From patchwork Fri Oct 18 13:40:15 2013 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Viresh Kumar X-Patchwork-Id: 21131 Return-Path: X-Original-To: linaro@patches.linaro.org Delivered-To: linaro@patches.linaro.org Received: from mail-qc0-f200.google.com (mail-qc0-f200.google.com [209.85.216.200]) by ip-10-151-82-157.ec2.internal (Postfix) with ESMTPS id 9D891202FF for ; Fri, 18 Oct 2013 13:40:28 +0000 (UTC) Received: by mail-qc0-f200.google.com with SMTP id x20sf7585282qcv.11 for ; Fri, 18 Oct 2013 06:40:28 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=mime-version:x-gm-message-state:delivered-to:from:to:cc:subject :date:message-id:x-original-sender:x-original-authentication-results :precedence:mailing-list:list-id:list-post:list-help:list-archive :list-unsubscribe; bh=TvlRZroiFH+RPBIaxZpVNYZaN5VZTgMOOIFzBnRyt+Y=; b=Lz0JblrRUhIFS+/W78VxJvhVswVOYwQNc6x6Id4vZbyV8beB9Igscwaz7bD0k3GoBD 7OmL+kg4Wbokxq0mUqcqyog/PCg2ETGLFgzYesMqiDeAl4qsBgM1LUnrRnGJe9seUSO+ 6fNAaCej5DDJI0ZervMYg61J9PWaumiZq82fktFCtJ6x+NUolb1G0H6F6Ae4b1EsW4eW vt7w4Vpz1qdv1gRkvVqXtYd95ttV9C9vI3onJ4z/pYh9XE8UH5FgLcbv02Uz+MZv0cRq tvUn6PobuoEcrMJPV3fpjZUyTfnSXF6mlhwPU0eBE/pA6r1vQxD3OZoP6HpSJTawzCfY 5iuw== X-Received: by 10.52.109.164 with SMTP id ht4mr983949vdb.8.1382103627901; Fri, 18 Oct 2013 06:40:27 -0700 (PDT) MIME-Version: 1.0 X-BeenThere: patchwork-forward@linaro.org Received: by 10.49.35.10 with SMTP id d10ls1298791qej.19.gmail; Fri, 18 Oct 2013 06:40:27 -0700 (PDT) X-Received: by 10.52.118.98 with SMTP id kl2mr170282vdb.30.1382103627777; Fri, 18 Oct 2013 06:40:27 -0700 (PDT) Received: from mail-vc0-f178.google.com (mail-vc0-f178.google.com [209.85.220.178]) by mx.google.com with ESMTPS id o10si316411vco.65.2013.10.18.06.40.27 for (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Fri, 18 Oct 2013 06:40:27 -0700 (PDT) Received-SPF: neutral (google.com: 209.85.220.178 is neither permitted nor denied by best guess record for domain of patch+caf_=patchwork-forward=linaro.org@linaro.org) client-ip=209.85.220.178; Received: by mail-vc0-f178.google.com with SMTP id lh4so399819vcb.23 for ; Fri, 18 Oct 2013 06:40:27 -0700 (PDT) X-Gm-Message-State: ALoCoQkRfy65OK1L41uIf/pE1MVBIOwpXgRuh73uKhW5eRB7u4xNYthe164AvY6yDax0IBDpvgUm X-Received: by 10.52.243.138 with SMTP id wy10mr1814549vdc.2.1382103627474; Fri, 18 Oct 2013 06:40:27 -0700 (PDT) X-Forwarded-To: patchwork-forward@linaro.org X-Forwarded-For: patch@linaro.org patchwork-forward@linaro.org Delivered-To: patches@linaro.org Received: by 10.220.174.196 with SMTP id u4csp36543vcz; Fri, 18 Oct 2013 06:40:26 -0700 (PDT) X-Received: by 10.68.203.195 with SMTP id ks3mr3075384pbc.83.1382103626416; Fri, 18 Oct 2013 06:40:26 -0700 (PDT) Received: from mail-pd0-f174.google.com (mail-pd0-f174.google.com [209.85.192.174]) by mx.google.com with ESMTPS id yk3si1538357pac.99.2013.10.18.06.40.26 for (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Fri, 18 Oct 2013 06:40:26 -0700 (PDT) Received-SPF: neutral (google.com: 209.85.192.174 is neither permitted nor denied by best guess record for domain of viresh.kumar@linaro.org) client-ip=209.85.192.174; Received: by mail-pd0-f174.google.com with SMTP id y13so4709726pdi.19 for ; Fri, 18 Oct 2013 06:40:25 -0700 (PDT) X-Received: by 10.68.0.101 with SMTP id 5mr3136382pbd.106.1382103625735; Fri, 18 Oct 2013 06:40:25 -0700 (PDT) Received: from localhost ([120.56.197.189]) by mx.google.com with ESMTPSA id be1sm2502745pbb.28.2013.10.18.06.40.21 for (version=TLSv1.2 cipher=RC4-SHA bits=128/128); Fri, 18 Oct 2013 06:40:25 -0700 (PDT) From: Viresh Kumar To: rjw@sisk.pl, andrew@lunn.ch Cc: linaro-kernel@lists.linaro.org, patches@linaro.org, cpufreq@vger.kernel.org, linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org, Viresh Kumar , "Rafael J. Wysocki" Subject: [PATCH] cpufreq: create per policy rwsem instead of per CPU cpu_policy_rwsem Date: Fri, 18 Oct 2013 19:10:15 +0530 Message-Id: X-Mailer: git-send-email 1.7.12.rc2.18.g61b472e X-Removed-Original-Auth: Dkim didn't pass. X-Original-Sender: viresh.kumar@linaro.org X-Original-Authentication-Results: mx.google.com; spf=neutral (google.com: 209.85.220.178 is neither permitted nor denied by best guess record for domain of patch+caf_=patchwork-forward=linaro.org@linaro.org) smtp.mail=patch+caf_=patchwork-forward=linaro.org@linaro.org Precedence: list Mailing-list: list patchwork-forward@linaro.org; contact patchwork-forward+owners@linaro.org List-ID: X-Google-Group-Id: 836684582541 List-Post: , List-Help: , List-Archive: List-Unsubscribe: , We have per-CPU cpu_policy_rwsem for cpufreq core, but we never use all of them. We always use rwsem of policy->cpu and so we can actually make this rwsem per policy instead. This patch does this change. With this change other tricky situations are also avoided now, like which lock to take while we are changing policy->cpu, etc. Suggested-by: Srivatsa S. Bhat Signed-off-by: Viresh Kumar Reviewed-by: Srivatsa S. Bhat Signed-off-by: Rafael J. Wysocki Tested-by: Andrew Lunn --- I thought I should send it formally as well. Though Andrew hasn't given his tested by until now. Rebased over your bleeding-edge branch. drivers/cpufreq/cpufreq.c | 110 +++++++++++++--------------------------------- include/linux/cpufreq.h | 14 ++++++ 2 files changed, 45 insertions(+), 79 deletions(-) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index ec391d7..3f03dcb 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -48,47 +48,6 @@ static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor); #endif /* - * cpu_policy_rwsem is a per CPU reader-writer semaphore designed to cure - * all cpufreq/hotplug/workqueue/etc related lock issues. - * - * The rules for this semaphore: - * - Any routine that wants to read from the policy structure will - * do a down_read on this semaphore. - * - Any routine that will write to the policy structure and/or may take away - * the policy altogether (eg. CPU hotplug), will hold this lock in write - * mode before doing so. - * - * Additional rules: - * - Governor routines that can be called in cpufreq hotplug path should not - * take this sem as top level hotplug notifier handler takes this. - * - Lock should not be held across - * __cpufreq_governor(data, CPUFREQ_GOV_STOP); - */ -static DEFINE_PER_CPU(struct rw_semaphore, cpu_policy_rwsem); - -#define lock_policy_rwsem(mode, cpu) \ -static void lock_policy_rwsem_##mode(int cpu) \ -{ \ - struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu); \ - BUG_ON(!policy); \ - down_##mode(&per_cpu(cpu_policy_rwsem, policy->cpu)); \ -} - -lock_policy_rwsem(read, cpu); -lock_policy_rwsem(write, cpu); - -#define unlock_policy_rwsem(mode, cpu) \ -static void unlock_policy_rwsem_##mode(int cpu) \ -{ \ - struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu); \ - BUG_ON(!policy); \ - up_##mode(&per_cpu(cpu_policy_rwsem, policy->cpu)); \ -} - -unlock_policy_rwsem(read, cpu); -unlock_policy_rwsem(write, cpu); - -/* * rwsem