#include <linux/debug_locks.h>
#include <linux/lockdep.h>
#include <linux/idr.h>
+#include <linux/hashtable.h>
-#include "workqueue_sched.h"
+#include "workqueue_internal.h"
enum {
/*
WORKER_NOT_RUNNING = WORKER_PREP | WORKER_UNBOUND |
WORKER_CPU_INTENSIVE,
- NR_WORKER_POOLS = 2, /* # worker pools per gcwq */
+ NR_STD_WORKER_POOLS = 2, /* # standard pools per cpu */
BUSY_WORKER_HASH_ORDER = 6, /* 64 pointers */
- BUSY_WORKER_HASH_SIZE = 1 << BUSY_WORKER_HASH_ORDER,
- BUSY_WORKER_HASH_MASK = BUSY_WORKER_HASH_SIZE - 1,
MAX_IDLE_WORKERS_RATIO = 4, /* 1/4 of busy can be idle */
IDLE_WORKER_TIMEOUT = 300 * HZ, /* keep idle ones for 5 mins */
* W: workqueue_lock protected.
*/
-struct global_cwq;
-struct worker_pool;
-
-/*
- * The poor guys doing the actual heavy lifting. All on-duty workers
- * are either serving the manager role, on idle list or on busy hash.
- */
-struct worker {
- /* on idle list while idle, on busy hash table while busy */
- union {
- struct list_head entry; /* L: while idle */
- struct hlist_node hentry; /* L: while busy */
- };
-
- struct work_struct *current_work; /* L: work being processed */
- struct cpu_workqueue_struct *current_cwq; /* L: current_work's cwq */
- struct list_head scheduled; /* L: scheduled works */
- struct task_struct *task; /* I: worker task */
- struct worker_pool *pool; /* I: the associated pool */
- /* 64 bytes boundary on 64bit, 32 on 32bit */
- unsigned long last_active; /* L: last active timestamp */
- unsigned int flags; /* X: flags */
- int id; /* I: worker id */
-
- /* for rebinding worker to CPU */
- struct work_struct rebind_work; /* L: for busy worker */
-};
+/* struct worker is defined in workqueue_internal.h */
struct worker_pool {
struct global_cwq *gcwq; /* I: the owning gcwq */
unsigned int flags; /* L: GCWQ_* flags */
/* workers are chained either in busy_hash or pool idle_list */
- struct hlist_head busy_hash[BUSY_WORKER_HASH_SIZE];
+ DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER);
/* L: hash of busy workers */
- struct worker_pool pools[NR_WORKER_POOLS];
+ struct worker_pool pools[NR_STD_WORKER_POOLS];
/* normal and highpri pools */
} ____cacheline_aligned_in_smp;
#define for_each_worker_pool(pool, gcwq) \
for ((pool) = &(gcwq)->pools[0]; \
- (pool) < &(gcwq)->pools[NR_WORKER_POOLS]; (pool)++)
+ (pool) < &(gcwq)->pools[NR_STD_WORKER_POOLS]; (pool)++)
#define for_each_busy_worker(worker, i, pos, gcwq) \
- for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++) \
- hlist_for_each_entry(worker, pos, &gcwq->busy_hash[i], hentry)
+ hash_for_each(gcwq->busy_hash, i, pos, worker, hentry)
static inline int __next_gcwq_cpu(int cpu, const struct cpumask *mask,
unsigned int sw)
* try_to_wake_up(). Put it in a separate cacheline.
*/
static DEFINE_PER_CPU(struct global_cwq, global_cwq);
-static DEFINE_PER_CPU_SHARED_ALIGNED(atomic_t, pool_nr_running[NR_WORKER_POOLS]);
+static DEFINE_PER_CPU_SHARED_ALIGNED(atomic_t, pool_nr_running[NR_STD_WORKER_POOLS]);
/*
* Global cpu workqueue and nr_running counter for unbound gcwq. The
* workers have WORKER_UNBOUND set.
