linux-sg2042/kernel/workqueue.c

3790 lines
104 KiB
C
Raw Normal View History

/*
* 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 <linux/hashtable.h>
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
#include "workqueue_internal.h"
enum {
/*
* worker_pool flags
2012-07-18 03:39:27 +08:00
*
* A bound pool is either associated or disassociated with its CPU.
2012-07-18 03:39:27 +08:00
* While associated (!DISASSOCIATED), all workers are bound to the
* CPU and none has %WORKER_UNBOUND set and concurrency management
* is in effect.
*
* While DISASSOCIATED, the cpu may be offline and all workers have
* %WORKER_UNBOUND set and concurrency management disabled, and may
* be executing on any CPU. The pool behaves as an unbound one.
2012-07-18 03:39:27 +08:00
*
* Note that DISASSOCIATED can be flipped only while holding
* assoc_mutex to avoid changing binding state while
* create_worker() is in progress.
2012-07-18 03:39:27 +08:00
*/
POOL_MANAGE_WORKERS = 1 << 0, /* need to manage workers */
POOL_MANAGING_WORKERS = 1 << 1, /* managing workers */
POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */
POOL_FREEZING = 1 << 3, /* freeze in progress */
/* worker flags */
WORKER_STARTED = 1 << 0, /* started */
WORKER_DIE = 1 << 1, /* die die die */
WORKER_IDLE = 1 << 2, /* is idle */
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
WORKER_PREP = 1 << 3, /* preparing to run works */
WORKER_CPU_INTENSIVE = 1 << 6, /* cpu intensive */
WORKER_UNBOUND = 1 << 7, /* worker is unbound */
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
WORKER_NOT_RUNNING = WORKER_PREP | WORKER_UNBOUND |
WORKER_CPU_INTENSIVE,
NR_STD_WORKER_POOLS = 2, /* # standard pools per cpu */
BUSY_WORKER_HASH_ORDER = 6, /* 64 pointers */
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
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) */
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */
CREATE_COOLDOWN = HZ, /* time to breath after fail */
/*
* Rescue workers are used only on emergencies and shared by
* all cpus. Give -20.
*/
RESCUER_NICE_LEVEL = -20,
HIGHPRI_NICE_LEVEL = -20,
};
/*
* Structure fields follow one of the following exclusion rules.
*
* I: Modifiable by initialization/destruction paths and read-only for
* everyone else.
*
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* P: Preemption protected. Disabling preemption is enough and should
* only be modified and accessed from the local cpu.
*
* L: pool->lock protected. Access with pool->lock held.
*
* X: During normal operation, modification requires pool->lock and should
* be done only from local cpu. Either disabling preemption on local
* cpu or grabbing pool->lock is enough for read access. If
* POOL_DISASSOCIATED is set, it's identical to L.
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
*
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
* F: wq->flush_mutex protected.
*
* W: workqueue_lock protected.
*/
/* struct worker is defined in workqueue_internal.h */
struct worker_pool {
spinlock_t lock; /* the pool lock */
unsigned int cpu; /* I: the associated cpu */
int id; /* I: pool ID */
unsigned int flags; /* X: flags */
struct list_head worklist; /* L: list of pending works */
int nr_workers; /* L: total number of workers */
workqueue: reimplement idle worker rebinding Currently rebind_workers() uses rebinds idle workers synchronously before proceeding to requesting busy workers to rebind. This is necessary because all workers on @worker_pool->idle_list must be bound before concurrency management local wake-ups from the busy workers take place. Unfortunately, the synchronous idle rebinding is quite complicated. This patch reimplements idle rebinding to simplify the code path. Rather than trying to make all idle workers bound before rebinding busy workers, we simply remove all to-be-bound idle workers from the idle list and let them add themselves back after completing rebinding (successful or not). As only workers which finished rebinding can on on the idle worker list, the idle worker list is guaranteed to have only bound workers unless CPU went down again and local wake-ups are safe. After the change, @worker_pool->nr_idle may deviate than the actual number of idle workers on @worker_pool->idle_list. More specifically, nr_idle may be non-zero while ->idle_list is empty. All users of ->nr_idle and ->idle_list are audited. The only affected one is too_many_workers() which is updated to check %false if ->idle_list is empty regardless of ->nr_idle. After this patch, rebind_workers() no longer performs the nasty idle-rebind retries which require temporary release of gcwq->lock, and both unbinding and rebinding are atomic w.r.t. global_cwq->lock. worker->idle_rebind and global_cwq->rebind_hold are now unnecessary and removed along with the definition of struct idle_rebind. Changed from V1: 1) remove unlikely from too_many_workers(), ->idle_list can be empty anytime, even before this patch, no reason to use unlikely. 2) fix a small rebasing mistake. (which is from rebasing the orignal fixing patch to for-next) 3) add a lot of comments. 4) clear WORKER_REBIND unconditionaly in idle_worker_rebind() tj: Updated comments and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2012-09-19 00:59:22 +08:00
/* nr_idle includes the ones off idle_list for rebinding */
int nr_idle; /* L: currently idle ones */
struct list_head idle_list; /* X: list of idle workers */
struct timer_list idle_timer; /* L: worker idle timeout */
struct timer_list mayday_timer; /* L: SOS timer for workers */
/* workers are chained either in busy_hash or idle_list */
DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER);
/* L: hash of busy workers */
struct mutex assoc_mutex; /* protect POOL_DISASSOCIATED */
struct ida worker_ida; /* L: for worker IDs */
/*
* The current concurrency level. As it's likely to be accessed
* from other CPUs during try_to_wake_up(), put it in a separate
* cacheline.
*/
atomic_t nr_running ____cacheline_aligned_in_smp;
} ____cacheline_aligned_in_smp;
/*
* The per-pool workqueue. While queued, the lower WORK_STRUCT_FLAG_BITS
* of work_struct->data are used for flags and the remaining high bits
* point to the pwq; thus, pwqs need to be aligned at two's power of the
* number of flag bits.
*/
struct pool_workqueue {
struct worker_pool *pool; /* I: the associated pool */
struct workqueue_struct *wq; /* I: the owning workqueue */
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
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 */
};
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
/*
* 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 pool_workqueue __percpu *pcpu;
struct pool_workqueue *single;
unsigned long v;
} pool_wq; /* I: pwq's */
struct list_head list; /* W: list of all workqueues */
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
struct mutex flush_mutex; /* protects wq flushing */
int work_color; /* F: current work color */
int flush_color; /* F: current flush color */
atomic_t nr_pwqs_to_flush; /* flush in progress */
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
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 */
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
struct worker *rescuer; /* I: rescue worker */
int nr_drainers; /* W: drain in progress */
int saved_max_active; /* W: saved pwq max_active */
#ifdef CONFIG_LOCKDEP
struct lockdep_map lockdep_map;
#endif
char name[]; /* I: workqueue name */
};
struct workqueue_struct *system_wq __read_mostly;
EXPORT_SYMBOL_GPL(system_wq);
struct workqueue_struct *system_highpri_wq __read_mostly;
EXPORT_SYMBOL_GPL(system_highpri_wq);
struct workqueue_struct *system_long_wq __read_mostly;
EXPORT_SYMBOL_GPL(system_long_wq);
struct workqueue_struct *system_unbound_wq __read_mostly;
EXPORT_SYMBOL_GPL(system_unbound_wq);
struct workqueue_struct *system_freezable_wq __read_mostly;
EXPORT_SYMBOL_GPL(system_freezable_wq);
#define CREATE_TRACE_POINTS
#include <trace/events/workqueue.h>
#define for_each_std_worker_pool(pool, cpu) \
for ((pool) = &std_worker_pools(cpu)[0]; \
(pool) < &std_worker_pools(cpu)[NR_STD_WORKER_POOLS]; (pool)++)
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:06:00 +08:00
#define for_each_busy_worker(worker, i, pool) \
hash_for_each(pool->busy_hash, i, worker, hentry)
static inline int __next_wq_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_END;
}
static inline int __next_pwq_cpu(int cpu, const struct cpumask *mask,
struct workqueue_struct *wq)
{
return __next_wq_cpu(cpu, mask, !(wq->flags & WQ_UNBOUND) ? 1 : 2);
}
/*
* CPU iterators
*
* An extra cpu number is defined using 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 CPU.
*
* for_each_wq_cpu() : possible CPUs + WORK_CPU_UNBOUND
* for_each_online_wq_cpu() : online CPUs + WORK_CPU_UNBOUND
* for_each_pwq_cpu() : possible CPUs for bound workqueues,
* WORK_CPU_UNBOUND for unbound workqueues
*/
#define for_each_wq_cpu(cpu) \
for ((cpu) = __next_wq_cpu(-1, cpu_possible_mask, 3); \
(cpu) < WORK_CPU_END; \
(cpu) = __next_wq_cpu((cpu), cpu_possible_mask, 3))
#define for_each_online_wq_cpu(cpu) \
for ((cpu) = __next_wq_cpu(-1, cpu_online_mask, 3); \
(cpu) < WORK_CPU_END; \
(cpu) = __next_wq_cpu((cpu), cpu_online_mask, 3))
#define for_each_pwq_cpu(cpu, wq) \
for ((cpu) = __next_pwq_cpu(-1, cpu_possible_mask, (wq)); \
(cpu) < WORK_CPU_END; \
(cpu) = __next_pwq_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? */
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/*
* The CPU and unbound standard worker pools. The unbound ones have
* POOL_DISASSOCIATED set, and their workers have WORKER_UNBOUND set.
*/
static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS],
cpu_std_worker_pools);
static struct worker_pool unbound_std_worker_pools[NR_STD_WORKER_POOLS];
/* idr of all pools */
static DEFINE_MUTEX(worker_pool_idr_mutex);
static DEFINE_IDR(worker_pool_idr);
static int worker_thread(void *__worker);
static struct worker_pool *std_worker_pools(int cpu)
{
if (cpu != WORK_CPU_UNBOUND)
return per_cpu(cpu_std_worker_pools, cpu);
else
return unbound_std_worker_pools;
}
static int std_worker_pool_pri(struct worker_pool *pool)
{
return pool - std_worker_pools(pool->cpu);
}
/* allocate ID and assign it to @pool */
static int worker_pool_assign_id(struct worker_pool *pool)
{
int ret;
mutex_lock(&worker_pool_idr_mutex);
idr_pre_get(&worker_pool_idr, GFP_KERNEL);
ret = idr_get_new(&worker_pool_idr, pool, &pool->id);
mutex_unlock(&worker_pool_idr_mutex);
return ret;
}
/*
* Lookup worker_pool by id. The idr currently is built during boot and
* never modified. Don't worry about locking for now.
*/
static struct worker_pool *worker_pool_by_id(int pool_id)
{
return idr_find(&worker_pool_idr, pool_id);
}
static struct worker_pool *get_std_worker_pool(int cpu, bool highpri)
{
struct worker_pool *pools = std_worker_pools(cpu);
return &pools[highpri];
}
static struct pool_workqueue *get_pwq(unsigned int cpu,
struct workqueue_struct *wq)
{
if (!(wq->flags & WQ_UNBOUND)) {
if (likely(cpu < nr_cpu_ids))
return per_cpu_ptr(wq->pool_wq.pcpu, cpu);
} else if (likely(cpu == WORK_CPU_UNBOUND))
return wq->pool_wq.single;
return NULL;
}
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
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;
}
/*
* While queued, %WORK_STRUCT_PWQ is set and non flag bits of a work's data
* contain the pointer to the queued pwq. Once execution starts, the flag
* is cleared and the high bits contain OFFQ flags and pool ID.
*
* set_work_pwq(), set_work_pool_and_clear_pending(), mark_work_canceling()
* and clear_work_data() can be used to set the pwq, pool or clear
workqueue: mark a work item being canceled as such There can be two reasons try_to_grab_pending() can fail with -EAGAIN. One is when someone else is queueing or deqeueing the work item. With the previous patches, it is guaranteed that PENDING and queued state will soon agree making it safe to busy-retry in this case. The other is if multiple __cancel_work_timer() invocations are racing one another. __cancel_work_timer() grabs PENDING and then waits for running instances of the target work item on all CPUs while holding PENDING and !queued. try_to_grab_pending() invoked from another task will keep returning -EAGAIN while the current owner is waiting. Not distinguishing the two cases is okay because __cancel_work_timer() is the only user of try_to_grab_pending() and it invokes wait_on_work() whenever grabbing fails. For the first case, busy looping should be fine but wait_on_work() doesn't cause any critical problem. For the latter case, the new contender usually waits for the same condition as the current owner, so no unnecessarily extended busy-looping happens. Combined, these make __cancel_work_timer() technically correct even without irq protection while grabbing PENDING or distinguishing the two different cases. While the current code is technically correct, not distinguishing the two cases makes it difficult to use try_to_grab_pending() for other purposes than canceling because it's impossible to tell whether it's safe to busy-retry grabbing. This patch adds a mechanism to mark a work item being canceled. try_to_grab_pending() now disables irq on success and returns -EAGAIN to indicate that grabbing failed but PENDING and queued states are gonna agree soon and it's safe to busy-loop. It returns -ENOENT if the work item is being canceled and it may stay PENDING && !queued for arbitrary amount of time. __cancel_work_timer() is modified to mark the work canceling with WORK_OFFQ_CANCELING after grabbing PENDING, thus making try_to_grab_pending() fail with -ENOENT instead of -EAGAIN. Also, it invokes wait_on_work() iff grabbing failed with -ENOENT. This isn't necessary for correctness but makes it consistent with other future users of try_to_grab_pending(). v2: try_to_grab_pending() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Updated so that try_to_grab_pending() disables irq on success rather than requiring preemption disabled by the caller. This makes busy-looping easier and will allow try_to_grap_pending() to be used from bh/irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:46 +08:00
* work->data. These functions should only be called while the work is
* owned - ie. while the PENDING bit is set.
*
* get_work_pool() and get_work_pwq() can be used to obtain the pool or pwq
* corresponding to a work. Pool is available once the work has been
* queued anywhere after initialization until it is sync canceled. pwq is
* available only while the work item is queued.
*
workqueue: mark a work item being canceled as such There can be two reasons try_to_grab_pending() can fail with -EAGAIN. One is when someone else is queueing or deqeueing the work item. With the previous patches, it is guaranteed that PENDING and queued state will soon agree making it safe to busy-retry in this case. The other is if multiple __cancel_work_timer() invocations are racing one another. __cancel_work_timer() grabs PENDING and then waits for running instances of the target work item on all CPUs while holding PENDING and !queued. try_to_grab_pending() invoked from another task will keep returning -EAGAIN while the current owner is waiting. Not distinguishing the two cases is okay because __cancel_work_timer() is the only user of try_to_grab_pending() and it invokes wait_on_work() whenever grabbing fails. For the first case, busy looping should be fine but wait_on_work() doesn't cause any critical problem. For the latter case, the new contender usually waits for the same condition as the current owner, so no unnecessarily extended busy-looping happens. Combined, these make __cancel_work_timer() technically correct even without irq protection while grabbing PENDING or distinguishing the two different cases. While the current code is technically correct, not distinguishing the two cases makes it difficult to use try_to_grab_pending() for other purposes than canceling because it's impossible to tell whether it's safe to busy-retry grabbing. This patch adds a mechanism to mark a work item being canceled. try_to_grab_pending() now disables irq on success and returns -EAGAIN to indicate that grabbing failed but PENDING and queued states are gonna agree soon and it's safe to busy-loop. It returns -ENOENT if the work item is being canceled and it may stay PENDING && !queued for arbitrary amount of time. __cancel_work_timer() is modified to mark the work canceling with WORK_OFFQ_CANCELING after grabbing PENDING, thus making try_to_grab_pending() fail with -ENOENT instead of -EAGAIN. Also, it invokes wait_on_work() iff grabbing failed with -ENOENT. This isn't necessary for correctness but makes it consistent with other future users of try_to_grab_pending(). v2: try_to_grab_pending() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Updated so that try_to_grab_pending() disables irq on success rather than requiring preemption disabled by the caller. This makes busy-looping easier and will allow try_to_grap_pending() to be used from bh/irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:46 +08:00
* %WORK_OFFQ_CANCELING is used to mark a work item which is being
* canceled. While being canceled, a work item may have its PENDING set
* but stay off timer and worklist for arbitrarily long and nobody should
* try to steal the PENDING bit.
*/
static inline void set_work_data(struct work_struct *work, unsigned long data,
unsigned long flags)
{
[PATCH] WorkStruct: Use direct assignment rather than cmpxchg() Use direct assignment rather than cmpxchg() as the latter is unavailable and unimplementable on some platforms and is actually unnecessary. The use of cmpxchg() was to guard against two possibilities, neither of which can actually occur: (1) The pending flag may have been unset or may be cleared. However, given where it's called, the pending flag is _always_ set. I don't think it can be unset whilst we're in set_wq_data(). Once the work is enqueued to be actually run, the only way off the queue is for it to be actually run. If it's a delayed work item, then the bit can't be cleared by the timer because we haven't started the timer yet. Also, the pending bit can't be cleared by cancelling the delayed work _until_ the work item has had its timer started. (2) The workqueue pointer might change. This can only happen in two cases: (a) The work item has just been queued to actually run, and so we're protected by the appropriate workqueue spinlock. (b) A delayed work item is being queued, and so the timer hasn't been started yet, and so no one else knows about the work item or can access it (the pending bit protects us). Besides, set_wq_data() _sets_ the workqueue pointer unconditionally, so it can be assigned instead. So, replacing the set_wq_data() with a straight assignment would be okay in most cases. The problem is where we end up tangling with test_and_set_bit() emulated using spinlocks, and even then it's not a problem _provided_ test_and_set_bit() doesn't attempt to modify the word if the bit was set. If that's a problem, then a bitops-proofed assignment will be required - equivalent to atomic_set() vs other atomic_xxx() ops. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-07 19:33:26 +08:00
BUG_ON(!work_pending(work));
atomic_long_set(&work->data, data | flags | work_static(work));
}
static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq,
unsigned long extra_flags)
{
set_work_data(work, (unsigned long)pwq,
WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | extra_flags);
}
static void set_work_pool_and_keep_pending(struct work_struct *work,
int pool_id)
{
set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT,
WORK_STRUCT_PENDING);
}
static void set_work_pool_and_clear_pending(struct work_struct *work,
int pool_id)
{
/*
* The following wmb is paired with the implied mb in
* test_and_set_bit(PENDING) and ensures all updates to @work made
* here are visible to and precede any updates by the next PENDING
* owner.
*/
smp_wmb();
set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, 0);
}
static void clear_work_data(struct work_struct *work)
{
smp_wmb(); /* see set_work_pool_and_clear_pending() */
set_work_data(work, WORK_STRUCT_NO_POOL, 0);
}
static struct pool_workqueue *get_work_pwq(struct work_struct *work)
{
unsigned long data = atomic_long_read(&work->data);
if (data & WORK_STRUCT_PWQ)
return (void *)(data & WORK_STRUCT_WQ_DATA_MASK);
else
return NULL;
}
/**
* 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.
*/
static struct worker_pool *get_work_pool(struct work_struct *work)
{
unsigned long data = atomic_long_read(&work->data);
struct worker_pool *pool;
int pool_id;
if (data & WORK_STRUCT_PWQ)
return ((struct pool_workqueue *)
(data & WORK_STRUCT_WQ_DATA_MASK))->pool;
pool_id = data >> WORK_OFFQ_POOL_SHIFT;
if (pool_id == WORK_OFFQ_POOL_NONE)
return NULL;
pool = worker_pool_by_id(pool_id);
WARN_ON_ONCE(!pool);
return pool;
}
/**
* 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.
* %WORK_OFFQ_POOL_NONE if none.
*/
static int get_work_pool_id(struct work_struct *work)
{
unsigned long data = atomic_long_read(&work->data);
if (data & WORK_STRUCT_PWQ)
return ((struct pool_workqueue *)
(data & WORK_STRUCT_WQ_DATA_MASK))->pool->id;
return data >> WORK_OFFQ_POOL_SHIFT;
}
workqueue: mark a work item being canceled as such There can be two reasons try_to_grab_pending() can fail with -EAGAIN. One is when someone else is queueing or deqeueing the work item. With the previous patches, it is guaranteed that PENDING and queued state will soon agree making it safe to busy-retry in this case. The other is if multiple __cancel_work_timer() invocations are racing one another. __cancel_work_timer() grabs PENDING and then waits for running instances of the target work item on all CPUs while holding PENDING and !queued. try_to_grab_pending() invoked from another task will keep returning -EAGAIN while the current owner is waiting. Not distinguishing the two cases is okay because __cancel_work_timer() is the only user of try_to_grab_pending() and it invokes wait_on_work() whenever grabbing fails. For the first case, busy looping should be fine but wait_on_work() doesn't cause any critical problem. For the latter case, the new contender usually waits for the same condition as the current owner, so no unnecessarily extended busy-looping happens. Combined, these make __cancel_work_timer() technically correct even without irq protection while grabbing PENDING or distinguishing the two different cases. While the current code is technically correct, not distinguishing the two cases makes it difficult to use try_to_grab_pending() for other purposes than canceling because it's impossible to tell whether it's safe to busy-retry grabbing. This patch adds a mechanism to mark a work item being canceled. try_to_grab_pending() now disables irq on success and returns -EAGAIN to indicate that grabbing failed but PENDING and queued states are gonna agree soon and it's safe to busy-loop. It returns -ENOENT if the work item is being canceled and it may stay PENDING && !queued for arbitrary amount of time. __cancel_work_timer() is modified to mark the work canceling with WORK_OFFQ_CANCELING after grabbing PENDING, thus making try_to_grab_pending() fail with -ENOENT instead of -EAGAIN. Also, it invokes wait_on_work() iff grabbing failed with -ENOENT. This isn't necessary for correctness but makes it consistent with other future users of try_to_grab_pending(). v2: try_to_grab_pending() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Updated so that try_to_grab_pending() disables irq on success rather than requiring preemption disabled by the caller. This makes busy-looping easier and will allow try_to_grap_pending() to be used from bh/irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:46 +08:00
static void mark_work_canceling(struct work_struct *work)
{
unsigned long pool_id = get_work_pool_id(work);
workqueue: mark a work item being canceled as such There can be two reasons try_to_grab_pending() can fail with -EAGAIN. One is when someone else is queueing or deqeueing the work item. With the previous patches, it is guaranteed that PENDING and queued state will soon agree making it safe to busy-retry in this case. The other is if multiple __cancel_work_timer() invocations are racing one another. __cancel_work_timer() grabs PENDING and then waits for running instances of the target work item on all CPUs while holding PENDING and !queued. try_to_grab_pending() invoked from another task will keep returning -EAGAIN while the current owner is waiting. Not distinguishing the two cases is okay because __cancel_work_timer() is the only user of try_to_grab_pending() and it invokes wait_on_work() whenever grabbing fails. For the first case, busy looping should be fine but wait_on_work() doesn't cause any critical problem. For the latter case, the new contender usually waits for the same condition as the current owner, so no unnecessarily extended busy-looping happens. Combined, these make __cancel_work_timer() technically correct even without irq protection while grabbing PENDING or distinguishing the two different cases. While the current code is technically correct, not distinguishing the two cases makes it difficult to use try_to_grab_pending() for other purposes than canceling because it's impossible to tell whether it's safe to busy-retry grabbing. This patch adds a mechanism to mark a work item being canceled. try_to_grab_pending() now disables irq on success and returns -EAGAIN to indicate that grabbing failed but PENDING and queued states are gonna agree soon and it's safe to busy-loop. It returns -ENOENT if the work item is being canceled and it may stay PENDING && !queued for arbitrary amount of time. __cancel_work_timer() is modified to mark the work canceling with WORK_OFFQ_CANCELING after grabbing PENDING, thus making try_to_grab_pending() fail with -ENOENT instead of -EAGAIN. Also, it invokes wait_on_work() iff grabbing failed with -ENOENT. This isn't necessary for correctness but makes it consistent with other future users of try_to_grab_pending(). v2: try_to_grab_pending() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Updated so that try_to_grab_pending() disables irq on success rather than requiring preemption disabled by the caller. This makes busy-looping easier and will allow try_to_grap_pending() to be used from bh/irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:46 +08:00
pool_id <<= WORK_OFFQ_POOL_SHIFT;
set_work_data(work, pool_id | WORK_OFFQ_CANCELING, WORK_STRUCT_PENDING);
workqueue: mark a work item being canceled as such There can be two reasons try_to_grab_pending() can fail with -EAGAIN. One is when someone else is queueing or deqeueing the work item. With the previous patches, it is guaranteed that PENDING and queued state will soon agree making it safe to busy-retry in this case. The other is if multiple __cancel_work_timer() invocations are racing one another. __cancel_work_timer() grabs PENDING and then waits for running instances of the target work item on all CPUs while holding PENDING and !queued. try_to_grab_pending() invoked from another task will keep returning -EAGAIN while the current owner is waiting. Not distinguishing the two cases is okay because __cancel_work_timer() is the only user of try_to_grab_pending() and it invokes wait_on_work() whenever grabbing fails. For the first case, busy looping should be fine but wait_on_work() doesn't cause any critical problem. For the latter case, the new contender usually waits for the same condition as the current owner, so no unnecessarily extended busy-looping happens. Combined, these make __cancel_work_timer() technically correct even without irq protection while grabbing PENDING or distinguishing the two different cases. While the current code is technically correct, not distinguishing the two cases makes it difficult to use try_to_grab_pending() for other purposes than canceling because it's impossible to tell whether it's safe to busy-retry grabbing. This patch adds a mechanism to mark a work item being canceled. try_to_grab_pending() now disables irq on success and returns -EAGAIN to indicate that grabbing failed but PENDING and queued states are gonna agree soon and it's safe to busy-loop. It returns -ENOENT if the work item is being canceled and it may stay PENDING && !queued for arbitrary amount of time. __cancel_work_timer() is modified to mark the work canceling with WORK_OFFQ_CANCELING after grabbing PENDING, thus making try_to_grab_pending() fail with -ENOENT instead of -EAGAIN. Also, it invokes wait_on_work() iff grabbing failed with -ENOENT. This isn't necessary for correctness but makes it consistent with other future users of try_to_grab_pending(). v2: try_to_grab_pending() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Updated so that try_to_grab_pending() disables irq on success rather than requiring preemption disabled by the caller. This makes busy-looping easier and will allow try_to_grap_pending() to be used from bh/irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:46 +08:00
}
static bool work_is_canceling(struct work_struct *work)
{
unsigned long data = atomic_long_read(&work->data);
return !(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_CANCELING);
workqueue: mark a work item being canceled as such There can be two reasons try_to_grab_pending() can fail with -EAGAIN. One is when someone else is queueing or deqeueing the work item. With the previous patches, it is guaranteed that PENDING and queued state will soon agree making it safe to busy-retry in this case. The other is if multiple __cancel_work_timer() invocations are racing one another. __cancel_work_timer() grabs PENDING and then waits for running instances of the target work item on all CPUs while holding PENDING and !queued. try_to_grab_pending() invoked from another task will keep returning -EAGAIN while the current owner is waiting. Not distinguishing the two cases is okay because __cancel_work_timer() is the only user of try_to_grab_pending() and it invokes wait_on_work() whenever grabbing fails. For the first case, busy looping should be fine but wait_on_work() doesn't cause any critical problem. For the latter case, the new contender usually waits for the same condition as the current owner, so no unnecessarily extended busy-looping happens. Combined, these make __cancel_work_timer() technically correct even without irq protection while grabbing PENDING or distinguishing the two different cases. While the current code is technically correct, not distinguishing the two cases makes it difficult to use try_to_grab_pending() for other purposes than canceling because it's impossible to tell whether it's safe to busy-retry grabbing. This patch adds a mechanism to mark a work item being canceled. try_to_grab_pending() now disables irq on success and returns -EAGAIN to indicate that grabbing failed but PENDING and queued states are gonna agree soon and it's safe to busy-loop. It returns -ENOENT if the work item is being canceled and it may stay PENDING && !queued for arbitrary amount of time. __cancel_work_timer() is modified to mark the work canceling with WORK_OFFQ_CANCELING after grabbing PENDING, thus making try_to_grab_pending() fail with -ENOENT instead of -EAGAIN. Also, it invokes wait_on_work() iff grabbing failed with -ENOENT. This isn't necessary for correctness but makes it consistent with other future users of try_to_grab_pending(). v2: try_to_grab_pending() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Updated so that try_to_grab_pending() disables irq on success rather than requiring preemption disabled by the caller. This makes busy-looping easier and will allow try_to_grap_pending() to be used from bh/irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:46 +08:00
}
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/*
* Policy functions. These define the policies on how the global worker
* pools are managed. Unless noted otherwise, these functions assume that
* they're being called with pool->lock held.
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
*/
static bool __need_more_worker(struct worker_pool *pool)
{
return !atomic_read(&pool->nr_running);
}
[PATCH] WorkStruct: Use direct assignment rather than cmpxchg() Use direct assignment rather than cmpxchg() as the latter is unavailable and unimplementable on some platforms and is actually unnecessary. The use of cmpxchg() was to guard against two possibilities, neither of which can actually occur: (1) The pending flag may have been unset or may be cleared. However, given where it's called, the pending flag is _always_ set. I don't think it can be unset whilst we're in set_wq_data(). Once the work is enqueued to be actually run, the only way off the queue is for it to be actually run. If it's a delayed work item, then the bit can't be cleared by the timer because we haven't started the timer yet. Also, the pending bit can't be cleared by cancelling the delayed work _until_ the work item has had its timer started. (2) The workqueue pointer might change. This can only happen in two cases: (a) The work item has just been queued to actually run, and so we're protected by the appropriate workqueue spinlock. (b) A delayed work item is being queued, and so the timer hasn't been started yet, and so no one else knows about the work item or can access it (the pending bit protects us). Besides, set_wq_data() _sets_ the workqueue pointer unconditionally, so it can be assigned instead. So, replacing the set_wq_data() with a straight assignment would be okay in most cases. The problem is where we end up tangling with test_and_set_bit() emulated using spinlocks, and even then it's not a problem _provided_ test_and_set_bit() doesn't attempt to modify the word if the bit was set. If that's a problem, then a bitops-proofed assignment will be required - equivalent to atomic_set() vs other atomic_xxx() ops. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-07 19:33:26 +08:00
/*
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* Need to wake up a worker? Called from anything but currently
* running workers.
*
* Note that, because unbound workers never contribute to nr_running, this
* function will always return %true for unbound pools as long as the
* worklist isn't empty.
[PATCH] WorkStruct: Use direct assignment rather than cmpxchg() Use direct assignment rather than cmpxchg() as the latter is unavailable and unimplementable on some platforms and is actually unnecessary. The use of cmpxchg() was to guard against two possibilities, neither of which can actually occur: (1) The pending flag may have been unset or may be cleared. However, given where it's called, the pending flag is _always_ set. I don't think it can be unset whilst we're in set_wq_data(). Once the work is enqueued to be actually run, the only way off the queue is for it to be actually run. If it's a delayed work item, then the bit can't be cleared by the timer because we haven't started the timer yet. Also, the pending bit can't be cleared by cancelling the delayed work _until_ the work item has had its timer started. (2) The workqueue pointer might change. This can only happen in two cases: (a) The work item has just been queued to actually run, and so we're protected by the appropriate workqueue spinlock. (b) A delayed work item is being queued, and so the timer hasn't been started yet, and so no one else knows about the work item or can access it (the pending bit protects us). Besides, set_wq_data() _sets_ the workqueue pointer unconditionally, so it can be assigned instead. So, replacing the set_wq_data() with a straight assignment would be okay in most cases. The problem is where we end up tangling with test_and_set_bit() emulated using spinlocks, and even then it's not a problem _provided_ test_and_set_bit() doesn't attempt to modify the word if the bit was set. If that's a problem, then a bitops-proofed assignment will be required - equivalent to atomic_set() vs other atomic_xxx() ops. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-07 19:33:26 +08:00
*/
static bool need_more_worker(struct worker_pool *pool)
{
return !list_empty(&pool->worklist) && __need_more_worker(pool);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
}
[PATCH] WorkStruct: Use direct assignment rather than cmpxchg() Use direct assignment rather than cmpxchg() as the latter is unavailable and unimplementable on some platforms and is actually unnecessary. The use of cmpxchg() was to guard against two possibilities, neither of which can actually occur: (1) The pending flag may have been unset or may be cleared. However, given where it's called, the pending flag is _always_ set. I don't think it can be unset whilst we're in set_wq_data(). Once the work is enqueued to be actually run, the only way off the queue is for it to be actually run. If it's a delayed work item, then the bit can't be cleared by the timer because we haven't started the timer yet. Also, the pending bit can't be cleared by cancelling the delayed work _until_ the work item has had its timer started. (2) The workqueue pointer might change. This can only happen in two cases: (a) The work item has just been queued to actually run, and so we're protected by the appropriate workqueue spinlock. (b) A delayed work item is being queued, and so the timer hasn't been started yet, and so no one else knows about the work item or can access it (the pending bit protects us). Besides, set_wq_data() _sets_ the workqueue pointer unconditionally, so it can be assigned instead. So, replacing the set_wq_data() with a straight assignment would be okay in most cases. The problem is where we end up tangling with test_and_set_bit() emulated using spinlocks, and even then it's not a problem _provided_ test_and_set_bit() doesn't attempt to modify the word if the bit was set. If that's a problem, then a bitops-proofed assignment will be required - equivalent to atomic_set() vs other atomic_xxx() ops. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-07 19:33:26 +08:00
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/* Can I start working? Called from busy but !running workers. */
static bool may_start_working(struct worker_pool *pool)
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
{
return pool->nr_idle;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
}
/* Do I need to keep working? Called from currently running workers. */
static bool keep_working(struct worker_pool *pool)
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
{
return !list_empty(&pool->worklist) &&
atomic_read(&pool->nr_running) <= 1;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
}
/* Do we need a new worker? Called from manager. */
static bool need_to_create_worker(struct worker_pool *pool)
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
{
return need_more_worker(pool) && !may_start_working(pool);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
}
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/* Do I need to be the manager? */
static bool need_to_manage_workers(struct worker_pool *pool)
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
{
return need_to_create_worker(pool) ||
(pool->flags & POOL_MANAGE_WORKERS);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
}
/* Do we have too many workers and should some go away? */
static bool too_many_workers(struct worker_pool *pool)
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
{
bool managing = pool->flags & POOL_MANAGING_WORKERS;
int nr_idle = pool->nr_idle + managing; /* manager is considered idle */
int nr_busy = pool->nr_workers - nr_idle;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
workqueue: reimplement idle worker rebinding Currently rebind_workers() uses rebinds idle workers synchronously before proceeding to requesting busy workers to rebind. This is necessary because all workers on @worker_pool->idle_list must be bound before concurrency management local wake-ups from the busy workers take place. Unfortunately, the synchronous idle rebinding is quite complicated. This patch reimplements idle rebinding to simplify the code path. Rather than trying to make all idle workers bound before rebinding busy workers, we simply remove all to-be-bound idle workers from the idle list and let them add themselves back after completing rebinding (successful or not). As only workers which finished rebinding can on on the idle worker list, the idle worker list is guaranteed to have only bound workers unless CPU went down again and local wake-ups are safe. After the change, @worker_pool->nr_idle may deviate than the actual number of idle workers on @worker_pool->idle_list. More specifically, nr_idle may be non-zero while ->idle_list is empty. All users of ->nr_idle and ->idle_list are audited. The only affected one is too_many_workers() which is updated to check %false if ->idle_list is empty regardless of ->nr_idle. After this patch, rebind_workers() no longer performs the nasty idle-rebind retries which require temporary release of gcwq->lock, and both unbinding and rebinding are atomic w.r.t. global_cwq->lock. worker->idle_rebind and global_cwq->rebind_hold are now unnecessary and removed along with the definition of struct idle_rebind. Changed from V1: 1) remove unlikely from too_many_workers(), ->idle_list can be empty anytime, even before this patch, no reason to use unlikely. 2) fix a small rebasing mistake. (which is from rebasing the orignal fixing patch to for-next) 3) add a lot of comments. 4) clear WORKER_REBIND unconditionaly in idle_worker_rebind() tj: Updated comments and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2012-09-19 00:59:22 +08:00
/*
* nr_idle and idle_list may disagree if idle rebinding is in
* progress. Never return %true if idle_list is empty.
