*
* This is the generic async execution mechanism. Work items as are
* executed in process context. The worker pool is shared and
- * automatically managed. There is one worker pool for each CPU and
- * one extra for works which are better served by workers which are
- * not bound to any specific CPU.
+ * automatically managed. There are two worker pools for each CPU (one for
+ * normal work items and the other for high priority ones) and some extra
+ * pools for workqueues which are not bound to any specific CPU - the
+ * number of these backing pools is dynamic.
*
* Please read Documentation/workqueue.txt for details.
*/
/* I: attributes used when instantiating standard unbound pools on demand */
static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS];
+/* I: attributes used when instantiating ordered pools on demand */
+static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS];
+
struct workqueue_struct *system_wq __read_mostly;
EXPORT_SYMBOL(system_wq);
struct workqueue_struct *system_highpri_wq __read_mostly;
static inline void debug_work_deactivate(struct work_struct *work) { }
#endif
-/* allocate ID and assign it to @pool */
+/**
+ * worker_pool_assign_id - allocate ID and assing it to @pool
+ * @pool: the pool pointer of interest
+ *
+ * Returns 0 if ID in [0, WORK_OFFQ_POOL_NONE) is allocated and assigned
+ * successfully, -errno on failure.
+ */
static int worker_pool_assign_id(struct worker_pool *pool)
{
int ret;
lockdep_assert_held(&wq_pool_mutex);
- ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
+ ret = idr_alloc(&worker_pool_idr, pool, 0, WORK_OFFQ_POOL_NONE,
+ GFP_KERNEL);
if (ret >= 0) {
pool->id = ret;
return 0;
* This must be called either with pwq_lock held or sched RCU read locked.
* If the pwq needs to be used beyond the locking in effect, the caller is
* responsible for guaranteeing that the pwq stays online.
+ *
+ * Return: The unbound pool_workqueue for @node.
*/
static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq,
int node)
* get_work_pool - return the worker_pool a given work was associated with
* @work: the work item of interest
*
- * Return the worker_pool @work was last associated with. %NULL if none.
- *
* Pools are created and destroyed under wq_pool_mutex, and allows read
* access under sched-RCU read lock. As such, this function should be
* called under wq_pool_mutex or with preemption disabled.
* mentioned locking is in effect. If the returned pool needs to be used
* beyond the critical section, the caller is responsible for ensuring the
* returned pool is and stays online.
+ *
+ * Return: The worker_pool @work was last associated with. %NULL if none.
*/
static struct worker_pool *get_work_pool(struct work_struct *work)
{
* get_work_pool_id - return the worker pool ID a given work is associated with
* @work: the work item of interest
*
- * Return the worker_pool ID @work was last associated with.
+ * Return: The worker_pool ID @work was last associated with.
* %WORK_OFFQ_POOL_NONE if none.
*/
static int get_work_pool_id(struct work_struct *work)
* CONTEXT:
* spin_lock_irq(rq->lock)
*
- * RETURNS:
+ * Return:
* Worker task on @cpu to wake up, %NULL if none.
*/
struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu)
* CONTEXT:
* spin_lock_irq(pool->lock).
*
- * RETURNS:
- * Pointer to worker which is executing @work if found, NULL
+ * Return:
+ * Pointer to worker which is executing @work if found, %NULL
* otherwise.
*/
static struct worker *find_worker_executing_work(struct worker_pool *pool,
* @flags: place to store irq state
*
* Try to grab PENDING bit of @work. This function can handle @work in any
- * stable state - idle, on timer or on worklist. Return values are
+ * stable state - idle, on timer or on worklist.
*
+ * Return:
* 1 if @work was pending and we successfully stole PENDING
* 0 if @work was idle and we claimed PENDING
* -EAGAIN if PENDING couldn't be grabbed at the moment, safe to busy-retry
* -ENOENT if someone else is canceling @work, this state may persist
* for arbitrarily long
*
+ * Note:
* On >= 0 return, the caller owns @work's PENDING bit. To avoid getting
* interrupted while holding PENDING and @work off queue, irq must be
* disabled on entry. This, combined with delayed_work->timer being
debug_work_activate(work);
- /* if dying, only works from the same workqueue are allowed */
+ /* if draining, only works from the same workqueue are allowed */
if (unlikely(wq->flags & __WQ_DRAINING) &&
WARN_ON_ONCE(!is_chained_work(wq)))
return;
* @wq: workqueue to use
* @work: work to queue
*
- * Returns %false if @work was already on a queue, %true otherwise.
