Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752617Ab3CBDbE (ORCPT ); Fri, 1 Mar 2013 22:31:04 -0500 Received: from mail-da0-f47.google.com ([209.85.210.47]:61194 "EHLO mail-da0-f47.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752488Ab3CBDY4 (ORCPT ); Fri, 1 Mar 2013 22:24:56 -0500 From: Tejun Heo To: linux-kernel@vger.kernel.org, laijs@cn.fujitsu.com Cc: axboe@kernel.dk, jmoyer@redhat.com, zab@redhat.com, Tejun Heo Subject: [PATCH 16/31] workqueue: introduce workqueue_attrs Date: Fri, 1 Mar 2013 19:24:07 -0800 Message-Id: <1362194662-2344-17-git-send-email-tj@kernel.org> X-Mailer: git-send-email 1.8.1.2 In-Reply-To: <1362194662-2344-1-git-send-email-tj@kernel.org> References: <1362194662-2344-1-git-send-email-tj@kernel.org> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 7893 Lines: 244 Introduce struct workqueue_attrs which carries worker attributes - currently the nice level and allowed cpumask along with helper routines alloc_workqueue_attrs() and free_workqueue_attrs(). Each worker_pool now carries ->attrs describing the attributes of its workers. All functions dealing with cpumask and nice level of workers are updated to follow worker_pool->attrs instead of determining them from other characteristics of the worker_pool, and init_workqueues() is updated to set worker_pool->attrs appropriately for all standard pools. Note that create_worker() is updated to always perform set_user_nice() and use set_cpus_allowed_ptr() combined with manual assertion of PF_THREAD_BOUND instead of kthread_bind(). This simplifies handling random attributes without affecting the outcome. This patch doesn't introduce any behavior changes. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 12 ++++++ kernel/workqueue.c | 103 ++++++++++++++++++++++++++++++++++++---------- 2 files changed, 93 insertions(+), 22 deletions(-) diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 899be66..2683e8e 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -115,6 +115,15 @@ struct delayed_work { int cpu; }; +/* + * A struct for workqueue attributes. This can be used to change + * attributes of an unbound workqueue. + */ +struct workqueue_attrs { + int nice; /* nice level */ + cpumask_var_t cpumask; /* allowed CPUs */ +}; + static inline struct delayed_work *to_delayed_work(struct work_struct *work) { return container_of(work, struct delayed_work, work); @@ -399,6 +408,9 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, extern void destroy_workqueue(struct workqueue_struct *wq); +struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask); +void free_workqueue_attrs(struct workqueue_attrs *attrs); + extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); extern bool queue_work(struct workqueue_struct *wq, struct work_struct *work); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index f97539b..7eba824 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -148,6 +148,8 @@ struct worker_pool { struct mutex assoc_mutex; /* protect POOL_DISASSOCIATED */ struct ida worker_ida; /* L: for worker IDs */ + struct workqueue_attrs *attrs; /* I: worker attributes */ + /* * The current concurrency level. As it's likely to be accessed * from other CPUs during try_to_wake_up(), put it in a separate @@ -1563,14 +1565,13 @@ __acquires(&pool->lock) * against POOL_DISASSOCIATED. */ if (!(pool->flags & POOL_DISASSOCIATED)) - set_cpus_allowed_ptr(current, get_cpu_mask(pool->cpu)); + set_cpus_allowed_ptr(current, pool->attrs->cpumask); spin_lock_irq(&pool->lock); if (pool->flags & POOL_DISASSOCIATED) return false; if (task_cpu(current) == pool->cpu && - cpumask_equal(¤t->cpus_allowed, - get_cpu_mask(pool->cpu))) + cpumask_equal(¤t->cpus_allowed, pool->attrs->cpumask)) return true; spin_unlock_irq(&pool->lock); @@ -1677,7 +1678,7 @@ static void rebind_workers(struct worker_pool *pool) * wq doesn't really matter but let's keep @worker->pool * and @pwq->pool consistent for sanity. */ - if (std_worker_pool_pri(worker->pool)) + if (worker->pool->attrs->nice < 0) wq = system_highpri_wq; else wq = system_wq; @@ -1719,7 +1720,7 @@ static struct worker *alloc_worker(void) */ static struct worker *create_worker(struct worker_pool *pool) { - const char *pri = std_worker_pool_pri(pool) ? "H" : ""; + const char *pri = pool->attrs->nice < 0 ? "H" : ""; struct worker *worker = NULL; int id = -1; @@ -1749,24 +1750,23 @@ static struct worker *create_worker(struct worker_pool *pool) if (IS_ERR(worker->task)) goto fail; - if (std_worker_pool_pri(pool)) - set_user_nice(worker->task, HIGHPRI_NICE_LEVEL); + set_user_nice(worker->task, pool->attrs->nice); + set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); /* - * Determine CPU binding of the new worker depending on - * %POOL_DISASSOCIATED. The caller is responsible for ensuring the - * 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. + * %PF_THREAD_BOUND is used to prevent userland from meddling with + * cpumask of workqueue workers. This is an abuse. We need + * %PF_KERNEL_CPUMASK. */ - if (!(pool->flags & POOL_DISASSOCIATED)) { - kthread_bind(worker->task, pool->cpu); - } else { - worker->task->flags |= PF_THREAD_BOUND; + worker->task->flags |= PF_THREAD_BOUND; + + /* + * The caller is responsible for ensuring %POOL_DISASSOCIATED + * remains stable across this function. See the comments above the + * flag definition for details. + */ + if (pool->flags & POOL_DISASSOCIATED) worker->flags |= WORKER_UNBOUND; - } return worker; fail: @@ -3121,7 +3121,52 @@ int keventd_up(void) return system_wq != NULL; } -static void init_worker_pool(struct worker_pool *pool) +/** + * free_workqueue_attrs - free a workqueue_attrs + * @attrs: workqueue_attrs to free + * + * Undo alloc_workqueue_attrs(). + */ +void free_workqueue_attrs(struct workqueue_attrs *attrs) +{ + if (attrs) { + free_cpumask_var(attrs->cpumask); + kfree(attrs); + } +} + +/** + * alloc_workqueue_attrs - allocate a workqueue_attrs + * @gfp_mask: allocation mask to use + * + * Allocate a new workqueue_attrs, initialize with default settings and + * return it. Returns NULL on failure. + */ +struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask) +{ + struct workqueue_attrs *attrs; + + attrs = kzalloc(sizeof(*attrs), gfp_mask); + if (!attrs) + goto fail; + if (!alloc_cpumask_var(&attrs->cpumask, gfp_mask)) + goto fail; + + cpumask_setall(attrs->cpumask); + return attrs; +fail: + free_workqueue_attrs(attrs); + return NULL; +} + +/** + * init_worker_pool - initialize a newly zalloc'd worker_pool + * @pool: worker_pool to initialize + * + * Initiailize a newly zalloc'd @pool. It also allocates @pool->attrs. + * Returns 0 on success, -errno on failure. + */ +static int init_worker_pool(struct worker_pool *pool) { spin_lock_init(&pool->lock); pool->flags |= POOL_DISASSOCIATED; @@ -3139,6 +3184,11 @@ static void init_worker_pool(struct worker_pool *pool) mutex_init(&pool->manager_mutex); mutex_init(&pool->assoc_mutex); ida_init(&pool->worker_ida); + + pool->attrs = alloc_workqueue_attrs(GFP_KERNEL); + if (!pool->attrs) + return -ENOMEM; + return 0; } static int alloc_and_link_pwqs(struct workqueue_struct *wq) @@ -3791,7 +3841,8 @@ out_unlock: static int __init init_workqueues(void) { - int cpu; + int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL }; + int i, cpu; /* make sure we have enough bits for OFFQ pool ID */ BUILD_BUG_ON((1LU << (BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT)) < @@ -3808,10 +3859,18 @@ static int __init init_workqueues(void) for_each_wq_cpu(cpu) { struct worker_pool *pool; + i = 0; for_each_std_worker_pool(pool, cpu) { - init_worker_pool(pool); + BUG_ON(init_worker_pool(pool)); pool->cpu = cpu; + if (cpu != WORK_CPU_UNBOUND) + cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu)); + else + cpumask_setall(pool->attrs->cpumask); + + pool->attrs->nice = std_nice[i++]; + /* alloc pool ID */ BUG_ON(worker_pool_assign_id(pool)); } -- 1.8.1.2 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/