*/
if (list_empty(&pool->idle_list))
return false;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy;
}
/*
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* Wake up functions.
*/
workqueue: use shared worklist and pool all workers per cpu Use gcwq->worklist instead of cwq->worklist and break the strict association between a cwq and its worker. All works queued on a cpu are queued on gcwq->worklist and processed by any available worker on the gcwq. As there no longer is strict association between a cwq and its worker, whether a work is executing can now only be determined by calling [__]find_worker_executing_work(). After this change, the only association between a cwq and its worker is that a cwq puts a worker into shared worker pool on creation and kills it on destruction. As all workqueues are still limited to max_active of one, this means that there are always at least as many workers as active works and thus there's no danger for deadlock. The break of strong association between cwqs and workers requires somewhat clumsy changes to current_is_keventd() and destroy_workqueue(). Dynamic worker pool management will remove both clumsy changes. current_is_keventd() won't be necessary at all as the only reason it exists is to avoid queueing a work from a work which will be allowed just fine. The clumsy part of destroy_workqueue() is added because a worker can only be destroyed while idle and there's no guarantee a worker is idle when its wq is going down. With dynamic pool management, workers are not associated with workqueues at all and only idle ones will be submitted to destroy_workqueue() so the code won't be necessary anymore. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:13 +08:00
/* Return the first worker. Safe with preemption disabled */
static struct worker *first_worker(struct worker_pool *pool)
workqueue: use shared worklist and pool all workers per cpu Use gcwq->worklist instead of cwq->worklist and break the strict association between a cwq and its worker. All works queued on a cpu are queued on gcwq->worklist and processed by any available worker on the gcwq. As there no longer is strict association between a cwq and its worker, whether a work is executing can now only be determined by calling [__]find_worker_executing_work(). After this change, the only association between a cwq and its worker is that a cwq puts a worker into shared worker pool on creation and kills it on destruction. As all workqueues are still limited to max_active of one, this means that there are always at least as many workers as active works and thus there's no danger for deadlock. The break of strong association between cwqs and workers requires somewhat clumsy changes to current_is_keventd() and destroy_workqueue(). Dynamic worker pool management will remove both clumsy changes. current_is_keventd() won't be necessary at all as the only reason it exists is to avoid queueing a work from a work which will be allowed just fine. The clumsy part of destroy_workqueue() is added because a worker can only be destroyed while idle and there's no guarantee a worker is idle when its wq is going down. With dynamic pool management, workers are not associated with workqueues at all and only idle ones will be submitted to destroy_workqueue() so the code won't be necessary anymore. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:13 +08:00
{
if (unlikely(list_empty(&pool->idle_list)))
workqueue: use shared worklist and pool all workers per cpu Use gcwq->worklist instead of cwq->worklist and break the strict association between a cwq and its worker. All works queued on a cpu are queued on gcwq->worklist and processed by any available worker on the gcwq. As there no longer is strict association between a cwq and its worker, whether a work is executing can now only be determined by calling [__]find_worker_executing_work(). After this change, the only association between a cwq and its worker is that a cwq puts a worker into shared worker pool on creation and kills it on destruction. As all workqueues are still limited to max_active of one, this means that there are always at least as many workers as active works and thus there's no danger for deadlock. The break of strong association between cwqs and workers requires somewhat clumsy changes to current_is_keventd() and destroy_workqueue(). Dynamic worker pool management will remove both clumsy changes. current_is_keventd() won't be necessary at all as the only reason it exists is to avoid queueing a work from a work which will be allowed just fine. The clumsy part of destroy_workqueue() is added because a worker can only be destroyed while idle and there's no guarantee a worker is idle when its wq is going down. With dynamic pool management, workers are not associated with workqueues at all and only idle ones will be submitted to destroy_workqueue() so the code won't be necessary anymore. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:13 +08:00
return NULL;
return list_first_entry(&pool->idle_list, struct worker, entry);
workqueue: use shared worklist and pool all workers per cpu Use gcwq->worklist instead of cwq->worklist and break the strict association between a cwq and its worker. All works queued on a cpu are queued on gcwq->worklist and processed by any available worker on the gcwq. As there no longer is strict association between a cwq and its worker, whether a work is executing can now only be determined by calling [__]find_worker_executing_work(). After this change, the only association between a cwq and its worker is that a cwq puts a worker into shared worker pool on creation and kills it on destruction. As all workqueues are still limited to max_active of one, this means that there are always at least as many workers as active works and thus there's no danger for deadlock. The break of strong association between cwqs and workers requires somewhat clumsy changes to current_is_keventd() and destroy_workqueue(). Dynamic worker pool management will remove both clumsy changes. current_is_keventd() won't be necessary at all as the only reason it exists is to avoid queueing a work from a work which will be allowed just fine. The clumsy part of destroy_workqueue() is added because a worker can only be destroyed while idle and there's no guarantee a worker is idle when its wq is going down. With dynamic pool management, workers are not associated with workqueues at all and only idle ones will be submitted to destroy_workqueue() so the code won't be necessary anymore. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:13 +08:00
}
/**
* wake_up_worker - wake up an idle worker
* @pool: worker pool to wake worker from
workqueue: use shared worklist and pool all workers per cpu Use gcwq->worklist instead of cwq->worklist and break the strict association between a cwq and its worker. All works queued on a cpu are queued on gcwq->worklist and processed by any available worker on the gcwq. As there no longer is strict association between a cwq and its worker, whether a work is executing can now only be determined by calling [__]find_worker_executing_work(). After this change, the only association between a cwq and its worker is that a cwq puts a worker into shared worker pool on creation and kills it on destruction. As all workqueues are still limited to max_active of one, this means that there are always at least as many workers as active works and thus there's no danger for deadlock. The break of strong association between cwqs and workers requires somewhat clumsy changes to current_is_keventd() and destroy_workqueue(). Dynamic worker pool management will remove both clumsy changes. current_is_keventd() won't be necessary at all as the only reason it exists is to avoid queueing a work from a work which will be allowed just fine. The clumsy part of destroy_workqueue() is added because a worker can only be destroyed while idle and there's no guarantee a worker is idle when its wq is going down. With dynamic pool management, workers are not associated with workqueues at all and only idle ones will be submitted to destroy_workqueue() so the code won't be necessary anymore. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:13 +08:00
*
* Wake up the first idle worker of @pool.
workqueue: use shared worklist and pool all workers per cpu Use gcwq->worklist instead of cwq->worklist and break the strict association between a cwq and its worker. All works queued on a cpu are queued on gcwq->worklist and processed by any available worker on the gcwq. As there no longer is strict association between a cwq and its worker, whether a work is executing can now only be determined by calling [__]find_worker_executing_work(). After this change, the only association between a cwq and its worker is that a cwq puts a worker into shared worker pool on creation and kills it on destruction. As all workqueues are still limited to max_active of one, this means that there are always at least as many workers as active works and thus there's no danger for deadlock. The break of strong association between cwqs and workers requires somewhat clumsy changes to current_is_keventd() and destroy_workqueue(). Dynamic worker pool management will remove both clumsy changes. current_is_keventd() won't be necessary at all as the only reason it exists is to avoid queueing a work from a work which will be allowed just fine. The clumsy part of destroy_workqueue() is added because a worker can only be destroyed while idle and there's no guarantee a worker is idle when its wq is going down. With dynamic pool management, workers are not associated with workqueues at all and only idle ones will be submitted to destroy_workqueue() so the code won't be necessary anymore. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:13 +08:00
*
* CONTEXT:
* spin_lock_irq(pool->lock).
workqueue: use shared worklist and pool all workers per cpu Use gcwq->worklist instead of cwq->worklist and break the strict association between a cwq and its worker. All works queued on a cpu are queued on gcwq->worklist and processed by any available worker on the gcwq. As there no longer is strict association between a cwq and its worker, whether a work is executing can now only be determined by calling [__]find_worker_executing_work(). After this change, the only association between a cwq and its worker is that a cwq puts a worker into shared worker pool on creation and kills it on destruction. As all workqueues are still limited to max_active of one, this means that there are always at least as many workers as active works and thus there's no danger for deadlock. The break of strong association between cwqs and workers requires somewhat clumsy changes to current_is_keventd() and destroy_workqueue(). Dynamic worker pool management will remove both clumsy changes. current_is_keventd() won't be necessary at all as the only reason it exists is to avoid queueing a work from a work which will be allowed just fine. The clumsy part of destroy_workqueue() is added because a worker can only be destroyed while idle and there's no guarantee a worker is idle when its wq is going down. With dynamic pool management, workers are not associated with workqueues at all and only idle ones will be submitted to destroy_workqueue() so the code won't be necessary anymore. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:13 +08:00
*/
static void wake_up_worker(struct worker_pool *pool)
workqueue: use shared worklist and pool all workers per cpu Use gcwq->worklist instead of cwq->worklist and break the strict association between a cwq and its worker. All works queued on a cpu are queued on gcwq->worklist and processed by any available worker on the gcwq. As there no longer is strict association between a cwq and its worker, whether a work is executing can now only be determined by calling [__]find_worker_executing_work(). After this change, the only association between a cwq and its worker is that a cwq puts a worker into shared worker pool on creation and kills it on destruction. As all workqueues are still limited to max_active of one, this means that there are always at least as many workers as active works and thus there's no danger for deadlock. The break of strong association between cwqs and workers requires somewhat clumsy changes to current_is_keventd() and destroy_workqueue(). Dynamic worker pool management will remove both clumsy changes. current_is_keventd() won't be necessary at all as the only reason it exists is to avoid queueing a work from a work which will be allowed just fine. The clumsy part of destroy_workqueue() is added because a worker can only be destroyed while idle and there's no guarantee a worker is idle when its wq is going down. With dynamic pool management, workers are not associated with workqueues at all and only idle ones will be submitted to destroy_workqueue() so the code won't be necessary anymore. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:13 +08:00
{
struct worker *worker = first_worker(pool);
workqueue: use shared worklist and pool all workers per cpu Use gcwq->worklist instead of cwq->worklist and break the strict association between a cwq and its worker. All works queued on a cpu are queued on gcwq->worklist and processed by any available worker on the gcwq. As there no longer is strict association between a cwq and its worker, whether a work is executing can now only be determined by calling [__]find_worker_executing_work(). After this change, the only association between a cwq and its worker is that a cwq puts a worker into shared worker pool on creation and kills it on destruction. As all workqueues are still limited to max_active of one, this means that there are always at least as many workers as active works and thus there's no danger for deadlock. The break of strong association between cwqs and workers requires somewhat clumsy changes to current_is_keventd() and destroy_workqueue(). Dynamic worker pool management will remove both clumsy changes. current_is_keventd() won't be necessary at all as the only reason it exists is to avoid queueing a work from a work which will be allowed just fine. The clumsy part of destroy_workqueue() is added because a worker can only be destroyed while idle and there's no guarantee a worker is idle when its wq is going down. With dynamic pool management, workers are not associated with workqueues at all and only idle ones will be submitted to destroy_workqueue() so the code won't be necessary anymore. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:13 +08:00
if (likely(worker))
wake_up_process(worker->task);
}
/**
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* wq_worker_waking_up - a worker is waking up
* @task: task waking up
* @cpu: CPU @task is waking up to
*
* This function is called during try_to_wake_up() when a worker is
* being awoken.
*
* CONTEXT:
* spin_lock_irq(rq->lock)
*/
void wq_worker_waking_up(struct task_struct *task, unsigned int cpu)
{
struct worker *worker = kthread_data(task);
if (!(worker->flags & WORKER_NOT_RUNNING)) {
WARN_ON_ONCE(worker->pool->cpu != cpu);
atomic_inc(&worker->pool->nr_running);
}
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
}
/**
* wq_worker_sleeping - a worker is going to sleep
* @task: task going to sleep
* @cpu: CPU in question, must be the current CPU number
*
* This function is called during schedule() when a busy worker is
* going to sleep. Worker on the same cpu can be woken up by
* returning pointer to its task.
*
* CONTEXT:
* spin_lock_irq(rq->lock)
*
* RETURNS:
* Worker task on @cpu to wake up, %NULL if none.
*/
struct task_struct *wq_worker_sleeping(struct task_struct *task,
unsigned int cpu)
{
struct worker *worker = kthread_data(task), *to_wakeup = NULL;
struct worker_pool *pool;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/*
* 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)
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
return NULL;
pool = worker->pool;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/* this can only happen on the local cpu */
BUG_ON(cpu != raw_smp_processor_id());
/*
* The counterpart of the following dec_and_test, implied mb,
* worklist not empty test sequence is in insert_work().
* Please read comment there.
*
* NOT_RUNNING is clear. This means that we're bound to and
* running on the local cpu w/ rq lock held and preemption
* disabled, which in turn means that none else could be
* manipulating idle_list, so dereferencing idle_list without pool
* lock is safe.
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
*/
if (atomic_dec_and_test(&pool->nr_running) &&
!list_empty(&pool->worklist))
to_wakeup = first_worker(pool);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
return to_wakeup ? to_wakeup->task : NULL;
}
/**
* worker_set_flags - set worker flags and adjust nr_running accordingly
* @worker: self
* @flags: flags to set
* @wakeup: wakeup an idle worker if necessary
*
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* Set @flags in @worker->flags and adjust nr_running accordingly. If
* nr_running becomes zero and @wakeup is %true, an idle worker is
* woken up.
*
* CONTEXT:
* spin_lock_irq(pool->lock)
*/
static inline void worker_set_flags(struct worker *worker, unsigned int flags,
bool wakeup)
{
struct worker_pool *pool = worker->pool;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
WARN_ON_ONCE(worker->task != current);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/*
* If transitioning into NOT_RUNNING, adjust nr_running and
* wake up an idle worker as necessary if requested by
* @wakeup.
*/
if ((flags & WORKER_NOT_RUNNING) &&
!(worker->flags & WORKER_NOT_RUNNING)) {
if (wakeup) {
if (atomic_dec_and_test(&pool->nr_running) &&
!list_empty(&pool->worklist))
wake_up_worker(pool);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
} else
atomic_dec(&pool->nr_running);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
}
worker->flags |= flags;
}
/**
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* worker_clr_flags - clear worker flags and adjust nr_running accordingly
* @worker: self
* @flags: flags to clear
*
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* Clear @flags in @worker->flags and adjust nr_running accordingly.
*
* CONTEXT:
* spin_lock_irq(pool->lock)
*/
static inline void worker_clr_flags(struct worker *worker, unsigned int flags)
{
struct worker_pool *pool = worker->pool;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
unsigned int oflags = worker->flags;
WARN_ON_ONCE(worker->task != current);
worker->flags &= ~flags;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/*
* If transitioning out of NOT_RUNNING, increment nr_running. Note
* that the nested NOT_RUNNING is not a noop. NOT_RUNNING is mask
* of multiple flags, not a single flag.
*/
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING))
if (!(worker->flags & WORKER_NOT_RUNNING))
atomic_inc(&pool->nr_running);
}
/**
* find_worker_executing_work - find worker which is executing a work
* @pool: pool of interest
* @work: work to find worker for
*
* Find a worker which is executing @work on @pool by searching
* @pool->busy_hash which is keyed by the address of @work. For a worker
workqueue: consider work function when searching for busy work items To avoid executing the same work item concurrenlty, workqueue hashes currently busy workers according to their current work items and looks up the the table when it wants to execute a new work item. If there already is a worker which is executing the new work item, the new item is queued to the found worker so that it gets executed only after the current execution finishes. Unfortunately, a work item may be freed while being executed and thus recycled for different purposes. If it gets recycled for a different work item and queued while the previous execution is still in progress, workqueue may make the new work item wait for the old one although the two aren't really related in any way. In extreme cases, this false dependency may lead to deadlock although it's extremely unlikely given that there aren't too many self-freeing work item users and they usually don't wait for other work items. To alleviate the problem, record the current work function in each busy worker and match it together with the work item address in find_worker_executing_work(). While this isn't complete, it ensures that unrelated work items don't interact with each other and in the very unlikely case where a twisted wq user triggers it, it's always onto itself making the culprit easy to spot. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Andrey Isakov <andy51@gmx.ru> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=51701 Cc: stable@vger.kernel.org
2012-12-19 02:35:02 +08:00
* 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(pool->lock).
*
* RETURNS:
* Pointer to worker which is executing @work if found, NULL
* otherwise.
*/
static struct worker *find_worker_executing_work(struct worker_pool *pool,
struct work_struct *work)
{
struct worker *worker;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:06:00 +08:00
hash_for_each_possible(pool->busy_hash, worker, hentry,
workqueue: consider work function when searching for busy work items To avoid executing the same work item concurrenlty, workqueue hashes currently busy workers according to their current work items and looks up the the table when it wants to execute a new work item. If there already is a worker which is executing the new work item, the new item is queued to the found worker so that it gets executed only after the current execution finishes. Unfortunately, a work item may be freed while being executed and thus recycled for different purposes. If it gets recycled for a different work item and queued while the previous execution is still in progress, workqueue may make the new work item wait for the old one although the two aren't really related in any way. In extreme cases, this false dependency may lead to deadlock although it's extremely unlikely given that there aren't too many self-freeing work item users and they usually don't wait for other work items. To alleviate the problem, record the current work function in each busy worker and match it together with the work item address in find_worker_executing_work(). While this isn't complete, it ensures that unrelated work items don't interact with each other and in the very unlikely case where a twisted wq user triggers it, it's always onto itself making the culprit easy to spot. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Andrey Isakov <andy51@gmx.ru> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=51701 Cc: stable@vger.kernel.org
2012-12-19 02:35:02 +08:00
(unsigned long)work)
if (worker->current_work == work &&
worker->current_func == work->func)
return worker;
return NULL;
}
/**
* move_linked_works - move linked works to a list
* @work: start of series of works to be scheduled
* @head: target list to append @work to
* @nextp: out paramter for nested worklist walking
*
* Schedule linked works starting from @work to @head. Work series to
* be scheduled starts at @work and includes any consecutive work with
* WORK_STRUCT_LINKED set in its predecessor.
*
* If @nextp is not NULL, it's updated to point to the next work of
* the last scheduled work. This allows move_linked_works() to be
* nested inside outer list_for_each_entry_safe().
*
* CONTEXT:
* spin_lock_irq(pool->lock).
*/
static void move_linked_works(struct work_struct *work, struct list_head *head,
struct work_struct **nextp)
{
struct work_struct *n;
/*
* Linked worklist will always end before the end of the list,
* use NULL for list head.
*/
list_for_each_entry_safe_from(work, n, NULL, entry) {
list_move_tail(&work->entry, head);
if (!(*work_data_bits(work) & WORK_STRUCT_LINKED))
break;
}
/*
* If we're already inside safe list traversal and have moved
* multiple works to the scheduled queue, the next position
* needs to be updated.
*/
if (nextp)
*nextp = n;
}
static void pwq_activate_delayed_work(struct work_struct *work)
{
struct pool_workqueue *pwq = get_work_pwq(work);
trace_workqueue_activate_work(work);
move_linked_works(work, &pwq->pool->worklist, NULL);
__clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work));
pwq->nr_active++;
}
static void pwq_activate_first_delayed(struct pool_workqueue *pwq)
{
struct work_struct *work = list_first_entry(&pwq->delayed_works,
struct work_struct, entry);
pwq_activate_delayed_work(work);
}
/**
* pwq_dec_nr_in_flight - decrement pwq's nr_in_flight
* @pwq: pwq of interest
* @color: color of work which left the queue
*
* A work either has completed or is removed from pending queue,
* decrement nr_in_flight of its pwq and handle workqueue flushing.
*
* CONTEXT:
* spin_lock_irq(pool->lock).
*/
static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, int color)
{
/* ignore uncolored works */
if (color == WORK_NO_COLOR)
return;
pwq->nr_in_flight[color]--;
pwq->nr_active--;
if (!list_empty(&pwq->delayed_works)) {
/* one down, submit a delayed one */
if (pwq->nr_active < pwq->max_active)
pwq_activate_first_delayed(pwq);
}
/* is flush in progress and are we at the flushing tip? */
if (likely(pwq->flush_color != color))
return;
/* are there still in-flight works? */
if (pwq->nr_in_flight[color])
return;
/* this pwq is done, clear flush_color */
pwq->flush_color = -1;
/*
* If this was the last pwq, wake up the first flusher. It
* will handle the rest.
*/
if (atomic_dec_and_test(&pwq->wq->nr_pwqs_to_flush))
complete(&pwq->wq->first_flusher->done);
}
/**
workqueue: mark a work item being canceled as such There can be two reasons try_to_grab_pending() can fail with -EAGAIN. One is when someone else is queueing or deqeueing the work item. With the previous patches, it is guaranteed that PENDING and queued state will soon agree making it safe to busy-retry in this case. The other is if multiple __cancel_work_timer() invocations are racing one another. __cancel_work_timer() grabs PENDING and then waits for running instances of the target work item on all CPUs while holding PENDING and !queued. try_to_grab_pending() invoked from another task will keep returning -EAGAIN while the current owner is waiting. Not distinguishing the two cases is okay because __cancel_work_timer() is the only user of try_to_grab_pending() and it invokes wait_on_work() whenever grabbing fails. For the first case, busy looping should be fine but wait_on_work() doesn't cause any critical problem. For the latter case, the new contender usually waits for the same condition as the current owner, so no unnecessarily extended busy-looping happens. Combined, these make __cancel_work_timer() technically correct even without irq protection while grabbing PENDING or distinguishing the two different cases. While the current code is technically correct, not distinguishing the two cases makes it difficult to use try_to_grab_pending() for other purposes than canceling because it's impossible to tell whether it's safe to busy-retry grabbing. This patch adds a mechanism to mark a work item being canceled. try_to_grab_pending() now disables irq on success and returns -EAGAIN to indicate that grabbing failed but PENDING and queued states are gonna agree soon and it's safe to busy-loop. It returns -ENOENT if the work item is being canceled and it may stay PENDING && !queued for arbitrary amount of time. __cancel_work_timer() is modified to mark the work canceling with WORK_OFFQ_CANCELING after grabbing PENDING, thus making try_to_grab_pending() fail with -ENOENT instead of -EAGAIN. Also, it invokes wait_on_work() iff grabbing failed with -ENOENT. This isn't necessary for correctness but makes it consistent with other future users of try_to_grab_pending(). v2: try_to_grab_pending() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Updated so that try_to_grab_pending() disables irq on success rather than requiring preemption disabled by the caller. This makes busy-looping easier and will allow try_to_grap_pending() to be used from bh/irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:46 +08:00
* try_to_grab_pending - steal work item from worklist and disable irq
* @work: work item to steal
* @is_dwork: @work is a delayed_work
workqueue: mark a work item being canceled as such There can be two reasons try_to_grab_pending() can fail with -EAGAIN. One is when someone else is queueing or deqeueing the work item. With the previous patches, it is guaranteed that PENDING and queued state will soon agree making it safe to busy-retry in this case. The other is if multiple __cancel_work_timer() invocations are racing one another. __cancel_work_timer() grabs PENDING and then waits for running instances of the target work item on all CPUs while holding PENDING and !queued. try_to_grab_pending() invoked from another task will keep returning -EAGAIN while the current owner is waiting. Not distinguishing the two cases is okay because __cancel_work_timer() is the only user of try_to_grab_pending() and it invokes wait_on_work() whenever grabbing fails. For the first case, busy looping should be fine but wait_on_work() doesn't cause any critical problem. For the latter case, the new contender usually waits for the same condition as the current owner, so no unnecessarily extended busy-looping happens. Combined, these make __cancel_work_timer() technically correct even without irq protection while grabbing PENDING or distinguishing the two different cases. While the current code is technically correct, not distinguishing the two cases makes it difficult to use try_to_grab_pending() for other purposes than canceling because it's impossible to tell whether it's safe to busy-retry grabbing. This patch adds a mechanism to mark a work item being canceled. try_to_grab_pending() now disables irq on success and returns -EAGAIN to indicate that grabbing failed but PENDING and queued states are gonna agree soon and it's safe to busy-loop. It returns -ENOENT if the work item is being canceled and it may stay PENDING && !queued for arbitrary amount of time. __cancel_work_timer() is modified to mark the work canceling with WORK_OFFQ_CANCELING after grabbing PENDING, thus making try_to_grab_pending() fail with -ENOENT instead of -EAGAIN. Also, it invokes wait_on_work() iff grabbing failed with -ENOENT. This isn't necessary for correctness but makes it consistent with other future users of try_to_grab_pending(). v2: try_to_grab_pending() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Updated so that try_to_grab_pending() disables irq on success rather than requiring preemption disabled by the caller. This makes busy-looping easier and will allow try_to_grap_pending() to be used from bh/irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:46 +08:00
* @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
*
* 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
workqueue: mark a work item being canceled as such There can be two reasons try_to_grab_pending() can fail with -EAGAIN. One is when someone else is queueing or deqeueing the work item. With the previous patches, it is guaranteed that PENDING and queued state will soon agree making it safe to busy-retry in this case. The other is if multiple __cancel_work_timer() invocations are racing one another. __cancel_work_timer() grabs PENDING and then waits for running instances of the target work item on all CPUs while holding PENDING and !queued. try_to_grab_pending() invoked from another task will keep returning -EAGAIN while the current owner is waiting. Not distinguishing the two cases is okay because __cancel_work_timer() is the only user of try_to_grab_pending() and it invokes wait_on_work() whenever grabbing fails. For the first case, busy looping should be fine but wait_on_work() doesn't cause any critical problem. For the latter case, the new contender usually waits for the same condition as the current owner, so no unnecessarily extended busy-looping happens. Combined, these make __cancel_work_timer() technically correct even without irq protection while grabbing PENDING or distinguishing the two different cases. While the current code is technically correct, not distinguishing the two cases makes it difficult to use try_to_grab_pending() for other purposes than canceling because it's impossible to tell whether it's safe to busy-retry grabbing. This patch adds a mechanism to mark a work item being canceled. try_to_grab_pending() now disables irq on success and returns -EAGAIN to indicate that grabbing failed but PENDING and queued states are gonna agree soon and it's safe to busy-loop. It returns -ENOENT if the work item is being canceled and it may stay PENDING && !queued for arbitrary amount of time. __cancel_work_timer() is modified to mark the work canceling with WORK_OFFQ_CANCELING after grabbing PENDING, thus making try_to_grab_pending() fail with -ENOENT instead of -EAGAIN. Also, it invokes wait_on_work() iff grabbing failed with -ENOENT. This isn't necessary for correctness but makes it consistent with other future users of try_to_grab_pending(). v2: try_to_grab_pending() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Updated so that try_to_grab_pending() disables irq on success rather than requiring preemption disabled by the caller. This makes busy-looping easier and will allow try_to_grap_pending() to be used from bh/irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:46 +08:00
* -ENOENT if someone else is canceling @work, this state may persist
* for arbitrarily long
*
workqueue: mark a work item being canceled as such There can be two reasons try_to_grab_pending() can fail with -EAGAIN. One is when someone else is queueing or deqeueing the work item. With the previous patches, it is guaranteed that PENDING and queued state will soon agree making it safe to busy-retry in this case. The other is if multiple __cancel_work_timer() invocations are racing one another. __cancel_work_timer() grabs PENDING and then waits for running instances of the target work item on all CPUs while holding PENDING and !queued. try_to_grab_pending() invoked from another task will keep returning -EAGAIN while the current owner is waiting. Not distinguishing the two cases is okay because __cancel_work_timer() is the only user of try_to_grab_pending() and it invokes wait_on_work() whenever grabbing fails. For the first case, busy looping should be fine but wait_on_work() doesn't cause any critical problem. For the latter case, the new contender usually waits for the same condition as the current owner, so no unnecessarily extended busy-looping happens. Combined, these make __cancel_work_timer() technically correct even without irq protection while grabbing PENDING or distinguishing the two different cases. While the current code is technically correct, not distinguishing the two cases makes it difficult to use try_to_grab_pending() for other purposes than canceling because it's impossible to tell whether it's safe to busy-retry grabbing. This patch adds a mechanism to mark a work item being canceled. try_to_grab_pending() now disables irq on success and returns -EAGAIN to indicate that grabbing failed but PENDING and queued states are gonna agree soon and it's safe to busy-loop. It returns -ENOENT if the work item is being canceled and it may stay PENDING && !queued for arbitrary amount of time. __cancel_work_timer() is modified to mark the work canceling with WORK_OFFQ_CANCELING after grabbing PENDING, thus making try_to_grab_pending() fail with -ENOENT instead of -EAGAIN. Also, it invokes wait_on_work() iff grabbing failed with -ENOENT. This isn't necessary for correctness but makes it consistent with other future users of try_to_grab_pending(). v2: try_to_grab_pending() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Updated so that try_to_grab_pending() disables irq on success rather than requiring preemption disabled by the caller. This makes busy-looping easier and will allow try_to_grap_pending() to be used from bh/irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:46 +08:00
* 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
* irqsafe, ensures that we return -EAGAIN for finite short period of time.
workqueue: mark a work item being canceled as such There can be two reasons try_to_grab_pending() can fail with -EAGAIN. One is when someone else is queueing or deqeueing the work item. With the previous patches, it is guaranteed that PENDING and queued state will soon agree making it safe to busy-retry in this case. The other is if multiple __cancel_work_timer() invocations are racing one another. __cancel_work_timer() grabs PENDING and then waits for running instances of the target work item on all CPUs while holding PENDING and !queued. try_to_grab_pending() invoked from another task will keep returning -EAGAIN while the current owner is waiting. Not distinguishing the two cases is okay because __cancel_work_timer() is the only user of try_to_grab_pending() and it invokes wait_on_work() whenever grabbing fails. For the first case, busy looping should be fine but wait_on_work() doesn't cause any critical problem. For the latter case, the new contender usually waits for the same condition as the current owner, so no unnecessarily extended busy-looping happens. Combined, these make __cancel_work_timer() technically correct even without irq protection while grabbing PENDING or distinguishing the two different cases. While the current code is technically correct, not distinguishing the two cases makes it difficult to use try_to_grab_pending() for other purposes than canceling because it's impossible to tell whether it's safe to busy-retry grabbing. This patch adds a mechanism to mark a work item being canceled. try_to_grab_pending() now disables irq on success and returns -EAGAIN to indicate that grabbing failed but PENDING and queued states are gonna agree soon and it's safe to busy-loop. It returns -ENOENT if the work item is being canceled and it may stay PENDING && !queued for arbitrary amount of time. __cancel_work_timer() is modified to mark the work canceling with WORK_OFFQ_CANCELING after grabbing PENDING, thus making try_to_grab_pending() fail with -ENOENT instead of -EAGAIN. Also, it invokes wait_on_work() iff grabbing failed with -ENOENT. This isn't necessary for correctness but makes it consistent with other future users of try_to_grab_pending(). v2: try_to_grab_pending() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Updated so that try_to_grab_pending() disables irq on success rather than requiring preemption disabled by the caller. This makes busy-looping easier and will allow try_to_grap_pending() to be used from bh/irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:46 +08:00
*
* On successful return, >= 0, irq is disabled and the caller is
* responsible for releasing it using local_irq_restore(*@flags).
