limited to 'kernel/cpuset.c')
| -rw-r--r-- | kernel/cpuset.c | 2700 |
1 files changed, 2700 insertions, 0 deletions
diff --git a/kernel/cpuset.c b/kernel/cpuset.c new file mode 100644 index 000000000..ee14e3a35 --- /dev/null +++ b/kernel/cpuset.c @@ -0,0 +1,2700 @@ +/* + * 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/seq_file.h> +#include <linux/security.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/stat.h> +#include <linux/string.h> +#include <linux/time.h> +#include <linux/backing-dev.h> +#include <linux/sort.h> + +#include <asm/uaccess.h> +#include <linux/atomic.h> +#include <linux/mutex.h> +#include <linux/workqueue.h> +#include <linux/cgroup.h> +#include <linux/wait.h> + +struct static_key cpusets_enabled_key __read_mostly = STATIC_KEY_INIT_FALSE; + +/* See "Frequency meter" comments, below. */ + +struct fmeter { + int cnt; /* unprocessed events count */ + int val; /* most recent output value */ + time_t time; /* clock (secs) when val computed */ + spinlock_t lock; /* guards read or write of above */ +}; + +struct cpuset { + struct cgroup_subsys_state css; + + unsigned long flags; /* "unsigned long" so bitops work */ + + /* + * 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; +} + +/* 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); +} + +#ifdef CONFIG_NUMA +static inline bool task_has_mempolicy(struct task_struct *task) +{ + return task->mempolicy; +} +#else +static inline bool task_has_mempolicy(struct task_struct *task) +{ + return false; +} +#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(const struct cpuset *cs) +{ + return test_bit(CS_ONLINE, &cs->flags); +} + +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 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); + +/* + * 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); + +/* + * 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; +} + +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. The top + * cpuset always has some cpus online. + * + * 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); + cpumask_and(pmask, cs->effective_cpus, cpu_online_mask); +} + +/* + * 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]); +} + +/* + * 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); +} + +/* + * 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); +} + +/** + * 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; +} + +/** + * 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); +} + +/* + * 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 (!cgroup_on_dfl(cur->css.cgroup) && !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_has_tasks(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; +} + +#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(); +} + +/* + * 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 */ + cpumask_var_t non_isolated_cpus; /* load balanced CPUs */ + 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; + + if (!alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL)) + goto done; + cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); + + /* 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, + non_isolated_cpus); + + 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, non_isolated_cpus))) + 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, non_isolated_cpus); + if (dattr) + update_domain_attr_tree(dattr + nslot, b); + + /* Done with this partition */ + b->pn = -1; + } + } + nslot++; + } + BUG_ON(nslot != ndoms); + +done: + free_cpumask_var(non_isolated_cpus); + 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; +} + +/* + * 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(); +} +#else /* !CONFIG_SMP */ +static void rebuild_sched_domains_locked(void) +{ +} +#endif /* CONFIG_SMP */ + +void rebuild_sched_domains(void) +{ + mutex_lock(&cpuset_mutex); + rebuild_sched_domains_locked(); + mutex_unlock(&cpuset_mutex); +} + +/** + * 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, &it); + while ((task = css_task_iter_next(&it))) + set_cpus_allowed_ptr(task, cs->effective_cpus); + css_task_iter_end(&it); +} + +/* + * 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 (cgroup_on_dfl(cp->css.cgroup) && 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(!cgroup_on_dfl(cp->css.cgroup) && + !