From cee22a15052faa817e3ec8985a28154d3fabc7aa Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Mon, 8 Apr 2013 16:45:40 +0530 Subject: workqueues: Introduce new flag WQ_POWER_EFFICIENT for power oriented workqueues Workqueues can be performance or power-oriented. Currently, most workqueues are bound to the CPU they were created on. This gives good performance (due to cache effects) at the cost of potentially waking up otherwise idle cores (Idle from scheduler's perspective. Which may or may not be physically idle) just to process some work. To save power, we can allow the work to be rescheduled on a core that is already awake. Workqueues created with the WQ_UNBOUND flag will allow some power savings. However, we don't change the default behaviour of the system. To enable power-saving behaviour, a new config option CONFIG_WQ_POWER_EFFICIENT needs to be turned on. This option can also be overridden by the workqueue.power_efficient boot parameter. tj: Updated config description and comments. Renamed CONFIG_WQ_POWER_EFFICIENT to CONFIG_WQ_POWER_EFFICIENT_DEFAULT. Signed-off-by: Viresh Kumar Reviewed-by: Amit Kucheria Signed-off-by: Tejun Heo --- kernel/workqueue.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'kernel/workqueue.c') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 4aa9f5bc6b2d..8068d97ce141 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -272,6 +272,15 @@ static cpumask_var_t *wq_numa_possible_cpumask; static bool wq_disable_numa; module_param_named(disable_numa, wq_disable_numa, bool, 0444); +/* see the comment above the definition of WQ_POWER_EFFICIENT */ +#ifdef CONFIG_WQ_POWER_EFFICIENT_DEFAULT +static bool wq_power_efficient = true; +#else +static bool wq_power_efficient; +#endif + +module_param_named(power_efficient, wq_power_efficient, bool, 0444); + static bool wq_numa_enabled; /* unbound NUMA affinity enabled */ /* buf for wq_update_unbound_numa_attrs(), protected by CPU hotplug exclusion */ @@ -4085,6 +4094,10 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt, struct workqueue_struct *wq; struct pool_workqueue *pwq; + /* see the comment above the definition of WQ_POWER_EFFICIENT */ + if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient) + flags |= WQ_UNBOUND; + /* allocate wq and format name */ if (flags & WQ_UNBOUND) tbl_size = wq_numa_tbl_len * sizeof(wq->numa_pwq_tbl[0]); -- cgit v1.2.3 From 0668106ca3865ba945e155097fb042bf66d364d3 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 24 Apr 2013 17:12:54 +0530 Subject: workqueue: Add system wide power_efficient workqueues This patch adds system wide workqueues aligned towards power saving. This is done by allocating them with WQ_UNBOUND flag if 'wq_power_efficient' is set to 'true'. tj: updated comments a bit. Signed-off-by: Viresh Kumar Signed-off-by: Tejun Heo --- kernel/workqueue.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'kernel/workqueue.c') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 8068d97ce141..16ca2d3dd29f 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -314,6 +314,10 @@ 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); +struct workqueue_struct *system_power_efficient_wq __read_mostly; +EXPORT_SYMBOL_GPL(system_power_efficient_wq); +struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly; +EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); static int worker_thread(void *__worker); static void copy_workqueue_attrs(struct workqueue_attrs *to, @@ -4987,8 +4991,15 @@ static int __init init_workqueues(void) WQ_UNBOUND_MAX_ACTIVE); system_freezable_wq = alloc_workqueue("events_freezable", WQ_FREEZABLE, 0); + system_power_efficient_wq = alloc_workqueue("events_power_efficient", + WQ_POWER_EFFICIENT, 0); + system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_power_efficient", + WQ_FREEZABLE | WQ_POWER_EFFICIENT, + 0); BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq || - !system_unbound_wq || !system_freezable_wq); + !system_unbound_wq || !system_freezable_wq || + !system_power_efficient_wq || + !system_freezable_power_efficient_wq); return 0; } early_initcall(init_workqueues); -- cgit v1.2.3 From 0db0628d90125193280eabb501c94feaf48fa9ab Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Wed, 19 Jun 2013 14:53:51 -0400 Subject: kernel: delete __cpuinit usage from all core kernel files The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. This removes all the uses of the __cpuinit macros from C files in the core kernel directories (kernel, init, lib, mm, and include) that don't really have a specific maintainer. [1] https://lkml.org/lkml/2013/5/20/589 Signed-off-by: Paul Gortmaker --- kernel/workqueue.