* Processor and Memory placement constraints for sets of tasks.
*
* Copyright (C) 2003 BULL SA.
- * Copyright (C) 2004-2006 Silicon Graphics, Inc.
+ * Copyright (C) 2004-2007 Silicon Graphics, Inc.
* Copyright (C) 2006 Google, Inc
*
* Portions derived from Patrick Mochel's sysfs code.
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/pagemap.h>
+#include <linux/prio_heap.h>
#include <linux/proc_fs.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <asm/uaccess.h>
#include <asm/atomic.h>
#include <linux/mutex.h>
+#include <linux/kfifo.h>
/*
* Tracks how many cpusets are currently defined in system.
int mems_generation;
struct fmeter fmeter; /* memory_pressure filter */
+
+ /* partition number for rebuild_sched_domains() */
+ int pn;
};
/* Retrieve the cpuset for a cgroup */
CS_CPU_EXCLUSIVE,
CS_MEM_EXCLUSIVE,
CS_MEMORY_MIGRATE,
+ CS_SCHED_LOAD_BALANCE,
CS_SPREAD_PAGE,
CS_SPREAD_SLAB,
} cpuset_flagbits_t;
return test_bit(CS_MEM_EXCLUSIVE, &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);
return -EINVAL;
}
+ /* Cpusets with tasks can't have empty cpus_allowed or mems_allowed */
+ if (cgroup_task_count(cur->css.cgroup)) {
+ if (cpus_empty(trial->cpus_allowed) ||
+ nodes_empty(trial->mems_allowed)) {
+ return -ENOSPC;
+ }
+ }
+
return 0;
}
+/*
+ * Helper routine for rebuild_sched_domains().
+ * Do cpusets a, b have overlapping cpus_allowed masks?
+ */
+
+static int cpusets_overlap(struct cpuset *a, struct cpuset *b)
+{
+ return cpus_intersects(a->cpus_allowed, b->cpus_allowed);
+}
+
+/*
+ * rebuild_sched_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.
+ *
+ * This routine builds a partial partition of the systems CPUs
+ * (the set of non-overlappping cpumask_t's in the array 'part'
+ * below), and passes that partial partition to the kernel/sched.c
+ * partition_sched_domains() routine, which will rebuild the
+ * schedulers load balancing domains (sched domains) as specified
+ * by that partial partition. A 'partial partition' is a set of
+ * non-overlapping subsets whose union is a subset of that set.
+ *
+ * See "What is sched_load_balance" in Documentation/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.
+ *
+ * Call with cgroup_mutex held. May take callback_mutex during
+ * call due to the kfifo_alloc() and kmalloc() calls. May nest
+ * a call to the lock_cpu_hotplug()/unlock_cpu_hotplug() pair.
+ * Must not be called holding callback_mutex, because we must not
+ * call lock_cpu_hotplug() while holding callback_mutex. Elsewhere
+ * the kernel nests callback_mutex inside lock_cpu_hotplug() calls.
+ * So the reverse nesting would risk an ABBA deadlock.
+ *
+ * The three key local variables below are:
+ * q - a kfifo 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.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 void rebuild_sched_domains(void)
+{
+ struct kfifo *q; /* queue of cpusets to be scanned */
+ 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_t *doms; /* resulting partition; i.e. sched domains */
+ int ndoms; /* number of sched domains in result */
+ int nslot; /* next empty doms[] cpumask_t slot */
+
+ q = NULL;
+ csa = NULL;
+ doms = NULL;
+
+ /* Special case for the 99% of systems with one, full, sched domain */
+ if (is_sched_load_balance(&top_cpuset)) {
+ ndoms = 1;
+ doms = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
+ if (!doms)
