From e41e704bc4f49057fc68b643108366e6e6781aa3 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 24 Aug 2010 14:22:47 +0200 Subject: workqueue: improve destroy_workqueue() debuggability Now that the worklist is global, having works pending after wq destruction can easily lead to oops and destroy_workqueue() have several BUG_ON()s to catch these cases. Unfortunately, BUG_ON() doesn't tell much about how the work became pending after the final flush_workqueue(). This patch adds WQ_DYING which is set before the final flush begins. If a work is requested to be queued on a dying workqueue, WARN_ON_ONCE() is triggered and the request is ignored. This clearly indicates which caller is trying to queue a work on a dying workqueue and keeps the system working in most cases. Locking rule comment is updated such that the 'I' rule includes modifying the field from destruction path. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 4f9d277bcd9a..c959666eafca 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -241,6 +241,8 @@ enum { WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ + WQ_DYING = 1 << 6, /* internal: workqueue is dying */ + WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, -- cgit From 8a2e8e5dec7e29c56a46ba176c664ab6a3d04118 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 25 Aug 2010 10:33:56 +0200 Subject: workqueue: fix cwq->nr_active underflow cwq->nr_active is used to keep track of how many work items are active for the cpu workqueue, where 'active' is defined as either pending on global worklist or executing. This is used to implement the max_active limit and workqueue freezing. If a work item is queued after nr_active has already reached max_active, the work item doesn't increment nr_active and is put on the delayed queue and gets activated later as previous active work items retire. try_to_grab_pending() which is used in the cancellation path unconditionally decremented nr_active whether the work item being cancelled is currently active or delayed, so cancelling a delayed work item makes nr_active underflow. This breaks max_active enforcement and triggers BUG_ON() in destroy_workqueue() later on. This patch fixes this bug by adding a flag WORK_STRUCT_DELAYED, which is set while a work item in on the delayed list and making try_to_grab_pending() decrement nr_active iff the work item is currently active. The addition of the flag enlarges cwq alignment to 256 bytes which is getting a bit too large. It's scheduled to be reduced back to 128 bytes by merging WORK_STRUCT_PENDING and WORK_STRUCT_CWQ in the next devel cycle. Signed-off-by: Tejun Heo Reported-by: Johannes Berg --- include/linux/workqueue.h | 16 +++++++++------- kernel/workqueue.c | 30 ++++++++++++++++++++---------- 2 files changed, 29 insertions(+), 17 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index c959666eafca..f11100f96482 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -25,18 +25,20 @@ typedef void (*work_func_t)(struct work_struct *work); enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ - WORK_STRUCT_CWQ_BIT = 1, /* data points to cwq */ - WORK_STRUCT_LINKED_BIT = 2, /* next work is linked to this one */ + WORK_STRUCT_DELAYED_BIT = 1, /* work item is delayed */ + WORK_STRUCT_CWQ_BIT = 2, /* data points to cwq */ + WORK_STRUCT_LINKED_BIT = 3, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK - WORK_STRUCT_STATIC_BIT = 3, /* static initializer (debugobjects) */ - WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */ + WORK_STRUCT_STATIC_BIT = 4, /* static initializer (debugobjects) */ + WORK_STRUCT_COLOR_SHIFT = 5, /* color for workqueue flushing */ #else - WORK_STRUCT_COLOR_SHIFT = 3, /* color for workqueue flushing */ + WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */ #endif WORK_STRUCT_COLOR_BITS = 4, WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, + WORK_STRUCT_DELAYED = 1 << WORK_STRUCT_DELAYED_BIT, WORK_STRUCT_CWQ = 1 << WORK_STRUCT_CWQ_BIT, WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK @@ -59,8 +61,8 @@ enum { /* * Reserve 7 bits off of cwq pointer w/ debugobjects turned - * off. This makes cwqs aligned to 128 bytes which isn't too - * excessive while allowing 15 workqueue flush colors. + * off. This makes cwqs aligned to 256 bytes and allows 15 + * workqueue flush colors. */ WORK_STRUCT_FLAG_BITS = WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 362b50d092e2..a2dccfca03ba 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -941,6 +941,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, struct global_cwq *gcwq; struct cpu_workqueue_struct *cwq; struct list_head *worklist; + unsigned int work_flags; unsigned long flags; debug_work_activate(work); @@ -990,14 +991,17 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, BUG_ON(!list_empty(&work->entry)); cwq->nr_in_flight[cwq->work_color]++; + work_flags = work_color_to_flags(cwq->work_color); if (likely(cwq->nr_active < cwq->max_active)) { cwq->nr_active++; worklist = gcwq_determine_ins_pos(gcwq, cwq); - } else + } else { + work_flags |= WORK_STRUCT_DELAYED; worklist = &cwq->delayed_works; + } - insert_work(cwq, work, worklist, work_color_to_flags(cwq->work_color)); + insert_work(cwq, work, worklist, work_flags); spin_unlock_irqrestore(&gcwq->lock, flags); } @@ -1666,6 +1670,7 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq) struct list_head *pos = gcwq_determine_ins_pos(cwq->gcwq, cwq); move_linked_works(work, pos, NULL); + __clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work)); cwq->nr_active++; } @@ -1673,6 +1678,7 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq) * cwq_dec_nr_in_flight - decrement cwq's nr_in_flight * @cwq: cwq of interest * @color: color of work which left the queue + * @delayed: for a delayed work * * A work either has completed or is removed from pending queue, * decrement nr_in_flight of its cwq and handle workqueue flushing. @@ -1680,19 +1686,22 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq) * CONTEXT: * spin_lock_irq(gcwq->lock). */ -static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color) +static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color, + bool delayed) { /* ignore uncolored works */ if (color == WORK_NO_COLOR) return; cwq->nr_in_flight[color]--; - cwq->nr_active--; - if (!list_empty(&cwq->delayed_works)) { - /* one down, submit a delayed one */ - if (cwq->nr_active < cwq->max_active) - cwq_activate_first_delayed(cwq); + if (!delayed) { + cwq->nr_active--; + if (!list_empty(&cwq->delayed_works)) { + /* one down, submit a delayed one */ + if (cwq->nr_active < cwq->max_active) + cwq_activate_first_delayed(cwq); + } } /* is flush in progress and are we at the flushing tip? */ @@ -1823,7 +1832,7 @@ __acquires(&gcwq->lock) hlist_del_init(&worker->hentry); worker->current_work = NULL; worker->current_cwq = NULL; - cwq_dec_nr_in_flight(cwq, work_color); + cwq_dec_nr_in_flight(cwq, work_color, false); } /** @@ -2388,7 +2397,8 @@ static int try_to_grab_pending(struct work_struct *work) debug_work_deactivate(work); list_del_init(&work->entry); cwq_dec_nr_in_flight(get_work_cwq(work), - get_work_color(work)); + get_work_color(work), + *work_data_bits(work) & WORK_STRUCT_DELAYED); ret = 1; } } -- cgit From c54fce6eff197d9c57c97afbf6c9722ce434fc8f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 10 Sep 2010 16:51:36 +0200 Subject: workqueue: add documentation Update copyright notice and add Documentation/workqueue.txt. Randy Dunlap, Dave Chinner: misc fixes. Signed-off-by: Tejun Heo Reviewed-By: Florian Mickler Cc: Ingo Molnar Cc: Christoph Lameter Cc: Randy Dunlap Cc: Dave Chinner --- Documentation/workqueue.txt | 380 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/workqueue.h | 4 + kernel/workqueue.c | 27 ++-- 3 files changed, 401 insertions(+), 10 deletions(-) create mode 100644 Documentation/workqueue.txt (limited to 'include/linux/workqueue.h') diff --git a/Documentation/workqueue.txt b/Documentation/workqueue.txt new file mode 100644 index 000000000000..e4498a2872c3 --- /dev/null +++ b/Documentation/workqueue.txt @@ -0,0 +1,380 @@ + +Concurrency Managed Workqueue (cmwq) + +September, 2010 Tejun Heo + Florian Mickler + +CONTENTS + +1. Introduction +2. Why cmwq? +3. The Design +4. Application Programming Interface (API) +5. Example Execution Scenarios +6. Guidelines + + +1. Introduction + +There are many cases where an asynchronous process execution context +is needed and the workqueue (wq) API is the most commonly used +mechanism for such cases. + +When such an asynchronous execution context is needed, a work item +describing which function to execute is put on a queue. An +independent thread serves as the asynchronous execution context. The +queue is called workqueue and the thread is called worker. + +While there are work items on the workqueue the worker executes the +functions associated with the work items one after the other. When +there is no work item left on the workqueue the worker becomes idle. +When a new work item gets queued, the worker begins executing again. + + +2. Why cmwq? + +In the original wq implementation, a multi threaded (MT) wq had one +worker thread per CPU and a single threaded (ST) wq had one worker +thread system-wide. A single MT wq needed to keep around the same +number of workers as the number of CPUs. The kernel grew a lot of MT +wq users over the years and with the number of CPU cores continuously +rising, some systems saturated the default 32k PID space just booting +up. + +Although MT wq wasted a lot of resource, the level of concurrency +provided was unsatisfactory. The limitation was common to both ST and +MT wq albeit less severe on MT. Each wq maintained its own separate +worker pool. A MT wq could provide only one execution context per CPU +while a ST wq one for the whole system. Work items had to compete for +those very limited execution contexts leading to various problems +including proneness to deadlocks around the single execution context. + +The tension between the provided level of concurrency and resource +usage also forced its users to make unnecessary tradeoffs like libata +choosing to use ST wq for polling PIOs and accepting an unnecessary +limitation that no two polling PIOs can progress at the same time. As +MT wq don't provide much better concurrency, users which require +higher level of concurrency, like async or fscache, had to implement +their own thread pool. + +Concurrency Managed Workqueue (cmwq) is a reimplementation of wq with +focus on the following goals. + +* Maintain compatibility with the original workqueue API. + +* Use per-CPU unified worker pools shared by all wq to provide + flexible level of concurrency on demand without wasting a lot of + resource. + +* Automatically regulate worker pool and level of concurrency so that + the API users don't need to worry about such details. + + +3. The Design + +In order to ease the asynchronous execution of functions a new +abstraction, the work item, is introduced. + +A work item is a simple struct that holds a pointer to the function +that is to be executed asynchronously. Whenever a driver or subsystem +wants a function to be executed asynchronously it has to set up a work +item pointing to that function and queue that work item on a +workqueue. + +Special purpose threads, called worker threads, execute the functions +off of the queue, one after the other. If no work is queued, the +worker threads become idle. These worker threads are managed in so +called thread-pools. + +The cmwq design differentiates between the user-facing workqueues that +subsystems and drivers queue work items on and the backend mechanism +which manages thread-pool and processes the queued work items. + +The backend is called gcwq. There is one gcwq for each possible CPU +and one gcwq to serve work items queued on unbound workqueues. + +Subsystems and drivers can create and queue work items through special +workqueue API functions as they see fit. They can influence some +aspects of the way the work items are executed by setting flags on the +workqueue they are putting the work item on. These flags include +things like CPU locality, reentrancy, concurrency limits and more. To +get a detailed overview refer to the API description of +alloc_workqueue() below. + +When a work item is queued to a workqueue, the target gcwq is +determined according to the queue parameters and workqueue attributes +and appended on the shared worklist of the gcwq. For example, unless +specifically overridden, a work item of a bound workqueue will be +queued on the worklist of exactly that gcwq that is associated to the +CPU the issuer is running on. + +For any worker pool implementation, managing the concurrency level +(how many execution