linux/kernel/kthread.c
Linus Torvalds 46d9be3e5e Merge branch 'for-3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq
Pull workqueue updates from Tejun Heo:
 "A lot of activities on workqueue side this time.  The changes achieve
  the followings.

   - WQ_UNBOUND workqueues - the workqueues which are per-cpu - are
     updated to be able to interface with multiple backend worker pools.
     This involved a lot of churning but the end result seems actually
     neater as unbound workqueues are now a lot closer to per-cpu ones.

   - The ability to interface with multiple backend worker pools are
     used to implement unbound workqueues with custom attributes.
     Currently the supported attributes are the nice level and CPU
     affinity.  It may be expanded to include cgroup association in
     future.  The attributes can be specified either by calling
     apply_workqueue_attrs() or through /sys/bus/workqueue/WQ_NAME/* if
     the workqueue in question is exported through sysfs.

     The backend worker pools are keyed by the actual attributes and
     shared by any workqueues which share the same attributes.  When
     attributes of a workqueue are changed, the workqueue binds to the
     worker pool with the specified attributes while leaving the work
     items which are already executing in its previous worker pools
     alone.

     This allows converting custom worker pool implementations which
     want worker attribute tuning to use workqueues.  The writeback pool
     is already converted in block tree and there are a couple others
     are likely to follow including btrfs io workers.

   - WQ_UNBOUND's ability to bind to multiple worker pools is also used
     to make it NUMA-aware.  Because there's no association between work
     item issuer and the specific worker assigned to execute it, before
     this change, using unbound workqueue led to unnecessary cross-node
     bouncing and it couldn't be helped by autonuma as it requires tasks
     to have implicit node affinity and workers are assigned randomly.

     After these changes, an unbound workqueue now binds to multiple
     NUMA-affine worker pools so that queued work items are executed in
     the same node.  This is turned on by default but can be disabled
     system-wide or for individual workqueues.

     Crypto was requesting NUMA affinity as encrypting data across
     different nodes can contribute noticeable overhead and doing it
     per-cpu was too limiting for certain cases and IO throughput could
     be bottlenecked by one CPU being fully occupied while others have
     idle cycles.

  While the new features required a lot of changes including
  restructuring locking, it didn't complicate the execution paths much.
  The unbound workqueue handling is now closer to per-cpu ones and the
  new features are implemented by simply associating a workqueue with
  different sets of backend worker pools without changing queue,
  execution or flush paths.

  As such, even though the amount of change is very high, I feel
  relatively safe in that it isn't likely to cause subtle issues with
  basic correctness of work item execution and handling.  If something
  is wrong, it's likely to show up as being associated with worker pools
  with the wrong attributes or OOPS while workqueue attributes are being
  changed or during CPU hotplug.

  While this creates more backend worker pools, it doesn't add too many
  more workers unless, of course, there are many workqueues with unique
  combinations of attributes.  Assuming everything else is the same,
  NUMA awareness costs an extra worker pool per NUMA node with online
  CPUs.

  There are also a couple things which are being routed outside the
  workqueue tree.

   - block tree pulled in workqueue for-3.10 so that writeback worker
     pool can be converted to unbound workqueue with sysfs control
     exposed.  This simplifies the code, makes writeback workers
     NUMA-aware and allows tuning nice level and CPU affinity via sysfs.

   - The conversion to workqueue means that there's no 1:1 association
     between a specific worker, which makes writeback folks unhappy as
     they want to be able to tell which filesystem caused a problem from
     backtrace on systems with many filesystems mounted.  This is
     resolved by allowing work items to set debug info string which is
     printed when the task is dumped.  As this change involves unifying
     implementations of dump_stack() and friends in arch codes, it's
     being routed through Andrew's -mm tree."

* 'for-3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq: (84 commits)
  workqueue: use kmem_cache_free() instead of kfree()
  workqueue: avoid false negative WARN_ON() in destroy_workqueue()
  workqueue: update sysfs interface to reflect NUMA awareness and a kernel param to disable NUMA affinity
  workqueue: implement NUMA affinity for unbound workqueues
  workqueue: introduce put_pwq_unlocked()
  workqueue: introduce numa_pwq_tbl_install()
  workqueue: use NUMA-aware allocation for pool_workqueues
  workqueue: break init_and_link_pwq() into two functions and introduce alloc_unbound_pwq()
  workqueue: map an unbound workqueues to multiple per-node pool_workqueues
  workqueue: move hot fields of workqueue_struct to the end
  workqueue: make workqueue->name[] fixed len
  workqueue: add workqueue->unbound_attrs
  workqueue: determine NUMA node of workers accourding to the allowed cpumask
  workqueue: drop 'H' from kworker names of unbound worker pools
  workqueue: add wq_numa_tbl_len and wq_numa_possible_cpumask[]
  workqueue: move pwq_pool_locking outside of get/put_unbound_pool()
  workqueue: fix memory leak in apply_workqueue_attrs()
  workqueue: fix unbound workqueue attrs hashing / comparison
  workqueue: fix race condition in unbound workqueue free path
  workqueue: remove pwq_lock which is no longer used
  ...
2013-04-29 19:07:40 -07:00

