From 3bd3706251ee8ab67e69d9340ac2abdca217e733 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 23 Apr 2019 16:26:36 +0200 Subject: sched/core: Provide a pointer to the valid CPU mask In commit: 4b53a3412d66 ("sched/core: Remove the tsk_nr_cpus_allowed() wrapper") the tsk_nr_cpus_allowed() wrapper was removed. There was not much difference in !RT but in RT we used this to implement migrate_disable(). Within a migrate_disable() section the CPU mask is restricted to single CPU while the "normal" CPU mask remains untouched. As an alternative implementation Ingo suggested to use: struct task_struct { const cpumask_t *cpus_ptr; cpumask_t cpus_mask; }; with t->cpus_ptr = &t->cpus_mask; In -RT we then can switch the cpus_ptr to: t->cpus_ptr = &cpumask_of(task_cpu(p)); in a migration disabled region. The rules are simple: - Code that 'uses' ->cpus_allowed would use the pointer. - Code that 'modifies' ->cpus_allowed would use the direct mask. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Link: https://lkml.kernel.org/r/20190423142636.14347-1-bigeasy@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/sched.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 11837410690f..1b2590a8d038 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -651,7 +651,8 @@ struct task_struct { unsigned int policy; int nr_cpus_allowed; - cpumask_t cpus_allowed; + const cpumask_t *cpus_ptr; + cpumask_t cpus_mask; #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; @@ -1399,7 +1400,7 @@ extern struct pid *cad_pid; #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ #define PF_MEMSTALL 0x01000000 /* Stalled due to lack of memory */ #define PF_UMH 0x02000000 /* I'm an Usermodehelper process */ -#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ +#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_NOCMA 0x10000000 /* All allocation request will have _GFP_MOVABLE cleared */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ -- cgit v1.2.3 From 5e83eafbfd3b351537c0d74467fc43e8a88f4ae4 Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Mon, 27 May 2019 07:21:10 +0100 Subject: sched/fair: Remove the rq->cpu_load[] update code With LB_BIAS disabled, there is no need to update the rq->cpu_load[idx] any more. Signed-off-by: Dietmar Eggemann Signed-off-by: Peter Zijlstra (Intel) Acked-by: Rik van Riel Cc: Frederic Weisbecker Cc: Linus Torvalds Cc: Morten Rasmussen Cc: Patrick Bellasi Cc: Peter Zijlstra Cc: Quentin Perret Cc: Thomas Gleixner Cc: Valentin Schneider Cc: Vincent Guittot Link: https://lkml.kernel.org/r/20190527062116.11512-2-dietmar.eggemann@arm.com Signed-off-by: Ingo Molnar --- include/linux/sched/nohz.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h index b36f4cf38111..1abe91ff6e4a 100644 --- a/include/linux/sched/nohz.h +++ b/include/linux/sched/nohz.h @@ -6,14 +6,6 @@ * This is the interface between the scheduler and nohz/dynticks: */ -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) -extern void cpu_load_update_nohz_start(void); -extern void cpu_load_update_nohz_stop(void); -#else -static inline void cpu_load_update_nohz_start(void) { } -static inline void cpu_load_update_nohz_stop(void) { } -#endif - #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) extern void nohz_balance_enter_idle(int cpu); extern int get_nohz_timer_target(void); -- cgit v1.2.3 From 0e1fef63d92d61ed561e504c3a078a827a0f9bfe Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Mon, 27 May 2019 07:21:14 +0100 Subject: sched/core: Remove sd->*_idx The sched domain per rq load index files also disappear from the /proc/sys/kernel/sched_domain/cpuX/domainY directories. Signed-off-by: Dietmar Eggemann Signed-off-by: Peter Zijlstra (Intel) Acked-by: Rik van Riel Cc: Frederic Weisbecker Cc: Linus Torvalds Cc: Morten Rasmussen Cc: Patrick Bellasi Cc: Peter Zijlstra Cc: Quentin Perret Cc: Thomas Gleixner Cc: Valentin Schneider Cc: Vincent Guittot Link: https://lkml.kernel.org/r/20190527062116.11512-6-dietmar.eggemann@arm.com Signed-off-by: Ingo Molnar --- include/linux/sched/topology.