contexts are active) is an important issue. cmwq +tries to keep the concurrency at a minimal but sufficient level. +Minimal to save resources and sufficient in that the system is used at +its full capacity. + +Each gcwq bound to an actual CPU implements concurrency management by +hooking into the scheduler. The gcwq is notified whenever an active +worker wakes up or sleeps and keeps track of the number of the +currently runnable workers. Generally, work items are not expected to +hog a CPU and consume many cycles. That means maintaining just enough +concurrency to prevent work processing from stalling should be +optimal. As long as there are one or more runnable workers on the +CPU, the gcwq doesn't start execution of a new work, but, when the +last running worker goes to sleep, it immediately schedules a new +worker so that the CPU doesn't sit idle while there are pending work +items. This allows using a minimal number of workers without losing +execution bandwidth. + +Keeping idle workers around doesn't cost other than the memory space +for kthreads, so cmwq holds onto idle ones for a while before killing +them. + +For an unbound wq, the above concurrency management doesn't apply and +the gcwq for the pseudo unbound CPU tries to start executing all work +items as soon as possible. The responsibility of regulating +concurrency level is on the users. There is also a flag to mark a +bound wq to ignore the concurrency management. Please refer to the +API section for details. + +Forward progress guarantee relies on that workers can be created when +more execution contexts are necessary, which in turn is guaranteed +through the use of rescue workers. All work items which might be used +on code paths that handle memory reclaim are required to be queued on +wq's that have a rescue-worker reserved for execution under memory +pressure. Else it is possible that the thread-pool deadlocks waiting +for execution contexts to free up. + + +4. Application Programming Interface (API) + +alloc_workqueue() allocates a wq. The original create_*workqueue() +functions are deprecated and scheduled for removal. alloc_workqueue() +takes three arguments - @name, @flags and @max_active. @name is the +name of the wq and also used as the name of the rescuer thread if +there is one. + +A wq no longer manages execution resources but serves as a domain for +forward progress guarantee, flush and work item attributes. @flags +and @max_active control how work items are assigned execution +resources, scheduled and executed. + +@flags: + + WQ_NON_REENTRANT + + By default, a wq guarantees non-reentrance only on the same + CPU. A work item may not be executed concurrently on the same + CPU by multiple workers but is allowed to be executed + concurrently on multiple CPUs. This flag makes sure + non-reentrance is enforced across all CPUs. Work items queued + to a non-reentrant wq are guaranteed to be executed by at most + one worker system-wide at any given time. + + WQ_UNBOUND + + Work items queued to an unbound wq are served by a special + gcwq which hosts workers which are not bound to any specific + CPU. This makes the wq behave as a simple execution context + provider without concurrency management. The unbound gcwq + tries to start execution of work items as soon as possible. + Unbound wq sacrifices locality but is useful for the following + cases. + + * Wide fluctuation in the concurrency level requirement is + expected and using bound wq may end up creating large number + of mostly unused workers across different CPUs as the issuer + hops through different CPUs. + + * Long running CPU intensive workloads which can be better + managed by the system scheduler. + + WQ_FREEZEABLE + + A freezeable wq participates in the freeze phase of the system + suspend operations. Work items on the wq are drained and no + new work item starts execution until thawed. + + WQ_RESCUER + + All wq which might be used in the memory reclaim paths _MUST_ + have this flag set. This reserves one worker exclusively for + the execution of this wq under memory pressure. + + WQ_HIGHPRI + + Work items of a highpri wq are queued at the head of the + worklist of the target gcwq and start execution regardless of + the current concurrency level. In other words, highpri work + items will always start execution as soon as execution + resource is available. + + Ordering among highpri work items is preserved - a highpri + work item queued after another highpri work item will start + execution after the earlier highpri work item starts. + + Although highpri work items are not held back by other + runnable work items, they still contribute to the concurrency + level. Highpri work items in runnable state will prevent + non-highpri work items from starting execution. + + This flag is meaningless for unbound wq. + + WQ_CPU_INTENSIVE + + Work items of a CPU intensive wq do not contribute to the + concurrency level. In other words, runnable CPU intensive + work items will not prevent other work items from starting + execution. This is useful for bound work items which are + expected to hog CPU cycles so that their execution is + regulated by the system scheduler. + + Although CPU intensive work items don't contribute to the + concurrency level, start of their executions is still + regulated by the concurrency management and runnable + non-CPU-intensive work items can delay execution of CPU + intensive work items. + + This flag is meaningless for unbound wq. + + WQ_HIGHPRI | WQ_CPU_INTENSIVE + + This combination makes the wq avoid interaction with + concurrency management completely and behave as a simple + per-CPU execution context provider. Work items queued on a + highpri CPU-intensive wq start execution as soon as resources + are available and don't affect execution of other work items. + +@max_active: + +@max_active determines the maximum number of execution contexts per +CPU which can be assigned to the work items of a wq. For example, +with @max_active of 16, at most 16 work items of the wq can be +executing at the same time per CPU. + +Currently, for a bound wq, the maximum limit for @max_active is 512 +and the default value used when 0 is specified is 256. For an unbound +wq, the limit is higher of 512 and 4 * num_possible_cpus(). These +values are chosen sufficiently high such that they are not the +limiting factor while