*
* This function is safe to call from any context including IRQ handler.
*/
workqueue: mark a work item being canceled as such There can be two reasons try_to_grab_pending() can fail with -EAGAIN. One is when someone else is queueing or deqeueing the work item. With the previous patches, it is guaranteed that PENDING and queued state will soon agree making it safe to busy-retry in this case. The other is if multiple __cancel_work_timer() invocations are racing one another. __cancel_work_timer() grabs PENDING and then waits for running instances of the target work item on all CPUs while holding PENDING and !queued. try_to_grab_pending() invoked from another task will keep returning -EAGAIN while the current owner is waiting. Not distinguishing the two cases is okay because __cancel_work_timer() is the only user of try_to_grab_pending() and it invokes wait_on_work() whenever grabbing fails. For the first case, busy looping should be fine but wait_on_work() doesn't cause any critical problem. For the latter case, the new contender usually waits for the same condition as the current owner, so no unnecessarily extended busy-looping happens. Combined, these make __cancel_work_timer() technically correct even without irq protection while grabbing PENDING or distinguishing the two different cases. While the current code is technically correct, not distinguishing the two cases makes it difficult to use try_to_grab_pending() for other purposes than canceling because it's impossible to tell whether it's safe to busy-retry grabbing. This patch adds a mechanism to mark a work item being canceled. try_to_grab_pending() now disables irq on success and returns -EAGAIN to indicate that grabbing failed but PENDING and queued states are gonna agree soon and it's safe to busy-loop. It returns -ENOENT if the work item is being canceled and it may stay PENDING && !queued for arbitrary amount of time. __cancel_work_timer() is modified to mark the work canceling with WORK_OFFQ_CANCELING after grabbing PENDING, thus making try_to_grab_pending() fail with -ENOENT instead of -EAGAIN. Also, it invokes wait_on_work() iff grabbing failed with -ENOENT. This isn't necessary for correctness but makes it consistent with other future users of try_to_grab_pending(). v2: try_to_grab_pending() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Updated so that try_to_grab_pending() disables irq on success rather than requiring preemption disabled by the caller. This makes busy-looping easier and will allow try_to_grap_pending() to be used from bh/irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:46 +08:00
static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
unsigned long *flags)
{
struct worker_pool *pool;
struct pool_workqueue *pwq;
workqueue: mark a work item being canceled as such There can be two reasons try_to_grab_pending() can fail with -EAGAIN. One is when someone else is queueing or deqeueing the work item. With the previous patches, it is guaranteed that PENDING and queued state will soon agree making it safe to busy-retry in this case. The other is if multiple __cancel_work_timer() invocations are racing one another. __cancel_work_timer() grabs PENDING and then waits for running instances of the target work item on all CPUs while holding PENDING and !queued. try_to_grab_pending() invoked from another task will keep returning -EAGAIN while the current owner is waiting. Not distinguishing the two cases is okay because __cancel_work_timer() is the only user of try_to_grab_pending() and it invokes wait_on_work() whenever grabbing fails. For the first case, busy looping should be fine but wait_on_work() doesn't cause any critical problem. For the latter case, the new contender usually waits for the same condition as the current owner, so no unnecessarily extended busy-looping happens. Combined, these make __cancel_work_timer() technically correct even without irq protection while grabbing PENDING or distinguishing the two different cases. While the current code is technically correct, not distinguishing the two cases makes it difficult to use try_to_grab_pending() for other purposes than canceling because it's impossible to tell whether it's safe to busy-retry grabbing. This patch adds a mechanism to mark a work item being canceled. try_to_grab_pending() now disables irq on success and returns -EAGAIN to indicate that grabbing failed but PENDING and queued states are gonna agree soon and it's safe to busy-loop. It returns -ENOENT if the work item is being canceled and it may stay PENDING && !queued for arbitrary amount of time. __cancel_work_timer() is modified to mark the work canceling with WORK_OFFQ_CANCELING after grabbing PENDING, thus making try_to_grab_pending() fail with -ENOENT instead of -EAGAIN. Also, it invokes wait_on_work() iff grabbing failed with -ENOENT. This isn't necessary for correctness but makes it consistent with other future users of try_to_grab_pending(). v2: try_to_grab_pending() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Updated so that try_to_grab_pending() disables irq on success rather than requiring preemption disabled by the caller. This makes busy-looping easier and will allow try_to_grap_pending() to be used from bh/irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:46 +08:00
local_irq_save(*flags);
/* try to steal the timer if it exists */
if (is_dwork) {
struct delayed_work *dwork = to_delayed_work(work);
/*
* dwork->timer is irqsafe. If del_timer() fails, it's
* guaranteed that the timer is not queued anywhere and not
* running on the local CPU.
*/
if (likely(del_timer(&dwork->timer)))
return 1;
}
/* try to claim PENDING the normal way */
if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)))
return 0;
/*
* The queueing is in progress, or it is already queued. Try to
* steal it from ->worklist without clearing WORK_STRUCT_PENDING.
*/
pool = get_work_pool(work);
if (!pool)
workqueue: mark a work item being canceled as such There can be two reasons try_to_grab_pending() can fail with -EAGAIN. One is when someone else is queueing or deqeueing the work item. With the previous patches, it is guaranteed that PENDING and queued state will soon agree making it safe to busy-retry in this case. The other is if multiple __cancel_work_timer() invocations are racing one another. __cancel_work_timer() grabs PENDING and then waits for running instances of the target work item on all CPUs while holding PENDING and !queued. try_to_grab_pending() invoked from another task will keep returning -EAGAIN while the current owner is waiting. Not distinguishing the two cases is okay because __cancel_work_timer() is the only user of try_to_grab_pending() and it invokes wait_on_work() whenever grabbing fails. For the first case, busy looping should be fine but wait_on_work() doesn't cause any critical problem. For the latter case, the new contender usually waits for the same condition as the current owner, so no unnecessarily extended busy-looping happens. Combined, these make __cancel_work_timer() technically correct even without irq protection while grabbing PENDING or distinguishing the two different cases. While the current code is technically correct, not distinguishing the two cases makes it difficult to use try_to_grab_pending() for other purposes than canceling because it's impossible to tell whether it's safe to busy-retry grabbing. This patch adds a mechanism to mark a work item being canceled. try_to_grab_pending() now disables irq on success and returns -EAGAIN to indicate that grabbing failed but PENDING and queued states are gonna agree soon and it's safe to busy-loop. It returns -ENOENT if the work item is being canceled and it may stay PENDING && !queued for arbitrary amount of time. __cancel_work_timer() is modified to mark the work canceling with WORK_OFFQ_CANCELING after grabbing PENDING, thus making try_to_grab_pending() fail with -ENOENT instead of -EAGAIN. Also, it invokes wait_on_work() iff grabbing failed with -ENOENT. This isn't necessary for correctness but makes it consistent with other future users of try_to_grab_pending(). v2: try_to_grab_pending() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Updated so that try_to_grab_pending() disables irq on success rather than requiring preemption disabled by the caller. This makes busy-looping easier and will allow try_to_grap_pending() to be used from bh/irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:46 +08:00
goto fail;
spin_lock(&pool->lock);
workqueue: simplify is-work-item-queued-here test Currently, determining whether a work item is queued on a locked pool involves somewhat convoluted memory barrier dancing. It goes like the following. * When a work item is queued on a pool, work->data is updated before work->entry is linked to the pending list with a wmb() inbetween. * When trying to determine whether a work item is currently queued on a pool pointed to by work->data, it locks the pool and looks at work->entry. If work->entry is linked, we then do rmb() and then check whether work->data points to the current pool. This works because, work->data can only point to a pool if it currently is or were on the pool and, * If it currently is on the pool, the tests would obviously succeed. * It it left the pool, its work->entry was cleared under pool->lock, so if we're seeing non-empty work->entry, it has to be from the work item being linked on another pool. Because work->data is updated before work->entry is linked with wmb() inbetween, work->data update from another pool is guaranteed to be visible if we do rmb() after seeing non-empty work->entry. So, we either see empty work->entry or we see updated work->data pointin to another pool. While this works, it's convoluted, to put it mildly. With recent updates, it's now guaranteed that work->data points to cwq only while the work item is queued and that updating work->data to point to cwq or back to pool is done under pool->lock, so we can simply test whether work->data points to cwq which is associated with the currently locked pool instead of the convoluted memory barrier dancing. This patch replaces the memory barrier based "are you still here, really?" test with much simpler "does work->data points to me?" test - if work->data points to a cwq which is associated with the currently locked pool, the work item is guaranteed to be queued on the pool as work->data can start and stop pointing to such cwq only under pool->lock and the start and stop coincide with queue and dequeue. tj: Rewrote the comments and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2013-02-07 10:04:53 +08:00
/*
* work->data is guaranteed to point to pwq only while the work
* item is queued on pwq->wq, and both updating work->data to point
* to pwq on queueing and to pool on dequeueing are done under
* pwq->pool->lock. This in turn guarantees that, if work->data
* points to pwq which is associated with a locked pool, the work
workqueue: simplify is-work-item-queued-here test Currently, determining whether a work item is queued on a locked pool involves somewhat convoluted memory barrier dancing. It goes like the following. * When a work item is queued on a pool, work->data is updated before work->entry is linked to the pending list with a wmb() inbetween. * When trying to determine whether a work item is currently queued on a pool pointed to by work->data, it locks the pool and looks at work->entry. If work->entry is linked, we then do rmb() and then check whether work->data points to the current pool. This works because, work->data can only point to a pool if it currently is or were on the pool and, * If it currently is on the pool, the tests would obviously succeed. * It it left the pool, its work->entry was cleared under pool->lock, so if we're seeing non-empty work->entry, it has to be from the work item being linked on another pool. Because work->data is updated before work->entry is linked with wmb() inbetween, work->data update from another pool is guaranteed to be visible if we do rmb() after seeing non-empty work->entry. So, we either see empty work->entry or we see updated work->data pointin to another pool. While this works, it's convoluted, to put it mildly. With recent updates, it's now guaranteed that work->data points to cwq only while the work item is queued and that updating work->data to point to cwq or back to pool is done under pool->lock, so we can simply test whether work->data points to cwq which is associated with the currently locked pool instead of the convoluted memory barrier dancing. This patch replaces the memory barrier based "are you still here, really?" test with much simpler "does work->data points to me?" test - if work->data points to a cwq which is associated with the currently locked pool, the work item is guaranteed to be queued on the pool as work->data can start and stop pointing to such cwq only under pool->lock and the start and stop coincide with queue and dequeue. tj: Rewrote the comments and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2013-02-07 10:04:53 +08:00
* item is currently queued on that pool.
*/
pwq = get_work_pwq(work);
if (pwq && pwq->pool == pool) {
debug_work_deactivate(work);
/*
* A delayed work item cannot be grabbed directly because
* it might have linked NO_COLOR work items which, if left
* on the delayed_list, will confuse pwq->nr_active
* management later on and cause stall. Make sure the work
* item is activated before grabbing.
*/
if (*work_data_bits(work) & WORK_STRUCT_DELAYED)
pwq_activate_delayed_work(work);
list_del_init(&work->entry);
pwq_dec_nr_in_flight(get_work_pwq(work), get_work_color(work));
/* work->data points to pwq iff queued, point to pool */
set_work_pool_and_keep_pending(work, pool->id);
spin_unlock(&pool->lock);
return 1;
}
spin_unlock(&pool->lock);
workqueue: mark a work item being canceled as such There can be two reasons try_to_grab_pending() can fail with -EAGAIN. One is when someone else is queueing or deqeueing the work item. With the previous patches, it is guaranteed that PENDING and queued state will soon agree making it safe to busy-retry in this case. The other is if multiple __cancel_work_timer() invocations are racing one another. __cancel_work_timer() grabs PENDING and then waits for running instances of the target work item on all CPUs while holding PENDING and !queued. try_to_grab_pending() invoked from another task will keep returning -EAGAIN while the current owner is waiting. Not distinguishing the two cases is okay because __cancel_work_timer() is the only user of try_to_grab_pending() and it invokes wait_on_work() whenever grabbing fails. For the first case, busy looping should be fine but wait_on_work() doesn't cause any critical problem. For the latter case, the new contender usually waits for the same condition as the current owner, so no unnecessarily extended busy-looping happens. Combined, these make __cancel_work_timer() technically correct even without irq protection while grabbing PENDING or distinguishing the two different cases. While the current code is technically correct, not distinguishing the two cases makes it difficult to use try_to_grab_pending() for other purposes than canceling because it's impossible to tell whether it's safe to busy-retry grabbing. This patch adds a mechanism to mark a work item being canceled. try_to_grab_pending() now disables irq on success and returns -EAGAIN to indicate that grabbing failed but PENDING and queued states are gonna agree soon and it's safe to busy-loop. It returns -ENOENT if the work item is being canceled and it may stay PENDING && !queued for arbitrary amount of time. __cancel_work_timer() is modified to mark the work canceling with WORK_OFFQ_CANCELING after grabbing PENDING, thus making try_to_grab_pending() fail with -ENOENT instead of -EAGAIN. Also, it invokes wait_on_work() iff grabbing failed with -ENOENT. This isn't necessary for correctness but makes it consistent with other future users of try_to_grab_pending(). v2: try_to_grab_pending() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Updated so that try_to_grab_pending() disables irq on success rather than requiring preemption disabled by the caller. This makes busy-looping easier and will allow try_to_grap_pending() to be used from bh/irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:46 +08:00
fail:
local_irq_restore(*flags);
if (work_is_canceling(work))
return -ENOENT;
cpu_relax();
return -EAGAIN;
}
/**
* insert_work - insert a work into a pool
* @pwq: pwq @work belongs to
* @work: work to insert
* @head: insertion point
* @extra_flags: extra WORK_STRUCT_* flags to set
*
* Insert @work which belongs to @pwq after @head. @extra_flags is or'd to
* work_struct flags.
*
* CONTEXT:
* spin_lock_irq(pool->lock).
*/
static void insert_work(struct pool_workqueue *pwq, struct work_struct *work,
struct list_head *head, unsigned int extra_flags)
implement flush_work() A basic problem with flush_scheduled_work() is that it blocks behind _all_ presently-queued works, rather than just the work whcih the caller wants to flush. If the caller holds some lock, and if one of the queued work happens to want that lock as well then accidental deadlocks can occur. One example of this is the phy layer: it wants to flush work while holding rtnl_lock(). But if a linkwatch event happens to be queued, the phy code will deadlock because the linkwatch callback function takes rtnl_lock. So we implement a new function which will flush a *single* work - just the one which the caller wants to free up. Thus we avoid the accidental deadlocks which can arise from unrelated subsystems' callbacks taking shared locks. flush_work() non-blockingly dequeues the work_struct which we want to kill, then it waits for its handler to complete on all CPUs. Add ->current_work to the "struct cpu_workqueue_struct", it points to currently running "struct work_struct". When flush_work(work) detects ->current_work == work, it inserts a barrier at the _head_ of ->worklist (and thus right _after_ that work) and waits for completition. This means that the next work fired on that CPU will be this barrier, or another barrier queued by concurrent flush_work(), so the caller of flush_work() will be woken before any "regular" work has a chance to run. When wait_on_work() unlocks workqueue_mutex (or whatever we choose to protect against CPU hotplug), CPU may go away. But in that case take_over_work() will move a barrier we queued to another CPU, it will be fired sometime, and wait_on_work() will be woken. Actually, we are doing cleanup_workqueue_thread()->kthread_stop() before take_over_work(), so cwq->thread should complete its ->worklist (and thus the barrier), because currently we don't check kthread_should_stop() in run_workqueue(). But even if we did, everything should be ok. [akpm@osdl.org: cleanup] [akpm@osdl.org: add flush_work_keventd() wrapper] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:33:52 +08:00
{
struct worker_pool *pool = pwq->pool;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/* we own @work, set data and link */
set_work_pwq(work, pwq, extra_flags);
list_add_tail(&work->entry, head);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/*
* Ensure either worker_sched_deactivated() sees the above
* list_add_tail() or we see zero nr_running to avoid workers
* lying around lazily while there are works to be processed.
*/
smp_mb();
if (__need_more_worker(pool))
wake_up_worker(pool);
implement flush_work() A basic problem with flush_scheduled_work() is that it blocks behind _all_ presently-queued works, rather than just the work whcih the caller wants to flush. If the caller holds some lock, and if one of the queued work happens to want that lock as well then accidental deadlocks can occur. One example of this is the phy layer: it wants to flush work while holding rtnl_lock(). But if a linkwatch event happens to be queued, the phy code will deadlock because the linkwatch callback function takes rtnl_lock. So we implement a new function which will flush a *single* work - just the one which the caller wants to free up. Thus we avoid the accidental deadlocks which can arise from unrelated subsystems' callbacks taking shared locks. flush_work() non-blockingly dequeues the work_struct which we want to kill, then it waits for its handler to complete on all CPUs. Add ->current_work to the "struct cpu_workqueue_struct", it points to currently running "struct work_struct". When flush_work(work) detects ->current_work == work, it inserts a barrier at the _head_ of ->worklist (and thus right _after_ that work) and waits for completition. This means that the next work fired on that CPU will be this barrier, or another barrier queued by concurrent flush_work(), so the caller of flush_work() will be woken before any "regular" work has a chance to run. When wait_on_work() unlocks workqueue_mutex (or whatever we choose to protect against CPU hotplug), CPU may go away. But in that case take_over_work() will move a barrier we queued to another CPU, it will be fired sometime, and wait_on_work() will be woken. Actually, we are doing cleanup_workqueue_thread()->kthread_stop() before take_over_work(), so cwq->thread should complete its ->worklist (and thus the barrier), because currently we don't check kthread_should_stop() in run_workqueue(). But even if we did, everything should be ok. [akpm@osdl.org: cleanup] [akpm@osdl.org: add flush_work_keventd() wrapper] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:33:52 +08:00
}
/*
* Test whether @work is being queued from another work executing on the
* same workqueue.
*/
static bool is_chained_work(struct workqueue_struct *wq)
{
struct worker *worker;
worker = current_wq_worker();
/*
* Return %true iff I'm a worker execuing a work item on @wq. If
* I'm @worker, it's safe to dereference it without locking.
*/
return worker && worker->current_pwq->wq == wq;
}
static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
struct work_struct *work)
{
struct pool_workqueue *pwq;
struct list_head *worklist;
unsigned int work_flags;
unsigned int req_cpu = cpu;
workqueue: disable irq while manipulating PENDING Queueing operations use WORK_STRUCT_PENDING_BIT to synchronize access to the target work item. They first try to claim the bit and proceed with queueing only after that succeeds and there's a window between PENDING being set and the actual queueing where the task can be interrupted or preempted. There's also a similar window in process_one_work() when clearing PENDING. A work item is dequeued, gcwq->lock is released and then PENDING is cleared and the worker might get interrupted or preempted between releasing gcwq->lock and clearing PENDING. cancel[_delayed]_work_sync() tries to claim or steal PENDING. The function assumes that a work item with PENDING is either queued or in the process of being [de]queued. In the latter case, it busy-loops until either the work item loses PENDING or is queued. If canceling coincides with the above described interrupts or preemptions, the canceling task will busy-loop while the queueing or executing task is preempted. This patch keeps irq disabled across claiming PENDING and actual queueing and moves PENDING clearing in process_one_work() inside gcwq->lock so that busy looping from PENDING && !queued doesn't wait for interrupted/preempted tasks. Note that, in process_one_work(), setting last CPU and clearing PENDING got merged into single operation. This removes possible long busy-loops and will allow using try_to_grab_pending() from bh and irq contexts. v2: __queue_work() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Disable irq instead of preemption. IRQ will be disabled while grabbing gcwq->lock later anyway and this allows using try_to_grab_pending() from bh and irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:45 +08:00
/*
* While a work item is PENDING && off queue, a task trying to
* steal the PENDING will busy-loop waiting for it to either get
* queued or lose PENDING. Grabbing PENDING and queueing should
* happen with IRQ disabled.
*/
WARN_ON_ONCE(!irqs_disabled());
debug_work_activate(work);
/* if dying, only works from the same workqueue are allowed */
if (unlikely(wq->flags & WQ_DRAINING) &&
WARN_ON_ONCE(!is_chained_work(wq)))
return;
/* determine the pwq to use */
if (!(wq->flags & WQ_UNBOUND)) {
struct worker_pool *last_pool;
if (cpu == WORK_CPU_UNBOUND)
cpu = raw_smp_processor_id();
/*
workqueue: make all workqueues non-reentrant By default, each per-cpu part of a bound workqueue operates separately and a work item may be executing concurrently on different CPUs. The behavior avoids some cross-cpu traffic but leads to subtle weirdities and not-so-subtle contortions in the API. * There's no sane usefulness in allowing a single work item to be executed concurrently on multiple CPUs. People just get the behavior unintentionally and get surprised after learning about it. Most either explicitly synchronize or use non-reentrant/ordered workqueue but this is error-prone. * flush_work() can't wait for multiple instances of the same work item on different CPUs. If a work item is executing on cpu0 and then queued on cpu1, flush_work() can only wait for the one on cpu1. Unfortunately, work items can easily cross CPU boundaries unintentionally when the queueing thread gets migrated. This means that if multiple queuers compete, flush_work() can't even guarantee that the instance queued right before it is finished before returning. * flush_work_sync() was added to work around some of the deficiencies of flush_work(). In addition to the usual flushing, it ensures that all currently executing instances are finished before returning. This operation is expensive as it has to walk all CPUs and at the same time fails to address competing queuer case. Incorrectly using flush_work() when flush_work_sync() is necessary is an easy error to make and can lead to bugs which are difficult to reproduce. * Similar problems exist for flush_delayed_work[_sync](). Other than the cross-cpu access concern, there's no benefit in allowing parallel execution and it's plain silly to have this level of contortion for workqueue which is widely used from core code to extremely obscure drivers. This patch makes all workqueues non-reentrant. If a work item is executing on a different CPU when queueing is requested, it is always queued to that CPU. This guarantees that any given work item can be executing on one CPU at maximum and if a work item is queued and executing, both are on the same CPU. The only behavior change which may affect workqueue users negatively is that non-reentrancy overrides the affinity specified by queue_work_on(). On a reentrant workqueue, the affinity specified by queue_work_on() is always followed. Now, if the work item is executing on one of the CPUs, the work item will be queued there regardless of the requested affinity. I've reviewed all workqueue users which request explicit affinity, and, fortunately, none seems to be crazy enough to exploit parallel execution of the same work item. This adds an additional busy_hash lookup if the work item was previously queued on a different CPU. This shouldn't be noticeable under any sane workload. Work item queueing isn't a very high-frequency operation and they don't jump across CPUs all the time. In a micro benchmark to exaggerate this difference - measuring the time it takes for two work items to repeatedly jump between two CPUs a number (10M) of times with busy_hash table densely populated, the difference was around 3%. While the overhead is measureable, it is only visible in pathological cases and the difference isn't huge. This change brings much needed sanity to workqueue and makes its behavior consistent with timer. I think this is the right tradeoff to make. This enables significant simplification of workqueue API. Simplification patches will follow. Signed-off-by: Tejun Heo <tj@kernel.org>
2012-08-21 05:51:23 +08:00
* It's multi cpu. If @work was previously on a different
* cpu, it might still be running there, in which case the
* work needs to be queued on that cpu to guarantee
* non-reentrancy.
*/
pwq = get_pwq(cpu, wq);
last_pool = get_work_pool(work);
workqueue: make all workqueues non-reentrant By default, each per-cpu part of a bound workqueue operates separately and a work item may be executing concurrently on different CPUs. The behavior avoids some cross-cpu traffic but leads to subtle weirdities and not-so-subtle contortions in the API. * There's no sane usefulness in allowing a single work item to be executed concurrently on multiple CPUs. People just get the behavior unintentionally and get surprised after learning about it. Most either explicitly synchronize or use non-reentrant/ordered workqueue but this is error-prone. * flush_work() can't wait for multiple instances of the same work item on different CPUs. If a work item is executing on cpu0 and then queued on cpu1, flush_work() can only wait for the one on cpu1. Unfortunately, work items can easily cross CPU boundaries unintentionally when the queueing thread gets migrated. This means that if multiple queuers compete, flush_work() can't even guarantee that the instance queued right before it is finished before returning. * flush_work_sync() was added to work around some of the deficiencies of flush_work(). In addition to the usual flushing, it ensures that all currently executing instances are finished before returning. This operation is expensive as it has to walk all CPUs and at the same time fails to address competing queuer case. Incorrectly using flush_work() when flush_work_sync() is necessary is an easy error to make and can lead to bugs which are difficult to reproduce. * Similar problems exist for flush_delayed_work[_sync](). Other than the cross-cpu access concern, there's no benefit in allowing parallel execution and it's plain silly to have this level of contortion for workqueue which is widely used from core code to extremely obscure drivers. This patch makes all workqueues non-reentrant. If a work item is executing on a different CPU when queueing is requested, it is always queued to that CPU. This guarantees that any given work item can be executing on one CPU at maximum and if a work item is queued and executing, both are on the same CPU. The only behavior change which may affect workqueue users negatively is that non-reentrancy overrides the affinity specified by queue_work_on(). On a reentrant workqueue, the affinity specified by queue_work_on() is always followed. Now, if the work item is executing on one of the CPUs, the work item will be queued there regardless of the requested affinity. I've reviewed all workqueue users which request explicit affinity, and, fortunately, none seems to be crazy enough to exploit parallel execution of the same work item. This adds an additional busy_hash lookup if the work item was previously queued on a different CPU. This shouldn't be noticeable under any sane workload. Work item queueing isn't a very high-frequency operation and they don't jump across CPUs all the time. In a micro benchmark to exaggerate this difference - measuring the time it takes for two work items to repeatedly jump between two CPUs a number (10M) of times with busy_hash table densely populated, the difference was around 3%. While the overhead is measureable, it is only visible in pathological cases and the difference isn't huge. This change brings much needed sanity to workqueue and makes its behavior consistent with timer. I think this is the right tradeoff to make. This enables significant simplification of workqueue API. Simplification patches will follow. Signed-off-by: Tejun Heo <tj@kernel.org>
2012-08-21 05:51:23 +08:00
if (last_pool && last_pool != pwq->pool) {
struct worker *worker;
spin_lock(&last_pool->lock);
worker = find_worker_executing_work(last_pool, work);
if (worker && worker->current_pwq->wq == wq) {
pwq = get_pwq(last_pool->cpu, wq);
} else {
/* meh... not running there, queue here */
spin_unlock(&last_pool->lock);
spin_lock(&pwq->pool->lock);
}
workqueue: disable irq while manipulating PENDING Queueing operations use WORK_STRUCT_PENDING_BIT to synchronize access to the target work item. They first try to claim the bit and proceed with queueing only after that succeeds and there's a window between PENDING being set and the actual queueing where the task can be interrupted or preempted. There's also a similar window in process_one_work() when clearing PENDING. A work item is dequeued, gcwq->lock is released and then PENDING is cleared and the worker might get interrupted or preempted between releasing gcwq->lock and clearing PENDING. cancel[_delayed]_work_sync() tries to claim or steal PENDING. The function assumes that a work item with PENDING is either queued or in the process of being [de]queued. In the latter case, it busy-loops until either the work item loses PENDING or is queued. If canceling coincides with the above described interrupts or preemptions, the canceling task will busy-loop while the queueing or executing task is preempted. This patch keeps irq disabled across claiming PENDING and actual queueing and moves PENDING clearing in process_one_work() inside gcwq->lock so that busy looping from PENDING && !queued doesn't wait for interrupted/preempted tasks. Note that, in process_one_work(), setting last CPU and clearing PENDING got merged into single operation. This removes possible long busy-loops and will allow using try_to_grab_pending() from bh and irq contexts. v2: __queue_work() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Disable irq instead of preemption. IRQ will be disabled while grabbing gcwq->lock later anyway and this allows using try_to_grab_pending() from bh and irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:45 +08:00
} else {
spin_lock(&pwq->pool->lock);
workqueue: disable irq while manipulating PENDING Queueing operations use WORK_STRUCT_PENDING_BIT to synchronize access to the target work item. They first try to claim the bit and proceed with queueing only after that succeeds and there's a window between PENDING being set and the actual queueing where the task can be interrupted or preempted. There's also a similar window in process_one_work() when clearing PENDING. A work item is dequeued, gcwq->lock is released and then PENDING is cleared and the worker might get interrupted or preempted between releasing gcwq->lock and clearing PENDING. cancel[_delayed]_work_sync() tries to claim or steal PENDING. The function assumes that a work item with PENDING is either queued or in the process of being [de]queued. In the latter case, it busy-loops until either the work item loses PENDING or is queued. If canceling coincides with the above described interrupts or preemptions, the canceling task will busy-loop while the queueing or executing task is preempted. This patch keeps irq disabled across claiming PENDING and actual queueing and moves PENDING clearing in process_one_work() inside gcwq->lock so that busy looping from PENDING && !queued doesn't wait for interrupted/preempted tasks. Note that, in process_one_work(), setting last CPU and clearing PENDING got merged into single operation. This removes possible long busy-loops and will allow using try_to_grab_pending() from bh and irq contexts. v2: __queue_work() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Disable irq instead of preemption. IRQ will be disabled while grabbing gcwq->lock later anyway and this allows using try_to_grab_pending() from bh and irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:45 +08:00
}
} else {
pwq = get_pwq(WORK_CPU_UNBOUND, wq);
spin_lock(&pwq->pool->lock);
}
/* pwq determined, queue */
trace_workqueue_queue_work(req_cpu, pwq, work);
if (WARN_ON(!list_empty(&work->entry))) {
spin_unlock(&pwq->pool->lock);
return;
}
pwq->nr_in_flight[pwq->work_color]++;
work_flags = work_color_to_flags(pwq->work_color);
if (likely(pwq->nr_active < pwq->max_active)) {
trace_workqueue_activate_work(work);
pwq->nr_active++;
worklist = &pwq->pool->worklist;
} else {
work_flags |= WORK_STRUCT_DELAYED;
worklist = &pwq->delayed_works;
}
insert_work(pwq, work, worklist, work_flags);
spin_unlock(&pwq->pool->lock);
}
/**
* queue_work_on - queue work on specific cpu
* @cpu: CPU number to execute work on
* @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.
*/
bool queue_work_on(int cpu, struct workqueue_struct *wq,
struct work_struct *work)
{
bool ret = false;
workqueue: disable irq while manipulating PENDING Queueing operations use WORK_STRUCT_PENDING_BIT to synchronize access to the target work item. They first try to claim the bit and proceed with queueing only after that succeeds and there's a window between PENDING being set and the actual queueing where the task can be interrupted or preempted. There's also a similar window in process_one_work() when clearing PENDING. A work item is dequeued, gcwq->lock is released and then PENDING is cleared and the worker might get interrupted or preempted between releasing gcwq->lock and clearing PENDING. cancel[_delayed]_work_sync() tries to claim or steal PENDING. The function assumes that a work item with PENDING is either queued or in the process of being [de]queued. In the latter case, it busy-loops until either the work item loses PENDING or is queued. If canceling coincides with the above described interrupts or preemptions, the canceling task will busy-loop while the queueing or executing task is preempted. This patch keeps irq disabled across claiming PENDING and actual queueing and moves PENDING clearing in process_one_work() inside gcwq->lock so that busy looping from PENDING && !queued doesn't wait for interrupted/preempted tasks. Note that, in process_one_work(), setting last CPU and clearing PENDING got merged into single operation. This removes possible long busy-loops and will allow using try_to_grab_pending() from bh and irq contexts. v2: __queue_work() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Disable irq instead of preemption. IRQ will be disabled while grabbing gcwq->lock later anyway and this allows using try_to_grab_pending() from bh and irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:45 +08:00
unsigned long flags;
workqueue: disable irq while manipulating PENDING Queueing operations use WORK_STRUCT_PENDING_BIT to synchronize access to the target work item. They first try to claim the bit and proceed with queueing only after that succeeds and there's a window between PENDING being set and the actual queueing where the task can be interrupted or preempted. There's also a similar window in process_one_work() when clearing PENDING. A work item is dequeued, gcwq->lock is released and then PENDING is cleared and the worker might get interrupted or preempted between releasing gcwq->lock and clearing PENDING. cancel[_delayed]_work_sync() tries to claim or steal PENDING. The function assumes that a work item with PENDING is either queued or in the process of being [de]queued. In the latter case, it busy-loops until either the work item loses PENDING or is queued. If canceling coincides with the above described interrupts or preemptions, the canceling task will busy-loop while the queueing or executing task is preempted. This patch keeps irq disabled across claiming PENDING and actual queueing and moves PENDING clearing in process_one_work() inside gcwq->lock so that busy looping from PENDING && !queued doesn't wait for interrupted/preempted tasks. Note that, in process_one_work(), setting last CPU and clearing PENDING got merged into single operation. This removes possible long busy-loops and will allow using try_to_grab_pending() from bh and irq contexts. v2: __queue_work() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Disable irq instead of preemption. IRQ will be disabled while grabbing gcwq->lock later anyway and this allows using try_to_grab_pending() from bh and irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:45 +08:00
local_irq_save(flags);
if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
__queue_work(cpu, wq, work);
ret = true;
}
workqueue: disable irq while manipulating PENDING Queueing operations use WORK_STRUCT_PENDING_BIT to synchronize access to the target work item. They first try to claim the bit and proceed with queueing only after that succeeds and there's a window between PENDING being set and the actual queueing where the task can be interrupted or preempted. There's also a similar window in process_one_work() when clearing PENDING. A work item is dequeued, gcwq->lock is released and then PENDING is cleared and the worker might get interrupted or preempted between releasing gcwq->lock and clearing PENDING. cancel[_delayed]_work_sync() tries to claim or steal PENDING. The function assumes that a work item with PENDING is either queued or in the process of being [de]queued. In the latter case, it busy-loops until either the work item loses PENDING or is queued. If canceling coincides with the above described interrupts or preemptions, the canceling task will busy-loop while the queueing or executing task is preempted. This patch keeps irq disabled across claiming PENDING and actual queueing and moves PENDING clearing in process_one_work() inside gcwq->lock so that busy looping from PENDING && !queued doesn't wait for interrupted/preempted tasks. Note that, in process_one_work(), setting last CPU and clearing PENDING got merged into single operation. This removes possible long busy-loops and will allow using try_to_grab_pending() from bh and irq contexts. v2: __queue_work() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Disable irq instead of preemption. IRQ will be disabled while grabbing gcwq->lock later anyway and this allows using try_to_grab_pending() from bh and irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:45 +08:00
local_irq_restore(flags);
return ret;
}
EXPORT_SYMBOL_GPL(queue_work_on);
/**
* queue_work - queue work on a workqueue
* @wq: workqueue to use
* @work: work to queue
*
* Returns %false if @work was already on a queue, %true otherwise.