+ goto rebuild;
+ *doms = top_cpuset.cpus_allowed;
+ goto rebuild;
+ }
+
+ q = kfifo_alloc(number_of_cpusets * sizeof(cp), GFP_KERNEL, NULL);
+ if (IS_ERR(q))
+ goto done;
+ csa = kmalloc(number_of_cpusets * sizeof(cp), GFP_KERNEL);
+ if (!csa)
+ goto done;
+ csn = 0;
+
+ cp = &top_cpuset;
+ __kfifo_put(q, (void *)&cp, sizeof(cp));
+ while (__kfifo_get(q, (void *)&cp, sizeof(cp))) {
+ struct cgroup *cont;
+ struct cpuset *child; /* scans child cpusets of cp */
+ if (is_sched_load_balance(cp))
+ csa[csn++] = cp;
+ list_for_each_entry(cont, &cp->css.cgroup->children, sibling) {
+ child = cgroup_cs(cont);
+ __kfifo_put(q, (void *)&child, sizeof(cp));
+ }
+ }
+
+ 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;
+ }
+ }
+ }
+
+ /* Convert <csn, csa> to <ndoms, doms> */
+ doms = kmalloc(ndoms * sizeof(cpumask_t), GFP_KERNEL);
+ if (!doms)
+ goto rebuild;
+
+ for (nslot = 0, i = 0; i < csn; i++) {
+ struct cpuset *a = csa[i];
+ int apn = a->pn;
+
+ if (apn >= 0) {
+ cpumask_t *dp = doms + nslot;
+
+ if (nslot == ndoms) {
+ static int warnings = 10;
+ if (warnings) {
+ printk(KERN_WARNING
+ "rebuild_sched_domains confused:"
+ " nslot %d, ndoms %d, csn %d, i %d,"
+ " apn %d\n",
+ nslot, ndoms, csn, i, apn);
+ warnings--;
+ }
+ continue;
+ }
+
+ cpus_clear(*dp);
+ for (j = i; j < csn; j++) {
+ struct cpuset *b = csa[j];
+
+ if (apn == b->pn) {
+ cpus_or(*dp, *dp, b->cpus_allowed);
+ b->pn = -1;
+ }
+ }
+ nslot++;
+ }
+ }
+ BUG_ON(nslot != ndoms);
+
+rebuild:
+ /* Have scheduler rebuild sched domains */
+ lock_cpu_hotplug();
+ partition_sched_domains(ndoms, doms);
+ unlock_cpu_hotplug();
+
+done:
+ if (q && !IS_ERR(q))
+ kfifo_free(q);
+ kfree(csa);
+ /* Don't kfree(doms) -- partition_sched_domains() does that. */
+}
+
+static inline int started_after_time(struct task_struct *t1,
+ struct timespec *time,
+ struct task_struct *t2)
+{
+ int start_diff = timespec_compare(&t1->start_time, time);
+ if (start_diff > 0) {
+ return 1;
+ } else if (start_diff < 0) {
+ return 0;
+ } else {
+ /*
+ * Arbitrarily, if two processes started at the same
+ * time, we'll say that the lower pointer value
+ * started first. Note that t2 may have exited by now
+ * so this may not be a valid pointer any longer, but
+ * that's fine - it still serves to distinguish
+ * between two tasks started (effectively)
+ * simultaneously.
+ */
+ return t1 > t2;
+ }
+}
+
+static inline int started_after(void *p1, void *p2)
+{
+ struct task_struct *t1 = p1;
+ struct task_struct *t2 = p2;
+ return started_after_time(t1, &t2->start_time, t2);
+}
+
/*
* Call with manage_mutex held. May take callback_mutex during call.
*/
static int update_cpumask(struct cpuset *cs, char *buf)
{
struct cpuset trialcs;
- int retval;
+ int retval, i;
+ int is_load_balanced;
+ struct cgroup_iter it;
+ struct cgroup *cgrp = cs->css.cgroup;
+ struct task_struct *p, *dropped;
+ /* Never dereference latest_task, since it's not refcounted */
+ struct task_struct *latest_task = NULL;
+ struct ptr_heap heap;
+ struct timespec latest_time = { 0, 0 };
/* top_cpuset.cpus_allowed tracks cpu_online_map; it's read-only */
if (cs == &top_cpuset)
trialcs = *cs;
/*
- * We allow a cpuset's cpus_allowed to be empty; if it has attached
- * tasks, we'll catch it later when we validate the change and return
- * -ENOSPC.
+ * An empty cpus_allowed is ok iff there are no tasks in the cpuset.