providing protection in runaway cases. + +The number of active work items of a wq is usually regulated by the +users of the wq, more specifically, by how many work items the users +may queue at the same time. Unless there is a specific need for +throttling the number of active work items, specifying '0' is +recommended. + +Some users depend on the strict execution ordering of ST wq. The +combination of @max_active of 1 and WQ_UNBOUND is used to achieve this +behavior. Work items on such wq are always queued to the unbound gcwq +and only one work item can be active at any given time thus achieving +the same ordering property as ST wq. + + +5. Example Execution Scenarios + +The following example execution scenarios try to illustrate how cmwq +behave under different configurations. + + Work items w0, w1, w2 are queued to a bound wq q0 on the same CPU. + w0 burns CPU for 5ms then sleeps for 10ms then burns CPU for 5ms + again before finishing. w1 and w2 burn CPU for 5ms then sleep for + 10ms. + +Ignoring all other tasks, works and processing overhead, and assuming +simple FIFO scheduling, the following is one highly simplified version +of possible sequences of events with the original wq. + + TIME IN MSECS EVENT + 0 w0 starts and burns CPU + 5 w0 sleeps + 15 w0 wakes up and burns CPU + 20 w0 finishes + 20 w1 starts and burns CPU + 25 w1 sleeps + 35 w1 wakes up and finishes + 35 w2 starts and burns CPU + 40 w2 sleeps + 50 w2 wakes up and finishes + +And with cmwq with @max_active >= 3, + + TIME IN MSECS EVENT + 0 w0 starts and burns CPU + 5 w0 sleeps + 5 w1 starts and burns CPU + 10 w1 sleeps + 10 w2 starts and burns CPU + 15 w2 sleeps + 15 w0 wakes up and burns CPU + 20 w0 finishes + 20 w1 wakes up and finishes + 25 w2 wakes up and finishes + +If @max_active == 2, + + TIME IN MSECS EVENT + 0 w0 starts and burns CPU + 5 w0 sleeps + 5 w1 starts and burns CPU + 10 w1 sleeps + 15 w0 wakes up and burns CPU + 20 w0 finishes + 20 w1 wakes up and finishes + 20 w2 starts and burns CPU + 25 w2 sleeps + 35 w2 wakes up and finishes + +Now, let's assume w1 and w2 are queued to a different wq q1 which has +WQ_HIGHPRI set, + + TIME IN MSECS EVENT + 0 w1 and w2 start and burn CPU + 5 w1 sleeps + 10 w2 sleeps + 10 w0 starts and burns CPU + 15 w0 sleeps + 15 w1 wakes up and finishes + 20 w2 wakes up and finishes + 25 w0 wakes up and burns CPU + 30 w0 finishes + +If q1 has WQ_CPU_INTENSIVE set, + + TIME IN MSECS EVENT + 0 w0 starts and burns CPU + 5 w0 sleeps + 5 w1 and w2 start and burn CPU + 10 w1 sleeps + 15 w2 sleeps + 15 w0 wakes up and burns CPU + 20 w0 finishes + 20 w1 wakes up and finishes + 25 w2 wakes up and finishes + + +6. Guidelines + +* Do not forget to use WQ_RESCUER if a wq may process work items which + are used during memory reclaim. Each wq with WQ_RESCUER set has one + rescuer thread reserved for it. If there is dependency among + multiple work items used during memory reclaim, they should be + queued to separate wq each with WQ_RESCUER. + +* Unless strict ordering is required, there is no need to use ST wq. + +* Unless there is a specific need, using 0 for @max_active is + recommended. In most use cases, concurrency level usually stays + well under the default limit. + +* A wq serves as a domain for forward progress guarantee (WQ_RESCUER), + flush and work item attributes. Work items which are not involved + in memory reclaim and don't need to be flushed as a part of a group + of work items, and don't require any special attribute, can use one + of the system wq. There is no difference in execution + characteristics between using a dedicated wq and a system wq. + +* Unless work items are expected to consume a huge amount of CPU + cycles, using a bound wq is usually beneficial due to the increased + level of locality in wq operations and work item execution. diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index f11100f96482..25e02c941bac 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -235,6 +235,10 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } #define work_clear_pending(work) \ clear_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) +/* + * Workqueue flags and constants. For details, please refer to + * Documentation/workqueue.txt. + */ enum { WQ_NON_REENTRANT = 1 << 0, /* guarantee non-reentrance */ WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 727f24e563ae..f77afd939229 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1,19 +1,26 @@ /* - * linux/kernel/workqueue.c + * kernel/workqueue.c - generic async execution with shared worker pool * - * Generic mechanism for defining kernel helper threads for running - * arbitrary tasks in process context. + * Copyright (C) 2002 Ingo Molnar * - * Started by Ingo Molnar, Copyright (C) 2002 + * Derived from the taskqueue/keventd code by: + * David Woodhouse + * Andrew Morton + * Kai Petzke + * Theodore Ts'o * - * Derived from the taskqueue/keventd code by: + * Made to use alloc_percpu by Christoph Lameter. * - * David Woodhouse - * Andrew Morton - * Kai Petzke - * Theodore Ts'o + * Copyright (C) 2010 SUSE Linux Products GmbH + * Copyright (C) 2010 Tejun Heo * - * Made to use alloc_percpu by Christoph Lameter. + * 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 -- cgit From 81dcaf6516d8bbd75b894862c8ae7bba04380cfe Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 16 Sep 2010 10:17:35 +0200 Subject: workqueue: implement alloc_ordered_workqueue() alloc_ordered_workqueue() creates a workqueue which processes each work itemp one by one in the queued order. This will be used to replace create_freezeable_workqueue() and create_singlethread_workqueue(). Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 25e02c941bac..07c48925a8fc 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -306,6 +306,24 @@ __alloc_workqueue_key(const char *name, unsigned int flags, int max_active, __alloc_workqueue_key((name), (flags), (max_active), NULL, NULL) #endif +/** + * alloc_ordered_workqueue - allocate an ordered workqueue + * @name: name of the workqueue + * @flags: WQ_* flags (only WQ_FREEZEABLE and WQ_RESCUER are meaningful) + * + * Allocate an ordered workqueue. An ordered workqueue executes at + * most one work item at any given time in the queued order. They are + * implemented as unbound workqueues with @max_active of one. + * + * RETURNS: + * Pointer to the allocated workqueue on success, %NULL on failure. + */ +static inline struct workqueue_struct * +alloc_ordered_workqueue(const char *name, unsigned int flags) +{ + return alloc_workqueue(name, WQ_UNBOUND | flags, 1); +} + #define create_workqueue(name) \ alloc_workqueue((name), WQ_RESCUER, 1) #define create_freezeable_workqueue(name) \ -- cgit From 401a8d048eadfbe1b1c1bf53d3b614fcc894c61a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 16 Sep 2010 10:36:00 +0200 Subject: workqueue: cleanup flush/cancel functions Make the following cleanup changes. * Relocate flush/cancel function prototypes and definitions. * Relocate wait_on_cpu_work() and wait_on_work() before try_to_grab_pending(). These will be used to implement flush_work_sync(). * Make all flush/cancel functions return bool instead of int. * Update wait_on_cpu_work() and wait_on_work() to return %true if they actually waited. * Add / update comments. This patch doesn't cause any functional changes. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 18 ++--- kernel/workqueue.c | 175 +++++++++++++++++++++++++--------------------- 2 files changed, 103 insertions(+), 90 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 07c48925a8fc..bb9b683ea6fa 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -343,7 +343,6 @@ extern int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, extern void flush_workqueue(struct workqueue_struct *wq); extern void flush_scheduled_work(void); -extern void flush_delayed_work(struct delayed_work *work); extern int schedule_work(struct work_struct *work); extern int schedule_work_on(int cpu, struct work_struct *work); @@ -355,8 +354,11 @@ extern int keventd_up(void); int execute_in_process_context(work_func_t fn, struct execute_work *); -extern int flush_work(struct work_struct *work); -extern int cancel_work_sync(struct work_struct *work); +extern bool flush_work(struct work_struct *work); +extern bool cancel_work_sync(struct work_struct *work); + +extern bool flush_delayed_work(struct delayed_work *dwork); +extern bool cancel_delayed_work_sync(struct delayed_work *dwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, int max_active); @@ -370,9 +372,9 @@ extern unsigned int work_busy(struct work_struct *work); * it returns 1 and the work doesn't re-arm itself. Run flush_workqueue() or * cancel_work_sync() to wait on it. */ -static inline int cancel_delayed_work(struct delayed_work *work) +static inline bool cancel_delayed_work(struct delayed_work *work) { - int ret; + bool ret; ret = del_timer_sync(&work->timer); if (ret) @@ -385,9 +387,9 @@ static inline int cancel_delayed_work(struct delayed_work *work) * if it returns 0 the timer function may be running and the queueing is in * progress. */ -static inline int __cancel_delayed_work(struct delayed_work *work) +static inline bool __cancel_delayed_work(struct delayed_work *work) { - int ret; + bool ret; ret = del_timer(&work->timer); if (ret) @@ -395,8 +397,6 @@ static inline int __cancel_delayed_work(struct delayed_work *work) return ret; } -extern int cancel_delayed_work_sync(struct delayed_work *work); - /* Obsolete. use cancel_delayed_work_sync() */ static inline void cancel_rearming_delayed_workqueue(struct workqueue_struct *wq, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index f77afd939229..1240b9d94b03 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2327,16 +2327,24 @@ out_unlock: EXPORT_SYMBOL_GPL(flush_workqueue); /** - * flush_work - block until a work_struct's callback has terminated - * @work: the work which is to be flushed + * flush_work - wait for a work to finish executing the last queueing instance + * @work: the work to flush * - * Returns false if @work has already terminated. + * Wait until @work has finished execution. This function considers + * only the last queueing instance of @work. If @work has been + * enqueued across different CPUs on a non-reentrant workqueue or on + * multiple workqueues, @work might still be executing on return on + * some of the CPUs from earlier queueing. * - * It is expected that, prior to calling flush_work(), the caller has - * arranged for the work to not be requeued, otherwise it doesn't make - * sense to use this function. + * If @work was queued only on a non-reentrant, ordered or unbound + * workqueue, @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. */ -int flush_work(struct work_struct *work) +bool flush_work(struct work_struct *work) { struct worker *worker = NULL; struct global_cwq *gcwq; @@ -2374,13 +2382,49 @@ int flush_work(struct work_struct *work) wait_for_completion(&barr.done); destroy_work_on_stack(&barr.work); - return 1; + return true; already_gone: spin_unlock_irq(&gcwq->lock); - return 0; + return false; } EXPORT_SYMBOL_GPL(flush_work); +static bool wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work) +{ + struct wq_barrier barr; + struct worker *worker; + + spin_lock_irq(&gcwq->lock); + + worker = find_worker_executing_work(gcwq, work); + if (unlikely(worker)) + insert_wq_barrier(worker->current_cwq, &barr, work, worker); + + spin_unlock_irq(&gcwq->lock); + + if (unlikely(worker)) { + wait_for_completion(&barr.done); + destroy_work_on_stack(&barr.work); + return true; + } else + return false; +} + +static bool wait_on_work(struct work_struct *work) +{ + bool ret = false; + int cpu; + + might_sleep(); + + lock_map_acquire(&work->lockdep_map); + lock_map_release(&work->lockdep_map); + + for_each_gcwq_cpu(cpu) + ret |= wait_on_cpu_work(get_gcwq(cpu), work); + return ret; +} + /* * Upon a successful return (>= 0), the caller "owns" WORK_STRUCT_PENDING bit, * so this work can't be re-armed in any way. @@ -2423,39 +2467,7 @@ static int try_to_grab_pending(struct work_struct *work) return ret; } -static void wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work) -{ - struct wq_barrier barr; - struct worker *worker; - - spin_lock_irq(&gcwq->lock); - - worker = find_worker_executing_work(gcwq, work); - if (unlikely(worker)) - insert_wq_barrier(worker->current_cwq, &barr, work, worker); - - spin_unlock_irq(&gcwq->lock); - - if (unlikely(worker)) { - wait_for_completion(&barr.done); - destroy_work_on_stack(&barr.work); - } -} - -static void wait_on_work(struct work_struct *work) -{ - int cpu; - - might_sleep(); - - lock_map_acquire(&work->lockdep_map); - lock_map_release(&work->lockdep_map); - - for_each_gcwq_cpu(cpu) - wait_on_cpu_work(get_gcwq(cpu), work); -} - -static