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(); +} + +/** + * 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; + + /* 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; + + retval = validate_change(cs, trialcs); + if (retval < 0) + return retval; + + spin_lock_irq(&callback_lock); + cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); + spin_unlock_irq(&callback_lock); + + /* use trialcs->cpus_allowed as a temp variable */ + update_cpumasks_hier(cs, trialcs->cpus_allowed); + return 0; +} + +/* + * cpuset_migrate_mm + * + * Migrate memory region from one set of nodes to another. + * + * Temporarilly set tasks mems_allowed to target nodes of migration, + * so that the migration code can allocate pages on these nodes. + * + * While the mm_struct we are migrating is typically from some + * other task, the task_struct mems_allowed that we are hacking + * is for our current task, which must allocate new pages for that + * migrating memory region. + */ + +static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, + const nodemask_t *to) +{ + struct task_struct *tsk = current; + + tsk->mems_allowed = *to; + + do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL); + + rcu_read_lock(); + guarantee_online_mems(task_cs(tsk), &tsk->mems_allowed); + rcu_read_unlock(); +} + +/* + * 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 + * + * In order to avoid seeing no nodes if the old and new nodes are disjoint, + * we structure updates as setting all new allowed nodes, then clearing newly + * disallowed ones. + */ +static void cpuset_change_task_nodemask(struct task_struct *tsk, + nodemask_t *newmems) +{ + bool need_loop; + + /* + * Allow tasks that have access to memory reserves because they have + * been OOM killed to get memory anywhere. + */ + if (unlikely(test_thread_flag(TIF_MEMDIE))) + return; + if (current->flags & PF_EXITING) /* Let dying task have memory */ + return; + + task_lock(tsk); + /* + * Determine if a loop is necessary if another thread is doing + * read_mems_allowed_begin(). If at least one node remains unchanged and + * tsk does not have a mempolicy, then an empty nodemask will not be + * possible when mems_allowed is larger than a word. + */ + need_loop = task_has_mempolicy(tsk) || + !nodes_intersects(*newmems, tsk->mems_allowed); + + if (need_loop) { + local_irq_disable(); + write_seqcount_begin(&tsk->mems_allowed_seq); + } + + nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); + mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1); + + mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2); + tsk->mems_allowed = *newmems; + + if (need_loop) { + 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_mutex held, + * cpuset membership stays stable. + */ +static void update_tasks_nodemask(struct cpuset *cs) +{ + static nodemask_t newmems; /* protected by cpuset_mutex */ + 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_sem, 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_mutex, 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, &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); + 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 hiearchy, effective_mems will be the same with mems_allowed. + * + * Called with cpuset_mutex 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 (cgroup_on_dfl(cp->css.cgroup) && 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(!cgroup_on_dfl(cp->css.cgroup) && + !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_mutex held. May take callback_lock during call. + * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, + * lock each such tasks mm->mmap_sem, scan its vma's and rebind + * their mempolicies to the cpusets new mems_allowed. + */ +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; + + 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, &cs->mems_allowed); +done: + return retval; +} + +int current_cpuset_is_being_rebound(void) +{ + int 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_mutex 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, &it); + while ((task = css_task_iter_next(&it))) + cpuset_update_task_spread_flag(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_mutex 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_trial_cpuset(trialcs); + return err; +} + +/* + * 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 ((time_t)99) /* useless computing more ticks than this */ +#define FM_MAXCNT 1000000 /* limit cnt to avoid overflow */ +#define FM_SCALE 1000 /* faux fixed point scale */ + +/* Initialize a frequency meter */ +static void fmeter_init(struct fmeter *fmp) +{ + fmp->cnt = 0; + fmp->val = 0; + fmp->time = 0; + spin_lock_init(&fmp->lock); +} + +/* Internal meter update - process cnt events and update value */ +static void