637 lines
17 KiB
C

/* Kernel thread helper functions.
* Copyright (C) 2004 IBM Corporation, Rusty Russell.
*
* Creation is done via kthreadd, so that we get a clean environment
* even if we're invoked from userspace (think modprobe, hotplug cpu,
* etc.).
*/
#include <linux/sched.h>
#include <linux/kthread.h>
#include <linux/completion.h>
#include <linux/err.h>
#include <linux/cpuset.h>
#include <linux/unistd.h>
#include <linux/file.h>
#include <linux/export.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/freezer.h>
#include <linux/ptrace.h>
#include <trace/events/sched.h>
static DEFINE_SPINLOCK(kthread_create_lock);
static LIST_HEAD(kthread_create_list);
struct task_struct *kthreadd_task;
struct kthread_create_info
{
/* Information passed to kthread() from kthreadd. */
int (*threadfn)(void *data);
void *data;
int node;
/* Result passed back to kthread_create() from kthreadd. */
struct task_struct *result;
struct completion done;
struct list_head list;
};
struct kthread {
unsigned long flags;
unsigned int cpu;
void *data;
struct completion parked;
struct completion exited;
};
enum KTHREAD_BITS {
KTHREAD_IS_PER_CPU = 0,
KTHREAD_SHOULD_STOP,
KTHREAD_SHOULD_PARK,
KTHREAD_IS_PARKED,
};
#define __to_kthread(vfork) \
container_of(vfork, struct kthread, exited)
static inline struct kthread *to_kthread(struct task_struct *k)
{
return __to_kthread(k->vfork_done);
}
static struct kthread *to_live_kthread(struct task_struct *k)
{
struct completion *vfork = ACCESS_ONCE(k->vfork_done);
if (likely(vfork))
return __to_kthread(vfork);
return NULL;
}
/**
* kthread_should_stop - should this kthread return now?
*
* When someone calls kthread_stop() on your kthread, it will be woken
* and this will return true. You should then return, and your return
* value will be passed through to kthread_stop().
*/
bool kthread_should_stop(void)
{
return test_bit(KTHREAD_SHOULD_STOP, &to_kthread(current)->flags);
}
EXPORT_SYMBOL(kthread_should_stop);
/**
* kthread_should_park - should this kthread park now?
*
* When someone calls kthread_park() on your kthread, it will be woken
* and this will return true. You should then do the necessary
* cleanup and call kthread_parkme()
*
* Similar to kthread_should_stop(), but this keeps the thread alive
* and in a park position. kthread_unpark() "restarts" the thread and
* calls the thread function again.
*/
bool kthread_should_park(void)
{
return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(current)->flags);
}
/**
* kthread_freezable_should_stop - should this freezable kthread return now?
* @was_frozen: optional out parameter, indicates whether %current was frozen
*
* kthread_should_stop() for freezable kthreads, which will enter
* refrigerator if necessary. This function is safe from kthread_stop() /
* freezer deadlock and freezable kthreads should use this function instead
* of calling try_to_freeze() directly.
*/
bool kthread_freezable_should_stop(bool *was_frozen)
{
bool frozen = false;
might_sleep();
if (unlikely(freezing(current)))
frozen = __refrigerator(true);
if (was_frozen)
*was_frozen = frozen;
return kthread_should_stop();
}
EXPORT_SYMBOL_GPL(kthread_freezable_should_stop);
/**
* kthread_data - return data value specified on kthread creation
* @task: kthread task in question
*
* Return the data value specified when kthread @task was created.
* The caller is responsible for ensuring the validity of @task when
* calling this function.
*/
void *kthread_data(struct task_struct *task)
{
return to_kthread(task)->data;
}
static void __kthread_parkme(struct kthread *self)
{
__set_current_state(TASK_PARKED);
while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) {
if (!test_and_set_bit(KTHREAD_IS_PARKED, &self->flags))
complete(&self->parked);
schedule();
__set_current_state(TASK_PARKED);
}
clear_bit(KTHREAD_IS_PARKED, &self->flags);
__set_current_state(TASK_RUNNING);
}
void kthread_parkme(void)
{
__kthread_parkme(to_kthread(current));
}
static int kthread(void *_create)
{
/* Copy data: it's on kthread's stack */
struct kthread_create_info *create = _create;
int (*threadfn)(void *data) = create->threadfn;
void *data = create->data;
struct kthread self;
int ret;