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index cfc0a89a7159..53afbe07354a 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -84,11 +84,6 @@ struct sched_domain { unsigned int busy_factor; /* less balancing by factor if busy */ unsigned int imbalance_pct; /* No balance until over watermark */ unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */ - unsigned int busy_idx; - unsigned int idle_idx; - unsigned int newidle_idx; - unsigned int wake_idx; - unsigned int forkexec_idx; int nohz_idle; /* NOHZ IDLE status */ int flags; /* See SD_* */ -- cgit v1.2.3 From 8ec59c0f5f4966f89f4e3e3cab81710c7fa959d0 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Mon, 17 Jun 2019 17:00:17 +0200 Subject: sched/topology: Remove unused 'sd' parameter from arch_scale_cpu_capacity() The 'struct sched_domain *sd' parameter to arch_scale_cpu_capacity() is unused since commit: 765d0af19f5f ("sched/topology: Remove the ::smt_gain field from 'struct sched_domain'") Remove it. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Viresh Kumar Reviewed-by: Valentin Schneider Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: gregkh@linuxfoundation.org Cc: linux@armlinux.org.uk Cc: quentin.perret@arm.com Cc: rafael@kernel.org Link: https://lkml.kernel.org/r/1560783617-5827-1-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- include/linux/arch_topology.h | 2 +- include/linux/energy_model.h | 2 +- include/linux/sched/topology.h | 14 +++----------- 3 files changed, 5 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index d9bdc1a7f4e7..1cfe05ea1d89 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -18,7 +18,7 @@ DECLARE_PER_CPU(unsigned long, cpu_scale); struct sched_domain; static inline -unsigned long topology_get_cpu_scale(struct sched_domain *sd, int cpu) +unsigned long topology_get_cpu_scale(int cpu) { return per_cpu(cpu_scale, cpu); } diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index aa027f7bcb3e..73f8c3cb9588 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -89,7 +89,7 @@ static inline unsigned long em_pd_energy(struct em_perf_domain *pd, * like schedutil. */ cpu = cpumask_first(to_cpumask(pd->cpus)); - scale_cpu = arch_scale_cpu_capacity(NULL, cpu); + scale_cpu = arch_scale_cpu_capacity(cpu); cs = &pd->table[pd->nr_cap_states - 1]; freq = map_util_freq(max_util, cs->frequency, scale_cpu); diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 53afbe07354a..e445d3767cdd 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -196,14 +196,6 @@ extern void set_sched_topology(struct sched_domain_topology_level *tl); # define SD_INIT_NAME(type) #endif -#ifndef arch_scale_cpu_capacity -static __always_inline -unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) -{ - return SCHED_CAPACITY_SCALE; -} -#endif - #else /* CONFIG_SMP */ struct sched_domain_attr; @@ -219,16 +211,16 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu) return true; } +#endif /* !CONFIG_SMP */ + #ifndef arch_scale_cpu_capacity static __always_inline -unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu) +unsigned long arch_scale_cpu_capacity(int cpu) { return SCHED_CAPACITY_SCALE; } #endif -#endif /* !CONFIG_SMP */ - static inline int task_node(const struct task_struct *p) { return cpu_to_node(task_cpu(p)); -- cgit v1.2.3 From 3c93a0c04dfdcba199982b53b97488b1b1d90eff Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Tue, 4 Jun 2019 12:14:55 +0100 Subject: sched/debug: Add a new sched_trace_*() helper functions The new functions allow modules to access internal data structures of unexported struct cfs_rq and struct rq to extract important information from the tracepoints to be introduced in later patches. While at it fix alphabetical order of struct declarations in sched.h Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Cc: Dietmar Eggemann Cc: Linus Torvalds Cc: Pavankumar Kondeti Cc: Peter Zijlstra Cc: Quentin Perret Cc: Sebastian Andrzej Siewior Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Uwe Kleine-Konig Link: https://lkml.kernel.org/r/20190604111459.2862-3-qais.yousef@arm.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 1b2590a8d038..044c023875e8 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -35,6 +35,7 @@ struct audit_context; struct backing_dev_info; struct bio_list; struct blk_plug; +struct capture_control; struct cfs_rq; struct fs_struct; struct futex_pi_state; @@ -47,8 +48,9 @@ struct pid_namespace; struct pipe_inode_info; struct rcu_node; struct reclaim_state; -struct capture_control; struct robust_list_head; +struct root_domain; +struct rq; struct sched_attr; struct sched_param; struct seq_file; @@ -1920,4 +1922,16 @@ static inline void rseq_syscall(struct pt_regs *regs) #endif +const struct sched_avg *sched_trace_cfs_rq_avg(struct cfs_rq *cfs_rq); +char *sched_trace_cfs_rq_path(struct cfs_rq *cfs_rq, char *str, int len); +int sched_trace_cfs_rq_cpu(struct cfs_rq *cfs_rq); + +const struct sched_avg *sched_trace_rq_avg_rt(struct rq *rq); +const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq); +const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq); + +int sched_trace_rq_cpu(struct rq *rq); + +const struct cpumask *sched_trace_rd_span(struct root_domain *rd); + #endif -- cgit v1.2.3 From ba19f51fcb549c7ee6261da243eea55a47e98d78 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Tue, 4 Jun 2019 12:14:56 +0100 Subject: sched/debug: Add new tracepoints to track PELT at rq level The new tracepoints allow tracking PELT signals at rq level for all scheduling classes + irq. Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Cc: Dietmar Eggemann Cc: Linus Torvalds Cc: Pavankumar Kondeti Cc: Peter Zijlstra Cc: Quentin Perret Cc: Sebastian Andrzej Siewior Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Uwe Kleine-Konig Link: https://lkml.kernel.org/r/20190604111459.2862-4-qais.yousef@arm.com Signed-off-by: Ingo Molnar --- include/trace/events/sched.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include') diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index c8c7c7efb487..520b89d384ec 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -594,6 +594,29 @@ TRACE_EVENT(sched_wake_idle_without_ipi, TP_printk("cpu=%d", __entry->cpu) ); + +/* + * Following tracepoints are not exported in tracefs and provide hooking + * mechanisms only for testing and debugging purposes. + * + * Postfixed with _tp to make them easily identifiable in the code. + */ +DECLARE_TRACE(pelt_cfs_tp, + TP_PROTO(struct cfs_rq *cfs_rq), + TP_ARGS(cfs_rq)); + +DECLARE_TRACE(pelt_rt_tp, + TP_PROTO(struct rq *rq), + TP_ARGS(rq)); + +DECLARE_TRACE(pelt_dl_tp, + TP_PROTO(struct rq *rq), + TP_ARGS(rq)); + +DECLARE_TRACE(pelt_irq_tp, + TP_PROTO(struct rq *rq), + TP_ARGS(rq)); + #endif /* _TRACE_SCHED_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 8de6242cca17d9299e654e29c966d8612d397272 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Tue, 4 Jun 2019 12:14:57 +0100 Subject: sched/debug: Add new tracepoint to track PELT at se level The new tracepoint allows tracking PELT signals at sched_entity level. Which is supported in CFS tasks and taskgroups only. Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Cc: Dietmar Eggemann Cc: Linus Torvalds Cc: Pavankumar Kondeti Cc: Peter Zijlstra Cc: Quentin Perret Cc: Sebastian Andrzej Siewior Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Uwe Kleine-Konig Link: https://lkml.kernel.org/r/20190604111459.2862-5-qais.yousef@arm.com Signed-off-by: Ingo Molnar --- include/trace/events/sched.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 520b89d384ec..c7dd9bc7f001 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -617,6 +617,10 @@ DECLARE_TRACE(pelt_irq_tp, TP_PROTO(struct rq *rq), TP_ARGS(rq)); +DECLARE_TRACE(pelt_se_tp, + TP_PROTO(struct sched_entity *se), + TP_ARGS(se)); + #endif /* _TRACE_SCHED_H */ /* This part must be outside protection */ -- cgit v1.2.3 From f9f240f96efc5bcec62379eac701523e11fbb45b Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Tue, 4 Jun 2019 12:14:58 +0100 Subject: sched/debug: Add sched_overutilized tracepoint The new tracepoint allows us to track the changes in overutilized status. Overutilized status is associated with EAS. It indicates that the system is in high performance state. EAS is disabled when the system is in this state since there's not much energy savings while high performance tasks are pushing the system to the limit and it's better to default to the spreading behavior of the scheduler. This tracepoint helps understanding and debugging the conditions under which this happens. Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Cc: Dietmar Eggemann Cc: Linus Torvalds Cc: Pavankumar Kondeti Cc: Peter Zijlstra Cc: Quentin Perret Cc: Sebastian Andrzej Siewior Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Uwe Kleine-Konig Link: https://lkml.kernel.org/r/20190604111459.2862-6-qais.yousef@arm.com Signed-off-by: Ingo Molnar --- include/trace/events/sched.