From a364298359e74a414857bbbf3b725564feb22d09 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 21 Feb 2018 05:17:24 +0100 Subject: nohz: Convert tick_nohz_tick_stopped() to bool It makes this function more self-explanatory about what it does and how to use it. Reported-by: Thomas Gleixner Signed-off-by: Frederic Weisbecker Reviewed-by: Thomas Gleixner Acked-by: Peter Zijlstra Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1519186649-3242-3-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/tick.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index 7cc35921218e..86576d9d2311 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -113,7 +113,7 @@ enum tick_dep_bits { #ifdef CONFIG_NO_HZ_COMMON extern bool tick_nohz_enabled; -extern int tick_nohz_tick_stopped(void); +extern bool tick_nohz_tick_stopped(void); extern void tick_nohz_idle_enter(void); extern void tick_nohz_idle_exit(void); extern void tick_nohz_irq_exit(void); -- cgit v1.2.3 From 22ab8bc02a5f6e8ffc418759894f7a6b0b632331 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 21 Feb 2018 05:17:25 +0100 Subject: nohz: Allow to check if remote CPU tick is stopped This check is racy but provides a good heuristic to determine whether a CPU may need a remote tick or not. Signed-off-by: Frederic Weisbecker Reviewed-by: Thomas Gleixner Acked-by: Peter Zijlstra Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1519186649-3242-4-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/tick.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index 86576d9d2311..7f8c9a127f5a 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -114,6 +114,7 @@ enum tick_dep_bits { #ifdef CONFIG_NO_HZ_COMMON extern bool tick_nohz_enabled; extern bool tick_nohz_tick_stopped(void); +extern bool tick_nohz_tick_stopped_cpu(int cpu); extern void tick_nohz_idle_enter(void); extern void tick_nohz_idle_exit(void); extern void tick_nohz_irq_exit(void); @@ -125,6 +126,7 @@ extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); #else /* !CONFIG_NO_HZ_COMMON */ #define tick_nohz_enabled (0) static inline int tick_nohz_tick_stopped(void) { return 0; } +static inline int tick_nohz_tick_stopped_cpu(int cpu) { return 0; } static inline void tick_nohz_idle_enter(void) { } static inline void tick_nohz_idle_exit(void) { } -- cgit v1.2.3 From 1bda3f8087fce9063da0b8aef87f17a3fe541aca Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 21 Feb 2018 05:17:26 +0100 Subject: sched/isolation: Isolate workqueues when "nohz_full=" is set As we prepare for offloading the residual 1hz scheduler ticks to workqueue, let's affine those to housekeepers so that they don't interrupt the CPUs that don't want to be disturbed. Signed-off-by: Frederic Weisbecker Reviewed-by: Thomas Gleixner Acked-by: Peter Zijlstra Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1519186649-3242-5-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/isolation.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index d849431c8060..4a6582c27dea 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -12,6 +12,7 @@ enum hk_flags { HK_FLAG_SCHED = (1 << 3), HK_FLAG_TICK = (1 << 4), HK_FLAG_DOMAIN = (1 << 5), + HK_FLAG_WQ = (1 << 6), }; #ifdef CONFIG_CPU_ISOLATION -- cgit v1.2.3 From dcdedb24159be3487e3dbbe1faa79ae7d00c92ac Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 21 Feb 2018 05:17:28 +0100 Subject: sched/nohz: Remove the 1 Hz tick code Now that the 1Hz tick is offloaded to workqueues, we can safely remove the residual code that used to handle it locally. Signed-off-by: Frederic Weisbecker Reviewed-by: Thomas Gleixner Acked-by: Peter Zijlstra Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1519186649-3242-7-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/nohz.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h index 3d3a97d9399d..094217273ff9 100644 --- a/include/linux/sched/nohz.h +++ b/include/linux/sched/nohz.h @@ -37,8 +37,4 @@ extern void wake_up_nohz_cpu(int cpu); static inline void wake_up_nohz_cpu(int cpu) { } #endif -#ifdef CONFIG_NO_HZ_FULL -extern u64 scheduler_tick_max_deferment(void); -#endif - #endif /* _LINUX_SCHED_NOHZ_H */ -- cgit v1.2.3 From 325ea10c0809406ce23f038602abbc454f3f761d Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 3 Mar 2018 12:20:47 +0100 Subject: sched/headers: Simplify and clean up header usage in the scheduler Do the following cleanups and simplifications: - sched/sched.h already includes , so no need to include it in sched/core.c again. - order the headers alphabetically - add all headers to kernel/sched/sched.h - remove all unnecessary includes from the .c files that are already included in kernel/sched/sched.h. Finally, make all scheduler .c files use a single common header: #include "sched.h" ... which now contains a union of the relied upon headers. This makes the various .c files easier to read and easier to handle. Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/deadline.