to guarantee that cpufreq driver module doesn't unload during critical * sections */ @@ -683,14 +642,14 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf) if (!down_read_trylock(&cpufreq_rwsem)) return -EINVAL; - lock_policy_rwsem_read(policy->cpu); + down_read(&policy->rwsem); if (fattr->show) ret = fattr->show(policy, buf); else ret = -EIO; - unlock_policy_rwsem_read(policy->cpu); + up_read(&policy->rwsem); up_read(&cpufreq_rwsem); return ret; @@ -711,14 +670,14 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, if (!down_read_trylock(&cpufreq_rwsem)) goto unlock; - lock_policy_rwsem_write(policy->cpu); + down_write(&policy->rwsem); if (fattr->store) ret = fattr->store(policy, buf, count); else ret = -EIO; - unlock_policy_rwsem_write(policy->cpu); + up_write(&policy->rwsem); up_read(&cpufreq_rwsem); unlock: @@ -895,7 +854,7 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, } } - lock_policy_rwsem_write(policy->cpu); + down_write(&policy->rwsem); write_lock_irqsave(&cpufreq_driver_lock, flags); @@ -903,7 +862,7 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, per_cpu(cpufreq_cpu_data, cpu) = policy; write_unlock_irqrestore(&cpufreq_driver_lock, flags); - unlock_policy_rwsem_write(policy->cpu); + up_write(&policy->rwsem); if (has_target) { if ((ret = __cpufreq_governor(policy, CPUFREQ_GOV_START)) || @@ -950,6 +909,8 @@ static struct cpufreq_policy *cpufreq_policy_alloc(void) goto err_free_cpumask; INIT_LIST_HEAD(&policy->policy_list); + init_rwsem(&policy->rwsem); + return policy; err_free_cpumask: @@ -972,19 +933,12 @@ static void update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu) if (WARN_ON(cpu == policy->cpu)) return; - /* - * Take direct locks as lock_policy_rwsem_write wouldn't work here. - * Also lock for last cpu is enough here as contention will happen only - * after policy->cpu is changed and after it is changed, other threads - * will try to acquire lock for new cpu. And policy is already updated - * by then. - */ - down_write(&per_cpu(cpu_policy_rwsem, policy->cpu)); + down_write(&policy->rwsem); policy->last_cpu = policy->cpu; policy->cpu = cpu; - up_write(&per_cpu(cpu_policy_rwsem, policy->last_cpu)); + up_write(&policy->rwsem); cpufreq_frequency_table_update_policy_cpu(policy); blocking_notifier_call_chain(&cpufreq_policy_notifier_list, @@ -1176,9 +1130,9 @@ static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *policy, if (ret) { pr_err("%s: Failed to move kobj: %d", __func__, ret); - lock_policy_rwsem_write(old_cpu); + down_write(&policy->rwsem); cpumask_set_cpu(old_cpu, policy->cpus); - unlock_policy_rwsem_write(old_cpu); + up_write(&policy->rwsem); ret = sysfs_create_link(&cpu_dev->kobj, &policy->kobj, "cpufreq"); @@ -1229,9 +1183,9 @@ static int __cpufreq_remove_dev_prepare(struct device *dev, policy->governor->name, CPUFREQ_NAME_LEN); #endif - lock_policy_rwsem_read(cpu); + down_read(&policy->rwsem); cpus = cpumask_weight(policy->cpus); - unlock_policy_rwsem_read(cpu); + up_read(&policy->rwsem); if (cpu != policy->cpu) { if (!frozen) @@ -1271,12 +1225,12 @@ static int __cpufreq_remove_dev_finish(struct device *dev, return -EINVAL; } - lock_policy_rwsem_write(cpu); + down_write(&policy->rwsem); cpus = cpumask_weight(policy->cpus); if (cpus > 1) cpumask_clear_cpu(cpu, policy->cpus); - unlock_policy_rwsem_write(cpu); + up_write(&policy->rwsem); /* If cpu is last user of policy, free policy */ if (cpus == 1) { @@ -1291,10 +1245,10 @@ static int __cpufreq_remove_dev_finish(struct device *dev, } if (!frozen) { - lock_policy_rwsem_read(cpu); + down_read(&policy->rwsem); kobj = &policy->kobj; cmp = &policy->kobj_unregister; - unlock_policy_rwsem_read(cpu); + up_read(&policy->rwsem); kobject_put(kobj); /* @@ -1474,19 +1428,22 @@ static unsigned int __cpufreq_get(unsigned int cpu) */ unsigned int cpufreq_get(unsigned int cpu) { + struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu); unsigned int ret_freq = 0; if (cpufreq_disabled() || !cpufreq_driver) return -ENOENT; + BUG_ON(!policy); + if (!down_read_trylock(&cpufreq_rwsem)) return 0; - lock_policy_rwsem_read(cpu); + down_read(&policy->rwsem); ret_freq = __cpufreq_get(cpu); - unlock_policy_rwsem_read(cpu); + up_read(&policy->rwsem); up_read(&cpufreq_rwsem); return ret_freq; @@ -1710,11 +1667,11 @@ int cpufreq_driver_target(struct cpufreq_policy *policy, { int ret = -EINVAL; - lock_policy_rwsem_write(policy->cpu); + down_write(&policy->rwsem); ret = __cpufreq_driver_target(policy, target_freq, relation); - unlock_policy_rwsem_write(policy->cpu); + up_write(&policy->rwsem); return ret; } @@ -1945,10 +1902,10 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, /* end old governor */ if (policy->governor) { __cpufreq_governor(policy, CPUFREQ_GOV_STOP); - unlock_policy_rwsem_write(new_policy->cpu); + up_write(&policy->rwsem); __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT); - lock_policy_rwsem_write(new_policy->cpu); + down_write(&policy->rwsem); } /* start new governor */ @@ -1957,10 +1914,10 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, if (!__cpufreq_governor(policy, CPUFREQ_GOV_START)) { failed = 0; } else { - unlock_policy_rwsem_write(new_policy->cpu); + up_write(&policy->rwsem); __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT); - lock_policy_rwsem_write(new_policy->cpu); + down_write(&policy->rwsem); } } @@ -2006,7 +1963,7 @@ int cpufreq_update_policy(unsigned int cpu) goto no_policy; } - lock_policy_rwsem_write(cpu); + down_write(&policy->rwsem); pr_debug("updating policy for CPU %u\n", cpu); memcpy(&new_policy, policy, sizeof(*policy)); @@ -2033,7 +1990,7 @@ int cpufreq_update_policy(unsigned int cpu) ret = cpufreq_set_policy(policy, &new_policy); - unlock_policy_rwsem_write(cpu); + up_write(&policy->rwsem); cpufreq_cpu_put(policy); no_policy: @@ -2190,14 +2147,9 @@ EXPORT_SYMBOL_GPL(cpufreq_unregister_driver); static int __init cpufreq_core_init(void) { - int cpu; - if (cpufreq_disabled()) return -ENODEV; - for_each_possible_cpu(cpu) - init_rwsem(&per_cpu(cpu_policy_rwsem, cpu)); - cpufreq_global_kobject = kobject_create(); BUG_ON(!cpufreq_global_kobject); register_syscore_ops(&cpufreq_syscore_ops); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 0aba2a6c..6b457d0 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -85,6 +85,20 @@ struct cpufreq_policy { struct list_head policy_list; struct kobject kobj; struct completion kobj_unregister; + + /* + * The rules for this semaphore: + * - Any routine that wants to read from the policy structure will + * do a down_read on this semaphore. + * - Any routine that will write to the policy structure and/or may take away + * the policy altogether (eg. CPU hotplug), will hold this lock in write + * mode before doing so. + * + * Additional rules: + * - Lock should not be held across + * __cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT); + */ + struct rw_semaphore rwsem; }; /* Only for ACPI */