fmeter_update(struct fmeter *fmp) +{ + time_t now = get_seconds(); + time_t ticks = now - fmp->time; + + if (ticks == 0) + return; + + ticks = min(FM_MAXTICKS, ticks); + while (ticks-- > 0) + fmp->val = (FM_COEF * fmp->val) / FM_SCALE; + fmp->time = now; + + fmp->val += ((FM_SCALE - FM_COEF) * fmp->cnt) / FM_SCALE; + fmp->cnt = 0; +} + +/* Process any previous ticks, then bump cnt by one (times scale). */ +static void fmeter_markevent(struct fmeter *fmp) +{ + spin_lock(&fmp->lock); + fmeter_update(fmp); + fmp->cnt = min(FM_MAXCNT, fmp->cnt + FM_SCALE); + spin_unlock(&fmp->lock); +} + +/* Process any previous ticks, then return current value. */ +static int fmeter_getrate(struct fmeter *fmp) +{ + int val; + + spin_lock(&fmp->lock); + fmeter_update(fmp); + val = fmp->val; + spin_unlock(&fmp->lock); + return val; +} + +static struct cpuset *cpuset_attach_old_cs; + +/* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ +static int cpuset_can_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) +{ + struct cpuset *cs = css_cs(css); + struct task_struct *task; + int ret; + + /* used later by cpuset_attach() */ + cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset)); + + mutex_lock(&cpuset_mutex); + + /* allow moving tasks into an empty cpuset if on default hierarchy */ + ret = -ENOSPC; + if (!cgroup_on_dfl(css->cgroup) && + (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) + goto out_unlock; + + cgroup_taskset_for_each(task, tset) { + ret = task_can_attach(task, cs->cpus_allowed); + 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++; + ret = 0; +out_unlock: + mutex_unlock(&cpuset_mutex); + return ret; +} + +static void cpuset_cancel_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) +{ + mutex_lock(&cpuset_mutex); + css_cs(css)->attach_in_progress--; + mutex_unlock(&cpuset_mutex); +} + +/* + * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach() + * but we can't allocate it dynamically there. Define it global and + * allocate from cpuset_init(). + */ +static cpumask_var_t cpus_attach; + +static void cpuset_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) +{ + /* static buf protected by cpuset_mutex */ + static nodemask_t cpuset_attach_nodemask_to; + struct mm_struct *mm; + struct task_struct *task; + struct task_struct *leader = cgroup_taskset_first(tset); + struct cpuset *cs = css_cs(css); + struct cpuset *oldcs = cpuset_attach_old_cs; + + mutex_lock(&cpuset_mutex); + + /* prepare for attach */ + if (cs == &top_cpuset) + cpumask_copy(cpus_attach, cpu_possible_mask); + else + guarantee_online_cpus(cs, cpus_attach); + + guarantee_online_mems(cs, &cpuset_attach_nodemask_to); + + cgroup_taskset_for_each(task, tset) { + /* + * 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_flag(cs, task); + } + + /* + * Change mm, possibly for multiple threads in a threadgroup. This is + * expensive and may sleep. + */ + cpuset_attach_nodemask_to = cs->effective_mems; + 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); + } + mmput(mm); + } + + cs->old_mems_allowed = cpuset_attach_nodemask_to; + + cs->attach_in_progress--; + if (!cs->attach_in_progress) + wake_up(&cpuset_attach_wq); + + mutex_unlock(&cpuset_mutex); +} + +/* 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_CPU_EXCLUSIVE, + FILE_MEM_EXCLUSIVE, + FILE_MEM_HARDWALL, + FILE_SCHED_LOAD_BALANCE, + 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; + + mutex_lock(&cpuset_mutex); + 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_MEMORY_PRESSURE: + retval = -EACCES; + 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: + mutex_unlock(&cpuset_mutex); + 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; + + mutex_lock(&cpuset_mutex); + 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: + mutex_unlock(&cpuset_mutex); + 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_mutex anyway. This only happens on the legacy + * hierarchies. + */ + css_get(&cs->css); + kernfs_break_active_protection(of->kn); + flush_work(&cpuset_hotplug_work); + + mutex_lock(&cpuset_mutex); + 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_trial_cpuset(trialcs); +out_unlock: + mutex_unlock(&cpuset_mutex); + kernfs_unbreak_active_protection(of->kn); + css_put(&cs->css); + 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; + 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(); + } + + /* Unrechable but makes gcc happy */ + return 0; +} + + +/* + * for the common functions, 'private' gives the type of file + */ + +static struct cftype 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, + .write_u64 = cpuset_write_u64, + .private = FILE_MEMORY_PRESSURE, + .mode = S_IRUGO, + }, + + { + .