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index c7dd9bc7f001..420e80e56e55 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -621,6 +621,10 @@ DECLARE_TRACE(pelt_se_tp, TP_PROTO(struct sched_entity *se), TP_ARGS(se)); +DECLARE_TRACE(sched_overutilized_tp, + TP_PROTO(struct root_domain *rd, bool overutilized), + TP_ARGS(rd, overutilized)); + #endif /* _TRACE_SCHED_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 69842cba9ace84849bb9b8edcdf2cefccd97901c Mon Sep 17 00:00:00 2001 From: Patrick Bellasi Date: Fri, 21 Jun 2019 09:42:02 +0100 Subject: sched/uclamp: Add CPU's clamp buckets refcounting Utilization clamping allows to clamp the CPU's utilization within a [util_min, util_max] range, depending on the set of RUNNABLE tasks on that CPU. Each task references two "clamp buckets" defining its minimum and maximum (util_{min,max}) utilization "clamp values". A CPU's clamp bucket is active if there is at least one RUNNABLE tasks enqueued on that CPU and refcounting that bucket. When a task is {en,de}queued {on,from} a rq, the set of active clamp buckets on that CPU can change. If the set of active clamp buckets changes for a CPU a new "aggregated" clamp value is computed for that CPU. This is because each clamp bucket enforces a different utilization clamp value. Clamp values are always MAX aggregated for both util_min and util_max. This ensures that no task can affect the performance of other co-scheduled tasks which are more boosted (i.e. with higher util_min clamp) or less capped (i.e. with higher util_max clamp). A task has: task_struct::uclamp[clamp_id]::bucket_id to track the "bucket index" of the CPU's clamp bucket it refcounts while enqueued, for each clamp index (clamp_id). A runqueue has: rq::uclamp[clamp_id]::bucket[bucket_id].tasks to track how many RUNNABLE tasks on that CPU refcount each clamp bucket (bucket_id) of a clamp index (clamp_id). It also has a: rq::uclamp[clamp_id]::bucket[bucket_id].value to track the clamp value of each clamp bucket (bucket_id) of a clamp index (clamp_id). The rq::uclamp::bucket[clamp_id][] array is scanned every time it's needed to find a new MAX aggregated clamp value for a clamp_id. This operation is required only when it's dequeued the last task of a clamp bucket tracking the current MAX aggregated clamp value. In this case, the CPU is either entering IDLE or going to schedule a less boosted or more clamped task. The expected number of different clamp values configured at build time is small enough to fit the full unordered array into a single cache line, for configurations of up to 7 buckets. Add to struct rq the basic data structures required to refcount the number of RUNNABLE tasks for each clamp bucket. Add also the max aggregation required to update the rq's clamp value at each enqueue/dequeue event. Use a simple linear mapping of clamp values into clamp buckets. Pre-compute and cache bucket_id to avoid integer divisions at enqueue/dequeue time. Signed-off-by: Patrick Bellasi Signed-off-by: Peter Zijlstra (Intel) Cc: Alessio Balsini Cc: Dietmar Eggemann Cc: Joel Fernandes Cc: Juri Lelli Cc: Linus Torvalds Cc: Morten Rasmussen Cc: Paul Turner Cc: Peter Zijlstra Cc: Quentin Perret Cc: Rafael J . Wysocki Cc: Steve Muckle Cc: Suren Baghdasaryan Cc: Tejun Heo Cc: Thomas Gleixner Cc: Todd Kjos Cc: Vincent Guittot Cc: Viresh Kumar Link: https://lkml.kernel.org/r/20190621084217.8167-2-patrick.bellasi@arm.com Signed-off-by: Ingo Molnar --- include/linux/log2.h | 34 ++++++++++++++++++++++++++++++++++ include/linux/sched.h | 39 +++++++++++++++++++++++++++++++++++++++ include/linux/sched/topology.h | 6 ------ 3 files changed, 73 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/log2.h b/include/linux/log2.h index 1aec01365ed4..83a4a3ca3e8a 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -220,4 +220,38 @@ int __order_base_2(unsigned long n) ilog2((n) - 1) + 1) : \ __order_base_2(n) \ ) + +static inline __attribute__((const)) +int __bits_per(unsigned long n) +{ + if (n < 2) + return 1; + if (is_power_of_2(n)) + return order_base_2(n) + 1; + return order_base_2(n); +} + +/** + * bits_per - calculate the number of bits required for the argument + * @n: parameter + * + * This is constant-capable and can be used for compile time + * initializations, e.g bitfields. + * + * The first few values calculated by this routine: + * bf(0) = 1 + * bf(1) = 1 + * bf(2) = 2 + * bf(3) = 2 + * bf(4) = 3 + * ... and so on. + */ +#define bits_per(n) \ +( \ + __builtin_constant_p(n) ? ( \ + ((n) == 0 || (n) == 1) \ + ? 