*/
static struct global_cwq unbound_global_cwq;
-static atomic_t unbound_pool_nr_running[NR_WORKER_POOLS] = {
- [0 ... NR_WORKER_POOLS - 1] = ATOMIC_INIT(0), /* always 0 */
+static atomic_t unbound_pool_nr_running[NR_STD_WORKER_POOLS] = {
+ [0 ... NR_STD_WORKER_POOLS - 1] = ATOMIC_INIT(0), /* always 0 */
};
static int worker_thread(void *__worker);
+static unsigned int work_cpu(struct work_struct *work);
-static int worker_pool_pri(struct worker_pool *pool)
+static int std_worker_pool_pri(struct worker_pool *pool)
{
return pool - pool->gcwq->pools;
}
static atomic_t *get_pool_nr_running(struct worker_pool *pool)
{
int cpu = pool->gcwq->cpu;
- int idx = worker_pool_pri(pool);
+ int idx = std_worker_pool_pri(pool);
if (cpu != WORK_CPU_UNBOUND)
return &per_cpu(pool_nr_running, cpu)[idx];
{
struct worker *worker = kthread_data(task);
- if (!(worker->flags & WORKER_NOT_RUNNING))
+ if (!(worker->flags & WORKER_NOT_RUNNING)) {
+ WARN_ON_ONCE(worker->pool->gcwq->cpu != cpu);
atomic_inc(get_pool_nr_running(worker->pool));
+ }
}
/**
unsigned int cpu)
{
struct worker *worker = kthread_data(task), *to_wakeup = NULL;
- struct worker_pool *pool = worker->pool;
- atomic_t *nr_running = get_pool_nr_running(pool);
+ struct worker_pool *pool;
+ atomic_t *nr_running;
+ /*
+ * Rescuers, which may not have all the fields set up like normal
+ * workers, also reach here, let's not access anything before
+ * checking NOT_RUNNING.
+ */
if (worker->flags & WORKER_NOT_RUNNING)
return NULL;
+ pool = worker->pool;
+ nr_running = get_pool_nr_running(pool);
+
/* this can only happen on the local cpu */
BUG_ON(cpu != raw_smp_processor_id());
}
/**
- * busy_worker_head - return the busy hash head for a work
- * @gcwq: gcwq of interest
- * @work: work to be hashed
- *
- * Return hash head of @gcwq for @work.
- *
- * CONTEXT:
- * spin_lock_irq(gcwq->lock).
- *
- * RETURNS:
- * Pointer to the hash head.
- */
-static struct hlist_head *busy_worker_head(struct global_cwq *gcwq,
- struct work_struct *work)
-{
- const int base_shift = ilog2(sizeof(struct work_struct));
- unsigned long v = (unsigned long)work;
-
- /* simple shift and fold hash, do we need something better? */
- v >>= base_shift;
- v += v >> BUSY_WORKER_HASH_ORDER;
- v &= BUSY_WORKER_HASH_MASK;
-
- return &gcwq->busy_hash[v];
-}
-
-/**
- * __find_worker_executing_work - find worker which is executing a work
+ * find_worker_executing_work - find worker which is executing a work
* @gcwq: gcwq of interest
- * @bwh: hash head as returned by busy_worker_head()
* @work: work to find worker for
*
- * Find a worker which is executing @work on @gcwq. @bwh should be
- * the hash head obtained by calling busy_worker_head() with the same
- * work.
+ * Find a worker which is executing @work on @gcwq by searching
+ * @gcwq->busy_hash which is keyed by the address of @work. For a worker
+ * to match, its current execution should match the address of @work and
+ * its work function. This is to avoid unwanted dependency between
+ * unrelated work executions through a work item being recycled while still
+ * being executed.
+ *
+ * This is a bit tricky. A work item may be freed once its execution
+ * starts and nothing prevents the freed area from being recycled for
+ * another work item. If the same work item address ends up being reused
+ * before the original execution finishes, workqueue will identify the
+ * recycled work item as currently executing and make it wait until the
+ * current execution finishes, introducing an unwanted dependency.
