arch/arm

/*
 * kernel/workqueue.c - generic async execution with shared worker pool
 *
 * Copyright (C) 2002		Ingo Molnar
 *
 *   Derived from the taskqueue/keventd code by:
 *     David Woodhouse <dwmw2@infradead.org>
 *     Andrew Morton
 *     Kai Petzke <wpp@marie.physik.tu-berlin.de>
 *     Theodore Ts'o <tytso@mit.edu>
 *
 * Made to use alloc_percpu by Christoph Lameter.
 *
 * Copyright (C) 2010		SUSE Linux Products GmbH
 * Copyright (C) 2010		Tejun Heo <tj@kernel.org>
 *
 * 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.
 *
 * Please read Documentation/workqueue.txt for details.
 */

#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/signal.h>
#include <linux/completion.h>
#include <linux/workqueue.h>
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/kthread.h>
#include <linux/hardirq.h>
#include <linux/mempolicy.h>
#include <linux/freezer.h>
#include <linux/kallsyms.h>
#include <linux/debug_locks.h>
#include <linux/lockdep.h>
#include <linux/idr.h>

#include "workqueue_sched.h"

enum {
	/* global_cwq flags */
	GCWQ_MANAGE_WORKERS	= 1 << 0,	/* need to manage workers */
	GCWQ_MANAGING_WORKERS	= 1 << 1,	/* managing workers */
	GCWQ_DISASSOCIATED	= 1 << 2,	/* cpu can't serve workers */
	GCWQ_FREEZING		= 1 << 3,	/* freeze in progress */
	GCWQ_HIGHPRI_PENDING	= 1 << 4,	/* highpri works on queue */

	/* worker flags */
	WORKER_STARTED		= 1 << 0,	/* started */
	WORKER_DIE		= 1 << 1,	/* die die die */
	WORKER_IDLE		= 1 << 2,	/* is idle */
	WORKER_PREP		= 1 << 3,	/* preparing to run works */
	WORKER_ROGUE		= 1 << 4,	/* not bound to any cpu */
	WORKER_REBIND		= 1 << 5,	/* mom is home, come back */
	WORKER_CPU_INTENSIVE	= 1 << 6,	/* cpu intensive */
	WORKER_UNBOUND		= 1 << 7,	/* worker is unbound */

	WORKER_NOT_RUNNING	= WORKER_PREP | WORKER_ROGUE | WORKER_REBIND |
				  WORKER_CPU_INTENSIVE | WORKER_UNBOUND,

	/* gcwq->trustee_state */
	TRUSTEE_START		= 0,		/* start */
	TRUSTEE_IN_CHARGE	= 1,		/* trustee in charge of gcwq */
	TRUSTEE_BUTCHER		= 2,		/* butcher workers */
	TRUSTEE_RELEASE		= 3,		/* release workers */
	TRUSTEE_DONE		= 4,		/* trustee is done */

	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 */

	MAYDAY_INITIAL_TIMEOUT  = HZ / 100 >= 2 ? HZ / 100 : 2,
						/* call for help after 10ms
						   (min two ticks) */
	MAYDAY_INTERVAL		= HZ / 10,	/* and then every 100ms */
	CREATE_COOLDOWN		= HZ,		/* time to breath after fail */
	TRUSTEE_COOLDOWN	= HZ / 10,	/* for trustee draining */

	/*
	 * Rescue workers are used only on emergencies and shared by
	 * all cpus.  Give -20.
	 */
	RESCUER_NICE_LEVEL	= -20,
};

/*
 * Structure fields follow one of the following exclusion rules.
 *
 * I: Modifiable by initialization/destruction paths and read-only for
 *    everyone else.
 *
 * P: Preemption protected.  Disabling preemption is enough and should
 *    only be modified and accessed from the local cpu.
 *
 * L: gcwq->lock protected.  Access with gcwq->lock held.
 *
 * X: During normal operation, modification requires gcwq->lock and
 *    should be done only from local cpu.  Either disabling preemption
 *    on local cpu or grabbing gcwq->lock is enough for read access.
 *    If GCWQ_DISASSOCIATED is set, it's identical to L.
 *
 * F: wq->flush_mutex protected.
 *
 * W: workqueue_lock protected.
 */

struct global_cwq;