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 */ +}; + +/* + * 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_cpumask_var(&cs->cpus_allowed, GFP_KERNEL)) + goto free_cs; + if (!alloc_cpumask_var(&cs->effective_cpus, GFP_KERNEL)) + goto free_cpus; + + set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); + cpumask_clear(cs->cpus_allowed); + nodes_clear(cs->mems_allowed); + cpumask_clear(cs->effective_cpus); + nodes_clear(cs->effective_mems); + fmeter_init(&cs->fmeter); + cs->relax_domain_level = -1; + + return &cs->css; + +free_cpus: + free_cpumask_var(cs->cpus_allowed); +free_cs: + kfree(cs); + return ERR_PTR(-ENOMEM); +} + +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; + + mutex_lock(&cpuset_mutex); + + 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 (cgroup_on_dfl(cs->css.cgroup)) { + cpumask_copy(cs->effective_cpus, parent->effective_cpus); + cs->effective_mems = parent->effective_mems; + } + 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 + * histrical 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: + mutex_unlock(&cpuset_mutex); + 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(). + */ + +static void cpuset_css_offline(struct cgroup_subsys_state *css) +{ + struct cpuset *cs = css_cs(css); + + mutex_lock(&cpuset_mutex); + + if (is_sched_load_balance(cs)) + update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); + + cpuset_dec(); + clear_bit(CS_ONLINE, &cs->flags); + + mutex_unlock(&cpuset_mutex); +} + +static void cpuset_css_free(struct cgroup_subsys_state *css) +{ + struct cpuset *cs = css_cs(css); + + free_cpumask_var(cs->effective_cpus); + free_cpumask_var(cs->cpus_allowed); + kfree(cs); +} + +static void cpuset_bind(struct cgroup_subsys_state *root_css) +{ + mutex_lock(&cpuset_mutex); + spin_lock_irq(&callback_lock); + + if (cgroup_on_dfl(root_css->cgroup)) { + 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); + mutex_unlock(&cpuset_mutex); +} + +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, + .bind = cpuset_bind, + .legacy_cftypes = files, + .early_init = 1, +}; + +/** + * cpuset_init - initialize cpusets at system boot + * + * Description: Initialize top_cpuset and the cpuset internal file system, + **/ + +int __init cpuset_init(void) +{ + int err = 0; + + if (!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)) + BUG(); + if (!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL)) + BUG(); + + cpumask_setall(top_cpuset.cpus_allowed); + nodes_setall(top_cpuset.mems_allowed); + cpumask_setall(top_cpuset.effective_cpus); + nodes_setall(top_cpuset.effective_mems); + + fmeter_init(&top_cpuset.fmeter); + set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags); + top_cpuset.relax_domain_level = -1; + + err = register_filesystem(&cpuset_fs_type); + if (err < 0) + return err; + + if (!alloc_cpumask_var(&cpus_attach, GFP_KERNEL)) + BUG(); + + return 0; +} + +/* + * If CPU and/or memory hotplug handlers, below, unplug any CPUs + * or memory nodes, we need to walk over the cpuset hierarchy, + * removing that CPU or node from all cpusets. If this removes the + * last CPU or node from a cpuset, then move the tasks in the empty + * cpuset to its next-highest non-empty parent. + */ +static void remove_tasks_in_empty_cpuset(struct cpuset *cs) +{ + struct cpuset *parent; + + /* + * Find its next-highest non-empty parent, (top cpuset + * has online cpus, so can't be empty). + */ + parent = parent_cs(cs); + while (cpumask_empty(parent->cpus_allowed) || + nodes_empty(parent->mems_allowed)) + parent = parent_cs(parent); + + if (cgroup_transfer_tasks(parent->css.cgroup, cs->css.cgroup)) { + pr_err("cpuset: failed to transfer tasks out of empty cpuset "); + pr_cont_cgroup_name(cs->css.cgroup); + pr_cont("\n"); + } +} + +static void +hotplug_update_tasks_legacy(struct cpuset *cs, + struct cpumask *new_cpus, nodemask_t *new_mems, + bool cpus_updated, bool mems_updated) +{ + bool is_empty; + + spin_lock_irq(&callback_lock); + cpumask_copy(cs->cpus_allowed, new_cpus); + cpumask_copy(cs->effective_cpus, new_cpus); + cs->mems_allowed = *new_mems; + cs->effective_mems = *new_mems; + spin_unlock_irq(&callback_lock); + + /* + * Don't call update_tasks_cpumask() if the cpuset becomes empty, + * as the tasks will be migratecd to an ancestor. + */ + if (cpus_updated && !cpumask_empty(cs->cpus_allowed)) + update_tasks_cpumask(cs); + if (mems_updated && !nodes_empty(cs->mems_allowed)) + update_tasks_nodemask(cs); + + is_empty = cpumask_empty(cs->cpus_allowed) || + nodes_empty(cs->mems_allowed); + + mutex_unlock(&cpuset_mutex); + + /* + * Move tasks to the nearest ancestor with execution resources, + * This is full cgroup operation which will also call back into + * cpuset. Should be done outside any lock. + */ + if (is_empty) + remove_tasks_in_empty_cpuset(cs); + + mutex_lock(&cpuset_mutex); +} + +static void +hotplug_update_tasks(struct cpuset *cs, + struct cpumask *new_cpus, nodemask_t *new_mems, + bool cpus_updated, bool mems_updated) +{ + if (cpumask_empty(new_cpus)) + cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus); + if (nodes_empty(*new_mems)) + *new_mems = parent_cs(cs)->effective_mems; + + spin_lock_irq(&callback_lock); + cpumask_copy(cs->effective_cpus, new_cpus); + cs->effective_mems = *new_mems; + spin_unlock_irq(&callback_lock); + + if (cpus_updated) + update_tasks_cpumask(cs); + if (mems_updated) + update_tasks_nodemask(cs); +} + +/** + * cpuset_hotplug_update_tasks - update tasks in a cpuset for hotunplug + * @cs: cpuset in interest + * + * Compare @cs's cpu and mem masks against top_cpuset and if some have gone + * offline, update @cs accordingly. If @cs ends up with no CPU or memory, + * all its tasks are moved to the nearest ancestor with both resources. + */ +static void cpuset_hotplug_update_tasks(struct cpuset *cs) +{ + static cpumask_t new_cpus; + static nodemask_t new_mems; + bool cpus_updated; + bool mems_updated; +retry: + wait_event(cpuset_attach_wq, cs->attach_in_progress == 0); + + mutex_lock(&cpuset_mutex); + + /* + * We have raced with task attaching. We wait until attaching + * is finished, so we won't attach a task to an empty cpuset. + */ + if (cs->attach_in_progress) { + mutex_unlock(&cpuset_mutex); + goto retry; + } + + cpumask_and(&new_cpus, cs->cpus_allowed, parent_cs(cs)->effective_cpus); + nodes_and(new_mems, cs->mems_allowed, parent_cs(cs)->effective_mems); + + cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus); + mems_updated = !nodes_equal(new_mems, cs->effective_mems); + + if (cgroup_on_dfl(cs->css.cgroup)) + hotplug_update_tasks(cs, &new_cpus, &new_mems, + cpus_updated, mems_updated); + else + hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems, + cpus_updated, mems_updated); + + mutex_unlock(&cpuset_mutex); +} + +/** + * cpuset_hotplug_workfn - handle CPU/memory hotunplug for a cpuset + * + * This function is called after either CPU or memory configuration has + * changed and updates cpuset accordingly. The top_cpuset is always + * synchronized to cpu_active_mask and N_MEMORY, which is necessary in + * order to make cpusets transparent (of no affect) on systems that are + * actively using CPU hotplug but making no active use of cpusets. + * + * Non-root cpusets are only affected by offlining. If any CPUs or memory + * nodes have been taken down, cpuset_hotplug_update_tasks() is invoked on + * all descendants. + * + * Note that CPU offlining during suspend is ignored. We don't modify + * cpusets across suspend/resume cycles at all. + */ +static void cpuset_hotplug_workfn(struct work_struct *work) +{ + static cpumask_t new_cpus; + static nodemask_t new_mems; + bool cpus_updated, mems_updated; + bool on_dfl = cgroup_on_dfl(top_cpuset.css.cgroup); + + mutex_lock(&cpuset_mutex); + + /* fetch the available cpus/mems and find out which changed how */ + cpumask_copy(&new_cpus, cpu_active_mask); + new_mems = node_states[N_MEMORY]; + + cpus_updated = !cpumask_equal(top_cpuset.effective_cpus, &new_cpus); + mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems); + + /* synchronize cpus_allowed to cpu_active_mask */ + if (cpus_updated) { + spin_lock_irq(&callback_lock); + if (!on_dfl) + cpumask_copy(top_cpuset.cpus_allowed, &new_cpus); + cpumask_copy(top_cpuset.effective_cpus, &new_cpus); + spin_unlock_irq(&callback_lock); + /* we don't mess with cpumasks of tasks in top_cpuset */ + } + + /* synchronize mems_allowed to N_MEMORY */ + if (mems_updated) { + spin_lock_irq(&callback_lock); + if (!on_dfl) + top_cpuset.mems_allowed = new_mems; + top_cpuset.effective_mems = new_mems; + spin_unlock_irq(&callback_lock); + update_tasks_nodemask(&top_cpuset); + } + + mutex_unlock(&cpuset_mutex); + + /* if cpus or mems changed, we need to propagate to descendants */ + if (cpus_updated || mems_updated) { + struct cpuset *cs; + struct cgroup_subsys_state *pos_css; + + rcu_read_lock(); + cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { + if (cs == &top_cpuset || !css_tryget_online(&cs->css)) + continue; + rcu_read_unlock(); + + cpuset_hotplug_update_tasks(cs); + + rcu_read_lock(); + css_put(&cs->css); + } + rcu_read_unlock(); + } + + /* rebuild sched domains if cpus_allowed has changed */ + if (cpus_updated) + rebuild_sched_domains(); +} + +void cpuset_update_active_cpus(bool cpu_online) +{ + /* + * We're inside cpu hotplug critical region which usually nests + * inside cgroup synchronization. Bounce actual hotplug processing + * to a work item to avoid reverse locking order. + * + * We still need to do partition_sched_domains() synchronously; + * otherwise, the scheduler will get confused and put tasks to the + * dead CPU. Fall back to the default single domain. + * cpuset_hotplug_workfn() will rebuild it as necessary. + */ + partition_sched_domains(1, NULL, NULL); + schedule_work(&cpuset_hotplug_work); +} + +/* + * Keep top_cpuset.mems_allowed tracking node_states[N_MEMORY]. + * Call this routine anytime after node_states[N_MEMORY] changes. + * See cpuset_update_active_cpus() for CPU hotplug handling. + */ +static int cpuset_track_online_nodes(struct notifier_block *self, + unsigned long action, void *arg) +{ + schedule_work(&cpuset_hotplug_work); + return NOTIFY_OK; +} + +static struct notifier_block cpuset_track_online_nodes_nb = { + .notifier_call = cpuset_track_online_nodes, + .priority = 10, /* ??! */ +}; + +/** + * cpuset_init_smp - initialize cpus_allowed + * + * Description: Finish top cpuset after cpu, node maps are initialized + */ +void __init cpuset_init_smp(void) +{ + cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask); + top_cpuset.mems_allowed = node_states[N_MEMORY]; + top_cpuset.old_mems_allowed = top_cpuset.mems_allowed; + + cpumask_copy(top_cpuset.effective_cpus, cpu_active_mask); + top_cpuset.effective_mems = node_states[N_MEMORY]; + + register_hotmemory_notifier(&cpuset_track_online_nodes_nb); +} + +/** + * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset. + * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed. + * @pmask: pointer to struct cpumask variable to receive cpus_allowed set. + * + * Description: Returns the cpumask_var_t cpus_allowed of the cpuset + * attached to the specified @tsk. Guaranteed to return some non-empty + * subset of cpu_online_mask, even if this means going outside the + * tasks cpuset. + **/ + +void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) +{ + unsigned long flags; + + spin_lock_irqsave(&callback_lock, flags); + rcu_read_lock(); + guarantee_online_cpus(task_cs(tsk), pmask); + rcu_read_unlock(); + spin_unlock_irqrestore(&callback_lock, flags); +} + +void cpuset_cpus_allowed_fallback(struct task_struct *tsk) +{ + rcu_read_lock(); + do_set_cpus_allowed(tsk, task_cs(tsk)->effective_cpus); + rcu_read_unlock(); + + /* + * We own tsk->cpus_allowed, nobody can change it under us. + * + * But we used cs && cs->cpus_allowed lockless and thus can + * race with cgroup_attach_task() or update_cpumask() and get + * the wrong tsk->cpus_allowed. However, both cases imply the + * subsequent cpuset_change_cpumask()->set_cpus_allowed_ptr() + * which takes task_rq_lock(). + * + * If we are called after it dropped the lock we must see all + * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary + * set any mask even if it is not right from task_cs() pov, + * the pending set_cpus_allowed_ptr() will fix things. + * + * select_fallback_rq() will fix things ups and set cpu_possible_mask + * if required. + */ +} + +void __init cpuset_init_current_mems_allowed(void) +{ + nodes_setall(current->mems_allowed); +} + +/** + * cpuset_mems_allowed - return mems_allowed mask from a tasks cpuset. + * @tsk: pointer to task_struct from which to obtain cpuset->mems_allowed. + * + * Description: Returns the nodemask_t mems_allowed of the cpuset + * attached to the specified @tsk. Guaranteed to return some non-empty + * subset of node_states[N_MEMORY], even if this means going outside the + * tasks cpuset. + **/ + +nodemask_t cpuset_mems_allowed(struct task_struct *tsk) +{ + nodemask_t mask; + unsigned long flags; + + spin_lock_irqsave(&callback_lock, flags); + rcu_read_lock(); + guarantee_online_mems(task_cs(tsk), &mask); + rcu_read_unlock(); + spin_unlock_irqrestore(&callback_lock, flags); + + return mask; +} + +/** + * cpuset_nodemask_valid_mems_allowed - check nodemask vs. curremt mems_allowed + * @nodemask: the nodemask to be checked + * + * Are any of the nodes in the nodemask allowed in current->mems_allowed? + */ +int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) +{ + return nodes_intersects(*nodemask, current->mems_allowed); +} + +/* + * nearest_hardwall_ancestor() - Returns the nearest mem_exclusive or + * mem_hardwall ancestor to the specified cpuset. Call holding + * callback_lock. If no ancestor is mem_exclusive or mem_hardwall + * (an unusual configuration), then returns the root cpuset. + */ +static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) +{ + while (!