*
* We queue the work to the CPU on which it was submitted, but if the CPU dies
* it can be processed by another CPU.
*/
bool queue_work(struct workqueue_struct *wq, struct work_struct *work)
{
return queue_work_on(WORK_CPU_UNBOUND, wq, work);
}
EXPORT_SYMBOL_GPL(queue_work);
void delayed_work_timer_fn(unsigned long __data)
{
struct delayed_work *dwork = (struct delayed_work *)__data;
/* should have been called from irqsafe timer with irq already off */
workqueue: add delayed_work->wq to simplify reentrancy handling To avoid executing the same work item from multiple CPUs concurrently, a work_struct records the last pool it was on in its ->data so that, on the next queueing, the pool can be queried to determine whether the work item is still executing or not. A delayed_work goes through timer before actually being queued on the target workqueue and the timer needs to know the target workqueue and CPU. This is currently achieved by modifying delayed_work->work.data such that it points to the cwq which points to the target workqueue and the last CPU the work item was on. __queue_delayed_work() extracts the last CPU from delayed_work->work.data and then combines it with the target workqueue to create new work.data. The only thing this rather ugly hack achieves is encoding the target workqueue into delayed_work->work.data without using a separate field, which could be a trade off one can make; unfortunately, this entangles work->data management between regular workqueue and delayed_work code by setting cwq pointer before the work item is actually queued and becomes a hindrance for further improvements of work->data handling. This can be easily made sane by adding a target workqueue field to delayed_work. While delayed_work is used widely in the kernel and this does make it a bit larger (<5%), I think this is the right trade-off especially given the prospect of much saner handling of work->data which currently involves quite tricky memory barrier dancing, and don't expect to see any measureable effect. Add delayed_work->wq and drop the delayed_work->work.data overloading. tj: Rewrote the description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2013-02-07 10:04:53 +08:00
__queue_work(dwork->cpu, dwork->wq, &dwork->work);
}
EXPORT_SYMBOL(delayed_work_timer_fn);
static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
struct delayed_work *dwork, unsigned long delay)
{
struct timer_list *timer = &dwork->timer;
struct work_struct *work = &dwork->work;
WARN_ON_ONCE(timer->function != delayed_work_timer_fn ||
timer->data != (unsigned long)dwork);
WARN_ON_ONCE(timer_pending(timer));
WARN_ON_ONCE(!list_empty(&work->entry));
workqueue: mod_delayed_work_on() shouldn't queue timer on 0 delay 8376fe22c7 ("workqueue: implement mod_delayed_work[_on]()") implemented mod_delayed_work[_on]() using the improved try_to_grab_pending(). The function is later used, among others, to replace [__]candel_delayed_work() + queue_delayed_work() combinations. Unfortunately, a delayed_work item w/ zero @delay is handled slightly differently by mod_delayed_work_on() compared to queue_delayed_work_on(). The latter skips timer altogether and directly queues it using queue_work_on() while the former schedules timer which will expire on the closest tick. This means, when @delay is zero, that [__]cancel_delayed_work() + queue_delayed_work_on() makes the target item immediately executable while mod_delayed_work_on() may induce delay of upto a full tick. This somewhat subtle difference breaks some of the converted users. e.g. block queue plugging uses delayed_work for deferred processing and uses mod_delayed_work_on() when the queue needs to be immediately unplugged. The above problem manifested as noticeably higher number of context switches under certain circumstances. The difference in behavior was caused by missing special case handling for 0 delay in mod_delayed_work_on() compared to queue_delayed_work_on(). Joonsoo Kim posted a patch to add it - ("workqueue: optimize mod_delayed_work_on() when @delay == 0")[1]. The patch was queued for 3.8 but it was described as optimization and I missed that it was a correctness issue. As both queue_delayed_work_on() and mod_delayed_work_on() use __queue_delayed_work() for queueing, it seems that the better approach is to move the 0 delay special handling to the function instead of duplicating it in mod_delayed_work_on(). Fix the problem by moving 0 delay special case handling from queue_delayed_work_on() to __queue_delayed_work(). This replaces Joonsoo's patch. [1] http://thread.gmane.org/gmane.linux.kernel/1379011/focus=1379012 Signed-off-by: Tejun Heo <tj@kernel.org> Reported-and-tested-by: Anders Kaseorg <andersk@MIT.EDU> Reported-and-tested-by: Zlatko Calusic <zlatko.calusic@iskon.hr> LKML-Reference: <alpine.DEB.2.00.1211280953350.26602@dr-wily.mit.edu> LKML-Reference: <50A78AA9.5040904@iskon.hr> Cc: Joonsoo Kim <js1304@gmail.com>
2012-12-02 08:23:42 +08:00
/*
* If @delay is 0, queue @dwork->work immediately. This is for
* both optimization and correctness. The earliest @timer can
* expire is on the closest next tick and delayed_work users depend
* on that there's no such delay when @delay is 0.
*/
if (!delay) {
__queue_work(cpu, wq, &dwork->work);
return;
}
timer_stats_timer_set_start_info(&dwork->timer);
workqueue: add delayed_work->wq to simplify reentrancy handling To avoid executing the same work item from multiple CPUs concurrently, a work_struct records the last pool it was on in its ->data so that, on the next queueing, the pool can be queried to determine whether the work item is still executing or not. A delayed_work goes through timer before actually being queued on the target workqueue and the timer needs to know the target workqueue and CPU. This is currently achieved by modifying delayed_work->work.data such that it points to the cwq which points to the target workqueue and the last CPU the work item was on. __queue_delayed_work() extracts the last CPU from delayed_work->work.data and then combines it with the target workqueue to create new work.data. The only thing this rather ugly hack achieves is encoding the target workqueue into delayed_work->work.data without using a separate field, which could be a trade off one can make; unfortunately, this entangles work->data management between regular workqueue and delayed_work code by setting cwq pointer before the work item is actually queued and becomes a hindrance for further improvements of work->data handling. This can be easily made sane by adding a target workqueue field to delayed_work. While delayed_work is used widely in the kernel and this does make it a bit larger (<5%), I think this is the right trade-off especially given the prospect of much saner handling of work->data which currently involves quite tricky memory barrier dancing, and don't expect to see any measureable effect. Add delayed_work->wq and drop the delayed_work->work.data overloading. tj: Rewrote the description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2013-02-07 10:04:53 +08:00
dwork->wq = wq;
dwork->cpu = cpu;
timer->expires = jiffies + delay;
if (unlikely(cpu != WORK_CPU_UNBOUND))
add_timer_on(timer, cpu);
else
add_timer(timer);
}
/**
* queue_delayed_work_on - queue work on specific CPU after delay
* @cpu: CPU number to execute work on
* @wq: workqueue to use
* @dwork: work to queue
* @delay: number of jiffies to wait before queueing
*
* Returns %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.
*/
bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
struct delayed_work *dwork, unsigned long delay)
{
struct work_struct *work = &dwork->work;
bool ret = false;
workqueue: disable irq while manipulating PENDING Queueing operations use WORK_STRUCT_PENDING_BIT to synchronize access to the target work item. They first try to claim the bit and proceed with queueing only after that succeeds and there's a window between PENDING being set and the actual queueing where the task can be interrupted or preempted. There's also a similar window in process_one_work() when clearing PENDING. A work item is dequeued, gcwq->lock is released and then PENDING is cleared and the worker might get interrupted or preempted between releasing gcwq->lock and clearing PENDING. cancel[_delayed]_work_sync() tries to claim or steal PENDING. The function assumes that a work item with PENDING is either queued or in the process of being [de]queued. In the latter case, it busy-loops until either the work item loses PENDING or is queued. If canceling coincides with the above described interrupts or preemptions, the canceling task will busy-loop while the queueing or executing task is preempted. This patch keeps irq disabled across claiming PENDING and actual queueing and moves PENDING clearing in process_one_work() inside gcwq->lock so that busy looping from PENDING && !queued doesn't wait for interrupted/preempted tasks. Note that, in process_one_work(), setting last CPU and clearing PENDING got merged into single operation. This removes possible long busy-loops and will allow using try_to_grab_pending() from bh and irq contexts. v2: __queue_work() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Disable irq instead of preemption. IRQ will be disabled while grabbing gcwq->lock later anyway and this allows using try_to_grab_pending() from bh and irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:45 +08:00
unsigned long flags;
workqueue: disable irq while manipulating PENDING Queueing operations use WORK_STRUCT_PENDING_BIT to synchronize access to the target work item. They first try to claim the bit and proceed with queueing only after that succeeds and there's a window between PENDING being set and the actual queueing where the task can be interrupted or preempted. There's also a similar window in process_one_work() when clearing PENDING. A work item is dequeued, gcwq->lock is released and then PENDING is cleared and the worker might get interrupted or preempted between releasing gcwq->lock and clearing PENDING. cancel[_delayed]_work_sync() tries to claim or steal PENDING. The function assumes that a work item with PENDING is either queued or in the process of being [de]queued. In the latter case, it busy-loops until either the work item loses PENDING or is queued. If canceling coincides with the above described interrupts or preemptions, the canceling task will busy-loop while the queueing or executing task is preempted. This patch keeps irq disabled across claiming PENDING and actual queueing and moves PENDING clearing in process_one_work() inside gcwq->lock so that busy looping from PENDING && !queued doesn't wait for interrupted/preempted tasks. Note that, in process_one_work(), setting last CPU and clearing PENDING got merged into single operation. This removes possible long busy-loops and will allow using try_to_grab_pending() from bh and irq contexts. v2: __queue_work() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Disable irq instead of preemption. IRQ will be disabled while grabbing gcwq->lock later anyway and this allows using try_to_grab_pending() from bh and irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:45 +08:00
/* read the comment in __queue_work() */
local_irq_save(flags);
if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
__queue_delayed_work(cpu, wq, dwork, delay);
ret = true;
}
workqueue: disable irq while manipulating PENDING Queueing operations use WORK_STRUCT_PENDING_BIT to synchronize access to the target work item. They first try to claim the bit and proceed with queueing only after that succeeds and there's a window between PENDING being set and the actual queueing where the task can be interrupted or preempted. There's also a similar window in process_one_work() when clearing PENDING. A work item is dequeued, gcwq->lock is released and then PENDING is cleared and the worker might get interrupted or preempted between releasing gcwq->lock and clearing PENDING. cancel[_delayed]_work_sync() tries to claim or steal PENDING. The function assumes that a work item with PENDING is either queued or in the process of being [de]queued. In the latter case, it busy-loops until either the work item loses PENDING or is queued. If canceling coincides with the above described interrupts or preemptions, the canceling task will busy-loop while the queueing or executing task is preempted. This patch keeps irq disabled across claiming PENDING and actual queueing and moves PENDING clearing in process_one_work() inside gcwq->lock so that busy looping from PENDING && !queued doesn't wait for interrupted/preempted tasks. Note that, in process_one_work(), setting last CPU and clearing PENDING got merged into single operation. This removes possible long busy-loops and will allow using try_to_grab_pending() from bh and irq contexts. v2: __queue_work() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Disable irq instead of preemption. IRQ will be disabled while grabbing gcwq->lock later anyway and this allows using try_to_grab_pending() from bh and irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:45 +08:00
local_irq_restore(flags);
return ret;
}
EXPORT_SYMBOL_GPL(queue_delayed_work_on);
/**
* queue_delayed_work - queue work on a workqueue after delay
* @wq: workqueue to use
* @dwork: delayable work to queue
* @delay: number of jiffies to wait before queueing
*
* Equivalent to queue_delayed_work_on() but tries to use the local CPU.
*/
bool queue_delayed_work(struct workqueue_struct *wq,
struct delayed_work *dwork, unsigned long delay)
{
return queue_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay);
}
EXPORT_SYMBOL_GPL(queue_delayed_work);
/**
* mod_delayed_work_on - modify delay of or queue a delayed work on specific CPU
* @cpu: CPU number to execute work on
* @wq: workqueue to use
* @dwork: work to queue
* @delay: number of jiffies to wait before queueing
*
* If @dwork is idle, equivalent to queue_delayed_work_on(); otherwise,
* modify @dwork's timer so that it expires after @delay. If @delay is
* 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
* pending and its timer was modified.
*
* This function is safe to call from any context including IRQ handler.
* See try_to_grab_pending() for details.
*/
bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq,
struct delayed_work *dwork, unsigned long delay)
{
unsigned long flags;
int ret;
do {
ret = try_to_grab_pending(&dwork->work, true, &flags);
} while (unlikely(ret == -EAGAIN));
if (likely(ret >= 0)) {
__queue_delayed_work(cpu, wq, dwork, delay);
local_irq_restore(flags);
}
/* -ENOENT from try_to_grab_pending() becomes %true */
return ret;
}
EXPORT_SYMBOL_GPL(mod_delayed_work_on);
/**
* mod_delayed_work - modify delay of or queue a delayed work
* @wq: workqueue to use
* @dwork: work to queue
* @delay: number of jiffies to wait before queueing
*
* mod_delayed_work_on() on local CPU.
*/
bool mod_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork,
unsigned long delay)
{
return mod_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay);
}
EXPORT_SYMBOL_GPL(mod_delayed_work);
/**
* worker_enter_idle - enter idle state
* @worker: worker which is entering idle state
*
* @worker is entering idle state. Update stats and idle timer if
* necessary.
*
* LOCKING:
* spin_lock_irq(pool->lock).
*/
static void worker_enter_idle(struct worker *worker)
{
struct worker_pool *pool = worker->pool;
BUG_ON(worker->flags & WORKER_IDLE);
BUG_ON(!list_empty(&worker->entry) &&
(worker->hentry.next || worker->hentry.pprev));
/* can't use worker_set_flags(), also called from start_worker() */
worker->flags |= WORKER_IDLE;
pool->nr_idle++;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
worker->last_active = jiffies;
/* idle_list is LIFO */
list_add(&worker->entry, &pool->idle_list);
if (too_many_workers(pool) && !timer_pending(&pool->idle_timer))
mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT);
/*
* Sanity check nr_running. Because wq_unbind_fn() releases
* pool->lock between setting %WORKER_UNBOUND and zapping
* nr_running, the warning may trigger spuriously. Check iff
* unbind is not in progress.
*/
WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) &&
pool->nr_workers == pool->nr_idle &&
atomic_read(&pool->nr_running));
}
/**
* worker_leave_idle - leave idle state
* @worker: worker which is leaving idle state
*
* @worker is leaving idle state. Update stats.
*
* LOCKING:
* spin_lock_irq(pool->lock).
*/
static void worker_leave_idle(struct worker *worker)
{
struct worker_pool *pool = worker->pool;
BUG_ON(!(worker->flags & WORKER_IDLE));
worker_clr_flags(worker, WORKER_IDLE);
pool->nr_idle--;
list_del_init(&worker->entry);
}
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/**
* worker_maybe_bind_and_lock - bind worker to its cpu if possible and lock pool
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* @worker: self
*
* Works which are scheduled while the cpu is online must at least be
* scheduled to a worker which is bound to the cpu so that if they are
* flushed from cpu callbacks while cpu is going down, they are
* guaranteed to execute on the cpu.
*
* This function is to be used by rogue workers and rescuers to bind
* themselves to the target cpu and may race with cpu going down or
* coming online. kthread_bind() can't be used because it may put the
* worker to already dead cpu and set_cpus_allowed_ptr() can't be used
* verbatim as it's best effort and blocking and pool may be
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* [dis]associated in the meantime.
*
* This function tries set_cpus_allowed() and locks pool and verifies the
* binding against %POOL_DISASSOCIATED which is set during
* %CPU_DOWN_PREPARE and cleared during %CPU_ONLINE, so if the worker
* enters idle state or fetches works without dropping lock, it can
* guarantee the scheduling requirement described in the first paragraph.
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
*
* CONTEXT:
* Might sleep. Called without any lock but returns with pool->lock
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* held.
*
* RETURNS:
* %true if the associated pool is online (@worker is successfully
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* bound), %false if offline.
*/
static bool worker_maybe_bind_and_lock(struct worker *worker)
__acquires(&pool->lock)
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
{
struct worker_pool *pool = worker->pool;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
struct task_struct *task = worker->task;
while (true) {
/*
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* The following call may fail, succeed or succeed
* without actually migrating the task to the cpu if
* it races with cpu hotunplug operation. Verify
* against POOL_DISASSOCIATED.
*/
if (!(pool->flags & POOL_DISASSOCIATED))
set_cpus_allowed_ptr(task, get_cpu_mask(pool->cpu));
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
spin_lock_irq(&pool->lock);
if (pool->flags & POOL_DISASSOCIATED)
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
return false;
if (task_cpu(task) == pool->cpu &&
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
cpumask_equal(&current->cpus_allowed,
get_cpu_mask(pool->cpu)))
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
return true;
spin_unlock_irq(&pool->lock);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/*
* We've raced with CPU hot[un]plug. Give it a breather
* and retry migration. cond_resched() is required here;
* otherwise, we might deadlock against cpu_stop trying to
* bring down the CPU on non-preemptive kernel.
*/
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
cpu_relax();
cond_resched();
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
}
}
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
/*
workqueue: reimplement idle worker rebinding Currently rebind_workers() uses rebinds idle workers synchronously before proceeding to requesting busy workers to rebind. This is necessary because all workers on @worker_pool->idle_list must be bound before concurrency management local wake-ups from the busy workers take place. Unfortunately, the synchronous idle rebinding is quite complicated. This patch reimplements idle rebinding to simplify the code path. Rather than trying to make all idle workers bound before rebinding busy workers, we simply remove all to-be-bound idle workers from the idle list and let them add themselves back after completing rebinding (successful or not). As only workers which finished rebinding can on on the idle worker list, the idle worker list is guaranteed to have only bound workers unless CPU went down again and local wake-ups are safe. After the change, @worker_pool->nr_idle may deviate than the actual number of idle workers on @worker_pool->idle_list. More specifically, nr_idle may be non-zero while ->idle_list is empty. All users of ->nr_idle and ->idle_list are audited. The only affected one is too_many_workers() which is updated to check %false if ->idle_list is empty regardless of ->nr_idle. After this patch, rebind_workers() no longer performs the nasty idle-rebind retries which require temporary release of gcwq->lock, and both unbinding and rebinding are atomic w.r.t. global_cwq->lock. worker->idle_rebind and global_cwq->rebind_hold are now unnecessary and removed along with the definition of struct idle_rebind. Changed from V1: 1) remove unlikely from too_many_workers(), ->idle_list can be empty anytime, even before this patch, no reason to use unlikely. 2) fix a small rebasing mistake. (which is from rebasing the orignal fixing patch to for-next) 3) add a lot of comments. 4) clear WORKER_REBIND unconditionaly in idle_worker_rebind() tj: Updated comments and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2012-09-19 00:59:22 +08:00
* Rebind an idle @worker to its CPU. worker_thread() will test
* list_empty(@worker->entry) before leaving idle and call this function.
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
*/
static void idle_worker_rebind(struct worker *worker)
{
/* CPU may go down again inbetween, clear UNBOUND only on success */
if (worker_maybe_bind_and_lock(worker))
worker_clr_flags(worker, WORKER_UNBOUND);
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
workqueue: reimplement idle worker rebinding Currently rebind_workers() uses rebinds idle workers synchronously before proceeding to requesting busy workers to rebind. This is necessary because all workers on @worker_pool->idle_list must be bound before concurrency management local wake-ups from the busy workers take place. Unfortunately, the synchronous idle rebinding is quite complicated. This patch reimplements idle rebinding to simplify the code path. Rather than trying to make all idle workers bound before rebinding busy workers, we simply remove all to-be-bound idle workers from the idle list and let them add themselves back after completing rebinding (successful or not). As only workers which finished rebinding can on on the idle worker list, the idle worker list is guaranteed to have only bound workers unless CPU went down again and local wake-ups are safe. After the change, @worker_pool->nr_idle may deviate than the actual number of idle workers on @worker_pool->idle_list. More specifically, nr_idle may be non-zero while ->idle_list is empty. All users of ->nr_idle and ->idle_list are audited. The only affected one is too_many_workers() which is updated to check %false if ->idle_list is empty regardless of ->nr_idle. After this patch, rebind_workers() no longer performs the nasty idle-rebind retries which require temporary release of gcwq->lock, and both unbinding and rebinding are atomic w.r.t. global_cwq->lock. worker->idle_rebind and global_cwq->rebind_hold are now unnecessary and removed along with the definition of struct idle_rebind. Changed from V1: 1) remove unlikely from too_many_workers(), ->idle_list can be empty anytime, even before this patch, no reason to use unlikely. 2) fix a small rebasing mistake. (which is from rebasing the orignal fixing patch to for-next) 3) add a lot of comments. 4) clear WORKER_REBIND unconditionaly in idle_worker_rebind() tj: Updated comments and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2012-09-19 00:59:22 +08:00
/* rebind complete, become available again */
list_add(&worker->entry, &worker->pool->idle_list);
spin_unlock_irq(&worker->pool->lock);
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
}
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/*
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
* Function for @worker->rebind.work used to rebind unbound busy workers to
* the associated cpu which is coming back online. This is scheduled by
* cpu up but can race with other cpu hotplug operations and may be
* executed twice without intervening cpu down.
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
*/
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
static void busy_worker_rebind_fn(struct work_struct *work)
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
{
struct worker *worker = container_of(work, struct worker, rebind_work);
if (worker_maybe_bind_and_lock(worker))
worker_clr_flags(worker, WORKER_UNBOUND);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
spin_unlock_irq(&worker->pool->lock);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
}
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
/**
* rebind_workers - rebind all workers of a pool to the associated CPU
* @pool: pool of interest
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
*
* @pool->cpu is coming online. Rebind all workers to the CPU. Rebinding
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
* is different for idle and busy ones.
*
workqueue: reimplement idle worker rebinding Currently rebind_workers() uses rebinds idle workers synchronously before proceeding to requesting busy workers to rebind. This is necessary because all workers on @worker_pool->idle_list must be bound before concurrency management local wake-ups from the busy workers take place. Unfortunately, the synchronous idle rebinding is quite complicated. This patch reimplements idle rebinding to simplify the code path. Rather than trying to make all idle workers bound before rebinding busy workers, we simply remove all to-be-bound idle workers from the idle list and let them add themselves back after completing rebinding (successful or not). As only workers which finished rebinding can on on the idle worker list, the idle worker list is guaranteed to have only bound workers unless CPU went down again and local wake-ups are safe. After the change, @worker_pool->nr_idle may deviate than the actual number of idle workers on @worker_pool->idle_list. More specifically, nr_idle may be non-zero while ->idle_list is empty. All users of ->nr_idle and ->idle_list are audited. The only affected one is too_many_workers() which is updated to check %false if ->idle_list is empty regardless of ->nr_idle. After this patch, rebind_workers() no longer performs the nasty idle-rebind retries which require temporary release of gcwq->lock, and both unbinding and rebinding are atomic w.r.t. global_cwq->lock. worker->idle_rebind and global_cwq->rebind_hold are now unnecessary and removed along with the definition of struct idle_rebind. Changed from V1: 1) remove unlikely from too_many_workers(), ->idle_list can be empty anytime, even before this patch, no reason to use unlikely. 2) fix a small rebasing mistake. (which is from rebasing the orignal fixing patch to for-next) 3) add a lot of comments. 4) clear WORKER_REBIND unconditionaly in idle_worker_rebind() tj: Updated comments and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2012-09-19 00:59:22 +08:00
* Idle ones will be removed from the idle_list and woken up. They will
* add themselves back after completing rebind. This ensures that the
* idle_list doesn't contain any unbound workers when re-bound busy workers
* try to perform local wake-ups for concurrency management.
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
*
workqueue: reimplement idle worker rebinding Currently rebind_workers() uses rebinds idle workers synchronously before proceeding to requesting busy workers to rebind. This is necessary because all workers on @worker_pool->idle_list must be bound before concurrency management local wake-ups from the busy workers take place. Unfortunately, the synchronous idle rebinding is quite complicated. This patch reimplements idle rebinding to simplify the code path. Rather than trying to make all idle workers bound before rebinding busy workers, we simply remove all to-be-bound idle workers from the idle list and let them add themselves back after completing rebinding (successful or not). As only workers which finished rebinding can on on the idle worker list, the idle worker list is guaranteed to have only bound workers unless CPU went down again and local wake-ups are safe. After the change, @worker_pool->nr_idle may deviate than the actual number of idle workers on @worker_pool->idle_list. More specifically, nr_idle may be non-zero while ->idle_list is empty. All users of ->nr_idle and ->idle_list are audited. The only affected one is too_many_workers() which is updated to check %false if ->idle_list is empty regardless of ->nr_idle. After this patch, rebind_workers() no longer performs the nasty idle-rebind retries which require temporary release of gcwq->lock, and both unbinding and rebinding are atomic w.r.t. global_cwq->lock. worker->idle_rebind and global_cwq->rebind_hold are now unnecessary and removed along with the definition of struct idle_rebind. Changed from V1: 1) remove unlikely from too_many_workers(), ->idle_list can be empty anytime, even before this patch, no reason to use unlikely. 2) fix a small rebasing mistake. (which is from rebasing the orignal fixing patch to for-next) 3) add a lot of comments. 4) clear WORKER_REBIND unconditionaly in idle_worker_rebind() tj: Updated comments and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2012-09-19 00:59:22 +08:00
* Busy workers can rebind after they finish their current work items.
* Queueing the rebind work item at the head of the scheduled list is
* enough. Note that nr_running will be properly bumped as busy workers
* rebind.
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
*
workqueue: reimplement idle worker rebinding Currently rebind_workers() uses rebinds idle workers synchronously before proceeding to requesting busy workers to rebind. This is necessary because all workers on @worker_pool->idle_list must be bound before concurrency management local wake-ups from the busy workers take place. Unfortunately, the synchronous idle rebinding is quite complicated. This patch reimplements idle rebinding to simplify the code path. Rather than trying to make all idle workers bound before rebinding busy workers, we simply remove all to-be-bound idle workers from the idle list and let them add themselves back after completing rebinding (successful or not). As only workers which finished rebinding can on on the idle worker list, the idle worker list is guaranteed to have only bound workers unless CPU went down again and local wake-ups are safe. After the change, @worker_pool->nr_idle may deviate than the actual number of idle workers on @worker_pool->idle_list. More specifically, nr_idle may be non-zero while ->idle_list is empty. All users of ->nr_idle and ->idle_list are audited. The only affected one is too_many_workers() which is updated to check %false if ->idle_list is empty regardless of ->nr_idle. After this patch, rebind_workers() no longer performs the nasty idle-rebind retries which require temporary release of gcwq->lock, and both unbinding and rebinding are atomic w.r.t. global_cwq->lock. worker->idle_rebind and global_cwq->rebind_hold are now unnecessary and removed along with the definition of struct idle_rebind. Changed from V1: 1) remove unlikely from too_many_workers(), ->idle_list can be empty anytime, even before this patch, no reason to use unlikely. 2) fix a small rebasing mistake. (which is from rebasing the orignal fixing patch to for-next) 3) add a lot of comments. 4) clear WORKER_REBIND unconditionaly in idle_worker_rebind() tj: Updated comments and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2012-09-19 00:59:22 +08:00
* On return, all non-manager workers are scheduled for rebind - see
* manage_workers() for the manager special case. Any idle worker
* including the manager will not appear on @idle_list until rebind is
* complete, making local wake-ups safe.
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
*/
static void rebind_workers(struct worker_pool *pool)
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
{
workqueue: reimplement idle worker rebinding Currently rebind_workers() uses rebinds idle workers synchronously before proceeding to requesting busy workers to rebind. This is necessary because all workers on @worker_pool->idle_list must be bound before concurrency management local wake-ups from the busy workers take place. Unfortunately, the synchronous idle rebinding is quite complicated. This patch reimplements idle rebinding to simplify the code path. Rather than trying to make all idle workers bound before rebinding busy workers, we simply remove all to-be-bound idle workers from the idle list and let them add themselves back after completing rebinding (successful or not). As only workers which finished rebinding can on on the idle worker list, the idle worker list is guaranteed to have only bound workers unless CPU went down again and local wake-ups are safe. After the change, @worker_pool->nr_idle may deviate than the actual number of idle workers on @worker_pool->idle_list. More specifically, nr_idle may be non-zero while ->idle_list is empty. All users of ->nr_idle and ->idle_list are audited. The only affected one is too_many_workers() which is updated to check %false if ->idle_list is empty regardless of ->nr_idle. After this patch, rebind_workers() no longer performs the nasty idle-rebind retries which require temporary release of gcwq->lock, and both unbinding and rebinding are atomic w.r.t. global_cwq->lock. worker->idle_rebind and global_cwq->rebind_hold are now unnecessary and removed along with the definition of struct idle_rebind. Changed from V1: 1) remove unlikely from too_many_workers(), ->idle_list can be empty anytime, even before this patch, no reason to use unlikely. 2) fix a small rebasing mistake. (which is from rebasing the orignal fixing patch to for-next) 3) add a lot of comments. 4) clear WORKER_REBIND unconditionaly in idle_worker_rebind() tj: Updated comments and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2012-09-19 00:59:22 +08:00
struct worker *worker, *n;
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
int i;
lockdep_assert_held(&pool->assoc_mutex);
lockdep_assert_held(&pool->lock);
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
/* dequeue and kick idle ones */
list_for_each_entry_safe(worker, n, &pool->idle_list, entry) {
/*
* idle workers should be off @pool->idle_list until rebind
* is complete to avoid receiving premature local wake-ups.
*/
list_del_init(&worker->entry);
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
/*
* worker_thread() will see the above dequeuing and call
* idle_worker_rebind().
*/
wake_up_process(worker->task);
}
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
/* rebind busy workers */
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:06:00 +08:00
for_each_busy_worker(worker, i, pool) {
struct work_struct *rebind_work = &worker->rebind_work;
struct workqueue_struct *wq;
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
if (test_and_set_bit(WORK_STRUCT_PENDING_BIT,
work_data_bits(rebind_work)))
continue;
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
debug_work_activate(rebind_work);
/*
* wq doesn't really matter but let's keep @worker->pool
* and @pwq->pool consistent for sanity.
*/
if (std_worker_pool_pri(worker->pool))
wq = system_highpri_wq;
else
wq = system_wq;
insert_work(get_pwq(pool->cpu, wq), rebind_work,
worker->scheduled.next,
work_color_to_flags(WORK_NO_COLOR));
workqueue: fix possible deadlock in idle worker rebinding Currently, rebind_workers() and idle_worker_rebind() are two-way interlocked. rebind_workers() waits for idle workers to finish rebinding and rebound idle workers wait for rebind_workers() to finish rebinding busy workers before proceeding. Unfortunately, this isn't enough. The second wait from idle workers is implemented as follows. wait_event(gcwq->rebind_hold, !(worker->flags & WORKER_REBIND)); rebind_workers() clears WORKER_REBIND, wakes up the idle workers and then returns. If CPU hotplug cycle happens again before one of the idle workers finishes the above wait_event(), rebind_workers() will repeat the first part of the handshake - set WORKER_REBIND again and wait for the idle worker to finish rebinding - and this leads to deadlock because the idle worker would be waiting for WORKER_REBIND to clear. This is fixed by adding another interlocking step at the end - rebind_workers() now waits for all the idle workers to finish the above WORKER_REBIND wait before returning. This ensures that all rebinding steps are complete on all idle workers before the next hotplug cycle can happen. This problem was diagnosed by Lai Jiangshan who also posted a patch to fix the issue, upon which this patch is based. This is the minimal fix and further patches are scheduled for the next merge window to simplify the CPU hotplug path. Signed-off-by: Tejun Heo <tj@kernel.org> Original-patch-by: Lai Jiangshan <laijs@cn.fujitsu.com> LKML-Reference: <1346516916-1991-3-git-send-email-laijs@cn.fujitsu.com>
2012-09-05 14:16:32 +08:00
}
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
}
static struct worker *alloc_worker(void)
{
struct worker *worker;
worker = kzalloc(sizeof(*worker), GFP_KERNEL);
if (worker) {
INIT_LIST_HEAD(&worker->entry);
INIT_LIST_HEAD(&worker->scheduled);
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
INIT_WORK(&worker->rebind_work, busy_worker_rebind_fn);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/* on creation a worker is in !idle && prep state */
worker->flags = WORKER_PREP;
}
return worker;
}
/**
* create_worker - create a new workqueue worker
* @pool: pool the new worker will belong to
*
* Create a new worker which is bound to @pool. The returned worker
* can be started by calling start_worker() or destroyed using
* destroy_worker().