/*
 * 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 global_cwq	*gcwq;		/* I: the associated gcwq */
	/* 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 */
	struct work_struct	rebind_work;	/* L: rebind worker to cpu */
};

/*
 * Global per-cpu workqueue.  There's one and only one for each cpu
 * and all works are queued and processed here regardless of their
 * target workqueues.
 */
struct global_cwq {
	spinlock_t		lock;		/* the gcwq lock */
	struct list_head	worklist;	/* L: list of pending works */
	unsigned int		cpu;		/* I: the associated cpu */
	unsigned int		flags;		/* L: GCWQ_* flags */

	int			nr_workers;	/* L: total number of workers */
	int			nr_idle;	/* L: currently idle ones */

	/* workers are chained either in the idle_list or busy_hash */
	struct list_head	idle_list;	/* X: list of idle workers */
	struct hlist_head	busy_hash[BUSY_WORKER_HASH_SIZE];
						/* L: hash of busy workers */

	struct timer_list	idle_timer;	/* L: worker idle timeout */
	struct timer_list	mayday_timer;	/* L: SOS timer for dworkers */

	struct ida		worker_ida;	/* L: for worker IDs */

	struct task_struct	*trustee;	/* L: for gcwq shutdown */
	unsigned int		trustee_state;	/* L: trustee state */
	wait_queue_head_t	trustee_wait;	/* trustee wait */
	struct worker		*first_idle;	/* L: first idle worker */
} ____cacheline_aligned_in_smp;

/*
 * The per-CPU workqueue.  The lower WORK_STRUCT_FLAG_BITS of
 * work_struct->data are used for flags and thus cwqs need to be
 * aligned at two's power of the number of flag bits.
 */
struct cpu_workqueue_struct {
	struct global_cwq	*gcwq;		/* I: the associated gcwq */
	struct workqueue_struct *wq;		/* I: the owning workqueue */
	int			work_color;	/* L: current color */
	int			flush_color;	/* L: flushing color */
	int			nr_in_flight[WORK_NR_COLORS];
						/* L: nr of in_flight works */
	int			nr_active;	/* L: nr of active works */
	int			max_active;	/* L: max active works */
	struct list_head	delayed_works;	/* L: delayed works */
};

/*
 * Structure used to wait for workqueue flush.
 */
struct wq_flusher {
	struct list_head	list;		/* F: list of flushers */
	int			flush_color;	/* F: flush color waiting for */
	struct completion	done;		/* flush completion */
};

/*
 * All cpumasks are assumed to be always set on UP and thus can't be
 * used to determine whether there's something to be done.
 */
#ifdef CONFIG_SMP
typedef cpumask_var_t mayday_mask_t;
#define mayday_test_and_set_cpu(cpu, mask)	\
	cpumask_test_and_set_cpu((cpu), (mask))
#define mayday_clear_cpu(cpu, mask)		cpumask_clear_cpu((cpu), (mask))
#define for_each_mayday_cpu(cpu, mask)		for_each_cpu((cpu), (mask))
#define alloc_mayday_mask(maskp, gfp)		zalloc_cpumask_var((maskp), (gfp))
#define free_mayday_mask(mask)			free_cpumask_var((mask))
#else
typedef unsigned long mayday_mask_t;
#define mayday_test_and_set_cpu(cpu, mask)	test_and_set_bit(0, &(mask))
#define mayday_clear_cpu(cpu, mask)		clear_bit(0, &(mask))
#define for_each_mayday_cpu(cpu, mask)		if ((cpu) = 0, (mask))
#define alloc_mayday_mask(maskp, gfp)		true
#define free_mayday_mask(mask)			do { } while (0)
#endif

