* The hooks from fork and exit, cpuset_fork() and cpuset_exit(), don't
* (usually) grab cpuset_sem. These are the two most performance
* critical pieces of code here. The exception occurs on exit(),
- * if the last task using a cpuset exits, and the cpuset was marked
- * notify_on_release. In that case, the cpuset_sem is taken, the
- * path to the released cpuset calculated, and a usermode call made
+ * when a task in a notify_on_release cpuset exits. Then cpuset_sem
+ * is taken, and if the cpuset count is zero, a usermode call made
* to /sbin/cpuset_release_agent with the name of the cpuset (path
* relative to the root of cpuset file system) as the argument.
*
static struct dentry *cpuset_get_dentry(struct dentry *parent, const char *name)
{
- struct qstr qstr;
- struct dentry *d;
-
- qstr.name = name;
- qstr.len = strlen(name);
- qstr.hash = full_name_hash(name, qstr.len);
- d = lookup_hash(&qstr, parent);
+ struct dentry *d = lookup_one_len(name, parent, strlen(name));
if (!IS_ERR(d))
d->d_op = &cpuset_dops;
return d;
return 0;
}
+/*
+ * For a given cpuset cur, partition the system as follows
+ * a. All cpus in the parent cpuset's cpus_allowed that are not part of any
+ * exclusive child cpusets
+ * b. All cpus in the current cpuset's cpus_allowed that are not part of any
+ * exclusive child cpusets
+ * Build these two partitions by calling partition_sched_domains
+ *
+ * Call with cpuset_sem held. May nest a call to the
+ * lock_cpu_hotplug()/unlock_cpu_hotplug() pair.
+ */
+static void update_cpu_domains(struct cpuset *cur)
+{
+ struct cpuset *c, *par = cur->parent;
+ cpumask_t pspan, cspan;
+
+ if (par == NULL || cpus_empty(cur->cpus_allowed))
+ return;
+
+ /*
+ * Get all cpus from parent's cpus_allowed not part of exclusive
+ * children
+ */
+ pspan = par->cpus_allowed;
+ list_for_each_entry(c, &par->children, sibling) {
+ if (is_cpu_exclusive(c))
+ cpus_andnot(pspan, pspan, c->cpus_allowed);
+ }
+ if (is_removed(cur) || !is_cpu_exclusive(cur)) {
+ cpus_or(pspan, pspan, cur->cpus_allowed);
+ if (cpus_equal(pspan, cur->cpus_allowed))
+ return;
+ cspan = CPU_MASK_NONE;
+ } else {
+ if (cpus_empty(pspan))
+ return;
+ cspan = cur->cpus_allowed;
+ /*
+ * Get all cpus from current cpuset's cpus_allowed not part
+ * of exclusive children
+ */
+ list_for_each_entry(c, &cur->children, sibling) {
+ if (is_cpu_exclusive(c))
+ cpus_andnot(cspan, cspan, c->cpus_allowed);
+ }
+ }
+
+ lock_cpu_hotplug();
+ partition_sched_domains(&pspan, &cspan);
+ unlock_cpu_hotplug();
+}
+
static int update_cpumask(struct cpuset *cs, char *buf)
{
struct cpuset trialcs;
- int retval;
+ int retval, cpus_unchanged;
trialcs = *cs;
retval = cpulist_parse(buf, trialcs.cpus_allowed);
if (cpus_empty(trialcs.cpus_allowed))
return -ENOSPC;
retval = validate_change(cs, &trialcs);
- if (retval == 0)
- cs->cpus_allowed = trialcs.cpus_allowed;
- return retval;
+ if (retval < 0)
+ return retval;
+ cpus_unchanged = cpus_equal(cs->cpus_allowed, trialcs.cpus_allowed);
+ cs->cpus_allowed = trialcs.cpus_allowed;
+ if (is_cpu_exclusive(cs) && !cpus_unchanged)
+ update_cpu_domains(cs);
+ return 0;
}
static int update_nodemask(struct cpuset *cs, char *buf)
{
int turning_on;
struct cpuset trialcs;
- int err;
+ int err, cpu_exclusive_changed;
turning_on = (simple_strtoul(buf, NULL, 10) != 0);
clear_bit(bit, &trialcs.flags);
err = validate_change(cs, &trialcs);
- if (err == 0) {
- if (turning_on)
- set_bit(bit, &cs->flags);
- else
- clear_bit(bit, &cs->flags);
- }
- return err;
+ if (err < 0)
+ return err;
+ cpu_exclusive_changed =
+ (is_cpu_exclusive(cs) != is_cpu_exclusive(&trialcs));
+ if (turning_on)
+ set_bit(bit, &cs->flags);
+ else
+ clear_bit(bit, &cs->flags);
+
+ if (cpu_exclusive_changed)
+ update_cpu_domains(cs);
+ return 0;
}
static int attach_task(struct cpuset *cs, char *buf)
up(&cpuset_sem);
return -EBUSY;
}
- spin_lock(&cs->dentry->d_lock);
parent = cs->parent;
set_bit(CS_REMOVED, &cs->flags);
+ if (is_cpu_exclusive(cs))
+ update_cpu_domains(cs);
list_del(&cs->sibling); /* delete my sibling from parent->children */
if (list_empty(&parent->children))
check_for_release(parent);
+ spin_lock(&cs->dentry->d_lock);
d = dget(cs->dentry);
cs->dentry = NULL;
spin_unlock(&d->d_lock);
*
* Description: Detach cpuset from @tsk and release it.
*
+ * Note that cpusets marked notify_on_release force every task
+ * in them to take the global cpuset_sem semaphore when exiting.
+ * This could impact scaling on very large systems. Be reluctant
+ * to use notify_on_release cpusets where very high task exit
+ * scaling is required on large systems.
+ *
+ * Don't even think about derefencing 'cs' after the cpuset use
+ * count goes to zero, except inside a critical section guarded
+ * by the cpuset_sem semaphore. If you don't hold cpuset_sem,
+ * then a zero cpuset use count is a license to any other task to
+ * nuke the cpuset immediately.
+ *
**/
void cpuset_exit(struct task_struct *tsk)
tsk->cpuset = NULL;
task_unlock(tsk);
- if (atomic_dec_and_test(&cs->count)) {
+ if (notify_on_release(cs)) {
down(&cpuset_sem);
- check_for_release(cs);
+ if (atomic_dec_and_test(&cs->count))
+ check_for_release(cs);
up(&cpuset_sem);
+ } else {
+ atomic_dec(&cs->count);
}
}
* tasks cpuset.
**/
-const cpumask_t cpuset_cpus_allowed(const struct task_struct *tsk)
+cpumask_t cpuset_cpus_allowed(const struct task_struct *tsk)
{
cpumask_t mask;
projects / linux-2.6 / blobdiff