1 : ilog2(n) + 1 \ + ) : \ + __bits_per(n) \ +) #endif /* _LINUX_LOG2_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 044c023875e8..80235bcd05f2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -283,6 +283,18 @@ struct vtime { u64 gtime; }; +/* + * Utilization clamp constraints. + * @UCLAMP_MIN: Minimum utilization + * @UCLAMP_MAX: Maximum utilization + * @UCLAMP_CNT: Utilization clamp constraints count + */ +enum uclamp_id { + UCLAMP_MIN = 0, + UCLAMP_MAX, + UCLAMP_CNT +}; + struct sched_info { #ifdef CONFIG_SCHED_INFO /* Cumulative counters: */ @@ -314,6 +326,10 @@ struct sched_info { # define SCHED_FIXEDPOINT_SHIFT 10 # define SCHED_FIXEDPOINT_SCALE (1L << SCHED_FIXEDPOINT_SHIFT) +/* Increase resolution of cpu_capacity calculations */ +# define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT +# define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) + struct load_weight { unsigned long weight; u32 inv_weight; @@ -562,6 +578,25 @@ struct sched_dl_entity { struct hrtimer inactive_timer; }; +#ifdef CONFIG_UCLAMP_TASK +/* Number of utilization clamp buckets (shorter alias) */ +#define UCLAMP_BUCKETS CONFIG_UCLAMP_BUCKETS_COUNT + +/* + * Utilization clamp for a scheduling entity + * @value: clamp value "assigned" to a se + * @bucket_id: bucket index corresponding to the "assigned" value + * + * The bucket_id is the index of the clamp bucket matching the clamp value + * which is pre-computed and stored to avoid expensive integer divisions from + * the fast path. + */ +struct uclamp_se { + unsigned int value : bits_per(SCHED_CAPACITY_SCALE); + unsigned int bucket_id : bits_per(UCLAMP_BUCKETS); +}; +#endif /* CONFIG_UCLAMP_TASK */ + union rcu_special { struct { u8 blocked; @@ -642,6 +677,10 @@ struct task_struct { #endif struct sched_dl_entity dl; +#ifdef CONFIG_UCLAMP_TASK + struct uclamp_se uclamp[UCLAMP_CNT]; +#endif + #ifdef CONFIG_PREEMPT_NOTIFIERS /* List of struct preempt_notifier: */ struct hlist_head preempt_notifiers; diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index e445d3767cdd..7863bb62d2ab 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -6,12 +6,6 @@ #include -/* - * Increase resolution of cpu_capacity calculations - */ -#define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT -#define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) - /* * sched-domains (multiprocessor balancing) declarations: */ -- cgit v1.2.3 From e8f14172c6b11e9a86c65532497087f8eb0f91b1 Mon Sep 17 00:00:00 2001 From: Patrick Bellasi Date: Fri, 21 Jun 2019 09:42:05 +0100 Subject: sched/uclamp: Add system default clamps Tasks without a user-defined clamp value are considered not clamped and by default their utilization can have any value in the [0..SCHED_CAPACITY_SCALE] range. Tasks with a user-defined clamp value are allowed to request any value in that range, and the required clamp is unconditionally enforced. However, a "System Management Software" could be interested in limiting the range of clamp values allowed for all tasks. Add a privileged interface to define a system default configuration via: /proc/sys/kernel/sched_uclamp_util_{min,max} which works as an unconditional clamp range restriction for all tasks. With the default configuration, the full SCHED_CAPACITY_SCALE range of values is allowed for each clamp index. Otherwise, the task-specific clamp is capped by the corresponding system default value. Do that by tracking, for each task, the "effective" clamp value and bucket the task has been refcounted in at enqueue time. This allows to lazy aggregate "requested" and "system default" values at enqueue time and simplifies refcounting updates at dequeue time. The cached bucket ids are used to avoid (relatively) more expensive integer divisions every time a task is enqueued. An active flag is used to report when the "effective" value is valid and thus the task is actually refcounted in the corresponding rq's bucket. Signed-off-by: Patrick Bellasi Signed-off-by: Peter Zijlstra (Intel) Cc: Alessio Balsini Cc: Dietmar Eggemann Cc: Joel Fernandes Cc: Juri Lelli Cc: Linus Torvalds Cc: Morten Rasmussen Cc: Paul Turner Cc: Peter Zijlstra Cc: Quentin Perret Cc: Rafael J . Wysocki Cc: Steve Muckle Cc: Suren Baghdasaryan Cc: Tejun Heo Cc: Thomas Gleixner Cc: Todd Kjos Cc: Vincent Guittot Cc: Viresh Kumar Link: https://lkml.kernel.org/r/20190621084217.8167-5-patrick.bellasi@arm.