(is_mem_exclusive(cs) || is_mem_hardwall(cs)) && parent_cs(cs)) + cs = parent_cs(cs); + return cs; +} + +/** + * cpuset_node_allowed - Can we allocate on a memory node? + * @node: is this an allowed node? + * @gfp_mask: memory allocation flags + * + * If we're in interrupt, yes, we can always allocate. If @node is set in + * current's mems_allowed, yes. If it's not a __GFP_HARDWALL request and this + * node is set in the nearest hardwalled cpuset ancestor to current's cpuset, + * yes. If current has access to memory reserves due to TIF_MEMDIE, yes. + * Otherwise, no. + * + * GFP_USER allocations are marked with the __GFP_HARDWALL bit, + * and do not allow allocations outside the current tasks cpuset + * unless the task has been OOM killed as is marked TIF_MEMDIE. + * GFP_KERNEL allocations are not so marked, so can escape to the + * nearest enclosing hardwalled ancestor cpuset. + * + * Scanning up parent cpusets requires callback_lock. The + * __alloc_pages() routine only calls here with __GFP_HARDWALL bit + * _not_ set if it's a GFP_KERNEL allocation, and all nodes in the + * current tasks mems_allowed came up empty on the first pass over + * the zonelist. So only GFP_KERNEL allocations, if all nodes in the + * cpuset are short of memory, might require taking the callback_lock. + * + * The first call here from mm/page_alloc:get_page_from_freelist() + * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets, + * so no allocation on a node outside the cpuset is allowed (unless + * in interrupt, of course). + * + * The second pass through get_page_from_freelist() doesn't even call + * here for GFP_ATOMIC calls. For those calls, the __alloc_pages() + * variable 'wait' is not set, and the bit ALLOC_CPUSET is not set + * in alloc_flags. That logic and the checks below have the combined + * affect that: + * in_interrupt - any node ok (current task context irrelevant) + * GFP_ATOMIC - any node ok + * TIF_MEMDIE - any node ok + * GFP_KERNEL - any node in enclosing hardwalled cpuset ok + * GFP_USER - only nodes in current tasks mems allowed ok. + */ +int __cpuset_node_allowed(int node, gfp_t gfp_mask) +{ + struct cpuset *cs; /* current cpuset ancestors */ + int allowed; /* is allocation in zone z allowed? */ + unsigned long flags; + + if (in_interrupt()) + return 1; + if (node_isset(node, current->mems_allowed)) + return 1; + /* + * Allow tasks that have access to memory reserves because they have + * been OOM killed to get memory anywhere. + */ + if (unlikely(test_thread_flag(TIF_MEMDIE))) + return 1; + if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */ + return 0; + + if (current->flags & PF_EXITING) /* Let dying task have memory */ + return 1; + + /* Not hardwall and node outside mems_allowed: scan up cpusets */ + spin_lock_irqsave(&callback_lock, flags); + + rcu_read_lock(); + cs = nearest_hardwall_ancestor(task_cs(current)); + allowed = node_isset(node, cs->mems_allowed); + rcu_read_unlock(); + + spin_unlock_irqrestore(&callback_lock, flags); + return allowed; +} + +/** + * cpuset_mem_spread_node() - On which node to begin search for a file page + * cpuset_slab_spread_node() - On which node to begin search for a slab page + * + * If a task is marked PF_SPREAD_PAGE or PF_SPREAD_SLAB (as for + * tasks in a cpuset with is_spread_page or is_spread_slab set), + * and if the memory allocation used cpuset_mem_spread_node() + * to determine on which node to start looking, as it will for + * certain page cache or slab cache pages such as used for file + * system buffers and inode caches, then instead of starting on the + * local node to look for a free page, rather spread the starting + * node around the tasks mems_allowed nodes. + * + * We don't have to worry about the returned node being offline + * because "it can't happen", and even if it did, it would be ok. + * + * The routines calling guarantee_online_mems() are careful to + * only set nodes in task->mems_allowed that are online. So it + * should not be possible for the following code to return an + * offline node. But if it