- *
* We queue the work to a specific CPU, the caller must ensure it
* can't go away.
+ *
+ * Return: %false if @work was already on a queue, %true otherwise.
*/
bool queue_work_on(int cpu, struct workqueue_struct *wq,
struct work_struct *work)
* @dwork: work to queue
* @delay: number of jiffies to wait before queueing
*
- * Returns %false if @work was already on a queue, %true otherwise. If
+ * Return: %false if @work was already on a queue, %true otherwise. If
* @delay is zero and @dwork is idle, it will be scheduled for immediate
* execution.
*/
* zero, @work is guaranteed to be scheduled immediately regardless of its
* current state.
*
- * Returns %false if @dwork was idle and queued, %true if @dwork was
+ * Return: %false if @dwork was idle and queued, %true if @dwork was
* pending and its timer was modified.
*
* This function is safe to call from any context including IRQ handler.
* Might sleep. Called without any lock but returns with pool->lock
* held.
*
- * RETURNS:
+ * Return:
* %true if the associated pool is online (@worker is successfully
* bound), %false if offline.
*/
* CONTEXT:
* Might sleep. Does GFP_KERNEL allocations.
*
- * RETURNS:
+ * Return:
* Pointer to the newly created worker.
*/
static struct worker *create_worker(struct worker_pool *pool)
* @pool: the target pool
*
* Grab the managership of @pool and create and start a new worker for it.
+ *
+ * Return: 0 on success. A negative error code otherwise.
*/
static int create_and_start_worker(struct worker_pool *pool)
{
* multiple times. Does GFP_KERNEL allocations. Called only from
* manager.
*
- * RETURNS:
+ * Return:
* %false if no action was taken and pool->lock stayed locked, %true
* otherwise.
*/
* spin_lock_irq(pool->lock) which may be released and regrabbed
* multiple times. Called only from manager.
*
- * RETURNS:
+ * Return:
* %false if no action was taken and pool->lock stayed locked, %true
* otherwise.
*/
* spin_lock_irq(pool->lock) which may be released and regrabbed
* multiple times. Does GFP_KERNEL allocations.
*
- * RETURNS:
- * spin_lock_irq(pool->lock) which may be released and regrabbed
- * multiple times. Does GFP_KERNEL allocations.
+ * Return:
+ * %false if the pool don't need management and the caller can safely start
+ * processing works, %true indicates that the function released pool->lock
+ * and reacquired it to perform some management function and that the
+ * conditions that the caller verified while holding the lock before
+ * calling the function might no longer be true.
*/
static bool manage_workers(struct worker *worker)
{
* work items regardless of their specific target workqueue. The only
* exception is work items which belong to workqueues with a rescuer which
* will be explained in rescuer_thread().
+ *
+ * Return: 0
*/
static int worker_thread(void *__worker)
{
* those works so that forward progress can be guaranteed.
*
* This should happen rarely.
+ *
+ * Return: 0
*/
static int rescuer_thread(void *__rescuer)
{
* CONTEXT:
* mutex_lock(wq->mutex).
*
- * RETURNS:
+ * Return:
* %true if @flush_color >= 0 and there's something to flush. %false
* otherwise.
*/
* Wait until @work has finished execution. @work is guaranteed to be idle
* on return if it hasn't been requeued since flush started.
*
- * RETURNS:
+ * Return:
* %true if flush_work() waited for the work to finish execution,
* %false if it was already idle.
*/
* The caller must ensure that the workqueue on which @work was last
* queued can't be destroyed before this function returns.
*
- * RETURNS:
+ * Return:
* %true if @work was pending, %false otherwise.
*/
bool cancel_work_sync(struct work_struct *work)
* immediate execution. Like flush_work(), this function only
* considers the last queueing instance of @dwork.
*
- * RETURNS:
+ * Return:
* %true if flush_work() waited for the work to finish execution,
* %false if it was already idle.
*/
* cancel_delayed_work - cancel a delayed work
* @dwork: delayed_work to cancel
*
- * Kill off a pending delayed_work. Returns %true if @dwork was pending
- * and canceled; %false if wasn't pending. Note that the work callback
- * function may still be running on return, unless it returns %true and the
- * work doesn't re-arm itself. Explicitly flush or use
- * cancel_delayed_work_sync() to wait on it.