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 10 ++++++++++ include/linux/sched/sysctl.h | 11 +++++++++++ 2 files changed, 21 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 80235bcd05f2..5485f411e8e1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -586,14 +586,21 @@ struct sched_dl_entity { * Utilization clamp for a scheduling entity * @value: clamp value "assigned" to a se * @bucket_id: bucket index corresponding to the "assigned" value + * @active: the se is currently refcounted in a rq's bucket * * The bucket_id is the index of the clamp bucket matching the clamp value * which is pre-computed and stored to avoid expensive integer divisions from * the fast path. + * + * The active bit is set whenever a task has got an "effective" value assigned, + * which can be different from the clamp value "requested" from user-space. + * This allows to know a task is refcounted in the rq's bucket corresponding + * to the "effective" bucket_id. */ struct uclamp_se { unsigned int value : bits_per(SCHED_CAPACITY_SCALE); unsigned int bucket_id : bits_per(UCLAMP_BUCKETS); + unsigned int active : 1; }; #endif /* CONFIG_UCLAMP_TASK */ @@ -678,6 +685,9 @@ struct task_struct { struct sched_dl_entity dl; #ifdef CONFIG_UCLAMP_TASK + /* Clamp values requested for a scheduling entity */ + struct uclamp_se uclamp_req[UCLAMP_CNT]; + /* Effective clamp values used for a scheduling entity */ struct uclamp_se uclamp[UCLAMP_CNT]; #endif diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 99ce6d728df7..d4f6215ee03f 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -56,6 +56,11 @@ int sched_proc_update_handler(struct ctl_table *table, int write, extern unsigned int sysctl_sched_rt_period; extern int sysctl_sched_rt_runtime; +#ifdef CONFIG_UCLAMP_TASK +extern unsigned int sysctl_sched_uclamp_util_min; +extern unsigned int sysctl_sched_uclamp_util_max; +#endif + #ifdef CONFIG_CFS_BANDWIDTH extern unsigned int sysctl_sched_cfs_bandwidth_slice; #endif @@ -75,6 +80,12 @@ extern int sched_rt_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +#ifdef CONFIG_UCLAMP_TASK +extern int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); +#endif + extern int sysctl_numa_balancing(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -- cgit v1.2.3 From 1d6362fa0cfc8c7b243fa92924429d826599e691 Mon Sep 17 00:00:00 2001 From: Patrick Bellasi Date: Fri, 21 Jun 2019 09:42:06 +0100 Subject: sched/core: Allow sched_setattr() to use the current policy The sched_setattr() syscall mandates that a policy is always specified. This requires to always know which policy a task will have when attributes are configured and this makes it impossible to add more generic task attributes valid across different scheduling policies. Reading the policy before setting generic tasks attributes is racy since we cannot be sure it is not changed concurrently. Introduce the required support to change generic task attributes without affecting the current task policy. This is done by adding an attribute flag (SCHED_FLAG_KEEP_POLICY) to enforce the usage of the current policy. Add support for the SETPARAM_POLICY policy, which is already used by the sched_setparam() POSIX syscall, to the sched_setattr() non-POSIX syscall. Signed-off-by: Patrick Bellasi Signed-off-by: Peter Zijlstra (Intel) Cc: Alessio Balsini Cc: Dietmar Eggemann Cc: Joel Fernandes Cc: Juri Lelli Cc: Linus Torvalds Cc: Morten Rasmussen Cc: Paul Turner Cc: Peter Zijlstra Cc: Quentin Perret Cc: Rafael J . Wysocki Cc: Steve Muckle Cc: Suren Baghdasaryan Cc: Tejun Heo Cc: Thomas Gleixner Cc: Todd Kjos Cc: Vincent Guittot Cc: Viresh Kumar Link: https://lkml.kernel.org/r/20190621084217.8167-6-patrick.bellasi@arm.com Signed-off-by: Ingo Molnar --- include/uapi/linux/sched.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h index ed4ee170bee2..58b2368d3634 100644 --- a/include/uapi/linux/sched.h +++ b/include/uapi/linux/sched.h @@ -51,9 +51,11 @@ #define SCHED_FLAG_RESET_ON_FORK 0x01 #define SCHED_FLAG_RECLAIM 0x02 #define SCHED_FLAG_DL_OVERRUN 0x04 +#define SCHED_FLAG_KEEP_POLICY 0x08 #define SCHED_FLAG_ALL (SCHED_FLAG_RESET_ON_FORK | \ SCHED_FLAG_RECLAIM | \ - SCHED_FLAG_DL_OVERRUN) + SCHED_FLAG_DL_OVERRUN | \ + SCHED_FLAG_KEEP_POLICY) #endif /* _UAPI_LINUX_SCHED_H */ -- cgit v1.2.3 From a509a7cd79747074a2c018a45bbbc52d1f4aed44 Mon Sep 17 00:00:00 2001 From: Patrick Bellasi Date: Fri, 21 Jun 2019 09:42:07 +0100 Subject: sched/uclamp: Extend sched_setattr() to support utilization clamping The SCHED_DEADLINE scheduling class