+ * 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[0] || (buf[0] == '\n' && !buf[1])) {
+ buf = strstrip(buf);
+ if (!*buf) {
cpus_clear(trialcs.cpus_allowed);
} else {
retval = cpulist_parse(buf, trialcs.cpus_allowed);
return retval;
}
cpus_and(trialcs.cpus_allowed, trialcs.cpus_allowed, cpu_online_map);
- /* cpus_allowed cannot be empty for a cpuset with attached tasks. */
- if (cgroup_task_count(cs->css.cgroup) &&
- cpus_empty(trialcs.cpus_allowed))
- return -ENOSPC;
retval = validate_change(cs, &trialcs);
if (retval < 0)
return retval;
+
+ /* Nothing to do if the cpus didn't change */
+ if (cpus_equal(cs->cpus_allowed, trialcs.cpus_allowed))
+ return 0;
+ retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, &started_after);
+ if (retval)
+ return retval;
+
+ is_load_balanced = is_sched_load_balance(&trialcs);
+
mutex_lock(&callback_mutex);
cs->cpus_allowed = trialcs.cpus_allowed;
mutex_unlock(&callback_mutex);
+
+ again:
+ /*
+ * Scan tasks in the cpuset, and update the cpumasks of any
+ * that need an update. Since we can't call set_cpus_allowed()
+ * while holding tasklist_lock, gather tasks to be processed
+ * in a heap structure. If the statically-sized heap fills up,
+ * overflow tasks that started later, and in future iterations
+ * only consider tasks that started after the latest task in
+ * the previous pass. This guarantees forward progress and
+ * that we don't miss any tasks
+ */
+ heap.size = 0;
+ cgroup_iter_start(cgrp, &it);
+ while ((p = cgroup_iter_next(cgrp, &it))) {
+ /* Only affect tasks that don't have the right cpus_allowed */
+ if (cpus_equal(p->cpus_allowed, cs->cpus_allowed))
+ continue;
+ /*
+ * Only process tasks that started after the last task
+ * we processed
+ */
+ if (!started_after_time(p, &latest_time, latest_task))
+ continue;
+ dropped = heap_insert(&heap, p);
+ if (dropped == NULL) {
+ get_task_struct(p);
+ } else if (dropped != p) {
+ get_task_struct(p);
+ put_task_struct(dropped);
+ }
+ }
+ cgroup_iter_end(cgrp, &it);
+ if (heap.size) {
+ for (i = 0; i < heap.size; i++) {
+ struct task_struct *p = heap.ptrs[i];
+ if (i == 0) {
+ latest_time = p->start_time;
+ latest_task = p;
+ }
+ set_cpus_allowed(p, cs->cpus_allowed);
+ put_task_struct(p);
+ }
+ /*
+ * If we had to process any tasks at all, scan again
+ * in case some of them were in the middle of forking
+ * children that didn't notice the new cpumask
+ * restriction. Not the most efficient way to do it,
+ * but it avoids having to take callback_mutex in the
+ * fork path
+ */
+ goto again;
+ }
+ heap_free(&heap);
+ if (is_load_balanced)
+ rebuild_sched_domains();
+
return 0;
}
trialcs = *cs;
/*
- * We allow a cpuset's mems_allowed to be empty; if it has attached
- * tasks, we'll catch it later when we validate the change and return
- * -ENOSPC.
+ * 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[0] || (buf[0] == '\n' && !buf[1])) {
+ buf = strstrip(buf);
+ if (!*buf) {
nodes_clear(trialcs.mems_allowed);
} else {
retval = nodelist_parse(buf, trialcs.mems_allowed);
if (retval < 0)
goto done;
- if (!nodes_intersects(trialcs.mems_allowed,
- node_states[N_HIGH_MEMORY])) {
- /*
- * error if only memoryless nodes specified.
- */
- retval = -ENOSPC;
- goto done;
- }
}
- /*
- * Exclude memoryless nodes. We know that trialcs.mems_allowed
- * contains at least one node with memory.
- */
nodes_and(trialcs.mems_allowed, trialcs.mems_allowed,
node_states[N_HIGH_MEMORY]);
oldmem = cs->mems_allowed;
retval = 0; /* Too easy - nothing to do */
goto done;
}
- /* mems_allowed cannot be empty for a cpuset with attached tasks. */
- if (cgroup_task_count(cs->css.cgroup) &&
- nodes_empty(trialcs.mems_allowed)) {
- retval = -ENOSPC;
- goto done;
- }
retval = validate_change(cs, &trialcs);
if (retval < 0)
goto done;
/*
* update_flag - read a 0 or a 1 in a file and update associated flag
* bit: the bit to update (CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE,
+ * CS_SCHED_LOAD_BALANCE,
* CS_NOTIFY_ON_RELEASE, CS_MEMORY_MIGRATE,
* CS_SPREAD_PAGE, CS_SPREAD_SLAB)
* cs: the cpuset to update
int turning_on;
struct cpuset trialcs;
int err;
+ int cpus_nonempty, balance_flag_changed;