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/workqueue.c') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index f02c4a4a0c3c..0b72e816b8d0 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4644,7 +4644,7 @@ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu) * 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, +static int workqueue_cpu_up_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { @@ -4697,7 +4697,7 @@ static int __cpuinit workqueue_cpu_up_callback(struct notifier_block *nfb, * 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, +static int workqueue_cpu_down_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { -- cgit v1.2.3 From c2fda509667b0fda4372a237f5a59ea4570b1627 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Wed, 24 Jul 2013 18:31:42 +0800 Subject: workqueue: allow work_on_cpu() to be called recursively If the @fn call work_on_cpu() again, the lockdep will complain: > [ INFO: possible recursive locking detected ] > 3.11.0-rc1-lockdep-fix-a #6 Not tainted > --------------------------------------------- > kworker/0:1/142 is trying to acquire lock: > ((&wfc.work)){+.+.+.}, at: [] flush_work+0x0/0xb0 > > but task is already holding lock: > ((&wfc.work)){+.+.+.}, at: [] process_one_work+0x169/0x610 > > other info that might help us debug this: > Possible unsafe locking scenario: > > CPU0 > ---- > lock((&wfc.work)); > lock((&wfc.work)); > > *** DEADLOCK *** It is false-positive lockdep report. In this sutiation, the two "wfc"s of the two work_on_cpu() are different, they are both on stack. flush_work() can't be deadlock. To fix this, we need to avoid the lockdep checking in this case, thus we instroduce a internal __flush_work() which skip the lockdep. tj: Minor comment adjustment. Signed-off-by: Lai Jiangshan Reported-by: "Srivatsa S. Bhat" Reported-by: Alexander Duyck Signed-off-by: Tejun Heo --- kernel/workqueue.c | 32 ++++++++++++++++++++++---------- 1 file changed, 22 insertions(+), 10 deletions(-) (limited to 'kernel/workqueue.c') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index f02c4a4a0c3c..55f5f0afcd0d 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2817,6 +2817,19 @@ already_gone: return false; } +static bool __flush_work(struct work_struct *work) +{ + struct wq_barrier barr; + + if (start_flush_work(work, &barr)) { + wait_for_completion(&barr.done); + destroy_work_on_stack(&barr.work); + return true; + } else { + return false; + } +} + /** * flush_work - wait for a work to finish executing the last queueing instance * @work: the work to flush @@ -2830,18 +2843,10 @@ already_gone: */ 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; - } + return __flush_work(work); } EXPORT_SYMBOL_GPL(flush_work); @@ -4756,7 +4761,14 @@ long work_on_cpu(int cpu, long (*fn)(void *), void *arg) INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn); schedule_work_on(cpu, &wfc.work); - flush_work(&wfc.work); + + /* + * The work item is on-stack and can't lead to deadlock through + * flushing. Use __flush_work() to avoid spurious lockdep warnings + * when work_on_cpu()s are nested. + */ + __flush_work(&wfc.work); + return wfc.ret; } EXPORT_SYMBOL_GPL(work_on_cpu); -- cgit v1.2.3 From 2865a8fb44cc32420407362cbda80c10fa09c6b2 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Thu, 1 Aug 2013 09:56:36 +0800 Subject: workqueue: copy workqueue_attrs with all fields $echo '0' > /sys/bus/workqueue/devices/xxx/numa $cat /sys/bus/workqueue/devices/xxx/numa I got 1. It should be 0, the reason is copy_workqueue_attrs() called in apply_workqueue_attrs() doesn't copy no_numa field. Fix it by making copy_workqueue_attrs() copy ->no_numa too. This would also make get_unbound_pool() set a pool's ->no_numa attribute according to the workqueue attributes used when the pool was created. While harmelss, as ->no_numa isn't a pool attribute, this is a bit confusing. Clear it explicitly. tj: Updated description and comments a bit. Signed-off-by: Shaohua Li Signed-off-by: Tejun Heo Cc: stable@vger.kernel.org --- kernel/workqueue.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'kernel/workqueue.c') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 55f5f0afcd0d..726adc84b3ca 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3416,6 +3416,12 @@ static void copy_workqueue_attrs(struct workqueue_attrs *to, { to->nice = from->nice; cpumask_copy(to->cpumask, from->cpumask); + /* + * Unlike hash and equality test, this function doesn't ignore + * ->no_numa as it is used for both pool and wq attrs. Instead, + * get_unbound_pool() explicitly clears ->no_numa after copying. + */ + to->no_numa = from->no_numa; } /* hash value of the content of @attr */ @@ -3583,6 +3589,12 @@ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) lockdep_set_subclass(&pool->lock, 1); /* see put_pwq() */ copy_workqueue_attrs(pool->attrs, attrs); + /* + * no_numa isn't a worker_pool attribute, always clear it. See + * 'struct workqueue_attrs' comments for detail. + */ + pool->attrs->no_numa = false; + /* if cpumask is contained inside a NUMA node, we belong to that node */ if (wq_numa_enabled) { for_each_node(node) { -- cgit v1.2.3