*
* CONTEXT:
* Might sleep. Does GFP_KERNEL allocations.
*
* RETURNS:
* Pointer to the newly created worker.
*/
2012-07-18 03:39:27 +08:00
static struct worker *create_worker(struct worker_pool *pool)
{
const char *pri = std_worker_pool_pri(pool) ? "H" : "";
struct worker *worker = NULL;
int id = -1;
spin_lock_irq(&pool->lock);
while (ida_get_new(&pool->worker_ida, &id)) {
spin_unlock_irq(&pool->lock);
if (!ida_pre_get(&pool->worker_ida, GFP_KERNEL))
goto fail;
spin_lock_irq(&pool->lock);
}
spin_unlock_irq(&pool->lock);
worker = alloc_worker();
if (!worker)
goto fail;
worker->pool = pool;
worker->id = id;
if (pool->cpu != WORK_CPU_UNBOUND)
worker->task = kthread_create_on_node(worker_thread,
worker, cpu_to_node(pool->cpu),
"kworker/%u:%d%s", pool->cpu, id, pri);
else
worker->task = kthread_create(worker_thread, worker,
"kworker/u:%d%s", id, pri);
if (IS_ERR(worker->task))
goto fail;
if (std_worker_pool_pri(pool))
set_user_nice(worker->task, HIGHPRI_NICE_LEVEL);
/*
2012-07-18 03:39:27 +08:00
* Determine CPU binding of the new worker depending on
* %POOL_DISASSOCIATED. The caller is responsible for ensuring the
2012-07-18 03:39:27 +08:00
* flag remains stable across this function. See the comments
* above the flag definition for details.
*
* As an unbound worker may later become a regular one if CPU comes
* online, make sure every worker has %PF_THREAD_BOUND set.
*/
if (!(pool->flags & POOL_DISASSOCIATED)) {
kthread_bind(worker->task, pool->cpu);
2012-07-18 03:39:27 +08:00
} else {
worker->task->flags |= PF_THREAD_BOUND;
2012-07-18 03:39:27 +08:00
worker->flags |= WORKER_UNBOUND;
}
return worker;
fail:
if (id >= 0) {
spin_lock_irq(&pool->lock);
ida_remove(&pool->worker_ida, id);
spin_unlock_irq(&pool->lock);
}
kfree(worker);
return NULL;
}
/**
* start_worker - start a newly created worker
* @worker: worker to start
*
* Make the pool aware of @worker and start it.
*
* CONTEXT:
* spin_lock_irq(pool->lock).
*/
static void start_worker(struct worker *worker)
{
worker->flags |= WORKER_STARTED;
worker->pool->nr_workers++;
worker_enter_idle(worker);
wake_up_process(worker->task);
}
/**
* destroy_worker - destroy a workqueue worker
* @worker: worker to be destroyed
*
* Destroy @worker and adjust @pool stats accordingly.
*
* CONTEXT:
* spin_lock_irq(pool->lock) which is released and regrabbed.
*/
static void destroy_worker(struct worker *worker)
{
struct worker_pool *pool = worker->pool;
int id = worker->id;
/* sanity check frenzy */
BUG_ON(worker->current_work);
BUG_ON(!list_empty(&worker->scheduled));
if (worker->flags & WORKER_STARTED)
pool->nr_workers--;
if (worker->flags & WORKER_IDLE)
pool->nr_idle--;
list_del_init(&worker->entry);
worker->flags |= WORKER_DIE;
spin_unlock_irq(&pool->lock);
kthread_stop(worker->task);
kfree(worker);
spin_lock_irq(&pool->lock);
ida_remove(&pool->worker_ida, id);
}
static void idle_worker_timeout(unsigned long __pool)
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
{
struct worker_pool *pool = (void *)__pool;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
spin_lock_irq(&pool->lock);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
if (too_many_workers(pool)) {
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
struct worker *worker;
unsigned long expires;
/* idle_list is kept in LIFO order, check the last one */
worker = list_entry(pool->idle_list.prev, struct worker, entry);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
expires = worker->last_active + IDLE_WORKER_TIMEOUT;
if (time_before(jiffies, expires))
mod_timer(&pool->idle_timer, expires);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
else {
/* it's been idle for too long, wake up manager */
pool->flags |= POOL_MANAGE_WORKERS;
wake_up_worker(pool);
}
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
}
spin_unlock_irq(&pool->lock);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
}
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
static bool send_mayday(struct work_struct *work)
{
struct pool_workqueue *pwq = get_work_pwq(work);
struct workqueue_struct *wq = pwq->wq;
unsigned int cpu;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
if (!(wq->flags & WQ_RESCUER))
return false;
/* mayday mayday mayday */
cpu = pwq->pool->cpu;
/* WORK_CPU_UNBOUND can't be set in cpumask, use cpu 0 instead */
if (cpu == WORK_CPU_UNBOUND)
cpu = 0;
if (!mayday_test_and_set_cpu(cpu, wq->mayday_mask))
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
wake_up_process(wq->rescuer->task);
return true;
}
static void pool_mayday_timeout(unsigned long __pool)
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
{
struct worker_pool *pool = (void *)__pool;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
struct work_struct *work;
spin_lock_irq(&pool->lock);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
if (need_to_create_worker(pool)) {
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/*
* We've been trying to create a new worker but
* haven't been successful. We might be hitting an
* allocation deadlock. Send distress signals to
* rescuers.
*/
list_for_each_entry(work, &pool->worklist, entry)
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
send_mayday(work);
}
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
spin_unlock_irq(&pool->lock);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL);
}
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/**
* maybe_create_worker - create a new worker if necessary
* @pool: pool to create a new worker for
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
*
* Create a new worker for @pool if necessary. @pool is guaranteed to
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* have at least one idle worker on return from this function. If
* creating a new worker takes longer than MAYDAY_INTERVAL, mayday is
* sent to all rescuers with works scheduled on @pool to resolve
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* possible allocation deadlock.
*
* On return, need_to_create_worker() is guaranteed to be false and
* may_start_working() true.
*
* LOCKING:
* spin_lock_irq(pool->lock) which may be released and regrabbed
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* multiple times. Does GFP_KERNEL allocations. Called only from
* manager.
*
* RETURNS:
* false if no action was taken and pool->lock stayed locked, true
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* otherwise.
*/
static bool maybe_create_worker(struct worker_pool *pool)
__releases(&pool->lock)
__acquires(&pool->lock)
{
if (!need_to_create_worker(pool))
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
return false;
restart:
spin_unlock_irq(&pool->lock);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/* if we don't make progress in MAYDAY_INITIAL_TIMEOUT, call for help */
mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
while (true) {
struct worker *worker;
2012-07-18 03:39:27 +08:00
worker = create_worker(pool);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
if (worker) {
del_timer_sync(&pool->mayday_timer);
spin_lock_irq(&pool->lock);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
start_worker(worker);
BUG_ON(need_to_create_worker(pool));
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
return true;
}
if (!need_to_create_worker(pool))
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
break;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
__set_current_state(TASK_INTERRUPTIBLE);
schedule_timeout(CREATE_COOLDOWN);
if (!need_to_create_worker(pool))
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
break;
}
del_timer_sync(&pool->mayday_timer);
spin_lock_irq(&pool->lock);
if (need_to_create_worker(pool))
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
goto restart;
return true;
}
/**
* maybe_destroy_worker - destroy workers which have been idle for a while
* @pool: pool to destroy workers for
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
*
* Destroy @pool workers which have been idle for longer than
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* IDLE_WORKER_TIMEOUT.
*
* LOCKING:
* spin_lock_irq(pool->lock) which may be released and regrabbed
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* multiple times. Called only from manager.
*
* RETURNS:
* false if no action was taken and pool->lock stayed locked, true
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* otherwise.
*/
static bool maybe_destroy_workers(struct worker_pool *pool)
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
{
bool ret = false;
while (too_many_workers(pool)) {
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
struct worker *worker;
unsigned long expires;
worker = list_entry(pool->idle_list.prev, struct worker, entry);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
expires = worker->last_active + IDLE_WORKER_TIMEOUT;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
if (time_before(jiffies, expires)) {
mod_timer(&pool->idle_timer, expires);
break;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
}
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
destroy_worker(worker);
ret = true;
}
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
return ret;
}
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
/**
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* manage_workers - manage worker pool
* @worker: self
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
*
* Assume the manager role and manage the worker pool @worker belongs
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* to. At any given time, there can be only zero or one manager per
* pool. The exclusion is handled automatically by this function.
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
*
* The caller can safely start processing works on false return. On
* true return, it's guaranteed that need_to_create_worker() is false
* and may_start_working() is true.
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
*
* CONTEXT:
* spin_lock_irq(pool->lock) which may be released and regrabbed
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* multiple times. Does GFP_KERNEL allocations.
*
* RETURNS:
* spin_lock_irq(pool->lock) which may be released and regrabbed
* multiple times. Does GFP_KERNEL allocations.
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
*/
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
static bool manage_workers(struct worker *worker)
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
{
struct worker_pool *pool = worker->pool;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
bool ret = false;
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
workqueue: fix possible idle worker depletion across CPU hotplug To simplify both normal and CPU hotplug paths, worker management is prevented while CPU hoplug is in progress. This is achieved by CPU hotplug holding the same exclusion mechanism used by workers to ensure there's only one manager per pool. If someone else seems to be performing the manager role, workers proceed to execute work items. CPU hotplug using the same mechanism can lead to idle worker depletion because all workers could proceed to execute work items while CPU hotplug is in progress and CPU hotplug itself wouldn't actually perform the worker management duty - it doesn't guarantee that there's an idle worker left when it releases management. This idle worker depletion, under extreme circumstances, can break forward-progress guarantee and thus lead to deadlock. This patch fixes the bug by using separate mechanisms for manager exclusion among workers and hotplug exclusion. For manager exclusion, POOL_MANAGING_WORKERS which was restored by the previous patch is used. pool->manager_mutex is now only used for exclusion between the elected manager and CPU hotplug. The elected manager won't proceed without holding pool->manager_mutex. This ensures that the worker which won the manager position can't skip managing while CPU hotplug is in progress. It will block on manager_mutex and perform management after CPU hotplug is complete. Note that hotplug may happen while waiting for manager_mutex. A manager isn't either on idle or busy list and thus the hoplug code can't unbind/rebind it. Make the manager handle its own un/rebinding. tj: Updated comment and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2012-09-11 01:03:44 +08:00
if (pool->flags & POOL_MANAGING_WORKERS)
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
return ret;
pool->flags |= POOL_MANAGING_WORKERS;
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
workqueue: fix possible idle worker depletion across CPU hotplug To simplify both normal and CPU hotplug paths, worker management is prevented while CPU hoplug is in progress. This is achieved by CPU hotplug holding the same exclusion mechanism used by workers to ensure there's only one manager per pool. If someone else seems to be performing the manager role, workers proceed to execute work items. CPU hotplug using the same mechanism can lead to idle worker depletion because all workers could proceed to execute work items while CPU hotplug is in progress and CPU hotplug itself wouldn't actually perform the worker management duty - it doesn't guarantee that there's an idle worker left when it releases management. This idle worker depletion, under extreme circumstances, can break forward-progress guarantee and thus lead to deadlock. This patch fixes the bug by using separate mechanisms for manager exclusion among workers and hotplug exclusion. For manager exclusion, POOL_MANAGING_WORKERS which was restored by the previous patch is used. pool->manager_mutex is now only used for exclusion between the elected manager and CPU hotplug. The elected manager won't proceed without holding pool->manager_mutex. This ensures that the worker which won the manager position can't skip managing while CPU hotplug is in progress. It will block on manager_mutex and perform management after CPU hotplug is complete. Note that hotplug may happen while waiting for manager_mutex. A manager isn't either on idle or busy list and thus the hoplug code can't unbind/rebind it. Make the manager handle its own un/rebinding. tj: Updated comment and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2012-09-11 01:03:44 +08:00
/*
* To simplify both worker management and CPU hotplug, hold off
* management while hotplug is in progress. CPU hotplug path can't
* grab %POOL_MANAGING_WORKERS to achieve this because that can
* lead to idle worker depletion (all become busy thinking someone
* else is managing) which in turn can result in deadlock under
* extreme circumstances. Use @pool->assoc_mutex to synchronize
workqueue: fix possible idle worker depletion across CPU hotplug To simplify both normal and CPU hotplug paths, worker management is prevented while CPU hoplug is in progress. This is achieved by CPU hotplug holding the same exclusion mechanism used by workers to ensure there's only one manager per pool. If someone else seems to be performing the manager role, workers proceed to execute work items. CPU hotplug using the same mechanism can lead to idle worker depletion because all workers could proceed to execute work items while CPU hotplug is in progress and CPU hotplug itself wouldn't actually perform the worker management duty - it doesn't guarantee that there's an idle worker left when it releases management. This idle worker depletion, under extreme circumstances, can break forward-progress guarantee and thus lead to deadlock. This patch fixes the bug by using separate mechanisms for manager exclusion among workers and hotplug exclusion. For manager exclusion, POOL_MANAGING_WORKERS which was restored by the previous patch is used. pool->manager_mutex is now only used for exclusion between the elected manager and CPU hotplug. The elected manager won't proceed without holding pool->manager_mutex. This ensures that the worker which won the manager position can't skip managing while CPU hotplug is in progress. It will block on manager_mutex and perform management after CPU hotplug is complete. Note that hotplug may happen while waiting for manager_mutex. A manager isn't either on idle or busy list and thus the hoplug code can't unbind/rebind it. Make the manager handle its own un/rebinding. tj: Updated comment and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2012-09-11 01:03:44 +08:00
* manager against CPU hotplug.
*
* assoc_mutex would always be free unless CPU hotplug is in
* progress. trylock first without dropping @pool->lock.
workqueue: fix possible idle worker depletion across CPU hotplug To simplify both normal and CPU hotplug paths, worker management is prevented while CPU hoplug is in progress. This is achieved by CPU hotplug holding the same exclusion mechanism used by workers to ensure there's only one manager per pool. If someone else seems to be performing the manager role, workers proceed to execute work items. CPU hotplug using the same mechanism can lead to idle worker depletion because all workers could proceed to execute work items while CPU hotplug is in progress and CPU hotplug itself wouldn't actually perform the worker management duty - it doesn't guarantee that there's an idle worker left when it releases management. This idle worker depletion, under extreme circumstances, can break forward-progress guarantee and thus lead to deadlock. This patch fixes the bug by using separate mechanisms for manager exclusion among workers and hotplug exclusion. For manager exclusion, POOL_MANAGING_WORKERS which was restored by the previous patch is used. pool->manager_mutex is now only used for exclusion between the elected manager and CPU hotplug. The elected manager won't proceed without holding pool->manager_mutex. This ensures that the worker which won the manager position can't skip managing while CPU hotplug is in progress. It will block on manager_mutex and perform management after CPU hotplug is complete. Note that hotplug may happen while waiting for manager_mutex. A manager isn't either on idle or busy list and thus the hoplug code can't unbind/rebind it. Make the manager handle its own un/rebinding. tj: Updated comment and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2012-09-11 01:03:44 +08:00
*/
if (unlikely(!mutex_trylock(&pool->assoc_mutex))) {
spin_unlock_irq(&pool->lock);
mutex_lock(&pool->assoc_mutex);
workqueue: fix possible idle worker depletion across CPU hotplug To simplify both normal and CPU hotplug paths, worker management is prevented while CPU hoplug is in progress. This is achieved by CPU hotplug holding the same exclusion mechanism used by workers to ensure there's only one manager per pool. If someone else seems to be performing the manager role, workers proceed to execute work items. CPU hotplug using the same mechanism can lead to idle worker depletion because all workers could proceed to execute work items while CPU hotplug is in progress and CPU hotplug itself wouldn't actually perform the worker management duty - it doesn't guarantee that there's an idle worker left when it releases management. This idle worker depletion, under extreme circumstances, can break forward-progress guarantee and thus lead to deadlock. This patch fixes the bug by using separate mechanisms for manager exclusion among workers and hotplug exclusion. For manager exclusion, POOL_MANAGING_WORKERS which was restored by the previous patch is used. pool->manager_mutex is now only used for exclusion between the elected manager and CPU hotplug. The elected manager won't proceed without holding pool->manager_mutex. This ensures that the worker which won the manager position can't skip managing while CPU hotplug is in progress. It will block on manager_mutex and perform management after CPU hotplug is complete. Note that hotplug may happen while waiting for manager_mutex. A manager isn't either on idle or busy list and thus the hoplug code can't unbind/rebind it. Make the manager handle its own un/rebinding. tj: Updated comment and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2012-09-11 01:03:44 +08:00
/*
* CPU hotplug could have happened while we were waiting
* for assoc_mutex. Hotplug itself can't handle us
workqueue: fix possible idle worker depletion across CPU hotplug To simplify both normal and CPU hotplug paths, worker management is prevented while CPU hoplug is in progress. This is achieved by CPU hotplug holding the same exclusion mechanism used by workers to ensure there's only one manager per pool. If someone else seems to be performing the manager role, workers proceed to execute work items. CPU hotplug using the same mechanism can lead to idle worker depletion because all workers could proceed to execute work items while CPU hotplug is in progress and CPU hotplug itself wouldn't actually perform the worker management duty - it doesn't guarantee that there's an idle worker left when it releases management. This idle worker depletion, under extreme circumstances, can break forward-progress guarantee and thus lead to deadlock. This patch fixes the bug by using separate mechanisms for manager exclusion among workers and hotplug exclusion. For manager exclusion, POOL_MANAGING_WORKERS which was restored by the previous patch is used. pool->manager_mutex is now only used for exclusion between the elected manager and CPU hotplug. The elected manager won't proceed without holding pool->manager_mutex. This ensures that the worker which won the manager position can't skip managing while CPU hotplug is in progress. It will block on manager_mutex and perform management after CPU hotplug is complete. Note that hotplug may happen while waiting for manager_mutex. A manager isn't either on idle or busy list and thus the hoplug code can't unbind/rebind it. Make the manager handle its own un/rebinding. tj: Updated comment and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2012-09-11 01:03:44 +08:00
* because manager isn't either on idle or busy list, and
* @pool's state and ours could have deviated.
workqueue: fix possible idle worker depletion across CPU hotplug To simplify both normal and CPU hotplug paths, worker management is prevented while CPU hoplug is in progress. This is achieved by CPU hotplug holding the same exclusion mechanism used by workers to ensure there's only one manager per pool. If someone else seems to be performing the manager role, workers proceed to execute work items. CPU hotplug using the same mechanism can lead to idle worker depletion because all workers could proceed to execute work items while CPU hotplug is in progress and CPU hotplug itself wouldn't actually perform the worker management duty - it doesn't guarantee that there's an idle worker left when it releases management. This idle worker depletion, under extreme circumstances, can break forward-progress guarantee and thus lead to deadlock. This patch fixes the bug by using separate mechanisms for manager exclusion among workers and hotplug exclusion. For manager exclusion, POOL_MANAGING_WORKERS which was restored by the previous patch is used. pool->manager_mutex is now only used for exclusion between the elected manager and CPU hotplug. The elected manager won't proceed without holding pool->manager_mutex. This ensures that the worker which won the manager position can't skip managing while CPU hotplug is in progress. It will block on manager_mutex and perform management after CPU hotplug is complete. Note that hotplug may happen while waiting for manager_mutex. A manager isn't either on idle or busy list and thus the hoplug code can't unbind/rebind it. Make the manager handle its own un/rebinding. tj: Updated comment and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2012-09-11 01:03:44 +08:00
*
* As hotplug is now excluded via assoc_mutex, we can
workqueue: fix possible idle worker depletion across CPU hotplug To simplify both normal and CPU hotplug paths, worker management is prevented while CPU hoplug is in progress. This is achieved by CPU hotplug holding the same exclusion mechanism used by workers to ensure there's only one manager per pool. If someone else seems to be performing the manager role, workers proceed to execute work items. CPU hotplug using the same mechanism can lead to idle worker depletion because all workers could proceed to execute work items while CPU hotplug is in progress and CPU hotplug itself wouldn't actually perform the worker management duty - it doesn't guarantee that there's an idle worker left when it releases management. This idle worker depletion, under extreme circumstances, can break forward-progress guarantee and thus lead to deadlock. This patch fixes the bug by using separate mechanisms for manager exclusion among workers and hotplug exclusion. For manager exclusion, POOL_MANAGING_WORKERS which was restored by the previous patch is used. pool->manager_mutex is now only used for exclusion between the elected manager and CPU hotplug. The elected manager won't proceed without holding pool->manager_mutex. This ensures that the worker which won the manager position can't skip managing while CPU hotplug is in progress. It will block on manager_mutex and perform management after CPU hotplug is complete. Note that hotplug may happen while waiting for manager_mutex. A manager isn't either on idle or busy list and thus the hoplug code can't unbind/rebind it. Make the manager handle its own un/rebinding. tj: Updated comment and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2012-09-11 01:03:44 +08:00
* simply try to bind. It will succeed or fail depending
* on @pool's current state. Try it and adjust
workqueue: fix possible idle worker depletion across CPU hotplug To simplify both normal and CPU hotplug paths, worker management is prevented while CPU hoplug is in progress. This is achieved by CPU hotplug holding the same exclusion mechanism used by workers to ensure there's only one manager per pool. If someone else seems to be performing the manager role, workers proceed to execute work items. CPU hotplug using the same mechanism can lead to idle worker depletion because all workers could proceed to execute work items while CPU hotplug is in progress and CPU hotplug itself wouldn't actually perform the worker management duty - it doesn't guarantee that there's an idle worker left when it releases management. This idle worker depletion, under extreme circumstances, can break forward-progress guarantee and thus lead to deadlock. This patch fixes the bug by using separate mechanisms for manager exclusion among workers and hotplug exclusion. For manager exclusion, POOL_MANAGING_WORKERS which was restored by the previous patch is used. pool->manager_mutex is now only used for exclusion between the elected manager and CPU hotplug. The elected manager won't proceed without holding pool->manager_mutex. This ensures that the worker which won the manager position can't skip managing while CPU hotplug is in progress. It will block on manager_mutex and perform management after CPU hotplug is complete. Note that hotplug may happen while waiting for manager_mutex. A manager isn't either on idle or busy list and thus the hoplug code can't unbind/rebind it. Make the manager handle its own un/rebinding. tj: Updated comment and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2012-09-11 01:03:44 +08:00
* %WORKER_UNBOUND accordingly.
*/
if (worker_maybe_bind_and_lock(worker))
worker->flags &= ~WORKER_UNBOUND;
else
worker->flags |= WORKER_UNBOUND;
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
workqueue: fix possible idle worker depletion across CPU hotplug To simplify both normal and CPU hotplug paths, worker management is prevented while CPU hoplug is in progress. This is achieved by CPU hotplug holding the same exclusion mechanism used by workers to ensure there's only one manager per pool. If someone else seems to be performing the manager role, workers proceed to execute work items. CPU hotplug using the same mechanism can lead to idle worker depletion because all workers could proceed to execute work items while CPU hotplug is in progress and CPU hotplug itself wouldn't actually perform the worker management duty - it doesn't guarantee that there's an idle worker left when it releases management. This idle worker depletion, under extreme circumstances, can break forward-progress guarantee and thus lead to deadlock. This patch fixes the bug by using separate mechanisms for manager exclusion among workers and hotplug exclusion. For manager exclusion, POOL_MANAGING_WORKERS which was restored by the previous patch is used. pool->manager_mutex is now only used for exclusion between the elected manager and CPU hotplug. The elected manager won't proceed without holding pool->manager_mutex. This ensures that the worker which won the manager position can't skip managing while CPU hotplug is in progress. It will block on manager_mutex and perform management after CPU hotplug is complete. Note that hotplug may happen while waiting for manager_mutex. A manager isn't either on idle or busy list and thus the hoplug code can't unbind/rebind it. Make the manager handle its own un/rebinding. tj: Updated comment and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2012-09-11 01:03:44 +08:00
ret = true;
}
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
pool->flags &= ~POOL_MANAGE_WORKERS;
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
/*
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* Destroy and then create so that may_start_working() is true
* on return.
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
*/
ret |= maybe_destroy_workers(pool);
ret |= maybe_create_worker(pool);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
pool->flags &= ~POOL_MANAGING_WORKERS;
mutex_unlock(&pool->assoc_mutex);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
return ret;
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
}
/**
* process_one_work - process single work
* @worker: self
* @work: work to process
*
* Process @work. This function contains all the logics necessary to
* process a single work including synchronization against and
* interaction with other workers on the same cpu, queueing and
* flushing. As long as context requirement is met, any worker can
* call this function to process a work.
*
* CONTEXT:
* spin_lock_irq(pool->lock) which is released and regrabbed.
*/
static void process_one_work(struct worker *worker, struct work_struct *work)
__releases(&pool->lock)
__acquires(&pool->lock)
{
struct pool_workqueue *pwq = get_work_pwq(work);
struct worker_pool *pool = worker->pool;
bool cpu_intensive = pwq->wq->flags & WQ_CPU_INTENSIVE;
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
int work_color;
workqueue: use shared worklist and pool all workers per cpu Use gcwq->worklist instead of cwq->worklist and break the strict association between a cwq and its worker. All works queued on a cpu are queued on gcwq->worklist and processed by any available worker on the gcwq. As there no longer is strict association between a cwq and its worker, whether a work is executing can now only be determined by calling [__]find_worker_executing_work(). After this change, the only association between a cwq and its worker is that a cwq puts a worker into shared worker pool on creation and kills it on destruction. As all workqueues are still limited to max_active of one, this means that there are always at least as many workers as active works and thus there's no danger for deadlock. The break of strong association between cwqs and workers requires somewhat clumsy changes to current_is_keventd() and destroy_workqueue(). Dynamic worker pool management will remove both clumsy changes. current_is_keventd() won't be necessary at all as the only reason it exists is to avoid queueing a work from a work which will be allowed just fine. The clumsy part of destroy_workqueue() is added because a worker can only be destroyed while idle and there's no guarantee a worker is idle when its wq is going down. With dynamic pool management, workers are not associated with workqueues at all and only idle ones will be submitted to destroy_workqueue() so the code won't be necessary anymore. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:13 +08:00
struct worker *collision;
#ifdef CONFIG_LOCKDEP
/*
* It is permissible to free the struct work_struct from
* inside the function that is called from it, this we need to
* take into account for lockdep too. To avoid bogus "held
* lock freed" warnings as well as problems when looking into
* work->lockdep_map, make a copy and use that here.
*/
lockdep: fix oops in processing workqueue Under memory load, on x86_64, with lockdep enabled, the workqueue's process_one_work() has been seen to oops in __lock_acquire(), barfing on a 0xffffffff00000000 pointer in the lockdep_map's class_cache[]. Because it's permissible to free a work_struct from its callout function, the map used is an onstack copy of the map given in the work_struct: and that copy is made without any locking. Surprisingly, gcc (4.5.1 in Hugh's case) uses "rep movsl" rather than "rep movsq" for that structure copy: which might race with a workqueue user's wait_on_work() doing lock_map_acquire() on the source of the copy, putting a pointer into the class_cache[], but only in time for the top half of that pointer to be copied to the destination map. Boom when process_one_work() subsequently does lock_map_acquire() on its onstack copy of the lockdep_map. Fix this, and a similar instance in call_timer_fn(), with a lockdep_copy_map() function which additionally NULLs the class_cache[]. Note: this oops was actually seen on 3.4-next, where flush_work() newly does the racing lock_map_acquire(); but Tejun points out that 3.4 and earlier are already vulnerable to the same through wait_on_work(). * Patch orginally from Peter. Hugh modified it a bit and wrote the description. Signed-off-by: Peter Zijlstra <peterz@infradead.org> Reported-by: Hugh Dickins <hughd@google.com> LKML-Reference: <alpine.LSU.2.00.1205070951170.1544@eggly.anvils> Signed-off-by: Tejun Heo <tj@kernel.org>
2012-05-15 23:06:19 +08:00
struct lockdep_map lockdep_map;
lockdep_copy_map(&lockdep_map, &work->lockdep_map);
#endif
/*
* Ensure we're on the correct CPU. DISASSOCIATED test is
* necessary to avoid spurious warnings from rescuers servicing the
* unbound or a disassociated pool.
*/
WARN_ON_ONCE(!(worker->flags & WORKER_UNBOUND) &&
!(pool->flags & POOL_DISASSOCIATED) &&
raw_smp_processor_id() != pool->cpu);
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
workqueue: use shared worklist and pool all workers per cpu Use gcwq->worklist instead of cwq->worklist and break the strict association between a cwq and its worker. All works queued on a cpu are queued on gcwq->worklist and processed by any available worker on the gcwq. As there no longer is strict association between a cwq and its worker, whether a work is executing can now only be determined by calling [__]find_worker_executing_work(). After this change, the only association between a cwq and its worker is that a cwq puts a worker into shared worker pool on creation and kills it on destruction. As all workqueues are still limited to max_active of one, this means that there are always at least as many workers as active works and thus there's no danger for deadlock. The break of strong association between cwqs and workers requires somewhat clumsy changes to current_is_keventd() and destroy_workqueue(). Dynamic worker pool management will remove both clumsy changes. current_is_keventd() won't be necessary at all as the only reason it exists is to avoid queueing a work from a work which will be allowed just fine. The clumsy part of destroy_workqueue() is added because a worker can only be destroyed while idle and there's no guarantee a worker is idle when its wq is going down. With dynamic pool management, workers are not associated with workqueues at all and only idle ones will be submitted to destroy_workqueue() so the code won't be necessary anymore. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:13 +08:00
/*
* A single work shouldn't be executed concurrently by
* multiple workers on a single cpu. Check whether anyone is
* already processing the work. If so, defer the work to the
* currently executing one.
*/
collision = find_worker_executing_work(pool, work);
workqueue: use shared worklist and pool all workers per cpu Use gcwq->worklist instead of cwq->worklist and break the strict association between a cwq and its worker. All works queued on a cpu are queued on gcwq->worklist and processed by any available worker on the gcwq. As there no longer is strict association between a cwq and its worker, whether a work is executing can now only be determined by calling [__]find_worker_executing_work(). After this change, the only association between a cwq and its worker is that a cwq puts a worker into shared worker pool on creation and kills it on destruction. As all workqueues are still limited to max_active of one, this means that there are always at least as many workers as active works and thus there's no danger for deadlock. The break of strong association between cwqs and workers requires somewhat clumsy changes to current_is_keventd() and destroy_workqueue(). Dynamic worker pool management will remove both clumsy changes. current_is_keventd() won't be necessary at all as the only reason it exists is to avoid queueing a work from a work which will be allowed just fine. The clumsy part of destroy_workqueue() is added because a worker can only be destroyed while idle and there's no guarantee a worker is idle when its wq is going down. With dynamic pool management, workers are not associated with workqueues at all and only idle ones will be submitted to destroy_workqueue() so the code won't be necessary anymore. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:13 +08:00
if (unlikely(collision)) {
move_linked_works(work, &collision->scheduled, NULL);
return;
}
workqueue: disable irq while manipulating PENDING Queueing operations use WORK_STRUCT_PENDING_BIT to synchronize access to the target work item. They first try to claim the bit and proceed with queueing only after that succeeds and there's a window between PENDING being set and the actual queueing where the task can be interrupted or preempted. There's also a similar window in process_one_work() when clearing PENDING. A work item is dequeued, gcwq->lock is released and then PENDING is cleared and the worker might get interrupted or preempted between releasing gcwq->lock and clearing PENDING. cancel[_delayed]_work_sync() tries to claim or steal PENDING. The function assumes that a work item with PENDING is either queued or in the process of being [de]queued. In the latter case, it busy-loops until either the work item loses PENDING or is queued. If canceling coincides with the above described interrupts or preemptions, the canceling task will busy-loop while the queueing or executing task is preempted. This patch keeps irq disabled across claiming PENDING and actual queueing and moves PENDING clearing in process_one_work() inside gcwq->lock so that busy looping from PENDING && !queued doesn't wait for interrupted/preempted tasks. Note that, in process_one_work(), setting last CPU and clearing PENDING got merged into single operation. This removes possible long busy-loops and will allow using try_to_grab_pending() from bh and irq contexts. v2: __queue_work() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Disable irq instead of preemption. IRQ will be disabled while grabbing gcwq->lock later anyway and this allows using try_to_grab_pending() from bh and irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:45 +08:00
/* claim and dequeue */
debug_work_deactivate(work);
hash_add(pool->busy_hash, &worker->hentry, (unsigned long)work);
worker->current_work = work;
workqueue: consider work function when searching for busy work items To avoid executing the same work item concurrenlty, workqueue hashes currently busy workers according to their current work items and looks up the the table when it wants to execute a new work item. If there already is a worker which is executing the new work item, the new item is queued to the found worker so that it gets executed only after the current execution finishes. Unfortunately, a work item may be freed while being executed and thus recycled for different purposes. If it gets recycled for a different work item and queued while the previous execution is still in progress, workqueue may make the new work item wait for the old one although the two aren't really related in any way. In extreme cases, this false dependency may lead to deadlock although it's extremely unlikely given that there aren't too many self-freeing work item users and they usually don't wait for other work items. To alleviate the problem, record the current work function in each busy worker and match it together with the work item address in find_worker_executing_work(). While this isn't complete, it ensures that unrelated work items don't interact with each other and in the very unlikely case where a twisted wq user triggers it, it's always onto itself making the culprit easy to spot. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Andrey Isakov <andy51@gmx.ru> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=51701 Cc: stable@vger.kernel.org
2012-12-19 02:35:02 +08:00
worker->current_func = work->func;
worker->current_pwq = pwq;
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
work_color = get_work_color(work);
list_del_init(&work->entry);
/*
* CPU intensive works don't participate in concurrency
* management. They're the scheduler's responsibility.