/*
 * The externally visible workqueue abstraction is an array of
 * per-CPU workqueues:
 */
struct workqueue_struct {
	unsigned int		flags;		/* W: WQ_* flags */
	union {
		struct cpu_workqueue_struct __percpu	*pcpu;
		struct cpu_workqueue_struct		*single;
		unsigned long				v;
	} cpu_wq;				/* I: cwq's */
	struct list_head	list;		/* W: list of all workqueues */

	struct mutex		flush_mutex;	/* protects wq flushing */
	int			work_color;	/* F: current work color */
	int			flush_color;	/* F: current flush color */
	atomic_t		nr_cwqs_to_flush; /* flush in progress */
	struct wq_flusher	*first_flusher;	/* F: first flusher */
	struct list_head	flusher_queue;	/* F: flush waiters */
	struct list_head	flusher_overflow; /* F: flush overflow list */

	mayday_mask_t		mayday_mask;	/* cpus requesting rescue */
	struct worker		*rescuer;	/* I: rescue worker */

	int			nr_drainers;	/* W: drain in progress */
	int			saved_max_active; /* W: saved cwq max_active */
	const char		*name;		/* I: workqueue name */
#ifdef CONFIG_LOCKDEP
	struct lockdep_map	lockdep_map;
#endif
};

struct workqueue_struct *system_wq __read_mostly;
struct workqueue_struct *system_long_wq __read_mostly;
struct workqueue_struct *system_nrt_wq __read_mostly;
struct workqueue_struct *system_unbound_wq __read_mostly;
struct workqueue_struct *system_freezable_wq __read_mostly;
EXPORT_SYMBOL_GPL(system_wq);
EXPORT_SYMBOL_GPL(system_long_wq);
EXPORT_SYMBOL_GPL(system_nrt_wq);
EXPORT_SYMBOL_GPL(system_unbound_wq);
EXPORT_SYMBOL_GPL(system_freezable_wq);

#define CREATE_TRACE_POINTS
#include <trace/events/workqueue.h>

#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)

static inline int __next_gcwq_cpu(int cpu, const struct cpumask *mask,
				  unsigned int sw)
{
	if (cpu < nr_cpu_ids) {
		if (sw & 1) {
			cpu = cpumask_next(cpu, mask);
			if (cpu < nr_cpu_ids)
				return cpu;
		}
		if (sw & 2)
			return WORK_CPU_UNBOUND;
	}
	return WORK_CPU_NONE;
}

static inline int __next_wq_cpu(int cpu, const struct cpumask *mask,
				struct workqueue_struct *wq)
{
	return __next_gcwq_cpu(cpu, mask, !(wq->flags & WQ_UNBOUND) ? 1 : 2);
}

/*
 * CPU iterators
 *
 * An extra gcwq is defined for an invalid cpu number
 * (WORK_CPU_UNBOUND) to host workqueues which are not bound to any
 * specific CPU.  The following iterators are similar to
 * for_each_*_cpu() iterators but also considers the unbound gcwq.
 *
 * for_each_gcwq_cpu()		: possible CPUs + WORK_CPU_UNBOUND
 * for_each_online_gcwq_cpu()	: online CPUs + WORK_CPU_UNBOUND
 * for_each_cwq_cpu()		: possible CPUs for bound workqueues,
 *				  WORK_CPU_UNBOUND for unbound workqueues
 */
#define for_each_gcwq_cpu(cpu)						\
	for ((cpu) = __next_gcwq_cpu(-1, cpu_possible_mask, 3);		\
	     (cpu) < WORK_CPU_NONE;					\
	     (cpu) = __next_gcwq_cpu((cpu), cpu_possible_mask, 3))

#define for_each_online_gcwq_cpu(cpu)					\
	for ((cpu) = __next_gcwq_cpu(-1, cpu_online_mask, 3);		\
	     (cpu) < WORK_CPU_NONE;					\
	     (cpu) = __next_gcwq_cpu((cpu), cpu_online_mask, 3))