self.flags = 0;
self.data = data;
init_completion(&self.exited);
init_completion(&self.parked);
current->vfork_done = &self.exited;
/* OK, tell user we're spawned, wait for stop or wakeup */
__set_current_state(TASK_UNINTERRUPTIBLE);
create->result = current;
complete(&create->done);
schedule();
ret = -EINTR;
if (!test_bit(KTHREAD_SHOULD_STOP, &self.flags)) {
__kthread_parkme(&self);
ret = threadfn(data);
}
/* we can't just return, we must preserve "self" on stack */
do_exit(ret);
}
/* called from do_fork() to get node information for about to be created task */
int tsk_fork_get_node(struct task_struct *tsk)
{
#ifdef CONFIG_NUMA
if (tsk == kthreadd_task)
return tsk->pref_node_fork;
#endif
return numa_node_id();
}
static void create_kthread(struct kthread_create_info *create)
{
int pid;
#ifdef CONFIG_NUMA
current->pref_node_fork = create->node;
#endif
/* We want our own signal handler (we take no signals by default). */
pid = kernel_thread(kthread, create, CLONE_FS | CLONE_FILES | SIGCHLD);
if (pid < 0) {
create->result = ERR_PTR(pid);
complete(&create->done);
}
}
/**
* kthread_create_on_node - create a kthread.
* @threadfn: the function to run until signal_pending(current).
* @data: data ptr for @threadfn.
* @node: memory node number.
* @namefmt: printf-style name for the thread.
*
* Description: This helper function creates and names a kernel
* thread. The thread will be stopped: use wake_up_process() to start
* it. See also kthread_run().
*
* If thread is going to be bound on a particular cpu, give its node
* in @node, to get NUMA affinity for kthread stack, or else give -1.
* When woken, the thread will run @threadfn() with @data as its
* argument. @threadfn() can either call do_exit() directly if it is a
* standalone thread for which no one will call kthread_stop(), or
* return when 'kthread_should_stop()' is true (which means
* kthread_stop() has been called). The return value should be zero
* or a negative error number; it will be passed to kthread_stop().
*
* Returns a task_struct or ERR_PTR(-ENOMEM).
*/
struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
void *data, int node,
const char namefmt[],
...)
{
struct kthread_create_info create;
create.threadfn = threadfn;
create.data = data;
create.node = node;
init_completion(&create.done);
spin_lock(&kthread_create_lock);
list_add_tail(&create.list, &kthread_create_list);
spin_unlock(&kthread_create_lock);
wake_up_process(kthreadd_task);
wait_for_completion(&create.done);
if (!IS_ERR(create.result)) {
static const struct sched_param param = { .sched_priority = 0 };
va_list args;
va_start(args, namefmt);
vsnprintf(create.result->comm, sizeof(create.result->comm),
namefmt, args);
va_end(args);
/*
* root may have changed our (kthreadd's) priority or CPU mask.
* The kernel thread should not inherit these properties.
*/
sched_setscheduler_nocheck(create.result, SCHED_NORMAL, &param);
set_cpus_allowed_ptr(create.result, cpu_all_mask);
}
return create.result;
}
EXPORT_SYMBOL(kthread_create_on_node);
static void __kthread_bind(struct task_struct *p, unsigned int cpu, long state)
{
/* Must have done schedule() in kthread() before we set_task_cpu */
if (!wait_task_inactive(p, state)) {
WARN_ON(1);
return;
}
/* It's safe because the task is inactive. */
do_set_cpus_allowed(p, cpumask_of(cpu));
p->flags |= PF_NO_SETAFFINITY;
}
/**
* kthread_bind - bind a just-created kthread to a cpu.
* @p: thread created by kthread_create().
* @cpu: cpu (might not be online, must be possible) for @k to run on.
*
* Description: This function is equivalent to set_cpus_allowed(),
* except that @cpu doesn't need to be online, and the thread must be
* stopped (i.e., just returned from kthread_create()).
*/
void kthread_bind(struct task_struct *p, unsigned int cpu)
{
__kthread_bind(p, cpu, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(kthread_bind);
/**
* kthread_create_on_cpu - Create a cpu bound kthread
* @threadfn: the function to run until signal_pending(current).
* @data: data ptr for @threadfn.
* @cpu: The cpu on which the thread should be bound,
* @namefmt: printf-style name for the thread. Format is restricted
* to "name.*%u". Code fills in cpu number.
