From patchwork Tue Jun 6 23:24:48 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Nicolas Pitre X-Patchwork-Id: 103191 Delivered-To: patch@linaro.org Received: by 10.140.91.77 with SMTP id y71csp1670817qgd; Tue, 6 Jun 2017 16:25:44 -0700 (PDT) X-Received: by 10.84.224.1 with SMTP id r1mr24684865plj.262.1496791544583; Tue, 06 Jun 2017 16:25:44 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1496791544; cv=none; d=google.com; s=arc-20160816; b=HtmwUqWQ/gDLzjjZjdDiF3s7g/cSmMkiLJv5P9Z18n8bn1T9vPE1SflrqQa42XSExe GLAYh4ksMbRDCnT6mJWoizJwdzx0edULIv4dgcMN9ZHdAy15JQaHXZRxiNi6DEMWGobv Vnsm3U9Vgr8YL4sutuGXRNql4l0zVsXXb/05LzHja826tn6J1a5npZYcfZ2oCv7hV4RD Sijd9m3Wl6z5oAQgoMu0+Zns6252ib1gWtUsqnca0c71lPU3+YSlRNxWogqE/XlFYnSp a4bGyA1N4H/9HhlIwdB22JGh2ZsPySYR18Cc953cDdhu+vjU3RRISIMoh6eOs7gLcjJi LFqw== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:sender:references:in-reply-to:message-id:date :subject:cc:to:from:arc-authentication-results; bh=Q9Hp4pWQlDYjnzskVUR2+VMUfYJqhcB1aGEbKTARt0k=; b=yz38ZMcK4CQeJntnsejLr7G0EBxbtpQBi4shlVCPvl225SrFNZz6m3Jqj0xB2naTgs DMYtsZ7clGholhghjQcO5DFLtyUResc2vo5iotq7V9r4qa6V5LBXSYnDMO5U9VhucRSU O4DmLTPKn4e1fsquGHMMeLBHgMRLaI/h+9HV3ZxtaJfVNgYOWoG035CXjiX2Lp1JjjyY bFWuRPppiXi3zVSFKCvRxQF9W1MbvUlozWE8MXR84ofQsq1N0QFvgr3sUfmAc+9bQLwR mcBwgN2WoXns3IGcg9AzgcbDJGjA5io9X86LKxHNNs6KP4UkEkEEe8ZlQS2sj/O/NyzP rcfg== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from vger.kernel.org (vger.kernel.org. [209.132.180.67]) by mx.google.com with ESMTP id k130si24058235pga.169.2017.06.06.16.25.44; Tue, 06 Jun 2017 16:25:44 -0700 (PDT) Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67; Authentication-Results: mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751605AbdFFXZ0 (ORCPT + 25 others); Tue, 6 Jun 2017 19:25:26 -0400 Received: from alt22.smtp-out.videotron.ca ([70.80.0.73]:30801 "EHLO alt22.smtp-out.videotron.ca" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751419AbdFFXZD (ORCPT ); Tue, 6 Jun 2017 19:25:03 -0400 Received: from yoda.home ([96.23.157.65]) by Videotron with SMTP id INqOdHhP3PTiyINqPdLUDt; Tue, 06 Jun 2017 19:25:01 -0400 X-Authority-Analysis: v=2.1 cv=L469O7n8 c=1 sm=1 tr=0 a=keA3yYpnlypCNW5BNWqu+w==:117 a=keA3yYpnlypCNW5BNWqu+w==:17 a=L9H7d07YOLsA:10 a=9cW_t1CCXrUA:10 a=s5jvgZ67dGcA:10 a=LWSFodeU3zMA:10 a=KKAkSRfTAAAA:8 a=fEWo_HegFTfSf3SAovgA:9 a=7Zwj6sZBwVKJAoWSPKxL6X1jA+E=:19 a=cvBusfyB2V15izCimMoJ:22 Received: from xanadu.home (xanadu.home [192.168.2.2]) by yoda.home (Postfix) with ESMTP id 52CD92DA06F3; Tue, 6 Jun 2017 19:24:59 -0400 (EDT) From: Nicolas Pitre To: Ingo Molnar , Peter Zijlstra Cc: linux-kernel@vger.kernel.org Subject: [PATCH v2 6/8] sched/deadline: make it configurable Date: Tue, 6 Jun 2017 19:24:48 -0400 Message-Id: <20170606232450.30278-7-nicolas.pitre@linaro.org> X-Mailer: git-send-email 2.9.4 In-Reply-To: <20170606232450.30278-1-nicolas.pitre@linaro.org> References: <20170606232450.30278-1-nicolas.pitre@linaro.org> X-CMAE-Envelope: MS4wfKNPmhSzK2WIc3XpjFoXpQFtP8dG7x2/mOFwC4AOeXYNMRL0XM9XBNuPmWoTrIG7s/Zl9qcWeGEjAGFnz382IKwOxqDIUVvQhkALWOCw9Q0vOHSKnP6d GHiPLNiuK056ZwQ3N2MAo3ke/si1vaUnmGlcErzjKAOxNXeqC+odMcI/xDKN0H2z8k25b1xvG0msnMoss9gHj8bmqQuP235PVsshfgfSDrt9ttn6hDyJJ7Pa Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On most small systems, the deadline scheduler class is a luxury that rarely gets used if at all. It is preferable to have the ability to configure it out to reduce the kernel size in that case. Signed-off-by: Nicolas Pitre --- include/linux/sched.h | 2 ++ include/linux/sched/deadline.h | 8 +++++++- init/Kconfig | 8 ++++++++ kernel/locking/rtmutex.c | 6 +++--- kernel/sched/Makefile | 5 +++-- kernel/sched/core.c | 15 +++++++++------ kernel/sched/cpudeadline.h | 7 ++++++- kernel/sched/debug.c | 4 ++++ kernel/sched/rt.c | 13 ++++++++----- kernel/sched/sched.h | 38 +++++++++++++++++++++++++++++++------- kernel/sched/stop_task.c | 4 ++++ 11 files changed, 85 insertions(+), 25 deletions(-) -- 2.9.4 diff --git a/include/linux/sched.h b/include/linux/sched.h index 2b69fc6502..ba0c203669 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -522,7 +522,9 @@ struct task_struct { #ifdef CONFIG_CGROUP_SCHED struct task_group *sched_task_group; #endif +#ifdef CONFIG_SCHED_DL struct sched_dl_entity dl; +#endif #ifdef CONFIG_PREEMPT_NOTIFIERS /* List of struct preempt_notifier: */ diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 975be862e0..8f191a17dd 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -13,7 +13,7 @@ static inline int dl_prio(int prio) { - if (unlikely(prio < MAX_DL_PRIO)) + if (IS_ENABLED(CONFIG_SCHED_DL) && unlikely(prio < MAX_DL_PRIO)) return 1; return 0; } @@ -28,4 +28,10 @@ static inline bool dl_time_before(u64 a, u64 b) return (s64)(a - b) < 0; } +#ifdef CONFIG_SCHED_DL +#define dl_deadline(tsk) (tsk)->dl.deadline +#else +#define dl_deadline(tsk) 0 +#endif + #endif /* _LINUX_SCHED_DEADLINE_H */ diff --git a/init/Kconfig b/init/Kconfig index ad91724f75..43e6ae3414 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1303,6 +1303,14 @@ config SCHED_AUTOGROUP desktop applications. Task group autogeneration is currently based upon task session. +config SCHED_DL + bool "Deadline Task Scheduling" if EXPERT + default y + help + This adds the sched_dl scheduling class to the kernel providing + support for the SCHED_DEADLINE policy. You might want to disable + this to reduce the kernel size. If unsure say y. + config SYSFS_DEPRECATED bool "Enable deprecated sysfs features to support old userspace tools" depends on SYSFS diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 28cd09e635..1deabf9ebd 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -228,7 +228,7 @@ static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock, * Only use with rt_mutex_waiter_{less,equal}() */ #define task_to_waiter(p) \ - &(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline } + &(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = dl_deadline(p) } static inline int rt_mutex_waiter_less(struct rt_mutex_waiter *left, @@ -692,7 +692,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * the values of the node being removed. */ waiter->prio = task->prio; - waiter->deadline = task->dl.deadline; + waiter->deadline = dl_deadline(task); rt_mutex_enqueue(lock, waiter); @@ -967,7 +967,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, waiter->task = task; waiter->lock = lock; waiter->prio = task->prio; - waiter->deadline = task->dl.deadline; + waiter->deadline = dl_deadline(task); /* Get the top priority waiter on the lock */ if (rt_mutex_has_waiters(lock)) diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 5e4c2e7a63..3bd6a7c1cc 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -16,9 +16,10 @@ CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer endif obj-y += core.o loadavg.o clock.o cputime.o -obj-y += idle_task.o fair.o rt.o deadline.o obj-y += wait.o swait.o completion.o idle.o -obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o +obj-y += idle_task.o fair.o rt.o +obj-$(CONFIG_SCHED_DL) += deadline.o $(if $(CONFIG_SMP),cpudeadline.o) +obj-$(CONFIG_SMP) += cpupri.o topology.o stop_task.o obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o obj-$(CONFIG_SCHEDSTATS) += stats.o obj-$(CONFIG_SCHED_DEBUG) += debug.o diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9923c4b742..30138033b7 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -635,7 +635,7 @@ bool sched_can_stop_tick(struct rq *rq) int fifo_nr_running; /* Deadline tasks, even if single, need the tick */ - if (rq->dl.dl_nr_running) + if (dl_nr_running(rq)) return false; /* @@ -2174,9 +2174,11 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) memset(&p->se.statistics, 0, sizeof(p->se.statistics)); #endif +#ifdef CONFIG_SCHED_DL RB_CLEAR_NODE(&p->dl.rb_node); init_dl_task_timer(&p->dl); __dl_clear_params(p); +#endif INIT_LIST_HEAD(&p->rt.run_list); p->rt.timeout = 0; @@ -3702,20 +3704,20 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) if (dl_prio(prio)) { if (!dl_prio(p->normal_prio) || (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) { - p->dl.dl_boosted = 1; + dl_boosted(p) = 1; queue_flag |= ENQUEUE_REPLENISH; } else - p->dl.dl_boosted = 0; + dl_boosted(p) = 0; p->sched_class = &dl_sched_class; } else if (rt_prio(prio)) { if (dl_prio(oldprio)) - p->dl.dl_boosted = 0; + dl_boosted(p) = 0; if (oldprio < prio) queue_flag |= ENQUEUE_HEAD; p->sched_class = &rt_sched_class; } else { if (dl_prio(oldprio)) - p->dl.dl_boosted = 0; + dl_boosted(p) = 0; if (rt_prio(oldprio)) p->rt.timeout = 0; p->sched_class = &fair_sched_class; @@ -5266,7 +5268,8 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur, if (!cpumask_weight(cur)) return ret; - ret = dl_cpuset_cpumask_can_shrink(cur, trial); + if (IS_ENABLED(CONFIG_SCHED_DL)) + ret = dl_cpuset_cpumask_can_shrink(cur, trial); return ret; } diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h index f7da8c55bb..5f4c10f837 100644 --- a/kernel/sched/cpudeadline.h +++ b/kernel/sched/cpudeadline.h @@ -25,10 +25,15 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p, struct cpumask *later_mask); void cpudl_set(struct cpudl *cp, int cpu, u64 dl); void cpudl_clear(struct cpudl *cp, int cpu); -int cpudl_init(struct cpudl *cp); void cpudl_set_freecpu(struct cpudl *cp, int cpu); void cpudl_clear_freecpu(struct cpudl *cp, int cpu); +#ifdef CONFIG_SCHED_DL +int cpudl_init(struct cpudl *cp); void cpudl_cleanup(struct cpudl *cp); +#else +#define cpudl_init(cp) 0 +#define cpudl_cleanup(cp) do { } while (0) +#endif #endif /* CONFIG_SMP */ #endif /* _LINUX_CPUDL_H */ diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 38f019324f..84f80a81ab 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -646,7 +646,9 @@ do { \ spin_lock_irqsave(&sched_debug_lock, flags); print_cfs_stats(m, cpu); print_rt_stats(m, cpu); +#ifdef CONFIG_SCHED_DL print_dl_stats(m, cpu); +#endif print_rq(m, rq, cpu); spin_unlock_irqrestore(&sched_debug_lock, flags); @@ -954,10 +956,12 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) #endif P(policy); P(prio); +#ifdef CONFIG_SCHED_DL if (p->policy == SCHED_DEADLINE) { P(dl.runtime); P(dl.deadline); } +#endif #undef PN_SCHEDSTAT #undef PN #undef __PN diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 29c48a6cfb..02ac9b336f 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1545,7 +1545,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) * to re-start task selection. */ if (unlikely((rq->stop && task_on_rq_queued(rq->stop)) || - rq->dl.dl_nr_running)) + dl_nr_running(rq))) return RETRY_TASK; } @@ -2705,16 +2705,19 @@ int sched_rt_handler(struct ctl_table *table, int write, if (ret) goto undo; - ret = sched_dl_global_validate(); - if (ret) - goto undo; + if (IS_ENABLED(CONFIG_SCHED_DL)) { + ret = sched_dl_global_validate(); + if (ret) + goto undo; + } ret = sched_rt_global_constraints(); if (ret) goto undo; sched_rt_do_global(); - sched_dl_do_global(); + if (IS_ENABLED(CONFIG_SCHED_DL)) + sched_dl_do_global(); } if (0) { undo: diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 84ab1be493..c05cc33848 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -137,7 +137,7 @@ static inline int rt_policy(int policy) static inline int dl_policy(int policy) { - return policy == SCHED_DEADLINE; + return