turning_on = (simple_strtoul(buf, NULL, 10) != 0);
err = validate_change(cs, &trialcs);
if (err < 0)
return err;
+
+ cpus_nonempty = !cpus_empty(trialcs.cpus_allowed);
+ balance_flag_changed = (is_sched_load_balance(cs) !=
+ is_sched_load_balance(&trialcs));
+
mutex_lock(&callback_mutex);
cs->flags = trialcs.flags;
mutex_unlock(&callback_mutex);
+ if (cpus_nonempty && balance_flag_changed)
+ rebuild_sched_domains();
+
return 0;
}
FILE_MEMLIST,
FILE_CPU_EXCLUSIVE,
FILE_MEM_EXCLUSIVE,
+ FILE_SCHED_LOAD_BALANCE,
FILE_MEMORY_PRESSURE_ENABLED,
FILE_MEMORY_PRESSURE,
FILE_SPREAD_PAGE,
int retval = 0;
/* Crude upper limit on largest legitimate cpulist user might write. */
- if (nbytes > 100 + 6 * max(NR_CPUS, MAX_NUMNODES))
+ if (nbytes > 100U + 6 * max(NR_CPUS, MAX_NUMNODES))
return -E2BIG;
/* +1 for nul-terminator */
case FILE_MEM_EXCLUSIVE:
retval = update_flag(CS_MEM_EXCLUSIVE, cs, buffer);
break;
+ case FILE_SCHED_LOAD_BALANCE:
+ retval = update_flag(CS_SCHED_LOAD_BALANCE, cs, buffer);
+ break;
case FILE_MEMORY_MIGRATE:
retval = update_flag(CS_MEMORY_MIGRATE, cs, buffer);
break;
case FILE_MEM_EXCLUSIVE:
*s++ = is_mem_exclusive(cs) ? '1' : '0';
break;
+ case FILE_SCHED_LOAD_BALANCE:
+ *s++ = is_sched_load_balance(cs) ? '1' : '0';
+ break;
case FILE_MEMORY_MIGRATE:
*s++ = is_memory_migrate(cs) ? '1' : '0';
break;
.private = FILE_MEM_EXCLUSIVE,
};
+static struct cftype cft_sched_load_balance = {
+ .name = "sched_load_balance",
+ .read = cpuset_common_file_read,
+ .write = cpuset_common_file_write,
+ .private = FILE_SCHED_LOAD_BALANCE,
+};
+
static struct cftype cft_memory_migrate = {
.name = "memory_migrate",
.read = cpuset_common_file_read,
return err;
if ((err = cgroup_add_file(cont, ss, &cft_memory_migrate)) < 0)
return err;
+ if ((err = cgroup_add_file(cont, ss, &cft_sched_load_balance)) < 0)
+ return err;
if ((err = cgroup_add_file(cont, ss, &cft_memory_pressure)) < 0)
return err;
if ((err = cgroup_add_file(cont, ss, &cft_spread_page)) < 0)
set_bit(CS_SPREAD_PAGE, &cs->flags);
if (is_spread_slab(parent))
set_bit(CS_SPREAD_SLAB, &cs->flags);
+ set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
cs->cpus_allowed = CPU_MASK_NONE;
cs->mems_allowed = NODE_MASK_NONE;
cs->mems_generation = cpuset_mems_generation++;
return &cs->css ;
}
+/*
+ * Locking note on the strange update_flag() call below:
+ *
+ * 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(). The lock_cpu_hotplug()
+ * call in rebuild_sched_domains() must not be made while holding
+ * callback_mutex. Elsewhere the kernel nests callback_mutex inside
+ * lock_cpu_hotplug() calls. So the reverse nesting would risk an
+ * ABBA deadlock.
+ */
+
static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
{
struct cpuset *cs = cgroup_cs(cont);
cpuset_update_task_memory_state();
+
+ if (is_sched_load_balance(cs))
+ update_flag(CS_SCHED_LOAD_BALANCE, cs, "0");
+
number_of_cpusets--;
kfree(cs);
}
fmeter_init(&top_cpuset.fmeter);
top_cpuset.mems_generation = cpuset_mems_generation++;
+ set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags);
err = register_filesystem(&cpuset_fs_type);
if (err < 0)
* cpu_online_map on each CPU hotplug (cpuhp) event.
*/
-static int cpuset_handle_cpuhp(struct notifier_block *nb,
- unsigned long phase, void *cpu)
+static int cpuset_handle_cpuhp(struct notifier_block *unused_nb,
+ unsigned long phase, void *unused_cpu)
{
if (phase == CPU_DYING || phase == CPU_DYING_FROZEN)
return NOTIFY_DONE;
cpumask_t mask;
mutex_lock(&callback_mutex);
+ mask = cpuset_cpus_allowed_locked(tsk);
+ mutex_unlock(&callback_mutex);
+
+ return mask;
+}
+
+/**
+ * cpuset_cpus_allowed_locked - return cpus_allowed mask from a tasks cpuset.
+ * Must be called with callback_mutex held.
+ **/
+cpumask_t cpuset_cpus_allowed_locked(struct task_struct *tsk)
+{
+ cpumask_t mask;
+
task_lock(tsk);
guarantee_online_cpus(task_cs(tsk), &mask);
task_unlock(tsk);
- mutex_unlock(&callback_mutex);
return mask;
}
* the_top_cpuset_hack in cpuset_exit(), which sets an exiting tasks
* cpuset to top_cpuset.
*/
-static int proc_cpuset_show(struct seq_file *m, void *v)
+static int proc_cpuset_show(struct seq_file *m, void *unused_v)
{
struct pid *pid;
struct task_struct *tsk;