+ * Kill off a pending delayed_work.
+ *
+ * Return: %true if @dwork was pending and canceled; %false if it wasn't
+ * pending.
+ *
+ * Note:
+ * The work callback function may still be running on return, unless
+ * it returns %true and the work doesn't re-arm itself. Explicitly flush or
+ * use cancel_delayed_work_sync() to wait on it.
*
* This function is safe to call from any context including IRQ handler.
*/
*
* This is cancel_work_sync() for delayed works.
*
- * RETURNS:
+ * Return:
* %true if @dwork was pending, %false otherwise.
*/
bool cancel_delayed_work_sync(struct delayed_work *dwork)
* system workqueue and blocks until all CPUs have completed.
* schedule_on_each_cpu() is very slow.
*
- * RETURNS:
+ * Return:
* 0 on success, -errno on failure.
*/
int schedule_on_each_cpu(work_func_t func)
* Executes the function immediately if process context is available,
* otherwise schedules the function for delayed execution.
*
- * Returns: 0 - function was executed
+ * Return: 0 - function was executed
* 1 - function was scheduled for execution
*/
int execute_in_process_context(work_func_t fn, struct execute_work *ew)
return wq_dev->wq;
}
-static ssize_t wq_per_cpu_show(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t per_cpu_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
{
struct workqueue_struct *wq = dev_to_wq(dev);
return scnprintf(buf, PAGE_SIZE, "%d\n", (bool)!(wq->flags & WQ_UNBOUND));
}
+static DEVICE_ATTR_RO(per_cpu);
-static ssize_t wq_max_active_show(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t max_active_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct workqueue_struct *wq = dev_to_wq(dev);
return scnprintf(buf, PAGE_SIZE, "%d\n", wq->saved_max_active);
}
-static ssize_t wq_max_active_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
+static ssize_t max_active_store(struct device *dev,
+ struct device_attribute *attr, const char *buf,
+ size_t count)
{
struct workqueue_struct *wq = dev_to_wq(dev);
int val;
workqueue_set_max_active(wq, val);
return count;
}
+static DEVICE_ATTR_RW(max_active);
-static struct device_attribute wq_sysfs_attrs[] = {
- __ATTR(per_cpu, 0444, wq_per_cpu_show, NULL),
- __ATTR(max_active, 0644, wq_max_active_show, wq_max_active_store),
- __ATTR_NULL,
+static struct attribute *wq_sysfs_attrs[] = {
+ &dev_attr_per_cpu.attr,
+ &dev_attr_max_active.attr,
+ NULL,
};
+ATTRIBUTE_GROUPS(wq_sysfs);
static ssize_t wq_pool_ids_show(struct device *dev,
struct device_attribute *attr, char *buf)
static struct bus_type wq_subsys = {
.name = "workqueue",
- .dev_attrs = wq_sysfs_attrs,
+ .dev_groups = wq_sysfs_groups,
};
static int __init wq_sysfs_init(void)
* apply_workqueue_attrs() may race against userland updating the
* attributes.
*
- * Returns 0 on success, -errno on failure.
+ * Return: 0 on success, -errno on failure.
*/
int workqueue_sysfs_register(struct workqueue_struct *wq)
{
* @gfp_mask: allocation mask to use
*
* Allocate a new workqueue_attrs, initialize with default settings and
- * return it. Returns NULL on failure.
+ * return it.
+ *
+ * Return: The allocated new workqueue_attr on success. %NULL on failure.
*/
struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask)
{
* @pool: worker_pool to initialize
*
* Initiailize a newly zalloc'd @pool. It also allocates @pool->attrs.
- * Returns 0 on success, -errno on failure. Even on failure, all fields
+ *
+ * Return: 0 on success, -errno on failure. Even on failure, all fields
* inside @pool proper are initialized and put_unbound_pool() can be called
* on @pool safely to release it.
*/
* Obtain a worker_pool which has the same attributes as @attrs, bump the
* reference count and return it. If there already is a matching
* worker_pool, it will be used; otherwise, this function attempts to
- * create a new one. On failure, returns NULL.
+ * create a new one.
*
* Should be called with wq_pool_mutex held.
+ *
+ * Return: On success, a worker_pool with the same attributes as @attrs.
+ * On failure, %NULL.