#define for_each_cwq_cpu(cpu, wq)					\
	for ((cpu) = __next_wq_cpu(-1, cpu_possible_mask, (wq));	\
	     (cpu) < WORK_CPU_NONE;					\
	     (cpu) = __next_wq_cpu((cpu), cpu_possible_mask, (wq)))

#ifdef CONFIG_DEBUG_OBJECTS_WORK

static struct debug_obj_descr work_debug_descr;

static void *work_debug_hint(void *addr)
{
	return ((struct work_struct *) addr)->func;
}

/*
 * fixup_init is called when:
 * - an active object is initialized
 */
static int work_fixup_init(void *addr, enum debug_obj_state state)
{
	struct work_struct *work = addr;

	switch (state) {
	case ODEBUG_STATE_ACTIVE:
		cancel_work_sync(work);
		debug_object_init(work, &work_debug_descr);
		return 1;
	default:
		return 0;
	}
}

/*
 * fixup_activate is called when:
 * - an active object is activated
 * - an unknown object is activated (might be a statically initialized object)
 */
static int work_fixup_activate(void *addr, enum debug_obj_state state)
{
	struct work_struct *work = addr;

	switch (state) {

	case ODEBUG_STATE_NOTAVAILABLE:
		/*
		 * This is not really a fixup. The work struct was
		 * statically initialized. We just make sure that it
		 * is tracked in the object tracker.
		 */
		if (test_bit(WORK_STRUCT_STATIC_BIT, work_data_bits(work))) {
			debug_object_init(work, &work_debug_descr);
			debug_object_activate(work, &work_debug_descr);
			return 0;
		}
		WARN_ON_ONCE(1);
		return 0;

	case ODEBUG_STATE_ACTIVE:
		WARN_ON(1);

	default:
		return 0;
	}
}

/*
 * fixup_free is called when:
 * - an active object is freed
 */
static int work_fixup_free(void *addr, enum debug_obj_state state)
{
	struct work_struct *work = addr;

	switch (state) {
	case ODEBUG_STATE_ACTIVE:
		cancel_work_sync(work);
		debug_object_free(work, &work_debug_descr);
		return 1;
	default:
		return 0;
	}
}

static struct debug_obj_descr work_debug_descr = {
	.name		= "work_struct",
	.debug_hint	= work_debug_hint,
	.fixup_init	= work_fixup_init,
	.fixup_activate	= work_fixup_activate,
	.fixup_free	= work_fixup_free,
};

static inline void debug_work_activate(struct work_struct *work)
{
	debug_object_activate(work, &work_debug_descr);
}

static inline void debug_work_deactivate(struct work_struct *work)
{
	debug_object_deactivate(work, &work_debug_descr);
}

void __init_work(struct work_struct *work, int onstack)
{
	if (onstack)
		debug_object_init_on_stack(work, &work_debug_descr);
	else
		debug_object_init(work, &work_debug_descr);
}
EXPORT_SYMBOL_GPL(__init_work);

void destroy_work_on_stack(struct work_struct *work)
{
	debug_object_free(work, &work_debug_descr);
}
EXPORT_SYMBOL_GPL(destroy_work_on_stack);

#else
static inline void debug_work_activate(struct work_struct *work) { }
static inline void debug_work_deactivate(struct work_struct *work) { }
#endif

/* Serializes the accesses to the list of workqueues. */
static DEFINE_SPINLOCK(workqueue_lock);
static LIST_HEAD(workqueues);
static bool workqueue_freezing;		/* W: have wqs started freezing? */

/*
 * The almighty global cpu workqueues.  nr_running is the only field
 * which is expected to be used frequently by other cpus via
 * 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, gcwq_nr_running);