*
* Description: This helper function creates and names a kernel thread
* The thread will be woken and put into park mode.
*/
struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
void *data, unsigned int cpu,
const char *namefmt)
{
struct task_struct *p;
p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt,
cpu);
if (IS_ERR(p))
return p;
set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags);
to_kthread(p)->cpu = cpu;
/* Park the thread to get it out of TASK_UNINTERRUPTIBLE state */
kthread_park(p);
return p;
}
static void __kthread_unpark(struct task_struct *k, struct kthread *kthread)
{
clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
/*
* We clear the IS_PARKED bit here as we don't wait
* until the task has left the park code. So if we'd
* park before that happens we'd see the IS_PARKED bit
* which might be about to be cleared.
*/
if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
__kthread_bind(k, kthread->cpu, TASK_PARKED);
wake_up_state(k, TASK_PARKED);
}
}
/**
* kthread_unpark - unpark a thread created by kthread_create().
* @k: thread created by kthread_create().
*
* Sets kthread_should_park() for @k to return false, wakes it, and
* waits for it to return. If the thread is marked percpu then its
* bound to the cpu again.
*/
void kthread_unpark(struct task_struct *k)
{
struct kthread *kthread = to_live_kthread(k);
if (kthread)
__kthread_unpark(k, kthread);
}
/**
* kthread_park - park a thread created by kthread_create().
* @k: thread created by kthread_create().
*
* Sets kthread_should_park() for @k to return true, wakes it, and
* waits for it to return. This can also be called after kthread_create()
* instead of calling wake_up_process(): the thread will park without
* calling threadfn().
*
* Returns 0 if the thread is parked, -ENOSYS if the thread exited.
* If called by the kthread itself just the park bit is set.
*/
int kthread_park(struct task_struct *k)
{
struct kthread *kthread = to_live_kthread(k);
int ret = -ENOSYS;
if (kthread) {
if (!test_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
if (k != current) {
wake_up_process(k);
wait_for_completion(&kthread->parked);
}
}
ret = 0;
}
return ret;
}
/**
* kthread_stop - stop a thread created by kthread_create().
* @k: thread created by kthread_create().
*
* Sets kthread_should_stop() for @k to return true, wakes it, and
* waits for it to exit. This can also be called after kthread_create()
* instead of calling wake_up_process(): the thread will exit without
* calling threadfn().
*
* If threadfn() may call do_exit() itself, the caller must ensure
* task_struct can't go away.
*
* Returns the result of threadfn(), or %-EINTR if wake_up_process()
* was never called.
*/
int kthread_stop(struct task_struct *k)
{
struct kthread *kthread;
int ret;
trace_sched_kthread_stop(k);
get_task_struct(k);
kthread = to_live_kthread(k);
if (kthread) {
set_bit(KTHREAD_SHOULD_STOP, &kthread->flags);
__kthread_unpark(k, kthread);
wake_up_process(k);
wait_for_completion(&kthread->exited);
}
ret = k->exit_code;
put_task_struct(k);
trace_sched_kthread_stop_ret(ret);
return ret;
}
EXPORT_SYMBOL(kthread_stop);
int kthreadd(void *unused)
{
struct task_struct *tsk = current;
/* Setup a clean context for our children to inherit. */
set_task_comm(tsk, "kthreadd");
ignore_signals(tsk);
set_cpus_allowed_ptr(tsk, cpu_all_mask);
set_mems_allowed(node_states[N_MEMORY]);
current->flags |= PF_NOFREEZE;
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
if (list_empty(&kthread_create_list))
schedule();
__set_current_state(TASK_RUNNING);
spin_lock(&kthread_create_lock);
while (!list_empty(&kthread_create_list)) {
struct kthread_create_info *create;
create = list_entry(kthread_create_list.next,
struct kthread_create_info, list);
list_del_init(&create->list);
spin_unlock(&kthread_create_lock);
create_kthread(create);
spin_lock(&kthread_create_lock);
}
spin_unlock(&kthread_create_lock);
}
return 0;
}
void __init_kthread_worker(struct kthread_worker *worker,
const char *name,
struct lock_class_key *key)
{
spin_lock_init(&worker->lock);
lockdep_set_class_and_name(&worker->lock, key, name);
INIT_LIST_HEAD(&worker->work_list);
worker->task = NULL;