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index a5bc8728ead7..0cb034331cbb 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -1,8 +1,4 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_SCHED_DEADLINE_H -#define _LINUX_SCHED_DEADLINE_H - -#include /* * SCHED_DEADLINE tasks has negative priorities, reflecting @@ -28,5 +24,3 @@ static inline bool dl_time_before(u64 a, u64 b) { return (s64)(a - b) < 0; } - -#endif /* _LINUX_SCHED_DEADLINE_H */ -- cgit v1.2.3 From 4042d003a0792a3b05c7c424219e4c6cf1abfe76 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 20 Dec 2017 15:37:26 +0100 Subject: cpufreq/schedutil: Remove unused CPUFREQ_DL Bitrot... Signed-off-by: Peter Zijlstra (Intel) Cc: Juri Lelli Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Thomas Gleixner Cc: Viresh Kumar Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/cpufreq.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h index 0b55834efd46..d963cfd3a0c2 100644 --- a/include/linux/sched/cpufreq.h +++ b/include/linux/sched/cpufreq.h @@ -9,8 +9,7 @@ */ #define SCHED_CPUFREQ_RT (1U << 0) -#define SCHED_CPUFREQ_DL (1U << 1) -#define SCHED_CPUFREQ_IOWAIT (1U << 2) +#define SCHED_CPUFREQ_IOWAIT (1U << 1) #ifdef CONFIG_CPU_FREQ struct update_util_data { -- cgit v1.2.3 From 8f111bc357aa811e0bb5fdfe34c4c9efdafc15b9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 20 Dec 2017 16:26:12 +0100 Subject: cpufreq/schedutil: Rewrite CPUFREQ_RT support Instead of trying to duplicate scheduler state to track if an RT task is running, directly use the scheduler runqueue state for it. This vastly simplifies things and fixes a number of bugs related to sugov and the scheduler getting out of sync wrt this state. As a consequence we not also update the remove cfs/dl state when iterating the shared mask. Signed-off-by: Peter Zijlstra (Intel) Cc: Juri Lelli Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Thomas Gleixner Cc: Viresh Kumar Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/cpufreq.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h index d963cfd3a0c2..b48f2fb3b316 100644 --- a/include/linux/sched/cpufreq.h +++ b/include/linux/sched/cpufreq.h @@ -8,8 +8,7 @@ * Interface between cpufreq drivers and the scheduler: */ -#define SCHED_CPUFREQ_RT (1U << 0) -#define SCHED_CPUFREQ_IOWAIT (1U << 1) +#define SCHED_CPUFREQ_IOWAIT (1U << 0) #ifdef CONFIG_CPU_FREQ struct update_util_data { -- cgit v1.2.3 From 00357f5ec5d67a52a175da6f29f85c2c19d59bc8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 21 Dec 2017 15:06:50 +0100 Subject: sched/nohz: Clean up nohz enter/exit The primary observation is that nohz enter/exit is always from the current CPU, therefore NOHZ_TICK_STOPPED does not in fact need to be an atomic. Secondary is that we appear to have 2 nearly identical hooks in the nohz enter code, set_cpu_sd_state_idle() and nohz_balance_enter_idle(). Fold the whole set_cpu_sd_state thing into nohz_balance_{enter,exit}_idle. Removes an atomic op from both enter and exit paths. Signed-off-by: Peter Zijlstra (Intel) Cc: Frederic Weisbecker Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/nohz.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h index 094217273ff9..b36f4cf38111 100644 --- a/include/linux/sched/nohz.h +++ b/include/linux/sched/nohz.h @@ -16,11 +16,9 @@ static inline void cpu_load_update_nohz_stop(void) { } #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) extern void nohz_balance_enter_idle(int cpu); -extern void set_cpu_sd_state_idle(void); extern int get_nohz_timer_target(void); #else static inline void nohz_balance_enter_idle(int cpu) { } -static inline void set_cpu_sd_state_idle(void) { } #endif #ifdef CONFIG_NO_HZ_COMMON -- cgit v1.2.3 From ea14b57e8a181ac0561eba7a787e088f8c89f822 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 2 Feb 2018 10:27:00 +0100 Subject: sched/cpufreq: Provide migration hint It was suggested that a migration hint might be usefull for the CPU-freq governors. Signed-off-by: Peter Zijlstra (Intel) Cc: Juri Lelli Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Thomas Gleixner Cc: Viresh Kumar Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/cpufreq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h index b48f2fb3b316..59667444669f 100644 --- a/include/linux/sched/cpufreq.h +++ b/include/linux/sched/cpufreq.h @@ -9,6 +9,7 @@ */ #define SCHED_CPUFREQ_IOWAIT (1U << 0) +#define SCHED_CPUFREQ_MIGRATION (1U << 1) #ifdef CONFIG_CPU_FREQ struct update_util_data { -- cgit v1.2.3 From 9e49e2447c6385e45c6fddd70d6c0e917e21b669 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 27 Feb 2018 17:05:10 +0100 Subject: sched/core: Remove TASK_ALL It's unused: $ git grep "\" | wc -l 1 ... and it is also dangerous, kill the bugger. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Sebastian Andrzej Siewior Acked-by: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20180227160510.10829-1-bigeasy@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b161ef8a902e..21b1168da951 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -93,7 +93,6 @@ struct task_group; /* Convenience macros for the sake of wake_up(): */ #define TASK_NORMAL (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE) -#define TASK_ALL (TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED) /* get_task_state(): */ #define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \ -- cgit v1.2.3 From 7f65ea42eb00bc902f1c37a71e984e4f4064cfa9 Mon Sep 17 00:00:00 2001 From: Patrick Bellasi Date: Fri, 9 Mar 2018 09:52:42 +0000 Subject: sched/fair: Add util_est on top of PELT The util_avg signal computed by PELT is too variable for some use-cases. For example, a big task waking up after a long sleep period will have its utilization almost completely decayed. This introduces some latency before schedutil will be able to pick the best frequency to run a task. The same issue can affect task placement. Indeed, since the task utilization is already decayed at wakeup, when the task is enqueued in a CPU, this can result in a CPU running a big task as being temporarily represented as being almost empty. This leads to a race condition where other tasks can be potentially allocated on a CPU which just started to run a big task which slept for a relatively long period. Moreover, the PELT utilization of a task can be updated every [ms], thus making it a continuously changing value for certain longer running tasks. This means that the instantaneous PELT utilization of a RUNNING task is not really meaningful to properly support scheduler decisions. For all these reasons, a more stable signal can do a better job of representing the expected/estimated utilization of a task/cfs_rq. Such a signal can be easily created on top of PELT by still using it as an estimator which produces values to be aggregated on meaningful events. This patch adds a simple implementation of util_est, a new signal built on top of PELT's util_avg where: util_est(task) = max(task::util_avg, f(task::util_avg@dequeue)) This allows to remember how big a task has been reported by PELT in its previous activations via f(task::util_avg@dequeue), which is the new _task_util_est(struct task_struct*) function added by this patch. If a task should change its behavior and it runs longer in a new activation, after a certain time its util_est will just track the original PELT signal (i.e. task::util_avg). The estimated utilization of cfs_rq is defined only for root ones. That's because the only sensible consumer of this signal are the scheduler and schedutil when looking for the overall CPU utilization due to FAIR tasks. For this reason, the estimated utilization of a root cfs_rq is simply defined as: util_est(cfs_rq) = max(cfs_rq::util_avg, cfs_rq::util_est::enqueued) where: cfs_rq::util_est::enqueued = sum(_task_util_est(task)) for each RUNNABLE task on that root cfs_rq It's worth noting that the estimated utilization is tracked only for objects of interests, specifically: - Tasks: to better support tasks placement decisions - root cfs_rqs: to better support both tasks placement decisions as well as frequencies selection Signed-off-by: Patrick Bellasi Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Dietmar Eggemann Cc: Joel Fernandes Cc: Juri Lelli Cc: Linus Torvalds Cc: Morten Rasmussen Cc: Paul Turner Cc: Rafael J . Wysocki Cc: Steve Muckle Cc: Thomas Gleixner Cc: Todd Kjos Cc: Vincent Guittot Cc: Viresh Kumar Link: http://lkml.kernel.org/r/20180309095245.11071-2-patrick.bellasi@arm.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 21b1168da951..f228c6033832 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -274,6 +274,34 @@ struct load_weight { u32 inv_weight; }; +/** + * struct util_est - Estimation utilization of FAIR tasks + * @enqueued: instantaneous estimated utilization of a task/cpu + * @ewma: the Exponential Weighted Moving Average (EWMA) + * utilization of a task + * + * Support data structure to track an Exponential Weighted Moving Average + * (EWMA) of a FAIR task's utilization. New samples are added to the moving + * average each time a task completes an activation. Sample's weight is chosen + * so that the EWMA will be relatively insensitive to transient changes to the + * task's workload. + * + * The enqueued attribute has a slightly different meaning for tasks and cpus: + * - task: the task's util_avg at last task dequeue time + * - cfs_rq: the sum of util_est.enqueued for each RUNNABLE task on that CPU + * Thus, the util_est.enqueued of a task represents the contribution on the + * estimated utilization of the CPU where that task is currently enqueued. + * + * Only for tasks we track a moving average of the past instantaneous + * estimated utilization. This allows to absorb sporadic drops in utilization + * of an otherwise almost periodic task. + */ +struct util_est { + unsigned int enqueued; + unsigned int ewma; +#define UTIL_EST_WEIGHT_SHIFT 2 +}; + /* * The load_avg/util_avg accumulates an infinite geometric series * (see __update_load_avg() in kernel/sched/fair.c). @@ -335,6 +363,7 @@ struct sched_avg { unsigned long load_avg; unsigned long runnable_load_avg; unsigned long util_avg; + struct util_est util_est; }; struct sched_statistics { -- cgit v1.2.3