did, that would be ok, as this routine + * is not returning the node where the allocation must be, only + * the node where the search should start. The zonelist passed to + * __alloc_pages() will include all nodes. If the slab allocator + * is passed an offline node, it will fall back to the local node. + * See kmem_cache_alloc_node(). + */ + +static int cpuset_spread_node(int *rotor) +{ + int node; + + node = next_node(*rotor, current->mems_allowed); + if (node == MAX_NUMNODES) + node = first_node(current->mems_allowed); + *rotor = node; + return node; +} + +int cpuset_mem_spread_node(void) +{ + if (current->cpuset_mem_spread_rotor == NUMA_NO_NODE) + current->cpuset_mem_spread_rotor = + node_random(¤t->mems_allowed); + + return cpuset_spread_node(¤t->cpuset_mem_spread_rotor); +} + +int cpuset_slab_spread_node(void) +{ + if (current->cpuset_slab_spread_rotor == NUMA_NO_NODE) + current->cpuset_slab_spread_rotor = + node_random(¤t->mems_allowed); + + return cpuset_spread_node(¤t->cpuset_slab_spread_rotor); +} + +EXPORT_SYMBOL_GPL(cpuset_mem_spread_node); + +/** + * cpuset_mems_allowed_intersects - Does @tsk1's mems_allowed intersect @tsk2's? + * @tsk1: pointer to task_struct of some task. + * @tsk2: pointer to task_struct of some other task. + * + * Description: Return true if @tsk1's mems_allowed intersects the + * mems_allowed of @tsk2. Used by the OOM killer to determine if + * one of the task's memory usage might impact the memory available + * to the other. + **/ + +int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, + const struct task_struct *tsk2) +{ + return nodes_intersects(tsk1->mems_allowed, tsk2->mems_allowed); +} + +/** + * cpuset_print_task_mems_allowed - prints task's cpuset and mems_allowed + * @tsk: pointer to task_struct of some task. + * + * Description: Prints @task's name, cpuset name, and cached copy of its + * mems_allowed to the kernel log. + */ +void cpuset_print_task_mems_allowed(struct task_struct *tsk) +{ + struct cgroup *cgrp; + + rcu_read_lock(); + + cgrp = task_cs(tsk)->css.cgroup; + pr_info("%s cpuset=", tsk->comm); + pr_cont_cgroup_name(cgrp); + pr_cont(" mems_allowed=%*pbl\n", nodemask_pr_args(&tsk->mems_allowed)); + + rcu_read_unlock(); +} + +/* + * Collection of memory_pressure is suppressed unless + * this flag is enabled by writing "1" to the special + * cpuset file 'memory_pressure_enabled' in the root cpuset. + */ + +int cpuset_memory_pressure_enabled __read_mostly; + +/** + * cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims. + * + * Keep a running average of the rate of synchronous (direct) + * page reclaim efforts initiated by tasks in each cpuset. + * + * This represents the rate at which some task in the cpuset + * ran low on memory on all nodes it was allowed to use, and + * had to enter the kernels page reclaim code in an effort to + * create more free memory by tossing clean pages or swapping + * or writing dirty pages. + * + * Display to user space in the per-cpuset read-only file + * "memory_pressure". Value displayed is an integer + * representing the recent rate of entry into the synchronous + * (direct) page reclaim by any task attached to the cpuset. + **/ + +void __cpuset_memory_pressure_bump(void) +{ + rcu_read_lock(); + fmeter_markevent(&task_cs(current)->fmeter); + rcu_read_unlock(); +} + +#ifdef CONFIG_PROC_PID_CPUSET +/* + * proc_cpuset_show() + * - Print tasks cpuset path into seq_file. + * - Used for /proc/<pid>/cpuset. + * - No need to task_lock(tsk) on this tsk->cpuset reference, as it + * doesn't really matter if tsk->cpuset changes after we read it, + * and we take cpuset_mutex, keeping cpuset_attach() from changing it + * anyway. + */ +int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *tsk) +{ + char *buf, *p; + struct cgroup_subsys_state *css; + int retval; + + retval = -ENOMEM; + buf = kmalloc(PATH_MAX, GFP_KERNEL); + if (!buf) + goto out; + + retval = -ENAMETOOLONG; + rcu_read_lock(); + css = task_css(tsk, cpuset_cgrp_id); + p = cgroup_path(css->cgroup, buf, PATH_MAX); + rcu_read_unlock(); + if (!p) + goto out_free; + seq_puts(m, p); + seq_putc(m, '\n'); + retval = 0; +out_free: + kfree(buf); +out: + return retval; +} +#endif /* CONFIG_PROC_PID_CPUSET */ + +/* Display task mems_allowed in /proc/<pid>/status file. */ +void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) +{ + seq_printf(m, "Mems_allowed:\t%*pb\n", + nodemask_pr_args(&task->mems_allowed)); + seq_printf(m, "Mems_allowed_list:\t%*pbl\n", + nodemask_pr_args(&task->mems_allowed)); +} |