*/
static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs)
{
*
* Calculate the cpumask a workqueue with @attrs should use on @node. If
* @cpu_going_down is >= 0, that cpu is considered offline during
- * calculation. The result is stored in @cpumask. This function returns
- * %true if the resulting @cpumask is different from @attrs->cpumask,
- * %false if equal.
+ * calculation. The result is stored in @cpumask.
*
* If NUMA affinity is not enabled, @attrs->cpumask is always used. If
* enabled and @node has online CPUs requested by @attrs, the returned
*
* The caller is responsible for ensuring that the cpumask of @node stays
* stable.
+ *
+ * Return: %true if the resulting @cpumask is different from @attrs->cpumask,
+ * %false if equal.
*/
static bool wq_calc_node_cpumask(const struct workqueue_attrs *attrs, int node,
int cpu_going_down, cpumask_t *cpumask)
* items finish. Note that a work item which repeatedly requeues itself
* back-to-back will stay on its current pwq.
*
- * Performs GFP_KERNEL allocations. Returns 0 on success and -errno on
- * failure.
+ * Performs GFP_KERNEL allocations.
+ *
+ * Return: 0 on success and -errno on failure.
*/
int apply_workqueue_attrs(struct workqueue_struct *wq,
const struct workqueue_attrs *attrs)
static int alloc_and_link_pwqs(struct workqueue_struct *wq)
{
bool highpri = wq->flags & WQ_HIGHPRI;
- int cpu;
+ int cpu, ret;
if (!(wq->flags & WQ_UNBOUND)) {
wq->cpu_pwqs = alloc_percpu(struct pool_workqueue);
mutex_unlock(&wq->mutex);
}
return 0;
+ } else if (wq->flags & __WQ_ORDERED) {
+ ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]);
+ /* there should only be single pwq for ordering guarantee */
+ WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node ||
+ wq->pwqs.prev != &wq->dfl_pwq->pwqs_node),
+ "ordering guarantee broken for workqueue %s\n", wq->name);
+ return ret;
} else {
return apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]);
}
*
* Determine whether %current is a workqueue rescuer. Can be used from
* work functions to determine whether it's being run off the rescuer task.
+ *
+ * Return: %true if %current is a workqueue rescuer. %false otherwise.
*/
bool current_is_workqueue_rescuer(void)
{
* workqueue being congested on one CPU doesn't mean the workqueue is also
* contested on other CPUs / NUMA nodes.
*
- * RETURNS:
+ * Return:
* %true if congested, %false otherwise.
*/
bool workqueue_congested(int cpu, struct workqueue_struct *wq)
* synchronization around this function and the test result is
* unreliable and only useful as advisory hints or for debugging.
*
- * RETURNS:
+ * Return:
* OR'd bitmask of WORK_BUSY_* bits.
*/
unsigned int work_busy(struct work_struct *work)
* @fn: the function to run
* @arg: the function arg
*
- * This will return the value @fn returns.
* It is up to the caller to ensure that the cpu doesn't go offline.
* The caller must not hold any locks which would prevent @fn from completing.
+ *
+ * Return: The value @fn returns.
*/
long work_on_cpu(int cpu, long (*fn)(void *), void *arg)
{
* CONTEXT:
* Grabs and releases wq_pool_mutex.
*
- * RETURNS:
+ * Return:
* %true if some freezable workqueues are still busy. %false if freezing
* is complete.
*/
int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL };
int i, cpu;
- /* make sure we have enough bits for OFFQ pool ID */
- BUILD_BUG_ON((1LU << (BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT)) <
- WORK_CPU_END * NR_STD_WORKER_POOLS);
-
WARN_ON(__alignof__(struct pool_workqueue) < __alignof__(long long));
pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);
}
}
- /* create default unbound wq attrs */
+ /* create default unbound and ordered wq attrs */
for (i = 0; i < NR_STD_WORKER_POOLS; i++) {
struct workqueue_attrs *attrs;
BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
attrs->nice = std_nice[i];
unbound_std_wq_attrs[i] = attrs;
+
+ /*
+ * An ordered wq should have only one pwq as ordering is
+ * guaranteed by max_active which is enforced by pwqs.
+ * Turn off NUMA so that dfl_pwq is used for all nodes.
+ */
+ BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
+ attrs->nice = std_nice[i];
+ attrs->no_numa = true;
+ ordered_wq_attrs[i] = attrs;
}
system_wq = alloc_workqueue("events", 0, 0);