+ *
+ * This function checks the work item address, work function and workqueue
+ * to avoid false positives. Note that this isn't complete as one may
+ * construct a work function which can introduce dependency onto itself
+ * through a recycled work item. Well, if somebody wants to shoot oneself
+ * in the foot that badly, there's only so much we can do, and if such
+ * deadlock actually occurs, it should be easy to locate the culprit work
+ * function.
*
* CONTEXT:
* spin_lock_irq(gcwq->lock).
* Pointer to worker which is executing @work if found, NULL
* otherwise.
*/
-static struct worker *__find_worker_executing_work(struct global_cwq *gcwq,
- struct hlist_head *bwh,
- struct work_struct *work)
+static struct worker *find_worker_executing_work(struct global_cwq *gcwq,
+ struct work_struct *work)
{
struct worker *worker;
struct hlist_node *tmp;
- hlist_for_each_entry(worker, tmp, bwh, hentry)
- if (worker->current_work == work)
+ hash_for_each_possible(gcwq->busy_hash, worker, tmp, hentry,
+ (unsigned long)work)
+ if (worker->current_work == work &&
+ worker->current_func == work->func)
return worker;
- return NULL;
-}
-/**
- * find_worker_executing_work - find worker which is executing a work
- * @gcwq: gcwq of interest
- * @work: work to find worker for
- *
- * Find a worker which is executing @work on @gcwq. This function is
- * identical to __find_worker_executing_work() except that this
- * function calculates @bwh itself.
- *
- * CONTEXT:
- * spin_lock_irq(gcwq->lock).
- *
- * RETURNS:
- * Pointer to worker which is executing @work if found, NULL
- * otherwise.
- */
-static struct worker *find_worker_executing_work(struct global_cwq *gcwq,
- struct work_struct *work)
-{
- return __find_worker_executing_work(gcwq, busy_worker_head(gcwq, work),
- work);
+ return NULL;
}
/**
* wq doesn't really matter but let's keep @worker->pool
* and @cwq->pool consistent for sanity.
*/
- if (worker_pool_pri(worker->pool))
+ if (std_worker_pool_pri(worker->pool))
wq = system_highpri_wq;
else
wq = system_wq;
static struct worker *create_worker(struct worker_pool *pool)
{
struct global_cwq *gcwq = pool->gcwq;
- const char *pri = worker_pool_pri(pool) ? "H" : "";
+ const char *pri = std_worker_pool_pri(pool) ? "H" : "";
struct worker *worker = NULL;
int id = -1;
if (IS_ERR(worker->task))
goto fail;
- if (worker_pool_pri(pool))
+ if (std_worker_pool_pri(pool))
set_user_nice(worker->task, HIGHPRI_NICE_LEVEL);
/*
struct cpu_workqueue_struct *cwq = get_work_cwq(work);
struct worker_pool *pool = worker->pool;
struct global_cwq *gcwq = pool->gcwq;
- struct hlist_head *bwh = busy_worker_head(gcwq, work);
bool cpu_intensive = cwq->wq->flags & WQ_CPU_INTENSIVE;
- work_func_t f = work->func;
int work_color;
struct worker *collision;
#ifdef CONFIG_LOCKDEP
* already processing the work. If so, defer the work to the
* currently executing one.
*/
- collision = __find_worker_executing_work(gcwq, bwh, work);
+ collision = find_worker_executing_work(gcwq, work);
if (unlikely(collision)) {
move_linked_works(work, &collision->scheduled, NULL);
return;
/* claim and dequeue */
debug_work_deactivate(work);
- hlist_add_head(&worker->hentry, bwh);
+ hash_add(gcwq->busy_hash, &worker->hentry, (unsigned long)work);
worker->current_work = work;
+ worker->current_func = work->func;
worker->current_cwq = cwq;
work_color = get_work_color(work);
lock_map_acquire_read(&cwq->wq->lockdep_map);
lock_map_acquire(&lockdep_map);
trace_workqueue_execute_start(work);
- f(work);
+ worker->current_func(work);
/*
* While we must be careful to not use "work" after this, the trace
* point will only record its address.