/*
 * Global cpu workqueue and nr_running counter for unbound gcwq.  The
 * gcwq is always online, has GCWQ_DISASSOCIATED set, and all its
 * workers have WORKER_UNBOUND set.
 */
static struct global_cwq unbound_global_cwq;
static atomic_t unbound_gcwq_nr_running = ATOMIC_INIT(0);	/* always 0 */

static int worker_thread(void *__worker);

static struct global_cwq *get_gcwq(unsigned int cpu)
{
	if (cpu != WORK_CPU_UNBOUND)
		return &per_cpu(global_cwq, cpu);
	else
		return &unbound_global_cwq;
}

static atomic_t *get_gcwq_nr_running(unsigned int cpu)
{
	if (cpu != WORK_CPU_UNBOUND)
		return &per_cpu(gcwq_nr_running, cpu);
	else
		return &unbound_gcwq_nr_running;
}

static struct cpu_workqueue_struct *get_cwq(unsigned int cpu,
					    struct workqueue_struct *wq)
{
	if (!(wq->flags & WQ_UNBOUND)) {
		if (likely(cpu < nr_cpu_ids)) {
#ifdef CONFIG_SMP
			return per_cpu_ptr(wq->cpu_wq.pcpu, cpu);
#else
			return wq->cpu_wq.single;
#endif
		}
	} else if (likely(cpu == WORK_CPU_UNBOUND))
		return wq->cpu_wq.single;
	return NULL;
}

static unsigned int work_color_to_flags(int color)
{
	return color << WORK_STRUCT_COLOR_SHIFT;
}

static int get_work_color(struct work_struct *work)
{
	return (*work_data_bits(work) >> WORK_STRUCT_COLOR_SHIFT) &
		((1 << WORK_STRUCT_COLOR_BITS) - 1);
}

static int work_next_color(int color)
{
	return (color + 1) % WORK_NR_COLORS;
}

/*
 * A work's data points to the cwq with WORK_STRUCT_CWQ set while the
 * work is on queue.  Once execution starts, WORK_STRUCT_CWQ is
 * cleared and the work data contains the cpu number it was last on.
 *
 * set_work_{cwq|cpu}() and clear_work_data() can be used to set the
Mode	Name	Size
-rw-r--r--	Kconfig	24815	log stats plain blame
-rw-r--r--	Kconfig-nommu	1318	log stats plain blame
-rw-r--r--	Kconfig.debug	3845	log stats plain blame
-rw-r--r--	Makefile	7957	log stats plain blame
d---------	boot	143	log stats plain
d---------	common	593	log stats plain
d---------	configs	2304	log stats plain
d---------	kernel	1428	log stats plain
d---------	lib	2091	log stats plain
d---------	mach-aaec2000	288	log stats plain
d---------	mach-at91rm9200	552	log stats plain
d---------	mach-clps711x	591	log stats plain
d---------	mach-clps7500	111	log stats plain
d---------	mach-ebsa110	177	log stats plain
d---------	mach-ep93xx	221	log stats plain
d---------	mach-footbridge	879	log stats plain
d---------	mach-h720x	342	log stats plain
d---------	mach-imx	431	log stats plain
d---------	mach-integrator	649	log stats plain
d---------	mach-iop3xx	798	log stats plain
d---------	mach-ixp2000	368	log stats plain
d---------	mach-ixp23xx	295	log stats plain
d---------	mach-ixp4xx	730	log stats plain
d---------	mach-l7200	111	log stats plain
d---------	mach-lh7a40x	434	log stats plain
d---------	mach-omap1	1138	log stats plain
d---------	mach-omap2	796	log stats plain
d---------	mach-pxa	1279	log stats plain
d---------	mach-realview	442	log stats plain
d---------	mach-rpc	179	log stats plain
d---------	mach-s3c2410	1698	log stats plain
d---------	mach-sa1100	1286	log stats plain
d---------	mach-shark	244	log stats plain
d---------	mach-versatile	367	log stats plain
d---------	mm	2197	log stats plain
d---------	nwfpe	966	log stats plain
d---------	oprofile	273	log stats plain
d---------	plat-omap	629	log stats plain
d---------	tools	116	log stats plain
d---------	vfp	294	log stats plain