}
EXPORT_SYMBOL_GPL(__init_kthread_worker);
/**
* kthread_worker_fn - kthread function to process kthread_worker
* @worker_ptr: pointer to initialized kthread_worker
*
* This function can be used as @threadfn to kthread_create() or
* kthread_run() with @worker_ptr argument pointing to an initialized
* kthread_worker. The started kthread will process work_list until
* the it is stopped with kthread_stop(). A kthread can also call
* this function directly after extra initialization.
*
* Different kthreads can be used for the same kthread_worker as long
* as there's only one kthread attached to it at any given time. A
* kthread_worker without an attached kthread simply collects queued
* kthread_works.
*/
int kthread_worker_fn(void *worker_ptr)
{
struct kthread_worker *worker = worker_ptr;
struct kthread_work *work;
WARN_ON(worker->task);
worker->task = current;
repeat:
set_current_state(TASK_INTERRUPTIBLE); /* mb paired w/ kthread_stop */
if (kthread_should_stop()) {
__set_current_state(TASK_RUNNING);
spin_lock_irq(&worker->lock);
worker->task = NULL;
spin_unlock_irq(&worker->lock);
return 0;
}
work = NULL;
spin_lock_irq(&worker->lock);
if (!list_empty(&worker->work_list)) {
work = list_first_entry(&worker->work_list,
struct kthread_work, node);
list_del_init(&work->node);
}
worker->current_work = work;
spin_unlock_irq(&worker->lock);
if (work) {
__set_current_state(TASK_RUNNING);
work->func(work);
} else if (!freezing(current))
schedule();
try_to_freeze();
goto repeat;
}
EXPORT_SYMBOL_GPL(kthread_worker_fn);
/* insert @work before @pos in @worker */
static void insert_kthread_work(struct kthread_worker *worker,
struct kthread_work *work,
struct list_head *pos)
{
lockdep_assert_held(&worker->lock);
list_add_tail(&work->node, pos);
work->worker = worker;
if (likely(worker->task))
wake_up_process(worker->task);
}
/**
* queue_kthread_work - queue a kthread_work
* @worker: target kthread_worker
* @work: kthread_work to queue
*
* Queue @work to work processor @task for async execution. @task
* must have been created with kthread_worker_create(). Returns %true
* if @work was successfully queued, %false if it was already pending.
*/
bool queue_kthread_work(struct kthread_worker *worker,
struct kthread_work *work)
{
bool ret = false;
unsigned long flags;
spin_lock_irqsave(&worker->lock, flags);
if (list_empty(&work->node)) {
insert_kthread_work(worker, work, &worker->work_list);
ret = true;
}
spin_unlock_irqrestore(&worker->lock, flags);
return ret;
}
EXPORT_SYMBOL_GPL(queue_kthread_work);
struct kthread_flush_work {
struct kthread_work work;
struct completion done;
};
static void kthread_flush_work_fn(struct kthread_work *work)
{
struct kthread_flush_work *fwork =
container_of(work, struct kthread_flush_work, work);
complete(&fwork->done);
}
/**
* flush_kthread_work - flush a kthread_work
* @work: work to flush
*
* If @work is queued or executing, wait for it to finish execution.
*/
void flush_kthread_work(struct kthread_work *work)
{
struct kthread_flush_work fwork = {
KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn),
COMPLETION_INITIALIZER_ONSTACK(fwork.done),
};
struct kthread_worker *worker;
bool noop = false;
retry:
worker = work->worker;
if (!worker)
return;
spin_lock_irq(&worker->lock);
if (work->worker != worker) {
spin_unlock_irq(&worker->lock);
goto retry;
}
if (!list_empty(&work->node))
insert_kthread_work(worker, &fwork.work, work->node.next);
else if (worker->current_work == work)
insert_kthread_work(worker, &fwork.work, worker->work_list.next);
else
noop = true;
spin_unlock_irq(&worker->lock);
if (!noop)
wait_for_completion(&fwork.done);
}
EXPORT_SYMBOL_GPL(flush_kthread_work);
/**
* flush_kthread_worker - flush all current works on a kthread_worker
* @worker: worker to flush
*
* Wait until all currently executing or pending works on @worker are
* finished.
*/
void flush_kthread_worker(struct kthread_worker *worker)
{
struct kthread_flush_work fwork = {
KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn),
COMPLETION_INITIALIZER_ONSTACK(fwork.done),
};
queue_kthread_work(worker, &fwork.work);
wait_for_completion(&fwork.done);
}
EXPORT_SYMBOL_GPL(flush_kthread_worker);