provides an advanced and formal model to define tasks requirements that can translate into proper decisions for both task placements and frequencies selections. Other classes have a more simplified model based on the POSIX concept of priorities. Such a simple priority based model however does not allow to exploit most advanced features of the Linux scheduler like, for example, driving frequencies selection via the schedutil cpufreq governor. However, also for non SCHED_DEADLINE tasks, it's still interesting to define tasks properties to support scheduler decisions. Utilization clamping exposes to user-space a new set of per-task attributes the scheduler can use as hints about the expected/required utilization for a task. This allows to implement a "proactive" per-task frequency control policy, a more advanced policy than the current one based just on "passive" measured task utilization. For example, it's possible to boost interactive tasks (e.g. to get better performance) or cap background tasks (e.g. to be more energy/thermal efficient). Introduce a new API to set utilization clamping values for a specified task by extending sched_setattr(), a syscall which already allows to define task specific properties for different scheduling classes. A new pair of attributes allows to specify a minimum and maximum utilization the scheduler can consider for a task. Do that by validating the required clamp values before and then applying the required changes using _the_ same pattern already in use for __setscheduler(). This ensures that the task is re-enqueued with the new clamp values. Signed-off-by: Patrick Bellasi Signed-off-by: Peter Zijlstra (Intel) Cc: Alessio Balsini Cc: Dietmar Eggemann Cc: Joel Fernandes Cc: Juri Lelli Cc: Linus Torvalds Cc: Morten Rasmussen Cc: Paul Turner Cc: Peter Zijlstra Cc: Quentin Perret Cc: Rafael J . Wysocki Cc: Steve Muckle Cc: Suren Baghdasaryan Cc: Tejun Heo Cc: Thomas Gleixner Cc: Todd Kjos Cc: Vincent Guittot Cc: Viresh Kumar Link: https://lkml.kernel.org/r/20190621084217.8167-7-patrick.bellasi@arm.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 9 ++++++ include/uapi/linux/sched.h | 12 +++++++- include/uapi/linux/sched/types.h | 66 ++++++++++++++++++++++++++++++++++------ 3 files changed, 77 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 5485f411e8e1..1113dd4706ae 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -587,6 +587,7 @@ struct sched_dl_entity { * @value: clamp value "assigned" to a se * @bucket_id: bucket index corresponding to the "assigned" value * @active: the se is currently refcounted in a rq's bucket + * @user_defined: the requested clamp value comes from user-space * * The bucket_id is the index of the clamp bucket matching the clamp value * which is pre-computed and stored to avoid expensive integer divisions from @@ -596,11 +597,19 @@ struct sched_dl_entity { * which can be different from the clamp value "requested" from user-space. * This allows to know a task is refcounted in the rq's bucket corresponding * to the "effective" bucket_id. + * + * The user_defined bit is set whenever a task has got a task-specific clamp + * value requested from userspace, i.e. the system defaults apply to this task + * just as a restriction. This allows to relax default clamps when a less + * restrictive task-specific value has been requested, thus allowing to + * implement a "nice" semantic. For example, a task running with a 20% + * default boost can still drop its own boosting to 0%. */ struct uclamp_se { unsigned int value : bits_per(SCHED_CAPACITY_SCALE); unsigned int bucket_id : bits_per(UCLAMP_BUCKETS); unsigned int active : 1; + unsigned int user_defined : 1; }; #endif /* CONFIG_UCLAMP_TASK */ diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h index 58b2368d3634..617bb59aa8ba 100644 --- a/include/uapi/linux/sched.h +++ b/include/uapi/linux/sched.h @@ -52,10 +52,20 @@ #define SCHED_FLAG_RECLAIM 0x02 #define SCHED_FLAG_DL_OVERRUN 0x04 #define SCHED_FLAG_KEEP_POLICY 0x08 +#define SCHED_FLAG_KEEP_PARAMS 0x10 +#define SCHED_FLAG_UTIL_CLAMP_MIN 0x20 +#define SCHED_FLAG_UTIL_CLAMP_MAX 0x40 + +#define SCHED_FLAG_KEEP_ALL (SCHED_FLAG_KEEP_POLICY | \ + SCHED_FLAG_KEEP_PARAMS) + +#define SCHED_FLAG_UTIL_CLAMP (SCHED_FLAG_UTIL_CLAMP_MIN | \ + SCHED_FLAG_UTIL_CLAMP_MAX) #define SCHED_FLAG_ALL (SCHED_FLAG_RESET_ON_FORK | \ SCHED_FLAG_RECLAIM | \ SCHED_FLAG_DL_OVERRUN | \ - SCHED_FLAG_KEEP_POLICY) + SCHED_FLAG_KEEP_ALL | \ + SCHED_FLAG_UTIL_CLAMP) #endif /* _UAPI_LINUX_SCHED_H */ diff --git a/include/uapi/linux/sched/types.h b/include/uapi/linux/sched/types.h index 10fbb8031930..c852153ddb0d 100644 --- a/include/uapi/linux/sched/types.h +++ b/include/uapi/linux/sched/types.h @@ -9,6 +9,7 @@ struct sched_param { }; #define SCHED_ATTR_SIZE_VER0 48 /* sizeof first published struct */ +#define SCHED_ATTR_SIZE_VER1 56 /* add: util_{min,max} */ /* * Extended scheduling parameters data structure. @@ -21,8 +22,33 @@ struct sched_param { * the tasks may be useful for a wide variety of application fields, e.g., * multimedia, streaming, automation and control, and many others. * - * This variant (sched_attr) is meant at describing a so-called - * sporadic time-constrained task. In such model a task is specified by: + * This variant (sched_attr) allows to define additional attributes to + * improve the scheduler knowledge about task requirements. + * + * Scheduling Class Attributes + * =========================== + * + * A subset of sched_attr attributes specifies the + * scheduling policy and relative POSIX attributes: + * + * @size size of the structure, for fwd/bwd compat. + * + * @sched_policy task's scheduling policy + * @sched_nice task's nice value (SCHED_NORMAL/BATCH) + * @sched_priority task's static priority (SCHED_FIFO/RR) + * + * Certain more advanced scheduling features can be controlled by a + * predefined set of flags via the attribute: + * + * @sched_flags for customizing the scheduler behaviour + * + * Sporadic Time-Constrained Task Attributes + * ========================================= + * + * A subset of sched_attr attributes allows to describe a so-called + * sporadic time-constrained task. + * + * In such a model a task is specified by: * - the activation period or minimum instance inter-arrival time; * - the maximum (or average, depending on the actual scheduling * discipline) computation time of all instances, a.k.a. runtime; @@ -34,14 +60,8 @@ struct sched_param { * than the runtime and must be completed by time instant t equal to * the instance activation time + the deadline. * - * This is reflected by the actual fields of the sched_attr structure: + * This is reflected by the following fields of the sched_attr structure: * - * @size size of the structure, for fwd/bwd compat. - * - * @sched_policy task's scheduling policy - * @sched_flags for customizing the scheduler behaviour - * @sched_nice task's nice value (SCHED_NORMAL/BATCH) - * @sched_priority task's static priority (SCHED_FIFO/RR) * @sched_deadline representative of the task's deadline * @sched_runtime representative of the task's runtime * @sched_period representative of the task's period @@ -53,6 +73,29 @@ struct sched_param { * As of now, the SCHED_DEADLINE policy (sched_dl scheduling class) is the * only user of this new interface. More information about the algorithm * available in the scheduling class file or in Documentation/. + * + * Task Utilization Attributes + * =========================== + * + * A subset of sched_attr attributes allows to specify the utilization + * expected for a task. These attributes allow to inform the scheduler about + * the utilization boundaries within which it should schedule the task. These + * boundaries are valuable hints to support scheduler decisions on both task + * placement and frequency selection. + * + * @sched_util_min represents the minimum utilization + * @sched_util_max represents the maximum utilization + * + * Utilization is a value in the range [0..SCHED_CAPACITY_SCALE]. It + * represents the percentage of CPU time used by a task when running at the + * maximum frequency on the highest capacity CPU of the system. For example, a + * 20% utilization task is a task running for 2ms every 10ms at maximum + * frequency. + * + * A task with a min utilization value bigger than 0 is more likely scheduled + * on a CPU with a capacity big enough to fit the specified value. + * A task with a max utilization value smaller than 1024 is more likely + * scheduled on a CPU with no more capacity than the specified value. */ struct sched_attr { __u32 size; @@ -70,6 +113,11 @@ struct sched_attr { __u64 sched_runtime; __u64 sched_deadline; __u64 sched_period; + + /* Utilization hints */ + __u32 sched_util_min; + __u32 sched_util_max; + }; #endif /* _UAPI_LINUX_SCHED_TYPES_H */ -- cgit v1.2.3