int __cancel_work_timer(struct work_struct *work, +static bool __cancel_work_timer(struct work_struct *work, struct timer_list* timer) { int ret; @@ -2472,42 +2484,60 @@ static int __cancel_work_timer(struct work_struct *work, } /** - * cancel_work_sync - block until a work_struct's callback has terminated - * @work: the work which is to be flushed - * - * Returns true if @work was pending. + * cancel_work_sync - cancel a work and wait for it to finish + * @work: the work to cancel * - * cancel_work_sync() will cancel the work if it is queued. If the work's - * callback appears to be running, cancel_work_sync() will block until it - * has completed. + * 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. * - * It is possible to use this function if the work re-queues itself. It can - * cancel the work even if it migrates to another workqueue, however in that - * case it only guarantees that work->func() has completed on the last queued - * workqueue. - * - * cancel_work_sync(&delayed_work->work) should be used only if ->timer is not - * pending, otherwise it goes into a busy-wait loop until the timer expires. + * cancel_work_sync(&delayed_work->work) must not be used for + * delayed_work's. Use cancel_delayed_work_sync() instead. * - * The caller must ensure that workqueue_struct on which this work was last + * The caller must ensure that the workqueue on which @work was last * queued can't be destroyed before this function returns. + * + * RETURNS: + * %true if @work was pending, %false otherwise. */ -int cancel_work_sync(struct work_struct *work) +bool cancel_work_sync(struct work_struct *work) { return __cancel_work_timer(work, NULL); } EXPORT_SYMBOL_GPL(cancel_work_sync); /** - * cancel_delayed_work_sync - reliably kill off a delayed work. - * @dwork: the delayed work struct + * flush_delayed_work - wait for a dwork to finish executing the last queueing + * @dwork: the delayed work to flush + * + * 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. + */ +bool flush_delayed_work(struct delayed_work *dwork) +{ + if (del_timer_sync(&dwork->timer)) + __queue_work(raw_smp_processor_id(), + get_work_cwq(&dwork->work)->wq, &dwork->work); + return flush_work(&dwork->work); +} +EXPORT_SYMBOL(flush_delayed_work); + +/** + * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish + * @dwork: the delayed work cancel * - * Returns true if @dwork was pending. + * This is cancel_work_sync() for delayed works. * - * It is possible to use this function if @dwork rearms itself via queue_work() - * or queue_delayed_work(). See also the comment for cancel_work_sync(). + * RETURNS: + * %true if @dwork was pending, %false otherwise. */ -int cancel_delayed_work_sync(struct delayed_work *dwork) +bool cancel_delayed_work_sync(struct delayed_work *dwork) { return __cancel_work_timer(&dwork->work, &dwork->timer); } @@ -2558,23 +2588,6 @@ int schedule_delayed_work(struct delayed_work *dwork, } EXPORT_SYMBOL(schedule_delayed_work); -/** - * flush_delayed_work - block until a dwork_struct's callback has terminated - * @dwork: the delayed work which is to be flushed - * - * Any timeout is cancelled, and any pending work is run immediately. - */ -void flush_delayed_work(struct delayed_work *dwork) -{ - if (del_timer_sync(&dwork->timer)) { - __queue_work(get_cpu(), get_work_cwq(&dwork->work)->wq, - &dwork->work); - put_cpu(); - } - flush_work(&dwork->work); -} -EXPORT_SYMBOL(flush_delayed_work); - /** * schedule_delayed_work_on - queue work in global workqueue on CPU after delay * @cpu: cpu to use -- cgit From 09383498c5d35262e643bfdbae84826177a3c624 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 16 Sep 2010 10:48:29 +0200 Subject: workqueue: implement flush[_delayed]_work_sync() Implement flush[_delayed]_work_sync(). These are flush functions which also make sure no CPU is still executing the target work from earlier queueing instances. These are similar to cancel[_delayed]_work_sync() except that the target work item is flushed instead of cancelled. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 2 ++ kernel/workqueue.c | 56 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 58 insertions(+) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index bb9b683ea6fa..e33ff4a91703 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -355,9 +355,11 @@ extern int keventd_up(void); int execute_in_process_context(work_func_t fn, struct execute_work *); extern bool flush_work(struct work_struct *work); +extern bool flush_work_sync(struct work_struct *work); extern bool cancel_work_sync(struct work_struct *work); extern bool flush_delayed_work(struct delayed_work *dwork); +extern bool flush_delayed_work_sync(struct delayed_work *work); extern bool cancel_delayed_work_sync(struct delayed_work *dwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 33d31d768706..19e4bc15ee99 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2435,6 +2435,41 @@ static bool wait_on_work(struct work_struct *work) return ret; } +/** + * flush_work_sync - wait until a work has finished execution + * @work: the work to flush + * + * Wait until @work has finished execution. On return, it's + * guaranteed that all queueing instances of @work which happened + * before this function is called are finished. In other words, if + * @work hasn't been requeued since this function was called, @work is + * guaranteed to be idle on return. + * + * RETURNS: + * %true if flush_work_sync() waited for the work to finish execution, + * %false if it was already idle. + */ +bool flush_work_sync(struct work_struct *work) +{ + struct wq_barrier barr; + bool pending, waited; + + /* we'll wait for executions separately, queue barr only if pending */ + pending = start_flush_work(work, &barr, false); + + /* wait for executions to finish */ + waited = wait_on_work(work); + + /* wait for the pending one */ + if (pending) { + wait_for_completion(&barr.done); + destroy_work_on_stack(&barr.work); + } + + return pending || waited; +} +EXPORT_SYMBOL_GPL(flush_work_sync); + /* * Upon a successful return (>= 0), the caller "owns" WORK_STRUCT_PENDING bit, * so this work can't be re-armed in any way. @@ -2538,6 +2573,27 @@ bool flush_delayed_work(struct delayed_work *dwork) } EXPORT_SYMBOL(flush_delayed_work); +/** + * flush_delayed_work_sync - wait for a dwork to finish + * @dwork: the delayed