*/
if (unlikely(cpu_intensive))
worker_set_flags(worker, WORKER_CPU_INTENSIVE, true);
/*
* Unbound pool isn't concurrency managed and work items should be
* executed ASAP. Wake up another worker if necessary.
*/
if ((worker->flags & WORKER_UNBOUND) && need_more_worker(pool))
wake_up_worker(pool);
workqueue: disable irq while manipulating PENDING Queueing operations use WORK_STRUCT_PENDING_BIT to synchronize access to the target work item. They first try to claim the bit and proceed with queueing only after that succeeds and there's a window between PENDING being set and the actual queueing where the task can be interrupted or preempted. There's also a similar window in process_one_work() when clearing PENDING. A work item is dequeued, gcwq->lock is released and then PENDING is cleared and the worker might get interrupted or preempted between releasing gcwq->lock and clearing PENDING. cancel[_delayed]_work_sync() tries to claim or steal PENDING. The function assumes that a work item with PENDING is either queued or in the process of being [de]queued. In the latter case, it busy-loops until either the work item loses PENDING or is queued. If canceling coincides with the above described interrupts or preemptions, the canceling task will busy-loop while the queueing or executing task is preempted. This patch keeps irq disabled across claiming PENDING and actual queueing and moves PENDING clearing in process_one_work() inside gcwq->lock so that busy looping from PENDING && !queued doesn't wait for interrupted/preempted tasks. Note that, in process_one_work(), setting last CPU and clearing PENDING got merged into single operation. This removes possible long busy-loops and will allow using try_to_grab_pending() from bh and irq contexts. v2: __queue_work() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Disable irq instead of preemption. IRQ will be disabled while grabbing gcwq->lock later anyway and this allows using try_to_grab_pending() from bh and irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:45 +08:00
/*
* Record the last pool and clear PENDING which should be the last
* update to @work. Also, do this inside @pool->lock so that
* PENDING and queued state changes happen together while IRQ is
* disabled.
workqueue: disable irq while manipulating PENDING Queueing operations use WORK_STRUCT_PENDING_BIT to synchronize access to the target work item. They first try to claim the bit and proceed with queueing only after that succeeds and there's a window between PENDING being set and the actual queueing where the task can be interrupted or preempted. There's also a similar window in process_one_work() when clearing PENDING. A work item is dequeued, gcwq->lock is released and then PENDING is cleared and the worker might get interrupted or preempted between releasing gcwq->lock and clearing PENDING. cancel[_delayed]_work_sync() tries to claim or steal PENDING. The function assumes that a work item with PENDING is either queued or in the process of being [de]queued. In the latter case, it busy-loops until either the work item loses PENDING or is queued. If canceling coincides with the above described interrupts or preemptions, the canceling task will busy-loop while the queueing or executing task is preempted. This patch keeps irq disabled across claiming PENDING and actual queueing and moves PENDING clearing in process_one_work() inside gcwq->lock so that busy looping from PENDING && !queued doesn't wait for interrupted/preempted tasks. Note that, in process_one_work(), setting last CPU and clearing PENDING got merged into single operation. This removes possible long busy-loops and will allow using try_to_grab_pending() from bh and irq contexts. v2: __queue_work() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Disable irq instead of preemption. IRQ will be disabled while grabbing gcwq->lock later anyway and this allows using try_to_grab_pending() from bh and irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:45 +08:00
*/
set_work_pool_and_clear_pending(work, pool->id);
spin_unlock_irq(&pool->lock);
lock_map_acquire_read(&pwq->wq->lockdep_map);
lock_map_acquire(&lockdep_map);
trace_workqueue_execute_start(work);
workqueue: consider work function when searching for busy work items To avoid executing the same work item concurrenlty, workqueue hashes currently busy workers according to their current work items and looks up the the table when it wants to execute a new work item. If there already is a worker which is executing the new work item, the new item is queued to the found worker so that it gets executed only after the current execution finishes. Unfortunately, a work item may be freed while being executed and thus recycled for different purposes. If it gets recycled for a different work item and queued while the previous execution is still in progress, workqueue may make the new work item wait for the old one although the two aren't really related in any way. In extreme cases, this false dependency may lead to deadlock although it's extremely unlikely given that there aren't too many self-freeing work item users and they usually don't wait for other work items. To alleviate the problem, record the current work function in each busy worker and match it together with the work item address in find_worker_executing_work(). While this isn't complete, it ensures that unrelated work items don't interact with each other and in the very unlikely case where a twisted wq user triggers it, it's always onto itself making the culprit easy to spot. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Andrey Isakov <andy51@gmx.ru> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=51701 Cc: stable@vger.kernel.org
2012-12-19 02:35:02 +08:00
worker->current_func(work);
/*
* While we must be careful to not use "work" after this, the trace
* point will only record its address.
*/
trace_workqueue_execute_end(work);
lock_map_release(&lockdep_map);
lock_map_release(&pwq->wq->lockdep_map);
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",
workqueue: consider work function when searching for busy work items To avoid executing the same work item concurrenlty, workqueue hashes currently busy workers according to their current work items and looks up the the table when it wants to execute a new work item. If there already is a worker which is executing the new work item, the new item is queued to the found worker so that it gets executed only after the current execution finishes. Unfortunately, a work item may be freed while being executed and thus recycled for different purposes. If it gets recycled for a different work item and queued while the previous execution is still in progress, workqueue may make the new work item wait for the old one although the two aren't really related in any way. In extreme cases, this false dependency may lead to deadlock although it's extremely unlikely given that there aren't too many self-freeing work item users and they usually don't wait for other work items. To alleviate the problem, record the current work function in each busy worker and match it together with the work item address in find_worker_executing_work(). While this isn't complete, it ensures that unrelated work items don't interact with each other and in the very unlikely case where a twisted wq user triggers it, it's always onto itself making the culprit easy to spot. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Andrey Isakov <andy51@gmx.ru> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=51701 Cc: stable@vger.kernel.org
2012-12-19 02:35:02 +08:00
current->comm, preempt_count(), task_pid_nr(current),
worker->current_func);
debug_show_held_locks(current);
dump_stack();
}
spin_lock_irq(&pool->lock);
/* clear cpu intensive status */
if (unlikely(cpu_intensive))
worker_clr_flags(worker, WORKER_CPU_INTENSIVE);
/* we're done with it, release */
hash_del(&worker->hentry);
worker->current_work = NULL;
workqueue: consider work function when searching for busy work items To avoid executing the same work item concurrenlty, workqueue hashes currently busy workers according to their current work items and looks up the the table when it wants to execute a new work item. If there already is a worker which is executing the new work item, the new item is queued to the found worker so that it gets executed only after the current execution finishes. Unfortunately, a work item may be freed while being executed and thus recycled for different purposes. If it gets recycled for a different work item and queued while the previous execution is still in progress, workqueue may make the new work item wait for the old one although the two aren't really related in any way. In extreme cases, this false dependency may lead to deadlock although it's extremely unlikely given that there aren't too many self-freeing work item users and they usually don't wait for other work items. To alleviate the problem, record the current work function in each busy worker and match it together with the work item address in find_worker_executing_work(). While this isn't complete, it ensures that unrelated work items don't interact with each other and in the very unlikely case where a twisted wq user triggers it, it's always onto itself making the culprit easy to spot. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Andrey Isakov <andy51@gmx.ru> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=51701 Cc: stable@vger.kernel.org
2012-12-19 02:35:02 +08:00
worker->current_func = NULL;
worker->current_pwq = NULL;
pwq_dec_nr_in_flight(pwq, work_color);
}
/**
* process_scheduled_works - process scheduled works
* @worker: self
*
* Process all scheduled works. Please note that the scheduled list
* may change while processing a work, so this function repeatedly
* fetches a work from the top and executes it.
*
* CONTEXT:
* spin_lock_irq(pool->lock) which may be released and regrabbed
* multiple times.
*/
static void process_scheduled_works(struct worker *worker)
{
while (!list_empty(&worker->scheduled)) {
struct work_struct *work = list_first_entry(&worker->scheduled,
struct work_struct, entry);
process_one_work(worker, work);
}
}
/**
* worker_thread - the worker thread function
* @__worker: self
*
* The worker thread function. There are NR_CPU_WORKER_POOLS dynamic pools
* of these per each cpu. These workers process all works regardless of
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* their specific target workqueue. The only exception is works which
* belong to workqueues with a rescuer which will be explained in
* rescuer_thread().
*/
static int worker_thread(void *__worker)
{
struct worker *worker = __worker;
struct worker_pool *pool = worker->pool;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/* tell the scheduler that this is a workqueue worker */
worker->task->flags |= PF_WQ_WORKER;
woke_up:
spin_lock_irq(&pool->lock);
/* we are off idle list if destruction or rebind is requested */
if (unlikely(list_empty(&worker->entry))) {
spin_unlock_irq(&pool->lock);
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
/* if DIE is set, destruction is requested */
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
if (worker->flags & WORKER_DIE) {
worker->task->flags &= ~PF_WQ_WORKER;
return 0;
}
/* otherwise, rebind */
workqueue: reimplement CPU online rebinding to handle idle workers Currently, if there are left workers when a CPU is being brough back online, the trustee kills all idle workers and scheduled rebind_work so that they re-bind to the CPU after the currently executing work is finished. This works for busy workers because concurrency management doesn't try to wake up them from scheduler callbacks, which require the target task to be on the local run queue. The busy worker bumps concurrency counter appropriately as it clears WORKER_UNBOUND from the rebind work item and it's bound to the CPU before returning to the idle state. To reduce CPU on/offlining overhead (as many embedded systems use it for powersaving) and simplify the code path, workqueue is planned to be modified to retain idle workers across CPU on/offlining. This patch reimplements CPU online rebinding such that it can also handle idle workers. As noted earlier, due to the local wakeup requirement, rebinding idle workers is tricky. All idle workers must be re-bound before scheduler callbacks are enabled. This is achieved by interlocking idle re-binding. Idle workers are requested to re-bind and then hold until all idle re-binding is complete so that no bound worker starts executing work item. Only after all idle workers are re-bound and parked, CPU_ONLINE proceeds to release them and queue rebind work item to busy workers thus guaranteeing scheduler callbacks aren't invoked until all idle workers are ready. worker_rebind_fn() is renamed to busy_worker_rebind_fn() and idle_worker_rebind() for idle workers is added. Rebinding logic is moved to rebind_workers() and now called from CPU_ONLINE after flushing trustee. While at it, add CPU sanity check in worker_thread(). Note that now a worker may become idle or the manager between trustee release and rebinding during CPU_ONLINE. As the previous patch updated create_worker() so that it can be used by regular manager while unbound and this patch implements idle re-binding, this is safe. This prepares for removal of trustee and keeping idle workers across CPU hotplugs. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:27 +08:00
idle_worker_rebind(worker);
goto woke_up;
}
worker_leave_idle(worker);
recheck:
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/* no more worker necessary? */
if (!need_more_worker(pool))
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
goto sleep;
/* do we need to manage? */
if (unlikely(!may_start_working(pool)) && manage_workers(worker))
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
goto recheck;
/*
* ->scheduled list can only be filled while a worker is
* preparing to process a work or actually processing it.
* Make sure nobody diddled with it while I was sleeping.
*/
BUG_ON(!list_empty(&worker->scheduled));
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/*
* When control reaches this point, we're guaranteed to have
* at least one idle worker or that someone else has already
* assumed the manager role.
*/
worker_clr_flags(worker, WORKER_PREP);
do {
struct work_struct *work =
list_first_entry(&pool->worklist,
struct work_struct, entry);
if (likely(!(*work_data_bits(work) & WORK_STRUCT_LINKED))) {
/* optimization path, not strictly necessary */
process_one_work(worker, work);
if (unlikely(!list_empty(&worker->scheduled)))
process_scheduled_works(worker);
} else {
move_linked_works(work, &worker->scheduled, NULL);
process_scheduled_works(worker);
}
} while (keep_working(pool));
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
worker_set_flags(worker, WORKER_PREP, false);
sleep:
if (unlikely(need_to_manage_workers(pool)) && manage_workers(worker))
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
goto recheck;
/*
* pool->lock is held and there's no work to process and no need to
* manage, sleep. Workers are woken up only while holding
* pool->lock or from local cpu, so setting the current state
* before releasing pool->lock is enough to prevent losing any
* event.
*/
worker_enter_idle(worker);
__set_current_state(TASK_INTERRUPTIBLE);
spin_unlock_irq(&pool->lock);
schedule();
goto woke_up;
}
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/**
* rescuer_thread - the rescuer thread function
* @__rescuer: self
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
*
* Workqueue rescuer thread function. There's one rescuer for each
* workqueue which has WQ_RESCUER set.
*
* Regular work processing on a pool may block trying to create a new
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* worker which uses GFP_KERNEL allocation which has slight chance of
* developing into deadlock if some works currently on the same queue
* need to be processed to satisfy the GFP_KERNEL allocation. This is
* the problem rescuer solves.
*
* When such condition is possible, the pool summons rescuers of all
* workqueues which have works queued on the pool and let them process
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* those works so that forward progress can be guaranteed.
*
* This should happen rarely.
*/
static int rescuer_thread(void *__rescuer)
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
{
struct worker *rescuer = __rescuer;
struct workqueue_struct *wq = rescuer->rescue_wq;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
struct list_head *scheduled = &rescuer->scheduled;
bool is_unbound = wq->flags & WQ_UNBOUND;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
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;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
repeat:
set_current_state(TASK_INTERRUPTIBLE);
workqueue: exit rescuer_thread() as TASK_RUNNING A rescue thread exiting TASK_INTERRUPTIBLE can lead to a task scheduling off, never to be seen again. In the case where this occurred, an exiting thread hit reiserfs homebrew conditional resched while holding a mutex, bringing the box to its knees. PID: 18105 TASK: ffff8807fd412180 CPU: 5 COMMAND: "kdmflush" #0 [ffff8808157e7670] schedule at ffffffff8143f489 #1 [ffff8808157e77b8] reiserfs_get_block at ffffffffa038ab2d [reiserfs] #2 [ffff8808157e79a8] __block_write_begin at ffffffff8117fb14 #3 [ffff8808157e7a98] reiserfs_write_begin at ffffffffa0388695 [reiserfs] #4 [ffff8808157e7ad8] generic_perform_write at ffffffff810ee9e2 #5 [ffff8808157e7b58] generic_file_buffered_write at ffffffff810eeb41 #6 [ffff8808157e7ba8] __generic_file_aio_write at ffffffff810f1a3a #7 [ffff8808157e7c58] generic_file_aio_write at ffffffff810f1c88 #8 [ffff8808157e7cc8] do_sync_write at ffffffff8114f850 #9 [ffff8808157e7dd8] do_acct_process at ffffffff810a268f [exception RIP: kernel_thread_helper] RIP: ffffffff8144a5c0 RSP: ffff8808157e7f58 RFLAGS: 00000202 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff8107af60 RDI: ffff8803ee491d18 RBP: 0000000000000000 R8: 0000000000000000 R9: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 Signed-off-by: Mike Galbraith <mgalbraith@suse.de> Signed-off-by: Tejun Heo <tj@kernel.org> Cc: stable@vger.kernel.org
2012-11-28 14:17:18 +08:00
if (kthread_should_stop()) {
__set_current_state(TASK_RUNNING);
rescuer->task->flags &= ~PF_WQ_WORKER;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
return 0;
workqueue: exit rescuer_thread() as TASK_RUNNING A rescue thread exiting TASK_INTERRUPTIBLE can lead to a task scheduling off, never to be seen again. In the case where this occurred, an exiting thread hit reiserfs homebrew conditional resched while holding a mutex, bringing the box to its knees. PID: 18105 TASK: ffff8807fd412180 CPU: 5 COMMAND: "kdmflush" #0 [ffff8808157e7670] schedule at ffffffff8143f489 #1 [ffff8808157e77b8] reiserfs_get_block at ffffffffa038ab2d [reiserfs] #2 [ffff8808157e79a8] __block_write_begin at ffffffff8117fb14 #3 [ffff8808157e7a98] reiserfs_write_begin at ffffffffa0388695 [reiserfs] #4 [ffff8808157e7ad8] generic_perform_write at ffffffff810ee9e2 #5 [ffff8808157e7b58] generic_file_buffered_write at ffffffff810eeb41 #6 [ffff8808157e7ba8] __generic_file_aio_write at ffffffff810f1a3a #7 [ffff8808157e7c58] generic_file_aio_write at ffffffff810f1c88 #8 [ffff8808157e7cc8] do_sync_write at ffffffff8114f850 #9 [ffff8808157e7dd8] do_acct_process at ffffffff810a268f [exception RIP: kernel_thread_helper] RIP: ffffffff8144a5c0 RSP: ffff8808157e7f58 RFLAGS: 00000202 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff8107af60 RDI: ffff8803ee491d18 RBP: 0000000000000000 R8: 0000000000000000 R9: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 Signed-off-by: Mike Galbraith <mgalbraith@suse.de> Signed-off-by: Tejun Heo <tj@kernel.org> Cc: stable@vger.kernel.org
2012-11-28 14:17:18 +08:00
}
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/*
* See whether any cpu is asking for help. Unbounded
* workqueues use cpu 0 in mayday_mask for CPU_UNBOUND.
*/
for_each_mayday_cpu(cpu, wq->mayday_mask) {
unsigned int tcpu = is_unbound ? WORK_CPU_UNBOUND : cpu;
struct pool_workqueue *pwq = get_pwq(tcpu, wq);
struct worker_pool *pool = pwq->pool;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
struct work_struct *work, *n;
__set_current_state(TASK_RUNNING);
mayday_clear_cpu(cpu, wq->mayday_mask);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/* migrate to the target cpu if possible */
rescuer->pool = pool;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
worker_maybe_bind_and_lock(rescuer);
/*
* Slurp in all works issued via this workqueue and
* process'em.
*/
BUG_ON(!list_empty(&rescuer->scheduled));
list_for_each_entry_safe(work, n, &pool->worklist, entry)
if (get_work_pwq(work) == pwq)
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
move_linked_works(work, scheduled, &n);
process_scheduled_works(rescuer);
/*
* Leave this pool. If keep_working() is %true, notify a
* regular worker; otherwise, we end up with 0 concurrency
* and stalling the execution.
*/
if (keep_working(pool))
wake_up_worker(pool);
spin_unlock_irq(&pool->lock);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
}
/* rescuers should never participate in concurrency management */
WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING));
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
schedule();
goto repeat;
}
struct wq_barrier {
struct work_struct work;
struct completion done;
};
static void wq_barrier_func(struct work_struct *work)
{
struct wq_barrier *barr = container_of(work, struct wq_barrier, work);
complete(&barr->done);
}
/**
* insert_wq_barrier - insert a barrier work
* @pwq: pwq to insert barrier into
* @barr: wq_barrier to insert
* @target: target work to attach @barr to
* @worker: worker currently executing @target, NULL if @target is not executing
*
* @barr is linked to @target such that @barr is completed only after
* @target finishes execution. Please note that the ordering
* guarantee is observed only with respect to @target and on the local
* cpu.
*
* Currently, a queued barrier can't be canceled. This is because
* try_to_grab_pending() can't determine whether the work to be
* grabbed is at the head of the queue and thus can't clear LINKED
* flag of the previous work while there must be a valid next work
* after a work with LINKED flag set.
*
* Note that when @worker is non-NULL, @target may be modified
* underneath us, so we can't reliably determine pwq from @target.
*
* CONTEXT:
* spin_lock_irq(pool->lock).
*/
static void insert_wq_barrier(struct pool_workqueue *pwq,
struct wq_barrier *barr,
struct work_struct *target, struct worker *worker)
{
struct list_head *head;
unsigned int linked = 0;
/*
* debugobject calls are safe here even with pool->lock locked
* as we know for sure that this will not trigger any of the
* checks and call back into the fixup functions where we
* might deadlock.
*/
INIT_WORK_ONSTACK(&barr->work, wq_barrier_func);
__set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work));
init_completion(&barr->done);
/*
* If @target is currently being executed, schedule the
* barrier to the worker; otherwise, put it after @target.
*/
if (worker)
head = worker->scheduled.next;
else {
unsigned long *bits = work_data_bits(target);
head = target->entry.next;
/* there can already be other linked works, inherit and set */
linked = *bits & WORK_STRUCT_LINKED;
__set_bit(WORK_STRUCT_LINKED_BIT, bits);
}
debug_work_activate(&barr->work);
insert_work(pwq, &barr->work, head,
work_color_to_flags(WORK_NO_COLOR) | linked);
}
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
/**
* flush_workqueue_prep_pwqs - prepare pwqs for workqueue flushing
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
* @wq: workqueue being flushed
* @flush_color: new flush color, < 0 for no-op
* @work_color: new work color, < 0 for no-op
*
* Prepare pwqs for workqueue flushing.
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
*
* If @flush_color is non-negative, flush_color on all pwqs should be
* -1. If no pwq has in-flight commands at the specified color, all
* pwq->flush_color's stay at -1 and %false is returned. If any pwq
* has in flight commands, its pwq->flush_color is set to
* @flush_color, @wq->nr_pwqs_to_flush is updated accordingly, pwq
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
* wakeup logic is armed and %true is returned.
*
* The caller should have initialized @wq->first_flusher prior to
* calling this function with non-negative @flush_color. If
* @flush_color is negative, no flush color update is done and %false
* is returned.
*
* If @work_color is non-negative, all pwqs should have the same
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
* work_color which is previous to @work_color and all will be
* advanced to @work_color.
*
* CONTEXT:
* mutex_lock(wq->flush_mutex).
*
* RETURNS:
* %true if @flush_color >= 0 and there's something to flush. %false
* otherwise.
*/
static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq,
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
int flush_color, int work_color)
{
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
bool wait = false;
unsigned int cpu;
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
if (flush_color >= 0) {
BUG_ON(atomic_read(&wq->nr_pwqs_to_flush));
atomic_set(&wq->nr_pwqs_to_flush, 1);
}
for_each_pwq_cpu(cpu, wq) {
struct pool_workqueue *pwq = get_pwq(cpu, wq);
struct worker_pool *pool = pwq->pool;
spin_lock_irq(&pool->lock);
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
if (flush_color >= 0) {
BUG_ON(pwq->flush_color != -1);
if (pwq->nr_in_flight[flush_color]) {
pwq->flush_color = flush_color;
atomic_inc(&wq->nr_pwqs_to_flush);
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
wait = true;
}
}
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
if (work_color >= 0) {
BUG_ON(work_color != work_next_color(pwq->work_color));
pwq->work_color = work_color;
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
}
spin_unlock_irq(&pool->lock);
}
if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_pwqs_to_flush))
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
complete(&wq->first_flusher->done);
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
return wait;
}
/**
* flush_workqueue - ensure that any scheduled work has run to completion.
* @wq: workqueue to flush
*
* Forces execution of the workqueue and blocks until its completion.
* This is typically used in driver shutdown handlers.
*
* We sleep until all works which were queued on entry have been handled,
* but we are not livelocked by new incoming ones.
*/
void flush_workqueue(struct workqueue_struct *wq)
{
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
struct wq_flusher this_flusher = {
.list = LIST_HEAD_INIT(this_flusher.list),
.flush_color = -1,
.done = COMPLETION_INITIALIZER_ONSTACK(this_flusher.done),
};
int next_color;
lock_map_acquire(&wq->lockdep_map);
lock_map_release(&wq->lockdep_map);
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
mutex_lock(&wq->flush_mutex);
/*
* Start-to-wait phase
*/
next_color = work_next_color(wq->work_color);
if (next_color != wq->flush_color) {
/*
* Color space is not full. The current work_color
* becomes our flush_color and work_color is advanced
* by one.
*/
BUG_ON(!list_empty(&wq->flusher_overflow));
this_flusher.flush_color = wq->work_color;
wq->work_color = next_color;
if (!wq->first_flusher) {
/* no flush in progress, become the first flusher */
BUG_ON(wq->flush_color != this_flusher.flush_color);
wq->first_flusher = &this_flusher;
if (!flush_workqueue_prep_pwqs(wq, wq->flush_color,
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
wq->work_color)) {
/* nothing to flush, done */
wq->flush_color = next_color;
wq->first_flusher = NULL;
goto out_unlock;
}
} else {
/* wait in queue */
BUG_ON(wq->flush_color == this_flusher.flush_color);
list_add_tail(&this_flusher.list, &wq->flusher_queue);
flush_workqueue_prep_pwqs(wq, -1, wq->work_color);
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
}
} else {
/*
* Oops, color space is full, wait on overflow queue.
* The next flush completion will assign us
* flush_color and transfer to flusher_queue.
*/
list_add_tail(&this_flusher.list, &wq->flusher_overflow);
}
mutex_unlock(&wq->flush_mutex);
wait_for_completion(&this_flusher.done);
/*
* Wake-up-and-cascade phase
*
* First flushers are responsible for cascading flushes and
* handling overflow. Non-first flushers can simply return.
*/
if (wq->first_flusher != &this_flusher)
return;
mutex_lock(&wq->flush_mutex);
/* we might have raced, check again with mutex held */
if (wq->first_flusher != &this_flusher)
goto out_unlock;
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
wq->first_flusher = NULL;
BUG_ON(!list_empty(&this_flusher.list));
BUG_ON(wq->flush_color != this_flusher.flush_color);
while (true) {
struct wq_flusher *next, *tmp;
/* complete all the flushers sharing the current flush color */
list_for_each_entry_safe(next, tmp, &wq->flusher_queue, list) {
if (next->flush_color != wq->flush_color)
break;
list_del_init(&next->list);
complete(&next->done);
}
BUG_ON(!list_empty(&wq->flusher_overflow) &&
wq->flush_color != work_next_color(wq->work_color));
/* this flush_color is finished, advance by one */
wq->flush_color = work_next_color(wq->flush_color);
/* one color has been freed, handle overflow queue */
if (!list_empty(&wq->flusher_overflow)) {
/*
* Assign the same color to all overflowed
* flushers, advance work_color and append to
* flusher_queue. This is the start-to-wait
* phase for these overflowed flushers.
*/
list_for_each_entry(tmp, &wq->flusher_overflow, list)
tmp->flush_color = wq->work_color;
wq->work_color = work_next_color(wq->work_color);
list_splice_tail_init(&wq->flusher_overflow,
&wq->flusher_queue);
flush_workqueue_prep_pwqs(wq, -1, wq->work_color);
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
}
if (list_empty(&wq->flusher_queue)) {
BUG_ON(wq->flush_color != wq->work_color);
break;
}
/*
* Need to flush more colors. Make the next flusher
* the new first flusher and arm pwqs.
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
*/
BUG_ON(wq->flush_color == wq->work_color);
BUG_ON(wq->flush_color != next->flush_color);
list_del_init(&next->list);
wq->first_flusher = next;
if (flush_workqueue_prep_pwqs(wq, wq->flush_color, -1))
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
break;
/*
* Meh... this color is already done, clear first
* flusher and repeat cascading.
*/
wq->first_flusher = NULL;
}
out_unlock:
mutex_unlock(&wq->flush_mutex);
}
EXPORT_SYMBOL_GPL(flush_workqueue);
/**
* drain_workqueue - drain a workqueue
* @wq: workqueue to drain
*
* Wait until the workqueue becomes empty. While draining is in progress,
* only chain queueing is allowed. IOW, only currently pending or running
* work items on @wq can queue further work items on it. @wq is flushed
* repeatedly until it becomes empty. The number of flushing is detemined
* by the depth of chaining and should be relatively short. Whine if it
* takes too long.
*/
void drain_workqueue(struct workqueue_struct *wq)
{
unsigned int flush_cnt = 0;
unsigned int cpu;
/*
* __queue_work() needs to test whether there are drainers, is much
* hotter than drain_workqueue() and already looks at @wq->flags.
* Use WQ_DRAINING so that queue doesn't have to check nr_drainers.
*/
spin_lock(&workqueue_lock);
if (!wq->nr_drainers++)
wq->flags |= WQ_DRAINING;
spin_unlock(&workqueue_lock);
reflush:
flush_workqueue(wq);
for_each_pwq_cpu(cpu, wq) {
struct pool_workqueue *pwq = get_pwq(cpu, wq);
bool drained;
spin_lock_irq(&pwq->pool->lock);
drained = !pwq->nr_active && list_empty(&pwq->delayed_works);
spin_unlock_irq(&pwq->pool->lock);
if (drained)
continue;
if (++flush_cnt == 10 ||
(flush_cnt % 100 == 0 && flush_cnt <= 1000))
pr_warn("workqueue %s: flush on destruction isn't complete after %u tries\n",
wq->name, flush_cnt);
goto reflush;
}
spin_lock(&workqueue_lock);
if (!--wq->nr_drainers)
wq->flags &= ~WQ_DRAINING;
spin_unlock(&workqueue_lock);
}
EXPORT_SYMBOL_GPL(drain_workqueue);
static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr)
{
struct worker *worker = NULL;
struct worker_pool *pool;
struct pool_workqueue *pwq;
might_sleep();
pool = get_work_pool(work);
if (!pool)
return false;
spin_lock_irq(&pool->lock);
workqueue: simplify is-work-item-queued-here test Currently, determining whether a work item is queued on a locked pool involves somewhat convoluted memory barrier dancing. It goes like the following. * When a work item is queued on a pool, work->data is updated before work->entry is linked to the pending list with a wmb() inbetween. * When trying to determine whether a work item is currently queued on a pool pointed to by work->data, it locks the pool and looks at work->entry. If work->entry is linked, we then do rmb() and then check whether work->data points to the current pool. This works because, work->data can only point to a pool if it currently is or were on the pool and, * If it currently is on the pool, the tests would obviously succeed. * It it left the pool, its work->entry was cleared under pool->lock, so if we're seeing non-empty work->entry, it has to be from the work item being linked on another pool. Because work->data is updated before work->entry is linked with wmb() inbetween, work->data update from another pool is guaranteed to be visible if we do rmb() after seeing non-empty work->entry. So, we either see empty work->entry or we see updated work->data pointin to another pool. While this works, it's convoluted, to put it mildly. With recent updates, it's now guaranteed that work->data points to cwq only while the work item is queued and that updating work->data to point to cwq or back to pool is done under pool->lock, so we can simply test whether work->data points to cwq which is associated with the currently locked pool instead of the convoluted memory barrier dancing. This patch replaces the memory barrier based "are you still here, really?" test with much simpler "does work->data points to me?" test - if work->data points to a cwq which is associated with the currently locked pool, the work item is guaranteed to be queued on the pool as work->data can start and stop pointing to such cwq only under pool->lock and the start and stop coincide with queue and dequeue. tj: Rewrote the comments and description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2013-02-07 10:04:53 +08:00
/* see the comment in try_to_grab_pending() with the same code */
pwq = get_work_pwq(work);
if (pwq) {
if (unlikely(pwq->pool != pool))
goto already_gone;
} else {
worker = find_worker_executing_work(pool, work);
if (!worker)
goto already_gone;
pwq = worker->current_pwq;
}
insert_wq_barrier(pwq, barr, work, worker);
spin_unlock_irq(&pool->lock);
/*
* If @max_active is 1 or rescuer is in use, flushing another work
* item on the same workqueue may lead to deadlock. Make sure the
* flusher is not running on the same workqueue by verifying write
* access.
*/
if (pwq->wq->saved_max_active == 1 || pwq->wq->flags & WQ_RESCUER)
lock_map_acquire(&pwq->wq->lockdep_map);
else
lock_map_acquire_read(&pwq->wq->lockdep_map);
lock_map_release(&pwq->wq->lockdep_map);
return true;
already_gone:
spin_unlock_irq(&pool->lock);
return false;
}
/**
* flush_work - wait for a work to finish executing the last queueing instance
* @work: the work to flush
*
* Wait until @work has finished execution. @work is guaranteed to be idle
* on return if it hasn't been requeued since flush started.
*
* RETURNS:
* %true if flush_work() waited for the work to finish execution,
* %false if it was already idle.