if (unlikely(in_atomic() || lockdep_depth(current) > 0)) {
pr_err("BUG: workqueue leaked lock or atomic: %s/0x%08x/%d\n"
" last function: %pf\n",
- current->comm, preempt_count(), task_pid_nr(current), f);
+ current->comm, preempt_count(), task_pid_nr(current),
+ worker->current_func);
debug_show_held_locks(current);
dump_stack();
}
worker_clr_flags(worker, WORKER_CPU_INTENSIVE);
/* we're done with it, release */
- hlist_del_init(&worker->hentry);
+ hash_del(&worker->hentry);
worker->current_work = NULL;
+ worker->current_func = NULL;
worker->current_cwq = NULL;
cwq_dec_nr_in_flight(cwq, work_color);
}
/**
* rescuer_thread - the rescuer thread function
- * @__wq: the associated workqueue
+ * @__rescuer: self
*
* Workqueue rescuer thread function. There's one rescuer for each
* workqueue which has WQ_RESCUER set.
*
* This should happen rarely.
*/
-static int rescuer_thread(void *__wq)
+static int rescuer_thread(void *__rescuer)
{
- struct workqueue_struct *wq = __wq;
- struct worker *rescuer = wq->rescuer;
+ struct worker *rescuer = __rescuer;
+ struct workqueue_struct *wq = rescuer->rescue_wq;
struct list_head *scheduled = &rescuer->scheduled;
bool is_unbound = wq->flags & WQ_UNBOUND;
unsigned int cpu;
set_user_nice(current, RESCUER_NICE_LEVEL);
+
+ /*
+ * Mark rescuer as worker too. As WORKER_PREP is never cleared, it
+ * doesn't participate in concurrency management.
+ */
+ rescuer->task->flags |= PF_WQ_WORKER;
repeat:
set_current_state(TASK_INTERRUPTIBLE);
if (kthread_should_stop()) {
__set_current_state(TASK_RUNNING);
+ rescuer->task->flags &= ~PF_WQ_WORKER;
return 0;
}
spin_unlock_irq(&gcwq->lock);
}
+ /* rescuers should never participate in concurrency management */
+ WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING));
schedule();
goto repeat;
}
if (!rescuer)
goto err;
- rescuer->task = kthread_create(rescuer_thread, wq, "%s",
+ rescuer->rescue_wq = wq;
+ rescuer->task = kthread_create(rescuer_thread, rescuer, "%s",
wq->name);
if (IS_ERR(rescuer->task))
goto err;
* RETURNS:
* CPU number if @work was ever queued. WORK_CPU_NONE otherwise.
*/
-unsigned int work_cpu(struct work_struct *work)
+static unsigned int work_cpu(struct work_struct *work)
{
struct global_cwq *gcwq = get_work_gcwq(work);
return gcwq ? gcwq->cpu : WORK_CPU_NONE;
}
-EXPORT_SYMBOL_GPL(work_cpu);
/**
* work_busy - test whether a work is currently pending or running
unsigned int ret = 0;
if (!gcwq)
- return false;
+ return 0;
spin_lock_irqsave(&gcwq->lock, flags);
static int __init init_workqueues(void)
{
unsigned int cpu;
- int i;
/* make sure we have enough bits for OFFQ CPU number */
BUILD_BUG_ON((1LU << (BITS_PER_LONG - WORK_OFFQ_CPU_SHIFT)) <
gcwq->cpu = cpu;
gcwq->flags |= GCWQ_DISASSOCIATED;
- for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++)
- INIT_HLIST_HEAD(&gcwq->busy_hash[i]);
+ hash_init(gcwq->busy_hash);
for_each_worker_pool(pool, gcwq) {
pool->gcwq = gcwq;