work to flush + * + * Delayed timer is cancelled and the pending work is queued for + * execution immediately. Other than timer handling, its behavior + * is identical to flush_work_sync(). + * + * RETURNS: + * %true if flush_work_sync() waited for the work to finish execution, + * %false if it was already idle. + */ +bool flush_delayed_work_sync(struct delayed_work *dwork) +{ + if (del_timer_sync(&dwork->timer)) + __queue_work(raw_smp_processor_id(), + get_work_cwq(&dwork->work)->wq, &dwork->work); + return flush_work_sync(&dwork->work); +} +EXPORT_SYMBOL(flush_delayed_work_sync); + /** * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish * @dwork: the delayed work cancel -- cgit From 6370a6ad3b53df90b4700977f7718118a2cd524a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 11 Oct 2010 15:12:27 +0200 Subject: workqueue: add and use WQ_MEM_RECLAIM flag Add WQ_MEM_RECLAIM flag which currently maps to WQ_RESCUER, mark WQ_RESCUER as internal and replace all external WQ_RESCUER usages to WQ_MEM_RECLAIM. This makes the API users express the intent of the workqueue instead of indicating the internal mechanism used to guarantee forward progress. This is also to make it cleaner to add more semantics to WQ_MEM_RECLAIM. For example, if deemed necessary, memory reclaim workqueues can be made highpri. This patch doesn't introduce any functional change. Signed-off-by: Tejun Heo Cc: Jeff Garzik Cc: Dave Chinner Cc: Steven Whitehouse --- Documentation/workqueue.txt | 29 +++++++++++++++-------------- drivers/ata/libata-sff.c | 2 +- fs/gfs2/main.c | 2 +- fs/xfs/linux-2.6/xfs_buf.c | 2 +- include/linux/workqueue.h | 11 ++++++----- kernel/workqueue.c | 7 +++++++ 6 files changed, 31 insertions(+), 22 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/Documentation/workqueue.txt b/Documentation/workqueue.txt index e4498a2872c3..996a27d9b8db 100644 --- a/Documentation/workqueue.txt +++ b/Documentation/workqueue.txt @@ -196,11 +196,11 @@ resources, scheduled and executed. suspend operations. Work items on the wq are drained and no new work item starts execution until thawed. - WQ_RESCUER + WQ_MEM_RECLAIM All wq which might be used in the memory reclaim paths _MUST_ - have this flag set. This reserves one worker exclusively for - the execution of this wq under memory pressure. + have this flag set. The wq is guaranteed to have at least one + execution context regardless of memory pressure. WQ_HIGHPRI @@ -356,11 +356,11 @@ If q1 has WQ_CPU_INTENSIVE set, 6. Guidelines -* Do not forget to use WQ_RESCUER if a wq may process work items which - are used during memory reclaim. Each wq with WQ_RESCUER set has one - rescuer thread reserved for it. If there is dependency among - multiple work items used during memory reclaim, they should be - queued to separate wq each with WQ_RESCUER. +* Do not forget to use WQ_MEM_RECLAIM if a wq may process work items + which are used during memory reclaim. Each wq with WQ_MEM_RECLAIM + set has an execution context reserved for it. If there is + dependency among multiple work items used during memory reclaim, + they should be queued to separate wq each with WQ_MEM_RECLAIM. * Unless strict ordering is required, there is no need to use ST wq. @@ -368,12 +368,13 @@ If q1 has WQ_CPU_INTENSIVE set, recommended. In most use cases, concurrency level usually stays well under the default limit. -* A wq serves as a domain for forward progress guarantee (WQ_RESCUER), - flush and work item attributes. Work items which are not involved - in memory reclaim and don't need to be flushed as a part of a group - of work items, and don't require any special attribute, can use one - of the system wq. There is no difference in execution - characteristics between using a dedicated wq and a system wq. +* A wq serves as a domain for forward progress guarantee + (WQ_MEM_RECLAIM, flush and work item attributes. Work items which + are not involved in memory reclaim and don't need to be flushed as a + part of a group of work items, and don't require any special + attribute, can use one of the system wq. There is no difference in + execution characteristics between using a dedicated wq and a system + wq. * Unless work items are expected to consume a huge amount of CPU cycles, using a bound wq is usually beneficial due to the increased diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index e30c537cce32..f5296bb19ec0 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -3335,7 +3335,7 @@ void ata_sff_port_init(struct ata_port *ap) int __init ata_sff_init(void) { - ata_sff_wq = alloc_workqueue("ata_sff", WQ_RESCUER, WQ_MAX_ACTIVE); + ata_sff_wq = alloc_workqueue("ata_sff", WQ_MEM_RECLAIM, WQ_MAX_ACTIVE); if (!ata_sff_wq) return -ENOMEM; diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index b1e9630eb46a..1c5f46075d52 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -140,7 +140,7 @@ static int __init init_gfs2_fs(void) error = -ENOMEM; gfs_recovery_wq = alloc_workqueue("gfs_recovery", - WQ_NON_REENTRANT | WQ_RESCUER, 0); + WQ_NON_REENTRANT | WQ_MEM_RECLAIM, 0); if (!gfs_recovery_wq) goto fail_wq; diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index 286e36e21dae..6838aefca71f 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -1933,7 +1933,7 @@ xfs_buf_init(void) goto out; xfslogd_workqueue = alloc_workqueue("xfslogd", - WQ_RESCUER | WQ_HIGHPRI, 1); + WQ_MEM_RECLAIM | WQ_HIGHPRI, 1); if (!xfslogd_workqueue) goto out_free_buf_zone; diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index e33ff4a91703..03bbe903e5ce 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -243,11 +243,12 @@ enum { WQ_NON_REENTRANT = 1 << 0, /* guarantee non-reentrance */ WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ WQ_FREEZEABLE = 1 << 2, /* freeze during suspend */ - WQ_RESCUER = 1 << 3, /* has an rescue worker */ + WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ WQ_DYING = 1 << 6, /* internal: workqueue is dying */ + WQ_RESCUER = 1 << 7, /* internal: workqueue has rescuer */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ @@ -309,7 +310,7 @@ __alloc_workqueue_key(const char *name, unsigned int flags, int max_active, /** * alloc_ordered_workqueue - allocate an ordered workqueue * @name: name of the workqueue - * @flags: WQ_* flags (only WQ_FREEZEABLE and WQ_RESCUER are meaningful) + * @flags: WQ_* flags (only WQ_FREEZEABLE and WQ_MEM_RECLAIM