*/
bool flush_work(struct work_struct *work)
{
struct wq_barrier barr;
lock_map_acquire(&work->lockdep_map);
lock_map_release(&work->lockdep_map);
if (start_flush_work(work, &barr)) {
wait_for_completion(&barr.done);
destroy_work_on_stack(&barr.work);
return true;
} else {
return false;
make cancel_rearming_delayed_work() reliable Thanks to Jarek Poplawski for the ideas and for spotting the bug in the initial draft patch. cancel_rearming_delayed_work() currently has many limitations, because it requires that dwork always re-arms itself via queue_delayed_work(). So it hangs forever if dwork doesn't do this, or cancel_rearming_delayed_work/ cancel_delayed_work was already called. It uses flush_workqueue() in a loop, so it can't be used if workqueue was freezed, and it is potentially live- lockable on busy system if delay is small. With this patch cancel_rearming_delayed_work() doesn't make any assumptions about dwork, it can re-arm itself via queue_delayed_work(), or queue_work(), or do nothing. As a "side effect", cancel_work_sync() was changed to handle re-arming works as well. Disadvantages: - this patch adds wmb() to insert_work(). - slowdowns the fast path (when del_timer() succeeds on entry) of cancel_rearming_delayed_work(), because wait_on_work() is called unconditionally. In that case, compared to the old version, we are doing "unneeded" lock/unlock for each online CPU. On the other hand, this means we don't need to use cancel_work_sync() after cancel_rearming_delayed_work(). - complicates the code (.text grows by 130 bytes). [akpm@linux-foundation.org: fix speling] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: David Chinner <dgc@sgi.com> Cc: David Howells <dhowells@redhat.com> Cc: Gautham Shenoy <ego@in.ibm.com> Acked-by: Jarek Poplawski <jarkao2@o2.pl> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:46 +08:00
}
}
EXPORT_SYMBOL_GPL(flush_work);
make cancel_rearming_delayed_work() reliable Thanks to Jarek Poplawski for the ideas and for spotting the bug in the initial draft patch. cancel_rearming_delayed_work() currently has many limitations, because it requires that dwork always re-arms itself via queue_delayed_work(). So it hangs forever if dwork doesn't do this, or cancel_rearming_delayed_work/ cancel_delayed_work was already called. It uses flush_workqueue() in a loop, so it can't be used if workqueue was freezed, and it is potentially live- lockable on busy system if delay is small. With this patch cancel_rearming_delayed_work() doesn't make any assumptions about dwork, it can re-arm itself via queue_delayed_work(), or queue_work(), or do nothing. As a "side effect", cancel_work_sync() was changed to handle re-arming works as well. Disadvantages: - this patch adds wmb() to insert_work(). - slowdowns the fast path (when del_timer() succeeds on entry) of cancel_rearming_delayed_work(), because wait_on_work() is called unconditionally. In that case, compared to the old version, we are doing "unneeded" lock/unlock for each online CPU. On the other hand, this means we don't need to use cancel_work_sync() after cancel_rearming_delayed_work(). - complicates the code (.text grows by 130 bytes). [akpm@linux-foundation.org: fix speling] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: David Chinner <dgc@sgi.com> Cc: David Howells <dhowells@redhat.com> Cc: Gautham Shenoy <ego@in.ibm.com> Acked-by: Jarek Poplawski <jarkao2@o2.pl> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:46 +08:00
static bool __cancel_work_timer(struct work_struct *work, bool is_dwork)
{
workqueue: mark a work item being canceled as such There can be two reasons try_to_grab_pending() can fail with -EAGAIN. One is when someone else is queueing or deqeueing the work item. With the previous patches, it is guaranteed that PENDING and queued state will soon agree making it safe to busy-retry in this case. The other is if multiple __cancel_work_timer() invocations are racing one another. __cancel_work_timer() grabs PENDING and then waits for running instances of the target work item on all CPUs while holding PENDING and !queued. try_to_grab_pending() invoked from another task will keep returning -EAGAIN while the current owner is waiting. Not distinguishing the two cases is okay because __cancel_work_timer() is the only user of try_to_grab_pending() and it invokes wait_on_work() whenever grabbing fails. For the first case, busy looping should be fine but wait_on_work() doesn't cause any critical problem. For the latter case, the new contender usually waits for the same condition as the current owner, so no unnecessarily extended busy-looping happens. Combined, these make __cancel_work_timer() technically correct even without irq protection while grabbing PENDING or distinguishing the two different cases. While the current code is technically correct, not distinguishing the two cases makes it difficult to use try_to_grab_pending() for other purposes than canceling because it's impossible to tell whether it's safe to busy-retry grabbing. This patch adds a mechanism to mark a work item being canceled. try_to_grab_pending() now disables irq on success and returns -EAGAIN to indicate that grabbing failed but PENDING and queued states are gonna agree soon and it's safe to busy-loop. It returns -ENOENT if the work item is being canceled and it may stay PENDING && !queued for arbitrary amount of time. __cancel_work_timer() is modified to mark the work canceling with WORK_OFFQ_CANCELING after grabbing PENDING, thus making try_to_grab_pending() fail with -ENOENT instead of -EAGAIN. Also, it invokes wait_on_work() iff grabbing failed with -ENOENT. This isn't necessary for correctness but makes it consistent with other future users of try_to_grab_pending(). v2: try_to_grab_pending() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Updated so that try_to_grab_pending() disables irq on success rather than requiring preemption disabled by the caller. This makes busy-looping easier and will allow try_to_grap_pending() to be used from bh/irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:46 +08:00
unsigned long flags;
int ret;
do {
workqueue: mark a work item being canceled as such There can be two reasons try_to_grab_pending() can fail with -EAGAIN. One is when someone else is queueing or deqeueing the work item. With the previous patches, it is guaranteed that PENDING and queued state will soon agree making it safe to busy-retry in this case. The other is if multiple __cancel_work_timer() invocations are racing one another. __cancel_work_timer() grabs PENDING and then waits for running instances of the target work item on all CPUs while holding PENDING and !queued. try_to_grab_pending() invoked from another task will keep returning -EAGAIN while the current owner is waiting. Not distinguishing the two cases is okay because __cancel_work_timer() is the only user of try_to_grab_pending() and it invokes wait_on_work() whenever grabbing fails. For the first case, busy looping should be fine but wait_on_work() doesn't cause any critical problem. For the latter case, the new contender usually waits for the same condition as the current owner, so no unnecessarily extended busy-looping happens. Combined, these make __cancel_work_timer() technically correct even without irq protection while grabbing PENDING or distinguishing the two different cases. While the current code is technically correct, not distinguishing the two cases makes it difficult to use try_to_grab_pending() for other purposes than canceling because it's impossible to tell whether it's safe to busy-retry grabbing. This patch adds a mechanism to mark a work item being canceled. try_to_grab_pending() now disables irq on success and returns -EAGAIN to indicate that grabbing failed but PENDING and queued states are gonna agree soon and it's safe to busy-loop. It returns -ENOENT if the work item is being canceled and it may stay PENDING && !queued for arbitrary amount of time. __cancel_work_timer() is modified to mark the work canceling with WORK_OFFQ_CANCELING after grabbing PENDING, thus making try_to_grab_pending() fail with -ENOENT instead of -EAGAIN. Also, it invokes wait_on_work() iff grabbing failed with -ENOENT. This isn't necessary for correctness but makes it consistent with other future users of try_to_grab_pending(). v2: try_to_grab_pending() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Updated so that try_to_grab_pending() disables irq on success rather than requiring preemption disabled by the caller. This makes busy-looping easier and will allow try_to_grap_pending() to be used from bh/irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:46 +08:00
ret = try_to_grab_pending(work, is_dwork, &flags);
/*
* If someone else is canceling, wait for the same event it
* would be waiting for before retrying.
*/
if (unlikely(ret == -ENOENT))
flush_work(work);
} while (unlikely(ret < 0));
workqueue: mark a work item being canceled as such There can be two reasons try_to_grab_pending() can fail with -EAGAIN. One is when someone else is queueing or deqeueing the work item. With the previous patches, it is guaranteed that PENDING and queued state will soon agree making it safe to busy-retry in this case. The other is if multiple __cancel_work_timer() invocations are racing one another. __cancel_work_timer() grabs PENDING and then waits for running instances of the target work item on all CPUs while holding PENDING and !queued. try_to_grab_pending() invoked from another task will keep returning -EAGAIN while the current owner is waiting. Not distinguishing the two cases is okay because __cancel_work_timer() is the only user of try_to_grab_pending() and it invokes wait_on_work() whenever grabbing fails. For the first case, busy looping should be fine but wait_on_work() doesn't cause any critical problem. For the latter case, the new contender usually waits for the same condition as the current owner, so no unnecessarily extended busy-looping happens. Combined, these make __cancel_work_timer() technically correct even without irq protection while grabbing PENDING or distinguishing the two different cases. While the current code is technically correct, not distinguishing the two cases makes it difficult to use try_to_grab_pending() for other purposes than canceling because it's impossible to tell whether it's safe to busy-retry grabbing. This patch adds a mechanism to mark a work item being canceled. try_to_grab_pending() now disables irq on success and returns -EAGAIN to indicate that grabbing failed but PENDING and queued states are gonna agree soon and it's safe to busy-loop. It returns -ENOENT if the work item is being canceled and it may stay PENDING && !queued for arbitrary amount of time. __cancel_work_timer() is modified to mark the work canceling with WORK_OFFQ_CANCELING after grabbing PENDING, thus making try_to_grab_pending() fail with -ENOENT instead of -EAGAIN. Also, it invokes wait_on_work() iff grabbing failed with -ENOENT. This isn't necessary for correctness but makes it consistent with other future users of try_to_grab_pending(). v2: try_to_grab_pending() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Updated so that try_to_grab_pending() disables irq on success rather than requiring preemption disabled by the caller. This makes busy-looping easier and will allow try_to_grap_pending() to be used from bh/irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:46 +08:00
/* tell other tasks trying to grab @work to back off */
mark_work_canceling(work);
local_irq_restore(flags);
flush_work(work);
clear_work_data(work);
return ret;
}
make cancel_rearming_delayed_work() reliable Thanks to Jarek Poplawski for the ideas and for spotting the bug in the initial draft patch. cancel_rearming_delayed_work() currently has many limitations, because it requires that dwork always re-arms itself via queue_delayed_work(). So it hangs forever if dwork doesn't do this, or cancel_rearming_delayed_work/ cancel_delayed_work was already called. It uses flush_workqueue() in a loop, so it can't be used if workqueue was freezed, and it is potentially live- lockable on busy system if delay is small. With this patch cancel_rearming_delayed_work() doesn't make any assumptions about dwork, it can re-arm itself via queue_delayed_work(), or queue_work(), or do nothing. As a "side effect", cancel_work_sync() was changed to handle re-arming works as well. Disadvantages: - this patch adds wmb() to insert_work(). - slowdowns the fast path (when del_timer() succeeds on entry) of cancel_rearming_delayed_work(), because wait_on_work() is called unconditionally. In that case, compared to the old version, we are doing "unneeded" lock/unlock for each online CPU. On the other hand, this means we don't need to use cancel_work_sync() after cancel_rearming_delayed_work(). - complicates the code (.text grows by 130 bytes). [akpm@linux-foundation.org: fix speling] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: David Chinner <dgc@sgi.com> Cc: David Howells <dhowells@redhat.com> Cc: Gautham Shenoy <ego@in.ibm.com> Acked-by: Jarek Poplawski <jarkao2@o2.pl> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:46 +08:00
/**
* cancel_work_sync - cancel a work and wait for it to finish
* @work: the work to cancel
make cancel_rearming_delayed_work() reliable Thanks to Jarek Poplawski for the ideas and for spotting the bug in the initial draft patch. cancel_rearming_delayed_work() currently has many limitations, because it requires that dwork always re-arms itself via queue_delayed_work(). So it hangs forever if dwork doesn't do this, or cancel_rearming_delayed_work/ cancel_delayed_work was already called. It uses flush_workqueue() in a loop, so it can't be used if workqueue was freezed, and it is potentially live- lockable on busy system if delay is small. With this patch cancel_rearming_delayed_work() doesn't make any assumptions about dwork, it can re-arm itself via queue_delayed_work(), or queue_work(), or do nothing. As a "side effect", cancel_work_sync() was changed to handle re-arming works as well. Disadvantages: - this patch adds wmb() to insert_work(). - slowdowns the fast path (when del_timer() succeeds on entry) of cancel_rearming_delayed_work(), because wait_on_work() is called unconditionally. In that case, compared to the old version, we are doing "unneeded" lock/unlock for each online CPU. On the other hand, this means we don't need to use cancel_work_sync() after cancel_rearming_delayed_work(). - complicates the code (.text grows by 130 bytes). [akpm@linux-foundation.org: fix speling] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: David Chinner <dgc@sgi.com> Cc: David Howells <dhowells@redhat.com> Cc: Gautham Shenoy <ego@in.ibm.com> Acked-by: Jarek Poplawski <jarkao2@o2.pl> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:46 +08:00
*
* Cancel @work and wait for its execution to finish. This function
* can be used even if the work re-queues itself or migrates to
* another workqueue. On return from this function, @work is
* guaranteed to be not pending or executing on any CPU.
*
* cancel_work_sync(&delayed_work->work) must not be used for
* delayed_work's. Use cancel_delayed_work_sync() instead.
make cancel_rearming_delayed_work() reliable Thanks to Jarek Poplawski for the ideas and for spotting the bug in the initial draft patch. cancel_rearming_delayed_work() currently has many limitations, because it requires that dwork always re-arms itself via queue_delayed_work(). So it hangs forever if dwork doesn't do this, or cancel_rearming_delayed_work/ cancel_delayed_work was already called. It uses flush_workqueue() in a loop, so it can't be used if workqueue was freezed, and it is potentially live- lockable on busy system if delay is small. With this patch cancel_rearming_delayed_work() doesn't make any assumptions about dwork, it can re-arm itself via queue_delayed_work(), or queue_work(), or do nothing. As a "side effect", cancel_work_sync() was changed to handle re-arming works as well. Disadvantages: - this patch adds wmb() to insert_work(). - slowdowns the fast path (when del_timer() succeeds on entry) of cancel_rearming_delayed_work(), because wait_on_work() is called unconditionally. In that case, compared to the old version, we are doing "unneeded" lock/unlock for each online CPU. On the other hand, this means we don't need to use cancel_work_sync() after cancel_rearming_delayed_work(). - complicates the code (.text grows by 130 bytes). [akpm@linux-foundation.org: fix speling] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: David Chinner <dgc@sgi.com> Cc: David Howells <dhowells@redhat.com> Cc: Gautham Shenoy <ego@in.ibm.com> Acked-by: Jarek Poplawski <jarkao2@o2.pl> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:46 +08:00
*
* The caller must ensure that the workqueue on which @work was last
make cancel_rearming_delayed_work() reliable Thanks to Jarek Poplawski for the ideas and for spotting the bug in the initial draft patch. cancel_rearming_delayed_work() currently has many limitations, because it requires that dwork always re-arms itself via queue_delayed_work(). So it hangs forever if dwork doesn't do this, or cancel_rearming_delayed_work/ cancel_delayed_work was already called. It uses flush_workqueue() in a loop, so it can't be used if workqueue was freezed, and it is potentially live- lockable on busy system if delay is small. With this patch cancel_rearming_delayed_work() doesn't make any assumptions about dwork, it can re-arm itself via queue_delayed_work(), or queue_work(), or do nothing. As a "side effect", cancel_work_sync() was changed to handle re-arming works as well. Disadvantages: - this patch adds wmb() to insert_work(). - slowdowns the fast path (when del_timer() succeeds on entry) of cancel_rearming_delayed_work(), because wait_on_work() is called unconditionally. In that case, compared to the old version, we are doing "unneeded" lock/unlock for each online CPU. On the other hand, this means we don't need to use cancel_work_sync() after cancel_rearming_delayed_work(). - complicates the code (.text grows by 130 bytes). [akpm@linux-foundation.org: fix speling] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: David Chinner <dgc@sgi.com> Cc: David Howells <dhowells@redhat.com> Cc: Gautham Shenoy <ego@in.ibm.com> Acked-by: Jarek Poplawski <jarkao2@o2.pl> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:46 +08:00
* queued can't be destroyed before this function returns.
*
* RETURNS:
* %true if @work was pending, %false otherwise.
make cancel_rearming_delayed_work() reliable Thanks to Jarek Poplawski for the ideas and for spotting the bug in the initial draft patch. cancel_rearming_delayed_work() currently has many limitations, because it requires that dwork always re-arms itself via queue_delayed_work(). So it hangs forever if dwork doesn't do this, or cancel_rearming_delayed_work/ cancel_delayed_work was already called. It uses flush_workqueue() in a loop, so it can't be used if workqueue was freezed, and it is potentially live- lockable on busy system if delay is small. With this patch cancel_rearming_delayed_work() doesn't make any assumptions about dwork, it can re-arm itself via queue_delayed_work(), or queue_work(), or do nothing. As a "side effect", cancel_work_sync() was changed to handle re-arming works as well. Disadvantages: - this patch adds wmb() to insert_work(). - slowdowns the fast path (when del_timer() succeeds on entry) of cancel_rearming_delayed_work(), because wait_on_work() is called unconditionally. In that case, compared to the old version, we are doing "unneeded" lock/unlock for each online CPU. On the other hand, this means we don't need to use cancel_work_sync() after cancel_rearming_delayed_work(). - complicates the code (.text grows by 130 bytes). [akpm@linux-foundation.org: fix speling] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: David Chinner <dgc@sgi.com> Cc: David Howells <dhowells@redhat.com> Cc: Gautham Shenoy <ego@in.ibm.com> Acked-by: Jarek Poplawski <jarkao2@o2.pl> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:46 +08:00
*/
bool cancel_work_sync(struct work_struct *work)
make cancel_rearming_delayed_work() reliable Thanks to Jarek Poplawski for the ideas and for spotting the bug in the initial draft patch. cancel_rearming_delayed_work() currently has many limitations, because it requires that dwork always re-arms itself via queue_delayed_work(). So it hangs forever if dwork doesn't do this, or cancel_rearming_delayed_work/ cancel_delayed_work was already called. It uses flush_workqueue() in a loop, so it can't be used if workqueue was freezed, and it is potentially live- lockable on busy system if delay is small. With this patch cancel_rearming_delayed_work() doesn't make any assumptions about dwork, it can re-arm itself via queue_delayed_work(), or queue_work(), or do nothing. As a "side effect", cancel_work_sync() was changed to handle re-arming works as well. Disadvantages: - this patch adds wmb() to insert_work(). - slowdowns the fast path (when del_timer() succeeds on entry) of cancel_rearming_delayed_work(), because wait_on_work() is called unconditionally. In that case, compared to the old version, we are doing "unneeded" lock/unlock for each online CPU. On the other hand, this means we don't need to use cancel_work_sync() after cancel_rearming_delayed_work(). - complicates the code (.text grows by 130 bytes). [akpm@linux-foundation.org: fix speling] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: David Chinner <dgc@sgi.com> Cc: David Howells <dhowells@redhat.com> Cc: Gautham Shenoy <ego@in.ibm.com> Acked-by: Jarek Poplawski <jarkao2@o2.pl> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:46 +08:00
{
return __cancel_work_timer(work, false);
implement flush_work() A basic problem with flush_scheduled_work() is that it blocks behind _all_ presently-queued works, rather than just the work whcih the caller wants to flush. If the caller holds some lock, and if one of the queued work happens to want that lock as well then accidental deadlocks can occur. One example of this is the phy layer: it wants to flush work while holding rtnl_lock(). But if a linkwatch event happens to be queued, the phy code will deadlock because the linkwatch callback function takes rtnl_lock. So we implement a new function which will flush a *single* work - just the one which the caller wants to free up. Thus we avoid the accidental deadlocks which can arise from unrelated subsystems' callbacks taking shared locks. flush_work() non-blockingly dequeues the work_struct which we want to kill, then it waits for its handler to complete on all CPUs. Add ->current_work to the "struct cpu_workqueue_struct", it points to currently running "struct work_struct". When flush_work(work) detects ->current_work == work, it inserts a barrier at the _head_ of ->worklist (and thus right _after_ that work) and waits for completition. This means that the next work fired on that CPU will be this barrier, or another barrier queued by concurrent flush_work(), so the caller of flush_work() will be woken before any "regular" work has a chance to run. When wait_on_work() unlocks workqueue_mutex (or whatever we choose to protect against CPU hotplug), CPU may go away. But in that case take_over_work() will move a barrier we queued to another CPU, it will be fired sometime, and wait_on_work() will be woken. Actually, we are doing cleanup_workqueue_thread()->kthread_stop() before take_over_work(), so cwq->thread should complete its ->worklist (and thus the barrier), because currently we don't check kthread_should_stop() in run_workqueue(). But even if we did, everything should be ok. [akpm@osdl.org: cleanup] [akpm@osdl.org: add flush_work_keventd() wrapper] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:33:52 +08:00
}
EXPORT_SYMBOL_GPL(cancel_work_sync);
implement flush_work() A basic problem with flush_scheduled_work() is that it blocks behind _all_ presently-queued works, rather than just the work whcih the caller wants to flush. If the caller holds some lock, and if one of the queued work happens to want that lock as well then accidental deadlocks can occur. One example of this is the phy layer: it wants to flush work while holding rtnl_lock(). But if a linkwatch event happens to be queued, the phy code will deadlock because the linkwatch callback function takes rtnl_lock. So we implement a new function which will flush a *single* work - just the one which the caller wants to free up. Thus we avoid the accidental deadlocks which can arise from unrelated subsystems' callbacks taking shared locks. flush_work() non-blockingly dequeues the work_struct which we want to kill, then it waits for its handler to complete on all CPUs. Add ->current_work to the "struct cpu_workqueue_struct", it points to currently running "struct work_struct". When flush_work(work) detects ->current_work == work, it inserts a barrier at the _head_ of ->worklist (and thus right _after_ that work) and waits for completition. This means that the next work fired on that CPU will be this barrier, or another barrier queued by concurrent flush_work(), so the caller of flush_work() will be woken before any "regular" work has a chance to run. When wait_on_work() unlocks workqueue_mutex (or whatever we choose to protect against CPU hotplug), CPU may go away. But in that case take_over_work() will move a barrier we queued to another CPU, it will be fired sometime, and wait_on_work() will be woken. Actually, we are doing cleanup_workqueue_thread()->kthread_stop() before take_over_work(), so cwq->thread should complete its ->worklist (and thus the barrier), because currently we don't check kthread_should_stop() in run_workqueue(). But even if we did, everything should be ok. [akpm@osdl.org: cleanup] [akpm@osdl.org: add flush_work_keventd() wrapper] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:33:52 +08:00
make cancel_rearming_delayed_work() reliable Thanks to Jarek Poplawski for the ideas and for spotting the bug in the initial draft patch. cancel_rearming_delayed_work() currently has many limitations, because it requires that dwork always re-arms itself via queue_delayed_work(). So it hangs forever if dwork doesn't do this, or cancel_rearming_delayed_work/ cancel_delayed_work was already called. It uses flush_workqueue() in a loop, so it can't be used if workqueue was freezed, and it is potentially live- lockable on busy system if delay is small. With this patch cancel_rearming_delayed_work() doesn't make any assumptions about dwork, it can re-arm itself via queue_delayed_work(), or queue_work(), or do nothing. As a "side effect", cancel_work_sync() was changed to handle re-arming works as well. Disadvantages: - this patch adds wmb() to insert_work(). - slowdowns the fast path (when del_timer() succeeds on entry) of cancel_rearming_delayed_work(), because wait_on_work() is called unconditionally. In that case, compared to the old version, we are doing "unneeded" lock/unlock for each online CPU. On the other hand, this means we don't need to use cancel_work_sync() after cancel_rearming_delayed_work(). - complicates the code (.text grows by 130 bytes). [akpm@linux-foundation.org: fix speling] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: David Chinner <dgc@sgi.com> Cc: David Howells <dhowells@redhat.com> Cc: Gautham Shenoy <ego@in.ibm.com> Acked-by: Jarek Poplawski <jarkao2@o2.pl> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:46 +08:00
/**
* flush_delayed_work - wait for a dwork to finish executing the last queueing
* @dwork: the delayed work to flush
make cancel_rearming_delayed_work() reliable Thanks to Jarek Poplawski for the ideas and for spotting the bug in the initial draft patch. cancel_rearming_delayed_work() currently has many limitations, because it requires that dwork always re-arms itself via queue_delayed_work(). So it hangs forever if dwork doesn't do this, or cancel_rearming_delayed_work/ cancel_delayed_work was already called. It uses flush_workqueue() in a loop, so it can't be used if workqueue was freezed, and it is potentially live- lockable on busy system if delay is small. With this patch cancel_rearming_delayed_work() doesn't make any assumptions about dwork, it can re-arm itself via queue_delayed_work(), or queue_work(), or do nothing. As a "side effect", cancel_work_sync() was changed to handle re-arming works as well. Disadvantages: - this patch adds wmb() to insert_work(). - slowdowns the fast path (when del_timer() succeeds on entry) of cancel_rearming_delayed_work(), because wait_on_work() is called unconditionally. In that case, compared to the old version, we are doing "unneeded" lock/unlock for each online CPU. On the other hand, this means we don't need to use cancel_work_sync() after cancel_rearming_delayed_work(). - complicates the code (.text grows by 130 bytes). [akpm@linux-foundation.org: fix speling] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: David Chinner <dgc@sgi.com> Cc: David Howells <dhowells@redhat.com> Cc: Gautham Shenoy <ego@in.ibm.com> Acked-by: Jarek Poplawski <jarkao2@o2.pl> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:46 +08:00
*
* Delayed timer is cancelled and the pending work is queued for
* immediate execution. Like flush_work(), this function only
* considers the last queueing instance of @dwork.
*
* RETURNS:
* %true if flush_work() waited for the work to finish execution,
* %false if it was already idle.
make cancel_rearming_delayed_work() reliable Thanks to Jarek Poplawski for the ideas and for spotting the bug in the initial draft patch. cancel_rearming_delayed_work() currently has many limitations, because it requires that dwork always re-arms itself via queue_delayed_work(). So it hangs forever if dwork doesn't do this, or cancel_rearming_delayed_work/ cancel_delayed_work was already called. It uses flush_workqueue() in a loop, so it can't be used if workqueue was freezed, and it is potentially live- lockable on busy system if delay is small. With this patch cancel_rearming_delayed_work() doesn't make any assumptions about dwork, it can re-arm itself via queue_delayed_work(), or queue_work(), or do nothing. As a "side effect", cancel_work_sync() was changed to handle re-arming works as well. Disadvantages: - this patch adds wmb() to insert_work(). - slowdowns the fast path (when del_timer() succeeds on entry) of cancel_rearming_delayed_work(), because wait_on_work() is called unconditionally. In that case, compared to the old version, we are doing "unneeded" lock/unlock for each online CPU. On the other hand, this means we don't need to use cancel_work_sync() after cancel_rearming_delayed_work(). - complicates the code (.text grows by 130 bytes). [akpm@linux-foundation.org: fix speling] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: David Chinner <dgc@sgi.com> Cc: David Howells <dhowells@redhat.com> Cc: Gautham Shenoy <ego@in.ibm.com> Acked-by: Jarek Poplawski <jarkao2@o2.pl> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:46 +08:00
*/
bool flush_delayed_work(struct delayed_work *dwork)
{
workqueue: disable irq while manipulating PENDING Queueing operations use WORK_STRUCT_PENDING_BIT to synchronize access to the target work item. They first try to claim the bit and proceed with queueing only after that succeeds and there's a window between PENDING being set and the actual queueing where the task can be interrupted or preempted. There's also a similar window in process_one_work() when clearing PENDING. A work item is dequeued, gcwq->lock is released and then PENDING is cleared and the worker might get interrupted or preempted between releasing gcwq->lock and clearing PENDING. cancel[_delayed]_work_sync() tries to claim or steal PENDING. The function assumes that a work item with PENDING is either queued or in the process of being [de]queued. In the latter case, it busy-loops until either the work item loses PENDING or is queued. If canceling coincides with the above described interrupts or preemptions, the canceling task will busy-loop while the queueing or executing task is preempted. This patch keeps irq disabled across claiming PENDING and actual queueing and moves PENDING clearing in process_one_work() inside gcwq->lock so that busy looping from PENDING && !queued doesn't wait for interrupted/preempted tasks. Note that, in process_one_work(), setting last CPU and clearing PENDING got merged into single operation. This removes possible long busy-loops and will allow using try_to_grab_pending() from bh and irq contexts. v2: __queue_work() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Disable irq instead of preemption. IRQ will be disabled while grabbing gcwq->lock later anyway and this allows using try_to_grab_pending() from bh and irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:45 +08:00
local_irq_disable();
if (del_timer_sync(&dwork->timer))
workqueue: add delayed_work->wq to simplify reentrancy handling To avoid executing the same work item from multiple CPUs concurrently, a work_struct records the last pool it was on in its ->data so that, on the next queueing, the pool can be queried to determine whether the work item is still executing or not. A delayed_work goes through timer before actually being queued on the target workqueue and the timer needs to know the target workqueue and CPU. This is currently achieved by modifying delayed_work->work.data such that it points to the cwq which points to the target workqueue and the last CPU the work item was on. __queue_delayed_work() extracts the last CPU from delayed_work->work.data and then combines it with the target workqueue to create new work.data. The only thing this rather ugly hack achieves is encoding the target workqueue into delayed_work->work.data without using a separate field, which could be a trade off one can make; unfortunately, this entangles work->data management between regular workqueue and delayed_work code by setting cwq pointer before the work item is actually queued and becomes a hindrance for further improvements of work->data handling. This can be easily made sane by adding a target workqueue field to delayed_work. While delayed_work is used widely in the kernel and this does make it a bit larger (<5%), I think this is the right trade-off especially given the prospect of much saner handling of work->data which currently involves quite tricky memory barrier dancing, and don't expect to see any measureable effect. Add delayed_work->wq and drop the delayed_work->work.data overloading. tj: Rewrote the description. Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2013-02-07 10:04:53 +08:00
__queue_work(dwork->cpu, dwork->wq, &dwork->work);
workqueue: disable irq while manipulating PENDING Queueing operations use WORK_STRUCT_PENDING_BIT to synchronize access to the target work item. They first try to claim the bit and proceed with queueing only after that succeeds and there's a window between PENDING being set and the actual queueing where the task can be interrupted or preempted. There's also a similar window in process_one_work() when clearing PENDING. A work item is dequeued, gcwq->lock is released and then PENDING is cleared and the worker might get interrupted or preempted between releasing gcwq->lock and clearing PENDING. cancel[_delayed]_work_sync() tries to claim or steal PENDING. The function assumes that a work item with PENDING is either queued or in the process of being [de]queued. In the latter case, it busy-loops until either the work item loses PENDING or is queued. If canceling coincides with the above described interrupts or preemptions, the canceling task will busy-loop while the queueing or executing task is preempted. This patch keeps irq disabled across claiming PENDING and actual queueing and moves PENDING clearing in process_one_work() inside gcwq->lock so that busy looping from PENDING && !queued doesn't wait for interrupted/preempted tasks. Note that, in process_one_work(), setting last CPU and clearing PENDING got merged into single operation. This removes possible long busy-loops and will allow using try_to_grab_pending() from bh and irq contexts. v2: __queue_work() was testing preempt_count() to ensure that the caller has disabled preemption. This triggers spuriously if !CONFIG_PREEMPT_COUNT. Use preemptible() instead. Reported by Fengguang Wu. v3: Disable irq instead of preemption. IRQ will be disabled while grabbing gcwq->lock later anyway and this allows using try_to_grab_pending() from bh and irq contexts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Fengguang Wu <fengguang.wu@intel.com>
2012-08-04 01:30:45 +08:00
local_irq_enable();
return flush_work(&dwork->work);
}
EXPORT_SYMBOL(flush_delayed_work);
/**
* 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.
*
* This function is safe to call from any context including IRQ handler.
*/
bool cancel_delayed_work(struct delayed_work *dwork)
{
unsigned long flags;
int ret;
do {
ret = try_to_grab_pending(&dwork->work, true, &flags);
} while (unlikely(ret == -EAGAIN));
if (unlikely(ret < 0))
return false;
set_work_pool_and_clear_pending(&dwork->work,
get_work_pool_id(&dwork->work));
local_irq_restore(flags);
return ret;
}
EXPORT_SYMBOL(cancel_delayed_work);
/**
* cancel_delayed_work_sync - cancel a delayed work and wait for it to finish
* @dwork: the delayed work cancel
*
* This is cancel_work_sync() for delayed works.
*
* RETURNS:
* %true if @dwork was pending, %false otherwise.
*/
bool cancel_delayed_work_sync(struct delayed_work *dwork)
make cancel_rearming_delayed_work() reliable Thanks to Jarek Poplawski for the ideas and for spotting the bug in the initial draft patch. cancel_rearming_delayed_work() currently has many limitations, because it requires that dwork always re-arms itself via queue_delayed_work(). So it hangs forever if dwork doesn't do this, or cancel_rearming_delayed_work/ cancel_delayed_work was already called. It uses flush_workqueue() in a loop, so it can't be used if workqueue was freezed, and it is potentially live- lockable on busy system if delay is small. With this patch cancel_rearming_delayed_work() doesn't make any assumptions about dwork, it can re-arm itself via queue_delayed_work(), or queue_work(), or do nothing. As a "side effect", cancel_work_sync() was changed to handle re-arming works as well. Disadvantages: - this patch adds wmb() to insert_work(). - slowdowns the fast path (when del_timer() succeeds on entry) of cancel_rearming_delayed_work(), because wait_on_work() is called unconditionally. In that case, compared to the old version, we are doing "unneeded" lock/unlock for each online CPU. On the other hand, this means we don't need to use cancel_work_sync() after cancel_rearming_delayed_work(). - complicates the code (.text grows by 130 bytes). [akpm@linux-foundation.org: fix speling] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: David Chinner <dgc@sgi.com> Cc: David Howells <dhowells@redhat.com> Cc: Gautham Shenoy <ego@in.ibm.com> Acked-by: Jarek Poplawski <jarkao2@o2.pl> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:46 +08:00
{
return __cancel_work_timer(&dwork->work, true);
make cancel_rearming_delayed_work() reliable Thanks to Jarek Poplawski for the ideas and for spotting the bug in the initial draft patch. cancel_rearming_delayed_work() currently has many limitations, because it requires that dwork always re-arms itself via queue_delayed_work(). So it hangs forever if dwork doesn't do this, or cancel_rearming_delayed_work/ cancel_delayed_work was already called. It uses flush_workqueue() in a loop, so it can't be used if workqueue was freezed, and it is potentially live- lockable on busy system if delay is small. With this patch cancel_rearming_delayed_work() doesn't make any assumptions about dwork, it can re-arm itself via queue_delayed_work(), or queue_work(), or do nothing. As a "side effect", cancel_work_sync() was changed to handle re-arming works as well. Disadvantages: - this patch adds wmb() to insert_work(). - slowdowns the fast path (when del_timer() succeeds on entry) of cancel_rearming_delayed_work(), because wait_on_work() is called unconditionally. In that case, compared to the old version, we are doing "unneeded" lock/unlock for each online CPU. On the other hand, this means we don't need to use cancel_work_sync() after cancel_rearming_delayed_work(). - complicates the code (.text grows by 130 bytes). [akpm@linux-foundation.org: fix speling] Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Cc: David Chinner <dgc@sgi.com> Cc: David Howells <dhowells@redhat.com> Cc: Gautham Shenoy <ego@in.ibm.com> Acked-by: Jarek Poplawski <jarkao2@o2.pl> Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-09 17:34:46 +08:00
}
EXPORT_SYMBOL(cancel_delayed_work_sync);
/**
* schedule_work_on - put work task on a specific cpu
* @cpu: cpu to put the work task on
* @work: job to be done
*
* This puts a job on a specific cpu
*/
bool schedule_work_on(int cpu, struct work_struct *work)
{
return queue_work_on(cpu, system_wq, work);
}
EXPORT_SYMBOL(schedule_work_on);
/**
* schedule_work - put work task in global workqueue
* @work: job to be done
*
* Returns %false if @work was already on the kernel-global workqueue and
* %true otherwise.