IS_ENABLED(CONFIG_SCHED_DL) && policy == SCHED_DEADLINE; } static inline bool valid_policy(int policy) { @@ -158,11 +158,15 @@ static inline int task_has_dl_policy(struct task_struct *p) /* * Tells if entity @a should preempt entity @b. */ +#ifdef CONFIG_SCHED_DL static inline bool dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b) { return dl_time_before(a->deadline, b->deadline); } +#else +#define dl_entity_preempt(a, b) false +#endif /* * This is the priority-queue data structure of the RT scheduling class: @@ -244,7 +248,6 @@ bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw) dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw; } -extern void init_dl_bw(struct dl_bw *dl_b); extern int sched_dl_global_validate(void); extern void sched_dl_do_global(void); extern int sched_dl_overflow(struct task_struct *p, int policy, @@ -258,7 +261,27 @@ extern int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed); extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); +extern struct dl_bandwidth def_dl_bandwidth; + +struct dl_rq; + +#ifdef CONFIG_SCHED_DL +#define dl_nr_running(rq) (rq)->dl.dl_nr_running +#define dl_boosted(tsk) (tsk)->dl.dl_boosted extern bool dl_cpu_busy(unsigned int cpu); +extern void init_dl_bw(struct dl_bw *dl_b); +extern void init_sched_dl_class(void); +extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime); +extern void init_dl_rq(struct dl_rq *dl_rq); +#else +#define dl_nr_running(rq) 0 +#define dl_boosted(tsk) (*(int *)0) +#define dl_cpu_busy(cpu) false +#define init_dl_bw(dl_b) do { } while (0) +#define init_sched_dl_class() do { } while (0) +#define init_dl_bandwidth(...) do { } while (0) +#define init_dl_rq(dl_rq) do { } while (0) +#endif #ifdef CONFIG_CGROUP_SCHED @@ -672,7 +695,9 @@ struct rq { struct cfs_rq cfs; struct rt_rq rt; +#ifdef CONFIG_SCHED_DL struct dl_rq dl; +#endif #ifdef CONFIG_FAIR_GROUP_SCHED /* list of leaf cfs_rq on this cpu: */ @@ -1443,9 +1468,12 @@ static inline void set_curr_task(struct rq *rq, struct task_struct *curr) #ifdef CONFIG_SMP #define sched_class_highest (&stop_sched_class) -#else +#elif defined(CONFIG_SCHED_DL) #define sched_class_highest (&dl_sched_class) +#else +#define sched_class_highest (&rt_sched_class) #endif + #define for_each_class(class) \ for (class = sched_class_highest; class; class = class->next) @@ -1496,7 +1524,6 @@ extern void sysrq_sched_debug_show(void); extern void sched_init_granularity(void); extern void update_max_interval(void); -extern void init_sched_dl_class(void); extern void init_sched_rt_class(void); extern void init_sched_fair_class(void); @@ -1506,8 +1533,6 @@ extern void resched_cpu(int cpu); extern struct rt_bandwidth def_rt_bandwidth; extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); -extern struct dl_bandwidth def_dl_bandwidth; -extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime); extern void init_dl_task_timer(struct sched_dl_entity *dl_se); unsigned long to_ratio(u64 period, u64 runtime); @@ -1933,7 +1958,6 @@ print_numa_stats(struct seq_file *m, int node, unsigned long tsf, extern void init_cfs_rq(struct cfs_rq *cfs_rq); extern void init_rt_rq(struct rt_rq *rt_rq); -extern void init_dl_rq(struct dl_rq *dl_rq); extern void cfs_bandwidth_usage_inc(void); extern void cfs_bandwidth_usage_dec(void); diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index 9f69fb6308..5632dc3e63 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -110,7 +110,11 @@ static void update_curr_stop(struct rq *rq) * Simple, special scheduling class for the per-CPU stop tasks: */ const struct sched_class stop_sched_class = { +#ifdef CONFIG_SCHED_DL .next = &dl_sched_class, +#else + .next = &rt_sched_class, +#endif .enqueue_task = enqueue_task_stop, .dequeue_task = dequeue_task_stop,