are meaningful) * * Allocate an ordered workqueue. An ordered workqueue executes at * most one work item at any given time in the queued order. They are @@ -325,11 +326,11 @@ alloc_ordered_workqueue(const char *name, unsigned int flags) } #define create_workqueue(name) \ - alloc_workqueue((name), WQ_RESCUER, 1) + alloc_workqueue((name), WQ_MEM_RECLAIM, 1) #define create_freezeable_workqueue(name) \ - alloc_workqueue((name), WQ_FREEZEABLE | WQ_UNBOUND | WQ_RESCUER, 1) + alloc_workqueue((name), WQ_FREEZEABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, 1) #define create_singlethread_workqueue(name) \ - alloc_workqueue((name), WQ_UNBOUND | WQ_RESCUER, 1) + alloc_workqueue((name), WQ_UNBOUND | WQ_MEM_RECLAIM, 1) extern void destroy_workqueue(struct workqueue_struct *wq); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index b57a8babdec3..2c6871cbcbee 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2847,6 +2847,13 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name, struct workqueue_struct *wq; unsigned int cpu; + /* + * Workqueues which may be used during memory reclaim should + * have a rescuer to guarantee forward progress. + */ + if (flags & WQ_MEM_RECLAIM) + flags |= WQ_RESCUER; + /* * Unbound workqueues aren't concurrency managed and should be * dispatched to workers immediately. -- cgit From daaae6b010ac0f60c9c35e481589966f9f1fcc22 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 19 Oct 2010 11:28:15 +0200 Subject: workqueue: remove in_workqueue_context() Commit a25909a4 (lockdep: Add an in_workqueue_context() lockdep-based test function) added in_workqueue_context() but there hasn't been any in-kernel user and the lockdep annotation in workqueue is scheduled to change. Remove the unused function. Signed-off-by: Tejun Heo Cc: Paul E. McKenney --- include/linux/workqueue.h | 4 ---- kernel/workqueue.c | 15 --------------- 2 files changed, 19 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 03bbe903e5ce..070bb7a88936 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -430,8 +430,4 @@ extern bool freeze_workqueues_busy(void); extern void thaw_workqueues(void); #endif /* CONFIG_FREEZER */ -#ifdef CONFIG_LOCKDEP -int in_workqueue_context(struct workqueue_struct *wq); -#endif - #endif diff --git a/kernel/workqueue.c b/kernel/workqueue.c index eb5c1972443a..30acdb74cc23 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -310,21 +310,6 @@ static inline int __next_wq_cpu(int cpu, const struct cpumask *mask, (cpu) < WORK_CPU_NONE; \ (cpu) = __next_wq_cpu((cpu), cpu_possible_mask, (wq))) -#ifdef CONFIG_LOCKDEP -/** - * in_workqueue_context() - in context of specified workqueue? - * @wq: the workqueue of interest - * - * Checks lockdep state to see if the current task is executing from - * within a workqueue item. This function exists only if lockdep is - * enabled. - */ -int in_workqueue_context(struct workqueue_struct *wq) -{ - return lock_is_held(&wq->lockdep_map); -} -#endif - #ifdef CONFIG_DEBUG_OBJECTS_WORK static struct debug_obj_descr work_debug_descr; -- cgit From ca1cab37d91cbe8a8333732540d43cabb54cfa85 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 26 Oct 2010 14:22:34 -0700 Subject: workqueues: s/ON_STACK/ONSTACK/ Silly though it is, completions and wait_queue_heads use foo_ONSTACK (COMPLETION_INITIALIZER_ONSTACK, DECLARE_COMPLETION_ONSTACK, __WAIT_QUEUE_HEAD_INIT_ONSTACK and DECLARE_WAIT_QUEUE_HEAD_ONSTACK) so I guess workqueues should do the same thing. s/INIT_WORK_ON_STACK/INIT_WORK_ONSTACK/ s/INIT_DELAYED_WORK_ON_STACK/INIT_DELAYED_WORK_ONSTACK/ Cc: Peter Zijlstra Acked-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/hpet.c | 2 +- arch/x86/kernel/smpboot.c | 2 +- drivers/md/dm-snap-persistent.c | 2 +- include/linux/workqueue.h | 6 +++--- kernel/workqueue.c | 2 +- 5 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index aff0b3c27509..ae03cab4352e 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -713,7 +713,7 @@ static int hpet_cpuhp_notify(struct notifier_block *n, switch (action & 0xf) { case CPU_ONLINE: - INIT_DELAYED_WORK_ON_STACK(&work.work, hpet_work); + INIT_DELAYED_WORK_ONSTACK(&work.work, hpet_work); init_completion(&work.complete); /* FIXME: add schedule_work_on() */ schedule_delayed_work_on(cpu, &work.work, 0); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6af118511b4a..6c7faecd9e4a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -747,7 +747,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu) .done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done), }; - INIT_WORK_ON_STACK(&c_idle.work, do_fork_idle); + INIT_WORK_ONSTACK(&c_idle.work, do_fork_idle); alternatives_smp_switch(1); diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 0b61792a2780..2129cdb115dc 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -254,7 +254,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw, * Issue the synchronous I/O from a different thread * to avoid generic_make_request recursion. */ - INIT_WORK_ON_STACK(&req.work, do_metadata); + INIT_WORK_ONSTACK(&req.work, do_metadata); queue_work(ps->metadata_wq, &req.work); flush_workqueue(ps->metadata_wq); diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 070bb7a88936..0c0771f06bfa 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -190,7 +190,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } __INIT_WORK((_work), (_func), 0); \ } while (0) -#define INIT_WORK_ON_STACK(_work, _func) \ +#define INIT_WORK_ONSTACK(_work, _func) \ do { \ __INIT_WORK((_work), (_func), 1); \ } while (0) @@ -201,9 +201,9 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } init_timer(&(_work)->timer); \ } while (0) -#define INIT_DELAYED_WORK_ON_STACK(_work, _func) \ +#define INIT_DELAYED_WORK_ONSTACK(_work, _func) \ do { \ - INIT_WORK_ON_STACK(&(_work)->work, (_func)); \ + INIT_WORK_ONSTACK(&(_work)->work, (_func)); \ init_timer_on_stack(&(_work)->timer); \ } while (0) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index e5ff2cbaadc2..90db1bd1a978 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2064,7 +2064,7 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, * checks and call back into the fixup functions where we * might deadlock. */ - INIT_WORK_ON_STACK(&barr->work, wq_barrier_func); + INIT_WORK_ONSTACK(&barr->work, wq_barrier_func); __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); init_completion(&barr->done); -- cgit