*
* This puts a job in the kernel-global workqueue if it was not already
* queued and leaves it in the same position on the kernel-global
* workqueue otherwise.
*/
bool schedule_work(struct work_struct *work)
{
return queue_work(system_wq, work);
}
EXPORT_SYMBOL(schedule_work);
/**
* schedule_delayed_work_on - queue work in global workqueue on CPU after delay
* @cpu: cpu to use
* @dwork: job to be done
* @delay: number of jiffies to wait
*
* After waiting for a given time this puts a job in the kernel-global
* workqueue on the specified CPU.
*/
bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork,
unsigned long delay)
{
return queue_delayed_work_on(cpu, system_wq, dwork, delay);
}
EXPORT_SYMBOL(schedule_delayed_work_on);
/**
* schedule_delayed_work - put work task in global workqueue after delay
* @dwork: job to be done
* @delay: number of jiffies to wait or 0 for immediate execution
*
* After waiting for a given time this puts a job in the kernel-global
* workqueue.
*/
bool schedule_delayed_work(struct delayed_work *dwork, unsigned long delay)
{
return queue_delayed_work(system_wq, dwork, delay);
}
EXPORT_SYMBOL(schedule_delayed_work);
/**
* schedule_on_each_cpu - execute a function synchronously on each online CPU
* @func: the function to call
*
* schedule_on_each_cpu() executes @func on each online CPU using the
* system workqueue and blocks until all CPUs have completed.
* schedule_on_each_cpu() is very slow.
*
* RETURNS:
* 0 on success, -errno on failure.
*/
2006-11-22 22:55:48 +08:00
int schedule_on_each_cpu(work_func_t func)
{
int cpu;
struct work_struct __percpu *works;
works = alloc_percpu(struct work_struct);
if (!works)
return -ENOMEM;
get_online_cpus();
for_each_online_cpu(cpu) {
struct work_struct *work = per_cpu_ptr(works, cpu);
INIT_WORK(work, func);
schedule_work_on(cpu, work);
}
for_each_online_cpu(cpu)
flush_work(per_cpu_ptr(works, cpu));
put_online_cpus();
free_percpu(works);
return 0;
}
/**
* flush_scheduled_work - ensure that any scheduled work has run to completion.
*
* Forces execution of the kernel-global workqueue and blocks until its
* completion.
*
* Think twice before calling this function! It's very easy to get into
* trouble if you don't take great care. Either of the following situations
* will lead to deadlock:
*
* One of the work items currently on the workqueue needs to acquire
* a lock held by your code or its caller.
*
* Your code is running in the context of a work routine.
*
* They will be detected by lockdep when they occur, but the first might not
* occur very often. It depends on what work items are on the workqueue and
* what locks they need, which you have no control over.
*
* In most situations flushing the entire workqueue is overkill; you merely
* need to know that a particular work item isn't queued and isn't running.
* In such cases you should use cancel_delayed_work_sync() or
* cancel_work_sync() instead.
*/
void flush_scheduled_work(void)
{
flush_workqueue(system_wq);
}
EXPORT_SYMBOL(flush_scheduled_work);
/**
* execute_in_process_context - reliably execute the routine with user context
* @fn: the function to execute
* @ew: guaranteed storage for the execute work structure (must
* be available when the work executes)
*
* Executes the function immediately if process context is available,
* otherwise schedules the function for delayed execution.
*
* Returns: 0 - function was executed
* 1 - function was scheduled for execution
*/
2006-11-22 22:55:48 +08:00
int execute_in_process_context(work_func_t fn, struct execute_work *ew)
{
if (!in_interrupt()) {
2006-11-22 22:55:48 +08:00
fn(&ew->work);
return 0;
}
2006-11-22 22:55:48 +08:00
INIT_WORK(&ew->work, fn);
schedule_work(&ew->work);
return 1;
}
EXPORT_SYMBOL_GPL(execute_in_process_context);
int keventd_up(void)
{
return system_wq != NULL;
}
static int alloc_pwqs(struct workqueue_struct *wq)
{
/*
* pwqs are forced aligned according to WORK_STRUCT_FLAG_BITS.
* Make sure that the alignment isn't lower than that of
* unsigned long long.
*/
const size_t size = sizeof(struct pool_workqueue);
const size_t align = max_t(size_t, 1 << WORK_STRUCT_FLAG_BITS,
__alignof__(unsigned long long));
if (!(wq->flags & WQ_UNBOUND))
wq->pool_wq.pcpu = __alloc_percpu(size, align);
else {
void *ptr;
/*
* Allocate enough room to align pwq and put an extra
* pointer at the end pointing back to the originally
* allocated pointer which will be used for free.
*/
ptr = kzalloc(size + align + sizeof(void *), GFP_KERNEL);
if (ptr) {
wq->pool_wq.single = PTR_ALIGN(ptr, align);
*(void **)(wq->pool_wq.single + 1) = ptr;
}
}
/* just in case, make sure it's actually aligned */
BUG_ON(!IS_ALIGNED(wq->pool_wq.v, align));
return wq->pool_wq.v ? 0 : -ENOMEM;
}
static void free_pwqs(struct workqueue_struct *wq)
{
if (!(wq->flags & WQ_UNBOUND))
free_percpu(wq->pool_wq.pcpu);
else if (wq->pool_wq.single) {
/* the pointer to free is stored right after the pwq */
kfree(*(void **)(wq->pool_wq.single + 1));
}
}
static int wq_clamp_max_active(int max_active, unsigned int flags,
const char *name)
{
int lim = flags & WQ_UNBOUND ? WQ_UNBOUND_MAX_ACTIVE : WQ_MAX_ACTIVE;
if (max_active < 1 || max_active > lim)
pr_warn("workqueue: max_active %d requested for %s is out of range, clamping between %d and %d\n",
max_active, name, 1, lim);
return clamp_val(max_active, 1, lim);
}
struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
unsigned int flags,
int max_active,
struct lock_class_key *key,
const char *lock_name, ...)
{
va_list args, args1;
struct workqueue_struct *wq;
unsigned int cpu;
size_t namelen;
/* determine namelen, allocate wq and format name */
va_start(args, lock_name);
va_copy(args1, args);
namelen = vsnprintf(NULL, 0, fmt, args) + 1;
wq = kzalloc(sizeof(*wq) + namelen, GFP_KERNEL);
if (!wq)
goto err;
vsnprintf(wq->name, namelen, fmt, args1);
va_end(args);
va_end(args1);
/*
* Workqueues which may be used during memory reclaim should
* have a rescuer to guarantee forward progress.
*/
if (flags & WQ_MEM_RECLAIM)
flags |= WQ_RESCUER;
max_active = max_active ?: WQ_DFL_ACTIVE;
max_active = wq_clamp_max_active(max_active, flags, wq->name);
/* init wq */
wq->flags = flags;
wq->saved_max_active = max_active;
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
mutex_init(&wq->flush_mutex);
atomic_set(&wq->nr_pwqs_to_flush, 0);
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
INIT_LIST_HEAD(&wq->flusher_queue);
INIT_LIST_HEAD(&wq->flusher_overflow);
lockdep_init_map(&wq->lockdep_map, lock_name, key, 0);
INIT_LIST_HEAD(&wq->list);
if (alloc_pwqs(wq) < 0)
goto err;
for_each_pwq_cpu(cpu, wq) {
struct pool_workqueue *pwq = get_pwq(cpu, wq);
BUG_ON((unsigned long)pwq & WORK_STRUCT_FLAG_MASK);
pwq->pool = get_std_worker_pool(cpu, flags & WQ_HIGHPRI);
pwq->wq = wq;
pwq->flush_color = -1;
pwq->max_active = max_active;
INIT_LIST_HEAD(&pwq->delayed_works);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
}
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
if (flags & WQ_RESCUER) {
struct worker *rescuer;
if (!alloc_mayday_mask(&wq->mayday_mask, GFP_KERNEL))
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
goto err;
wq->rescuer = rescuer = alloc_worker();
if (!rescuer)
goto err;
rescuer->rescue_wq = wq;
rescuer->task = kthread_create(rescuer_thread, rescuer, "%s",
wq->name);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
if (IS_ERR(rescuer->task))
goto err;
rescuer->task->flags |= PF_THREAD_BOUND;
wake_up_process(rescuer->task);
}
/*
* workqueue_lock protects global freeze state and workqueues
* list. Grab it, set max_active accordingly and add the new
* workqueue to workqueues list.
*/
spin_lock(&workqueue_lock);
if (workqueue_freezing && wq->flags & WQ_FREEZABLE)
for_each_pwq_cpu(cpu, wq)
get_pwq(cpu, wq)->max_active = 0;
list_add(&wq->list, &workqueues);
spin_unlock(&workqueue_lock);
return wq;
err:
if (wq) {
free_pwqs(wq);
free_mayday_mask(wq->mayday_mask);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
kfree(wq->rescuer);
kfree(wq);
}
return NULL;
}
EXPORT_SYMBOL_GPL(__alloc_workqueue_key);
/**
* destroy_workqueue - safely terminate a workqueue
* @wq: target workqueue
*
* Safely destroy a workqueue. All work currently pending will be done first.
*/
void destroy_workqueue(struct workqueue_struct *wq)
{
unsigned int cpu;
/* drain it before proceeding with destruction */
drain_workqueue(wq);
/*
* wq list is used to freeze wq, remove from list after
* flushing is complete in case freeze races us.
*/
spin_lock(&workqueue_lock);
list_del(&wq->list);
spin_unlock(&workqueue_lock);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/* sanity check */
for_each_pwq_cpu(cpu, wq) {
struct pool_workqueue *pwq = get_pwq(cpu, wq);
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
int i;
for (i = 0; i < WORK_NR_COLORS; i++)
BUG_ON(pwq->nr_in_flight[i]);
BUG_ON(pwq->nr_active);
BUG_ON(!list_empty(&pwq->delayed_works));
workqueue: reimplement workqueue flushing using color coded works Reimplement workqueue flushing using color coded works. wq has the current work color which is painted on the works being issued via cwqs. Flushing a workqueue is achieved by advancing the current work colors of cwqs and waiting for all the works which have any of the previous colors to drain. Currently there are 16 possible colors, one is reserved for no color and 15 colors are useable allowing 14 concurrent flushes. When color space gets full, flush attempts are batched up and processed together when color frees up, so even with many concurrent flushers, the new implementation won't build up huge queue of flushers which has to be processed one after another. Only works which are queued via __queue_work() are colored. Works which are directly put on queue using insert_work() use NO_COLOR and don't participate in workqueue flushing. Currently only works used for work-specific flush fall in this category. This new implementation leaves only cleanup_workqueue_thread() as the user of flush_cpu_workqueue(). Just make its users use flush_workqueue() and kthread_stop() directly and kill cleanup_workqueue_thread(). As workqueue flushing doesn't use barrier request anymore, the comment describing the complex synchronization around it in cleanup_workqueue_thread() is removed together with the function. This new implementation is to allow having and sharing multiple workers per cpu. Please note that one more bit is reserved for a future work flag by this patch. This is to avoid shifting bits and updating comments later. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:11 +08:00
}
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
if (wq->flags & WQ_RESCUER) {
kthread_stop(wq->rescuer->task);
free_mayday_mask(wq->mayday_mask);
kfree(wq->rescuer);
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
}
free_pwqs(wq);
kfree(wq);
}
EXPORT_SYMBOL_GPL(destroy_workqueue);
/**
* pwq_set_max_active - adjust max_active of a pwq
* @pwq: target pool_workqueue
* @max_active: new max_active value.
*
* Set @pwq->max_active to @max_active and activate delayed works if
* increased.
*
* CONTEXT:
* spin_lock_irq(pool->lock).
*/
static void pwq_set_max_active(struct pool_workqueue *pwq, int max_active)
{
pwq->max_active = max_active;
while (!list_empty(&pwq->delayed_works) &&
pwq->nr_active < pwq->max_active)
pwq_activate_first_delayed(pwq);
}
/**
* workqueue_set_max_active - adjust max_active of a workqueue
* @wq: target workqueue
* @max_active: new max_active value.
*
* Set max_active of @wq to @max_active.
*
* CONTEXT:
* Don't call from IRQ context.
*/
void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
{
unsigned int cpu;
max_active = wq_clamp_max_active(max_active, wq->flags, wq->name);
spin_lock(&workqueue_lock);
wq->saved_max_active = max_active;
for_each_pwq_cpu(cpu, wq) {
struct pool_workqueue *pwq = get_pwq(cpu, wq);
struct worker_pool *pool = pwq->pool;
spin_lock_irq(&pool->lock);
if (!(wq->flags & WQ_FREEZABLE) ||
!(pool->flags & POOL_FREEZING))
pwq_set_max_active(pwq, max_active);
spin_unlock_irq(&pool->lock);
}
spin_unlock(&workqueue_lock);
}
EXPORT_SYMBOL_GPL(workqueue_set_max_active);
/**
* workqueue_congested - test whether a workqueue is congested
* @cpu: CPU in question
* @wq: target workqueue
*
* Test whether @wq's cpu workqueue for @cpu is congested. There is
* no synchronization around this function and the test result is
* unreliable and only useful as advisory hints or for debugging.
*
* RETURNS:
* %true if congested, %false otherwise.
*/
bool workqueue_congested(unsigned int cpu, struct workqueue_struct *wq)
{
struct pool_workqueue *pwq = get_pwq(cpu, wq);
return !list_empty(&pwq->delayed_works);
}
EXPORT_SYMBOL_GPL(workqueue_congested);
/**
* work_busy - test whether a work is currently pending or running
* @work: the work to be tested
*
* Test whether @work is currently pending or running. There is no
* synchronization around this function and the test result is
* unreliable and only useful as advisory hints or for debugging.
*
* RETURNS:
* OR'd bitmask of WORK_BUSY_* bits.
*/
unsigned int work_busy(struct work_struct *work)
{
struct worker_pool *pool = get_work_pool(work);
unsigned long flags;
unsigned int ret = 0;
if (work_pending(work))
ret |= WORK_BUSY_PENDING;
if (pool) {
spin_lock_irqsave(&pool->lock, flags);
if (find_worker_executing_work(pool, work))
ret |= WORK_BUSY_RUNNING;
spin_unlock_irqrestore(&pool->lock, flags);
}
return ret;
}
EXPORT_SYMBOL_GPL(work_busy);
/*
* CPU hotplug.
*
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* There are two challenges in supporting CPU hotplug. Firstly, there
* are a lot of assumptions on strong associations among work, pwq and
* pool which make migrating pending and scheduled works very
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* difficult to implement without impacting hot paths. Secondly,
* worker pools serve mix of short, long and very long running works making
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
* blocked draining impractical.
*
* This is solved by allowing the pools to be disassociated from the CPU
* running as an unbound one and allowing it to be reattached later if the
* cpu comes back online.
*/
static void wq_unbind_fn(struct work_struct *work)
{
int cpu = smp_processor_id();
struct worker_pool *pool;
struct worker *worker;
int i;
for_each_std_worker_pool(pool, cpu) {
BUG_ON(cpu != smp_processor_id());
mutex_lock(&pool->assoc_mutex);
spin_lock_irq(&pool->lock);
/*
* We've claimed all manager positions. Make all workers
* unbound and set DISASSOCIATED. Before this, all workers
* except for the ones which are still executing works from
* before the last CPU down must be on the cpu. After
* this, they may become diasporas.
*/
list_for_each_entry(worker, &pool->idle_list, entry)
worker->flags |= WORKER_UNBOUND;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:06:00 +08:00
for_each_busy_worker(worker, i, pool)
worker->flags |= WORKER_UNBOUND;
pool->flags |= POOL_DISASSOCIATED;
spin_unlock_irq(&pool->lock);
mutex_unlock(&pool->assoc_mutex);
}
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/*
* Call schedule() so that we cross rq->lock and thus can guarantee
* sched callbacks see the %WORKER_UNBOUND flag. This is necessary
* as scheduler callbacks may be invoked from other cpus.
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
*/
schedule();
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/*
* Sched callbacks are disabled now. Zap nr_running. After this,
* nr_running stays zero and need_more_worker() and keep_working()
* are always true as long as the worklist is not empty. Pools on
* @cpu now behave as unbound (in terms of concurrency management)
* pools which are served by workers tied to the CPU.
*
* On return from this function, the current worker would trigger
* unbound chain execution of pending work items if other workers
* didn't already.
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
*/
for_each_std_worker_pool(pool, cpu)
atomic_set(&pool->nr_running, 0);
}
/*
* Workqueues should be brought up before normal priority CPU notifiers.
* This will be registered high priority CPU notifier.
*/
static int __cpuinit workqueue_cpu_up_callback(struct notifier_block *nfb,
unsigned long action,
void *hcpu)
{
unsigned int cpu = (unsigned long)hcpu;
struct worker_pool *pool;
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_UP_PREPARE:
for_each_std_worker_pool(pool, cpu) {
struct worker *worker;
if (pool->nr_workers)
continue;
worker = create_worker(pool);
if (!worker)
return NOTIFY_BAD;
spin_lock_irq(&pool->lock);
start_worker(worker);
spin_unlock_irq(&pool->lock);
}
break;
case CPU_DOWN_FAILED:
case CPU_ONLINE:
for_each_std_worker_pool(pool, cpu) {
mutex_lock(&pool->assoc_mutex);
spin_lock_irq(&pool->lock);
pool->flags &= ~POOL_DISASSOCIATED;
rebind_workers(pool);
spin_unlock_irq(&pool->lock);
mutex_unlock(&pool->assoc_mutex);
}
break;
}
workqueue: perform cpu down operations from low priority cpu_notifier() Currently, all workqueue cpu hotplug operations run off CPU_PRI_WORKQUEUE which is higher than normal notifiers. This is to ensure that workqueue is up and running while bringing up a CPU before other notifiers try to use workqueue on the CPU. Per-cpu workqueues are supposed to remain working and bound to the CPU for normal CPU_DOWN_PREPARE notifiers. This holds mostly true even with workqueue offlining running with higher priority because workqueue CPU_DOWN_PREPARE only creates a bound trustee thread which runs the per-cpu workqueue without concurrency management without explicitly detaching the existing workers. However, if the trustee needs to create new workers, it creates unbound workers which may wander off to other CPUs while CPU_DOWN_PREPARE notifiers are in progress. Furthermore, if the CPU down is cancelled, the per-CPU workqueue may end up with workers which aren't bound to the CPU. While reliably reproducible with a convoluted artificial test-case involving scheduling and flushing CPU burning work items from CPU down notifiers, this isn't very likely to happen in the wild, and, even when it happens, the effects are likely to be hidden by the following successful CPU down. Fix it by using different priorities for up and down notifiers - high priority for up operations and low priority for down operations. Workqueue cpu hotplug operations will soon go through further cleanup. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: stable@vger.kernel.org Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:26 +08:00
return NOTIFY_OK;
}
/*
* Workqueues should be brought down after normal priority CPU notifiers.
* This will be registered as low priority CPU notifier.
*/
static int __cpuinit workqueue_cpu_down_callback(struct notifier_block *nfb,
workqueue: perform cpu down operations from low priority cpu_notifier() Currently, all workqueue cpu hotplug operations run off CPU_PRI_WORKQUEUE which is higher than normal notifiers. This is to ensure that workqueue is up and running while bringing up a CPU before other notifiers try to use workqueue on the CPU. Per-cpu workqueues are supposed to remain working and bound to the CPU for normal CPU_DOWN_PREPARE notifiers. This holds mostly true even with workqueue offlining running with higher priority because workqueue CPU_DOWN_PREPARE only creates a bound trustee thread which runs the per-cpu workqueue without concurrency management without explicitly detaching the existing workers. However, if the trustee needs to create new workers, it creates unbound workers which may wander off to other CPUs while CPU_DOWN_PREPARE notifiers are in progress. Furthermore, if the CPU down is cancelled, the per-CPU workqueue may end up with workers which aren't bound to the CPU. While reliably reproducible with a convoluted artificial test-case involving scheduling and flushing CPU burning work items from CPU down notifiers, this isn't very likely to happen in the wild, and, even when it happens, the effects are likely to be hidden by the following successful CPU down. Fix it by using different priorities for up and down notifiers - high priority for up operations and low priority for down operations. Workqueue cpu hotplug operations will soon go through further cleanup. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: stable@vger.kernel.org Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:26 +08:00
unsigned long action,
void *hcpu)
{
unsigned int cpu = (unsigned long)hcpu;
struct work_struct unbind_work;
workqueue: perform cpu down operations from low priority cpu_notifier() Currently, all workqueue cpu hotplug operations run off CPU_PRI_WORKQUEUE which is higher than normal notifiers. This is to ensure that workqueue is up and running while bringing up a CPU before other notifiers try to use workqueue on the CPU. Per-cpu workqueues are supposed to remain working and bound to the CPU for normal CPU_DOWN_PREPARE notifiers. This holds mostly true even with workqueue offlining running with higher priority because workqueue CPU_DOWN_PREPARE only creates a bound trustee thread which runs the per-cpu workqueue without concurrency management without explicitly detaching the existing workers. However, if the trustee needs to create new workers, it creates unbound workers which may wander off to other CPUs while CPU_DOWN_PREPARE notifiers are in progress. Furthermore, if the CPU down is cancelled, the per-CPU workqueue may end up with workers which aren't bound to the CPU. While reliably reproducible with a convoluted artificial test-case involving scheduling and flushing CPU burning work items from CPU down notifiers, this isn't very likely to happen in the wild, and, even when it happens, the effects are likely to be hidden by the following successful CPU down. Fix it by using different priorities for up and down notifiers - high priority for up operations and low priority for down operations. Workqueue cpu hotplug operations will soon go through further cleanup. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: stable@vger.kernel.org Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:26 +08:00
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_DOWN_PREPARE:
/* unbinding should happen on the local CPU */
INIT_WORK_ONSTACK(&unbind_work, wq_unbind_fn);
queue_work_on(cpu, system_highpri_wq, &unbind_work);
flush_work(&unbind_work);
break;
workqueue: perform cpu down operations from low priority cpu_notifier() Currently, all workqueue cpu hotplug operations run off CPU_PRI_WORKQUEUE which is higher than normal notifiers. This is to ensure that workqueue is up and running while bringing up a CPU before other notifiers try to use workqueue on the CPU. Per-cpu workqueues are supposed to remain working and bound to the CPU for normal CPU_DOWN_PREPARE notifiers. This holds mostly true even with workqueue offlining running with higher priority because workqueue CPU_DOWN_PREPARE only creates a bound trustee thread which runs the per-cpu workqueue without concurrency management without explicitly detaching the existing workers. However, if the trustee needs to create new workers, it creates unbound workers which may wander off to other CPUs while CPU_DOWN_PREPARE notifiers are in progress. Furthermore, if the CPU down is cancelled, the per-CPU workqueue may end up with workers which aren't bound to the CPU. While reliably reproducible with a convoluted artificial test-case involving scheduling and flushing CPU burning work items from CPU down notifiers, this isn't very likely to happen in the wild, and, even when it happens, the effects are likely to be hidden by the following successful CPU down. Fix it by using different priorities for up and down notifiers - high priority for up operations and low priority for down operations. Workqueue cpu hotplug operations will soon go through further cleanup. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: stable@vger.kernel.org Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:26 +08:00
}
return NOTIFY_OK;
}
#ifdef CONFIG_SMP
struct work_for_cpu {
struct work_struct work;
long (*fn)(void *);
void *arg;
long ret;
};
static void work_for_cpu_fn(struct work_struct *work)
{
struct work_for_cpu *wfc = container_of(work, struct work_for_cpu, work);
wfc->ret = wfc->fn(wfc->arg);
}
/**
* work_on_cpu - run a function in user context on a particular cpu
* @cpu: the cpu to run on
* @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.
*/
long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
{
struct work_for_cpu wfc = { .fn = fn, .arg = arg };
INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn);
schedule_work_on(cpu, &wfc.work);
flush_work(&wfc.work);
return wfc.ret;
}
EXPORT_SYMBOL_GPL(work_on_cpu);
#endif /* CONFIG_SMP */
#ifdef CONFIG_FREEZER
/**
* freeze_workqueues_begin - begin freezing workqueues
*
* Start freezing workqueues. After this function returns, all freezable
* workqueues will queue new works to their frozen_works list instead of
* pool->worklist.
*
* CONTEXT:
* Grabs and releases workqueue_lock and pool->lock's.
*/
void freeze_workqueues_begin(void)
{
unsigned int cpu;
spin_lock(&workqueue_lock);
BUG_ON(workqueue_freezing);
workqueue_freezing = true;
for_each_wq_cpu(cpu) {
struct worker_pool *pool;
struct workqueue_struct *wq;
for_each_std_worker_pool(pool, cpu) {
spin_lock_irq(&pool->lock);
WARN_ON_ONCE(pool->flags & POOL_FREEZING);
pool->flags |= POOL_FREEZING;
list_for_each_entry(wq, &workqueues, list) {
struct pool_workqueue *pwq = get_pwq(cpu, wq);
if (pwq && pwq->pool == pool &&
(wq->flags & WQ_FREEZABLE))
pwq->max_active = 0;
}
spin_unlock_irq(&pool->lock);
}
}
spin_unlock(&workqueue_lock);
}
/**
* freeze_workqueues_busy - are freezable workqueues still busy?
*
* Check whether freezing is complete. This function must be called
* between freeze_workqueues_begin() and thaw_workqueues().
*
* CONTEXT:
* Grabs and releases workqueue_lock.
*
* RETURNS:
* %true if some freezable workqueues are still busy. %false if freezing
* is complete.
*/
bool freeze_workqueues_busy(void)
{
unsigned int cpu;
bool busy = false;
spin_lock(&workqueue_lock);
BUG_ON(!workqueue_freezing);
for_each_wq_cpu(cpu) {
struct workqueue_struct *wq;
/*
* nr_active is monotonically decreasing. It's safe
* to peek without lock.
*/
list_for_each_entry(wq, &workqueues, list) {
struct pool_workqueue *pwq = get_pwq(cpu, wq);
if (!pwq || !(wq->flags & WQ_FREEZABLE))
continue;
BUG_ON(pwq->nr_active < 0);
if (pwq->nr_active) {
busy = true;
goto out_unlock;
}
}
}
out_unlock:
spin_unlock(&workqueue_lock);
return busy;
}
/**
* thaw_workqueues - thaw workqueues
*
* Thaw workqueues. Normal queueing is restored and all collected
* frozen works are transferred to their respective pool worklists.
*
* CONTEXT:
* Grabs and releases workqueue_lock and pool->lock's.
*/
void thaw_workqueues(void)
{
unsigned int cpu;
spin_lock(&workqueue_lock);
if (!workqueue_freezing)
goto out_unlock;
for_each_wq_cpu(cpu) {
struct worker_pool *pool;
struct workqueue_struct *wq;
for_each_std_worker_pool(pool, cpu) {
spin_lock_irq(&pool->lock);
WARN_ON_ONCE(!(pool->flags & POOL_FREEZING));
pool->flags &= ~POOL_FREEZING;
list_for_each_entry(wq, &workqueues, list) {
struct pool_workqueue *pwq = get_pwq(cpu, wq);
if (!pwq || pwq->pool != pool ||
!(wq->flags & WQ_FREEZABLE))
continue;
/* restore max_active and repopulate worklist */
pwq_set_max_active(pwq, wq->saved_max_active);
}
wake_up_worker(pool);
spin_unlock_irq(&pool->lock);
}
}
workqueue_freezing = false;
out_unlock:
spin_unlock(&workqueue_lock);
}
#endif /* CONFIG_FREEZER */
static int __init init_workqueues(void)
{
unsigned int 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);
workqueue: perform cpu down operations from low priority cpu_notifier() Currently, all workqueue cpu hotplug operations run off CPU_PRI_WORKQUEUE which is higher than normal notifiers. This is to ensure that workqueue is up and running while bringing up a CPU before other notifiers try to use workqueue on the CPU. Per-cpu workqueues are supposed to remain working and bound to the CPU for normal CPU_DOWN_PREPARE notifiers. This holds mostly true even with workqueue offlining running with higher priority because workqueue CPU_DOWN_PREPARE only creates a bound trustee thread which runs the per-cpu workqueue without concurrency management without explicitly detaching the existing workers. However, if the trustee needs to create new workers, it creates unbound workers which may wander off to other CPUs while CPU_DOWN_PREPARE notifiers are in progress. Furthermore, if the CPU down is cancelled, the per-CPU workqueue may end up with workers which aren't bound to the CPU. While reliably reproducible with a convoluted artificial test-case involving scheduling and flushing CPU burning work items from CPU down notifiers, this isn't very likely to happen in the wild, and, even when it happens, the effects are likely to be hidden by the following successful CPU down. Fix it by using different priorities for up and down notifiers - high priority for up operations and low priority for down operations. Workqueue cpu hotplug operations will soon go through further cleanup. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: stable@vger.kernel.org Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
2012-07-18 03:39:26 +08:00
cpu_notifier(workqueue_cpu_up_callback, CPU_PRI_WORKQUEUE_UP);
hotcpu_notifier(workqueue_cpu_down_callback, CPU_PRI_WORKQUEUE_DOWN);
/* initialize CPU pools */
for_each_wq_cpu(cpu) {
struct worker_pool *pool;
for_each_std_worker_pool(pool, cpu) {
spin_lock_init(&pool->lock);
pool->cpu = cpu;
pool->flags |= POOL_DISASSOCIATED;
INIT_LIST_HEAD(&pool->worklist);
INIT_LIST_HEAD(&pool->idle_list);
hash_init(pool->busy_hash);
init_timer_deferrable(&pool->idle_timer);
pool->idle_timer.function = idle_worker_timeout;
pool->idle_timer.data = (unsigned long)pool;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
setup_timer(&pool->mayday_timer, pool_mayday_timeout,
(unsigned long)pool);
mutex_init(&pool->assoc_mutex);
ida_init(&pool->worker_ida);
/* alloc pool ID */
BUG_ON(worker_pool_assign_id(pool));
}
}
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
/* create the initial worker */
for_each_online_wq_cpu(cpu) {
struct worker_pool *pool;
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
for_each_std_worker_pool(pool, cpu) {
struct worker *worker;
if (cpu != WORK_CPU_UNBOUND)
pool->flags &= ~POOL_DISASSOCIATED;
2012-07-18 03:39:27 +08:00
worker = create_worker(pool);
BUG_ON(!worker);
spin_lock_irq(&pool->lock);
start_worker(worker);
spin_unlock_irq(&pool->lock);
}
workqueue: implement concurrency managed dynamic worker pool Instead of creating a worker for each cwq and putting it into the shared pool, manage per-cpu workers dynamically. Works aren't supposed to be cpu cycle hogs and maintaining just enough concurrency to prevent work processing from stalling due to lack of processing context is optimal. gcwq keeps the number of concurrent active workers to minimum but no less. As long as there's one or more running workers on the cpu, no new worker is scheduled so that works can be processed in batch as much as possible but when the last running worker blocks, gcwq immediately schedules new worker so that the cpu doesn't sit idle while there are works to be processed. gcwq always keeps at least single idle worker around. When a new worker is necessary and the worker is the last idle one, the worker assumes the role of "manager" and manages the worker pool - ie. creates another worker. Forward-progress is guaranteed by having dedicated rescue workers for workqueues which may be necessary while creating a new worker. When the manager is having problem creating a new worker, mayday timer activates and rescue workers are summoned to the cpu and execute works which might be necessary to create new workers. Trustee is expanded to serve the role of manager while a CPU is being taken down and stays down. As no new works are supposed to be queued on a dead cpu, it just needs to drain all the existing ones. Trustee continues to try to create new workers and summon rescuers as long as there are pending works. If the CPU is brought back up while the trustee is still trying to drain the gcwq from the previous offlining, the trustee will kill all idles ones and tell workers which are still busy to rebind to the cpu, and pass control over to gcwq which assumes the manager role as necessary. Concurrency managed worker pool reduces the number of workers drastically. Only workers which are necessary to keep the processing going are created and kept. Also, it reduces cache footprint by avoiding unnecessarily switching contexts between different workers. Please note that this patch does not increase max_active of any workqueue. All workqueues can still only process one work per cpu. Signed-off-by: Tejun Heo <tj@kernel.org>
2010-06-29 16:07:14 +08:00
}
system_wq = alloc_workqueue("events", 0, 0);
system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0);
system_long_wq = alloc_workqueue("events_long", 0, 0);
system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND,
WQ_UNBOUND_MAX_ACTIVE);
system_freezable_wq = alloc_workqueue("events_freezable",
WQ_FREEZABLE, 0);
BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq ||
!system_unbound_wq || !system_freezable_wq);
return 0;
}
early_initcall(init_workqueues);